[2025-01-18 23:37:52 internimage_b_1k_224] (main.py 665): INFO Full config saved to work_dirs/internimage_b_1k_224/config.json
[2025-01-18 23:37:52 internimage_b_1k_224] (main.py 668): INFO AMP_OPT_LEVEL: O1
AMP_TYPE: float16
AUG:
  AUTO_AUGMENT: rand-m9-mstd0.5-inc1
  COLOR_JITTER: 0.4
  CUTMIX: 1.0
  CUTMIX_MINMAX: null
  MEAN:
  - 0.485
  - 0.456
  - 0.406
  MIXUP: 0.8
  MIXUP_MODE: batch
  MIXUP_PROB: 1.0
  MIXUP_SWITCH_PROB: 0.5
  RANDOM_RESIZED_CROP: false
  RECOUNT: 1
  REMODE: pixel
  REPROB: 0.25
  STD:
  - 0.229
  - 0.224
  - 0.225
BASE:
- ''
DATA:
  BATCH_SIZE: 128
  CACHE_MODE: part
  DATASET: imagenet
  DATA_PATH: data/imagenet
  IMG_ON_MEMORY: true
  IMG_SIZE: 224
  INTERPOLATION: bicubic
  NUM_WORKERS: 8
  PIN_MEMORY: true
  ZIP_MODE: false
EVAL_22K_TO_1K: false
EVAL_FREQ: 1
EVAL_MODE: false
LOCAL_RANK: 0
MODEL:
  DROP_PATH_RATE: 0.5
  DROP_PATH_TYPE: linear
  DROP_RATE: 0.0
  INTERN_IMAGE:
    CENTER_FEATURE_SCALE: false
    CHANNELS: 112
    CORE_OP: DCNv3
    DEPTHS:
    - 4
    - 4
    - 21
    - 4
    DW_KERNEL_SIZE: null
    GROUPS:
    - 7
    - 14
    - 28
    - 56
    LAYER_SCALE: 1.0e-05
    LEVEL2_POST_NORM: false
    LEVEL2_POST_NORM_BLOCK_IDS: null
    MLP_RATIO: 4.0
    OFFSET_SCALE: 1.0
    POST_NORM: true
    REMOVE_CENTER: false
    RES_POST_NORM: false
    USE_CLIP_PROJECTOR: false
  LABEL_SMOOTHING: 0.1
  NAME: internimage_b_1k_224
  NUM_CLASSES: 1000
  PRETRAINED: ''
  RESUME: ''
  TYPE: intern_image
OUTPUT: work_dirs/internimage_b_1k_224
PRINT_FREQ: 10
SAVE_CKPT_NUM: 1
SAVE_FREQ: 1
SEED: 0
TAG: default
TEST:
  CROP: true
  SEQUENTIAL: false
THROUGHPUT_MODE: false
TRAIN:
  ACCUMULATION_STEPS: 1
  AUTO_RESUME: true
  BASE_LR: 0.004
  CLIP_GRAD: 5.0
  EMA:
    DECAY: 0.9999
    ENABLE: true
  EPOCHS: 300
  LR_LAYER_DECAY: false
  LR_LAYER_DECAY_RATIO: 0.875
  LR_SCHEDULER:
    DECAY_EPOCHS: 30
    DECAY_RATE: 0.1
    NAME: cosine
  MIN_LR: 4.0e-05
  OPTIMIZER:
    BETAS:
    - 0.9
    - 0.999
    DCN_LR_MUL: null
    EPS: 1.0e-08
    FREEZE_BACKBONE: null
    MOMENTUM: 0.9
    NAME: adamw
    USE_ZERO: false
  RAND_INIT_FT_HEAD: false
  START_EPOCH: 0
  USE_CHECKPOINT: false
  WARMUP_EPOCHS: 20
  WARMUP_LR: 4.0e-06
  WEIGHT_DECAY: 0.05

[2025-01-18 23:44:26 internimage_b_1k_224] (main.py 174): INFO Creating model:intern_image/internimage_b_1k_224
[2025-01-18 23:44:55 internimage_b_1k_224] (main.py 177): INFO InternImage(
  (patch_embed): StemLayer(
    (conv1): Conv2d(3, 56, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
    (norm1): Sequential(
      (0): to_channels_last()
      (1): LayerNorm((56,), eps=1e-06, elementwise_affine=True)
      (2): to_channels_first()
    )
    (act): GELU()
    (conv2): Conv2d(56, 112, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
    (norm2): Sequential(
      (0): to_channels_last()
      (1): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
    )
  )
  (pos_drop): Dropout(p=0.0, inplace=False)
  (levels): ModuleList(
    (0): InternImageBlock(
      (blocks): ModuleList(
        (0): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=112)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=112, out_features=126, bias=True)
            (mask): Linear(in_features=112, out_features=63, bias=True)
            (input_proj): Linear(in_features=112, out_features=112, bias=True)
            (output_proj): Linear(in_features=112, out_features=112, bias=True)
          )
          (drop_path): Identity()
          (norm2): Sequential(
            (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=112, out_features=448, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=448, out_features=112, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (1): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=112)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=112, out_features=126, bias=True)
            (mask): Linear(in_features=112, out_features=63, bias=True)
            (input_proj): Linear(in_features=112, out_features=112, bias=True)
            (output_proj): Linear(in_features=112, out_features=112, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.016)
          (norm2): Sequential(
            (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=112, out_features=448, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=448, out_features=112, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (2): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=112)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=112, out_features=126, bias=True)
            (mask): Linear(in_features=112, out_features=63, bias=True)
            (input_proj): Linear(in_features=112, out_features=112, bias=True)
            (output_proj): Linear(in_features=112, out_features=112, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.031)
          (norm2): Sequential(
            (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=112, out_features=448, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=448, out_features=112, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (3): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=112)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=112, out_features=126, bias=True)
            (mask): Linear(in_features=112, out_features=63, bias=True)
            (input_proj): Linear(in_features=112, out_features=112, bias=True)
            (output_proj): Linear(in_features=112, out_features=112, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.047)
          (norm2): Sequential(
            (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=112, out_features=448, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=448, out_features=112, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
      )
      (downsample): DownsampleLayer(
        (conv): Conv2d(112, 224, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        (norm): Sequential(
          (0): to_channels_last()
          (1): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
        )
      )
    )
    (1): InternImageBlock(
      (blocks): ModuleList(
        (0): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(224, 224, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=224)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=224, out_features=252, bias=True)
            (mask): Linear(in_features=224, out_features=126, bias=True)
            (input_proj): Linear(in_features=224, out_features=224, bias=True)
            (output_proj): Linear(in_features=224, out_features=224, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.062)
          (norm2): Sequential(
            (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=224, out_features=896, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=896, out_features=224, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (1): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(224, 224, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=224)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=224, out_features=252, bias=True)
            (mask): Linear(in_features=224, out_features=126, bias=True)
            (input_proj): Linear(in_features=224, out_features=224, bias=True)
            (output_proj): Linear(in_features=224, out_features=224, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.078)
          (norm2): Sequential(
            (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=224, out_features=896, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=896, out_features=224, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (2): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(224, 224, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=224)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=224, out_features=252, bias=True)
            (mask): Linear(in_features=224, out_features=126, bias=True)
            (input_proj): Linear(in_features=224, out_features=224, bias=True)
            (output_proj): Linear(in_features=224, out_features=224, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.094)
          (norm2): Sequential(
            (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=224, out_features=896, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=896, out_features=224, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (3): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(224, 224, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=224)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=224, out_features=252, bias=True)
            (mask): Linear(in_features=224, out_features=126, bias=True)
            (input_proj): Linear(in_features=224, out_features=224, bias=True)
            (output_proj): Linear(in_features=224, out_features=224, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.109)
          (norm2): Sequential(
            (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=224, out_features=896, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=896, out_features=224, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
      )
      (downsample): DownsampleLayer(
        (conv): Conv2d(224, 448, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        (norm): Sequential(
          (0): to_channels_last()
          (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
        )
      )
    )
    (2): InternImageBlock(
      (blocks): ModuleList(
        (0): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.125)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (1): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.141)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (2): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.156)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (3): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.172)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (4): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.188)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (5): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.203)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (6): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.219)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (7): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.234)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (8): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.250)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (9): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.266)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (10): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.281)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (11): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.297)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (12): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.312)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (13): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.328)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (14): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.344)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (15): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.359)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (16): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.375)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (17): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.391)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (18): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.406)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (19): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.422)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (20): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.438)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
      )
      (downsample): DownsampleLayer(
        (conv): Conv2d(448, 896, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        (norm): Sequential(
          (0): to_channels_last()
          (1): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
        )
      )
    )
    (3): InternImageBlock(
      (blocks): ModuleList(
        (0): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(896, 896, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=896)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=896, out_features=1008, bias=True)
            (mask): Linear(in_features=896, out_features=504, bias=True)
            (input_proj): Linear(in_features=896, out_features=896, bias=True)
            (output_proj): Linear(in_features=896, out_features=896, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.453)
          (norm2): Sequential(
            (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=896, out_features=3584, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=3584, out_features=896, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (1): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(896, 896, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=896)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=896, out_features=1008, bias=True)
            (mask): Linear(in_features=896, out_features=504, bias=True)
            (input_proj): Linear(in_features=896, out_features=896, bias=True)
            (output_proj): Linear(in_features=896, out_features=896, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.469)
          (norm2): Sequential(
            (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=896, out_features=3584, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=3584, out_features=896, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (2): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(896, 896, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=896)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=896, out_features=1008, bias=True)
            (mask): Linear(in_features=896, out_features=504, bias=True)
            (input_proj): Linear(in_features=896, out_features=896, bias=True)
            (output_proj): Linear(in_features=896, out_features=896, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.484)
          (norm2): Sequential(
            (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=896, out_features=3584, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=3584, out_features=896, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (3): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(896, 896, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=896)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=896, out_features=1008, bias=True)
            (mask): Linear(in_features=896, out_features=504, bias=True)
            (input_proj): Linear(in_features=896, out_features=896, bias=True)
            (output_proj): Linear(in_features=896, out_features=896, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.500)
          (norm2): Sequential(
            (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=896, out_features=3584, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=3584, out_features=896, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
      )
    )
  )
  (conv_head): Sequential(
    (0): Conv2d(896, 1344, kernel_size=(1, 1), stride=(1, 1), bias=False)
    (1): Sequential(
      (0): BatchNorm2d(1344, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (2): GELU()
  )
  (head): Linear(in_features=1344, out_features=1000, bias=True)
  (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
)
[2025-01-18 23:44:55 internimage_b_1k_224] (main.py 213): INFO Using native Torch AMP. Training in mixed precision.
[2025-01-18 23:44:56 internimage_b_1k_224] (main.py 225): INFO using fp16_compress_hook!
[2025-01-18 23:44:56 internimage_b_1k_224] (main.py 233): INFO number of params: 97461832
[2025-01-18 23:44:56 internimage_b_1k_224] (main.py 267): INFO no checkpoint found in work_dirs/internimage_b_1k_224, ignoring auto resume
[2025-01-18 23:44:56 internimage_b_1k_224] (main.py 308): INFO Start training
[2025-01-18 23:45:07 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][0/312]	eta 0:58:40 lr 0.000004	time 11.2831 (11.2831)	model_time 7.4084 (7.4084)	loss 6.8928 (6.8928)	grad_norm 0.4664 (0.4664/0.0000)	mem 33484MB
[2025-01-18 23:45:15 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][10/312]	eta 0:08:47 lr 0.000010	time 0.7666 (1.7472)	model_time 0.7665 (1.3947)	loss 6.9166 (6.9367)	grad_norm 0.4344 (0.4595/0.0126)	mem 34602MB
[2025-01-18 23:45:22 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][20/312]	eta 0:06:09 lr 0.000017	time 0.7237 (1.2648)	model_time 0.7235 (1.0800)	loss 6.9336 (6.9302)	grad_norm 0.4350 (0.4512/0.0144)	mem 34602MB
[2025-01-18 23:45:30 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][30/312]	eta 0:05:08 lr 0.000023	time 0.7516 (1.0941)	model_time 0.7513 (0.9688)	loss 6.9148 (6.9264)	grad_norm 0.4448 (0.4459/0.0167)	mem 34602MB
[2025-01-18 23:45:37 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][40/312]	eta 0:04:34 lr 0.000030	time 0.7258 (1.0092)	model_time 0.7254 (0.9144)	loss 6.9128 (6.9192)	grad_norm 0.4095 (0.4399/0.0185)	mem 34602MB
[2025-01-18 23:45:44 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][50/312]	eta 0:04:10 lr 0.000036	time 0.7281 (0.9576)	model_time 0.7279 (0.8813)	loss 6.8347 (6.9119)	grad_norm 0.4083 (0.4341/0.0206)	mem 34602MB
[2025-01-18 23:45:52 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][60/312]	eta 0:03:52 lr 0.000042	time 0.7731 (0.9211)	model_time 0.7730 (0.8573)	loss 6.8855 (6.9054)	grad_norm 0.3937 (0.4284/0.0232)	mem 34602MB
[2025-01-18 23:45:59 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][70/312]	eta 0:03:36 lr 0.000049	time 0.7283 (0.8946)	model_time 0.7281 (0.8397)	loss 6.8634 (6.8993)	grad_norm 0.3883 (0.4233/0.0251)	mem 34602MB
[2025-01-18 23:46:06 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][80/312]	eta 0:03:23 lr 0.000055	time 0.7292 (0.8753)	model_time 0.7288 (0.8271)	loss 6.8096 (6.8945)	grad_norm 0.3777 (0.4184/0.0270)	mem 34602MB
[2025-01-18 23:46:14 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][90/312]	eta 0:03:10 lr 0.000062	time 0.7223 (0.8595)	model_time 0.7222 (0.8166)	loss 6.8731 (6.8901)	grad_norm 0.3854 (0.4145/0.0280)	mem 34602MB
[2025-01-18 23:46:21 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][100/312]	eta 0:02:59 lr 0.000068	time 0.7222 (0.8477)	model_time 0.7217 (0.8090)	loss 6.8827 (6.8860)	grad_norm 0.4446 (0.4134/0.0290)	mem 34602MB
[2025-01-18 23:46:29 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][110/312]	eta 0:02:49 lr 0.000074	time 0.7253 (0.8374)	model_time 0.7252 (0.8022)	loss 6.7858 (6.8807)	grad_norm 0.3825 (0.4132/0.0290)	mem 34602MB
[2025-01-18 23:46:36 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][120/312]	eta 0:02:39 lr 0.000081	time 0.7241 (0.8288)	model_time 0.7240 (0.7964)	loss 6.7814 (6.8760)	grad_norm 0.4421 (0.4161/0.0316)	mem 34602MB
[2025-01-18 23:46:43 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][130/312]	eta 0:02:29 lr 0.000087	time 0.7312 (0.8215)	model_time 0.7311 (0.7916)	loss 6.8430 (6.8711)	grad_norm 0.4024 (0.4221/0.0430)	mem 34602MB
[2025-01-18 23:46:51 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][140/312]	eta 0:02:20 lr 0.000094	time 0.7637 (0.8159)	model_time 0.7632 (0.7881)	loss 6.7929 (6.8658)	grad_norm 0.5155 (0.4277/0.0514)	mem 34602MB
[2025-01-18 23:46:58 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][150/312]	eta 0:02:11 lr 0.000100	time 0.7202 (0.8106)	model_time 0.7201 (0.7846)	loss 6.7103 (6.8618)	grad_norm 0.4378 (0.4374/0.0672)	mem 34602MB
[2025-01-18 23:47:06 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][160/312]	eta 0:02:02 lr 0.000106	time 0.7250 (0.8074)	model_time 0.7245 (0.7830)	loss 6.8355 (6.8584)	grad_norm 0.7493 (0.4503/0.0896)	mem 34602MB
[2025-01-18 23:47:13 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][170/312]	eta 0:01:54 lr 0.000113	time 0.7247 (0.8032)	model_time 0.7246 (0.7802)	loss 6.7528 (6.8542)	grad_norm 0.4783 (0.4669/0.1206)	mem 34602MB
[2025-01-18 23:47:20 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][180/312]	eta 0:01:45 lr 0.000119	time 0.7515 (0.7997)	model_time 0.7514 (0.7780)	loss 6.8103 (6.8493)	grad_norm 0.9858 (0.4833/0.1450)	mem 34602MB
[2025-01-18 23:47:28 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][190/312]	eta 0:01:37 lr 0.000126	time 0.7223 (0.7961)	model_time 0.7222 (0.7755)	loss 6.7356 (6.8460)	grad_norm 1.4407 (0.5131/0.2131)	mem 34602MB
[2025-01-18 23:47:35 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][200/312]	eta 0:01:28 lr 0.000132	time 0.7191 (0.7929)	model_time 0.7186 (0.7733)	loss 6.7865 (6.8412)	grad_norm 0.9900 (0.5304/0.2252)	mem 34602MB
[2025-01-18 23:47:42 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][210/312]	eta 0:01:20 lr 0.000138	time 0.7371 (0.7902)	model_time 0.7369 (0.7715)	loss 6.7611 (6.8368)	grad_norm 1.0857 (0.5437/0.2313)	mem 34602MB
[2025-01-18 23:47:50 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][220/312]	eta 0:01:12 lr 0.000145	time 0.7252 (0.7878)	model_time 0.7248 (0.7699)	loss 6.7587 (6.8325)	grad_norm 1.9680 (0.5812/0.3080)	mem 34602MB
[2025-01-18 23:47:57 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][230/312]	eta 0:01:04 lr 0.000151	time 0.7409 (0.7854)	model_time 0.7408 (0.7683)	loss 6.7579 (6.8299)	grad_norm 1.0783 (0.5974/0.3142)	mem 34602MB
[2025-01-18 23:48:04 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][240/312]	eta 0:00:56 lr 0.000158	time 0.7289 (0.7833)	model_time 0.7284 (0.7669)	loss 6.7468 (6.8262)	grad_norm 1.0125 (0.6206/0.3375)	mem 34602MB
[2025-01-18 23:48:12 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][250/312]	eta 0:00:48 lr 0.000164	time 0.7309 (0.7814)	model_time 0.7308 (0.7657)	loss 6.7498 (6.8214)	grad_norm 0.8242 (0.6442/0.3631)	mem 34602MB
[2025-01-18 23:48:19 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][260/312]	eta 0:00:40 lr 0.000170	time 0.7247 (0.7797)	model_time 0.7242 (0.7645)	loss 6.7415 (6.8172)	grad_norm 1.3718 (0.6780/0.4033)	mem 34602MB
[2025-01-18 23:48:26 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][270/312]	eta 0:00:32 lr 0.000177	time 0.7274 (0.7781)	model_time 0.7269 (0.7634)	loss 6.7707 (6.8143)	grad_norm 1.5377 (0.7138/0.4409)	mem 34602MB
[2025-01-18 23:48:34 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][280/312]	eta 0:00:24 lr 0.000183	time 0.7254 (0.7772)	model_time 0.7250 (0.7631)	loss 6.7244 (6.8125)	grad_norm 2.3168 (0.7658/0.5193)	mem 34602MB
[2025-01-18 23:48:41 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][290/312]	eta 0:00:17 lr 0.000190	time 0.7397 (0.7760)	model_time 0.7396 (0.7623)	loss 6.6181 (6.8080)	grad_norm 1.7785 (0.8103/0.5687)	mem 34602MB
[2025-01-18 23:48:49 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][300/312]	eta 0:00:09 lr 0.000196	time 0.7229 (0.7745)	model_time 0.7228 (0.7613)	loss 6.7275 (6.8031)	grad_norm 1.3072 (0.8504/0.6065)	mem 34602MB
[2025-01-18 23:48:56 internimage_b_1k_224] (main.py 510): INFO Train: [0/300][310/312]	eta 0:00:01 lr 0.000203	time 0.7222 (0.7728)	model_time 0.7221 (0.7600)	loss 6.7994 (6.8013)	grad_norm 4.6589 (0.9284/0.7093)	mem 34602MB
[2025-01-18 23:48:57 internimage_b_1k_224] (main.py 519): INFO EPOCH 0 training takes 0:04:01
[2025-01-18 23:48:57 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_0.pth saving......
[2025-01-18 23:49:00 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_0.pth saved !!!
[2025-01-18 23:49:08 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.363 (8.363)	Loss 6.1789 (6.1789)	Acc@1 2.075 (2.075)	Acc@5 6.763 (6.763)	Mem 34602MB
[2025-01-18 23:49:11 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.998)	Loss 6.5390 (6.3797)	Acc@1 0.977 (1.520)	Acc@5 4.102 (5.489)	Mem 34602MB
[2025-01-18 23:49:11 internimage_b_1k_224] (main.py 575): INFO [Epoch:0] * Acc@1 1.979 Acc@5 6.648
[2025-01-18 23:49:11 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 2.0%
[2025-01-18 23:49:11 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 23:49:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 23:49:14 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 1.98%
[2025-01-18 23:49:21 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.988 (6.988)	Loss 6.9284 (6.9284)	Acc@1 0.488 (0.488)	Acc@5 0.977 (0.977)	Mem 34602MB
[2025-01-18 23:49:24 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.891)	Loss 6.9240 (6.9215)	Acc@1 0.049 (0.120)	Acc@5 0.220 (0.517)	Mem 34602MB
[2025-01-18 23:49:25 internimage_b_1k_224] (main.py 575): INFO [Epoch:0] * Acc@1 0.122 Acc@5 0.526
[2025-01-18 23:49:25 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.1%
[2025-01-18 23:49:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 23:49:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 23:49:28 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.12%
[2025-01-18 23:49:30 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][0/312]	eta 0:10:11 lr 0.000204	time 1.9598 (1.9598)	model_time 0.7750 (0.7750)	loss 6.7993 (6.7993)	grad_norm 2.3940 (2.3940/0.0000)	mem 34602MB
[2025-01-18 23:49:37 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][10/312]	eta 0:04:15 lr 0.000210	time 0.7434 (0.8457)	model_time 0.7430 (0.7376)	loss 6.7612 (6.7544)	grad_norm 2.9489 (2.6895/1.1114)	mem 34602MB
[2025-01-18 23:49:45 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][20/312]	eta 0:03:51 lr 0.000217	time 0.7435 (0.7923)	model_time 0.7431 (0.7355)	loss 6.7573 (6.7181)	grad_norm 3.3291 (2.5855/0.8809)	mem 34602MB
[2025-01-18 23:49:52 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][30/312]	eta 0:03:38 lr 0.000223	time 0.7382 (0.7764)	model_time 0.7379 (0.7379)	loss 6.7185 (6.7136)	grad_norm 2.2938 (2.6645/0.8607)	mem 34602MB
[2025-01-18 23:49:59 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][40/312]	eta 0:03:28 lr 0.000229	time 0.7605 (0.7678)	model_time 0.7601 (0.7386)	loss 6.6687 (6.7000)	grad_norm 1.2039 (2.7763/0.9590)	mem 34602MB
[2025-01-18 23:50:07 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][50/312]	eta 0:03:19 lr 0.000236	time 0.7328 (0.7602)	model_time 0.7326 (0.7366)	loss 6.6428 (6.6847)	grad_norm 2.8149 (2.7782/0.9327)	mem 34602MB
[2025-01-18 23:50:14 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][60/312]	eta 0:03:10 lr 0.000242	time 0.7268 (0.7561)	model_time 0.7263 (0.7363)	loss 6.6333 (6.6788)	grad_norm 7.0442 (2.9207/1.0594)	mem 34602MB
[2025-01-18 23:50:21 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][70/312]	eta 0:03:02 lr 0.000249	time 0.7211 (0.7538)	model_time 0.7206 (0.7367)	loss 6.5606 (6.6733)	grad_norm 3.6513 (3.0005/1.1529)	mem 34602MB
[2025-01-18 23:50:29 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][80/312]	eta 0:02:54 lr 0.000255	time 0.7259 (0.7513)	model_time 0.7254 (0.7363)	loss 6.7132 (6.6641)	grad_norm 3.0407 (3.0087/1.1079)	mem 34602MB
[2025-01-18 23:50:36 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][90/312]	eta 0:02:47 lr 0.000261	time 0.7240 (0.7525)	model_time 0.7238 (0.7391)	loss 6.5001 (6.6655)	grad_norm 1.4955 (2.9915/1.0942)	mem 34602MB
[2025-01-18 23:50:44 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][100/312]	eta 0:02:39 lr 0.000268	time 0.7271 (0.7503)	model_time 0.7269 (0.7382)	loss 6.6468 (6.6634)	grad_norm 4.8898 (3.1152/1.2387)	mem 34602MB
[2025-01-18 23:50:51 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][110/312]	eta 0:02:31 lr 0.000274	time 0.7234 (0.7488)	model_time 0.7230 (0.7377)	loss 6.3421 (6.6550)	grad_norm 5.4456 (3.1284/1.2231)	mem 34602MB
[2025-01-18 23:50:58 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][120/312]	eta 0:02:23 lr 0.000281	time 0.7558 (0.7475)	model_time 0.7556 (0.7374)	loss 6.6920 (6.6569)	grad_norm 2.1529 (3.1896/1.2968)	mem 34602MB
[2025-01-18 23:51:06 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][130/312]	eta 0:02:15 lr 0.000287	time 0.7225 (0.7465)	model_time 0.7221 (0.7371)	loss 6.5963 (6.6551)	grad_norm 3.4248 (3.1810/1.2680)	mem 34602MB
[2025-01-18 23:51:13 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][140/312]	eta 0:02:08 lr 0.000293	time 0.7235 (0.7457)	model_time 0.7230 (0.7369)	loss 6.4654 (6.6509)	grad_norm 5.2685 (3.2299/1.2774)	mem 34602MB
[2025-01-18 23:51:20 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][150/312]	eta 0:02:00 lr 0.000300	time 0.7429 (0.7450)	model_time 0.7423 (0.7367)	loss 6.5397 (6.6439)	grad_norm 6.3243 (3.2480/1.2757)	mem 34602MB
[2025-01-18 23:51:28 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][160/312]	eta 0:01:53 lr 0.000306	time 0.7243 (0.7441)	model_time 0.7242 (0.7364)	loss 6.5139 (6.6352)	grad_norm 4.8908 (3.2810/1.2718)	mem 34602MB
[2025-01-18 23:51:35 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][170/312]	eta 0:01:45 lr 0.000313	time 0.7348 (0.7434)	model_time 0.7344 (0.7361)	loss 6.6830 (6.6328)	grad_norm 2.1641 (3.2989/1.2690)	mem 34602MB
[2025-01-18 23:51:42 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][180/312]	eta 0:01:38 lr 0.000319	time 0.7476 (0.7428)	model_time 0.7472 (0.7358)	loss 6.3962 (6.6314)	grad_norm 1.9483 (3.2862/1.2589)	mem 34602MB
[2025-01-18 23:51:50 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][190/312]	eta 0:01:30 lr 0.000325	time 0.7294 (0.7422)	model_time 0.7293 (0.7356)	loss 6.2699 (6.6254)	grad_norm 9.0586 (3.3490/1.3778)	mem 34602MB
[2025-01-18 23:51:57 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][200/312]	eta 0:01:23 lr 0.000332	time 0.7233 (0.7417)	model_time 0.7229 (0.7355)	loss 6.6815 (6.6270)	grad_norm 3.2357 (3.3583/1.3613)	mem 34602MB
[2025-01-18 23:52:05 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][210/312]	eta 0:01:15 lr 0.000338	time 0.7192 (0.7438)	model_time 0.7190 (0.7378)	loss 6.6087 (6.6202)	grad_norm 3.2411 (3.3938/1.3771)	mem 34602MB
[2025-01-18 23:52:12 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][220/312]	eta 0:01:08 lr 0.000345	time 0.7452 (0.7435)	model_time 0.7450 (0.7378)	loss 6.5987 (6.6162)	grad_norm 3.6698 (3.4303/1.4156)	mem 34602MB
[2025-01-18 23:52:20 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][230/312]	eta 0:01:00 lr 0.000351	time 0.7204 (0.7431)	model_time 0.7202 (0.7376)	loss 6.6167 (6.6106)	grad_norm 3.3350 (3.4309/1.4010)	mem 34602MB
[2025-01-18 23:52:27 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][240/312]	eta 0:00:53 lr 0.000357	time 0.7204 (0.7426)	model_time 0.7200 (0.7373)	loss 6.5302 (6.6062)	grad_norm 2.6540 (3.4494/1.3900)	mem 34602MB
[2025-01-18 23:52:34 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][250/312]	eta 0:00:46 lr 0.000364	time 0.7232 (0.7421)	model_time 0.7228 (0.7370)	loss 6.6308 (6.6058)	grad_norm 2.1476 (3.4542/1.3906)	mem 34602MB
[2025-01-18 23:52:42 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][260/312]	eta 0:00:38 lr 0.000370	time 0.7527 (0.7417)	model_time 0.7522 (0.7368)	loss 6.4498 (6.6027)	grad_norm 3.3207 (3.4569/1.3747)	mem 34602MB
[2025-01-18 23:52:49 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][270/312]	eta 0:00:31 lr 0.000377	time 0.7209 (0.7414)	model_time 0.7208 (0.7367)	loss 6.6379 (6.6004)	grad_norm 6.9291 (3.4619/1.3777)	mem 34602MB
[2025-01-18 23:52:56 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][280/312]	eta 0:00:23 lr 0.000383	time 0.7225 (0.7406)	model_time 0.7224 (0.7361)	loss 6.2986 (6.5965)	grad_norm 6.0228 (3.4742/1.3714)	mem 34602MB
[2025-01-18 23:53:03 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][290/312]	eta 0:00:16 lr 0.000390	time 0.7202 (0.7403)	model_time 0.7200 (0.7359)	loss 6.1704 (6.5898)	grad_norm 5.2318 (3.4843/1.3656)	mem 34602MB
[2025-01-18 23:53:11 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][300/312]	eta 0:00:08 lr 0.000396	time 0.7589 (0.7401)	model_time 0.7588 (0.7358)	loss 6.5326 (6.5867)	grad_norm 2.9821 (3.5049/1.3578)	mem 34602MB
[2025-01-18 23:53:18 internimage_b_1k_224] (main.py 510): INFO Train: [1/300][310/312]	eta 0:00:01 lr 0.000402	time 0.7223 (0.7395)	model_time 0.7222 (0.7353)	loss 6.6317 (6.5858)	grad_norm 2.8486 (3.5236/1.3399)	mem 34602MB
[2025-01-18 23:53:19 internimage_b_1k_224] (main.py 519): INFO EPOCH 1 training takes 0:03:50
[2025-01-18 23:53:19 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_1.pth saving......
[2025-01-18 23:53:22 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_1.pth saved !!!
[2025-01-18 23:53:29 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.995 (6.995)	Loss 5.5450 (5.5450)	Acc@1 4.614 (4.614)	Acc@5 14.795 (14.795)	Mem 34602MB
[2025-01-18 23:53:32 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.898)	Loss 5.7963 (5.7109)	Acc@1 4.175 (4.381)	Acc@5 12.744 (13.998)	Mem 34602MB
[2025-01-18 23:53:32 internimage_b_1k_224] (main.py 575): INFO [Epoch:1] * Acc@1 5.052 Acc@5 15.363
[2025-01-18 23:53:32 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 5.1%
[2025-01-18 23:53:32 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 23:53:35 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 23:53:35 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 5.05%
[2025-01-18 23:53:49 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 13.657 (13.657)	Loss 6.9211 (6.9211)	Acc@1 0.513 (0.513)	Acc@5 0.952 (0.952)	Mem 34602MB
[2025-01-18 23:53:55 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.766)	Loss 6.9149 (6.9129)	Acc@1 0.073 (0.153)	Acc@5 0.293 (0.595)	Mem 34602MB
[2025-01-18 23:53:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:1] * Acc@1 0.156 Acc@5 0.642
[2025-01-18 23:53:55 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.2%
[2025-01-18 23:53:55 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 23:53:58 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 23:53:58 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.16%
[2025-01-18 23:54:01 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][0/312]	eta 0:12:34 lr 0.000404	time 2.4194 (2.4194)	model_time 0.7764 (0.7764)	loss 6.4725 (6.4725)	grad_norm 3.1110 (3.1110/0.0000)	mem 34602MB
[2025-01-18 23:54:08 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][10/312]	eta 0:04:31 lr 0.000410	time 0.8257 (0.9004)	model_time 0.8256 (0.7507)	loss 6.4398 (6.4613)	grad_norm 2.8557 (3.3268/0.4083)	mem 34602MB
[2025-01-18 23:54:16 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][20/312]	eta 0:04:01 lr 0.000416	time 0.7412 (0.8264)	model_time 0.7410 (0.7479)	loss 6.1796 (6.3987)	grad_norm 2.5157 (3.4098/0.7115)	mem 34602MB
[2025-01-18 23:54:23 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][30/312]	eta 0:03:44 lr 0.000423	time 0.7217 (0.7950)	model_time 0.7213 (0.7416)	loss 6.3155 (6.3885)	grad_norm 2.0586 (3.2355/0.9586)	mem 34602MB
[2025-01-18 23:54:30 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][40/312]	eta 0:03:31 lr 0.000429	time 0.7284 (0.7791)	model_time 0.7283 (0.7387)	loss 6.3599 (6.3731)	grad_norm 3.2296 (3.6789/1.8430)	mem 34602MB
[2025-01-18 23:54:38 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][50/312]	eta 0:03:21 lr 0.000436	time 0.7364 (0.7694)	model_time 0.7360 (0.7369)	loss 6.4767 (6.4015)	grad_norm 2.4642 (3.6213/1.6926)	mem 34602MB
[2025-01-18 23:54:45 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][60/312]	eta 0:03:12 lr 0.000442	time 0.7198 (0.7627)	model_time 0.7194 (0.7354)	loss 6.5635 (6.4080)	grad_norm 3.2584 (3.8667/1.7158)	mem 34602MB
[2025-01-18 23:54:52 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][70/312]	eta 0:03:03 lr 0.000448	time 0.7179 (0.7575)	model_time 0.7178 (0.7340)	loss 6.4275 (6.3946)	grad_norm 2.5541 (3.7433/1.6361)	mem 34602MB
[2025-01-18 23:54:59 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][80/312]	eta 0:02:54 lr 0.000455	time 0.7219 (0.7536)	model_time 0.7215 (0.7330)	loss 6.4757 (6.3818)	grad_norm 3.6313 (3.6275/1.5775)	mem 34602MB
[2025-01-18 23:55:07 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][90/312]	eta 0:02:46 lr 0.000461	time 0.7283 (0.7509)	model_time 0.7282 (0.7324)	loss 6.4349 (6.3656)	grad_norm 1.6695 (3.6558/1.5957)	mem 34602MB
[2025-01-18 23:55:14 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][100/312]	eta 0:02:38 lr 0.000468	time 0.7230 (0.7492)	model_time 0.7225 (0.7326)	loss 6.1150 (6.3558)	grad_norm 5.2493 (3.6685/1.5522)	mem 34602MB
[2025-01-18 23:55:21 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][110/312]	eta 0:02:30 lr 0.000474	time 0.7207 (0.7473)	model_time 0.7206 (0.7321)	loss 6.3885 (6.3591)	grad_norm 4.5092 (3.6421/1.4964)	mem 34602MB
[2025-01-18 23:55:29 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][120/312]	eta 0:02:23 lr 0.000480	time 0.7390 (0.7455)	model_time 0.7389 (0.7316)	loss 6.4224 (6.3614)	grad_norm 2.7299 (3.6612/1.5729)	mem 34602MB
[2025-01-18 23:55:36 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][130/312]	eta 0:02:15 lr 0.000487	time 0.7201 (0.7450)	model_time 0.7199 (0.7321)	loss 5.9764 (6.3536)	grad_norm 3.4477 (3.6365/1.5258)	mem 34602MB
[2025-01-18 23:55:44 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][140/312]	eta 0:02:08 lr 0.000493	time 0.7214 (0.7463)	model_time 0.7209 (0.7343)	loss 6.3286 (6.3545)	grad_norm 2.5957 (3.6326/1.4978)	mem 34602MB
[2025-01-18 23:55:51 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][150/312]	eta 0:02:00 lr 0.000500	time 0.7206 (0.7455)	model_time 0.7202 (0.7342)	loss 5.8210 (6.3513)	grad_norm 2.7679 (3.6298/1.4673)	mem 34602MB
[2025-01-18 23:55:58 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][160/312]	eta 0:01:53 lr 0.000506	time 0.7164 (0.7443)	model_time 0.7162 (0.7337)	loss 5.9839 (6.3496)	grad_norm 3.4442 (3.6445/1.4491)	mem 34602MB
[2025-01-18 23:56:05 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][170/312]	eta 0:01:45 lr 0.000512	time 0.7402 (0.7435)	model_time 0.7398 (0.7335)	loss 6.2786 (6.3485)	grad_norm 3.0414 (3.6237/1.4114)	mem 34602MB
[2025-01-18 23:56:13 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][180/312]	eta 0:01:37 lr 0.000519	time 0.7216 (0.7423)	model_time 0.7212 (0.7328)	loss 6.5516 (6.3401)	grad_norm 3.5260 (3.6326/1.3802)	mem 34602MB
[2025-01-18 23:56:20 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][190/312]	eta 0:01:30 lr 0.000525	time 0.7234 (0.7414)	model_time 0.7232 (0.7324)	loss 6.3411 (6.3258)	grad_norm 2.3725 (3.5996/1.3721)	mem 34602MB
[2025-01-18 23:56:27 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][200/312]	eta 0:01:22 lr 0.000532	time 0.7190 (0.7406)	model_time 0.7188 (0.7321)	loss 5.7962 (6.3198)	grad_norm 4.5908 (3.5994/1.3514)	mem 34602MB
[2025-01-18 23:56:34 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][210/312]	eta 0:01:15 lr 0.000538	time 0.7179 (0.7402)	model_time 0.7174 (0.7320)	loss 5.9539 (6.3110)	grad_norm 4.4810 (3.5920/1.3482)	mem 34602MB
[2025-01-18 23:56:42 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][220/312]	eta 0:01:08 lr 0.000544	time 0.7759 (0.7398)	model_time 0.7755 (0.7320)	loss 5.8253 (6.3026)	grad_norm 5.1246 (3.5959/1.3260)	mem 34602MB
[2025-01-18 23:56:49 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][230/312]	eta 0:01:00 lr 0.000551	time 0.7649 (0.7390)	model_time 0.7644 (0.7315)	loss 6.4334 (6.3026)	grad_norm 3.0172 (3.5618/1.3183)	mem 34602MB
[2025-01-18 23:56:56 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][240/312]	eta 0:00:53 lr 0.000557	time 0.7192 (0.7387)	model_time 0.7188 (0.7315)	loss 6.0645 (6.2969)	grad_norm 2.6634 (3.5442/1.3163)	mem 34602MB
[2025-01-18 23:57:04 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][250/312]	eta 0:00:45 lr 0.000564	time 0.7191 (0.7385)	model_time 0.7187 (0.7316)	loss 6.0422 (6.2935)	grad_norm 2.4019 (3.5001/1.3108)	mem 34602MB
[2025-01-18 23:57:11 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][260/312]	eta 0:00:38 lr 0.000570	time 0.7586 (0.7398)	model_time 0.7585 (0.7331)	loss 5.7956 (6.2823)	grad_norm 2.2827 (3.4905/1.3007)	mem 34602MB
[2025-01-18 23:57:19 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][270/312]	eta 0:00:31 lr 0.000577	time 0.7170 (0.7394)	model_time 0.7169 (0.7330)	loss 6.3938 (6.2787)	grad_norm 4.4434 (3.4842/1.2924)	mem 34602MB
[2025-01-18 23:57:26 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][280/312]	eta 0:00:23 lr 0.000583	time 0.7218 (0.7391)	model_time 0.7217 (0.7329)	loss 6.2511 (6.2730)	grad_norm 2.5803 (3.4677/1.2787)	mem 34602MB
[2025-01-18 23:57:33 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][290/312]	eta 0:00:16 lr 0.000589	time 0.7469 (0.7389)	model_time 0.7465 (0.7328)	loss 6.5407 (6.2660)	grad_norm 2.2864 (3.4374/1.2718)	mem 34602MB
[2025-01-18 23:57:41 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][300/312]	eta 0:00:08 lr 0.000596	time 0.7137 (0.7384)	model_time 0.7136 (0.7325)	loss 6.2005 (6.2666)	grad_norm 1.9836 (3.4105/1.2657)	mem 34602MB
[2025-01-18 23:57:48 internimage_b_1k_224] (main.py 510): INFO Train: [2/300][310/312]	eta 0:00:01 lr 0.000602	time 0.7136 (0.7377)	model_time 0.7135 (0.7320)	loss 5.5983 (6.2634)	grad_norm 3.5223 (3.3976/1.2712)	mem 34602MB
[2025-01-18 23:57:48 internimage_b_1k_224] (main.py 519): INFO EPOCH 2 training takes 0:03:50
[2025-01-18 23:57:48 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_2.pth saving......
[2025-01-18 23:57:52 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_2.pth saved !!!
[2025-01-18 23:58:00 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.593 (7.593)	Loss 4.7808 (4.7808)	Acc@1 11.377 (11.377)	Acc@5 29.736 (29.736)	Mem 34602MB
[2025-01-18 23:58:03 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.976)	Loss 4.9343 (4.8172)	Acc@1 10.596 (11.528)	Acc@5 25.610 (28.786)	Mem 34602MB
[2025-01-18 23:58:03 internimage_b_1k_224] (main.py 575): INFO [Epoch:2] * Acc@1 12.556 Acc@5 30.268
[2025-01-18 23:58:03 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 12.6%
[2025-01-18 23:58:03 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 23:58:06 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 23:58:06 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 12.56%
[2025-01-18 23:58:14 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.268 (7.268)	Loss 6.9103 (6.9103)	Acc@1 0.439 (0.439)	Acc@5 1.343 (1.343)	Mem 34602MB
[2025-01-18 23:58:17 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.920)	Loss 6.9017 (6.9005)	Acc@1 0.073 (0.186)	Acc@5 0.488 (0.783)	Mem 34602MB
[2025-01-18 23:58:17 internimage_b_1k_224] (main.py 575): INFO [Epoch:2] * Acc@1 0.208 Acc@5 0.894
[2025-01-18 23:58:17 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.2%
[2025-01-18 23:58:17 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 23:58:20 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 23:58:20 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.21%
[2025-01-18 23:58:23 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][0/312]	eta 0:12:13 lr 0.000603	time 2.3505 (2.3505)	model_time 0.7517 (0.7517)	loss 6.3026 (6.3026)	grad_norm 4.6912 (4.6912/0.0000)	mem 34602MB
[2025-01-18 23:58:30 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][10/312]	eta 0:04:24 lr 0.000610	time 0.7224 (0.8743)	model_time 0.7220 (0.7286)	loss 5.5810 (6.0042)	grad_norm 3.0422 (2.9886/0.8152)	mem 34602MB
[2025-01-18 23:58:37 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][20/312]	eta 0:03:55 lr 0.000616	time 0.7573 (0.8070)	model_time 0.7569 (0.7305)	loss 5.9914 (5.9733)	grad_norm 2.6133 (2.9547/0.7399)	mem 34602MB
[2025-01-18 23:58:44 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][30/312]	eta 0:03:40 lr 0.000623	time 0.7451 (0.7828)	model_time 0.7449 (0.7308)	loss 6.2561 (6.0328)	grad_norm 3.0618 (2.8734/0.7503)	mem 34602MB
[2025-01-18 23:58:52 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][40/312]	eta 0:03:29 lr 0.000629	time 0.7704 (0.7701)	model_time 0.7699 (0.7307)	loss 5.4978 (6.0515)	grad_norm 2.6533 (2.8557/0.7097)	mem 34602MB
[2025-01-18 23:58:59 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][50/312]	eta 0:03:19 lr 0.000635	time 0.7325 (0.7632)	model_time 0.7321 (0.7315)	loss 6.3144 (6.0565)	grad_norm 4.2063 (2.9130/0.7776)	mem 34602MB
[2025-01-18 23:59:07 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][60/312]	eta 0:03:11 lr 0.000642	time 0.8115 (0.7601)	model_time 0.8111 (0.7335)	loss 5.5261 (6.0482)	grad_norm 3.5949 (2.9258/0.7740)	mem 34602MB
[2025-01-18 23:59:15 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][70/312]	eta 0:03:05 lr 0.000648	time 0.7554 (0.7657)	model_time 0.7553 (0.7429)	loss 6.0881 (6.0505)	grad_norm 3.1684 (3.0149/0.8604)	mem 34602MB
[2025-01-18 23:59:22 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][80/312]	eta 0:02:56 lr 0.000655	time 0.7187 (0.7615)	model_time 0.7182 (0.7414)	loss 5.3780 (6.0540)	grad_norm 2.9519 (2.9707/0.8323)	mem 34602MB
[2025-01-18 23:59:29 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][90/312]	eta 0:02:48 lr 0.000661	time 0.7268 (0.7571)	model_time 0.7264 (0.7392)	loss 6.0600 (6.0331)	grad_norm 1.9080 (2.9236/0.8083)	mem 34602MB
[2025-01-18 23:59:36 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][100/312]	eta 0:02:39 lr 0.000667	time 0.7221 (0.7539)	model_time 0.7217 (0.7376)	loss 6.3603 (6.0348)	grad_norm 2.0789 (2.8688/0.7958)	mem 34602MB
[2025-01-18 23:59:44 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][110/312]	eta 0:02:31 lr 0.000674	time 0.7207 (0.7511)	model_time 0.7206 (0.7363)	loss 5.7246 (6.0326)	grad_norm 2.9304 (2.8311/0.7896)	mem 34602MB
[2025-01-18 23:59:51 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][120/312]	eta 0:02:23 lr 0.000680	time 0.7190 (0.7484)	model_time 0.7186 (0.7348)	loss 6.1332 (6.0345)	grad_norm 2.1742 (2.8193/0.7743)	mem 34602MB
[2025-01-18 23:59:58 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][130/312]	eta 0:02:15 lr 0.000687	time 0.7175 (0.7470)	model_time 0.7173 (0.7344)	loss 5.6668 (6.0328)	grad_norm 2.4828 (2.8045/0.7598)	mem 34602MB
[2025-01-19 00:00:05 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][140/312]	eta 0:02:08 lr 0.000693	time 0.7410 (0.7459)	model_time 0.7406 (0.7342)	loss 6.2278 (6.0190)	grad_norm 2.8867 (2.7666/0.7720)	mem 34602MB
[2025-01-19 00:00:13 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][150/312]	eta 0:02:00 lr 0.000699	time 0.7186 (0.7448)	model_time 0.7181 (0.7339)	loss 5.9670 (6.0164)	grad_norm 2.5301 (2.7567/0.7888)	mem 34602MB
[2025-01-19 00:00:20 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][160/312]	eta 0:01:53 lr 0.000706	time 0.7190 (0.7438)	model_time 0.7185 (0.7335)	loss 6.3345 (6.0080)	grad_norm 3.4950 (2.7249/0.7881)	mem 34602MB
[2025-01-19 00:00:27 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][170/312]	eta 0:01:45 lr 0.000712	time 0.7168 (0.7434)	model_time 0.7167 (0.7336)	loss 6.0474 (6.0055)	grad_norm 2.2219 (2.7069/0.7762)	mem 34602MB
[2025-01-19 00:00:35 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][180/312]	eta 0:01:38 lr 0.000719	time 0.8077 (0.7437)	model_time 0.8076 (0.7345)	loss 6.0740 (6.0059)	grad_norm 2.3150 (2.7058/0.7699)	mem 34602MB
[2025-01-19 00:00:42 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][190/312]	eta 0:01:30 lr 0.000725	time 0.7184 (0.7448)	model_time 0.7179 (0.7360)	loss 6.0525 (6.0027)	grad_norm 1.9744 (2.6935/0.7751)	mem 34602MB
[2025-01-19 00:00:50 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][200/312]	eta 0:01:23 lr 0.000731	time 0.7168 (0.7439)	model_time 0.7164 (0.7356)	loss 5.7811 (6.0016)	grad_norm 2.1979 (2.7279/0.8560)	mem 34602MB
[2025-01-19 00:00:57 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][210/312]	eta 0:01:15 lr 0.000738	time 0.7144 (0.7430)	model_time 0.7142 (0.7350)	loss 6.3918 (5.9977)	grad_norm 2.4259 (2.7062/0.8440)	mem 34602MB
[2025-01-19 00:01:04 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][220/312]	eta 0:01:08 lr 0.000744	time 0.7215 (0.7422)	model_time 0.7211 (0.7346)	loss 5.7446 (5.9934)	grad_norm 2.3537 (2.6815/0.8372)	mem 34602MB
[2025-01-19 00:01:12 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][230/312]	eta 0:01:00 lr 0.000751	time 0.7177 (0.7417)	model_time 0.7173 (0.7344)	loss 5.8364 (5.9817)	grad_norm 2.0866 (2.6714/0.8246)	mem 34602MB
[2025-01-19 00:01:19 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][240/312]	eta 0:00:53 lr 0.000757	time 0.7540 (0.7412)	model_time 0.7536 (0.7342)	loss 6.3692 (5.9876)	grad_norm 3.5280 (2.6670/0.8148)	mem 34602MB
[2025-01-19 00:01:26 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][250/312]	eta 0:00:45 lr 0.000763	time 0.7129 (0.7404)	model_time 0.7125 (0.7337)	loss 6.2402 (5.9928)	grad_norm 2.0597 (2.6623/0.8077)	mem 34602MB
[2025-01-19 00:01:33 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][260/312]	eta 0:00:38 lr 0.000770	time 0.7193 (0.7396)	model_time 0.7191 (0.7331)	loss 5.8520 (5.9862)	grad_norm 1.9096 (2.6547/0.8032)	mem 34602MB
[2025-01-19 00:01:41 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][270/312]	eta 0:00:31 lr 0.000776	time 0.7181 (0.7392)	model_time 0.7177 (0.7329)	loss 6.0491 (5.9864)	grad_norm 1.8595 (2.6329/0.7992)	mem 34602MB
[2025-01-19 00:01:48 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][280/312]	eta 0:00:23 lr 0.000783	time 0.7179 (0.7388)	model_time 0.7175 (0.7327)	loss 6.2710 (5.9824)	grad_norm 1.8611 (2.6126/0.7946)	mem 34602MB
[2025-01-19 00:01:55 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][290/312]	eta 0:00:16 lr 0.000789	time 0.7350 (0.7386)	model_time 0.7349 (0.7328)	loss 5.8326 (5.9725)	grad_norm 2.8515 (2.6069/0.7866)	mem 34602MB
[2025-01-19 00:02:03 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][300/312]	eta 0:00:08 lr 0.000796	time 0.7960 (0.7385)	model_time 0.7959 (0.7328)	loss 5.9338 (5.9651)	grad_norm 2.8926 (2.6126/0.7894)	mem 34602MB
[2025-01-19 00:02:10 internimage_b_1k_224] (main.py 510): INFO Train: [3/300][310/312]	eta 0:00:01 lr 0.000802	time 0.8182 (0.7402)	model_time 0.8181 (0.7347)	loss 6.1690 (5.9629)	grad_norm 1.7734 (2.6044/0.7883)	mem 34602MB
[2025-01-19 00:02:11 internimage_b_1k_224] (main.py 519): INFO EPOCH 3 training takes 0:03:50
[2025-01-19 00:02:11 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_3.pth saving......
[2025-01-19 00:02:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_3.pth saved !!!
[2025-01-19 00:02:22 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.377 (7.377)	Loss 3.9084 (3.9084)	Acc@1 22.314 (22.314)	Acc@5 47.192 (47.192)	Mem 34602MB
[2025-01-19 00:02:25 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.936)	Loss 4.4575 (4.1562)	Acc@1 14.893 (19.050)	Acc@5 33.716 (41.231)	Mem 34602MB
[2025-01-19 00:02:25 internimage_b_1k_224] (main.py 575): INFO [Epoch:3] * Acc@1 20.116 Acc@5 42.750
[2025-01-19 00:02:25 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 20.1%
[2025-01-19 00:02:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:02:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:02:28 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 20.12%
[2025-01-19 00:02:35 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.180 (7.180)	Loss 6.8982 (6.8982)	Acc@1 0.513 (0.513)	Acc@5 1.465 (1.465)	Mem 34602MB
[2025-01-19 00:02:38 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.916)	Loss 6.8842 (6.8845)	Acc@1 0.098 (0.289)	Acc@5 0.879 (1.136)	Mem 34602MB
[2025-01-19 00:02:39 internimage_b_1k_224] (main.py 575): INFO [Epoch:3] * Acc@1 0.348 Acc@5 1.316
[2025-01-19 00:02:39 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.3%
[2025-01-19 00:02:39 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:02:43 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:02:43 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.35%
[2025-01-19 00:02:45 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][0/312]	eta 0:11:29 lr 0.000803	time 2.2084 (2.2084)	model_time 0.7387 (0.7387)	loss 5.1921 (5.1921)	grad_norm 2.8921 (2.8921/0.0000)	mem 34602MB
[2025-01-19 00:02:52 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][10/312]	eta 0:04:19 lr 0.000810	time 0.7256 (0.8591)	model_time 0.7255 (0.7253)	loss 6.3161 (5.8249)	grad_norm 2.5334 (2.4362/0.6528)	mem 34602MB
[2025-01-19 00:02:59 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][20/312]	eta 0:03:53 lr 0.000816	time 0.7262 (0.7987)	model_time 0.7261 (0.7284)	loss 5.9766 (5.8804)	grad_norm 2.0163 (2.4676/0.6677)	mem 34602MB
[2025-01-19 00:03:07 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][30/312]	eta 0:03:38 lr 0.000822	time 0.7348 (0.7764)	model_time 0.7347 (0.7286)	loss 5.5757 (5.8750)	grad_norm 4.4660 (2.5647/0.7886)	mem 34602MB
[2025-01-19 00:03:14 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][40/312]	eta 0:03:27 lr 0.000829	time 0.7202 (0.7641)	model_time 0.7200 (0.7279)	loss 5.4686 (5.8970)	grad_norm 1.6712 (2.5663/0.8276)	mem 34602MB
[2025-01-19 00:03:21 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][50/312]	eta 0:03:18 lr 0.000835	time 0.7186 (0.7566)	model_time 0.7185 (0.7275)	loss 6.1731 (5.8754)	grad_norm 2.9569 (2.4946/0.8081)	mem 34602MB
[2025-01-19 00:03:28 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][60/312]	eta 0:03:09 lr 0.000842	time 0.7136 (0.7513)	model_time 0.7131 (0.7269)	loss 5.0820 (5.8509)	grad_norm 1.6577 (2.4131/0.7912)	mem 34602MB
[2025-01-19 00:03:36 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][70/312]	eta 0:03:00 lr 0.000848	time 0.7164 (0.7472)	model_time 0.7159 (0.7261)	loss 5.6122 (5.8090)	grad_norm 3.6006 (2.3739/0.7725)	mem 34602MB
[2025-01-19 00:03:43 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][80/312]	eta 0:02:53 lr 0.000854	time 0.7144 (0.7460)	model_time 0.7142 (0.7275)	loss 5.7044 (5.7920)	grad_norm 2.2935 (2.3910/0.7584)	mem 34602MB
[2025-01-19 00:03:50 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][90/312]	eta 0:02:45 lr 0.000861	time 0.7185 (0.7439)	model_time 0.7181 (0.7274)	loss 6.3957 (5.7921)	grad_norm 2.4870 (2.4613/1.0307)	mem 34602MB
[2025-01-19 00:03:57 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][100/312]	eta 0:02:37 lr 0.000867	time 0.7165 (0.7417)	model_time 0.7164 (0.7268)	loss 6.1056 (5.7868)	grad_norm 2.6482 (2.5066/1.0238)	mem 34602MB
[2025-01-19 00:04:05 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][110/312]	eta 0:02:29 lr 0.000874	time 0.8486 (0.7421)	model_time 0.8481 (0.7285)	loss 5.2993 (5.7932)	grad_norm 2.4573 (2.4817/0.9957)	mem 34602MB
[2025-01-19 00:04:13 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][120/312]	eta 0:02:23 lr 0.000880	time 0.8081 (0.7452)	model_time 0.8079 (0.7327)	loss 5.5760 (5.7948)	grad_norm 1.7536 (2.4836/0.9987)	mem 34602MB
[2025-01-19 00:04:20 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][130/312]	eta 0:02:15 lr 0.000886	time 0.7636 (0.7439)	model_time 0.7635 (0.7323)	loss 5.9686 (5.7993)	grad_norm 2.8595 (2.4762/0.9703)	mem 34602MB
[2025-01-19 00:04:27 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][140/312]	eta 0:02:07 lr 0.000893	time 0.7188 (0.7423)	model_time 0.7183 (0.7315)	loss 6.0786 (5.7980)	grad_norm 1.8597 (2.4674/0.9570)	mem 34602MB
[2025-01-19 00:04:35 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][150/312]	eta 0:02:00 lr 0.000899	time 0.7217 (0.7413)	model_time 0.7216 (0.7312)	loss 5.0838 (5.7883)	grad_norm 1.9120 (2.4818/0.9576)	mem 34602MB
[2025-01-19 00:04:42 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][160/312]	eta 0:01:52 lr 0.000906	time 0.7606 (0.7407)	model_time 0.7604 (0.7312)	loss 5.6255 (5.7884)	grad_norm 1.9664 (2.4711/0.9383)	mem 34602MB
[2025-01-19 00:04:49 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][170/312]	eta 0:01:45 lr 0.000912	time 0.7478 (0.7398)	model_time 0.7473 (0.7308)	loss 5.8492 (5.7830)	grad_norm 2.0055 (2.4573/0.9232)	mem 34602MB
[2025-01-19 00:04:56 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][180/312]	eta 0:01:37 lr 0.000918	time 0.7264 (0.7390)	model_time 0.7260 (0.7305)	loss 5.6789 (5.7711)	grad_norm 3.7261 (2.4820/0.9390)	mem 34602MB
[2025-01-19 00:05:04 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][190/312]	eta 0:01:30 lr 0.000925	time 0.7186 (0.7381)	model_time 0.7182 (0.7300)	loss 5.2929 (5.7637)	grad_norm 2.1458 (2.4642/0.9232)	mem 34602MB
[2025-01-19 00:05:11 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][200/312]	eta 0:01:22 lr 0.000931	time 0.7144 (0.7381)	model_time 0.7139 (0.7304)	loss 5.1100 (5.7587)	grad_norm 1.6016 (2.4660/0.9151)	mem 34602MB
[2025-01-19 00:05:18 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][210/312]	eta 0:01:15 lr 0.000938	time 0.7236 (0.7372)	model_time 0.7234 (0.7299)	loss 5.2710 (5.7575)	grad_norm 2.6895 (2.4443/0.9007)	mem 34602MB
[2025-01-19 00:05:25 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][220/312]	eta 0:01:07 lr 0.000944	time 0.7222 (0.7365)	model_time 0.7217 (0.7294)	loss 5.7720 (5.7577)	grad_norm 2.4782 (2.4838/0.9196)	mem 34602MB
[2025-01-19 00:05:33 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][230/312]	eta 0:01:00 lr 0.000950	time 0.8131 (0.7364)	model_time 0.8127 (0.7297)	loss 5.2260 (5.7433)	grad_norm 2.2375 (2.4723/0.9062)	mem 34602MB
[2025-01-19 00:05:40 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][240/312]	eta 0:00:53 lr 0.000957	time 0.8076 (0.7380)	model_time 0.8072 (0.7315)	loss 5.9527 (5.7235)	grad_norm 2.5170 (2.5199/0.9344)	mem 34602MB
[2025-01-19 00:05:48 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][250/312]	eta 0:00:45 lr 0.000963	time 0.7142 (0.7381)	model_time 0.7140 (0.7318)	loss 5.5484 (5.7113)	grad_norm 2.3398 (2.5194/0.9268)	mem 34602MB
[2025-01-19 00:05:55 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][260/312]	eta 0:00:38 lr 0.000970	time 0.7236 (0.7376)	model_time 0.7232 (0.7316)	loss 5.2370 (5.7117)	grad_norm 1.4474 (2.5107/0.9275)	mem 34602MB
[2025-01-19 00:06:02 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][270/312]	eta 0:00:30 lr 0.000976	time 0.7131 (0.7372)	model_time 0.7127 (0.7314)	loss 5.7335 (5.7113)	grad_norm 1.9695 (2.4947/0.9187)	mem 34602MB
[2025-01-19 00:06:10 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][280/312]	eta 0:00:23 lr 0.000983	time 0.7173 (0.7367)	model_time 0.7168 (0.7311)	loss 5.6675 (5.7068)	grad_norm 2.1999 (2.4719/0.9121)	mem 34602MB
[2025-01-19 00:06:17 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][290/312]	eta 0:00:16 lr 0.000989	time 0.7224 (0.7363)	model_time 0.7223 (0.7309)	loss 5.6409 (5.7016)	grad_norm 2.0725 (2.4552/0.9039)	mem 34602MB
[2025-01-19 00:06:24 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][300/312]	eta 0:00:08 lr 0.000995	time 0.7131 (0.7359)	model_time 0.7130 (0.7306)	loss 4.8313 (5.6907)	grad_norm 2.7841 (2.4424/0.8970)	mem 34602MB
[2025-01-19 00:06:31 internimage_b_1k_224] (main.py 510): INFO Train: [4/300][310/312]	eta 0:00:01 lr 0.001002	time 0.7092 (0.7352)	model_time 0.7091 (0.7301)	loss 5.7165 (5.6897)	grad_norm 2.2236 (2.5167/1.1099)	mem 34602MB
[2025-01-19 00:06:32 internimage_b_1k_224] (main.py 519): INFO EPOCH 4 training takes 0:03:49
[2025-01-19 00:06:32 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_4.pth saving......
[2025-01-19 00:06:35 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_4.pth saved !!!
[2025-01-19 00:06:43 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.376 (7.376)	Loss 3.3936 (3.3936)	Acc@1 30.835 (30.835)	Acc@5 57.690 (57.690)	Mem 34602MB
[2025-01-19 00:06:46 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.929)	Loss 3.9035 (3.6098)	Acc@1 23.169 (27.344)	Acc@5 46.924 (53.129)	Mem 34602MB
[2025-01-19 00:06:46 internimage_b_1k_224] (main.py 575): INFO [Epoch:4] * Acc@1 28.379 Acc@5 54.305
[2025-01-19 00:06:46 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 28.4%
[2025-01-19 00:06:46 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:06:49 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:06:49 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 28.38%
[2025-01-19 00:06:57 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.484 (7.484)	Loss 6.8872 (6.8872)	Acc@1 0.342 (0.342)	Acc@5 1.074 (1.074)	Mem 34602MB
[2025-01-19 00:07:00 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.187 (0.941)	Loss 6.8639 (6.8674)	Acc@1 0.244 (0.317)	Acc@5 1.025 (1.343)	Mem 34602MB
[2025-01-19 00:07:00 internimage_b_1k_224] (main.py 575): INFO [Epoch:4] * Acc@1 0.458 Acc@5 1.565
[2025-01-19 00:07:00 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.5%
[2025-01-19 00:07:00 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:07:03 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:07:03 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.46%
[2025-01-19 00:07:05 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][0/312]	eta 0:10:36 lr 0.001003	time 2.0402 (2.0402)	model_time 0.7448 (0.7448)	loss 4.5596 (4.5596)	grad_norm 1.7232 (1.7232/0.0000)	mem 34602MB
[2025-01-19 00:07:13 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][10/312]	eta 0:04:18 lr 0.001009	time 0.7153 (0.8562)	model_time 0.7151 (0.7380)	loss 5.4715 (5.2300)	grad_norm 3.1463 (2.1422/0.6829)	mem 34602MB
[2025-01-19 00:07:20 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][20/312]	eta 0:03:52 lr 0.001016	time 0.7252 (0.7975)	model_time 0.7250 (0.7355)	loss 4.8149 (5.3755)	grad_norm 2.3299 (2.1378/0.5698)	mem 34602MB
[2025-01-19 00:07:27 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][30/312]	eta 0:03:37 lr 0.001022	time 0.7112 (0.7728)	model_time 0.7107 (0.7306)	loss 5.5408 (5.4594)	grad_norm 1.7104 (2.0910/0.5117)	mem 34602MB
[2025-01-19 00:07:35 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][40/312]	eta 0:03:29 lr 0.001029	time 0.8062 (0.7697)	model_time 0.8058 (0.7378)	loss 5.8986 (5.5331)	grad_norm 2.7736 (2.2648/0.7880)	mem 34602MB
[2025-01-19 00:07:43 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][50/312]	eta 0:03:22 lr 0.001035	time 0.7173 (0.7730)	model_time 0.7168 (0.7473)	loss 5.2127 (5.5454)	grad_norm 4.0041 (2.2522/0.7836)	mem 34602MB
[2025-01-19 00:07:50 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][60/312]	eta 0:03:13 lr 0.001041	time 0.7190 (0.7666)	model_time 0.7188 (0.7450)	loss 5.2585 (5.5284)	grad_norm 1.5440 (2.3478/0.8502)	mem 34602MB
[2025-01-19 00:07:57 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][70/312]	eta 0:03:04 lr 0.001048	time 0.7166 (0.7607)	model_time 0.7162 (0.7421)	loss 5.8611 (5.5379)	grad_norm 3.9075 (2.4137/0.8397)	mem 34602MB
[2025-01-19 00:08:05 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][80/312]	eta 0:02:55 lr 0.001054	time 0.7140 (0.7569)	model_time 0.7136 (0.7406)	loss 5.4674 (5.5286)	grad_norm 1.8205 (2.3900/0.8979)	mem 34602MB
[2025-01-19 00:08:12 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][90/312]	eta 0:02:47 lr 0.001061	time 0.7136 (0.7533)	model_time 0.7134 (0.7387)	loss 5.1057 (5.4870)	grad_norm 2.1902 (2.3708/0.8705)	mem 34602MB
[2025-01-19 00:08:19 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][100/312]	eta 0:02:39 lr 0.001067	time 0.7192 (0.7505)	model_time 0.7188 (0.7373)	loss 5.2829 (5.4622)	grad_norm 2.1263 (2.4000/0.8608)	mem 34602MB
[2025-01-19 00:08:26 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][110/312]	eta 0:02:31 lr 0.001073	time 0.7457 (0.7482)	model_time 0.7453 (0.7361)	loss 5.6283 (5.4685)	grad_norm 1.8525 (2.3992/0.8385)	mem 34602MB
[2025-01-19 00:08:34 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][120/312]	eta 0:02:23 lr 0.001080	time 0.7196 (0.7461)	model_time 0.7194 (0.7350)	loss 5.7695 (5.4664)	grad_norm 2.3576 (2.3767/0.8215)	mem 34602MB
[2025-01-19 00:08:41 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][130/312]	eta 0:02:15 lr 0.001086	time 0.8308 (0.7450)	model_time 0.8307 (0.7348)	loss 5.1991 (5.4654)	grad_norm 2.5129 (2.3780/0.8279)	mem 34602MB
[2025-01-19 00:08:48 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][140/312]	eta 0:02:07 lr 0.001093	time 0.7168 (0.7434)	model_time 0.7166 (0.7338)	loss 5.9858 (5.4857)	grad_norm 4.4588 (2.4197/0.8497)	mem 34602MB
[2025-01-19 00:08:55 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][150/312]	eta 0:02:00 lr 0.001099	time 0.7197 (0.7425)	model_time 0.7193 (0.7336)	loss 5.3537 (5.4763)	grad_norm 1.8957 (2.4261/0.8397)	mem 34602MB
[2025-01-19 00:09:03 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][160/312]	eta 0:01:52 lr 0.001105	time 0.7206 (0.7427)	model_time 0.7204 (0.7343)	loss 4.6120 (5.4636)	grad_norm 1.6526 (2.3904/0.8296)	mem 34602MB
[2025-01-19 00:09:11 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][170/312]	eta 0:01:45 lr 0.001112	time 0.7139 (0.7461)	model_time 0.7135 (0.7381)	loss 5.9103 (5.4742)	grad_norm 3.3303 (2.3768/0.8192)	mem 34602MB
[2025-01-19 00:09:18 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][180/312]	eta 0:01:38 lr 0.001118	time 0.7599 (0.7456)	model_time 0.7594 (0.7381)	loss 4.9437 (5.4641)	grad_norm 3.9987 (2.4044/0.8278)	mem 34602MB
[2025-01-19 00:09:26 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][190/312]	eta 0:01:30 lr 0.001125	time 0.7223 (0.7445)	model_time 0.7222 (0.7373)	loss 5.0816 (5.4548)	grad_norm 1.8267 (2.3951/0.8149)	mem 34602MB
[2025-01-19 00:09:33 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][200/312]	eta 0:01:23 lr 0.001131	time 0.7280 (0.7436)	model_time 0.7276 (0.7367)	loss 5.8706 (5.4472)	grad_norm 2.4181 (2.4030/0.8132)	mem 34602MB
[2025-01-19 00:09:40 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][210/312]	eta 0:01:15 lr 0.001137	time 0.7217 (0.7428)	model_time 0.7212 (0.7363)	loss 5.3599 (5.4486)	grad_norm 4.0765 (2.4339/0.8405)	mem 34602MB
[2025-01-19 00:09:47 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][220/312]	eta 0:01:08 lr 0.001144	time 0.7223 (0.7421)	model_time 0.7222 (0.7359)	loss 5.9183 (5.4482)	grad_norm 2.0220 (2.4645/0.9324)	mem 34602MB
[2025-01-19 00:09:55 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][230/312]	eta 0:01:00 lr 0.001150	time 0.7230 (0.7415)	model_time 0.7225 (0.7355)	loss 5.4577 (5.4371)	grad_norm 2.2127 (2.4618/0.9363)	mem 34602MB
[2025-01-19 00:10:02 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][240/312]	eta 0:00:53 lr 0.001157	time 0.7176 (0.7407)	model_time 0.7174 (0.7350)	loss 5.3190 (5.4443)	grad_norm 1.5750 (2.4406/0.9297)	mem 34602MB
[2025-01-19 00:10:09 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][250/312]	eta 0:00:45 lr 0.001163	time 0.8209 (0.7404)	model_time 0.8207 (0.7349)	loss 4.5544 (5.4338)	grad_norm 3.3955 (2.4757/0.9629)	mem 34602MB
[2025-01-19 00:10:16 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][260/312]	eta 0:00:38 lr 0.001170	time 0.7171 (0.7397)	model_time 0.7167 (0.7343)	loss 5.6322 (5.4358)	grad_norm 3.1780 (2.4649/0.9502)	mem 34602MB
[2025-01-19 00:10:24 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][270/312]	eta 0:00:31 lr 0.001176	time 0.7125 (0.7392)	model_time 0.7121 (0.7341)	loss 5.7621 (5.4389)	grad_norm 2.8474 (2.4641/0.9418)	mem 34602MB
[2025-01-19 00:10:31 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][280/312]	eta 0:00:23 lr 0.001182	time 0.7143 (0.7396)	model_time 0.7141 (0.7346)	loss 4.4961 (5.4321)	grad_norm 2.1809 (2.4715/0.9322)	mem 34602MB
[2025-01-19 00:10:39 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][290/312]	eta 0:00:16 lr 0.001189	time 0.7180 (0.7415)	model_time 0.7179 (0.7367)	loss 4.1876 (5.4216)	grad_norm 3.4487 (2.4813/0.9370)	mem 34602MB
[2025-01-19 00:10:46 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][300/312]	eta 0:00:08 lr 0.001195	time 0.7225 (0.7413)	model_time 0.7224 (0.7366)	loss 5.2758 (5.4164)	grad_norm 1.7025 (2.4901/0.9447)	mem 34602MB
[2025-01-19 00:10:54 internimage_b_1k_224] (main.py 510): INFO Train: [5/300][310/312]	eta 0:00:01 lr 0.001202	time 0.7085 (0.7403)	model_time 0.7084 (0.7358)	loss 5.6219 (5.4063)	grad_norm 1.8839 (2.4814/0.9416)	mem 34602MB
[2025-01-19 00:10:54 internimage_b_1k_224] (main.py 519): INFO EPOCH 5 training takes 0:03:50
[2025-01-19 00:10:54 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_5.pth saving......
[2025-01-19 00:10:58 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_5.pth saved !!!
[2025-01-19 00:11:05 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.473 (7.473)	Loss 2.8054 (2.8054)	Acc@1 40.552 (40.552)	Acc@5 68.066 (68.066)	Mem 34602MB
[2025-01-19 00:11:08 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.937)	Loss 3.5671 (3.1492)	Acc@1 27.246 (34.863)	Acc@5 53.735 (61.659)	Mem 34602MB
[2025-01-19 00:11:08 internimage_b_1k_224] (main.py 575): INFO [Epoch:5] * Acc@1 35.653 Acc@5 62.458
[2025-01-19 00:11:08 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 35.7%
[2025-01-19 00:11:08 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:11:12 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:11:12 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 35.65%
[2025-01-19 00:11:19 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.148 (7.148)	Loss 6.8787 (6.8787)	Acc@1 0.317 (0.317)	Acc@5 1.416 (1.416)	Mem 34602MB
[2025-01-19 00:11:22 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.907)	Loss 6.8494 (6.8535)	Acc@1 0.659 (0.346)	Acc@5 1.465 (1.498)	Mem 34602MB
[2025-01-19 00:11:22 internimage_b_1k_224] (main.py 575): INFO [Epoch:5] * Acc@1 0.506 Acc@5 1.799
[2025-01-19 00:11:22 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.5%
[2025-01-19 00:11:22 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:11:26 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:11:26 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.51%
[2025-01-19 00:11:28 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][0/312]	eta 0:11:37 lr 0.001203	time 2.2369 (2.2369)	model_time 0.7492 (0.7492)	loss 5.7889 (5.7889)	grad_norm 1.9155 (1.9155/0.0000)	mem 34602MB
[2025-01-19 00:11:35 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][10/312]	eta 0:04:21 lr 0.001209	time 0.7162 (0.8655)	model_time 0.7158 (0.7299)	loss 4.5100 (5.5220)	grad_norm 1.3585 (2.2818/0.7443)	mem 34602MB
[2025-01-19 00:11:42 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][20/312]	eta 0:03:53 lr 0.001216	time 0.7472 (0.7995)	model_time 0.7468 (0.7282)	loss 5.9574 (5.3904)	grad_norm 2.0664 (2.3761/0.7375)	mem 34602MB
[2025-01-19 00:11:50 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][30/312]	eta 0:03:38 lr 0.001222	time 0.7216 (0.7752)	model_time 0.7211 (0.7268)	loss 5.4301 (5.3325)	grad_norm 1.5718 (2.3501/0.6924)	mem 34602MB
[2025-01-19 00:11:57 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][40/312]	eta 0:03:27 lr 0.001228	time 0.7341 (0.7634)	model_time 0.7340 (0.7268)	loss 4.8033 (5.3231)	grad_norm 1.9823 (2.2912/0.6829)	mem 34602MB
[2025-01-19 00:12:04 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][50/312]	eta 0:03:17 lr 0.001235	time 0.7320 (0.7555)	model_time 0.7316 (0.7259)	loss 4.8158 (5.2460)	grad_norm 1.7529 (2.3856/0.7862)	mem 34602MB
[2025-01-19 00:12:11 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][60/312]	eta 0:03:09 lr 0.001241	time 0.7225 (0.7511)	model_time 0.7221 (0.7263)	loss 5.0571 (5.2189)	grad_norm 1.5804 (2.4542/0.8295)	mem 34602MB
[2025-01-19 00:12:19 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][70/312]	eta 0:03:00 lr 0.001248	time 0.7195 (0.7474)	model_time 0.7194 (0.7261)	loss 5.2647 (5.2277)	grad_norm 1.4212 (2.3653/0.8241)	mem 34602MB
[2025-01-19 00:12:26 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][80/312]	eta 0:02:52 lr 0.001254	time 0.7272 (0.7444)	model_time 0.7271 (0.7257)	loss 4.2061 (5.1934)	grad_norm 3.0325 (2.3641/0.8205)	mem 34602MB
[2025-01-19 00:12:33 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][90/312]	eta 0:02:45 lr 0.001260	time 0.7924 (0.7447)	model_time 0.7920 (0.7279)	loss 4.4512 (5.1968)	grad_norm 1.6420 (2.4011/0.8207)	mem 34602MB
[2025-01-19 00:12:41 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][100/312]	eta 0:02:38 lr 0.001267	time 0.8089 (0.7479)	model_time 0.8087 (0.7328)	loss 5.0683 (5.1699)	grad_norm 1.7042 (2.3869/0.8044)	mem 34602MB
[2025-01-19 00:12:48 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][110/312]	eta 0:02:30 lr 0.001273	time 0.7228 (0.7463)	model_time 0.7226 (0.7325)	loss 5.6823 (5.1605)	grad_norm 2.0671 (2.3668/0.7745)	mem 34602MB
[2025-01-19 00:12:56 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][120/312]	eta 0:02:23 lr 0.001280	time 0.7216 (0.7450)	model_time 0.7212 (0.7323)	loss 4.6519 (5.1639)	grad_norm 1.9849 (2.3764/0.7720)	mem 34602MB
[2025-01-19 00:13:03 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][130/312]	eta 0:02:15 lr 0.001286	time 0.7250 (0.7440)	model_time 0.7248 (0.7322)	loss 5.6815 (5.1673)	grad_norm 3.0260 (2.3907/0.7696)	mem 34602MB
[2025-01-19 00:13:10 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][140/312]	eta 0:02:07 lr 0.001292	time 0.7236 (0.7427)	model_time 0.7232 (0.7318)	loss 4.3223 (5.1863)	grad_norm 2.5629 (2.4168/0.7730)	mem 34602MB
[2025-01-19 00:13:18 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][150/312]	eta 0:02:00 lr 0.001299	time 0.7466 (0.7419)	model_time 0.7462 (0.7317)	loss 5.5492 (5.1911)	grad_norm 2.1975 (2.4568/0.8193)	mem 34602MB
[2025-01-19 00:13:25 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][160/312]	eta 0:01:52 lr 0.001305	time 0.7729 (0.7410)	model_time 0.7725 (0.7314)	loss 5.3767 (5.2015)	grad_norm 2.2719 (2.4851/0.8661)	mem 34602MB
[2025-01-19 00:13:32 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][170/312]	eta 0:01:45 lr 0.001312	time 0.7264 (0.7399)	model_time 0.7260 (0.7308)	loss 5.2447 (5.2046)	grad_norm 1.9367 (2.4489/0.8554)	mem 34602MB
[2025-01-19 00:13:39 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][180/312]	eta 0:01:37 lr 0.001318	time 0.7236 (0.7389)	model_time 0.7234 (0.7303)	loss 5.8367 (5.2007)	grad_norm 1.6684 (2.4537/0.8443)	mem 34602MB
[2025-01-19 00:13:47 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][190/312]	eta 0:01:30 lr 0.001324	time 0.7518 (0.7387)	model_time 0.7514 (0.7305)	loss 5.1881 (5.1868)	grad_norm 1.8142 (2.4766/0.8560)	mem 34602MB
[2025-01-19 00:13:54 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][200/312]	eta 0:01:22 lr 0.001331	time 0.7237 (0.7381)	model_time 0.7233 (0.7303)	loss 5.1222 (5.1976)	grad_norm 1.8400 (2.4799/0.8500)	mem 34602MB
[2025-01-19 00:14:01 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][210/312]	eta 0:01:15 lr 0.001337	time 0.8013 (0.7387)	model_time 0.8009 (0.7312)	loss 5.1662 (5.1913)	grad_norm 2.2612 (2.4579/0.8406)	mem 34602MB
[2025-01-19 00:14:09 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][220/312]	eta 0:01:08 lr 0.001344	time 0.8056 (0.7407)	model_time 0.8055 (0.7336)	loss 5.5807 (5.2045)	grad_norm 2.2254 (2.4400/0.8323)	mem 34602MB
[2025-01-19 00:14:17 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][230/312]	eta 0:01:00 lr 0.001350	time 0.7607 (0.7409)	model_time 0.7602 (0.7341)	loss 5.4031 (5.1974)	grad_norm 3.2426 (2.4414/0.8224)	mem 34602MB
[2025-01-19 00:14:24 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][240/312]	eta 0:00:53 lr 0.001356	time 0.7377 (0.7403)	model_time 0.7375 (0.7338)	loss 4.7226 (5.1935)	grad_norm 2.4875 (2.4598/0.8313)	mem 34602MB
[2025-01-19 00:14:31 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][250/312]	eta 0:00:45 lr 0.001363	time 0.7410 (0.7396)	model_time 0.7409 (0.7333)	loss 5.4436 (5.1952)	grad_norm 1.9019 (2.4857/0.8506)	mem 34602MB
[2025-01-19 00:14:38 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][260/312]	eta 0:00:38 lr 0.001369	time 0.7268 (0.7391)	model_time 0.7263 (0.7330)	loss 5.6148 (5.2000)	grad_norm 2.5103 (2.4829/0.8573)	mem 34602MB
[2025-01-19 00:14:46 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][270/312]	eta 0:00:31 lr 0.001376	time 0.7208 (0.7386)	model_time 0.7206 (0.7328)	loss 4.7249 (5.2029)	grad_norm 2.0687 (2.4609/0.8508)	mem 34602MB
[2025-01-19 00:14:53 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][280/312]	eta 0:00:23 lr 0.001382	time 0.7201 (0.7380)	model_time 0.7197 (0.7323)	loss 5.0560 (5.2032)	grad_norm 1.7769 (2.4420/0.8454)	mem 34602MB
[2025-01-19 00:15:00 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][290/312]	eta 0:00:16 lr 0.001389	time 0.7352 (0.7375)	model_time 0.7349 (0.7320)	loss 5.5573 (5.2030)	grad_norm 1.3055 (2.4394/0.8417)	mem 34602MB
[2025-01-19 00:15:07 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][300/312]	eta 0:00:08 lr 0.001395	time 0.7053 (0.7369)	model_time 0.7052 (0.7316)	loss 4.4885 (5.2034)	grad_norm 2.4618 (2.4352/0.8355)	mem 34602MB
[2025-01-19 00:15:15 internimage_b_1k_224] (main.py 510): INFO Train: [6/300][310/312]	eta 0:00:01 lr 0.001401	time 0.7099 (0.7365)	model_time 0.7098 (0.7313)	loss 4.8449 (5.2033)	grad_norm 1.5938 (2.4561/0.8483)	mem 34602MB
[2025-01-19 00:15:15 internimage_b_1k_224] (main.py 519): INFO EPOCH 6 training takes 0:03:49
[2025-01-19 00:15:15 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_6.pth saving......
[2025-01-19 00:15:19 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_6.pth saved !!!
[2025-01-19 00:15:26 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.095 (7.095)	Loss 2.4021 (2.4021)	Acc@1 48.438 (48.438)	Acc@5 74.585 (74.585)	Mem 34602MB
[2025-01-19 00:15:29 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.899)	Loss 3.2882 (2.8289)	Acc@1 32.251 (40.942)	Acc@5 59.204 (67.556)	Mem 34602MB
[2025-01-19 00:15:29 internimage_b_1k_224] (main.py 575): INFO [Epoch:6] * Acc@1 41.679 Acc@5 68.216
[2025-01-19 00:15:29 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 41.7%
[2025-01-19 00:15:29 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:15:32 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:15:32 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 41.68%
[2025-01-19 00:15:39 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.283 (7.283)	Loss 6.8684 (6.8684)	Acc@1 0.146 (0.146)	Acc@5 1.562 (1.562)	Mem 34602MB
[2025-01-19 00:15:42 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.930)	Loss 6.8409 (6.8431)	Acc@1 0.732 (0.360)	Acc@5 1.807 (1.507)	Mem 34602MB
[2025-01-19 00:15:43 internimage_b_1k_224] (main.py 575): INFO [Epoch:6] * Acc@1 0.536 Acc@5 1.929
[2025-01-19 00:15:43 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.5%
[2025-01-19 00:15:43 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:15:47 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:15:47 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.54%
[2025-01-19 00:15:49 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][0/312]	eta 0:11:17 lr 0.001403	time 2.1719 (2.1719)	model_time 0.7385 (0.7385)	loss 5.5059 (5.5059)	grad_norm 2.8439 (2.8439/0.0000)	mem 34602MB
[2025-01-19 00:15:56 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][10/312]	eta 0:04:18 lr 0.001409	time 0.7218 (0.8566)	model_time 0.7217 (0.7260)	loss 4.5517 (5.3154)	grad_norm 2.4261 (3.0805/1.1343)	mem 34602MB
[2025-01-19 00:16:04 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][20/312]	eta 0:03:56 lr 0.001415	time 0.8130 (0.8095)	model_time 0.8125 (0.7409)	loss 4.2890 (5.0531)	grad_norm 1.6322 (2.7675/1.1003)	mem 34602MB
[2025-01-19 00:16:12 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][30/312]	eta 0:03:45 lr 0.001422	time 0.8125 (0.8005)	model_time 0.8120 (0.7539)	loss 5.5485 (5.0802)	grad_norm 3.7180 (2.5764/1.0159)	mem 34602MB
[2025-01-19 00:16:19 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][40/312]	eta 0:03:33 lr 0.001428	time 0.7136 (0.7839)	model_time 0.7134 (0.7486)	loss 4.5719 (5.0055)	grad_norm 3.2964 (2.5610/0.9370)	mem 34602MB
[2025-01-19 00:16:26 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][50/312]	eta 0:03:22 lr 0.001435	time 0.7137 (0.7731)	model_time 0.7135 (0.7446)	loss 5.3172 (5.0000)	grad_norm 2.5499 (2.5345/0.8913)	mem 34602MB
[2025-01-19 00:16:34 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][60/312]	eta 0:03:12 lr 0.001441	time 0.7401 (0.7656)	model_time 0.7399 (0.7418)	loss 4.8582 (4.9947)	grad_norm 1.4438 (2.5198/0.8945)	mem 34602MB
[2025-01-19 00:16:41 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][70/312]	eta 0:03:03 lr 0.001447	time 0.7256 (0.7599)	model_time 0.7255 (0.7394)	loss 4.4722 (4.9909)	grad_norm 2.8469 (2.5867/0.9345)	mem 34602MB
[2025-01-19 00:16:48 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][80/312]	eta 0:02:55 lr 0.001454	time 0.7139 (0.7552)	model_time 0.7134 (0.7372)	loss 5.5498 (5.0128)	grad_norm 1.7905 (2.5768/0.9199)	mem 34602MB
[2025-01-19 00:16:55 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][90/312]	eta 0:02:46 lr 0.001460	time 0.7266 (0.7520)	model_time 0.7262 (0.7359)	loss 5.3277 (5.0317)	grad_norm 2.2882 (2.4937/0.9066)	mem 34602MB
[2025-01-19 00:17:03 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][100/312]	eta 0:02:38 lr 0.001467	time 0.7196 (0.7492)	model_time 0.7194 (0.7346)	loss 4.3062 (5.0224)	grad_norm 2.6688 (2.4934/0.8732)	mem 34602MB
[2025-01-19 00:17:10 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][110/312]	eta 0:02:30 lr 0.001473	time 0.7177 (0.7470)	model_time 0.7175 (0.7337)	loss 4.3915 (5.0237)	grad_norm 1.6296 (2.4417/0.8563)	mem 34602MB
[2025-01-19 00:17:17 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][120/312]	eta 0:02:23 lr 0.001479	time 0.7221 (0.7459)	model_time 0.7216 (0.7337)	loss 4.1711 (5.0214)	grad_norm 2.3350 (2.3887/0.8431)	mem 34602MB
[2025-01-19 00:17:24 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][130/312]	eta 0:02:15 lr 0.001486	time 0.7528 (0.7444)	model_time 0.7527 (0.7331)	loss 5.1364 (5.0198)	grad_norm 1.1100 (2.4038/0.8604)	mem 34602MB
[2025-01-19 00:17:32 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][140/312]	eta 0:02:08 lr 0.001492	time 0.8313 (0.7463)	model_time 0.8309 (0.7357)	loss 5.2476 (5.0334)	grad_norm 1.9972 (2.4130/0.8451)	mem 34602MB
[2025-01-19 00:17:40 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][150/312]	eta 0:02:01 lr 0.001499	time 0.8012 (0.7479)	model_time 0.8008 (0.7381)	loss 5.4041 (5.0411)	grad_norm 5.0656 (2.4535/0.9097)	mem 34602MB
[2025-01-19 00:17:47 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][160/312]	eta 0:01:53 lr 0.001505	time 0.7126 (0.7473)	model_time 0.7122 (0.7380)	loss 5.0748 (5.0388)	grad_norm 1.5895 (2.4377/0.9003)	mem 34602MB
[2025-01-19 00:17:54 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][170/312]	eta 0:01:45 lr 0.001511	time 0.7193 (0.7462)	model_time 0.7192 (0.7374)	loss 4.4630 (5.0350)	grad_norm 2.4481 (2.4530/0.9028)	mem 34602MB
[2025-01-19 00:18:02 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][180/312]	eta 0:01:38 lr 0.001518	time 0.7149 (0.7453)	model_time 0.7145 (0.7370)	loss 4.8966 (5.0297)	grad_norm 1.2305 (2.4349/0.9090)	mem 34602MB
[2025-01-19 00:18:09 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][190/312]	eta 0:01:30 lr 0.001524	time 0.7773 (0.7445)	model_time 0.7768 (0.7366)	loss 3.9578 (5.0201)	grad_norm 3.1728 (2.4603/0.9202)	mem 34602MB
[2025-01-19 00:18:16 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][200/312]	eta 0:01:23 lr 0.001531	time 0.7248 (0.7432)	model_time 0.7247 (0.7357)	loss 5.5872 (5.0271)	grad_norm 3.2922 (2.4584/0.9177)	mem 34602MB
[2025-01-19 00:18:24 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][210/312]	eta 0:01:15 lr 0.001537	time 0.7223 (0.7427)	model_time 0.7222 (0.7355)	loss 4.8452 (5.0167)	grad_norm 1.5813 (2.4242/0.9113)	mem 34602MB
[2025-01-19 00:18:31 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][220/312]	eta 0:01:08 lr 0.001543	time 0.7201 (0.7417)	model_time 0.7197 (0.7348)	loss 5.3747 (5.0213)	grad_norm 1.5009 (2.4111/0.9029)	mem 34602MB
[2025-01-19 00:18:38 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][230/312]	eta 0:01:00 lr 0.001550	time 0.7151 (0.7407)	model_time 0.7150 (0.7341)	loss 5.3025 (5.0199)	grad_norm 1.3240 (2.4220/0.9224)	mem 34602MB
[2025-01-19 00:18:45 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][240/312]	eta 0:00:53 lr 0.001556	time 0.7293 (0.7404)	model_time 0.7289 (0.7341)	loss 4.9608 (5.0122)	grad_norm 1.6190 (2.4236/0.9062)	mem 34602MB
[2025-01-19 00:18:53 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][250/312]	eta 0:00:45 lr 0.001563	time 0.7157 (0.7399)	model_time 0.7151 (0.7338)	loss 5.0312 (5.0134)	grad_norm 2.7125 (2.4147/0.8928)	mem 34602MB
[2025-01-19 00:19:00 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][260/312]	eta 0:00:38 lr 0.001569	time 0.8061 (0.7401)	model_time 0.8057 (0.7342)	loss 5.3270 (5.0153)	grad_norm 3.5624 (2.4179/0.8865)	mem 34602MB
[2025-01-19 00:19:08 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][270/312]	eta 0:00:31 lr 0.001576	time 0.8311 (0.7414)	model_time 0.8310 (0.7358)	loss 5.4243 (5.0279)	grad_norm 2.9315 (2.4154/0.8876)	mem 34602MB
[2025-01-19 00:19:15 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][280/312]	eta 0:00:23 lr 0.001582	time 0.7562 (0.7414)	model_time 0.7558 (0.7359)	loss 5.3531 (5.0127)	grad_norm 1.5645 (2.4157/0.8847)	mem 34602MB
[2025-01-19 00:19:22 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][290/312]	eta 0:00:16 lr 0.001588	time 0.7200 (0.7408)	model_time 0.7198 (0.7355)	loss 5.1060 (5.0110)	grad_norm 3.0171 (2.4085/0.8740)	mem 34602MB
[2025-01-19 00:19:30 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][300/312]	eta 0:00:08 lr 0.001595	time 0.7081 (0.7403)	model_time 0.7081 (0.7352)	loss 5.1521 (5.0103)	grad_norm 1.8284 (2.4105/0.8711)	mem 34602MB
[2025-01-19 00:19:37 internimage_b_1k_224] (main.py 510): INFO Train: [7/300][310/312]	eta 0:00:01 lr 0.001601	time 0.7109 (0.7393)	model_time 0.7108 (0.7344)	loss 4.9593 (5.0109)	grad_norm 1.8892 (2.3795/0.8362)	mem 34602MB
[2025-01-19 00:19:38 internimage_b_1k_224] (main.py 519): INFO EPOCH 7 training takes 0:03:50
[2025-01-19 00:19:38 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_7.pth saving......
[2025-01-19 00:19:41 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_7.pth saved !!!
[2025-01-19 00:19:56 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.145 (15.145)	Loss 2.2450 (2.2450)	Acc@1 52.051 (52.051)	Acc@5 77.417 (77.417)	Mem 34602MB
[2025-01-19 00:20:03 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (1.984)	Loss 2.9503 (2.5424)	Acc@1 37.793 (45.632)	Acc@5 64.014 (72.141)	Mem 34602MB
[2025-01-19 00:20:03 internimage_b_1k_224] (main.py 575): INFO [Epoch:7] * Acc@1 46.415 Acc@5 72.733
[2025-01-19 00:20:03 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 46.4%
[2025-01-19 00:20:03 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:20:06 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:20:06 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 46.42%
[2025-01-19 00:20:13 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.376 (7.376)	Loss 6.8579 (6.8579)	Acc@1 0.000 (0.000)	Acc@5 1.807 (1.807)	Mem 34602MB
[2025-01-19 00:20:16 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.927)	Loss 6.8365 (6.8341)	Acc@1 0.732 (0.375)	Acc@5 1.953 (1.585)	Mem 34602MB
[2025-01-19 00:20:16 internimage_b_1k_224] (main.py 575): INFO [Epoch:7] * Acc@1 0.564 Acc@5 2.075
[2025-01-19 00:20:16 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.6%
[2025-01-19 00:20:16 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:20:20 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:20:20 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.56%
[2025-01-19 00:20:22 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][0/312]	eta 0:10:34 lr 0.001602	time 2.0326 (2.0326)	model_time 0.7482 (0.7482)	loss 4.5733 (4.5733)	grad_norm 1.9639 (1.9639/0.0000)	mem 34602MB
[2025-01-19 00:20:29 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][10/312]	eta 0:04:14 lr 0.001609	time 0.7141 (0.8425)	model_time 0.7140 (0.7255)	loss 4.4867 (4.8633)	grad_norm 2.1681 (2.3326/0.7586)	mem 34602MB
[2025-01-19 00:20:37 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][20/312]	eta 0:03:49 lr 0.001615	time 0.7372 (0.7854)	model_time 0.7367 (0.7239)	loss 5.6364 (4.9335)	grad_norm 1.2489 (2.1845/0.8244)	mem 34602MB
[2025-01-19 00:20:44 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][30/312]	eta 0:03:36 lr 0.001622	time 0.7141 (0.7685)	model_time 0.7139 (0.7267)	loss 5.2336 (5.0053)	grad_norm 1.9686 (2.1690/0.6986)	mem 34602MB
[2025-01-19 00:20:51 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][40/312]	eta 0:03:26 lr 0.001628	time 0.7221 (0.7579)	model_time 0.7219 (0.7263)	loss 5.0569 (5.0080)	grad_norm 2.2217 (2.2377/0.7048)	mem 34602MB
[2025-01-19 00:20:58 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][50/312]	eta 0:03:16 lr 0.001634	time 0.7195 (0.7505)	model_time 0.7193 (0.7250)	loss 5.5629 (4.9863)	grad_norm 2.0998 (2.2015/0.6575)	mem 34602MB
[2025-01-19 00:21:06 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][60/312]	eta 0:03:08 lr 0.001641	time 0.7159 (0.7468)	model_time 0.7157 (0.7254)	loss 5.2619 (5.0298)	grad_norm 3.0117 (2.2028/0.6318)	mem 34602MB
[2025-01-19 00:21:13 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][70/312]	eta 0:03:01 lr 0.001647	time 0.8047 (0.7492)	model_time 0.8046 (0.7308)	loss 5.0792 (5.0561)	grad_norm 2.6364 (2.3037/0.7423)	mem 34602MB
[2025-01-19 00:21:21 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][80/312]	eta 0:02:54 lr 0.001654	time 0.7167 (0.7520)	model_time 0.7162 (0.7358)	loss 3.9242 (5.0449)	grad_norm 2.1586 (2.2289/0.7331)	mem 34602MB
[2025-01-19 00:21:29 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][90/312]	eta 0:02:46 lr 0.001660	time 0.7210 (0.7504)	model_time 0.7209 (0.7360)	loss 5.2197 (5.0375)	grad_norm 2.2811 (2.1936/0.7033)	mem 34602MB
[2025-01-19 00:21:36 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][100/312]	eta 0:02:38 lr 0.001666	time 0.7238 (0.7477)	model_time 0.7237 (0.7346)	loss 4.7613 (5.0132)	grad_norm 2.1243 (2.2058/0.6996)	mem 34602MB
[2025-01-19 00:21:43 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][110/312]	eta 0:02:30 lr 0.001673	time 0.7161 (0.7456)	model_time 0.7159 (0.7336)	loss 5.1472 (5.0147)	grad_norm 2.9497 (2.2065/0.6985)	mem 34602MB
[2025-01-19 00:21:50 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][120/312]	eta 0:02:22 lr 0.001679	time 0.7659 (0.7436)	model_time 0.7654 (0.7326)	loss 5.1845 (4.9975)	grad_norm 2.4128 (2.2238/0.7110)	mem 34602MB
[2025-01-19 00:21:57 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][130/312]	eta 0:02:15 lr 0.001686	time 0.7361 (0.7420)	model_time 0.7359 (0.7318)	loss 5.8043 (4.9993)	grad_norm 1.9056 (2.1924/0.7078)	mem 34602MB
[2025-01-19 00:22:05 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][140/312]	eta 0:02:07 lr 0.001692	time 0.7610 (0.7407)	model_time 0.7605 (0.7312)	loss 4.2733 (4.9920)	grad_norm 2.9802 (2.2086/0.6993)	mem 34602MB
[2025-01-19 00:22:12 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][150/312]	eta 0:01:59 lr 0.001698	time 0.7601 (0.7406)	model_time 0.7600 (0.7317)	loss 5.5787 (5.0029)	grad_norm 1.6478 (2.2455/0.7069)	mem 34602MB
[2025-01-19 00:22:19 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][160/312]	eta 0:01:52 lr 0.001705	time 0.7214 (0.7395)	model_time 0.7213 (0.7312)	loss 5.1340 (4.9884)	grad_norm 3.2813 (2.2530/0.7012)	mem 34602MB
[2025-01-19 00:22:26 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][170/312]	eta 0:01:44 lr 0.001711	time 0.7146 (0.7385)	model_time 0.7144 (0.7306)	loss 4.6866 (4.9817)	grad_norm 3.5004 (2.2506/0.7086)	mem 34602MB
[2025-01-19 00:22:34 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][180/312]	eta 0:01:37 lr 0.001718	time 0.7139 (0.7377)	model_time 0.7135 (0.7303)	loss 5.3249 (4.9830)	grad_norm 3.7283 (2.2915/0.7279)	mem 34602MB
[2025-01-19 00:22:41 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][190/312]	eta 0:01:30 lr 0.001724	time 0.8010 (0.7389)	model_time 0.8005 (0.7318)	loss 5.7190 (4.9854)	grad_norm 2.0090 (2.2819/0.7242)	mem 34602MB
[2025-01-19 00:22:49 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][200/312]	eta 0:01:22 lr 0.001730	time 0.7162 (0.7405)	model_time 0.7161 (0.7338)	loss 5.2947 (4.9868)	grad_norm 2.0381 (2.2783/0.7172)	mem 34602MB
[2025-01-19 00:22:56 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][210/312]	eta 0:01:15 lr 0.001737	time 0.7148 (0.7402)	model_time 0.7146 (0.7338)	loss 5.5605 (5.0027)	grad_norm 1.3929 (2.2923/0.7922)	mem 34602MB
[2025-01-19 00:23:04 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][220/312]	eta 0:01:08 lr 0.001743	time 0.7494 (0.7394)	model_time 0.7493 (0.7332)	loss 3.7645 (4.9976)	grad_norm 1.5522 (2.2608/0.7882)	mem 34602MB
[2025-01-19 00:23:11 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][230/312]	eta 0:01:00 lr 0.001750	time 0.7160 (0.7389)	model_time 0.7159 (0.7330)	loss 5.4092 (4.9986)	grad_norm 2.4225 (2.2849/0.8250)	mem 34602MB
[2025-01-19 00:23:18 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][240/312]	eta 0:00:53 lr 0.001756	time 0.7224 (0.7385)	model_time 0.7223 (0.7328)	loss 5.0979 (4.9848)	grad_norm 1.9513 (2.2761/0.8192)	mem 34602MB
[2025-01-19 00:23:25 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][250/312]	eta 0:00:45 lr 0.001762	time 0.7132 (0.7379)	model_time 0.7128 (0.7324)	loss 3.8164 (4.9721)	grad_norm 3.1747 (2.2872/0.8182)	mem 34602MB
[2025-01-19 00:23:33 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][260/312]	eta 0:00:38 lr 0.001769	time 0.7613 (0.7375)	model_time 0.7609 (0.7322)	loss 5.0799 (4.9621)	grad_norm 2.0007 (2.2877/0.8206)	mem 34602MB
[2025-01-19 00:23:40 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][270/312]	eta 0:00:30 lr 0.001775	time 0.7167 (0.7371)	model_time 0.7165 (0.7320)	loss 5.1989 (4.9622)	grad_norm 4.9978 (2.2941/0.8328)	mem 34602MB
[2025-01-19 00:23:47 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][280/312]	eta 0:00:23 lr 0.001782	time 0.7168 (0.7368)	model_time 0.7164 (0.7319)	loss 5.5887 (4.9619)	grad_norm 1.2593 (2.2905/0.8262)	mem 34602MB
[2025-01-19 00:23:54 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][290/312]	eta 0:00:16 lr 0.001788	time 0.7364 (0.7363)	model_time 0.7360 (0.7315)	loss 3.5110 (4.9465)	grad_norm 1.8291 (2.2719/0.8214)	mem 34602MB
[2025-01-19 00:24:02 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][300/312]	eta 0:00:08 lr 0.001795	time 0.7193 (0.7358)	model_time 0.7192 (0.7311)	loss 4.9850 (4.9378)	grad_norm 1.5554 (2.2827/0.8602)	mem 34602MB
[2025-01-19 00:24:09 internimage_b_1k_224] (main.py 510): INFO Train: [8/300][310/312]	eta 0:00:01 lr 0.001801	time 0.7091 (0.7352)	model_time 0.7090 (0.7308)	loss 5.0021 (4.9351)	grad_norm 3.2316 (2.2805/0.8552)	mem 34602MB
[2025-01-19 00:24:10 internimage_b_1k_224] (main.py 519): INFO EPOCH 8 training takes 0:03:49
[2025-01-19 00:24:10 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_8.pth saving......
[2025-01-19 00:24:13 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_8.pth saved !!!
[2025-01-19 00:24:20 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.201 (7.201)	Loss 2.1082 (2.1082)	Acc@1 54.785 (54.785)	Acc@5 80.054 (80.054)	Mem 34602MB
[2025-01-19 00:24:23 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.916)	Loss 2.7839 (2.3752)	Acc@1 40.674 (49.288)	Acc@5 67.896 (75.337)	Mem 34602MB
[2025-01-19 00:24:23 internimage_b_1k_224] (main.py 575): INFO [Epoch:8] * Acc@1 49.850 Acc@5 75.730
[2025-01-19 00:24:23 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 49.9%
[2025-01-19 00:24:23 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:24:27 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:24:27 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 49.85%
[2025-01-19 00:24:34 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.088 (7.088)	Loss 6.8471 (6.8471)	Acc@1 0.049 (0.049)	Acc@5 2.222 (2.222)	Mem 34602MB
[2025-01-19 00:24:37 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.906)	Loss 6.8338 (6.8243)	Acc@1 0.391 (0.431)	Acc@5 1.807 (1.707)	Mem 34602MB
[2025-01-19 00:24:37 internimage_b_1k_224] (main.py 575): INFO [Epoch:8] * Acc@1 0.650 Acc@5 2.217
[2025-01-19 00:24:37 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.6%
[2025-01-19 00:24:37 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:24:41 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:24:41 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.65%
[2025-01-19 00:24:43 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][0/312]	eta 0:10:40 lr 0.001802	time 2.0539 (2.0539)	model_time 0.7603 (0.7603)	loss 4.9710 (4.9710)	grad_norm 1.7995 (1.7995/0.0000)	mem 34602MB
[2025-01-19 00:24:50 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][10/312]	eta 0:04:30 lr 0.001809	time 0.7232 (0.8970)	model_time 0.7230 (0.7791)	loss 4.4018 (4.7789)	grad_norm 1.7536 (2.4173/0.8320)	mem 34602MB
[2025-01-19 00:24:58 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][20/312]	eta 0:03:59 lr 0.001815	time 0.7244 (0.8189)	model_time 0.7243 (0.7570)	loss 5.1733 (4.8044)	grad_norm 2.3903 (2.2030/0.7699)	mem 34602MB
[2025-01-19 00:25:05 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][30/312]	eta 0:03:42 lr 0.001821	time 0.7220 (0.7906)	model_time 0.7218 (0.7486)	loss 5.0143 (4.7786)	grad_norm 3.9526 (2.3508/0.8438)	mem 34602MB
[2025-01-19 00:25:12 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][40/312]	eta 0:03:30 lr 0.001828	time 0.7323 (0.7756)	model_time 0.7319 (0.7437)	loss 5.1872 (4.7464)	grad_norm 2.1199 (2.3517/0.7719)	mem 34602MB
[2025-01-19 00:25:20 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][50/312]	eta 0:03:20 lr 0.001834	time 0.7191 (0.7653)	model_time 0.7189 (0.7396)	loss 3.7619 (4.6833)	grad_norm 4.3947 (2.4023/0.9428)	mem 34602MB
[2025-01-19 00:25:27 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][60/312]	eta 0:03:11 lr 0.001841	time 0.7171 (0.7591)	model_time 0.7169 (0.7376)	loss 5.2442 (4.6542)	grad_norm 1.4587 (2.3093/0.9030)	mem 34602MB
[2025-01-19 00:25:34 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][70/312]	eta 0:03:02 lr 0.001847	time 0.7182 (0.7547)	model_time 0.7177 (0.7362)	loss 3.9468 (4.6563)	grad_norm 1.9688 (2.2874/0.8738)	mem 34602MB
[2025-01-19 00:25:42 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][80/312]	eta 0:02:54 lr 0.001853	time 0.7140 (0.7528)	model_time 0.7139 (0.7364)	loss 4.8088 (4.6265)	grad_norm 1.7144 (2.2289/0.8400)	mem 34602MB
[2025-01-19 00:25:49 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][90/312]	eta 0:02:46 lr 0.001860	time 0.7166 (0.7489)	model_time 0.7165 (0.7344)	loss 5.3087 (4.6753)	grad_norm 2.8414 (2.2388/0.8266)	mem 34602MB
[2025-01-19 00:25:56 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][100/312]	eta 0:02:38 lr 0.001866	time 0.7132 (0.7462)	model_time 0.7128 (0.7331)	loss 3.8382 (4.6618)	grad_norm 1.3686 (2.2604/0.9036)	mem 34602MB
[2025-01-19 00:26:03 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][110/312]	eta 0:02:30 lr 0.001873	time 0.7418 (0.7444)	model_time 0.7416 (0.7324)	loss 4.1238 (4.6767)	grad_norm 2.9015 (2.2493/0.8899)	mem 34602MB
[2025-01-19 00:26:11 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][120/312]	eta 0:02:23 lr 0.001879	time 0.8182 (0.7454)	model_time 0.8178 (0.7344)	loss 5.6190 (4.6930)	grad_norm 3.3737 (2.2208/0.8762)	mem 34602MB
[2025-01-19 00:26:19 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][130/312]	eta 0:02:16 lr 0.001885	time 0.7146 (0.7489)	model_time 0.7141 (0.7387)	loss 5.1880 (4.7199)	grad_norm 3.0411 (2.2175/0.8583)	mem 34602MB
[2025-01-19 00:26:26 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][140/312]	eta 0:02:08 lr 0.001892	time 0.7179 (0.7483)	model_time 0.7177 (0.7388)	loss 4.2414 (4.7106)	grad_norm 1.7330 (2.1979/0.8395)	mem 34602MB
[2025-01-19 00:26:33 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][150/312]	eta 0:02:01 lr 0.001898	time 0.7567 (0.7470)	model_time 0.7565 (0.7381)	loss 4.3314 (4.7114)	grad_norm 1.9940 (2.1976/0.8260)	mem 34602MB
[2025-01-19 00:26:41 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][160/312]	eta 0:01:53 lr 0.001905	time 0.7205 (0.7457)	model_time 0.7201 (0.7373)	loss 5.3123 (4.7108)	grad_norm 1.7532 (2.1752/0.8113)	mem 34602MB
[2025-01-19 00:26:48 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][170/312]	eta 0:01:45 lr 0.001911	time 0.7299 (0.7446)	model_time 0.7297 (0.7366)	loss 4.3676 (4.7232)	grad_norm 2.0219 (2.1916/0.8245)	mem 34602MB
[2025-01-19 00:26:55 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][180/312]	eta 0:01:38 lr 0.001917	time 0.7163 (0.7432)	model_time 0.7161 (0.7357)	loss 4.8801 (4.7165)	grad_norm 2.8459 (2.2018/0.8168)	mem 34602MB
[2025-01-19 00:27:02 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][190/312]	eta 0:01:30 lr 0.001924	time 0.7148 (0.7423)	model_time 0.7144 (0.7352)	loss 3.9298 (4.7181)	grad_norm 1.8107 (2.1982/0.8020)	mem 34602MB
[2025-01-19 00:27:10 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][200/312]	eta 0:01:23 lr 0.001930	time 0.7143 (0.7419)	model_time 0.7138 (0.7351)	loss 4.5343 (4.7168)	grad_norm 1.7433 (2.2001/0.7911)	mem 34602MB
[2025-01-19 00:27:17 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][210/312]	eta 0:01:15 lr 0.001937	time 0.7178 (0.7410)	model_time 0.7176 (0.7345)	loss 4.8680 (4.7263)	grad_norm 1.9376 (2.1921/0.7772)	mem 34602MB
[2025-01-19 00:27:24 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][220/312]	eta 0:01:08 lr 0.001943	time 0.7233 (0.7404)	model_time 0.7231 (0.7342)	loss 5.0942 (4.7183)	grad_norm 1.8964 (2.1680/0.7686)	mem 34602MB
[2025-01-19 00:27:31 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][230/312]	eta 0:01:00 lr 0.001949	time 0.7134 (0.7397)	model_time 0.7133 (0.7337)	loss 4.8211 (4.7303)	grad_norm 1.5744 (2.1832/0.7782)	mem 34602MB
[2025-01-19 00:27:39 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][240/312]	eta 0:00:53 lr 0.001956	time 0.8144 (0.7405)	model_time 0.8140 (0.7347)	loss 5.4183 (4.7270)	grad_norm 1.7468 (2.1598/0.7729)	mem 34602MB
[2025-01-19 00:27:47 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][250/312]	eta 0:00:46 lr 0.001962	time 0.7313 (0.7425)	model_time 0.7311 (0.7370)	loss 3.8702 (4.7290)	grad_norm 2.5762 (2.1542/0.7665)	mem 34602MB
[2025-01-19 00:27:54 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][260/312]	eta 0:00:38 lr 0.001969	time 0.7187 (0.7423)	model_time 0.7183 (0.7370)	loss 5.2139 (4.7200)	grad_norm 8.2659 (2.2049/0.8813)	mem 34602MB
[2025-01-19 00:28:02 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][270/312]	eta 0:00:31 lr 0.001975	time 0.7139 (0.7416)	model_time 0.7135 (0.7364)	loss 4.9328 (4.7166)	grad_norm 2.2560 (2.2137/0.8749)	mem 34602MB
[2025-01-19 00:28:09 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][280/312]	eta 0:00:23 lr 0.001982	time 0.7167 (0.7411)	model_time 0.7165 (0.7361)	loss 4.0659 (4.7094)	grad_norm 2.3497 (2.2165/0.8668)	mem 34602MB
[2025-01-19 00:28:16 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][290/312]	eta 0:00:16 lr 0.001988	time 0.7633 (0.7406)	model_time 0.7631 (0.7358)	loss 4.1024 (4.7169)	grad_norm 2.0911 (2.2169/0.8678)	mem 34602MB
[2025-01-19 00:28:23 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][300/312]	eta 0:00:08 lr 0.001994	time 0.7099 (0.7400)	model_time 0.7098 (0.7353)	loss 4.5964 (4.7131)	grad_norm 2.3847 (2.2247/0.8609)	mem 34602MB
[2025-01-19 00:28:30 internimage_b_1k_224] (main.py 510): INFO Train: [9/300][310/312]	eta 0:00:01 lr 0.002001	time 0.7125 (0.7391)	model_time 0.7124 (0.7346)	loss 4.6425 (4.7149)	grad_norm 1.5385 (2.2133/0.8533)	mem 34602MB
[2025-01-19 00:28:31 internimage_b_1k_224] (main.py 519): INFO EPOCH 9 training takes 0:03:50
[2025-01-19 00:28:31 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_9.pth saving......
[2025-01-19 00:28:34 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_9.pth saved !!!
[2025-01-19 00:28:42 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.220 (7.220)	Loss 1.8907 (1.8907)	Acc@1 58.887 (58.887)	Acc@5 83.594 (83.594)	Mem 34602MB
[2025-01-19 00:28:45 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.926)	Loss 2.6404 (2.2172)	Acc@1 43.286 (52.002)	Acc@5 69.141 (77.630)	Mem 34602MB
[2025-01-19 00:28:45 internimage_b_1k_224] (main.py 575): INFO [Epoch:9] * Acc@1 52.411 Acc@5 77.929
[2025-01-19 00:28:45 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 52.4%
[2025-01-19 00:28:45 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:28:48 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:28:48 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 52.41%
[2025-01-19 00:28:55 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.475 (7.475)	Loss 6.8340 (6.8340)	Acc@1 0.098 (0.098)	Acc@5 2.466 (2.466)	Mem 34602MB
[2025-01-19 00:28:58 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.943)	Loss 6.8299 (6.8130)	Acc@1 0.122 (0.442)	Acc@5 1.465 (1.756)	Mem 34602MB
[2025-01-19 00:28:59 internimage_b_1k_224] (main.py 575): INFO [Epoch:9] * Acc@1 0.664 Acc@5 2.265
[2025-01-19 00:28:59 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.7%
[2025-01-19 00:28:59 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:29:02 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:29:02 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.66%
[2025-01-19 00:29:04 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][0/312]	eta 0:10:43 lr 0.002002	time 2.0625 (2.0625)	model_time 0.7517 (0.7517)	loss 4.9546 (4.9546)	grad_norm 2.3170 (2.3170/0.0000)	mem 34602MB
[2025-01-19 00:29:12 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][10/312]	eta 0:04:17 lr 0.002008	time 0.7150 (0.8524)	model_time 0.7149 (0.7329)	loss 4.9766 (4.7554)	grad_norm 2.5845 (2.0503/0.6160)	mem 34602MB
[2025-01-19 00:29:19 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][20/312]	eta 0:03:51 lr 0.002015	time 0.7205 (0.7919)	model_time 0.7203 (0.7292)	loss 4.1234 (4.6039)	grad_norm 1.4750 (2.0235/0.6462)	mem 34602MB
[2025-01-19 00:29:26 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][30/312]	eta 0:03:37 lr 0.002021	time 0.7154 (0.7704)	model_time 0.7150 (0.7278)	loss 3.5253 (4.6400)	grad_norm 2.1340 (2.0536/0.7660)	mem 34602MB
[2025-01-19 00:29:33 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][40/312]	eta 0:03:26 lr 0.002028	time 0.7215 (0.7590)	model_time 0.7214 (0.7267)	loss 3.8700 (4.6381)	grad_norm 2.1320 (2.0247/0.6946)	mem 34602MB
[2025-01-19 00:29:41 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][50/312]	eta 0:03:18 lr 0.002034	time 0.7895 (0.7586)	model_time 0.7894 (0.7326)	loss 4.9880 (4.6552)	grad_norm 2.2416 (2.0342/0.6577)	mem 34602MB
[2025-01-19 00:29:49 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][60/312]	eta 0:03:12 lr 0.002040	time 0.7929 (0.7636)	model_time 0.7928 (0.7418)	loss 5.1510 (4.6699)	grad_norm 3.4109 (2.1258/0.6860)	mem 34602MB
[2025-01-19 00:29:56 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][70/312]	eta 0:03:03 lr 0.002047	time 0.7194 (0.7589)	model_time 0.7189 (0.7401)	loss 4.7095 (4.6383)	grad_norm 1.6784 (2.0349/0.6837)	mem 34602MB
[2025-01-19 00:30:04 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][80/312]	eta 0:02:55 lr 0.002053	time 0.7172 (0.7555)	model_time 0.7168 (0.7390)	loss 5.4299 (4.6609)	grad_norm 1.2215 (2.0495/0.6943)	mem 34602MB
[2025-01-19 00:30:11 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][90/312]	eta 0:02:47 lr 0.002060	time 0.7168 (0.7523)	model_time 0.7166 (0.7376)	loss 5.4971 (4.6741)	grad_norm 2.1234 (2.0571/0.7118)	mem 34602MB
[2025-01-19 00:30:18 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][100/312]	eta 0:02:38 lr 0.002066	time 0.7189 (0.7497)	model_time 0.7187 (0.7364)	loss 5.5607 (4.6837)	grad_norm 2.2535 (2.1089/0.7305)	mem 34602MB
[2025-01-19 00:30:25 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][110/312]	eta 0:02:30 lr 0.002072	time 0.7246 (0.7475)	model_time 0.7242 (0.7353)	loss 5.2689 (4.6950)	grad_norm 2.2163 (2.0793/0.7110)	mem 34602MB
[2025-01-19 00:30:33 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][120/312]	eta 0:02:23 lr 0.002079	time 0.7268 (0.7458)	model_time 0.7264 (0.7346)	loss 5.4563 (4.7301)	grad_norm 1.8206 (2.1219/0.7510)	mem 34602MB
[2025-01-19 00:30:40 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][130/312]	eta 0:02:15 lr 0.002085	time 0.7436 (0.7453)	model_time 0.7432 (0.7350)	loss 5.5081 (4.7283)	grad_norm 1.4714 (2.1039/0.7432)	mem 34602MB
[2025-01-19 00:30:47 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][140/312]	eta 0:02:08 lr 0.002092	time 0.7164 (0.7442)	model_time 0.7162 (0.7346)	loss 4.2172 (4.7271)	grad_norm 2.3967 (2.1045/0.7247)	mem 34602MB
[2025-01-19 00:30:55 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][150/312]	eta 0:02:00 lr 0.002098	time 0.7185 (0.7431)	model_time 0.7184 (0.7341)	loss 4.3426 (4.7183)	grad_norm 1.8456 (2.1430/0.7856)	mem 34602MB
[2025-01-19 00:31:02 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][160/312]	eta 0:01:52 lr 0.002104	time 0.7178 (0.7419)	model_time 0.7174 (0.7335)	loss 5.1400 (4.7094)	grad_norm 2.5331 (2.1226/0.7725)	mem 34602MB
[2025-01-19 00:31:09 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][170/312]	eta 0:01:45 lr 0.002111	time 0.8022 (0.7431)	model_time 0.8020 (0.7351)	loss 4.8193 (4.7085)	grad_norm 1.2093 (2.0918/0.7674)	mem 34602MB
[2025-01-19 00:31:17 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][180/312]	eta 0:01:38 lr 0.002117	time 0.8071 (0.7459)	model_time 0.8070 (0.7383)	loss 3.7378 (4.7108)	grad_norm 1.6742 (2.1071/0.7984)	mem 34602MB
[2025-01-19 00:31:25 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][190/312]	eta 0:01:30 lr 0.002124	time 0.7474 (0.7453)	model_time 0.7472 (0.7381)	loss 5.2550 (4.7219)	grad_norm 2.2075 (2.0939/0.7864)	mem 34602MB
[2025-01-19 00:31:32 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][200/312]	eta 0:01:23 lr 0.002130	time 0.7164 (0.7441)	model_time 0.7162 (0.7373)	loss 4.7489 (4.7255)	grad_norm 2.5305 (2.0796/0.7745)	mem 34602MB
[2025-01-19 00:31:39 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][210/312]	eta 0:01:15 lr 0.002136	time 0.7210 (0.7433)	model_time 0.7208 (0.7368)	loss 4.3820 (4.7084)	grad_norm 2.8382 (2.0861/0.7688)	mem 34602MB
[2025-01-19 00:31:46 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][220/312]	eta 0:01:08 lr 0.002143	time 0.7204 (0.7425)	model_time 0.7200 (0.7362)	loss 5.1761 (4.6889)	grad_norm 1.0518 (2.0793/0.7609)	mem 34602MB
[2025-01-19 00:31:54 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][230/312]	eta 0:01:00 lr 0.002149	time 0.7268 (0.7418)	model_time 0.7266 (0.7358)	loss 5.0803 (4.6890)	grad_norm 1.8489 (2.0640/0.7495)	mem 34602MB
[2025-01-19 00:32:01 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][240/312]	eta 0:00:53 lr 0.002156	time 0.7638 (0.7411)	model_time 0.7634 (0.7353)	loss 4.7324 (4.6852)	grad_norm 1.2129 (2.0732/0.7978)	mem 34602MB
[2025-01-19 00:32:08 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][250/312]	eta 0:00:45 lr 0.002162	time 0.7245 (0.7411)	model_time 0.7241 (0.7356)	loss 4.7849 (4.6833)	grad_norm 1.6847 (2.0792/0.7955)	mem 34602MB
[2025-01-19 00:32:16 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][260/312]	eta 0:00:38 lr 0.002169	time 0.7142 (0.7404)	model_time 0.7138 (0.7350)	loss 4.8185 (4.6851)	grad_norm 1.4709 (2.0759/0.7896)	mem 34602MB
[2025-01-19 00:32:23 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][270/312]	eta 0:00:31 lr 0.002175	time 0.7157 (0.7399)	model_time 0.7155 (0.7347)	loss 4.9002 (4.6863)	grad_norm 1.4188 (2.0706/0.7829)	mem 34602MB
[2025-01-19 00:32:30 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][280/312]	eta 0:00:23 lr 0.002181	time 0.7142 (0.7392)	model_time 0.7138 (0.7343)	loss 4.0397 (4.6736)	grad_norm 2.4231 (2.1126/0.8697)	mem 34602MB
[2025-01-19 00:32:37 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][290/312]	eta 0:00:16 lr 0.002188	time 0.8061 (0.7393)	model_time 0.8059 (0.7344)	loss 5.3365 (4.6803)	grad_norm 2.4701 (2.0994/0.8626)	mem 34602MB
[2025-01-19 00:32:45 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][300/312]	eta 0:00:08 lr 0.002194	time 0.7908 (0.7406)	model_time 0.7907 (0.7359)	loss 3.8979 (4.6760)	grad_norm 1.3029 (2.0765/0.8592)	mem 34602MB
[2025-01-19 00:32:53 internimage_b_1k_224] (main.py 510): INFO Train: [10/300][310/312]	eta 0:00:01 lr 0.002201	time 0.7116 (0.7407)	model_time 0.7115 (0.7361)	loss 4.2827 (4.6718)	grad_norm 1.7802 (2.0824/0.8690)	mem 34602MB
[2025-01-19 00:32:53 internimage_b_1k_224] (main.py 519): INFO EPOCH 10 training takes 0:03:51
[2025-01-19 00:32:53 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_10.pth saving......
[2025-01-19 00:32:56 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_10.pth saved !!!
[2025-01-19 00:33:04 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.183 (7.183)	Loss 1.7465 (1.7465)	Acc@1 61.499 (61.499)	Acc@5 85.205 (85.205)	Mem 34602MB
[2025-01-19 00:33:07 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.915)	Loss 2.4728 (2.0446)	Acc@1 47.339 (55.305)	Acc@5 72.803 (80.251)	Mem 34602MB
[2025-01-19 00:33:07 internimage_b_1k_224] (main.py 575): INFO [Epoch:10] * Acc@1 55.602 Acc@5 80.434
[2025-01-19 00:33:07 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 55.6%
[2025-01-19 00:33:07 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:33:10 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:33:10 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 55.60%
[2025-01-19 00:33:17 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.084 (7.084)	Loss 6.8163 (6.8163)	Acc@1 0.122 (0.122)	Acc@5 2.515 (2.515)	Mem 34602MB
[2025-01-19 00:33:20 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.916)	Loss 6.8269 (6.7995)	Acc@1 0.073 (0.428)	Acc@5 1.050 (1.804)	Mem 34602MB
[2025-01-19 00:33:21 internimage_b_1k_224] (main.py 575): INFO [Epoch:10] * Acc@1 0.668 Acc@5 2.297
[2025-01-19 00:33:21 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.7%
[2025-01-19 00:33:21 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:33:24 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:33:24 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.67%
[2025-01-19 00:33:26 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][0/312]	eta 0:11:13 lr 0.002202	time 2.1571 (2.1571)	model_time 0.7399 (0.7399)	loss 5.2623 (5.2623)	grad_norm 1.8399 (1.8399/0.0000)	mem 34602MB
[2025-01-19 00:33:34 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][10/312]	eta 0:04:17 lr 0.002208	time 0.7183 (0.8536)	model_time 0.7182 (0.7244)	loss 5.1923 (4.5508)	grad_norm 1.5940 (2.0712/0.6740)	mem 34602MB
[2025-01-19 00:33:41 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][20/312]	eta 0:03:52 lr 0.002215	time 0.7327 (0.7951)	model_time 0.7325 (0.7273)	loss 5.0068 (4.5471)	grad_norm 1.9516 (1.8276/0.5710)	mem 34602MB
[2025-01-19 00:33:48 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][30/312]	eta 0:03:37 lr 0.002221	time 0.7159 (0.7712)	model_time 0.7154 (0.7251)	loss 5.2723 (4.5999)	grad_norm 1.8430 (2.0026/0.7858)	mem 34602MB
[2025-01-19 00:33:55 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][40/312]	eta 0:03:26 lr 0.002227	time 0.7387 (0.7596)	model_time 0.7383 (0.7247)	loss 4.3124 (4.5051)	grad_norm 2.9805 (1.9714/0.7889)	mem 34602MB
[2025-01-19 00:34:03 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][50/312]	eta 0:03:17 lr 0.002234	time 0.7129 (0.7542)	model_time 0.7128 (0.7261)	loss 3.8295 (4.5249)	grad_norm 1.6019 (1.9729/0.7284)	mem 34602MB
[2025-01-19 00:34:10 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][60/312]	eta 0:03:09 lr 0.002240	time 0.7127 (0.7504)	model_time 0.7125 (0.7269)	loss 4.9758 (4.5506)	grad_norm 2.6704 (2.0856/0.8179)	mem 34602MB
[2025-01-19 00:34:17 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][70/312]	eta 0:03:00 lr 0.002247	time 0.7112 (0.7462)	model_time 0.7110 (0.7259)	loss 5.3375 (4.5519)	grad_norm 1.6057 (2.0751/0.7810)	mem 34602MB
[2025-01-19 00:34:25 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][80/312]	eta 0:02:52 lr 0.002253	time 0.7221 (0.7436)	model_time 0.7220 (0.7258)	loss 5.3451 (4.5635)	grad_norm 2.0408 (2.0412/0.7453)	mem 34602MB
[2025-01-19 00:34:32 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][90/312]	eta 0:02:44 lr 0.002259	time 0.7153 (0.7410)	model_time 0.7149 (0.7251)	loss 5.1800 (4.5349)	grad_norm 2.0449 (2.0436/0.7224)	mem 34602MB
[2025-01-19 00:34:39 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][100/312]	eta 0:02:37 lr 0.002266	time 0.7248 (0.7422)	model_time 0.7246 (0.7279)	loss 5.3006 (4.5427)	grad_norm 1.3912 (2.0163/0.6975)	mem 34602MB
[2025-01-19 00:34:47 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][110/312]	eta 0:02:30 lr 0.002272	time 0.7203 (0.7456)	model_time 0.7201 (0.7326)	loss 3.5045 (4.5267)	grad_norm 2.3185 (1.9959/0.6745)	mem 34602MB
[2025-01-19 00:34:55 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][120/312]	eta 0:02:23 lr 0.002279	time 0.7153 (0.7465)	model_time 0.7151 (0.7344)	loss 5.3144 (4.5259)	grad_norm 1.5923 (2.0050/0.6647)	mem 34602MB
[2025-01-19 00:35:02 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][130/312]	eta 0:02:15 lr 0.002285	time 0.7162 (0.7456)	model_time 0.7160 (0.7344)	loss 5.4679 (4.5583)	grad_norm 3.1401 (2.0526/0.7167)	mem 34602MB
[2025-01-19 00:35:09 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][140/312]	eta 0:02:07 lr 0.002291	time 0.7157 (0.7440)	model_time 0.7155 (0.7337)	loss 4.9638 (4.5619)	grad_norm 1.2374 (2.0509/0.7137)	mem 34602MB
[2025-01-19 00:35:16 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][150/312]	eta 0:02:00 lr 0.002298	time 0.7254 (0.7427)	model_time 0.7253 (0.7330)	loss 4.6328 (4.5771)	grad_norm 1.2244 (2.0433/0.7081)	mem 34602MB
[2025-01-19 00:35:24 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][160/312]	eta 0:01:52 lr 0.002304	time 0.7455 (0.7419)	model_time 0.7451 (0.7327)	loss 3.7032 (4.5815)	grad_norm 1.2062 (2.0116/0.6995)	mem 34602MB
[2025-01-19 00:35:31 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][170/312]	eta 0:01:45 lr 0.002311	time 0.7134 (0.7413)	model_time 0.7133 (0.7327)	loss 3.4377 (4.5647)	grad_norm 3.0405 (2.0092/0.6931)	mem 34602MB
[2025-01-19 00:35:38 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][180/312]	eta 0:01:37 lr 0.002317	time 0.7539 (0.7405)	model_time 0.7538 (0.7323)	loss 4.3744 (4.5808)	grad_norm 1.2202 (2.0162/0.6855)	mem 34602MB
[2025-01-19 00:35:46 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][190/312]	eta 0:01:30 lr 0.002323	time 0.7344 (0.7398)	model_time 0.7339 (0.7321)	loss 4.0845 (4.5861)	grad_norm 2.1811 (2.0276/0.6887)	mem 34602MB
[2025-01-19 00:35:53 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][200/312]	eta 0:01:22 lr 0.002330	time 0.7173 (0.7388)	model_time 0.7172 (0.7314)	loss 4.5764 (4.5985)	grad_norm 3.1631 (2.0284/0.6892)	mem 34602MB
[2025-01-19 00:36:00 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][210/312]	eta 0:01:15 lr 0.002336	time 0.7165 (0.7380)	model_time 0.7164 (0.7310)	loss 5.6588 (4.5997)	grad_norm 1.4550 (2.0379/0.7010)	mem 34602MB
[2025-01-19 00:36:07 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][220/312]	eta 0:01:07 lr 0.002343	time 0.7197 (0.7382)	model_time 0.7193 (0.7314)	loss 5.0382 (4.6047)	grad_norm 2.9093 (2.0330/0.6921)	mem 34602MB
[2025-01-19 00:36:15 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][230/312]	eta 0:01:00 lr 0.002349	time 0.7273 (0.7401)	model_time 0.7267 (0.7336)	loss 4.8170 (4.6005)	grad_norm 1.3335 (2.0194/0.6891)	mem 34602MB
[2025-01-19 00:36:23 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][240/312]	eta 0:00:53 lr 0.002355	time 0.7162 (0.7410)	model_time 0.7161 (0.7347)	loss 4.1436 (4.6017)	grad_norm 5.1282 (2.0275/0.7122)	mem 34602MB
[2025-01-19 00:36:30 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][250/312]	eta 0:00:45 lr 0.002362	time 0.7279 (0.7401)	model_time 0.7277 (0.7341)	loss 4.7184 (4.6050)	grad_norm 1.8365 (2.0367/0.7330)	mem 34602MB
[2025-01-19 00:36:37 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][260/312]	eta 0:00:38 lr 0.002368	time 0.7359 (0.7397)	model_time 0.7357 (0.7340)	loss 4.1118 (4.6026)	grad_norm 1.5812 (2.0180/0.7280)	mem 34602MB
[2025-01-19 00:36:45 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][270/312]	eta 0:00:31 lr 0.002375	time 0.7185 (0.7391)	model_time 0.7181 (0.7336)	loss 4.5577 (4.5973)	grad_norm 3.9029 (2.0215/0.7421)	mem 34602MB
[2025-01-19 00:36:52 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][280/312]	eta 0:00:23 lr 0.002381	time 0.7167 (0.7386)	model_time 0.7165 (0.7333)	loss 5.1927 (4.5946)	grad_norm 1.8502 (2.0267/0.7413)	mem 34602MB
[2025-01-19 00:36:59 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][290/312]	eta 0:00:16 lr 0.002388	time 0.7134 (0.7385)	model_time 0.7133 (0.7333)	loss 4.8485 (4.5981)	grad_norm 1.8637 (2.0121/0.7357)	mem 34602MB
[2025-01-19 00:37:06 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][300/312]	eta 0:00:08 lr 0.002394	time 0.7112 (0.7380)	model_time 0.7110 (0.7330)	loss 4.1570 (4.5983)	grad_norm 2.7687 (2.0159/0.7318)	mem 34602MB
[2025-01-19 00:37:14 internimage_b_1k_224] (main.py 510): INFO Train: [11/300][310/312]	eta 0:00:01 lr 0.002400	time 0.7162 (0.7373)	model_time 0.7161 (0.7324)	loss 5.0748 (4.6000)	grad_norm 1.6870 (1.9997/0.7256)	mem 34602MB
[2025-01-19 00:37:14 internimage_b_1k_224] (main.py 519): INFO EPOCH 11 training takes 0:03:50
[2025-01-19 00:37:14 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_11.pth saving......
[2025-01-19 00:37:18 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_11.pth saved !!!
[2025-01-19 00:37:25 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.290 (7.290)	Loss 1.6597 (1.6597)	Acc@1 63.843 (63.843)	Acc@5 85.962 (85.962)	Mem 34602MB
[2025-01-19 00:37:28 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.919)	Loss 2.4148 (1.9887)	Acc@1 49.268 (57.244)	Acc@5 73.804 (81.550)	Mem 34602MB
[2025-01-19 00:37:28 internimage_b_1k_224] (main.py 575): INFO [Epoch:11] * Acc@1 57.684 Acc@5 81.884
[2025-01-19 00:37:28 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 57.7%
[2025-01-19 00:37:28 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:37:31 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:37:31 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 57.68%
[2025-01-19 00:37:38 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.146 (7.146)	Loss 6.7928 (6.7928)	Acc@1 0.049 (0.049)	Acc@5 2.710 (2.710)	Mem 34602MB
[2025-01-19 00:37:41 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.916)	Loss 6.8253 (6.7846)	Acc@1 0.024 (0.391)	Acc@5 1.221 (1.938)	Mem 34602MB
[2025-01-19 00:37:41 internimage_b_1k_224] (main.py 575): INFO [Epoch:11] * Acc@1 0.620 Acc@5 2.441
[2025-01-19 00:37:42 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.6%
[2025-01-19 00:37:42 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.67%
[2025-01-19 00:37:45 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][0/312]	eta 0:17:19 lr 0.002402	time 3.3309 (3.3309)	model_time 1.6140 (1.6140)	loss 4.7799 (4.7799)	grad_norm 1.3760 (1.3760/0.0000)	mem 34602MB
[2025-01-19 00:37:52 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][10/312]	eta 0:04:52 lr 0.002408	time 0.7161 (0.9672)	model_time 0.7160 (0.8108)	loss 5.0138 (4.3094)	grad_norm 2.8400 (2.2077/1.2013)	mem 34602MB
[2025-01-19 00:38:00 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][20/312]	eta 0:04:10 lr 0.002414	time 0.7329 (0.8582)	model_time 0.7325 (0.7761)	loss 3.5941 (4.4277)	grad_norm 1.7829 (2.2660/1.0490)	mem 34602MB
[2025-01-19 00:38:07 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][30/312]	eta 0:03:51 lr 0.002421	time 0.8140 (0.8221)	model_time 0.8138 (0.7664)	loss 4.8308 (4.4538)	grad_norm 1.7253 (2.1104/0.9274)	mem 34602MB
[2025-01-19 00:38:15 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][40/312]	eta 0:03:40 lr 0.002427	time 0.7144 (0.8114)	model_time 0.7142 (0.7691)	loss 4.5024 (4.4654)	grad_norm 1.3585 (2.1235/0.8589)	mem 34602MB
[2025-01-19 00:38:22 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][50/312]	eta 0:03:29 lr 0.002434	time 0.7151 (0.7996)	model_time 0.7150 (0.7655)	loss 4.1647 (4.4922)	grad_norm 4.4630 (2.2655/0.9628)	mem 34602MB
[2025-01-19 00:38:30 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][60/312]	eta 0:03:18 lr 0.002440	time 0.7229 (0.7883)	model_time 0.7225 (0.7598)	loss 3.4519 (4.5078)	grad_norm 1.3110 (2.1595/0.9247)	mem 34602MB
[2025-01-19 00:38:37 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][70/312]	eta 0:03:08 lr 0.002446	time 0.7304 (0.7789)	model_time 0.7303 (0.7543)	loss 3.5964 (4.4702)	grad_norm 3.1412 (2.1239/0.8884)	mem 34602MB
[2025-01-19 00:38:44 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][80/312]	eta 0:02:59 lr 0.002453	time 0.7405 (0.7717)	model_time 0.7400 (0.7501)	loss 5.1462 (4.5016)	grad_norm 1.6006 (2.1078/0.8548)	mem 34602MB
[2025-01-19 00:38:51 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][90/312]	eta 0:02:50 lr 0.002459	time 0.7225 (0.7667)	model_time 0.7223 (0.7475)	loss 4.6554 (4.5092)	grad_norm 2.2582 (2.2299/0.9933)	mem 34602MB
[2025-01-19 00:38:58 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][100/312]	eta 0:02:41 lr 0.002466	time 0.7138 (0.7620)	model_time 0.7134 (0.7446)	loss 5.3001 (4.4856)	grad_norm 1.1859 (2.1755/0.9689)	mem 34602MB
[2025-01-19 00:39:06 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][110/312]	eta 0:02:33 lr 0.002472	time 0.7170 (0.7582)	model_time 0.7168 (0.7424)	loss 3.2046 (4.4923)	grad_norm 1.7131 (2.1779/0.9603)	mem 34602MB
[2025-01-19 00:39:13 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][120/312]	eta 0:02:25 lr 0.002478	time 0.7161 (0.7556)	model_time 0.7157 (0.7411)	loss 4.0341 (4.4753)	grad_norm 1.6926 (2.1414/0.9413)	mem 34602MB
[2025-01-19 00:39:20 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][130/312]	eta 0:02:17 lr 0.002485	time 0.7148 (0.7528)	model_time 0.7143 (0.7393)	loss 5.3584 (4.4763)	grad_norm 1.5992 (2.1058/0.9154)	mem 34602MB
[2025-01-19 00:39:27 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][140/312]	eta 0:02:09 lr 0.002491	time 0.7168 (0.7514)	model_time 0.7167 (0.7388)	loss 4.8299 (4.4635)	grad_norm 1.8644 (2.0819/0.8904)	mem 34602MB
[2025-01-19 00:39:35 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][150/312]	eta 0:02:01 lr 0.002498	time 0.8001 (0.7512)	model_time 0.7996 (0.7395)	loss 4.5749 (4.4634)	grad_norm 2.3681 (2.0809/0.8881)	mem 34602MB
[2025-01-19 00:39:43 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][160/312]	eta 0:01:54 lr 0.002504	time 0.7187 (0.7529)	model_time 0.7183 (0.7419)	loss 4.1322 (4.4581)	grad_norm 1.1897 (2.0458/0.8763)	mem 34602MB
[2025-01-19 00:39:50 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][170/312]	eta 0:01:46 lr 0.002510	time 0.7193 (0.7530)	model_time 0.7191 (0.7426)	loss 5.4669 (4.4692)	grad_norm 1.5204 (2.0458/0.8755)	mem 34602MB
[2025-01-19 00:39:58 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][180/312]	eta 0:01:39 lr 0.002517	time 0.7427 (0.7516)	model_time 0.7423 (0.7418)	loss 3.9362 (4.4726)	grad_norm 2.7091 (2.0251/0.8627)	mem 34602MB
[2025-01-19 00:40:05 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][190/312]	eta 0:01:31 lr 0.002523	time 0.7176 (0.7503)	model_time 0.7171 (0.7409)	loss 3.9507 (4.4657)	grad_norm 1.7191 (2.0042/0.8551)	mem 34602MB
[2025-01-19 00:40:12 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][200/312]	eta 0:01:23 lr 0.002530	time 0.7274 (0.7489)	model_time 0.7270 (0.7399)	loss 4.6777 (4.4579)	grad_norm 3.8233 (1.9987/0.8593)	mem 34602MB
[2025-01-19 00:40:19 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][210/312]	eta 0:01:16 lr 0.002536	time 0.7157 (0.7476)	model_time 0.7155 (0.7391)	loss 4.7162 (4.4545)	grad_norm 1.2162 (2.0018/0.8710)	mem 34602MB
[2025-01-19 00:40:27 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][220/312]	eta 0:01:08 lr 0.002542	time 0.7346 (0.7467)	model_time 0.7342 (0.7386)	loss 4.8684 (4.4605)	grad_norm 1.6856 (2.0124/0.8697)	mem 34602MB
[2025-01-19 00:40:34 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][230/312]	eta 0:01:01 lr 0.002549	time 0.7126 (0.7456)	model_time 0.7122 (0.7378)	loss 4.4802 (4.4667)	grad_norm 2.2051 (2.0259/0.8622)	mem 34602MB
[2025-01-19 00:40:41 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][240/312]	eta 0:00:53 lr 0.002555	time 0.7128 (0.7447)	model_time 0.7126 (0.7372)	loss 3.5618 (4.4679)	grad_norm 1.9143 (2.0091/0.8528)	mem 34602MB
[2025-01-19 00:40:48 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][250/312]	eta 0:00:46 lr 0.002562	time 0.7162 (0.7437)	model_time 0.7160 (0.7365)	loss 3.4978 (4.4727)	grad_norm 1.8675 (1.9925/0.8434)	mem 34602MB
[2025-01-19 00:40:56 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][260/312]	eta 0:00:38 lr 0.002568	time 0.7148 (0.7435)	model_time 0.7144 (0.7366)	loss 4.4644 (4.4703)	grad_norm 1.5151 (1.9843/0.8314)	mem 34602MB
[2025-01-19 00:41:03 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][270/312]	eta 0:00:31 lr 0.002575	time 0.8193 (0.7435)	model_time 0.8188 (0.7367)	loss 3.9671 (4.4634)	grad_norm 2.3853 (1.9731/0.8242)	mem 34602MB
[2025-01-19 00:41:11 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][280/312]	eta 0:00:23 lr 0.002581	time 0.7160 (0.7444)	model_time 0.7159 (0.7380)	loss 5.4664 (4.4721)	grad_norm 3.8880 (1.9916/0.8475)	mem 34602MB
[2025-01-19 00:41:18 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][290/312]	eta 0:00:16 lr 0.002587	time 0.8042 (0.7450)	model_time 0.8040 (0.7387)	loss 4.4527 (4.4653)	grad_norm 1.2679 (1.9836/0.8376)	mem 34602MB
[2025-01-19 00:41:26 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][300/312]	eta 0:00:08 lr 0.002594	time 0.7130 (0.7442)	model_time 0.7129 (0.7382)	loss 4.5987 (4.4790)	grad_norm 2.0967 (1.9877/0.8298)	mem 34602MB
[2025-01-19 00:41:33 internimage_b_1k_224] (main.py 510): INFO Train: [12/300][310/312]	eta 0:00:01 lr 0.002600	time 0.7470 (0.7433)	model_time 0.7469 (0.7374)	loss 5.4676 (4.4884)	grad_norm 3.0539 (1.9810/0.8068)	mem 34602MB
[2025-01-19 00:41:33 internimage_b_1k_224] (main.py 519): INFO EPOCH 12 training takes 0:03:51
[2025-01-19 00:41:33 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_12.pth saving......
[2025-01-19 00:41:36 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_12.pth saved !!!
[2025-01-19 00:41:51 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.577 (14.577)	Loss 1.6446 (1.6446)	Acc@1 64.941 (64.941)	Acc@5 87.012 (87.012)	Mem 34602MB
[2025-01-19 00:41:57 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.183 (1.873)	Loss 2.3150 (1.9201)	Acc@1 51.196 (58.636)	Acc@5 75.391 (82.415)	Mem 34602MB
[2025-01-19 00:41:57 internimage_b_1k_224] (main.py 575): INFO [Epoch:12] * Acc@1 58.997 Acc@5 82.646
[2025-01-19 00:41:57 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 59.0%
[2025-01-19 00:41:57 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:42:01 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:42:01 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 59.00%
[2025-01-19 00:42:16 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.585 (15.585)	Loss 6.7627 (6.7627)	Acc@1 0.073 (0.073)	Acc@5 2.881 (2.881)	Mem 34602MB
[2025-01-19 00:42:24 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.070)	Loss 6.8277 (6.7689)	Acc@1 0.024 (0.408)	Acc@5 1.172 (2.086)	Mem 34602MB
[2025-01-19 00:42:24 internimage_b_1k_224] (main.py 575): INFO [Epoch:12] * Acc@1 0.618 Acc@5 2.607
[2025-01-19 00:42:24 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.6%
[2025-01-19 00:42:24 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.67%
[2025-01-19 00:42:27 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][0/312]	eta 0:14:59 lr 0.002601	time 2.8834 (2.8834)	model_time 1.3959 (1.3959)	loss 4.7112 (4.7112)	grad_norm 2.0612 (2.0612/0.0000)	mem 34602MB
[2025-01-19 00:42:34 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][10/312]	eta 0:04:38 lr 0.002608	time 0.7349 (0.9215)	model_time 0.7348 (0.7859)	loss 3.3930 (4.0945)	grad_norm 1.7843 (2.1647/1.1231)	mem 34602MB
[2025-01-19 00:42:41 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][20/312]	eta 0:04:02 lr 0.002614	time 0.7214 (0.8301)	model_time 0.7213 (0.7589)	loss 5.2766 (4.2186)	grad_norm 1.7200 (1.9313/0.8871)	mem 34602MB
[2025-01-19 00:42:49 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][30/312]	eta 0:03:45 lr 0.002621	time 0.7186 (0.7981)	model_time 0.7182 (0.7497)	loss 4.1678 (4.1561)	grad_norm 1.0489 (1.9538/0.8685)	mem 34602MB
[2025-01-19 00:42:56 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][40/312]	eta 0:03:32 lr 0.002627	time 0.7170 (0.7801)	model_time 0.7166 (0.7435)	loss 3.9606 (4.2417)	grad_norm 1.7612 (1.9592/0.8504)	mem 34602MB
[2025-01-19 00:43:03 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][50/312]	eta 0:03:21 lr 0.002633	time 0.7360 (0.7698)	model_time 0.7358 (0.7403)	loss 4.9047 (4.2252)	grad_norm 1.1567 (1.9484/0.7910)	mem 34602MB
[2025-01-19 00:43:10 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][60/312]	eta 0:03:12 lr 0.002640	time 0.7137 (0.7626)	model_time 0.7135 (0.7378)	loss 4.3759 (4.2877)	grad_norm 1.1739 (1.9234/0.7518)	mem 34602MB
[2025-01-19 00:43:18 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][70/312]	eta 0:03:03 lr 0.002646	time 0.7233 (0.7571)	model_time 0.7229 (0.7358)	loss 5.4001 (4.3124)	grad_norm 1.8186 (1.9050/0.7289)	mem 34602MB
[2025-01-19 00:43:25 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][80/312]	eta 0:02:55 lr 0.002653	time 0.8259 (0.7566)	model_time 0.8258 (0.7378)	loss 4.3639 (4.3073)	grad_norm 1.7994 (1.9342/0.7469)	mem 34602MB
[2025-01-19 00:43:33 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][90/312]	eta 0:02:48 lr 0.002659	time 0.7174 (0.7604)	model_time 0.7172 (0.7437)	loss 4.3963 (4.3127)	grad_norm 1.7865 (1.9053/0.7197)	mem 34602MB
[2025-01-19 00:43:41 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][100/312]	eta 0:02:41 lr 0.002665	time 0.8070 (0.7601)	model_time 0.8066 (0.7451)	loss 4.8772 (4.3540)	grad_norm 1.2952 (1.9326/0.7953)	mem 34602MB
[2025-01-19 00:43:48 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][110/312]	eta 0:02:32 lr 0.002672	time 0.7153 (0.7569)	model_time 0.7152 (0.7432)	loss 4.7193 (4.3717)	grad_norm 2.0328 (1.9496/0.7907)	mem 34602MB
[2025-01-19 00:43:55 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][120/312]	eta 0:02:24 lr 0.002678	time 0.7219 (0.7544)	model_time 0.7217 (0.7418)	loss 4.8266 (4.3938)	grad_norm 1.2863 (1.9301/0.7661)	mem 34602MB
[2025-01-19 00:44:02 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][130/312]	eta 0:02:17 lr 0.002685	time 0.7142 (0.7529)	model_time 0.7138 (0.7412)	loss 3.8959 (4.3899)	grad_norm 2.3272 (1.9175/0.7488)	mem 34602MB
[2025-01-19 00:44:10 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][140/312]	eta 0:02:09 lr 0.002691	time 0.7474 (0.7511)	model_time 0.7472 (0.7402)	loss 5.3518 (4.3920)	grad_norm 1.4125 (1.8970/0.7301)	mem 34602MB
[2025-01-19 00:44:17 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][150/312]	eta 0:02:01 lr 0.002697	time 0.7420 (0.7493)	model_time 0.7416 (0.7391)	loss 4.6840 (4.3960)	grad_norm 1.8637 (1.8862/0.7093)	mem 34602MB
[2025-01-19 00:44:24 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][160/312]	eta 0:01:53 lr 0.002704	time 0.7256 (0.7478)	model_time 0.7254 (0.7382)	loss 4.9565 (4.4055)	grad_norm 1.7095 (1.9233/0.7400)	mem 34602MB
[2025-01-19 00:44:31 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][170/312]	eta 0:01:45 lr 0.002710	time 0.7433 (0.7464)	model_time 0.7432 (0.7373)	loss 4.6039 (4.4044)	grad_norm 2.6535 (1.9270/0.7351)	mem 34602MB
[2025-01-19 00:44:39 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][180/312]	eta 0:01:38 lr 0.002717	time 0.7732 (0.7456)	model_time 0.7730 (0.7370)	loss 4.3841 (4.3892)	grad_norm 2.2468 (1.9204/0.7267)	mem 34602MB
[2025-01-19 00:44:46 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][190/312]	eta 0:01:30 lr 0.002723	time 0.7129 (0.7445)	model_time 0.7125 (0.7364)	loss 5.3037 (4.3983)	grad_norm 1.9947 (1.9049/0.7181)	mem 34602MB
[2025-01-19 00:44:54 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][200/312]	eta 0:01:23 lr 0.002729	time 0.8175 (0.7447)	model_time 0.8174 (0.7370)	loss 4.9062 (4.4094)	grad_norm 1.6310 (1.9275/0.7345)	mem 34602MB
[2025-01-19 00:45:01 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][210/312]	eta 0:01:16 lr 0.002736	time 0.8117 (0.7464)	model_time 0.8113 (0.7390)	loss 3.7182 (4.3981)	grad_norm 1.0913 (1.9036/0.7298)	mem 34602MB
[2025-01-19 00:45:09 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][220/312]	eta 0:01:08 lr 0.002742	time 0.7905 (0.7468)	model_time 0.7903 (0.7397)	loss 3.2944 (4.3900)	grad_norm 1.4790 (1.8939/0.7237)	mem 34602MB
[2025-01-19 00:45:16 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][230/312]	eta 0:01:01 lr 0.002749	time 0.7223 (0.7462)	model_time 0.7219 (0.7394)	loss 5.2590 (4.3938)	grad_norm 2.1043 (1.9131/0.7715)	mem 34602MB
[2025-01-19 00:45:23 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][240/312]	eta 0:00:53 lr 0.002755	time 0.7289 (0.7451)	model_time 0.7285 (0.7386)	loss 5.3013 (4.3983)	grad_norm 1.2332 (1.9071/0.7624)	mem 34602MB
[2025-01-19 00:45:31 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][250/312]	eta 0:00:46 lr 0.002761	time 0.7148 (0.7445)	model_time 0.7147 (0.7383)	loss 4.5399 (4.3873)	grad_norm 1.5343 (1.9034/0.7588)	mem 34602MB
[2025-01-19 00:45:38 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][260/312]	eta 0:00:38 lr 0.002768	time 0.7247 (0.7438)	model_time 0.7242 (0.7378)	loss 4.5771 (4.3963)	grad_norm 2.4058 (1.8914/0.7520)	mem 34602MB
[2025-01-19 00:45:45 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][270/312]	eta 0:00:31 lr 0.002774	time 0.7188 (0.7431)	model_time 0.7184 (0.7372)	loss 3.2407 (4.3990)	grad_norm 2.1434 (1.9031/0.7481)	mem 34602MB
[2025-01-19 00:45:53 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][280/312]	eta 0:00:23 lr 0.002781	time 0.7262 (0.7426)	model_time 0.7257 (0.7369)	loss 3.1149 (4.3919)	grad_norm 1.6147 (1.9004/0.7384)	mem 34602MB
[2025-01-19 00:46:00 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][290/312]	eta 0:00:16 lr 0.002787	time 0.7165 (0.7419)	model_time 0.7164 (0.7364)	loss 4.7534 (4.3851)	grad_norm 1.5420 (1.8979/0.7336)	mem 34602MB
[2025-01-19 00:46:07 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][300/312]	eta 0:00:08 lr 0.002794	time 0.7134 (0.7413)	model_time 0.7133 (0.7360)	loss 4.5171 (4.3873)	grad_norm 1.7187 (1.8782/0.7327)	mem 34602MB
[2025-01-19 00:46:14 internimage_b_1k_224] (main.py 510): INFO Train: [13/300][310/312]	eta 0:00:01 lr 0.002800	time 0.7110 (0.7404)	model_time 0.7109 (0.7353)	loss 4.5820 (4.3819)	grad_norm 2.0250 (1.8775/0.7205)	mem 34602MB
[2025-01-19 00:46:15 internimage_b_1k_224] (main.py 519): INFO EPOCH 13 training takes 0:03:50
[2025-01-19 00:46:15 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_13.pth saving......
[2025-01-19 00:46:18 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_13.pth saved !!!
[2025-01-19 00:46:25 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.163 (7.163)	Loss 1.5529 (1.5529)	Acc@1 65.283 (65.283)	Acc@5 88.281 (88.281)	Mem 34602MB
[2025-01-19 00:46:28 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.921)	Loss 2.2403 (1.8395)	Acc@1 52.930 (60.529)	Acc@5 78.076 (84.038)	Mem 34602MB
[2025-01-19 00:46:28 internimage_b_1k_224] (main.py 575): INFO [Epoch:13] * Acc@1 60.793 Acc@5 84.205
[2025-01-19 00:46:28 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 60.8%
[2025-01-19 00:46:28 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:46:32 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:46:32 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 60.79%
[2025-01-19 00:46:39 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.269 (7.269)	Loss 6.7326 (6.7326)	Acc@1 0.122 (0.122)	Acc@5 2.930 (2.930)	Mem 34602MB
[2025-01-19 00:46:42 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.930)	Loss 6.8307 (6.7534)	Acc@1 0.049 (0.448)	Acc@5 1.147 (2.268)	Mem 34602MB
[2025-01-19 00:46:42 internimage_b_1k_224] (main.py 575): INFO [Epoch:13] * Acc@1 0.652 Acc@5 2.783
[2025-01-19 00:46:42 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.7%
[2025-01-19 00:46:42 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.67%
[2025-01-19 00:46:45 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][0/312]	eta 0:17:01 lr 0.002801	time 3.2740 (3.2740)	model_time 0.9536 (0.9536)	loss 4.7148 (4.7148)	grad_norm 2.5246 (2.5246/0.0000)	mem 34602MB
[2025-01-19 00:46:53 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][10/312]	eta 0:04:57 lr 0.002808	time 0.8111 (0.9860)	model_time 0.8109 (0.7747)	loss 3.1634 (4.2945)	grad_norm 1.8924 (2.3658/0.9865)	mem 34602MB
[2025-01-19 00:47:01 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][20/312]	eta 0:04:18 lr 0.002814	time 0.7153 (0.8859)	model_time 0.7149 (0.7751)	loss 4.7334 (4.3128)	grad_norm 1.6339 (2.1556/0.9573)	mem 34602MB
[2025-01-19 00:47:08 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][30/312]	eta 0:03:55 lr 0.002820	time 0.7184 (0.8358)	model_time 0.7182 (0.7607)	loss 5.0066 (4.4050)	grad_norm 1.9179 (1.9637/0.8673)	mem 34602MB
[2025-01-19 00:47:15 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][40/312]	eta 0:03:40 lr 0.002827	time 0.7171 (0.8112)	model_time 0.7167 (0.7543)	loss 4.4747 (4.4211)	grad_norm 1.6335 (2.0706/0.9176)	mem 34602MB
[2025-01-19 00:47:23 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][50/312]	eta 0:03:28 lr 0.002833	time 0.7166 (0.7944)	model_time 0.7164 (0.7486)	loss 4.6138 (4.3748)	grad_norm 1.6800 (1.9564/0.8640)	mem 34602MB
[2025-01-19 00:47:30 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][60/312]	eta 0:03:17 lr 0.002840	time 0.7552 (0.7831)	model_time 0.7550 (0.7448)	loss 5.0586 (4.3607)	grad_norm 1.0694 (1.9256/0.8588)	mem 34602MB
[2025-01-19 00:47:37 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][70/312]	eta 0:03:07 lr 0.002846	time 0.7142 (0.7749)	model_time 0.7138 (0.7419)	loss 4.9848 (4.3863)	grad_norm 1.5485 (1.9534/0.8529)	mem 34602MB
[2025-01-19 00:47:44 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][80/312]	eta 0:02:58 lr 0.002852	time 0.7243 (0.7681)	model_time 0.7239 (0.7391)	loss 4.6819 (4.4016)	grad_norm 2.5627 (1.9260/0.8214)	mem 34602MB
[2025-01-19 00:47:52 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][90/312]	eta 0:02:49 lr 0.002859	time 0.7172 (0.7636)	model_time 0.7168 (0.7378)	loss 4.2921 (4.3641)	grad_norm 1.0907 (1.8842/0.7917)	mem 34602MB
[2025-01-19 00:47:59 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][100/312]	eta 0:02:41 lr 0.002865	time 0.7150 (0.7605)	model_time 0.7146 (0.7372)	loss 4.0361 (4.3922)	grad_norm 1.3093 (1.9043/0.8392)	mem 34602MB
[2025-01-19 00:48:06 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][110/312]	eta 0:02:32 lr 0.002872	time 0.7572 (0.7572)	model_time 0.7571 (0.7359)	loss 3.9703 (4.3974)	grad_norm 2.2984 (1.8831/0.8107)	mem 34602MB
[2025-01-19 00:48:13 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][120/312]	eta 0:02:24 lr 0.002878	time 0.7248 (0.7543)	model_time 0.7244 (0.7348)	loss 3.5372 (4.3910)	grad_norm 1.4615 (1.8713/0.7888)	mem 34602MB
[2025-01-19 00:48:21 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][130/312]	eta 0:02:17 lr 0.002884	time 0.8088 (0.7545)	model_time 0.8086 (0.7364)	loss 4.0462 (4.3895)	grad_norm 0.9990 (1.8353/0.7764)	mem 34602MB
[2025-01-19 00:48:29 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][140/312]	eta 0:02:10 lr 0.002891	time 0.7964 (0.7569)	model_time 0.7960 (0.7401)	loss 4.9290 (4.3974)	grad_norm 1.6710 (1.8297/0.7667)	mem 34602MB
[2025-01-19 00:48:36 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][150/312]	eta 0:02:02 lr 0.002897	time 0.7269 (0.7558)	model_time 0.7265 (0.7401)	loss 5.0533 (4.3931)	grad_norm 1.4184 (1.8790/0.8233)	mem 34602MB
[2025-01-19 00:48:43 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][160/312]	eta 0:01:54 lr 0.002904	time 0.7225 (0.7543)	model_time 0.7223 (0.7395)	loss 4.7035 (4.3949)	grad_norm 1.8923 (1.8649/0.8049)	mem 34602MB
[2025-01-19 00:48:51 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][170/312]	eta 0:01:46 lr 0.002910	time 0.7156 (0.7524)	model_time 0.7151 (0.7385)	loss 3.0734 (4.3771)	grad_norm 1.1236 (1.8838/0.8190)	mem 34602MB
[2025-01-19 00:48:58 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][180/312]	eta 0:01:39 lr 0.002916	time 0.7443 (0.7511)	model_time 0.7441 (0.7380)	loss 5.1445 (4.3824)	grad_norm 3.0350 (1.8805/0.8168)	mem 34602MB
[2025-01-19 00:49:05 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][190/312]	eta 0:01:31 lr 0.002923	time 0.7203 (0.7496)	model_time 0.7201 (0.7371)	loss 4.2441 (4.3919)	grad_norm 1.3726 (1.8687/0.8107)	mem 34602MB
[2025-01-19 00:49:12 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][200/312]	eta 0:01:23 lr 0.002929	time 0.7185 (0.7484)	model_time 0.7184 (0.7365)	loss 4.5058 (4.3910)	grad_norm 1.6086 (1.8524/0.7970)	mem 34602MB
[2025-01-19 00:49:20 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][210/312]	eta 0:01:16 lr 0.002936	time 0.7255 (0.7475)	model_time 0.7251 (0.7362)	loss 4.6298 (4.3887)	grad_norm 3.7449 (1.8660/0.7956)	mem 34602MB
[2025-01-19 00:49:27 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][220/312]	eta 0:01:08 lr 0.002942	time 0.7169 (0.7468)	model_time 0.7167 (0.7360)	loss 3.7913 (4.3981)	grad_norm 1.7505 (1.8765/0.7968)	mem 34602MB
[2025-01-19 00:49:34 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][230/312]	eta 0:01:01 lr 0.002948	time 0.7258 (0.7460)	model_time 0.7254 (0.7356)	loss 4.4177 (4.4029)	grad_norm 1.4533 (1.8516/0.7908)	mem 34602MB
[2025-01-19 00:49:42 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][240/312]	eta 0:00:53 lr 0.002955	time 0.7150 (0.7451)	model_time 0.7148 (0.7351)	loss 4.0778 (4.3915)	grad_norm 1.5878 (1.8836/0.8563)	mem 34602MB
[2025-01-19 00:49:49 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][250/312]	eta 0:00:46 lr 0.002961	time 0.7433 (0.7454)	model_time 0.7428 (0.7359)	loss 4.3128 (4.4023)	grad_norm 1.2410 (1.8628/0.8458)	mem 34602MB
[2025-01-19 00:49:57 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][260/312]	eta 0:00:38 lr 0.002968	time 0.7945 (0.7474)	model_time 0.7943 (0.7382)	loss 5.0315 (4.4002)	grad_norm 2.5781 (1.8536/0.8353)	mem 34602MB
[2025-01-19 00:50:04 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][270/312]	eta 0:00:31 lr 0.002974	time 0.7181 (0.7470)	model_time 0.7177 (0.7381)	loss 3.9459 (4.3990)	grad_norm 2.1353 (1.8657/0.8358)	mem 34602MB
[2025-01-19 00:50:12 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][280/312]	eta 0:00:23 lr 0.002981	time 0.7365 (0.7468)	model_time 0.7363 (0.7382)	loss 3.9755 (4.4011)	grad_norm 2.0806 (1.8616/0.8288)	mem 34602MB
[2025-01-19 00:50:19 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][290/312]	eta 0:00:16 lr 0.002987	time 0.7163 (0.7460)	model_time 0.7161 (0.7377)	loss 4.6648 (4.4090)	grad_norm 3.7626 (1.8633/0.8439)	mem 34602MB
[2025-01-19 00:50:26 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][300/312]	eta 0:00:08 lr 0.002993	time 0.7171 (0.7451)	model_time 0.7170 (0.7370)	loss 4.2125 (4.4106)	grad_norm 1.5521 (1.8635/0.8565)	mem 34602MB
[2025-01-19 00:50:34 internimage_b_1k_224] (main.py 510): INFO Train: [14/300][310/312]	eta 0:00:01 lr 0.003000	time 0.7142 (0.7442)	model_time 0.7140 (0.7364)	loss 5.3644 (4.4110)	grad_norm 1.8570 (1.8422/0.8343)	mem 34602MB
[2025-01-19 00:50:34 internimage_b_1k_224] (main.py 519): INFO EPOCH 14 training takes 0:03:52
[2025-01-19 00:50:34 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_14.pth saving......
[2025-01-19 00:50:37 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_14.pth saved !!!
[2025-01-19 00:50:45 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.045 (7.045)	Loss 1.4268 (1.4268)	Acc@1 68.579 (68.579)	Acc@5 89.185 (89.185)	Mem 34602MB
[2025-01-19 00:50:48 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.912)	Loss 2.2042 (1.7614)	Acc@1 53.735 (62.021)	Acc@5 77.734 (84.950)	Mem 34602MB
[2025-01-19 00:50:48 internimage_b_1k_224] (main.py 575): INFO [Epoch:14] * Acc@1 62.160 Acc@5 85.097
[2025-01-19 00:50:48 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 62.2%
[2025-01-19 00:50:48 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:50:51 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:50:51 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 62.16%
[2025-01-19 00:50:58 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.272 (7.272)	Loss 6.7008 (6.7008)	Acc@1 0.122 (0.122)	Acc@5 3.149 (3.149)	Mem 34602MB
[2025-01-19 00:51:01 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.926)	Loss 6.8397 (6.7398)	Acc@1 0.000 (0.493)	Acc@5 1.147 (2.337)	Mem 34602MB
[2025-01-19 00:51:01 internimage_b_1k_224] (main.py 575): INFO [Epoch:14] * Acc@1 0.720 Acc@5 2.879
[2025-01-19 00:51:01 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.7%
[2025-01-19 00:51:01 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:51:05 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:51:05 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.72%
[2025-01-19 00:51:08 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][0/312]	eta 0:10:48 lr 0.003001	time 2.0772 (2.0772)	model_time 0.7529 (0.7529)	loss 4.4083 (4.4083)	grad_norm 1.6645 (1.6645/0.0000)	mem 34602MB
[2025-01-19 00:51:15 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][10/312]	eta 0:04:17 lr 0.003007	time 0.7245 (0.8536)	model_time 0.7241 (0.7329)	loss 4.7362 (4.5065)	grad_norm 2.5197 (1.8837/0.5822)	mem 34602MB
[2025-01-19 00:51:22 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][20/312]	eta 0:03:52 lr 0.003014	time 0.7173 (0.7966)	model_time 0.7172 (0.7332)	loss 5.3712 (4.6122)	grad_norm 1.6581 (2.0745/1.1159)	mem 34602MB
[2025-01-19 00:51:29 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][30/312]	eta 0:03:38 lr 0.003020	time 0.7209 (0.7738)	model_time 0.7204 (0.7308)	loss 4.5347 (4.4816)	grad_norm 1.0399 (1.8792/0.9903)	mem 34602MB
[2025-01-19 00:51:37 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][40/312]	eta 0:03:27 lr 0.003027	time 0.7239 (0.7636)	model_time 0.7235 (0.7310)	loss 4.4892 (4.4603)	grad_norm 1.5372 (1.7238/0.9089)	mem 34602MB
[2025-01-19 00:51:44 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][50/312]	eta 0:03:18 lr 0.003033	time 0.7192 (0.7559)	model_time 0.7190 (0.7296)	loss 3.6456 (4.4155)	grad_norm 1.7704 (1.7487/0.8679)	mem 34602MB
[2025-01-19 00:51:52 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][60/312]	eta 0:03:11 lr 0.003039	time 0.9864 (0.7608)	model_time 0.9863 (0.7388)	loss 4.4440 (4.4345)	grad_norm 1.6454 (1.7138/0.8102)	mem 34602MB
[2025-01-19 00:52:00 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][70/312]	eta 0:03:04 lr 0.003046	time 0.7157 (0.7638)	model_time 0.7155 (0.7449)	loss 4.0874 (4.4141)	grad_norm 3.2040 (1.7288/0.8119)	mem 34602MB
[2025-01-19 00:52:07 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][80/312]	eta 0:02:57 lr 0.003052	time 0.7997 (0.7634)	model_time 0.7996 (0.7467)	loss 3.8656 (4.3804)	grad_norm 4.0040 (1.7836/0.8301)	mem 34602MB
[2025-01-19 00:52:15 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][90/312]	eta 0:02:48 lr 0.003059	time 0.7196 (0.7593)	model_time 0.7194 (0.7444)	loss 4.7516 (4.3700)	grad_norm 1.9358 (1.7704/0.8036)	mem 34602MB
[2025-01-19 00:52:22 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][100/312]	eta 0:02:40 lr 0.003065	time 0.7190 (0.7555)	model_time 0.7189 (0.7421)	loss 4.5362 (4.3640)	grad_norm 2.2070 (1.7517/0.7769)	mem 34602MB
[2025-01-19 00:52:29 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][110/312]	eta 0:02:32 lr 0.003071	time 0.7154 (0.7528)	model_time 0.7152 (0.7405)	loss 4.8156 (4.3655)	grad_norm 1.2145 (1.7294/0.7594)	mem 34602MB
[2025-01-19 00:52:36 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][120/312]	eta 0:02:24 lr 0.003078	time 0.7220 (0.7507)	model_time 0.7215 (0.7394)	loss 4.8839 (4.3655)	grad_norm 3.1840 (1.7177/0.7474)	mem 34602MB
[2025-01-19 00:52:44 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][130/312]	eta 0:02:16 lr 0.003084	time 0.7272 (0.7488)	model_time 0.7271 (0.7384)	loss 4.0523 (4.3630)	grad_norm 2.9703 (1.7678/0.7759)	mem 34602MB
[2025-01-19 00:52:51 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][140/312]	eta 0:02:08 lr 0.003091	time 0.7423 (0.7472)	model_time 0.7421 (0.7374)	loss 3.3545 (4.3610)	grad_norm 1.1350 (1.7802/0.7654)	mem 34602MB
[2025-01-19 00:52:58 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][150/312]	eta 0:02:00 lr 0.003097	time 0.7253 (0.7460)	model_time 0.7249 (0.7369)	loss 4.4666 (4.3483)	grad_norm 0.8804 (1.7463/0.7591)	mem 34602MB
[2025-01-19 00:53:05 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][160/312]	eta 0:01:53 lr 0.003103	time 0.7350 (0.7454)	model_time 0.7345 (0.7369)	loss 4.2688 (4.3558)	grad_norm 2.0525 (1.7451/0.7531)	mem 34602MB
[2025-01-19 00:53:13 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][170/312]	eta 0:01:45 lr 0.003110	time 0.7234 (0.7444)	model_time 0.7229 (0.7363)	loss 4.5209 (4.3479)	grad_norm 2.5246 (1.7351/0.7393)	mem 34602MB
[2025-01-19 00:53:20 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][180/312]	eta 0:01:38 lr 0.003116	time 0.8174 (0.7451)	model_time 0.8172 (0.7375)	loss 4.1334 (4.3326)	grad_norm 1.7958 (1.7559/0.7456)	mem 34602MB
[2025-01-19 00:53:28 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][190/312]	eta 0:01:31 lr 0.003123	time 0.7153 (0.7469)	model_time 0.7149 (0.7396)	loss 3.3378 (4.3137)	grad_norm 1.6903 (1.7521/0.7342)	mem 34602MB
[2025-01-19 00:53:36 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][200/312]	eta 0:01:23 lr 0.003129	time 0.8041 (0.7480)	model_time 0.8037 (0.7411)	loss 5.2733 (4.3126)	grad_norm 1.4430 (1.7399/0.7213)	mem 34602MB
[2025-01-19 00:53:43 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][210/312]	eta 0:01:16 lr 0.003135	time 0.7159 (0.7472)	model_time 0.7157 (0.7405)	loss 4.6729 (4.3075)	grad_norm 2.1619 (1.7478/0.7086)	mem 34602MB
[2025-01-19 00:53:50 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][220/312]	eta 0:01:08 lr 0.003142	time 0.7335 (0.7463)	model_time 0.7334 (0.7399)	loss 3.4815 (4.2941)	grad_norm 1.7527 (1.7361/0.6967)	mem 34602MB
[2025-01-19 00:53:58 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][230/312]	eta 0:01:01 lr 0.003148	time 0.7257 (0.7452)	model_time 0.7253 (0.7391)	loss 3.3933 (4.2953)	grad_norm 2.6722 (1.7521/0.7194)	mem 34602MB
[2025-01-19 00:54:05 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][240/312]	eta 0:00:53 lr 0.003155	time 0.7242 (0.7443)	model_time 0.7241 (0.7385)	loss 4.1273 (4.3008)	grad_norm 1.8463 (1.7728/0.7332)	mem 34602MB
[2025-01-19 00:54:12 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][250/312]	eta 0:00:46 lr 0.003161	time 0.7206 (0.7435)	model_time 0.7201 (0.7378)	loss 4.6182 (4.2975)	grad_norm 1.4273 (1.7617/0.7220)	mem 34602MB
[2025-01-19 00:54:19 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][260/312]	eta 0:00:38 lr 0.003168	time 0.7693 (0.7431)	model_time 0.7692 (0.7376)	loss 5.3527 (4.3142)	grad_norm 2.3079 (1.7641/0.7185)	mem 34602MB
[2025-01-19 00:54:27 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][270/312]	eta 0:00:31 lr 0.003174	time 0.7189 (0.7422)	model_time 0.7185 (0.7370)	loss 4.1837 (4.3175)	grad_norm 1.1913 (1.7630/0.7111)	mem 34602MB
[2025-01-19 00:54:34 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][280/312]	eta 0:00:23 lr 0.003180	time 0.8176 (0.7418)	model_time 0.8172 (0.7368)	loss 3.4942 (4.3204)	grad_norm 1.7987 (1.7663/0.7110)	mem 34602MB
[2025-01-19 00:54:41 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][290/312]	eta 0:00:16 lr 0.003187	time 0.7200 (0.7414)	model_time 0.7198 (0.7365)	loss 5.0989 (4.3136)	grad_norm 1.2128 (1.7551/0.7044)	mem 34602MB
[2025-01-19 00:54:49 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][300/312]	eta 0:00:08 lr 0.003193	time 0.8125 (0.7420)	model_time 0.8124 (0.7372)	loss 4.7006 (4.3225)	grad_norm 3.0007 (1.7585/0.7085)	mem 34602MB
[2025-01-19 00:54:56 internimage_b_1k_224] (main.py 510): INFO Train: [15/300][310/312]	eta 0:00:01 lr 0.003200	time 0.7143 (0.7429)	model_time 0.7142 (0.7383)	loss 4.2926 (4.3238)	grad_norm 1.3521 (1.7446/0.7038)	mem 34602MB
[2025-01-19 00:54:57 internimage_b_1k_224] (main.py 519): INFO EPOCH 15 training takes 0:03:51
[2025-01-19 00:54:57 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_15.pth saving......
[2025-01-19 00:55:00 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_15.pth saved !!!
[2025-01-19 00:55:08 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.376 (7.376)	Loss 1.4526 (1.4526)	Acc@1 68.481 (68.481)	Acc@5 88.330 (88.330)	Mem 34602MB
[2025-01-19 00:55:11 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.929)	Loss 2.0997 (1.7177)	Acc@1 55.688 (62.356)	Acc@5 78.882 (85.165)	Mem 34602MB
[2025-01-19 00:55:11 internimage_b_1k_224] (main.py 575): INFO [Epoch:15] * Acc@1 62.532 Acc@5 85.289
[2025-01-19 00:55:11 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 62.5%
[2025-01-19 00:55:11 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:55:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:55:14 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 62.53%
[2025-01-19 00:55:21 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.195 (7.195)	Loss 6.6719 (6.6719)	Acc@1 0.146 (0.146)	Acc@5 3.198 (3.198)	Mem 34602MB
[2025-01-19 00:55:24 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.926)	Loss 6.8523 (6.7283)	Acc@1 0.049 (0.526)	Acc@5 0.952 (2.339)	Mem 34602MB
[2025-01-19 00:55:24 internimage_b_1k_224] (main.py 575): INFO [Epoch:15] * Acc@1 0.768 Acc@5 2.881
[2025-01-19 00:55:24 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.8%
[2025-01-19 00:55:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:55:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:55:28 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.77%
[2025-01-19 00:55:31 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][0/312]	eta 0:11:16 lr 0.003201	time 2.1684 (2.1684)	model_time 0.7455 (0.7455)	loss 4.0101 (4.0101)	grad_norm 3.5184 (3.5184/0.0000)	mem 34602MB
[2025-01-19 00:55:38 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][10/312]	eta 0:04:29 lr 0.003207	time 0.8072 (0.8930)	model_time 0.8071 (0.7635)	loss 3.4745 (4.4235)	grad_norm 1.3129 (1.9129/0.6653)	mem 34602MB
[2025-01-19 00:55:46 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][20/312]	eta 0:03:58 lr 0.003214	time 0.7155 (0.8154)	model_time 0.7153 (0.7473)	loss 4.8659 (4.3843)	grad_norm 1.1642 (1.7420/0.5686)	mem 34602MB
[2025-01-19 00:55:53 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][30/312]	eta 0:03:42 lr 0.003220	time 0.7271 (0.7893)	model_time 0.7270 (0.7431)	loss 3.9550 (4.3189)	grad_norm 1.0828 (1.7176/0.5283)	mem 34602MB
[2025-01-19 00:56:00 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][40/312]	eta 0:03:30 lr 0.003226	time 0.7439 (0.7751)	model_time 0.7434 (0.7401)	loss 3.5132 (4.2761)	grad_norm 1.0847 (1.7728/0.5941)	mem 34602MB
[2025-01-19 00:56:08 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][50/312]	eta 0:03:20 lr 0.003233	time 0.7209 (0.7664)	model_time 0.7207 (0.7382)	loss 3.7948 (4.2802)	grad_norm 1.0953 (1.7606/0.5889)	mem 34602MB
[2025-01-19 00:56:15 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][60/312]	eta 0:03:11 lr 0.003239	time 0.7455 (0.7600)	model_time 0.7453 (0.7364)	loss 3.9755 (4.2584)	grad_norm 1.5557 (1.7467/0.5574)	mem 34602MB
[2025-01-19 00:56:22 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][70/312]	eta 0:03:02 lr 0.003246	time 0.7267 (0.7552)	model_time 0.7265 (0.7349)	loss 3.8653 (4.2987)	grad_norm 1.3971 (1.7528/0.5780)	mem 34602MB
[2025-01-19 00:56:29 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][80/312]	eta 0:02:54 lr 0.003252	time 0.7160 (0.7523)	model_time 0.7155 (0.7344)	loss 3.3926 (4.2730)	grad_norm 2.9226 (1.8053/0.6419)	mem 34602MB
[2025-01-19 00:56:37 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][90/312]	eta 0:02:46 lr 0.003258	time 0.7163 (0.7493)	model_time 0.7159 (0.7333)	loss 5.0594 (4.2805)	grad_norm 0.9671 (1.7914/0.6327)	mem 34602MB
[2025-01-19 00:56:44 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][100/312]	eta 0:02:38 lr 0.003265	time 0.7142 (0.7471)	model_time 0.7141 (0.7327)	loss 3.4893 (4.2555)	grad_norm 1.1572 (1.7653/0.6184)	mem 34602MB
[2025-01-19 00:56:52 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][110/312]	eta 0:02:31 lr 0.003271	time 0.7219 (0.7498)	model_time 0.7217 (0.7367)	loss 4.7319 (4.2550)	grad_norm 2.6015 (1.7936/0.6358)	mem 34602MB
[2025-01-19 00:57:00 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][120/312]	eta 0:02:24 lr 0.003278	time 0.8211 (0.7533)	model_time 0.8209 (0.7412)	loss 4.7664 (4.2626)	grad_norm 1.5014 (1.7726/0.6286)	mem 34602MB
[2025-01-19 00:57:07 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][130/312]	eta 0:02:17 lr 0.003284	time 0.7145 (0.7535)	model_time 0.7144 (0.7424)	loss 3.9641 (4.2539)	grad_norm 1.3711 (1.7433/0.6200)	mem 34602MB
[2025-01-19 00:57:14 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][140/312]	eta 0:02:09 lr 0.003290	time 0.7358 (0.7519)	model_time 0.7356 (0.7415)	loss 4.4401 (4.2750)	grad_norm 1.0932 (1.7326/0.6289)	mem 34602MB
[2025-01-19 00:57:22 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][150/312]	eta 0:02:01 lr 0.003297	time 0.7549 (0.7504)	model_time 0.7544 (0.7407)	loss 4.4958 (4.2896)	grad_norm 0.9280 (1.7391/0.6368)	mem 34602MB
[2025-01-19 00:57:29 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][160/312]	eta 0:01:53 lr 0.003303	time 0.7580 (0.7491)	model_time 0.7578 (0.7400)	loss 3.8222 (4.2888)	grad_norm 1.0924 (1.7374/0.6291)	mem 34602MB
[2025-01-19 00:57:36 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][170/312]	eta 0:01:46 lr 0.003310	time 0.7400 (0.7481)	model_time 0.7395 (0.7395)	loss 5.2463 (4.3033)	grad_norm 1.5700 (1.7475/0.6416)	mem 34602MB
[2025-01-19 00:57:44 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][180/312]	eta 0:01:38 lr 0.003316	time 0.7161 (0.7469)	model_time 0.7159 (0.7388)	loss 4.7194 (4.2971)	grad_norm 1.3803 (1.7720/0.6574)	mem 34602MB
[2025-01-19 00:57:51 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][190/312]	eta 0:01:30 lr 0.003322	time 0.7192 (0.7457)	model_time 0.7191 (0.7379)	loss 4.5539 (4.3086)	grad_norm 1.7444 (1.7538/0.6538)	mem 34602MB
[2025-01-19 00:57:58 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][200/312]	eta 0:01:23 lr 0.003329	time 0.7143 (0.7447)	model_time 0.7141 (0.7373)	loss 3.9937 (4.2966)	grad_norm 1.2979 (1.7445/0.6500)	mem 34602MB
[2025-01-19 00:58:05 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][210/312]	eta 0:01:15 lr 0.003335	time 0.7314 (0.7443)	model_time 0.7310 (0.7372)	loss 5.1398 (4.3067)	grad_norm 1.2357 (1.7336/0.6431)	mem 34602MB
[2025-01-19 00:58:13 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][220/312]	eta 0:01:08 lr 0.003342	time 0.7178 (0.7434)	model_time 0.7174 (0.7367)	loss 3.7646 (4.3077)	grad_norm 1.3929 (1.7196/0.6373)	mem 34602MB
[2025-01-19 00:58:21 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][230/312]	eta 0:01:01 lr 0.003348	time 0.8082 (0.7454)	model_time 0.8078 (0.7389)	loss 4.3092 (4.3180)	grad_norm 1.7303 (1.7581/0.7133)	mem 34602MB
[2025-01-19 00:58:28 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][240/312]	eta 0:00:53 lr 0.003354	time 0.8415 (0.7471)	model_time 0.8411 (0.7409)	loss 4.3637 (4.3125)	grad_norm 1.2497 (1.7379/0.7083)	mem 34602MB
[2025-01-19 00:58:36 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][250/312]	eta 0:00:46 lr 0.003361	time 0.7166 (0.7476)	model_time 0.7162 (0.7416)	loss 3.9983 (4.3211)	grad_norm 1.7504 (1.7233/0.7003)	mem 34602MB
[2025-01-19 00:58:43 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][260/312]	eta 0:00:38 lr 0.003367	time 0.7228 (0.7470)	model_time 0.7226 (0.7412)	loss 3.8623 (4.3213)	grad_norm 1.4218 (1.7461/0.7406)	mem 34602MB
[2025-01-19 00:58:51 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][270/312]	eta 0:00:31 lr 0.003374	time 0.7137 (0.7464)	model_time 0.7135 (0.7408)	loss 3.7137 (4.3244)	grad_norm 1.9534 (1.7504/0.7323)	mem 34602MB
[2025-01-19 00:58:58 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][280/312]	eta 0:00:23 lr 0.003380	time 0.7740 (0.7459)	model_time 0.7738 (0.7405)	loss 4.3749 (4.3230)	grad_norm 2.5053 (1.7637/0.7501)	mem 34602MB
[2025-01-19 00:59:05 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][290/312]	eta 0:00:16 lr 0.003387	time 0.7656 (0.7453)	model_time 0.7654 (0.7400)	loss 4.2030 (4.3214)	grad_norm 0.8540 (1.7443/0.7490)	mem 34602MB
[2025-01-19 00:59:13 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][300/312]	eta 0:00:08 lr 0.003393	time 0.7117 (0.7445)	model_time 0.7116 (0.7394)	loss 4.9194 (4.3285)	grad_norm 2.5804 (1.7555/0.7570)	mem 34602MB
[2025-01-19 00:59:20 internimage_b_1k_224] (main.py 510): INFO Train: [16/300][310/312]	eta 0:00:01 lr 0.003399	time 0.7123 (0.7437)	model_time 0.7122 (0.7388)	loss 4.6381 (4.3357)	grad_norm 1.0196 (1.7539/0.7588)	mem 34602MB
[2025-01-19 00:59:20 internimage_b_1k_224] (main.py 519): INFO EPOCH 16 training takes 0:03:51
[2025-01-19 00:59:20 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_16.pth saving......
[2025-01-19 00:59:24 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_16.pth saved !!!
[2025-01-19 00:59:31 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.234 (7.234)	Loss 1.4031 (1.4031)	Acc@1 69.922 (69.922)	Acc@5 90.161 (90.161)	Mem 34602MB
[2025-01-19 00:59:34 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.922)	Loss 2.0762 (1.7005)	Acc@1 54.834 (63.170)	Acc@5 79.590 (85.809)	Mem 34602MB
[2025-01-19 00:59:34 internimage_b_1k_224] (main.py 575): INFO [Epoch:16] * Acc@1 63.356 Acc@5 86.038
[2025-01-19 00:59:34 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 63.4%
[2025-01-19 00:59:34 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:59:37 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:59:37 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 63.36%
[2025-01-19 00:59:45 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.542 (7.542)	Loss 6.6463 (6.6463)	Acc@1 0.195 (0.195)	Acc@5 3.442 (3.442)	Mem 34602MB
[2025-01-19 00:59:48 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.964)	Loss 6.8709 (6.7194)	Acc@1 0.073 (0.542)	Acc@5 0.903 (2.344)	Mem 34602MB
[2025-01-19 00:59:48 internimage_b_1k_224] (main.py 575): INFO [Epoch:16] * Acc@1 0.816 Acc@5 2.915
[2025-01-19 00:59:48 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.8%
[2025-01-19 00:59:48 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:59:52 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:59:52 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.82%
[2025-01-19 00:59:54 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][0/312]	eta 0:11:57 lr 0.003401	time 2.2998 (2.2998)	model_time 0.7535 (0.7535)	loss 3.9893 (3.9893)	grad_norm 1.7119 (1.7119/0.0000)	mem 34602MB
[2025-01-19 01:00:02 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][10/312]	eta 0:04:24 lr 0.003407	time 0.7400 (0.8769)	model_time 0.7399 (0.7360)	loss 4.3726 (4.0650)	grad_norm 2.3748 (1.6025/0.4614)	mem 34602MB
[2025-01-19 01:00:09 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][20/312]	eta 0:03:55 lr 0.003413	time 0.7825 (0.8070)	model_time 0.7823 (0.7330)	loss 4.8783 (4.1287)	grad_norm 0.7119 (1.5797/0.4632)	mem 34602MB
[2025-01-19 01:00:16 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][30/312]	eta 0:03:40 lr 0.003420	time 0.7179 (0.7809)	model_time 0.7177 (0.7307)	loss 3.5519 (4.1014)	grad_norm 1.6432 (1.5412/0.4792)	mem 34602MB
[2025-01-19 01:00:24 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][40/312]	eta 0:03:32 lr 0.003426	time 0.8245 (0.7795)	model_time 0.8241 (0.7414)	loss 4.3389 (4.1839)	grad_norm 2.3226 (1.5276/0.4629)	mem 34602MB
[2025-01-19 01:00:32 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][50/312]	eta 0:03:24 lr 0.003433	time 0.7615 (0.7819)	model_time 0.7613 (0.7513)	loss 4.6916 (4.2211)	grad_norm 1.1959 (1.5454/0.4670)	mem 34602MB
[2025-01-19 01:00:40 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][60/312]	eta 0:03:16 lr 0.003439	time 0.8032 (0.7778)	model_time 0.8028 (0.7521)	loss 4.0891 (4.2196)	grad_norm 0.8330 (1.5808/0.5503)	mem 34602MB
[2025-01-19 01:00:47 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][70/312]	eta 0:03:06 lr 0.003445	time 0.7149 (0.7720)	model_time 0.7147 (0.7499)	loss 4.3326 (4.2099)	grad_norm 2.5491 (1.5585/0.5429)	mem 34602MB
[2025-01-19 01:00:54 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][80/312]	eta 0:02:57 lr 0.003452	time 0.7199 (0.7665)	model_time 0.7197 (0.7471)	loss 4.5987 (4.1996)	grad_norm 1.8302 (1.5730/0.5608)	mem 34602MB
[2025-01-19 01:01:01 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][90/312]	eta 0:02:49 lr 0.003458	time 0.7286 (0.7616)	model_time 0.7285 (0.7443)	loss 4.4352 (4.2004)	grad_norm 1.0920 (1.5655/0.5412)	mem 34602MB
[2025-01-19 01:01:09 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][100/312]	eta 0:02:40 lr 0.003465	time 0.6713 (0.7575)	model_time 0.6711 (0.7419)	loss 4.8195 (4.2229)	grad_norm inf (1.5795/0.5420)	mem 34602MB
[2025-01-19 01:01:16 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][110/312]	eta 0:02:32 lr 0.003471	time 0.7404 (0.7547)	model_time 0.7402 (0.7404)	loss 4.4213 (4.2381)	grad_norm 1.5769 (1.6163/0.6387)	mem 34602MB
[2025-01-19 01:01:23 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][120/312]	eta 0:02:24 lr 0.003477	time 0.7149 (0.7526)	model_time 0.7145 (0.7395)	loss 4.1016 (4.2197)	grad_norm 2.4487 (1.6014/0.6306)	mem 34602MB
[2025-01-19 01:01:31 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][130/312]	eta 0:02:16 lr 0.003484	time 0.7191 (0.7512)	model_time 0.7189 (0.7391)	loss 4.5580 (4.2232)	grad_norm 0.9985 (1.6254/0.6942)	mem 34602MB
[2025-01-19 01:01:38 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][140/312]	eta 0:02:08 lr 0.003490	time 0.7202 (0.7493)	model_time 0.7201 (0.7381)	loss 4.6639 (4.2240)	grad_norm 1.9355 (1.6219/0.6806)	mem 34602MB
[2025-01-19 01:01:45 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][150/312]	eta 0:02:01 lr 0.003497	time 0.7154 (0.7474)	model_time 0.7152 (0.7369)	loss 4.0530 (4.2319)	grad_norm 1.5034 (1.6140/0.6649)	mem 34602MB
[2025-01-19 01:01:53 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][160/312]	eta 0:01:53 lr 0.003503	time 0.8324 (0.7490)	model_time 0.8320 (0.7391)	loss 4.6726 (4.2465)	grad_norm 1.7505 (1.6173/0.6631)	mem 34602MB
[2025-01-19 01:02:01 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][170/312]	eta 0:01:46 lr 0.003509	time 0.8284 (0.7512)	model_time 0.8283 (0.7418)	loss 4.4663 (4.2500)	grad_norm 1.4675 (1.6055/0.6517)	mem 34602MB
[2025-01-19 01:02:08 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][180/312]	eta 0:01:39 lr 0.003516	time 0.8022 (0.7518)	model_time 0.8021 (0.7429)	loss 3.4295 (4.2341)	grad_norm 2.7704 (1.6510/0.6978)	mem 34602MB
[2025-01-19 01:02:16 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][190/312]	eta 0:01:31 lr 0.003522	time 0.7195 (0.7507)	model_time 0.7193 (0.7423)	loss 4.7335 (4.2477)	grad_norm 0.8454 (1.6537/0.6949)	mem 34602MB
[2025-01-19 01:02:23 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][200/312]	eta 0:01:23 lr 0.003529	time 0.7273 (0.7493)	model_time 0.7272 (0.7413)	loss 5.1854 (4.2475)	grad_norm 1.3836 (1.6451/0.6842)	mem 34602MB
[2025-01-19 01:02:30 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][210/312]	eta 0:01:16 lr 0.003535	time 0.7137 (0.7481)	model_time 0.7136 (0.7404)	loss 3.9625 (4.2408)	grad_norm 1.0880 (1.6271/0.6752)	mem 34602MB
[2025-01-19 01:02:37 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][220/312]	eta 0:01:08 lr 0.003541	time 0.7440 (0.7470)	model_time 0.7436 (0.7397)	loss 5.1777 (4.2530)	grad_norm 2.0844 (1.6257/0.6631)	mem 34602MB
[2025-01-19 01:02:44 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][230/312]	eta 0:01:01 lr 0.003548	time 0.7466 (0.7461)	model_time 0.7462 (0.7391)	loss 3.2470 (4.2337)	grad_norm 1.9010 (1.6277/0.6567)	mem 34602MB
[2025-01-19 01:02:52 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][240/312]	eta 0:00:53 lr 0.003554	time 0.7191 (0.7451)	model_time 0.7187 (0.7384)	loss 3.0629 (4.2307)	grad_norm 1.5880 (1.6182/0.6474)	mem 34602MB
[2025-01-19 01:02:59 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][250/312]	eta 0:00:46 lr 0.003561	time 0.7170 (0.7447)	model_time 0.7168 (0.7382)	loss 4.3546 (4.2233)	grad_norm 1.2120 (1.6155/0.6386)	mem 34602MB
[2025-01-19 01:03:06 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][260/312]	eta 0:00:38 lr 0.003567	time 0.7146 (0.7440)	model_time 0.7144 (0.7378)	loss 3.4443 (4.2263)	grad_norm 3.0876 (1.6319/0.6520)	mem 34602MB
[2025-01-19 01:03:14 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][270/312]	eta 0:00:31 lr 0.003574	time 0.7543 (0.7436)	model_time 0.7542 (0.7376)	loss 3.5648 (4.2209)	grad_norm 2.2504 (1.6324/0.6450)	mem 34602MB
[2025-01-19 01:03:21 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][280/312]	eta 0:00:23 lr 0.003580	time 0.7175 (0.7443)	model_time 0.7174 (0.7385)	loss 4.4892 (4.2221)	grad_norm 1.3501 (1.6211/0.6388)	mem 34602MB
[2025-01-19 01:03:29 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][290/312]	eta 0:00:16 lr 0.003586	time 0.7972 (0.7461)	model_time 0.7971 (0.7405)	loss 5.1560 (4.2320)	grad_norm 1.3553 (1.6238/0.6374)	mem 34602MB
[2025-01-19 01:03:37 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][300/312]	eta 0:00:08 lr 0.003593	time 0.7918 (0.7466)	model_time 0.7917 (0.7412)	loss 3.5645 (4.2285)	grad_norm 1.8789 (1.6164/0.6296)	mem 34602MB
[2025-01-19 01:03:44 internimage_b_1k_224] (main.py 510): INFO Train: [17/300][310/312]	eta 0:00:01 lr 0.003599	time 0.7139 (0.7458)	model_time 0.7138 (0.7405)	loss 4.8183 (4.2309)	grad_norm 1.6669 (1.6284/0.6506)	mem 34602MB
[2025-01-19 01:03:45 internimage_b_1k_224] (main.py 519): INFO EPOCH 17 training takes 0:03:52
[2025-01-19 01:03:45 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_17.pth saving......
[2025-01-19 01:03:48 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_17.pth saved !!!
[2025-01-19 01:03:55 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.324 (7.324)	Loss 1.3652 (1.3652)	Acc@1 70.117 (70.117)	Acc@5 90.649 (90.649)	Mem 34602MB
[2025-01-19 01:03:59 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.984)	Loss 1.9789 (1.6396)	Acc@1 57.861 (64.278)	Acc@5 81.152 (86.819)	Mem 34602MB
[2025-01-19 01:03:59 internimage_b_1k_224] (main.py 575): INFO [Epoch:17] * Acc@1 64.503 Acc@5 87.044
[2025-01-19 01:03:59 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 64.5%
[2025-01-19 01:03:59 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 01:04:03 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 01:04:03 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 64.50%
[2025-01-19 01:04:12 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.551 (9.551)	Loss 6.6193 (6.6193)	Acc@1 0.244 (0.244)	Acc@5 3.564 (3.564)	Mem 34602MB
[2025-01-19 01:04:18 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.386)	Loss 6.8946 (6.7128)	Acc@1 0.073 (0.562)	Acc@5 0.781 (2.248)	Mem 34602MB
[2025-01-19 01:04:18 internimage_b_1k_224] (main.py 575): INFO [Epoch:17] * Acc@1 0.838 Acc@5 2.861
[2025-01-19 01:04:18 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.8%
[2025-01-19 01:04:18 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:04:22 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:04:22 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.84%
[2025-01-19 01:04:24 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][0/312]	eta 0:10:49 lr 0.003600	time 2.0822 (2.0822)	model_time 0.7552 (0.7552)	loss 3.5365 (3.5365)	grad_norm 1.8293 (1.8293/0.0000)	mem 34602MB
[2025-01-19 01:04:32 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][10/312]	eta 0:04:17 lr 0.003607	time 0.7293 (0.8519)	model_time 0.7291 (0.7309)	loss 5.2721 (4.2996)	grad_norm 1.0696 (1.4155/0.4703)	mem 34602MB
[2025-01-19 01:04:39 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][20/312]	eta 0:03:51 lr 0.003613	time 0.7432 (0.7912)	model_time 0.7428 (0.7277)	loss 3.5006 (4.4219)	grad_norm 2.2676 (1.4776/0.5181)	mem 34602MB
[2025-01-19 01:04:46 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][30/312]	eta 0:03:37 lr 0.003620	time 0.7194 (0.7711)	model_time 0.7192 (0.7279)	loss 3.5423 (4.3298)	grad_norm 3.3617 (1.7841/0.9097)	mem 34602MB
[2025-01-19 01:04:53 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][40/312]	eta 0:03:27 lr 0.003626	time 0.7208 (0.7625)	model_time 0.7206 (0.7298)	loss 3.5956 (4.2746)	grad_norm 0.9977 (1.7632/0.8912)	mem 34602MB
[2025-01-19 01:05:01 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][50/312]	eta 0:03:17 lr 0.003632	time 0.7148 (0.7552)	model_time 0.7144 (0.7288)	loss 3.9078 (4.2829)	grad_norm 1.7974 (1.6894/0.8296)	mem 34602MB
[2025-01-19 01:05:08 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][60/312]	eta 0:03:08 lr 0.003639	time 0.7152 (0.7499)	model_time 0.7148 (0.7278)	loss 4.5588 (4.2614)	grad_norm 2.1747 (1.6412/0.8050)	mem 34602MB
[2025-01-19 01:05:15 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][70/312]	eta 0:03:01 lr 0.003645	time 0.7567 (0.7480)	model_time 0.7565 (0.7290)	loss 4.5148 (4.2679)	grad_norm 1.9407 (1.6347/0.7674)	mem 34602MB
[2025-01-19 01:05:23 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][80/312]	eta 0:02:52 lr 0.003652	time 0.7421 (0.7452)	model_time 0.7417 (0.7284)	loss 4.5478 (4.2721)	grad_norm 1.4059 (1.6310/0.7345)	mem 34602MB
[2025-01-19 01:05:30 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][90/312]	eta 0:02:45 lr 0.003658	time 0.8125 (0.7467)	model_time 0.8120 (0.7317)	loss 3.4778 (4.2710)	grad_norm 1.6260 (1.6129/0.6983)	mem 34602MB
[2025-01-19 01:05:38 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][100/312]	eta 0:02:39 lr 0.003664	time 0.7160 (0.7503)	model_time 0.7158 (0.7368)	loss 3.5519 (4.2498)	grad_norm 3.8549 (1.6399/0.7247)	mem 34602MB
[2025-01-19 01:05:46 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][110/312]	eta 0:02:31 lr 0.003671	time 0.7370 (0.7518)	model_time 0.7369 (0.7395)	loss 4.5145 (4.2415)	grad_norm 1.1674 (1.6548/0.7169)	mem 34602MB
[2025-01-19 01:05:53 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][120/312]	eta 0:02:24 lr 0.003677	time 0.7206 (0.7511)	model_time 0.7202 (0.7398)	loss 3.7236 (4.2220)	grad_norm 1.1588 (1.6355/0.6984)	mem 34602MB
[2025-01-19 01:06:00 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][130/312]	eta 0:02:16 lr 0.003684	time 0.7306 (0.7491)	model_time 0.7302 (0.7386)	loss 4.3138 (4.2250)	grad_norm 0.8257 (1.6286/0.6840)	mem 34602MB
[2025-01-19 01:06:08 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][140/312]	eta 0:02:08 lr 0.003690	time 0.7351 (0.7475)	model_time 0.7349 (0.7377)	loss 4.5568 (4.2372)	grad_norm 0.9134 (1.6340/0.6938)	mem 34602MB
[2025-01-19 01:06:15 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][150/312]	eta 0:02:00 lr 0.003696	time 0.7164 (0.7457)	model_time 0.7160 (0.7366)	loss 4.0705 (4.2487)	grad_norm 1.6304 (1.6852/0.7844)	mem 34602MB
[2025-01-19 01:06:22 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][160/312]	eta 0:01:53 lr 0.003703	time 0.7190 (0.7444)	model_time 0.7186 (0.7358)	loss 4.2454 (4.2451)	grad_norm 1.4572 (1.6648/0.7663)	mem 34602MB
[2025-01-19 01:06:29 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][170/312]	eta 0:01:45 lr 0.003709	time 0.7476 (0.7434)	model_time 0.7472 (0.7352)	loss 2.8958 (4.2353)	grad_norm 1.7249 (1.6512/0.7503)	mem 34602MB
[2025-01-19 01:06:37 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][180/312]	eta 0:01:38 lr 0.003716	time 0.7157 (0.7425)	model_time 0.7152 (0.7348)	loss 4.0038 (4.2263)	grad_norm 0.8655 (1.6602/0.7707)	mem 34602MB
[2025-01-19 01:06:44 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][190/312]	eta 0:01:30 lr 0.003722	time 0.7319 (0.7423)	model_time 0.7317 (0.7350)	loss 4.9646 (4.2369)	grad_norm 1.9491 (1.6528/0.7621)	mem 34602MB
[2025-01-19 01:06:51 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][200/312]	eta 0:01:23 lr 0.003728	time 0.7179 (0.7415)	model_time 0.7177 (0.7346)	loss 4.1350 (4.2266)	grad_norm 2.1017 (1.6333/0.7514)	mem 34602MB
[2025-01-19 01:06:59 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][210/312]	eta 0:01:15 lr 0.003735	time 0.8137 (0.7424)	model_time 0.8136 (0.7357)	loss 4.6873 (4.2450)	grad_norm 1.5650 (1.6255/0.7366)	mem 34602MB
[2025-01-19 01:07:07 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][220/312]	eta 0:01:08 lr 0.003741	time 0.7201 (0.7437)	model_time 0.7197 (0.7373)	loss 4.3820 (4.2527)	grad_norm 1.3709 (1.6232/0.7278)	mem 34602MB
[2025-01-19 01:07:14 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][230/312]	eta 0:01:01 lr 0.003748	time 0.8081 (0.7450)	model_time 0.8077 (0.7388)	loss 4.3693 (4.2477)	grad_norm 1.0394 (1.6253/0.7231)	mem 34602MB
[2025-01-19 01:07:22 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][240/312]	eta 0:00:53 lr 0.003754	time 0.7277 (0.7448)	model_time 0.7272 (0.7389)	loss 4.3348 (4.2423)	grad_norm 1.7052 (1.6433/0.7250)	mem 34602MB
[2025-01-19 01:07:29 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][250/312]	eta 0:00:46 lr 0.003760	time 0.7197 (0.7441)	model_time 0.7193 (0.7384)	loss 4.8669 (4.2585)	grad_norm 1.9847 (1.6290/0.7177)	mem 34602MB
[2025-01-19 01:07:36 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][260/312]	eta 0:00:38 lr 0.003767	time 0.7421 (0.7434)	model_time 0.7420 (0.7379)	loss 4.6540 (4.2771)	grad_norm 1.6652 (1.6233/0.7079)	mem 34602MB
[2025-01-19 01:07:43 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][270/312]	eta 0:00:31 lr 0.003773	time 0.7212 (0.7428)	model_time 0.7210 (0.7375)	loss 4.8665 (4.2772)	grad_norm 1.6372 (1.6078/0.7010)	mem 34602MB
[2025-01-19 01:07:51 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][280/312]	eta 0:00:23 lr 0.003780	time 0.7244 (0.7420)	model_time 0.7240 (0.7369)	loss 3.3562 (4.2600)	grad_norm 2.2004 (1.6241/0.7195)	mem 34602MB
[2025-01-19 01:07:58 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][290/312]	eta 0:00:16 lr 0.003786	time 0.7171 (0.7415)	model_time 0.7166 (0.7366)	loss 5.1078 (4.2606)	grad_norm 1.0206 (1.6189/0.7172)	mem 34602MB
[2025-01-19 01:08:05 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][300/312]	eta 0:00:08 lr 0.003793	time 0.7125 (0.7410)	model_time 0.7124 (0.7362)	loss 3.3071 (4.2585)	grad_norm 1.0199 (1.6041/0.7137)	mem 34602MB
[2025-01-19 01:08:13 internimage_b_1k_224] (main.py 510): INFO Train: [18/300][310/312]	eta 0:00:01 lr 0.003799	time 0.7124 (0.7405)	model_time 0.7123 (0.7359)	loss 3.0055 (4.2575)	grad_norm 1.2761 (1.6004/0.7125)	mem 34602MB
[2025-01-19 01:08:13 internimage_b_1k_224] (main.py 519): INFO EPOCH 18 training takes 0:03:51
[2025-01-19 01:08:13 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_18.pth saving......
[2025-01-19 01:08:16 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_18.pth saved !!!
[2025-01-19 01:08:30 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 13.760 (13.760)	Loss 1.3333 (1.3333)	Acc@1 69.702 (69.702)	Acc@5 90.723 (90.723)	Mem 34602MB
[2025-01-19 01:08:34 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (1.615)	Loss 2.0226 (1.6355)	Acc@1 56.616 (64.853)	Acc@5 80.981 (86.936)	Mem 34602MB
[2025-01-19 01:08:34 internimage_b_1k_224] (main.py 575): INFO [Epoch:18] * Acc@1 65.143 Acc@5 87.122
[2025-01-19 01:08:34 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 65.1%
[2025-01-19 01:08:34 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 01:08:38 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 01:08:38 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 65.14%
[2025-01-19 01:08:45 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.432 (7.432)	Loss 6.5922 (6.5922)	Acc@1 0.269 (0.269)	Acc@5 3.833 (3.833)	Mem 34602MB
[2025-01-19 01:08:48 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.955)	Loss 6.9223 (6.7089)	Acc@1 0.073 (0.568)	Acc@5 0.806 (2.255)	Mem 34602MB
[2025-01-19 01:08:48 internimage_b_1k_224] (main.py 575): INFO [Epoch:18] * Acc@1 0.834 Acc@5 2.883
[2025-01-19 01:08:48 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.8%
[2025-01-19 01:08:48 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.84%
[2025-01-19 01:08:52 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][0/312]	eta 0:16:54 lr 0.003800	time 3.2521 (3.2521)	model_time 1.7347 (1.7347)	loss 4.6375 (4.6375)	grad_norm 1.3548 (1.3548/0.0000)	mem 34602MB
[2025-01-19 01:08:59 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][10/312]	eta 0:04:51 lr 0.003807	time 0.7458 (0.9652)	model_time 0.7456 (0.8270)	loss 4.5297 (4.4425)	grad_norm 1.2880 (1.5403/0.4842)	mem 34602MB
[2025-01-19 01:09:07 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][20/312]	eta 0:04:13 lr 0.003813	time 0.9001 (0.8671)	model_time 0.8996 (0.7944)	loss 4.4149 (4.3425)	grad_norm 2.6267 (1.5150/0.4724)	mem 34602MB
[2025-01-19 01:09:14 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][30/312]	eta 0:03:57 lr 0.003819	time 0.7927 (0.8428)	model_time 0.7923 (0.7934)	loss 3.6707 (4.2224)	grad_norm 1.1910 (1.5176/0.4803)	mem 34602MB
[2025-01-19 01:09:22 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][40/312]	eta 0:03:43 lr 0.003826	time 0.8062 (0.8217)	model_time 0.8060 (0.7843)	loss 5.0915 (4.2664)	grad_norm 1.5373 (1.5552/0.5539)	mem 34602MB
[2025-01-19 01:09:29 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][50/312]	eta 0:03:31 lr 0.003832	time 0.7229 (0.8062)	model_time 0.7227 (0.7760)	loss 4.7587 (4.2617)	grad_norm 2.0131 (1.5049/0.5469)	mem 34602MB
[2025-01-19 01:09:37 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][60/312]	eta 0:03:20 lr 0.003839	time 0.7396 (0.7939)	model_time 0.7395 (0.7687)	loss 4.7222 (4.2844)	grad_norm 1.1712 (1.6276/0.7152)	mem 34602MB
[2025-01-19 01:09:44 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][70/312]	eta 0:03:09 lr 0.003845	time 0.7244 (0.7844)	model_time 0.7242 (0.7627)	loss 3.6085 (4.2669)	grad_norm 1.9335 (1.6378/0.6963)	mem 34602MB
[2025-01-19 01:09:51 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][80/312]	eta 0:03:00 lr 0.003851	time 0.7340 (0.7777)	model_time 0.7338 (0.7586)	loss 4.6194 (4.2740)	grad_norm 1.5050 (1.6232/0.6709)	mem 34602MB
[2025-01-19 01:09:59 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][90/312]	eta 0:02:51 lr 0.003858	time 0.7270 (0.7722)	model_time 0.7266 (0.7552)	loss 3.9763 (4.2807)	grad_norm 1.1914 (1.6346/0.6519)	mem 34602MB
[2025-01-19 01:10:06 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][100/312]	eta 0:02:42 lr 0.003864	time 0.7195 (0.7685)	model_time 0.7188 (0.7531)	loss 3.5444 (4.2524)	grad_norm 2.0626 (1.6443/0.6370)	mem 34602MB
[2025-01-19 01:10:13 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][110/312]	eta 0:02:34 lr 0.003871	time 0.7239 (0.7647)	model_time 0.7237 (0.7507)	loss 4.3709 (4.2352)	grad_norm 0.9784 (1.6425/0.6253)	mem 34602MB
[2025-01-19 01:10:21 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][120/312]	eta 0:02:26 lr 0.003877	time 0.7174 (0.7616)	model_time 0.7173 (0.7487)	loss 3.1994 (4.2253)	grad_norm 1.1353 (1.6114/0.6187)	mem 34602MB
[2025-01-19 01:10:28 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][130/312]	eta 0:02:18 lr 0.003883	time 0.7235 (0.7588)	model_time 0.7233 (0.7469)	loss 3.8679 (4.2207)	grad_norm 1.0485 (1.6056/0.6189)	mem 34602MB
[2025-01-19 01:10:35 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][140/312]	eta 0:02:10 lr 0.003890	time 0.7951 (0.7582)	model_time 0.7949 (0.7471)	loss 4.7014 (4.2526)	grad_norm 1.5816 (1.5978/0.6151)	mem 34602MB
[2025-01-19 01:10:43 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][150/312]	eta 0:02:03 lr 0.003896	time 0.8067 (0.7605)	model_time 0.8063 (0.7500)	loss 4.9042 (4.2578)	grad_norm 1.7688 (1.6184/0.6121)	mem 34602MB
[2025-01-19 01:10:51 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][160/312]	eta 0:01:55 lr 0.003903	time 0.7612 (0.7607)	model_time 0.7611 (0.7509)	loss 3.3888 (4.2495)	grad_norm 1.3927 (1.6177/0.6038)	mem 34602MB
[2025-01-19 01:10:58 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][170/312]	eta 0:01:47 lr 0.003909	time 0.7194 (0.7598)	model_time 0.7190 (0.7506)	loss 3.6479 (4.2455)	grad_norm 1.0291 (1.5941/0.5988)	mem 34602MB
[2025-01-19 01:11:05 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][180/312]	eta 0:01:40 lr 0.003915	time 0.7223 (0.7577)	model_time 0.7222 (0.7490)	loss 3.3268 (4.2351)	grad_norm 1.0823 (1.6077/0.6019)	mem 34602MB
[2025-01-19 01:11:13 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][190/312]	eta 0:01:32 lr 0.003922	time 0.7226 (0.7563)	model_time 0.7222 (0.7480)	loss 4.6975 (4.2337)	grad_norm 1.5059 (1.6017/0.5938)	mem 34602MB
[2025-01-19 01:11:20 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][200/312]	eta 0:01:24 lr 0.003928	time 0.7266 (0.7549)	model_time 0.7262 (0.7470)	loss 4.7766 (4.2241)	grad_norm 1.4799 (1.5989/0.5843)	mem 34602MB
[2025-01-19 01:11:27 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][210/312]	eta 0:01:16 lr 0.003935	time 0.7311 (0.7538)	model_time 0.7309 (0.7462)	loss 3.9384 (4.2149)	grad_norm 1.4465 (1.5912/0.5791)	mem 34602MB
[2025-01-19 01:11:35 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][220/312]	eta 0:01:09 lr 0.003941	time 0.7515 (0.7525)	model_time 0.7513 (0.7453)	loss 5.1725 (4.2097)	grad_norm 1.8823 (1.5861/0.5728)	mem 34602MB
[2025-01-19 01:11:42 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][230/312]	eta 0:01:01 lr 0.003947	time 0.7230 (0.7517)	model_time 0.7228 (0.7444)	loss 3.2251 (4.2063)	grad_norm 2.2925 (1.6099/0.6135)	mem 34602MB
[2025-01-19 01:11:49 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][240/312]	eta 0:00:54 lr 0.003954	time 0.7145 (0.7506)	model_time 0.7141 (0.7436)	loss 3.8048 (4.2108)	grad_norm 1.4804 (1.6014/0.6056)	mem 34602MB
[2025-01-19 01:11:56 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][250/312]	eta 0:00:46 lr 0.003960	time 0.7193 (0.7495)	model_time 0.7191 (0.7427)	loss 3.9524 (4.2202)	grad_norm 3.4921 (1.6127/0.6303)	mem 34602MB
[2025-01-19 01:12:04 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][260/312]	eta 0:00:38 lr 0.003967	time 0.7434 (0.7497)	model_time 0.7430 (0.7432)	loss 5.0867 (4.2231)	grad_norm 0.9145 (1.6040/0.6333)	mem 34602MB
[2025-01-19 01:12:12 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][270/312]	eta 0:00:31 lr 0.003973	time 0.8031 (0.7516)	model_time 0.8029 (0.7454)	loss 4.5094 (4.2255)	grad_norm 3.0754 (1.6079/0.6430)	mem 34602MB
[2025-01-19 01:12:20 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][280/312]	eta 0:00:24 lr 0.003980	time 0.7157 (0.7520)	model_time 0.7153 (0.7459)	loss 3.2056 (4.2115)	grad_norm 1.0053 (1.6028/0.6420)	mem 34602MB
[2025-01-19 01:12:27 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][290/312]	eta 0:00:16 lr 0.003986	time 0.7177 (0.7517)	model_time 0.7175 (0.7459)	loss 4.1163 (4.2048)	grad_norm 1.3280 (1.5882/0.6375)	mem 34602MB
[2025-01-19 01:12:34 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][300/312]	eta 0:00:09 lr 0.003992	time 0.7114 (0.7508)	model_time 0.7113 (0.7451)	loss 4.0857 (4.2008)	grad_norm 1.4952 (1.5853/0.6333)	mem 34602MB
[2025-01-19 01:12:42 internimage_b_1k_224] (main.py 510): INFO Train: [19/300][310/312]	eta 0:00:01 lr 0.003999	time 0.7678 (0.7498)	model_time 0.7677 (0.7443)	loss 4.4026 (4.2059)	grad_norm 1.4159 (1.5743/0.6318)	mem 34602MB
[2025-01-19 01:12:42 internimage_b_1k_224] (main.py 519): INFO EPOCH 19 training takes 0:03:53
[2025-01-19 01:12:42 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_19.pth saving......
[2025-01-19 01:12:45 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_19.pth saved !!!
[2025-01-19 01:12:53 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.382 (7.382)	Loss 1.3034 (1.3034)	Acc@1 71.021 (71.021)	Acc@5 91.748 (91.748)	Mem 34602MB
[2025-01-19 01:12:56 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.184 (0.942)	Loss 1.9189 (1.6072)	Acc@1 57.666 (65.024)	Acc@5 82.300 (87.349)	Mem 34602MB
[2025-01-19 01:12:56 internimage_b_1k_224] (main.py 575): INFO [Epoch:19] * Acc@1 65.197 Acc@5 87.492
[2025-01-19 01:12:56 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 65.2%
[2025-01-19 01:12:56 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 01:13:00 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 01:13:00 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 65.20%
[2025-01-19 01:13:07 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.129 (7.129)	Loss 6.5677 (6.5677)	Acc@1 0.342 (0.342)	Acc@5 3.979 (3.979)	Mem 34602MB
[2025-01-19 01:13:10 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.915)	Loss 6.9512 (6.7065)	Acc@1 0.098 (0.586)	Acc@5 0.806 (2.304)	Mem 34602MB
[2025-01-19 01:13:10 internimage_b_1k_224] (main.py 575): INFO [Epoch:19] * Acc@1 0.834 Acc@5 2.925
[2025-01-19 01:13:10 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.8%
[2025-01-19 01:13:10 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.84%
[2025-01-19 01:13:13 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][0/312]	eta 0:15:56 lr 0.003957	time 3.0666 (3.0666)	model_time 0.9333 (0.9333)	loss 4.5472 (4.5472)	grad_norm 2.2245 (2.2245/0.0000)	mem 34602MB
[2025-01-19 01:13:20 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][10/312]	eta 0:04:46 lr 0.003957	time 0.7186 (0.9502)	model_time 0.7185 (0.7559)	loss 4.9654 (4.5851)	grad_norm 1.6389 (1.5714/0.4364)	mem 34602MB
[2025-01-19 01:13:28 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][20/312]	eta 0:04:06 lr 0.003956	time 0.7197 (0.8435)	model_time 0.7196 (0.7416)	loss 4.9899 (4.4269)	grad_norm 1.6159 (1.8084/0.9360)	mem 34602MB
[2025-01-19 01:13:35 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][30/312]	eta 0:03:48 lr 0.003956	time 0.7374 (0.8086)	model_time 0.7370 (0.7394)	loss 4.3660 (4.4721)	grad_norm 0.7678 (1.6747/0.8190)	mem 34602MB
[2025-01-19 01:13:42 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][40/312]	eta 0:03:34 lr 0.003956	time 0.7396 (0.7888)	model_time 0.7395 (0.7364)	loss 5.0895 (4.4000)	grad_norm 0.8350 (1.5209/0.7716)	mem 34602MB
[2025-01-19 01:13:49 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][50/312]	eta 0:03:23 lr 0.003956	time 0.7316 (0.7766)	model_time 0.7315 (0.7344)	loss 5.0438 (4.3983)	grad_norm 2.5893 (1.5716/0.7487)	mem 34602MB
[2025-01-19 01:13:57 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][60/312]	eta 0:03:13 lr 0.003956	time 0.7414 (0.7682)	model_time 0.7410 (0.7329)	loss 4.5294 (4.3976)	grad_norm 1.1072 (1.6154/0.7381)	mem 34602MB
[2025-01-19 01:14:04 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][70/312]	eta 0:03:05 lr 0.003956	time 0.8051 (0.7671)	model_time 0.8046 (0.7367)	loss 5.0073 (4.4285)	grad_norm 1.5051 (1.6150/0.7113)	mem 34602MB
[2025-01-19 01:14:12 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][80/312]	eta 0:02:58 lr 0.003956	time 0.8378 (0.7704)	model_time 0.8376 (0.7437)	loss 3.6252 (4.3743)	grad_norm 1.8514 (1.5537/0.6945)	mem 34602MB
[2025-01-19 01:14:20 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][90/312]	eta 0:02:50 lr 0.003955	time 0.7865 (0.7686)	model_time 0.7861 (0.7448)	loss 4.2730 (4.3615)	grad_norm 2.0597 (1.5425/0.6725)	mem 34602MB
[2025-01-19 01:14:27 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][100/312]	eta 0:02:42 lr 0.003955	time 0.7228 (0.7652)	model_time 0.7226 (0.7438)	loss 2.8680 (4.3371)	grad_norm 2.4640 (1.6251/0.8514)	mem 34602MB
[2025-01-19 01:14:34 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][110/312]	eta 0:02:33 lr 0.003955	time 0.7278 (0.7619)	model_time 0.7273 (0.7423)	loss 3.3809 (4.3183)	grad_norm 1.4260 (1.6235/0.8243)	mem 34602MB
[2025-01-19 01:14:42 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][120/312]	eta 0:02:25 lr 0.003955	time 0.7180 (0.7585)	model_time 0.7179 (0.7405)	loss 5.2161 (4.3120)	grad_norm 0.8428 (1.6046/0.8110)	mem 34602MB
[2025-01-19 01:14:49 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][130/312]	eta 0:02:17 lr 0.003955	time 0.7157 (0.7563)	model_time 0.7156 (0.7397)	loss 4.3218 (4.3048)	grad_norm 1.1256 (1.5628/0.7959)	mem 34602MB
[2025-01-19 01:14:56 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][140/312]	eta 0:02:09 lr 0.003955	time 0.7164 (0.7543)	model_time 0.7162 (0.7389)	loss 5.0816 (4.3164)	grad_norm 0.8182 (1.5445/0.7769)	mem 34602MB
[2025-01-19 01:15:03 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][150/312]	eta 0:02:01 lr 0.003955	time 0.7189 (0.7522)	model_time 0.7185 (0.7378)	loss 5.2589 (4.3001)	grad_norm 2.0935 (1.5306/0.7595)	mem 34602MB
[2025-01-19 01:15:11 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][160/312]	eta 0:01:54 lr 0.003954	time 0.7282 (0.7507)	model_time 0.7281 (0.7371)	loss 2.7130 (4.2884)	grad_norm 1.0150 (1.5409/0.7600)	mem 34602MB
[2025-01-19 01:15:18 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][170/312]	eta 0:01:46 lr 0.003954	time 0.7603 (0.7498)	model_time 0.7602 (0.7370)	loss 3.2505 (4.2789)	grad_norm 2.0132 (1.5576/0.7533)	mem 34602MB
[2025-01-19 01:15:25 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][180/312]	eta 0:01:38 lr 0.003954	time 0.7256 (0.7485)	model_time 0.7251 (0.7364)	loss 4.7254 (4.2926)	grad_norm 1.9558 (1.5533/0.7406)	mem 34602MB
[2025-01-19 01:15:33 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][190/312]	eta 0:01:31 lr 0.003954	time 0.8108 (0.7491)	model_time 0.8104 (0.7376)	loss 3.9867 (4.2716)	grad_norm 0.9339 (1.5406/0.7292)	mem 34602MB
[2025-01-19 01:15:41 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][200/312]	eta 0:01:24 lr 0.003954	time 0.9080 (0.7513)	model_time 0.9079 (0.7403)	loss 4.2186 (4.2634)	grad_norm 2.8138 (1.5383/0.7225)	mem 34602MB
[2025-01-19 01:15:48 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][210/312]	eta 0:01:16 lr 0.003954	time 0.8545 (0.7518)	model_time 0.8543 (0.7413)	loss 4.8662 (4.2425)	grad_norm 1.8815 (1.5655/0.7325)	mem 34602MB
[2025-01-19 01:15:56 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][220/312]	eta 0:01:09 lr 0.003954	time 0.7175 (0.7512)	model_time 0.7173 (0.7412)	loss 3.3151 (4.2335)	grad_norm 1.1164 (1.5626/0.7296)	mem 34602MB
[2025-01-19 01:16:03 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][230/312]	eta 0:01:01 lr 0.003953	time 0.7147 (0.7506)	model_time 0.7142 (0.7410)	loss 3.5507 (4.2228)	grad_norm 1.4761 (1.5635/0.7222)	mem 34602MB
[2025-01-19 01:16:10 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][240/312]	eta 0:00:53 lr 0.003953	time 0.7202 (0.7496)	model_time 0.7201 (0.7404)	loss 4.2838 (4.2087)	grad_norm 0.9620 (1.5480/0.7137)	mem 34602MB
[2025-01-19 01:16:18 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][250/312]	eta 0:00:46 lr 0.003953	time 0.7172 (0.7491)	model_time 0.7167 (0.7402)	loss 5.0893 (4.2103)	grad_norm 1.1672 (1.5472/0.7194)	mem 34602MB
[2025-01-19 01:16:25 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][260/312]	eta 0:00:38 lr 0.003953	time 0.7162 (0.7481)	model_time 0.7160 (0.7396)	loss 4.0576 (4.1989)	grad_norm 1.8882 (1.5457/0.7125)	mem 34602MB
[2025-01-19 01:16:32 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][270/312]	eta 0:00:31 lr 0.003953	time 0.7209 (0.7473)	model_time 0.7207 (0.7391)	loss 4.3914 (4.2056)	grad_norm 0.9969 (1.5534/0.7164)	mem 34602MB
[2025-01-19 01:16:40 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][280/312]	eta 0:00:23 lr 0.003953	time 0.7228 (0.7468)	model_time 0.7227 (0.7388)	loss 3.5092 (4.1999)	grad_norm 1.1592 (1.5412/0.7082)	mem 34602MB
[2025-01-19 01:16:47 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][290/312]	eta 0:00:16 lr 0.003953	time 0.7688 (0.7462)	model_time 0.7684 (0.7385)	loss 3.3649 (4.2004)	grad_norm 1.0545 (1.5451/0.7064)	mem 34602MB
[2025-01-19 01:16:54 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][300/312]	eta 0:00:08 lr 0.003952	time 0.7166 (0.7454)	model_time 0.7165 (0.7379)	loss 4.7142 (4.2061)	grad_norm 1.0548 (1.5379/0.6976)	mem 34602MB
[2025-01-19 01:17:01 internimage_b_1k_224] (main.py 510): INFO Train: [20/300][310/312]	eta 0:00:01 lr 0.003952	time 0.7127 (0.7450)	model_time 0.7126 (0.7378)	loss 5.0168 (4.2091)	grad_norm 2.1291 (1.5530/0.7062)	mem 34602MB
[2025-01-19 01:17:02 internimage_b_1k_224] (main.py 519): INFO EPOCH 20 training takes 0:03:52
[2025-01-19 01:17:02 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_20.pth saving......
[2025-01-19 01:17:05 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_20.pth saved !!!
[2025-01-19 01:17:13 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.425 (7.425)	Loss 1.2686 (1.2686)	Acc@1 72.290 (72.290)	Acc@5 91.992 (91.992)	Mem 34602MB
[2025-01-19 01:17:16 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.183 (0.941)	Loss 1.8985 (1.5486)	Acc@1 58.154 (66.089)	Acc@5 83.350 (87.813)	Mem 34602MB
[2025-01-19 01:17:16 internimage_b_1k_224] (main.py 575): INFO [Epoch:20] * Acc@1 66.327 Acc@5 87.996
[2025-01-19 01:17:16 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 66.3%
[2025-01-19 01:17:16 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 01:17:19 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 01:17:19 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 66.33%
[2025-01-19 01:17:27 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.445 (7.445)	Loss 6.5495 (6.5495)	Acc@1 0.415 (0.415)	Acc@5 3.979 (3.979)	Mem 34602MB
[2025-01-19 01:17:30 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.958)	Loss 6.9799 (6.7052)	Acc@1 0.073 (0.637)	Acc@5 0.806 (2.335)	Mem 34602MB
[2025-01-19 01:17:30 internimage_b_1k_224] (main.py 575): INFO [Epoch:20] * Acc@1 0.880 Acc@5 2.971
[2025-01-19 01:17:30 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.9%
[2025-01-19 01:17:30 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:17:34 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:17:34 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.88%
[2025-01-19 01:17:36 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][0/312]	eta 0:11:30 lr 0.003952	time 2.2139 (2.2139)	model_time 0.7598 (0.7598)	loss 3.3810 (3.3810)	grad_norm 1.1168 (1.1168/0.0000)	mem 34602MB
[2025-01-19 01:17:44 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][10/312]	eta 0:04:37 lr 0.003952	time 0.8198 (0.9178)	model_time 0.8197 (0.7852)	loss 3.2530 (4.0471)	grad_norm 1.3603 (1.2195/0.3788)	mem 34602MB
[2025-01-19 01:17:52 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][20/312]	eta 0:04:06 lr 0.003952	time 0.8114 (0.8443)	model_time 0.8110 (0.7747)	loss 4.9005 (4.2621)	grad_norm 1.6545 (1.5045/0.4815)	mem 34602MB
[2025-01-19 01:17:59 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][30/312]	eta 0:03:48 lr 0.003952	time 0.7307 (0.8097)	model_time 0.7306 (0.7624)	loss 4.4181 (4.1085)	grad_norm 2.4036 (1.5755/0.5290)	mem 34602MB
[2025-01-19 01:18:06 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][40/312]	eta 0:03:34 lr 0.003952	time 0.7442 (0.7897)	model_time 0.7438 (0.7539)	loss 4.2986 (4.1396)	grad_norm 2.0366 (1.5351/0.5142)	mem 34602MB
[2025-01-19 01:18:14 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][50/312]	eta 0:03:23 lr 0.003952	time 0.7394 (0.7783)	model_time 0.7390 (0.7494)	loss 3.2816 (4.1290)	grad_norm 1.1767 (1.4853/0.4820)	mem 34602MB
[2025-01-19 01:18:21 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][60/312]	eta 0:03:14 lr 0.003951	time 0.7581 (0.7712)	model_time 0.7580 (0.7470)	loss 3.8363 (4.0863)	grad_norm 2.1495 (1.4729/0.4691)	mem 34602MB
[2025-01-19 01:18:28 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][70/312]	eta 0:03:05 lr 0.003951	time 0.7164 (0.7649)	model_time 0.7162 (0.7441)	loss 4.6730 (4.1420)	grad_norm 1.1841 (1.5229/0.5380)	mem 34602MB
[2025-01-19 01:18:36 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][80/312]	eta 0:02:56 lr 0.003951	time 0.7208 (0.7600)	model_time 0.7204 (0.7417)	loss 4.0419 (4.1078)	grad_norm 1.3649 (1.4941/0.5143)	mem 34602MB
[2025-01-19 01:18:43 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][90/312]	eta 0:02:48 lr 0.003951	time 0.7679 (0.7580)	model_time 0.7678 (0.7416)	loss 4.8013 (4.1295)	grad_norm 1.9850 (1.5120/0.5057)	mem 34602MB
[2025-01-19 01:18:50 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][100/312]	eta 0:02:40 lr 0.003951	time 0.7177 (0.7548)	model_time 0.7173 (0.7400)	loss 4.0119 (4.1321)	grad_norm 1.0692 (1.5000/0.5018)	mem 34602MB
[2025-01-19 01:18:57 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][110/312]	eta 0:02:31 lr 0.003951	time 0.7302 (0.7523)	model_time 0.7298 (0.7388)	loss 3.1745 (4.1144)	grad_norm 1.1441 (1.4940/0.5025)	mem 34602MB
[2025-01-19 01:19:05 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][120/312]	eta 0:02:24 lr 0.003951	time 0.8469 (0.7516)	model_time 0.8465 (0.7392)	loss 4.1791 (4.0995)	grad_norm 2.4090 (1.4937/0.5039)	mem 34602MB
[2025-01-19 01:19:13 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][130/312]	eta 0:02:17 lr 0.003950	time 0.7986 (0.7563)	model_time 0.7984 (0.7448)	loss 4.2354 (4.0814)	grad_norm 0.8868 (1.4778/0.4924)	mem 34602MB
[2025-01-19 01:19:21 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][140/312]	eta 0:02:10 lr 0.003950	time 0.7255 (0.7569)	model_time 0.7254 (0.7462)	loss 4.0983 (4.0660)	grad_norm 1.3854 (1.4548/0.4867)	mem 34602MB
[2025-01-19 01:19:28 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][150/312]	eta 0:02:02 lr 0.003950	time 0.7332 (0.7567)	model_time 0.7328 (0.7467)	loss 4.7385 (4.0881)	grad_norm 0.9889 (1.4678/0.4925)	mem 34602MB
[2025-01-19 01:19:36 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][160/312]	eta 0:01:54 lr 0.003950	time 0.7265 (0.7550)	model_time 0.7263 (0.7456)	loss 4.3555 (4.0957)	grad_norm 2.4545 (1.4464/0.4987)	mem 34602MB
[2025-01-19 01:19:43 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][170/312]	eta 0:01:47 lr 0.003950	time 0.7188 (0.7536)	model_time 0.7187 (0.7448)	loss 4.5849 (4.1204)	grad_norm 1.2205 (1.4991/0.6082)	mem 34602MB
[2025-01-19 01:19:50 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][180/312]	eta 0:01:39 lr 0.003950	time 0.7171 (0.7520)	model_time 0.7167 (0.7436)	loss 3.6479 (4.1198)	grad_norm 1.7008 (1.4859/0.6015)	mem 34602MB
[2025-01-19 01:19:57 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][190/312]	eta 0:01:31 lr 0.003950	time 0.7175 (0.7507)	model_time 0.7174 (0.7427)	loss 3.6499 (4.1100)	grad_norm 1.3727 (1.4906/0.5928)	mem 34602MB
[2025-01-19 01:20:05 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][200/312]	eta 0:01:23 lr 0.003949	time 0.7229 (0.7496)	model_time 0.7227 (0.7420)	loss 4.5887 (4.0966)	grad_norm 1.1137 (1.4768/0.5816)	mem 34602MB
[2025-01-19 01:20:12 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][210/312]	eta 0:01:16 lr 0.003949	time 0.7300 (0.7488)	model_time 0.7296 (0.7415)	loss 5.2512 (4.0977)	grad_norm 0.6547 (1.4703/0.5798)	mem 34602MB
[2025-01-19 01:20:19 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][220/312]	eta 0:01:08 lr 0.003949	time 0.7306 (0.7479)	model_time 0.7304 (0.7409)	loss 4.0352 (4.0875)	grad_norm 0.8729 (1.4787/0.5796)	mem 34602MB
[2025-01-19 01:20:27 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][230/312]	eta 0:01:01 lr 0.003949	time 0.7181 (0.7469)	model_time 0.7177 (0.7403)	loss 2.9595 (4.0930)	grad_norm 0.8638 (1.4668/0.5753)	mem 34602MB
[2025-01-19 01:20:34 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][240/312]	eta 0:00:53 lr 0.003949	time 0.8130 (0.7467)	model_time 0.8126 (0.7403)	loss 4.7556 (4.1091)	grad_norm 1.7571 (1.4508/0.5712)	mem 34602MB
[2025-01-19 01:20:42 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][250/312]	eta 0:00:46 lr 0.003949	time 0.7951 (0.7482)	model_time 0.7949 (0.7421)	loss 4.7575 (4.1091)	grad_norm 1.2286 (1.4464/0.5632)	mem 34602MB
[2025-01-19 01:20:49 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][260/312]	eta 0:00:38 lr 0.003948	time 0.7325 (0.7490)	model_time 0.7321 (0.7431)	loss 3.0435 (4.1049)	grad_norm 2.0490 (1.4514/0.5598)	mem 34602MB
[2025-01-19 01:20:57 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][270/312]	eta 0:00:31 lr 0.003948	time 0.7349 (0.7489)	model_time 0.7345 (0.7431)	loss 3.4285 (4.1064)	grad_norm 0.7439 (1.4561/0.5669)	mem 34602MB
[2025-01-19 01:21:04 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][280/312]	eta 0:00:23 lr 0.003948	time 0.7299 (0.7482)	model_time 0.7298 (0.7426)	loss 3.1225 (4.1041)	grad_norm 3.7113 (1.4631/0.5825)	mem 34602MB
[2025-01-19 01:21:12 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][290/312]	eta 0:00:16 lr 0.003948	time 0.7479 (0.7479)	model_time 0.7475 (0.7425)	loss 5.0247 (4.1065)	grad_norm 1.0001 (1.4569/0.5790)	mem 34602MB
[2025-01-19 01:21:19 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][300/312]	eta 0:00:08 lr 0.003948	time 0.7134 (0.7469)	model_time 0.7133 (0.7417)	loss 3.6460 (4.0969)	grad_norm 4.3896 (1.4602/0.5986)	mem 34602MB
[2025-01-19 01:21:26 internimage_b_1k_224] (main.py 510): INFO Train: [21/300][310/312]	eta 0:00:01 lr 0.003948	time 0.7168 (0.7458)	model_time 0.7167 (0.7408)	loss 4.3761 (4.0955)	grad_norm 1.1801 (1.4914/0.7196)	mem 34602MB
[2025-01-19 01:21:27 internimage_b_1k_224] (main.py 519): INFO EPOCH 21 training takes 0:03:52
[2025-01-19 01:21:27 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_21.pth saving......
[2025-01-19 01:21:30 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_21.pth saved !!!
[2025-01-19 01:21:37 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.589 (7.589)	Loss 1.2532 (1.2532)	Acc@1 73.242 (73.242)	Acc@5 92.017 (92.017)	Mem 34602MB
[2025-01-19 01:21:40 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.969)	Loss 1.8648 (1.5092)	Acc@1 59.985 (67.154)	Acc@5 83.203 (88.457)	Mem 34602MB
[2025-01-19 01:21:41 internimage_b_1k_224] (main.py 575): INFO [Epoch:21] * Acc@1 67.330 Acc@5 88.634
[2025-01-19 01:21:41 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 67.3%
[2025-01-19 01:21:41 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 01:21:44 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 01:21:44 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 67.33%
[2025-01-19 01:21:51 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.474 (7.474)	Loss 6.5292 (6.5292)	Acc@1 0.513 (0.513)	Acc@5 4.126 (4.126)	Mem 34602MB
[2025-01-19 01:21:54 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.941)	Loss 7.0019 (6.7016)	Acc@1 0.049 (0.668)	Acc@5 0.806 (2.430)	Mem 34602MB
[2025-01-19 01:21:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:21] * Acc@1 0.912 Acc@5 3.101
[2025-01-19 01:21:55 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.9%
[2025-01-19 01:21:55 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:21:59 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:21:59 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.91%
[2025-01-19 01:22:01 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][0/312]	eta 0:11:12 lr 0.003948	time 2.1568 (2.1568)	model_time 0.7491 (0.7491)	loss 4.1354 (4.1354)	grad_norm 1.0048 (1.0048/0.0000)	mem 34602MB
[2025-01-19 01:22:08 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][10/312]	eta 0:04:19 lr 0.003948	time 0.7243 (0.8599)	model_time 0.7239 (0.7316)	loss 4.3055 (4.2173)	grad_norm 1.3842 (1.5602/0.5674)	mem 34602MB
[2025-01-19 01:22:15 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][20/312]	eta 0:03:53 lr 0.003947	time 0.7209 (0.7983)	model_time 0.7205 (0.7310)	loss 3.2862 (4.0986)	grad_norm 1.1728 (1.5935/0.5326)	mem 34602MB
[2025-01-19 01:22:23 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][30/312]	eta 0:03:38 lr 0.003947	time 0.7196 (0.7761)	model_time 0.7192 (0.7303)	loss 4.4268 (4.0986)	grad_norm 2.1845 (1.4480/0.5358)	mem 34602MB
[2025-01-19 01:22:30 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][40/312]	eta 0:03:28 lr 0.003947	time 0.7696 (0.7647)	model_time 0.7695 (0.7300)	loss 3.2807 (4.0448)	grad_norm 1.1284 (1.4593/0.5603)	mem 34602MB
[2025-01-19 01:22:38 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][50/312]	eta 0:03:19 lr 0.003947	time 0.7322 (0.7627)	model_time 0.7318 (0.7348)	loss 4.8462 (4.0526)	grad_norm 1.3814 (1.4744/0.5360)	mem 34602MB
[2025-01-19 01:22:45 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][60/312]	eta 0:03:12 lr 0.003947	time 0.8083 (0.7654)	model_time 0.8082 (0.7420)	loss 3.3715 (4.0301)	grad_norm 0.9656 (1.4517/0.5218)	mem 34602MB
[2025-01-19 01:22:53 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][70/312]	eta 0:03:04 lr 0.003947	time 0.7392 (0.7643)	model_time 0.7390 (0.7441)	loss 3.8778 (4.0614)	grad_norm 1.0093 (1.4479/0.5021)	mem 34602MB
[2025-01-19 01:23:00 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][80/312]	eta 0:02:56 lr 0.003946	time 0.7455 (0.7628)	model_time 0.7450 (0.7451)	loss 2.9342 (4.0390)	grad_norm 1.1863 (1.4728/0.5092)	mem 34602MB
[2025-01-19 01:23:08 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][90/312]	eta 0:02:48 lr 0.003946	time 0.7261 (0.7581)	model_time 0.7259 (0.7423)	loss 3.2168 (4.0087)	grad_norm 1.2333 (1.4859/0.5153)	mem 34602MB
[2025-01-19 01:23:15 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][100/312]	eta 0:02:40 lr 0.003946	time 0.7306 (0.7549)	model_time 0.7302 (0.7406)	loss 4.3296 (4.0260)	grad_norm 2.1538 (1.4625/0.5161)	mem 34602MB
[2025-01-19 01:23:22 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][110/312]	eta 0:02:31 lr 0.003946	time 0.7182 (0.7520)	model_time 0.7177 (0.7390)	loss 2.9884 (4.0166)	grad_norm 3.0027 (1.4829/0.5291)	mem 34602MB
[2025-01-19 01:23:30 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][120/312]	eta 0:02:24 lr 0.003946	time 0.7246 (0.7507)	model_time 0.7242 (0.7387)	loss 4.7880 (4.0342)	grad_norm 1.1523 (1.4737/0.5266)	mem 34602MB
[2025-01-19 01:23:37 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][130/312]	eta 0:02:16 lr 0.003946	time 0.7196 (0.7485)	model_time 0.7194 (0.7375)	loss 3.7590 (4.0283)	grad_norm 0.9711 (1.4818/0.5479)	mem 34602MB
[2025-01-19 01:23:44 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][140/312]	eta 0:02:08 lr 0.003946	time 0.7430 (0.7479)	model_time 0.7426 (0.7375)	loss 3.8459 (4.0012)	grad_norm 1.6970 (1.4633/0.5363)	mem 34602MB
[2025-01-19 01:23:51 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][150/312]	eta 0:02:00 lr 0.003945	time 0.7142 (0.7465)	model_time 0.7140 (0.7368)	loss 4.2919 (4.0014)	grad_norm 1.5816 (1.4605/0.5384)	mem 34602MB
[2025-01-19 01:23:59 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][160/312]	eta 0:01:53 lr 0.003945	time 0.7156 (0.7452)	model_time 0.7151 (0.7362)	loss 3.1455 (4.0062)	grad_norm 1.2139 (1.4845/0.5721)	mem 34602MB
[2025-01-19 01:24:06 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][170/312]	eta 0:01:45 lr 0.003945	time 0.8993 (0.7464)	model_time 0.8991 (0.7378)	loss 4.4934 (4.0142)	grad_norm 1.3684 (1.4763/0.5747)	mem 34602MB
[2025-01-19 01:24:14 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][180/312]	eta 0:01:38 lr 0.003945	time 0.7174 (0.7484)	model_time 0.7169 (0.7402)	loss 4.3738 (4.0026)	grad_norm 1.2044 (1.4521/0.5697)	mem 34602MB
[2025-01-19 01:24:22 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][190/312]	eta 0:01:31 lr 0.003945	time 0.7163 (0.7496)	model_time 0.7159 (0.7419)	loss 3.1483 (4.0002)	grad_norm 1.7075 (1.4603/0.5646)	mem 34602MB
[2025-01-19 01:24:29 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][200/312]	eta 0:01:23 lr 0.003945	time 0.7162 (0.7496)	model_time 0.7158 (0.7423)	loss 4.0137 (4.0184)	grad_norm 0.9442 (1.4533/0.5570)	mem 34602MB
[2025-01-19 01:24:37 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][210/312]	eta 0:01:16 lr 0.003944	time 0.7892 (0.7489)	model_time 0.7887 (0.7419)	loss 3.3270 (4.0104)	grad_norm 1.3589 (1.4610/0.5521)	mem 34602MB
[2025-01-19 01:24:44 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][220/312]	eta 0:01:08 lr 0.003944	time 0.7472 (0.7480)	model_time 0.7470 (0.7413)	loss 3.9606 (4.0056)	grad_norm 1.3953 (1.4544/0.5463)	mem 34602MB
[2025-01-19 01:24:51 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][230/312]	eta 0:01:01 lr 0.003944	time 0.7169 (0.7473)	model_time 0.7164 (0.7408)	loss 2.9124 (4.0132)	grad_norm 2.3951 (1.4458/0.5469)	mem 34602MB
[2025-01-19 01:24:59 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][240/312]	eta 0:00:53 lr 0.003944	time 0.7610 (0.7468)	model_time 0.7605 (0.7406)	loss 4.0763 (4.0182)	grad_norm 0.8879 (1.4428/0.5411)	mem 34602MB
[2025-01-19 01:25:06 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][250/312]	eta 0:00:46 lr 0.003944	time 0.7169 (0.7459)	model_time 0.7168 (0.7400)	loss 4.1821 (4.0140)	grad_norm 2.6502 (1.4644/0.5832)	mem 34602MB
[2025-01-19 01:25:13 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][260/312]	eta 0:00:38 lr 0.003944	time 0.7162 (0.7451)	model_time 0.7158 (0.7393)	loss 3.9248 (4.0148)	grad_norm 0.9967 (1.4605/0.5836)	mem 34602MB
[2025-01-19 01:25:20 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][270/312]	eta 0:00:31 lr 0.003944	time 0.7176 (0.7445)	model_time 0.7172 (0.7389)	loss 3.0741 (4.0195)	grad_norm 1.4451 (1.4553/0.5799)	mem 34602MB
[2025-01-19 01:25:28 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][280/312]	eta 0:00:23 lr 0.003943	time 0.7169 (0.7437)	model_time 0.7168 (0.7384)	loss 4.5132 (4.0171)	grad_norm 1.1387 (1.4592/0.5844)	mem 34602MB
[2025-01-19 01:25:35 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][290/312]	eta 0:00:16 lr 0.003943	time 0.8312 (0.7441)	model_time 0.8310 (0.7389)	loss 4.8066 (4.0370)	grad_norm 1.5439 (1.4529/0.5784)	mem 34602MB
[2025-01-19 01:25:43 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][300/312]	eta 0:00:08 lr 0.003943	time 0.7908 (0.7455)	model_time 0.7907 (0.7404)	loss 4.1734 (4.0500)	grad_norm 1.6795 (1.4487/0.5717)	mem 34602MB
[2025-01-19 01:25:51 internimage_b_1k_224] (main.py 510): INFO Train: [22/300][310/312]	eta 0:00:01 lr 0.003943	time 0.7111 (0.7462)	model_time 0.7110 (0.7413)	loss 4.3899 (4.0562)	grad_norm 1.9182 (1.4532/0.5869)	mem 34602MB
[2025-01-19 01:25:51 internimage_b_1k_224] (main.py 519): INFO EPOCH 22 training takes 0:03:52
[2025-01-19 01:25:52 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_22.pth saving......
[2025-01-19 01:25:55 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_22.pth saved !!!
[2025-01-19 01:26:03 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.691 (7.691)	Loss 1.1970 (1.1970)	Acc@1 73.706 (73.706)	Acc@5 92.358 (92.358)	Mem 34602MB
[2025-01-19 01:26:06 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.980)	Loss 1.7362 (1.4484)	Acc@1 62.183 (68.137)	Acc@5 84.888 (89.076)	Mem 34602MB
[2025-01-19 01:26:06 internimage_b_1k_224] (main.py 575): INFO [Epoch:22] * Acc@1 68.248 Acc@5 89.223
[2025-01-19 01:26:06 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 68.2%
[2025-01-19 01:26:06 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 01:26:09 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 01:26:09 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 68.25%
[2025-01-19 01:26:17 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.875 (7.875)	Loss 6.5144 (6.5144)	Acc@1 0.757 (0.757)	Acc@5 4.517 (4.517)	Mem 34602MB
[2025-01-19 01:26:20 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.999)	Loss 7.0128 (6.6936)	Acc@1 0.073 (0.768)	Acc@5 0.806 (2.539)	Mem 34602MB
[2025-01-19 01:26:20 internimage_b_1k_224] (main.py 575): INFO [Epoch:22] * Acc@1 0.994 Acc@5 3.219
[2025-01-19 01:26:20 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 1.0%
[2025-01-19 01:26:20 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:26:24 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:26:24 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 0.99%
[2025-01-19 01:26:26 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][0/312]	eta 0:11:12 lr 0.003943	time 2.1557 (2.1557)	model_time 0.7509 (0.7509)	loss 4.2371 (4.2371)	grad_norm 1.2148 (1.2148/0.0000)	mem 34602MB
[2025-01-19 01:26:34 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][10/312]	eta 0:04:26 lr 0.003943	time 0.7419 (0.8812)	model_time 0.7418 (0.7532)	loss 3.2731 (3.6589)	grad_norm 0.7854 (1.1954/0.3564)	mem 34602MB
[2025-01-19 01:26:41 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][20/312]	eta 0:03:56 lr 0.003943	time 0.7212 (0.8091)	model_time 0.7211 (0.7418)	loss 4.8005 (3.9646)	grad_norm 0.9743 (1.1683/0.3172)	mem 34602MB
[2025-01-19 01:26:48 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][30/312]	eta 0:03:40 lr 0.003942	time 0.7407 (0.7833)	model_time 0.7402 (0.7377)	loss 3.6010 (3.9394)	grad_norm 1.6577 (1.2698/0.5240)	mem 34602MB
[2025-01-19 01:26:56 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][40/312]	eta 0:03:29 lr 0.003942	time 0.7389 (0.7690)	model_time 0.7385 (0.7344)	loss 4.8435 (3.9976)	grad_norm 2.8142 (1.3533/0.6206)	mem 34602MB
[2025-01-19 01:27:03 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][50/312]	eta 0:03:19 lr 0.003942	time 0.7211 (0.7609)	model_time 0.7210 (0.7330)	loss 3.7773 (4.0223)	grad_norm 0.8514 (1.3459/0.5968)	mem 34602MB
[2025-01-19 01:27:10 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][60/312]	eta 0:03:10 lr 0.003942	time 0.7176 (0.7568)	model_time 0.7172 (0.7334)	loss 4.0146 (4.0513)	grad_norm 0.9307 (1.2966/0.5677)	mem 34602MB
[2025-01-19 01:27:18 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][70/312]	eta 0:03:02 lr 0.003942	time 0.7198 (0.7528)	model_time 0.7197 (0.7327)	loss 3.1300 (4.0396)	grad_norm 1.3542 (1.3242/0.5690)	mem 34602MB
[2025-01-19 01:27:25 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][80/312]	eta 0:02:53 lr 0.003942	time 0.7187 (0.7491)	model_time 0.7185 (0.7314)	loss 4.8856 (4.0550)	grad_norm 1.0533 (1.3296/0.5624)	mem 34602MB
[2025-01-19 01:27:32 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][90/312]	eta 0:02:45 lr 0.003941	time 0.7240 (0.7468)	model_time 0.7239 (0.7310)	loss 4.3368 (4.1003)	grad_norm 1.9782 (1.3158/0.5454)	mem 34602MB
[2025-01-19 01:27:40 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][100/312]	eta 0:02:38 lr 0.003941	time 0.8773 (0.7487)	model_time 0.8768 (0.7344)	loss 4.9667 (4.1099)	grad_norm 1.0285 (1.3196/0.5263)	mem 34602MB
[2025-01-19 01:27:48 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][110/312]	eta 0:02:32 lr 0.003941	time 0.8085 (0.7531)	model_time 0.8083 (0.7401)	loss 4.2976 (4.0665)	grad_norm 1.0027 (1.3512/0.5582)	mem 34602MB
[2025-01-19 01:27:55 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][120/312]	eta 0:02:24 lr 0.003941	time 0.7168 (0.7538)	model_time 0.7166 (0.7419)	loss 4.2567 (4.0681)	grad_norm 2.7068 (1.3884/0.6134)	mem 34602MB
[2025-01-19 01:28:03 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][130/312]	eta 0:02:17 lr 0.003941	time 0.7200 (0.7530)	model_time 0.7198 (0.7419)	loss 3.6809 (4.0709)	grad_norm 1.2312 (1.3968/0.5984)	mem 34602MB
[2025-01-19 01:28:10 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][140/312]	eta 0:02:09 lr 0.003941	time 0.7169 (0.7513)	model_time 0.7168 (0.7410)	loss 3.6411 (4.0776)	grad_norm 1.3758 (1.3830/0.5869)	mem 34602MB
[2025-01-19 01:28:17 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][150/312]	eta 0:02:01 lr 0.003940	time 0.7225 (0.7496)	model_time 0.7220 (0.7400)	loss 3.9910 (4.0702)	grad_norm 1.0510 (1.3742/0.5713)	mem 34602MB
[2025-01-19 01:28:25 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][160/312]	eta 0:01:53 lr 0.003940	time 0.7183 (0.7485)	model_time 0.7177 (0.7394)	loss 4.0435 (4.0594)	grad_norm 1.4402 (1.3500/0.5632)	mem 34602MB
[2025-01-19 01:28:32 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][170/312]	eta 0:01:46 lr 0.003940	time 0.7193 (0.7470)	model_time 0.7191 (0.7385)	loss 5.0085 (4.0828)	grad_norm 1.0418 (1.3755/0.6192)	mem 34602MB
[2025-01-19 01:28:39 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][180/312]	eta 0:01:38 lr 0.003940	time 0.7699 (0.7472)	model_time 0.7694 (0.7391)	loss 4.7995 (4.0776)	grad_norm 1.6904 (1.3873/0.6274)	mem 34602MB
[2025-01-19 01:28:47 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][190/312]	eta 0:01:30 lr 0.003940	time 0.7133 (0.7459)	model_time 0.7131 (0.7381)	loss 3.8242 (4.0757)	grad_norm 1.0763 (1.3685/0.6170)	mem 34602MB
[2025-01-19 01:28:54 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][200/312]	eta 0:01:23 lr 0.003940	time 0.7285 (0.7452)	model_time 0.7281 (0.7379)	loss 4.8665 (4.0785)	grad_norm 1.9277 (1.3838/0.6164)	mem 34602MB
[2025-01-19 01:29:01 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][210/312]	eta 0:01:15 lr 0.003939	time 0.7178 (0.7447)	model_time 0.7177 (0.7377)	loss 4.7918 (4.0811)	grad_norm 1.2137 (1.3708/0.6063)	mem 34602MB
[2025-01-19 01:29:09 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][220/312]	eta 0:01:08 lr 0.003939	time 0.8192 (0.7455)	model_time 0.8188 (0.7387)	loss 3.9923 (4.0735)	grad_norm 1.1479 (1.3726/0.5958)	mem 34602MB
[2025-01-19 01:29:17 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][230/312]	eta 0:01:01 lr 0.003939	time 0.8072 (0.7474)	model_time 0.8068 (0.7409)	loss 4.0243 (4.0600)	grad_norm 1.2203 (1.3903/0.6084)	mem 34602MB
[2025-01-19 01:29:24 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][240/312]	eta 0:00:53 lr 0.003939	time 0.7211 (0.7474)	model_time 0.7207 (0.7412)	loss 4.0203 (4.0607)	grad_norm 1.2153 (1.3888/0.6053)	mem 34602MB
[2025-01-19 01:29:32 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][250/312]	eta 0:00:46 lr 0.003939	time 0.7710 (0.7476)	model_time 0.7708 (0.7416)	loss 3.8546 (4.0637)	grad_norm 2.1387 (1.3891/0.5979)	mem 34602MB
[2025-01-19 01:29:39 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][260/312]	eta 0:00:38 lr 0.003939	time 0.7166 (0.7472)	model_time 0.7165 (0.7414)	loss 3.2567 (4.0544)	grad_norm 0.9275 (1.4007/0.5992)	mem 34602MB
[2025-01-19 01:29:46 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][270/312]	eta 0:00:31 lr 0.003938	time 0.7155 (0.7465)	model_time 0.7153 (0.7410)	loss 5.0361 (4.0533)	grad_norm 1.2961 (1.3955/0.5916)	mem 34602MB
[2025-01-19 01:29:54 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][280/312]	eta 0:00:23 lr 0.003938	time 0.7392 (0.7458)	model_time 0.7390 (0.7404)	loss 2.8214 (4.0496)	grad_norm 0.9332 (1.3958/0.5863)	mem 34602MB
[2025-01-19 01:30:01 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][290/312]	eta 0:00:16 lr 0.003938	time 0.7481 (0.7452)	model_time 0.7476 (0.7400)	loss 5.0671 (4.0576)	grad_norm 0.9293 (1.4008/0.5862)	mem 34602MB
[2025-01-19 01:30:08 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][300/312]	eta 0:00:08 lr 0.003938	time 0.7117 (0.7448)	model_time 0.7116 (0.7398)	loss 4.1608 (4.0596)	grad_norm 1.0475 (1.3922/0.5809)	mem 34602MB
[2025-01-19 01:30:15 internimage_b_1k_224] (main.py 510): INFO Train: [23/300][310/312]	eta 0:00:01 lr 0.003938	time 0.7174 (0.7438)	model_time 0.7172 (0.7389)	loss 3.2625 (4.0591)	grad_norm 2.0414 (1.4040/0.5831)	mem 34602MB
[2025-01-19 01:30:16 internimage_b_1k_224] (main.py 519): INFO EPOCH 23 training takes 0:03:52
[2025-01-19 01:30:16 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_23.pth saving......
[2025-01-19 01:30:19 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_23.pth saved !!!
[2025-01-19 01:30:34 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.479 (14.479)	Loss 1.2268 (1.2268)	Acc@1 73.584 (73.584)	Acc@5 92.358 (92.358)	Mem 34602MB
[2025-01-19 01:30:42 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (2.001)	Loss 1.7548 (1.4562)	Acc@1 61.646 (68.344)	Acc@5 84.814 (89.189)	Mem 34602MB
[2025-01-19 01:30:42 internimage_b_1k_224] (main.py 575): INFO [Epoch:23] * Acc@1 68.526 Acc@5 89.381
[2025-01-19 01:30:42 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 68.5%
[2025-01-19 01:30:42 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 01:30:45 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 01:30:45 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 68.53%
[2025-01-19 01:31:00 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.727 (14.727)	Loss 6.4976 (6.4976)	Acc@1 0.806 (0.806)	Acc@5 4.590 (4.590)	Mem 34602MB
[2025-01-19 01:31:03 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.674)	Loss 7.0164 (6.6815)	Acc@1 0.073 (0.817)	Acc@5 0.879 (2.666)	Mem 34602MB
[2025-01-19 01:31:04 internimage_b_1k_224] (main.py 575): INFO [Epoch:23] * Acc@1 1.060 Acc@5 3.391
[2025-01-19 01:31:04 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 1.1%
[2025-01-19 01:31:04 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:31:08 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:31:08 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 1.06%
[2025-01-19 01:31:10 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][0/312]	eta 0:11:07 lr 0.003938	time 2.1400 (2.1400)	model_time 0.7592 (0.7592)	loss 4.2208 (4.2208)	grad_norm 1.2875 (1.2875/0.0000)	mem 34602MB
[2025-01-19 01:31:17 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][10/312]	eta 0:04:18 lr 0.003938	time 0.7335 (0.8571)	model_time 0.7333 (0.7313)	loss 4.0653 (4.0061)	grad_norm 1.6535 (1.4742/0.4515)	mem 34602MB
[2025-01-19 01:31:25 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][20/312]	eta 0:03:52 lr 0.003937	time 0.7185 (0.7959)	model_time 0.7181 (0.7299)	loss 3.9281 (3.9480)	grad_norm 0.9875 (1.3654/0.4536)	mem 34602MB
[2025-01-19 01:31:32 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][30/312]	eta 0:03:42 lr 0.003937	time 0.8024 (0.7903)	model_time 0.8022 (0.7455)	loss 4.4689 (3.9664)	grad_norm 0.9596 (1.5831/0.8745)	mem 34602MB
[2025-01-19 01:31:41 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][40/312]	eta 0:03:36 lr 0.003937	time 0.7168 (0.7948)	model_time 0.7164 (0.7609)	loss 4.1264 (3.9793)	grad_norm 0.8403 (1.4854/0.7949)	mem 34602MB
[2025-01-19 01:31:48 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][50/312]	eta 0:03:26 lr 0.003937	time 0.7203 (0.7866)	model_time 0.7202 (0.7592)	loss 3.8031 (3.9663)	grad_norm 1.1631 (1.5209/0.8224)	mem 34602MB
[2025-01-19 01:31:56 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][60/312]	eta 0:03:16 lr 0.003937	time 0.7162 (0.7809)	model_time 0.7158 (0.7580)	loss 4.8271 (4.0285)	grad_norm 1.0273 (1.5029/0.7753)	mem 34602MB
[2025-01-19 01:32:03 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][70/312]	eta 0:03:07 lr 0.003937	time 0.7147 (0.7728)	model_time 0.7145 (0.7530)	loss 4.1169 (3.9764)	grad_norm 1.4336 (1.4604/0.7372)	mem 34602MB
[2025-01-19 01:32:10 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][80/312]	eta 0:02:58 lr 0.003936	time 0.7167 (0.7676)	model_time 0.7165 (0.7502)	loss 4.2813 (3.9371)	grad_norm 1.4352 (1.4234/0.7040)	mem 34602MB
[2025-01-19 01:32:17 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][90/312]	eta 0:02:49 lr 0.003936	time 0.7539 (0.7635)	model_time 0.7535 (0.7480)	loss 4.3094 (3.9535)	grad_norm 1.6911 (1.4375/0.6880)	mem 34602MB
[2025-01-19 01:32:25 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][100/312]	eta 0:02:41 lr 0.003936	time 0.7197 (0.7611)	model_time 0.7193 (0.7470)	loss 2.9961 (3.9735)	grad_norm 1.3342 (1.4198/0.6678)	mem 34602MB
[2025-01-19 01:32:32 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][110/312]	eta 0:02:33 lr 0.003936	time 0.7284 (0.7583)	model_time 0.7283 (0.7455)	loss 4.4497 (3.9702)	grad_norm 0.7632 (1.4353/0.6645)	mem 34602MB
[2025-01-19 01:32:39 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][120/312]	eta 0:02:25 lr 0.003936	time 0.7479 (0.7561)	model_time 0.7475 (0.7443)	loss 3.7777 (3.9794)	grad_norm 2.8729 (1.4702/0.6659)	mem 34602MB
[2025-01-19 01:32:47 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][130/312]	eta 0:02:17 lr 0.003936	time 0.7248 (0.7540)	model_time 0.7244 (0.7431)	loss 4.5324 (3.9774)	grad_norm 0.9874 (1.4958/0.6972)	mem 34602MB
[2025-01-19 01:32:54 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][140/312]	eta 0:02:09 lr 0.003935	time 0.7298 (0.7519)	model_time 0.7296 (0.7418)	loss 4.0923 (3.9847)	grad_norm 1.2283 (1.4801/0.6801)	mem 34602MB
[2025-01-19 01:33:02 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][150/312]	eta 0:02:01 lr 0.003935	time 0.8043 (0.7530)	model_time 0.8039 (0.7435)	loss 4.1470 (3.9885)	grad_norm 1.6413 (1.4520/0.6700)	mem 34602MB
[2025-01-19 01:33:10 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][160/312]	eta 0:01:54 lr 0.003935	time 0.7987 (0.7561)	model_time 0.7986 (0.7472)	loss 3.8344 (3.9921)	grad_norm 0.8450 (1.4394/0.6530)	mem 34602MB
[2025-01-19 01:33:17 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][170/312]	eta 0:01:47 lr 0.003935	time 0.7458 (0.7566)	model_time 0.7456 (0.7482)	loss 4.2112 (3.9949)	grad_norm 1.6208 (1.4495/0.6466)	mem 34602MB
[2025-01-19 01:33:25 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][180/312]	eta 0:01:39 lr 0.003935	time 0.8204 (0.7566)	model_time 0.8203 (0.7486)	loss 4.2332 (4.0180)	grad_norm 1.4118 (1.4463/0.6350)	mem 34602MB
[2025-01-19 01:33:32 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][190/312]	eta 0:01:32 lr 0.003935	time 0.7160 (0.7548)	model_time 0.7158 (0.7473)	loss 4.4246 (4.0028)	grad_norm 1.7530 (1.4464/0.6223)	mem 34602MB
[2025-01-19 01:33:39 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][200/312]	eta 0:01:24 lr 0.003934	time 0.7247 (0.7533)	model_time 0.7245 (0.7461)	loss 4.6155 (4.0087)	grad_norm 1.4774 (1.4356/0.6134)	mem 34602MB
[2025-01-19 01:33:47 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][210/312]	eta 0:01:16 lr 0.003934	time 0.7208 (0.7520)	model_time 0.7204 (0.7451)	loss 3.8549 (4.0165)	grad_norm 1.0126 (1.4160/0.6086)	mem 34602MB
[2025-01-19 01:33:54 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][220/312]	eta 0:01:09 lr 0.003934	time 0.7321 (0.7514)	model_time 0.7319 (0.7448)	loss 4.2024 (4.0284)	grad_norm 1.5057 (1.4313/0.6243)	mem 34602MB
[2025-01-19 01:34:01 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][230/312]	eta 0:01:01 lr 0.003934	time 0.7265 (0.7505)	model_time 0.7264 (0.7442)	loss 2.9559 (4.0128)	grad_norm 0.9977 (1.4155/0.6199)	mem 34602MB
[2025-01-19 01:34:09 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][240/312]	eta 0:00:53 lr 0.003934	time 0.7373 (0.7497)	model_time 0.7368 (0.7436)	loss 3.8696 (4.0013)	grad_norm 1.0159 (1.4345/0.6746)	mem 34602MB
[2025-01-19 01:34:16 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][250/312]	eta 0:00:46 lr 0.003934	time 0.7167 (0.7488)	model_time 0.7166 (0.7430)	loss 4.2963 (4.0032)	grad_norm 0.6602 (1.4326/0.6670)	mem 34602MB
[2025-01-19 01:34:23 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][260/312]	eta 0:00:38 lr 0.003933	time 0.7446 (0.7481)	model_time 0.7442 (0.7424)	loss 3.5418 (3.9988)	grad_norm 0.7047 (1.4176/0.6594)	mem 34602MB
[2025-01-19 01:34:31 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][270/312]	eta 0:00:31 lr 0.003933	time 0.7177 (0.7485)	model_time 0.7175 (0.7430)	loss 4.1094 (3.9998)	grad_norm 1.6146 (1.4202/0.6525)	mem 34602MB
[2025-01-19 01:34:39 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][280/312]	eta 0:00:23 lr 0.003933	time 0.8065 (0.7496)	model_time 0.8060 (0.7443)	loss 3.9838 (3.9964)	grad_norm 1.2807 (1.4156/0.6481)	mem 34602MB
[2025-01-19 01:34:46 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][290/312]	eta 0:00:16 lr 0.003933	time 0.7160 (0.7499)	model_time 0.7158 (0.7448)	loss 3.5149 (3.9959)	grad_norm 1.1740 (1.4104/0.6400)	mem 34602MB
[2025-01-19 01:34:54 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][300/312]	eta 0:00:08 lr 0.003933	time 0.8022 (0.7500)	model_time 0.8022 (0.7450)	loss 4.7587 (3.9989)	grad_norm 1.6028 (1.4138/0.6349)	mem 34602MB
[2025-01-19 01:35:01 internimage_b_1k_224] (main.py 510): INFO Train: [24/300][310/312]	eta 0:00:01 lr 0.003933	time 0.7231 (0.7489)	model_time 0.7230 (0.7441)	loss 2.7887 (3.9997)	grad_norm 2.5102 (1.4100/0.6345)	mem 34602MB
[2025-01-19 01:35:02 internimage_b_1k_224] (main.py 519): INFO EPOCH 24 training takes 0:03:53
[2025-01-19 01:35:02 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_24.pth saving......
[2025-01-19 01:35:05 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_24.pth saved !!!
[2025-01-19 01:35:13 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.636 (7.636)	Loss 1.1816 (1.1816)	Acc@1 73.047 (73.047)	Acc@5 92.310 (92.310)	Mem 34602MB
[2025-01-19 01:35:15 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.948)	Loss 1.7149 (1.4139)	Acc@1 62.012 (68.399)	Acc@5 84.888 (89.302)	Mem 34602MB
[2025-01-19 01:35:16 internimage_b_1k_224] (main.py 575): INFO [Epoch:24] * Acc@1 68.598 Acc@5 89.417
[2025-01-19 01:35:16 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 68.6%
[2025-01-19 01:35:16 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 01:35:19 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 01:35:19 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 68.60%
[2025-01-19 01:35:26 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.313 (7.313)	Loss 6.4704 (6.4704)	Acc@1 0.830 (0.830)	Acc@5 4.834 (4.834)	Mem 34602MB
[2025-01-19 01:35:29 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.937)	Loss 7.0036 (6.6601)	Acc@1 0.122 (0.859)	Acc@5 0.928 (2.876)	Mem 34602MB
[2025-01-19 01:35:29 internimage_b_1k_224] (main.py 575): INFO [Epoch:24] * Acc@1 1.116 Acc@5 3.643
[2025-01-19 01:35:29 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 1.1%
[2025-01-19 01:35:29 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:35:33 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:35:33 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 1.12%
[2025-01-19 01:35:35 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][0/312]	eta 0:11:53 lr 0.003933	time 2.2861 (2.2861)	model_time 0.7386 (0.7386)	loss 4.8584 (4.8584)	grad_norm 2.4438 (2.4438/0.0000)	mem 34602MB
[2025-01-19 01:35:43 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][10/312]	eta 0:04:24 lr 0.003932	time 0.7354 (0.8754)	model_time 0.7353 (0.7344)	loss 4.3347 (4.1732)	grad_norm 1.7568 (2.0928/1.0581)	mem 34602MB
[2025-01-19 01:35:50 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][20/312]	eta 0:03:56 lr 0.003932	time 0.7172 (0.8097)	model_time 0.7170 (0.7357)	loss 4.3765 (4.1625)	grad_norm 1.4423 (1.7838/0.9190)	mem 34602MB
[2025-01-19 01:35:57 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][30/312]	eta 0:03:40 lr 0.003932	time 0.7232 (0.7834)	model_time 0.7230 (0.7332)	loss 3.4256 (4.0520)	grad_norm 1.4347 (1.5734/0.8253)	mem 34602MB
[2025-01-19 01:36:04 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][40/312]	eta 0:03:29 lr 0.003932	time 0.7254 (0.7688)	model_time 0.7253 (0.7308)	loss 4.7600 (4.0381)	grad_norm 1.3019 (1.4819/0.7513)	mem 34602MB
[2025-01-19 01:36:12 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][50/312]	eta 0:03:19 lr 0.003932	time 0.7254 (0.7606)	model_time 0.7252 (0.7300)	loss 3.0470 (4.0632)	grad_norm 2.1570 (1.5350/0.7450)	mem 34602MB
[2025-01-19 01:36:19 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][60/312]	eta 0:03:10 lr 0.003931	time 0.7341 (0.7548)	model_time 0.7339 (0.7292)	loss 3.5983 (4.0463)	grad_norm 1.1261 (1.5185/0.7168)	mem 34602MB
[2025-01-19 01:36:26 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][70/312]	eta 0:03:01 lr 0.003931	time 0.7320 (0.7512)	model_time 0.7318 (0.7291)	loss 4.1490 (4.0863)	grad_norm 0.8551 (1.4760/0.7168)	mem 34602MB
[2025-01-19 01:36:34 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][80/312]	eta 0:02:54 lr 0.003931	time 0.7163 (0.7517)	model_time 0.7162 (0.7323)	loss 3.8453 (4.0807)	grad_norm 1.2811 (1.4450/0.6869)	mem 34602MB
[2025-01-19 01:36:42 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][90/312]	eta 0:02:47 lr 0.003931	time 0.8076 (0.7554)	model_time 0.8073 (0.7381)	loss 4.0978 (4.0727)	grad_norm 2.1812 (1.4724/0.7055)	mem 34602MB
[2025-01-19 01:36:49 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][100/312]	eta 0:02:40 lr 0.003931	time 0.7659 (0.7569)	model_time 0.7658 (0.7413)	loss 4.2127 (4.0773)	grad_norm 1.0941 (1.4307/0.6833)	mem 34602MB
[2025-01-19 01:36:57 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][110/312]	eta 0:02:32 lr 0.003931	time 0.8230 (0.7569)	model_time 0.8225 (0.7427)	loss 3.9496 (4.0957)	grad_norm 0.9210 (1.4096/0.6635)	mem 34602MB
[2025-01-19 01:37:04 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][120/312]	eta 0:02:24 lr 0.003930	time 0.7193 (0.7541)	model_time 0.7191 (0.7409)	loss 3.5063 (4.0611)	grad_norm 1.4315 (1.4364/0.6664)	mem 34602MB
[2025-01-19 01:37:12 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][130/312]	eta 0:02:16 lr 0.003930	time 0.7283 (0.7524)	model_time 0.7281 (0.7402)	loss 3.9113 (4.0587)	grad_norm 1.0336 (1.4327/0.6550)	mem 34602MB
[2025-01-19 01:37:19 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][140/312]	eta 0:02:09 lr 0.003930	time 0.7124 (0.7512)	model_time 0.7122 (0.7398)	loss 4.6430 (4.0627)	grad_norm 1.9131 (1.4113/0.6413)	mem 34602MB
[2025-01-19 01:37:26 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][150/312]	eta 0:02:01 lr 0.003930	time 0.7189 (0.7497)	model_time 0.7188 (0.7391)	loss 3.5647 (4.0643)	grad_norm 2.2479 (1.4287/0.6478)	mem 34602MB
[2025-01-19 01:37:33 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][160/312]	eta 0:01:53 lr 0.003930	time 0.7217 (0.7484)	model_time 0.7212 (0.7384)	loss 4.1652 (4.0477)	grad_norm 1.0661 (1.4403/0.6424)	mem 34602MB
[2025-01-19 01:37:41 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][170/312]	eta 0:01:46 lr 0.003930	time 0.7225 (0.7473)	model_time 0.7219 (0.7379)	loss 3.0798 (4.0177)	grad_norm 1.1649 (1.4364/0.6264)	mem 34602MB
[2025-01-19 01:37:48 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][180/312]	eta 0:01:38 lr 0.003929	time 0.7284 (0.7462)	model_time 0.7279 (0.7372)	loss 4.3325 (4.0175)	grad_norm 0.8986 (1.4419/0.6190)	mem 34602MB
[2025-01-19 01:37:55 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][190/312]	eta 0:01:30 lr 0.003929	time 0.7234 (0.7450)	model_time 0.7233 (0.7365)	loss 2.7030 (4.0136)	grad_norm 2.2546 (1.4270/0.6135)	mem 34602MB
[2025-01-19 01:38:03 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][200/312]	eta 0:01:23 lr 0.003929	time 0.8018 (0.7457)	model_time 0.8016 (0.7376)	loss 4.2343 (4.0116)	grad_norm 0.9398 (1.4254/0.6060)	mem 34602MB
[2025-01-19 01:38:11 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][210/312]	eta 0:01:16 lr 0.003929	time 0.8226 (0.7472)	model_time 0.8224 (0.7395)	loss 3.9516 (4.0078)	grad_norm 1.8542 (1.4213/0.5958)	mem 34602MB
[2025-01-19 01:38:18 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][220/312]	eta 0:01:08 lr 0.003929	time 0.7288 (0.7477)	model_time 0.7287 (0.7403)	loss 3.4417 (4.0118)	grad_norm 1.6545 (1.4195/0.5904)	mem 34602MB
[2025-01-19 01:38:26 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][230/312]	eta 0:01:01 lr 0.003929	time 0.8908 (0.7481)	model_time 0.8906 (0.7410)	loss 3.2089 (3.9996)	grad_norm 1.4400 (1.4094/0.5809)	mem 34602MB
[2025-01-19 01:38:33 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][240/312]	eta 0:00:53 lr 0.003928	time 0.7096 (0.7479)	model_time 0.7094 (0.7411)	loss 3.7022 (4.0016)	grad_norm 0.9436 (1.4449/0.6371)	mem 34602MB
[2025-01-19 01:38:41 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][250/312]	eta 0:00:46 lr 0.003928	time 0.7357 (0.7474)	model_time 0.7352 (0.7408)	loss 3.9338 (3.9859)	grad_norm 1.0421 (1.4326/0.6299)	mem 34602MB
[2025-01-19 01:38:48 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][260/312]	eta 0:00:38 lr 0.003928	time 0.7293 (0.7465)	model_time 0.7292 (0.7402)	loss 4.2040 (3.9825)	grad_norm 1.6521 (1.4303/0.6205)	mem 34602MB
[2025-01-19 01:38:55 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][270/312]	eta 0:00:31 lr 0.003928	time 0.7193 (0.7467)	model_time 0.7191 (0.7406)	loss 4.8847 (3.9934)	grad_norm 1.2215 (1.4323/0.6130)	mem 34602MB
[2025-01-19 01:39:03 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][280/312]	eta 0:00:23 lr 0.003928	time 0.7169 (0.7462)	model_time 0.7167 (0.7403)	loss 4.0663 (3.9934)	grad_norm 1.7539 (1.4343/0.6126)	mem 34602MB
[2025-01-19 01:39:10 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][290/312]	eta 0:00:16 lr 0.003927	time 0.7261 (0.7455)	model_time 0.7259 (0.7398)	loss 4.8829 (4.0030)	grad_norm 0.9235 (1.4233/0.6068)	mem 34602MB
[2025-01-19 01:39:17 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][300/312]	eta 0:00:08 lr 0.003927	time 0.7192 (0.7446)	model_time 0.7190 (0.7391)	loss 4.3471 (4.0040)	grad_norm 2.7192 (1.4247/0.6171)	mem 34602MB
[2025-01-19 01:39:24 internimage_b_1k_224] (main.py 510): INFO Train: [25/300][310/312]	eta 0:00:01 lr 0.003927	time 0.7165 (0.7438)	model_time 0.7164 (0.7385)	loss 3.6768 (4.0014)	grad_norm 2.1784 (1.4130/0.5825)	mem 34602MB
[2025-01-19 01:39:25 internimage_b_1k_224] (main.py 519): INFO EPOCH 25 training takes 0:03:52
[2025-01-19 01:39:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_25.pth saving......
[2025-01-19 01:39:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_25.pth saved !!!
[2025-01-19 01:39:35 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.178 (7.178)	Loss 1.1492 (1.1492)	Acc@1 74.634 (74.634)	Acc@5 92.969 (92.969)	Mem 34602MB
[2025-01-19 01:39:38 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.920)	Loss 1.7226 (1.4003)	Acc@1 62.793 (69.245)	Acc@5 84.863 (89.728)	Mem 34602MB
[2025-01-19 01:39:39 internimage_b_1k_224] (main.py 575): INFO [Epoch:25] * Acc@1 69.374 Acc@5 89.839
[2025-01-19 01:39:39 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 69.4%
[2025-01-19 01:39:39 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 01:39:42 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 01:39:42 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 69.37%
[2025-01-19 01:39:49 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.216 (7.216)	Loss 6.4341 (6.4341)	Acc@1 0.854 (0.854)	Acc@5 5.103 (5.103)	Mem 34602MB
[2025-01-19 01:39:52 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.927)	Loss 6.9627 (6.6228)	Acc@1 0.146 (0.866)	Acc@5 1.123 (3.163)	Mem 34602MB
[2025-01-19 01:39:52 internimage_b_1k_224] (main.py 575): INFO [Epoch:25] * Acc@1 1.182 Acc@5 3.995
[2025-01-19 01:39:52 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 1.2%
[2025-01-19 01:39:52 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:39:56 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:39:56 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 1.18%
[2025-01-19 01:39:58 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][0/312]	eta 0:11:37 lr 0.003927	time 2.2362 (2.2362)	model_time 0.7475 (0.7475)	loss 4.5383 (4.5383)	grad_norm 2.1609 (2.1609/0.0000)	mem 34602MB
[2025-01-19 01:40:06 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][10/312]	eta 0:04:26 lr 0.003927	time 0.8163 (0.8840)	model_time 0.8161 (0.7484)	loss 4.1384 (4.0400)	grad_norm 0.7845 (1.4285/0.6761)	mem 34602MB
[2025-01-19 01:40:14 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][20/312]	eta 0:04:04 lr 0.003927	time 0.8024 (0.8386)	model_time 0.8019 (0.7674)	loss 3.4331 (3.9761)	grad_norm 0.8416 (1.2830/0.5700)	mem 34602MB
[2025-01-19 01:40:21 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][30/312]	eta 0:03:49 lr 0.003927	time 0.7178 (0.8125)	model_time 0.7176 (0.7641)	loss 3.8916 (3.9762)	grad_norm 1.0634 (1.1849/0.5021)	mem 34602MB
[2025-01-19 01:40:29 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][40/312]	eta 0:03:36 lr 0.003926	time 0.7177 (0.7967)	model_time 0.7172 (0.7600)	loss 2.8047 (3.9395)	grad_norm 1.7404 (1.2237/0.5238)	mem 34602MB
[2025-01-19 01:40:36 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][50/312]	eta 0:03:25 lr 0.003926	time 0.7492 (0.7854)	model_time 0.7490 (0.7558)	loss 2.6686 (3.9259)	grad_norm 1.5190 (1.3888/0.7360)	mem 34602MB
[2025-01-19 01:40:43 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][60/312]	eta 0:03:15 lr 0.003926	time 0.7214 (0.7759)	model_time 0.7212 (0.7511)	loss 2.6947 (3.9394)	grad_norm 0.7271 (1.3322/0.6949)	mem 34602MB
[2025-01-19 01:40:51 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][70/312]	eta 0:03:07 lr 0.003926	time 0.7207 (0.7731)	model_time 0.7205 (0.7518)	loss 3.2227 (3.9443)	grad_norm 2.0289 (1.3251/0.6695)	mem 34602MB
[2025-01-19 01:40:58 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][80/312]	eta 0:02:58 lr 0.003926	time 0.7352 (0.7674)	model_time 0.7350 (0.7486)	loss 4.0402 (3.9420)	grad_norm 1.6514 (1.3625/0.6638)	mem 34602MB
[2025-01-19 01:41:05 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][90/312]	eta 0:02:49 lr 0.003925	time 0.7200 (0.7626)	model_time 0.7194 (0.7458)	loss 4.3767 (3.9523)	grad_norm 3.0316 (1.3867/0.6719)	mem 34602MB
[2025-01-19 01:41:13 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][100/312]	eta 0:02:40 lr 0.003925	time 0.7303 (0.7591)	model_time 0.7301 (0.7440)	loss 2.7112 (3.9606)	grad_norm 1.2975 (1.4169/0.7353)	mem 34602MB
[2025-01-19 01:41:20 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][110/312]	eta 0:02:32 lr 0.003925	time 0.7198 (0.7564)	model_time 0.7197 (0.7427)	loss 3.7952 (3.9606)	grad_norm 1.1443 (1.3918/0.7188)	mem 34602MB
[2025-01-19 01:41:27 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][120/312]	eta 0:02:24 lr 0.003925	time 0.7146 (0.7543)	model_time 0.7141 (0.7416)	loss 3.3218 (3.9323)	grad_norm 1.0096 (1.3823/0.7044)	mem 34602MB
[2025-01-19 01:41:35 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][130/312]	eta 0:02:17 lr 0.003925	time 0.8094 (0.7536)	model_time 0.8092 (0.7418)	loss 2.9161 (3.9313)	grad_norm 1.3513 (1.3664/0.6838)	mem 34602MB
[2025-01-19 01:41:43 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][140/312]	eta 0:02:10 lr 0.003925	time 0.7163 (0.7565)	model_time 0.7161 (0.7456)	loss 4.6085 (3.9333)	grad_norm 1.5789 (1.3784/0.6925)	mem 34602MB
[2025-01-19 01:41:50 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][150/312]	eta 0:02:02 lr 0.003924	time 0.7160 (0.7570)	model_time 0.7159 (0.7468)	loss 4.4225 (3.9518)	grad_norm 0.9670 (1.3669/0.6839)	mem 34602MB
[2025-01-19 01:41:58 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][160/312]	eta 0:01:54 lr 0.003924	time 0.7244 (0.7561)	model_time 0.7240 (0.7465)	loss 4.3905 (3.9737)	grad_norm 1.3504 (1.3717/0.6769)	mem 34602MB
[2025-01-19 01:42:05 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][170/312]	eta 0:01:47 lr 0.003924	time 0.7157 (0.7550)	model_time 0.7152 (0.7459)	loss 4.3354 (3.9776)	grad_norm 0.9782 (1.3651/0.6594)	mem 34602MB
[2025-01-19 01:42:12 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][180/312]	eta 0:01:39 lr 0.003924	time 0.7295 (0.7535)	model_time 0.7294 (0.7449)	loss 4.5579 (3.9919)	grad_norm 2.0299 (1.3628/0.6485)	mem 34602MB
[2025-01-19 01:42:20 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][190/312]	eta 0:01:31 lr 0.003924	time 0.7159 (0.7530)	model_time 0.7155 (0.7448)	loss 3.2395 (3.9817)	grad_norm 1.1954 (1.3724/0.6375)	mem 34602MB
[2025-01-19 01:42:27 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][200/312]	eta 0:01:24 lr 0.003923	time 0.7183 (0.7515)	model_time 0.7182 (0.7437)	loss 4.1385 (3.9827)	grad_norm 0.7318 (1.3521/0.6287)	mem 34602MB
[2025-01-19 01:42:34 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][210/312]	eta 0:01:16 lr 0.003923	time 0.7228 (0.7503)	model_time 0.7227 (0.7429)	loss 5.0566 (3.9830)	grad_norm 0.9412 (1.3595/0.6257)	mem 34602MB
[2025-01-19 01:42:42 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][220/312]	eta 0:01:08 lr 0.003923	time 0.7178 (0.7492)	model_time 0.7174 (0.7420)	loss 3.8117 (3.9737)	grad_norm 1.0663 (1.3659/0.6236)	mem 34602MB
[2025-01-19 01:42:49 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][230/312]	eta 0:01:01 lr 0.003923	time 0.7245 (0.7483)	model_time 0.7243 (0.7415)	loss 4.9689 (3.9833)	grad_norm 0.9238 (1.3569/0.6161)	mem 34602MB
[2025-01-19 01:42:56 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][240/312]	eta 0:00:53 lr 0.003923	time 0.7264 (0.7474)	model_time 0.7262 (0.7408)	loss 4.3765 (3.9775)	grad_norm 0.9450 (1.3439/0.6094)	mem 34602MB
[2025-01-19 01:43:04 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][250/312]	eta 0:00:46 lr 0.003923	time 0.8123 (0.7472)	model_time 0.8121 (0.7409)	loss 4.7198 (3.9876)	grad_norm 3.6784 (1.3574/0.6216)	mem 34602MB
[2025-01-19 01:43:12 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][260/312]	eta 0:00:38 lr 0.003922	time 0.7288 (0.7488)	model_time 0.7284 (0.7427)	loss 4.3021 (3.9820)	grad_norm 1.2167 (1.3600/0.6215)	mem 34602MB
[2025-01-19 01:43:19 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][270/312]	eta 0:00:31 lr 0.003922	time 0.7305 (0.7497)	model_time 0.7303 (0.7438)	loss 3.8707 (3.9823)	grad_norm 2.1671 (1.3530/0.6177)	mem 34602MB
[2025-01-19 01:43:27 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][280/312]	eta 0:00:23 lr 0.003922	time 0.7171 (0.7493)	model_time 0.7170 (0.7436)	loss 3.6226 (3.9930)	grad_norm 0.9768 (1.3456/0.6092)	mem 34602MB
[2025-01-19 01:43:34 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][290/312]	eta 0:00:16 lr 0.003922	time 0.7204 (0.7487)	model_time 0.7202 (0.7432)	loss 5.0111 (3.9955)	grad_norm 1.0606 (1.3394/0.6035)	mem 34602MB
[2025-01-19 01:43:41 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][300/312]	eta 0:00:08 lr 0.003922	time 0.7119 (0.7478)	model_time 0.7117 (0.7425)	loss 3.4437 (3.9933)	grad_norm 1.2834 (1.3278/0.5974)	mem 34602MB
[2025-01-19 01:43:49 internimage_b_1k_224] (main.py 510): INFO Train: [26/300][310/312]	eta 0:00:01 lr 0.003921	time 0.7199 (0.7477)	model_time 0.7198 (0.7425)	loss 3.9903 (3.9819)	grad_norm 2.0656 (1.3491/0.6085)	mem 34602MB
[2025-01-19 01:43:49 internimage_b_1k_224] (main.py 519): INFO EPOCH 26 training takes 0:03:53
[2025-01-19 01:43:49 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_26.pth saving......
[2025-01-19 01:43:52 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_26.pth saved !!!
[2025-01-19 01:44:00 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.367 (7.367)	Loss 1.1442 (1.1442)	Acc@1 74.146 (74.146)	Acc@5 93.042 (93.042)	Mem 34602MB
[2025-01-19 01:44:03 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.941)	Loss 1.6881 (1.3916)	Acc@1 63.232 (69.596)	Acc@5 86.157 (90.010)	Mem 34602MB
[2025-01-19 01:44:03 internimage_b_1k_224] (main.py 575): INFO [Epoch:26] * Acc@1 69.724 Acc@5 90.143
[2025-01-19 01:44:03 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 69.7%
[2025-01-19 01:44:03 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 01:44:07 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 01:44:07 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 69.72%
[2025-01-19 01:44:14 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.318 (7.318)	Loss 6.3948 (6.3948)	Acc@1 0.928 (0.928)	Acc@5 5.469 (5.469)	Mem 34602MB
[2025-01-19 01:44:17 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.928)	Loss 6.8983 (6.5692)	Acc@1 0.171 (0.919)	Acc@5 1.440 (3.544)	Mem 34602MB
[2025-01-19 01:44:17 internimage_b_1k_224] (main.py 575): INFO [Epoch:26] * Acc@1 1.288 Acc@5 4.455
[2025-01-19 01:44:17 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 1.3%
[2025-01-19 01:44:17 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:44:21 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:44:21 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 1.29%
[2025-01-19 01:44:23 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][0/312]	eta 0:11:37 lr 0.003921	time 2.2348 (2.2348)	model_time 0.7407 (0.7407)	loss 3.7469 (3.7469)	grad_norm 1.0613 (1.0613/0.0000)	mem 34602MB
[2025-01-19 01:44:31 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][10/312]	eta 0:04:21 lr 0.003921	time 0.7077 (0.8647)	model_time 0.7076 (0.7286)	loss 3.1830 (3.7855)	grad_norm 0.9316 (1.1797/0.3718)	mem 34602MB
[2025-01-19 01:44:38 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][20/312]	eta 0:03:54 lr 0.003921	time 0.7548 (0.8023)	model_time 0.7546 (0.7309)	loss 4.2492 (4.0436)	grad_norm 2.3295 (1.3106/0.4361)	mem 34602MB
[2025-01-19 01:44:45 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][30/312]	eta 0:03:38 lr 0.003921	time 0.7245 (0.7764)	model_time 0.7240 (0.7279)	loss 3.7940 (4.0734)	grad_norm 1.2319 (1.3039/0.4626)	mem 34602MB
[2025-01-19 01:44:53 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][40/312]	eta 0:03:28 lr 0.003921	time 0.7520 (0.7662)	model_time 0.7519 (0.7294)	loss 3.4880 (4.0636)	grad_norm 1.1497 (1.3103/0.4558)	mem 34602MB
[2025-01-19 01:45:00 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][50/312]	eta 0:03:19 lr 0.003920	time 0.7994 (0.7604)	model_time 0.7989 (0.7308)	loss 4.9748 (4.0074)	grad_norm 1.0190 (1.3608/0.4793)	mem 34602MB
[2025-01-19 01:45:07 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][60/312]	eta 0:03:11 lr 0.003920	time 0.7169 (0.7581)	model_time 0.7167 (0.7333)	loss 3.5307 (3.9554)	grad_norm 0.7688 (1.3102/0.4800)	mem 34602MB
[2025-01-19 01:45:15 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][70/312]	eta 0:03:04 lr 0.003920	time 0.7999 (0.7617)	model_time 0.7998 (0.7403)	loss 4.1547 (4.0046)	grad_norm 0.6842 (1.2764/0.4662)	mem 34602MB
[2025-01-19 01:45:23 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][80/312]	eta 0:02:57 lr 0.003920	time 0.7882 (0.7632)	model_time 0.7880 (0.7444)	loss 4.2505 (4.0264)	grad_norm 0.9477 (1.3416/0.6531)	mem 34602MB
[2025-01-19 01:45:31 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][90/312]	eta 0:02:49 lr 0.003920	time 0.7167 (0.7621)	model_time 0.7165 (0.7453)	loss 3.6823 (4.0345)	grad_norm 1.4657 (1.3248/0.6233)	mem 34602MB
[2025-01-19 01:45:38 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][100/312]	eta 0:02:40 lr 0.003920	time 0.7233 (0.7586)	model_time 0.7229 (0.7434)	loss 4.2693 (4.0267)	grad_norm 1.1125 (1.3416/0.6175)	mem 34602MB
[2025-01-19 01:45:45 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][110/312]	eta 0:02:32 lr 0.003919	time 0.7188 (0.7564)	model_time 0.7186 (0.7426)	loss 3.4207 (4.0291)	grad_norm 1.8087 (1.3105/0.6053)	mem 34602MB
[2025-01-19 01:45:53 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][120/312]	eta 0:02:24 lr 0.003919	time 0.7263 (0.7547)	model_time 0.7261 (0.7420)	loss 3.3043 (4.0378)	grad_norm 0.8533 (1.2914/0.5904)	mem 34602MB
[2025-01-19 01:46:00 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][130/312]	eta 0:02:16 lr 0.003919	time 0.7208 (0.7526)	model_time 0.7206 (0.7408)	loss 3.2533 (4.0513)	grad_norm 3.3023 (1.2982/0.6067)	mem 34602MB
[2025-01-19 01:46:07 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][140/312]	eta 0:02:09 lr 0.003919	time 0.7292 (0.7512)	model_time 0.7288 (0.7402)	loss 4.3647 (4.0472)	grad_norm 1.2527 (1.3371/0.6345)	mem 34602MB
[2025-01-19 01:46:14 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][150/312]	eta 0:02:01 lr 0.003919	time 0.7268 (0.7493)	model_time 0.7266 (0.7391)	loss 4.7378 (4.0417)	grad_norm 2.0146 (1.3313/0.6216)	mem 34602MB
[2025-01-19 01:46:22 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][160/312]	eta 0:01:53 lr 0.003918	time 0.7140 (0.7477)	model_time 0.7136 (0.7381)	loss 2.7444 (4.0164)	grad_norm 1.1118 (1.3232/0.6048)	mem 34602MB
[2025-01-19 01:46:29 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][170/312]	eta 0:01:46 lr 0.003918	time 0.7900 (0.7472)	model_time 0.7895 (0.7381)	loss 4.6780 (4.0409)	grad_norm 2.4985 (1.3294/0.6030)	mem 34602MB
[2025-01-19 01:46:37 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][180/312]	eta 0:01:38 lr 0.003918	time 0.7226 (0.7476)	model_time 0.7224 (0.7390)	loss 4.5551 (4.0481)	grad_norm 1.0950 (1.3345/0.5983)	mem 34602MB
[2025-01-19 01:46:44 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][190/312]	eta 0:01:31 lr 0.003918	time 0.8016 (0.7490)	model_time 0.8011 (0.7408)	loss 4.0735 (4.0440)	grad_norm 1.2354 (1.3362/0.5880)	mem 34602MB
[2025-01-19 01:46:52 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][200/312]	eta 0:01:23 lr 0.003918	time 0.8007 (0.7499)	model_time 0.8005 (0.7421)	loss 3.1127 (4.0456)	grad_norm 2.1753 (1.3319/0.5831)	mem 34602MB
[2025-01-19 01:47:00 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][210/312]	eta 0:01:16 lr 0.003917	time 0.8242 (0.7501)	model_time 0.8240 (0.7426)	loss 2.9998 (4.0325)	grad_norm 0.9528 (1.3434/0.5997)	mem 34602MB
[2025-01-19 01:47:07 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][220/312]	eta 0:01:08 lr 0.003917	time 0.7183 (0.7489)	model_time 0.7181 (0.7417)	loss 3.9054 (4.0386)	grad_norm 2.2434 (1.3426/0.5915)	mem 34602MB
[2025-01-19 01:47:14 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][230/312]	eta 0:01:01 lr 0.003917	time 0.7189 (0.7478)	model_time 0.7187 (0.7409)	loss 4.4617 (4.0370)	grad_norm 4.8266 (1.3615/0.6309)	mem 34602MB
[2025-01-19 01:47:21 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][240/312]	eta 0:00:53 lr 0.003917	time 0.7317 (0.7470)	model_time 0.7312 (0.7404)	loss 2.9446 (4.0219)	grad_norm 1.2602 (1.3615/0.6243)	mem 34602MB
[2025-01-19 01:47:29 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][250/312]	eta 0:00:46 lr 0.003917	time 0.7171 (0.7462)	model_time 0.7169 (0.7399)	loss 4.1411 (4.0199)	grad_norm 0.9874 (1.3481/0.6161)	mem 34602MB
[2025-01-19 01:47:36 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][260/312]	eta 0:00:38 lr 0.003916	time 0.7189 (0.7460)	model_time 0.7187 (0.7399)	loss 3.1893 (4.0045)	grad_norm 1.1618 (1.3503/0.6082)	mem 34602MB
[2025-01-19 01:47:43 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][270/312]	eta 0:00:31 lr 0.003916	time 0.7218 (0.7452)	model_time 0.7213 (0.7393)	loss 3.3947 (4.0001)	grad_norm 1.8955 (1.3569/0.6012)	mem 34602MB
[2025-01-19 01:47:50 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][280/312]	eta 0:00:23 lr 0.003916	time 0.7285 (0.7445)	model_time 0.7283 (0.7388)	loss 3.9905 (4.0031)	grad_norm 1.2670 (1.3504/0.5966)	mem 34602MB
[2025-01-19 01:47:58 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][290/312]	eta 0:00:16 lr 0.003916	time 0.8056 (0.7442)	model_time 0.8051 (0.7387)	loss 3.7751 (3.9965)	grad_norm 1.3756 (1.3478/0.5915)	mem 34602MB
[2025-01-19 01:48:05 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][300/312]	eta 0:00:08 lr 0.003916	time 0.7120 (0.7441)	model_time 0.7119 (0.7387)	loss 4.4712 (3.9988)	grad_norm 1.4372 (1.3523/0.5885)	mem 34602MB
[2025-01-19 01:48:13 internimage_b_1k_224] (main.py 510): INFO Train: [27/300][310/312]	eta 0:00:01 lr 0.003916	time 0.8783 (0.7444)	model_time 0.8783 (0.7392)	loss 3.5173 (3.9981)	grad_norm 1.1609 (1.3621/0.5929)	mem 34602MB
[2025-01-19 01:48:14 internimage_b_1k_224] (main.py 519): INFO EPOCH 27 training takes 0:03:52
[2025-01-19 01:48:14 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_27.pth saving......
[2025-01-19 01:48:17 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_27.pth saved !!!
[2025-01-19 01:48:25 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.576 (7.576)	Loss 1.0904 (1.0904)	Acc@1 75.195 (75.195)	Acc@5 92.969 (92.969)	Mem 34602MB
[2025-01-19 01:48:28 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.949)	Loss 1.6779 (1.3760)	Acc@1 63.794 (69.720)	Acc@5 85.718 (90.083)	Mem 34602MB
[2025-01-19 01:48:28 internimage_b_1k_224] (main.py 575): INFO [Epoch:27] * Acc@1 69.786 Acc@5 90.199
[2025-01-19 01:48:28 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 69.8%
[2025-01-19 01:48:28 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 01:48:31 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 01:48:31 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 69.79%
[2025-01-19 01:48:39 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.237 (7.237)	Loss 6.3419 (6.3419)	Acc@1 1.074 (1.074)	Acc@5 5.957 (5.957)	Mem 34602MB
[2025-01-19 01:48:41 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.911)	Loss 6.8065 (6.4974)	Acc@1 0.317 (1.041)	Acc@5 1.831 (4.048)	Mem 34602MB
[2025-01-19 01:48:42 internimage_b_1k_224] (main.py 575): INFO [Epoch:27] * Acc@1 1.434 Acc@5 5.078
[2025-01-19 01:48:42 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 1.4%
[2025-01-19 01:48:42 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:48:46 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:48:46 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 1.43%
[2025-01-19 01:48:48 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][0/312]	eta 0:10:34 lr 0.003915	time 2.0324 (2.0324)	model_time 0.7453 (0.7453)	loss 4.8558 (4.8558)	grad_norm 0.6873 (0.6873/0.0000)	mem 34602MB
[2025-01-19 01:48:55 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][10/312]	eta 0:04:26 lr 0.003915	time 0.7895 (0.8811)	model_time 0.7891 (0.7638)	loss 4.2991 (4.1569)	grad_norm 2.0364 (1.2445/0.4402)	mem 34602MB
[2025-01-19 01:49:03 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][20/312]	eta 0:03:59 lr 0.003915	time 0.7134 (0.8196)	model_time 0.7132 (0.7580)	loss 4.3339 (4.1566)	grad_norm 3.1468 (1.4552/0.6069)	mem 34602MB
[2025-01-19 01:49:10 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][30/312]	eta 0:03:42 lr 0.003915	time 0.7322 (0.7896)	model_time 0.7317 (0.7477)	loss 4.9654 (4.1176)	grad_norm 1.4232 (1.4668/0.5830)	mem 34602MB
[2025-01-19 01:49:17 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][40/312]	eta 0:03:30 lr 0.003915	time 0.7159 (0.7744)	model_time 0.7157 (0.7427)	loss 3.6567 (4.1059)	grad_norm 2.4778 (1.4381/0.5866)	mem 34602MB
[2025-01-19 01:49:25 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][50/312]	eta 0:03:20 lr 0.003915	time 0.7306 (0.7646)	model_time 0.7304 (0.7390)	loss 4.7318 (4.0755)	grad_norm 1.8918 (1.4222/0.5532)	mem 34602MB
[2025-01-19 01:49:32 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][60/312]	eta 0:03:11 lr 0.003914	time 0.7205 (0.7583)	model_time 0.7204 (0.7369)	loss 3.1538 (4.0589)	grad_norm 1.1344 (1.3867/0.5278)	mem 34602MB
[2025-01-19 01:49:39 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][70/312]	eta 0:03:02 lr 0.003914	time 0.7287 (0.7554)	model_time 0.7286 (0.7369)	loss 3.6153 (4.0295)	grad_norm 1.4979 (1.3981/0.5087)	mem 34602MB
[2025-01-19 01:49:46 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][80/312]	eta 0:02:54 lr 0.003914	time 0.7450 (0.7522)	model_time 0.7448 (0.7360)	loss 4.2870 (4.0224)	grad_norm 1.4225 (1.3894/0.4950)	mem 34602MB
[2025-01-19 01:49:54 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][90/312]	eta 0:02:46 lr 0.003914	time 0.7237 (0.7494)	model_time 0.7236 (0.7350)	loss 4.2411 (4.0246)	grad_norm 1.7569 (1.3964/0.4888)	mem 34602MB
[2025-01-19 01:50:01 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][100/312]	eta 0:02:38 lr 0.003914	time 0.7213 (0.7475)	model_time 0.7211 (0.7344)	loss 4.2226 (4.0114)	grad_norm 2.7077 (1.3638/0.5076)	mem 34602MB
[2025-01-19 01:50:09 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][110/312]	eta 0:02:31 lr 0.003913	time 0.7174 (0.7482)	model_time 0.7169 (0.7363)	loss 4.5781 (4.0275)	grad_norm 1.2525 (1.3618/0.5224)	mem 34602MB
[2025-01-19 01:50:16 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][120/312]	eta 0:02:24 lr 0.003913	time 0.8004 (0.7511)	model_time 0.8002 (0.7401)	loss 4.0217 (4.0074)	grad_norm 0.7297 (1.3345/0.5129)	mem 34602MB
[2025-01-19 01:50:24 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][130/312]	eta 0:02:16 lr 0.003913	time 0.7311 (0.7524)	model_time 0.7309 (0.7422)	loss 2.7627 (3.9943)	grad_norm 1.0299 (1.3063/0.5054)	mem 34602MB
[2025-01-19 01:50:32 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][140/312]	eta 0:02:09 lr 0.003913	time 0.7144 (0.7524)	model_time 0.7142 (0.7429)	loss 2.5106 (3.9865)	grad_norm 1.2222 (1.3141/0.5125)	mem 34602MB
[2025-01-19 01:50:39 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][150/312]	eta 0:02:01 lr 0.003913	time 0.7161 (0.7509)	model_time 0.7157 (0.7421)	loss 3.6710 (3.9835)	grad_norm 0.6849 (1.3682/0.5883)	mem 34602MB
[2025-01-19 01:50:46 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][160/312]	eta 0:01:53 lr 0.003912	time 0.7159 (0.7495)	model_time 0.7157 (0.7412)	loss 4.2724 (3.9695)	grad_norm 1.4107 (1.3722/0.5779)	mem 34602MB
[2025-01-19 01:50:53 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][170/312]	eta 0:01:46 lr 0.003912	time 0.7082 (0.7481)	model_time 0.7077 (0.7403)	loss 3.5976 (3.9588)	grad_norm 0.9154 (1.3519/0.5739)	mem 34602MB
[2025-01-19 01:51:01 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][180/312]	eta 0:01:38 lr 0.003912	time 0.7453 (0.7472)	model_time 0.7451 (0.7397)	loss 2.8225 (3.9724)	grad_norm 1.4507 (1.3356/0.5660)	mem 34602MB
[2025-01-19 01:51:08 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][190/312]	eta 0:01:31 lr 0.003912	time 0.7188 (0.7469)	model_time 0.7183 (0.7398)	loss 4.6025 (3.9777)	grad_norm 0.8350 (1.3788/0.6561)	mem 34602MB
[2025-01-19 01:51:15 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][200/312]	eta 0:01:23 lr 0.003912	time 0.7240 (0.7457)	model_time 0.7236 (0.7390)	loss 4.5601 (3.9843)	grad_norm 0.9801 (1.3706/0.6447)	mem 34602MB
[2025-01-19 01:51:23 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][210/312]	eta 0:01:15 lr 0.003911	time 0.7256 (0.7449)	model_time 0.7255 (0.7384)	loss 3.9371 (3.9747)	grad_norm 1.9405 (1.3616/0.6368)	mem 34602MB
[2025-01-19 01:51:30 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][220/312]	eta 0:01:08 lr 0.003911	time 0.7234 (0.7441)	model_time 0.7232 (0.7379)	loss 4.3396 (3.9669)	grad_norm 0.7697 (1.3353/0.6345)	mem 34602MB
[2025-01-19 01:51:38 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][230/312]	eta 0:01:01 lr 0.003911	time 0.7953 (0.7446)	model_time 0.7948 (0.7387)	loss 4.3553 (3.9866)	grad_norm 1.1708 (1.3356/0.6270)	mem 34602MB
[2025-01-19 01:51:45 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][240/312]	eta 0:00:53 lr 0.003911	time 0.8031 (0.7455)	model_time 0.8029 (0.7398)	loss 3.1837 (3.9782)	grad_norm 1.0343 (1.3368/0.6222)	mem 34602MB
[2025-01-19 01:51:53 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][250/312]	eta 0:00:46 lr 0.003911	time 0.7239 (0.7464)	model_time 0.7237 (0.7409)	loss 4.6868 (3.9804)	grad_norm 1.4993 (1.3318/0.6130)	mem 34602MB
[2025-01-19 01:52:00 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][260/312]	eta 0:00:38 lr 0.003910	time 0.8077 (0.7464)	model_time 0.8075 (0.7411)	loss 3.8875 (3.9772)	grad_norm 2.1196 (1.3305/0.6073)	mem 34602MB
[2025-01-19 01:52:08 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][270/312]	eta 0:00:31 lr 0.003910	time 0.7164 (0.7459)	model_time 0.7162 (0.7408)	loss 4.2772 (3.9609)	grad_norm 1.7630 (1.3322/0.5995)	mem 34602MB
[2025-01-19 01:52:15 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][280/312]	eta 0:00:23 lr 0.003910	time 0.7161 (0.7451)	model_time 0.7159 (0.7402)	loss 4.3919 (3.9538)	grad_norm 2.2199 (1.3446/0.6041)	mem 34602MB
[2025-01-19 01:52:22 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][290/312]	eta 0:00:16 lr 0.003910	time 0.7438 (0.7445)	model_time 0.7436 (0.7397)	loss 4.2250 (3.9640)	grad_norm 1.3657 (1.3430/0.5964)	mem 34602MB
[2025-01-19 01:52:29 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][300/312]	eta 0:00:08 lr 0.003910	time 0.7135 (0.7438)	model_time 0.7134 (0.7392)	loss 3.5207 (3.9637)	grad_norm 1.2686 (1.3383/0.5918)	mem 34602MB
[2025-01-19 01:52:37 internimage_b_1k_224] (main.py 510): INFO Train: [28/300][310/312]	eta 0:00:01 lr 0.003909	time 0.7142 (0.7429)	model_time 0.7141 (0.7384)	loss 4.2612 (3.9538)	grad_norm 1.0356 (1.3310/0.5894)	mem 34602MB
[2025-01-19 01:52:37 internimage_b_1k_224] (main.py 519): INFO EPOCH 28 training takes 0:03:51
[2025-01-19 01:52:37 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_28.pth saving......
[2025-01-19 01:52:40 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_28.pth saved !!!
[2025-01-19 01:52:56 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.436 (15.436)	Loss 1.0961 (1.0961)	Acc@1 74.805 (74.805)	Acc@5 93.799 (93.799)	Mem 34602MB
[2025-01-19 01:53:03 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (2.074)	Loss 1.6674 (1.3326)	Acc@1 62.451 (70.379)	Acc@5 86.279 (90.456)	Mem 34602MB
[2025-01-19 01:53:04 internimage_b_1k_224] (main.py 575): INFO [Epoch:28] * Acc@1 70.519 Acc@5 90.565
[2025-01-19 01:53:04 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 70.5%
[2025-01-19 01:53:04 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 01:53:07 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 01:53:07 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 70.52%
[2025-01-19 01:53:22 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.787 (14.787)	Loss 6.2774 (6.2774)	Acc@1 1.196 (1.196)	Acc@5 6.836 (6.836)	Mem 34602MB
[2025-01-19 01:53:26 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.711)	Loss 6.6909 (6.4059)	Acc@1 0.488 (1.238)	Acc@5 2.466 (4.945)	Mem 34602MB
[2025-01-19 01:53:26 internimage_b_1k_224] (main.py 575): INFO [Epoch:28] * Acc@1 1.657 Acc@5 6.092
[2025-01-19 01:53:26 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 1.7%
[2025-01-19 01:53:26 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:53:30 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:53:30 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 1.66%
[2025-01-19 01:53:32 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][0/312]	eta 0:11:36 lr 0.003909	time 2.2312 (2.2312)	model_time 0.7380 (0.7380)	loss 3.2905 (3.2905)	grad_norm 1.0867 (1.0867/0.0000)	mem 34602MB
[2025-01-19 01:53:39 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][10/312]	eta 0:04:23 lr 0.003909	time 0.7162 (0.8734)	model_time 0.7160 (0.7373)	loss 3.2202 (3.8901)	grad_norm 1.9799 (1.3797/0.4106)	mem 34602MB
[2025-01-19 01:53:46 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][20/312]	eta 0:03:54 lr 0.003909	time 0.7180 (0.8024)	model_time 0.7178 (0.7309)	loss 3.2078 (3.8886)	grad_norm 1.2722 (1.3154/0.3810)	mem 34602MB
[2025-01-19 01:53:54 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][30/312]	eta 0:03:40 lr 0.003909	time 0.7158 (0.7809)	model_time 0.7157 (0.7324)	loss 3.1001 (3.8913)	grad_norm 1.3434 (1.3660/0.4465)	mem 34602MB
[2025-01-19 01:54:01 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][40/312]	eta 0:03:30 lr 0.003909	time 0.7167 (0.7751)	model_time 0.7163 (0.7383)	loss 4.1482 (3.8989)	grad_norm 1.2120 (1.3628/0.4706)	mem 34602MB
[2025-01-19 01:54:09 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][50/312]	eta 0:03:24 lr 0.003908	time 0.8194 (0.7802)	model_time 0.8190 (0.7505)	loss 4.4116 (3.8953)	grad_norm 1.2438 (1.3372/0.4707)	mem 34602MB
[2025-01-19 01:54:17 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][60/312]	eta 0:03:15 lr 0.003908	time 0.7200 (0.7765)	model_time 0.7198 (0.7516)	loss 3.8735 (3.9321)	grad_norm 1.1032 (1.3080/0.4425)	mem 34602MB
[2025-01-19 01:54:24 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][70/312]	eta 0:03:07 lr 0.003908	time 0.8050 (0.7737)	model_time 0.8046 (0.7523)	loss 3.1808 (3.8757)	grad_norm 1.2327 (1.3298/0.4591)	mem 34602MB
[2025-01-19 01:54:32 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][80/312]	eta 0:02:58 lr 0.003908	time 0.7225 (0.7674)	model_time 0.7220 (0.7486)	loss 3.6806 (3.8821)	grad_norm 0.6513 (1.3265/0.4527)	mem 34602MB
[2025-01-19 01:54:39 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][90/312]	eta 0:02:49 lr 0.003908	time 0.7265 (0.7630)	model_time 0.7263 (0.7462)	loss 3.7891 (3.8799)	grad_norm 1.5502 (1.3705/0.5022)	mem 34602MB
[2025-01-19 01:54:46 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][100/312]	eta 0:02:40 lr 0.003907	time 0.7335 (0.7592)	model_time 0.7330 (0.7440)	loss 2.9038 (3.8800)	grad_norm 1.4633 (1.3707/0.4887)	mem 34602MB
[2025-01-19 01:54:53 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][110/312]	eta 0:02:32 lr 0.003907	time 0.7327 (0.7561)	model_time 0.7322 (0.7422)	loss 2.5662 (3.8663)	grad_norm 1.8187 (1.3970/0.4981)	mem 34602MB
[2025-01-19 01:55:01 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][120/312]	eta 0:02:24 lr 0.003907	time 0.7365 (0.7540)	model_time 0.7361 (0.7413)	loss 3.0485 (3.8815)	grad_norm 1.5771 (1.3925/0.4876)	mem 34602MB
[2025-01-19 01:55:08 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][130/312]	eta 0:02:16 lr 0.003907	time 0.7317 (0.7526)	model_time 0.7315 (0.7408)	loss 3.4683 (3.8697)	grad_norm 1.4662 (1.3742/0.4818)	mem 34602MB
[2025-01-19 01:55:15 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][140/312]	eta 0:02:09 lr 0.003907	time 0.7275 (0.7505)	model_time 0.7271 (0.7395)	loss 4.2685 (3.8656)	grad_norm 0.9287 (1.4150/0.5482)	mem 34602MB
[2025-01-19 01:55:23 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][150/312]	eta 0:02:01 lr 0.003906	time 0.7166 (0.7489)	model_time 0.7162 (0.7386)	loss 3.4701 (3.8784)	grad_norm 1.0982 (1.3951/0.5400)	mem 34602MB
[2025-01-19 01:55:30 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][160/312]	eta 0:01:53 lr 0.003906	time 0.8101 (0.7494)	model_time 0.8097 (0.7398)	loss 4.5342 (3.8755)	grad_norm 0.9836 (1.3816/0.5313)	mem 34602MB
[2025-01-19 01:55:38 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][170/312]	eta 0:01:46 lr 0.003906	time 0.8334 (0.7516)	model_time 0.8332 (0.7425)	loss 4.4269 (3.8886)	grad_norm 2.7079 (1.3816/0.5295)	mem 34602MB
[2025-01-19 01:55:46 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][180/312]	eta 0:01:39 lr 0.003906	time 0.7111 (0.7521)	model_time 0.7106 (0.7435)	loss 3.4147 (3.8868)	grad_norm 0.6707 (1.3730/0.5398)	mem 34602MB
[2025-01-19 01:55:53 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][190/312]	eta 0:01:31 lr 0.003906	time 0.7150 (0.7519)	model_time 0.7149 (0.7437)	loss 4.0857 (3.8825)	grad_norm 1.2548 (1.3526/0.5338)	mem 34602MB
[2025-01-19 01:56:01 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][200/312]	eta 0:01:24 lr 0.003905	time 0.7260 (0.7511)	model_time 0.7258 (0.7433)	loss 4.2351 (3.8668)	grad_norm 0.7191 (1.3490/0.5264)	mem 34602MB
[2025-01-19 01:56:08 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][210/312]	eta 0:01:16 lr 0.003905	time 0.7183 (0.7499)	model_time 0.7178 (0.7425)	loss 3.8569 (3.8716)	grad_norm 2.3259 (1.3419/0.5227)	mem 34602MB
[2025-01-19 01:56:15 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][220/312]	eta 0:01:08 lr 0.003905	time 0.7171 (0.7490)	model_time 0.7169 (0.7419)	loss 3.1702 (3.8821)	grad_norm 0.7806 (1.3572/0.5499)	mem 34602MB
[2025-01-19 01:56:22 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][230/312]	eta 0:01:01 lr 0.003905	time 0.7181 (0.7480)	model_time 0.7180 (0.7411)	loss 4.4547 (3.8913)	grad_norm 0.6700 (1.3780/0.5724)	mem 34602MB
[2025-01-19 01:56:30 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][240/312]	eta 0:00:53 lr 0.003905	time 0.7355 (0.7473)	model_time 0.7350 (0.7408)	loss 3.8806 (3.8908)	grad_norm 0.6454 (1.3633/0.5682)	mem 34602MB
[2025-01-19 01:56:37 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][250/312]	eta 0:00:46 lr 0.003904	time 0.7192 (0.7469)	model_time 0.7191 (0.7406)	loss 4.5086 (3.8848)	grad_norm 1.1761 (1.3704/0.5681)	mem 34602MB
[2025-01-19 01:56:44 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][260/312]	eta 0:00:38 lr 0.003904	time 0.7186 (0.7460)	model_time 0.7182 (0.7399)	loss 4.3462 (3.8953)	grad_norm 2.9480 (1.3671/0.5714)	mem 34602MB
[2025-01-19 01:56:52 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][270/312]	eta 0:00:31 lr 0.003904	time 0.7231 (0.7455)	model_time 0.7230 (0.7396)	loss 4.6366 (3.8884)	grad_norm 0.6809 (1.3529/0.5707)	mem 34602MB
[2025-01-19 01:56:59 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][280/312]	eta 0:00:23 lr 0.003904	time 0.8103 (0.7459)	model_time 0.8101 (0.7402)	loss 3.9209 (3.8826)	grad_norm 1.0639 (1.3560/0.5695)	mem 34602MB
[2025-01-19 01:57:07 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][290/312]	eta 0:00:16 lr 0.003904	time 0.8135 (0.7470)	model_time 0.8133 (0.7415)	loss 3.9043 (3.8771)	grad_norm 0.9440 (1.3625/0.5799)	mem 34602MB
[2025-01-19 01:57:15 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][300/312]	eta 0:00:08 lr 0.003903	time 0.7256 (0.7477)	model_time 0.7255 (0.7423)	loss 3.3832 (3.8715)	grad_norm 1.8978 (1.3659/0.5799)	mem 34602MB
[2025-01-19 01:57:22 internimage_b_1k_224] (main.py 510): INFO Train: [29/300][310/312]	eta 0:00:01 lr 0.003903	time 0.7152 (0.7471)	model_time 0.7151 (0.7419)	loss 4.4149 (3.8757)	grad_norm 1.0332 (1.3512/0.5813)	mem 34602MB
[2025-01-19 01:57:23 internimage_b_1k_224] (main.py 519): INFO EPOCH 29 training takes 0:03:53
[2025-01-19 01:57:23 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_29.pth saving......
[2025-01-19 01:57:26 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_29.pth saved !!!
[2025-01-19 01:57:33 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.270 (7.270)	Loss 1.0821 (1.0821)	Acc@1 76.514 (76.514)	Acc@5 93.701 (93.701)	Mem 34602MB
[2025-01-19 01:57:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.927)	Loss 1.5946 (1.3212)	Acc@1 66.187 (71.123)	Acc@5 87.280 (90.809)	Mem 34602MB
[2025-01-19 01:57:36 internimage_b_1k_224] (main.py 575): INFO [Epoch:29] * Acc@1 71.125 Acc@5 90.837
[2025-01-19 01:57:36 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 71.1%
[2025-01-19 01:57:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 01:57:40 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 01:57:40 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 71.13%
[2025-01-19 01:57:47 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.600 (7.600)	Loss 6.1936 (6.1936)	Acc@1 1.465 (1.465)	Acc@5 7.910 (7.910)	Mem 34602MB
[2025-01-19 01:57:50 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.978)	Loss 6.5504 (6.2928)	Acc@1 0.732 (1.549)	Acc@5 3.735 (6.248)	Mem 34602MB
[2025-01-19 01:57:51 internimage_b_1k_224] (main.py 575): INFO [Epoch:29] * Acc@1 1.983 Acc@5 7.520
[2025-01-19 01:57:51 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 2.0%
[2025-01-19 01:57:51 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:57:55 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:57:55 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 1.98%
[2025-01-19 01:57:57 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][0/312]	eta 0:11:26 lr 0.003903	time 2.2002 (2.2002)	model_time 0.7740 (0.7740)	loss 4.6771 (4.6771)	grad_norm 0.7888 (0.7888/0.0000)	mem 34602MB
[2025-01-19 01:58:04 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][10/312]	eta 0:04:21 lr 0.003903	time 0.7262 (0.8675)	model_time 0.7260 (0.7375)	loss 3.9524 (4.1458)	grad_norm 4.1684 (1.8449/1.1765)	mem 34602MB
[2025-01-19 01:58:11 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][20/312]	eta 0:03:54 lr 0.003903	time 0.7336 (0.8016)	model_time 0.7334 (0.7334)	loss 4.8608 (4.0065)	grad_norm 1.0075 (1.4783/1.0060)	mem 34602MB
[2025-01-19 01:58:19 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][30/312]	eta 0:03:40 lr 0.003902	time 0.7231 (0.7807)	model_time 0.7226 (0.7343)	loss 4.5021 (4.0259)	grad_norm 0.9194 (1.4633/0.8878)	mem 34602MB
[2025-01-19 01:58:26 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][40/312]	eta 0:03:28 lr 0.003902	time 0.7172 (0.7671)	model_time 0.7171 (0.7320)	loss 3.9713 (3.9673)	grad_norm 1.7047 (1.4138/0.7884)	mem 34602MB
[2025-01-19 01:58:33 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][50/312]	eta 0:03:19 lr 0.003902	time 0.7180 (0.7600)	model_time 0.7178 (0.7317)	loss 4.2433 (3.9962)	grad_norm 0.9237 (1.3755/0.7410)	mem 34602MB
[2025-01-19 01:58:41 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][60/312]	eta 0:03:10 lr 0.003902	time 0.7182 (0.7566)	model_time 0.7181 (0.7329)	loss 4.3376 (4.0215)	grad_norm 1.0904 (1.3372/0.7040)	mem 34602MB
[2025-01-19 01:58:48 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][70/312]	eta 0:03:02 lr 0.003902	time 0.7219 (0.7523)	model_time 0.7218 (0.7319)	loss 4.1359 (4.0331)	grad_norm 1.1583 (1.3702/0.7012)	mem 34602MB
[2025-01-19 01:58:55 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][80/312]	eta 0:02:53 lr 0.003901	time 0.7825 (0.7496)	model_time 0.7821 (0.7316)	loss 4.4596 (4.0138)	grad_norm 1.8067 (1.3352/0.6719)	mem 34602MB
[2025-01-19 01:59:03 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][90/312]	eta 0:02:46 lr 0.003901	time 0.7217 (0.7500)	model_time 0.7215 (0.7340)	loss 3.7146 (4.0168)	grad_norm 0.8721 (1.3291/0.6435)	mem 34602MB
[2025-01-19 01:59:11 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][100/312]	eta 0:02:39 lr 0.003901	time 0.8239 (0.7534)	model_time 0.8237 (0.7389)	loss 3.2889 (3.9858)	grad_norm 1.8672 (1.3378/0.6173)	mem 34602MB
[2025-01-19 01:59:18 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][110/312]	eta 0:02:32 lr 0.003901	time 0.7988 (0.7547)	model_time 0.7986 (0.7415)	loss 4.1868 (3.9894)	grad_norm 0.8661 (1.3368/0.6019)	mem 34602MB
[2025-01-19 01:59:26 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][120/312]	eta 0:02:24 lr 0.003901	time 0.7969 (0.7538)	model_time 0.7967 (0.7417)	loss 4.1056 (4.0005)	grad_norm 1.0485 (1.3394/0.5862)	mem 34602MB
[2025-01-19 01:59:33 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][130/312]	eta 0:02:16 lr 0.003900	time 0.7153 (0.7524)	model_time 0.7152 (0.7411)	loss 2.9010 (3.9967)	grad_norm 0.9195 (1.3339/0.5697)	mem 34602MB
[2025-01-19 01:59:40 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][140/312]	eta 0:02:09 lr 0.003900	time 0.7194 (0.7510)	model_time 0.7189 (0.7406)	loss 3.6572 (3.9931)	grad_norm 0.8552 (1.3204/0.5558)	mem 34602MB
[2025-01-19 01:59:48 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][150/312]	eta 0:02:01 lr 0.003900	time 0.7415 (0.7495)	model_time 0.7411 (0.7397)	loss 3.6833 (3.9466)	grad_norm 2.2451 (1.3329/0.5504)	mem 34602MB
[2025-01-19 01:59:55 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][160/312]	eta 0:01:53 lr 0.003900	time 0.7358 (0.7480)	model_time 0.7356 (0.7388)	loss 4.1465 (3.9379)	grad_norm 0.6783 (1.3405/0.5502)	mem 34602MB
[2025-01-19 02:00:02 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][170/312]	eta 0:01:46 lr 0.003900	time 0.7371 (0.7468)	model_time 0.7369 (0.7381)	loss 4.0779 (3.9374)	grad_norm 0.9523 (1.3405/0.5421)	mem 34602MB
[2025-01-19 02:00:10 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][180/312]	eta 0:01:38 lr 0.003899	time 0.7392 (0.7460)	model_time 0.7390 (0.7378)	loss 4.2719 (3.9495)	grad_norm 1.3930 (1.3339/0.5333)	mem 34602MB
[2025-01-19 02:00:17 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][190/312]	eta 0:01:30 lr 0.003899	time 0.7144 (0.7448)	model_time 0.7142 (0.7370)	loss 4.3853 (3.9406)	grad_norm 1.1798 (1.3377/0.5309)	mem 34602MB
[2025-01-19 02:00:24 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][200/312]	eta 0:01:23 lr 0.003899	time 0.7948 (0.7445)	model_time 0.7946 (0.7371)	loss 2.6547 (3.9407)	grad_norm 1.1205 (1.3602/0.5487)	mem 34602MB
[2025-01-19 02:00:32 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][210/312]	eta 0:01:15 lr 0.003899	time 0.7175 (0.7446)	model_time 0.7174 (0.7375)	loss 3.6141 (3.9427)	grad_norm 0.8527 (1.3592/0.5500)	mem 34602MB
[2025-01-19 02:00:39 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][220/312]	eta 0:01:08 lr 0.003899	time 0.8086 (0.7459)	model_time 0.8084 (0.7391)	loss 3.2640 (3.9367)	grad_norm 0.9651 (1.3410/0.5446)	mem 34602MB
[2025-01-19 02:00:47 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][230/312]	eta 0:01:01 lr 0.003898	time 0.7950 (0.7475)	model_time 0.7945 (0.7410)	loss 4.3049 (3.9370)	grad_norm 1.5607 (1.3314/0.5379)	mem 34602MB
[2025-01-19 02:00:55 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][240/312]	eta 0:00:53 lr 0.003898	time 0.7988 (0.7469)	model_time 0.7984 (0.7407)	loss 4.5725 (3.9314)	grad_norm 1.5353 (1.3557/0.5730)	mem 34602MB
[2025-01-19 02:01:02 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][250/312]	eta 0:00:46 lr 0.003898	time 0.7140 (0.7468)	model_time 0.7135 (0.7407)	loss 4.4520 (3.9326)	grad_norm 1.1046 (1.3485/0.5638)	mem 34602MB
[2025-01-19 02:01:09 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][260/312]	eta 0:00:38 lr 0.003898	time 0.7392 (0.7462)	model_time 0.7390 (0.7404)	loss 4.3009 (3.9254)	grad_norm 1.0624 (1.3440/0.5558)	mem 34602MB
[2025-01-19 02:01:17 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][270/312]	eta 0:00:31 lr 0.003897	time 0.7196 (0.7455)	model_time 0.7191 (0.7399)	loss 4.1578 (3.9299)	grad_norm 2.9509 (1.3459/0.5692)	mem 34602MB
[2025-01-19 02:01:24 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][280/312]	eta 0:00:23 lr 0.003897	time 0.7213 (0.7447)	model_time 0.7212 (0.7393)	loss 3.2218 (3.9138)	grad_norm 2.4512 (1.3545/0.5675)	mem 34602MB
[2025-01-19 02:01:31 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][290/312]	eta 0:00:16 lr 0.003897	time 0.7379 (0.7441)	model_time 0.7378 (0.7388)	loss 4.2155 (3.9144)	grad_norm 1.9557 (1.3735/0.5792)	mem 34602MB
[2025-01-19 02:01:38 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][300/312]	eta 0:00:08 lr 0.003897	time 0.7106 (0.7436)	model_time 0.7105 (0.7385)	loss 4.6795 (3.9219)	grad_norm 1.2371 (1.3642/0.5749)	mem 34602MB
[2025-01-19 02:01:46 internimage_b_1k_224] (main.py 510): INFO Train: [30/300][310/312]	eta 0:00:01 lr 0.003897	time 0.7143 (0.7427)	model_time 0.7142 (0.7378)	loss 4.1761 (3.9321)	grad_norm 1.0325 (1.3507/0.5506)	mem 34602MB
[2025-01-19 02:01:46 internimage_b_1k_224] (main.py 519): INFO EPOCH 30 training takes 0:03:51
[2025-01-19 02:01:46 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_30.pth saving......
[2025-01-19 02:01:49 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_30.pth saved !!!
[2025-01-19 02:01:57 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.471 (7.471)	Loss 1.0376 (1.0376)	Acc@1 75.806 (75.806)	Acc@5 93.701 (93.701)	Mem 34602MB
[2025-01-19 02:02:00 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.948)	Loss 1.5719 (1.2914)	Acc@1 63.965 (71.043)	Acc@5 86.914 (90.798)	Mem 34602MB
[2025-01-19 02:02:00 internimage_b_1k_224] (main.py 575): INFO [Epoch:30] * Acc@1 71.131 Acc@5 90.991
[2025-01-19 02:02:00 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 71.1%
[2025-01-19 02:02:00 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 02:02:03 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 02:02:03 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 71.13%
[2025-01-19 02:02:11 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.467 (7.467)	Loss 6.0856 (6.0856)	Acc@1 1.733 (1.733)	Acc@5 9.082 (9.082)	Mem 34602MB
[2025-01-19 02:02:14 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.964)	Loss 6.3869 (6.1558)	Acc@1 1.074 (2.002)	Acc@5 5.737 (7.921)	Mem 34602MB
[2025-01-19 02:02:14 internimage_b_1k_224] (main.py 575): INFO [Epoch:30] * Acc@1 2.483 Acc@5 9.277
[2025-01-19 02:02:14 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 2.5%
[2025-01-19 02:02:14 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:02:18 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:02:18 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 2.48%
[2025-01-19 02:02:20 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][0/312]	eta 0:10:49 lr 0.003897	time 2.0822 (2.0822)	model_time 0.7406 (0.7406)	loss 3.3875 (3.3875)	grad_norm 1.3083 (1.3083/0.0000)	mem 34602MB
[2025-01-19 02:02:28 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][10/312]	eta 0:04:18 lr 0.003896	time 0.7177 (0.8562)	model_time 0.7175 (0.7340)	loss 4.3593 (3.9948)	grad_norm 0.7739 (1.0545/0.2177)	mem 34602MB
[2025-01-19 02:02:35 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][20/312]	eta 0:03:54 lr 0.003896	time 0.7222 (0.8032)	model_time 0.7221 (0.7390)	loss 3.9828 (3.9526)	grad_norm 0.8227 (1.2481/0.4686)	mem 34602MB
[2025-01-19 02:02:43 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][30/312]	eta 0:03:44 lr 0.003896	time 0.8029 (0.7977)	model_time 0.8027 (0.7542)	loss 3.8549 (3.9817)	grad_norm 1.4979 (1.2110/0.4148)	mem 34602MB
[2025-01-19 02:02:51 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][40/312]	eta 0:03:35 lr 0.003896	time 0.7958 (0.7924)	model_time 0.7953 (0.7594)	loss 4.0520 (4.0102)	grad_norm 2.7363 (1.3672/0.5586)	mem 34602MB
[2025-01-19 02:02:58 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][50/312]	eta 0:03:24 lr 0.003896	time 0.7185 (0.7808)	model_time 0.7181 (0.7541)	loss 4.2998 (3.9260)	grad_norm 0.7798 (1.3911/0.6143)	mem 34602MB
[2025-01-19 02:03:06 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][60/312]	eta 0:03:15 lr 0.003895	time 0.7171 (0.7745)	model_time 0.7169 (0.7521)	loss 4.0394 (3.9440)	grad_norm 0.7503 (1.3304/0.5940)	mem 34602MB
[2025-01-19 02:03:13 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][70/312]	eta 0:03:05 lr 0.003895	time 0.7173 (0.7677)	model_time 0.7169 (0.7485)	loss 3.4375 (3.9313)	grad_norm 1.6382 (1.3473/0.6019)	mem 34602MB
[2025-01-19 02:03:20 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][80/312]	eta 0:02:56 lr 0.003895	time 0.7369 (0.7623)	model_time 0.7367 (0.7453)	loss 2.6349 (3.9010)	grad_norm 0.9349 (1.3148/0.5766)	mem 34602MB
[2025-01-19 02:03:27 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][90/312]	eta 0:02:48 lr 0.003895	time 0.7199 (0.7581)	model_time 0.7197 (0.7430)	loss 4.1950 (3.9033)	grad_norm 1.2520 (1.2946/0.5569)	mem 34602MB
[2025-01-19 02:03:35 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][100/312]	eta 0:02:40 lr 0.003894	time 0.7214 (0.7553)	model_time 0.7209 (0.7417)	loss 4.0454 (3.8772)	grad_norm 1.1926 (1.3288/0.5704)	mem 34602MB
[2025-01-19 02:03:42 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][110/312]	eta 0:02:32 lr 0.003894	time 0.7225 (0.7529)	model_time 0.7224 (0.7404)	loss 4.0776 (3.8759)	grad_norm 0.9541 (1.3301/0.5536)	mem 34602MB
[2025-01-19 02:03:49 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][120/312]	eta 0:02:24 lr 0.003894	time 0.7177 (0.7506)	model_time 0.7172 (0.7391)	loss 3.2921 (3.8861)	grad_norm 1.0867 (1.3363/0.5491)	mem 34602MB
[2025-01-19 02:03:56 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][130/312]	eta 0:02:16 lr 0.003894	time 0.7179 (0.7492)	model_time 0.7178 (0.7386)	loss 2.6947 (3.8798)	grad_norm 0.8588 (1.3668/0.6101)	mem 34602MB
[2025-01-19 02:04:04 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][140/312]	eta 0:02:08 lr 0.003894	time 0.7305 (0.7488)	model_time 0.7301 (0.7389)	loss 2.7132 (3.8665)	grad_norm 2.0721 (1.3559/0.5975)	mem 34602MB
[2025-01-19 02:04:12 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][150/312]	eta 0:02:01 lr 0.003893	time 0.7982 (0.7515)	model_time 0.7977 (0.7422)	loss 3.2213 (3.8713)	grad_norm 0.6320 (1.3315/0.5875)	mem 34602MB
[2025-01-19 02:04:20 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][160/312]	eta 0:01:54 lr 0.003893	time 0.7100 (0.7527)	model_time 0.7098 (0.7440)	loss 4.2337 (3.8672)	grad_norm 1.6205 (1.3221/0.5795)	mem 34602MB
[2025-01-19 02:04:27 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][170/312]	eta 0:01:46 lr 0.003893	time 0.7171 (0.7522)	model_time 0.7169 (0.7440)	loss 3.4972 (3.8685)	grad_norm 1.6977 (1.3648/0.6336)	mem 34602MB
[2025-01-19 02:04:34 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][180/312]	eta 0:01:39 lr 0.003893	time 0.7291 (0.7514)	model_time 0.7289 (0.7436)	loss 3.0730 (3.8536)	grad_norm 1.1207 (1.3658/0.6313)	mem 34602MB
[2025-01-19 02:04:42 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][190/312]	eta 0:01:31 lr 0.003893	time 0.7278 (0.7501)	model_time 0.7276 (0.7427)	loss 4.0442 (3.8491)	grad_norm 0.9623 (1.3555/0.6222)	mem 34602MB
[2025-01-19 02:04:49 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][200/312]	eta 0:01:23 lr 0.003892	time 0.7181 (0.7492)	model_time 0.7179 (0.7422)	loss 2.8669 (3.8472)	grad_norm 1.0920 (1.3324/0.6159)	mem 34602MB
[2025-01-19 02:04:56 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][210/312]	eta 0:01:16 lr 0.003892	time 0.7158 (0.7481)	model_time 0.7157 (0.7413)	loss 4.2160 (3.8529)	grad_norm 2.6455 (1.3340/0.6134)	mem 34602MB
[2025-01-19 02:05:04 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][220/312]	eta 0:01:08 lr 0.003892	time 0.7316 (0.7477)	model_time 0.7314 (0.7412)	loss 3.4282 (3.8616)	grad_norm 1.3418 (1.3336/0.6007)	mem 34602MB
[2025-01-19 02:05:11 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][230/312]	eta 0:01:01 lr 0.003892	time 0.7455 (0.7470)	model_time 0.7453 (0.7408)	loss 3.7747 (3.8542)	grad_norm 1.2683 (1.3473/0.5955)	mem 34602MB
[2025-01-19 02:05:18 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][240/312]	eta 0:00:53 lr 0.003891	time 0.7174 (0.7462)	model_time 0.7172 (0.7403)	loss 4.7125 (3.8582)	grad_norm 0.6853 (1.3328/0.5886)	mem 34602MB
[2025-01-19 02:05:26 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][250/312]	eta 0:00:46 lr 0.003891	time 0.7203 (0.7457)	model_time 0.7201 (0.7400)	loss 4.1711 (3.8595)	grad_norm 0.9466 (1.3256/0.5813)	mem 34602MB
[2025-01-19 02:05:33 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][260/312]	eta 0:00:38 lr 0.003891	time 0.8269 (0.7468)	model_time 0.8267 (0.7413)	loss 4.1554 (3.8627)	grad_norm 1.8443 (1.3347/0.5789)	mem 34602MB
[2025-01-19 02:05:41 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][270/312]	eta 0:00:31 lr 0.003891	time 0.8218 (0.7481)	model_time 0.8213 (0.7427)	loss 3.7812 (3.8634)	grad_norm 0.9683 (1.3475/0.5885)	mem 34602MB
[2025-01-19 02:05:49 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][280/312]	eta 0:00:24 lr 0.003891	time 0.7160 (0.7510)	model_time 0.7155 (0.7459)	loss 4.1928 (3.8625)	grad_norm 2.1352 (1.3435/0.5853)	mem 34602MB
[2025-01-19 02:05:57 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][290/312]	eta 0:00:16 lr 0.003890	time 0.7180 (0.7509)	model_time 0.7178 (0.7459)	loss 3.7358 (3.8548)	grad_norm 0.8991 (1.3345/0.5787)	mem 34602MB
[2025-01-19 02:06:04 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][300/312]	eta 0:00:09 lr 0.003890	time 0.7171 (0.7506)	model_time 0.7170 (0.7458)	loss 2.4760 (3.8564)	grad_norm 0.8432 (1.3213/0.5754)	mem 34602MB
[2025-01-19 02:06:11 internimage_b_1k_224] (main.py 510): INFO Train: [31/300][310/312]	eta 0:00:01 lr 0.003890	time 0.7067 (0.7495)	model_time 0.7065 (0.7448)	loss 4.1611 (3.8653)	grad_norm 1.0413 (1.3324/0.5780)	mem 34602MB
[2025-01-19 02:06:12 internimage_b_1k_224] (main.py 519): INFO EPOCH 31 training takes 0:03:53
[2025-01-19 02:06:12 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_31.pth saving......
[2025-01-19 02:06:16 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_31.pth saved !!!
[2025-01-19 02:06:23 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.441 (7.441)	Loss 1.0691 (1.0691)	Acc@1 75.439 (75.439)	Acc@5 93.872 (93.872)	Mem 34602MB
[2025-01-19 02:06:26 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.930)	Loss 1.6071 (1.2946)	Acc@1 64.209 (71.504)	Acc@5 87.085 (90.927)	Mem 34602MB
[2025-01-19 02:06:26 internimage_b_1k_224] (main.py 575): INFO [Epoch:31] * Acc@1 71.521 Acc@5 91.039
[2025-01-19 02:06:26 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 71.5%
[2025-01-19 02:06:26 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 02:06:29 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 02:06:30 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 71.52%
[2025-01-19 02:06:37 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.568 (7.568)	Loss 5.9605 (5.9605)	Acc@1 2.393 (2.393)	Acc@5 11.426 (11.426)	Mem 34602MB
[2025-01-19 02:06:40 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.953)	Loss 6.1997 (5.9909)	Acc@1 1.782 (2.863)	Acc@5 7.642 (10.316)	Mem 34602MB
[2025-01-19 02:06:40 internimage_b_1k_224] (main.py 575): INFO [Epoch:31] * Acc@1 3.375 Acc@5 11.764
[2025-01-19 02:06:40 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 3.4%
[2025-01-19 02:06:40 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:06:44 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:06:44 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 3.37%
[2025-01-19 02:06:46 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][0/312]	eta 0:10:19 lr 0.003890	time 1.9840 (1.9840)	model_time 0.7325 (0.7325)	loss 3.1588 (3.1588)	grad_norm 2.5185 (2.5185/0.0000)	mem 34602MB
[2025-01-19 02:06:53 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][10/312]	eta 0:04:15 lr 0.003890	time 0.7217 (0.8444)	model_time 0.7216 (0.7303)	loss 3.2608 (3.6827)	grad_norm 0.9058 (1.4503/0.4887)	mem 34602MB
[2025-01-19 02:07:01 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][20/312]	eta 0:03:51 lr 0.003889	time 0.7094 (0.7939)	model_time 0.7090 (0.7339)	loss 4.6478 (3.7801)	grad_norm 1.1301 (1.3077/0.4489)	mem 34602MB
[2025-01-19 02:07:08 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][30/312]	eta 0:03:38 lr 0.003889	time 0.7531 (0.7735)	model_time 0.7527 (0.7328)	loss 3.9666 (3.8623)	grad_norm 0.9796 (1.2933/0.4331)	mem 34602MB
[2025-01-19 02:07:15 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][40/312]	eta 0:03:27 lr 0.003889	time 0.7226 (0.7614)	model_time 0.7224 (0.7305)	loss 4.0835 (3.8821)	grad_norm 0.9071 (1.5043/0.7695)	mem 34602MB
[2025-01-19 02:07:23 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][50/312]	eta 0:03:17 lr 0.003889	time 0.7528 (0.7556)	model_time 0.7527 (0.7307)	loss 4.0896 (3.9271)	grad_norm 0.9360 (1.4521/0.7316)	mem 34602MB
[2025-01-19 02:07:30 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][60/312]	eta 0:03:09 lr 0.003889	time 0.7198 (0.7527)	model_time 0.7193 (0.7318)	loss 3.4765 (3.9323)	grad_norm 0.7323 (1.3626/0.7016)	mem 34602MB
[2025-01-19 02:07:37 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][70/312]	eta 0:03:01 lr 0.003888	time 0.7485 (0.7508)	model_time 0.7484 (0.7328)	loss 4.8326 (3.9255)	grad_norm 1.2062 (1.3207/0.6623)	mem 34602MB
[2025-01-19 02:07:45 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][80/312]	eta 0:02:55 lr 0.003888	time 0.9408 (0.7562)	model_time 0.9405 (0.7404)	loss 4.2864 (3.9504)	grad_norm 1.1849 (1.3141/0.6317)	mem 34602MB
[2025-01-19 02:07:53 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][90/312]	eta 0:02:48 lr 0.003888	time 0.7186 (0.7605)	model_time 0.7184 (0.7464)	loss 4.7595 (3.9493)	grad_norm 1.8268 (1.3497/0.6274)	mem 34602MB
[2025-01-19 02:08:01 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][100/312]	eta 0:02:40 lr 0.003888	time 0.7229 (0.7587)	model_time 0.7227 (0.7459)	loss 3.4989 (3.9581)	grad_norm 1.0882 (1.3430/0.6181)	mem 34602MB
[2025-01-19 02:08:08 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][110/312]	eta 0:02:32 lr 0.003887	time 0.7230 (0.7560)	model_time 0.7225 (0.7443)	loss 4.6723 (3.9531)	grad_norm 1.6453 (1.3415/0.6065)	mem 34602MB
[2025-01-19 02:08:15 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][120/312]	eta 0:02:24 lr 0.003887	time 0.7297 (0.7536)	model_time 0.7295 (0.7429)	loss 4.2443 (3.9313)	grad_norm 1.5177 (1.3508/0.6385)	mem 34602MB
[2025-01-19 02:08:23 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][130/312]	eta 0:02:16 lr 0.003887	time 0.7159 (0.7511)	model_time 0.7154 (0.7411)	loss 4.2243 (3.9465)	grad_norm 2.4614 (1.3836/0.6698)	mem 34602MB
[2025-01-19 02:08:30 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][140/312]	eta 0:02:09 lr 0.003887	time 0.7387 (0.7500)	model_time 0.7385 (0.7408)	loss 4.2857 (3.9413)	grad_norm 0.8889 (1.3632/0.6543)	mem 34602MB
[2025-01-19 02:08:37 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][150/312]	eta 0:02:01 lr 0.003887	time 0.7148 (0.7482)	model_time 0.7146 (0.7395)	loss 3.9754 (3.9292)	grad_norm 1.4702 (1.3458/0.6384)	mem 34602MB
[2025-01-19 02:08:44 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][160/312]	eta 0:01:53 lr 0.003886	time 0.7237 (0.7468)	model_time 0.7236 (0.7387)	loss 4.5503 (3.9213)	grad_norm 1.2799 (1.3267/0.6277)	mem 34602MB
[2025-01-19 02:08:52 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][170/312]	eta 0:01:45 lr 0.003886	time 0.7309 (0.7454)	model_time 0.7308 (0.7377)	loss 2.9857 (3.9127)	grad_norm 1.3080 (1.3349/0.6230)	mem 34602MB
[2025-01-19 02:08:59 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][180/312]	eta 0:01:38 lr 0.003886	time 0.7233 (0.7447)	model_time 0.7231 (0.7374)	loss 4.0979 (3.8978)	grad_norm 0.6768 (1.3159/0.6156)	mem 34602MB
[2025-01-19 02:09:06 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][190/312]	eta 0:01:30 lr 0.003886	time 0.7223 (0.7445)	model_time 0.7222 (0.7375)	loss 4.8845 (3.9128)	grad_norm 1.1215 (1.3058/0.6047)	mem 34602MB
[2025-01-19 02:09:14 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][200/312]	eta 0:01:23 lr 0.003885	time 0.8207 (0.7465)	model_time 0.8205 (0.7399)	loss 4.3681 (3.9106)	grad_norm 1.0042 (1.3022/0.5954)	mem 34602MB
[2025-01-19 02:09:22 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][210/312]	eta 0:01:16 lr 0.003885	time 0.7995 (0.7493)	model_time 0.7994 (0.7430)	loss 3.3107 (3.9122)	grad_norm 1.3557 (1.2901/0.5858)	mem 34602MB
[2025-01-19 02:09:30 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][220/312]	eta 0:01:08 lr 0.003885	time 0.7171 (0.7491)	model_time 0.7169 (0.7431)	loss 3.5360 (3.9184)	grad_norm 1.5906 (1.2968/0.5758)	mem 34602MB
[2025-01-19 02:09:37 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][230/312]	eta 0:01:01 lr 0.003885	time 0.7154 (0.7485)	model_time 0.7149 (0.7427)	loss 3.1294 (3.9122)	grad_norm 2.6784 (1.3072/0.5847)	mem 34602MB
[2025-01-19 02:09:44 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][240/312]	eta 0:00:53 lr 0.003885	time 0.7080 (0.7476)	model_time 0.7078 (0.7420)	loss 3.8287 (3.9026)	grad_norm 1.3350 (1.3071/0.5788)	mem 34602MB
[2025-01-19 02:09:52 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][250/312]	eta 0:00:46 lr 0.003884	time 0.7227 (0.7468)	model_time 0.7225 (0.7414)	loss 4.0960 (3.8927)	grad_norm 3.3886 (1.3393/0.6111)	mem 34602MB
[2025-01-19 02:09:59 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][260/312]	eta 0:00:38 lr 0.003884	time 0.7159 (0.7462)	model_time 0.7155 (0.7410)	loss 4.4495 (3.8940)	grad_norm 0.5628 (1.3326/0.6057)	mem 34602MB
[2025-01-19 02:10:06 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][270/312]	eta 0:00:31 lr 0.003884	time 0.7295 (0.7457)	model_time 0.7291 (0.7407)	loss 4.1761 (3.9118)	grad_norm 0.6632 (1.3195/0.5996)	mem 34602MB
[2025-01-19 02:10:13 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][280/312]	eta 0:00:23 lr 0.003884	time 0.7120 (0.7447)	model_time 0.7118 (0.7399)	loss 4.7779 (3.9206)	grad_norm 2.2470 (1.3199/0.6103)	mem 34602MB
[2025-01-19 02:10:21 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][290/312]	eta 0:00:16 lr 0.003883	time 0.7313 (0.7442)	model_time 0.7309 (0.7395)	loss 3.2725 (3.9054)	grad_norm 1.6096 (1.3231/0.6137)	mem 34602MB
[2025-01-19 02:10:28 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][300/312]	eta 0:00:08 lr 0.003883	time 0.7120 (0.7436)	model_time 0.7119 (0.7391)	loss 4.1251 (3.9090)	grad_norm 0.6491 (1.3132/0.6052)	mem 34602MB
[2025-01-19 02:10:35 internimage_b_1k_224] (main.py 510): INFO Train: [32/300][310/312]	eta 0:00:01 lr 0.003883	time 0.7307 (0.7432)	model_time 0.7306 (0.7388)	loss 3.2655 (3.9058)	grad_norm 1.0105 (1.3063/0.6037)	mem 34602MB
[2025-01-19 02:10:36 internimage_b_1k_224] (main.py 519): INFO EPOCH 32 training takes 0:03:51
[2025-01-19 02:10:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_32.pth saving......
[2025-01-19 02:10:39 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_32.pth saved !!!
[2025-01-19 02:10:47 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.475 (7.475)	Loss 1.0708 (1.0708)	Acc@1 75.464 (75.464)	Acc@5 93.701 (93.701)	Mem 34602MB
[2025-01-19 02:10:50 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.948)	Loss 1.5672 (1.2950)	Acc@1 65.771 (71.442)	Acc@5 87.695 (91.109)	Mem 34602MB
[2025-01-19 02:10:50 internimage_b_1k_224] (main.py 575): INFO [Epoch:32] * Acc@1 71.521 Acc@5 91.245
[2025-01-19 02:10:50 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 71.5%
[2025-01-19 02:10:50 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 71.52%
[2025-01-19 02:10:59 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.313 (9.313)	Loss 5.8155 (5.8155)	Acc@1 3.320 (3.320)	Acc@5 13.721 (13.721)	Mem 34602MB
[2025-01-19 02:11:04 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.259)	Loss 6.0021 (5.8096)	Acc@1 2.783 (3.973)	Acc@5 10.498 (13.201)	Mem 34602MB
[2025-01-19 02:11:04 internimage_b_1k_224] (main.py 575): INFO [Epoch:32] * Acc@1 4.501 Acc@5 14.731
[2025-01-19 02:11:04 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 4.5%
[2025-01-19 02:11:04 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:11:08 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:11:08 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 4.50%
[2025-01-19 02:11:11 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][0/312]	eta 0:11:03 lr 0.003883	time 2.1256 (2.1256)	model_time 0.7481 (0.7481)	loss 3.8412 (3.8412)	grad_norm 1.4796 (1.4796/0.0000)	mem 34602MB
[2025-01-19 02:11:19 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][10/312]	eta 0:04:48 lr 0.003883	time 0.8121 (0.9539)	model_time 0.8119 (0.8283)	loss 4.8476 (4.2344)	grad_norm 0.8865 (1.2845/0.3143)	mem 34602MB
[2025-01-19 02:11:27 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][20/312]	eta 0:04:12 lr 0.003882	time 0.7986 (0.8657)	model_time 0.7981 (0.7998)	loss 3.9990 (3.8667)	grad_norm 2.3060 (1.3568/0.4122)	mem 34602MB
[2025-01-19 02:11:34 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][30/312]	eta 0:03:54 lr 0.003882	time 0.8173 (0.8303)	model_time 0.8172 (0.7855)	loss 4.0688 (3.8206)	grad_norm 1.5094 (1.3576/0.4008)	mem 34602MB
[2025-01-19 02:11:42 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][40/312]	eta 0:03:39 lr 0.003882	time 0.7166 (0.8072)	model_time 0.7163 (0.7733)	loss 4.1715 (3.8318)	grad_norm 1.0952 (1.3031/0.3931)	mem 34602MB
[2025-01-19 02:11:49 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][50/312]	eta 0:03:27 lr 0.003882	time 0.7272 (0.7912)	model_time 0.7270 (0.7638)	loss 3.7177 (3.8615)	grad_norm 0.9213 (1.2881/0.3687)	mem 34602MB
[2025-01-19 02:11:56 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][60/312]	eta 0:03:16 lr 0.003882	time 0.7305 (0.7807)	model_time 0.7300 (0.7578)	loss 4.2042 (3.8719)	grad_norm 1.1277 (1.2941/0.3892)	mem 34602MB
[2025-01-19 02:12:03 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][70/312]	eta 0:03:07 lr 0.003881	time 0.7110 (0.7733)	model_time 0.7108 (0.7535)	loss 4.7805 (3.8758)	grad_norm 1.3665 (1.3034/0.3831)	mem 34602MB
[2025-01-19 02:12:11 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][80/312]	eta 0:02:57 lr 0.003881	time 0.7162 (0.7667)	model_time 0.7153 (0.7494)	loss 3.4276 (3.8367)	grad_norm 1.4402 (1.2748/0.3817)	mem 34602MB
[2025-01-19 02:12:18 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][90/312]	eta 0:02:49 lr 0.003881	time 0.7287 (0.7624)	model_time 0.7286 (0.7469)	loss 2.9975 (3.8118)	grad_norm 2.8540 (1.3392/0.4929)	mem 34602MB
[2025-01-19 02:12:25 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][100/312]	eta 0:02:40 lr 0.003881	time 0.7296 (0.7586)	model_time 0.7294 (0.7446)	loss 3.3574 (3.8365)	grad_norm 1.3426 (1.3788/0.5222)	mem 34602MB
[2025-01-19 02:12:32 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][110/312]	eta 0:02:32 lr 0.003880	time 0.7166 (0.7563)	model_time 0.7161 (0.7435)	loss 3.3892 (3.8148)	grad_norm 0.6857 (1.3524/0.5196)	mem 34602MB
[2025-01-19 02:12:40 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][120/312]	eta 0:02:25 lr 0.003880	time 0.7092 (0.7558)	model_time 0.7090 (0.7440)	loss 3.4802 (3.8292)	grad_norm 1.8392 (1.3415/0.5107)	mem 34602MB
[2025-01-19 02:12:48 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][130/312]	eta 0:02:18 lr 0.003880	time 0.8003 (0.7587)	model_time 0.8001 (0.7479)	loss 3.6256 (3.8189)	grad_norm 1.2636 (1.3372/0.5070)	mem 34602MB
[2025-01-19 02:12:56 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][140/312]	eta 0:02:10 lr 0.003880	time 0.8270 (0.7598)	model_time 0.8266 (0.7496)	loss 3.4949 (3.8083)	grad_norm 1.3628 (1.3328/0.4984)	mem 34602MB
[2025-01-19 02:13:03 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][150/312]	eta 0:02:02 lr 0.003880	time 0.8006 (0.7582)	model_time 0.8002 (0.7488)	loss 3.9175 (3.8113)	grad_norm 1.0063 (1.3249/0.4957)	mem 34602MB
[2025-01-19 02:13:10 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][160/312]	eta 0:01:55 lr 0.003879	time 0.7504 (0.7570)	model_time 0.7502 (0.7481)	loss 2.7096 (3.8112)	grad_norm 0.8777 (1.3191/0.4948)	mem 34602MB
[2025-01-19 02:13:18 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][170/312]	eta 0:01:47 lr 0.003879	time 0.7298 (0.7551)	model_time 0.7296 (0.7467)	loss 4.2145 (3.7999)	grad_norm 0.8434 (1.3019/0.4873)	mem 34602MB
[2025-01-19 02:13:25 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][180/312]	eta 0:01:39 lr 0.003879	time 0.7442 (0.7535)	model_time 0.7437 (0.7455)	loss 3.9989 (3.8178)	grad_norm 1.0206 (1.3205/0.5062)	mem 34602MB
[2025-01-19 02:13:32 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][190/312]	eta 0:01:31 lr 0.003879	time 0.7128 (0.7519)	model_time 0.7127 (0.7444)	loss 4.1813 (3.8227)	grad_norm 1.1516 (1.3294/0.5149)	mem 34602MB
[2025-01-19 02:13:39 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][200/312]	eta 0:01:24 lr 0.003878	time 0.7208 (0.7506)	model_time 0.7204 (0.7434)	loss 3.0792 (3.8163)	grad_norm 1.2241 (1.3297/0.5062)	mem 34602MB
[2025-01-19 02:13:47 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][210/312]	eta 0:01:16 lr 0.003878	time 0.7251 (0.7493)	model_time 0.7246 (0.7425)	loss 3.9865 (3.8338)	grad_norm 2.2019 (1.3333/0.5061)	mem 34602MB
[2025-01-19 02:13:54 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][220/312]	eta 0:01:08 lr 0.003878	time 0.7273 (0.7481)	model_time 0.7271 (0.7415)	loss 3.7413 (3.8389)	grad_norm 1.2505 (1.3238/0.4979)	mem 34602MB
[2025-01-19 02:14:01 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][230/312]	eta 0:01:01 lr 0.003878	time 0.7606 (0.7477)	model_time 0.7601 (0.7413)	loss 3.6304 (3.8340)	grad_norm 0.6599 (1.3133/0.4912)	mem 34602MB
[2025-01-19 02:14:09 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][240/312]	eta 0:00:53 lr 0.003877	time 0.7210 (0.7472)	model_time 0.7208 (0.7412)	loss 4.6106 (3.8375)	grad_norm 0.8236 (1.3242/0.5013)	mem 34602MB
[2025-01-19 02:14:17 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][250/312]	eta 0:00:46 lr 0.003877	time 0.7983 (0.7493)	model_time 0.7978 (0.7435)	loss 3.5120 (3.8331)	grad_norm 1.1232 (1.3129/0.4965)	mem 34602MB
[2025-01-19 02:14:24 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][260/312]	eta 0:00:39 lr 0.003877	time 0.9893 (0.7503)	model_time 0.9891 (0.7446)	loss 3.7996 (3.8401)	grad_norm 1.0799 (1.3085/0.4919)	mem 34602MB
[2025-01-19 02:14:32 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][270/312]	eta 0:00:31 lr 0.003877	time 0.7993 (0.7500)	model_time 0.7991 (0.7446)	loss 2.6411 (3.8196)	grad_norm 0.9877 (1.3013/0.4865)	mem 34602MB
[2025-01-19 02:14:39 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][280/312]	eta 0:00:23 lr 0.003877	time 0.7170 (0.7494)	model_time 0.7166 (0.7441)	loss 3.9461 (3.8222)	grad_norm 1.2278 (1.2892/0.4831)	mem 34602MB
[2025-01-19 02:14:46 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][290/312]	eta 0:00:16 lr 0.003876	time 0.7177 (0.7485)	model_time 0.7176 (0.7434)	loss 3.4757 (3.8260)	grad_norm 2.2652 (1.2918/0.4794)	mem 34602MB
[2025-01-19 02:14:53 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][300/312]	eta 0:00:08 lr 0.003876	time 0.7159 (0.7476)	model_time 0.7158 (0.7427)	loss 2.9501 (3.8155)	grad_norm 0.9172 (1.2972/0.4777)	mem 34602MB
[2025-01-19 02:15:01 internimage_b_1k_224] (main.py 510): INFO Train: [33/300][310/312]	eta 0:00:01 lr 0.003876	time 0.7162 (0.7467)	model_time 0.7160 (0.7420)	loss 4.0976 (3.8121)	grad_norm 1.5008 (1.3047/0.4863)	mem 34602MB
[2025-01-19 02:15:01 internimage_b_1k_224] (main.py 519): INFO EPOCH 33 training takes 0:03:52
[2025-01-19 02:15:01 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_33.pth saving......
[2025-01-19 02:15:05 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_33.pth saved !!!
[2025-01-19 02:15:20 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.532 (15.532)	Loss 1.0017 (1.0017)	Acc@1 77.393 (77.393)	Acc@5 93.970 (93.970)	Mem 34602MB
[2025-01-19 02:15:27 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.052)	Loss 1.5612 (1.2569)	Acc@1 65.234 (72.006)	Acc@5 87.354 (91.120)	Mem 34602MB
[2025-01-19 02:15:28 internimage_b_1k_224] (main.py 575): INFO [Epoch:33] * Acc@1 72.163 Acc@5 91.267
[2025-01-19 02:15:28 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 72.2%
[2025-01-19 02:15:28 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 02:15:31 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 02:15:31 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 72.16%
[2025-01-19 02:15:47 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.155 (16.155)	Loss 5.6464 (5.6464)	Acc@1 4.614 (4.614)	Acc@5 16.919 (16.919)	Mem 34602MB
[2025-01-19 02:15:50 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (1.784)	Loss 5.7895 (5.6069)	Acc@1 3.979 (5.544)	Acc@5 14.258 (16.748)	Mem 34602MB
[2025-01-19 02:15:51 internimage_b_1k_224] (main.py 575): INFO [Epoch:33] * Acc@1 6.122 Acc@5 18.278
[2025-01-19 02:15:51 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 6.1%
[2025-01-19 02:15:51 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:15:54 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:15:54 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 6.12%
[2025-01-19 02:15:57 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][0/312]	eta 0:12:47 lr 0.003876	time 2.4610 (2.4610)	model_time 0.7632 (0.7632)	loss 4.1307 (4.1307)	grad_norm 0.8651 (0.8651/0.0000)	mem 34602MB
[2025-01-19 02:16:04 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][10/312]	eta 0:04:25 lr 0.003876	time 0.7287 (0.8802)	model_time 0.7286 (0.7256)	loss 3.7699 (3.7643)	grad_norm 0.7084 (1.7406/1.0876)	mem 34602MB
[2025-01-19 02:16:11 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][20/312]	eta 0:03:55 lr 0.003875	time 0.7171 (0.8055)	model_time 0.7169 (0.7243)	loss 4.5556 (3.7640)	grad_norm 0.8144 (1.4184/0.8879)	mem 34602MB
[2025-01-19 02:16:19 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][30/312]	eta 0:03:39 lr 0.003875	time 0.7141 (0.7784)	model_time 0.7140 (0.7233)	loss 3.3772 (3.8954)	grad_norm 1.4227 (1.3534/0.7657)	mem 34602MB
[2025-01-19 02:16:26 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][40/312]	eta 0:03:29 lr 0.003875	time 0.7277 (0.7692)	model_time 0.7275 (0.7274)	loss 4.3335 (3.8232)	grad_norm 0.9551 (1.4505/0.7912)	mem 34602MB
[2025-01-19 02:16:33 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][50/312]	eta 0:03:20 lr 0.003875	time 0.7912 (0.7650)	model_time 0.7910 (0.7314)	loss 3.6374 (3.7912)	grad_norm 1.4017 (1.4426/0.7431)	mem 34602MB
[2025-01-19 02:16:41 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][60/312]	eta 0:03:13 lr 0.003874	time 0.8052 (0.7695)	model_time 0.8050 (0.7413)	loss 3.9103 (3.8006)	grad_norm 1.3295 (1.3545/0.7123)	mem 34602MB
[2025-01-19 02:16:49 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][70/312]	eta 0:03:06 lr 0.003874	time 0.7152 (0.7693)	model_time 0.7147 (0.7451)	loss 3.8357 (3.7997)	grad_norm 1.1919 (1.3320/0.6763)	mem 34602MB
[2025-01-19 02:16:57 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][80/312]	eta 0:02:58 lr 0.003874	time 0.8109 (0.7680)	model_time 0.8105 (0.7467)	loss 4.2602 (3.8444)	grad_norm 1.2035 (1.3187/0.6545)	mem 34602MB
[2025-01-19 02:17:04 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][90/312]	eta 0:02:49 lr 0.003874	time 0.7231 (0.7632)	model_time 0.7229 (0.7442)	loss 4.2802 (3.8488)	grad_norm 0.8644 (1.2870/0.6322)	mem 34602MB
[2025-01-19 02:17:11 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][100/312]	eta 0:02:41 lr 0.003873	time 0.7169 (0.7596)	model_time 0.7167 (0.7425)	loss 3.0495 (3.8488)	grad_norm 0.8014 (1.3043/0.6251)	mem 34602MB
[2025-01-19 02:17:18 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][110/312]	eta 0:02:32 lr 0.003873	time 0.7210 (0.7567)	model_time 0.7205 (0.7410)	loss 2.4441 (3.8289)	grad_norm 1.1183 (1.3322/0.6225)	mem 34602MB
[2025-01-19 02:17:26 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][120/312]	eta 0:02:24 lr 0.003873	time 0.7482 (0.7541)	model_time 0.7477 (0.7397)	loss 4.3490 (3.8244)	grad_norm 1.8816 (1.3163/0.6064)	mem 34602MB
[2025-01-19 02:17:33 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][130/312]	eta 0:02:16 lr 0.003873	time 0.7181 (0.7518)	model_time 0.7179 (0.7384)	loss 4.7721 (3.8450)	grad_norm 1.3661 (1.3167/0.5963)	mem 34602MB
[2025-01-19 02:17:40 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][140/312]	eta 0:02:08 lr 0.003873	time 0.7231 (0.7496)	model_time 0.7229 (0.7372)	loss 3.6582 (3.8412)	grad_norm 0.9608 (1.3024/0.5857)	mem 34602MB
[2025-01-19 02:17:47 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][150/312]	eta 0:02:01 lr 0.003872	time 0.7162 (0.7479)	model_time 0.7160 (0.7363)	loss 2.8716 (3.8442)	grad_norm 2.7267 (1.3191/0.5925)	mem 34602MB
[2025-01-19 02:17:55 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][160/312]	eta 0:01:53 lr 0.003872	time 0.7185 (0.7471)	model_time 0.7180 (0.7362)	loss 4.0477 (3.8416)	grad_norm 1.4512 (1.3001/0.5829)	mem 34602MB
[2025-01-19 02:18:02 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][170/312]	eta 0:01:46 lr 0.003872	time 0.8017 (0.7475)	model_time 0.8015 (0.7372)	loss 3.6851 (3.8329)	grad_norm 0.8678 (1.3074/0.5861)	mem 34602MB
[2025-01-19 02:18:10 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][180/312]	eta 0:01:38 lr 0.003872	time 0.8600 (0.7497)	model_time 0.8598 (0.7399)	loss 4.1680 (3.8438)	grad_norm 1.1905 (1.3293/0.6075)	mem 34602MB
[2025-01-19 02:18:18 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][190/312]	eta 0:01:31 lr 0.003871	time 0.7953 (0.7514)	model_time 0.7949 (0.7421)	loss 3.1109 (3.8255)	grad_norm 0.7481 (1.3206/0.5995)	mem 34602MB
[2025-01-19 02:18:26 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][200/312]	eta 0:01:24 lr 0.003871	time 0.8115 (0.7524)	model_time 0.8113 (0.7436)	loss 3.7518 (3.8258)	grad_norm 1.4979 (1.3156/0.5876)	mem 34602MB
[2025-01-19 02:18:33 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][210/312]	eta 0:01:16 lr 0.003871	time 0.7319 (0.7514)	model_time 0.7315 (0.7430)	loss 4.0155 (3.8298)	grad_norm 0.8992 (1.3021/0.5785)	mem 34602MB
[2025-01-19 02:18:40 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][220/312]	eta 0:01:09 lr 0.003871	time 0.7181 (0.7503)	model_time 0.7176 (0.7423)	loss 3.0599 (3.8212)	grad_norm 1.5706 (1.3176/0.5849)	mem 34602MB
[2025-01-19 02:18:47 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][230/312]	eta 0:01:01 lr 0.003870	time 0.7215 (0.7492)	model_time 0.7211 (0.7415)	loss 3.9935 (3.8252)	grad_norm 0.8587 (1.3115/0.5766)	mem 34602MB
[2025-01-19 02:18:55 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][240/312]	eta 0:00:53 lr 0.003870	time 0.7399 (0.7481)	model_time 0.7394 (0.7407)	loss 4.1618 (3.8261)	grad_norm 1.1449 (1.3171/0.5694)	mem 34602MB
[2025-01-19 02:19:02 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][250/312]	eta 0:00:46 lr 0.003870	time 0.7275 (0.7471)	model_time 0.7273 (0.7399)	loss 4.2213 (3.8282)	grad_norm 0.7575 (1.3152/0.5625)	mem 34602MB
[2025-01-19 02:19:09 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][260/312]	eta 0:00:38 lr 0.003870	time 0.7441 (0.7463)	model_time 0.7436 (0.7394)	loss 3.9870 (3.8354)	grad_norm 1.1527 (1.3216/0.5624)	mem 34602MB
[2025-01-19 02:19:16 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][270/312]	eta 0:00:31 lr 0.003869	time 0.7103 (0.7454)	model_time 0.7098 (0.7388)	loss 4.6115 (3.8374)	grad_norm 1.0782 (1.3126/0.5556)	mem 34602MB
[2025-01-19 02:19:24 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][280/312]	eta 0:00:23 lr 0.003869	time 0.7254 (0.7449)	model_time 0.7252 (0.7385)	loss 3.9786 (3.8398)	grad_norm 1.3357 (1.3099/0.5494)	mem 34602MB
[2025-01-19 02:19:31 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][290/312]	eta 0:00:16 lr 0.003869	time 0.7936 (0.7450)	model_time 0.7935 (0.7388)	loss 3.7955 (3.8364)	grad_norm 1.2117 (1.3027/0.5430)	mem 34602MB
[2025-01-19 02:19:39 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][300/312]	eta 0:00:08 lr 0.003869	time 0.8102 (0.7462)	model_time 0.8101 (0.7402)	loss 3.7284 (3.8378)	grad_norm 0.6955 (1.3019/0.5398)	mem 34602MB
[2025-01-19 02:19:47 internimage_b_1k_224] (main.py 510): INFO Train: [34/300][310/312]	eta 0:00:01 lr 0.003869	time 0.7218 (0.7475)	model_time 0.7217 (0.7417)	loss 4.3296 (3.8287)	grad_norm 1.0042 (1.2869/0.4970)	mem 34602MB
[2025-01-19 02:19:48 internimage_b_1k_224] (main.py 519): INFO EPOCH 34 training takes 0:03:53
[2025-01-19 02:19:48 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_34.pth saving......
[2025-01-19 02:19:51 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_34.pth saved !!!
[2025-01-19 02:19:58 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.250 (7.250)	Loss 1.0094 (1.0094)	Acc@1 77.612 (77.612)	Acc@5 94.556 (94.556)	Mem 34602MB
[2025-01-19 02:20:01 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.933)	Loss 1.4673 (1.2453)	Acc@1 67.944 (72.330)	Acc@5 88.940 (91.675)	Mem 34602MB
[2025-01-19 02:20:01 internimage_b_1k_224] (main.py 575): INFO [Epoch:34] * Acc@1 72.325 Acc@5 91.717
[2025-01-19 02:20:01 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 72.3%
[2025-01-19 02:20:01 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 02:20:05 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 02:20:05 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 72.32%
[2025-01-19 02:20:12 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.196 (7.196)	Loss 5.4546 (5.4546)	Acc@1 6.226 (6.226)	Acc@5 20.776 (20.776)	Mem 34602MB
[2025-01-19 02:20:15 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.923)	Loss 5.5676 (5.3883)	Acc@1 5.762 (7.404)	Acc@5 17.896 (20.628)	Mem 34602MB
[2025-01-19 02:20:15 internimage_b_1k_224] (main.py 575): INFO [Epoch:34] * Acc@1 7.999 Acc@5 22.169
[2025-01-19 02:20:15 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 8.0%
[2025-01-19 02:20:15 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:20:19 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:20:19 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 8.00%
[2025-01-19 02:20:21 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][0/312]	eta 0:11:28 lr 0.003868	time 2.2061 (2.2061)	model_time 0.7490 (0.7490)	loss 3.1462 (3.1462)	grad_norm 0.8193 (0.8193/0.0000)	mem 34602MB
[2025-01-19 02:20:29 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][10/312]	eta 0:04:26 lr 0.003868	time 0.7967 (0.8832)	model_time 0.7962 (0.7504)	loss 3.1191 (3.6754)	grad_norm 1.0311 (1.1028/0.6227)	mem 34602MB
[2025-01-19 02:20:36 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][20/312]	eta 0:03:57 lr 0.003868	time 0.7328 (0.8124)	model_time 0.7326 (0.7426)	loss 3.6919 (3.7072)	grad_norm 0.8366 (1.1419/0.5615)	mem 34602MB
[2025-01-19 02:20:44 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][30/312]	eta 0:03:41 lr 0.003868	time 0.7166 (0.7843)	model_time 0.7164 (0.7370)	loss 4.4452 (3.8502)	grad_norm 0.9219 (1.3020/0.6279)	mem 34602MB
[2025-01-19 02:20:51 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][40/312]	eta 0:03:29 lr 0.003868	time 0.7547 (0.7708)	model_time 0.7546 (0.7349)	loss 4.0457 (3.8134)	grad_norm 2.8262 (1.3078/0.6106)	mem 34602MB
[2025-01-19 02:20:58 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][50/312]	eta 0:03:19 lr 0.003867	time 0.7237 (0.7615)	model_time 0.7235 (0.7326)	loss 2.7585 (3.8221)	grad_norm 2.0649 (1.2884/0.5749)	mem 34602MB
[2025-01-19 02:21:05 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][60/312]	eta 0:03:10 lr 0.003867	time 0.7341 (0.7564)	model_time 0.7340 (0.7321)	loss 3.8502 (3.8381)	grad_norm 3.1066 (1.4113/0.7349)	mem 34602MB
[2025-01-19 02:21:13 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][70/312]	eta 0:03:01 lr 0.003867	time 0.7182 (0.7516)	model_time 0.7180 (0.7307)	loss 2.3407 (3.7922)	grad_norm 1.3734 (1.4053/0.7124)	mem 34602MB
[2025-01-19 02:21:20 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][80/312]	eta 0:02:53 lr 0.003867	time 0.7174 (0.7482)	model_time 0.7172 (0.7298)	loss 4.1056 (3.8078)	grad_norm 0.7647 (1.4180/0.6949)	mem 34602MB
[2025-01-19 02:21:27 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][90/312]	eta 0:02:45 lr 0.003866	time 0.7285 (0.7466)	model_time 0.7283 (0.7303)	loss 4.1104 (3.8413)	grad_norm 0.8122 (1.3721/0.6696)	mem 34602MB
[2025-01-19 02:21:35 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][100/312]	eta 0:02:38 lr 0.003866	time 0.7251 (0.7476)	model_time 0.7249 (0.7328)	loss 3.4861 (3.8637)	grad_norm 0.9676 (1.3573/0.6544)	mem 34602MB
[2025-01-19 02:21:43 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][110/312]	eta 0:02:32 lr 0.003866	time 0.8032 (0.7528)	model_time 0.8030 (0.7394)	loss 4.2438 (3.8595)	grad_norm 1.3419 (1.4046/0.6910)	mem 34602MB
[2025-01-19 02:21:51 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][120/312]	eta 0:02:25 lr 0.003866	time 0.8024 (0.7557)	model_time 0.8019 (0.7433)	loss 3.8971 (3.8498)	grad_norm 0.6933 (1.3653/0.6787)	mem 34602MB
[2025-01-19 02:21:58 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][130/312]	eta 0:02:17 lr 0.003865	time 0.7188 (0.7545)	model_time 0.7187 (0.7430)	loss 3.1255 (3.8618)	grad_norm 0.6714 (1.3463/0.6628)	mem 34602MB
[2025-01-19 02:22:05 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][140/312]	eta 0:02:09 lr 0.003865	time 0.7193 (0.7535)	model_time 0.7187 (0.7429)	loss 4.0984 (3.8602)	grad_norm 0.9593 (1.3149/0.6513)	mem 34602MB
[2025-01-19 02:22:13 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][150/312]	eta 0:02:01 lr 0.003865	time 0.7329 (0.7517)	model_time 0.7328 (0.7417)	loss 4.3067 (3.8684)	grad_norm 1.8035 (1.3033/0.6384)	mem 34602MB
[2025-01-19 02:22:20 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][160/312]	eta 0:01:54 lr 0.003865	time 0.7213 (0.7501)	model_time 0.7211 (0.7407)	loss 3.0337 (3.8520)	grad_norm 2.5082 (1.3276/0.6403)	mem 34602MB
[2025-01-19 02:22:27 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][170/312]	eta 0:01:46 lr 0.003864	time 0.7255 (0.7491)	model_time 0.7250 (0.7402)	loss 4.1618 (3.8476)	grad_norm 0.5714 (1.3085/0.6314)	mem 34602MB
[2025-01-19 02:22:35 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][180/312]	eta 0:01:38 lr 0.003864	time 0.7253 (0.7476)	model_time 0.7251 (0.7392)	loss 3.1074 (3.8551)	grad_norm 1.2414 (1.2946/0.6181)	mem 34602MB
[2025-01-19 02:22:42 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][190/312]	eta 0:01:31 lr 0.003864	time 0.7171 (0.7472)	model_time 0.7170 (0.7393)	loss 3.6519 (3.8459)	grad_norm 0.9531 (1.2808/0.6065)	mem 34602MB
[2025-01-19 02:22:49 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][200/312]	eta 0:01:23 lr 0.003864	time 0.7507 (0.7463)	model_time 0.7505 (0.7387)	loss 4.0895 (3.8392)	grad_norm 1.4712 (1.2844/0.6092)	mem 34602MB
[2025-01-19 02:22:57 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][210/312]	eta 0:01:16 lr 0.003863	time 0.7240 (0.7458)	model_time 0.7236 (0.7386)	loss 4.9157 (3.8502)	grad_norm 0.8275 (1.2788/0.5995)	mem 34602MB
[2025-01-19 02:23:04 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][220/312]	eta 0:01:08 lr 0.003863	time 0.8277 (0.7464)	model_time 0.8275 (0.7395)	loss 3.8092 (3.8458)	grad_norm 0.8261 (1.2738/0.6000)	mem 34602MB
[2025-01-19 02:23:12 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][230/312]	eta 0:01:01 lr 0.003863	time 0.8033 (0.7478)	model_time 0.8029 (0.7412)	loss 4.1517 (3.8562)	grad_norm 0.8277 (1.2707/0.5903)	mem 34602MB
[2025-01-19 02:23:20 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][240/312]	eta 0:00:53 lr 0.003863	time 0.8256 (0.7490)	model_time 0.8251 (0.7426)	loss 3.9278 (3.8502)	grad_norm 0.7434 (1.2662/0.5826)	mem 34602MB
[2025-01-19 02:23:27 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][250/312]	eta 0:00:46 lr 0.003862	time 0.7265 (0.7494)	model_time 0.7263 (0.7433)	loss 3.9722 (3.8479)	grad_norm 2.6942 (1.2790/0.5874)	mem 34602MB
[2025-01-19 02:23:35 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][260/312]	eta 0:00:38 lr 0.003862	time 0.7166 (0.7490)	model_time 0.7164 (0.7431)	loss 2.8561 (3.8429)	grad_norm 1.6453 (1.2803/0.5790)	mem 34602MB
[2025-01-19 02:23:42 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][270/312]	eta 0:00:31 lr 0.003862	time 0.7229 (0.7481)	model_time 0.7227 (0.7424)	loss 3.9636 (3.8360)	grad_norm 0.9968 (1.2899/0.5840)	mem 34602MB
[2025-01-19 02:23:49 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][280/312]	eta 0:00:23 lr 0.003862	time 0.7338 (0.7473)	model_time 0.7336 (0.7417)	loss 4.7422 (3.8417)	grad_norm 1.6926 (1.3033/0.5847)	mem 34602MB
[2025-01-19 02:23:57 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][290/312]	eta 0:00:16 lr 0.003861	time 0.7281 (0.7466)	model_time 0.7277 (0.7413)	loss 3.9525 (3.8334)	grad_norm 0.6224 (1.3093/0.5846)	mem 34602MB
[2025-01-19 02:24:04 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][300/312]	eta 0:00:08 lr 0.003861	time 0.7138 (0.7458)	model_time 0.7137 (0.7406)	loss 3.3576 (3.8358)	grad_norm 1.0978 (1.3023/0.5836)	mem 34602MB
[2025-01-19 02:24:11 internimage_b_1k_224] (main.py 510): INFO Train: [35/300][310/312]	eta 0:00:01 lr 0.003861	time 0.7222 (0.7448)	model_time 0.7221 (0.7398)	loss 4.8592 (3.8452)	grad_norm 1.4999 (1.2955/0.5765)	mem 34602MB
[2025-01-19 02:24:12 internimage_b_1k_224] (main.py 519): INFO EPOCH 35 training takes 0:03:52
[2025-01-19 02:24:12 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_35.pth saving......
[2025-01-19 02:24:15 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_35.pth saved !!!
[2025-01-19 02:24:22 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.132 (7.132)	Loss 1.0590 (1.0590)	Acc@1 77.295 (77.295)	Acc@5 93.970 (93.970)	Mem 34602MB
[2025-01-19 02:24:25 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.913)	Loss 1.4856 (1.2530)	Acc@1 67.139 (72.665)	Acc@5 88.574 (91.566)	Mem 34602MB
[2025-01-19 02:24:25 internimage_b_1k_224] (main.py 575): INFO [Epoch:35] * Acc@1 72.775 Acc@5 91.685
[2025-01-19 02:24:25 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 72.8%
[2025-01-19 02:24:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 02:24:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 02:24:28 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 72.77%
[2025-01-19 02:24:36 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.226 (7.226)	Loss 5.2407 (5.2407)	Acc@1 8.984 (8.984)	Acc@5 24.756 (24.756)	Mem 34602MB
[2025-01-19 02:24:39 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.939)	Loss 5.3360 (5.1577)	Acc@1 7.861 (9.710)	Acc@5 21.387 (24.802)	Mem 34602MB
[2025-01-19 02:24:39 internimage_b_1k_224] (main.py 575): INFO [Epoch:35] * Acc@1 10.303 Acc@5 26.302
[2025-01-19 02:24:39 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 10.3%
[2025-01-19 02:24:39 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:24:43 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:24:43 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 10.30%
[2025-01-19 02:24:45 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][0/312]	eta 0:11:11 lr 0.003861	time 2.1509 (2.1509)	model_time 0.7466 (0.7466)	loss 4.1713 (4.1713)	grad_norm 0.7697 (0.7697/0.0000)	mem 34602MB
[2025-01-19 02:24:52 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][10/312]	eta 0:04:22 lr 0.003861	time 0.8117 (0.8692)	model_time 0.8112 (0.7412)	loss 3.9822 (3.6974)	grad_norm 0.9588 (1.2140/0.3422)	mem 34602MB
[2025-01-19 02:25:00 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][20/312]	eta 0:03:55 lr 0.003860	time 0.7165 (0.8051)	model_time 0.7160 (0.7378)	loss 3.5953 (3.7046)	grad_norm 1.8304 (1.2443/0.3041)	mem 34602MB
[2025-01-19 02:25:07 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][30/312]	eta 0:03:42 lr 0.003860	time 0.7381 (0.7904)	model_time 0.7379 (0.7447)	loss 2.8005 (3.6779)	grad_norm 1.8816 (1.3461/0.3711)	mem 34602MB
[2025-01-19 02:25:15 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][40/312]	eta 0:03:35 lr 0.003860	time 0.7995 (0.7917)	model_time 0.7990 (0.7571)	loss 4.7196 (3.7083)	grad_norm 0.9537 (1.3437/0.3743)	mem 34602MB
[2025-01-19 02:25:23 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][50/312]	eta 0:03:26 lr 0.003860	time 0.7155 (0.7879)	model_time 0.7153 (0.7600)	loss 4.0492 (3.6730)	grad_norm 1.0235 (1.2854/0.3793)	mem 34602MB
[2025-01-19 02:25:31 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][60/312]	eta 0:03:17 lr 0.003859	time 0.7936 (0.7842)	model_time 0.7932 (0.7608)	loss 4.3966 (3.7314)	grad_norm 0.9622 (1.3313/0.4447)	mem 34602MB
[2025-01-19 02:25:38 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][70/312]	eta 0:03:08 lr 0.003859	time 0.7233 (0.7777)	model_time 0.7226 (0.7576)	loss 3.9558 (3.7650)	grad_norm 1.6245 (1.4232/0.5305)	mem 34602MB
[2025-01-19 02:25:45 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][80/312]	eta 0:02:58 lr 0.003859	time 0.7191 (0.7715)	model_time 0.7190 (0.7538)	loss 3.8458 (3.7708)	grad_norm 1.0334 (1.4032/0.5304)	mem 34602MB
[2025-01-19 02:25:52 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][90/312]	eta 0:02:50 lr 0.003859	time 0.7381 (0.7669)	model_time 0.7379 (0.7511)	loss 4.1071 (3.7741)	grad_norm 0.8841 (1.3515/0.5293)	mem 34602MB
[2025-01-19 02:26:00 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][100/312]	eta 0:02:41 lr 0.003859	time 0.7263 (0.7629)	model_time 0.7258 (0.7486)	loss 4.3367 (3.7696)	grad_norm 1.3347 (1.3351/0.5190)	mem 34602MB
[2025-01-19 02:26:07 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][110/312]	eta 0:02:33 lr 0.003858	time 0.7418 (0.7592)	model_time 0.7417 (0.7462)	loss 4.1204 (3.7928)	grad_norm 2.2286 (1.3425/0.5085)	mem 34602MB
[2025-01-19 02:26:14 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][120/312]	eta 0:02:25 lr 0.003858	time 0.7153 (0.7566)	model_time 0.7149 (0.7446)	loss 2.8976 (3.8109)	grad_norm 1.6059 (1.3569/0.4996)	mem 34602MB
[2025-01-19 02:26:22 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][130/312]	eta 0:02:17 lr 0.003858	time 0.7958 (0.7543)	model_time 0.7956 (0.7432)	loss 4.2917 (3.8114)	grad_norm 0.6895 (1.3633/0.5128)	mem 34602MB
[2025-01-19 02:26:29 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][140/312]	eta 0:02:09 lr 0.003858	time 0.7185 (0.7528)	model_time 0.7184 (0.7425)	loss 4.7021 (3.8235)	grad_norm 0.6890 (1.3647/0.5196)	mem 34602MB
[2025-01-19 02:26:36 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][150/312]	eta 0:02:02 lr 0.003857	time 0.7342 (0.7532)	model_time 0.7338 (0.7435)	loss 3.3902 (3.8271)	grad_norm 0.6957 (1.3555/0.5135)	mem 34602MB
[2025-01-19 02:26:44 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][160/312]	eta 0:01:54 lr 0.003857	time 0.8042 (0.7548)	model_time 0.8041 (0.7457)	loss 4.3942 (3.8247)	grad_norm 2.1115 (1.3500/0.5092)	mem 34602MB
[2025-01-19 02:26:52 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][170/312]	eta 0:01:47 lr 0.003857	time 0.7152 (0.7560)	model_time 0.7150 (0.7474)	loss 2.8639 (3.8223)	grad_norm 1.0674 (1.3682/0.5172)	mem 34602MB
[2025-01-19 02:27:00 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][180/312]	eta 0:01:39 lr 0.003857	time 0.8329 (0.7558)	model_time 0.8324 (0.7477)	loss 4.0756 (3.8167)	grad_norm 1.4102 (1.3584/0.5090)	mem 34602MB
[2025-01-19 02:27:07 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][190/312]	eta 0:01:32 lr 0.003856	time 0.7636 (0.7551)	model_time 0.7634 (0.7474)	loss 3.2400 (3.8336)	grad_norm 1.4885 (1.3472/0.5011)	mem 34602MB
[2025-01-19 02:27:14 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][200/312]	eta 0:01:24 lr 0.003856	time 0.7198 (0.7535)	model_time 0.7196 (0.7462)	loss 4.5964 (3.8352)	grad_norm 0.7576 (1.3439/0.5027)	mem 34602MB
[2025-01-19 02:27:21 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][210/312]	eta 0:01:16 lr 0.003856	time 0.7235 (0.7520)	model_time 0.7234 (0.7450)	loss 3.4488 (3.8287)	grad_norm 1.1649 (1.3363/0.4961)	mem 34602MB
[2025-01-19 02:27:29 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][220/312]	eta 0:01:09 lr 0.003856	time 0.7172 (0.7510)	model_time 0.7170 (0.7442)	loss 2.4565 (3.8276)	grad_norm 0.7400 (1.3349/0.4938)	mem 34602MB
[2025-01-19 02:27:36 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][230/312]	eta 0:01:01 lr 0.003855	time 0.7172 (0.7501)	model_time 0.7170 (0.7436)	loss 4.2244 (3.8361)	grad_norm 1.0975 (1.3352/0.4913)	mem 34602MB
[2025-01-19 02:27:43 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][240/312]	eta 0:00:53 lr 0.003855	time 0.7383 (0.7493)	model_time 0.7381 (0.7431)	loss 4.5564 (3.8309)	grad_norm 1.8194 (1.3387/0.4897)	mem 34602MB
[2025-01-19 02:27:51 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][250/312]	eta 0:00:46 lr 0.003855	time 0.7557 (0.7485)	model_time 0.7555 (0.7426)	loss 4.8183 (3.8368)	grad_norm 1.4512 (1.3363/0.4880)	mem 34602MB
[2025-01-19 02:27:58 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][260/312]	eta 0:00:38 lr 0.003855	time 0.7333 (0.7483)	model_time 0.7328 (0.7425)	loss 3.9377 (3.8423)	grad_norm 1.2159 (1.3250/0.4845)	mem 34602MB
[2025-01-19 02:28:05 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][270/312]	eta 0:00:31 lr 0.003854	time 0.7200 (0.7476)	model_time 0.7195 (0.7420)	loss 4.1559 (3.8591)	grad_norm 1.2371 (1.3222/0.4855)	mem 34602MB
[2025-01-19 02:28:13 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][280/312]	eta 0:00:23 lr 0.003854	time 0.8064 (0.7494)	model_time 0.8060 (0.7440)	loss 4.1101 (3.8663)	grad_norm 1.3011 (1.3228/0.4804)	mem 34602MB
[2025-01-19 02:28:21 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][290/312]	eta 0:00:16 lr 0.003854	time 0.7172 (0.7507)	model_time 0.7170 (0.7455)	loss 4.1327 (3.8538)	grad_norm 1.3876 (1.3262/0.4821)	mem 34602MB
[2025-01-19 02:28:29 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][300/312]	eta 0:00:09 lr 0.003854	time 0.9849 (0.7513)	model_time 0.9848 (0.7463)	loss 4.7542 (3.8481)	grad_norm 1.5193 (1.3235/0.4826)	mem 34602MB
[2025-01-19 02:28:36 internimage_b_1k_224] (main.py 510): INFO Train: [36/300][310/312]	eta 0:00:01 lr 0.003853	time 0.7133 (0.7509)	model_time 0.7132 (0.7460)	loss 3.5136 (3.8507)	grad_norm 0.7317 (1.3234/0.4846)	mem 34602MB
[2025-01-19 02:28:37 internimage_b_1k_224] (main.py 519): INFO EPOCH 36 training takes 0:03:54
[2025-01-19 02:28:37 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_36.pth saving......
[2025-01-19 02:28:40 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_36.pth saved !!!
[2025-01-19 02:28:48 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.551 (7.551)	Loss 1.0384 (1.0384)	Acc@1 77.075 (77.075)	Acc@5 93.774 (93.774)	Mem 34602MB
[2025-01-19 02:28:51 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.961)	Loss 1.5062 (1.2462)	Acc@1 66.211 (72.694)	Acc@5 88.306 (91.566)	Mem 34602MB
[2025-01-19 02:28:51 internimage_b_1k_224] (main.py 575): INFO [Epoch:36] * Acc@1 72.765 Acc@5 91.649
[2025-01-19 02:28:51 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 72.8%
[2025-01-19 02:28:51 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 72.77%
[2025-01-19 02:29:00 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.025 (9.025)	Loss 5.0137 (5.0137)	Acc@1 11.646 (11.646)	Acc@5 28.491 (28.491)	Mem 34602MB
[2025-01-19 02:29:05 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.232)	Loss 5.0966 (4.9188)	Acc@1 10.718 (12.484)	Acc@5 25.952 (29.372)	Mem 34602MB
[2025-01-19 02:29:05 internimage_b_1k_224] (main.py 575): INFO [Epoch:36] * Acc@1 13.076 Acc@5 30.822
[2025-01-19 02:29:05 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 13.1%
[2025-01-19 02:29:05 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:29:09 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:29:09 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 13.08%
[2025-01-19 02:29:11 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][0/312]	eta 0:10:44 lr 0.003853	time 2.0654 (2.0654)	model_time 0.7591 (0.7591)	loss 4.6876 (4.6876)	grad_norm 1.9694 (1.9694/0.0000)	mem 34602MB
[2025-01-19 02:29:18 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][10/312]	eta 0:04:15 lr 0.003853	time 0.7214 (0.8463)	model_time 0.7212 (0.7272)	loss 3.1001 (4.0369)	grad_norm 0.9550 (1.4123/0.5550)	mem 34602MB
[2025-01-19 02:29:25 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][20/312]	eta 0:03:51 lr 0.003853	time 0.7193 (0.7936)	model_time 0.7189 (0.7311)	loss 3.7952 (3.8119)	grad_norm 1.1424 (1.4532/0.5360)	mem 34602MB
[2025-01-19 02:29:33 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][30/312]	eta 0:03:37 lr 0.003852	time 0.7164 (0.7725)	model_time 0.7162 (0.7300)	loss 3.5083 (3.7788)	grad_norm 0.8923 (1.3936/0.5746)	mem 34602MB
[2025-01-19 02:29:40 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][40/312]	eta 0:03:27 lr 0.003852	time 0.7333 (0.7611)	model_time 0.7332 (0.7289)	loss 4.0517 (3.6950)	grad_norm 1.3212 (1.3127/0.5517)	mem 34602MB
[2025-01-19 02:29:47 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][50/312]	eta 0:03:17 lr 0.003852	time 0.7190 (0.7548)	model_time 0.7188 (0.7289)	loss 2.5401 (3.6854)	grad_norm 1.4868 (1.2535/0.5354)	mem 34602MB
[2025-01-19 02:29:55 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][60/312]	eta 0:03:09 lr 0.003852	time 0.7345 (0.7504)	model_time 0.7343 (0.7287)	loss 3.7750 (3.7173)	grad_norm 0.7513 (1.2083/0.5100)	mem 34602MB
[2025-01-19 02:30:02 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][70/312]	eta 0:03:00 lr 0.003851	time 0.7247 (0.7477)	model_time 0.7242 (0.7290)	loss 3.8179 (3.7267)	grad_norm 1.3909 (1.2264/0.4885)	mem 34602MB
[2025-01-19 02:30:09 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][80/312]	eta 0:02:53 lr 0.003851	time 0.7925 (0.7484)	model_time 0.7920 (0.7319)	loss 4.0666 (3.6989)	grad_norm 1.0740 (1.2118/0.4768)	mem 34602MB
[2025-01-19 02:30:17 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][90/312]	eta 0:02:46 lr 0.003851	time 0.8422 (0.7517)	model_time 0.8420 (0.7370)	loss 4.1398 (3.7042)	grad_norm 1.5330 (1.2553/0.4822)	mem 34602MB
[2025-01-19 02:30:25 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][100/312]	eta 0:02:39 lr 0.003851	time 0.8029 (0.7542)	model_time 0.8028 (0.7409)	loss 3.3100 (3.7245)	grad_norm 1.9459 (1.3028/0.5148)	mem 34602MB
[2025-01-19 02:30:33 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][110/312]	eta 0:02:32 lr 0.003850	time 0.7157 (0.7546)	model_time 0.7155 (0.7424)	loss 3.9384 (3.7219)	grad_norm 1.0174 (1.3197/0.5251)	mem 34602MB
[2025-01-19 02:30:40 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][120/312]	eta 0:02:24 lr 0.003850	time 0.7197 (0.7539)	model_time 0.7192 (0.7427)	loss 4.7379 (3.7655)	grad_norm 2.6780 (1.3537/0.5593)	mem 34602MB
[2025-01-19 02:30:47 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][130/312]	eta 0:02:16 lr 0.003850	time 0.7133 (0.7519)	model_time 0.7132 (0.7416)	loss 4.3027 (3.7489)	grad_norm 1.1004 (1.3403/0.5530)	mem 34602MB
[2025-01-19 02:30:55 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][140/312]	eta 0:02:09 lr 0.003850	time 0.7101 (0.7500)	model_time 0.7099 (0.7404)	loss 3.1674 (3.7514)	grad_norm 0.7244 (1.3504/0.5674)	mem 34602MB
[2025-01-19 02:31:02 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][150/312]	eta 0:02:01 lr 0.003849	time 0.7199 (0.7484)	model_time 0.7194 (0.7394)	loss 3.8031 (3.7616)	grad_norm 1.1234 (1.3298/0.5552)	mem 34602MB
[2025-01-19 02:31:09 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][160/312]	eta 0:01:53 lr 0.003849	time 0.7289 (0.7471)	model_time 0.7286 (0.7386)	loss 3.1562 (3.7641)	grad_norm 0.8914 (1.3235/0.5443)	mem 34602MB
[2025-01-19 02:31:16 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][170/312]	eta 0:01:45 lr 0.003849	time 0.7413 (0.7463)	model_time 0.7411 (0.7383)	loss 3.0324 (3.7609)	grad_norm 1.1229 (1.3219/0.5400)	mem 34602MB
[2025-01-19 02:31:24 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][180/312]	eta 0:01:38 lr 0.003849	time 0.7621 (0.7454)	model_time 0.7617 (0.7378)	loss 3.6505 (3.7419)	grad_norm 0.9206 (1.3227/0.5370)	mem 34602MB
[2025-01-19 02:31:31 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][190/312]	eta 0:01:30 lr 0.003848	time 0.7214 (0.7446)	model_time 0.7212 (0.7374)	loss 3.9289 (3.7420)	grad_norm 1.4702 (1.3143/0.5270)	mem 34602MB
[2025-01-19 02:31:39 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][200/312]	eta 0:01:23 lr 0.003848	time 0.8026 (0.7449)	model_time 0.8022 (0.7380)	loss 4.5430 (3.7462)	grad_norm 1.9222 (1.3596/0.6142)	mem 34602MB
[2025-01-19 02:31:47 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][210/312]	eta 0:01:16 lr 0.003848	time 1.0028 (0.7492)	model_time 1.0027 (0.7427)	loss 3.2657 (3.7350)	grad_norm 0.8314 (1.3435/0.6053)	mem 34602MB
[2025-01-19 02:31:55 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][220/312]	eta 0:01:09 lr 0.003848	time 0.8158 (0.7505)	model_time 0.8153 (0.7443)	loss 3.8032 (3.7381)	grad_norm 1.3369 (1.3536/0.6108)	mem 34602MB
[2025-01-19 02:32:02 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][230/312]	eta 0:01:01 lr 0.003847	time 0.7424 (0.7516)	model_time 0.7422 (0.7456)	loss 4.3565 (3.7347)	grad_norm 1.2975 (1.3357/0.6056)	mem 34602MB
[2025-01-19 02:32:10 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][240/312]	eta 0:00:54 lr 0.003847	time 0.8040 (0.7517)	model_time 0.8039 (0.7459)	loss 3.8937 (3.7381)	grad_norm 1.4571 (1.3392/0.6033)	mem 34602MB
[2025-01-19 02:32:17 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][250/312]	eta 0:00:46 lr 0.003847	time 0.7204 (0.7508)	model_time 0.7202 (0.7452)	loss 3.7416 (3.7317)	grad_norm 0.9242 (1.3387/0.5970)	mem 34602MB
[2025-01-19 02:32:25 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][260/312]	eta 0:00:38 lr 0.003847	time 0.7193 (0.7498)	model_time 0.7187 (0.7445)	loss 4.5005 (3.7361)	grad_norm 1.4997 (1.3359/0.5927)	mem 34602MB
[2025-01-19 02:32:32 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][270/312]	eta 0:00:31 lr 0.003846	time 0.7154 (0.7489)	model_time 0.7149 (0.7438)	loss 4.1894 (3.7473)	grad_norm 1.7623 (1.3230/0.5893)	mem 34602MB
[2025-01-19 02:32:39 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][280/312]	eta 0:00:23 lr 0.003846	time 0.7201 (0.7479)	model_time 0.7198 (0.7429)	loss 2.6184 (3.7490)	grad_norm 1.4026 (1.3425/0.6231)	mem 34602MB
[2025-01-19 02:32:46 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][290/312]	eta 0:00:16 lr 0.003846	time 0.7296 (0.7472)	model_time 0.7294 (0.7423)	loss 3.8080 (3.7472)	grad_norm 1.4618 (1.3410/0.6168)	mem 34602MB
[2025-01-19 02:32:53 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][300/312]	eta 0:00:08 lr 0.003846	time 0.7127 (0.7462)	model_time 0.7126 (0.7415)	loss 4.1909 (3.7500)	grad_norm 1.3282 (1.3258/0.6114)	mem 34602MB
[2025-01-19 02:33:01 internimage_b_1k_224] (main.py 510): INFO Train: [37/300][310/312]	eta 0:00:01 lr 0.003845	time 0.7142 (0.7455)	model_time 0.7140 (0.7409)	loss 4.4709 (3.7578)	grad_norm 2.3410 (1.3282/0.6117)	mem 34602MB
[2025-01-19 02:33:01 internimage_b_1k_224] (main.py 519): INFO EPOCH 37 training takes 0:03:52
[2025-01-19 02:33:01 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_37.pth saving......
[2025-01-19 02:33:05 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_37.pth saved !!!
[2025-01-19 02:33:12 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.501 (7.501)	Loss 1.0103 (1.0103)	Acc@1 78.833 (78.833)	Acc@5 94.531 (94.531)	Mem 34602MB
[2025-01-19 02:33:15 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.936)	Loss 1.5246 (1.2527)	Acc@1 67.480 (73.438)	Acc@5 88.184 (91.879)	Mem 34602MB
[2025-01-19 02:33:15 internimage_b_1k_224] (main.py 575): INFO [Epoch:37] * Acc@1 73.335 Acc@5 91.891
[2025-01-19 02:33:15 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 73.3%
[2025-01-19 02:33:15 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 02:33:19 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 02:33:19 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 73.33%
[2025-01-19 02:33:26 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.041 (7.041)	Loss 4.7748 (4.7748)	Acc@1 15.063 (15.063)	Acc@5 33.057 (33.057)	Mem 34602MB
[2025-01-19 02:33:29 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.913)	Loss 4.8579 (4.6748)	Acc@1 13.403 (15.407)	Acc@5 30.762 (34.277)	Mem 34602MB
[2025-01-19 02:33:29 internimage_b_1k_224] (main.py 575): INFO [Epoch:37] * Acc@1 16.033 Acc@5 35.657
[2025-01-19 02:33:29 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 16.0%
[2025-01-19 02:33:29 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:33:33 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:33:33 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 16.03%
[2025-01-19 02:33:35 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][0/312]	eta 0:12:04 lr 0.003845	time 2.3225 (2.3225)	model_time 0.7530 (0.7530)	loss 2.9973 (2.9973)	grad_norm 2.1512 (2.1512/0.0000)	mem 34602MB
[2025-01-19 02:33:43 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][10/312]	eta 0:04:29 lr 0.003845	time 0.7985 (0.8916)	model_time 0.7983 (0.7487)	loss 2.9023 (3.4943)	grad_norm 1.8628 (1.4569/0.6197)	mem 34602MB
[2025-01-19 02:33:51 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][20/312]	eta 0:04:08 lr 0.003845	time 0.7219 (0.8520)	model_time 0.7217 (0.7769)	loss 3.2494 (3.6381)	grad_norm 1.3695 (1.4927/0.4973)	mem 34602MB
[2025-01-19 02:33:59 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][30/312]	eta 0:03:56 lr 0.003845	time 1.0108 (0.8392)	model_time 1.0106 (0.7883)	loss 2.7507 (3.6359)	grad_norm 0.8122 (1.3301/0.4940)	mem 34602MB
[2025-01-19 02:34:06 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][40/312]	eta 0:03:42 lr 0.003844	time 0.7202 (0.8184)	model_time 0.7201 (0.7798)	loss 4.2203 (3.6918)	grad_norm 0.9217 (1.3858/0.5528)	mem 34602MB
[2025-01-19 02:34:14 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][50/312]	eta 0:03:30 lr 0.003844	time 0.7333 (0.8052)	model_time 0.7331 (0.7741)	loss 2.5464 (3.7636)	grad_norm 1.0607 (1.3391/0.5432)	mem 34602MB
[2025-01-19 02:34:21 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][60/312]	eta 0:03:19 lr 0.003844	time 0.7199 (0.7923)	model_time 0.7198 (0.7663)	loss 4.2435 (3.7552)	grad_norm 1.3174 (1.2717/0.5320)	mem 34602MB
[2025-01-19 02:34:28 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][70/312]	eta 0:03:09 lr 0.003843	time 0.7243 (0.7830)	model_time 0.7241 (0.7605)	loss 3.9468 (3.7820)	grad_norm 0.8399 (1.2578/0.5382)	mem 34602MB
[2025-01-19 02:34:36 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][80/312]	eta 0:03:00 lr 0.003843	time 0.7152 (0.7767)	model_time 0.7150 (0.7570)	loss 2.8896 (3.7582)	grad_norm 0.9148 (1.2361/0.5158)	mem 34602MB
[2025-01-19 02:34:43 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][90/312]	eta 0:02:51 lr 0.003843	time 0.7505 (0.7716)	model_time 0.7503 (0.7540)	loss 4.1615 (3.7622)	grad_norm 2.6045 (1.2697/0.5292)	mem 34602MB
[2025-01-19 02:34:50 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][100/312]	eta 0:02:42 lr 0.003843	time 0.7249 (0.7677)	model_time 0.7244 (0.7518)	loss 3.1844 (3.7585)	grad_norm 1.6011 (1.3024/0.5327)	mem 34602MB
[2025-01-19 02:34:58 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][110/312]	eta 0:02:34 lr 0.003842	time 0.7424 (0.7636)	model_time 0.7419 (0.7491)	loss 4.0086 (3.7641)	grad_norm 0.9075 (1.3120/0.5637)	mem 34602MB
[2025-01-19 02:35:05 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][120/312]	eta 0:02:26 lr 0.003842	time 0.7415 (0.7612)	model_time 0.7413 (0.7479)	loss 2.6709 (3.7606)	grad_norm 0.7018 (1.3159/0.5531)	mem 34602MB
[2025-01-19 02:35:12 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][130/312]	eta 0:02:18 lr 0.003842	time 0.7951 (0.7593)	model_time 0.7949 (0.7470)	loss 3.5914 (3.7429)	grad_norm 0.7660 (1.3081/0.5432)	mem 34602MB
[2025-01-19 02:35:20 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][140/312]	eta 0:02:11 lr 0.003842	time 0.7197 (0.7619)	model_time 0.7196 (0.7505)	loss 4.4614 (3.7400)	grad_norm 1.4241 (1.3085/0.5340)	mem 34602MB
[2025-01-19 02:35:28 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][150/312]	eta 0:02:03 lr 0.003841	time 0.7161 (0.7633)	model_time 0.7159 (0.7526)	loss 2.8649 (3.7500)	grad_norm 0.9598 (1.3071/0.5320)	mem 34602MB
[2025-01-19 02:35:36 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][160/312]	eta 0:01:56 lr 0.003841	time 0.7186 (0.7632)	model_time 0.7182 (0.7532)	loss 4.5504 (3.7595)	grad_norm 2.0422 (1.2941/0.5262)	mem 34602MB
[2025-01-19 02:35:43 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][170/312]	eta 0:01:48 lr 0.003841	time 0.7221 (0.7636)	model_time 0.7219 (0.7541)	loss 3.8351 (3.7582)	grad_norm 0.5880 (1.3113/0.5406)	mem 34602MB
[2025-01-19 02:35:51 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][180/312]	eta 0:01:40 lr 0.003841	time 0.7158 (0.7613)	model_time 0.7154 (0.7523)	loss 4.1360 (3.7599)	grad_norm 0.9692 (1.3064/0.5339)	mem 34602MB
[2025-01-19 02:35:58 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][190/312]	eta 0:01:32 lr 0.003840	time 0.7375 (0.7597)	model_time 0.7374 (0.7511)	loss 3.1340 (3.7592)	grad_norm 0.6741 (1.2984/0.5338)	mem 34602MB
[2025-01-19 02:36:05 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][200/312]	eta 0:01:24 lr 0.003840	time 0.7453 (0.7582)	model_time 0.7448 (0.7501)	loss 4.4216 (3.7656)	grad_norm 0.8352 (1.2933/0.5274)	mem 34602MB
[2025-01-19 02:36:12 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][210/312]	eta 0:01:17 lr 0.003840	time 0.7158 (0.7565)	model_time 0.7153 (0.7487)	loss 3.1308 (3.7702)	grad_norm 1.2701 (1.2799/0.5209)	mem 34602MB
[2025-01-19 02:36:20 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][220/312]	eta 0:01:09 lr 0.003840	time 0.7180 (0.7549)	model_time 0.7178 (0.7475)	loss 3.1470 (3.7832)	grad_norm 0.9728 (1.2654/0.5154)	mem 34602MB
[2025-01-19 02:36:27 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][230/312]	eta 0:01:01 lr 0.003839	time 0.7459 (0.7539)	model_time 0.7457 (0.7468)	loss 3.6507 (3.7794)	grad_norm 1.4978 (1.2757/0.5105)	mem 34602MB
[2025-01-19 02:36:34 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][240/312]	eta 0:00:54 lr 0.003839	time 0.7275 (0.7530)	model_time 0.7270 (0.7461)	loss 2.7174 (3.7662)	grad_norm 1.0907 (1.2754/0.5018)	mem 34602MB
[2025-01-19 02:36:42 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][250/312]	eta 0:00:46 lr 0.003839	time 0.7437 (0.7522)	model_time 0.7435 (0.7456)	loss 3.5747 (3.7603)	grad_norm 2.2309 (1.2716/0.4990)	mem 34602MB
[2025-01-19 02:36:49 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][260/312]	eta 0:00:39 lr 0.003839	time 0.7195 (0.7530)	model_time 0.7194 (0.7466)	loss 2.6758 (3.7643)	grad_norm 0.7109 (1.2703/0.5051)	mem 34602MB
[2025-01-19 02:36:57 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][270/312]	eta 0:00:31 lr 0.003838	time 0.7153 (0.7547)	model_time 0.7151 (0.7485)	loss 3.2591 (3.7572)	grad_norm 1.7909 (1.2725/0.5056)	mem 34602MB
[2025-01-19 02:37:05 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][280/312]	eta 0:00:24 lr 0.003838	time 0.7233 (0.7549)	model_time 0.7231 (0.7489)	loss 2.8764 (3.7490)	grad_norm 1.3443 (1.3018/0.5465)	mem 34602MB
[2025-01-19 02:37:12 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][290/312]	eta 0:00:16 lr 0.003838	time 0.7296 (0.7546)	model_time 0.7295 (0.7489)	loss 4.0698 (3.7502)	grad_norm 1.0614 (1.2938/0.5419)	mem 34602MB
[2025-01-19 02:37:20 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][300/312]	eta 0:00:09 lr 0.003837	time 0.7198 (0.7535)	model_time 0.7197 (0.7479)	loss 3.9295 (3.7468)	grad_norm 0.8788 (1.2753/0.5386)	mem 34602MB
[2025-01-19 02:37:27 internimage_b_1k_224] (main.py 510): INFO Train: [38/300][310/312]	eta 0:00:01 lr 0.003837	time 0.7134 (0.7523)	model_time 0.7133 (0.7469)	loss 3.7431 (3.7497)	grad_norm 0.7895 (1.2668/0.5294)	mem 34602MB
[2025-01-19 02:37:28 internimage_b_1k_224] (main.py 519): INFO EPOCH 38 training takes 0:03:54
[2025-01-19 02:37:28 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_38.pth saving......
[2025-01-19 02:37:31 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_38.pth saved !!!
[2025-01-19 02:37:45 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.174 (14.174)	Loss 0.9691 (0.9691)	Acc@1 77.515 (77.515)	Acc@5 94.653 (94.653)	Mem 34602MB
[2025-01-19 02:37:53 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.978)	Loss 1.4323 (1.1691)	Acc@1 67.017 (73.324)	Acc@5 88.672 (92.006)	Mem 34602MB
[2025-01-19 02:37:53 internimage_b_1k_224] (main.py 575): INFO [Epoch:38] * Acc@1 73.311 Acc@5 92.113
[2025-01-19 02:37:53 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 73.3%
[2025-01-19 02:37:53 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 73.33%
[2025-01-19 02:38:07 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.163 (14.163)	Loss 4.5383 (4.5383)	Acc@1 17.920 (17.920)	Acc@5 37.646 (37.646)	Mem 34602MB
[2025-01-19 02:38:11 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.687)	Loss 4.6281 (4.4390)	Acc@1 16.064 (18.426)	Acc@5 34.937 (38.934)	Mem 34602MB
[2025-01-19 02:38:12 internimage_b_1k_224] (main.py 575): INFO [Epoch:38] * Acc@1 19.018 Acc@5 40.239
[2025-01-19 02:38:12 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 19.0%
[2025-01-19 02:38:12 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:38:16 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:38:16 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 19.02%
[2025-01-19 02:38:18 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][0/312]	eta 0:11:53 lr 0.003837	time 2.2853 (2.2853)	model_time 0.7455 (0.7455)	loss 4.2302 (4.2302)	grad_norm 0.7779 (0.7779/0.0000)	mem 34602MB
[2025-01-19 02:38:25 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][10/312]	eta 0:04:23 lr 0.003837	time 0.7378 (0.8719)	model_time 0.7376 (0.7316)	loss 4.4077 (3.5676)	grad_norm 1.1604 (1.1517/0.3822)	mem 34602MB
[2025-01-19 02:38:32 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][20/312]	eta 0:03:55 lr 0.003837	time 0.7171 (0.8068)	model_time 0.7170 (0.7331)	loss 2.5639 (3.5355)	grad_norm 1.3833 (1.2169/0.4063)	mem 34602MB
[2025-01-19 02:38:40 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][30/312]	eta 0:03:39 lr 0.003836	time 0.7152 (0.7797)	model_time 0.7150 (0.7297)	loss 2.4286 (3.4993)	grad_norm 0.8581 (1.2485/0.4213)	mem 34602MB
[2025-01-19 02:38:47 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][40/312]	eta 0:03:28 lr 0.003836	time 0.7206 (0.7661)	model_time 0.7202 (0.7282)	loss 2.5023 (3.5031)	grad_norm 1.2629 (1.2490/0.3944)	mem 34602MB
[2025-01-19 02:38:54 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][50/312]	eta 0:03:19 lr 0.003836	time 0.7197 (0.7611)	model_time 0.7195 (0.7306)	loss 3.7032 (3.5503)	grad_norm 2.7446 (1.3351/0.4701)	mem 34602MB
[2025-01-19 02:39:02 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][60/312]	eta 0:03:11 lr 0.003836	time 0.7118 (0.7590)	model_time 0.7117 (0.7335)	loss 4.4745 (3.5888)	grad_norm 1.0992 (1.2885/0.4540)	mem 34602MB
[2025-01-19 02:39:10 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][70/312]	eta 0:03:04 lr 0.003835	time 0.8117 (0.7631)	model_time 0.8115 (0.7410)	loss 2.7739 (3.6159)	grad_norm 0.8450 (1.2577/0.4312)	mem 34602MB
[2025-01-19 02:39:17 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][80/312]	eta 0:02:57 lr 0.003835	time 0.7186 (0.7652)	model_time 0.7184 (0.7458)	loss 4.5586 (3.6448)	grad_norm 1.3466 (1.2669/0.4293)	mem 34602MB
[2025-01-19 02:39:25 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][90/312]	eta 0:02:49 lr 0.003835	time 0.8103 (0.7648)	model_time 0.8101 (0.7476)	loss 3.2036 (3.6706)	grad_norm 1.2993 (1.2744/0.4397)	mem 34602MB
[2025-01-19 02:39:33 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][100/312]	eta 0:02:41 lr 0.003835	time 0.7200 (0.7627)	model_time 0.7195 (0.7471)	loss 3.5430 (3.6993)	grad_norm 0.6074 (1.2895/0.4657)	mem 34602MB
[2025-01-19 02:39:40 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][110/312]	eta 0:02:33 lr 0.003834	time 0.7163 (0.7597)	model_time 0.7159 (0.7455)	loss 3.9856 (3.6770)	grad_norm 1.3164 (1.2926/0.4563)	mem 34602MB
[2025-01-19 02:39:47 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][120/312]	eta 0:02:25 lr 0.003834	time 0.7174 (0.7569)	model_time 0.7172 (0.7438)	loss 3.1903 (3.7048)	grad_norm 0.8605 (1.2722/0.4453)	mem 34602MB
[2025-01-19 02:39:54 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][130/312]	eta 0:02:17 lr 0.003834	time 0.7246 (0.7545)	model_time 0.7244 (0.7424)	loss 4.2273 (3.7117)	grad_norm 0.9453 (1.2627/0.4422)	mem 34602MB
[2025-01-19 02:40:02 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][140/312]	eta 0:02:09 lr 0.003833	time 0.7237 (0.7534)	model_time 0.7235 (0.7422)	loss 4.0728 (3.7167)	grad_norm 1.2240 (1.3163/0.4993)	mem 34602MB
[2025-01-19 02:40:09 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][150/312]	eta 0:02:01 lr 0.003833	time 0.7686 (0.7521)	model_time 0.7682 (0.7416)	loss 3.6168 (3.7178)	grad_norm 0.8497 (1.3155/0.5007)	mem 34602MB
[2025-01-19 02:40:16 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][160/312]	eta 0:01:54 lr 0.003833	time 0.7195 (0.7505)	model_time 0.7190 (0.7406)	loss 2.6135 (3.7294)	grad_norm 0.8867 (1.2940/0.4944)	mem 34602MB
[2025-01-19 02:40:24 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][170/312]	eta 0:01:46 lr 0.003833	time 0.7168 (0.7497)	model_time 0.7166 (0.7403)	loss 4.2054 (3.7213)	grad_norm 1.0508 (1.2766/0.4873)	mem 34602MB
[2025-01-19 02:40:31 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][180/312]	eta 0:01:38 lr 0.003832	time 0.7294 (0.7486)	model_time 0.7292 (0.7398)	loss 3.3836 (3.7330)	grad_norm 1.5006 (1.2697/0.4841)	mem 34602MB
[2025-01-19 02:40:39 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][190/312]	eta 0:01:31 lr 0.003832	time 0.7155 (0.7502)	model_time 0.7151 (0.7418)	loss 3.8503 (3.7223)	grad_norm 2.2484 (1.2971/0.5121)	mem 34602MB
[2025-01-19 02:40:47 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][200/312]	eta 0:01:24 lr 0.003832	time 0.7164 (0.7518)	model_time 0.7163 (0.7438)	loss 2.9136 (3.7055)	grad_norm 1.6365 (1.3002/0.5042)	mem 34602MB
[2025-01-19 02:40:54 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][210/312]	eta 0:01:16 lr 0.003832	time 0.8421 (0.7523)	model_time 0.8420 (0.7447)	loss 4.1258 (3.6990)	grad_norm 2.2684 (1.3014/0.5020)	mem 34602MB
[2025-01-19 02:41:02 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][220/312]	eta 0:01:09 lr 0.003831	time 0.7242 (0.7521)	model_time 0.7237 (0.7448)	loss 3.0659 (3.6996)	grad_norm 1.4415 (1.3162/0.5025)	mem 34602MB
[2025-01-19 02:41:09 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][230/312]	eta 0:01:01 lr 0.003831	time 0.7234 (0.7513)	model_time 0.7232 (0.7443)	loss 3.7225 (3.6899)	grad_norm 1.0036 (1.3064/0.4972)	mem 34602MB
[2025-01-19 02:41:16 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][240/312]	eta 0:00:54 lr 0.003831	time 0.7186 (0.7501)	model_time 0.7185 (0.7434)	loss 4.5108 (3.6957)	grad_norm 0.8628 (1.3014/0.4958)	mem 34602MB
[2025-01-19 02:41:24 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][250/312]	eta 0:00:46 lr 0.003830	time 0.7182 (0.7489)	model_time 0.7178 (0.7425)	loss 4.5220 (3.6896)	grad_norm 1.0731 (1.2980/0.4960)	mem 34602MB
[2025-01-19 02:41:31 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][260/312]	eta 0:00:38 lr 0.003830	time 0.7431 (0.7485)	model_time 0.7429 (0.7422)	loss 3.8674 (3.6918)	grad_norm 2.6826 (1.3115/0.5016)	mem 34602MB
[2025-01-19 02:41:38 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][270/312]	eta 0:00:31 lr 0.003830	time 0.7421 (0.7476)	model_time 0.7416 (0.7416)	loss 3.8503 (3.6823)	grad_norm 1.1112 (1.3092/0.5071)	mem 34602MB
[2025-01-19 02:41:45 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][280/312]	eta 0:00:23 lr 0.003830	time 0.7433 (0.7468)	model_time 0.7429 (0.7410)	loss 3.7884 (3.6816)	grad_norm 2.3245 (1.3096/0.5074)	mem 34602MB
[2025-01-19 02:41:53 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][290/312]	eta 0:00:16 lr 0.003829	time 0.7169 (0.7465)	model_time 0.7167 (0.7408)	loss 4.1008 (3.6769)	grad_norm 1.8117 (1.3120/0.5014)	mem 34602MB
[2025-01-19 02:42:00 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][300/312]	eta 0:00:08 lr 0.003829	time 0.7120 (0.7456)	model_time 0.7119 (0.7402)	loss 4.0525 (3.6861)	grad_norm 0.9253 (1.3094/0.4969)	mem 34602MB
[2025-01-19 02:42:07 internimage_b_1k_224] (main.py 510): INFO Train: [39/300][310/312]	eta 0:00:01 lr 0.003829	time 0.8183 (0.7457)	model_time 0.8182 (0.7405)	loss 3.7416 (3.6852)	grad_norm 0.9291 (1.3029/0.4976)	mem 34602MB
[2025-01-19 02:42:08 internimage_b_1k_224] (main.py 519): INFO EPOCH 39 training takes 0:03:52
[2025-01-19 02:42:08 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_39.pth saving......
[2025-01-19 02:42:11 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_39.pth saved !!!
[2025-01-19 02:42:19 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.757 (7.757)	Loss 1.0795 (1.0795)	Acc@1 76.514 (76.514)	Acc@5 94.214 (94.214)	Mem 34602MB
[2025-01-19 02:42:22 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.975)	Loss 1.5070 (1.2253)	Acc@1 66.772 (73.335)	Acc@5 88.501 (92.150)	Mem 34602MB
[2025-01-19 02:42:22 internimage_b_1k_224] (main.py 575): INFO [Epoch:39] * Acc@1 73.369 Acc@5 92.206
[2025-01-19 02:42:22 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 73.4%
[2025-01-19 02:42:22 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 02:42:26 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 02:42:26 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 73.37%
[2025-01-19 02:42:33 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.071 (7.071)	Loss 4.2938 (4.2938)	Acc@1 20.996 (20.996)	Acc@5 43.164 (43.164)	Mem 34602MB
[2025-01-19 02:42:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.909)	Loss 4.4002 (4.2022)	Acc@1 19.922 (21.784)	Acc@5 39.185 (43.788)	Mem 34602MB
[2025-01-19 02:42:36 internimage_b_1k_224] (main.py 575): INFO [Epoch:39] * Acc@1 22.323 Acc@5 45.004
[2025-01-19 02:42:36 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 22.3%
[2025-01-19 02:42:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:42:40 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:42:40 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 22.32%
[2025-01-19 02:42:42 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][0/312]	eta 0:11:08 lr 0.003829	time 2.1411 (2.1411)	model_time 0.7418 (0.7418)	loss 3.4947 (3.4947)	grad_norm 1.0196 (1.0196/0.0000)	mem 34602MB
[2025-01-19 02:42:50 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][10/312]	eta 0:04:34 lr 0.003829	time 0.7316 (0.9079)	model_time 0.7315 (0.7804)	loss 3.0363 (3.5759)	grad_norm 1.8918 (1.1315/0.3654)	mem 34602MB
[2025-01-19 02:42:58 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][20/312]	eta 0:04:04 lr 0.003828	time 0.8113 (0.8370)	model_time 0.8111 (0.7701)	loss 4.0746 (3.7229)	grad_norm 2.7389 (1.7336/1.1395)	mem 34602MB
[2025-01-19 02:43:05 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][30/312]	eta 0:03:48 lr 0.003828	time 0.8124 (0.8089)	model_time 0.8119 (0.7635)	loss 4.0769 (3.7612)	grad_norm 0.8973 (1.5485/0.9850)	mem 34602MB
[2025-01-19 02:43:12 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][40/312]	eta 0:03:34 lr 0.003828	time 0.7281 (0.7879)	model_time 0.7277 (0.7535)	loss 3.8694 (3.8087)	grad_norm 0.8542 (1.4793/0.9001)	mem 34602MB
[2025-01-19 02:43:20 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][50/312]	eta 0:03:23 lr 0.003827	time 0.7208 (0.7778)	model_time 0.7204 (0.7500)	loss 2.8719 (3.8117)	grad_norm 1.3954 (1.3628/0.8472)	mem 34602MB
[2025-01-19 02:43:27 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][60/312]	eta 0:03:13 lr 0.003827	time 0.7181 (0.7695)	model_time 0.7177 (0.7463)	loss 4.7377 (3.7850)	grad_norm 1.0151 (1.3502/0.7983)	mem 34602MB
[2025-01-19 02:43:34 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][70/312]	eta 0:03:04 lr 0.003827	time 0.7154 (0.7630)	model_time 0.7153 (0.7430)	loss 4.2562 (3.7838)	grad_norm 1.7934 (1.2987/0.7601)	mem 34602MB
[2025-01-19 02:43:42 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][80/312]	eta 0:02:55 lr 0.003827	time 0.7210 (0.7584)	model_time 0.7209 (0.7408)	loss 3.0011 (3.7667)	grad_norm 0.8906 (1.2953/0.7419)	mem 34602MB
[2025-01-19 02:43:49 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][90/312]	eta 0:02:47 lr 0.003826	time 0.7368 (0.7545)	model_time 0.7364 (0.7388)	loss 4.0628 (3.7516)	grad_norm 1.1598 (1.3187/0.7532)	mem 34602MB
[2025-01-19 02:43:56 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][100/312]	eta 0:02:39 lr 0.003826	time 0.7145 (0.7527)	model_time 0.7144 (0.7385)	loss 3.0054 (3.7735)	grad_norm 0.6216 (1.3255/0.7274)	mem 34602MB
[2025-01-19 02:44:03 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][110/312]	eta 0:02:31 lr 0.003826	time 0.8252 (0.7513)	model_time 0.8250 (0.7383)	loss 4.0651 (3.7937)	grad_norm 1.0688 (1.3038/0.7006)	mem 34602MB
[2025-01-19 02:44:11 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][120/312]	eta 0:02:24 lr 0.003826	time 0.8058 (0.7514)	model_time 0.8056 (0.7394)	loss 4.3442 (3.7756)	grad_norm 0.9773 (1.2945/0.6820)	mem 34602MB
[2025-01-19 02:44:19 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][130/312]	eta 0:02:17 lr 0.003825	time 0.7238 (0.7531)	model_time 0.7236 (0.7421)	loss 3.6365 (3.7660)	grad_norm 0.8803 (1.2832/0.6632)	mem 34602MB
[2025-01-19 02:44:26 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][140/312]	eta 0:02:09 lr 0.003825	time 0.8438 (0.7538)	model_time 0.8437 (0.7435)	loss 3.2033 (3.7689)	grad_norm 2.4886 (1.2937/0.6600)	mem 34602MB
[2025-01-19 02:44:34 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][150/312]	eta 0:02:02 lr 0.003825	time 0.8145 (0.7535)	model_time 0.8144 (0.7439)	loss 4.1631 (3.7674)	grad_norm 1.0400 (1.3035/0.6605)	mem 34602MB
[2025-01-19 02:44:41 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][160/312]	eta 0:01:54 lr 0.003824	time 0.7414 (0.7520)	model_time 0.7410 (0.7430)	loss 4.1747 (3.7605)	grad_norm 0.8870 (1.2866/0.6471)	mem 34602MB
[2025-01-19 02:44:49 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][170/312]	eta 0:01:46 lr 0.003824	time 0.7292 (0.7512)	model_time 0.7288 (0.7427)	loss 3.8241 (3.7602)	grad_norm 1.1701 (1.3199/0.6682)	mem 34602MB
[2025-01-19 02:44:56 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][180/312]	eta 0:01:38 lr 0.003824	time 0.7331 (0.7500)	model_time 0.7329 (0.7419)	loss 4.0526 (3.7675)	grad_norm 1.1629 (1.3193/0.6586)	mem 34602MB
[2025-01-19 02:45:03 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][190/312]	eta 0:01:31 lr 0.003824	time 0.7245 (0.7488)	model_time 0.7240 (0.7411)	loss 4.2710 (3.7743)	grad_norm 0.9024 (1.2960/0.6505)	mem 34602MB
[2025-01-19 02:45:10 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][200/312]	eta 0:01:23 lr 0.003823	time 0.7204 (0.7477)	model_time 0.7200 (0.7404)	loss 4.1128 (3.7822)	grad_norm 1.0648 (1.2859/0.6373)	mem 34602MB
[2025-01-19 02:45:18 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][210/312]	eta 0:01:16 lr 0.003823	time 0.7278 (0.7471)	model_time 0.7276 (0.7401)	loss 4.3183 (3.7844)	grad_norm 1.5272 (1.2900/0.6270)	mem 34602MB
[2025-01-19 02:45:25 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][220/312]	eta 0:01:08 lr 0.003823	time 0.7549 (0.7466)	model_time 0.7545 (0.7399)	loss 3.8906 (3.7864)	grad_norm 0.8408 (1.2809/0.6163)	mem 34602MB
[2025-01-19 02:45:33 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][230/312]	eta 0:01:01 lr 0.003823	time 0.8222 (0.7464)	model_time 0.8217 (0.7400)	loss 3.8580 (3.7837)	grad_norm 1.1200 (1.2840/0.6091)	mem 34602MB
[2025-01-19 02:45:40 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][240/312]	eta 0:00:53 lr 0.003822	time 0.8166 (0.7469)	model_time 0.8162 (0.7407)	loss 4.3524 (3.7954)	grad_norm 1.1761 (1.2966/0.6105)	mem 34602MB
[2025-01-19 02:45:48 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][250/312]	eta 0:00:46 lr 0.003822	time 0.8394 (0.7482)	model_time 0.8389 (0.7423)	loss 3.0823 (3.7972)	grad_norm 1.1217 (1.2885/0.6016)	mem 34602MB
[2025-01-19 02:45:55 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][260/312]	eta 0:00:38 lr 0.003822	time 0.7188 (0.7485)	model_time 0.7184 (0.7428)	loss 4.8756 (3.7994)	grad_norm 2.2856 (1.2821/0.5972)	mem 34602MB
[2025-01-19 02:46:03 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][270/312]	eta 0:00:31 lr 0.003821	time 0.8084 (0.7488)	model_time 0.8082 (0.7433)	loss 3.3612 (3.7878)	grad_norm 0.8887 (1.2880/0.5934)	mem 34602MB
[2025-01-19 02:46:10 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][280/312]	eta 0:00:23 lr 0.003821	time 0.7724 (0.7483)	model_time 0.7720 (0.7429)	loss 2.8734 (3.7856)	grad_norm 0.7096 (1.2856/0.5877)	mem 34602MB
[2025-01-19 02:46:18 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][290/312]	eta 0:00:16 lr 0.003821	time 0.8223 (0.7479)	model_time 0.8222 (0.7427)	loss 4.9057 (3.7975)	grad_norm 1.0200 (1.2827/0.5828)	mem 34602MB
[2025-01-19 02:46:25 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][300/312]	eta 0:00:08 lr 0.003821	time 0.7139 (0.7470)	model_time 0.7138 (0.7419)	loss 3.2477 (3.7871)	grad_norm 1.8827 (1.2797/0.5786)	mem 34602MB
[2025-01-19 02:46:32 internimage_b_1k_224] (main.py 510): INFO Train: [40/300][310/312]	eta 0:00:01 lr 0.003820	time 0.7121 (0.7459)	model_time 0.7120 (0.7411)	loss 3.6912 (3.7788)	grad_norm 0.6918 (1.2760/0.5807)	mem 34602MB
[2025-01-19 02:46:33 internimage_b_1k_224] (main.py 519): INFO EPOCH 40 training takes 0:03:52
[2025-01-19 02:46:33 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_40.pth saving......
[2025-01-19 02:46:36 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_40.pth saved !!!
[2025-01-19 02:46:43 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.186 (7.186)	Loss 1.0130 (1.0130)	Acc@1 77.197 (77.197)	Acc@5 95.142 (95.142)	Mem 34602MB
[2025-01-19 02:46:46 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.922)	Loss 1.4667 (1.2287)	Acc@1 68.799 (73.178)	Acc@5 88.989 (92.090)	Mem 34602MB
[2025-01-19 02:46:46 internimage_b_1k_224] (main.py 575): INFO [Epoch:40] * Acc@1 73.185 Acc@5 92.157
[2025-01-19 02:46:46 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 73.2%
[2025-01-19 02:46:46 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 73.37%
[2025-01-19 02:46:56 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.089 (9.089)	Loss 4.0513 (4.0513)	Acc@1 25.342 (25.342)	Acc@5 48.047 (48.047)	Mem 34602MB
[2025-01-19 02:47:00 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.231)	Loss 4.1813 (3.9726)	Acc@1 22.754 (25.257)	Acc@5 43.579 (48.413)	Mem 34602MB
[2025-01-19 02:47:00 internimage_b_1k_224] (main.py 575): INFO [Epoch:40] * Acc@1 25.814 Acc@5 49.520
[2025-01-19 02:47:00 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 25.8%
[2025-01-19 02:47:00 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:47:04 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:47:04 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 25.81%
[2025-01-19 02:47:06 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][0/312]	eta 0:10:57 lr 0.003820	time 2.1059 (2.1059)	model_time 0.7415 (0.7415)	loss 3.0378 (3.0378)	grad_norm 1.2802 (1.2802/0.0000)	mem 34602MB
[2025-01-19 02:47:14 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][10/312]	eta 0:04:19 lr 0.003820	time 0.7293 (0.8601)	model_time 0.7289 (0.7357)	loss 2.6186 (3.4656)	grad_norm 0.8141 (1.1633/0.3834)	mem 34602MB
[2025-01-19 02:47:21 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][20/312]	eta 0:03:54 lr 0.003820	time 0.7499 (0.8018)	model_time 0.7497 (0.7365)	loss 3.9251 (3.6827)	grad_norm 3.4235 (1.2999/0.5795)	mem 34602MB
[2025-01-19 02:47:28 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][30/312]	eta 0:03:39 lr 0.003819	time 0.7159 (0.7787)	model_time 0.7155 (0.7343)	loss 3.7628 (3.6861)	grad_norm 0.8225 (1.3876/0.5842)	mem 34602MB
[2025-01-19 02:47:36 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][40/312]	eta 0:03:29 lr 0.003819	time 0.7394 (0.7712)	model_time 0.7393 (0.7376)	loss 4.4640 (3.7508)	grad_norm 0.8437 (1.3147/0.5580)	mem 34602MB
[2025-01-19 02:47:43 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][50/312]	eta 0:03:21 lr 0.003819	time 0.7179 (0.7706)	model_time 0.7177 (0.7435)	loss 3.9355 (3.7072)	grad_norm 0.8582 (1.2905/0.5225)	mem 34602MB
[2025-01-19 02:47:51 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][60/312]	eta 0:03:14 lr 0.003819	time 0.7390 (0.7713)	model_time 0.7386 (0.7486)	loss 4.3928 (3.7579)	grad_norm 1.0213 (1.2722/0.5001)	mem 34602MB
[2025-01-19 02:47:59 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][70/312]	eta 0:03:06 lr 0.003818	time 0.7202 (0.7694)	model_time 0.7198 (0.7498)	loss 3.3418 (3.6993)	grad_norm 1.2709 (1.3917/0.6767)	mem 34602MB
[2025-01-19 02:48:06 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][80/312]	eta 0:02:58 lr 0.003818	time 0.7409 (0.7673)	model_time 0.7405 (0.7501)	loss 3.3617 (3.7294)	grad_norm 1.1648 (1.3712/0.6591)	mem 34602MB
[2025-01-19 02:48:14 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][90/312]	eta 0:02:49 lr 0.003818	time 0.7253 (0.7637)	model_time 0.7251 (0.7483)	loss 4.0232 (3.7275)	grad_norm 1.0274 (1.3473/0.6276)	mem 34602MB
[2025-01-19 02:48:21 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][100/312]	eta 0:02:41 lr 0.003818	time 0.7253 (0.7613)	model_time 0.7248 (0.7474)	loss 4.3928 (3.7371)	grad_norm 3.2439 (1.3481/0.6358)	mem 34602MB
[2025-01-19 02:48:28 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][110/312]	eta 0:02:33 lr 0.003817	time 0.7619 (0.7586)	model_time 0.7618 (0.7460)	loss 4.5302 (3.7471)	grad_norm 1.3816 (1.3311/0.6164)	mem 34602MB
[2025-01-19 02:48:36 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][120/312]	eta 0:02:25 lr 0.003817	time 0.7471 (0.7563)	model_time 0.7469 (0.7446)	loss 4.5627 (3.7594)	grad_norm 1.9111 (1.3243/0.5997)	mem 34602MB
[2025-01-19 02:48:43 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][130/312]	eta 0:02:17 lr 0.003817	time 0.7232 (0.7548)	model_time 0.7230 (0.7440)	loss 3.9768 (3.7827)	grad_norm 1.7799 (1.3233/0.5841)	mem 34602MB
[2025-01-19 02:48:50 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][140/312]	eta 0:02:09 lr 0.003816	time 0.7518 (0.7536)	model_time 0.7516 (0.7435)	loss 3.7366 (3.7666)	grad_norm 0.9975 (1.3095/0.5722)	mem 34602MB
[2025-01-19 02:48:58 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][150/312]	eta 0:02:01 lr 0.003816	time 0.7178 (0.7521)	model_time 0.7177 (0.7427)	loss 4.8722 (3.7749)	grad_norm 1.2088 (1.3181/0.5786)	mem 34602MB
[2025-01-19 02:49:05 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][160/312]	eta 0:01:54 lr 0.003816	time 0.7379 (0.7513)	model_time 0.7374 (0.7424)	loss 3.5294 (3.7681)	grad_norm 2.3995 (1.3246/0.5720)	mem 34602MB
[2025-01-19 02:49:13 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][170/312]	eta 0:01:46 lr 0.003816	time 0.7157 (0.7534)	model_time 0.7153 (0.7450)	loss 4.0908 (3.7745)	grad_norm 0.7828 (1.3189/0.5644)	mem 34602MB
[2025-01-19 02:49:21 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][180/312]	eta 0:01:39 lr 0.003815	time 0.7216 (0.7549)	model_time 0.7215 (0.7470)	loss 3.7959 (3.7727)	grad_norm 1.6708 (1.3233/0.5525)	mem 34602MB
[2025-01-19 02:49:28 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][190/312]	eta 0:01:32 lr 0.003815	time 0.7184 (0.7547)	model_time 0.7180 (0.7472)	loss 3.1685 (3.7592)	grad_norm 0.6407 (1.3246/0.5466)	mem 34602MB
[2025-01-19 02:49:36 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][200/312]	eta 0:01:24 lr 0.003815	time 0.7276 (0.7541)	model_time 0.7275 (0.7470)	loss 4.4826 (3.7499)	grad_norm 1.8191 (1.3181/0.5419)	mem 34602MB
[2025-01-19 02:49:43 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][210/312]	eta 0:01:16 lr 0.003814	time 0.7232 (0.7526)	model_time 0.7230 (0.7458)	loss 3.0503 (3.7373)	grad_norm 1.9352 (1.3290/0.5453)	mem 34602MB
[2025-01-19 02:49:50 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][220/312]	eta 0:01:09 lr 0.003814	time 0.7152 (0.7516)	model_time 0.7148 (0.7450)	loss 2.6486 (3.7486)	grad_norm 1.5389 (1.3156/0.5384)	mem 34602MB
[2025-01-19 02:49:57 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][230/312]	eta 0:01:01 lr 0.003814	time 0.7273 (0.7503)	model_time 0.7271 (0.7441)	loss 4.6717 (3.7732)	grad_norm 1.6364 (1.3202/0.5422)	mem 34602MB
[2025-01-19 02:50:05 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][240/312]	eta 0:00:53 lr 0.003814	time 0.7163 (0.7496)	model_time 0.7159 (0.7435)	loss 4.5050 (3.7714)	grad_norm 1.5095 (1.3259/0.5424)	mem 34602MB
[2025-01-19 02:50:12 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][250/312]	eta 0:00:46 lr 0.003813	time 0.7562 (0.7494)	model_time 0.7560 (0.7436)	loss 4.5961 (3.7755)	grad_norm 1.2481 (1.3161/0.5349)	mem 34602MB
[2025-01-19 02:50:20 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][260/312]	eta 0:00:38 lr 0.003813	time 0.7549 (0.7487)	model_time 0.7548 (0.7431)	loss 3.5994 (3.7815)	grad_norm 1.1425 (1.3166/0.5308)	mem 34602MB
[2025-01-19 02:50:27 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][270/312]	eta 0:00:31 lr 0.003813	time 0.7307 (0.7483)	model_time 0.7306 (0.7429)	loss 4.6041 (3.7767)	grad_norm 1.5156 (1.3139/0.5249)	mem 34602MB
[2025-01-19 02:50:34 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][280/312]	eta 0:00:23 lr 0.003812	time 0.7168 (0.7480)	model_time 0.7164 (0.7428)	loss 2.5608 (3.7665)	grad_norm 0.9277 (1.3082/0.5186)	mem 34602MB
[2025-01-19 02:50:42 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][290/312]	eta 0:00:16 lr 0.003812	time 0.7168 (0.7488)	model_time 0.7164 (0.7438)	loss 4.5630 (3.7616)	grad_norm 0.7265 (1.3007/0.5140)	mem 34602MB
[2025-01-19 02:50:50 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][300/312]	eta 0:00:08 lr 0.003812	time 0.7935 (0.7498)	model_time 0.7934 (0.7449)	loss 3.9396 (3.7683)	grad_norm 1.7129 (1.2913/0.5124)	mem 34602MB
[2025-01-19 02:50:57 internimage_b_1k_224] (main.py 510): INFO Train: [41/300][310/312]	eta 0:00:01 lr 0.003812	time 0.7240 (0.7494)	model_time 0.7239 (0.7447)	loss 4.5004 (3.7717)	grad_norm 1.2060 (1.3228/0.5713)	mem 34602MB
[2025-01-19 02:50:58 internimage_b_1k_224] (main.py 519): INFO EPOCH 41 training takes 0:03:53
[2025-01-19 02:50:58 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_41.pth saving......
[2025-01-19 02:51:01 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_41.pth saved !!!
[2025-01-19 02:51:09 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.442 (7.442)	Loss 1.0207 (1.0207)	Acc@1 78.003 (78.003)	Acc@5 94.653 (94.653)	Mem 34602MB
[2025-01-19 02:51:12 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.946)	Loss 1.5097 (1.2461)	Acc@1 67.529 (73.675)	Acc@5 88.794 (92.174)	Mem 34602MB
[2025-01-19 02:51:12 internimage_b_1k_224] (main.py 575): INFO [Epoch:41] * Acc@1 73.698 Acc@5 92.242
[2025-01-19 02:51:12 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 73.7%
[2025-01-19 02:51:12 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 02:51:15 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 02:51:15 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 73.70%
[2025-01-19 02:51:23 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.381 (7.381)	Loss 3.8190 (3.8190)	Acc@1 28.931 (28.931)	Acc@5 52.002 (52.002)	Mem 34602MB
[2025-01-19 02:51:25 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.928)	Loss 3.9806 (3.7589)	Acc@1 25.952 (28.687)	Acc@5 47.607 (52.459)	Mem 34602MB
[2025-01-19 02:51:26 internimage_b_1k_224] (main.py 575): INFO [Epoch:41] * Acc@1 29.227 Acc@5 53.533
[2025-01-19 02:51:26 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 29.2%
[2025-01-19 02:51:26 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:51:30 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:51:30 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 29.23%
[2025-01-19 02:51:32 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][0/312]	eta 0:11:11 lr 0.003812	time 2.1510 (2.1510)	model_time 0.7612 (0.7612)	loss 4.4190 (4.4190)	grad_norm 1.1713 (1.1713/0.0000)	mem 34602MB
[2025-01-19 02:51:40 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][10/312]	eta 0:04:23 lr 0.003811	time 0.7252 (0.8728)	model_time 0.7251 (0.7462)	loss 3.5703 (3.5977)	grad_norm 1.8040 (1.1540/0.3833)	mem 34602MB
[2025-01-19 02:51:47 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][20/312]	eta 0:03:55 lr 0.003811	time 0.7239 (0.8049)	model_time 0.7237 (0.7384)	loss 4.7179 (3.6946)	grad_norm 0.9004 (1.2699/0.5069)	mem 34602MB
[2025-01-19 02:51:54 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][30/312]	eta 0:03:39 lr 0.003811	time 0.7209 (0.7794)	model_time 0.7204 (0.7342)	loss 3.8308 (3.6546)	grad_norm 1.1599 (1.2947/0.4552)	mem 34602MB
[2025-01-19 02:52:01 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][40/312]	eta 0:03:29 lr 0.003810	time 0.7518 (0.7686)	model_time 0.7517 (0.7344)	loss 4.0769 (3.6626)	grad_norm 1.4364 (1.3060/0.4290)	mem 34602MB
[2025-01-19 02:52:09 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][50/312]	eta 0:03:19 lr 0.003810	time 0.7182 (0.7610)	model_time 0.7180 (0.7333)	loss 3.4865 (3.7594)	grad_norm 1.4479 (1.3592/0.4372)	mem 34602MB
[2025-01-19 02:52:16 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][60/312]	eta 0:03:10 lr 0.003810	time 0.7467 (0.7577)	model_time 0.7465 (0.7345)	loss 3.9655 (3.7135)	grad_norm 1.5057 (1.3935/0.4509)	mem 34602MB
[2025-01-19 02:52:23 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][70/312]	eta 0:03:02 lr 0.003810	time 0.7182 (0.7530)	model_time 0.7181 (0.7331)	loss 4.6156 (3.7068)	grad_norm 1.3273 (1.3494/0.4441)	mem 34602MB
[2025-01-19 02:52:31 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][80/312]	eta 0:02:54 lr 0.003809	time 0.7478 (0.7511)	model_time 0.7477 (0.7336)	loss 3.5749 (3.7275)	grad_norm 0.9630 (1.3116/0.4451)	mem 34602MB
[2025-01-19 02:52:38 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][90/312]	eta 0:02:46 lr 0.003809	time 0.7182 (0.7492)	model_time 0.7180 (0.7335)	loss 3.6255 (3.6991)	grad_norm 1.1012 (1.3087/0.4427)	mem 34602MB
[2025-01-19 02:52:46 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][100/312]	eta 0:02:39 lr 0.003809	time 0.7902 (0.7519)	model_time 0.7898 (0.7377)	loss 3.4852 (3.6948)	grad_norm 0.9203 (1.3220/0.4403)	mem 34602MB
[2025-01-19 02:52:54 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][110/312]	eta 0:02:32 lr 0.003808	time 0.7244 (0.7548)	model_time 0.7242 (0.7419)	loss 3.8325 (3.7433)	grad_norm 1.3305 (1.3032/0.4360)	mem 34602MB
[2025-01-19 02:53:01 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][120/312]	eta 0:02:25 lr 0.003808	time 0.8762 (0.7555)	model_time 0.8761 (0.7436)	loss 3.9435 (3.7466)	grad_norm 0.7281 (1.2719/0.4344)	mem 34602MB
[2025-01-19 02:53:09 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][130/312]	eta 0:02:17 lr 0.003808	time 0.7233 (0.7551)	model_time 0.7228 (0.7441)	loss 3.4351 (3.7471)	grad_norm 0.9412 (1.2722/0.4322)	mem 34602MB
[2025-01-19 02:53:16 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][140/312]	eta 0:02:09 lr 0.003808	time 0.7254 (0.7530)	model_time 0.7249 (0.7428)	loss 3.7697 (3.7260)	grad_norm 0.9387 (1.3290/0.5557)	mem 34602MB
[2025-01-19 02:53:23 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][150/312]	eta 0:02:01 lr 0.003807	time 0.7378 (0.7518)	model_time 0.7226 (0.7421)	loss 3.5914 (3.7260)	grad_norm 0.7817 (1.3260/0.5607)	mem 34602MB
[2025-01-19 02:53:31 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][160/312]	eta 0:01:54 lr 0.003807	time 0.7938 (0.7508)	model_time 0.7934 (0.7417)	loss 4.0392 (3.7272)	grad_norm 0.9085 (1.3010/0.5540)	mem 34602MB
[2025-01-19 02:53:38 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][170/312]	eta 0:01:46 lr 0.003807	time 0.7330 (0.7492)	model_time 0.7329 (0.7406)	loss 3.2977 (3.7148)	grad_norm 1.8073 (1.3009/0.5498)	mem 34602MB
[2025-01-19 02:53:45 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][180/312]	eta 0:01:38 lr 0.003806	time 0.7234 (0.7484)	model_time 0.7230 (0.7403)	loss 2.3939 (3.7117)	grad_norm 1.0726 (1.3099/0.5403)	mem 34602MB
[2025-01-19 02:53:53 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][190/312]	eta 0:01:31 lr 0.003806	time 0.7394 (0.7472)	model_time 0.7390 (0.7395)	loss 2.7964 (3.7281)	grad_norm 1.5925 (1.3204/0.5479)	mem 34602MB
[2025-01-19 02:54:00 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][200/312]	eta 0:01:23 lr 0.003806	time 0.8036 (0.7465)	model_time 0.8035 (0.7391)	loss 2.6852 (3.7157)	grad_norm 1.2085 (1.3200/0.5474)	mem 34602MB
[2025-01-19 02:54:07 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][210/312]	eta 0:01:16 lr 0.003806	time 0.7418 (0.7462)	model_time 0.7414 (0.7391)	loss 4.4373 (3.7028)	grad_norm 2.8865 (1.3348/0.5647)	mem 34602MB
[2025-01-19 02:54:15 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][220/312]	eta 0:01:08 lr 0.003805	time 0.7998 (0.7474)	model_time 0.7997 (0.7406)	loss 4.0601 (3.7066)	grad_norm 2.0865 (1.3364/0.5570)	mem 34602MB
[2025-01-19 02:54:23 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][230/312]	eta 0:01:01 lr 0.003805	time 0.8086 (0.7483)	model_time 0.8081 (0.7418)	loss 4.5918 (3.7017)	grad_norm 1.0183 (1.3218/0.5538)	mem 34602MB
[2025-01-19 02:54:30 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][240/312]	eta 0:00:53 lr 0.003805	time 0.8204 (0.7485)	model_time 0.8202 (0.7422)	loss 4.1816 (3.7038)	grad_norm 0.5883 (1.3248/0.5522)	mem 34602MB
[2025-01-19 02:54:38 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][250/312]	eta 0:00:46 lr 0.003804	time 0.7179 (0.7489)	model_time 0.7178 (0.7430)	loss 4.1614 (3.7057)	grad_norm 0.9228 (1.3229/0.5441)	mem 34602MB
[2025-01-19 02:54:45 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][260/312]	eta 0:00:38 lr 0.003804	time 0.7317 (0.7483)	model_time 0.7312 (0.7425)	loss 3.9857 (3.7031)	grad_norm 1.4543 (1.3112/0.5412)	mem 34602MB
[2025-01-19 02:54:52 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][270/312]	eta 0:00:31 lr 0.003804	time 0.7342 (0.7473)	model_time 0.7341 (0.7418)	loss 4.0749 (3.7158)	grad_norm 1.4509 (1.3286/0.5545)	mem 34602MB
[2025-01-19 02:55:00 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][280/312]	eta 0:00:23 lr 0.003804	time 0.7153 (0.7466)	model_time 0.7151 (0.7412)	loss 3.0127 (3.7212)	grad_norm 2.3588 (1.3320/0.5509)	mem 34602MB
[2025-01-19 02:55:07 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][290/312]	eta 0:00:16 lr 0.003803	time 0.7171 (0.7459)	model_time 0.7167 (0.7407)	loss 3.0470 (3.7144)	grad_norm 0.8514 (1.3219/0.5477)	mem 34602MB
[2025-01-19 02:55:14 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][300/312]	eta 0:00:08 lr 0.003803	time 0.7094 (0.7454)	model_time 0.7092 (0.7404)	loss 3.7126 (3.6976)	grad_norm 1.0054 (1.3213/0.5448)	mem 34602MB
[2025-01-19 02:55:21 internimage_b_1k_224] (main.py 510): INFO Train: [42/300][310/312]	eta 0:00:01 lr 0.003803	time 0.7122 (0.7447)	model_time 0.7121 (0.7398)	loss 4.9210 (3.6957)	grad_norm 1.2680 (1.3384/0.5549)	mem 34602MB
[2025-01-19 02:55:22 internimage_b_1k_224] (main.py 519): INFO EPOCH 42 training takes 0:03:52
[2025-01-19 02:55:22 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_42.pth saving......
[2025-01-19 02:55:25 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_42.pth saved !!!
[2025-01-19 02:55:33 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.290 (7.290)	Loss 0.9780 (0.9780)	Acc@1 78.662 (78.662)	Acc@5 95.166 (95.166)	Mem 34602MB
[2025-01-19 02:55:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.931)	Loss 1.4548 (1.1998)	Acc@1 67.188 (73.901)	Acc@5 89.355 (92.376)	Mem 34602MB
[2025-01-19 02:55:36 internimage_b_1k_224] (main.py 575): INFO [Epoch:42] * Acc@1 73.856 Acc@5 92.432
[2025-01-19 02:55:36 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 73.9%
[2025-01-19 02:55:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 02:55:39 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 02:55:39 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 73.86%
[2025-01-19 02:55:46 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.276 (7.276)	Loss 3.5957 (3.5957)	Acc@1 32.739 (32.739)	Acc@5 55.859 (55.859)	Mem 34602MB
[2025-01-19 02:55:49 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.928)	Loss 3.7920 (3.5551)	Acc@1 28.857 (32.069)	Acc@5 50.903 (56.485)	Mem 34602MB
[2025-01-19 02:55:50 internimage_b_1k_224] (main.py 575): INFO [Epoch:42] * Acc@1 32.626 Acc@5 57.506
[2025-01-19 02:55:50 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 32.6%
[2025-01-19 02:55:50 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:55:54 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:55:54 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 32.63%
[2025-01-19 02:55:56 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][0/312]	eta 0:10:54 lr 0.003803	time 2.0988 (2.0988)	model_time 0.7676 (0.7676)	loss 3.8833 (3.8833)	grad_norm 1.5032 (1.5032/0.0000)	mem 34602MB
[2025-01-19 02:56:03 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][10/312]	eta 0:04:17 lr 0.003802	time 0.7327 (0.8516)	model_time 0.7325 (0.7302)	loss 4.3532 (3.5797)	grad_norm 1.4247 (1.0775/0.2693)	mem 34602MB
[2025-01-19 02:56:10 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][20/312]	eta 0:03:54 lr 0.003802	time 0.8062 (0.8016)	model_time 0.8057 (0.7379)	loss 4.4255 (3.8672)	grad_norm 1.6026 (1.4061/0.8082)	mem 34602MB
[2025-01-19 02:56:18 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][30/312]	eta 0:03:43 lr 0.003802	time 0.8294 (0.7942)	model_time 0.8292 (0.7510)	loss 3.9537 (3.8856)	grad_norm 1.0992 (1.2859/0.6965)	mem 34602MB
[2025-01-19 02:56:26 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][40/312]	eta 0:03:34 lr 0.003801	time 0.8606 (0.7890)	model_time 0.8601 (0.7561)	loss 3.4547 (3.8566)	grad_norm 2.0040 (1.2475/0.6424)	mem 34602MB
[2025-01-19 02:56:34 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][50/312]	eta 0:03:25 lr 0.003801	time 0.8171 (0.7837)	model_time 0.8169 (0.7573)	loss 4.0380 (3.8568)	grad_norm 0.8909 (1.2085/0.5953)	mem 34602MB
[2025-01-19 02:56:41 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][60/312]	eta 0:03:16 lr 0.003801	time 0.7274 (0.7784)	model_time 0.7272 (0.7563)	loss 3.5874 (3.8200)	grad_norm 1.1874 (1.1705/0.5574)	mem 34602MB
[2025-01-19 02:56:48 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][70/312]	eta 0:03:06 lr 0.003801	time 0.7440 (0.7709)	model_time 0.7436 (0.7518)	loss 3.5729 (3.7769)	grad_norm 0.9294 (1.1942/0.5483)	mem 34602MB
[2025-01-19 02:56:56 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][80/312]	eta 0:02:57 lr 0.003800	time 0.7339 (0.7654)	model_time 0.7335 (0.7486)	loss 3.3246 (3.7811)	grad_norm 0.9102 (1.1555/0.5254)	mem 34602MB
[2025-01-19 02:57:03 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][90/312]	eta 0:02:49 lr 0.003800	time 0.7243 (0.7615)	model_time 0.7239 (0.7465)	loss 4.0817 (3.7781)	grad_norm 1.3231 (1.2022/0.5393)	mem 34602MB
[2025-01-19 02:57:10 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][100/312]	eta 0:02:40 lr 0.003800	time 0.7195 (0.7585)	model_time 0.7193 (0.7449)	loss 3.8842 (3.7700)	grad_norm 2.4616 (1.2536/0.5548)	mem 34602MB
[2025-01-19 02:57:17 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][110/312]	eta 0:02:32 lr 0.003799	time 0.7246 (0.7555)	model_time 0.7245 (0.7432)	loss 3.8109 (3.7134)	grad_norm 0.8678 (1.2301/0.5377)	mem 34602MB
[2025-01-19 02:57:25 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][120/312]	eta 0:02:24 lr 0.003799	time 0.7504 (0.7529)	model_time 0.7502 (0.7416)	loss 3.9729 (3.7251)	grad_norm 0.8039 (1.2333/0.5256)	mem 34602MB
[2025-01-19 02:57:32 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][130/312]	eta 0:02:16 lr 0.003799	time 0.7169 (0.7517)	model_time 0.7165 (0.7412)	loss 4.2418 (3.7169)	grad_norm 0.7380 (1.2394/0.5378)	mem 34602MB
[2025-01-19 02:57:39 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][140/312]	eta 0:02:09 lr 0.003799	time 0.8095 (0.7512)	model_time 0.8094 (0.7414)	loss 2.6511 (3.7221)	grad_norm 1.1710 (1.2391/0.5403)	mem 34602MB
[2025-01-19 02:57:47 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][150/312]	eta 0:02:01 lr 0.003798	time 0.8351 (0.7531)	model_time 0.8347 (0.7439)	loss 3.7252 (3.7021)	grad_norm 0.8732 (1.2344/0.5386)	mem 34602MB
[2025-01-19 02:57:55 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][160/312]	eta 0:01:54 lr 0.003798	time 0.8123 (0.7543)	model_time 0.8118 (0.7456)	loss 4.4230 (3.7097)	grad_norm 0.8933 (1.2126/0.5299)	mem 34602MB
[2025-01-19 02:58:03 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][170/312]	eta 0:01:47 lr 0.003798	time 0.8412 (0.7554)	model_time 0.8408 (0.7472)	loss 3.9082 (3.7056)	grad_norm 1.4705 (1.1962/0.5210)	mem 34602MB
[2025-01-19 02:58:10 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][180/312]	eta 0:01:39 lr 0.003797	time 0.7184 (0.7550)	model_time 0.7183 (0.7472)	loss 4.3566 (3.6962)	grad_norm 1.7038 (1.1962/0.5088)	mem 34602MB
[2025-01-19 02:58:17 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][190/312]	eta 0:01:31 lr 0.003797	time 0.7287 (0.7534)	model_time 0.7285 (0.7461)	loss 3.1988 (3.6934)	grad_norm 1.1115 (1.1953/0.5056)	mem 34602MB
[2025-01-19 02:58:25 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][200/312]	eta 0:01:24 lr 0.003797	time 0.7222 (0.7522)	model_time 0.7218 (0.7452)	loss 3.0323 (3.6976)	grad_norm 0.8233 (1.1932/0.4988)	mem 34602MB
[2025-01-19 02:58:32 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][210/312]	eta 0:01:16 lr 0.003797	time 0.7452 (0.7509)	model_time 0.7450 (0.7443)	loss 4.2305 (3.7021)	grad_norm 3.4568 (1.2074/0.5246)	mem 34602MB
[2025-01-19 02:58:39 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][220/312]	eta 0:01:09 lr 0.003796	time 0.7279 (0.7503)	model_time 0.7274 (0.7439)	loss 4.4218 (3.6959)	grad_norm 0.8321 (1.2189/0.5587)	mem 34602MB
[2025-01-19 02:58:47 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][230/312]	eta 0:01:01 lr 0.003796	time 0.7282 (0.7494)	model_time 0.7280 (0.7432)	loss 4.0904 (3.6760)	grad_norm 0.6782 (1.2045/0.5517)	mem 34602MB
[2025-01-19 02:58:54 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][240/312]	eta 0:00:53 lr 0.003796	time 0.7410 (0.7485)	model_time 0.7408 (0.7426)	loss 3.8148 (3.6602)	grad_norm 2.8890 (1.2147/0.5552)	mem 34602MB
[2025-01-19 02:59:01 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][250/312]	eta 0:00:46 lr 0.003795	time 0.7188 (0.7477)	model_time 0.7184 (0.7420)	loss 4.1470 (3.6657)	grad_norm 1.1288 (1.2380/0.6287)	mem 34602MB
[2025-01-19 02:59:09 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][260/312]	eta 0:00:38 lr 0.003795	time 0.8033 (0.7477)	model_time 0.8032 (0.7422)	loss 3.0946 (3.6698)	grad_norm 1.2454 (1.2371/0.6217)	mem 34602MB
[2025-01-19 02:59:16 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][270/312]	eta 0:00:31 lr 0.003795	time 0.8123 (0.7485)	model_time 0.8118 (0.7432)	loss 2.7854 (3.6734)	grad_norm 1.6955 (1.2479/0.6224)	mem 34602MB
[2025-01-19 02:59:24 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][280/312]	eta 0:00:23 lr 0.003794	time 0.8323 (0.7490)	model_time 0.8319 (0.7439)	loss 3.9895 (3.6723)	grad_norm 2.1963 (1.2500/0.6163)	mem 34602MB
[2025-01-19 02:59:32 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][290/312]	eta 0:00:16 lr 0.003794	time 0.7288 (0.7493)	model_time 0.7286 (0.7443)	loss 2.9920 (3.6673)	grad_norm 1.4402 (1.2477/0.6110)	mem 34602MB
[2025-01-19 02:59:39 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][300/312]	eta 0:00:08 lr 0.003794	time 0.7147 (0.7495)	model_time 0.7146 (0.7447)	loss 4.3659 (3.6761)	grad_norm 0.8517 (1.2422/0.6056)	mem 34602MB
[2025-01-19 02:59:46 internimage_b_1k_224] (main.py 510): INFO Train: [43/300][310/312]	eta 0:00:01 lr 0.003794	time 0.7194 (0.7484)	model_time 0.7193 (0.7437)	loss 3.6855 (3.6793)	grad_norm 1.0727 (1.2537/0.6110)	mem 34602MB
[2025-01-19 02:59:47 internimage_b_1k_224] (main.py 519): INFO EPOCH 43 training takes 0:03:53
[2025-01-19 02:59:47 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_43.pth saving......
[2025-01-19 02:59:50 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_43.pth saved !!!
[2025-01-19 03:00:06 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.501 (15.501)	Loss 0.9858 (0.9858)	Acc@1 78.198 (78.198)	Acc@5 95.068 (95.068)	Mem 34602MB
[2025-01-19 03:00:13 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.044)	Loss 1.4590 (1.2023)	Acc@1 69.043 (74.119)	Acc@5 89.331 (92.396)	Mem 34602MB
[2025-01-19 03:00:13 internimage_b_1k_224] (main.py 575): INFO [Epoch:43] * Acc@1 74.240 Acc@5 92.548
[2025-01-19 03:00:13 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 74.2%
[2025-01-19 03:00:13 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 03:00:16 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 03:00:16 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 74.24%
[2025-01-19 03:00:28 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 11.608 (11.608)	Loss 3.3901 (3.3901)	Acc@1 36.279 (36.279)	Acc@5 59.351 (59.351)	Mem 34602MB
[2025-01-19 03:00:31 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.393)	Loss 3.6171 (3.3663)	Acc@1 31.665 (35.409)	Acc@5 54.419 (60.063)	Mem 34602MB
[2025-01-19 03:00:32 internimage_b_1k_224] (main.py 575): INFO [Epoch:43] * Acc@1 35.895 Acc@5 60.984
[2025-01-19 03:00:32 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 35.9%
[2025-01-19 03:00:32 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:00:36 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:00:36 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 35.89%
[2025-01-19 03:00:38 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][0/312]	eta 0:11:17 lr 0.003794	time 2.1701 (2.1701)	model_time 0.7381 (0.7381)	loss 3.6689 (3.6689)	grad_norm 2.2053 (2.2053/0.0000)	mem 34602MB
[2025-01-19 03:00:45 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][10/312]	eta 0:04:19 lr 0.003793	time 0.7327 (0.8576)	model_time 0.7326 (0.7272)	loss 3.5128 (3.6436)	grad_norm 0.9373 (1.2811/0.4244)	mem 34602MB
[2025-01-19 03:00:52 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][20/312]	eta 0:03:53 lr 0.003793	time 0.7239 (0.8001)	model_time 0.7237 (0.7316)	loss 3.4351 (3.7339)	grad_norm 0.9214 (1.1583/0.3676)	mem 34602MB
[2025-01-19 03:01:00 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][30/312]	eta 0:03:39 lr 0.003793	time 0.7192 (0.7767)	model_time 0.7188 (0.7302)	loss 4.1007 (3.7604)	grad_norm 1.0348 (1.1463/0.3468)	mem 34602MB
[2025-01-19 03:01:07 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][40/312]	eta 0:03:28 lr 0.003792	time 0.7359 (0.7648)	model_time 0.7357 (0.7295)	loss 3.8243 (3.7706)	grad_norm 0.9578 (1.1934/0.3990)	mem 34602MB
[2025-01-19 03:01:14 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][50/312]	eta 0:03:18 lr 0.003792	time 0.7287 (0.7565)	model_time 0.7285 (0.7280)	loss 4.3879 (3.8326)	grad_norm 0.9491 (1.2140/0.4078)	mem 34602MB
[2025-01-19 03:01:21 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][60/312]	eta 0:03:09 lr 0.003792	time 0.7191 (0.7526)	model_time 0.7186 (0.7288)	loss 4.6833 (3.8043)	grad_norm 0.5917 (1.2079/0.3948)	mem 34602MB
[2025-01-19 03:01:29 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][70/312]	eta 0:03:01 lr 0.003791	time 0.7149 (0.7505)	model_time 0.7148 (0.7299)	loss 4.5498 (3.8007)	grad_norm 2.3662 (1.2251/0.4220)	mem 34602MB
[2025-01-19 03:01:37 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][80/312]	eta 0:02:55 lr 0.003791	time 0.8116 (0.7547)	model_time 0.8114 (0.7367)	loss 2.3645 (3.7480)	grad_norm 1.6247 (1.2906/0.4936)	mem 34602MB
[2025-01-19 03:01:45 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][90/312]	eta 0:02:48 lr 0.003791	time 0.8027 (0.7579)	model_time 0.8026 (0.7418)	loss 3.5575 (3.7225)	grad_norm 2.0585 (1.2694/0.4852)	mem 34602MB
[2025-01-19 03:01:52 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][100/312]	eta 0:02:40 lr 0.003791	time 0.7236 (0.7575)	model_time 0.7234 (0.7430)	loss 3.5307 (3.7050)	grad_norm 1.0641 (1.2937/0.4949)	mem 34602MB
[2025-01-19 03:02:00 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][110/312]	eta 0:02:32 lr 0.003790	time 0.7213 (0.7571)	model_time 0.7209 (0.7438)	loss 3.8282 (3.6988)	grad_norm 0.8721 (1.2686/0.4847)	mem 34602MB
[2025-01-19 03:02:07 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][120/312]	eta 0:02:24 lr 0.003790	time 0.7305 (0.7548)	model_time 0.7300 (0.7426)	loss 3.8323 (3.6987)	grad_norm 0.9419 (1.2534/0.4711)	mem 34602MB
[2025-01-19 03:02:14 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][130/312]	eta 0:02:17 lr 0.003790	time 0.7410 (0.7528)	model_time 0.7407 (0.7415)	loss 3.5368 (3.7203)	grad_norm 0.7768 (1.2321/0.4622)	mem 34602MB
[2025-01-19 03:02:22 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][140/312]	eta 0:02:09 lr 0.003789	time 0.7162 (0.7516)	model_time 0.7157 (0.7411)	loss 4.5696 (3.7159)	grad_norm 0.7159 (1.2222/0.4580)	mem 34602MB
[2025-01-19 03:02:29 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][150/312]	eta 0:02:01 lr 0.003789	time 0.7167 (0.7505)	model_time 0.7164 (0.7407)	loss 4.0523 (3.7130)	grad_norm 1.9557 (1.2321/0.4644)	mem 34602MB
[2025-01-19 03:02:36 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][160/312]	eta 0:01:53 lr 0.003789	time 0.7412 (0.7491)	model_time 0.7408 (0.7399)	loss 4.0777 (3.7065)	grad_norm 1.0545 (1.2607/0.4970)	mem 34602MB
[2025-01-19 03:02:44 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][170/312]	eta 0:01:46 lr 0.003788	time 0.7288 (0.7483)	model_time 0.7287 (0.7396)	loss 3.7271 (3.7194)	grad_norm 1.0507 (1.2403/0.4913)	mem 34602MB
[2025-01-19 03:02:51 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][180/312]	eta 0:01:38 lr 0.003788	time 0.7166 (0.7475)	model_time 0.7164 (0.7392)	loss 3.9826 (3.7089)	grad_norm 2.2113 (1.2426/0.4848)	mem 34602MB
[2025-01-19 03:02:58 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][190/312]	eta 0:01:31 lr 0.003788	time 0.7191 (0.7469)	model_time 0.7190 (0.7390)	loss 2.6865 (3.7048)	grad_norm 1.3858 (1.2488/0.4835)	mem 34602MB
[2025-01-19 03:03:06 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][200/312]	eta 0:01:23 lr 0.003788	time 0.8091 (0.7494)	model_time 0.8089 (0.7419)	loss 3.9384 (3.6973)	grad_norm 2.2957 (1.2611/0.4907)	mem 34602MB
[2025-01-19 03:03:14 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][210/312]	eta 0:01:16 lr 0.003787	time 0.7975 (0.7500)	model_time 0.7973 (0.7428)	loss 4.0832 (3.6948)	grad_norm 0.7924 (1.2599/0.4892)	mem 34602MB
[2025-01-19 03:03:21 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][220/312]	eta 0:01:09 lr 0.003787	time 0.7169 (0.7508)	model_time 0.7164 (0.7439)	loss 3.6521 (3.6907)	grad_norm 0.8991 (1.2531/0.4818)	mem 34602MB
[2025-01-19 03:03:29 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][230/312]	eta 0:01:01 lr 0.003787	time 0.7158 (0.7518)	model_time 0.7156 (0.7453)	loss 3.2917 (3.6812)	grad_norm 0.8913 (1.2445/0.4751)	mem 34602MB
[2025-01-19 03:03:37 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][240/312]	eta 0:00:54 lr 0.003786	time 0.7208 (0.7508)	model_time 0.7204 (0.7445)	loss 3.9446 (3.6837)	grad_norm 1.4431 (1.2417/0.4699)	mem 34602MB
[2025-01-19 03:03:44 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][250/312]	eta 0:00:46 lr 0.003786	time 0.7222 (0.7500)	model_time 0.7221 (0.7439)	loss 3.7001 (3.6743)	grad_norm 2.0224 (1.2687/0.5362)	mem 34602MB
[2025-01-19 03:03:51 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][260/312]	eta 0:00:38 lr 0.003786	time 0.7377 (0.7494)	model_time 0.7376 (0.7435)	loss 4.0465 (3.6821)	grad_norm 1.4132 (1.2629/0.5303)	mem 34602MB
[2025-01-19 03:03:58 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][270/312]	eta 0:00:31 lr 0.003785	time 0.7270 (0.7487)	model_time 0.7266 (0.7431)	loss 4.1404 (3.6984)	grad_norm 1.0393 (1.2528/0.5263)	mem 34602MB
[2025-01-19 03:04:06 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][280/312]	eta 0:00:23 lr 0.003785	time 0.7172 (0.7482)	model_time 0.7170 (0.7427)	loss 4.1390 (3.7012)	grad_norm 1.4276 (1.2452/0.5209)	mem 34602MB
[2025-01-19 03:04:13 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][290/312]	eta 0:00:16 lr 0.003785	time 0.7159 (0.7475)	model_time 0.7157 (0.7422)	loss 4.3863 (3.7069)	grad_norm 1.0441 (1.2534/0.5382)	mem 34602MB
[2025-01-19 03:04:20 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][300/312]	eta 0:00:08 lr 0.003785	time 0.7121 (0.7470)	model_time 0.7119 (0.7418)	loss 3.4104 (3.7076)	grad_norm 0.7631 (1.2537/0.5380)	mem 34602MB
[2025-01-19 03:04:28 internimage_b_1k_224] (main.py 510): INFO Train: [44/300][310/312]	eta 0:00:01 lr 0.003784	time 0.7136 (0.7461)	model_time 0.7135 (0.7412)	loss 3.2078 (3.7086)	grad_norm 1.3426 (1.2608/0.5396)	mem 34602MB
[2025-01-19 03:04:28 internimage_b_1k_224] (main.py 519): INFO EPOCH 44 training takes 0:03:52
[2025-01-19 03:04:28 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_44.pth saving......
[2025-01-19 03:04:31 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_44.pth saved !!!
[2025-01-19 03:04:39 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.212 (7.212)	Loss 0.9712 (0.9712)	Acc@1 78.687 (78.687)	Acc@5 94.995 (94.995)	Mem 34602MB
[2025-01-19 03:04:42 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.936)	Loss 1.4281 (1.1548)	Acc@1 66.602 (74.316)	Acc@5 89.575 (92.478)	Mem 34602MB
[2025-01-19 03:04:42 internimage_b_1k_224] (main.py 575): INFO [Epoch:44] * Acc@1 74.276 Acc@5 92.518
[2025-01-19 03:04:42 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 74.3%
[2025-01-19 03:04:42 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 03:04:46 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 03:04:46 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 74.28%
[2025-01-19 03:04:53 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.362 (7.362)	Loss 3.1938 (3.1938)	Acc@1 39.771 (39.771)	Acc@5 63.452 (63.452)	Mem 34602MB
[2025-01-19 03:04:56 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.939)	Loss 3.4514 (3.1893)	Acc@1 34.204 (38.661)	Acc@5 57.446 (63.519)	Mem 34602MB
[2025-01-19 03:04:56 internimage_b_1k_224] (main.py 575): INFO [Epoch:44] * Acc@1 39.056 Acc@5 64.337
[2025-01-19 03:04:56 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 39.1%
[2025-01-19 03:04:56 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:05:00 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:05:00 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 39.06%
[2025-01-19 03:05:02 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][0/312]	eta 0:11:45 lr 0.003784	time 2.2625 (2.2625)	model_time 0.7478 (0.7478)	loss 2.4990 (2.4990)	grad_norm 0.9812 (0.9812/0.0000)	mem 34602MB
[2025-01-19 03:05:10 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][10/312]	eta 0:04:40 lr 0.003784	time 0.8265 (0.9300)	model_time 0.8259 (0.7919)	loss 4.0480 (3.7336)	grad_norm 0.7294 (1.2927/0.6424)	mem 34602MB
[2025-01-19 03:05:18 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][20/312]	eta 0:04:09 lr 0.003784	time 0.8164 (0.8548)	model_time 0.8162 (0.7824)	loss 3.8369 (3.6225)	grad_norm 1.2774 (1.1295/0.5159)	mem 34602MB
[2025-01-19 03:05:26 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][30/312]	eta 0:03:53 lr 0.003783	time 0.8025 (0.8286)	model_time 0.8021 (0.7793)	loss 4.2243 (3.7444)	grad_norm 1.2366 (1.2308/0.5202)	mem 34602MB
[2025-01-19 03:05:33 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][40/312]	eta 0:03:40 lr 0.003783	time 0.7180 (0.8104)	model_time 0.7179 (0.7731)	loss 4.4637 (3.7640)	grad_norm 1.0126 (1.2192/0.4884)	mem 34602MB
[2025-01-19 03:05:41 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][50/312]	eta 0:03:28 lr 0.003783	time 0.7159 (0.7947)	model_time 0.7158 (0.7646)	loss 3.7033 (3.8130)	grad_norm 1.3893 (1.2886/0.5368)	mem 34602MB
[2025-01-19 03:05:48 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][60/312]	eta 0:03:17 lr 0.003782	time 0.7290 (0.7837)	model_time 0.7285 (0.7585)	loss 2.5539 (3.7867)	grad_norm 1.0165 (1.2427/0.5192)	mem 34602MB
[2025-01-19 03:05:55 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][70/312]	eta 0:03:07 lr 0.003782	time 0.7365 (0.7767)	model_time 0.7363 (0.7550)	loss 4.4572 (3.7587)	grad_norm 1.1160 (1.2259/0.5007)	mem 34602MB
[2025-01-19 03:06:03 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][80/312]	eta 0:02:58 lr 0.003782	time 0.7159 (0.7714)	model_time 0.7158 (0.7523)	loss 2.7993 (3.7329)	grad_norm 1.1947 (1.2351/0.5105)	mem 34602MB
[2025-01-19 03:06:10 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][90/312]	eta 0:02:50 lr 0.003781	time 0.7264 (0.7667)	model_time 0.7262 (0.7497)	loss 3.0226 (3.7454)	grad_norm 0.9933 (1.2185/0.4886)	mem 34602MB
[2025-01-19 03:06:17 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][100/312]	eta 0:02:41 lr 0.003781	time 0.7365 (0.7629)	model_time 0.7363 (0.7476)	loss 3.7682 (3.7441)	grad_norm 0.9764 (1.2085/0.4756)	mem 34602MB
[2025-01-19 03:06:24 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][110/312]	eta 0:02:33 lr 0.003781	time 0.7369 (0.7601)	model_time 0.7368 (0.7461)	loss 2.6935 (3.7611)	grad_norm 0.8480 (1.2509/0.5012)	mem 34602MB
[2025-01-19 03:06:32 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][120/312]	eta 0:02:25 lr 0.003781	time 0.7164 (0.7575)	model_time 0.7158 (0.7446)	loss 2.8019 (3.7537)	grad_norm 1.1361 (1.2445/0.4924)	mem 34602MB
[2025-01-19 03:06:40 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][130/312]	eta 0:02:18 lr 0.003780	time 0.8196 (0.7593)	model_time 0.8194 (0.7474)	loss 2.5476 (3.7447)	grad_norm 1.6543 (1.2864/0.5352)	mem 34602MB
[2025-01-19 03:06:47 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][140/312]	eta 0:02:10 lr 0.003780	time 0.8147 (0.7604)	model_time 0.8146 (0.7493)	loss 2.5941 (3.7325)	grad_norm 0.9967 (1.2775/0.5288)	mem 34602MB
[2025-01-19 03:06:55 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][150/312]	eta 0:02:03 lr 0.003780	time 0.8421 (0.7628)	model_time 0.8420 (0.7524)	loss 4.0586 (3.7532)	grad_norm 1.6216 (1.2692/0.5156)	mem 34602MB
[2025-01-19 03:07:03 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][160/312]	eta 0:01:55 lr 0.003779	time 0.7222 (0.7629)	model_time 0.7217 (0.7531)	loss 3.5232 (3.7609)	grad_norm 0.7464 (1.2630/0.5056)	mem 34602MB
[2025-01-19 03:07:10 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][170/312]	eta 0:01:48 lr 0.003779	time 0.7347 (0.7606)	model_time 0.7346 (0.7514)	loss 3.7636 (3.7275)	grad_norm 0.9352 (1.2459/0.4964)	mem 34602MB
[2025-01-19 03:07:17 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][180/312]	eta 0:01:40 lr 0.003779	time 0.7154 (0.7585)	model_time 0.7149 (0.7498)	loss 3.6963 (3.7159)	grad_norm 1.0723 (1.2594/0.5080)	mem 34602MB
[2025-01-19 03:07:25 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][190/312]	eta 0:01:32 lr 0.003778	time 0.7211 (0.7575)	model_time 0.7210 (0.7492)	loss 4.1829 (3.7123)	grad_norm 1.3246 (1.2617/0.5019)	mem 34602MB
[2025-01-19 03:07:32 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][200/312]	eta 0:01:24 lr 0.003778	time 0.7159 (0.7559)	model_time 0.7155 (0.7480)	loss 3.8494 (3.7188)	grad_norm 1.6490 (1.3017/0.5545)	mem 34602MB
[2025-01-19 03:07:39 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][210/312]	eta 0:01:16 lr 0.003778	time 0.7231 (0.7542)	model_time 0.7227 (0.7467)	loss 3.8213 (3.7219)	grad_norm 1.0529 (1.2898/0.5484)	mem 34602MB
[2025-01-19 03:07:47 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][220/312]	eta 0:01:09 lr 0.003778	time 0.7697 (0.7532)	model_time 0.7696 (0.7459)	loss 3.7445 (3.7177)	grad_norm 0.7457 (1.2956/0.5575)	mem 34602MB
[2025-01-19 03:07:54 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][230/312]	eta 0:01:01 lr 0.003777	time 0.7826 (0.7522)	model_time 0.7821 (0.7453)	loss 3.9903 (3.7131)	grad_norm 0.8128 (1.3059/0.5535)	mem 34602MB
[2025-01-19 03:08:01 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][240/312]	eta 0:00:54 lr 0.003777	time 0.7159 (0.7516)	model_time 0.7158 (0.7450)	loss 3.1657 (3.7081)	grad_norm 1.2723 (1.2963/0.5459)	mem 34602MB
[2025-01-19 03:08:09 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][250/312]	eta 0:00:46 lr 0.003777	time 0.8034 (0.7522)	model_time 0.8032 (0.7458)	loss 4.3967 (3.7151)	grad_norm 0.7697 (1.2884/0.5400)	mem 34602MB
[2025-01-19 03:08:17 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][260/312]	eta 0:00:39 lr 0.003776	time 0.8414 (0.7541)	model_time 0.8409 (0.7479)	loss 4.1779 (3.7136)	grad_norm 0.8225 (1.2907/0.5383)	mem 34602MB
[2025-01-19 03:08:25 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][270/312]	eta 0:00:31 lr 0.003776	time 0.8105 (0.7551)	model_time 0.8103 (0.7492)	loss 2.9206 (3.7021)	grad_norm 0.7519 (1.2831/0.5326)	mem 34602MB
[2025-01-19 03:08:32 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][280/312]	eta 0:00:24 lr 0.003776	time 0.7311 (0.7551)	model_time 0.7306 (0.7494)	loss 3.7888 (3.7052)	grad_norm 0.9318 (1.2741/0.5297)	mem 34602MB
[2025-01-19 03:08:40 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][290/312]	eta 0:00:16 lr 0.003775	time 0.7305 (0.7542)	model_time 0.7303 (0.7486)	loss 3.8873 (3.7054)	grad_norm 1.1869 (1.2864/0.5499)	mem 34602MB
[2025-01-19 03:08:47 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][300/312]	eta 0:00:09 lr 0.003775	time 0.7093 (0.7533)	model_time 0.7092 (0.7479)	loss 3.6583 (3.7049)	grad_norm 1.4164 (1.2821/0.5445)	mem 34602MB
[2025-01-19 03:08:54 internimage_b_1k_224] (main.py 510): INFO Train: [45/300][310/312]	eta 0:00:01 lr 0.003775	time 0.7151 (0.7525)	model_time 0.7150 (0.7472)	loss 3.6937 (3.7070)	grad_norm 1.1750 (1.2689/0.5367)	mem 34602MB
[2025-01-19 03:08:55 internimage_b_1k_224] (main.py 519): INFO EPOCH 45 training takes 0:03:54
[2025-01-19 03:08:55 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_45.pth saving......
[2025-01-19 03:08:58 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_45.pth saved !!!
[2025-01-19 03:09:06 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.646 (7.646)	Loss 0.9566 (0.9566)	Acc@1 78.955 (78.955)	Acc@5 94.897 (94.897)	Mem 34602MB
[2025-01-19 03:09:09 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.957)	Loss 1.4079 (1.1738)	Acc@1 69.336 (74.339)	Acc@5 89.893 (92.578)	Mem 34602MB
[2025-01-19 03:09:09 internimage_b_1k_224] (main.py 575): INFO [Epoch:45] * Acc@1 74.362 Acc@5 92.672
[2025-01-19 03:09:09 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 74.4%
[2025-01-19 03:09:09 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 03:09:12 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 03:09:12 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 74.36%
[2025-01-19 03:09:19 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.460 (7.460)	Loss 3.0181 (3.0181)	Acc@1 42.773 (42.773)	Acc@5 66.748 (66.748)	Mem 34602MB
[2025-01-19 03:09:22 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.951)	Loss 3.3033 (3.0317)	Acc@1 36.572 (41.479)	Acc@5 60.815 (66.606)	Mem 34602MB
[2025-01-19 03:09:23 internimage_b_1k_224] (main.py 575): INFO [Epoch:45] * Acc@1 41.847 Acc@5 67.346
[2025-01-19 03:09:23 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 41.8%
[2025-01-19 03:09:23 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:09:27 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:09:27 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 41.85%
[2025-01-19 03:09:29 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][0/312]	eta 0:10:59 lr 0.003775	time 2.1129 (2.1129)	model_time 0.7730 (0.7730)	loss 3.5058 (3.5058)	grad_norm 0.6949 (0.6949/0.0000)	mem 34602MB
[2025-01-19 03:09:36 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][10/312]	eta 0:04:18 lr 0.003774	time 0.7256 (0.8564)	model_time 0.7252 (0.7343)	loss 4.0624 (3.6479)	grad_norm 1.3464 (1.1567/0.3493)	mem 34602MB
[2025-01-19 03:09:43 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][20/312]	eta 0:03:52 lr 0.003774	time 0.7283 (0.7963)	model_time 0.7278 (0.7321)	loss 3.4467 (3.7078)	grad_norm 0.9954 (1.3046/0.4900)	mem 34602MB
[2025-01-19 03:09:51 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][30/312]	eta 0:03:38 lr 0.003774	time 0.7323 (0.7759)	model_time 0.7321 (0.7323)	loss 4.2555 (3.7652)	grad_norm 1.3276 (1.2425/0.4477)	mem 34602MB
[2025-01-19 03:09:58 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][40/312]	eta 0:03:28 lr 0.003773	time 0.7234 (0.7655)	model_time 0.7233 (0.7324)	loss 3.2869 (3.7448)	grad_norm 0.8607 (1.3330/0.5610)	mem 34602MB
[2025-01-19 03:10:06 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][50/312]	eta 0:03:19 lr 0.003773	time 0.7398 (0.7605)	model_time 0.7396 (0.7338)	loss 3.9631 (3.8018)	grad_norm 0.8744 (1.2782/0.5307)	mem 34602MB
[2025-01-19 03:10:13 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][60/312]	eta 0:03:11 lr 0.003773	time 0.7217 (0.7610)	model_time 0.7215 (0.7387)	loss 3.5635 (3.7994)	grad_norm 2.4081 (1.2931/0.5410)	mem 34602MB
[2025-01-19 03:10:21 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][70/312]	eta 0:03:04 lr 0.003773	time 0.7299 (0.7623)	model_time 0.7297 (0.7430)	loss 4.4685 (3.7887)	grad_norm 1.1668 (1.2492/0.5172)	mem 34602MB
[2025-01-19 03:10:29 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][80/312]	eta 0:02:57 lr 0.003772	time 0.8275 (0.7654)	model_time 0.8274 (0.7484)	loss 3.6018 (3.7973)	grad_norm 2.7229 (1.2570/0.5180)	mem 34602MB
[2025-01-19 03:10:36 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][90/312]	eta 0:02:49 lr 0.003772	time 0.7273 (0.7624)	model_time 0.7271 (0.7473)	loss 3.0089 (3.7762)	grad_norm 1.0709 (1.2444/0.5060)	mem 34602MB
[2025-01-19 03:10:43 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][100/312]	eta 0:02:41 lr 0.003772	time 0.7290 (0.7595)	model_time 0.7288 (0.7458)	loss 4.6397 (3.7844)	grad_norm 1.5324 (1.2487/0.4995)	mem 34602MB
[2025-01-19 03:10:51 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][110/312]	eta 0:02:32 lr 0.003771	time 0.7251 (0.7567)	model_time 0.7247 (0.7442)	loss 4.1166 (3.7831)	grad_norm 1.1846 (1.2499/0.4845)	mem 34602MB
[2025-01-19 03:10:58 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][120/312]	eta 0:02:24 lr 0.003771	time 0.7377 (0.7540)	model_time 0.7372 (0.7425)	loss 3.8361 (3.8160)	grad_norm 0.8905 (1.2747/0.5229)	mem 34602MB
[2025-01-19 03:11:05 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][130/312]	eta 0:02:16 lr 0.003771	time 0.7213 (0.7521)	model_time 0.7211 (0.7414)	loss 3.7565 (3.8058)	grad_norm 0.9699 (1.2536/0.5101)	mem 34602MB
[2025-01-19 03:11:13 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][140/312]	eta 0:02:09 lr 0.003770	time 0.7331 (0.7510)	model_time 0.7326 (0.7411)	loss 2.8641 (3.8160)	grad_norm 1.0775 (1.2526/0.4959)	mem 34602MB
[2025-01-19 03:11:20 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][150/312]	eta 0:02:01 lr 0.003770	time 0.7554 (0.7503)	model_time 0.7550 (0.7410)	loss 2.4930 (3.8029)	grad_norm 0.9919 (1.2579/0.4896)	mem 34602MB
[2025-01-19 03:11:27 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][160/312]	eta 0:01:53 lr 0.003770	time 0.7342 (0.7491)	model_time 0.7338 (0.7404)	loss 3.7692 (3.8013)	grad_norm 0.9385 (1.2782/0.5030)	mem 34602MB
[2025-01-19 03:11:35 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][170/312]	eta 0:01:46 lr 0.003769	time 0.7227 (0.7489)	model_time 0.7222 (0.7407)	loss 3.0533 (3.8121)	grad_norm 1.0805 (1.2942/0.5167)	mem 34602MB
[2025-01-19 03:11:43 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][180/312]	eta 0:01:39 lr 0.003769	time 0.8019 (0.7502)	model_time 0.8017 (0.7424)	loss 3.2541 (3.8140)	grad_norm 1.9691 (1.3025/0.5208)	mem 34602MB
[2025-01-19 03:11:50 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][190/312]	eta 0:01:31 lr 0.003769	time 0.7229 (0.7517)	model_time 0.7227 (0.7443)	loss 4.3239 (3.8102)	grad_norm 1.9065 (1.3142/0.5231)	mem 34602MB
[2025-01-19 03:11:59 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][200/312]	eta 0:01:24 lr 0.003768	time 0.9697 (0.7552)	model_time 0.9692 (0.7481)	loss 4.5912 (3.8093)	grad_norm 1.5370 (1.3049/0.5148)	mem 34602MB
[2025-01-19 03:12:06 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][210/312]	eta 0:01:17 lr 0.003768	time 0.7595 (0.7551)	model_time 0.7593 (0.7484)	loss 2.5697 (3.7981)	grad_norm 0.7334 (1.2923/0.5116)	mem 34602MB
[2025-01-19 03:12:14 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][220/312]	eta 0:01:09 lr 0.003768	time 0.7485 (0.7545)	model_time 0.7484 (0.7481)	loss 4.3973 (3.7949)	grad_norm 1.0154 (1.2894/0.5054)	mem 34602MB
[2025-01-19 03:12:21 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][230/312]	eta 0:01:01 lr 0.003768	time 0.7453 (0.7534)	model_time 0.7448 (0.7472)	loss 4.2946 (3.7962)	grad_norm 0.9905 (1.2875/0.5042)	mem 34602MB
[2025-01-19 03:12:28 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][240/312]	eta 0:00:54 lr 0.003767	time 0.7341 (0.7523)	model_time 0.7336 (0.7464)	loss 3.6709 (3.7956)	grad_norm 0.8640 (1.2987/0.5247)	mem 34602MB
[2025-01-19 03:12:35 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][250/312]	eta 0:00:46 lr 0.003767	time 0.7251 (0.7513)	model_time 0.7250 (0.7456)	loss 4.0537 (3.7997)	grad_norm 1.4225 (1.2913/0.5186)	mem 34602MB
[2025-01-19 03:12:43 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][260/312]	eta 0:00:39 lr 0.003767	time 0.7296 (0.7506)	model_time 0.7292 (0.7451)	loss 4.5454 (3.8123)	grad_norm 1.2730 (1.2906/0.5154)	mem 34602MB
[2025-01-19 03:12:50 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][270/312]	eta 0:00:31 lr 0.003766	time 0.7136 (0.7498)	model_time 0.7131 (0.7444)	loss 3.3107 (3.8108)	grad_norm 1.7819 (1.2938/0.5125)	mem 34602MB
[2025-01-19 03:12:57 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][280/312]	eta 0:00:23 lr 0.003766	time 0.7358 (0.7489)	model_time 0.7356 (0.7437)	loss 2.2966 (3.8023)	grad_norm 2.0762 (1.2913/0.5113)	mem 34602MB
[2025-01-19 03:13:05 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][290/312]	eta 0:00:16 lr 0.003766	time 0.8140 (0.7486)	model_time 0.8135 (0.7436)	loss 4.5547 (3.7945)	grad_norm 0.6873 (1.2885/0.5082)	mem 34602MB
[2025-01-19 03:13:12 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][300/312]	eta 0:00:08 lr 0.003765	time 0.8209 (0.7489)	model_time 0.8208 (0.7441)	loss 4.3958 (3.7845)	grad_norm 1.4256 (1.3020/0.5185)	mem 34602MB
[2025-01-19 03:13:20 internimage_b_1k_224] (main.py 510): INFO Train: [46/300][310/312]	eta 0:00:01 lr 0.003765	time 0.7956 (0.7492)	model_time 0.7955 (0.7445)	loss 2.8707 (3.7813)	grad_norm 0.8560 (1.2978/0.5191)	mem 34602MB
[2025-01-19 03:13:21 internimage_b_1k_224] (main.py 519): INFO EPOCH 46 training takes 0:03:53
[2025-01-19 03:13:21 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_46.pth saving......
[2025-01-19 03:13:24 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_46.pth saved !!!
[2025-01-19 03:13:31 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.018 (7.018)	Loss 0.9459 (0.9459)	Acc@1 78.491 (78.491)	Acc@5 94.849 (94.849)	Mem 34602MB
[2025-01-19 03:13:34 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.901)	Loss 1.4143 (1.1776)	Acc@1 69.116 (74.518)	Acc@5 89.575 (92.520)	Mem 34602MB
[2025-01-19 03:13:34 internimage_b_1k_224] (main.py 575): INFO [Epoch:46] * Acc@1 74.438 Acc@5 92.590
[2025-01-19 03:13:34 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 74.4%
[2025-01-19 03:13:34 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 03:13:37 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 03:13:37 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 74.44%
[2025-01-19 03:13:45 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.206 (7.206)	Loss 2.8581 (2.8581)	Acc@1 46.191 (46.191)	Acc@5 69.678 (69.678)	Mem 34602MB
[2025-01-19 03:13:47 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.913)	Loss 3.1697 (2.8884)	Acc@1 39.087 (44.101)	Acc@5 63.428 (69.303)	Mem 34602MB
[2025-01-19 03:13:48 internimage_b_1k_224] (main.py 575): INFO [Epoch:46] * Acc@1 44.470 Acc@5 69.950
[2025-01-19 03:13:48 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 44.5%
[2025-01-19 03:13:48 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:13:52 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:13:52 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 44.47%
[2025-01-19 03:13:54 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][0/312]	eta 0:11:23 lr 0.003765	time 2.1892 (2.1892)	model_time 0.7517 (0.7517)	loss 4.1288 (4.1288)	grad_norm 0.8969 (0.8969/0.0000)	mem 34602MB
[2025-01-19 03:14:02 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][10/312]	eta 0:04:35 lr 0.003765	time 0.7999 (0.9136)	model_time 0.7997 (0.7826)	loss 3.7858 (3.5996)	grad_norm 1.1882 (1.0172/0.1291)	mem 34602MB
[2025-01-19 03:14:09 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][20/312]	eta 0:04:02 lr 0.003764	time 0.7213 (0.8321)	model_time 0.7209 (0.7633)	loss 3.7463 (3.5051)	grad_norm 0.6585 (1.2476/0.6156)	mem 34602MB
[2025-01-19 03:14:16 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][30/312]	eta 0:03:45 lr 0.003764	time 0.7161 (0.7996)	model_time 0.7159 (0.7529)	loss 2.5524 (3.4170)	grad_norm 0.9796 (1.1856/0.5315)	mem 34602MB
[2025-01-19 03:14:24 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][40/312]	eta 0:03:33 lr 0.003764	time 0.7175 (0.7862)	model_time 0.7171 (0.7508)	loss 3.9569 (3.4375)	grad_norm 1.7986 (1.2469/0.5473)	mem 34602MB
[2025-01-19 03:14:31 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][50/312]	eta 0:03:23 lr 0.003763	time 0.7501 (0.7759)	model_time 0.7497 (0.7473)	loss 4.5433 (3.4832)	grad_norm 1.6457 (1.2144/0.5154)	mem 34602MB
[2025-01-19 03:14:38 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][60/312]	eta 0:03:13 lr 0.003763	time 0.7209 (0.7670)	model_time 0.7207 (0.7431)	loss 4.5573 (3.4909)	grad_norm 1.4215 (1.1894/0.4842)	mem 34602MB
[2025-01-19 03:14:46 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][70/312]	eta 0:03:04 lr 0.003763	time 0.7363 (0.7617)	model_time 0.7359 (0.7411)	loss 3.5212 (3.5003)	grad_norm 2.5037 (1.2404/0.4980)	mem 34602MB
[2025-01-19 03:14:53 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][80/312]	eta 0:02:55 lr 0.003762	time 0.7405 (0.7583)	model_time 0.7403 (0.7402)	loss 3.9952 (3.5251)	grad_norm 2.1915 (1.2907/0.5404)	mem 34602MB
[2025-01-19 03:15:00 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][90/312]	eta 0:02:47 lr 0.003762	time 0.7352 (0.7561)	model_time 0.7350 (0.7400)	loss 3.7419 (3.5371)	grad_norm 1.7243 (1.2919/0.5261)	mem 34602MB
[2025-01-19 03:15:08 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][100/312]	eta 0:02:40 lr 0.003762	time 0.7978 (0.7553)	model_time 0.7976 (0.7407)	loss 3.8379 (3.5425)	grad_norm 1.2258 (1.2785/0.5095)	mem 34602MB
[2025-01-19 03:15:16 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][110/312]	eta 0:02:32 lr 0.003762	time 0.8303 (0.7571)	model_time 0.8301 (0.7438)	loss 3.4648 (3.5345)	grad_norm 0.5224 (1.2860/0.5475)	mem 34602MB
[2025-01-19 03:15:23 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][120/312]	eta 0:02:25 lr 0.003761	time 0.7156 (0.7576)	model_time 0.7151 (0.7454)	loss 3.7631 (3.5347)	grad_norm 2.0845 (1.2892/0.5546)	mem 34602MB
[2025-01-19 03:15:31 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][130/312]	eta 0:02:18 lr 0.003761	time 0.8100 (0.7602)	model_time 0.8098 (0.7488)	loss 3.4796 (3.5706)	grad_norm 1.6012 (1.2870/0.5473)	mem 34602MB
[2025-01-19 03:15:39 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][140/312]	eta 0:02:10 lr 0.003761	time 0.7234 (0.7587)	model_time 0.7232 (0.7481)	loss 3.7241 (3.5847)	grad_norm 1.3230 (1.2936/0.5380)	mem 34602MB
[2025-01-19 03:15:46 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][150/312]	eta 0:02:02 lr 0.003760	time 0.7309 (0.7570)	model_time 0.7307 (0.7471)	loss 3.5697 (3.5888)	grad_norm 0.9022 (1.2891/0.5306)	mem 34602MB
[2025-01-19 03:15:53 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][160/312]	eta 0:01:54 lr 0.003760	time 0.7368 (0.7556)	model_time 0.7366 (0.7463)	loss 3.2295 (3.5703)	grad_norm 0.8918 (1.2661/0.5241)	mem 34602MB
[2025-01-19 03:16:01 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][170/312]	eta 0:01:47 lr 0.003760	time 0.7208 (0.7544)	model_time 0.7204 (0.7456)	loss 4.8110 (3.5954)	grad_norm 2.2727 (1.2799/0.5353)	mem 34602MB
[2025-01-19 03:16:08 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][180/312]	eta 0:01:39 lr 0.003759	time 0.7486 (0.7529)	model_time 0.7481 (0.7446)	loss 4.3872 (3.6050)	grad_norm 1.0462 (1.2848/0.5278)	mem 34602MB
[2025-01-19 03:16:15 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][190/312]	eta 0:01:31 lr 0.003759	time 0.7267 (0.7518)	model_time 0.7262 (0.7439)	loss 3.6575 (3.6069)	grad_norm 0.7248 (1.2962/0.5296)	mem 34602MB
[2025-01-19 03:16:22 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][200/312]	eta 0:01:24 lr 0.003759	time 0.7168 (0.7507)	model_time 0.7163 (0.7432)	loss 3.9895 (3.6194)	grad_norm 1.6198 (1.3130/0.5388)	mem 34602MB
[2025-01-19 03:16:30 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][210/312]	eta 0:01:16 lr 0.003758	time 0.7161 (0.7499)	model_time 0.7158 (0.7428)	loss 3.9908 (3.6220)	grad_norm 1.0971 (1.3124/0.5431)	mem 34602MB
[2025-01-19 03:16:37 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][220/312]	eta 0:01:08 lr 0.003758	time 0.7956 (0.7499)	model_time 0.7951 (0.7430)	loss 3.0184 (3.6257)	grad_norm 2.2387 (1.3137/0.5397)	mem 34602MB
[2025-01-19 03:16:45 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][230/312]	eta 0:01:01 lr 0.003758	time 0.8366 (0.7503)	model_time 0.8361 (0.7437)	loss 3.3460 (3.6243)	grad_norm 1.1574 (1.3154/0.5379)	mem 34602MB
[2025-01-19 03:16:53 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][240/312]	eta 0:00:54 lr 0.003757	time 0.7164 (0.7517)	model_time 0.7162 (0.7453)	loss 4.3190 (3.6274)	grad_norm 1.2340 (1.3171/0.5332)	mem 34602MB
[2025-01-19 03:17:01 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][250/312]	eta 0:00:46 lr 0.003757	time 0.8185 (0.7530)	model_time 0.8180 (0.7469)	loss 3.8505 (3.6421)	grad_norm 0.5621 (1.3155/0.5275)	mem 34602MB
[2025-01-19 03:17:08 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][260/312]	eta 0:00:39 lr 0.003757	time 0.7166 (0.7525)	model_time 0.7164 (0.7467)	loss 3.8236 (3.6413)	grad_norm 0.9945 (1.3038/0.5222)	mem 34602MB
[2025-01-19 03:17:15 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][270/312]	eta 0:00:31 lr 0.003756	time 0.7530 (0.7518)	model_time 0.7526 (0.7462)	loss 4.3787 (3.6333)	grad_norm 1.3786 (1.2967/0.5223)	mem 34602MB
[2025-01-19 03:17:23 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][280/312]	eta 0:00:24 lr 0.003756	time 0.7476 (0.7509)	model_time 0.7471 (0.7455)	loss 3.1573 (3.6405)	grad_norm 1.4541 (1.2978/0.5212)	mem 34602MB
[2025-01-19 03:17:30 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][290/312]	eta 0:00:16 lr 0.003756	time 0.7151 (0.7505)	model_time 0.7149 (0.7452)	loss 3.4919 (3.6460)	grad_norm 0.9748 (1.2910/0.5158)	mem 34602MB
[2025-01-19 03:17:37 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][300/312]	eta 0:00:08 lr 0.003755	time 0.7063 (0.7498)	model_time 0.7062 (0.7447)	loss 3.6999 (3.6491)	grad_norm 0.8733 (1.3027/0.5437)	mem 34602MB
[2025-01-19 03:17:44 internimage_b_1k_224] (main.py 510): INFO Train: [47/300][310/312]	eta 0:00:01 lr 0.003755	time 0.7143 (0.7487)	model_time 0.7142 (0.7437)	loss 3.7794 (3.6431)	grad_norm 0.9915 (1.3077/0.5491)	mem 34602MB
[2025-01-19 03:17:45 internimage_b_1k_224] (main.py 519): INFO EPOCH 47 training takes 0:03:53
[2025-01-19 03:17:45 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_47.pth saving......
[2025-01-19 03:17:48 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_47.pth saved !!!
[2025-01-19 03:17:56 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.388 (7.388)	Loss 0.9731 (0.9731)	Acc@1 78.931 (78.931)	Acc@5 95.093 (95.093)	Mem 34602MB
[2025-01-19 03:17:59 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.938)	Loss 1.4113 (1.1609)	Acc@1 68.970 (74.585)	Acc@5 89.819 (92.671)	Mem 34602MB
[2025-01-19 03:17:59 internimage_b_1k_224] (main.py 575): INFO [Epoch:47] * Acc@1 74.560 Acc@5 92.740
[2025-01-19 03:17:59 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 74.6%
[2025-01-19 03:17:59 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 03:18:02 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 03:18:02 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 74.56%
[2025-01-19 03:18:09 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.102 (7.102)	Loss 2.7050 (2.7050)	Acc@1 49.463 (49.463)	Acc@5 72.266 (72.266)	Mem 34602MB
[2025-01-19 03:18:12 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.898)	Loss 3.0453 (2.7534)	Acc@1 41.504 (46.737)	Acc@5 65.649 (71.575)	Mem 34602MB
[2025-01-19 03:18:12 internimage_b_1k_224] (main.py 575): INFO [Epoch:47] * Acc@1 47.061 Acc@5 72.153
[2025-01-19 03:18:12 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 47.1%
[2025-01-19 03:18:13 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:18:16 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:18:16 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 47.06%
[2025-01-19 03:18:19 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][0/312]	eta 0:11:32 lr 0.003755	time 2.2193 (2.2193)	model_time 0.7439 (0.7439)	loss 3.2683 (3.2683)	grad_norm 0.8258 (0.8258/0.0000)	mem 34602MB
[2025-01-19 03:18:26 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][10/312]	eta 0:04:21 lr 0.003755	time 0.7342 (0.8655)	model_time 0.7338 (0.7310)	loss 2.8006 (3.7020)	grad_norm 1.1127 (1.2209/0.2906)	mem 34602MB
[2025-01-19 03:18:33 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][20/312]	eta 0:03:54 lr 0.003754	time 0.7524 (0.8027)	model_time 0.7520 (0.7321)	loss 4.2965 (3.6690)	grad_norm 1.1040 (1.1580/0.3122)	mem 34602MB
[2025-01-19 03:18:41 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][30/312]	eta 0:03:41 lr 0.003754	time 0.7382 (0.7850)	model_time 0.7380 (0.7371)	loss 4.1839 (3.7453)	grad_norm 0.7584 (1.1015/0.3041)	mem 34602MB
[2025-01-19 03:18:49 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][40/312]	eta 0:03:32 lr 0.003754	time 0.8107 (0.7815)	model_time 0.8102 (0.7451)	loss 3.9520 (3.7095)	grad_norm 0.7714 (1.1291/0.3107)	mem 34602MB
[2025-01-19 03:18:56 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][50/312]	eta 0:03:24 lr 0.003753	time 0.7203 (0.7802)	model_time 0.7201 (0.7509)	loss 2.9328 (3.6996)	grad_norm 1.1486 (1.1899/0.3736)	mem 34602MB
[2025-01-19 03:19:04 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][60/312]	eta 0:03:16 lr 0.003753	time 0.8059 (0.7798)	model_time 0.8054 (0.7552)	loss 3.4801 (3.7175)	grad_norm 2.4011 (1.2971/0.4380)	mem 34602MB
[2025-01-19 03:19:12 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][70/312]	eta 0:03:07 lr 0.003753	time 0.7501 (0.7748)	model_time 0.7499 (0.7537)	loss 3.1159 (3.7020)	grad_norm 0.9745 (1.2971/0.4525)	mem 34602MB
[2025-01-19 03:19:19 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][80/312]	eta 0:02:58 lr 0.003753	time 0.7156 (0.7701)	model_time 0.7152 (0.7515)	loss 3.0890 (3.6847)	grad_norm 1.3633 (1.2601/0.4470)	mem 34602MB
[2025-01-19 03:19:26 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][90/312]	eta 0:02:49 lr 0.003752	time 0.7284 (0.7652)	model_time 0.7283 (0.7486)	loss 4.1052 (3.6517)	grad_norm 2.6086 (1.3184/0.5621)	mem 34602MB
[2025-01-19 03:19:33 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][100/312]	eta 0:02:41 lr 0.003752	time 0.7306 (0.7609)	model_time 0.7305 (0.7460)	loss 4.0175 (3.6634)	grad_norm 1.2560 (1.2951/0.5463)	mem 34602MB
[2025-01-19 03:19:41 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][110/312]	eta 0:02:33 lr 0.003752	time 0.7204 (0.7577)	model_time 0.7200 (0.7441)	loss 2.4657 (3.6521)	grad_norm 0.9162 (1.2861/0.5276)	mem 34602MB
[2025-01-19 03:19:48 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][120/312]	eta 0:02:24 lr 0.003751	time 0.7148 (0.7552)	model_time 0.7146 (0.7426)	loss 4.0458 (3.6876)	grad_norm 1.2902 (1.2779/0.5131)	mem 34602MB
[2025-01-19 03:19:55 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][130/312]	eta 0:02:17 lr 0.003751	time 0.7152 (0.7530)	model_time 0.7148 (0.7414)	loss 4.0799 (3.6636)	grad_norm 1.4442 (1.2979/0.5068)	mem 34602MB
[2025-01-19 03:20:02 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][140/312]	eta 0:02:09 lr 0.003751	time 0.7313 (0.7517)	model_time 0.7311 (0.7409)	loss 4.2672 (3.6871)	grad_norm 1.4827 (1.3617/0.6494)	mem 34602MB
[2025-01-19 03:20:10 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][150/312]	eta 0:02:01 lr 0.003750	time 0.7226 (0.7498)	model_time 0.7224 (0.7397)	loss 4.3004 (3.6867)	grad_norm 1.3248 (1.3416/0.6374)	mem 34602MB
[2025-01-19 03:20:17 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][160/312]	eta 0:01:54 lr 0.003750	time 0.7170 (0.7513)	model_time 0.7166 (0.7418)	loss 4.4756 (3.6681)	grad_norm 1.1693 (1.3196/0.6257)	mem 34602MB
[2025-01-19 03:20:25 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][170/312]	eta 0:01:46 lr 0.003750	time 0.8190 (0.7533)	model_time 0.8188 (0.7443)	loss 4.5716 (3.6740)	grad_norm 1.3336 (1.2975/0.6172)	mem 34602MB
[2025-01-19 03:20:33 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][180/312]	eta 0:01:39 lr 0.003749	time 0.8100 (0.7544)	model_time 0.8098 (0.7459)	loss 4.0690 (3.6859)	grad_norm 2.4945 (1.2968/0.6121)	mem 34602MB
[2025-01-19 03:20:41 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][190/312]	eta 0:01:32 lr 0.003749	time 0.7184 (0.7542)	model_time 0.7183 (0.7462)	loss 3.8357 (3.6817)	grad_norm 1.0238 (1.3013/0.6036)	mem 34602MB
[2025-01-19 03:20:48 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][200/312]	eta 0:01:24 lr 0.003749	time 0.7699 (0.7531)	model_time 0.7695 (0.7454)	loss 3.6317 (3.6820)	grad_norm 0.9371 (1.3109/0.6058)	mem 34602MB
[2025-01-19 03:20:55 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][210/312]	eta 0:01:16 lr 0.003748	time 0.7162 (0.7521)	model_time 0.7160 (0.7447)	loss 4.1612 (3.6892)	grad_norm 1.5801 (1.3085/0.6013)	mem 34602MB
[2025-01-19 03:21:02 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][220/312]	eta 0:01:09 lr 0.003748	time 0.7244 (0.7510)	model_time 0.7240 (0.7440)	loss 3.0700 (3.6797)	grad_norm 0.8056 (1.3080/0.5941)	mem 34602MB
[2025-01-19 03:21:10 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][230/312]	eta 0:01:01 lr 0.003748	time 0.7404 (0.7498)	model_time 0.7403 (0.7431)	loss 3.1573 (3.6753)	grad_norm 1.0721 (1.3007/0.5848)	mem 34602MB
[2025-01-19 03:21:17 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][240/312]	eta 0:00:53 lr 0.003747	time 0.7475 (0.7490)	model_time 0.7471 (0.7425)	loss 3.0620 (3.6717)	grad_norm 3.0363 (1.3127/0.5941)	mem 34602MB
[2025-01-19 03:21:24 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][250/312]	eta 0:00:46 lr 0.003747	time 0.7282 (0.7484)	model_time 0.7280 (0.7422)	loss 4.5087 (3.6768)	grad_norm 1.0142 (1.3169/0.5906)	mem 34602MB
[2025-01-19 03:21:32 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][260/312]	eta 0:00:38 lr 0.003747	time 0.7613 (0.7478)	model_time 0.7609 (0.7418)	loss 4.0881 (3.6774)	grad_norm 0.8119 (1.3011/0.5881)	mem 34602MB
[2025-01-19 03:21:39 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][270/312]	eta 0:00:31 lr 0.003746	time 0.7252 (0.7471)	model_time 0.7250 (0.7413)	loss 4.5945 (3.6798)	grad_norm 1.2009 (1.2970/0.5832)	mem 34602MB
[2025-01-19 03:21:47 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][280/312]	eta 0:00:23 lr 0.003746	time 0.7183 (0.7478)	model_time 0.7181 (0.7422)	loss 3.4840 (3.6785)	grad_norm 0.9658 (1.2864/0.5780)	mem 34602MB
[2025-01-19 03:21:54 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][290/312]	eta 0:00:16 lr 0.003746	time 0.8081 (0.7489)	model_time 0.8077 (0.7435)	loss 3.2223 (3.6773)	grad_norm 0.9199 (1.3146/0.6415)	mem 34602MB
[2025-01-19 03:22:02 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][300/312]	eta 0:00:08 lr 0.003745	time 0.8124 (0.7495)	model_time 0.8123 (0.7442)	loss 4.5722 (3.6829)	grad_norm 0.9993 (1.3141/0.6373)	mem 34602MB
[2025-01-19 03:22:10 internimage_b_1k_224] (main.py 510): INFO Train: [48/300][310/312]	eta 0:00:01 lr 0.003745	time 0.7126 (0.7500)	model_time 0.7125 (0.7449)	loss 3.9680 (3.6825)	grad_norm 0.8616 (1.3083/0.6385)	mem 34602MB
[2025-01-19 03:22:10 internimage_b_1k_224] (main.py 519): INFO EPOCH 48 training takes 0:03:53
[2025-01-19 03:22:10 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_48.pth saving......
[2025-01-19 03:22:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_48.pth saved !!!
[2025-01-19 03:22:28 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.763 (14.763)	Loss 0.9350 (0.9350)	Acc@1 78.735 (78.735)	Acc@5 95.508 (95.508)	Mem 34602MB
[2025-01-19 03:22:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.043)	Loss 1.4135 (1.1534)	Acc@1 69.287 (74.680)	Acc@5 89.575 (92.773)	Mem 34602MB
[2025-01-19 03:22:36 internimage_b_1k_224] (main.py 575): INFO [Epoch:48] * Acc@1 74.640 Acc@5 92.866
[2025-01-19 03:22:36 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 74.6%
[2025-01-19 03:22:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 03:22:40 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 03:22:40 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 74.64%
[2025-01-19 03:22:47 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.220 (7.220)	Loss 2.5666 (2.5666)	Acc@1 52.075 (52.075)	Acc@5 74.805 (74.805)	Mem 34602MB
[2025-01-19 03:22:50 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.936)	Loss 2.9282 (2.6288)	Acc@1 43.628 (49.099)	Acc@5 67.480 (73.739)	Mem 34602MB
[2025-01-19 03:22:50 internimage_b_1k_224] (main.py 575): INFO [Epoch:48] * Acc@1 49.402 Acc@5 74.252
[2025-01-19 03:22:50 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 49.4%
[2025-01-19 03:22:50 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:22:54 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:22:54 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 49.40%
[2025-01-19 03:22:57 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][0/312]	eta 0:11:51 lr 0.003745	time 2.2799 (2.2799)	model_time 0.7451 (0.7451)	loss 4.0238 (4.0238)	grad_norm 0.8717 (0.8717/0.0000)	mem 34602MB
[2025-01-19 03:23:04 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][10/312]	eta 0:04:25 lr 0.003745	time 0.7338 (0.8794)	model_time 0.7334 (0.7394)	loss 3.0792 (3.8925)	grad_norm 0.9169 (1.0325/0.2960)	mem 34602MB
[2025-01-19 03:23:11 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][20/312]	eta 0:03:56 lr 0.003744	time 0.7215 (0.8111)	model_time 0.7211 (0.7376)	loss 2.7842 (3.6404)	grad_norm 0.8892 (1.0013/0.2519)	mem 34602MB
[2025-01-19 03:23:19 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][30/312]	eta 0:03:41 lr 0.003744	time 0.7161 (0.7841)	model_time 0.7159 (0.7343)	loss 2.4315 (3.6502)	grad_norm 1.1220 (1.1232/0.4323)	mem 34602MB
[2025-01-19 03:23:26 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][40/312]	eta 0:03:29 lr 0.003744	time 0.7343 (0.7698)	model_time 0.7339 (0.7320)	loss 3.7609 (3.5901)	grad_norm 0.8350 (1.0815/0.3995)	mem 34602MB
[2025-01-19 03:23:33 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][50/312]	eta 0:03:19 lr 0.003743	time 0.7250 (0.7613)	model_time 0.7246 (0.7309)	loss 3.3319 (3.5737)	grad_norm 1.2094 (1.0631/0.3895)	mem 34602MB
[2025-01-19 03:23:40 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][60/312]	eta 0:03:10 lr 0.003743	time 0.7317 (0.7559)	model_time 0.7315 (0.7304)	loss 2.6989 (3.5665)	grad_norm 2.3977 (1.2010/0.5807)	mem 34602MB
[2025-01-19 03:23:48 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][70/312]	eta 0:03:02 lr 0.003743	time 0.7238 (0.7530)	model_time 0.7234 (0.7311)	loss 3.7997 (3.6358)	grad_norm 1.3885 (1.2139/0.5517)	mem 34602MB
[2025-01-19 03:23:55 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][80/312]	eta 0:02:53 lr 0.003742	time 0.7334 (0.7496)	model_time 0.7330 (0.7303)	loss 3.8223 (3.6457)	grad_norm 0.9935 (1.2093/0.5262)	mem 34602MB
[2025-01-19 03:24:03 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][90/312]	eta 0:02:47 lr 0.003742	time 0.8021 (0.7543)	model_time 0.8018 (0.7371)	loss 2.6348 (3.6680)	grad_norm 0.5386 (1.2032/0.5122)	mem 34602MB
[2025-01-19 03:24:11 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][100/312]	eta 0:02:40 lr 0.003742	time 0.8069 (0.7555)	model_time 0.8064 (0.7400)	loss 3.4207 (3.6731)	grad_norm 0.7070 (1.2026/0.5094)	mem 34602MB
[2025-01-19 03:24:18 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][110/312]	eta 0:02:32 lr 0.003741	time 0.7113 (0.7565)	model_time 0.7111 (0.7424)	loss 4.6031 (3.6421)	grad_norm 1.1034 (1.2289/0.5121)	mem 34602MB
[2025-01-19 03:24:26 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][120/312]	eta 0:02:25 lr 0.003741	time 0.7401 (0.7578)	model_time 0.7399 (0.7448)	loss 3.9225 (3.6425)	grad_norm 1.1377 (1.2051/0.4998)	mem 34602MB
[2025-01-19 03:24:33 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][130/312]	eta 0:02:17 lr 0.003741	time 0.7190 (0.7560)	model_time 0.7186 (0.7439)	loss 4.4597 (3.6557)	grad_norm 1.0870 (1.2398/0.5467)	mem 34602MB
[2025-01-19 03:24:41 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][140/312]	eta 0:02:09 lr 0.003740	time 0.7161 (0.7538)	model_time 0.7159 (0.7426)	loss 3.7287 (3.6448)	grad_norm 2.0780 (1.2585/0.5475)	mem 34602MB
[2025-01-19 03:24:48 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][150/312]	eta 0:02:01 lr 0.003740	time 0.7169 (0.7520)	model_time 0.7167 (0.7415)	loss 3.4457 (3.6448)	grad_norm 1.0713 (1.2454/0.5347)	mem 34602MB
[2025-01-19 03:24:55 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][160/312]	eta 0:01:54 lr 0.003740	time 0.7387 (0.7509)	model_time 0.7383 (0.7410)	loss 4.1224 (3.6522)	grad_norm 0.8486 (1.2309/0.5271)	mem 34602MB
[2025-01-19 03:25:02 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][170/312]	eta 0:01:46 lr 0.003739	time 0.7232 (0.7492)	model_time 0.7231 (0.7398)	loss 2.7786 (3.6401)	grad_norm 0.7542 (1.2171/0.5199)	mem 34602MB
[2025-01-19 03:25:10 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][180/312]	eta 0:01:38 lr 0.003739	time 0.7178 (0.7474)	model_time 0.7176 (0.7386)	loss 2.9769 (3.6323)	grad_norm 0.7270 (1.2377/0.5340)	mem 34602MB
[2025-01-19 03:25:17 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][190/312]	eta 0:01:31 lr 0.003739	time 0.7207 (0.7465)	model_time 0.7206 (0.7381)	loss 2.7318 (3.6268)	grad_norm 0.9036 (1.2408/0.5316)	mem 34602MB
[2025-01-19 03:25:24 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][200/312]	eta 0:01:23 lr 0.003738	time 0.7240 (0.7456)	model_time 0.7238 (0.7376)	loss 4.2557 (3.6379)	grad_norm 0.8565 (1.2325/0.5223)	mem 34602MB
[2025-01-19 03:25:32 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][210/312]	eta 0:01:16 lr 0.003738	time 0.8054 (0.7472)	model_time 0.8053 (0.7396)	loss 3.9666 (3.6536)	grad_norm 1.3115 (1.2411/0.5281)	mem 34602MB
[2025-01-19 03:25:40 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][220/312]	eta 0:01:08 lr 0.003738	time 0.8075 (0.7484)	model_time 0.8074 (0.7411)	loss 3.0966 (3.6486)	grad_norm 1.6052 (1.2363/0.5230)	mem 34602MB
[2025-01-19 03:25:47 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][230/312]	eta 0:01:01 lr 0.003737	time 0.7182 (0.7491)	model_time 0.7177 (0.7421)	loss 3.8842 (3.6518)	grad_norm 2.1002 (1.2627/0.5527)	mem 34602MB
[2025-01-19 03:25:55 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][240/312]	eta 0:00:53 lr 0.003737	time 0.7188 (0.7491)	model_time 0.7187 (0.7424)	loss 3.1611 (3.6614)	grad_norm 1.0414 (1.2640/0.5490)	mem 34602MB
[2025-01-19 03:26:02 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][250/312]	eta 0:00:46 lr 0.003737	time 0.7141 (0.7487)	model_time 0.7139 (0.7422)	loss 2.6416 (3.6573)	grad_norm 1.0371 (1.2483/0.5438)	mem 34602MB
[2025-01-19 03:26:09 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][260/312]	eta 0:00:38 lr 0.003736	time 0.7176 (0.7479)	model_time 0.7172 (0.7417)	loss 3.4099 (3.6584)	grad_norm 1.1095 (1.2491/0.5401)	mem 34602MB
[2025-01-19 03:26:17 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][270/312]	eta 0:00:31 lr 0.003736	time 0.7205 (0.7471)	model_time 0.7203 (0.7411)	loss 2.7179 (3.6569)	grad_norm 1.8270 (1.2615/0.5434)	mem 34602MB
[2025-01-19 03:26:24 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][280/312]	eta 0:00:23 lr 0.003736	time 0.7197 (0.7465)	model_time 0.7192 (0.7407)	loss 4.0466 (3.6678)	grad_norm 2.3174 (1.2742/0.5530)	mem 34602MB
[2025-01-19 03:26:31 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][290/312]	eta 0:00:16 lr 0.003735	time 0.7177 (0.7457)	model_time 0.7175 (0.7401)	loss 4.1358 (3.6736)	grad_norm 1.8447 (1.2780/0.5511)	mem 34602MB
[2025-01-19 03:26:39 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][300/312]	eta 0:00:08 lr 0.003735	time 0.7134 (0.7452)	model_time 0.7133 (0.7397)	loss 3.9526 (3.6687)	grad_norm 1.0314 (1.2781/0.5472)	mem 34602MB
[2025-01-19 03:26:46 internimage_b_1k_224] (main.py 510): INFO Train: [49/300][310/312]	eta 0:00:01 lr 0.003735	time 0.7149 (0.7445)	model_time 0.7148 (0.7392)	loss 4.0402 (3.6634)	grad_norm 0.7573 (1.2877/0.5502)	mem 34602MB
[2025-01-19 03:26:47 internimage_b_1k_224] (main.py 519): INFO EPOCH 49 training takes 0:03:52
[2025-01-19 03:26:47 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_49.pth saving......
[2025-01-19 03:26:50 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_49.pth saved !!!
[2025-01-19 03:26:57 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.362 (7.362)	Loss 0.9605 (0.9605)	Acc@1 79.468 (79.468)	Acc@5 95.264 (95.264)	Mem 34602MB
[2025-01-19 03:27:00 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.948)	Loss 1.4379 (1.1776)	Acc@1 68.506 (74.603)	Acc@5 89.673 (92.736)	Mem 34602MB
[2025-01-19 03:27:00 internimage_b_1k_224] (main.py 575): INFO [Epoch:49] * Acc@1 74.660 Acc@5 92.782
[2025-01-19 03:27:00 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 74.7%
[2025-01-19 03:27:00 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 03:27:04 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 03:27:04 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 74.66%
[2025-01-19 03:27:11 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.894 (6.894)	Loss 2.4409 (2.4409)	Acc@1 54.590 (54.590)	Acc@5 76.831 (76.831)	Mem 34602MB
[2025-01-19 03:27:14 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.905)	Loss 2.8206 (2.5158)	Acc@1 45.801 (51.281)	Acc@5 69.458 (75.648)	Mem 34602MB
[2025-01-19 03:27:14 internimage_b_1k_224] (main.py 575): INFO [Epoch:49] * Acc@1 51.569 Acc@5 76.108
[2025-01-19 03:27:14 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 51.6%
[2025-01-19 03:27:14 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:27:18 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:27:18 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 51.57%
[2025-01-19 03:27:20 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][0/312]	eta 0:11:48 lr 0.003735	time 2.2723 (2.2723)	model_time 0.7608 (0.7608)	loss 3.3368 (3.3368)	grad_norm 1.0769 (1.0769/0.0000)	mem 34602MB
[2025-01-19 03:27:28 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][10/312]	eta 0:04:23 lr 0.003734	time 0.7282 (0.8715)	model_time 0.7281 (0.7338)	loss 2.8146 (3.6064)	grad_norm 1.2980 (1.0595/0.2218)	mem 34602MB
[2025-01-19 03:27:35 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][20/312]	eta 0:04:01 lr 0.003734	time 0.7200 (0.8283)	model_time 0.7198 (0.7560)	loss 4.6976 (3.7220)	grad_norm 1.2701 (1.2110/0.6784)	mem 34602MB
[2025-01-19 03:27:43 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][30/312]	eta 0:03:48 lr 0.003734	time 0.7173 (0.8088)	model_time 0.7169 (0.7597)	loss 3.5137 (3.7779)	grad_norm 0.9134 (1.2392/0.5964)	mem 34602MB
[2025-01-19 03:27:51 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][40/312]	eta 0:03:37 lr 0.003733	time 0.8043 (0.7995)	model_time 0.8042 (0.7623)	loss 4.6895 (3.7427)	grad_norm 1.2333 (1.2249/0.5330)	mem 34602MB
[2025-01-19 03:27:58 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][50/312]	eta 0:03:27 lr 0.003733	time 0.7350 (0.7909)	model_time 0.7348 (0.7609)	loss 3.1904 (3.6531)	grad_norm 1.1174 (1.2270/0.4996)	mem 34602MB
[2025-01-19 03:28:06 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][60/312]	eta 0:03:16 lr 0.003733	time 0.7327 (0.7807)	model_time 0.7325 (0.7556)	loss 3.9195 (3.6834)	grad_norm 2.3323 (1.2427/0.4913)	mem 34602MB
[2025-01-19 03:28:13 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][70/312]	eta 0:03:07 lr 0.003732	time 0.7183 (0.7756)	model_time 0.7181 (0.7540)	loss 3.9012 (3.6780)	grad_norm 1.8077 (1.2641/0.4776)	mem 34602MB
[2025-01-19 03:28:20 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][80/312]	eta 0:02:58 lr 0.003732	time 0.7149 (0.7702)	model_time 0.7147 (0.7512)	loss 3.1203 (3.6754)	grad_norm 0.8534 (1.2663/0.4627)	mem 34602MB
[2025-01-19 03:28:28 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][90/312]	eta 0:02:49 lr 0.003732	time 0.7293 (0.7657)	model_time 0.7291 (0.7487)	loss 3.2467 (3.6459)	grad_norm 0.9875 (1.2517/0.4577)	mem 34602MB
[2025-01-19 03:28:35 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][100/312]	eta 0:02:41 lr 0.003731	time 0.7157 (0.7618)	model_time 0.7155 (0.7464)	loss 3.8842 (3.6448)	grad_norm 0.9796 (1.2451/0.4499)	mem 34602MB
[2025-01-19 03:28:42 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][110/312]	eta 0:02:33 lr 0.003731	time 0.7195 (0.7590)	model_time 0.7190 (0.7450)	loss 3.7663 (3.6539)	grad_norm 0.8228 (1.2449/0.4392)	mem 34602MB
[2025-01-19 03:28:50 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][120/312]	eta 0:02:25 lr 0.003731	time 0.7499 (0.7568)	model_time 0.7495 (0.7440)	loss 3.1314 (3.6682)	grad_norm 1.1541 (1.2395/0.4299)	mem 34602MB
[2025-01-19 03:28:57 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][130/312]	eta 0:02:17 lr 0.003730	time 0.7259 (0.7549)	model_time 0.7257 (0.7430)	loss 2.7864 (3.6486)	grad_norm 2.4822 (1.2395/0.4392)	mem 34602MB
[2025-01-19 03:29:05 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][140/312]	eta 0:02:09 lr 0.003730	time 0.8159 (0.7556)	model_time 0.8157 (0.7445)	loss 2.7770 (3.6563)	grad_norm 0.6834 (1.2548/0.4734)	mem 34602MB
[2025-01-19 03:29:12 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][150/312]	eta 0:02:02 lr 0.003730	time 0.7330 (0.7567)	model_time 0.7328 (0.7463)	loss 3.4564 (3.6708)	grad_norm 1.4469 (1.2382/0.4702)	mem 34602MB
[2025-01-19 03:29:20 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][160/312]	eta 0:01:55 lr 0.003729	time 0.7229 (0.7571)	model_time 0.7227 (0.7474)	loss 3.6813 (3.6722)	grad_norm 1.1110 (1.2429/0.4724)	mem 34602MB
[2025-01-19 03:29:28 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][170/312]	eta 0:01:47 lr 0.003729	time 0.7578 (0.7583)	model_time 0.7574 (0.7491)	loss 4.4069 (3.6674)	grad_norm 1.7465 (1.2388/0.4662)	mem 34602MB
[2025-01-19 03:29:35 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][180/312]	eta 0:01:39 lr 0.003729	time 0.7237 (0.7566)	model_time 0.7236 (0.7479)	loss 4.0892 (3.6601)	grad_norm 2.0594 (1.2616/0.4885)	mem 34602MB
[2025-01-19 03:29:42 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][190/312]	eta 0:01:32 lr 0.003728	time 0.7154 (0.7554)	model_time 0.7150 (0.7471)	loss 2.3559 (3.6576)	grad_norm 0.7562 (1.2629/0.4949)	mem 34602MB
[2025-01-19 03:29:50 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][200/312]	eta 0:01:24 lr 0.003728	time 0.7227 (0.7540)	model_time 0.7222 (0.7462)	loss 3.7562 (3.6651)	grad_norm 2.4751 (1.2677/0.4938)	mem 34602MB
[2025-01-19 03:29:57 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][210/312]	eta 0:01:16 lr 0.003728	time 0.7303 (0.7526)	model_time 0.7299 (0.7451)	loss 3.2842 (3.6628)	grad_norm 1.0439 (1.2797/0.5051)	mem 34602MB
[2025-01-19 03:30:04 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][220/312]	eta 0:01:09 lr 0.003727	time 0.7547 (0.7516)	model_time 0.7546 (0.7444)	loss 3.1413 (3.6676)	grad_norm 1.4428 (1.2718/0.4975)	mem 34602MB
[2025-01-19 03:30:11 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][230/312]	eta 0:01:01 lr 0.003727	time 0.7266 (0.7504)	model_time 0.7265 (0.7435)	loss 3.2824 (3.6697)	grad_norm 1.6040 (1.2639/0.4929)	mem 34602MB
[2025-01-19 03:30:19 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][240/312]	eta 0:00:53 lr 0.003727	time 0.7203 (0.7495)	model_time 0.7198 (0.7428)	loss 4.0940 (3.6767)	grad_norm 0.8291 (1.2577/0.4873)	mem 34602MB
[2025-01-19 03:30:26 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][250/312]	eta 0:00:46 lr 0.003726	time 0.7193 (0.7486)	model_time 0.7191 (0.7422)	loss 2.6259 (3.6717)	grad_norm 1.1122 (1.2686/0.4846)	mem 34602MB
[2025-01-19 03:30:34 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][260/312]	eta 0:00:38 lr 0.003726	time 0.8044 (0.7488)	model_time 0.8039 (0.7427)	loss 3.3414 (3.6797)	grad_norm 1.1982 (1.2689/0.4847)	mem 34602MB
[2025-01-19 03:30:41 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][270/312]	eta 0:00:31 lr 0.003726	time 0.7169 (0.7491)	model_time 0.7168 (0.7432)	loss 3.6474 (3.6820)	grad_norm 1.6657 (1.2724/0.4876)	mem 34602MB
[2025-01-19 03:30:49 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][280/312]	eta 0:00:23 lr 0.003725	time 0.7246 (0.7499)	model_time 0.7244 (0.7441)	loss 4.3014 (3.6898)	grad_norm 1.2654 (1.2684/0.4819)	mem 34602MB
[2025-01-19 03:30:56 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][290/312]	eta 0:00:16 lr 0.003725	time 0.7263 (0.7499)	model_time 0.7259 (0.7443)	loss 4.2666 (3.6898)	grad_norm 0.7646 (1.2768/0.4884)	mem 34602MB
[2025-01-19 03:31:04 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][300/312]	eta 0:00:08 lr 0.003725	time 0.7196 (0.7490)	model_time 0.7195 (0.7437)	loss 3.5515 (3.6910)	grad_norm 1.0461 (1.2776/0.4847)	mem 34602MB
[2025-01-19 03:31:11 internimage_b_1k_224] (main.py 510): INFO Train: [50/300][310/312]	eta 0:00:01 lr 0.003724	time 0.7155 (0.7483)	model_time 0.7153 (0.7431)	loss 2.9036 (3.6874)	grad_norm 0.7175 (1.2820/0.4849)	mem 34602MB
[2025-01-19 03:31:12 internimage_b_1k_224] (main.py 519): INFO EPOCH 50 training takes 0:03:53
[2025-01-19 03:31:12 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_50.pth saving......
[2025-01-19 03:31:15 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_50.pth saved !!!
[2025-01-19 03:31:22 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.275 (7.275)	Loss 0.9875 (0.9875)	Acc@1 79.248 (79.248)	Acc@5 95.337 (95.337)	Mem 34602MB
[2025-01-19 03:31:25 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.941)	Loss 1.4204 (1.1739)	Acc@1 69.312 (75.087)	Acc@5 89.380 (92.816)	Mem 34602MB
[2025-01-19 03:31:25 internimage_b_1k_224] (main.py 575): INFO [Epoch:50] * Acc@1 75.088 Acc@5 92.910
[2025-01-19 03:31:25 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.1%
[2025-01-19 03:31:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 03:31:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 03:31:28 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 75.09%
[2025-01-19 03:31:36 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.596 (7.596)	Loss 2.3246 (2.3246)	Acc@1 56.885 (56.885)	Acc@5 78.394 (78.394)	Mem 34602MB
[2025-01-19 03:31:39 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.961)	Loss 2.7218 (2.4121)	Acc@1 47.827 (53.267)	Acc@5 70.776 (77.137)	Mem 34602MB
[2025-01-19 03:31:39 internimage_b_1k_224] (main.py 575): INFO [Epoch:50] * Acc@1 53.551 Acc@5 77.595
[2025-01-19 03:31:39 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 53.6%
[2025-01-19 03:31:39 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:31:43 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:31:43 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 53.55%
[2025-01-19 03:31:45 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][0/312]	eta 0:11:04 lr 0.003724	time 2.1286 (2.1286)	model_time 0.7415 (0.7415)	loss 3.8288 (3.8288)	grad_norm 0.7264 (0.7264/0.0000)	mem 34602MB
[2025-01-19 03:31:53 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][10/312]	eta 0:04:18 lr 0.003724	time 0.7166 (0.8551)	model_time 0.7164 (0.7286)	loss 4.5168 (3.6247)	grad_norm 1.3716 (1.1981/0.3726)	mem 34602MB
[2025-01-19 03:32:00 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][20/312]	eta 0:03:51 lr 0.003724	time 0.7295 (0.7935)	model_time 0.7291 (0.7271)	loss 3.1680 (3.4153)	grad_norm 0.6035 (1.2731/0.4565)	mem 34602MB
[2025-01-19 03:32:07 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][30/312]	eta 0:03:38 lr 0.003723	time 0.7514 (0.7737)	model_time 0.7512 (0.7286)	loss 4.3922 (3.5021)	grad_norm 1.2635 (1.2496/0.4129)	mem 34602MB
[2025-01-19 03:32:14 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][40/312]	eta 0:03:27 lr 0.003723	time 0.7357 (0.7621)	model_time 0.7352 (0.7279)	loss 3.3029 (3.4623)	grad_norm 1.2238 (1.2408/0.4280)	mem 34602MB
[2025-01-19 03:32:22 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][50/312]	eta 0:03:18 lr 0.003723	time 0.7181 (0.7577)	model_time 0.7179 (0.7301)	loss 4.5185 (3.4879)	grad_norm 1.0281 (1.3416/0.6234)	mem 34602MB
[2025-01-19 03:32:29 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][60/312]	eta 0:03:09 lr 0.003722	time 0.7235 (0.7530)	model_time 0.7234 (0.7299)	loss 3.8107 (3.4894)	grad_norm 2.2317 (1.3464/0.6065)	mem 34602MB
[2025-01-19 03:32:37 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][70/312]	eta 0:03:03 lr 0.003722	time 0.7174 (0.7565)	model_time 0.7170 (0.7366)	loss 2.7139 (3.4887)	grad_norm 1.7618 (1.3553/0.5814)	mem 34602MB
[2025-01-19 03:32:45 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][80/312]	eta 0:02:56 lr 0.003722	time 0.7245 (0.7589)	model_time 0.7244 (0.7414)	loss 3.6378 (3.4757)	grad_norm 0.9489 (1.3210/0.5706)	mem 34602MB
[2025-01-19 03:32:52 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][90/312]	eta 0:02:48 lr 0.003721	time 0.8045 (0.7599)	model_time 0.8043 (0.7443)	loss 4.3177 (3.5112)	grad_norm 1.6179 (1.2842/0.5551)	mem 34602MB
[2025-01-19 03:33:00 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][100/312]	eta 0:02:41 lr 0.003721	time 0.7220 (0.7601)	model_time 0.7215 (0.7460)	loss 3.6706 (3.5201)	grad_norm 1.0160 (1.3601/0.6833)	mem 34602MB
[2025-01-19 03:33:07 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][110/312]	eta 0:02:32 lr 0.003721	time 0.7228 (0.7570)	model_time 0.7226 (0.7442)	loss 2.6687 (3.5414)	grad_norm 1.2346 (1.3411/0.6585)	mem 34602MB
[2025-01-19 03:33:15 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][120/312]	eta 0:02:25 lr 0.003720	time 0.7315 (0.7553)	model_time 0.7314 (0.7435)	loss 3.9075 (3.5434)	grad_norm 1.1970 (1.3087/0.6416)	mem 34602MB
[2025-01-19 03:33:22 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][130/312]	eta 0:02:17 lr 0.003720	time 0.7256 (0.7534)	model_time 0.7251 (0.7424)	loss 3.3479 (3.5546)	grad_norm 1.7106 (1.3210/0.6429)	mem 34602MB
[2025-01-19 03:33:29 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][140/312]	eta 0:02:09 lr 0.003720	time 0.7137 (0.7515)	model_time 0.7133 (0.7413)	loss 2.9744 (3.5526)	grad_norm 1.1064 (1.3209/0.6314)	mem 34602MB
[2025-01-19 03:33:36 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][150/312]	eta 0:02:01 lr 0.003719	time 0.7219 (0.7499)	model_time 0.7215 (0.7404)	loss 4.2490 (3.5530)	grad_norm 0.9656 (1.3085/0.6158)	mem 34602MB
[2025-01-19 03:33:44 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][160/312]	eta 0:01:53 lr 0.003719	time 0.7283 (0.7485)	model_time 0.7281 (0.7395)	loss 3.9367 (3.5591)	grad_norm 0.6947 (1.2825/0.6086)	mem 34602MB
[2025-01-19 03:33:51 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][170/312]	eta 0:01:46 lr 0.003718	time 0.7156 (0.7478)	model_time 0.7154 (0.7394)	loss 4.5361 (3.5796)	grad_norm 2.1734 (1.2690/0.6025)	mem 34602MB
[2025-01-19 03:33:58 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][180/312]	eta 0:01:38 lr 0.003718	time 0.7146 (0.7471)	model_time 0.7145 (0.7391)	loss 2.9512 (3.5722)	grad_norm 1.1806 (1.3048/0.6530)	mem 34602MB
[2025-01-19 03:34:06 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][190/312]	eta 0:01:31 lr 0.003718	time 0.7190 (0.7484)	model_time 0.7185 (0.7408)	loss 3.6839 (3.5663)	grad_norm 0.9389 (1.2985/0.6407)	mem 34602MB
[2025-01-19 03:34:14 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][200/312]	eta 0:01:24 lr 0.003717	time 0.8167 (0.7501)	model_time 0.8165 (0.7428)	loss 3.0789 (3.5687)	grad_norm 2.4381 (1.3042/0.6401)	mem 34602MB
[2025-01-19 03:34:21 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][210/312]	eta 0:01:16 lr 0.003717	time 0.8178 (0.7500)	model_time 0.8176 (0.7430)	loss 2.2768 (3.5718)	grad_norm 0.5337 (1.2859/0.6323)	mem 34602MB
[2025-01-19 03:34:29 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][220/312]	eta 0:01:09 lr 0.003717	time 0.7199 (0.7514)	model_time 0.7197 (0.7447)	loss 3.2840 (3.5702)	grad_norm 1.3198 (1.2905/0.6254)	mem 34602MB
[2025-01-19 03:34:36 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][230/312]	eta 0:01:01 lr 0.003716	time 0.7190 (0.7502)	model_time 0.7188 (0.7438)	loss 3.0626 (3.5783)	grad_norm 2.4013 (1.2975/0.6287)	mem 34602MB
[2025-01-19 03:34:44 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][240/312]	eta 0:00:53 lr 0.003716	time 0.7437 (0.7497)	model_time 0.7436 (0.7436)	loss 3.0561 (3.5915)	grad_norm 1.4164 (1.2971/0.6203)	mem 34602MB
[2025-01-19 03:34:51 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][250/312]	eta 0:00:46 lr 0.003716	time 0.7271 (0.7492)	model_time 0.7269 (0.7433)	loss 2.8134 (3.5942)	grad_norm 1.1185 (1.2912/0.6103)	mem 34602MB
[2025-01-19 03:34:59 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][260/312]	eta 0:00:38 lr 0.003715	time 0.7362 (0.7483)	model_time 0.7360 (0.7426)	loss 3.9695 (3.5958)	grad_norm 0.8873 (1.2786/0.6034)	mem 34602MB
[2025-01-19 03:35:06 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][270/312]	eta 0:00:31 lr 0.003715	time 0.7239 (0.7475)	model_time 0.7237 (0.7420)	loss 3.3267 (3.5859)	grad_norm 1.0301 (1.2861/0.5988)	mem 34602MB
[2025-01-19 03:35:13 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][280/312]	eta 0:00:23 lr 0.003715	time 0.7265 (0.7466)	model_time 0.7260 (0.7413)	loss 3.9859 (3.5903)	grad_norm 1.1628 (1.2935/0.6106)	mem 34602MB
[2025-01-19 03:35:20 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][290/312]	eta 0:00:16 lr 0.003714	time 0.7291 (0.7461)	model_time 0.7290 (0.7410)	loss 4.5388 (3.6023)	grad_norm 0.6494 (1.2883/0.6037)	mem 34602MB
[2025-01-19 03:35:28 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][300/312]	eta 0:00:08 lr 0.003714	time 0.7044 (0.7452)	model_time 0.7043 (0.7403)	loss 2.8109 (3.6082)	grad_norm 1.3245 (1.2842/0.5965)	mem 34602MB
[2025-01-19 03:35:35 internimage_b_1k_224] (main.py 510): INFO Train: [51/300][310/312]	eta 0:00:01 lr 0.003714	time 0.7817 (0.7453)	model_time 0.7816 (0.7405)	loss 3.9198 (3.6067)	grad_norm 1.7955 (1.2931/0.6008)	mem 34602MB
[2025-01-19 03:35:36 internimage_b_1k_224] (main.py 519): INFO EPOCH 51 training takes 0:03:52
[2025-01-19 03:35:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_51.pth saving......
[2025-01-19 03:35:39 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_51.pth saved !!!
[2025-01-19 03:35:47 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.634 (7.634)	Loss 0.9859 (0.9859)	Acc@1 78.638 (78.638)	Acc@5 95.020 (95.020)	Mem 34602MB
[2025-01-19 03:35:50 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.973)	Loss 1.3874 (1.1849)	Acc@1 69.434 (74.656)	Acc@5 89.917 (92.767)	Mem 34602MB
[2025-01-19 03:35:50 internimage_b_1k_224] (main.py 575): INFO [Epoch:51] * Acc@1 74.626 Acc@5 92.806
[2025-01-19 03:35:50 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 74.6%
[2025-01-19 03:35:50 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 75.09%
[2025-01-19 03:35:59 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.411 (9.411)	Loss 2.2162 (2.2162)	Acc@1 58.667 (58.667)	Acc@5 80.371 (80.371)	Mem 34602MB
[2025-01-19 03:36:04 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.268)	Loss 2.6303 (2.3155)	Acc@1 49.194 (54.972)	Acc@5 72.681 (78.755)	Mem 34602MB
[2025-01-19 03:36:04 internimage_b_1k_224] (main.py 575): INFO [Epoch:51] * Acc@1 55.242 Acc@5 79.163
[2025-01-19 03:36:04 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 55.2%
[2025-01-19 03:36:04 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:36:08 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:36:08 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 55.24%
[2025-01-19 03:36:11 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][0/312]	eta 0:12:02 lr 0.003714	time 2.3166 (2.3166)	model_time 0.7374 (0.7374)	loss 3.6901 (3.6901)	grad_norm 1.6027 (1.6027/0.0000)	mem 34602MB
[2025-01-19 03:36:19 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][10/312]	eta 0:04:43 lr 0.003713	time 0.8090 (0.9373)	model_time 0.8089 (0.7935)	loss 2.5734 (3.6162)	grad_norm 1.2035 (1.3119/0.3546)	mem 34602MB
[2025-01-19 03:36:26 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][20/312]	eta 0:04:08 lr 0.003713	time 0.8314 (0.8525)	model_time 0.8313 (0.7770)	loss 4.3041 (3.5800)	grad_norm 0.8571 (1.2907/0.4342)	mem 34602MB
[2025-01-19 03:36:34 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][30/312]	eta 0:03:51 lr 0.003713	time 0.7260 (0.8222)	model_time 0.7257 (0.7710)	loss 3.2507 (3.5511)	grad_norm 1.1697 (1.2006/0.4017)	mem 34602MB
[2025-01-19 03:36:41 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][40/312]	eta 0:03:37 lr 0.003712	time 0.7169 (0.7993)	model_time 0.7167 (0.7605)	loss 4.1478 (3.5879)	grad_norm 0.7842 (1.1368/0.3752)	mem 34602MB
[2025-01-19 03:36:48 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][50/312]	eta 0:03:25 lr 0.003712	time 0.7228 (0.7846)	model_time 0.7224 (0.7533)	loss 4.1849 (3.5440)	grad_norm 1.0968 (1.0978/0.3677)	mem 34602MB
[2025-01-19 03:36:55 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][60/312]	eta 0:03:15 lr 0.003712	time 0.7196 (0.7750)	model_time 0.7194 (0.7488)	loss 3.5739 (3.5719)	grad_norm 1.1973 (1.0491/0.3614)	mem 34602MB
[2025-01-19 03:37:03 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][70/312]	eta 0:03:05 lr 0.003711	time 0.7315 (0.7680)	model_time 0.7313 (0.7454)	loss 3.6731 (3.5650)	grad_norm 1.1498 (1.1476/0.4739)	mem 34602MB
[2025-01-19 03:37:10 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][80/312]	eta 0:02:57 lr 0.003711	time 0.7165 (0.7639)	model_time 0.7161 (0.7441)	loss 3.8422 (3.5510)	grad_norm 1.1939 (1.1816/0.4682)	mem 34602MB
[2025-01-19 03:37:17 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][90/312]	eta 0:02:48 lr 0.003711	time 0.7090 (0.7591)	model_time 0.7089 (0.7415)	loss 4.5932 (3.5794)	grad_norm 0.7117 (1.1827/0.4544)	mem 34602MB
[2025-01-19 03:37:25 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][100/312]	eta 0:02:40 lr 0.003710	time 0.7125 (0.7565)	model_time 0.7124 (0.7405)	loss 3.4590 (3.5978)	grad_norm 0.9528 (1.1551/0.4444)	mem 34602MB
[2025-01-19 03:37:32 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][110/312]	eta 0:02:32 lr 0.003710	time 0.7568 (0.7547)	model_time 0.7566 (0.7401)	loss 4.4650 (3.5973)	grad_norm 1.2959 (1.1764/0.4562)	mem 34602MB
[2025-01-19 03:37:40 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][120/312]	eta 0:02:25 lr 0.003709	time 0.7172 (0.7554)	model_time 0.7167 (0.7420)	loss 3.0112 (3.5872)	grad_norm 1.2026 (1.1808/0.4456)	mem 34602MB
[2025-01-19 03:37:47 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][130/312]	eta 0:02:17 lr 0.003709	time 0.8070 (0.7573)	model_time 0.8069 (0.7449)	loss 2.5328 (3.5697)	grad_norm 0.9026 (1.1767/0.4331)	mem 34602MB
[2025-01-19 03:37:55 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][140/312]	eta 0:02:10 lr 0.003709	time 0.8175 (0.7581)	model_time 0.8173 (0.7465)	loss 3.6623 (3.5760)	grad_norm 2.0297 (1.1862/0.4327)	mem 34602MB
[2025-01-19 03:38:03 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][150/312]	eta 0:02:03 lr 0.003708	time 0.7169 (0.7600)	model_time 0.7167 (0.7492)	loss 4.0726 (3.5747)	grad_norm 1.3371 (1.2092/0.4554)	mem 34602MB
[2025-01-19 03:38:10 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][160/312]	eta 0:01:55 lr 0.003708	time 0.7179 (0.7582)	model_time 0.7175 (0.7481)	loss 3.7255 (3.5721)	grad_norm 0.7544 (1.1908/0.4510)	mem 34602MB
[2025-01-19 03:38:18 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][170/312]	eta 0:01:47 lr 0.003708	time 0.7315 (0.7564)	model_time 0.7313 (0.7469)	loss 3.9152 (3.5832)	grad_norm 2.2735 (1.1871/0.4517)	mem 34602MB
[2025-01-19 03:38:25 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][180/312]	eta 0:01:39 lr 0.003707	time 0.7238 (0.7548)	model_time 0.7237 (0.7457)	loss 3.3012 (3.5790)	grad_norm 2.4310 (1.1984/0.4556)	mem 34602MB
[2025-01-19 03:38:32 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][190/312]	eta 0:01:31 lr 0.003707	time 0.7302 (0.7534)	model_time 0.7300 (0.7448)	loss 3.8622 (3.5885)	grad_norm 1.1737 (1.2032/0.4575)	mem 34602MB
[2025-01-19 03:38:39 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][200/312]	eta 0:01:24 lr 0.003707	time 0.7165 (0.7526)	model_time 0.7161 (0.7444)	loss 4.0702 (3.5850)	grad_norm 0.7750 (1.1920/0.4513)	mem 34602MB
[2025-01-19 03:38:47 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][210/312]	eta 0:01:16 lr 0.003706	time 0.7168 (0.7514)	model_time 0.7166 (0.7436)	loss 4.5742 (3.5859)	grad_norm 1.0950 (1.2009/0.4519)	mem 34602MB
[2025-01-19 03:38:54 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][220/312]	eta 0:01:09 lr 0.003706	time 0.7173 (0.7505)	model_time 0.7169 (0.7430)	loss 4.5227 (3.6138)	grad_norm 1.0010 (1.2044/0.4469)	mem 34602MB
[2025-01-19 03:39:01 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][230/312]	eta 0:01:01 lr 0.003706	time 0.7155 (0.7493)	model_time 0.7151 (0.7421)	loss 3.4653 (3.6009)	grad_norm 0.7928 (1.2120/0.4510)	mem 34602MB
[2025-01-19 03:39:09 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][240/312]	eta 0:00:53 lr 0.003705	time 0.7270 (0.7500)	model_time 0.7268 (0.7431)	loss 3.6286 (3.5951)	grad_norm 0.8284 (1.2050/0.4478)	mem 34602MB
[2025-01-19 03:39:17 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][250/312]	eta 0:00:46 lr 0.003705	time 0.7158 (0.7502)	model_time 0.7154 (0.7435)	loss 3.2029 (3.5980)	grad_norm 0.7424 (1.1987/0.4472)	mem 34602MB
[2025-01-19 03:39:24 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][260/312]	eta 0:00:38 lr 0.003705	time 0.7232 (0.7499)	model_time 0.7227 (0.7435)	loss 4.4056 (3.5967)	grad_norm 1.4857 (1.2103/0.4497)	mem 34602MB
[2025-01-19 03:39:32 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][270/312]	eta 0:00:31 lr 0.003704	time 0.7205 (0.7508)	model_time 0.7201 (0.7446)	loss 4.1945 (3.5938)	grad_norm 1.5224 (1.2354/0.4786)	mem 34602MB
[2025-01-19 03:39:39 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][280/312]	eta 0:00:23 lr 0.003704	time 0.7249 (0.7499)	model_time 0.7245 (0.7440)	loss 4.3521 (3.6063)	grad_norm 0.8918 (1.2386/0.4861)	mem 34602MB
[2025-01-19 03:39:46 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][290/312]	eta 0:00:16 lr 0.003704	time 0.7670 (0.7495)	model_time 0.7669 (0.7437)	loss 3.5785 (3.6134)	grad_norm 2.3818 (1.2401/0.4858)	mem 34602MB
[2025-01-19 03:39:54 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][300/312]	eta 0:00:08 lr 0.003703	time 0.7105 (0.7487)	model_time 0.7104 (0.7431)	loss 3.8128 (3.6111)	grad_norm 1.7695 (1.2392/0.4800)	mem 34602MB
[2025-01-19 03:40:01 internimage_b_1k_224] (main.py 510): INFO Train: [52/300][310/312]	eta 0:00:01 lr 0.003703	time 0.7117 (0.7476)	model_time 0.7116 (0.7421)	loss 3.5792 (3.6070)	grad_norm 1.4505 (1.2446/0.4856)	mem 34602MB
[2025-01-19 03:40:01 internimage_b_1k_224] (main.py 519): INFO EPOCH 52 training takes 0:03:53
[2025-01-19 03:40:01 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_52.pth saving......
[2025-01-19 03:40:05 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_52.pth saved !!!
[2025-01-19 03:40:12 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.173 (7.173)	Loss 0.9341 (0.9341)	Acc@1 80.273 (80.273)	Acc@5 95.410 (95.410)	Mem 34602MB
[2025-01-19 03:40:15 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.933)	Loss 1.3528 (1.1313)	Acc@1 70.752 (75.533)	Acc@5 90.259 (93.113)	Mem 34602MB
[2025-01-19 03:40:15 internimage_b_1k_224] (main.py 575): INFO [Epoch:52] * Acc@1 75.552 Acc@5 93.238
[2025-01-19 03:40:15 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.6%
[2025-01-19 03:40:15 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 03:40:18 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 03:40:18 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 75.55%
[2025-01-19 03:40:26 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.459 (7.459)	Loss 2.1179 (2.1179)	Acc@1 60.400 (60.400)	Acc@5 81.812 (81.812)	Mem 34602MB
[2025-01-19 03:40:29 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.186 (0.967)	Loss 2.5452 (2.2268)	Acc@1 50.391 (56.658)	Acc@5 73.828 (80.085)	Mem 34602MB
[2025-01-19 03:40:29 internimage_b_1k_224] (main.py 575): INFO [Epoch:52] * Acc@1 56.874 Acc@5 80.456
[2025-01-19 03:40:29 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 56.9%
[2025-01-19 03:40:29 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:40:33 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:40:33 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 56.87%
[2025-01-19 03:40:35 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][0/312]	eta 0:11:24 lr 0.003703	time 2.1944 (2.1944)	model_time 0.7427 (0.7427)	loss 3.6416 (3.6416)	grad_norm 1.1193 (1.1193/0.0000)	mem 34602MB
[2025-01-19 03:40:43 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][10/312]	eta 0:04:23 lr 0.003702	time 0.7548 (0.8713)	model_time 0.7547 (0.7391)	loss 2.8362 (3.5557)	grad_norm 1.1805 (0.9955/0.1299)	mem 34602MB
[2025-01-19 03:40:50 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][20/312]	eta 0:03:54 lr 0.003702	time 0.7338 (0.8027)	model_time 0.7336 (0.7333)	loss 3.7731 (3.4305)	grad_norm 2.2218 (1.0563/0.3064)	mem 34602MB
[2025-01-19 03:40:57 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][30/312]	eta 0:03:40 lr 0.003702	time 0.7436 (0.7809)	model_time 0.7434 (0.7337)	loss 3.5523 (3.4804)	grad_norm 1.1375 (1.0700/0.3071)	mem 34602MB
[2025-01-19 03:41:04 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][40/312]	eta 0:03:29 lr 0.003701	time 0.7448 (0.7686)	model_time 0.7447 (0.7329)	loss 4.0793 (3.5263)	grad_norm 1.0317 (1.1107/0.3146)	mem 34602MB
[2025-01-19 03:41:12 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][50/312]	eta 0:03:21 lr 0.003701	time 0.7244 (0.7695)	model_time 0.7242 (0.7407)	loss 3.8071 (3.6094)	grad_norm 2.2527 (1.2401/0.4307)	mem 34602MB
[2025-01-19 03:41:20 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][60/312]	eta 0:03:14 lr 0.003701	time 0.7188 (0.7721)	model_time 0.7186 (0.7480)	loss 2.5213 (3.5851)	grad_norm 0.7301 (1.2158/0.4150)	mem 34602MB
[2025-01-19 03:41:28 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][70/312]	eta 0:03:06 lr 0.003700	time 0.7177 (0.7710)	model_time 0.7173 (0.7503)	loss 3.6511 (3.5925)	grad_norm 1.3544 (1.2083/0.3934)	mem 34602MB
[2025-01-19 03:41:36 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][80/312]	eta 0:02:59 lr 0.003700	time 0.8216 (0.7726)	model_time 0.8214 (0.7544)	loss 3.8301 (3.5984)	grad_norm 0.7671 (1.2494/0.4434)	mem 34602MB
[2025-01-19 03:41:43 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][90/312]	eta 0:02:50 lr 0.003700	time 0.7491 (0.7681)	model_time 0.7487 (0.7518)	loss 4.0809 (3.5985)	grad_norm 1.2975 (1.2247/0.4398)	mem 34602MB
[2025-01-19 03:41:50 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][100/312]	eta 0:02:42 lr 0.003699	time 0.7163 (0.7642)	model_time 0.7162 (0.7495)	loss 3.2260 (3.6024)	grad_norm 1.0925 (1.2655/0.4969)	mem 34602MB
[2025-01-19 03:41:57 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][110/312]	eta 0:02:33 lr 0.003699	time 0.7285 (0.7610)	model_time 0.7283 (0.7476)	loss 3.8909 (3.6175)	grad_norm 1.7556 (1.2545/0.4834)	mem 34602MB
[2025-01-19 03:42:05 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][120/312]	eta 0:02:25 lr 0.003699	time 0.7177 (0.7580)	model_time 0.7172 (0.7457)	loss 3.5655 (3.6099)	grad_norm 1.0958 (1.2507/0.4792)	mem 34602MB
[2025-01-19 03:42:12 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][130/312]	eta 0:02:17 lr 0.003698	time 0.7360 (0.7564)	model_time 0.7359 (0.7450)	loss 3.9235 (3.6033)	grad_norm 1.3989 (1.2897/0.5237)	mem 34602MB
[2025-01-19 03:42:19 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][140/312]	eta 0:02:09 lr 0.003698	time 0.7309 (0.7544)	model_time 0.7304 (0.7438)	loss 3.4082 (3.5997)	grad_norm 0.6831 (1.2589/0.5207)	mem 34602MB
[2025-01-19 03:42:27 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][150/312]	eta 0:02:01 lr 0.003698	time 0.7318 (0.7529)	model_time 0.7317 (0.7429)	loss 3.3524 (3.6102)	grad_norm 0.7864 (1.2602/0.5151)	mem 34602MB
[2025-01-19 03:42:34 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][160/312]	eta 0:01:54 lr 0.003697	time 0.7298 (0.7511)	model_time 0.7297 (0.7418)	loss 3.7059 (3.6236)	grad_norm 2.5091 (1.2799/0.5170)	mem 34602MB
[2025-01-19 03:42:42 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][170/312]	eta 0:01:46 lr 0.003697	time 0.8093 (0.7522)	model_time 0.8088 (0.7433)	loss 4.1589 (3.6405)	grad_norm 1.0880 (1.2822/0.5077)	mem 34602MB
[2025-01-19 03:42:49 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][180/312]	eta 0:01:39 lr 0.003696	time 0.7159 (0.7535)	model_time 0.7155 (0.7451)	loss 3.7936 (3.6387)	grad_norm 3.8608 (1.3282/0.5773)	mem 34602MB
[2025-01-19 03:42:57 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][190/312]	eta 0:01:31 lr 0.003696	time 0.7201 (0.7530)	model_time 0.7196 (0.7451)	loss 3.8477 (3.6235)	grad_norm 1.5394 (1.3389/0.5985)	mem 34602MB
[2025-01-19 03:43:05 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][200/312]	eta 0:01:24 lr 0.003696	time 0.8312 (0.7545)	model_time 0.8307 (0.7470)	loss 3.5685 (3.6196)	grad_norm 3.4221 (1.3337/0.6077)	mem 34602MB
[2025-01-19 03:43:12 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][210/312]	eta 0:01:16 lr 0.003695	time 0.7272 (0.7532)	model_time 0.7268 (0.7460)	loss 4.6215 (3.6290)	grad_norm 1.6925 (1.3386/0.6111)	mem 34602MB
[2025-01-19 03:43:19 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][220/312]	eta 0:01:09 lr 0.003695	time 0.7163 (0.7520)	model_time 0.7161 (0.7451)	loss 3.8672 (3.6396)	grad_norm 0.8360 (1.3312/0.6037)	mem 34602MB
[2025-01-19 03:43:26 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][230/312]	eta 0:01:01 lr 0.003695	time 0.7466 (0.7510)	model_time 0.7465 (0.7443)	loss 3.3274 (3.6489)	grad_norm 1.0274 (1.3202/0.5963)	mem 34602MB
[2025-01-19 03:43:34 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][240/312]	eta 0:00:54 lr 0.003694	time 0.7305 (0.7500)	model_time 0.7303 (0.7437)	loss 3.9285 (3.6635)	grad_norm 0.8982 (1.3118/0.5936)	mem 34602MB
[2025-01-19 03:43:41 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][250/312]	eta 0:00:46 lr 0.003694	time 0.7145 (0.7498)	model_time 0.7144 (0.7436)	loss 3.5637 (3.6515)	grad_norm 1.0849 (1.2969/0.5883)	mem 34602MB
[2025-01-19 03:43:48 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][260/312]	eta 0:00:38 lr 0.003694	time 0.7279 (0.7488)	model_time 0.7275 (0.7429)	loss 3.3543 (3.6384)	grad_norm 1.0737 (1.2839/0.5825)	mem 34602MB
[2025-01-19 03:43:56 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][270/312]	eta 0:00:31 lr 0.003693	time 0.7155 (0.7481)	model_time 0.7153 (0.7424)	loss 4.3722 (3.6379)	grad_norm 1.0544 (1.2863/0.5786)	mem 34602MB
[2025-01-19 03:44:03 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][280/312]	eta 0:00:23 lr 0.003693	time 0.7163 (0.7473)	model_time 0.7159 (0.7418)	loss 2.3817 (3.6231)	grad_norm 1.1213 (1.2805/0.5716)	mem 34602MB
[2025-01-19 03:44:11 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][290/312]	eta 0:00:16 lr 0.003693	time 0.8076 (0.7482)	model_time 0.8071 (0.7429)	loss 3.9648 (3.6302)	grad_norm 0.7993 (1.2849/0.5775)	mem 34602MB
[2025-01-19 03:44:18 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][300/312]	eta 0:00:08 lr 0.003692	time 0.7114 (0.7482)	model_time 0.7112 (0.7430)	loss 4.1201 (3.6349)	grad_norm 1.5773 (1.2937/0.5843)	mem 34602MB
[2025-01-19 03:44:26 internimage_b_1k_224] (main.py 510): INFO Train: [53/300][310/312]	eta 0:00:01 lr 0.003692	time 0.7115 (0.7481)	model_time 0.7114 (0.7431)	loss 3.6103 (3.6388)	grad_norm 0.9049 (1.2892/0.5874)	mem 34602MB
[2025-01-19 03:44:26 internimage_b_1k_224] (main.py 519): INFO EPOCH 53 training takes 0:03:53
[2025-01-19 03:44:26 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_53.pth saving......
[2025-01-19 03:44:29 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_53.pth saved !!!
[2025-01-19 03:44:46 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.708 (16.708)	Loss 0.9553 (0.9553)	Acc@1 79.590 (79.590)	Acc@5 95.410 (95.410)	Mem 34602MB
[2025-01-19 03:44:53 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (2.131)	Loss 1.3887 (1.1499)	Acc@1 70.020 (75.462)	Acc@5 90.186 (93.140)	Mem 34602MB
[2025-01-19 03:44:53 internimage_b_1k_224] (main.py 575): INFO [Epoch:53] * Acc@1 75.438 Acc@5 93.206
[2025-01-19 03:44:53 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.4%
[2025-01-19 03:44:53 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 75.55%
[2025-01-19 03:45:02 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.058 (9.058)	Loss 2.0270 (2.0270)	Acc@1 61.792 (61.792)	Acc@5 83.179 (83.179)	Mem 34602MB
[2025-01-19 03:45:07 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.234)	Loss 2.4679 (2.1458)	Acc@1 51.733 (58.088)	Acc@5 74.951 (81.228)	Mem 34602MB
[2025-01-19 03:45:07 internimage_b_1k_224] (main.py 575): INFO [Epoch:53] * Acc@1 58.269 Acc@5 81.594
[2025-01-19 03:45:07 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 58.3%
[2025-01-19 03:45:07 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:45:11 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:45:11 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 58.27%
[2025-01-19 03:45:13 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][0/312]	eta 0:10:29 lr 0.003692	time 2.0176 (2.0176)	model_time 0.7501 (0.7501)	loss 4.6265 (4.6265)	grad_norm 1.9934 (1.9934/0.0000)	mem 34602MB
[2025-01-19 03:45:21 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][10/312]	eta 0:04:36 lr 0.003691	time 0.8814 (0.9164)	model_time 0.8812 (0.8009)	loss 2.4920 (3.5429)	grad_norm 2.0644 (1.5812/0.4770)	mem 34602MB
[2025-01-19 03:45:28 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][20/312]	eta 0:04:01 lr 0.003691	time 0.7191 (0.8263)	model_time 0.7186 (0.7656)	loss 3.4067 (3.7190)	grad_norm 0.7530 (1.4030/0.4813)	mem 34602MB
[2025-01-19 03:45:36 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][30/312]	eta 0:03:44 lr 0.003691	time 0.7700 (0.7953)	model_time 0.7699 (0.7540)	loss 4.2607 (3.7035)	grad_norm 0.9565 (1.3689/0.4846)	mem 34602MB
[2025-01-19 03:45:43 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][40/312]	eta 0:03:31 lr 0.003690	time 0.7272 (0.7792)	model_time 0.7267 (0.7479)	loss 3.1050 (3.6744)	grad_norm 1.1093 (1.4082/0.5908)	mem 34602MB
[2025-01-19 03:45:50 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][50/312]	eta 0:03:21 lr 0.003690	time 0.7228 (0.7697)	model_time 0.7224 (0.7445)	loss 4.3398 (3.6754)	grad_norm 2.3048 (1.3843/0.5735)	mem 34602MB
[2025-01-19 03:45:58 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][60/312]	eta 0:03:12 lr 0.003690	time 0.7274 (0.7629)	model_time 0.7273 (0.7417)	loss 2.9751 (3.6127)	grad_norm 0.7729 (1.3979/0.5427)	mem 34602MB
[2025-01-19 03:46:05 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][70/312]	eta 0:03:03 lr 0.003689	time 0.7227 (0.7584)	model_time 0.7225 (0.7402)	loss 4.0993 (3.6457)	grad_norm 1.2587 (1.3610/0.5427)	mem 34602MB
[2025-01-19 03:46:12 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][80/312]	eta 0:02:55 lr 0.003689	time 0.7452 (0.7556)	model_time 0.7448 (0.7396)	loss 3.1281 (3.6185)	grad_norm 1.7233 (1.3967/0.5479)	mem 34602MB
[2025-01-19 03:46:20 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][90/312]	eta 0:02:47 lr 0.003689	time 0.7382 (0.7527)	model_time 0.7381 (0.7384)	loss 3.5247 (3.5814)	grad_norm 0.8702 (1.3563/0.5378)	mem 34602MB
[2025-01-19 03:46:27 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][100/312]	eta 0:02:39 lr 0.003688	time 0.7196 (0.7539)	model_time 0.7192 (0.7409)	loss 4.1592 (3.6113)	grad_norm 1.4131 (1.3480/0.5210)	mem 34602MB
[2025-01-19 03:46:35 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][110/312]	eta 0:02:32 lr 0.003688	time 0.8138 (0.7556)	model_time 0.8136 (0.7438)	loss 3.0883 (3.6229)	grad_norm 1.1817 (1.3140/0.5120)	mem 34602MB
[2025-01-19 03:46:43 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][120/312]	eta 0:02:25 lr 0.003687	time 0.7272 (0.7566)	model_time 0.7270 (0.7457)	loss 3.4060 (3.6097)	grad_norm 0.7968 (1.3057/0.5098)	mem 34602MB
[2025-01-19 03:46:50 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][130/312]	eta 0:02:17 lr 0.003687	time 0.7184 (0.7578)	model_time 0.7183 (0.7478)	loss 2.3961 (3.6174)	grad_norm 1.1698 (1.2865/0.4999)	mem 34602MB
[2025-01-19 03:46:58 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][140/312]	eta 0:02:10 lr 0.003687	time 0.7283 (0.7572)	model_time 0.7282 (0.7479)	loss 2.9318 (3.5980)	grad_norm 1.5817 (1.2926/0.4848)	mem 34602MB
[2025-01-19 03:47:05 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][150/312]	eta 0:02:02 lr 0.003686	time 0.7143 (0.7554)	model_time 0.7141 (0.7466)	loss 3.2918 (3.6021)	grad_norm 1.1851 (1.3174/0.5037)	mem 34602MB
[2025-01-19 03:47:12 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][160/312]	eta 0:01:54 lr 0.003686	time 0.7190 (0.7537)	model_time 0.7185 (0.7455)	loss 4.3226 (3.6027)	grad_norm 1.5368 (1.3109/0.4930)	mem 34602MB
[2025-01-19 03:47:20 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][170/312]	eta 0:01:46 lr 0.003686	time 0.7176 (0.7521)	model_time 0.7175 (0.7444)	loss 3.7238 (3.5956)	grad_norm 1.8886 (1.3194/0.4923)	mem 34602MB
[2025-01-19 03:47:27 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][180/312]	eta 0:01:39 lr 0.003685	time 0.7168 (0.7508)	model_time 0.7166 (0.7434)	loss 2.4514 (3.5808)	grad_norm 2.3422 (1.3292/0.4950)	mem 34602MB
[2025-01-19 03:47:34 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][190/312]	eta 0:01:31 lr 0.003685	time 0.7397 (0.7497)	model_time 0.7392 (0.7427)	loss 3.9157 (3.5672)	grad_norm 1.5485 (1.3141/0.4891)	mem 34602MB
[2025-01-19 03:47:42 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][200/312]	eta 0:01:23 lr 0.003685	time 0.7165 (0.7489)	model_time 0.7164 (0.7423)	loss 2.1682 (3.5666)	grad_norm 0.8567 (1.3011/0.4879)	mem 34602MB
[2025-01-19 03:47:49 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][210/312]	eta 0:01:16 lr 0.003684	time 0.7526 (0.7480)	model_time 0.7524 (0.7416)	loss 3.7354 (3.5628)	grad_norm 1.4820 (1.3165/0.4942)	mem 34602MB
[2025-01-19 03:47:56 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][220/312]	eta 0:01:08 lr 0.003684	time 0.8032 (0.7485)	model_time 0.8028 (0.7424)	loss 3.1765 (3.5659)	grad_norm 1.9258 (1.3284/0.5068)	mem 34602MB
[2025-01-19 03:48:04 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][230/312]	eta 0:01:01 lr 0.003684	time 0.8315 (0.7501)	model_time 0.8314 (0.7442)	loss 2.9861 (3.5662)	grad_norm 1.5724 (1.3442/0.5073)	mem 34602MB
[2025-01-19 03:48:12 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][240/312]	eta 0:00:54 lr 0.003683	time 0.7190 (0.7505)	model_time 0.7188 (0.7449)	loss 3.4517 (3.5821)	grad_norm 1.5096 (1.3455/0.5022)	mem 34602MB
[2025-01-19 03:48:20 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][250/312]	eta 0:00:46 lr 0.003683	time 0.7351 (0.7515)	model_time 0.7346 (0.7461)	loss 3.8328 (3.5833)	grad_norm 0.8219 (1.3478/0.5051)	mem 34602MB
[2025-01-19 03:48:27 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][260/312]	eta 0:00:39 lr 0.003682	time 0.7300 (0.7513)	model_time 0.7298 (0.7461)	loss 3.8539 (3.5872)	grad_norm 1.4095 (1.3477/0.5027)	mem 34602MB
[2025-01-19 03:48:34 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][270/312]	eta 0:00:31 lr 0.003682	time 0.7457 (0.7505)	model_time 0.7456 (0.7454)	loss 3.8870 (3.5996)	grad_norm 2.5773 (1.3461/0.5014)	mem 34602MB
[2025-01-19 03:48:42 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][280/312]	eta 0:00:23 lr 0.003682	time 0.7257 (0.7499)	model_time 0.7253 (0.7450)	loss 2.8263 (3.5928)	grad_norm 0.7697 (1.3447/0.4962)	mem 34602MB
[2025-01-19 03:48:49 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][290/312]	eta 0:00:16 lr 0.003681	time 0.7580 (0.7493)	model_time 0.7574 (0.7446)	loss 3.9307 (3.5985)	grad_norm 1.0448 (1.3471/0.4963)	mem 34602MB
[2025-01-19 03:48:56 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][300/312]	eta 0:00:08 lr 0.003681	time 0.7186 (0.7484)	model_time 0.7185 (0.7438)	loss 4.4397 (3.6019)	grad_norm 1.0471 (1.3384/0.4932)	mem 34602MB
[2025-01-19 03:49:03 internimage_b_1k_224] (main.py 510): INFO Train: [54/300][310/312]	eta 0:00:01 lr 0.003681	time 0.7107 (0.7472)	model_time 0.7106 (0.7428)	loss 4.4468 (3.6114)	grad_norm 1.4986 (1.3346/0.4936)	mem 34602MB
[2025-01-19 03:49:04 internimage_b_1k_224] (main.py 519): INFO EPOCH 54 training takes 0:03:53
[2025-01-19 03:49:04 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_54.pth saving......
[2025-01-19 03:49:07 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_54.pth saved !!!
[2025-01-19 03:49:15 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.669 (7.669)	Loss 0.9272 (0.9272)	Acc@1 78.906 (78.906)	Acc@5 95.068 (95.068)	Mem 34602MB
[2025-01-19 03:49:18 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.970)	Loss 1.3258 (1.1179)	Acc@1 70.410 (75.073)	Acc@5 90.405 (92.858)	Mem 34602MB
[2025-01-19 03:49:18 internimage_b_1k_224] (main.py 575): INFO [Epoch:54] * Acc@1 75.084 Acc@5 92.904
[2025-01-19 03:49:18 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.1%
[2025-01-19 03:49:18 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 75.55%
[2025-01-19 03:49:27 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.996 (8.996)	Loss 1.9424 (1.9424)	Acc@1 63.330 (63.330)	Acc@5 84.229 (84.229)	Mem 34602MB
[2025-01-19 03:49:32 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.229)	Loss 2.3935 (2.0694)	Acc@1 52.979 (59.495)	Acc@5 75.952 (82.282)	Mem 34602MB
[2025-01-19 03:49:32 internimage_b_1k_224] (main.py 575): INFO [Epoch:54] * Acc@1 59.663 Acc@5 82.638
[2025-01-19 03:49:32 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 59.7%
[2025-01-19 03:49:32 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:49:36 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:49:36 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 59.66%
[2025-01-19 03:49:38 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][0/312]	eta 0:11:36 lr 0.003681	time 2.2311 (2.2311)	model_time 0.7558 (0.7558)	loss 4.7168 (4.7168)	grad_norm 1.9114 (1.9114/0.0000)	mem 34602MB
[2025-01-19 03:49:46 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][10/312]	eta 0:04:23 lr 0.003680	time 0.7146 (0.8713)	model_time 0.7144 (0.7369)	loss 3.3072 (3.6534)	grad_norm 2.1368 (1.4381/0.4542)	mem 34602MB
[2025-01-19 03:49:53 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][20/312]	eta 0:03:54 lr 0.003680	time 0.7208 (0.8022)	model_time 0.7204 (0.7316)	loss 2.3444 (3.5819)	grad_norm 1.9451 (1.5106/0.4593)	mem 34602MB
[2025-01-19 03:50:00 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][30/312]	eta 0:03:42 lr 0.003679	time 0.7240 (0.7880)	model_time 0.7238 (0.7401)	loss 3.7668 (3.4587)	grad_norm 0.7118 (1.3970/0.4579)	mem 34602MB
[2025-01-19 03:50:08 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][40/312]	eta 0:03:34 lr 0.003679	time 0.8115 (0.7895)	model_time 0.8113 (0.7532)	loss 3.4535 (3.5310)	grad_norm 1.2336 (1.3227/0.4294)	mem 34602MB
[2025-01-19 03:50:16 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][50/312]	eta 0:03:24 lr 0.003679	time 0.7175 (0.7818)	model_time 0.7173 (0.7526)	loss 3.7313 (3.5510)	grad_norm 2.0724 (1.2859/0.4209)	mem 34602MB
[2025-01-19 03:50:24 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][60/312]	eta 0:03:17 lr 0.003678	time 0.7178 (0.7827)	model_time 0.7177 (0.7582)	loss 4.3180 (3.5625)	grad_norm 1.0321 (1.2998/0.4283)	mem 34602MB
[2025-01-19 03:50:31 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][70/312]	eta 0:03:07 lr 0.003678	time 0.7304 (0.7751)	model_time 0.7302 (0.7539)	loss 2.9871 (3.5368)	grad_norm 1.6243 (1.3008/0.4172)	mem 34602MB
[2025-01-19 03:50:38 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][80/312]	eta 0:02:58 lr 0.003678	time 0.7162 (0.7692)	model_time 0.7157 (0.7506)	loss 3.3437 (3.5510)	grad_norm 0.7791 (1.2830/0.4096)	mem 34602MB
[2025-01-19 03:50:46 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][90/312]	eta 0:02:49 lr 0.003677	time 0.7104 (0.7642)	model_time 0.7099 (0.7476)	loss 3.5573 (3.5777)	grad_norm 1.5668 (1.2595/0.4017)	mem 34602MB
[2025-01-19 03:50:53 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][100/312]	eta 0:02:41 lr 0.003677	time 0.7164 (0.7614)	model_time 0.7162 (0.7464)	loss 4.5160 (3.5931)	grad_norm 0.9410 (1.2331/0.3940)	mem 34602MB
[2025-01-19 03:51:00 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][110/312]	eta 0:02:33 lr 0.003677	time 0.7366 (0.7583)	model_time 0.7364 (0.7447)	loss 2.5022 (3.5894)	grad_norm 1.1135 (1.2212/0.3885)	mem 34602MB
[2025-01-19 03:51:07 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][120/312]	eta 0:02:25 lr 0.003676	time 0.7442 (0.7555)	model_time 0.7437 (0.7429)	loss 3.7738 (3.5738)	grad_norm 1.8065 (1.2351/0.3904)	mem 34602MB
[2025-01-19 03:51:15 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][130/312]	eta 0:02:17 lr 0.003676	time 0.7173 (0.7535)	model_time 0.7171 (0.7419)	loss 3.7984 (3.5963)	grad_norm 1.7959 (1.2661/0.4335)	mem 34602MB
[2025-01-19 03:51:22 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][140/312]	eta 0:02:09 lr 0.003675	time 0.7147 (0.7518)	model_time 0.7142 (0.7410)	loss 3.6855 (3.5977)	grad_norm 0.9725 (1.2732/0.4450)	mem 34602MB
[2025-01-19 03:51:30 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][150/312]	eta 0:02:01 lr 0.003675	time 0.7305 (0.7517)	model_time 0.7300 (0.7416)	loss 3.6824 (3.6022)	grad_norm 0.9426 (1.2415/0.4470)	mem 34602MB
[2025-01-19 03:51:37 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][160/312]	eta 0:01:54 lr 0.003675	time 0.8328 (0.7531)	model_time 0.8327 (0.7436)	loss 3.9822 (3.6059)	grad_norm 1.1922 (1.2610/0.4534)	mem 34602MB
[2025-01-19 03:51:45 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][170/312]	eta 0:01:47 lr 0.003674	time 0.7169 (0.7536)	model_time 0.7165 (0.7446)	loss 3.6722 (3.6121)	grad_norm 0.7482 (1.2543/0.4635)	mem 34602MB
[2025-01-19 03:51:53 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][180/312]	eta 0:01:39 lr 0.003674	time 0.8473 (0.7561)	model_time 0.8471 (0.7476)	loss 2.9428 (3.6033)	grad_norm 2.7144 (1.2468/0.4717)	mem 34602MB
[2025-01-19 03:52:00 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][190/312]	eta 0:01:32 lr 0.003674	time 0.7459 (0.7554)	model_time 0.7458 (0.7473)	loss 4.1545 (3.5977)	grad_norm 1.2727 (1.2529/0.4647)	mem 34602MB
[2025-01-19 03:52:08 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][200/312]	eta 0:01:24 lr 0.003673	time 0.7333 (0.7540)	model_time 0.7328 (0.7463)	loss 3.8318 (3.6008)	grad_norm 1.0218 (1.2569/0.4618)	mem 34602MB
[2025-01-19 03:52:15 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][210/312]	eta 0:01:16 lr 0.003673	time 0.7177 (0.7529)	model_time 0.7175 (0.7456)	loss 4.4311 (3.6035)	grad_norm 0.9535 (1.2505/0.4565)	mem 34602MB
[2025-01-19 03:52:22 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][220/312]	eta 0:01:09 lr 0.003673	time 0.7146 (0.7519)	model_time 0.7141 (0.7449)	loss 2.3450 (3.5887)	grad_norm 0.8935 (1.2554/0.4581)	mem 34602MB
[2025-01-19 03:52:29 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][230/312]	eta 0:01:01 lr 0.003672	time 0.7216 (0.7507)	model_time 0.7212 (0.7439)	loss 4.4989 (3.5887)	grad_norm 2.2879 (1.2715/0.4756)	mem 34602MB
[2025-01-19 03:52:37 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][240/312]	eta 0:00:53 lr 0.003672	time 0.7498 (0.7497)	model_time 0.7493 (0.7432)	loss 3.8230 (3.5957)	grad_norm 0.7455 (1.2795/0.4883)	mem 34602MB
[2025-01-19 03:52:44 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][250/312]	eta 0:00:46 lr 0.003671	time 0.7474 (0.7491)	model_time 0.7470 (0.7429)	loss 3.6182 (3.6017)	grad_norm 1.1019 (1.2870/0.4859)	mem 34602MB
[2025-01-19 03:52:51 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][260/312]	eta 0:00:38 lr 0.003671	time 0.7178 (0.7482)	model_time 0.7176 (0.7422)	loss 4.2192 (3.6073)	grad_norm 0.6697 (1.2818/0.4844)	mem 34602MB
[2025-01-19 03:52:59 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][270/312]	eta 0:00:31 lr 0.003671	time 0.7188 (0.7486)	model_time 0.7186 (0.7428)	loss 4.1225 (3.6081)	grad_norm 0.6911 (1.2856/0.4956)	mem 34602MB
[2025-01-19 03:53:07 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][280/312]	eta 0:00:23 lr 0.003670	time 0.9386 (0.7498)	model_time 0.9381 (0.7442)	loss 3.0969 (3.6097)	grad_norm 0.9686 (1.2747/0.4929)	mem 34602MB
[2025-01-19 03:53:14 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][290/312]	eta 0:00:16 lr 0.003670	time 0.7211 (0.7500)	model_time 0.7206 (0.7446)	loss 3.1416 (3.6003)	grad_norm 1.6110 (1.2663/0.4902)	mem 34602MB
[2025-01-19 03:53:22 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][300/312]	eta 0:00:09 lr 0.003670	time 0.7968 (0.7507)	model_time 0.7967 (0.7455)	loss 3.9716 (3.5920)	grad_norm 1.3236 (1.2741/0.4961)	mem 34602MB
[2025-01-19 03:53:29 internimage_b_1k_224] (main.py 510): INFO Train: [55/300][310/312]	eta 0:00:01 lr 0.003669	time 0.7114 (0.7504)	model_time 0.7113 (0.7453)	loss 4.4681 (3.5975)	grad_norm 1.3416 (1.2638/0.4914)	mem 34602MB
[2025-01-19 03:53:30 internimage_b_1k_224] (main.py 519): INFO EPOCH 55 training takes 0:03:54
[2025-01-19 03:53:30 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_55.pth saving......
[2025-01-19 03:53:33 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_55.pth saved !!!
[2025-01-19 03:53:41 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.150 (7.150)	Loss 0.9465 (0.9465)	Acc@1 79.785 (79.785)	Acc@5 95.410 (95.410)	Mem 34602MB
[2025-01-19 03:53:44 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.910)	Loss 1.3472 (1.1239)	Acc@1 70.947 (75.781)	Acc@5 90.771 (93.180)	Mem 34602MB
[2025-01-19 03:53:44 internimage_b_1k_224] (main.py 575): INFO [Epoch:55] * Acc@1 75.728 Acc@5 93.240
[2025-01-19 03:53:44 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.7%
[2025-01-19 03:53:44 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 03:53:47 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 03:53:47 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 75.73%
[2025-01-19 03:53:54 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.413 (7.413)	Loss 1.8644 (1.8644)	Acc@1 64.551 (64.551)	Acc@5 85.303 (85.303)	Mem 34602MB
[2025-01-19 03:53:57 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.184 (0.946)	Loss 2.3245 (1.9990)	Acc@1 53.906 (60.784)	Acc@5 77.246 (83.248)	Mem 34602MB
[2025-01-19 03:53:58 internimage_b_1k_224] (main.py 575): INFO [Epoch:55] * Acc@1 60.933 Acc@5 83.589
[2025-01-19 03:53:58 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 60.9%
[2025-01-19 03:53:58 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:54:01 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:54:01 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 60.93%
[2025-01-19 03:54:04 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][0/312]	eta 0:11:17 lr 0.003669	time 2.1708 (2.1708)	model_time 0.7315 (0.7315)	loss 3.2755 (3.2755)	grad_norm 3.0491 (3.0491/0.0000)	mem 34602MB
[2025-01-19 03:54:11 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][10/312]	eta 0:04:19 lr 0.003669	time 0.7296 (0.8582)	model_time 0.7295 (0.7271)	loss 3.8215 (3.5425)	grad_norm 1.3581 (1.2743/0.6297)	mem 34602MB
[2025-01-19 03:54:18 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][20/312]	eta 0:03:53 lr 0.003668	time 0.7515 (0.8005)	model_time 0.7513 (0.7316)	loss 2.7803 (3.5438)	grad_norm 1.0153 (1.1299/0.4938)	mem 34602MB
[2025-01-19 03:54:26 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][30/312]	eta 0:03:39 lr 0.003668	time 0.7237 (0.7784)	model_time 0.7235 (0.7316)	loss 2.5667 (3.4363)	grad_norm 0.7833 (1.0457/0.4378)	mem 34602MB
[2025-01-19 03:54:33 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][40/312]	eta 0:03:28 lr 0.003668	time 0.7251 (0.7666)	model_time 0.7246 (0.7312)	loss 2.8885 (3.5068)	grad_norm 1.5773 (1.0621/0.4234)	mem 34602MB
[2025-01-19 03:54:40 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][50/312]	eta 0:03:18 lr 0.003667	time 0.7177 (0.7587)	model_time 0.7172 (0.7301)	loss 4.4599 (3.5657)	grad_norm 1.2800 (1.0881/0.4251)	mem 34602MB
[2025-01-19 03:54:47 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][60/312]	eta 0:03:09 lr 0.003667	time 0.7170 (0.7532)	model_time 0.7168 (0.7292)	loss 2.9329 (3.5346)	grad_norm 2.4760 (1.2452/0.6901)	mem 34602MB
[2025-01-19 03:54:55 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][70/312]	eta 0:03:01 lr 0.003667	time 0.7148 (0.7499)	model_time 0.7146 (0.7293)	loss 4.0827 (3.5668)	grad_norm 1.0062 (1.2621/0.6588)	mem 34602MB
[2025-01-19 03:55:02 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][80/312]	eta 0:02:54 lr 0.003666	time 0.7174 (0.7520)	model_time 0.7172 (0.7339)	loss 4.4505 (3.5416)	grad_norm 0.7559 (1.2476/0.6347)	mem 34602MB
[2025-01-19 03:55:10 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][90/312]	eta 0:02:47 lr 0.003666	time 0.7150 (0.7556)	model_time 0.7145 (0.7394)	loss 3.1601 (3.5280)	grad_norm 1.2081 (1.2229/0.6093)	mem 34602MB
[2025-01-19 03:55:18 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][100/312]	eta 0:02:40 lr 0.003665	time 0.7392 (0.7559)	model_time 0.7390 (0.7413)	loss 4.2632 (3.5648)	grad_norm 3.3241 (1.2473/0.6505)	mem 34602MB
[2025-01-19 03:55:26 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][110/312]	eta 0:02:33 lr 0.003665	time 0.8083 (0.7584)	model_time 0.8078 (0.7451)	loss 3.7428 (3.5645)	grad_norm 1.3979 (1.2476/0.6421)	mem 34602MB
[2025-01-19 03:55:33 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][120/312]	eta 0:02:25 lr 0.003665	time 0.7438 (0.7564)	model_time 0.7432 (0.7442)	loss 4.0984 (3.5817)	grad_norm 1.1390 (1.2217/0.6243)	mem 34602MB
[2025-01-19 03:55:40 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][130/312]	eta 0:02:17 lr 0.003664	time 0.7108 (0.7542)	model_time 0.7106 (0.7428)	loss 3.6554 (3.5830)	grad_norm 0.7777 (1.2258/0.6078)	mem 34602MB
[2025-01-19 03:55:48 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][140/312]	eta 0:02:09 lr 0.003664	time 0.7443 (0.7532)	model_time 0.7438 (0.7426)	loss 3.8981 (3.5839)	grad_norm 1.1339 (1.2354/0.6079)	mem 34602MB
[2025-01-19 03:55:55 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][150/312]	eta 0:02:01 lr 0.003664	time 0.7160 (0.7514)	model_time 0.7156 (0.7416)	loss 4.0605 (3.5830)	grad_norm 1.9822 (1.2438/0.6165)	mem 34602MB
[2025-01-19 03:56:02 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][160/312]	eta 0:01:53 lr 0.003663	time 0.7161 (0.7499)	model_time 0.7159 (0.7406)	loss 2.6608 (3.5741)	grad_norm 1.0174 (1.2309/0.6023)	mem 34602MB
[2025-01-19 03:56:09 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][170/312]	eta 0:01:46 lr 0.003663	time 0.7217 (0.7483)	model_time 0.7213 (0.7395)	loss 4.0161 (3.5901)	grad_norm 1.4269 (1.2286/0.5951)	mem 34602MB
[2025-01-19 03:56:17 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][180/312]	eta 0:01:38 lr 0.003663	time 0.7192 (0.7472)	model_time 0.7187 (0.7389)	loss 4.1569 (3.5813)	grad_norm 1.1443 (1.2239/0.5808)	mem 34602MB
[2025-01-19 03:56:24 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][190/312]	eta 0:01:31 lr 0.003662	time 0.7254 (0.7465)	model_time 0.7252 (0.7386)	loss 3.7405 (3.5883)	grad_norm 1.9758 (1.2460/0.5902)	mem 34602MB
[2025-01-19 03:56:32 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][200/312]	eta 0:01:23 lr 0.003662	time 0.8158 (0.7476)	model_time 0.8156 (0.7401)	loss 3.8779 (3.5918)	grad_norm 3.8140 (1.2642/0.6082)	mem 34602MB
[2025-01-19 03:56:39 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][210/312]	eta 0:01:16 lr 0.003661	time 0.7182 (0.7481)	model_time 0.7178 (0.7409)	loss 4.4871 (3.5867)	grad_norm 0.7945 (1.2678/0.6094)	mem 34602MB
[2025-01-19 03:56:47 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][220/312]	eta 0:01:08 lr 0.003661	time 0.7375 (0.7486)	model_time 0.7374 (0.7418)	loss 2.4343 (3.5682)	grad_norm 1.4292 (1.2651/0.5979)	mem 34602MB
[2025-01-19 03:56:55 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][230/312]	eta 0:01:01 lr 0.003661	time 0.8074 (0.7501)	model_time 0.8072 (0.7435)	loss 3.6284 (3.5714)	grad_norm 2.0810 (1.2650/0.5889)	mem 34602MB
[2025-01-19 03:57:02 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][240/312]	eta 0:00:54 lr 0.003660	time 0.7220 (0.7502)	model_time 0.7216 (0.7438)	loss 4.5267 (3.5747)	grad_norm 1.1257 (1.2695/0.5867)	mem 34602MB
[2025-01-19 03:57:10 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][250/312]	eta 0:00:46 lr 0.003660	time 0.7239 (0.7491)	model_time 0.7237 (0.7430)	loss 3.4978 (3.5739)	grad_norm 1.4000 (1.2641/0.5774)	mem 34602MB
[2025-01-19 03:57:17 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][260/312]	eta 0:00:38 lr 0.003660	time 0.7176 (0.7484)	model_time 0.7172 (0.7425)	loss 3.2451 (3.5731)	grad_norm 1.2776 (1.2630/0.5679)	mem 34602MB
[2025-01-19 03:57:24 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][270/312]	eta 0:00:31 lr 0.003659	time 0.7816 (0.7478)	model_time 0.7815 (0.7421)	loss 4.5719 (3.5749)	grad_norm 1.0913 (1.2620/0.5611)	mem 34602MB
[2025-01-19 03:57:31 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][280/312]	eta 0:00:23 lr 0.003659	time 0.7254 (0.7469)	model_time 0.7252 (0.7414)	loss 4.5809 (3.5784)	grad_norm 1.1535 (1.2605/0.5528)	mem 34602MB
[2025-01-19 03:57:39 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][290/312]	eta 0:00:16 lr 0.003658	time 0.7326 (0.7462)	model_time 0.7324 (0.7409)	loss 4.0259 (3.5821)	grad_norm 1.6112 (1.2677/0.5538)	mem 34602MB
[2025-01-19 03:57:46 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][300/312]	eta 0:00:08 lr 0.003658	time 0.7132 (0.7452)	model_time 0.7131 (0.7401)	loss 4.2991 (3.5861)	grad_norm 1.0858 (1.2617/0.5480)	mem 34602MB
[2025-01-19 03:57:53 internimage_b_1k_224] (main.py 510): INFO Train: [56/300][310/312]	eta 0:00:01 lr 0.003658	time 0.7140 (0.7447)	model_time 0.7139 (0.7397)	loss 3.3912 (3.5809)	grad_norm 2.8310 (1.2736/0.5464)	mem 34602MB
[2025-01-19 03:57:54 internimage_b_1k_224] (main.py 519): INFO EPOCH 56 training takes 0:03:52
[2025-01-19 03:57:54 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_56.pth saving......
[2025-01-19 03:57:57 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_56.pth saved !!!
[2025-01-19 03:58:04 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.416 (7.416)	Loss 0.9651 (0.9651)	Acc@1 80.127 (80.127)	Acc@5 95.801 (95.801)	Mem 34602MB
[2025-01-19 03:58:07 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.183 (0.933)	Loss 1.3349 (1.1294)	Acc@1 70.435 (75.544)	Acc@5 90.210 (93.144)	Mem 34602MB
[2025-01-19 03:58:08 internimage_b_1k_224] (main.py 575): INFO [Epoch:56] * Acc@1 75.596 Acc@5 93.206
[2025-01-19 03:58:08 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.6%
[2025-01-19 03:58:08 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 75.73%
[2025-01-19 03:58:17 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.091 (9.091)	Loss 1.7930 (1.7930)	Acc@1 65.430 (65.430)	Acc@5 86.206 (86.206)	Mem 34602MB
[2025-01-19 03:58:21 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.231)	Loss 2.2604 (1.9339)	Acc@1 54.956 (61.899)	Acc@5 78.296 (84.151)	Mem 34602MB
[2025-01-19 03:58:21 internimage_b_1k_224] (main.py 575): INFO [Epoch:56] * Acc@1 62.062 Acc@5 84.465
[2025-01-19 03:58:21 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 62.1%
[2025-01-19 03:58:21 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:58:25 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:58:25 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 62.06%
[2025-01-19 03:58:27 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][0/312]	eta 0:11:00 lr 0.003658	time 2.1172 (2.1172)	model_time 0.7537 (0.7537)	loss 2.8409 (2.8409)	grad_norm 2.9574 (2.9574/0.0000)	mem 34602MB
[2025-01-19 03:58:35 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][10/312]	eta 0:04:34 lr 0.003657	time 0.8064 (0.9104)	model_time 0.8062 (0.7860)	loss 3.4351 (3.4999)	grad_norm 1.5572 (1.3745/0.6292)	mem 34602MB
[2025-01-19 03:58:43 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][20/312]	eta 0:04:06 lr 0.003657	time 0.7177 (0.8431)	model_time 0.7172 (0.7778)	loss 3.8812 (3.5440)	grad_norm 1.1024 (1.2352/0.5026)	mem 34602MB
[2025-01-19 03:58:51 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][30/312]	eta 0:03:50 lr 0.003656	time 0.7190 (0.8161)	model_time 0.7189 (0.7718)	loss 3.0826 (3.5816)	grad_norm 0.8843 (1.3234/0.5173)	mem 34602MB
[2025-01-19 03:58:58 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][40/312]	eta 0:03:38 lr 0.003656	time 0.8061 (0.8047)	model_time 0.8056 (0.7711)	loss 3.4616 (3.5016)	grad_norm 1.2656 (1.3143/0.4679)	mem 34602MB
[2025-01-19 03:59:06 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][50/312]	eta 0:03:27 lr 0.003656	time 0.7184 (0.7913)	model_time 0.7182 (0.7643)	loss 3.9177 (3.5162)	grad_norm 1.8659 (1.3280/0.4618)	mem 34602MB
[2025-01-19 03:59:13 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][60/312]	eta 0:03:16 lr 0.003655	time 0.7360 (0.7815)	model_time 0.7359 (0.7588)	loss 3.5877 (3.5337)	grad_norm 0.5458 (1.3946/0.6047)	mem 34602MB
[2025-01-19 03:59:20 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][70/312]	eta 0:03:07 lr 0.003655	time 0.7284 (0.7739)	model_time 0.7280 (0.7543)	loss 3.4423 (3.5139)	grad_norm 0.9094 (1.3399/0.5805)	mem 34602MB
[2025-01-19 03:59:27 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][80/312]	eta 0:02:58 lr 0.003655	time 0.7164 (0.7684)	model_time 0.7160 (0.7512)	loss 2.8956 (3.5178)	grad_norm 1.0489 (1.3655/0.5843)	mem 34602MB
[2025-01-19 03:59:35 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][90/312]	eta 0:02:49 lr 0.003654	time 0.7210 (0.7631)	model_time 0.7208 (0.7478)	loss 4.3844 (3.5443)	grad_norm 1.6396 (1.3619/0.5673)	mem 34602MB
[2025-01-19 03:59:42 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][100/312]	eta 0:02:41 lr 0.003654	time 0.7540 (0.7596)	model_time 0.7535 (0.7457)	loss 3.9967 (3.5315)	grad_norm 1.1006 (1.3394/0.5528)	mem 34602MB
[2025-01-19 03:59:49 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][110/312]	eta 0:02:32 lr 0.003653	time 0.7884 (0.7569)	model_time 0.7883 (0.7442)	loss 3.0800 (3.5479)	grad_norm 2.2888 (1.3328/0.5518)	mem 34602MB
[2025-01-19 03:59:57 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][120/312]	eta 0:02:24 lr 0.003653	time 0.7287 (0.7547)	model_time 0.7282 (0.7431)	loss 4.3783 (3.5502)	grad_norm 1.0580 (1.3053/0.5411)	mem 34602MB
[2025-01-19 04:00:04 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][130/312]	eta 0:02:17 lr 0.003653	time 0.8000 (0.7559)	model_time 0.7999 (0.7451)	loss 3.7101 (3.5601)	grad_norm 1.1107 (1.2822/0.5289)	mem 34602MB
[2025-01-19 04:00:12 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][140/312]	eta 0:02:10 lr 0.003652	time 0.8153 (0.7573)	model_time 0.8146 (0.7472)	loss 4.0100 (3.5663)	grad_norm 2.0463 (1.2887/0.5330)	mem 34602MB
[2025-01-19 04:00:20 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][150/312]	eta 0:02:02 lr 0.003652	time 0.7223 (0.7571)	model_time 0.7219 (0.7478)	loss 3.1655 (3.5527)	grad_norm 0.9428 (1.2900/0.5270)	mem 34602MB
[2025-01-19 04:00:27 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][160/312]	eta 0:01:55 lr 0.003652	time 0.8041 (0.7573)	model_time 0.8039 (0.7485)	loss 3.5101 (3.5656)	grad_norm 0.8567 (1.2960/0.5255)	mem 34602MB
[2025-01-19 04:00:35 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][170/312]	eta 0:01:47 lr 0.003651	time 0.7248 (0.7564)	model_time 0.7247 (0.7481)	loss 3.7840 (3.5527)	grad_norm 1.5447 (1.3002/0.5149)	mem 34602MB
[2025-01-19 04:00:42 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][180/312]	eta 0:01:39 lr 0.003651	time 0.7181 (0.7550)	model_time 0.7176 (0.7471)	loss 3.4648 (3.5534)	grad_norm 1.4889 (1.2919/0.5076)	mem 34602MB
[2025-01-19 04:00:49 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][190/312]	eta 0:01:31 lr 0.003650	time 0.7235 (0.7533)	model_time 0.7231 (0.7458)	loss 3.9420 (3.5645)	grad_norm 2.8684 (1.3092/0.5407)	mem 34602MB
[2025-01-19 04:00:56 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][200/312]	eta 0:01:24 lr 0.003650	time 0.7540 (0.7522)	model_time 0.7538 (0.7451)	loss 4.3616 (3.5509)	grad_norm 0.9943 (1.3015/0.5337)	mem 34602MB
[2025-01-19 04:01:04 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][210/312]	eta 0:01:16 lr 0.003650	time 0.7177 (0.7509)	model_time 0.7175 (0.7441)	loss 3.1585 (3.5489)	grad_norm 0.8683 (1.3022/0.5455)	mem 34602MB
[2025-01-19 04:01:11 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][220/312]	eta 0:01:08 lr 0.003649	time 0.7201 (0.7499)	model_time 0.7200 (0.7434)	loss 3.5558 (3.5569)	grad_norm 1.3055 (1.3063/0.5513)	mem 34602MB
[2025-01-19 04:01:18 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][230/312]	eta 0:01:01 lr 0.003649	time 0.7952 (0.7493)	model_time 0.7948 (0.7431)	loss 4.4490 (3.5651)	grad_norm 1.1317 (1.3113/0.5673)	mem 34602MB
[2025-01-19 04:01:26 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][240/312]	eta 0:00:53 lr 0.003649	time 0.7176 (0.7488)	model_time 0.7174 (0.7428)	loss 3.1570 (3.5727)	grad_norm 0.8495 (1.3026/0.5612)	mem 34602MB
[2025-01-19 04:01:33 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][250/312]	eta 0:00:46 lr 0.003648	time 0.8280 (0.7492)	model_time 0.8275 (0.7434)	loss 3.7174 (3.5680)	grad_norm 1.3825 (1.3033/0.5581)	mem 34602MB
[2025-01-19 04:01:41 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][260/312]	eta 0:00:39 lr 0.003648	time 0.8318 (0.7505)	model_time 0.8316 (0.7450)	loss 3.9688 (3.5691)	grad_norm 1.6850 (1.2957/0.5529)	mem 34602MB
[2025-01-19 04:01:49 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][270/312]	eta 0:00:31 lr 0.003647	time 0.7171 (0.7505)	model_time 0.7166 (0.7451)	loss 2.3683 (3.5613)	grad_norm 1.0855 (1.3042/0.5509)	mem 34602MB
[2025-01-19 04:01:56 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][280/312]	eta 0:00:24 lr 0.003647	time 0.7974 (0.7507)	model_time 0.7972 (0.7455)	loss 2.6217 (3.5618)	grad_norm 0.9125 (1.2937/0.5455)	mem 34602MB
[2025-01-19 04:02:04 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][290/312]	eta 0:00:16 lr 0.003647	time 0.7159 (0.7506)	model_time 0.7154 (0.7456)	loss 3.0673 (3.5689)	grad_norm 1.5555 (1.2912/0.5430)	mem 34602MB
[2025-01-19 04:02:11 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][300/312]	eta 0:00:08 lr 0.003646	time 0.7133 (0.7496)	model_time 0.7132 (0.7447)	loss 3.4109 (3.5721)	grad_norm 1.8508 (1.2925/0.5418)	mem 34602MB
[2025-01-19 04:02:18 internimage_b_1k_224] (main.py 510): INFO Train: [57/300][310/312]	eta 0:00:01 lr 0.003646	time 0.7140 (0.7485)	model_time 0.7138 (0.7438)	loss 4.4700 (3.5837)	grad_norm 0.7140 (1.2878/0.5404)	mem 34602MB
[2025-01-19 04:02:19 internimage_b_1k_224] (main.py 519): INFO EPOCH 57 training takes 0:03:53
[2025-01-19 04:02:19 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_57.pth saving......
[2025-01-19 04:02:22 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_57.pth saved !!!
[2025-01-19 04:02:30 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.557 (7.557)	Loss 0.9580 (0.9580)	Acc@1 78.833 (78.833)	Acc@5 95.630 (95.630)	Mem 34602MB
[2025-01-19 04:02:33 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.955)	Loss 1.3604 (1.1464)	Acc@1 71.167 (75.706)	Acc@5 90.674 (93.266)	Mem 34602MB
[2025-01-19 04:02:33 internimage_b_1k_224] (main.py 575): INFO [Epoch:57] * Acc@1 75.748 Acc@5 93.338
[2025-01-19 04:02:33 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.7%
[2025-01-19 04:02:33 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 04:02:36 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 04:02:36 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 75.75%
[2025-01-19 04:02:43 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.295 (7.295)	Loss 1.7297 (1.7297)	Acc@1 66.577 (66.577)	Acc@5 87.036 (87.036)	Mem 34602MB
[2025-01-19 04:02:46 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.184 (0.924)	Loss 2.2016 (1.8743)	Acc@1 55.835 (63.035)	Acc@5 79.395 (84.963)	Mem 34602MB
[2025-01-19 04:02:46 internimage_b_1k_224] (main.py 575): INFO [Epoch:57] * Acc@1 63.170 Acc@5 85.241
[2025-01-19 04:02:46 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 63.2%
[2025-01-19 04:02:46 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:02:50 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:02:50 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 63.17%
[2025-01-19 04:02:53 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][0/312]	eta 0:12:10 lr 0.003646	time 2.3422 (2.3422)	model_time 0.7472 (0.7472)	loss 3.8943 (3.8943)	grad_norm 1.3126 (1.3126/0.0000)	mem 34602MB
[2025-01-19 04:03:00 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][10/312]	eta 0:04:23 lr 0.003645	time 0.7343 (0.8727)	model_time 0.7342 (0.7274)	loss 2.9305 (3.7429)	grad_norm 0.9690 (1.1215/0.2949)	mem 34602MB
[2025-01-19 04:03:07 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][20/312]	eta 0:03:54 lr 0.003645	time 0.7342 (0.8043)	model_time 0.7340 (0.7280)	loss 2.5103 (3.6569)	grad_norm 1.1100 (1.3857/0.5365)	mem 34602MB
[2025-01-19 04:03:15 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][30/312]	eta 0:03:41 lr 0.003645	time 0.7168 (0.7851)	model_time 0.7166 (0.7333)	loss 4.0899 (3.6598)	grad_norm 1.7277 (1.3171/0.4927)	mem 34602MB
[2025-01-19 04:03:22 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][40/312]	eta 0:03:30 lr 0.003644	time 0.8034 (0.7738)	model_time 0.8029 (0.7346)	loss 3.9953 (3.6122)	grad_norm 0.7347 (1.3413/0.5777)	mem 34602MB
[2025-01-19 04:03:29 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][50/312]	eta 0:03:20 lr 0.003644	time 0.7321 (0.7653)	model_time 0.7319 (0.7336)	loss 3.4608 (3.5948)	grad_norm 0.7759 (1.2907/0.5477)	mem 34602MB
[2025-01-19 04:03:37 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][60/312]	eta 0:03:12 lr 0.003644	time 0.7306 (0.7653)	model_time 0.7305 (0.7388)	loss 3.8030 (3.5914)	grad_norm 1.2253 (1.3044/0.5330)	mem 34602MB
[2025-01-19 04:03:45 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][70/312]	eta 0:03:05 lr 0.003643	time 0.8097 (0.7682)	model_time 0.8095 (0.7454)	loss 4.0320 (3.5734)	grad_norm 1.0422 (1.2905/0.5068)	mem 34602MB
[2025-01-19 04:03:52 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][80/312]	eta 0:02:57 lr 0.003643	time 0.8054 (0.7666)	model_time 0.8053 (0.7466)	loss 3.3934 (3.5996)	grad_norm 1.2096 (1.2828/0.4820)	mem 34602MB
[2025-01-19 04:04:00 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][90/312]	eta 0:02:50 lr 0.003642	time 0.8293 (0.7662)	model_time 0.8291 (0.7483)	loss 3.2721 (3.5945)	grad_norm 1.4683 (1.2806/0.4670)	mem 34602MB
[2025-01-19 04:04:08 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][100/312]	eta 0:02:42 lr 0.003642	time 0.7167 (0.7646)	model_time 0.7163 (0.7484)	loss 3.8236 (3.6082)	grad_norm 1.0564 (1.3125/0.5049)	mem 34602MB
[2025-01-19 04:04:15 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][110/312]	eta 0:02:33 lr 0.003642	time 0.7484 (0.7610)	model_time 0.7482 (0.7463)	loss 3.6001 (3.6141)	grad_norm 1.1316 (1.3166/0.5035)	mem 34602MB
[2025-01-19 04:04:22 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][120/312]	eta 0:02:25 lr 0.003641	time 0.7339 (0.7585)	model_time 0.7334 (0.7450)	loss 4.4137 (3.6270)	grad_norm 2.0777 (1.3396/0.5347)	mem 34602MB
[2025-01-19 04:04:29 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][130/312]	eta 0:02:17 lr 0.003641	time 0.7237 (0.7562)	model_time 0.7236 (0.7437)	loss 4.1040 (3.6396)	grad_norm 0.8421 (1.3379/0.5308)	mem 34602MB
[2025-01-19 04:04:37 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][140/312]	eta 0:02:09 lr 0.003641	time 0.7185 (0.7541)	model_time 0.7184 (0.7425)	loss 3.3996 (3.6395)	grad_norm 0.9232 (1.3149/0.5238)	mem 34602MB
[2025-01-19 04:04:44 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][150/312]	eta 0:02:01 lr 0.003640	time 0.7190 (0.7527)	model_time 0.7186 (0.7418)	loss 3.3131 (3.6465)	grad_norm 0.7547 (1.3176/0.5530)	mem 34602MB
[2025-01-19 04:04:51 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][160/312]	eta 0:01:54 lr 0.003640	time 0.7307 (0.7515)	model_time 0.7306 (0.7412)	loss 3.9358 (3.6595)	grad_norm 1.6587 (1.3123/0.5413)	mem 34602MB
[2025-01-19 04:04:59 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][170/312]	eta 0:01:46 lr 0.003639	time 0.7291 (0.7506)	model_time 0.7289 (0.7410)	loss 3.8078 (3.6679)	grad_norm 0.6339 (1.2913/0.5367)	mem 34602MB
[2025-01-19 04:05:06 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][180/312]	eta 0:01:39 lr 0.003639	time 0.7183 (0.7514)	model_time 0.7181 (0.7422)	loss 3.8583 (3.6762)	grad_norm 0.8294 (1.3002/0.5461)	mem 34602MB
[2025-01-19 04:05:14 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][190/312]	eta 0:01:31 lr 0.003639	time 0.9489 (0.7537)	model_time 0.9488 (0.7450)	loss 4.3400 (3.6862)	grad_norm 1.2367 (1.2986/0.5365)	mem 34602MB
[2025-01-19 04:05:22 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][200/312]	eta 0:01:24 lr 0.003638	time 0.8053 (0.7542)	model_time 0.8051 (0.7459)	loss 3.9446 (3.6721)	grad_norm 0.8466 (1.3045/0.5342)	mem 34602MB
[2025-01-19 04:05:30 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][210/312]	eta 0:01:16 lr 0.003638	time 0.8283 (0.7547)	model_time 0.8282 (0.7468)	loss 3.0063 (3.6797)	grad_norm 1.2583 (1.3078/0.5271)	mem 34602MB
[2025-01-19 04:05:37 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][220/312]	eta 0:01:09 lr 0.003637	time 0.7162 (0.7540)	model_time 0.7160 (0.7465)	loss 3.7244 (3.6761)	grad_norm 0.8502 (1.3060/0.5265)	mem 34602MB
[2025-01-19 04:05:44 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][230/312]	eta 0:01:01 lr 0.003637	time 0.7176 (0.7529)	model_time 0.7171 (0.7457)	loss 2.9617 (3.6809)	grad_norm 1.3529 (1.3019/0.5219)	mem 34602MB
[2025-01-19 04:05:52 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][240/312]	eta 0:00:54 lr 0.003637	time 0.7134 (0.7518)	model_time 0.7128 (0.7448)	loss 4.6264 (3.6830)	grad_norm 0.8023 (1.2957/0.5166)	mem 34602MB
[2025-01-19 04:05:59 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][250/312]	eta 0:00:46 lr 0.003636	time 0.7180 (0.7509)	model_time 0.7178 (0.7442)	loss 3.6885 (3.6710)	grad_norm 1.1761 (1.2948/0.5150)	mem 34602MB
[2025-01-19 04:06:06 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][260/312]	eta 0:00:38 lr 0.003636	time 0.7257 (0.7499)	model_time 0.7253 (0.7434)	loss 3.0934 (3.6639)	grad_norm 0.6819 (1.2969/0.5130)	mem 34602MB
[2025-01-19 04:06:13 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][270/312]	eta 0:00:31 lr 0.003636	time 0.7264 (0.7492)	model_time 0.7263 (0.7430)	loss 3.2245 (3.6574)	grad_norm 1.1611 (1.2871/0.5069)	mem 34602MB
[2025-01-19 04:06:21 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][280/312]	eta 0:00:23 lr 0.003635	time 0.7159 (0.7482)	model_time 0.7154 (0.7422)	loss 3.7202 (3.6556)	grad_norm 0.9548 (1.2747/0.5033)	mem 34602MB
[2025-01-19 04:06:28 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][290/312]	eta 0:00:16 lr 0.003635	time 0.7209 (0.7476)	model_time 0.7204 (0.7417)	loss 3.6286 (3.6633)	grad_norm 2.2292 (1.2885/0.5137)	mem 34602MB
[2025-01-19 04:06:35 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][300/312]	eta 0:00:08 lr 0.003634	time 0.7108 (0.7478)	model_time 0.7107 (0.7422)	loss 3.3989 (3.6605)	grad_norm 1.7459 (1.2888/0.5089)	mem 34602MB
[2025-01-19 04:06:43 internimage_b_1k_224] (main.py 510): INFO Train: [58/300][310/312]	eta 0:00:01 lr 0.003634	time 0.7972 (0.7484)	model_time 0.7971 (0.7429)	loss 3.9804 (3.6630)	grad_norm 0.7586 (1.2984/0.5156)	mem 34602MB
[2025-01-19 04:06:44 internimage_b_1k_224] (main.py 519): INFO EPOCH 58 training takes 0:03:53
[2025-01-19 04:06:44 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_58.pth saving......
[2025-01-19 04:06:47 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_58.pth saved !!!
[2025-01-19 04:07:03 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.113 (16.113)	Loss 0.9224 (0.9224)	Acc@1 79.712 (79.712)	Acc@5 94.897 (94.897)	Mem 34602MB
[2025-01-19 04:07:10 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.073)	Loss 1.3155 (1.0986)	Acc@1 70.264 (75.737)	Acc@5 90.894 (93.171)	Mem 34602MB
[2025-01-19 04:07:10 internimage_b_1k_224] (main.py 575): INFO [Epoch:58] * Acc@1 75.678 Acc@5 93.224
[2025-01-19 04:07:10 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.7%
[2025-01-19 04:07:10 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 75.75%
[2025-01-19 04:07:19 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.916 (8.916)	Loss 1.6687 (1.6687)	Acc@1 67.651 (67.651)	Acc@5 87.866 (87.866)	Mem 34602MB
[2025-01-19 04:07:24 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.221)	Loss 2.1454 (1.8173)	Acc@1 56.543 (63.991)	Acc@5 80.273 (85.667)	Mem 34602MB
[2025-01-19 04:07:24 internimage_b_1k_224] (main.py 575): INFO [Epoch:58] * Acc@1 64.115 Acc@5 85.921
[2025-01-19 04:07:24 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 64.1%
[2025-01-19 04:07:24 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:07:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:07:28 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 64.12%
[2025-01-19 04:07:30 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][0/312]	eta 0:12:29 lr 0.003634	time 2.4025 (2.4025)	model_time 0.7659 (0.7659)	loss 3.6128 (3.6128)	grad_norm 1.2221 (1.2221/0.0000)	mem 34602MB
[2025-01-19 04:07:38 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][10/312]	eta 0:04:34 lr 0.003634	time 0.8300 (0.9074)	model_time 0.8298 (0.7584)	loss 3.6839 (3.8244)	grad_norm 1.8722 (1.1842/0.4325)	mem 34602MB
[2025-01-19 04:07:46 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][20/312]	eta 0:04:06 lr 0.003633	time 0.8380 (0.8426)	model_time 0.8379 (0.7643)	loss 2.3327 (3.6446)	grad_norm 0.9671 (1.3025/0.5964)	mem 34602MB
[2025-01-19 04:07:53 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][30/312]	eta 0:03:48 lr 0.003633	time 0.7153 (0.8104)	model_time 0.7151 (0.7573)	loss 2.7485 (3.6240)	grad_norm 0.7778 (1.2110/0.5295)	mem 34602MB
[2025-01-19 04:08:00 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][40/312]	eta 0:03:34 lr 0.003632	time 0.7105 (0.7886)	model_time 0.7104 (0.7484)	loss 2.6667 (3.5631)	grad_norm 1.7736 (1.1995/0.5055)	mem 34602MB
[2025-01-19 04:08:08 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][50/312]	eta 0:03:23 lr 0.003632	time 0.7198 (0.7773)	model_time 0.7196 (0.7449)	loss 4.0375 (3.5477)	grad_norm 0.6428 (1.2683/0.5683)	mem 34602MB
[2025-01-19 04:08:15 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][60/312]	eta 0:03:13 lr 0.003632	time 0.7454 (0.7698)	model_time 0.7450 (0.7427)	loss 3.5906 (3.5066)	grad_norm 0.9638 (1.1862/0.5538)	mem 34602MB
[2025-01-19 04:08:22 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][70/312]	eta 0:03:05 lr 0.003631	time 0.7435 (0.7646)	model_time 0.7433 (0.7413)	loss 3.6640 (3.5769)	grad_norm 0.9624 (1.1843/0.5453)	mem 34602MB
[2025-01-19 04:08:29 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][80/312]	eta 0:02:56 lr 0.003631	time 0.7256 (0.7595)	model_time 0.7255 (0.7389)	loss 3.0968 (3.5701)	grad_norm 0.7969 (1.1727/0.5343)	mem 34602MB
[2025-01-19 04:08:37 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][90/312]	eta 0:02:47 lr 0.003630	time 0.7162 (0.7562)	model_time 0.7161 (0.7379)	loss 3.9703 (3.5793)	grad_norm 2.1435 (1.2534/0.5762)	mem 34602MB
[2025-01-19 04:08:44 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][100/312]	eta 0:02:39 lr 0.003630	time 0.7189 (0.7541)	model_time 0.7187 (0.7376)	loss 2.4415 (3.5947)	grad_norm 1.3060 (1.2466/0.5527)	mem 34602MB
[2025-01-19 04:08:52 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][110/312]	eta 0:02:32 lr 0.003630	time 0.7165 (0.7549)	model_time 0.7164 (0.7398)	loss 3.9995 (3.6084)	grad_norm 0.5394 (1.2268/0.5388)	mem 34602MB
[2025-01-19 04:09:00 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][120/312]	eta 0:02:25 lr 0.003629	time 0.9231 (0.7587)	model_time 0.9229 (0.7448)	loss 3.9587 (3.6100)	grad_norm 2.0011 (1.2283/0.5225)	mem 34602MB
[2025-01-19 04:09:07 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][130/312]	eta 0:02:18 lr 0.003629	time 0.7573 (0.7591)	model_time 0.7571 (0.7463)	loss 3.9208 (3.5838)	grad_norm 2.9350 (1.2596/0.5392)	mem 34602MB
[2025-01-19 04:09:15 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][140/312]	eta 0:02:10 lr 0.003629	time 0.8438 (0.7609)	model_time 0.8437 (0.7489)	loss 3.9325 (3.5680)	grad_norm 0.6532 (1.2973/0.5778)	mem 34602MB
[2025-01-19 04:09:23 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][150/312]	eta 0:02:03 lr 0.003628	time 0.7404 (0.7605)	model_time 0.7400 (0.7493)	loss 3.8938 (3.5852)	grad_norm 1.8926 (1.2905/0.5750)	mem 34602MB
[2025-01-19 04:09:30 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][160/312]	eta 0:01:55 lr 0.003628	time 0.7206 (0.7587)	model_time 0.7201 (0.7482)	loss 2.9292 (3.5645)	grad_norm 2.0078 (1.2885/0.5738)	mem 34602MB
[2025-01-19 04:09:37 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][170/312]	eta 0:01:47 lr 0.003627	time 0.7407 (0.7568)	model_time 0.7405 (0.7469)	loss 3.3293 (3.5730)	grad_norm 1.0435 (1.2876/0.5664)	mem 34602MB
[2025-01-19 04:09:45 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][180/312]	eta 0:01:39 lr 0.003627	time 0.7259 (0.7550)	model_time 0.7257 (0.7456)	loss 2.6339 (3.5719)	grad_norm 2.1148 (1.3044/0.5745)	mem 34602MB
[2025-01-19 04:09:52 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][190/312]	eta 0:01:31 lr 0.003627	time 0.7154 (0.7535)	model_time 0.7152 (0.7446)	loss 2.8691 (3.5700)	grad_norm 1.3730 (1.3067/0.5697)	mem 34602MB
[2025-01-19 04:09:59 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][200/312]	eta 0:01:24 lr 0.003626	time 0.7198 (0.7525)	model_time 0.7197 (0.7441)	loss 3.8959 (3.5760)	grad_norm 0.7426 (1.2848/0.5657)	mem 34602MB
[2025-01-19 04:10:06 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][210/312]	eta 0:01:16 lr 0.003626	time 0.7205 (0.7514)	model_time 0.7201 (0.7433)	loss 3.4673 (3.5722)	grad_norm 1.3173 (1.2761/0.5607)	mem 34602MB
[2025-01-19 04:10:14 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][220/312]	eta 0:01:09 lr 0.003625	time 0.7203 (0.7505)	model_time 0.7202 (0.7428)	loss 3.8494 (3.5532)	grad_norm 1.7192 (1.2818/0.5582)	mem 34602MB
[2025-01-19 04:10:21 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][230/312]	eta 0:01:01 lr 0.003625	time 0.8115 (0.7513)	model_time 0.8110 (0.7438)	loss 4.0223 (3.5552)	grad_norm 2.9045 (1.2931/0.5727)	mem 34602MB
[2025-01-19 04:10:29 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][240/312]	eta 0:00:54 lr 0.003625	time 0.7206 (0.7521)	model_time 0.7205 (0.7450)	loss 3.8371 (3.5663)	grad_norm 1.7616 (1.3127/0.5982)	mem 34602MB
[2025-01-19 04:10:37 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][250/312]	eta 0:00:46 lr 0.003624	time 0.7747 (0.7525)	model_time 0.7741 (0.7457)	loss 4.2578 (3.5725)	grad_norm 0.8679 (1.3068/0.5917)	mem 34602MB
[2025-01-19 04:10:45 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][260/312]	eta 0:00:39 lr 0.003624	time 0.7948 (0.7537)	model_time 0.7943 (0.7470)	loss 3.2099 (3.5745)	grad_norm 0.8166 (1.2934/0.5869)	mem 34602MB
[2025-01-19 04:10:52 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][270/312]	eta 0:00:31 lr 0.003623	time 0.7608 (0.7536)	model_time 0.7606 (0.7472)	loss 3.7809 (3.5673)	grad_norm 0.7678 (1.2908/0.5801)	mem 34602MB
[2025-01-19 04:10:59 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][280/312]	eta 0:00:24 lr 0.003623	time 0.7188 (0.7527)	model_time 0.7187 (0.7465)	loss 4.4585 (3.5754)	grad_norm 1.0315 (1.2927/0.5717)	mem 34602MB
[2025-01-19 04:11:07 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][290/312]	eta 0:00:16 lr 0.003623	time 0.7457 (0.7520)	model_time 0.7456 (0.7460)	loss 3.7262 (3.5802)	grad_norm 1.9902 (1.2984/0.5714)	mem 34602MB
[2025-01-19 04:11:14 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][300/312]	eta 0:00:09 lr 0.003622	time 0.7129 (0.7509)	model_time 0.7128 (0.7451)	loss 2.9390 (3.5737)	grad_norm 1.1032 (1.3206/0.6159)	mem 34602MB
[2025-01-19 04:11:21 internimage_b_1k_224] (main.py 510): INFO Train: [59/300][310/312]	eta 0:00:01 lr 0.003622	time 0.7174 (0.7498)	model_time 0.7173 (0.7441)	loss 3.1984 (3.5659)	grad_norm 0.6472 (1.3153/0.6141)	mem 34602MB
[2025-01-19 04:11:22 internimage_b_1k_224] (main.py 519): INFO EPOCH 59 training takes 0:03:53
[2025-01-19 04:11:22 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_59.pth saving......
[2025-01-19 04:11:25 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_59.pth saved !!!
[2025-01-19 04:11:33 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.918 (7.918)	Loss 0.9358 (0.9358)	Acc@1 79.688 (79.688)	Acc@5 95.898 (95.898)	Mem 34602MB
[2025-01-19 04:11:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (1.002)	Loss 1.3265 (1.1079)	Acc@1 71.362 (76.005)	Acc@5 90.967 (93.444)	Mem 34602MB
[2025-01-19 04:11:37 internimage_b_1k_224] (main.py 575): INFO [Epoch:59] * Acc@1 75.970 Acc@5 93.480
[2025-01-19 04:11:37 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.0%
[2025-01-19 04:11:37 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 04:11:40 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 04:11:40 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 75.97%
[2025-01-19 04:11:47 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.143 (7.143)	Loss 1.6115 (1.6115)	Acc@1 68.457 (68.457)	Acc@5 88.477 (88.477)	Mem 34602MB
[2025-01-19 04:11:50 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.923)	Loss 2.0914 (1.7635)	Acc@1 57.520 (64.901)	Acc@5 81.372 (86.355)	Mem 34602MB
[2025-01-19 04:11:50 internimage_b_1k_224] (main.py 575): INFO [Epoch:59] * Acc@1 65.021 Acc@5 86.590
[2025-01-19 04:11:50 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 65.0%
[2025-01-19 04:11:50 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:11:54 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:11:54 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 65.02%
[2025-01-19 04:11:56 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][0/312]	eta 0:11:41 lr 0.003622	time 2.2496 (2.2496)	model_time 0.7560 (0.7560)	loss 3.5726 (3.5726)	grad_norm 0.8651 (0.8651/0.0000)	mem 34602MB
[2025-01-19 04:12:04 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][10/312]	eta 0:04:19 lr 0.003621	time 0.7220 (0.8607)	model_time 0.7214 (0.7246)	loss 3.0133 (3.5575)	grad_norm 1.1726 (1.2741/0.4339)	mem 34602MB
[2025-01-19 04:12:11 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][20/312]	eta 0:03:52 lr 0.003621	time 0.7154 (0.7973)	model_time 0.7152 (0.7258)	loss 3.2781 (3.4638)	grad_norm 0.7382 (1.2210/0.4114)	mem 34602MB
[2025-01-19 04:12:18 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][30/312]	eta 0:03:39 lr 0.003621	time 0.7273 (0.7779)	model_time 0.7271 (0.7293)	loss 2.2574 (3.4500)	grad_norm 1.7494 (1.1901/0.3858)	mem 34602MB
[2025-01-19 04:12:26 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][40/312]	eta 0:03:30 lr 0.003620	time 0.7160 (0.7733)	model_time 0.7158 (0.7365)	loss 3.1379 (3.4374)	grad_norm 1.5355 (1.2684/0.4585)	mem 34602MB
[2025-01-19 04:12:34 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][50/312]	eta 0:03:22 lr 0.003620	time 0.7456 (0.7728)	model_time 0.7451 (0.7431)	loss 3.9333 (3.4815)	grad_norm 0.9611 (1.1909/0.4495)	mem 34602MB
[2025-01-19 04:12:41 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][60/312]	eta 0:03:14 lr 0.003620	time 0.7177 (0.7703)	model_time 0.7173 (0.7454)	loss 3.7467 (3.5057)	grad_norm 1.2033 (1.1978/0.4299)	mem 34602MB
[2025-01-19 04:12:49 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][70/312]	eta 0:03:06 lr 0.003619	time 0.8034 (0.7701)	model_time 0.8032 (0.7487)	loss 2.9449 (3.5127)	grad_norm 0.9345 (1.1760/0.4105)	mem 34602MB
[2025-01-19 04:12:56 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][80/312]	eta 0:02:58 lr 0.003619	time 0.7303 (0.7697)	model_time 0.7299 (0.7509)	loss 4.4103 (3.5458)	grad_norm 1.0694 (1.1761/0.3935)	mem 34602MB
[2025-01-19 04:13:04 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][90/312]	eta 0:02:49 lr 0.003618	time 0.7183 (0.7645)	model_time 0.7178 (0.7477)	loss 3.7622 (3.5582)	grad_norm 0.8173 (1.1669/0.4029)	mem 34602MB
[2025-01-19 04:13:11 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][100/312]	eta 0:02:41 lr 0.003618	time 0.7242 (0.7610)	model_time 0.7240 (0.7458)	loss 3.1102 (3.5419)	grad_norm 1.0058 (1.1951/0.4376)	mem 34602MB
[2025-01-19 04:13:18 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][110/312]	eta 0:02:33 lr 0.003618	time 0.7396 (0.7577)	model_time 0.7395 (0.7439)	loss 2.7206 (3.5358)	grad_norm 1.8247 (1.2104/0.4623)	mem 34602MB
[2025-01-19 04:13:26 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][120/312]	eta 0:02:24 lr 0.003617	time 0.7222 (0.7552)	model_time 0.7220 (0.7425)	loss 2.9017 (3.5370)	grad_norm 1.4339 (1.2692/0.5638)	mem 34602MB
[2025-01-19 04:13:33 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][130/312]	eta 0:02:17 lr 0.003617	time 0.7219 (0.7530)	model_time 0.7214 (0.7412)	loss 3.4531 (3.5137)	grad_norm 0.5775 (1.2600/0.5550)	mem 34602MB
[2025-01-19 04:13:40 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][140/312]	eta 0:02:09 lr 0.003616	time 0.7234 (0.7511)	model_time 0.7232 (0.7401)	loss 3.6626 (3.5131)	grad_norm 1.3870 (1.2981/0.5950)	mem 34602MB
[2025-01-19 04:13:47 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][150/312]	eta 0:02:01 lr 0.003616	time 0.7225 (0.7502)	model_time 0.7221 (0.7399)	loss 3.6883 (3.5245)	grad_norm 0.7002 (1.2852/0.5823)	mem 34602MB
[2025-01-19 04:13:55 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][160/312]	eta 0:01:54 lr 0.003616	time 0.8031 (0.7511)	model_time 0.8030 (0.7415)	loss 2.5059 (3.5233)	grad_norm 1.4074 (1.2797/0.5670)	mem 34602MB
[2025-01-19 04:14:03 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][170/312]	eta 0:01:47 lr 0.003615	time 0.7249 (0.7539)	model_time 0.7247 (0.7448)	loss 3.7099 (3.5488)	grad_norm 1.4746 (1.2646/0.5562)	mem 34602MB
[2025-01-19 04:14:11 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][180/312]	eta 0:01:39 lr 0.003615	time 0.7236 (0.7543)	model_time 0.7231 (0.7456)	loss 4.2743 (3.5602)	grad_norm 0.9363 (1.2583/0.5469)	mem 34602MB
[2025-01-19 04:14:18 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][190/312]	eta 0:01:32 lr 0.003614	time 0.8198 (0.7551)	model_time 0.8196 (0.7469)	loss 3.5068 (3.5513)	grad_norm 0.5941 (1.2541/0.5380)	mem 34602MB
[2025-01-19 04:14:26 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][200/312]	eta 0:01:24 lr 0.003614	time 0.7201 (0.7548)	model_time 0.7197 (0.7470)	loss 3.5611 (3.5485)	grad_norm 0.9275 (1.2420/0.5295)	mem 34602MB
[2025-01-19 04:14:33 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][210/312]	eta 0:01:16 lr 0.003614	time 0.7167 (0.7534)	model_time 0.7166 (0.7460)	loss 2.9876 (3.5594)	grad_norm 0.8215 (1.2318/0.5221)	mem 34602MB
[2025-01-19 04:14:40 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][220/312]	eta 0:01:09 lr 0.003613	time 0.7252 (0.7524)	model_time 0.7248 (0.7453)	loss 3.2027 (3.5527)	grad_norm 1.3617 (1.2550/0.5580)	mem 34602MB
[2025-01-19 04:14:48 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][230/312]	eta 0:01:01 lr 0.003613	time 0.7447 (0.7513)	model_time 0.7445 (0.7445)	loss 3.7353 (3.5579)	grad_norm 1.0349 (1.2546/0.5541)	mem 34602MB
[2025-01-19 04:14:55 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][240/312]	eta 0:00:54 lr 0.003612	time 0.7267 (0.7504)	model_time 0.7262 (0.7438)	loss 3.3193 (3.5450)	grad_norm 0.6236 (1.2425/0.5485)	mem 34602MB
[2025-01-19 04:15:02 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][250/312]	eta 0:00:46 lr 0.003612	time 0.7244 (0.7496)	model_time 0.7242 (0.7433)	loss 3.6449 (3.5494)	grad_norm 2.7614 (1.2592/0.5577)	mem 34602MB
[2025-01-19 04:15:10 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][260/312]	eta 0:00:38 lr 0.003612	time 0.7193 (0.7486)	model_time 0.7188 (0.7425)	loss 3.0615 (3.5561)	grad_norm 0.7688 (1.2608/0.5551)	mem 34602MB
[2025-01-19 04:15:17 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][270/312]	eta 0:00:31 lr 0.003611	time 0.7211 (0.7481)	model_time 0.7206 (0.7421)	loss 3.9151 (3.5499)	grad_norm 0.6895 (1.2487/0.5497)	mem 34602MB
[2025-01-19 04:15:25 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][280/312]	eta 0:00:23 lr 0.003611	time 0.8116 (0.7487)	model_time 0.8114 (0.7430)	loss 3.7519 (3.5440)	grad_norm 1.1680 (1.2366/0.5457)	mem 34602MB
[2025-01-19 04:15:32 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][290/312]	eta 0:00:16 lr 0.003610	time 0.7971 (0.7497)	model_time 0.7966 (0.7441)	loss 3.6750 (3.5495)	grad_norm 1.1677 (1.2283/0.5398)	mem 34602MB
[2025-01-19 04:15:40 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][300/312]	eta 0:00:09 lr 0.003610	time 0.7149 (0.7503)	model_time 0.7148 (0.7448)	loss 3.6573 (3.5501)	grad_norm 1.9688 (1.2496/0.5444)	mem 34602MB
[2025-01-19 04:15:47 internimage_b_1k_224] (main.py 510): INFO Train: [60/300][310/312]	eta 0:00:01 lr 0.003610	time 0.7137 (0.7498)	model_time 0.7136 (0.7446)	loss 3.3555 (3.5475)	grad_norm 1.0242 (1.2526/0.5421)	mem 34602MB
[2025-01-19 04:15:48 internimage_b_1k_224] (main.py 519): INFO EPOCH 60 training takes 0:03:54
[2025-01-19 04:15:48 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_60.pth saving......
[2025-01-19 04:15:51 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_60.pth saved !!!
[2025-01-19 04:15:59 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.086 (7.086)	Loss 0.9369 (0.9369)	Acc@1 79.688 (79.688)	Acc@5 95.630 (95.630)	Mem 34602MB
[2025-01-19 04:16:02 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.897)	Loss 1.3403 (1.1249)	Acc@1 71.118 (75.748)	Acc@5 90.991 (93.375)	Mem 34602MB
[2025-01-19 04:16:02 internimage_b_1k_224] (main.py 575): INFO [Epoch:60] * Acc@1 75.808 Acc@5 93.480
[2025-01-19 04:16:02 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.8%
[2025-01-19 04:16:02 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 75.97%
[2025-01-19 04:16:11 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.224 (9.224)	Loss 1.5593 (1.5593)	Acc@1 69.360 (69.360)	Acc@5 89.038 (89.038)	Mem 34602MB
[2025-01-19 04:16:15 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.245)	Loss 2.0414 (1.7141)	Acc@1 58.252 (65.725)	Acc@5 81.909 (86.961)	Mem 34602MB
[2025-01-19 04:16:16 internimage_b_1k_224] (main.py 575): INFO [Epoch:60] * Acc@1 65.859 Acc@5 87.182
[2025-01-19 04:16:16 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 65.9%
[2025-01-19 04:16:16 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:16:20 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:16:20 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 65.86%
[2025-01-19 04:16:22 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][0/312]	eta 0:11:24 lr 0.003610	time 2.1930 (2.1930)	model_time 0.7450 (0.7450)	loss 3.8469 (3.8469)	grad_norm 1.5364 (1.5364/0.0000)	mem 34602MB
[2025-01-19 04:16:29 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][10/312]	eta 0:04:30 lr 0.003609	time 0.7368 (0.8953)	model_time 0.7364 (0.7634)	loss 2.4218 (3.2598)	grad_norm 0.8549 (1.2791/0.3687)	mem 34602MB
[2025-01-19 04:16:37 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][20/312]	eta 0:03:58 lr 0.003609	time 0.7280 (0.8155)	model_time 0.7275 (0.7462)	loss 3.8727 (3.4057)	grad_norm 1.2989 (1.1264/0.3350)	mem 34602MB
[2025-01-19 04:16:44 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][30/312]	eta 0:03:43 lr 0.003608	time 0.7236 (0.7923)	model_time 0.7235 (0.7452)	loss 3.3820 (3.4793)	grad_norm 1.6632 (1.3055/0.5108)	mem 34602MB
[2025-01-19 04:16:51 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][40/312]	eta 0:03:31 lr 0.003608	time 0.7551 (0.7783)	model_time 0.7549 (0.7426)	loss 3.3785 (3.5561)	grad_norm 0.9369 (1.3471/0.5059)	mem 34602MB
[2025-01-19 04:16:59 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][50/312]	eta 0:03:21 lr 0.003608	time 0.7167 (0.7684)	model_time 0.7166 (0.7397)	loss 3.8306 (3.5921)	grad_norm 1.0065 (1.2990/0.4808)	mem 34602MB
[2025-01-19 04:17:06 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][60/312]	eta 0:03:12 lr 0.003607	time 0.7283 (0.7624)	model_time 0.7278 (0.7383)	loss 4.4871 (3.5487)	grad_norm 1.2628 (1.2559/0.4574)	mem 34602MB
[2025-01-19 04:17:13 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][70/312]	eta 0:03:03 lr 0.003607	time 0.7157 (0.7577)	model_time 0.7155 (0.7370)	loss 3.7986 (3.5929)	grad_norm 0.7979 (1.2139/0.4440)	mem 34602MB
[2025-01-19 04:17:21 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][80/312]	eta 0:02:55 lr 0.003606	time 0.7279 (0.7551)	model_time 0.7277 (0.7368)	loss 2.7067 (3.6295)	grad_norm 1.4165 (1.2039/0.4573)	mem 34602MB
[2025-01-19 04:17:28 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][90/312]	eta 0:02:47 lr 0.003606	time 0.7157 (0.7565)	model_time 0.7153 (0.7403)	loss 3.2637 (3.6094)	grad_norm 1.5831 (1.2576/0.5314)	mem 34602MB
[2025-01-19 04:17:36 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][100/312]	eta 0:02:41 lr 0.003606	time 0.8088 (0.7596)	model_time 0.8086 (0.7449)	loss 2.4095 (3.5627)	grad_norm 1.0930 (1.2565/0.5109)	mem 34602MB
[2025-01-19 04:17:44 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][110/312]	eta 0:02:33 lr 0.003605	time 0.8049 (0.7601)	model_time 0.8045 (0.7467)	loss 3.8993 (3.5562)	grad_norm 1.1003 (1.2484/0.5107)	mem 34602MB
[2025-01-19 04:17:51 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][120/312]	eta 0:02:25 lr 0.003605	time 0.8014 (0.7593)	model_time 0.8009 (0.7470)	loss 3.5530 (3.5607)	grad_norm 0.9704 (1.2389/0.5006)	mem 34602MB
[2025-01-19 04:17:59 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][130/312]	eta 0:02:18 lr 0.003604	time 0.7184 (0.7604)	model_time 0.7180 (0.7490)	loss 3.9324 (3.5508)	grad_norm 1.4388 (1.2542/0.4980)	mem 34602MB
[2025-01-19 04:18:06 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][140/312]	eta 0:02:10 lr 0.003604	time 0.7238 (0.7583)	model_time 0.7234 (0.7476)	loss 3.2585 (3.5719)	grad_norm 0.6317 (1.2396/0.4906)	mem 34602MB
[2025-01-19 04:18:14 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][150/312]	eta 0:02:02 lr 0.003604	time 0.7221 (0.7572)	model_time 0.7219 (0.7472)	loss 3.5861 (3.5754)	grad_norm 1.6116 (1.2262/0.4834)	mem 34602MB
[2025-01-19 04:18:21 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][160/312]	eta 0:01:54 lr 0.003603	time 0.7263 (0.7554)	model_time 0.7262 (0.7461)	loss 3.6764 (3.5783)	grad_norm 1.7032 (1.2368/0.4850)	mem 34602MB
[2025-01-19 04:18:28 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][170/312]	eta 0:01:47 lr 0.003603	time 0.7155 (0.7537)	model_time 0.7151 (0.7448)	loss 3.7847 (3.5785)	grad_norm 0.7567 (1.2218/0.4767)	mem 34602MB
[2025-01-19 04:18:36 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][180/312]	eta 0:01:39 lr 0.003602	time 0.7200 (0.7521)	model_time 0.7198 (0.7438)	loss 3.4944 (3.5807)	grad_norm 0.9517 (1.2105/0.4684)	mem 34602MB
[2025-01-19 04:18:43 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][190/312]	eta 0:01:31 lr 0.003602	time 0.7148 (0.7512)	model_time 0.7147 (0.7432)	loss 3.8435 (3.5994)	grad_norm 0.9370 (1.2155/0.4629)	mem 34602MB
[2025-01-19 04:18:50 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][200/312]	eta 0:01:24 lr 0.003602	time 0.7164 (0.7503)	model_time 0.7162 (0.7427)	loss 4.5439 (3.6126)	grad_norm 1.4655 (1.2178/0.4623)	mem 34602MB
[2025-01-19 04:18:58 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][210/312]	eta 0:01:16 lr 0.003601	time 0.7277 (0.7525)	model_time 0.7275 (0.7452)	loss 3.0572 (3.6090)	grad_norm 1.2076 (1.2356/0.4798)	mem 34602MB
[2025-01-19 04:19:06 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][220/312]	eta 0:01:09 lr 0.003601	time 0.7173 (0.7535)	model_time 0.7172 (0.7465)	loss 2.8823 (3.5965)	grad_norm 1.6854 (1.2532/0.4856)	mem 34602MB
[2025-01-19 04:19:14 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][230/312]	eta 0:01:01 lr 0.003600	time 0.8055 (0.7549)	model_time 0.8051 (0.7483)	loss 3.8254 (3.5913)	grad_norm 1.0479 (1.2465/0.4803)	mem 34602MB
[2025-01-19 04:19:22 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][240/312]	eta 0:00:54 lr 0.003600	time 0.8140 (0.7552)	model_time 0.8138 (0.7489)	loss 3.3522 (3.5840)	grad_norm 2.2430 (1.2484/0.4796)	mem 34602MB
[2025-01-19 04:19:29 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][250/312]	eta 0:00:46 lr 0.003600	time 0.7239 (0.7553)	model_time 0.7238 (0.7492)	loss 2.7219 (3.5738)	grad_norm 0.8309 (1.2391/0.4744)	mem 34602MB
[2025-01-19 04:19:36 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][260/312]	eta 0:00:39 lr 0.003599	time 0.7560 (0.7544)	model_time 0.7558 (0.7485)	loss 3.7953 (3.5777)	grad_norm 1.5085 (1.2445/0.4788)	mem 34602MB
[2025-01-19 04:19:44 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][270/312]	eta 0:00:31 lr 0.003599	time 0.7166 (0.7533)	model_time 0.7164 (0.7476)	loss 3.8919 (3.5778)	grad_norm 1.5251 (1.2608/0.4847)	mem 34602MB
[2025-01-19 04:19:51 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][280/312]	eta 0:00:24 lr 0.003598	time 0.7166 (0.7527)	model_time 0.7162 (0.7471)	loss 4.6610 (3.5773)	grad_norm 1.1877 (1.2675/0.4873)	mem 34602MB
[2025-01-19 04:19:58 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][290/312]	eta 0:00:16 lr 0.003598	time 0.7243 (0.7517)	model_time 0.7239 (0.7464)	loss 3.7518 (3.5756)	grad_norm 1.4041 (1.2625/0.4835)	mem 34602MB
[2025-01-19 04:20:06 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][300/312]	eta 0:00:09 lr 0.003598	time 0.7141 (0.7508)	model_time 0.7140 (0.7456)	loss 3.3697 (3.5700)	grad_norm 1.7130 (1.2590/0.4817)	mem 34602MB
[2025-01-19 04:20:13 internimage_b_1k_224] (main.py 510): INFO Train: [61/300][310/312]	eta 0:00:01 lr 0.003597	time 0.7152 (0.7497)	model_time 0.7151 (0.7447)	loss 4.0786 (3.5780)	grad_norm 1.0417 (1.2654/0.4821)	mem 34602MB
[2025-01-19 04:20:13 internimage_b_1k_224] (main.py 519): INFO EPOCH 61 training takes 0:03:53
[2025-01-19 04:20:13 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_61.pth saving......
[2025-01-19 04:20:16 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_61.pth saved !!!
[2025-01-19 04:20:24 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.578 (7.578)	Loss 0.9059 (0.9059)	Acc@1 80.737 (80.737)	Acc@5 95.825 (95.825)	Mem 34602MB
[2025-01-19 04:20:27 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.966)	Loss 1.2873 (1.1111)	Acc@1 71.167 (76.008)	Acc@5 91.138 (93.346)	Mem 34602MB
[2025-01-19 04:20:27 internimage_b_1k_224] (main.py 575): INFO [Epoch:61] * Acc@1 76.068 Acc@5 93.426
[2025-01-19 04:20:27 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.1%
[2025-01-19 04:20:27 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 04:20:31 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 04:20:31 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 76.07%
[2025-01-19 04:20:38 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.607 (7.607)	Loss 1.5099 (1.5099)	Acc@1 70.166 (70.166)	Acc@5 89.575 (89.575)	Mem 34602MB
[2025-01-19 04:20:41 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.958)	Loss 1.9936 (1.6674)	Acc@1 59.229 (66.513)	Acc@5 82.446 (87.445)	Mem 34602MB
[2025-01-19 04:20:41 internimage_b_1k_224] (main.py 575): INFO [Epoch:61] * Acc@1 66.621 Acc@5 87.668
[2025-01-19 04:20:41 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 66.6%
[2025-01-19 04:20:41 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:20:45 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:20:45 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 66.62%
[2025-01-19 04:20:48 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][0/312]	eta 0:10:44 lr 0.003597	time 2.0670 (2.0670)	model_time 0.7550 (0.7550)	loss 4.0693 (4.0693)	grad_norm 1.0600 (1.0600/0.0000)	mem 34602MB
[2025-01-19 04:20:55 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][10/312]	eta 0:04:18 lr 0.003597	time 0.7264 (0.8571)	model_time 0.7260 (0.7375)	loss 4.3174 (3.7258)	grad_norm 0.8701 (1.0459/0.2391)	mem 34602MB
[2025-01-19 04:21:03 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][20/312]	eta 0:03:58 lr 0.003596	time 0.8056 (0.8154)	model_time 0.8052 (0.7525)	loss 3.5456 (3.6953)	grad_norm 1.0025 (1.3161/0.7603)	mem 34602MB
[2025-01-19 04:21:10 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][30/312]	eta 0:03:45 lr 0.003596	time 0.8073 (0.8012)	model_time 0.8071 (0.7585)	loss 3.7424 (3.5563)	grad_norm 0.6997 (1.2976/0.6700)	mem 34602MB
[2025-01-19 04:21:18 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][40/312]	eta 0:03:35 lr 0.003596	time 0.8266 (0.7931)	model_time 0.8261 (0.7608)	loss 3.9510 (3.5260)	grad_norm 1.4068 (1.3197/0.6117)	mem 34602MB
[2025-01-19 04:21:26 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][50/312]	eta 0:03:26 lr 0.003595	time 0.8114 (0.7872)	model_time 0.8109 (0.7611)	loss 2.4496 (3.4445)	grad_norm 1.5957 (1.2727/0.5684)	mem 34602MB
[2025-01-19 04:21:33 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][60/312]	eta 0:03:17 lr 0.003595	time 0.7202 (0.7837)	model_time 0.7197 (0.7618)	loss 4.1583 (3.4888)	grad_norm 0.9276 (1.2685/0.5427)	mem 34602MB
[2025-01-19 04:21:41 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][70/312]	eta 0:03:07 lr 0.003594	time 0.7327 (0.7760)	model_time 0.7322 (0.7571)	loss 3.2402 (3.5169)	grad_norm 1.2540 (1.3583/0.6117)	mem 34602MB
[2025-01-19 04:21:48 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][80/312]	eta 0:02:58 lr 0.003594	time 0.7164 (0.7713)	model_time 0.7163 (0.7547)	loss 4.5116 (3.5809)	grad_norm 1.0979 (1.3640/0.6243)	mem 34602MB
[2025-01-19 04:21:55 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][90/312]	eta 0:02:50 lr 0.003594	time 0.7224 (0.7667)	model_time 0.7223 (0.7519)	loss 3.5027 (3.5731)	grad_norm 0.6162 (1.3264/0.6146)	mem 34602MB
[2025-01-19 04:22:03 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][100/312]	eta 0:02:41 lr 0.003593	time 0.7376 (0.7632)	model_time 0.7372 (0.7498)	loss 2.5660 (3.5934)	grad_norm 0.8978 (1.2796/0.6043)	mem 34602MB
[2025-01-19 04:22:10 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][110/312]	eta 0:02:33 lr 0.003593	time 0.7193 (0.7598)	model_time 0.7192 (0.7476)	loss 4.1089 (3.6076)	grad_norm 0.8030 (1.2507/0.5850)	mem 34602MB
[2025-01-19 04:22:17 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][120/312]	eta 0:02:25 lr 0.003592	time 0.7398 (0.7570)	model_time 0.7393 (0.7458)	loss 2.6978 (3.6076)	grad_norm 3.4906 (1.2593/0.6022)	mem 34602MB
[2025-01-19 04:22:24 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][130/312]	eta 0:02:17 lr 0.003592	time 0.7299 (0.7552)	model_time 0.7295 (0.7448)	loss 3.1120 (3.6058)	grad_norm 2.2882 (1.3033/0.6653)	mem 34602MB
[2025-01-19 04:22:32 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][140/312]	eta 0:02:10 lr 0.003591	time 0.8301 (0.7562)	model_time 0.8297 (0.7465)	loss 3.3721 (3.6206)	grad_norm 1.7790 (1.3049/0.6614)	mem 34602MB
[2025-01-19 04:22:40 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][150/312]	eta 0:02:02 lr 0.003591	time 0.8095 (0.7568)	model_time 0.8091 (0.7477)	loss 4.1365 (3.6200)	grad_norm 0.9027 (1.3048/0.6500)	mem 34602MB
[2025-01-19 04:22:47 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][160/312]	eta 0:01:55 lr 0.003591	time 0.7189 (0.7569)	model_time 0.7185 (0.7484)	loss 2.3311 (3.6106)	grad_norm 1.0147 (1.2811/0.6376)	mem 34602MB
[2025-01-19 04:22:55 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][170/312]	eta 0:01:47 lr 0.003590	time 0.7183 (0.7568)	model_time 0.7179 (0.7487)	loss 4.1110 (3.5977)	grad_norm 1.5079 (1.2953/0.6288)	mem 34602MB
[2025-01-19 04:23:03 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][180/312]	eta 0:01:39 lr 0.003590	time 0.7407 (0.7574)	model_time 0.7402 (0.7498)	loss 3.9834 (3.6008)	grad_norm 0.9594 (1.2822/0.6196)	mem 34602MB
[2025-01-19 04:23:10 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][190/312]	eta 0:01:32 lr 0.003589	time 0.7613 (0.7560)	model_time 0.7609 (0.7487)	loss 4.2797 (3.6048)	grad_norm 1.8495 (1.2935/0.6151)	mem 34602MB
[2025-01-19 04:23:17 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][200/312]	eta 0:01:24 lr 0.003589	time 0.7151 (0.7548)	model_time 0.7150 (0.7479)	loss 2.9345 (3.6081)	grad_norm 1.6651 (1.2803/0.6073)	mem 34602MB
[2025-01-19 04:23:24 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][210/312]	eta 0:01:16 lr 0.003589	time 0.7198 (0.7535)	model_time 0.7196 (0.7469)	loss 3.7911 (3.6032)	grad_norm 1.6450 (1.2862/0.6131)	mem 34602MB
[2025-01-19 04:23:32 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][220/312]	eta 0:01:09 lr 0.003588	time 0.7106 (0.7523)	model_time 0.7102 (0.7460)	loss 4.2719 (3.6060)	grad_norm 1.5538 (1.2841/0.6056)	mem 34602MB
[2025-01-19 04:23:39 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][230/312]	eta 0:01:01 lr 0.003588	time 0.7231 (0.7513)	model_time 0.7227 (0.7452)	loss 3.7130 (3.6140)	grad_norm 0.6488 (1.2735/0.5964)	mem 34602MB
[2025-01-19 04:23:46 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][240/312]	eta 0:00:54 lr 0.003587	time 0.7156 (0.7501)	model_time 0.7155 (0.7442)	loss 2.5788 (3.6085)	grad_norm 1.0935 (1.2663/0.5914)	mem 34602MB
[2025-01-19 04:23:54 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][250/312]	eta 0:00:46 lr 0.003587	time 0.7152 (0.7493)	model_time 0.7150 (0.7436)	loss 3.6406 (3.6106)	grad_norm 1.0865 (1.2546/0.5841)	mem 34602MB
[2025-01-19 04:24:01 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][260/312]	eta 0:00:39 lr 0.003587	time 1.0002 (0.7502)	model_time 1.0000 (0.7447)	loss 3.9452 (3.6109)	grad_norm 0.6464 (1.2455/0.5778)	mem 34602MB
[2025-01-19 04:24:09 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][270/312]	eta 0:00:31 lr 0.003586	time 0.8062 (0.7512)	model_time 0.8057 (0.7459)	loss 3.4996 (3.6112)	grad_norm 1.6160 (1.2529/0.5744)	mem 34602MB
[2025-01-19 04:24:17 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][280/312]	eta 0:00:24 lr 0.003586	time 0.7130 (0.7514)	model_time 0.7129 (0.7463)	loss 4.4579 (3.6121)	grad_norm 1.5453 (1.2552/0.5679)	mem 34602MB
[2025-01-19 04:24:24 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][290/312]	eta 0:00:16 lr 0.003585	time 0.7146 (0.7518)	model_time 0.7144 (0.7469)	loss 3.8634 (3.6123)	grad_norm 1.5636 (1.2588/0.5688)	mem 34602MB
[2025-01-19 04:24:32 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][300/312]	eta 0:00:09 lr 0.003585	time 0.7131 (0.7527)	model_time 0.7130 (0.7479)	loss 3.2083 (3.6056)	grad_norm 1.9805 (1.2624/0.5646)	mem 34602MB
[2025-01-19 04:24:39 internimage_b_1k_224] (main.py 510): INFO Train: [62/300][310/312]	eta 0:00:01 lr 0.003585	time 0.7141 (0.7516)	model_time 0.7140 (0.7469)	loss 4.2827 (3.5985)	grad_norm 0.8813 (1.2771/0.5699)	mem 34602MB
[2025-01-19 04:24:40 internimage_b_1k_224] (main.py 519): INFO EPOCH 62 training takes 0:03:54
[2025-01-19 04:24:40 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_62.pth saving......
[2025-01-19 04:24:43 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_62.pth saved !!!
[2025-01-19 04:24:51 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.282 (7.282)	Loss 0.9278 (0.9278)	Acc@1 80.688 (80.688)	Acc@5 95.386 (95.386)	Mem 34602MB
[2025-01-19 04:24:54 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.931)	Loss 1.3523 (1.1332)	Acc@1 71.240 (76.238)	Acc@5 90.649 (93.457)	Mem 34602MB
[2025-01-19 04:24:54 internimage_b_1k_224] (main.py 575): INFO [Epoch:62] * Acc@1 76.228 Acc@5 93.500
[2025-01-19 04:24:54 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.2%
[2025-01-19 04:24:54 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 04:24:57 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 04:24:57 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 76.23%
[2025-01-19 04:25:05 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.497 (7.497)	Loss 1.4644 (1.4644)	Acc@1 70.996 (70.996)	Acc@5 89.868 (89.868)	Mem 34602MB
[2025-01-19 04:25:08 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.185 (0.981)	Loss 1.9481 (1.6233)	Acc@1 59.863 (67.247)	Acc@5 83.179 (87.942)	Mem 34602MB
[2025-01-19 04:25:08 internimage_b_1k_224] (main.py 575): INFO [Epoch:62] * Acc@1 67.338 Acc@5 88.136
[2025-01-19 04:25:08 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 67.3%
[2025-01-19 04:25:08 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:25:12 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:25:12 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 67.34%
[2025-01-19 04:25:14 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][0/312]	eta 0:10:33 lr 0.003585	time 2.0294 (2.0294)	model_time 0.7520 (0.7520)	loss 2.8664 (2.8664)	grad_norm 1.4084 (1.4084/0.0000)	mem 34602MB
[2025-01-19 04:25:21 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][10/312]	eta 0:04:18 lr 0.003584	time 0.7194 (0.8545)	model_time 0.7193 (0.7380)	loss 4.1099 (3.4781)	grad_norm 0.9113 (1.0417/0.2502)	mem 34602MB
[2025-01-19 04:25:29 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][20/312]	eta 0:03:52 lr 0.003584	time 0.7331 (0.7947)	model_time 0.7327 (0.7334)	loss 2.6494 (3.4882)	grad_norm 0.8173 (1.0255/0.2254)	mem 34602MB
[2025-01-19 04:25:36 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][30/312]	eta 0:03:37 lr 0.003583	time 0.7137 (0.7728)	model_time 0.7132 (0.7313)	loss 2.4036 (3.5074)	grad_norm 1.0497 (1.0810/0.2526)	mem 34602MB
[2025-01-19 04:25:43 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][40/312]	eta 0:03:27 lr 0.003583	time 0.7234 (0.7641)	model_time 0.7230 (0.7326)	loss 3.7731 (3.5313)	grad_norm 1.1406 (1.1639/0.3465)	mem 34602MB
[2025-01-19 04:25:51 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][50/312]	eta 0:03:18 lr 0.003582	time 0.7198 (0.7562)	model_time 0.7194 (0.7308)	loss 3.8314 (3.5692)	grad_norm 0.6119 (1.1505/0.3370)	mem 34602MB
[2025-01-19 04:25:58 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][60/312]	eta 0:03:09 lr 0.003582	time 0.7269 (0.7534)	model_time 0.7265 (0.7321)	loss 3.6682 (3.5177)	grad_norm 1.0887 (1.1503/0.3359)	mem 34602MB
[2025-01-19 04:26:06 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][70/312]	eta 0:03:02 lr 0.003582	time 0.7980 (0.7545)	model_time 0.7976 (0.7361)	loss 3.5610 (3.5673)	grad_norm 1.3761 (1.1906/0.3449)	mem 34602MB
[2025-01-19 04:26:13 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][80/312]	eta 0:02:55 lr 0.003581	time 0.7213 (0.7574)	model_time 0.7211 (0.7413)	loss 3.2873 (3.5789)	grad_norm 1.1260 (1.2168/0.3771)	mem 34602MB
[2025-01-19 04:26:21 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][90/312]	eta 0:02:47 lr 0.003581	time 0.7212 (0.7561)	model_time 0.7208 (0.7417)	loss 3.6386 (3.5803)	grad_norm 1.7262 (1.2445/0.3838)	mem 34602MB
[2025-01-19 04:26:28 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][100/312]	eta 0:02:40 lr 0.003580	time 0.8030 (0.7569)	model_time 0.8028 (0.7439)	loss 2.5853 (3.5629)	grad_norm 0.5959 (1.2375/0.3849)	mem 34602MB
[2025-01-19 04:26:36 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][110/312]	eta 0:02:33 lr 0.003580	time 0.7397 (0.7587)	model_time 0.7391 (0.7468)	loss 3.7779 (3.5867)	grad_norm 0.7936 (1.2301/0.3783)	mem 34602MB
[2025-01-19 04:26:44 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][120/312]	eta 0:02:25 lr 0.003580	time 0.7189 (0.7560)	model_time 0.7187 (0.7451)	loss 3.4370 (3.5688)	grad_norm 0.7115 (1.2289/0.3733)	mem 34602MB
[2025-01-19 04:26:51 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][130/312]	eta 0:02:17 lr 0.003579	time 0.7290 (0.7545)	model_time 0.7285 (0.7444)	loss 4.5227 (3.5635)	grad_norm 1.7271 (1.2328/0.3782)	mem 34602MB
[2025-01-19 04:26:58 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][140/312]	eta 0:02:09 lr 0.003579	time 0.7136 (0.7523)	model_time 0.7134 (0.7428)	loss 2.4610 (3.5426)	grad_norm 0.8968 (1.2347/0.3790)	mem 34602MB
[2025-01-19 04:27:05 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][150/312]	eta 0:02:01 lr 0.003578	time 0.7291 (0.7503)	model_time 0.7289 (0.7415)	loss 2.7839 (3.5388)	grad_norm 0.5831 (1.2505/0.4033)	mem 34602MB
[2025-01-19 04:27:13 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][160/312]	eta 0:01:53 lr 0.003578	time 0.7437 (0.7490)	model_time 0.7433 (0.7407)	loss 3.9995 (3.5267)	grad_norm 1.0388 (1.2481/0.4012)	mem 34602MB
[2025-01-19 04:27:20 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][170/312]	eta 0:01:46 lr 0.003578	time 0.7243 (0.7479)	model_time 0.7242 (0.7401)	loss 3.8227 (3.5190)	grad_norm 0.8657 (1.2558/0.4166)	mem 34602MB
[2025-01-19 04:27:27 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][180/312]	eta 0:01:38 lr 0.003577	time 0.7441 (0.7473)	model_time 0.7437 (0.7398)	loss 3.9497 (3.5279)	grad_norm 2.4406 (1.2692/0.4375)	mem 34602MB
[2025-01-19 04:27:35 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][190/312]	eta 0:01:31 lr 0.003577	time 0.8049 (0.7474)	model_time 0.8044 (0.7403)	loss 2.4872 (3.5264)	grad_norm 1.2502 (1.2637/0.4395)	mem 34602MB
[2025-01-19 04:27:42 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][200/312]	eta 0:01:23 lr 0.003576	time 0.8060 (0.7486)	model_time 0.8058 (0.7418)	loss 3.8635 (3.5204)	grad_norm 0.9130 (1.2712/0.4441)	mem 34602MB
[2025-01-19 04:27:50 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][210/312]	eta 0:01:16 lr 0.003576	time 0.7247 (0.7484)	model_time 0.7242 (0.7419)	loss 3.2710 (3.5296)	grad_norm 0.8875 (1.2681/0.4391)	mem 34602MB
[2025-01-19 04:27:58 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][220/312]	eta 0:01:08 lr 0.003576	time 0.8004 (0.7493)	model_time 0.8000 (0.7431)	loss 2.7801 (3.5258)	grad_norm 1.2293 (1.2596/0.4351)	mem 34602MB
[2025-01-19 04:28:05 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][230/312]	eta 0:01:01 lr 0.003575	time 0.7201 (0.7491)	model_time 0.7196 (0.7431)	loss 3.7749 (3.5387)	grad_norm 1.8026 (1.2725/0.4436)	mem 34602MB
[2025-01-19 04:28:12 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][240/312]	eta 0:00:53 lr 0.003575	time 0.7578 (0.7483)	model_time 0.7574 (0.7426)	loss 3.9377 (3.5473)	grad_norm 0.4998 (1.2670/0.4497)	mem 34602MB
[2025-01-19 04:28:20 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][250/312]	eta 0:00:46 lr 0.003574	time 0.7173 (0.7478)	model_time 0.7169 (0.7423)	loss 3.8724 (3.5486)	grad_norm 1.1513 (1.2655/0.4478)	mem 34602MB
[2025-01-19 04:28:27 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][260/312]	eta 0:00:38 lr 0.003574	time 0.7198 (0.7470)	model_time 0.7193 (0.7417)	loss 4.0282 (3.5525)	grad_norm 2.7183 (1.2638/0.4540)	mem 34602MB
[2025-01-19 04:28:34 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][270/312]	eta 0:00:31 lr 0.003573	time 0.7162 (0.7461)	model_time 0.7160 (0.7410)	loss 3.1701 (3.5543)	grad_norm 1.1780 (1.2743/0.4618)	mem 34602MB
[2025-01-19 04:28:41 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][280/312]	eta 0:00:23 lr 0.003573	time 0.7192 (0.7453)	model_time 0.7190 (0.7404)	loss 4.2983 (3.5616)	grad_norm 1.3738 (1.2891/0.4751)	mem 34602MB
[2025-01-19 04:28:49 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][290/312]	eta 0:00:16 lr 0.003573	time 0.7224 (0.7447)	model_time 0.7220 (0.7399)	loss 3.6112 (3.5555)	grad_norm 1.0201 (1.2858/0.4752)	mem 34602MB
[2025-01-19 04:28:56 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][300/312]	eta 0:00:08 lr 0.003572	time 0.7150 (0.7442)	model_time 0.7149 (0.7395)	loss 3.7428 (3.5608)	grad_norm 0.5463 (1.2760/0.4779)	mem 34602MB
[2025-01-19 04:29:03 internimage_b_1k_224] (main.py 510): INFO Train: [63/300][310/312]	eta 0:00:01 lr 0.003572	time 0.8044 (0.7435)	model_time 0.8043 (0.7390)	loss 3.7513 (3.5624)	grad_norm 1.3841 (1.2774/0.4798)	mem 34602MB
[2025-01-19 04:29:04 internimage_b_1k_224] (main.py 519): INFO EPOCH 63 training takes 0:03:52
[2025-01-19 04:29:04 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_63.pth saving......
[2025-01-19 04:29:08 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_63.pth saved !!!
[2025-01-19 04:29:24 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.545 (16.545)	Loss 0.8883 (0.8883)	Acc@1 80.444 (80.444)	Acc@5 95.825 (95.825)	Mem 34602MB
[2025-01-19 04:29:28 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (1.856)	Loss 1.2860 (1.0641)	Acc@1 71.411 (76.234)	Acc@5 90.942 (93.552)	Mem 34602MB
[2025-01-19 04:29:28 internimage_b_1k_224] (main.py 575): INFO [Epoch:63] * Acc@1 76.256 Acc@5 93.624
[2025-01-19 04:29:28 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.3%
[2025-01-19 04:29:28 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 04:29:32 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 04:29:32 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 76.26%
[2025-01-19 04:29:39 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.285 (7.285)	Loss 1.4217 (1.4217)	Acc@1 71.826 (71.826)	Acc@5 90.186 (90.186)	Mem 34602MB
[2025-01-19 04:29:42 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.921)	Loss 1.9050 (1.5819)	Acc@1 60.938 (67.982)	Acc@5 83.813 (88.348)	Mem 34602MB
[2025-01-19 04:29:42 internimage_b_1k_224] (main.py 575): INFO [Epoch:63] * Acc@1 68.088 Acc@5 88.536
[2025-01-19 04:29:42 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 68.1%
[2025-01-19 04:29:42 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:29:46 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:29:46 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 68.09%
[2025-01-19 04:29:49 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][0/312]	eta 0:10:59 lr 0.003572	time 2.1126 (2.1126)	model_time 0.7319 (0.7319)	loss 3.5225 (3.5225)	grad_norm 0.9869 (0.9869/0.0000)	mem 34602MB
[2025-01-19 04:29:56 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][10/312]	eta 0:04:34 lr 0.003571	time 0.7193 (0.9084)	model_time 0.7189 (0.7825)	loss 4.2975 (3.5015)	grad_norm 1.9421 (1.3976/0.3793)	mem 34602MB
[2025-01-19 04:30:04 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][20/312]	eta 0:04:02 lr 0.003571	time 0.7326 (0.8309)	model_time 0.7325 (0.7648)	loss 3.6815 (3.4463)	grad_norm 1.0090 (1.2513/0.3839)	mem 34602MB
[2025-01-19 04:30:12 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][30/312]	eta 0:03:49 lr 0.003570	time 0.7282 (0.8134)	model_time 0.7281 (0.7685)	loss 3.1285 (3.4457)	grad_norm 1.4458 (1.2427/0.4717)	mem 34602MB
[2025-01-19 04:30:19 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][40/312]	eta 0:03:37 lr 0.003570	time 0.7157 (0.7990)	model_time 0.7156 (0.7649)	loss 2.4429 (3.4518)	grad_norm 0.8420 (1.2430/0.4453)	mem 34602MB
[2025-01-19 04:30:26 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][50/312]	eta 0:03:25 lr 0.003570	time 0.7225 (0.7846)	model_time 0.7220 (0.7572)	loss 3.8459 (3.4907)	grad_norm 1.9230 (1.3365/0.5237)	mem 34602MB
[2025-01-19 04:30:34 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][60/312]	eta 0:03:15 lr 0.003569	time 0.7164 (0.7771)	model_time 0.7159 (0.7541)	loss 4.4149 (3.4845)	grad_norm 2.3091 (1.4057/0.5722)	mem 34602MB
[2025-01-19 04:30:41 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][70/312]	eta 0:03:06 lr 0.003569	time 0.7184 (0.7692)	model_time 0.7179 (0.7494)	loss 4.1648 (3.5456)	grad_norm 2.2692 (1.4063/0.5764)	mem 34602MB
[2025-01-19 04:30:48 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][80/312]	eta 0:02:57 lr 0.003568	time 0.7323 (0.7644)	model_time 0.7322 (0.7470)	loss 3.7087 (3.5631)	grad_norm 1.7524 (1.4453/0.6018)	mem 34602MB
[2025-01-19 04:30:56 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][90/312]	eta 0:02:48 lr 0.003568	time 0.7198 (0.7602)	model_time 0.7193 (0.7447)	loss 3.8158 (3.5593)	grad_norm 1.3003 (1.4153/0.5824)	mem 34602MB
[2025-01-19 04:31:03 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][100/312]	eta 0:02:40 lr 0.003568	time 0.7238 (0.7567)	model_time 0.7233 (0.7427)	loss 3.6257 (3.5755)	grad_norm 0.6273 (1.3634/0.5770)	mem 34602MB
[2025-01-19 04:31:10 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][110/312]	eta 0:02:32 lr 0.003567	time 0.7551 (0.7549)	model_time 0.7549 (0.7421)	loss 4.1419 (3.5985)	grad_norm 2.0092 (1.3685/0.5725)	mem 34602MB
[2025-01-19 04:31:18 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][120/312]	eta 0:02:24 lr 0.003567	time 0.7201 (0.7531)	model_time 0.7200 (0.7414)	loss 2.4647 (3.5874)	grad_norm 2.3548 (1.3712/0.5685)	mem 34602MB
[2025-01-19 04:31:26 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][130/312]	eta 0:02:17 lr 0.003566	time 0.7965 (0.7581)	model_time 0.7964 (0.7471)	loss 4.0073 (3.6130)	grad_norm 1.8430 (1.3843/0.5757)	mem 34602MB
[2025-01-19 04:31:33 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][140/312]	eta 0:02:10 lr 0.003566	time 0.7202 (0.7590)	model_time 0.7197 (0.7488)	loss 3.1186 (3.6036)	grad_norm 2.4058 (1.3711/0.5799)	mem 34602MB
[2025-01-19 04:31:41 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][150/312]	eta 0:02:02 lr 0.003566	time 0.7415 (0.7591)	model_time 0.7413 (0.7496)	loss 2.4992 (3.5843)	grad_norm 1.4121 (1.3783/0.5902)	mem 34602MB
[2025-01-19 04:31:49 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][160/312]	eta 0:01:55 lr 0.003565	time 0.7241 (0.7597)	model_time 0.7240 (0.7507)	loss 2.7874 (3.5772)	grad_norm 1.8642 (1.3583/0.5827)	mem 34602MB
[2025-01-19 04:31:56 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][170/312]	eta 0:01:47 lr 0.003565	time 0.7248 (0.7581)	model_time 0.7244 (0.7496)	loss 4.0411 (3.5738)	grad_norm 1.7686 (1.3383/0.5763)	mem 34602MB
[2025-01-19 04:32:03 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][180/312]	eta 0:01:39 lr 0.003564	time 0.7358 (0.7567)	model_time 0.7354 (0.7487)	loss 4.0142 (3.5739)	grad_norm 0.9403 (1.3422/0.5784)	mem 34602MB
[2025-01-19 04:32:11 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][190/312]	eta 0:01:32 lr 0.003564	time 0.7368 (0.7554)	model_time 0.7366 (0.7478)	loss 3.2538 (3.5757)	grad_norm 0.7503 (1.3404/0.5851)	mem 34602MB
[2025-01-19 04:32:18 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][200/312]	eta 0:01:24 lr 0.003563	time 0.7280 (0.7541)	model_time 0.7275 (0.7468)	loss 2.3107 (3.5714)	grad_norm 1.0278 (1.3632/0.6114)	mem 34602MB
[2025-01-19 04:32:25 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][210/312]	eta 0:01:16 lr 0.003563	time 0.7175 (0.7528)	model_time 0.7170 (0.7459)	loss 2.2356 (3.5668)	grad_norm 0.8905 (1.3635/0.6064)	mem 34602MB
[2025-01-19 04:32:32 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][220/312]	eta 0:01:09 lr 0.003563	time 0.7165 (0.7515)	model_time 0.7162 (0.7449)	loss 3.8227 (3.5573)	grad_norm 1.1137 (1.3501/0.5994)	mem 34602MB
[2025-01-19 04:32:40 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][230/312]	eta 0:01:01 lr 0.003562	time 0.7177 (0.7507)	model_time 0.7172 (0.7443)	loss 3.7881 (3.5584)	grad_norm 2.1766 (1.3474/0.5971)	mem 34602MB
[2025-01-19 04:32:47 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][240/312]	eta 0:00:53 lr 0.003562	time 0.7217 (0.7496)	model_time 0.7216 (0.7435)	loss 3.6349 (3.5537)	grad_norm 1.0935 (1.3451/0.5923)	mem 34602MB
[2025-01-19 04:32:55 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][250/312]	eta 0:00:46 lr 0.003561	time 0.8288 (0.7511)	model_time 0.8286 (0.7453)	loss 3.5016 (3.5540)	grad_norm 1.3966 (1.3427/0.5870)	mem 34602MB
[2025-01-19 04:33:03 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][260/312]	eta 0:00:39 lr 0.003561	time 0.7330 (0.7515)	model_time 0.7326 (0.7458)	loss 4.0503 (3.5585)	grad_norm 1.2717 (1.3429/0.5786)	mem 34602MB
[2025-01-19 04:33:10 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][270/312]	eta 0:00:31 lr 0.003561	time 0.8029 (0.7514)	model_time 0.8027 (0.7459)	loss 3.8784 (3.5580)	grad_norm 0.9867 (1.3320/0.5793)	mem 34602MB
[2025-01-19 04:33:18 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][280/312]	eta 0:00:24 lr 0.003560	time 0.7451 (0.7517)	model_time 0.7446 (0.7464)	loss 2.6357 (3.5622)	grad_norm 1.0275 (1.3224/0.5736)	mem 34602MB
[2025-01-19 04:33:25 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][290/312]	eta 0:00:16 lr 0.003560	time 0.7221 (0.7509)	model_time 0.7218 (0.7458)	loss 4.3691 (3.5553)	grad_norm 2.0817 (1.3237/0.5756)	mem 34602MB
[2025-01-19 04:33:32 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][300/312]	eta 0:00:09 lr 0.003559	time 0.7127 (0.7504)	model_time 0.7126 (0.7454)	loss 3.3005 (3.5533)	grad_norm 0.9360 (1.3140/0.5703)	mem 34602MB
[2025-01-19 04:33:39 internimage_b_1k_224] (main.py 510): INFO Train: [64/300][310/312]	eta 0:00:01 lr 0.003559	time 0.7091 (0.7495)	model_time 0.7090 (0.7447)	loss 3.7424 (3.5549)	grad_norm 0.9758 (1.3060/0.5677)	mem 34602MB
[2025-01-19 04:33:40 internimage_b_1k_224] (main.py 519): INFO EPOCH 64 training takes 0:03:53
[2025-01-19 04:33:40 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_64.pth saving......
[2025-01-19 04:33:43 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_64.pth saved !!!
[2025-01-19 04:33:51 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.320 (7.320)	Loss 0.9815 (0.9815)	Acc@1 80.444 (80.444)	Acc@5 95.923 (95.923)	Mem 34602MB
[2025-01-19 04:33:54 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.945)	Loss 1.3289 (1.1460)	Acc@1 71.460 (76.580)	Acc@5 91.284 (93.759)	Mem 34602MB
[2025-01-19 04:33:54 internimage_b_1k_224] (main.py 575): INFO [Epoch:64] * Acc@1 76.514 Acc@5 93.842
[2025-01-19 04:33:54 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.5%
[2025-01-19 04:33:54 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 04:33:58 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 04:33:58 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 76.51%
[2025-01-19 04:34:05 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.270 (7.270)	Loss 1.3804 (1.3804)	Acc@1 72.437 (72.437)	Acc@5 90.649 (90.649)	Mem 34602MB
[2025-01-19 04:34:08 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.935)	Loss 1.8630 (1.5420)	Acc@1 61.743 (68.643)	Acc@5 84.253 (88.790)	Mem 34602MB
[2025-01-19 04:34:08 internimage_b_1k_224] (main.py 575): INFO [Epoch:64] * Acc@1 68.742 Acc@5 88.958
[2025-01-19 04:34:08 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 68.7%
[2025-01-19 04:34:08 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:34:12 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:34:12 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 68.74%
[2025-01-19 04:34:14 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][0/312]	eta 0:10:52 lr 0.003559	time 2.0916 (2.0916)	model_time 0.7490 (0.7490)	loss 4.2645 (4.2645)	grad_norm 1.8887 (1.8887/0.0000)	mem 34602MB
[2025-01-19 04:34:21 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][10/312]	eta 0:04:16 lr 0.003558	time 0.7333 (0.8503)	model_time 0.7332 (0.7279)	loss 3.5548 (3.7659)	grad_norm 0.8091 (1.0661/0.3368)	mem 34602MB
[2025-01-19 04:34:29 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][20/312]	eta 0:03:51 lr 0.003558	time 0.7262 (0.7917)	model_time 0.7261 (0.7274)	loss 2.3997 (3.7308)	grad_norm 1.4653 (1.1560/0.3763)	mem 34602MB
[2025-01-19 04:34:36 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][30/312]	eta 0:03:37 lr 0.003557	time 0.7574 (0.7727)	model_time 0.7572 (0.7291)	loss 3.9329 (3.6276)	grad_norm 2.1483 (1.2755/0.4852)	mem 34602MB
[2025-01-19 04:34:43 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][40/312]	eta 0:03:27 lr 0.003557	time 0.7263 (0.7637)	model_time 0.7258 (0.7306)	loss 3.7435 (3.6061)	grad_norm 1.5497 (1.3498/0.5575)	mem 34602MB
[2025-01-19 04:34:51 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][50/312]	eta 0:03:19 lr 0.003557	time 0.8474 (0.7626)	model_time 0.8472 (0.7360)	loss 3.4559 (3.5811)	grad_norm 0.8051 (1.3020/0.5270)	mem 34602MB
[2025-01-19 04:34:59 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][60/312]	eta 0:03:13 lr 0.003556	time 0.8134 (0.7674)	model_time 0.8132 (0.7451)	loss 4.3993 (3.6307)	grad_norm 1.0996 (1.2725/0.4888)	mem 34602MB
[2025-01-19 04:35:06 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][70/312]	eta 0:03:05 lr 0.003556	time 0.7097 (0.7654)	model_time 0.7093 (0.7461)	loss 3.1788 (3.5622)	grad_norm 1.4732 (1.2354/0.4725)	mem 34602MB
[2025-01-19 04:35:14 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][80/312]	eta 0:02:57 lr 0.003555	time 0.7182 (0.7653)	model_time 0.7180 (0.7484)	loss 3.0830 (3.5271)	grad_norm 1.2110 (1.1960/0.4628)	mem 34602MB
[2025-01-19 04:35:22 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][90/312]	eta 0:02:49 lr 0.003555	time 0.7317 (0.7652)	model_time 0.7316 (0.7501)	loss 3.8167 (3.5478)	grad_norm 1.0374 (1.2601/0.5396)	mem 34602MB
[2025-01-19 04:35:29 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][100/312]	eta 0:02:41 lr 0.003555	time 0.7192 (0.7617)	model_time 0.7190 (0.7480)	loss 3.6250 (3.5491)	grad_norm 0.7742 (1.2568/0.5515)	mem 34602MB
[2025-01-19 04:35:36 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][110/312]	eta 0:02:33 lr 0.003554	time 0.7391 (0.7586)	model_time 0.7384 (0.7461)	loss 4.0517 (3.5575)	grad_norm 0.7947 (1.2330/0.5361)	mem 34602MB
[2025-01-19 04:35:44 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][120/312]	eta 0:02:25 lr 0.003554	time 0.7182 (0.7565)	model_time 0.7180 (0.7451)	loss 2.9525 (3.5589)	grad_norm 2.2512 (1.2567/0.5394)	mem 34602MB
[2025-01-19 04:35:51 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][130/312]	eta 0:02:17 lr 0.003553	time 0.7259 (0.7541)	model_time 0.7257 (0.7435)	loss 4.3801 (3.5397)	grad_norm 0.8803 (1.2485/0.5280)	mem 34602MB
[2025-01-19 04:35:58 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][140/312]	eta 0:02:09 lr 0.003553	time 0.7162 (0.7522)	model_time 0.7158 (0.7423)	loss 3.5874 (3.5516)	grad_norm 1.9125 (1.2380/0.5201)	mem 34602MB
[2025-01-19 04:36:05 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][150/312]	eta 0:02:01 lr 0.003552	time 0.7260 (0.7505)	model_time 0.7258 (0.7412)	loss 2.9276 (3.5642)	grad_norm 1.8902 (1.2665/0.5256)	mem 34602MB
[2025-01-19 04:36:13 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][160/312]	eta 0:01:53 lr 0.003552	time 0.7185 (0.7490)	model_time 0.7180 (0.7403)	loss 3.0784 (3.5552)	grad_norm 1.0196 (1.2666/0.5228)	mem 34602MB
[2025-01-19 04:36:20 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][170/312]	eta 0:01:46 lr 0.003552	time 0.9504 (0.7493)	model_time 0.9503 (0.7410)	loss 3.5679 (3.5498)	grad_norm 1.1708 (1.2691/0.5255)	mem 34602MB
[2025-01-19 04:36:28 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][180/312]	eta 0:01:39 lr 0.003551	time 0.8108 (0.7520)	model_time 0.8107 (0.7442)	loss 3.8665 (3.5562)	grad_norm 2.0039 (1.2780/0.5245)	mem 34602MB
[2025-01-19 04:36:36 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][190/312]	eta 0:01:31 lr 0.003551	time 0.7147 (0.7519)	model_time 0.7143 (0.7445)	loss 3.5175 (3.5580)	grad_norm 0.6893 (1.2853/0.5232)	mem 34602MB
[2025-01-19 04:36:43 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][200/312]	eta 0:01:24 lr 0.003550	time 0.7162 (0.7525)	model_time 0.7160 (0.7455)	loss 4.1164 (3.5664)	grad_norm 0.8201 (1.2703/0.5164)	mem 34602MB
[2025-01-19 04:36:51 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][210/312]	eta 0:01:16 lr 0.003550	time 0.7921 (0.7531)	model_time 0.7919 (0.7464)	loss 4.4129 (3.5651)	grad_norm 0.7949 (1.2856/0.5401)	mem 34602MB
[2025-01-19 04:36:58 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][220/312]	eta 0:01:09 lr 0.003550	time 0.7260 (0.7519)	model_time 0.7256 (0.7455)	loss 2.4646 (3.5539)	grad_norm 1.0691 (1.2752/0.5336)	mem 34602MB
[2025-01-19 04:37:06 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][230/312]	eta 0:01:01 lr 0.003549	time 0.7220 (0.7508)	model_time 0.7218 (0.7446)	loss 3.5036 (3.5580)	grad_norm 0.6748 (1.2876/0.5389)	mem 34602MB
[2025-01-19 04:37:13 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][240/312]	eta 0:00:54 lr 0.003549	time 0.7184 (0.7502)	model_time 0.7180 (0.7443)	loss 3.7508 (3.5600)	grad_norm 0.8923 (1.2893/0.5384)	mem 34602MB
[2025-01-19 04:37:20 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][250/312]	eta 0:00:46 lr 0.003548	time 0.7192 (0.7491)	model_time 0.7191 (0.7434)	loss 3.8350 (3.5589)	grad_norm 0.9368 (1.2692/0.5375)	mem 34602MB
[2025-01-19 04:37:27 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][260/312]	eta 0:00:38 lr 0.003548	time 0.7158 (0.7482)	model_time 0.7154 (0.7427)	loss 3.7314 (3.5724)	grad_norm 1.3424 (1.2752/0.5344)	mem 34602MB
[2025-01-19 04:37:35 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][270/312]	eta 0:00:31 lr 0.003547	time 0.7161 (0.7474)	model_time 0.7156 (0.7421)	loss 4.3805 (3.5733)	grad_norm 1.3606 (1.2780/0.5298)	mem 34602MB
[2025-01-19 04:37:42 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][280/312]	eta 0:00:23 lr 0.003547	time 0.7213 (0.7470)	model_time 0.7211 (0.7419)	loss 3.8429 (3.5667)	grad_norm 0.7476 (1.2980/0.5453)	mem 34602MB
[2025-01-19 04:37:50 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][290/312]	eta 0:00:16 lr 0.003547	time 0.8169 (0.7469)	model_time 0.8165 (0.7420)	loss 3.9847 (3.5731)	grad_norm 1.3049 (1.3097/0.5662)	mem 34602MB
[2025-01-19 04:37:57 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][300/312]	eta 0:00:08 lr 0.003546	time 0.8026 (0.7482)	model_time 0.8025 (0.7434)	loss 3.9700 (3.5733)	grad_norm 0.8637 (1.2997/0.5643)	mem 34602MB
[2025-01-19 04:38:05 internimage_b_1k_224] (main.py 510): INFO Train: [65/300][310/312]	eta 0:00:01 lr 0.003546	time 0.7154 (0.7481)	model_time 0.7153 (0.7434)	loss 3.4598 (3.5822)	grad_norm 0.9130 (1.3051/0.5646)	mem 34602MB
[2025-01-19 04:38:06 internimage_b_1k_224] (main.py 519): INFO EPOCH 65 training takes 0:03:53
[2025-01-19 04:38:06 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_65.pth saving......
[2025-01-19 04:38:09 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_65.pth saved !!!
[2025-01-19 04:38:16 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.430 (7.430)	Loss 0.9343 (0.9343)	Acc@1 80.176 (80.176)	Acc@5 95.605 (95.605)	Mem 34602MB
[2025-01-19 04:38:19 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.941)	Loss 1.3047 (1.0987)	Acc@1 71.826 (76.341)	Acc@5 90.918 (93.510)	Mem 34602MB
[2025-01-19 04:38:19 internimage_b_1k_224] (main.py 575): INFO [Epoch:65] * Acc@1 76.252 Acc@5 93.574
[2025-01-19 04:38:19 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.3%
[2025-01-19 04:38:19 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 76.51%
[2025-01-19 04:38:28 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.016 (9.016)	Loss 1.3417 (1.3417)	Acc@1 73.022 (73.022)	Acc@5 91.235 (91.235)	Mem 34602MB
[2025-01-19 04:38:33 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.220)	Loss 1.8234 (1.5047)	Acc@1 62.305 (69.201)	Acc@5 84.839 (89.180)	Mem 34602MB
[2025-01-19 04:38:33 internimage_b_1k_224] (main.py 575): INFO [Epoch:65] * Acc@1 69.300 Acc@5 89.347
[2025-01-19 04:38:33 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 69.3%
[2025-01-19 04:38:33 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:38:37 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:38:37 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 69.30%
[2025-01-19 04:38:39 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][0/312]	eta 0:11:13 lr 0.003546	time 2.1571 (2.1571)	model_time 0.7465 (0.7465)	loss 3.9968 (3.9968)	grad_norm 2.0486 (2.0486/0.0000)	mem 34602MB
[2025-01-19 04:38:47 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][10/312]	eta 0:04:32 lr 0.003545	time 0.7102 (0.9011)	model_time 0.7099 (0.7726)	loss 4.2412 (3.7546)	grad_norm 1.5890 (1.4793/0.6757)	mem 34602MB
[2025-01-19 04:38:55 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][20/312]	eta 0:04:03 lr 0.003545	time 0.7137 (0.8335)	model_time 0.7133 (0.7660)	loss 4.3332 (3.7653)	grad_norm 1.5513 (1.4564/0.6000)	mem 34602MB
[2025-01-19 04:39:02 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][30/312]	eta 0:03:46 lr 0.003544	time 0.7183 (0.8017)	model_time 0.7181 (0.7559)	loss 4.1307 (3.7331)	grad_norm 0.9643 (1.3611/0.5324)	mem 34602MB
[2025-01-19 04:39:09 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][40/312]	eta 0:03:33 lr 0.003544	time 0.7342 (0.7833)	model_time 0.7340 (0.7486)	loss 3.6107 (3.6740)	grad_norm 2.7367 (1.3681/0.5245)	mem 34602MB
[2025-01-19 04:39:16 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][50/312]	eta 0:03:22 lr 0.003543	time 0.7221 (0.7724)	model_time 0.7219 (0.7444)	loss 4.4441 (3.6383)	grad_norm 0.8892 (1.3902/0.6294)	mem 34602MB
[2025-01-19 04:39:24 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][60/312]	eta 0:03:12 lr 0.003543	time 0.7204 (0.7643)	model_time 0.7202 (0.7408)	loss 3.8289 (3.6604)	grad_norm 0.8516 (1.3269/0.6208)	mem 34602MB
[2025-01-19 04:39:31 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][70/312]	eta 0:03:03 lr 0.003543	time 0.7425 (0.7596)	model_time 0.7423 (0.7394)	loss 3.8884 (3.6487)	grad_norm 1.3254 (1.2810/0.5935)	mem 34602MB
[2025-01-19 04:39:38 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][80/312]	eta 0:02:55 lr 0.003542	time 0.7123 (0.7562)	model_time 0.7118 (0.7385)	loss 2.6374 (3.6208)	grad_norm 1.0647 (1.2689/0.5662)	mem 34602MB
[2025-01-19 04:39:46 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][90/312]	eta 0:02:47 lr 0.003542	time 0.7413 (0.7538)	model_time 0.7411 (0.7380)	loss 3.4981 (3.6298)	grad_norm 0.8783 (1.2571/0.5465)	mem 34602MB
[2025-01-19 04:39:53 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][100/312]	eta 0:02:39 lr 0.003541	time 0.8056 (0.7535)	model_time 0.8054 (0.7391)	loss 3.7925 (3.6147)	grad_norm 1.0297 (1.2540/0.5362)	mem 34602MB
[2025-01-19 04:40:01 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][110/312]	eta 0:02:32 lr 0.003541	time 0.7178 (0.7560)	model_time 0.7173 (0.7429)	loss 4.1340 (3.6204)	grad_norm 3.1504 (1.2812/0.5485)	mem 34602MB
[2025-01-19 04:40:08 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][120/312]	eta 0:02:25 lr 0.003541	time 0.7216 (0.7558)	model_time 0.7211 (0.7437)	loss 2.9125 (3.6025)	grad_norm 1.6806 (1.2983/0.5446)	mem 34602MB
[2025-01-19 04:40:16 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][130/312]	eta 0:02:17 lr 0.003540	time 0.7168 (0.7560)	model_time 0.7167 (0.7449)	loss 3.8713 (3.5949)	grad_norm 1.3344 (1.3345/0.5559)	mem 34602MB
[2025-01-19 04:40:24 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][140/312]	eta 0:02:10 lr 0.003540	time 0.7179 (0.7566)	model_time 0.7174 (0.7462)	loss 3.5278 (3.5924)	grad_norm 1.3555 (1.3389/0.5425)	mem 34602MB
[2025-01-19 04:40:31 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][150/312]	eta 0:02:02 lr 0.003539	time 0.7196 (0.7554)	model_time 0.7194 (0.7457)	loss 4.2983 (3.5770)	grad_norm 1.7905 (1.3185/0.5409)	mem 34602MB
[2025-01-19 04:40:38 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][160/312]	eta 0:01:54 lr 0.003539	time 0.7233 (0.7538)	model_time 0.7230 (0.7447)	loss 3.5443 (3.5840)	grad_norm 1.2174 (1.3333/0.5458)	mem 34602MB
[2025-01-19 04:40:46 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][170/312]	eta 0:01:46 lr 0.003538	time 0.7249 (0.7525)	model_time 0.7247 (0.7439)	loss 4.0768 (3.5870)	grad_norm 1.5665 (1.3259/0.5373)	mem 34602MB
[2025-01-19 04:40:53 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][180/312]	eta 0:01:39 lr 0.003538	time 0.7104 (0.7513)	model_time 0.7102 (0.7431)	loss 3.7588 (3.5890)	grad_norm 1.7736 (1.3215/0.5379)	mem 34602MB
[2025-01-19 04:41:00 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][190/312]	eta 0:01:31 lr 0.003538	time 0.7163 (0.7500)	model_time 0.7162 (0.7422)	loss 3.9833 (3.5921)	grad_norm 0.8451 (1.3169/0.5328)	mem 34602MB
[2025-01-19 04:41:08 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][200/312]	eta 0:01:23 lr 0.003537	time 0.7889 (0.7491)	model_time 0.7887 (0.7417)	loss 4.3329 (3.5931)	grad_norm 1.6859 (1.3365/0.5503)	mem 34602MB
[2025-01-19 04:41:15 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][210/312]	eta 0:01:16 lr 0.003537	time 0.7176 (0.7484)	model_time 0.7172 (0.7414)	loss 2.3460 (3.5699)	grad_norm 2.6109 (1.3328/0.5507)	mem 34602MB
[2025-01-19 04:41:22 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][220/312]	eta 0:01:08 lr 0.003536	time 0.7205 (0.7481)	model_time 0.7203 (0.7413)	loss 3.6243 (3.5769)	grad_norm 1.0555 (1.3274/0.5456)	mem 34602MB
[2025-01-19 04:41:30 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][230/312]	eta 0:01:01 lr 0.003536	time 0.7949 (0.7502)	model_time 0.7948 (0.7437)	loss 3.4647 (3.5844)	grad_norm 0.9029 (1.3259/0.5401)	mem 34602MB
[2025-01-19 04:41:38 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][240/312]	eta 0:00:54 lr 0.003535	time 0.7213 (0.7504)	model_time 0.7212 (0.7441)	loss 3.4772 (3.5828)	grad_norm 1.0459 (1.3179/0.5333)	mem 34602MB
[2025-01-19 04:41:45 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][250/312]	eta 0:00:46 lr 0.003535	time 0.7133 (0.7509)	model_time 0.7130 (0.7449)	loss 3.3519 (3.5918)	grad_norm 0.9457 (1.3201/0.5305)	mem 34602MB
[2025-01-19 04:41:53 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][260/312]	eta 0:00:39 lr 0.003535	time 0.7187 (0.7511)	model_time 0.7183 (0.7453)	loss 3.2786 (3.5799)	grad_norm 1.1452 (1.3093/0.5259)	mem 34602MB
[2025-01-19 04:42:00 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][270/312]	eta 0:00:31 lr 0.003534	time 0.7220 (0.7508)	model_time 0.7218 (0.7452)	loss 3.8378 (3.5767)	grad_norm 1.0257 (1.3021/0.5206)	mem 34602MB
[2025-01-19 04:42:08 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][280/312]	eta 0:00:23 lr 0.003534	time 0.7225 (0.7500)	model_time 0.7223 (0.7446)	loss 2.6716 (3.5694)	grad_norm 3.5879 (1.3184/0.5440)	mem 34602MB
[2025-01-19 04:42:15 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][290/312]	eta 0:00:16 lr 0.003533	time 0.7556 (0.7493)	model_time 0.7554 (0.7441)	loss 2.3861 (3.5686)	grad_norm 0.9527 (1.3349/0.5634)	mem 34602MB
[2025-01-19 04:42:22 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][300/312]	eta 0:00:08 lr 0.003533	time 0.7527 (0.7485)	model_time 0.7526 (0.7434)	loss 4.2207 (3.5729)	grad_norm 1.0805 (1.3313/0.5612)	mem 34602MB
[2025-01-19 04:42:29 internimage_b_1k_224] (main.py 510): INFO Train: [66/300][310/312]	eta 0:00:01 lr 0.003532	time 0.7244 (0.7474)	model_time 0.7243 (0.7425)	loss 4.4583 (3.5716)	grad_norm 1.1194 (1.3174/0.5513)	mem 34602MB
[2025-01-19 04:42:30 internimage_b_1k_224] (main.py 519): INFO EPOCH 66 training takes 0:03:53
[2025-01-19 04:42:30 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_66.pth saving......
[2025-01-19 04:42:33 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_66.pth saved !!!
[2025-01-19 04:42:41 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.452 (7.452)	Loss 0.9213 (0.9213)	Acc@1 80.322 (80.322)	Acc@5 95.898 (95.898)	Mem 34602MB
[2025-01-19 04:42:44 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.944)	Loss 1.2444 (1.0760)	Acc@1 72.437 (76.438)	Acc@5 91.235 (93.601)	Mem 34602MB
[2025-01-19 04:42:44 internimage_b_1k_224] (main.py 575): INFO [Epoch:66] * Acc@1 76.432 Acc@5 93.706
[2025-01-19 04:42:44 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.4%
[2025-01-19 04:42:44 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 76.51%
[2025-01-19 04:42:53 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.339 (9.339)	Loss 1.3041 (1.3041)	Acc@1 73.779 (73.779)	Acc@5 91.504 (91.504)	Mem 34602MB
[2025-01-19 04:42:58 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.254)	Loss 1.7857 (1.4688)	Acc@1 62.842 (69.773)	Acc@5 85.254 (89.555)	Mem 34602MB
[2025-01-19 04:42:58 internimage_b_1k_224] (main.py 575): INFO [Epoch:66] * Acc@1 69.858 Acc@5 89.713
[2025-01-19 04:42:58 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 69.9%
[2025-01-19 04:42:58 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:43:02 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:43:02 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 69.86%
[2025-01-19 04:43:04 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][0/312]	eta 0:10:25 lr 0.003532	time 2.0056 (2.0056)	model_time 0.7525 (0.7525)	loss 3.4080 (3.4080)	grad_norm 0.7402 (0.7402/0.0000)	mem 34602MB
[2025-01-19 04:43:11 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][10/312]	eta 0:04:15 lr 0.003532	time 0.7176 (0.8465)	model_time 0.7174 (0.7322)	loss 3.8266 (3.4099)	grad_norm 1.1695 (1.3326/0.4944)	mem 34602MB
[2025-01-19 04:43:19 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][20/312]	eta 0:03:52 lr 0.003531	time 0.7449 (0.7953)	model_time 0.7447 (0.7352)	loss 3.4020 (3.5062)	grad_norm 2.6283 (1.2114/0.5419)	mem 34602MB
[2025-01-19 04:43:26 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][30/312]	eta 0:03:39 lr 0.003531	time 0.7988 (0.7801)	model_time 0.7983 (0.7393)	loss 3.9308 (3.4972)	grad_norm 1.5926 (1.4450/0.8538)	mem 34602MB
[2025-01-19 04:43:34 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][40/312]	eta 0:03:34 lr 0.003531	time 0.8091 (0.7881)	model_time 0.8090 (0.7571)	loss 3.0570 (3.4407)	grad_norm 1.1641 (1.3925/0.7733)	mem 34602MB
[2025-01-19 04:43:42 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][50/312]	eta 0:03:24 lr 0.003530	time 0.7405 (0.7821)	model_time 0.7401 (0.7571)	loss 4.4284 (3.5043)	grad_norm 0.8786 (1.3175/0.7255)	mem 34602MB
[2025-01-19 04:43:49 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][60/312]	eta 0:03:15 lr 0.003530	time 0.7349 (0.7773)	model_time 0.7344 (0.7564)	loss 2.6155 (3.4957)	grad_norm 0.8132 (1.2631/0.6826)	mem 34602MB
[2025-01-19 04:43:57 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][70/312]	eta 0:03:07 lr 0.003529	time 0.7362 (0.7744)	model_time 0.7361 (0.7564)	loss 4.1167 (3.4889)	grad_norm 0.8090 (1.2277/0.6442)	mem 34602MB
[2025-01-19 04:44:04 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][80/312]	eta 0:02:58 lr 0.003529	time 0.7386 (0.7701)	model_time 0.7382 (0.7543)	loss 4.2596 (3.4852)	grad_norm 2.4734 (1.2680/0.6801)	mem 34602MB
[2025-01-19 04:44:12 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][90/312]	eta 0:02:50 lr 0.003528	time 0.7249 (0.7661)	model_time 0.7247 (0.7519)	loss 3.7699 (3.4897)	grad_norm 1.4994 (1.2853/0.6701)	mem 34602MB
[2025-01-19 04:44:19 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][100/312]	eta 0:02:41 lr 0.003528	time 0.7190 (0.7617)	model_time 0.7188 (0.7489)	loss 3.4779 (3.5044)	grad_norm 0.5933 (1.2664/0.6524)	mem 34602MB
[2025-01-19 04:44:26 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][110/312]	eta 0:02:33 lr 0.003528	time 0.7167 (0.7587)	model_time 0.7163 (0.7470)	loss 2.5769 (3.4951)	grad_norm 0.8311 (1.2865/0.6414)	mem 34602MB
[2025-01-19 04:44:33 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][120/312]	eta 0:02:25 lr 0.003527	time 0.7312 (0.7566)	model_time 0.7310 (0.7458)	loss 3.8093 (3.4810)	grad_norm 0.9965 (1.3008/0.6347)	mem 34602MB
[2025-01-19 04:44:41 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][130/312]	eta 0:02:17 lr 0.003527	time 0.7398 (0.7546)	model_time 0.7393 (0.7447)	loss 2.8213 (3.4787)	grad_norm 1.0490 (1.3006/0.6164)	mem 34602MB
[2025-01-19 04:44:48 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][140/312]	eta 0:02:09 lr 0.003526	time 0.7207 (0.7528)	model_time 0.7202 (0.7435)	loss 3.5979 (3.4939)	grad_norm 0.6185 (1.2814/0.6073)	mem 34602MB
[2025-01-19 04:44:56 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][150/312]	eta 0:02:01 lr 0.003526	time 0.8026 (0.7522)	model_time 0.8025 (0.7435)	loss 4.6511 (3.4928)	grad_norm 0.7014 (1.2555/0.5960)	mem 34602MB
[2025-01-19 04:45:03 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][160/312]	eta 0:01:54 lr 0.003525	time 0.7959 (0.7548)	model_time 0.7955 (0.7466)	loss 4.2456 (3.4985)	grad_norm 1.8915 (1.2799/0.6243)	mem 34602MB
[2025-01-19 04:45:11 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][170/312]	eta 0:01:47 lr 0.003525	time 0.7053 (0.7555)	model_time 0.7051 (0.7478)	loss 3.4670 (3.4947)	grad_norm 0.7829 (1.2613/0.6123)	mem 34602MB
[2025-01-19 04:45:19 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][180/312]	eta 0:01:39 lr 0.003525	time 0.7491 (0.7569)	model_time 0.7486 (0.7496)	loss 2.9898 (3.4860)	grad_norm 1.3178 (1.2544/0.5974)	mem 34602MB
[2025-01-19 04:45:27 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][190/312]	eta 0:01:32 lr 0.003524	time 0.8035 (0.7573)	model_time 0.8033 (0.7504)	loss 3.8739 (3.4867)	grad_norm 1.2326 (1.2563/0.5936)	mem 34602MB
[2025-01-19 04:45:34 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][200/312]	eta 0:01:24 lr 0.003524	time 0.7213 (0.7570)	model_time 0.7211 (0.7504)	loss 3.7121 (3.4852)	grad_norm 0.8190 (1.2581/0.5877)	mem 34602MB
[2025-01-19 04:45:41 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][210/312]	eta 0:01:17 lr 0.003523	time 0.7294 (0.7555)	model_time 0.7290 (0.7492)	loss 4.2691 (3.4797)	grad_norm 1.3496 (1.2575/0.5823)	mem 34602MB
[2025-01-19 04:45:49 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][220/312]	eta 0:01:09 lr 0.003523	time 0.7200 (0.7541)	model_time 0.7195 (0.7480)	loss 4.1143 (3.4698)	grad_norm 2.4352 (1.2678/0.5962)	mem 34602MB
[2025-01-19 04:45:56 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][230/312]	eta 0:01:01 lr 0.003522	time 0.7187 (0.7530)	model_time 0.7185 (0.7472)	loss 4.2575 (3.4727)	grad_norm 0.6183 (1.2610/0.5928)	mem 34602MB
[2025-01-19 04:46:03 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][240/312]	eta 0:00:54 lr 0.003522	time 0.7343 (0.7520)	model_time 0.7341 (0.7464)	loss 3.9370 (3.4754)	grad_norm 1.2606 (1.2476/0.5854)	mem 34602MB
[2025-01-19 04:46:10 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][250/312]	eta 0:00:46 lr 0.003522	time 0.7403 (0.7510)	model_time 0.7400 (0.7456)	loss 2.3524 (3.4849)	grad_norm 0.9229 (1.2327/0.5798)	mem 34602MB
[2025-01-19 04:46:18 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][260/312]	eta 0:00:39 lr 0.003521	time 0.7252 (0.7501)	model_time 0.7248 (0.7450)	loss 3.0500 (3.4846)	grad_norm 3.3344 (1.2531/0.5935)	mem 34602MB
[2025-01-19 04:46:25 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][270/312]	eta 0:00:31 lr 0.003521	time 0.8001 (0.7500)	model_time 0.7996 (0.7450)	loss 2.7901 (3.4831)	grad_norm 0.6405 (1.2636/0.5936)	mem 34602MB
[2025-01-19 04:46:33 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][280/312]	eta 0:00:24 lr 0.003520	time 0.8060 (0.7516)	model_time 0.8055 (0.7468)	loss 3.9551 (3.4832)	grad_norm 0.8883 (1.2522/0.5879)	mem 34602MB
[2025-01-19 04:46:41 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][290/312]	eta 0:00:16 lr 0.003520	time 0.7091 (0.7527)	model_time 0.7089 (0.7480)	loss 4.2407 (3.4982)	grad_norm 1.3518 (1.2506/0.5806)	mem 34602MB
[2025-01-19 04:46:48 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][300/312]	eta 0:00:09 lr 0.003519	time 0.7891 (0.7527)	model_time 0.7890 (0.7482)	loss 3.4706 (3.5059)	grad_norm 1.6038 (1.2471/0.5736)	mem 34602MB
[2025-01-19 04:46:56 internimage_b_1k_224] (main.py 510): INFO Train: [67/300][310/312]	eta 0:00:01 lr 0.003519	time 0.7115 (0.7524)	model_time 0.7114 (0.7480)	loss 2.8473 (3.5071)	grad_norm 1.4757 (1.2554/0.5830)	mem 34602MB
[2025-01-19 04:46:57 internimage_b_1k_224] (main.py 519): INFO EPOCH 67 training takes 0:03:54
[2025-01-19 04:46:57 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_67.pth saving......
[2025-01-19 04:47:00 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_67.pth saved !!!
[2025-01-19 04:47:07 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.486 (7.486)	Loss 0.9413 (0.9413)	Acc@1 79.761 (79.761)	Acc@5 96.045 (96.045)	Mem 34602MB
[2025-01-19 04:47:10 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.950)	Loss 1.3643 (1.1248)	Acc@1 71.289 (76.232)	Acc@5 90.796 (93.643)	Mem 34602MB
[2025-01-19 04:47:11 internimage_b_1k_224] (main.py 575): INFO [Epoch:67] * Acc@1 76.174 Acc@5 93.680
[2025-01-19 04:47:11 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.2%
[2025-01-19 04:47:11 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 76.51%
[2025-01-19 04:47:20 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.083 (9.083)	Loss 1.2686 (1.2686)	Acc@1 74.292 (74.292)	Acc@5 92.163 (92.163)	Mem 34602MB
[2025-01-19 04:47:24 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.239)	Loss 1.7498 (1.4347)	Acc@1 63.159 (70.248)	Acc@5 85.718 (89.881)	Mem 34602MB
[2025-01-19 04:47:24 internimage_b_1k_224] (main.py 575): INFO [Epoch:67] * Acc@1 70.335 Acc@5 90.019
[2025-01-19 04:47:24 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 70.3%
[2025-01-19 04:47:24 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:47:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:47:28 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 70.34%
[2025-01-19 04:47:31 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][0/312]	eta 0:13:39 lr 0.003519	time 2.6278 (2.6278)	model_time 0.7598 (0.7598)	loss 3.6060 (3.6060)	grad_norm 2.1143 (2.1143/0.0000)	mem 34602MB
[2025-01-19 04:47:38 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][10/312]	eta 0:04:38 lr 0.003518	time 0.7157 (0.9219)	model_time 0.7156 (0.7517)	loss 3.8915 (3.5548)	grad_norm 1.6789 (1.3030/0.4226)	mem 34602MB
[2025-01-19 04:47:46 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][20/312]	eta 0:04:02 lr 0.003518	time 0.7641 (0.8290)	model_time 0.7639 (0.7397)	loss 3.3029 (3.5842)	grad_norm 0.9132 (1.2182/0.4113)	mem 34602MB
[2025-01-19 04:47:53 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][30/312]	eta 0:03:44 lr 0.003518	time 0.7284 (0.7966)	model_time 0.7282 (0.7360)	loss 3.5856 (3.5806)	grad_norm 1.3119 (1.2736/0.4187)	mem 34602MB
[2025-01-19 04:48:00 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][40/312]	eta 0:03:32 lr 0.003517	time 0.7386 (0.7808)	model_time 0.7384 (0.7350)	loss 3.6638 (3.5726)	grad_norm 1.9563 (1.3203/0.4865)	mem 34602MB
[2025-01-19 04:48:08 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][50/312]	eta 0:03:22 lr 0.003517	time 0.7204 (0.7727)	model_time 0.7202 (0.7357)	loss 3.6097 (3.5746)	grad_norm 2.0969 (1.4095/0.5076)	mem 34602MB
[2025-01-19 04:48:15 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][60/312]	eta 0:03:13 lr 0.003516	time 0.7073 (0.7665)	model_time 0.7071 (0.7355)	loss 3.1558 (3.5793)	grad_norm 2.5689 (1.4038/0.5180)	mem 34602MB
[2025-01-19 04:48:22 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][70/312]	eta 0:03:04 lr 0.003516	time 0.7379 (0.7613)	model_time 0.7374 (0.7346)	loss 3.6918 (3.5850)	grad_norm 1.9698 (1.3885/0.5037)	mem 34602MB
[2025-01-19 04:48:30 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][80/312]	eta 0:02:56 lr 0.003515	time 0.7098 (0.7608)	model_time 0.7092 (0.7374)	loss 3.2580 (3.5416)	grad_norm 0.6535 (1.3587/0.5152)	mem 34602MB
[2025-01-19 04:48:38 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][90/312]	eta 0:02:49 lr 0.003515	time 0.8123 (0.7645)	model_time 0.8121 (0.7436)	loss 2.1762 (3.5104)	grad_norm 2.0420 (1.3334/0.5145)	mem 34602MB
[2025-01-19 04:48:45 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][100/312]	eta 0:02:41 lr 0.003514	time 0.7234 (0.7626)	model_time 0.7232 (0.7438)	loss 3.0458 (3.4526)	grad_norm 1.2109 (1.2990/0.5073)	mem 34602MB
[2025-01-19 04:48:53 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][110/312]	eta 0:02:34 lr 0.003514	time 0.7195 (0.7632)	model_time 0.7191 (0.7460)	loss 3.7112 (3.4663)	grad_norm 0.6119 (1.2877/0.5048)	mem 34602MB
[2025-01-19 04:49:01 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][120/312]	eta 0:02:26 lr 0.003514	time 0.7815 (0.7624)	model_time 0.7813 (0.7467)	loss 3.8008 (3.4736)	grad_norm 1.2843 (1.2672/0.4955)	mem 34602MB
[2025-01-19 04:49:08 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][130/312]	eta 0:02:19 lr 0.003513	time 0.7123 (0.7642)	model_time 0.7122 (0.7496)	loss 2.8331 (3.4881)	grad_norm 1.0770 (1.3185/0.5591)	mem 34602MB
[2025-01-19 04:49:16 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][140/312]	eta 0:02:11 lr 0.003513	time 0.7494 (0.7622)	model_time 0.7492 (0.7486)	loss 3.4402 (3.5114)	grad_norm 1.2003 (1.3271/0.5632)	mem 34602MB
[2025-01-19 04:49:23 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][150/312]	eta 0:02:03 lr 0.003512	time 0.7195 (0.7601)	model_time 0.7194 (0.7474)	loss 2.9361 (3.5285)	grad_norm 0.9630 (1.3364/0.5619)	mem 34602MB
[2025-01-19 04:49:30 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][160/312]	eta 0:01:55 lr 0.003512	time 0.7166 (0.7580)	model_time 0.7162 (0.7461)	loss 3.8569 (3.5303)	grad_norm 0.9526 (1.3335/0.5526)	mem 34602MB
[2025-01-19 04:49:38 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][170/312]	eta 0:01:47 lr 0.003511	time 0.7612 (0.7562)	model_time 0.7610 (0.7450)	loss 4.1311 (3.5189)	grad_norm 1.5364 (1.3110/0.5476)	mem 34602MB
[2025-01-19 04:49:45 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][180/312]	eta 0:01:39 lr 0.003511	time 0.7164 (0.7551)	model_time 0.7160 (0.7445)	loss 3.4476 (3.5239)	grad_norm 1.6047 (1.3058/0.5446)	mem 34602MB
[2025-01-19 04:49:52 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][190/312]	eta 0:01:31 lr 0.003511	time 0.7161 (0.7536)	model_time 0.7160 (0.7435)	loss 3.5146 (3.5183)	grad_norm 0.9673 (1.3026/0.5366)	mem 34602MB
[2025-01-19 04:50:00 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][200/312]	eta 0:01:24 lr 0.003510	time 0.7327 (0.7532)	model_time 0.7322 (0.7436)	loss 2.4959 (3.5127)	grad_norm 1.7726 (1.2935/0.5364)	mem 34602MB
[2025-01-19 04:50:08 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][210/312]	eta 0:01:16 lr 0.003510	time 0.8091 (0.7547)	model_time 0.8090 (0.7455)	loss 3.8026 (3.5136)	grad_norm 0.5104 (1.2816/0.5341)	mem 34602MB
[2025-01-19 04:50:15 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][220/312]	eta 0:01:09 lr 0.003509	time 0.7356 (0.7546)	model_time 0.7351 (0.7458)	loss 3.1773 (3.5086)	grad_norm 1.5045 (1.2853/0.5321)	mem 34602MB
[2025-01-19 04:50:23 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][230/312]	eta 0:01:01 lr 0.003509	time 0.7240 (0.7553)	model_time 0.7239 (0.7469)	loss 3.5722 (3.5083)	grad_norm 1.2722 (1.3004/0.5342)	mem 34602MB
[2025-01-19 04:50:30 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][240/312]	eta 0:00:54 lr 0.003508	time 0.8039 (0.7551)	model_time 0.8034 (0.7470)	loss 3.6814 (3.5111)	grad_norm 1.1136 (1.2894/0.5285)	mem 34602MB
[2025-01-19 04:50:38 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][250/312]	eta 0:00:46 lr 0.003508	time 0.7157 (0.7553)	model_time 0.7155 (0.7475)	loss 3.7099 (3.5013)	grad_norm 2.5324 (1.2965/0.5329)	mem 34602MB
[2025-01-19 04:50:45 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][260/312]	eta 0:00:39 lr 0.003508	time 0.7226 (0.7543)	model_time 0.7225 (0.7467)	loss 3.6779 (3.5067)	grad_norm 1.1532 (1.3005/0.5376)	mem 34602MB
[2025-01-19 04:50:52 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][270/312]	eta 0:00:31 lr 0.003507	time 0.7224 (0.7529)	model_time 0.7219 (0.7456)	loss 3.4258 (3.5111)	grad_norm 0.7362 (1.2977/0.5351)	mem 34602MB
[2025-01-19 04:51:00 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][280/312]	eta 0:00:24 lr 0.003507	time 0.7307 (0.7519)	model_time 0.7305 (0.7449)	loss 2.9005 (3.5039)	grad_norm 0.9438 (1.2961/0.5312)	mem 34602MB
[2025-01-19 04:51:07 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][290/312]	eta 0:00:16 lr 0.003506	time 0.7205 (0.7511)	model_time 0.7203 (0.7443)	loss 2.8938 (3.5018)	grad_norm 0.8731 (1.2888/0.5270)	mem 34602MB
[2025-01-19 04:51:14 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][300/312]	eta 0:00:09 lr 0.003506	time 0.7132 (0.7505)	model_time 0.7131 (0.7439)	loss 2.1706 (3.4971)	grad_norm 0.9869 (1.2794/0.5236)	mem 34602MB
[2025-01-19 04:51:21 internimage_b_1k_224] (main.py 510): INFO Train: [68/300][310/312]	eta 0:00:01 lr 0.003505	time 0.7125 (0.7495)	model_time 0.7124 (0.7431)	loss 3.3817 (3.5040)	grad_norm 1.2382 (1.2726/0.5201)	mem 34602MB
[2025-01-19 04:51:22 internimage_b_1k_224] (main.py 519): INFO EPOCH 68 training takes 0:03:53
[2025-01-19 04:51:22 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_68.pth saving......
[2025-01-19 04:51:25 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_68.pth saved !!!
[2025-01-19 04:51:42 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.338 (16.338)	Loss 0.9007 (0.9007)	Acc@1 80.493 (80.493)	Acc@5 95.996 (95.996)	Mem 34602MB
[2025-01-19 04:51:47 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.985)	Loss 1.2817 (1.0851)	Acc@1 71.631 (76.744)	Acc@5 91.382 (93.732)	Mem 34602MB
[2025-01-19 04:51:47 internimage_b_1k_224] (main.py 575): INFO [Epoch:68] * Acc@1 76.711 Acc@5 93.768
[2025-01-19 04:51:47 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.7%
[2025-01-19 04:51:47 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 04:51:51 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 04:51:51 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 76.71%
[2025-01-19 04:51:58 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.383 (7.383)	Loss 1.2356 (1.2356)	Acc@1 74.438 (74.438)	Acc@5 92.480 (92.480)	Mem 34602MB
[2025-01-19 04:52:01 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.934)	Loss 1.7147 (1.4025)	Acc@1 63.721 (70.699)	Acc@5 86.133 (90.174)	Mem 34602MB
[2025-01-19 04:52:02 internimage_b_1k_224] (main.py 575): INFO [Epoch:68] * Acc@1 70.783 Acc@5 90.295
[2025-01-19 04:52:02 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 70.8%
[2025-01-19 04:52:02 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:52:05 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:52:05 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 70.78%
[2025-01-19 04:52:08 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][0/312]	eta 0:11:44 lr 0.003505	time 2.2577 (2.2577)	model_time 0.7525 (0.7525)	loss 2.7646 (2.7646)	grad_norm 0.5871 (0.5871/0.0000)	mem 34602MB
[2025-01-19 04:52:15 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][10/312]	eta 0:04:32 lr 0.003505	time 0.8051 (0.9036)	model_time 0.8050 (0.7664)	loss 2.8281 (3.1494)	grad_norm 1.5284 (1.4413/0.5963)	mem 34602MB
[2025-01-19 04:52:23 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][20/312]	eta 0:04:06 lr 0.003504	time 0.7091 (0.8426)	model_time 0.7089 (0.7706)	loss 3.6990 (3.2898)	grad_norm 0.5941 (1.4027/0.6303)	mem 34602MB
[2025-01-19 04:52:31 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][30/312]	eta 0:03:50 lr 0.003504	time 0.7392 (0.8159)	model_time 0.7390 (0.7670)	loss 3.1043 (3.2435)	grad_norm 1.0749 (1.3791/0.6312)	mem 34602MB
[2025-01-19 04:52:38 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][40/312]	eta 0:03:37 lr 0.003503	time 0.7330 (0.8011)	model_time 0.7328 (0.7641)	loss 4.3545 (3.3801)	grad_norm 1.1513 (1.3676/0.6230)	mem 34602MB
[2025-01-19 04:52:46 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][50/312]	eta 0:03:28 lr 0.003503	time 0.7226 (0.7949)	model_time 0.7225 (0.7650)	loss 3.7700 (3.4200)	grad_norm 2.1242 (1.4186/0.6432)	mem 34602MB
[2025-01-19 04:52:53 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][60/312]	eta 0:03:18 lr 0.003503	time 0.7292 (0.7861)	model_time 0.7288 (0.7611)	loss 3.3017 (3.4260)	grad_norm 0.9616 (1.3857/0.6363)	mem 34602MB
[2025-01-19 04:53:00 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][70/312]	eta 0:03:08 lr 0.003502	time 0.7212 (0.7776)	model_time 0.7210 (0.7560)	loss 3.5504 (3.3718)	grad_norm 0.6550 (1.3345/0.6208)	mem 34602MB
[2025-01-19 04:53:08 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][80/312]	eta 0:02:58 lr 0.003502	time 0.7215 (0.7712)	model_time 0.7214 (0.7522)	loss 2.5682 (3.3720)	grad_norm 1.8926 (1.3559/0.6113)	mem 34602MB
[2025-01-19 04:53:15 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][90/312]	eta 0:02:50 lr 0.003501	time 0.7161 (0.7661)	model_time 0.7159 (0.7492)	loss 4.2606 (3.3621)	grad_norm 1.0678 (1.3378/0.5984)	mem 34602MB
[2025-01-19 04:53:22 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][100/312]	eta 0:02:41 lr 0.003501	time 0.7201 (0.7623)	model_time 0.7197 (0.7470)	loss 3.8216 (3.3999)	grad_norm 1.4263 (1.3342/0.5822)	mem 34602MB
[2025-01-19 04:53:30 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][110/312]	eta 0:02:33 lr 0.003500	time 0.7268 (0.7598)	model_time 0.7264 (0.7459)	loss 3.2596 (3.4178)	grad_norm 0.7770 (1.3533/0.5779)	mem 34602MB
[2025-01-19 04:53:37 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][120/312]	eta 0:02:25 lr 0.003500	time 0.7311 (0.7575)	model_time 0.7307 (0.7446)	loss 3.9284 (3.4390)	grad_norm 1.6140 (1.3252/0.5676)	mem 34602MB
[2025-01-19 04:53:45 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][130/312]	eta 0:02:17 lr 0.003499	time 0.8387 (0.7580)	model_time 0.8386 (0.7461)	loss 2.9009 (3.4284)	grad_norm 1.0073 (1.3508/0.5974)	mem 34602MB
[2025-01-19 04:53:52 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][140/312]	eta 0:02:10 lr 0.003499	time 0.7158 (0.7588)	model_time 0.7156 (0.7478)	loss 3.3896 (3.4299)	grad_norm 0.6885 (1.3798/0.6294)	mem 34602MB
[2025-01-19 04:54:00 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][150/312]	eta 0:02:02 lr 0.003499	time 0.7170 (0.7587)	model_time 0.7168 (0.7484)	loss 4.4338 (3.4490)	grad_norm 1.2894 (1.3761/0.6166)	mem 34602MB
[2025-01-19 04:54:07 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][160/312]	eta 0:01:55 lr 0.003498	time 0.7533 (0.7582)	model_time 0.7532 (0.7485)	loss 3.2523 (3.4488)	grad_norm 1.3816 (1.3463/0.6106)	mem 34602MB
[2025-01-19 04:54:15 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][170/312]	eta 0:01:47 lr 0.003498	time 0.7504 (0.7588)	model_time 0.7501 (0.7496)	loss 3.1288 (3.4551)	grad_norm 1.5772 (1.3384/0.6004)	mem 34602MB
[2025-01-19 04:54:23 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][180/312]	eta 0:01:40 lr 0.003497	time 0.7275 (0.7587)	model_time 0.7270 (0.7500)	loss 4.0509 (3.4593)	grad_norm 0.9488 (1.3609/0.6193)	mem 34602MB
[2025-01-19 04:54:30 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][190/312]	eta 0:01:32 lr 0.003497	time 0.7220 (0.7573)	model_time 0.7218 (0.7491)	loss 3.7500 (3.4763)	grad_norm 1.9160 (1.3734/0.6202)	mem 34602MB
[2025-01-19 04:54:37 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][200/312]	eta 0:01:24 lr 0.003496	time 0.7170 (0.7559)	model_time 0.7166 (0.7481)	loss 2.8870 (3.4825)	grad_norm 1.4659 (1.3565/0.6130)	mem 34602MB
[2025-01-19 04:54:44 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][210/312]	eta 0:01:16 lr 0.003496	time 0.7275 (0.7546)	model_time 0.7273 (0.7471)	loss 3.6631 (3.4880)	grad_norm 1.9075 (1.3432/0.6080)	mem 34602MB
[2025-01-19 04:54:52 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][220/312]	eta 0:01:09 lr 0.003496	time 0.7168 (0.7534)	model_time 0.7163 (0.7463)	loss 2.7962 (3.4845)	grad_norm 2.6182 (1.3639/0.6121)	mem 34602MB
[2025-01-19 04:54:59 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][230/312]	eta 0:01:01 lr 0.003495	time 0.7162 (0.7526)	model_time 0.7158 (0.7457)	loss 3.9608 (3.4922)	grad_norm 1.3183 (1.3593/0.6011)	mem 34602MB
[2025-01-19 04:55:06 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][240/312]	eta 0:00:54 lr 0.003495	time 0.7399 (0.7516)	model_time 0.7397 (0.7450)	loss 2.7513 (3.4977)	grad_norm 1.0804 (1.3476/0.5921)	mem 34602MB
[2025-01-19 04:55:14 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][250/312]	eta 0:00:46 lr 0.003494	time 0.8075 (0.7517)	model_time 0.8073 (0.7453)	loss 3.7797 (3.4956)	grad_norm 0.7701 (1.3330/0.5866)	mem 34602MB
[2025-01-19 04:55:22 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][260/312]	eta 0:00:39 lr 0.003494	time 0.7247 (0.7527)	model_time 0.7243 (0.7466)	loss 2.8411 (3.5029)	grad_norm 1.2044 (1.3367/0.5833)	mem 34602MB
[2025-01-19 04:55:29 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][270/312]	eta 0:00:31 lr 0.003493	time 0.7180 (0.7531)	model_time 0.7175 (0.7472)	loss 3.9890 (3.4954)	grad_norm 1.6892 (1.3336/0.5759)	mem 34602MB
[2025-01-19 04:55:37 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][280/312]	eta 0:00:24 lr 0.003493	time 0.7235 (0.7534)	model_time 0.7233 (0.7477)	loss 4.0055 (3.5036)	grad_norm 2.0141 (1.3551/0.5987)	mem 34602MB
[2025-01-19 04:55:45 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][290/312]	eta 0:00:16 lr 0.003492	time 0.7178 (0.7539)	model_time 0.7176 (0.7484)	loss 4.1389 (3.5158)	grad_norm 0.9763 (1.3498/0.5923)	mem 34602MB
[2025-01-19 04:55:52 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][300/312]	eta 0:00:09 lr 0.003492	time 0.7187 (0.7534)	model_time 0.7185 (0.7480)	loss 4.7590 (3.5243)	grad_norm 2.3108 (1.3515/0.5928)	mem 34602MB
[2025-01-19 04:55:59 internimage_b_1k_224] (main.py 510): INFO Train: [69/300][310/312]	eta 0:00:01 lr 0.003492	time 0.7147 (0.7525)	model_time 0.7145 (0.7473)	loss 3.8333 (3.5175)	grad_norm 1.2730 (1.3384/0.5883)	mem 34602MB
[2025-01-19 04:56:00 internimage_b_1k_224] (main.py 519): INFO EPOCH 69 training takes 0:03:54
[2025-01-19 04:56:00 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_69.pth saving......
[2025-01-19 04:56:03 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_69.pth saved !!!
[2025-01-19 04:56:11 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.356 (7.356)	Loss 0.9356 (0.9356)	Acc@1 79.810 (79.810)	Acc@5 95.581 (95.581)	Mem 34602MB
[2025-01-19 04:56:14 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.928)	Loss 1.2982 (1.1080)	Acc@1 72.754 (76.642)	Acc@5 90.942 (93.588)	Mem 34602MB
[2025-01-19 04:56:14 internimage_b_1k_224] (main.py 575): INFO [Epoch:69] * Acc@1 76.621 Acc@5 93.634
[2025-01-19 04:56:14 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.6%
[2025-01-19 04:56:14 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 76.71%
[2025-01-19 04:56:23 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.290 (9.290)	Loss 1.2045 (1.2045)	Acc@1 74.780 (74.780)	Acc@5 92.773 (92.773)	Mem 34602MB
[2025-01-19 04:56:28 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.274)	Loss 1.6828 (1.3724)	Acc@1 64.160 (71.167)	Acc@5 86.377 (90.414)	Mem 34602MB
[2025-01-19 04:56:28 internimage_b_1k_224] (main.py 575): INFO [Epoch:69] * Acc@1 71.241 Acc@5 90.539
[2025-01-19 04:56:28 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 71.2%
[2025-01-19 04:56:28 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:56:32 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:56:32 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 71.24%
[2025-01-19 04:56:34 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][0/312]	eta 0:10:30 lr 0.003491	time 2.0220 (2.0220)	model_time 0.7557 (0.7557)	loss 3.9243 (3.9243)	grad_norm 1.0058 (1.0058/0.0000)	mem 34602MB
[2025-01-19 04:56:41 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][10/312]	eta 0:04:15 lr 0.003491	time 0.7286 (0.8473)	model_time 0.7284 (0.7319)	loss 3.9013 (3.4201)	grad_norm 1.0604 (1.2758/0.4848)	mem 34602MB
[2025-01-19 04:56:49 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][20/312]	eta 0:03:50 lr 0.003491	time 0.7294 (0.7896)	model_time 0.7292 (0.7290)	loss 3.4116 (3.4400)	grad_norm 1.2208 (1.2825/0.5170)	mem 34602MB
[2025-01-19 04:56:56 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][30/312]	eta 0:03:36 lr 0.003490	time 0.7149 (0.7674)	model_time 0.7144 (0.7263)	loss 4.2394 (3.5744)	grad_norm 1.1322 (1.1541/0.4848)	mem 34602MB
[2025-01-19 04:57:03 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][40/312]	eta 0:03:26 lr 0.003490	time 0.7076 (0.7598)	model_time 0.7075 (0.7285)	loss 2.9417 (3.5581)	grad_norm 0.7232 (1.1854/0.5047)	mem 34602MB
[2025-01-19 04:57:11 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][50/312]	eta 0:03:17 lr 0.003489	time 0.7268 (0.7540)	model_time 0.7267 (0.7288)	loss 4.4113 (3.5355)	grad_norm 1.8223 (1.2655/0.5306)	mem 34602MB
[2025-01-19 04:57:18 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][60/312]	eta 0:03:10 lr 0.003489	time 0.8062 (0.7560)	model_time 0.8057 (0.7349)	loss 4.1499 (3.5770)	grad_norm 0.7819 (1.2606/0.5148)	mem 34602MB
[2025-01-19 04:57:26 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][70/312]	eta 0:03:03 lr 0.003488	time 0.8038 (0.7592)	model_time 0.8034 (0.7410)	loss 2.9903 (3.5109)	grad_norm 1.2961 (1.2549/0.4911)	mem 34602MB
[2025-01-19 04:57:34 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][80/312]	eta 0:02:56 lr 0.003488	time 0.7158 (0.7588)	model_time 0.7156 (0.7428)	loss 3.0162 (3.5510)	grad_norm 2.1205 (1.3041/0.5326)	mem 34602MB
[2025-01-19 04:57:41 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][90/312]	eta 0:02:48 lr 0.003487	time 0.7164 (0.7585)	model_time 0.7162 (0.7442)	loss 3.0495 (3.5695)	grad_norm 1.5926 (1.2903/0.5174)	mem 34602MB
[2025-01-19 04:57:49 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][100/312]	eta 0:02:40 lr 0.003487	time 0.7193 (0.7582)	model_time 0.7191 (0.7453)	loss 4.1497 (3.5677)	grad_norm 0.8677 (1.2871/0.5032)	mem 34602MB
[2025-01-19 04:57:56 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][110/312]	eta 0:02:33 lr 0.003487	time 0.8081 (0.7575)	model_time 0.8079 (0.7458)	loss 3.9082 (3.5509)	grad_norm 1.3029 (1.2656/0.4913)	mem 34602MB
[2025-01-19 04:58:04 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][120/312]	eta 0:02:24 lr 0.003486	time 0.7216 (0.7551)	model_time 0.7214 (0.7442)	loss 3.9945 (3.5520)	grad_norm 0.8819 (1.2787/0.4890)	mem 34602MB
[2025-01-19 04:58:11 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][130/312]	eta 0:02:17 lr 0.003486	time 0.7385 (0.7528)	model_time 0.7384 (0.7427)	loss 3.1390 (3.5424)	grad_norm 1.4674 (1.3635/0.6551)	mem 34602MB
[2025-01-19 04:58:18 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][140/312]	eta 0:02:09 lr 0.003485	time 0.7536 (0.7518)	model_time 0.7531 (0.7424)	loss 2.4194 (3.5557)	grad_norm 0.8473 (1.3433/0.6371)	mem 34602MB
[2025-01-19 04:58:25 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][150/312]	eta 0:02:01 lr 0.003485	time 0.7205 (0.7499)	model_time 0.7203 (0.7411)	loss 2.5716 (3.5565)	grad_norm 0.7469 (1.3158/0.6276)	mem 34602MB
[2025-01-19 04:58:33 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][160/312]	eta 0:01:53 lr 0.003484	time 0.7169 (0.7489)	model_time 0.7168 (0.7407)	loss 3.0752 (3.5533)	grad_norm 0.9921 (1.3018/0.6190)	mem 34602MB
[2025-01-19 04:58:40 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][170/312]	eta 0:01:46 lr 0.003484	time 0.7451 (0.7476)	model_time 0.7447 (0.7399)	loss 3.0344 (3.5720)	grad_norm 1.7926 (1.3090/0.6051)	mem 34602MB
[2025-01-19 04:58:48 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][180/312]	eta 0:01:38 lr 0.003483	time 0.7959 (0.7479)	model_time 0.7957 (0.7406)	loss 3.4649 (3.5683)	grad_norm 2.6086 (1.3201/0.6010)	mem 34602MB
[2025-01-19 04:58:55 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][190/312]	eta 0:01:31 lr 0.003483	time 0.8002 (0.7488)	model_time 0.8000 (0.7418)	loss 2.2491 (3.5547)	grad_norm 0.9610 (1.3095/0.5936)	mem 34602MB
[2025-01-19 04:59:03 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][200/312]	eta 0:01:23 lr 0.003483	time 0.8074 (0.7494)	model_time 0.8072 (0.7427)	loss 4.4134 (3.5428)	grad_norm 0.9958 (1.2924/0.5849)	mem 34602MB
[2025-01-19 04:59:10 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][210/312]	eta 0:01:16 lr 0.003482	time 0.7187 (0.7493)	model_time 0.7185 (0.7429)	loss 3.0108 (3.5465)	grad_norm 1.1668 (1.2956/0.5790)	mem 34602MB
[2025-01-19 04:59:18 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][220/312]	eta 0:01:09 lr 0.003482	time 0.7251 (0.7500)	model_time 0.7249 (0.7439)	loss 2.7727 (3.5443)	grad_norm 0.7690 (1.2998/0.5782)	mem 34602MB
[2025-01-19 04:59:25 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][230/312]	eta 0:01:01 lr 0.003481	time 0.8050 (0.7501)	model_time 0.8048 (0.7442)	loss 3.6192 (3.5525)	grad_norm 0.7629 (1.3011/0.5748)	mem 34602MB
[2025-01-19 04:59:33 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][240/312]	eta 0:00:53 lr 0.003481	time 0.7224 (0.7490)	model_time 0.7222 (0.7434)	loss 4.0423 (3.5455)	grad_norm 0.8880 (1.2909/0.5689)	mem 34602MB
[2025-01-19 04:59:40 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][250/312]	eta 0:00:46 lr 0.003480	time 0.7260 (0.7481)	model_time 0.7259 (0.7427)	loss 4.4317 (3.5433)	grad_norm 2.5906 (1.3013/0.5711)	mem 34602MB
[2025-01-19 04:59:47 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][260/312]	eta 0:00:38 lr 0.003480	time 0.7238 (0.7475)	model_time 0.7236 (0.7423)	loss 3.6530 (3.5386)	grad_norm 1.2284 (1.2971/0.5657)	mem 34602MB
[2025-01-19 04:59:54 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][270/312]	eta 0:00:31 lr 0.003479	time 0.7259 (0.7466)	model_time 0.7254 (0.7416)	loss 3.7087 (3.5441)	grad_norm 1.1989 (1.2937/0.5583)	mem 34602MB
[2025-01-19 05:00:02 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][280/312]	eta 0:00:23 lr 0.003479	time 0.7206 (0.7463)	model_time 0.7204 (0.7414)	loss 2.6045 (3.5325)	grad_norm 1.5705 (1.2918/0.5519)	mem 34602MB
[2025-01-19 05:00:09 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][290/312]	eta 0:00:16 lr 0.003478	time 0.7249 (0.7455)	model_time 0.7244 (0.7408)	loss 3.0136 (3.5265)	grad_norm 1.0531 (1.2925/0.5511)	mem 34602MB
[2025-01-19 05:00:17 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][300/312]	eta 0:00:08 lr 0.003478	time 0.8025 (0.7456)	model_time 0.8024 (0.7410)	loss 3.7757 (3.5234)	grad_norm 1.2647 (1.2965/0.5466)	mem 34602MB
[2025-01-19 05:00:24 internimage_b_1k_224] (main.py 510): INFO Train: [70/300][310/312]	eta 0:00:01 lr 0.003478	time 0.7151 (0.7455)	model_time 0.7150 (0.7411)	loss 4.1882 (3.5250)	grad_norm 1.9264 (1.2978/0.5448)	mem 34602MB
[2025-01-19 05:00:25 internimage_b_1k_224] (main.py 519): INFO EPOCH 70 training takes 0:03:52
[2025-01-19 05:00:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_70.pth saving......
[2025-01-19 05:00:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_70.pth saved !!!
[2025-01-19 05:00:35 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.464 (7.464)	Loss 0.9239 (0.9239)	Acc@1 80.249 (80.249)	Acc@5 95.898 (95.898)	Mem 34602MB
[2025-01-19 05:00:38 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.945)	Loss 1.2709 (1.0843)	Acc@1 71.704 (76.798)	Acc@5 91.406 (93.692)	Mem 34602MB
[2025-01-19 05:00:39 internimage_b_1k_224] (main.py 575): INFO [Epoch:70] * Acc@1 76.867 Acc@5 93.794
[2025-01-19 05:00:39 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.9%
[2025-01-19 05:00:39 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 05:00:42 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 05:00:42 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 76.87%
[2025-01-19 05:00:50 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.427 (7.427)	Loss 1.1753 (1.1753)	Acc@1 75.317 (75.317)	Acc@5 93.140 (93.140)	Mem 34602MB
[2025-01-19 05:00:52 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.929)	Loss 1.6515 (1.3437)	Acc@1 64.355 (71.580)	Acc@5 86.719 (90.678)	Mem 34602MB
[2025-01-19 05:00:53 internimage_b_1k_224] (main.py 575): INFO [Epoch:70] * Acc@1 71.657 Acc@5 90.811
[2025-01-19 05:00:53 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 71.7%
[2025-01-19 05:00:53 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:00:56 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:00:56 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 71.66%
[2025-01-19 05:00:59 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][0/312]	eta 0:11:34 lr 0.003477	time 2.2265 (2.2265)	model_time 0.7550 (0.7550)	loss 2.7992 (2.7992)	grad_norm 0.6529 (0.6529/0.0000)	mem 34602MB
[2025-01-19 05:01:06 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][10/312]	eta 0:04:32 lr 0.003477	time 0.7459 (0.9019)	model_time 0.7458 (0.7679)	loss 3.9752 (3.3604)	grad_norm 1.0778 (1.5442/0.7435)	mem 34602MB
[2025-01-19 05:01:14 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][20/312]	eta 0:04:02 lr 0.003477	time 0.7229 (0.8297)	model_time 0.7224 (0.7593)	loss 3.7543 (3.5079)	grad_norm 1.4787 (1.7419/0.8824)	mem 34602MB
[2025-01-19 05:01:21 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][30/312]	eta 0:03:48 lr 0.003476	time 0.8405 (0.8094)	model_time 0.8400 (0.7616)	loss 3.6719 (3.6043)	grad_norm 1.5572 (1.5503/0.8093)	mem 34602MB
[2025-01-19 05:01:29 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][40/312]	eta 0:03:36 lr 0.003476	time 0.8405 (0.7964)	model_time 0.8400 (0.7602)	loss 2.8328 (3.5545)	grad_norm 1.7626 (1.5087/0.7242)	mem 34602MB
[2025-01-19 05:01:36 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][50/312]	eta 0:03:25 lr 0.003475	time 0.7355 (0.7835)	model_time 0.7353 (0.7543)	loss 3.9425 (3.5347)	grad_norm 1.2584 (1.4153/0.6828)	mem 34602MB
[2025-01-19 05:01:44 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][60/312]	eta 0:03:15 lr 0.003475	time 0.7162 (0.7742)	model_time 0.7158 (0.7497)	loss 3.7797 (3.5257)	grad_norm 0.6400 (1.3543/0.6553)	mem 34602MB
[2025-01-19 05:01:51 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][70/312]	eta 0:03:06 lr 0.003474	time 0.7168 (0.7692)	model_time 0.7166 (0.7481)	loss 4.0981 (3.5441)	grad_norm 0.7207 (1.2991/0.6292)	mem 34602MB
[2025-01-19 05:01:58 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][80/312]	eta 0:02:57 lr 0.003474	time 0.7255 (0.7637)	model_time 0.7253 (0.7452)	loss 4.2063 (3.5351)	grad_norm 0.6371 (1.2689/0.6106)	mem 34602MB
[2025-01-19 05:02:06 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][90/312]	eta 0:02:48 lr 0.003473	time 0.7156 (0.7602)	model_time 0.7152 (0.7437)	loss 3.5115 (3.5224)	grad_norm 2.3646 (1.2686/0.6029)	mem 34602MB
[2025-01-19 05:02:13 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][100/312]	eta 0:02:40 lr 0.003473	time 0.7291 (0.7570)	model_time 0.7289 (0.7421)	loss 3.6509 (3.5378)	grad_norm 1.7722 (1.3624/0.6640)	mem 34602MB
[2025-01-19 05:02:20 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][110/312]	eta 0:02:32 lr 0.003473	time 0.7309 (0.7568)	model_time 0.7307 (0.7432)	loss 4.2428 (3.5695)	grad_norm 1.7452 (1.3615/0.6525)	mem 34602MB
[2025-01-19 05:02:28 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][120/312]	eta 0:02:25 lr 0.003472	time 0.8283 (0.7571)	model_time 0.8278 (0.7446)	loss 3.3166 (3.5888)	grad_norm 0.8270 (1.3613/0.6600)	mem 34602MB
[2025-01-19 05:02:36 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][130/312]	eta 0:02:17 lr 0.003472	time 0.7174 (0.7571)	model_time 0.7172 (0.7455)	loss 4.0564 (3.6140)	grad_norm 0.7109 (1.3400/0.6508)	mem 34602MB
[2025-01-19 05:02:43 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][140/312]	eta 0:02:10 lr 0.003471	time 0.7196 (0.7573)	model_time 0.7194 (0.7465)	loss 3.8090 (3.5903)	grad_norm 1.7897 (1.3275/0.6356)	mem 34602MB
[2025-01-19 05:02:51 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][150/312]	eta 0:02:02 lr 0.003471	time 0.8703 (0.7572)	model_time 0.8701 (0.7470)	loss 4.5128 (3.5712)	grad_norm 1.9392 (1.3716/0.6771)	mem 34602MB
[2025-01-19 05:02:58 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][160/312]	eta 0:01:54 lr 0.003470	time 0.7271 (0.7560)	model_time 0.7269 (0.7465)	loss 3.5803 (3.5738)	grad_norm 0.8296 (1.3729/0.6636)	mem 34602MB
[2025-01-19 05:03:05 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][170/312]	eta 0:01:47 lr 0.003470	time 0.7286 (0.7548)	model_time 0.7282 (0.7458)	loss 4.3372 (3.5791)	grad_norm 1.2143 (1.3529/0.6535)	mem 34602MB
[2025-01-19 05:03:13 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][180/312]	eta 0:01:39 lr 0.003469	time 0.7241 (0.7534)	model_time 0.7239 (0.7449)	loss 4.2280 (3.5973)	grad_norm 1.3186 (1.3324/0.6425)	mem 34602MB
[2025-01-19 05:03:20 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][190/312]	eta 0:01:31 lr 0.003469	time 0.7143 (0.7523)	model_time 0.7142 (0.7442)	loss 3.7081 (3.6041)	grad_norm 2.2005 (1.3456/0.6415)	mem 34602MB
[2025-01-19 05:03:27 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][200/312]	eta 0:01:24 lr 0.003468	time 0.7226 (0.7511)	model_time 0.7222 (0.7434)	loss 3.2185 (3.6051)	grad_norm 0.7004 (1.3291/0.6342)	mem 34602MB
[2025-01-19 05:03:35 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][210/312]	eta 0:01:16 lr 0.003468	time 0.7156 (0.7503)	model_time 0.7155 (0.7429)	loss 3.8413 (3.6095)	grad_norm 1.1174 (1.3236/0.6268)	mem 34602MB
[2025-01-19 05:03:42 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][220/312]	eta 0:01:08 lr 0.003468	time 0.7322 (0.7493)	model_time 0.7320 (0.7423)	loss 4.1112 (3.5972)	grad_norm 2.5427 (1.3155/0.6269)	mem 34602MB
[2025-01-19 05:03:50 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][230/312]	eta 0:01:01 lr 0.003467	time 0.7226 (0.7498)	model_time 0.7224 (0.7431)	loss 3.6109 (3.5991)	grad_norm 1.4350 (1.3110/0.6201)	mem 34602MB
[2025-01-19 05:03:57 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][240/312]	eta 0:00:54 lr 0.003467	time 0.8189 (0.7504)	model_time 0.8187 (0.7439)	loss 3.4965 (3.6008)	grad_norm 2.6207 (1.3147/0.6161)	mem 34602MB
[2025-01-19 05:04:05 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][250/312]	eta 0:00:46 lr 0.003466	time 0.7177 (0.7513)	model_time 0.7173 (0.7451)	loss 4.5047 (3.6043)	grad_norm 0.8812 (1.3223/0.6195)	mem 34602MB
[2025-01-19 05:04:12 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][260/312]	eta 0:00:39 lr 0.003466	time 0.7173 (0.7512)	model_time 0.7168 (0.7452)	loss 2.5259 (3.5963)	grad_norm 0.9930 (1.3196/0.6152)	mem 34602MB
[2025-01-19 05:04:20 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][270/312]	eta 0:00:31 lr 0.003465	time 0.8204 (0.7512)	model_time 0.8202 (0.7454)	loss 3.5170 (3.5999)	grad_norm 0.8106 (1.3095/0.6104)	mem 34602MB
[2025-01-19 05:04:27 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][280/312]	eta 0:00:24 lr 0.003465	time 0.7180 (0.7509)	model_time 0.7178 (0.7453)	loss 3.5802 (3.5989)	grad_norm 0.8790 (1.2958/0.6053)	mem 34602MB
[2025-01-19 05:04:35 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][290/312]	eta 0:00:16 lr 0.003464	time 0.7290 (0.7506)	model_time 0.7288 (0.7452)	loss 2.8942 (3.6050)	grad_norm 1.3717 (1.2866/0.5995)	mem 34602MB
[2025-01-19 05:04:42 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][300/312]	eta 0:00:08 lr 0.003464	time 0.7153 (0.7499)	model_time 0.7152 (0.7446)	loss 3.5705 (3.6092)	grad_norm 1.3112 (1.2942/0.5928)	mem 34602MB
[2025-01-19 05:04:49 internimage_b_1k_224] (main.py 510): INFO Train: [71/300][310/312]	eta 0:00:01 lr 0.003463	time 0.7157 (0.7493)	model_time 0.7156 (0.7442)	loss 3.8579 (3.6126)	grad_norm 2.3962 (1.2823/0.5829)	mem 34602MB
[2025-01-19 05:04:50 internimage_b_1k_224] (main.py 519): INFO EPOCH 71 training takes 0:03:53
[2025-01-19 05:04:50 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_71.pth saving......
[2025-01-19 05:04:53 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_71.pth saved !!!
[2025-01-19 05:05:01 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.241 (7.241)	Loss 0.8973 (0.8973)	Acc@1 80.127 (80.127)	Acc@5 95.703 (95.703)	Mem 34602MB
[2025-01-19 05:05:04 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.922)	Loss 1.2644 (1.0597)	Acc@1 71.509 (76.880)	Acc@5 91.431 (93.686)	Mem 34602MB
[2025-01-19 05:05:04 internimage_b_1k_224] (main.py 575): INFO [Epoch:71] * Acc@1 76.809 Acc@5 93.772
[2025-01-19 05:05:04 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.8%
[2025-01-19 05:05:04 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 76.87%
[2025-01-19 05:05:13 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.907 (8.907)	Loss 1.1468 (1.1468)	Acc@1 75.708 (75.708)	Acc@5 93.457 (93.457)	Mem 34602MB
[2025-01-19 05:05:17 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.222)	Loss 1.6214 (1.3164)	Acc@1 64.648 (71.959)	Acc@5 87.109 (90.920)	Mem 34602MB
[2025-01-19 05:05:18 internimage_b_1k_224] (main.py 575): INFO [Epoch:71] * Acc@1 72.055 Acc@5 91.063
[2025-01-19 05:05:18 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 72.1%
[2025-01-19 05:05:18 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:05:21 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:05:21 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 72.05%
[2025-01-19 05:05:24 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][0/312]	eta 0:12:13 lr 0.003463	time 2.3521 (2.3521)	model_time 0.7545 (0.7545)	loss 2.7388 (2.7388)	grad_norm 2.1124 (2.1124/0.0000)	mem 34602MB
[2025-01-19 05:05:31 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][10/312]	eta 0:04:24 lr 0.003463	time 0.7321 (0.8765)	model_time 0.7319 (0.7309)	loss 3.7072 (3.3214)	grad_norm 1.9587 (1.3611/0.4175)	mem 34602MB
[2025-01-19 05:05:38 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][20/312]	eta 0:03:56 lr 0.003462	time 0.7575 (0.8115)	model_time 0.7573 (0.7351)	loss 4.2803 (3.4711)	grad_norm 1.4291 (1.4062/0.5418)	mem 34602MB
[2025-01-19 05:05:46 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][30/312]	eta 0:03:41 lr 0.003462	time 0.7221 (0.7872)	model_time 0.7219 (0.7353)	loss 3.4446 (3.4796)	grad_norm 1.1790 (1.4291/0.5700)	mem 34602MB
[2025-01-19 05:05:54 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][40/312]	eta 0:03:33 lr 0.003462	time 0.9533 (0.7841)	model_time 0.9528 (0.7448)	loss 3.8810 (3.5069)	grad_norm 1.0768 (1.3115/0.5467)	mem 34602MB
[2025-01-19 05:06:01 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][50/312]	eta 0:03:24 lr 0.003461	time 0.8157 (0.7811)	model_time 0.8155 (0.7494)	loss 3.6307 (3.5762)	grad_norm 1.2075 (1.2639/0.5197)	mem 34602MB
[2025-01-19 05:06:09 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][60/312]	eta 0:03:15 lr 0.003461	time 0.7208 (0.7771)	model_time 0.7207 (0.7505)	loss 3.8900 (3.5728)	grad_norm 2.1328 (1.2196/0.5155)	mem 34602MB
[2025-01-19 05:06:16 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][70/312]	eta 0:03:06 lr 0.003460	time 0.7384 (0.7726)	model_time 0.7382 (0.7498)	loss 2.4769 (3.5689)	grad_norm 1.3444 (1.2520/0.5067)	mem 34602MB
[2025-01-19 05:06:24 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][80/312]	eta 0:02:59 lr 0.003460	time 0.8156 (0.7717)	model_time 0.8151 (0.7516)	loss 2.5180 (3.5387)	grad_norm 0.9274 (1.2172/0.4892)	mem 34602MB
[2025-01-19 05:06:31 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][90/312]	eta 0:02:50 lr 0.003459	time 0.7289 (0.7683)	model_time 0.7286 (0.7504)	loss 4.4723 (3.5465)	grad_norm 1.1592 (1.2025/0.4711)	mem 34602MB
[2025-01-19 05:06:39 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][100/312]	eta 0:02:42 lr 0.003459	time 0.7206 (0.7660)	model_time 0.7205 (0.7498)	loss 3.8607 (3.5217)	grad_norm 1.4557 (1.1883/0.4566)	mem 34602MB
[2025-01-19 05:06:46 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][110/312]	eta 0:02:34 lr 0.003458	time 0.7180 (0.7626)	model_time 0.7178 (0.7478)	loss 4.3983 (3.5314)	grad_norm 0.9972 (1.1861/0.4547)	mem 34602MB
[2025-01-19 05:06:53 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][120/312]	eta 0:02:25 lr 0.003458	time 0.7189 (0.7594)	model_time 0.7185 (0.7459)	loss 4.0725 (3.5336)	grad_norm 2.2081 (1.2306/0.4825)	mem 34602MB
[2025-01-19 05:07:01 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][130/312]	eta 0:02:17 lr 0.003457	time 0.7186 (0.7572)	model_time 0.7184 (0.7446)	loss 3.7973 (3.5024)	grad_norm 1.1770 (1.2567/0.5050)	mem 34602MB
[2025-01-19 05:07:08 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][140/312]	eta 0:02:10 lr 0.003457	time 0.7562 (0.7559)	model_time 0.7560 (0.7442)	loss 3.3568 (3.5186)	grad_norm 1.5100 (1.2758/0.5067)	mem 34602MB
[2025-01-19 05:07:15 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][150/312]	eta 0:02:02 lr 0.003457	time 0.7174 (0.7543)	model_time 0.7169 (0.7434)	loss 4.3157 (3.5155)	grad_norm 1.1070 (1.2749/0.4946)	mem 34602MB
[2025-01-19 05:07:23 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][160/312]	eta 0:01:54 lr 0.003456	time 0.8281 (0.7548)	model_time 0.8276 (0.7445)	loss 3.1362 (3.5170)	grad_norm 1.1293 (1.2783/0.4923)	mem 34602MB
[2025-01-19 05:07:31 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][170/312]	eta 0:01:47 lr 0.003456	time 0.8073 (0.7554)	model_time 0.8072 (0.7457)	loss 3.7234 (3.5320)	grad_norm 1.0056 (1.2698/0.4957)	mem 34602MB
[2025-01-19 05:07:38 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][180/312]	eta 0:01:39 lr 0.003455	time 0.7198 (0.7556)	model_time 0.7196 (0.7464)	loss 3.4492 (3.5353)	grad_norm 1.8441 (1.2802/0.4975)	mem 34602MB
[2025-01-19 05:07:46 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][190/312]	eta 0:01:32 lr 0.003455	time 0.7096 (0.7552)	model_time 0.7094 (0.7465)	loss 3.9273 (3.5415)	grad_norm 1.3306 (1.2703/0.4872)	mem 34602MB
[2025-01-19 05:07:53 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][200/312]	eta 0:01:24 lr 0.003454	time 0.7180 (0.7553)	model_time 0.7176 (0.7469)	loss 2.8702 (3.5405)	grad_norm 1.8843 (1.2791/0.4856)	mem 34602MB
[2025-01-19 05:08:01 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][210/312]	eta 0:01:16 lr 0.003454	time 0.7188 (0.7546)	model_time 0.7186 (0.7466)	loss 2.8793 (3.5292)	grad_norm 2.0034 (1.2795/0.4828)	mem 34602MB
[2025-01-19 05:08:08 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][220/312]	eta 0:01:09 lr 0.003453	time 0.7215 (0.7542)	model_time 0.7211 (0.7466)	loss 3.4217 (3.5181)	grad_norm 1.1763 (1.2805/0.4785)	mem 34602MB
[2025-01-19 05:08:15 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][230/312]	eta 0:01:01 lr 0.003453	time 0.7253 (0.7531)	model_time 0.7251 (0.7458)	loss 3.2966 (3.5027)	grad_norm 1.2551 (1.2746/0.4719)	mem 34602MB
[2025-01-19 05:08:23 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][240/312]	eta 0:00:54 lr 0.003452	time 0.7133 (0.7519)	model_time 0.7127 (0.7448)	loss 2.4263 (3.4967)	grad_norm 2.5317 (1.2884/0.4759)	mem 34602MB
[2025-01-19 05:08:30 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][250/312]	eta 0:00:46 lr 0.003452	time 0.7270 (0.7509)	model_time 0.7268 (0.7442)	loss 2.6315 (3.4970)	grad_norm 1.3195 (1.2886/0.4733)	mem 34602MB
[2025-01-19 05:08:37 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][260/312]	eta 0:00:39 lr 0.003451	time 0.7218 (0.7505)	model_time 0.7216 (0.7440)	loss 4.2258 (3.4989)	grad_norm 2.0526 (1.2890/0.4728)	mem 34602MB
[2025-01-19 05:08:45 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][270/312]	eta 0:00:31 lr 0.003451	time 0.7153 (0.7502)	model_time 0.7151 (0.7439)	loss 2.4796 (3.4992)	grad_norm 1.8196 (1.3014/0.4712)	mem 34602MB
[2025-01-19 05:08:52 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][280/312]	eta 0:00:24 lr 0.003451	time 0.8239 (0.7502)	model_time 0.8235 (0.7442)	loss 4.0553 (3.5052)	grad_norm 2.2396 (1.3298/0.5228)	mem 34602MB
[2025-01-19 05:09:00 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][290/312]	eta 0:00:16 lr 0.003450	time 0.8098 (0.7510)	model_time 0.8096 (0.7452)	loss 3.5667 (3.5106)	grad_norm 1.2005 (1.3254/0.5183)	mem 34602MB
[2025-01-19 05:09:07 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][300/312]	eta 0:00:09 lr 0.003450	time 0.7172 (0.7510)	model_time 0.7171 (0.7453)	loss 2.9743 (3.5154)	grad_norm 1.2365 (1.3324/0.5187)	mem 34602MB
[2025-01-19 05:09:15 internimage_b_1k_224] (main.py 510): INFO Train: [72/300][310/312]	eta 0:00:01 lr 0.003449	time 0.8767 (0.7508)	model_time 0.8766 (0.7453)	loss 3.5791 (3.5051)	grad_norm 0.8151 (1.3321/0.5191)	mem 34602MB
[2025-01-19 05:09:16 internimage_b_1k_224] (main.py 519): INFO EPOCH 72 training takes 0:03:54
[2025-01-19 05:09:16 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_72.pth saving......
[2025-01-19 05:09:19 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_72.pth saved !!!
[2025-01-19 05:09:26 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.589 (7.589)	Loss 0.9201 (0.9201)	Acc@1 80.371 (80.371)	Acc@5 95.801 (95.801)	Mem 34602MB
[2025-01-19 05:09:29 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.962)	Loss 1.3232 (1.1056)	Acc@1 71.777 (76.993)	Acc@5 91.211 (93.799)	Mem 34602MB
[2025-01-19 05:09:30 internimage_b_1k_224] (main.py 575): INFO [Epoch:72] * Acc@1 76.911 Acc@5 93.840
[2025-01-19 05:09:30 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.9%
[2025-01-19 05:09:30 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 05:09:33 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 05:09:33 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 76.91%
[2025-01-19 05:09:40 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.354 (7.354)	Loss 1.1202 (1.1202)	Acc@1 76.074 (76.074)	Acc@5 93.823 (93.823)	Mem 34602MB
[2025-01-19 05:09:45 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.119)	Loss 1.5931 (1.2905)	Acc@1 65.015 (72.359)	Acc@5 87.402 (91.171)	Mem 34602MB
[2025-01-19 05:09:46 internimage_b_1k_224] (main.py 575): INFO [Epoch:72] * Acc@1 72.439 Acc@5 91.307
[2025-01-19 05:09:46 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 72.4%
[2025-01-19 05:09:46 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:09:50 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:09:50 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 72.44%
[2025-01-19 05:09:52 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][0/312]	eta 0:12:29 lr 0.003449	time 2.4012 (2.4012)	model_time 0.7731 (0.7731)	loss 4.3562 (4.3562)	grad_norm 0.7222 (0.7222/0.0000)	mem 34602MB
[2025-01-19 05:10:00 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][10/312]	eta 0:04:34 lr 0.003449	time 0.7544 (0.9100)	model_time 0.7543 (0.7617)	loss 4.1361 (3.8413)	grad_norm 0.9803 (1.0970/0.2100)	mem 34602MB
[2025-01-19 05:10:07 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][20/312]	eta 0:04:04 lr 0.003448	time 0.8048 (0.8362)	model_time 0.8043 (0.7584)	loss 3.5053 (3.6242)	grad_norm 0.8251 (1.2842/0.5081)	mem 34602MB
[2025-01-19 05:10:14 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][30/312]	eta 0:03:46 lr 0.003448	time 0.7225 (0.8033)	model_time 0.7223 (0.7504)	loss 3.5580 (3.6664)	grad_norm 0.5546 (1.2474/0.4853)	mem 34602MB
[2025-01-19 05:10:22 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][40/312]	eta 0:03:33 lr 0.003447	time 0.7540 (0.7851)	model_time 0.7535 (0.7451)	loss 4.3681 (3.6605)	grad_norm 0.7902 (1.1972/0.4612)	mem 34602MB
[2025-01-19 05:10:29 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][50/312]	eta 0:03:22 lr 0.003447	time 0.7160 (0.7729)	model_time 0.7158 (0.7406)	loss 3.7156 (3.5749)	grad_norm 1.9603 (1.2285/0.4935)	mem 34602MB
[2025-01-19 05:10:36 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][60/312]	eta 0:03:13 lr 0.003446	time 0.7160 (0.7664)	model_time 0.7158 (0.7394)	loss 3.5495 (3.5631)	grad_norm 1.1295 (1.2583/0.4991)	mem 34602MB
[2025-01-19 05:10:44 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][70/312]	eta 0:03:04 lr 0.003446	time 0.7897 (0.7622)	model_time 0.7895 (0.7389)	loss 3.3929 (3.5395)	grad_norm 0.7091 (1.3019/0.5136)	mem 34602MB
[2025-01-19 05:10:51 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][80/312]	eta 0:02:56 lr 0.003445	time 0.7823 (0.7591)	model_time 0.7817 (0.7387)	loss 3.8452 (3.5424)	grad_norm 1.0625 (1.2538/0.5022)	mem 34602MB
[2025-01-19 05:10:59 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][90/312]	eta 0:02:48 lr 0.003445	time 0.7362 (0.7602)	model_time 0.7360 (0.7419)	loss 3.7320 (3.5132)	grad_norm 1.0292 (1.2521/0.4801)	mem 34602MB
[2025-01-19 05:11:06 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][100/312]	eta 0:02:41 lr 0.003444	time 0.8098 (0.7607)	model_time 0.8097 (0.7442)	loss 3.2378 (3.4870)	grad_norm 1.0434 (1.2247/0.4682)	mem 34602MB
[2025-01-19 05:11:14 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][110/312]	eta 0:02:33 lr 0.003444	time 0.8248 (0.7605)	model_time 0.8243 (0.7455)	loss 3.4778 (3.4837)	grad_norm 0.7537 (1.2057/0.4602)	mem 34602MB
[2025-01-19 05:11:21 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][120/312]	eta 0:02:25 lr 0.003444	time 0.7198 (0.7599)	model_time 0.7196 (0.7461)	loss 2.3389 (3.4933)	grad_norm 0.7894 (1.2098/0.4539)	mem 34602MB
[2025-01-19 05:11:29 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][130/312]	eta 0:02:18 lr 0.003443	time 0.7209 (0.7599)	model_time 0.7207 (0.7471)	loss 3.8657 (3.4900)	grad_norm 1.0241 (1.2233/0.4544)	mem 34602MB
[2025-01-19 05:11:37 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][140/312]	eta 0:02:10 lr 0.003443	time 0.9073 (0.7599)	model_time 0.9071 (0.7480)	loss 3.3531 (3.5068)	grad_norm 2.1785 (1.2375/0.4585)	mem 34602MB
[2025-01-19 05:11:44 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][150/312]	eta 0:02:02 lr 0.003442	time 0.7594 (0.7585)	model_time 0.7589 (0.7474)	loss 3.4074 (3.4946)	grad_norm 1.0061 (1.2670/0.4818)	mem 34602MB
[2025-01-19 05:11:51 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][160/312]	eta 0:01:54 lr 0.003442	time 0.7233 (0.7566)	model_time 0.7231 (0.7461)	loss 4.0508 (3.4946)	grad_norm 0.8346 (1.2467/0.4774)	mem 34602MB
[2025-01-19 05:11:59 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][170/312]	eta 0:01:47 lr 0.003441	time 0.7220 (0.7552)	model_time 0.7219 (0.7453)	loss 3.9260 (3.4935)	grad_norm 0.7210 (1.2355/0.4680)	mem 34602MB
[2025-01-19 05:12:06 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][180/312]	eta 0:01:39 lr 0.003441	time 0.7324 (0.7536)	model_time 0.7323 (0.7442)	loss 3.0767 (3.4873)	grad_norm 1.2945 (1.2230/0.4647)	mem 34602MB
[2025-01-19 05:12:13 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][190/312]	eta 0:01:31 lr 0.003440	time 0.7220 (0.7522)	model_time 0.7216 (0.7433)	loss 2.7909 (3.4934)	grad_norm 0.5873 (1.2141/0.4600)	mem 34602MB
[2025-01-19 05:12:21 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][200/312]	eta 0:01:24 lr 0.003440	time 0.7976 (0.7517)	model_time 0.7975 (0.7432)	loss 3.9727 (3.4884)	grad_norm 1.1175 (1.2098/0.4542)	mem 34602MB
[2025-01-19 05:12:28 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][210/312]	eta 0:01:16 lr 0.003439	time 0.7165 (0.7509)	model_time 0.7163 (0.7428)	loss 3.7431 (3.4918)	grad_norm 0.8367 (1.2352/0.4746)	mem 34602MB
[2025-01-19 05:12:36 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][220/312]	eta 0:01:09 lr 0.003439	time 0.8171 (0.7532)	model_time 0.8169 (0.7454)	loss 3.4702 (3.4935)	grad_norm 0.9935 (1.2249/0.4696)	mem 34602MB
[2025-01-19 05:12:44 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][230/312]	eta 0:01:01 lr 0.003438	time 0.8145 (0.7535)	model_time 0.8144 (0.7461)	loss 3.6816 (3.4966)	grad_norm 2.2994 (1.2310/0.4697)	mem 34602MB
[2025-01-19 05:12:51 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][240/312]	eta 0:00:54 lr 0.003438	time 0.7371 (0.7541)	model_time 0.7369 (0.7470)	loss 4.2887 (3.5059)	grad_norm 0.6359 (1.2365/0.4714)	mem 34602MB
[2025-01-19 05:12:59 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][250/312]	eta 0:00:46 lr 0.003438	time 0.7149 (0.7547)	model_time 0.7148 (0.7479)	loss 3.6712 (3.4997)	grad_norm 0.7589 (1.2268/0.4680)	mem 34602MB
[2025-01-19 05:13:07 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][260/312]	eta 0:00:39 lr 0.003437	time 0.8510 (0.7549)	model_time 0.8506 (0.7483)	loss 4.4382 (3.4975)	grad_norm 1.1543 (1.2260/0.4673)	mem 34602MB
[2025-01-19 05:13:14 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][270/312]	eta 0:00:31 lr 0.003437	time 0.7252 (0.7541)	model_time 0.7250 (0.7477)	loss 3.0162 (3.4954)	grad_norm 1.0589 (1.2295/0.4671)	mem 34602MB
[2025-01-19 05:13:21 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][280/312]	eta 0:00:24 lr 0.003436	time 0.7287 (0.7532)	model_time 0.7286 (0.7471)	loss 2.5896 (3.4872)	grad_norm 1.5432 (1.2361/0.4691)	mem 34602MB
[2025-01-19 05:13:29 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][290/312]	eta 0:00:16 lr 0.003436	time 0.7163 (0.7525)	model_time 0.7158 (0.7465)	loss 3.7397 (3.4873)	grad_norm 1.8291 (1.2520/0.4877)	mem 34602MB
[2025-01-19 05:13:36 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][300/312]	eta 0:00:09 lr 0.003435	time 0.7152 (0.7513)	model_time 0.7151 (0.7455)	loss 2.2437 (3.4877)	grad_norm 1.0080 (1.2673/0.5161)	mem 34602MB
[2025-01-19 05:13:43 internimage_b_1k_224] (main.py 510): INFO Train: [73/300][310/312]	eta 0:00:01 lr 0.003435	time 0.7157 (0.7501)	model_time 0.7156 (0.7445)	loss 3.4808 (3.4985)	grad_norm 0.7313 (1.2722/0.5219)	mem 34602MB
[2025-01-19 05:13:44 internimage_b_1k_224] (main.py 519): INFO EPOCH 73 training takes 0:03:54
[2025-01-19 05:13:44 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_73.pth saving......
[2025-01-19 05:13:47 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_73.pth saved !!!
[2025-01-19 05:14:00 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 13.218 (13.218)	Loss 0.8804 (0.8804)	Acc@1 81.079 (81.079)	Acc@5 96.191 (96.191)	Mem 34602MB
[2025-01-19 05:14:04 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.553)	Loss 1.3007 (1.0657)	Acc@1 71.631 (77.146)	Acc@5 91.187 (93.912)	Mem 34602MB
[2025-01-19 05:14:04 internimage_b_1k_224] (main.py 575): INFO [Epoch:73] * Acc@1 77.037 Acc@5 93.968
[2025-01-19 05:14:04 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.0%
[2025-01-19 05:14:04 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 05:14:07 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 05:14:07 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 77.04%
[2025-01-19 05:14:15 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.656 (7.656)	Loss 1.0950 (1.0950)	Acc@1 76.318 (76.318)	Acc@5 93.970 (93.970)	Mem 34602MB
[2025-01-19 05:14:18 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.967)	Loss 1.5658 (1.2660)	Acc@1 65.698 (72.729)	Acc@5 87.720 (91.393)	Mem 34602MB
[2025-01-19 05:14:18 internimage_b_1k_224] (main.py 575): INFO [Epoch:73] * Acc@1 72.807 Acc@5 91.525
[2025-01-19 05:14:18 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 72.8%
[2025-01-19 05:14:18 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:14:22 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:14:22 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 72.81%
[2025-01-19 05:14:24 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][0/312]	eta 0:10:46 lr 0.003435	time 2.0735 (2.0735)	model_time 0.7433 (0.7433)	loss 3.5873 (3.5873)	grad_norm 1.0988 (1.0988/0.0000)	mem 34602MB
[2025-01-19 05:14:32 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][10/312]	eta 0:04:24 lr 0.003434	time 0.9099 (0.8756)	model_time 0.9094 (0.7543)	loss 3.9521 (3.5285)	grad_norm 1.6608 (1.5458/0.6171)	mem 34602MB
[2025-01-19 05:14:39 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][20/312]	eta 0:03:56 lr 0.003434	time 0.7225 (0.8090)	model_time 0.7224 (0.7453)	loss 3.3376 (3.6173)	grad_norm 1.1586 (1.2714/0.5581)	mem 34602MB
[2025-01-19 05:14:47 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][30/312]	eta 0:03:46 lr 0.003433	time 0.7998 (0.8024)	model_time 0.7996 (0.7591)	loss 3.9415 (3.4531)	grad_norm 1.0030 (1.2672/0.5204)	mem 34602MB
[2025-01-19 05:14:55 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][40/312]	eta 0:03:35 lr 0.003433	time 0.7277 (0.7904)	model_time 0.7272 (0.7577)	loss 3.3378 (3.4767)	grad_norm 2.0721 (1.2616/0.4969)	mem 34602MB
[2025-01-19 05:15:02 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][50/312]	eta 0:03:25 lr 0.003432	time 0.7203 (0.7858)	model_time 0.7201 (0.7594)	loss 4.0748 (3.4703)	grad_norm 0.9714 (1.2672/0.4904)	mem 34602MB
[2025-01-19 05:15:10 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][60/312]	eta 0:03:17 lr 0.003432	time 0.8402 (0.7818)	model_time 0.8400 (0.7597)	loss 3.9058 (3.4732)	grad_norm 1.5848 (1.2657/0.4783)	mem 34602MB
[2025-01-19 05:15:17 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][70/312]	eta 0:03:07 lr 0.003431	time 0.7311 (0.7757)	model_time 0.7309 (0.7567)	loss 3.7709 (3.4947)	grad_norm 1.1325 (1.2636/0.4686)	mem 34602MB
[2025-01-19 05:15:25 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][80/312]	eta 0:02:59 lr 0.003431	time 0.7272 (0.7722)	model_time 0.7270 (0.7555)	loss 2.3594 (3.4719)	grad_norm 1.3143 (1.3627/0.6118)	mem 34602MB
[2025-01-19 05:15:32 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][90/312]	eta 0:02:50 lr 0.003430	time 0.7415 (0.7681)	model_time 0.7413 (0.7531)	loss 4.1138 (3.4841)	grad_norm 0.6195 (1.3715/0.6040)	mem 34602MB
[2025-01-19 05:15:39 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][100/312]	eta 0:02:41 lr 0.003430	time 0.7482 (0.7640)	model_time 0.7479 (0.7505)	loss 3.3656 (3.4600)	grad_norm 1.3340 (1.3292/0.5911)	mem 34602MB
[2025-01-19 05:15:47 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][110/312]	eta 0:02:33 lr 0.003430	time 0.7287 (0.7604)	model_time 0.7285 (0.7481)	loss 4.1925 (3.4798)	grad_norm 1.1916 (1.3087/0.5809)	mem 34602MB
[2025-01-19 05:15:54 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][120/312]	eta 0:02:25 lr 0.003429	time 0.7279 (0.7579)	model_time 0.7278 (0.7466)	loss 4.0177 (3.4730)	grad_norm 1.2754 (1.2947/0.5679)	mem 34602MB
[2025-01-19 05:16:01 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][130/312]	eta 0:02:17 lr 0.003429	time 0.7292 (0.7561)	model_time 0.7290 (0.7456)	loss 3.8349 (3.4792)	grad_norm 0.8751 (1.2662/0.5600)	mem 34602MB
[2025-01-19 05:16:09 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][140/312]	eta 0:02:09 lr 0.003428	time 0.7100 (0.7555)	model_time 0.7099 (0.7457)	loss 4.0922 (3.4964)	grad_norm 0.9293 (1.2510/0.5511)	mem 34602MB
[2025-01-19 05:16:16 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][150/312]	eta 0:02:02 lr 0.003428	time 0.8022 (0.7571)	model_time 0.8021 (0.7479)	loss 3.5845 (3.5099)	grad_norm 2.0768 (1.2494/0.5414)	mem 34602MB
[2025-01-19 05:16:24 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][160/312]	eta 0:01:54 lr 0.003427	time 0.8081 (0.7565)	model_time 0.8080 (0.7479)	loss 3.2857 (3.5021)	grad_norm 0.8261 (1.2648/0.5434)	mem 34602MB
[2025-01-19 05:16:31 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][170/312]	eta 0:01:47 lr 0.003427	time 0.7221 (0.7563)	model_time 0.7220 (0.7482)	loss 3.7950 (3.5035)	grad_norm 0.8086 (1.2499/0.5349)	mem 34602MB
[2025-01-19 05:16:39 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][180/312]	eta 0:01:40 lr 0.003426	time 0.8712 (0.7583)	model_time 0.8707 (0.7506)	loss 3.1865 (3.5209)	grad_norm 0.7724 (1.2467/0.5293)	mem 34602MB
[2025-01-19 05:16:47 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][190/312]	eta 0:01:32 lr 0.003426	time 0.7339 (0.7569)	model_time 0.7337 (0.7496)	loss 4.4466 (3.5251)	grad_norm 1.1745 (1.2632/0.5339)	mem 34602MB
[2025-01-19 05:16:54 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][200/312]	eta 0:01:24 lr 0.003425	time 0.7186 (0.7560)	model_time 0.7181 (0.7491)	loss 2.4066 (3.5001)	grad_norm 2.5653 (1.2683/0.5389)	mem 34602MB
[2025-01-19 05:17:01 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][210/312]	eta 0:01:16 lr 0.003425	time 0.7599 (0.7549)	model_time 0.7598 (0.7482)	loss 1.9744 (3.4934)	grad_norm 1.7350 (1.2764/0.5394)	mem 34602MB
[2025-01-19 05:17:09 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][220/312]	eta 0:01:09 lr 0.003424	time 0.7267 (0.7538)	model_time 0.7265 (0.7475)	loss 4.0581 (3.5013)	grad_norm 1.6483 (1.2683/0.5322)	mem 34602MB
[2025-01-19 05:17:16 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][230/312]	eta 0:01:01 lr 0.003424	time 0.7232 (0.7525)	model_time 0.7230 (0.7464)	loss 3.4540 (3.5139)	grad_norm 1.1677 (1.2694/0.5301)	mem 34602MB
[2025-01-19 05:17:23 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][240/312]	eta 0:00:54 lr 0.003423	time 0.7188 (0.7514)	model_time 0.7186 (0.7455)	loss 3.6159 (3.5129)	grad_norm 1.0961 (1.2691/0.5360)	mem 34602MB
[2025-01-19 05:17:31 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][250/312]	eta 0:00:46 lr 0.003423	time 0.7202 (0.7507)	model_time 0.7197 (0.7450)	loss 3.3204 (3.5035)	grad_norm 1.2777 (1.2632/0.5294)	mem 34602MB
[2025-01-19 05:17:38 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][260/312]	eta 0:00:39 lr 0.003423	time 0.7167 (0.7506)	model_time 0.7164 (0.7452)	loss 3.7475 (3.5103)	grad_norm 0.7960 (1.2871/0.5544)	mem 34602MB
[2025-01-19 05:17:46 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][270/312]	eta 0:00:31 lr 0.003422	time 0.8190 (0.7520)	model_time 0.8185 (0.7468)	loss 3.5869 (3.5083)	grad_norm 1.4217 (1.2752/0.5492)	mem 34602MB
[2025-01-19 05:17:53 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][280/312]	eta 0:00:24 lr 0.003422	time 0.8467 (0.7521)	model_time 0.8465 (0.7470)	loss 3.7205 (3.5105)	grad_norm 1.7344 (1.2793/0.5489)	mem 34602MB
[2025-01-19 05:18:01 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][290/312]	eta 0:00:16 lr 0.003421	time 0.7259 (0.7524)	model_time 0.7258 (0.7474)	loss 3.5748 (3.5055)	grad_norm 1.6093 (1.2785/0.5438)	mem 34602MB
[2025-01-19 05:18:09 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][300/312]	eta 0:00:09 lr 0.003421	time 0.8057 (0.7523)	model_time 0.8056 (0.7475)	loss 2.6483 (3.5024)	grad_norm 1.2953 (1.2721/0.5387)	mem 34602MB
[2025-01-19 05:18:16 internimage_b_1k_224] (main.py 510): INFO Train: [74/300][310/312]	eta 0:00:01 lr 0.003420	time 0.7276 (0.7520)	model_time 0.7275 (0.7474)	loss 3.6790 (3.4965)	grad_norm 2.2564 (1.2616/0.5286)	mem 34602MB
[2025-01-19 05:18:17 internimage_b_1k_224] (main.py 519): INFO EPOCH 74 training takes 0:03:54
[2025-01-19 05:18:17 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_74.pth saving......
[2025-01-19 05:18:20 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_74.pth saved !!!
[2025-01-19 05:18:27 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.202 (7.202)	Loss 0.8893 (0.8893)	Acc@1 80.176 (80.176)	Acc@5 96.118 (96.118)	Mem 34602MB
[2025-01-19 05:18:30 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.935)	Loss 1.2687 (1.0548)	Acc@1 71.753 (76.820)	Acc@5 91.772 (93.934)	Mem 34602MB
[2025-01-19 05:18:30 internimage_b_1k_224] (main.py 575): INFO [Epoch:74] * Acc@1 76.817 Acc@5 93.996
[2025-01-19 05:18:30 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.8%
[2025-01-19 05:18:30 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 77.04%
[2025-01-19 05:18:40 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.223 (9.223)	Loss 1.0704 (1.0704)	Acc@1 76.685 (76.685)	Acc@5 94.214 (94.214)	Mem 34602MB
[2025-01-19 05:18:44 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.232)	Loss 1.5392 (1.2421)	Acc@1 65.967 (73.038)	Acc@5 88.110 (91.622)	Mem 34602MB
[2025-01-19 05:18:44 internimage_b_1k_224] (main.py 575): INFO [Epoch:74] * Acc@1 73.129 Acc@5 91.755
[2025-01-19 05:18:44 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 73.1%
[2025-01-19 05:18:44 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:18:48 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:18:48 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 73.13%
[2025-01-19 05:18:50 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][0/312]	eta 0:10:29 lr 0.003420	time 2.0187 (2.0187)	model_time 0.7542 (0.7542)	loss 3.8891 (3.8891)	grad_norm 2.8074 (2.8074/0.0000)	mem 34602MB
[2025-01-19 05:18:58 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][10/312]	eta 0:04:19 lr 0.003420	time 0.7287 (0.8591)	model_time 0.7284 (0.7438)	loss 3.2749 (3.3051)	grad_norm 1.6432 (1.6591/0.6896)	mem 34602MB
[2025-01-19 05:19:05 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][20/312]	eta 0:03:53 lr 0.003419	time 0.7721 (0.8001)	model_time 0.7719 (0.7395)	loss 3.9276 (3.2751)	grad_norm 0.6921 (1.3463/0.6217)	mem 34602MB
[2025-01-19 05:19:12 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][30/312]	eta 0:03:39 lr 0.003419	time 0.7353 (0.7783)	model_time 0.7348 (0.7371)	loss 3.9053 (3.3064)	grad_norm 0.9469 (1.2552/0.5387)	mem 34602MB
[2025-01-19 05:19:20 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][40/312]	eta 0:03:28 lr 0.003418	time 0.7189 (0.7662)	model_time 0.7184 (0.7350)	loss 2.6934 (3.3360)	grad_norm 1.2344 (1.2611/0.5264)	mem 34602MB
[2025-01-19 05:19:27 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][50/312]	eta 0:03:19 lr 0.003418	time 0.7220 (0.7605)	model_time 0.7218 (0.7353)	loss 3.2697 (3.3748)	grad_norm 1.4466 (1.3107/0.5382)	mem 34602MB
[2025-01-19 05:19:34 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][60/312]	eta 0:03:10 lr 0.003417	time 0.7214 (0.7550)	model_time 0.7209 (0.7339)	loss 3.8947 (3.4541)	grad_norm 2.4478 (1.3514/0.5387)	mem 34602MB
[2025-01-19 05:19:42 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][70/312]	eta 0:03:02 lr 0.003417	time 0.8669 (0.7542)	model_time 0.8663 (0.7360)	loss 3.6456 (3.4718)	grad_norm 0.9051 (1.3695/0.5509)	mem 34602MB
[2025-01-19 05:19:50 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][80/312]	eta 0:02:55 lr 0.003416	time 0.8287 (0.7584)	model_time 0.8285 (0.7424)	loss 3.2514 (3.4965)	grad_norm 1.3673 (1.3767/0.5418)	mem 34602MB
[2025-01-19 05:19:57 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][90/312]	eta 0:02:48 lr 0.003416	time 0.7173 (0.7577)	model_time 0.7171 (0.7434)	loss 3.3186 (3.4935)	grad_norm 0.7576 (1.3440/0.5342)	mem 34602MB
[2025-01-19 05:20:05 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][100/312]	eta 0:02:40 lr 0.003415	time 0.8013 (0.7576)	model_time 0.8008 (0.7447)	loss 3.1000 (3.4641)	grad_norm 0.7572 (1.3066/0.5266)	mem 34602MB
[2025-01-19 05:20:12 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][110/312]	eta 0:02:33 lr 0.003415	time 0.8075 (0.7585)	model_time 0.8073 (0.7467)	loss 2.8805 (3.4687)	grad_norm 1.3410 (1.3132/0.5355)	mem 34602MB
[2025-01-19 05:20:20 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][120/312]	eta 0:02:25 lr 0.003414	time 0.7183 (0.7577)	model_time 0.7181 (0.7469)	loss 3.0416 (3.4717)	grad_norm 0.8828 (1.3072/0.5281)	mem 34602MB
[2025-01-19 05:20:27 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][130/312]	eta 0:02:17 lr 0.003414	time 0.7183 (0.7564)	model_time 0.7181 (0.7464)	loss 3.8969 (3.4751)	grad_norm 2.3573 (1.3130/0.5310)	mem 34602MB
[2025-01-19 05:20:34 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][140/312]	eta 0:02:09 lr 0.003413	time 0.7181 (0.7543)	model_time 0.7179 (0.7450)	loss 4.2186 (3.4729)	grad_norm 0.7785 (1.3061/0.5232)	mem 34602MB
[2025-01-19 05:20:42 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][150/312]	eta 0:02:01 lr 0.003413	time 0.7182 (0.7529)	model_time 0.7178 (0.7442)	loss 4.3491 (3.4865)	grad_norm 1.3987 (1.3285/0.5410)	mem 34602MB
[2025-01-19 05:20:49 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][160/312]	eta 0:01:54 lr 0.003413	time 0.7517 (0.7515)	model_time 0.7516 (0.7433)	loss 3.5890 (3.5007)	grad_norm 1.0129 (1.3148/0.5327)	mem 34602MB
[2025-01-19 05:20:56 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][170/312]	eta 0:01:46 lr 0.003412	time 0.7177 (0.7506)	model_time 0.7175 (0.7429)	loss 3.7537 (3.5086)	grad_norm 0.9697 (1.3043/0.5277)	mem 34602MB
[2025-01-19 05:21:04 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][180/312]	eta 0:01:38 lr 0.003412	time 0.7337 (0.7495)	model_time 0.7335 (0.7421)	loss 4.1991 (3.5244)	grad_norm 1.1489 (1.2943/0.5207)	mem 34602MB
[2025-01-19 05:21:11 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][190/312]	eta 0:01:31 lr 0.003411	time 0.8048 (0.7494)	model_time 0.8047 (0.7424)	loss 4.1521 (3.5226)	grad_norm 1.5404 (1.3018/0.5168)	mem 34602MB
[2025-01-19 05:21:19 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][200/312]	eta 0:01:24 lr 0.003411	time 0.8299 (0.7508)	model_time 0.8295 (0.7442)	loss 3.6962 (3.5281)	grad_norm 1.3942 (1.3155/0.5252)	mem 34602MB
[2025-01-19 05:21:26 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][210/312]	eta 0:01:16 lr 0.003410	time 0.7164 (0.7505)	model_time 0.7162 (0.7442)	loss 3.8357 (3.5377)	grad_norm 0.9757 (1.3075/0.5158)	mem 34602MB
[2025-01-19 05:21:34 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][220/312]	eta 0:01:09 lr 0.003410	time 0.7995 (0.7514)	model_time 0.7991 (0.7453)	loss 3.4230 (3.5435)	grad_norm 1.0089 (1.3010/0.5088)	mem 34602MB
[2025-01-19 05:21:42 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][230/312]	eta 0:01:01 lr 0.003409	time 0.8109 (0.7514)	model_time 0.8108 (0.7455)	loss 3.4504 (3.5409)	grad_norm 0.8831 (1.2912/0.5028)	mem 34602MB
[2025-01-19 05:21:49 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][240/312]	eta 0:00:54 lr 0.003409	time 0.7522 (0.7513)	model_time 0.7520 (0.7457)	loss 2.5812 (3.5382)	grad_norm 1.5403 (1.2895/0.4950)	mem 34602MB
[2025-01-19 05:21:57 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][250/312]	eta 0:00:46 lr 0.003408	time 0.7304 (0.7509)	model_time 0.7300 (0.7455)	loss 2.8154 (3.5285)	grad_norm 1.2215 (1.2854/0.4902)	mem 34602MB
[2025-01-19 05:22:04 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][260/312]	eta 0:00:39 lr 0.003408	time 0.7137 (0.7501)	model_time 0.7135 (0.7449)	loss 2.7626 (3.5205)	grad_norm 3.0802 (1.2937/0.5031)	mem 34602MB
[2025-01-19 05:22:11 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][270/312]	eta 0:00:31 lr 0.003407	time 0.7147 (0.7493)	model_time 0.7143 (0.7442)	loss 3.0256 (3.5216)	grad_norm 1.4574 (1.3045/0.5153)	mem 34602MB
[2025-01-19 05:22:19 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][280/312]	eta 0:00:23 lr 0.003407	time 0.7333 (0.7487)	model_time 0.7331 (0.7439)	loss 3.0245 (3.5339)	grad_norm 0.9918 (1.2996/0.5149)	mem 34602MB
[2025-01-19 05:22:26 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][290/312]	eta 0:00:16 lr 0.003406	time 0.7208 (0.7481)	model_time 0.7207 (0.7434)	loss 4.2318 (3.5340)	grad_norm 0.7725 (1.2919/0.5104)	mem 34602MB
[2025-01-19 05:22:33 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][300/312]	eta 0:00:08 lr 0.003406	time 0.7137 (0.7474)	model_time 0.7136 (0.7428)	loss 3.5997 (3.5333)	grad_norm 1.3912 (1.2834/0.5031)	mem 34602MB
[2025-01-19 05:22:40 internimage_b_1k_224] (main.py 510): INFO Train: [75/300][310/312]	eta 0:00:01 lr 0.003405	time 0.7244 (0.7470)	model_time 0.7243 (0.7426)	loss 2.8445 (3.5284)	grad_norm 0.8206 (1.2679/0.4910)	mem 34602MB
[2025-01-19 05:22:41 internimage_b_1k_224] (main.py 519): INFO EPOCH 75 training takes 0:03:53
[2025-01-19 05:22:41 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_75.pth saving......
[2025-01-19 05:22:44 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_75.pth saved !!!
[2025-01-19 05:22:52 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.496 (7.496)	Loss 0.8935 (0.8935)	Acc@1 80.640 (80.640)	Acc@5 95.923 (95.923)	Mem 34602MB
[2025-01-19 05:22:55 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.947)	Loss 1.2928 (1.0605)	Acc@1 71.631 (76.614)	Acc@5 91.064 (93.774)	Mem 34602MB
[2025-01-19 05:22:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:75] * Acc@1 76.562 Acc@5 93.798
[2025-01-19 05:22:55 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.6%
[2025-01-19 05:22:55 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 77.04%
[2025-01-19 05:23:04 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.104 (9.104)	Loss 1.0472 (1.0472)	Acc@1 77.002 (77.002)	Acc@5 94.409 (94.409)	Mem 34602MB
[2025-01-19 05:23:09 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.232)	Loss 1.5136 (1.2194)	Acc@1 66.211 (73.358)	Acc@5 88.403 (91.819)	Mem 34602MB
[2025-01-19 05:23:09 internimage_b_1k_224] (main.py 575): INFO [Epoch:75] * Acc@1 73.438 Acc@5 91.943
[2025-01-19 05:23:09 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 73.4%
[2025-01-19 05:23:09 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:23:13 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:23:13 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 73.44%
[2025-01-19 05:23:15 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][0/312]	eta 0:11:17 lr 0.003405	time 2.1719 (2.1719)	model_time 0.7375 (0.7375)	loss 3.4903 (3.4903)	grad_norm 1.5422 (1.5422/0.0000)	mem 34602MB
[2025-01-19 05:23:23 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][10/312]	eta 0:04:35 lr 0.003405	time 0.7993 (0.9136)	model_time 0.7992 (0.7829)	loss 3.5518 (3.6148)	grad_norm 1.0249 (1.4833/0.6160)	mem 34602MB
[2025-01-19 05:23:30 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][20/312]	eta 0:04:02 lr 0.003404	time 0.7167 (0.8319)	model_time 0.7166 (0.7633)	loss 3.5910 (3.4888)	grad_norm 1.0783 (1.2613/0.5137)	mem 34602MB
[2025-01-19 05:23:38 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][30/312]	eta 0:03:49 lr 0.003404	time 0.7540 (0.8140)	model_time 0.7536 (0.7675)	loss 3.2021 (3.4557)	grad_norm 0.8687 (1.2611/0.5069)	mem 34602MB
[2025-01-19 05:23:45 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][40/312]	eta 0:03:37 lr 0.003403	time 0.7242 (0.8008)	model_time 0.7240 (0.7655)	loss 4.2888 (3.4629)	grad_norm 1.2236 (1.2936/0.5144)	mem 34602MB
[2025-01-19 05:23:53 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][50/312]	eta 0:03:26 lr 0.003403	time 0.7170 (0.7890)	model_time 0.7166 (0.7606)	loss 3.6864 (3.4510)	grad_norm 1.0031 (1.2754/0.4957)	mem 34602MB
[2025-01-19 05:24:00 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][60/312]	eta 0:03:16 lr 0.003402	time 0.7194 (0.7810)	model_time 0.7192 (0.7571)	loss 3.3920 (3.4625)	grad_norm 1.2234 (1.2651/0.4792)	mem 34602MB
[2025-01-19 05:24:08 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][70/312]	eta 0:03:07 lr 0.003402	time 0.7306 (0.7745)	model_time 0.7301 (0.7540)	loss 2.5792 (3.4644)	grad_norm 0.9978 (1.2366/0.4597)	mem 34602MB
[2025-01-19 05:24:15 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][80/312]	eta 0:02:58 lr 0.003402	time 0.7383 (0.7684)	model_time 0.7381 (0.7503)	loss 3.2388 (3.4370)	grad_norm 0.8076 (1.3460/0.6123)	mem 34602MB
[2025-01-19 05:24:22 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][90/312]	eta 0:02:49 lr 0.003401	time 0.7311 (0.7635)	model_time 0.7306 (0.7474)	loss 3.5449 (3.4399)	grad_norm 1.2045 (1.4260/0.6850)	mem 34602MB
[2025-01-19 05:24:30 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][100/312]	eta 0:02:41 lr 0.003401	time 0.8178 (0.7612)	model_time 0.8176 (0.7467)	loss 3.9258 (3.4437)	grad_norm 1.3693 (1.3980/0.6625)	mem 34602MB
[2025-01-19 05:24:37 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][110/312]	eta 0:02:33 lr 0.003400	time 0.7180 (0.7582)	model_time 0.7179 (0.7449)	loss 4.3573 (3.4371)	grad_norm 0.7718 (1.3704/0.6470)	mem 34602MB
[2025-01-19 05:24:44 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][120/312]	eta 0:02:25 lr 0.003400	time 0.7517 (0.7564)	model_time 0.7515 (0.7442)	loss 3.8619 (3.4559)	grad_norm 0.8462 (1.3506/0.6304)	mem 34602MB
[2025-01-19 05:24:52 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][130/312]	eta 0:02:17 lr 0.003399	time 0.7166 (0.7580)	model_time 0.7161 (0.7467)	loss 2.7611 (3.4592)	grad_norm 0.7315 (1.3302/0.6216)	mem 34602MB
[2025-01-19 05:24:59 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][140/312]	eta 0:02:10 lr 0.003399	time 0.7326 (0.7570)	model_time 0.7324 (0.7465)	loss 2.5697 (3.4476)	grad_norm 1.4361 (1.3209/0.6038)	mem 34602MB
[2025-01-19 05:25:07 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][150/312]	eta 0:02:02 lr 0.003398	time 0.7572 (0.7586)	model_time 0.7567 (0.7488)	loss 3.3029 (3.4627)	grad_norm 0.6728 (1.2957/0.5950)	mem 34602MB
[2025-01-19 05:25:15 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][160/312]	eta 0:01:55 lr 0.003398	time 0.7167 (0.7584)	model_time 0.7165 (0.7492)	loss 2.3663 (3.4808)	grad_norm 0.8607 (1.3074/0.5945)	mem 34602MB
[2025-01-19 05:25:22 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][170/312]	eta 0:01:47 lr 0.003397	time 0.7289 (0.7573)	model_time 0.7285 (0.7486)	loss 4.1468 (3.4763)	grad_norm 1.7485 (1.3156/0.5973)	mem 34602MB
[2025-01-19 05:25:29 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][180/312]	eta 0:01:39 lr 0.003397	time 0.7147 (0.7560)	model_time 0.7142 (0.7477)	loss 2.3635 (3.4838)	grad_norm 0.6737 (1.3099/0.5910)	mem 34602MB
[2025-01-19 05:25:37 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][190/312]	eta 0:01:32 lr 0.003396	time 0.7161 (0.7549)	model_time 0.7157 (0.7471)	loss 3.6462 (3.4840)	grad_norm 0.9785 (1.3130/0.5817)	mem 34602MB
[2025-01-19 05:25:44 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][200/312]	eta 0:01:24 lr 0.003396	time 0.7306 (0.7535)	model_time 0.7304 (0.7460)	loss 3.5812 (3.4769)	grad_norm 0.8095 (1.2928/0.5765)	mem 34602MB
[2025-01-19 05:25:51 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][210/312]	eta 0:01:16 lr 0.003395	time 0.7349 (0.7524)	model_time 0.7347 (0.7452)	loss 3.1802 (3.4858)	grad_norm 1.4978 (1.2872/0.5698)	mem 34602MB
[2025-01-19 05:25:59 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][220/312]	eta 0:01:09 lr 0.003395	time 0.7868 (0.7514)	model_time 0.7866 (0.7446)	loss 3.5238 (3.4924)	grad_norm 1.6611 (1.2946/0.5622)	mem 34602MB
[2025-01-19 05:26:06 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][230/312]	eta 0:01:01 lr 0.003394	time 0.7186 (0.7504)	model_time 0.7184 (0.7438)	loss 2.8157 (3.4906)	grad_norm 2.0107 (1.3073/0.5604)	mem 34602MB
[2025-01-19 05:26:13 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][240/312]	eta 0:00:54 lr 0.003394	time 0.7196 (0.7500)	model_time 0.7192 (0.7437)	loss 3.9727 (3.4925)	grad_norm 0.9311 (1.3120/0.5612)	mem 34602MB
[2025-01-19 05:26:21 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][250/312]	eta 0:00:46 lr 0.003393	time 0.8033 (0.7517)	model_time 0.8031 (0.7456)	loss 4.1075 (3.5001)	grad_norm 1.4075 (1.2992/0.5552)	mem 34602MB
[2025-01-19 05:26:29 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][260/312]	eta 0:00:39 lr 0.003393	time 0.7179 (0.7514)	model_time 0.7174 (0.7455)	loss 2.3387 (3.4967)	grad_norm 1.1205 (1.2936/0.5496)	mem 34602MB
[2025-01-19 05:26:36 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][270/312]	eta 0:00:31 lr 0.003392	time 0.8106 (0.7521)	model_time 0.8104 (0.7464)	loss 3.8492 (3.5040)	grad_norm 0.6749 (1.2895/0.5461)	mem 34602MB
[2025-01-19 05:26:44 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][280/312]	eta 0:00:24 lr 0.003392	time 0.7153 (0.7528)	model_time 0.7151 (0.7473)	loss 4.1885 (3.5027)	grad_norm 1.4863 (1.2933/0.5458)	mem 34602MB
[2025-01-19 05:26:52 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][290/312]	eta 0:00:16 lr 0.003391	time 0.7161 (0.7521)	model_time 0.7160 (0.7468)	loss 3.7109 (3.5004)	grad_norm 0.6780 (1.3024/0.5506)	mem 34602MB
[2025-01-19 05:26:59 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][300/312]	eta 0:00:09 lr 0.003391	time 0.7122 (0.7514)	model_time 0.7121 (0.7463)	loss 3.6128 (3.5075)	grad_norm 0.9173 (1.2898/0.5473)	mem 34602MB
[2025-01-19 05:27:06 internimage_b_1k_224] (main.py 510): INFO Train: [76/300][310/312]	eta 0:00:01 lr 0.003391	time 0.7123 (0.7504)	model_time 0.7122 (0.7455)	loss 3.6642 (3.5006)	grad_norm 1.2038 (1.2742/0.5384)	mem 34602MB
[2025-01-19 05:27:07 internimage_b_1k_224] (main.py 519): INFO EPOCH 76 training takes 0:03:54
[2025-01-19 05:27:07 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_76.pth saving......
[2025-01-19 05:27:10 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_76.pth saved !!!
[2025-01-19 05:27:17 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.336 (7.336)	Loss 0.9162 (0.9162)	Acc@1 80.884 (80.884)	Acc@5 95.947 (95.947)	Mem 34602MB
[2025-01-19 05:27:20 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.929)	Loss 1.2907 (1.0702)	Acc@1 72.046 (77.390)	Acc@5 91.772 (93.883)	Mem 34602MB
[2025-01-19 05:27:20 internimage_b_1k_224] (main.py 575): INFO [Epoch:76] * Acc@1 77.355 Acc@5 93.956
[2025-01-19 05:27:20 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.4%
[2025-01-19 05:27:20 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 05:27:24 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 05:27:24 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 77.36%
[2025-01-19 05:27:31 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.452 (7.452)	Loss 1.0250 (1.0250)	Acc@1 77.441 (77.441)	Acc@5 94.482 (94.482)	Mem 34602MB
[2025-01-19 05:27:34 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.955)	Loss 1.4893 (1.1980)	Acc@1 66.699 (73.728)	Acc@5 88.599 (91.979)	Mem 34602MB
[2025-01-19 05:27:34 internimage_b_1k_224] (main.py 575): INFO [Epoch:76] * Acc@1 73.792 Acc@5 92.105
[2025-01-19 05:27:34 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 73.8%
[2025-01-19 05:27:34 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:27:38 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:27:38 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 73.79%
[2025-01-19 05:27:40 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][0/312]	eta 0:10:39 lr 0.003390	time 2.0511 (2.0511)	model_time 0.7402 (0.7402)	loss 4.2450 (4.2450)	grad_norm 1.8181 (1.8181/0.0000)	mem 34602MB
[2025-01-19 05:27:48 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][10/312]	eta 0:04:19 lr 0.003390	time 0.7268 (0.8590)	model_time 0.7266 (0.7395)	loss 3.4052 (3.2418)	grad_norm 0.8688 (1.4663/0.3960)	mem 34602MB
[2025-01-19 05:27:55 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][20/312]	eta 0:03:53 lr 0.003389	time 0.7187 (0.7981)	model_time 0.7185 (0.7353)	loss 3.8274 (3.4234)	grad_norm 2.4817 (1.6706/0.5497)	mem 34602MB
[2025-01-19 05:28:02 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][30/312]	eta 0:03:39 lr 0.003389	time 0.7241 (0.7779)	model_time 0.7236 (0.7353)	loss 3.9344 (3.4792)	grad_norm 1.3543 (1.5720/0.5290)	mem 34602MB
[2025-01-19 05:28:10 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][40/312]	eta 0:03:28 lr 0.003389	time 0.7276 (0.7658)	model_time 0.7274 (0.7335)	loss 3.0380 (3.4307)	grad_norm 0.6985 (1.5553/0.6105)	mem 34602MB
[2025-01-19 05:28:17 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][50/312]	eta 0:03:19 lr 0.003388	time 0.7241 (0.7623)	model_time 0.7237 (0.7362)	loss 4.0196 (3.4340)	grad_norm 1.2139 (1.5161/0.5926)	mem 34602MB
[2025-01-19 05:28:25 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][60/312]	eta 0:03:13 lr 0.003388	time 0.7584 (0.7664)	model_time 0.7581 (0.7446)	loss 3.1547 (3.4437)	grad_norm 1.2042 (1.4529/0.5725)	mem 34602MB
[2025-01-19 05:28:32 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][70/312]	eta 0:03:04 lr 0.003387	time 0.7209 (0.7627)	model_time 0.7208 (0.7439)	loss 4.2644 (3.4989)	grad_norm 0.7837 (1.4084/0.5697)	mem 34602MB
[2025-01-19 05:28:40 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][80/312]	eta 0:02:57 lr 0.003387	time 0.8152 (0.7640)	model_time 0.8150 (0.7474)	loss 3.1986 (3.4965)	grad_norm 0.7650 (1.3566/0.5594)	mem 34602MB
[2025-01-19 05:28:48 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][90/312]	eta 0:02:49 lr 0.003386	time 0.7134 (0.7623)	model_time 0.7133 (0.7475)	loss 4.2887 (3.5014)	grad_norm 1.0756 (1.3082/0.5483)	mem 34602MB
[2025-01-19 05:28:55 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][100/312]	eta 0:02:41 lr 0.003386	time 0.8112 (0.7606)	model_time 0.8110 (0.7473)	loss 3.4646 (3.4752)	grad_norm 0.8442 (1.2869/0.5292)	mem 34602MB
[2025-01-19 05:29:02 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][110/312]	eta 0:02:33 lr 0.003385	time 0.7336 (0.7580)	model_time 0.7334 (0.7459)	loss 4.3799 (3.4830)	grad_norm 2.6860 (1.3108/0.5749)	mem 34602MB
[2025-01-19 05:29:10 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][120/312]	eta 0:02:25 lr 0.003385	time 0.7353 (0.7553)	model_time 0.7348 (0.7441)	loss 2.5077 (3.5023)	grad_norm 0.7921 (1.3007/0.5604)	mem 34602MB
[2025-01-19 05:29:17 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][130/312]	eta 0:02:17 lr 0.003384	time 0.7388 (0.7545)	model_time 0.7386 (0.7442)	loss 2.5604 (3.4982)	grad_norm 0.7226 (1.2781/0.5490)	mem 34602MB
[2025-01-19 05:29:24 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][140/312]	eta 0:02:09 lr 0.003384	time 0.7382 (0.7526)	model_time 0.7380 (0.7430)	loss 4.5173 (3.5283)	grad_norm 0.9800 (1.2584/0.5383)	mem 34602MB
[2025-01-19 05:29:32 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][150/312]	eta 0:02:01 lr 0.003383	time 0.7314 (0.7513)	model_time 0.7310 (0.7422)	loss 2.8872 (3.5111)	grad_norm 3.3510 (1.2837/0.5657)	mem 34602MB
[2025-01-19 05:29:39 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][160/312]	eta 0:01:54 lr 0.003383	time 0.7204 (0.7502)	model_time 0.7199 (0.7417)	loss 3.9873 (3.5219)	grad_norm 0.9400 (1.3024/0.5816)	mem 34602MB
[2025-01-19 05:29:46 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][170/312]	eta 0:01:46 lr 0.003382	time 0.7168 (0.7492)	model_time 0.7163 (0.7412)	loss 3.6280 (3.5227)	grad_norm 1.7385 (1.2911/0.5708)	mem 34602MB
[2025-01-19 05:29:54 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][180/312]	eta 0:01:39 lr 0.003382	time 0.7282 (0.7505)	model_time 0.7280 (0.7428)	loss 4.0582 (3.5243)	grad_norm 1.3382 (1.2934/0.5584)	mem 34602MB
[2025-01-19 05:30:02 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][190/312]	eta 0:01:31 lr 0.003381	time 0.7198 (0.7502)	model_time 0.7196 (0.7430)	loss 2.7278 (3.5236)	grad_norm 0.7407 (1.3061/0.5742)	mem 34602MB
[2025-01-19 05:30:09 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][200/312]	eta 0:01:24 lr 0.003381	time 0.8109 (0.7511)	model_time 0.8104 (0.7442)	loss 3.5278 (3.5217)	grad_norm 1.3138 (1.2994/0.5686)	mem 34602MB
[2025-01-19 05:30:17 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][210/312]	eta 0:01:16 lr 0.003380	time 0.8028 (0.7509)	model_time 0.8026 (0.7443)	loss 3.7973 (3.5089)	grad_norm 1.9962 (1.2978/0.5623)	mem 34602MB
[2025-01-19 05:30:24 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][220/312]	eta 0:01:09 lr 0.003380	time 0.8253 (0.7508)	model_time 0.8248 (0.7445)	loss 3.7623 (3.5104)	grad_norm 0.7686 (1.2991/0.5606)	mem 34602MB
[2025-01-19 05:30:32 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][230/312]	eta 0:01:01 lr 0.003379	time 0.7174 (0.7502)	model_time 0.7169 (0.7441)	loss 3.3286 (3.5086)	grad_norm 0.9847 (1.2892/0.5533)	mem 34602MB
[2025-01-19 05:30:39 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][240/312]	eta 0:00:53 lr 0.003379	time 0.7068 (0.7490)	model_time 0.7063 (0.7432)	loss 3.7962 (3.5185)	grad_norm 0.9277 (1.3001/0.5629)	mem 34602MB
[2025-01-19 05:30:46 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][250/312]	eta 0:00:46 lr 0.003378	time 0.7485 (0.7488)	model_time 0.7481 (0.7432)	loss 3.5849 (3.5186)	grad_norm 1.3620 (1.3037/0.5621)	mem 34602MB
[2025-01-19 05:30:53 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][260/312]	eta 0:00:38 lr 0.003378	time 0.7186 (0.7478)	model_time 0.7181 (0.7424)	loss 3.0915 (3.5149)	grad_norm 1.4390 (1.3182/0.5702)	mem 34602MB
[2025-01-19 05:31:01 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][270/312]	eta 0:00:31 lr 0.003377	time 0.7401 (0.7473)	model_time 0.7399 (0.7421)	loss 3.6781 (3.5142)	grad_norm 2.0238 (1.3130/0.5647)	mem 34602MB
[2025-01-19 05:31:08 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][280/312]	eta 0:00:23 lr 0.003377	time 0.7456 (0.7467)	model_time 0.7455 (0.7416)	loss 3.8558 (3.5226)	grad_norm 0.8544 (1.3031/0.5592)	mem 34602MB
[2025-01-19 05:31:15 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][290/312]	eta 0:00:16 lr 0.003376	time 0.7212 (0.7462)	model_time 0.7207 (0.7413)	loss 3.6898 (3.5268)	grad_norm 1.6472 (1.3046/0.5575)	mem 34602MB
[2025-01-19 05:31:23 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][300/312]	eta 0:00:08 lr 0.003376	time 0.7129 (0.7464)	model_time 0.7128 (0.7417)	loss 3.6493 (3.5288)	grad_norm 1.3781 (1.2974/0.5516)	mem 34602MB
[2025-01-19 05:31:30 internimage_b_1k_224] (main.py 510): INFO Train: [77/300][310/312]	eta 0:00:01 lr 0.003376	time 0.7774 (0.7463)	model_time 0.7773 (0.7417)	loss 2.7513 (3.5245)	grad_norm 2.1815 (1.3011/0.5615)	mem 34602MB
[2025-01-19 05:31:31 internimage_b_1k_224] (main.py 519): INFO EPOCH 77 training takes 0:03:52
[2025-01-19 05:31:31 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_77.pth saving......
[2025-01-19 05:31:34 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_77.pth saved !!!
[2025-01-19 05:31:42 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.573 (7.573)	Loss 0.8497 (0.8497)	Acc@1 81.787 (81.787)	Acc@5 96.240 (96.240)	Mem 34602MB
[2025-01-19 05:31:45 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.953)	Loss 1.2692 (1.0413)	Acc@1 70.947 (77.066)	Acc@5 91.724 (94.067)	Mem 34602MB
[2025-01-19 05:31:45 internimage_b_1k_224] (main.py 575): INFO [Epoch:77] * Acc@1 77.019 Acc@5 94.100
[2025-01-19 05:31:45 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.0%
[2025-01-19 05:31:45 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 77.36%
[2025-01-19 05:31:54 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.004 (9.004)	Loss 1.0043 (1.0043)	Acc@1 77.808 (77.808)	Acc@5 94.604 (94.604)	Mem 34602MB
[2025-01-19 05:32:03 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (1.624)	Loss 1.4657 (1.1776)	Acc@1 67.041 (74.072)	Acc@5 88.892 (92.110)	Mem 34602MB
[2025-01-19 05:32:03 internimage_b_1k_224] (main.py 575): INFO [Epoch:77] * Acc@1 74.126 Acc@5 92.228
[2025-01-19 05:32:03 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 74.1%
[2025-01-19 05:32:03 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:32:07 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:32:07 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 74.13%
[2025-01-19 05:32:09 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][0/312]	eta 0:12:39 lr 0.003375	time 2.4359 (2.4359)	model_time 0.7694 (0.7694)	loss 2.3614 (2.3614)	grad_norm 2.7330 (2.7330/0.0000)	mem 34602MB
[2025-01-19 05:32:17 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][10/312]	eta 0:04:39 lr 0.003375	time 0.7963 (0.9262)	model_time 0.7961 (0.7745)	loss 3.8535 (3.5212)	grad_norm 1.3949 (1.5005/0.7308)	mem 34602MB
[2025-01-19 05:32:25 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][20/312]	eta 0:04:05 lr 0.003374	time 0.8047 (0.8412)	model_time 0.8045 (0.7615)	loss 3.3096 (3.3609)	grad_norm 1.3113 (1.3300/0.6399)	mem 34602MB
[2025-01-19 05:32:32 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][30/312]	eta 0:03:48 lr 0.003374	time 0.7164 (0.8087)	model_time 0.7160 (0.7546)	loss 2.5122 (3.3979)	grad_norm 1.5541 (1.2460/0.5681)	mem 34602MB
[2025-01-19 05:32:39 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][40/312]	eta 0:03:34 lr 0.003373	time 0.7196 (0.7901)	model_time 0.7195 (0.7491)	loss 3.3948 (3.4339)	grad_norm 1.1413 (1.3364/0.5984)	mem 34602MB
[2025-01-19 05:32:47 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][50/312]	eta 0:03:23 lr 0.003373	time 0.7329 (0.7784)	model_time 0.7327 (0.7454)	loss 2.8981 (3.3728)	grad_norm 1.8671 (1.3471/0.5579)	mem 34602MB
[2025-01-19 05:32:54 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][60/312]	eta 0:03:14 lr 0.003372	time 0.7383 (0.7706)	model_time 0.7382 (0.7430)	loss 3.9493 (3.4211)	grad_norm 2.0714 (1.3398/0.5568)	mem 34602MB
[2025-01-19 05:33:01 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][70/312]	eta 0:03:05 lr 0.003372	time 0.7215 (0.7650)	model_time 0.7211 (0.7411)	loss 4.0694 (3.4374)	grad_norm 1.4181 (1.3725/0.5749)	mem 34602MB
[2025-01-19 05:33:09 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][80/312]	eta 0:02:56 lr 0.003372	time 0.7187 (0.7610)	model_time 0.7185 (0.7400)	loss 2.4639 (3.4556)	grad_norm 0.6665 (1.3633/0.5604)	mem 34602MB
[2025-01-19 05:33:16 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][90/312]	eta 0:02:48 lr 0.003371	time 0.7296 (0.7568)	model_time 0.7294 (0.7382)	loss 4.1723 (3.4450)	grad_norm 1.0002 (1.3229/0.5492)	mem 34602MB
[2025-01-19 05:33:23 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][100/312]	eta 0:02:40 lr 0.003371	time 0.7149 (0.7564)	model_time 0.7148 (0.7395)	loss 2.3047 (3.4339)	grad_norm 1.5236 (1.3108/0.5323)	mem 34602MB
[2025-01-19 05:33:31 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][110/312]	eta 0:02:32 lr 0.003370	time 0.7287 (0.7566)	model_time 0.7285 (0.7413)	loss 3.4557 (3.4165)	grad_norm 1.1201 (1.3224/0.5423)	mem 34602MB
[2025-01-19 05:33:39 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][120/312]	eta 0:02:25 lr 0.003370	time 0.7224 (0.7563)	model_time 0.7220 (0.7421)	loss 4.2883 (3.3997)	grad_norm 0.8865 (1.3399/0.5500)	mem 34602MB
[2025-01-19 05:33:46 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][130/312]	eta 0:02:17 lr 0.003369	time 0.7921 (0.7569)	model_time 0.7920 (0.7438)	loss 3.7513 (3.4036)	grad_norm 1.1014 (1.3381/0.5502)	mem 34602MB
[2025-01-19 05:33:54 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][140/312]	eta 0:02:10 lr 0.003369	time 0.8043 (0.7573)	model_time 0.8037 (0.7452)	loss 4.4096 (3.4248)	grad_norm 0.7295 (1.3302/0.5447)	mem 34602MB
[2025-01-19 05:34:01 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][150/312]	eta 0:02:02 lr 0.003368	time 0.7426 (0.7569)	model_time 0.7424 (0.7455)	loss 2.7719 (3.4221)	grad_norm 1.1915 (1.3461/0.5535)	mem 34602MB
[2025-01-19 05:34:09 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][160/312]	eta 0:01:54 lr 0.003368	time 0.7153 (0.7554)	model_time 0.7151 (0.7447)	loss 2.2771 (3.4312)	grad_norm 1.9594 (1.3500/0.5497)	mem 34602MB
[2025-01-19 05:34:16 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][170/312]	eta 0:01:47 lr 0.003367	time 0.7301 (0.7536)	model_time 0.7296 (0.7435)	loss 3.8033 (3.4386)	grad_norm 0.9442 (1.3415/0.5441)	mem 34602MB
[2025-01-19 05:34:23 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][180/312]	eta 0:01:39 lr 0.003367	time 0.7230 (0.7522)	model_time 0.7228 (0.7427)	loss 3.8226 (3.4412)	grad_norm 1.0412 (1.3377/0.5386)	mem 34602MB
[2025-01-19 05:34:30 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][190/312]	eta 0:01:31 lr 0.003366	time 0.7155 (0.7509)	model_time 0.7148 (0.7418)	loss 3.6476 (3.4405)	grad_norm 0.7364 (1.3191/0.5341)	mem 34602MB
[2025-01-19 05:34:38 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][200/312]	eta 0:01:24 lr 0.003366	time 0.7405 (0.7501)	model_time 0.7401 (0.7414)	loss 4.3898 (3.4529)	grad_norm 1.5276 (1.3177/0.5286)	mem 34602MB
[2025-01-19 05:34:45 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][210/312]	eta 0:01:16 lr 0.003365	time 0.7209 (0.7489)	model_time 0.7208 (0.7407)	loss 3.7701 (3.4612)	grad_norm 1.6192 (1.3357/0.5466)	mem 34602MB
[2025-01-19 05:34:53 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][220/312]	eta 0:01:08 lr 0.003365	time 0.7535 (0.7488)	model_time 0.7532 (0.7410)	loss 4.1090 (3.4637)	grad_norm 1.5846 (1.3432/0.5459)	mem 34602MB
[2025-01-19 05:35:00 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][230/312]	eta 0:01:01 lr 0.003364	time 0.7151 (0.7491)	model_time 0.7146 (0.7415)	loss 3.6287 (3.4598)	grad_norm 2.1440 (1.3498/0.5600)	mem 34602MB
[2025-01-19 05:35:08 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][240/312]	eta 0:00:53 lr 0.003364	time 0.7631 (0.7491)	model_time 0.7629 (0.7419)	loss 3.8407 (3.4697)	grad_norm 1.7542 (1.3602/0.5688)	mem 34602MB
[2025-01-19 05:35:15 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][250/312]	eta 0:00:46 lr 0.003363	time 0.8000 (0.7496)	model_time 0.7999 (0.7426)	loss 2.6905 (3.4681)	grad_norm 0.8976 (1.3479/0.5645)	mem 34602MB
[2025-01-19 05:35:23 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][260/312]	eta 0:00:38 lr 0.003363	time 0.7211 (0.7499)	model_time 0.7206 (0.7431)	loss 3.8489 (3.4758)	grad_norm 0.9580 (1.3406/0.5578)	mem 34602MB
[2025-01-19 05:35:30 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][270/312]	eta 0:00:31 lr 0.003362	time 0.7465 (0.7498)	model_time 0.7463 (0.7433)	loss 2.6213 (3.4727)	grad_norm 0.8415 (1.3345/0.5550)	mem 34602MB
[2025-01-19 05:35:38 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][280/312]	eta 0:00:23 lr 0.003362	time 0.7184 (0.7494)	model_time 0.7182 (0.7431)	loss 3.6806 (3.4675)	grad_norm 1.5019 (1.3245/0.5500)	mem 34602MB
[2025-01-19 05:35:45 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][290/312]	eta 0:00:16 lr 0.003361	time 0.7235 (0.7485)	model_time 0.7233 (0.7424)	loss 3.7652 (3.4801)	grad_norm 0.7485 (1.3340/0.5713)	mem 34602MB
[2025-01-19 05:35:52 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][300/312]	eta 0:00:08 lr 0.003361	time 0.7044 (0.7475)	model_time 0.7042 (0.7416)	loss 3.2755 (3.4809)	grad_norm 0.9032 (1.3192/0.5606)	mem 34602MB
[2025-01-19 05:35:59 internimage_b_1k_224] (main.py 510): INFO Train: [78/300][310/312]	eta 0:00:01 lr 0.003360	time 0.7116 (0.7466)	model_time 0.7115 (0.7409)	loss 3.4336 (3.4812)	grad_norm 1.5775 (1.3189/0.5539)	mem 34602MB
[2025-01-19 05:36:00 internimage_b_1k_224] (main.py 519): INFO EPOCH 78 training takes 0:03:52
[2025-01-19 05:36:00 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_78.pth saving......
[2025-01-19 05:36:03 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_78.pth saved !!!
[2025-01-19 05:36:14 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 10.806 (10.806)	Loss 0.9334 (0.9334)	Acc@1 80.542 (80.542)	Acc@5 96.191 (96.191)	Mem 34602MB
[2025-01-19 05:36:18 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.309)	Loss 1.2956 (1.0974)	Acc@1 71.655 (76.953)	Acc@5 91.797 (94.019)	Mem 34602MB
[2025-01-19 05:36:18 internimage_b_1k_224] (main.py 575): INFO [Epoch:78] * Acc@1 76.923 Acc@5 94.092
[2025-01-19 05:36:18 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.9%
[2025-01-19 05:36:18 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 77.36%
[2025-01-19 05:36:27 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.117 (9.117)	Loss 0.9860 (0.9860)	Acc@1 77.930 (77.930)	Acc@5 94.653 (94.653)	Mem 34602MB
[2025-01-19 05:36:31 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.239)	Loss 1.4433 (1.1586)	Acc@1 67.432 (74.367)	Acc@5 89.185 (92.259)	Mem 34602MB
[2025-01-19 05:36:32 internimage_b_1k_224] (main.py 575): INFO [Epoch:78] * Acc@1 74.402 Acc@5 92.370
[2025-01-19 05:36:32 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 74.4%
[2025-01-19 05:36:32 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:36:35 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:36:35 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 74.40%
[2025-01-19 05:36:38 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][0/312]	eta 0:11:04 lr 0.003360	time 2.1305 (2.1305)	model_time 0.7561 (0.7561)	loss 3.2429 (3.2429)	grad_norm 1.4419 (1.4419/0.0000)	mem 34602MB
[2025-01-19 05:36:45 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][10/312]	eta 0:04:19 lr 0.003360	time 0.7275 (0.8583)	model_time 0.7274 (0.7330)	loss 4.1701 (3.6761)	grad_norm 0.9928 (1.3615/0.4318)	mem 34602MB
[2025-01-19 05:36:52 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][20/312]	eta 0:03:52 lr 0.003359	time 0.7585 (0.7975)	model_time 0.7584 (0.7317)	loss 2.5788 (3.6093)	grad_norm 1.0239 (1.2449/0.4301)	mem 34602MB
[2025-01-19 05:37:00 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][30/312]	eta 0:03:40 lr 0.003359	time 0.8127 (0.7805)	model_time 0.8123 (0.7359)	loss 4.1591 (3.5523)	grad_norm 2.5017 (1.3294/0.5082)	mem 34602MB
[2025-01-19 05:37:07 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][40/312]	eta 0:03:31 lr 0.003358	time 0.7247 (0.7761)	model_time 0.7246 (0.7423)	loss 3.3573 (3.5477)	grad_norm 1.2289 (1.4147/0.5838)	mem 34602MB
[2025-01-19 05:37:15 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][50/312]	eta 0:03:21 lr 0.003358	time 0.7216 (0.7700)	model_time 0.7215 (0.7427)	loss 4.4041 (3.5492)	grad_norm 1.3649 (1.3848/0.5409)	mem 34602MB
[2025-01-19 05:37:22 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][60/312]	eta 0:03:14 lr 0.003357	time 0.8303 (0.7705)	model_time 0.8298 (0.7477)	loss 2.6868 (3.5326)	grad_norm 2.6120 (1.4040/0.5536)	mem 34602MB
[2025-01-19 05:37:30 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][70/312]	eta 0:03:05 lr 0.003357	time 0.7170 (0.7675)	model_time 0.7169 (0.7478)	loss 4.0129 (3.5446)	grad_norm 1.0282 (1.3934/0.5384)	mem 34602MB
[2025-01-19 05:37:37 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][80/312]	eta 0:02:57 lr 0.003356	time 0.7291 (0.7655)	model_time 0.7286 (0.7482)	loss 3.6280 (3.5383)	grad_norm 0.8270 (1.3916/0.5242)	mem 34602MB
[2025-01-19 05:37:45 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][90/312]	eta 0:02:49 lr 0.003356	time 0.7223 (0.7619)	model_time 0.7222 (0.7465)	loss 3.6245 (3.5903)	grad_norm 1.7961 (1.4150/0.5372)	mem 34602MB
[2025-01-19 05:37:52 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][100/312]	eta 0:02:40 lr 0.003355	time 0.7161 (0.7580)	model_time 0.7159 (0.7441)	loss 3.6639 (3.6157)	grad_norm 0.8143 (1.3725/0.5299)	mem 34602MB
[2025-01-19 05:37:59 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][110/312]	eta 0:02:32 lr 0.003355	time 0.7144 (0.7548)	model_time 0.7142 (0.7421)	loss 4.1356 (3.6150)	grad_norm 0.8057 (1.3431/0.5258)	mem 34602MB
[2025-01-19 05:38:07 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][120/312]	eta 0:02:24 lr 0.003354	time 0.7280 (0.7525)	model_time 0.7279 (0.7408)	loss 3.0042 (3.6071)	grad_norm 1.1986 (1.3512/0.5312)	mem 34602MB
[2025-01-19 05:38:14 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][130/312]	eta 0:02:16 lr 0.003354	time 0.7264 (0.7511)	model_time 0.7263 (0.7403)	loss 4.4445 (3.6205)	grad_norm 0.9147 (1.3341/0.5230)	mem 34602MB
[2025-01-19 05:38:21 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][140/312]	eta 0:02:08 lr 0.003353	time 0.7259 (0.7492)	model_time 0.7258 (0.7391)	loss 3.0490 (3.5635)	grad_norm 0.9604 (1.3008/0.5221)	mem 34602MB
[2025-01-19 05:38:29 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][150/312]	eta 0:02:01 lr 0.003353	time 0.8135 (0.7486)	model_time 0.8133 (0.7391)	loss 2.3632 (3.5579)	grad_norm 1.4553 (1.3031/0.5126)	mem 34602MB
[2025-01-19 05:38:36 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][160/312]	eta 0:01:53 lr 0.003352	time 0.7215 (0.7496)	model_time 0.7210 (0.7407)	loss 2.2752 (3.5452)	grad_norm 1.1127 (1.3132/0.5219)	mem 34602MB
[2025-01-19 05:38:44 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][170/312]	eta 0:01:46 lr 0.003352	time 0.7158 (0.7496)	model_time 0.7157 (0.7412)	loss 3.7106 (3.5474)	grad_norm 0.6884 (1.3087/0.5159)	mem 34602MB
[2025-01-19 05:38:51 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][180/312]	eta 0:01:39 lr 0.003351	time 0.8062 (0.7509)	model_time 0.8061 (0.7429)	loss 3.0208 (3.5379)	grad_norm 0.9408 (1.3068/0.5113)	mem 34602MB
[2025-01-19 05:38:59 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][190/312]	eta 0:01:31 lr 0.003351	time 0.7164 (0.7510)	model_time 0.7159 (0.7435)	loss 3.5909 (3.5335)	grad_norm 3.7092 (1.3292/0.5556)	mem 34602MB
[2025-01-19 05:39:06 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][200/312]	eta 0:01:24 lr 0.003350	time 0.7328 (0.7509)	model_time 0.7324 (0.7437)	loss 3.6150 (3.5299)	grad_norm 1.5551 (1.3291/0.5591)	mem 34602MB
[2025-01-19 05:39:14 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][210/312]	eta 0:01:16 lr 0.003350	time 0.7284 (0.7495)	model_time 0.7282 (0.7427)	loss 3.3714 (3.5336)	grad_norm 1.3144 (1.3225/0.5497)	mem 34602MB
[2025-01-19 05:39:21 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][220/312]	eta 0:01:08 lr 0.003349	time 0.7163 (0.7487)	model_time 0.7161 (0.7421)	loss 4.2486 (3.5413)	grad_norm 0.6923 (1.3072/0.5456)	mem 34602MB
[2025-01-19 05:39:28 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][230/312]	eta 0:01:01 lr 0.003349	time 0.7245 (0.7476)	model_time 0.7241 (0.7413)	loss 2.9584 (3.5386)	grad_norm 1.0184 (1.2932/0.5393)	mem 34602MB
[2025-01-19 05:39:35 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][240/312]	eta 0:00:53 lr 0.003348	time 0.7171 (0.7467)	model_time 0.7167 (0.7407)	loss 3.7802 (3.5451)	grad_norm 0.8715 (1.2928/0.5306)	mem 34602MB
[2025-01-19 05:39:43 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][250/312]	eta 0:00:46 lr 0.003348	time 0.7177 (0.7462)	model_time 0.7176 (0.7404)	loss 3.8978 (3.5345)	grad_norm 1.2936 (1.2996/0.5395)	mem 34602MB
[2025-01-19 05:39:50 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][260/312]	eta 0:00:38 lr 0.003347	time 0.7240 (0.7453)	model_time 0.7234 (0.7397)	loss 3.4159 (3.5287)	grad_norm 1.3185 (1.3072/0.5372)	mem 34602MB
[2025-01-19 05:39:57 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][270/312]	eta 0:00:31 lr 0.003347	time 0.8453 (0.7454)	model_time 0.8451 (0.7400)	loss 3.2999 (3.5186)	grad_norm 0.7748 (1.2997/0.5313)	mem 34602MB
[2025-01-19 05:40:05 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][280/312]	eta 0:00:23 lr 0.003346	time 0.7164 (0.7458)	model_time 0.7160 (0.7406)	loss 3.7951 (3.5204)	grad_norm 1.1809 (1.2872/0.5281)	mem 34602MB
[2025-01-19 05:40:13 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][290/312]	eta 0:00:16 lr 0.003346	time 0.7248 (0.7459)	model_time 0.7246 (0.7408)	loss 2.3192 (3.5134)	grad_norm 2.2145 (1.2864/0.5243)	mem 34602MB
[2025-01-19 05:40:20 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][300/312]	eta 0:00:08 lr 0.003345	time 0.7885 (0.7466)	model_time 0.7884 (0.7416)	loss 2.9267 (3.5141)	grad_norm 1.4915 (1.2841/0.5238)	mem 34602MB
[2025-01-19 05:40:27 internimage_b_1k_224] (main.py 510): INFO Train: [79/300][310/312]	eta 0:00:01 lr 0.003345	time 0.7150 (0.7458)	model_time 0.7149 (0.7411)	loss 3.7577 (3.5228)	grad_norm 0.9150 (1.2831/0.5212)	mem 34602MB
[2025-01-19 05:40:28 internimage_b_1k_224] (main.py 519): INFO EPOCH 79 training takes 0:03:52
[2025-01-19 05:40:28 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_79.pth saving......
[2025-01-19 05:40:31 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_79.pth saved !!!
[2025-01-19 05:40:39 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.530 (7.530)	Loss 0.8997 (0.8997)	Acc@1 81.396 (81.396)	Acc@5 95.825 (95.825)	Mem 34602MB
[2025-01-19 05:40:42 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.951)	Loss 1.2617 (1.0768)	Acc@1 72.949 (77.395)	Acc@5 91.895 (93.950)	Mem 34602MB
[2025-01-19 05:40:42 internimage_b_1k_224] (main.py 575): INFO [Epoch:79] * Acc@1 77.275 Acc@5 93.988
[2025-01-19 05:40:42 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.3%
[2025-01-19 05:40:42 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 77.36%
[2025-01-19 05:40:51 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.193 (9.193)	Loss 0.9682 (0.9682)	Acc@1 78.345 (78.345)	Acc@5 94.800 (94.800)	Mem 34602MB
[2025-01-19 05:40:56 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.240)	Loss 1.4222 (1.1405)	Acc@1 67.505 (74.603)	Acc@5 89.355 (92.394)	Mem 34602MB
[2025-01-19 05:40:56 internimage_b_1k_224] (main.py 575): INFO [Epoch:79] * Acc@1 74.630 Acc@5 92.506
[2025-01-19 05:40:56 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 74.6%
[2025-01-19 05:40:56 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:41:00 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:41:00 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 74.63%
[2025-01-19 05:41:02 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][0/312]	eta 0:10:24 lr 0.003345	time 2.0020 (2.0020)	model_time 0.7501 (0.7501)	loss 3.8077 (3.8077)	grad_norm 1.0011 (1.0011/0.0000)	mem 34602MB
[2025-01-19 05:41:09 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][10/312]	eta 0:04:22 lr 0.003344	time 0.7176 (0.8682)	model_time 0.7174 (0.7541)	loss 4.2766 (3.4912)	grad_norm 1.0108 (0.9320/0.2064)	mem 34602MB
[2025-01-19 05:41:17 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][20/312]	eta 0:03:54 lr 0.003344	time 0.7172 (0.8020)	model_time 0.7167 (0.7420)	loss 3.2311 (3.6060)	grad_norm 1.3946 (0.9443/0.2169)	mem 34602MB
[2025-01-19 05:41:24 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][30/312]	eta 0:03:40 lr 0.003343	time 0.7214 (0.7834)	model_time 0.7212 (0.7426)	loss 3.3299 (3.4842)	grad_norm 1.3542 (1.2771/0.8493)	mem 34602MB
[2025-01-19 05:41:31 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][40/312]	eta 0:03:29 lr 0.003343	time 0.7246 (0.7688)	model_time 0.7244 (0.7380)	loss 3.5950 (3.5105)	grad_norm 1.3292 (1.2628/0.7620)	mem 34602MB
[2025-01-19 05:41:39 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][50/312]	eta 0:03:19 lr 0.003342	time 0.7203 (0.7607)	model_time 0.7199 (0.7358)	loss 3.9871 (3.5046)	grad_norm 0.9135 (1.2276/0.6961)	mem 34602MB
[2025-01-19 05:41:46 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][60/312]	eta 0:03:10 lr 0.003342	time 0.7181 (0.7564)	model_time 0.7180 (0.7355)	loss 3.1419 (3.4843)	grad_norm 1.2519 (1.2008/0.6450)	mem 34602MB
[2025-01-19 05:41:53 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][70/312]	eta 0:03:01 lr 0.003341	time 0.7281 (0.7518)	model_time 0.7279 (0.7338)	loss 2.9539 (3.5020)	grad_norm 1.0517 (1.1630/0.6092)	mem 34602MB
[2025-01-19 05:42:01 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][80/312]	eta 0:02:54 lr 0.003341	time 0.7178 (0.7501)	model_time 0.7174 (0.7343)	loss 2.5471 (3.5204)	grad_norm 1.4628 (1.1968/0.5981)	mem 34602MB
[2025-01-19 05:42:08 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][90/312]	eta 0:02:46 lr 0.003340	time 0.7165 (0.7506)	model_time 0.7163 (0.7365)	loss 4.3074 (3.5112)	grad_norm 1.2087 (1.2007/0.5721)	mem 34602MB
[2025-01-19 05:42:16 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][100/312]	eta 0:02:39 lr 0.003340	time 0.7170 (0.7517)	model_time 0.7165 (0.7389)	loss 2.6518 (3.4796)	grad_norm 1.1844 (1.2509/0.5827)	mem 34602MB
[2025-01-19 05:42:23 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][110/312]	eta 0:02:31 lr 0.003339	time 0.7150 (0.7524)	model_time 0.7146 (0.7407)	loss 2.4451 (3.4694)	grad_norm 1.2067 (1.2479/0.5664)	mem 34602MB
[2025-01-19 05:42:31 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][120/312]	eta 0:02:24 lr 0.003339	time 0.7941 (0.7512)	model_time 0.7939 (0.7405)	loss 3.1778 (3.4714)	grad_norm 0.7072 (1.2335/0.5504)	mem 34602MB
[2025-01-19 05:42:38 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][130/312]	eta 0:02:16 lr 0.003338	time 0.7165 (0.7507)	model_time 0.7160 (0.7407)	loss 3.5423 (3.4821)	grad_norm 1.4256 (1.2215/0.5371)	mem 34602MB
[2025-01-19 05:42:46 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][140/312]	eta 0:02:08 lr 0.003338	time 0.7181 (0.7497)	model_time 0.7180 (0.7405)	loss 3.8824 (3.4852)	grad_norm 1.6280 (1.2471/0.5721)	mem 34602MB
[2025-01-19 05:42:53 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][150/312]	eta 0:02:01 lr 0.003337	time 0.7408 (0.7493)	model_time 0.7404 (0.7407)	loss 2.8382 (3.4649)	grad_norm 1.8202 (1.2503/0.5655)	mem 34602MB
[2025-01-19 05:43:00 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][160/312]	eta 0:01:53 lr 0.003337	time 0.7153 (0.7478)	model_time 0.7149 (0.7397)	loss 3.4608 (3.4372)	grad_norm 1.4223 (1.2518/0.5551)	mem 34602MB
[2025-01-19 05:43:08 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][170/312]	eta 0:01:46 lr 0.003336	time 0.7246 (0.7465)	model_time 0.7244 (0.7388)	loss 4.6896 (3.4471)	grad_norm 1.5993 (1.2593/0.5514)	mem 34602MB
[2025-01-19 05:43:15 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][180/312]	eta 0:01:38 lr 0.003336	time 0.7128 (0.7454)	model_time 0.7126 (0.7381)	loss 3.6356 (3.4426)	grad_norm 1.4055 (1.2663/0.5627)	mem 34602MB
[2025-01-19 05:43:22 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][190/312]	eta 0:01:30 lr 0.003335	time 0.7162 (0.7448)	model_time 0.7158 (0.7379)	loss 2.4806 (3.4333)	grad_norm 1.0711 (1.2576/0.5519)	mem 34602MB
[2025-01-19 05:43:29 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][200/312]	eta 0:01:23 lr 0.003335	time 0.7092 (0.7443)	model_time 0.7088 (0.7377)	loss 3.3774 (3.4281)	grad_norm 3.8934 (1.2870/0.5789)	mem 34602MB
[2025-01-19 05:43:37 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][210/312]	eta 0:01:15 lr 0.003334	time 0.7124 (0.7448)	model_time 0.7122 (0.7385)	loss 3.4925 (3.4402)	grad_norm 0.7600 (1.2946/0.5815)	mem 34602MB
[2025-01-19 05:43:45 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][220/312]	eta 0:01:08 lr 0.003334	time 0.7107 (0.7451)	model_time 0.7106 (0.7391)	loss 3.8058 (3.4455)	grad_norm 0.8801 (1.2819/0.5747)	mem 34602MB
[2025-01-19 05:43:52 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][230/312]	eta 0:01:01 lr 0.003333	time 0.8120 (0.7463)	model_time 0.8116 (0.7406)	loss 2.6710 (3.4337)	grad_norm 1.1420 (1.2891/0.5731)	mem 34602MB
[2025-01-19 05:44:00 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][240/312]	eta 0:00:53 lr 0.003333	time 0.7998 (0.7463)	model_time 0.7994 (0.7408)	loss 3.8488 (3.4462)	grad_norm 0.8267 (1.2792/0.5646)	mem 34602MB
[2025-01-19 05:44:07 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][250/312]	eta 0:00:46 lr 0.003332	time 0.7998 (0.7465)	model_time 0.7996 (0.7411)	loss 3.0934 (3.4575)	grad_norm 3.0536 (1.2859/0.5672)	mem 34602MB
[2025-01-19 05:44:15 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][260/312]	eta 0:00:38 lr 0.003332	time 0.7346 (0.7468)	model_time 0.7345 (0.7416)	loss 3.2901 (3.4738)	grad_norm 1.9111 (1.2857/0.5634)	mem 34602MB
[2025-01-19 05:44:22 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][270/312]	eta 0:00:31 lr 0.003331	time 0.7140 (0.7466)	model_time 0.7138 (0.7417)	loss 3.0777 (3.4809)	grad_norm 1.4989 (1.2830/0.5637)	mem 34602MB
[2025-01-19 05:44:30 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][280/312]	eta 0:00:23 lr 0.003331	time 0.7405 (0.7461)	model_time 0.7400 (0.7412)	loss 2.5209 (3.4834)	grad_norm 1.5816 (1.2746/0.5576)	mem 34602MB
[2025-01-19 05:44:37 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][290/312]	eta 0:00:16 lr 0.003330	time 0.7301 (0.7454)	model_time 0.7300 (0.7408)	loss 3.4134 (3.4868)	grad_norm 2.0297 (1.2809/0.5516)	mem 34602MB
[2025-01-19 05:44:44 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][300/312]	eta 0:00:08 lr 0.003330	time 0.7198 (0.7446)	model_time 0.7197 (0.7401)	loss 2.4952 (3.4829)	grad_norm 1.6077 (1.2834/0.5442)	mem 34602MB
[2025-01-19 05:44:51 internimage_b_1k_224] (main.py 510): INFO Train: [80/300][310/312]	eta 0:00:01 lr 0.003329	time 0.7148 (0.7439)	model_time 0.7147 (0.7395)	loss 3.5574 (3.4814)	grad_norm 1.6222 (1.2941/0.5429)	mem 34602MB
[2025-01-19 05:44:52 internimage_b_1k_224] (main.py 519): INFO EPOCH 80 training takes 0:03:52
[2025-01-19 05:44:52 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_80.pth saving......
[2025-01-19 05:44:55 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_80.pth saved !!!
[2025-01-19 05:45:03 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.501 (7.501)	Loss 0.8988 (0.8988)	Acc@1 82.031 (82.031)	Acc@5 95.972 (95.972)	Mem 34602MB
[2025-01-19 05:45:06 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.959)	Loss 1.2544 (1.0717)	Acc@1 72.021 (77.399)	Acc@5 92.065 (93.868)	Mem 34602MB
[2025-01-19 05:45:06 internimage_b_1k_224] (main.py 575): INFO [Epoch:80] * Acc@1 77.351 Acc@5 93.936
[2025-01-19 05:45:06 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.4%
[2025-01-19 05:45:06 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 77.36%
[2025-01-19 05:45:15 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.992 (8.992)	Loss 0.9507 (0.9507)	Acc@1 78.687 (78.687)	Acc@5 94.849 (94.849)	Mem 34602MB
[2025-01-19 05:45:19 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.226)	Loss 1.4023 (1.1235)	Acc@1 68.018 (74.865)	Acc@5 89.697 (92.560)	Mem 34602MB
[2025-01-19 05:45:20 internimage_b_1k_224] (main.py 575): INFO [Epoch:80] * Acc@1 74.882 Acc@5 92.662
[2025-01-19 05:45:20 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 74.9%
[2025-01-19 05:45:20 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:45:24 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:45:24 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 74.88%
[2025-01-19 05:45:26 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][0/312]	eta 0:10:36 lr 0.003329	time 2.0413 (2.0413)	model_time 0.7571 (0.7571)	loss 4.0654 (4.0654)	grad_norm 1.4194 (1.4194/0.0000)	mem 34602MB
[2025-01-19 05:45:33 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][10/312]	eta 0:04:20 lr 0.003329	time 0.7165 (0.8617)	model_time 0.7163 (0.7446)	loss 3.5226 (3.6313)	grad_norm 1.4340 (1.3510/0.3245)	mem 34602MB
[2025-01-19 05:45:41 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][20/312]	eta 0:03:57 lr 0.003328	time 0.7225 (0.8136)	model_time 0.7224 (0.7521)	loss 3.7949 (3.5237)	grad_norm 2.1166 (1.5160/0.4113)	mem 34602MB
[2025-01-19 05:45:48 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][30/312]	eta 0:03:44 lr 0.003328	time 0.8009 (0.7945)	model_time 0.8007 (0.7527)	loss 3.3143 (3.5199)	grad_norm 2.2422 (1.5054/0.5233)	mem 34602MB
[2025-01-19 05:45:56 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][40/312]	eta 0:03:34 lr 0.003327	time 0.7515 (0.7893)	model_time 0.7510 (0.7576)	loss 4.2604 (3.5114)	grad_norm 0.8793 (1.3838/0.5248)	mem 34602MB
[2025-01-19 05:46:04 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][50/312]	eta 0:03:24 lr 0.003327	time 0.7261 (0.7810)	model_time 0.7258 (0.7555)	loss 3.2133 (3.4922)	grad_norm 0.9743 (1.3274/0.5065)	mem 34602MB
[2025-01-19 05:46:11 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][60/312]	eta 0:03:15 lr 0.003326	time 0.7343 (0.7754)	model_time 0.7338 (0.7540)	loss 3.8446 (3.4807)	grad_norm 1.1815 (1.3097/0.4837)	mem 34602MB
[2025-01-19 05:46:19 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][70/312]	eta 0:03:06 lr 0.003326	time 0.7517 (0.7711)	model_time 0.7515 (0.7526)	loss 2.3691 (3.4750)	grad_norm 1.2634 (1.3812/0.5143)	mem 34602MB
[2025-01-19 05:46:26 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][80/312]	eta 0:02:57 lr 0.003325	time 0.7273 (0.7667)	model_time 0.7270 (0.7505)	loss 3.9235 (3.4965)	grad_norm 1.0587 (1.3515/0.5092)	mem 34602MB
[2025-01-19 05:46:33 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][90/312]	eta 0:02:49 lr 0.003325	time 0.7297 (0.7628)	model_time 0.7295 (0.7483)	loss 3.8880 (3.5095)	grad_norm 1.0030 (1.3099/0.4981)	mem 34602MB
[2025-01-19 05:46:41 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][100/312]	eta 0:02:40 lr 0.003324	time 0.7204 (0.7594)	model_time 0.7199 (0.7463)	loss 3.3999 (3.4946)	grad_norm 1.6846 (1.3091/0.4839)	mem 34602MB
[2025-01-19 05:46:48 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][110/312]	eta 0:02:32 lr 0.003324	time 0.7119 (0.7572)	model_time 0.7117 (0.7453)	loss 2.6979 (3.4750)	grad_norm 0.9177 (1.3474/0.5568)	mem 34602MB
[2025-01-19 05:46:55 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][120/312]	eta 0:02:24 lr 0.003323	time 0.7181 (0.7547)	model_time 0.7179 (0.7437)	loss 2.7492 (3.4759)	grad_norm 1.0717 (1.3216/0.5428)	mem 34602MB
[2025-01-19 05:47:03 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][130/312]	eta 0:02:17 lr 0.003323	time 0.7154 (0.7542)	model_time 0.7150 (0.7440)	loss 3.2990 (3.4831)	grad_norm 1.1150 (1.3123/0.5287)	mem 34602MB
[2025-01-19 05:47:10 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][140/312]	eta 0:02:09 lr 0.003322	time 0.7945 (0.7546)	model_time 0.7943 (0.7451)	loss 4.0297 (3.4752)	grad_norm 1.3433 (1.3134/0.5175)	mem 34602MB
[2025-01-19 05:47:18 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][150/312]	eta 0:02:02 lr 0.003322	time 0.7754 (0.7551)	model_time 0.7752 (0.7463)	loss 2.5361 (3.4580)	grad_norm 0.6740 (1.2935/0.5136)	mem 34602MB
[2025-01-19 05:47:25 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][160/312]	eta 0:01:54 lr 0.003321	time 0.7160 (0.7558)	model_time 0.7158 (0.7475)	loss 3.8818 (3.4692)	grad_norm 1.0136 (1.3000/0.5193)	mem 34602MB
[2025-01-19 05:47:33 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][170/312]	eta 0:01:47 lr 0.003321	time 0.7153 (0.7552)	model_time 0.7151 (0.7473)	loss 3.5600 (3.4942)	grad_norm 1.3023 (1.2920/0.5096)	mem 34602MB
[2025-01-19 05:47:40 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][180/312]	eta 0:01:39 lr 0.003320	time 0.7307 (0.7544)	model_time 0.7302 (0.7469)	loss 2.2247 (3.4981)	grad_norm 1.1375 (1.2937/0.5056)	mem 34602MB
[2025-01-19 05:47:48 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][190/312]	eta 0:01:31 lr 0.003320	time 0.7387 (0.7536)	model_time 0.7382 (0.7465)	loss 3.5688 (3.4882)	grad_norm 1.3534 (1.2888/0.4970)	mem 34602MB
[2025-01-19 05:47:55 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][200/312]	eta 0:01:24 lr 0.003319	time 0.7348 (0.7524)	model_time 0.7344 (0.7457)	loss 3.9269 (3.4711)	grad_norm 1.1225 (1.3045/0.5171)	mem 34602MB
[2025-01-19 05:48:02 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][210/312]	eta 0:01:16 lr 0.003319	time 0.7421 (0.7512)	model_time 0.7419 (0.7448)	loss 3.8141 (3.4821)	grad_norm 1.4708 (1.3052/0.5130)	mem 34602MB
[2025-01-19 05:48:10 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][220/312]	eta 0:01:09 lr 0.003318	time 0.7218 (0.7503)	model_time 0.7216 (0.7441)	loss 3.7030 (3.4829)	grad_norm 2.3508 (1.3256/0.5274)	mem 34602MB
[2025-01-19 05:48:17 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][230/312]	eta 0:01:01 lr 0.003318	time 0.7178 (0.7494)	model_time 0.7173 (0.7435)	loss 3.6620 (3.4691)	grad_norm 0.9718 (1.3254/0.5312)	mem 34602MB
[2025-01-19 05:48:24 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][240/312]	eta 0:00:53 lr 0.003317	time 0.7189 (0.7483)	model_time 0.7187 (0.7426)	loss 3.7937 (3.4620)	grad_norm 0.9316 (1.3100/0.5270)	mem 34602MB
[2025-01-19 05:48:32 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][250/312]	eta 0:00:46 lr 0.003317	time 0.7231 (0.7478)	model_time 0.7229 (0.7424)	loss 3.6083 (3.4537)	grad_norm 2.9202 (1.3146/0.5340)	mem 34602MB
[2025-01-19 05:48:39 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][260/312]	eta 0:00:38 lr 0.003316	time 0.7663 (0.7481)	model_time 0.7662 (0.7428)	loss 2.8911 (3.4367)	grad_norm 2.0307 (1.3065/0.5294)	mem 34602MB
[2025-01-19 05:48:47 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][270/312]	eta 0:00:31 lr 0.003316	time 0.7231 (0.7481)	model_time 0.7230 (0.7430)	loss 3.0000 (3.4315)	grad_norm 1.2498 (1.3216/0.5469)	mem 34602MB
[2025-01-19 05:48:54 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][280/312]	eta 0:00:23 lr 0.003315	time 0.7164 (0.7489)	model_time 0.7163 (0.7440)	loss 2.4168 (3.4349)	grad_norm 0.9581 (1.3201/0.5418)	mem 34602MB
[2025-01-19 05:49:02 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][290/312]	eta 0:00:16 lr 0.003315	time 0.7892 (0.7485)	model_time 0.7891 (0.7437)	loss 3.8732 (3.4337)	grad_norm 0.9954 (1.3145/0.5360)	mem 34602MB
[2025-01-19 05:49:09 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][300/312]	eta 0:00:08 lr 0.003314	time 0.7151 (0.7483)	model_time 0.7150 (0.7437)	loss 3.1013 (3.4350)	grad_norm 0.7579 (1.3274/0.5437)	mem 34602MB
[2025-01-19 05:49:16 internimage_b_1k_224] (main.py 510): INFO Train: [81/300][310/312]	eta 0:00:01 lr 0.003314	time 0.7136 (0.7478)	model_time 0.7135 (0.7433)	loss 3.5508 (3.4392)	grad_norm 1.7278 (1.3310/0.5497)	mem 34602MB
[2025-01-19 05:49:17 internimage_b_1k_224] (main.py 519): INFO EPOCH 81 training takes 0:03:53
[2025-01-19 05:49:17 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_81.pth saving......
[2025-01-19 05:49:20 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_81.pth saved !!!
[2025-01-19 05:49:28 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.304 (7.304)	Loss 0.8899 (0.8899)	Acc@1 81.396 (81.396)	Acc@5 96.216 (96.216)	Mem 34602MB
[2025-01-19 05:49:31 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.940)	Loss 1.2891 (1.0578)	Acc@1 72.095 (77.548)	Acc@5 91.528 (94.098)	Mem 34602MB
[2025-01-19 05:49:31 internimage_b_1k_224] (main.py 575): INFO [Epoch:81] * Acc@1 77.501 Acc@5 94.148
[2025-01-19 05:49:31 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.5%
[2025-01-19 05:49:31 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 05:49:34 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 05:49:34 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 77.50%
[2025-01-19 05:49:42 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.254 (7.254)	Loss 0.9346 (0.9346)	Acc@1 78.906 (78.906)	Acc@5 95.020 (95.020)	Mem 34602MB
[2025-01-19 05:49:45 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.947)	Loss 1.3828 (1.1072)	Acc@1 68.481 (75.133)	Acc@5 89.844 (92.705)	Mem 34602MB
[2025-01-19 05:49:45 internimage_b_1k_224] (main.py 575): INFO [Epoch:81] * Acc@1 75.154 Acc@5 92.794
[2025-01-19 05:49:45 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 75.2%
[2025-01-19 05:49:45 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:49:49 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:49:49 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 75.15%
[2025-01-19 05:49:51 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][0/312]	eta 0:10:13 lr 0.003314	time 1.9650 (1.9650)	model_time 0.7420 (0.7420)	loss 2.8872 (2.8872)	grad_norm 1.9365 (1.9365/0.0000)	mem 34602MB
[2025-01-19 05:49:58 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][10/312]	eta 0:04:17 lr 0.003313	time 0.7321 (0.8516)	model_time 0.7319 (0.7401)	loss 3.7549 (3.6520)	grad_norm 2.1600 (1.2571/0.5285)	mem 34602MB
[2025-01-19 05:50:06 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][20/312]	eta 0:03:52 lr 0.003313	time 0.7204 (0.7964)	model_time 0.7202 (0.7377)	loss 3.7360 (3.4590)	grad_norm 1.1092 (1.2489/0.5138)	mem 34602MB
[2025-01-19 05:50:13 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][30/312]	eta 0:03:38 lr 0.003312	time 0.7163 (0.7736)	model_time 0.7161 (0.7338)	loss 3.9851 (3.6076)	grad_norm 0.5132 (1.3087/0.5497)	mem 34602MB
[2025-01-19 05:50:20 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][40/312]	eta 0:03:27 lr 0.003312	time 0.8016 (0.7639)	model_time 0.8011 (0.7336)	loss 2.9156 (3.5786)	grad_norm 1.3610 (1.2855/0.5428)	mem 34602MB
[2025-01-19 05:50:27 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][50/312]	eta 0:03:18 lr 0.003311	time 0.7225 (0.7579)	model_time 0.7223 (0.7335)	loss 2.4600 (3.5709)	grad_norm 1.1086 (1.2180/0.5157)	mem 34602MB
[2025-01-19 05:50:35 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][60/312]	eta 0:03:10 lr 0.003311	time 0.8502 (0.7564)	model_time 0.8500 (0.7360)	loss 3.4558 (3.5146)	grad_norm 2.0019 (1.2869/0.5558)	mem 34602MB
[2025-01-19 05:50:43 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][70/312]	eta 0:03:03 lr 0.003310	time 0.8098 (0.7568)	model_time 0.8094 (0.7392)	loss 3.3392 (3.5105)	grad_norm 0.6610 (1.2937/0.5700)	mem 34602MB
[2025-01-19 05:50:50 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][80/312]	eta 0:02:55 lr 0.003310	time 0.7173 (0.7562)	model_time 0.7169 (0.7408)	loss 3.7439 (3.4962)	grad_norm 1.1692 (1.2834/0.5605)	mem 34602MB
[2025-01-19 05:50:58 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][90/312]	eta 0:02:48 lr 0.003309	time 0.8093 (0.7585)	model_time 0.8091 (0.7447)	loss 3.6089 (3.4798)	grad_norm 0.7707 (1.2462/0.5457)	mem 34602MB
[2025-01-19 05:51:05 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][100/312]	eta 0:02:40 lr 0.003309	time 0.7198 (0.7569)	model_time 0.7196 (0.7444)	loss 3.3316 (3.4521)	grad_norm 1.9616 (1.2802/0.5856)	mem 34602MB
[2025-01-19 05:51:13 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][110/312]	eta 0:02:32 lr 0.003308	time 0.7267 (0.7556)	model_time 0.7266 (0.7443)	loss 3.9750 (3.4404)	grad_norm 2.6838 (1.2895/0.5820)	mem 34602MB
[2025-01-19 05:51:20 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][120/312]	eta 0:02:25 lr 0.003308	time 0.7297 (0.7559)	model_time 0.7292 (0.7455)	loss 4.2522 (3.4528)	grad_norm 1.4185 (1.3193/0.6111)	mem 34602MB
[2025-01-19 05:51:28 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][130/312]	eta 0:02:17 lr 0.003307	time 0.7187 (0.7544)	model_time 0.7186 (0.7447)	loss 3.2211 (3.4630)	grad_norm 1.2519 (1.3158/0.5949)	mem 34602MB
[2025-01-19 05:51:35 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][140/312]	eta 0:02:09 lr 0.003307	time 0.7450 (0.7529)	model_time 0.7448 (0.7439)	loss 3.1822 (3.4768)	grad_norm 2.4605 (1.3200/0.5915)	mem 34602MB
[2025-01-19 05:51:42 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][150/312]	eta 0:02:01 lr 0.003306	time 0.7258 (0.7517)	model_time 0.7256 (0.7432)	loss 4.2358 (3.4883)	grad_norm 1.4779 (1.3098/0.5793)	mem 34602MB
[2025-01-19 05:51:50 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][160/312]	eta 0:01:54 lr 0.003306	time 0.7916 (0.7504)	model_time 0.7914 (0.7425)	loss 3.0451 (3.4855)	grad_norm 2.2091 (1.3000/0.5758)	mem 34602MB
[2025-01-19 05:51:57 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][170/312]	eta 0:01:46 lr 0.003305	time 0.7181 (0.7494)	model_time 0.7180 (0.7419)	loss 3.4958 (3.4754)	grad_norm 1.4467 (1.3107/0.5705)	mem 34602MB
[2025-01-19 05:52:04 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][180/312]	eta 0:01:38 lr 0.003305	time 0.8126 (0.7491)	model_time 0.8124 (0.7420)	loss 2.1329 (3.4677)	grad_norm 1.0034 (1.3203/0.5746)	mem 34602MB
[2025-01-19 05:52:12 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][190/312]	eta 0:01:31 lr 0.003304	time 0.8176 (0.7495)	model_time 0.8170 (0.7428)	loss 4.3475 (3.4593)	grad_norm 2.0210 (1.3154/0.5660)	mem 34602MB
[2025-01-19 05:52:19 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][200/312]	eta 0:01:23 lr 0.003304	time 0.7178 (0.7496)	model_time 0.7176 (0.7432)	loss 3.1587 (3.4643)	grad_norm 1.8590 (1.3255/0.5658)	mem 34602MB
[2025-01-19 05:52:27 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][210/312]	eta 0:01:16 lr 0.003303	time 0.8068 (0.7505)	model_time 0.8066 (0.7444)	loss 2.7174 (3.4583)	grad_norm 1.5224 (1.3238/0.5607)	mem 34602MB
[2025-01-19 05:52:35 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][220/312]	eta 0:01:08 lr 0.003303	time 0.7185 (0.7500)	model_time 0.7184 (0.7441)	loss 3.3054 (3.4651)	grad_norm 1.3639 (1.3153/0.5512)	mem 34602MB
[2025-01-19 05:52:42 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][230/312]	eta 0:01:01 lr 0.003302	time 0.7169 (0.7496)	model_time 0.7164 (0.7440)	loss 3.9234 (3.4626)	grad_norm 1.1377 (1.3109/0.5450)	mem 34602MB
[2025-01-19 05:52:49 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][240/312]	eta 0:00:53 lr 0.003302	time 0.7321 (0.7492)	model_time 0.7316 (0.7438)	loss 3.7590 (3.4623)	grad_norm 1.5667 (1.3217/0.5433)	mem 34602MB
[2025-01-19 05:52:57 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][250/312]	eta 0:00:46 lr 0.003301	time 0.7153 (0.7487)	model_time 0.7152 (0.7434)	loss 2.7865 (3.4665)	grad_norm 1.6028 (1.3297/0.5453)	mem 34602MB
[2025-01-19 05:53:04 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][260/312]	eta 0:00:38 lr 0.003301	time 0.7141 (0.7477)	model_time 0.7136 (0.7427)	loss 3.7349 (3.4690)	grad_norm 0.7019 (1.3392/0.5455)	mem 34602MB
[2025-01-19 05:53:11 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][270/312]	eta 0:00:31 lr 0.003300	time 0.7168 (0.7470)	model_time 0.7163 (0.7422)	loss 3.8304 (3.4812)	grad_norm 2.0933 (1.3469/0.5432)	mem 34602MB
[2025-01-19 05:53:19 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][280/312]	eta 0:00:23 lr 0.003300	time 0.7837 (0.7464)	model_time 0.7835 (0.7417)	loss 3.6495 (3.4845)	grad_norm 1.0841 (1.3436/0.5375)	mem 34602MB
[2025-01-19 05:53:26 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][290/312]	eta 0:00:16 lr 0.003299	time 0.7397 (0.7463)	model_time 0.7395 (0.7417)	loss 4.2090 (3.4905)	grad_norm 1.1986 (1.3407/0.5334)	mem 34602MB
[2025-01-19 05:53:33 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][300/312]	eta 0:00:08 lr 0.003299	time 0.8190 (0.7462)	model_time 0.8189 (0.7418)	loss 3.3958 (3.4720)	grad_norm 1.4878 (1.3248/0.5312)	mem 34602MB
[2025-01-19 05:53:41 internimage_b_1k_224] (main.py 510): INFO Train: [82/300][310/312]	eta 0:00:01 lr 0.003298	time 0.7113 (0.7461)	model_time 0.7112 (0.7418)	loss 3.8090 (3.4683)	grad_norm 0.7983 (1.3187/0.5267)	mem 34602MB
[2025-01-19 05:53:42 internimage_b_1k_224] (main.py 519): INFO EPOCH 82 training takes 0:03:52
[2025-01-19 05:53:42 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_82.pth saving......
[2025-01-19 05:53:45 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_82.pth saved !!!
[2025-01-19 05:53:52 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.627 (7.627)	Loss 0.8570 (0.8570)	Acc@1 80.859 (80.859)	Acc@5 96.411 (96.411)	Mem 34602MB
[2025-01-19 05:53:55 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.948)	Loss 1.2034 (1.0223)	Acc@1 72.729 (77.490)	Acc@5 92.065 (94.138)	Mem 34602MB
[2025-01-19 05:53:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:82] * Acc@1 77.339 Acc@5 94.222
[2025-01-19 05:53:55 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.3%
[2025-01-19 05:53:55 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 77.50%
[2025-01-19 05:54:05 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.116 (9.116)	Loss 0.9191 (0.9191)	Acc@1 79.150 (79.150)	Acc@5 95.093 (95.093)	Mem 34602MB
[2025-01-19 05:54:10 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.279)	Loss 1.3638 (1.0915)	Acc@1 68.774 (75.364)	Acc@5 89.990 (92.816)	Mem 34602MB
[2025-01-19 05:54:10 internimage_b_1k_224] (main.py 575): INFO [Epoch:82] * Acc@1 75.370 Acc@5 92.916
[2025-01-19 05:54:10 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 75.4%
[2025-01-19 05:54:10 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:54:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:54:14 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 75.37%
[2025-01-19 05:54:16 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][0/312]	eta 0:12:11 lr 0.003298	time 2.3456 (2.3456)	model_time 0.7529 (0.7529)	loss 3.6293 (3.6293)	grad_norm 1.0522 (1.0522/0.0000)	mem 34602MB
[2025-01-19 05:54:23 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][10/312]	eta 0:04:32 lr 0.003297	time 0.7233 (0.9012)	model_time 0.7229 (0.7561)	loss 3.4301 (3.1820)	grad_norm 1.3799 (1.3020/0.5090)	mem 34602MB
[2025-01-19 05:54:31 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][20/312]	eta 0:04:04 lr 0.003297	time 0.8032 (0.8378)	model_time 0.8030 (0.7617)	loss 3.1888 (3.3294)	grad_norm 0.6527 (1.2683/0.5646)	mem 34602MB
[2025-01-19 05:54:39 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][30/312]	eta 0:03:47 lr 0.003296	time 0.8007 (0.8074)	model_time 0.8006 (0.7557)	loss 3.5057 (3.3508)	grad_norm 2.1830 (1.2870/0.5234)	mem 34602MB
[2025-01-19 05:54:46 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][40/312]	eta 0:03:36 lr 0.003296	time 0.7928 (0.7942)	model_time 0.7924 (0.7550)	loss 2.2811 (3.3472)	grad_norm 1.2093 (1.3234/0.5876)	mem 34602MB
[2025-01-19 05:54:53 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][50/312]	eta 0:03:25 lr 0.003295	time 0.7202 (0.7829)	model_time 0.7200 (0.7513)	loss 3.4897 (3.3720)	grad_norm 2.8469 (1.3389/0.6111)	mem 34602MB
[2025-01-19 05:55:01 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][60/312]	eta 0:03:15 lr 0.003295	time 0.7290 (0.7752)	model_time 0.7285 (0.7488)	loss 3.2803 (3.3382)	grad_norm 1.7949 (1.4050/0.6186)	mem 34602MB
[2025-01-19 05:55:08 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][70/312]	eta 0:03:06 lr 0.003294	time 0.7198 (0.7689)	model_time 0.7196 (0.7461)	loss 4.1338 (3.3666)	grad_norm 0.8670 (1.3578/0.5925)	mem 34602MB
[2025-01-19 05:55:15 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][80/312]	eta 0:02:57 lr 0.003294	time 0.7163 (0.7637)	model_time 0.7161 (0.7437)	loss 3.3047 (3.3643)	grad_norm 0.8144 (1.3161/0.5751)	mem 34602MB
[2025-01-19 05:55:23 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][90/312]	eta 0:02:48 lr 0.003293	time 0.7177 (0.7607)	model_time 0.7173 (0.7428)	loss 3.2092 (3.3521)	grad_norm 1.7710 (1.3114/0.5629)	mem 34602MB
[2025-01-19 05:55:30 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][100/312]	eta 0:02:40 lr 0.003293	time 0.7168 (0.7576)	model_time 0.7166 (0.7415)	loss 3.3041 (3.3428)	grad_norm 1.3756 (1.2971/0.5440)	mem 34602MB
[2025-01-19 05:55:38 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][110/312]	eta 0:02:32 lr 0.003292	time 0.7168 (0.7562)	model_time 0.7164 (0.7415)	loss 3.3455 (3.3486)	grad_norm 1.6038 (1.2902/0.5306)	mem 34602MB
[2025-01-19 05:55:45 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][120/312]	eta 0:02:25 lr 0.003292	time 0.8258 (0.7566)	model_time 0.8256 (0.7431)	loss 2.8251 (3.3478)	grad_norm 0.5817 (1.2856/0.5297)	mem 34602MB
[2025-01-19 05:55:53 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][130/312]	eta 0:02:17 lr 0.003291	time 0.7172 (0.7570)	model_time 0.7171 (0.7445)	loss 4.4603 (3.3676)	grad_norm 2.0681 (1.3109/0.5408)	mem 34602MB
[2025-01-19 05:56:00 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][140/312]	eta 0:02:10 lr 0.003291	time 0.7443 (0.7572)	model_time 0.7441 (0.7456)	loss 3.6055 (3.3731)	grad_norm 1.1655 (1.3044/0.5356)	mem 34602MB
[2025-01-19 05:56:08 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][150/312]	eta 0:02:02 lr 0.003290	time 0.7899 (0.7566)	model_time 0.7894 (0.7457)	loss 2.8924 (3.3664)	grad_norm 1.6344 (1.3000/0.5297)	mem 34602MB
[2025-01-19 05:56:15 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][160/312]	eta 0:01:55 lr 0.003290	time 0.8011 (0.7573)	model_time 0.8009 (0.7471)	loss 2.8525 (3.3635)	grad_norm 1.7379 (1.3007/0.5200)	mem 34602MB
[2025-01-19 05:56:23 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][170/312]	eta 0:01:47 lr 0.003289	time 0.7984 (0.7555)	model_time 0.7982 (0.7459)	loss 3.6083 (3.3618)	grad_norm 0.9974 (1.2988/0.5127)	mem 34602MB
[2025-01-19 05:56:30 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][180/312]	eta 0:01:39 lr 0.003289	time 0.7333 (0.7546)	model_time 0.7332 (0.7454)	loss 3.6291 (3.3733)	grad_norm 0.6511 (1.2806/0.5082)	mem 34602MB
[2025-01-19 05:56:37 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][190/312]	eta 0:01:31 lr 0.003288	time 0.7155 (0.7529)	model_time 0.7153 (0.7442)	loss 4.1502 (3.3923)	grad_norm 1.4344 (1.2702/0.5047)	mem 34602MB
[2025-01-19 05:56:45 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][200/312]	eta 0:01:24 lr 0.003288	time 0.7293 (0.7518)	model_time 0.7288 (0.7436)	loss 3.8307 (3.3934)	grad_norm 0.9150 (1.2644/0.4988)	mem 34602MB
[2025-01-19 05:56:52 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][210/312]	eta 0:01:16 lr 0.003287	time 0.7392 (0.7506)	model_time 0.7384 (0.7427)	loss 3.8917 (3.3939)	grad_norm 1.6066 (1.2648/0.4966)	mem 34602MB
[2025-01-19 05:56:59 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][220/312]	eta 0:01:08 lr 0.003287	time 0.7215 (0.7498)	model_time 0.7211 (0.7422)	loss 3.1905 (3.3955)	grad_norm 0.6758 (1.2839/0.5071)	mem 34602MB
[2025-01-19 05:57:07 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][230/312]	eta 0:01:01 lr 0.003286	time 0.7249 (0.7495)	model_time 0.7244 (0.7423)	loss 2.6179 (3.4012)	grad_norm 1.2169 (1.2887/0.5026)	mem 34602MB
[2025-01-19 05:57:14 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][240/312]	eta 0:00:53 lr 0.003286	time 0.7956 (0.7498)	model_time 0.7954 (0.7429)	loss 3.4583 (3.4017)	grad_norm 0.8126 (1.2778/0.5003)	mem 34602MB
[2025-01-19 05:57:22 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][250/312]	eta 0:00:46 lr 0.003285	time 0.7173 (0.7502)	model_time 0.7171 (0.7435)	loss 2.9749 (3.3936)	grad_norm 0.7114 (1.2661/0.4958)	mem 34602MB
[2025-01-19 05:57:29 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][260/312]	eta 0:00:39 lr 0.003285	time 0.7151 (0.7506)	model_time 0.7150 (0.7441)	loss 2.5817 (3.3922)	grad_norm 1.4209 (1.2956/0.5515)	mem 34602MB
[2025-01-19 05:57:37 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][270/312]	eta 0:00:31 lr 0.003284	time 0.8059 (0.7504)	model_time 0.8057 (0.7442)	loss 2.0363 (3.3913)	grad_norm 0.7126 (1.2990/0.5479)	mem 34602MB
[2025-01-19 05:57:44 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][280/312]	eta 0:00:24 lr 0.003284	time 0.7995 (0.7502)	model_time 0.7993 (0.7442)	loss 3.9316 (3.4030)	grad_norm 0.7080 (1.2947/0.5417)	mem 34602MB
[2025-01-19 05:57:52 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][290/312]	eta 0:00:16 lr 0.003283	time 0.8211 (0.7500)	model_time 0.8209 (0.7442)	loss 3.6373 (3.4045)	grad_norm 2.3283 (1.2929/0.5385)	mem 34602MB
[2025-01-19 05:57:59 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][300/312]	eta 0:00:08 lr 0.003283	time 0.7138 (0.7494)	model_time 0.7137 (0.7438)	loss 3.5304 (3.4020)	grad_norm 0.9900 (1.2919/0.5382)	mem 34602MB
[2025-01-19 05:58:06 internimage_b_1k_224] (main.py 510): INFO Train: [83/300][310/312]	eta 0:00:01 lr 0.003282	time 0.7152 (0.7486)	model_time 0.7151 (0.7431)	loss 3.4428 (3.4001)	grad_norm 1.3280 (1.2798/0.5345)	mem 34602MB
[2025-01-19 05:58:07 internimage_b_1k_224] (main.py 519): INFO EPOCH 83 training takes 0:03:53
[2025-01-19 05:58:07 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_83.pth saving......
[2025-01-19 05:58:10 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_83.pth saved !!!
[2025-01-19 05:58:27 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.883 (16.883)	Loss 0.9058 (0.9058)	Acc@1 81.128 (81.128)	Acc@5 96.167 (96.167)	Mem 34602MB
[2025-01-19 05:58:32 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.925)	Loss 1.2441 (1.0577)	Acc@1 73.169 (77.641)	Acc@5 92.065 (94.176)	Mem 34602MB
[2025-01-19 05:58:32 internimage_b_1k_224] (main.py 575): INFO [Epoch:83] * Acc@1 77.557 Acc@5 94.248
[2025-01-19 05:58:32 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.6%
[2025-01-19 05:58:32 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 05:58:35 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 05:58:35 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 77.56%
[2025-01-19 05:58:43 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.431 (7.431)	Loss 0.9048 (0.9048)	Acc@1 79.468 (79.468)	Acc@5 95.215 (95.215)	Mem 34602MB
[2025-01-19 05:58:46 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.949)	Loss 1.3462 (1.0768)	Acc@1 68.896 (75.577)	Acc@5 90.259 (92.918)	Mem 34602MB
[2025-01-19 05:58:46 internimage_b_1k_224] (main.py 575): INFO [Epoch:83] * Acc@1 75.578 Acc@5 93.018
[2025-01-19 05:58:46 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 75.6%
[2025-01-19 05:58:46 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:58:50 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:58:50 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 75.58%
[2025-01-19 05:58:52 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][0/312]	eta 0:10:40 lr 0.003282	time 2.0537 (2.0537)	model_time 0.7449 (0.7449)	loss 3.2551 (3.2551)	grad_norm 1.1556 (1.1556/0.0000)	mem 34602MB
[2025-01-19 05:58:59 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][10/312]	eta 0:04:14 lr 0.003282	time 0.7096 (0.8444)	model_time 0.7094 (0.7250)	loss 2.5555 (3.5696)	grad_norm 0.8567 (1.1645/0.4097)	mem 34602MB
[2025-01-19 05:59:07 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][20/312]	eta 0:03:51 lr 0.003281	time 0.7197 (0.7916)	model_time 0.7195 (0.7289)	loss 2.4535 (3.4783)	grad_norm 1.6404 (1.0918/0.3548)	mem 34602MB
[2025-01-19 05:59:14 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][30/312]	eta 0:03:38 lr 0.003281	time 0.7416 (0.7752)	model_time 0.7412 (0.7327)	loss 3.5501 (3.4372)	grad_norm 2.5505 (1.3082/0.5984)	mem 34602MB
[2025-01-19 05:59:22 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][40/312]	eta 0:03:29 lr 0.003280	time 0.7181 (0.7686)	model_time 0.7177 (0.7363)	loss 3.6949 (3.4584)	grad_norm 1.0502 (1.3616/0.6177)	mem 34602MB
[2025-01-19 05:59:29 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][50/312]	eta 0:03:20 lr 0.003280	time 0.8005 (0.7662)	model_time 0.8004 (0.7401)	loss 4.5427 (3.5234)	grad_norm 2.4282 (1.3565/0.5920)	mem 34602MB
[2025-01-19 05:59:37 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][60/312]	eta 0:03:12 lr 0.003279	time 0.7618 (0.7632)	model_time 0.7616 (0.7414)	loss 3.2139 (3.5413)	grad_norm 1.9537 (1.3525/0.5615)	mem 34602MB
[2025-01-19 05:59:44 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][70/312]	eta 0:03:05 lr 0.003279	time 0.7142 (0.7646)	model_time 0.7140 (0.7458)	loss 2.7272 (3.5461)	grad_norm 2.5812 (1.4272/0.6284)	mem 34602MB
[2025-01-19 05:59:52 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][80/312]	eta 0:02:57 lr 0.003278	time 0.8256 (0.7637)	model_time 0.8254 (0.7472)	loss 3.8386 (3.5712)	grad_norm 1.1341 (1.3943/0.6071)	mem 34602MB
[2025-01-19 05:59:59 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][90/312]	eta 0:02:49 lr 0.003277	time 0.7275 (0.7636)	model_time 0.7270 (0.7489)	loss 4.2354 (3.5374)	grad_norm 1.0627 (1.3681/0.5945)	mem 34602MB
[2025-01-19 06:00:07 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][100/312]	eta 0:02:41 lr 0.003277	time 0.7241 (0.7605)	model_time 0.7237 (0.7472)	loss 3.9889 (3.5469)	grad_norm 1.6058 (1.3356/0.5821)	mem 34602MB
[2025-01-19 06:00:14 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][110/312]	eta 0:02:33 lr 0.003276	time 0.7198 (0.7583)	model_time 0.7196 (0.7461)	loss 4.1553 (3.5321)	grad_norm 2.1415 (1.3250/0.5736)	mem 34602MB
[2025-01-19 06:00:21 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][120/312]	eta 0:02:25 lr 0.003276	time 0.7346 (0.7559)	model_time 0.7341 (0.7447)	loss 4.1654 (3.5483)	grad_norm 3.4438 (1.3542/0.6221)	mem 34602MB
[2025-01-19 06:00:29 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][130/312]	eta 0:02:17 lr 0.003275	time 0.7169 (0.7539)	model_time 0.7167 (0.7436)	loss 4.2468 (3.5475)	grad_norm 0.6859 (1.3554/0.6223)	mem 34602MB
[2025-01-19 06:00:36 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][140/312]	eta 0:02:09 lr 0.003275	time 0.7197 (0.7523)	model_time 0.7193 (0.7427)	loss 3.2281 (3.5538)	grad_norm 1.0906 (1.3532/0.6125)	mem 34602MB
[2025-01-19 06:00:43 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][150/312]	eta 0:02:01 lr 0.003274	time 0.7209 (0.7508)	model_time 0.7208 (0.7418)	loss 4.1606 (3.5385)	grad_norm 1.8761 (1.3651/0.6080)	mem 34602MB
[2025-01-19 06:00:51 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][160/312]	eta 0:01:54 lr 0.003274	time 0.7481 (0.7516)	model_time 0.7480 (0.7431)	loss 3.7922 (3.5382)	grad_norm 1.2303 (1.3365/0.6031)	mem 34602MB
[2025-01-19 06:00:59 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][170/312]	eta 0:01:46 lr 0.003273	time 0.8187 (0.7516)	model_time 0.8185 (0.7436)	loss 3.1487 (3.5424)	grad_norm 0.5322 (1.3144/0.5957)	mem 34602MB
[2025-01-19 06:01:06 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][180/312]	eta 0:01:39 lr 0.003273	time 0.7080 (0.7513)	model_time 0.7078 (0.7437)	loss 3.0483 (3.5460)	grad_norm 1.3264 (1.3148/0.5834)	mem 34602MB
[2025-01-19 06:01:14 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][190/312]	eta 0:01:31 lr 0.003272	time 0.7169 (0.7523)	model_time 0.7167 (0.7451)	loss 3.2546 (3.5398)	grad_norm 1.5962 (1.3166/0.5879)	mem 34602MB
[2025-01-19 06:01:21 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][200/312]	eta 0:01:24 lr 0.003272	time 0.7255 (0.7515)	model_time 0.7250 (0.7446)	loss 3.9368 (3.5292)	grad_norm 0.6746 (1.3346/0.5999)	mem 34602MB
[2025-01-19 06:01:29 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][210/312]	eta 0:01:16 lr 0.003271	time 0.7169 (0.7518)	model_time 0.7167 (0.7452)	loss 3.9003 (3.5347)	grad_norm 0.9583 (1.3296/0.5907)	mem 34602MB
[2025-01-19 06:01:36 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][220/312]	eta 0:01:09 lr 0.003271	time 0.7160 (0.7511)	model_time 0.7157 (0.7448)	loss 3.7593 (3.5293)	grad_norm 0.6329 (1.3236/0.5844)	mem 34602MB
[2025-01-19 06:01:43 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][230/312]	eta 0:01:01 lr 0.003270	time 0.7291 (0.7506)	model_time 0.7286 (0.7445)	loss 3.6879 (3.5350)	grad_norm 0.6128 (1.3044/0.5797)	mem 34602MB
[2025-01-19 06:01:51 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][240/312]	eta 0:00:53 lr 0.003270	time 0.7160 (0.7497)	model_time 0.7158 (0.7439)	loss 3.7533 (3.5340)	grad_norm 0.8594 (1.3044/0.5759)	mem 34602MB
[2025-01-19 06:01:58 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][250/312]	eta 0:00:46 lr 0.003269	time 0.7164 (0.7487)	model_time 0.7163 (0.7431)	loss 3.4576 (3.5384)	grad_norm 2.5412 (1.3119/0.5779)	mem 34602MB
[2025-01-19 06:02:05 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][260/312]	eta 0:00:38 lr 0.003269	time 0.7164 (0.7482)	model_time 0.7160 (0.7428)	loss 4.1912 (3.5395)	grad_norm 0.7394 (1.3197/0.5925)	mem 34602MB
[2025-01-19 06:02:13 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][270/312]	eta 0:00:31 lr 0.003268	time 0.7143 (0.7473)	model_time 0.7142 (0.7421)	loss 3.6632 (3.5219)	grad_norm 0.7061 (1.3171/0.5846)	mem 34602MB
[2025-01-19 06:02:20 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][280/312]	eta 0:00:23 lr 0.003268	time 0.7260 (0.7470)	model_time 0.7256 (0.7420)	loss 2.8668 (3.5178)	grad_norm 1.3414 (1.3110/0.5763)	mem 34602MB
[2025-01-19 06:02:27 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][290/312]	eta 0:00:16 lr 0.003267	time 0.7965 (0.7470)	model_time 0.7962 (0.7422)	loss 4.2585 (3.5160)	grad_norm 1.5301 (1.3236/0.5878)	mem 34602MB
[2025-01-19 06:02:35 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][300/312]	eta 0:00:08 lr 0.003267	time 0.7144 (0.7468)	model_time 0.7143 (0.7421)	loss 3.7598 (3.5190)	grad_norm 1.0450 (1.3266/0.5857)	mem 34602MB
[2025-01-19 06:02:42 internimage_b_1k_224] (main.py 510): INFO Train: [84/300][310/312]	eta 0:00:01 lr 0.003266	time 0.7127 (0.7465)	model_time 0.7126 (0.7420)	loss 3.8363 (3.5150)	grad_norm 0.9360 (1.3184/0.5870)	mem 34602MB
[2025-01-19 06:02:43 internimage_b_1k_224] (main.py 519): INFO EPOCH 84 training takes 0:03:53
[2025-01-19 06:02:43 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_84.pth saving......
[2025-01-19 06:02:46 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_84.pth saved !!!
[2025-01-19 06:02:54 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.327 (7.327)	Loss 0.8968 (0.8968)	Acc@1 81.006 (81.006)	Acc@5 96.216 (96.216)	Mem 34602MB
[2025-01-19 06:02:57 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.918)	Loss 1.2723 (1.0604)	Acc@1 71.973 (77.484)	Acc@5 91.577 (94.105)	Mem 34602MB
[2025-01-19 06:02:57 internimage_b_1k_224] (main.py 575): INFO [Epoch:84] * Acc@1 77.439 Acc@5 94.168
[2025-01-19 06:02:57 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.4%
[2025-01-19 06:02:57 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 77.56%
[2025-01-19 06:03:06 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.065 (9.065)	Loss 0.8911 (0.8911)	Acc@1 79.663 (79.663)	Acc@5 95.312 (95.312)	Mem 34602MB
[2025-01-19 06:03:10 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.228)	Loss 1.3295 (1.0627)	Acc@1 69.067 (75.746)	Acc@5 90.356 (93.026)	Mem 34602MB
[2025-01-19 06:03:11 internimage_b_1k_224] (main.py 575): INFO [Epoch:84] * Acc@1 75.748 Acc@5 93.124
[2025-01-19 06:03:11 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 75.7%
[2025-01-19 06:03:11 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 06:03:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 06:03:14 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 75.75%
[2025-01-19 06:03:17 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][0/312]	eta 0:10:51 lr 0.003266	time 2.0887 (2.0887)	model_time 0.7416 (0.7416)	loss 3.2307 (3.2307)	grad_norm 0.9385 (0.9385/0.0000)	mem 34602MB
[2025-01-19 06:03:24 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][10/312]	eta 0:04:21 lr 0.003266	time 0.7945 (0.8671)	model_time 0.7943 (0.7443)	loss 3.6041 (3.4872)	grad_norm 1.2397 (1.1473/0.3418)	mem 34602MB
[2025-01-19 06:03:31 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][20/312]	eta 0:03:56 lr 0.003265	time 0.7355 (0.8096)	model_time 0.7353 (0.7451)	loss 3.8741 (3.6262)	grad_norm 0.8524 (1.0831/0.3407)	mem 34602MB
[2025-01-19 06:03:39 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][30/312]	eta 0:03:42 lr 0.003265	time 0.7277 (0.7898)	model_time 0.7275 (0.7460)	loss 3.6226 (3.6352)	grad_norm 1.7517 (1.3105/0.7005)	mem 34602MB
[2025-01-19 06:03:46 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][40/312]	eta 0:03:31 lr 0.003264	time 0.7280 (0.7770)	model_time 0.7278 (0.7438)	loss 4.1176 (3.6105)	grad_norm 1.0088 (1.3743/0.6888)	mem 34602MB
[2025-01-19 06:03:54 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][50/312]	eta 0:03:21 lr 0.003263	time 0.7471 (0.7676)	model_time 0.7466 (0.7408)	loss 3.8178 (3.5912)	grad_norm 2.1690 (1.3800/0.6647)	mem 34602MB
[2025-01-19 06:04:01 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][60/312]	eta 0:03:11 lr 0.003263	time 0.7243 (0.7611)	model_time 0.7238 (0.7386)	loss 3.5167 (3.5582)	grad_norm 2.1458 (1.3811/0.6224)	mem 34602MB
[2025-01-19 06:04:08 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][70/312]	eta 0:03:03 lr 0.003262	time 0.7913 (0.7571)	model_time 0.7908 (0.7378)	loss 3.8427 (3.5570)	grad_norm 1.0118 (1.3801/0.6068)	mem 34602MB
[2025-01-19 06:04:15 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][80/312]	eta 0:02:54 lr 0.003262	time 0.7206 (0.7529)	model_time 0.7205 (0.7359)	loss 3.5737 (3.5353)	grad_norm 1.0466 (1.3490/0.5790)	mem 34602MB
[2025-01-19 06:04:23 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][90/312]	eta 0:02:46 lr 0.003261	time 0.7144 (0.7512)	model_time 0.7142 (0.7360)	loss 2.4948 (3.5125)	grad_norm 1.8967 (1.3316/0.5643)	mem 34602MB
[2025-01-19 06:04:30 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][100/312]	eta 0:02:39 lr 0.003261	time 0.7180 (0.7516)	model_time 0.7176 (0.7379)	loss 3.0763 (3.4919)	grad_norm 1.0395 (1.3292/0.5587)	mem 34602MB
[2025-01-19 06:04:38 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][110/312]	eta 0:02:31 lr 0.003260	time 0.8009 (0.7511)	model_time 0.8004 (0.7386)	loss 3.7575 (3.4807)	grad_norm 0.8400 (1.3002/0.5478)	mem 34602MB
[2025-01-19 06:04:45 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][120/312]	eta 0:02:24 lr 0.003260	time 0.8093 (0.7522)	model_time 0.8091 (0.7407)	loss 2.4756 (3.4493)	grad_norm 0.9641 (1.2708/0.5375)	mem 34602MB
[2025-01-19 06:04:53 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][130/312]	eta 0:02:16 lr 0.003259	time 0.7182 (0.7506)	model_time 0.7177 (0.7400)	loss 3.5847 (3.4590)	grad_norm 2.2564 (1.2867/0.5387)	mem 34602MB
[2025-01-19 06:05:00 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][140/312]	eta 0:02:09 lr 0.003259	time 0.7161 (0.7510)	model_time 0.7159 (0.7410)	loss 3.3638 (3.4820)	grad_norm 1.4057 (1.2807/0.5305)	mem 34602MB
[2025-01-19 06:05:08 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][150/312]	eta 0:02:01 lr 0.003258	time 0.7218 (0.7505)	model_time 0.7213 (0.7412)	loss 2.8239 (3.4931)	grad_norm 0.9303 (1.2876/0.5309)	mem 34602MB
[2025-01-19 06:05:15 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][160/312]	eta 0:01:53 lr 0.003258	time 0.7207 (0.7500)	model_time 0.7206 (0.7413)	loss 3.9984 (3.5063)	grad_norm 2.2995 (1.3241/0.5738)	mem 34602MB
[2025-01-19 06:05:23 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][170/312]	eta 0:01:46 lr 0.003257	time 0.7191 (0.7489)	model_time 0.7189 (0.7406)	loss 2.9987 (3.5039)	grad_norm 0.8345 (1.3429/0.5869)	mem 34602MB
[2025-01-19 06:05:30 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][180/312]	eta 0:01:38 lr 0.003257	time 0.7202 (0.7476)	model_time 0.7198 (0.7398)	loss 4.2300 (3.5089)	grad_norm 0.7141 (1.3390/0.5834)	mem 34602MB
[2025-01-19 06:05:37 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][190/312]	eta 0:01:31 lr 0.003256	time 0.7989 (0.7471)	model_time 0.7987 (0.7396)	loss 3.0364 (3.5054)	grad_norm 0.6714 (1.3232/0.5794)	mem 34602MB
[2025-01-19 06:05:44 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][200/312]	eta 0:01:23 lr 0.003256	time 0.7223 (0.7461)	model_time 0.7222 (0.7390)	loss 3.5180 (3.5063)	grad_norm 0.6747 (1.3051/0.5729)	mem 34602MB
[2025-01-19 06:05:52 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][210/312]	eta 0:01:16 lr 0.003255	time 0.7628 (0.7463)	model_time 0.7626 (0.7395)	loss 3.8718 (3.5097)	grad_norm 1.1542 (1.3117/0.5730)	mem 34602MB
[2025-01-19 06:05:59 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][220/312]	eta 0:01:08 lr 0.003255	time 0.7154 (0.7464)	model_time 0.7151 (0.7399)	loss 3.1831 (3.5078)	grad_norm 2.4131 (1.3105/0.5699)	mem 34602MB
[2025-01-19 06:06:07 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][230/312]	eta 0:01:01 lr 0.003254	time 0.8145 (0.7464)	model_time 0.8143 (0.7402)	loss 3.8777 (3.5046)	grad_norm 0.9273 (1.3053/0.5644)	mem 34602MB
[2025-01-19 06:06:15 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][240/312]	eta 0:00:53 lr 0.003254	time 0.8084 (0.7475)	model_time 0.8082 (0.7416)	loss 3.3540 (3.4897)	grad_norm 1.7275 (1.3042/0.5588)	mem 34602MB
[2025-01-19 06:06:22 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][250/312]	eta 0:00:46 lr 0.003253	time 0.7156 (0.7475)	model_time 0.7154 (0.7418)	loss 3.6948 (3.4917)	grad_norm 2.0558 (1.3207/0.5793)	mem 34602MB
[2025-01-19 06:06:30 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][260/312]	eta 0:00:38 lr 0.003253	time 0.8114 (0.7478)	model_time 0.8113 (0.7423)	loss 4.0255 (3.4927)	grad_norm 0.7856 (1.3157/0.5774)	mem 34602MB
[2025-01-19 06:06:37 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][270/312]	eta 0:00:31 lr 0.003252	time 0.7197 (0.7475)	model_time 0.7192 (0.7421)	loss 3.8383 (3.4967)	grad_norm 1.0798 (1.3233/0.5813)	mem 34602MB
[2025-01-19 06:06:44 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][280/312]	eta 0:00:23 lr 0.003252	time 0.7253 (0.7474)	model_time 0.7252 (0.7423)	loss 3.3990 (3.4946)	grad_norm 0.7587 (1.3227/0.5788)	mem 34602MB
[2025-01-19 06:06:52 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][290/312]	eta 0:00:16 lr 0.003251	time 0.7272 (0.7467)	model_time 0.7270 (0.7417)	loss 3.1992 (3.5026)	grad_norm 0.9003 (1.3154/0.5741)	mem 34602MB
[2025-01-19 06:06:59 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][300/312]	eta 0:00:08 lr 0.003250	time 0.7136 (0.7459)	model_time 0.7135 (0.7411)	loss 3.3701 (3.5048)	grad_norm 0.7324 (1.3138/0.5726)	mem 34602MB
[2025-01-19 06:07:06 internimage_b_1k_224] (main.py 510): INFO Train: [85/300][310/312]	eta 0:00:01 lr 0.003250	time 0.7116 (0.7450)	model_time 0.7115 (0.7403)	loss 3.4878 (3.5083)	grad_norm 0.7624 (1.3250/0.5764)	mem 34602MB
[2025-01-19 06:07:07 internimage_b_1k_224] (main.py 519): INFO EPOCH 85 training takes 0:03:52
[2025-01-19 06:07:07 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_85.pth saving......
[2025-01-19 06:07:10 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_85.pth saved !!!
[2025-01-19 06:07:18 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.520 (7.520)	Loss 0.8886 (0.8886)	Acc@1 81.104 (81.104)	Acc@5 96.265 (96.265)	Mem 34602MB
[2025-01-19 06:07:21 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.963)	Loss 1.2168 (1.0389)	Acc@1 74.316 (77.732)	Acc@5 92.188 (94.258)	Mem 34602MB
[2025-01-19 06:07:21 internimage_b_1k_224] (main.py 575): INFO [Epoch:85] * Acc@1 77.773 Acc@5 94.352
[2025-01-19 06:07:21 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.8%
[2025-01-19 06:07:21 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 06:07:24 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 06:07:24 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 77.77%
[2025-01-19 06:07:33 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.168 (8.168)	Loss 0.8785 (0.8785)	Acc@1 79.761 (79.761)	Acc@5 95.410 (95.410)	Mem 34602MB
[2025-01-19 06:07:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.047)	Loss 1.3137 (1.0496)	Acc@1 69.312 (75.881)	Acc@5 90.479 (93.135)	Mem 34602MB
[2025-01-19 06:07:36 internimage_b_1k_224] (main.py 575): INFO [Epoch:85] * Acc@1 75.882 Acc@5 93.230
[2025-01-19 06:07:36 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 75.9%
[2025-01-19 06:07:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 06:07:40 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 06:07:40 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 75.88%
[2025-01-19 06:07:42 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][0/312]	eta 0:12:12 lr 0.003250	time 2.3476 (2.3476)	model_time 0.7637 (0.7637)	loss 2.1949 (2.1949)	grad_norm 0.4785 (0.4785/0.0000)	mem 34602MB
[2025-01-19 06:07:50 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][10/312]	eta 0:04:24 lr 0.003249	time 0.7488 (0.8752)	model_time 0.7483 (0.7309)	loss 3.2991 (3.1411)	grad_norm 0.8325 (1.2130/0.6552)	mem 34602MB
[2025-01-19 06:07:57 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][20/312]	eta 0:03:57 lr 0.003249	time 0.7161 (0.8130)	model_time 0.7156 (0.7372)	loss 3.9648 (3.3695)	grad_norm 0.9854 (1.3558/0.7062)	mem 34602MB
[2025-01-19 06:08:05 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][30/312]	eta 0:03:46 lr 0.003248	time 0.8089 (0.8031)	model_time 0.8084 (0.7516)	loss 3.8407 (3.4593)	grad_norm 1.6237 (1.3550/0.6267)	mem 34602MB
[2025-01-19 06:08:12 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][40/312]	eta 0:03:34 lr 0.003248	time 0.7322 (0.7903)	model_time 0.7320 (0.7514)	loss 4.3577 (3.4985)	grad_norm 2.0435 (1.3494/0.6104)	mem 34602MB
[2025-01-19 06:08:20 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][50/312]	eta 0:03:27 lr 0.003247	time 0.8193 (0.7904)	model_time 0.8188 (0.7590)	loss 3.9215 (3.5062)	grad_norm 2.3447 (1.4460/0.6205)	mem 34602MB
[2025-01-19 06:08:28 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][60/312]	eta 0:03:17 lr 0.003247	time 0.7161 (0.7830)	model_time 0.7156 (0.7567)	loss 2.6475 (3.4646)	grad_norm 1.5023 (1.4254/0.6078)	mem 34602MB
[2025-01-19 06:08:35 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][70/312]	eta 0:03:08 lr 0.003246	time 0.7291 (0.7779)	model_time 0.7289 (0.7553)	loss 3.1690 (3.4948)	grad_norm 1.4734 (1.4035/0.5740)	mem 34602MB
[2025-01-19 06:08:43 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][80/312]	eta 0:02:59 lr 0.003246	time 0.7106 (0.7737)	model_time 0.7104 (0.7538)	loss 3.3534 (3.4971)	grad_norm 0.9135 (1.4079/0.5674)	mem 34602MB
[2025-01-19 06:08:50 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][90/312]	eta 0:02:50 lr 0.003245	time 0.7223 (0.7701)	model_time 0.7222 (0.7524)	loss 3.2396 (3.4955)	grad_norm 1.2489 (1.3916/0.5554)	mem 34602MB
[2025-01-19 06:08:57 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][100/312]	eta 0:02:42 lr 0.003245	time 0.7173 (0.7657)	model_time 0.7171 (0.7497)	loss 3.6108 (3.4739)	grad_norm 1.2257 (1.3526/0.5513)	mem 34602MB
[2025-01-19 06:09:05 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][110/312]	eta 0:02:33 lr 0.003244	time 0.7201 (0.7621)	model_time 0.7196 (0.7474)	loss 3.2769 (3.4748)	grad_norm 1.4297 (1.3365/0.5387)	mem 34602MB
[2025-01-19 06:09:12 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][120/312]	eta 0:02:25 lr 0.003244	time 0.7210 (0.7593)	model_time 0.7205 (0.7458)	loss 3.7646 (3.4888)	grad_norm 0.9379 (1.3278/0.5260)	mem 34602MB
[2025-01-19 06:09:19 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][130/312]	eta 0:02:17 lr 0.003243	time 0.7279 (0.7574)	model_time 0.7277 (0.7450)	loss 2.9286 (3.4949)	grad_norm 0.9044 (1.3619/0.5427)	mem 34602MB
[2025-01-19 06:09:27 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][140/312]	eta 0:02:10 lr 0.003243	time 0.7374 (0.7567)	model_time 0.7373 (0.7451)	loss 3.1094 (3.4889)	grad_norm 0.8923 (1.3711/0.5449)	mem 34602MB
[2025-01-19 06:09:34 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][150/312]	eta 0:02:02 lr 0.003242	time 0.8085 (0.7570)	model_time 0.8083 (0.7461)	loss 3.2261 (3.4754)	grad_norm 1.2256 (1.3619/0.5400)	mem 34602MB
[2025-01-19 06:09:42 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][160/312]	eta 0:01:54 lr 0.003242	time 0.7195 (0.7559)	model_time 0.7194 (0.7457)	loss 3.7763 (3.4803)	grad_norm 1.6510 (1.3552/0.5363)	mem 34602MB
[2025-01-19 06:09:49 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][170/312]	eta 0:01:47 lr 0.003241	time 0.8109 (0.7570)	model_time 0.8105 (0.7474)	loss 4.3232 (3.4878)	grad_norm 0.8017 (1.3597/0.5368)	mem 34602MB
[2025-01-19 06:09:57 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][180/312]	eta 0:01:39 lr 0.003240	time 0.7153 (0.7568)	model_time 0.7152 (0.7477)	loss 3.5756 (3.4742)	grad_norm 1.5458 (1.3575/0.5247)	mem 34602MB
[2025-01-19 06:10:04 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][190/312]	eta 0:01:32 lr 0.003240	time 0.7411 (0.7559)	model_time 0.7410 (0.7472)	loss 2.9269 (3.4650)	grad_norm 1.6511 (1.3418/0.5195)	mem 34602MB
[2025-01-19 06:10:12 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][200/312]	eta 0:01:24 lr 0.003239	time 0.7992 (0.7560)	model_time 0.7987 (0.7477)	loss 3.6207 (3.4703)	grad_norm 1.4160 (1.3471/0.5172)	mem 34602MB
[2025-01-19 06:10:19 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][210/312]	eta 0:01:16 lr 0.003239	time 0.7140 (0.7548)	model_time 0.7139 (0.7469)	loss 3.8084 (3.4671)	grad_norm 1.4577 (1.3589/0.5286)	mem 34602MB
[2025-01-19 06:10:27 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][220/312]	eta 0:01:09 lr 0.003238	time 0.7194 (0.7537)	model_time 0.7192 (0.7462)	loss 3.6463 (3.4761)	grad_norm 1.2717 (1.3456/0.5229)	mem 34602MB
[2025-01-19 06:10:34 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][230/312]	eta 0:01:01 lr 0.003238	time 0.7553 (0.7528)	model_time 0.7548 (0.7456)	loss 4.1744 (3.4710)	grad_norm 1.1292 (1.3283/0.5193)	mem 34602MB
[2025-01-19 06:10:41 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][240/312]	eta 0:00:54 lr 0.003237	time 0.7310 (0.7515)	model_time 0.7305 (0.7446)	loss 3.0591 (3.4579)	grad_norm 0.7230 (1.3359/0.5287)	mem 34602MB
[2025-01-19 06:10:48 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][250/312]	eta 0:00:46 lr 0.003237	time 0.7216 (0.7507)	model_time 0.7214 (0.7440)	loss 4.3175 (3.4622)	grad_norm 0.7080 (1.3202/0.5261)	mem 34602MB
[2025-01-19 06:10:56 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][260/312]	eta 0:00:39 lr 0.003236	time 0.7167 (0.7503)	model_time 0.7166 (0.7438)	loss 4.2453 (3.4788)	grad_norm 2.9622 (1.3294/0.5375)	mem 34602MB
[2025-01-19 06:11:03 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][270/312]	eta 0:00:31 lr 0.003236	time 0.8100 (0.7503)	model_time 0.8094 (0.7441)	loss 3.4196 (3.4794)	grad_norm 0.5452 (1.3379/0.5536)	mem 34602MB
[2025-01-19 06:11:11 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][280/312]	eta 0:00:23 lr 0.003235	time 0.7228 (0.7499)	model_time 0.7223 (0.7439)	loss 3.6911 (3.4869)	grad_norm 1.7520 (1.3501/0.5635)	mem 34602MB
[2025-01-19 06:11:18 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][290/312]	eta 0:00:16 lr 0.003235	time 0.8069 (0.7507)	model_time 0.8068 (0.7449)	loss 4.3405 (3.4935)	grad_norm 0.9085 (1.3428/0.5578)	mem 34602MB
[2025-01-19 06:11:26 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][300/312]	eta 0:00:09 lr 0.003234	time 0.7094 (0.7510)	model_time 0.7093 (0.7453)	loss 3.9303 (3.4932)	grad_norm 1.4075 (1.3505/0.5510)	mem 34602MB
[2025-01-19 06:11:33 internimage_b_1k_224] (main.py 510): INFO Train: [86/300][310/312]	eta 0:00:01 lr 0.003234	time 0.7101 (0.7503)	model_time 0.7100 (0.7448)	loss 3.5514 (3.4918)	grad_norm 1.0704 (1.3541/0.5423)	mem 34602MB
[2025-01-19 06:11:34 internimage_b_1k_224] (main.py 519): INFO EPOCH 86 training takes 0:03:54
[2025-01-19 06:11:34 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_86.pth saving......
[2025-01-19 06:11:37 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_86.pth saved !!!
[2025-01-19 06:11:45 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.293 (7.293)	Loss 0.8699 (0.8699)	Acc@1 81.152 (81.152)	Acc@5 95.972 (95.972)	Mem 34602MB
[2025-01-19 06:11:48 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.924)	Loss 1.2207 (1.0150)	Acc@1 73.242 (77.785)	Acc@5 91.895 (94.285)	Mem 34602MB
[2025-01-19 06:11:48 internimage_b_1k_224] (main.py 575): INFO [Epoch:86] * Acc@1 77.693 Acc@5 94.350
[2025-01-19 06:11:48 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.7%
[2025-01-19 06:11:48 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 77.77%
[2025-01-19 06:11:57 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.231 (9.231)	Loss 0.8665 (0.8665)	Acc@1 79.980 (79.980)	Acc@5 95.508 (95.508)	Mem 34602MB
[2025-01-19 06:12:02 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.228)	Loss 1.2989 (1.0372)	Acc@1 69.556 (76.048)	Acc@5 90.674 (93.244)	Mem 34602MB
[2025-01-19 06:12:02 internimage_b_1k_224] (main.py 575): INFO [Epoch:86] * Acc@1 76.046 Acc@5 93.336
[2025-01-19 06:12:02 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 76.0%
[2025-01-19 06:12:02 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 06:12:06 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 06:12:06 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 76.05%
[2025-01-19 06:12:08 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][0/312]	eta 0:10:19 lr 0.003234	time 1.9853 (1.9853)	model_time 0.7561 (0.7561)	loss 3.2326 (3.2326)	grad_norm 1.2346 (1.2346/0.0000)	mem 34602MB
[2025-01-19 06:12:15 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][10/312]	eta 0:04:19 lr 0.003233	time 0.7188 (0.8600)	model_time 0.7183 (0.7478)	loss 3.4300 (3.6990)	grad_norm 0.6934 (1.4008/0.5335)	mem 34602MB
[2025-01-19 06:12:23 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][20/312]	eta 0:03:55 lr 0.003233	time 0.7294 (0.8053)	model_time 0.7292 (0.7464)	loss 3.8010 (3.6537)	grad_norm 0.9763 (1.2084/0.4598)	mem 34602MB
[2025-01-19 06:12:30 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][30/312]	eta 0:03:39 lr 0.003232	time 0.7291 (0.7797)	model_time 0.7289 (0.7397)	loss 3.2646 (3.5710)	grad_norm 0.6866 (1.1542/0.4275)	mem 34602MB
[2025-01-19 06:12:37 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][40/312]	eta 0:03:29 lr 0.003231	time 0.7290 (0.7688)	model_time 0.7288 (0.7385)	loss 3.0490 (3.5243)	grad_norm 2.7387 (1.2798/0.5953)	mem 34602MB
[2025-01-19 06:12:45 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][50/312]	eta 0:03:20 lr 0.003231	time 0.7188 (0.7634)	model_time 0.7186 (0.7389)	loss 4.1941 (3.5382)	grad_norm 1.4281 (1.2795/0.5535)	mem 34602MB
[2025-01-19 06:12:52 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][60/312]	eta 0:03:11 lr 0.003230	time 0.7225 (0.7585)	model_time 0.7224 (0.7380)	loss 3.3302 (3.5404)	grad_norm 1.7494 (1.2903/0.5420)	mem 34602MB
[2025-01-19 06:13:00 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][70/312]	eta 0:03:03 lr 0.003230	time 0.7203 (0.7573)	model_time 0.7198 (0.7396)	loss 3.9382 (3.5008)	grad_norm 1.7154 (1.2959/0.5333)	mem 34602MB
[2025-01-19 06:13:07 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][80/312]	eta 0:02:55 lr 0.003229	time 0.8256 (0.7571)	model_time 0.8254 (0.7416)	loss 3.3059 (3.4665)	grad_norm 0.8627 (1.2886/0.5287)	mem 34602MB
[2025-01-19 06:13:15 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][90/312]	eta 0:02:47 lr 0.003229	time 0.7376 (0.7557)	model_time 0.7374 (0.7419)	loss 4.4456 (3.4365)	grad_norm 1.5729 (1.3347/0.5498)	mem 34602MB
[2025-01-19 06:13:23 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][100/312]	eta 0:02:40 lr 0.003228	time 0.7184 (0.7589)	model_time 0.7181 (0.7464)	loss 2.7104 (3.4123)	grad_norm 1.0356 (1.3300/0.5290)	mem 34602MB
[2025-01-19 06:13:30 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][110/312]	eta 0:02:33 lr 0.003228	time 0.8024 (0.7591)	model_time 0.8020 (0.7477)	loss 4.0490 (3.4389)	grad_norm 0.8322 (1.3166/0.5266)	mem 34602MB
[2025-01-19 06:13:38 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][120/312]	eta 0:02:25 lr 0.003227	time 0.7171 (0.7574)	model_time 0.7169 (0.7469)	loss 3.6003 (3.4568)	grad_norm 1.2130 (1.2843/0.5185)	mem 34602MB
[2025-01-19 06:13:45 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][130/312]	eta 0:02:17 lr 0.003227	time 0.7382 (0.7568)	model_time 0.7377 (0.7471)	loss 2.6520 (3.4633)	grad_norm 1.3936 (1.3249/0.5489)	mem 34602MB
[2025-01-19 06:13:52 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][140/312]	eta 0:02:09 lr 0.003226	time 0.8145 (0.7556)	model_time 0.8143 (0.7465)	loss 3.7721 (3.4531)	grad_norm 1.3040 (1.3193/0.5530)	mem 34602MB
[2025-01-19 06:14:00 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][150/312]	eta 0:02:02 lr 0.003226	time 0.7231 (0.7539)	model_time 0.7229 (0.7455)	loss 2.5468 (3.4506)	grad_norm 0.9543 (1.3099/0.5442)	mem 34602MB
[2025-01-19 06:14:07 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][160/312]	eta 0:01:54 lr 0.003225	time 0.7226 (0.7522)	model_time 0.7224 (0.7442)	loss 3.5065 (3.4449)	grad_norm 0.9305 (1.3111/0.5335)	mem 34602MB
[2025-01-19 06:14:15 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][170/312]	eta 0:01:46 lr 0.003225	time 0.7170 (0.7526)	model_time 0.7169 (0.7451)	loss 2.7426 (3.4377)	grad_norm 1.0383 (1.3261/0.5317)	mem 34602MB
[2025-01-19 06:14:22 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][180/312]	eta 0:01:39 lr 0.003224	time 0.7314 (0.7517)	model_time 0.7313 (0.7446)	loss 4.1677 (3.4522)	grad_norm 1.5184 (1.3423/0.5274)	mem 34602MB
[2025-01-19 06:14:29 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][190/312]	eta 0:01:31 lr 0.003224	time 0.7127 (0.7518)	model_time 0.7125 (0.7451)	loss 2.8079 (3.4460)	grad_norm 2.0727 (1.3391/0.5251)	mem 34602MB
[2025-01-19 06:14:37 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][200/312]	eta 0:01:24 lr 0.003223	time 0.7246 (0.7519)	model_time 0.7245 (0.7455)	loss 4.1413 (3.4397)	grad_norm 1.4817 (1.3369/0.5221)	mem 34602MB
[2025-01-19 06:14:45 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][210/312]	eta 0:01:16 lr 0.003222	time 0.7170 (0.7525)	model_time 0.7167 (0.7464)	loss 2.3876 (3.4309)	grad_norm 1.6701 (1.3592/0.5354)	mem 34602MB
[2025-01-19 06:14:52 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][220/312]	eta 0:01:09 lr 0.003222	time 0.7185 (0.7528)	model_time 0.7183 (0.7469)	loss 3.1151 (3.4378)	grad_norm 0.6398 (1.3549/0.5308)	mem 34602MB
[2025-01-19 06:15:00 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][230/312]	eta 0:01:01 lr 0.003221	time 0.7725 (0.7523)	model_time 0.7718 (0.7467)	loss 3.1670 (3.4408)	grad_norm 2.6541 (1.3555/0.5337)	mem 34602MB
[2025-01-19 06:15:07 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][240/312]	eta 0:00:54 lr 0.003221	time 0.7205 (0.7517)	model_time 0.7202 (0.7463)	loss 3.6688 (3.4424)	grad_norm 0.8740 (1.3466/0.5311)	mem 34602MB
[2025-01-19 06:15:14 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][250/312]	eta 0:00:46 lr 0.003220	time 0.7185 (0.7512)	model_time 0.7183 (0.7460)	loss 3.1575 (3.4517)	grad_norm 1.1512 (1.3337/0.5256)	mem 34602MB
[2025-01-19 06:15:22 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][260/312]	eta 0:00:39 lr 0.003220	time 0.8028 (0.7511)	model_time 0.8027 (0.7461)	loss 3.6036 (3.4490)	grad_norm 1.4587 (1.3308/0.5168)	mem 34602MB
[2025-01-19 06:15:29 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][270/312]	eta 0:00:31 lr 0.003219	time 0.7190 (0.7504)	model_time 0.7188 (0.7456)	loss 3.7140 (3.4485)	grad_norm 0.8617 (1.3292/0.5126)	mem 34602MB
[2025-01-19 06:15:36 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][280/312]	eta 0:00:23 lr 0.003219	time 0.7193 (0.7495)	model_time 0.7192 (0.7448)	loss 4.1818 (3.4482)	grad_norm 1.5145 (1.3266/0.5103)	mem 34602MB
[2025-01-19 06:15:44 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][290/312]	eta 0:00:16 lr 0.003218	time 0.7312 (0.7491)	model_time 0.7311 (0.7445)	loss 3.4456 (3.4447)	grad_norm 1.2329 (1.3285/0.5055)	mem 34602MB
[2025-01-19 06:15:51 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][300/312]	eta 0:00:08 lr 0.003218	time 0.7116 (0.7484)	model_time 0.7115 (0.7440)	loss 3.6287 (3.4461)	grad_norm 1.1054 (1.3386/0.5039)	mem 34602MB
[2025-01-19 06:15:58 internimage_b_1k_224] (main.py 510): INFO Train: [87/300][310/312]	eta 0:00:01 lr 0.003217	time 0.8190 (0.7477)	model_time 0.8189 (0.7434)	loss 3.0165 (3.4448)	grad_norm 1.1422 (1.3369/0.4984)	mem 34602MB
[2025-01-19 06:15:59 internimage_b_1k_224] (main.py 519): INFO EPOCH 87 training takes 0:03:53
[2025-01-19 06:15:59 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_87.pth saving......
[2025-01-19 06:16:02 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_87.pth saved !!!
[2025-01-19 06:16:10 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.517 (7.517)	Loss 0.9118 (0.9118)	Acc@1 80.688 (80.688)	Acc@5 96.265 (96.265)	Mem 34602MB
[2025-01-19 06:16:13 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.942)	Loss 1.2835 (1.0814)	Acc@1 73.462 (77.763)	Acc@5 91.724 (94.260)	Mem 34602MB
[2025-01-19 06:16:13 internimage_b_1k_224] (main.py 575): INFO [Epoch:87] * Acc@1 77.655 Acc@5 94.298
[2025-01-19 06:16:13 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.7%
[2025-01-19 06:16:13 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 77.77%
[2025-01-19 06:16:22 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.951 (8.951)	Loss 0.8549 (0.8549)	Acc@1 80.127 (80.127)	Acc@5 95.508 (95.508)	Mem 34602MB
[2025-01-19 06:16:26 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.209)	Loss 1.2844 (1.0253)	Acc@1 69.702 (76.205)	Acc@5 90.796 (93.333)	Mem 34602MB
[2025-01-19 06:16:26 internimage_b_1k_224] (main.py 575): INFO [Epoch:87] * Acc@1 76.206 Acc@5 93.422
[2025-01-19 06:16:26 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 76.2%
[2025-01-19 06:16:26 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 06:16:30 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 06:16:30 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 76.21%
[2025-01-19 06:16:33 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][0/312]	eta 0:11:15 lr 0.003217	time 2.1660 (2.1660)	model_time 0.7408 (0.7408)	loss 2.4707 (2.4707)	grad_norm 0.7138 (0.7138/0.0000)	mem 34602MB
[2025-01-19 06:16:40 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][10/312]	eta 0:04:30 lr 0.003217	time 0.7335 (0.8965)	model_time 0.7330 (0.7667)	loss 3.0382 (3.1622)	grad_norm 1.8197 (1.0069/0.3782)	mem 34602MB
[2025-01-19 06:16:48 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][20/312]	eta 0:04:03 lr 0.003216	time 0.7175 (0.8329)	model_time 0.7174 (0.7647)	loss 2.7431 (3.2756)	grad_norm 2.6425 (1.0887/0.4607)	mem 34602MB
[2025-01-19 06:16:56 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][30/312]	eta 0:03:49 lr 0.003216	time 0.8041 (0.8130)	model_time 0.8039 (0.7667)	loss 3.1355 (3.3701)	grad_norm 1.7569 (1.1414/0.4674)	mem 34602MB
[2025-01-19 06:17:03 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][40/312]	eta 0:03:36 lr 0.003215	time 0.7312 (0.7963)	model_time 0.7310 (0.7613)	loss 4.0063 (3.3871)	grad_norm 2.7701 (1.2225/0.5738)	mem 34602MB
[2025-01-19 06:17:11 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][50/312]	eta 0:03:25 lr 0.003214	time 0.7320 (0.7857)	model_time 0.7318 (0.7574)	loss 3.2121 (3.3848)	grad_norm 0.7758 (1.2129/0.5673)	mem 34602MB
[2025-01-19 06:17:18 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][60/312]	eta 0:03:16 lr 0.003214	time 0.7611 (0.7792)	model_time 0.7610 (0.7555)	loss 2.7689 (3.3568)	grad_norm 0.8843 (1.2251/0.5673)	mem 34602MB
[2025-01-19 06:17:25 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][70/312]	eta 0:03:07 lr 0.003213	time 0.7211 (0.7729)	model_time 0.7206 (0.7525)	loss 3.2485 (3.3691)	grad_norm 1.6334 (1.2234/0.5364)	mem 34602MB
[2025-01-19 06:17:33 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][80/312]	eta 0:02:58 lr 0.003213	time 0.7274 (0.7690)	model_time 0.7271 (0.7511)	loss 2.3333 (3.3977)	grad_norm 1.1169 (1.2641/0.5337)	mem 34602MB
[2025-01-19 06:17:40 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][90/312]	eta 0:02:49 lr 0.003212	time 0.7163 (0.7643)	model_time 0.7158 (0.7483)	loss 3.8260 (3.4046)	grad_norm 0.8500 (1.2983/0.5955)	mem 34602MB
[2025-01-19 06:17:47 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][100/312]	eta 0:02:41 lr 0.003212	time 0.7221 (0.7605)	model_time 0.7219 (0.7460)	loss 4.3987 (3.4219)	grad_norm 2.5715 (1.3023/0.5924)	mem 34602MB
[2025-01-19 06:17:55 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][110/312]	eta 0:02:33 lr 0.003211	time 0.7297 (0.7579)	model_time 0.7295 (0.7447)	loss 2.2340 (3.3979)	grad_norm 1.2890 (1.2975/0.5718)	mem 34602MB
[2025-01-19 06:18:02 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][120/312]	eta 0:02:25 lr 0.003211	time 0.7168 (0.7576)	model_time 0.7166 (0.7455)	loss 3.3827 (3.3844)	grad_norm 0.8923 (1.2886/0.5546)	mem 34602MB
[2025-01-19 06:18:10 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][130/312]	eta 0:02:18 lr 0.003210	time 0.7167 (0.7587)	model_time 0.7162 (0.7474)	loss 3.8147 (3.3958)	grad_norm 1.3046 (1.2664/0.5410)	mem 34602MB
[2025-01-19 06:18:17 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][140/312]	eta 0:02:10 lr 0.003210	time 0.7339 (0.7588)	model_time 0.7337 (0.7483)	loss 3.4805 (3.3919)	grad_norm 0.9301 (1.2530/0.5266)	mem 34602MB
[2025-01-19 06:18:25 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][150/312]	eta 0:02:03 lr 0.003209	time 0.8112 (0.7598)	model_time 0.8107 (0.7500)	loss 3.7607 (3.4009)	grad_norm 1.2933 (1.2544/0.5148)	mem 34602MB
[2025-01-19 06:18:33 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][160/312]	eta 0:01:55 lr 0.003209	time 0.7282 (0.7595)	model_time 0.7280 (0.7503)	loss 3.5608 (3.4008)	grad_norm 1.5731 (1.2683/0.5174)	mem 34602MB
[2025-01-19 06:18:40 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][170/312]	eta 0:01:47 lr 0.003208	time 0.7254 (0.7584)	model_time 0.7253 (0.7497)	loss 3.4750 (3.3978)	grad_norm 0.9006 (1.2602/0.5072)	mem 34602MB
[2025-01-19 06:18:48 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][180/312]	eta 0:01:39 lr 0.003208	time 0.7210 (0.7573)	model_time 0.7208 (0.7491)	loss 3.1104 (3.4095)	grad_norm 1.1169 (1.2736/0.5069)	mem 34602MB
[2025-01-19 06:18:55 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][190/312]	eta 0:01:32 lr 0.003207	time 0.7182 (0.7574)	model_time 0.7178 (0.7496)	loss 3.2205 (3.4007)	grad_norm 0.8275 (1.2662/0.5014)	mem 34602MB
[2025-01-19 06:19:03 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][200/312]	eta 0:01:24 lr 0.003206	time 0.7175 (0.7565)	model_time 0.7174 (0.7491)	loss 4.2549 (3.4120)	grad_norm 1.0538 (1.2678/0.4993)	mem 34602MB
[2025-01-19 06:19:10 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][210/312]	eta 0:01:17 lr 0.003206	time 0.7286 (0.7553)	model_time 0.7284 (0.7482)	loss 3.9244 (3.4227)	grad_norm 1.1095 (1.2837/0.5014)	mem 34602MB
[2025-01-19 06:19:17 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][220/312]	eta 0:01:09 lr 0.003205	time 0.7189 (0.7541)	model_time 0.7185 (0.7473)	loss 2.3815 (3.4051)	grad_norm 1.0618 (1.2764/0.4937)	mem 34602MB
[2025-01-19 06:19:25 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][230/312]	eta 0:01:01 lr 0.003205	time 0.7219 (0.7534)	model_time 0.7217 (0.7469)	loss 3.8385 (3.4113)	grad_norm 1.0903 (1.2627/0.4887)	mem 34602MB
[2025-01-19 06:19:32 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][240/312]	eta 0:00:54 lr 0.003204	time 0.7159 (0.7528)	model_time 0.7153 (0.7466)	loss 3.5292 (3.4184)	grad_norm 1.5716 (1.2696/0.5025)	mem 34602MB
[2025-01-19 06:19:39 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][250/312]	eta 0:00:46 lr 0.003204	time 0.7186 (0.7527)	model_time 0.7184 (0.7467)	loss 2.8274 (3.4226)	grad_norm 1.4578 (1.2751/0.5042)	mem 34602MB
[2025-01-19 06:19:47 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][260/312]	eta 0:00:39 lr 0.003203	time 0.7249 (0.7532)	model_time 0.7247 (0.7474)	loss 3.5408 (3.4172)	grad_norm 1.5656 (1.2749/0.5012)	mem 34602MB
[2025-01-19 06:19:55 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][270/312]	eta 0:00:31 lr 0.003203	time 0.8159 (0.7536)	model_time 0.8157 (0.7480)	loss 3.4341 (3.4203)	grad_norm 1.3627 (1.2816/0.5011)	mem 34602MB
[2025-01-19 06:20:02 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][280/312]	eta 0:00:24 lr 0.003202	time 0.7253 (0.7532)	model_time 0.7251 (0.7478)	loss 2.9519 (3.4167)	grad_norm 1.0774 (1.2911/0.5015)	mem 34602MB
[2025-01-19 06:20:10 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][290/312]	eta 0:00:16 lr 0.003202	time 0.7165 (0.7529)	model_time 0.7160 (0.7476)	loss 2.9451 (3.4155)	grad_norm 1.5173 (1.2899/0.5008)	mem 34602MB
[2025-01-19 06:20:17 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][300/312]	eta 0:00:09 lr 0.003201	time 0.7125 (0.7524)	model_time 0.7124 (0.7473)	loss 3.1986 (3.4130)	grad_norm 0.9113 (1.2990/0.5112)	mem 34602MB
[2025-01-19 06:20:24 internimage_b_1k_224] (main.py 510): INFO Train: [88/300][310/312]	eta 0:00:01 lr 0.003201	time 0.7156 (0.7515)	model_time 0.7155 (0.7466)	loss 3.2190 (3.4119)	grad_norm 0.6786 (1.3053/0.5073)	mem 34602MB
[2025-01-19 06:20:25 internimage_b_1k_224] (main.py 519): INFO EPOCH 88 training takes 0:03:54
[2025-01-19 06:20:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_88.pth saving......
[2025-01-19 06:20:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_88.pth saved !!!
[2025-01-19 06:20:41 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 12.937 (12.937)	Loss 0.8822 (0.8822)	Acc@1 81.299 (81.299)	Acc@5 96.655 (96.655)	Mem 34602MB
[2025-01-19 06:20:45 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.512)	Loss 1.2726 (1.0430)	Acc@1 72.192 (77.812)	Acc@5 91.455 (94.241)	Mem 34602MB
[2025-01-19 06:20:45 internimage_b_1k_224] (main.py 575): INFO [Epoch:88] * Acc@1 77.783 Acc@5 94.278
[2025-01-19 06:20:45 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.8%
[2025-01-19 06:20:45 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 06:20:48 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 06:20:48 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 77.78%
[2025-01-19 06:20:56 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.198 (7.198)	Loss 0.8438 (0.8438)	Acc@1 80.347 (80.347)	Acc@5 95.581 (95.581)	Mem 34602MB
[2025-01-19 06:20:58 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.906)	Loss 1.2704 (1.0138)	Acc@1 69.824 (76.367)	Acc@5 90.967 (93.466)	Mem 34602MB
[2025-01-19 06:20:59 internimage_b_1k_224] (main.py 575): INFO [Epoch:88] * Acc@1 76.366 Acc@5 93.542
[2025-01-19 06:20:59 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 76.4%
[2025-01-19 06:20:59 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 06:21:02 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 06:21:02 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 76.37%
[2025-01-19 06:21:04 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][0/312]	eta 0:10:39 lr 0.003201	time 2.0509 (2.0509)	model_time 0.7541 (0.7541)	loss 4.1549 (4.1549)	grad_norm 0.7392 (0.7392/0.0000)	mem 34602MB
[2025-01-19 06:21:12 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][10/312]	eta 0:04:21 lr 0.003200	time 0.7252 (0.8643)	model_time 0.7250 (0.7462)	loss 3.3035 (3.5428)	grad_norm 0.7486 (1.1964/0.5305)	mem 34602MB
[2025-01-19 06:21:19 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][20/312]	eta 0:03:54 lr 0.003199	time 0.7355 (0.8030)	model_time 0.7353 (0.7410)	loss 3.7368 (3.4743)	grad_norm 1.9825 (1.5358/0.7574)	mem 34602MB
[2025-01-19 06:21:27 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][30/312]	eta 0:03:40 lr 0.003199	time 0.7483 (0.7824)	model_time 0.7480 (0.7402)	loss 4.1050 (3.4544)	grad_norm 1.2254 (1.4785/0.6889)	mem 34602MB
[2025-01-19 06:21:34 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][40/312]	eta 0:03:29 lr 0.003198	time 0.7092 (0.7694)	model_time 0.7090 (0.7375)	loss 4.1786 (3.4876)	grad_norm 1.2899 (1.4569/0.6662)	mem 34602MB
[2025-01-19 06:21:41 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][50/312]	eta 0:03:20 lr 0.003198	time 0.7209 (0.7642)	model_time 0.7207 (0.7385)	loss 4.0364 (3.4681)	grad_norm 0.7901 (1.5152/0.6565)	mem 34602MB
[2025-01-19 06:21:49 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][60/312]	eta 0:03:13 lr 0.003197	time 0.8128 (0.7665)	model_time 0.8124 (0.7449)	loss 3.8321 (3.4943)	grad_norm 1.0422 (1.4560/0.6293)	mem 34602MB
[2025-01-19 06:21:57 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][70/312]	eta 0:03:05 lr 0.003197	time 0.7467 (0.7675)	model_time 0.7465 (0.7490)	loss 4.0238 (3.4851)	grad_norm 1.1425 (1.3947/0.6090)	mem 34602MB
[2025-01-19 06:22:05 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][80/312]	eta 0:02:58 lr 0.003196	time 0.8099 (0.7694)	model_time 0.8097 (0.7530)	loss 3.5642 (3.4951)	grad_norm 0.7633 (1.3838/0.6074)	mem 34602MB
[2025-01-19 06:22:12 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][90/312]	eta 0:02:50 lr 0.003196	time 0.7181 (0.7663)	model_time 0.7180 (0.7518)	loss 4.1844 (3.5168)	grad_norm 1.2198 (1.4209/0.6342)	mem 34602MB
[2025-01-19 06:22:20 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][100/312]	eta 0:02:41 lr 0.003195	time 0.7242 (0.7634)	model_time 0.7238 (0.7502)	loss 3.0609 (3.5217)	grad_norm 1.5102 (1.4236/0.6162)	mem 34602MB
[2025-01-19 06:22:27 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][110/312]	eta 0:02:33 lr 0.003195	time 0.8150 (0.7618)	model_time 0.8148 (0.7498)	loss 3.7455 (3.5369)	grad_norm 1.5017 (1.4267/0.6004)	mem 34602MB
[2025-01-19 06:22:34 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][120/312]	eta 0:02:25 lr 0.003194	time 0.7178 (0.7600)	model_time 0.7176 (0.7489)	loss 3.7668 (3.5284)	grad_norm 0.8474 (1.4002/0.5853)	mem 34602MB
[2025-01-19 06:22:42 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][130/312]	eta 0:02:18 lr 0.003194	time 0.7397 (0.7590)	model_time 0.7393 (0.7488)	loss 2.8076 (3.5022)	grad_norm 1.2124 (1.3795/0.5698)	mem 34602MB
[2025-01-19 06:22:49 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][140/312]	eta 0:02:10 lr 0.003193	time 0.7407 (0.7572)	model_time 0.7405 (0.7476)	loss 3.0842 (3.4760)	grad_norm 0.8100 (1.3655/0.5696)	mem 34602MB
[2025-01-19 06:22:56 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][150/312]	eta 0:02:02 lr 0.003193	time 0.7235 (0.7550)	model_time 0.7233 (0.7461)	loss 3.5864 (3.4733)	grad_norm 1.2991 (1.3615/0.5550)	mem 34602MB
[2025-01-19 06:23:04 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][160/312]	eta 0:01:54 lr 0.003192	time 0.7296 (0.7539)	model_time 0.7294 (0.7455)	loss 3.1942 (3.4752)	grad_norm 1.7867 (1.3550/0.5464)	mem 34602MB
[2025-01-19 06:23:11 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][170/312]	eta 0:01:46 lr 0.003191	time 0.7180 (0.7528)	model_time 0.7175 (0.7448)	loss 2.6300 (3.4627)	grad_norm 1.0974 (1.3429/0.5360)	mem 34602MB
[2025-01-19 06:23:19 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][180/312]	eta 0:01:39 lr 0.003191	time 0.8142 (0.7531)	model_time 0.8137 (0.7456)	loss 4.0973 (3.4695)	grad_norm 1.5625 (1.3473/0.5289)	mem 34602MB
[2025-01-19 06:23:26 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][190/312]	eta 0:01:31 lr 0.003190	time 0.7127 (0.7525)	model_time 0.7123 (0.7453)	loss 3.1864 (3.4605)	grad_norm 1.7597 (1.3690/0.5471)	mem 34602MB
[2025-01-19 06:23:34 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][200/312]	eta 0:01:24 lr 0.003190	time 0.8071 (0.7533)	model_time 0.8066 (0.7465)	loss 3.7069 (3.4671)	grad_norm 0.8823 (1.3770/0.5484)	mem 34602MB
[2025-01-19 06:23:41 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][210/312]	eta 0:01:16 lr 0.003189	time 0.7186 (0.7532)	model_time 0.7185 (0.7467)	loss 3.2754 (3.4705)	grad_norm 1.5817 (1.3693/0.5452)	mem 34602MB
[2025-01-19 06:23:49 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][220/312]	eta 0:01:09 lr 0.003189	time 0.7252 (0.7533)	model_time 0.7247 (0.7471)	loss 2.9033 (3.4603)	grad_norm 0.7766 (1.3737/0.5518)	mem 34602MB
[2025-01-19 06:23:56 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][230/312]	eta 0:01:01 lr 0.003188	time 0.8083 (0.7528)	model_time 0.8081 (0.7469)	loss 4.1339 (3.4590)	grad_norm 1.6458 (1.3597/0.5485)	mem 34602MB
[2025-01-19 06:24:04 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][240/312]	eta 0:00:54 lr 0.003188	time 0.7223 (0.7523)	model_time 0.7218 (0.7465)	loss 4.2606 (3.4636)	grad_norm 1.7918 (1.3551/0.5453)	mem 34602MB
[2025-01-19 06:24:11 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][250/312]	eta 0:00:46 lr 0.003187	time 0.7189 (0.7516)	model_time 0.7184 (0.7461)	loss 2.9806 (3.4606)	grad_norm 2.0031 (1.3495/0.5448)	mem 34602MB
[2025-01-19 06:24:18 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][260/312]	eta 0:00:39 lr 0.003187	time 0.7209 (0.7508)	model_time 0.7207 (0.7455)	loss 2.9870 (3.4487)	grad_norm 1.6860 (1.3506/0.5476)	mem 34602MB
[2025-01-19 06:24:26 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][270/312]	eta 0:00:31 lr 0.003186	time 0.7169 (0.7499)	model_time 0.7165 (0.7448)	loss 3.2314 (3.4551)	grad_norm 1.9720 (1.3657/0.5479)	mem 34602MB
[2025-01-19 06:24:33 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][280/312]	eta 0:00:23 lr 0.003186	time 0.7193 (0.7491)	model_time 0.7192 (0.7442)	loss 3.6933 (3.4556)	grad_norm 1.1761 (1.3690/0.5421)	mem 34602MB
[2025-01-19 06:24:40 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][290/312]	eta 0:00:16 lr 0.003185	time 0.7192 (0.7483)	model_time 0.7187 (0.7435)	loss 3.9430 (3.4541)	grad_norm 1.6779 (1.3676/0.5353)	mem 34602MB
[2025-01-19 06:24:48 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][300/312]	eta 0:00:08 lr 0.003184	time 0.7939 (0.7487)	model_time 0.7937 (0.7440)	loss 3.9561 (3.4465)	grad_norm 0.7780 (1.3665/0.5346)	mem 34602MB
[2025-01-19 06:24:55 internimage_b_1k_224] (main.py 510): INFO Train: [89/300][310/312]	eta 0:00:01 lr 0.003184	time 0.7927 (0.7487)	model_time 0.7926 (0.7441)	loss 4.2541 (3.4531)	grad_norm 1.2233 (1.3612/0.5312)	mem 34602MB
[2025-01-19 06:24:56 internimage_b_1k_224] (main.py 519): INFO EPOCH 89 training takes 0:03:53
[2025-01-19 06:24:56 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_89.pth saving......
[2025-01-19 06:24:59 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_89.pth saved !!!
[2025-01-19 06:25:06 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.310 (7.310)	Loss 0.9049 (0.9049)	Acc@1 81.738 (81.738)	Acc@5 96.313 (96.313)	Mem 34602MB
[2025-01-19 06:25:09 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.938)	Loss 1.2358 (1.0476)	Acc@1 72.803 (77.987)	Acc@5 92.358 (94.289)	Mem 34602MB
[2025-01-19 06:25:10 internimage_b_1k_224] (main.py 575): INFO [Epoch:89] * Acc@1 77.977 Acc@5 94.344
[2025-01-19 06:25:10 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.0%
[2025-01-19 06:25:10 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 06:25:13 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 06:25:13 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 77.98%
[2025-01-19 06:25:20 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.163 (7.163)	Loss 0.8331 (0.8331)	Acc@1 80.615 (80.615)	Acc@5 95.605 (95.605)	Mem 34602MB
[2025-01-19 06:25:23 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.937)	Loss 1.2571 (1.0030)	Acc@1 70.166 (76.554)	Acc@5 91.040 (93.521)	Mem 34602MB
[2025-01-19 06:25:23 internimage_b_1k_224] (main.py 575): INFO [Epoch:89] * Acc@1 76.554 Acc@5 93.606
[2025-01-19 06:25:23 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 76.6%
[2025-01-19 06:25:23 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 06:25:27 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 06:25:27 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 76.55%
[2025-01-19 06:25:29 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][0/312]	eta 0:10:29 lr 0.003184	time 2.0185 (2.0185)	model_time 0.7639 (0.7639)	loss 2.7664 (2.7664)	grad_norm 1.6266 (1.6266/0.0000)	mem 34602MB
[2025-01-19 06:25:37 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][10/312]	eta 0:04:23 lr 0.003183	time 0.7247 (0.8719)	model_time 0.7246 (0.7576)	loss 3.9661 (3.6708)	grad_norm 0.8376 (1.3809/0.4456)	mem 34602MB
[2025-01-19 06:25:44 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][20/312]	eta 0:03:57 lr 0.003183	time 0.7985 (0.8120)	model_time 0.7981 (0.7519)	loss 3.2740 (3.3805)	grad_norm 0.8960 (1.2773/0.3815)	mem 34602MB
[2025-01-19 06:25:52 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][30/312]	eta 0:03:43 lr 0.003182	time 0.7693 (0.7924)	model_time 0.7691 (0.7516)	loss 3.2500 (3.4104)	grad_norm 0.9110 (1.2368/0.4117)	mem 34602MB
[2025-01-19 06:25:59 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][40/312]	eta 0:03:32 lr 0.003182	time 0.7960 (0.7806)	model_time 0.7958 (0.7496)	loss 2.8038 (3.4005)	grad_norm 0.7430 (1.2732/0.5270)	mem 34602MB
[2025-01-19 06:26:07 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][50/312]	eta 0:03:22 lr 0.003181	time 0.7216 (0.7724)	model_time 0.7214 (0.7475)	loss 3.8879 (3.4040)	grad_norm 0.9685 (1.2567/0.5082)	mem 34602MB
[2025-01-19 06:26:14 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][60/312]	eta 0:03:13 lr 0.003181	time 0.7336 (0.7663)	model_time 0.7332 (0.7454)	loss 4.1628 (3.3659)	grad_norm 0.9717 (1.2823/0.4911)	mem 34602MB
[2025-01-19 06:26:21 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][70/312]	eta 0:03:04 lr 0.003180	time 0.7185 (0.7608)	model_time 0.7183 (0.7427)	loss 3.6530 (3.4155)	grad_norm 1.0708 (1.2992/0.4972)	mem 34602MB
[2025-01-19 06:26:29 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][80/312]	eta 0:02:55 lr 0.003180	time 0.7608 (0.7570)	model_time 0.7606 (0.7412)	loss 3.8877 (3.4142)	grad_norm 1.1772 (1.3518/0.5566)	mem 34602MB
[2025-01-19 06:26:36 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][90/312]	eta 0:02:47 lr 0.003179	time 0.7104 (0.7541)	model_time 0.7102 (0.7400)	loss 3.9953 (3.4198)	grad_norm 1.1396 (1.3643/0.5407)	mem 34602MB
[2025-01-19 06:26:43 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][100/312]	eta 0:02:39 lr 0.003178	time 0.7951 (0.7524)	model_time 0.7949 (0.7396)	loss 3.5134 (3.4379)	grad_norm 0.9621 (1.3214/0.5330)	mem 34602MB
[2025-01-19 06:26:51 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][110/312]	eta 0:02:31 lr 0.003178	time 0.8354 (0.7523)	model_time 0.8349 (0.7406)	loss 3.3556 (3.4331)	grad_norm 0.5949 (1.3349/0.5599)	mem 34602MB
[2025-01-19 06:26:58 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][120/312]	eta 0:02:24 lr 0.003177	time 0.7309 (0.7517)	model_time 0.7304 (0.7410)	loss 3.6863 (3.4265)	grad_norm 0.6297 (1.3198/0.5441)	mem 34602MB
[2025-01-19 06:27:06 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][130/312]	eta 0:02:16 lr 0.003177	time 0.7165 (0.7516)	model_time 0.7163 (0.7416)	loss 3.1754 (3.4292)	grad_norm 0.9276 (1.3158/0.5464)	mem 34602MB
[2025-01-19 06:27:13 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][140/312]	eta 0:02:09 lr 0.003176	time 0.8027 (0.7518)	model_time 0.8026 (0.7425)	loss 3.2334 (3.4092)	grad_norm 2.1168 (1.3169/0.5428)	mem 34602MB
[2025-01-19 06:27:21 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][150/312]	eta 0:02:01 lr 0.003176	time 0.8120 (0.7526)	model_time 0.8115 (0.7439)	loss 3.7602 (3.4262)	grad_norm 1.3905 (1.3698/0.6220)	mem 34602MB
[2025-01-19 06:27:28 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][160/312]	eta 0:01:54 lr 0.003175	time 0.7181 (0.7514)	model_time 0.7179 (0.7432)	loss 2.1716 (3.4157)	grad_norm 1.8636 (1.3692/0.6132)	mem 34602MB
[2025-01-19 06:27:36 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][170/312]	eta 0:01:46 lr 0.003175	time 0.7238 (0.7511)	model_time 0.7236 (0.7434)	loss 3.3993 (3.4140)	grad_norm 0.7536 (1.3408/0.6085)	mem 34602MB
[2025-01-19 06:27:43 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][180/312]	eta 0:01:39 lr 0.003174	time 0.7216 (0.7509)	model_time 0.7212 (0.7436)	loss 4.1031 (3.4294)	grad_norm 1.0434 (1.3753/0.6279)	mem 34602MB
[2025-01-19 06:27:50 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][190/312]	eta 0:01:31 lr 0.003174	time 0.7199 (0.7496)	model_time 0.7198 (0.7426)	loss 3.4183 (3.4386)	grad_norm 1.7293 (1.3774/0.6171)	mem 34602MB
[2025-01-19 06:27:58 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][200/312]	eta 0:01:23 lr 0.003173	time 0.7223 (0.7483)	model_time 0.7219 (0.7417)	loss 3.1880 (3.4424)	grad_norm 1.0815 (1.3737/0.6119)	mem 34602MB
[2025-01-19 06:28:05 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][210/312]	eta 0:01:16 lr 0.003172	time 0.7102 (0.7476)	model_time 0.7098 (0.7413)	loss 3.9643 (3.4328)	grad_norm 1.6096 (1.3859/0.6130)	mem 34602MB
[2025-01-19 06:28:12 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][220/312]	eta 0:01:08 lr 0.003172	time 0.8402 (0.7471)	model_time 0.8400 (0.7410)	loss 3.7809 (3.4290)	grad_norm 1.4057 (1.3707/0.6058)	mem 34602MB
[2025-01-19 06:28:20 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][230/312]	eta 0:01:01 lr 0.003171	time 0.8081 (0.7471)	model_time 0.8080 (0.7413)	loss 3.7360 (3.4353)	grad_norm 1.0495 (1.3589/0.5981)	mem 34602MB
[2025-01-19 06:28:27 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][240/312]	eta 0:00:53 lr 0.003171	time 0.7157 (0.7473)	model_time 0.7155 (0.7417)	loss 3.7421 (3.4307)	grad_norm 0.7995 (1.3433/0.5947)	mem 34602MB
[2025-01-19 06:28:35 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][250/312]	eta 0:00:46 lr 0.003170	time 0.7159 (0.7474)	model_time 0.7158 (0.7420)	loss 2.5831 (3.4313)	grad_norm 0.8060 (1.3449/0.5935)	mem 34602MB
[2025-01-19 06:28:43 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][260/312]	eta 0:00:38 lr 0.003170	time 0.7965 (0.7482)	model_time 0.7961 (0.7430)	loss 2.9649 (3.4263)	grad_norm 0.6568 (1.3331/0.5902)	mem 34602MB
[2025-01-19 06:28:50 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][270/312]	eta 0:00:31 lr 0.003169	time 0.8077 (0.7480)	model_time 0.8075 (0.7430)	loss 3.3903 (3.4162)	grad_norm 1.6191 (1.3492/0.6094)	mem 34602MB
[2025-01-19 06:28:57 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][280/312]	eta 0:00:23 lr 0.003169	time 0.7278 (0.7475)	model_time 0.7276 (0.7426)	loss 2.5336 (3.4228)	grad_norm 1.3545 (1.3511/0.6076)	mem 34602MB
[2025-01-19 06:29:05 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][290/312]	eta 0:00:16 lr 0.003168	time 0.7350 (0.7480)	model_time 0.7348 (0.7433)	loss 3.8121 (3.4308)	grad_norm 1.3484 (1.3413/0.6021)	mem 34602MB
[2025-01-19 06:29:12 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][300/312]	eta 0:00:08 lr 0.003168	time 0.7134 (0.7475)	model_time 0.7133 (0.7429)	loss 3.2608 (3.4307)	grad_norm 1.8554 (1.3553/0.6082)	mem 34602MB
[2025-01-19 06:29:19 internimage_b_1k_224] (main.py 510): INFO Train: [90/300][310/312]	eta 0:00:01 lr 0.003167	time 0.7210 (0.7466)	model_time 0.7209 (0.7422)	loss 2.8124 (3.4256)	grad_norm 4.0585 (1.3717/0.6346)	mem 34602MB
[2025-01-19 06:29:20 internimage_b_1k_224] (main.py 519): INFO EPOCH 90 training takes 0:03:52
[2025-01-19 06:29:20 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_90.pth saving......
[2025-01-19 06:29:23 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_90.pth saved !!!
[2025-01-19 06:29:31 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.201 (7.201)	Loss 0.8989 (0.8989)	Acc@1 81.250 (81.250)	Acc@5 96.191 (96.191)	Mem 34602MB
[2025-01-19 06:29:34 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.915)	Loss 1.2223 (1.0416)	Acc@1 72.949 (78.167)	Acc@5 92.114 (94.283)	Mem 34602MB
[2025-01-19 06:29:34 internimage_b_1k_224] (main.py 575): INFO [Epoch:90] * Acc@1 78.103 Acc@5 94.318
[2025-01-19 06:29:34 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.1%
[2025-01-19 06:29:34 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 06:29:37 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 06:29:37 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 78.10%
[2025-01-19 06:29:44 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.443 (7.443)	Loss 0.8229 (0.8229)	Acc@1 80.713 (80.713)	Acc@5 95.679 (95.679)	Mem 34602MB
[2025-01-19 06:29:47 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.943)	Loss 1.2446 (0.9926)	Acc@1 70.288 (76.709)	Acc@5 91.138 (93.595)	Mem 34602MB
[2025-01-19 06:29:48 internimage_b_1k_224] (main.py 575): INFO [Epoch:90] * Acc@1 76.709 Acc@5 93.680
[2025-01-19 06:29:48 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 76.7%
[2025-01-19 06:29:48 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 06:29:51 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 06:29:51 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 76.71%
[2025-01-19 06:29:54 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][0/312]	eta 0:11:15 lr 0.003167	time 2.1654 (2.1654)	model_time 0.7538 (0.7538)	loss 3.0653 (3.0653)	grad_norm 3.3303 (3.3303/0.0000)	mem 34602MB
[2025-01-19 06:30:01 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][10/312]	eta 0:04:20 lr 0.003166	time 0.7441 (0.8610)	model_time 0.7440 (0.7323)	loss 4.2223 (3.4265)	grad_norm 0.9696 (1.5052/0.7702)	mem 34602MB
[2025-01-19 06:30:08 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][20/312]	eta 0:03:53 lr 0.003166	time 0.7288 (0.7984)	model_time 0.7283 (0.7308)	loss 3.7213 (3.3713)	grad_norm 1.3786 (1.2601/0.6302)	mem 34602MB
[2025-01-19 06:30:16 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][30/312]	eta 0:03:40 lr 0.003165	time 0.7160 (0.7806)	model_time 0.7155 (0.7347)	loss 3.4904 (3.3915)	grad_norm 0.8697 (1.2032/0.5726)	mem 34602MB
[2025-01-19 06:30:23 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][40/312]	eta 0:03:31 lr 0.003165	time 0.8330 (0.7772)	model_time 0.8328 (0.7424)	loss 2.8571 (3.3748)	grad_norm 1.5519 (1.1880/0.5561)	mem 34602MB
[2025-01-19 06:30:31 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][50/312]	eta 0:03:21 lr 0.003164	time 0.7288 (0.7692)	model_time 0.7287 (0.7412)	loss 3.5800 (3.3473)	grad_norm 0.8510 (1.1948/0.5297)	mem 34602MB
[2025-01-19 06:30:38 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][60/312]	eta 0:03:13 lr 0.003164	time 0.8066 (0.7694)	model_time 0.8062 (0.7458)	loss 2.8730 (3.3519)	grad_norm 2.0491 (1.2325/0.5224)	mem 34602MB
[2025-01-19 06:30:46 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][70/312]	eta 0:03:05 lr 0.003163	time 0.8147 (0.7677)	model_time 0.8142 (0.7475)	loss 3.6425 (3.3746)	grad_norm 1.6454 (1.2997/0.5969)	mem 34602MB
[2025-01-19 06:30:53 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][80/312]	eta 0:02:57 lr 0.003163	time 0.7176 (0.7636)	model_time 0.7175 (0.7459)	loss 3.4230 (3.3682)	grad_norm 0.7028 (1.2442/0.5801)	mem 34602MB
[2025-01-19 06:31:01 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][90/312]	eta 0:02:48 lr 0.003162	time 0.7432 (0.7610)	model_time 0.7430 (0.7451)	loss 3.7261 (3.3602)	grad_norm 1.0928 (1.2217/0.5534)	mem 34602MB
[2025-01-19 06:31:08 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][100/312]	eta 0:02:40 lr 0.003162	time 0.7207 (0.7594)	model_time 0.7205 (0.7450)	loss 3.2066 (3.3767)	grad_norm 2.1855 (1.2870/0.6188)	mem 34602MB
[2025-01-19 06:31:15 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][110/312]	eta 0:02:32 lr 0.003161	time 0.7334 (0.7570)	model_time 0.7329 (0.7439)	loss 3.7848 (3.3867)	grad_norm 2.1715 (1.2889/0.6023)	mem 34602MB
[2025-01-19 06:31:23 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][120/312]	eta 0:02:24 lr 0.003160	time 0.7331 (0.7545)	model_time 0.7326 (0.7425)	loss 3.4915 (3.4064)	grad_norm 1.2039 (1.2728/0.5863)	mem 34602MB
[2025-01-19 06:31:30 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][130/312]	eta 0:02:16 lr 0.003160	time 0.7118 (0.7522)	model_time 0.7113 (0.7410)	loss 3.3929 (3.3967)	grad_norm 0.9569 (1.2798/0.5806)	mem 34602MB
[2025-01-19 06:31:37 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][140/312]	eta 0:02:09 lr 0.003159	time 0.7222 (0.7509)	model_time 0.7220 (0.7406)	loss 3.6454 (3.4047)	grad_norm 1.1172 (1.3143/0.6093)	mem 34602MB
[2025-01-19 06:31:45 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][150/312]	eta 0:02:01 lr 0.003159	time 0.7150 (0.7497)	model_time 0.7148 (0.7400)	loss 4.1255 (3.4153)	grad_norm 0.9295 (1.2920/0.5986)	mem 34602MB
[2025-01-19 06:31:52 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][160/312]	eta 0:01:54 lr 0.003158	time 0.7238 (0.7503)	model_time 0.7236 (0.7412)	loss 4.2192 (3.4190)	grad_norm 0.8722 (1.2792/0.5877)	mem 34602MB
[2025-01-19 06:32:00 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][170/312]	eta 0:01:46 lr 0.003158	time 0.7226 (0.7507)	model_time 0.7225 (0.7421)	loss 3.3450 (3.4301)	grad_norm 1.7065 (1.2902/0.5935)	mem 34602MB
[2025-01-19 06:32:07 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][180/312]	eta 0:01:39 lr 0.003157	time 0.8069 (0.7513)	model_time 0.8065 (0.7432)	loss 4.0523 (3.4184)	grad_norm 0.9479 (1.2776/0.5827)	mem 34602MB
[2025-01-19 06:32:15 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][190/312]	eta 0:01:31 lr 0.003157	time 0.8102 (0.7523)	model_time 0.8101 (0.7445)	loss 3.5799 (3.4269)	grad_norm 1.2693 (1.2645/0.5725)	mem 34602MB
[2025-01-19 06:32:22 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][200/312]	eta 0:01:24 lr 0.003156	time 0.7729 (0.7515)	model_time 0.7725 (0.7441)	loss 3.6367 (3.4298)	grad_norm 1.1015 (1.2860/0.5756)	mem 34602MB
[2025-01-19 06:32:30 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][210/312]	eta 0:01:16 lr 0.003156	time 0.7182 (0.7509)	model_time 0.7180 (0.7439)	loss 3.7745 (3.4336)	grad_norm 0.8721 (1.2773/0.5663)	mem 34602MB
[2025-01-19 06:32:38 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][220/312]	eta 0:01:09 lr 0.003155	time 0.7166 (0.7515)	model_time 0.7161 (0.7447)	loss 4.1944 (3.4467)	grad_norm 0.8652 (1.2536/0.5652)	mem 34602MB
[2025-01-19 06:32:45 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][230/312]	eta 0:01:01 lr 0.003154	time 0.7094 (0.7509)	model_time 0.7092 (0.7445)	loss 4.6541 (3.4626)	grad_norm 0.8338 (1.2534/0.5603)	mem 34602MB
[2025-01-19 06:32:52 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][240/312]	eta 0:00:54 lr 0.003154	time 0.7327 (0.7502)	model_time 0.7322 (0.7440)	loss 3.7859 (3.4568)	grad_norm 1.0851 (1.2480/0.5521)	mem 34602MB
[2025-01-19 06:33:00 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][250/312]	eta 0:00:46 lr 0.003153	time 0.7329 (0.7493)	model_time 0.7327 (0.7433)	loss 2.3265 (3.4583)	grad_norm 0.8843 (1.2456/0.5462)	mem 34602MB
[2025-01-19 06:33:07 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][260/312]	eta 0:00:38 lr 0.003153	time 0.7220 (0.7486)	model_time 0.7218 (0.7429)	loss 2.8687 (3.4586)	grad_norm 1.3654 (1.2683/0.5566)	mem 34602MB
[2025-01-19 06:33:14 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][270/312]	eta 0:00:31 lr 0.003152	time 0.7202 (0.7482)	model_time 0.7197 (0.7426)	loss 3.3367 (3.4648)	grad_norm 1.2275 (1.2722/0.5520)	mem 34602MB
[2025-01-19 06:33:22 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][280/312]	eta 0:00:23 lr 0.003152	time 0.7206 (0.7487)	model_time 0.7205 (0.7433)	loss 3.0408 (3.4563)	grad_norm 1.1753 (1.2682/0.5456)	mem 34602MB
[2025-01-19 06:33:29 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][290/312]	eta 0:00:16 lr 0.003151	time 0.7103 (0.7486)	model_time 0.7101 (0.7434)	loss 3.2550 (3.4599)	grad_norm 1.3096 (1.2691/0.5447)	mem 34602MB
[2025-01-19 06:33:37 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][300/312]	eta 0:00:08 lr 0.003151	time 0.7947 (0.7486)	model_time 0.7946 (0.7435)	loss 4.0667 (3.4612)	grad_norm 0.7736 (1.2559/0.5255)	mem 34602MB
[2025-01-19 06:33:44 internimage_b_1k_224] (main.py 510): INFO Train: [91/300][310/312]	eta 0:00:01 lr 0.003150	time 0.7150 (0.7485)	model_time 0.7148 (0.7436)	loss 4.2397 (3.4667)	grad_norm 0.9055 (1.2552/0.5255)	mem 34602MB
[2025-01-19 06:33:45 internimage_b_1k_224] (main.py 519): INFO EPOCH 91 training takes 0:03:53
[2025-01-19 06:33:45 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_91.pth saving......
[2025-01-19 06:33:48 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_91.pth saved !!!
[2025-01-19 06:33:56 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.369 (7.369)	Loss 0.8505 (0.8505)	Acc@1 82.007 (82.007)	Acc@5 96.729 (96.729)	Mem 34602MB
[2025-01-19 06:33:59 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.932)	Loss 1.1998 (1.0124)	Acc@1 74.170 (78.152)	Acc@5 91.992 (94.354)	Mem 34602MB
[2025-01-19 06:33:59 internimage_b_1k_224] (main.py 575): INFO [Epoch:91] * Acc@1 78.031 Acc@5 94.358
[2025-01-19 06:33:59 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.0%
[2025-01-19 06:33:59 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 78.10%
[2025-01-19 06:34:08 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.857 (8.857)	Loss 0.8134 (0.8134)	Acc@1 80.762 (80.762)	Acc@5 95.825 (95.825)	Mem 34602MB
[2025-01-19 06:34:12 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.205)	Loss 1.2317 (0.9826)	Acc@1 70.483 (76.818)	Acc@5 91.235 (93.681)	Mem 34602MB
[2025-01-19 06:34:12 internimage_b_1k_224] (main.py 575): INFO [Epoch:91] * Acc@1 76.831 Acc@5 93.760
[2025-01-19 06:34:12 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 76.8%
[2025-01-19 06:34:12 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 06:34:16 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 06:34:16 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 76.83%
[2025-01-19 06:34:18 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][0/312]	eta 0:10:41 lr 0.003150	time 2.0564 (2.0564)	model_time 0.7456 (0.7456)	loss 4.1723 (4.1723)	grad_norm 0.9611 (0.9611/0.0000)	mem 34602MB
[2025-01-19 06:34:25 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][10/312]	eta 0:04:20 lr 0.003149	time 0.7248 (0.8618)	model_time 0.7244 (0.7423)	loss 3.8823 (3.3454)	grad_norm 1.2161 (0.9839/0.2229)	mem 34602MB
[2025-01-19 06:34:33 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][20/312]	eta 0:03:55 lr 0.003149	time 0.7244 (0.8062)	model_time 0.7243 (0.7435)	loss 2.4174 (3.4256)	grad_norm 1.6717 (1.1190/0.3259)	mem 34602MB
[2025-01-19 06:34:40 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][30/312]	eta 0:03:41 lr 0.003148	time 0.7239 (0.7864)	model_time 0.7237 (0.7438)	loss 4.2258 (3.4933)	grad_norm 1.3779 (1.2147/0.3930)	mem 34602MB
[2025-01-19 06:34:48 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][40/312]	eta 0:03:30 lr 0.003148	time 0.7367 (0.7754)	model_time 0.7365 (0.7431)	loss 3.9905 (3.4338)	grad_norm 1.3336 (1.2700/0.4056)	mem 34602MB
[2025-01-19 06:34:55 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][50/312]	eta 0:03:21 lr 0.003147	time 0.7262 (0.7684)	model_time 0.7261 (0.7424)	loss 3.0354 (3.4373)	grad_norm 0.9753 (1.2319/0.3988)	mem 34602MB
[2025-01-19 06:35:02 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][60/312]	eta 0:03:12 lr 0.003147	time 0.7413 (0.7621)	model_time 0.7412 (0.7403)	loss 2.8170 (3.3916)	grad_norm 1.4635 (1.2191/0.3784)	mem 34602MB
[2025-01-19 06:35:10 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][70/312]	eta 0:03:03 lr 0.003146	time 0.7208 (0.7579)	model_time 0.7207 (0.7391)	loss 2.9753 (3.3577)	grad_norm 1.9559 (1.2468/0.4224)	mem 34602MB
[2025-01-19 06:35:17 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][80/312]	eta 0:02:55 lr 0.003146	time 0.8028 (0.7565)	model_time 0.8024 (0.7400)	loss 2.7771 (3.3464)	grad_norm 0.8965 (1.2486/0.4123)	mem 34602MB
[2025-01-19 06:35:25 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][90/312]	eta 0:02:47 lr 0.003145	time 0.8376 (0.7563)	model_time 0.8374 (0.7415)	loss 2.4127 (3.3616)	grad_norm 1.6560 (1.2483/0.4167)	mem 34602MB
[2025-01-19 06:35:32 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][100/312]	eta 0:02:40 lr 0.003145	time 0.7216 (0.7557)	model_time 0.7212 (0.7424)	loss 3.4758 (3.3750)	grad_norm 0.9299 (1.3136/0.4986)	mem 34602MB
[2025-01-19 06:35:40 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][110/312]	eta 0:02:32 lr 0.003144	time 0.7999 (0.7560)	model_time 0.7998 (0.7438)	loss 3.8628 (3.3788)	grad_norm 1.1259 (1.2806/0.4963)	mem 34602MB
[2025-01-19 06:35:48 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][120/312]	eta 0:02:25 lr 0.003143	time 0.7179 (0.7565)	model_time 0.7177 (0.7453)	loss 3.5402 (3.3827)	grad_norm 1.4664 (1.3038/0.5147)	mem 34602MB
[2025-01-19 06:35:55 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][130/312]	eta 0:02:17 lr 0.003143	time 0.7203 (0.7552)	model_time 0.7202 (0.7448)	loss 3.5590 (3.3890)	grad_norm 1.7660 (1.3271/0.5312)	mem 34602MB
[2025-01-19 06:36:02 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][140/312]	eta 0:02:09 lr 0.003142	time 0.7386 (0.7553)	model_time 0.7384 (0.7457)	loss 3.2436 (3.3809)	grad_norm 1.1654 (1.3131/0.5219)	mem 34602MB
[2025-01-19 06:36:10 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][150/312]	eta 0:02:02 lr 0.003142	time 0.7112 (0.7559)	model_time 0.7110 (0.7469)	loss 3.6158 (3.3997)	grad_norm 1.2257 (1.3120/0.5132)	mem 34602MB
[2025-01-19 06:36:18 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][160/312]	eta 0:01:54 lr 0.003141	time 0.7629 (0.7548)	model_time 0.7628 (0.7463)	loss 3.7893 (3.4177)	grad_norm 1.0013 (1.3321/0.5364)	mem 34602MB
[2025-01-19 06:36:25 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][170/312]	eta 0:01:47 lr 0.003141	time 0.7165 (0.7538)	model_time 0.7160 (0.7458)	loss 3.0315 (3.4311)	grad_norm 0.8513 (1.3491/0.5532)	mem 34602MB
[2025-01-19 06:36:32 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][180/312]	eta 0:01:39 lr 0.003140	time 0.7148 (0.7522)	model_time 0.7145 (0.7446)	loss 2.3452 (3.4277)	grad_norm 1.9021 (1.3319/0.5495)	mem 34602MB
[2025-01-19 06:36:39 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][190/312]	eta 0:01:31 lr 0.003140	time 0.7225 (0.7511)	model_time 0.7220 (0.7439)	loss 2.5358 (3.4129)	grad_norm 1.1205 (1.3474/0.5680)	mem 34602MB
[2025-01-19 06:36:47 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][200/312]	eta 0:01:24 lr 0.003139	time 0.8136 (0.7507)	model_time 0.8134 (0.7439)	loss 3.2677 (3.4089)	grad_norm 0.8333 (1.3491/0.5633)	mem 34602MB
[2025-01-19 06:36:54 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][210/312]	eta 0:01:16 lr 0.003139	time 0.8103 (0.7507)	model_time 0.8102 (0.7441)	loss 3.6088 (3.4051)	grad_norm 0.8795 (1.3337/0.5581)	mem 34602MB
[2025-01-19 06:37:02 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][220/312]	eta 0:01:09 lr 0.003138	time 0.7091 (0.7508)	model_time 0.7087 (0.7445)	loss 2.9106 (3.3934)	grad_norm 0.9780 (1.3252/0.5487)	mem 34602MB
[2025-01-19 06:37:09 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][230/312]	eta 0:01:01 lr 0.003137	time 0.8226 (0.7508)	model_time 0.8224 (0.7448)	loss 3.7049 (3.3977)	grad_norm 1.8714 (1.3216/0.5467)	mem 34602MB
[2025-01-19 06:37:17 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][240/312]	eta 0:00:54 lr 0.003137	time 0.7159 (0.7511)	model_time 0.7155 (0.7453)	loss 2.8680 (3.3954)	grad_norm 0.9265 (1.3342/0.5571)	mem 34602MB
[2025-01-19 06:37:24 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][250/312]	eta 0:00:46 lr 0.003136	time 0.7184 (0.7508)	model_time 0.7182 (0.7452)	loss 3.7668 (3.3886)	grad_norm 0.6226 (1.3265/0.5510)	mem 34602MB
[2025-01-19 06:37:32 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][260/312]	eta 0:00:39 lr 0.003136	time 0.7303 (0.7504)	model_time 0.7298 (0.7450)	loss 4.0539 (3.3981)	grad_norm 0.7788 (1.3272/0.5485)	mem 34602MB
[2025-01-19 06:37:39 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][270/312]	eta 0:00:31 lr 0.003135	time 0.7088 (0.7501)	model_time 0.7086 (0.7450)	loss 2.4483 (3.3956)	grad_norm 0.9814 (1.3203/0.5424)	mem 34602MB
[2025-01-19 06:37:47 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][280/312]	eta 0:00:23 lr 0.003135	time 0.7215 (0.7498)	model_time 0.7213 (0.7448)	loss 3.9260 (3.4029)	grad_norm 1.1892 (1.3250/0.5475)	mem 34602MB
[2025-01-19 06:37:54 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][290/312]	eta 0:00:16 lr 0.003134	time 0.7211 (0.7493)	model_time 0.7209 (0.7444)	loss 4.1481 (3.4018)	grad_norm 0.8933 (1.3252/0.5460)	mem 34602MB
[2025-01-19 06:38:01 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][300/312]	eta 0:00:08 lr 0.003134	time 0.7140 (0.7483)	model_time 0.7139 (0.7436)	loss 4.1594 (3.4024)	grad_norm 0.5652 (1.3288/0.5443)	mem 34602MB
[2025-01-19 06:38:08 internimage_b_1k_224] (main.py 510): INFO Train: [92/300][310/312]	eta 0:00:01 lr 0.003133	time 0.7806 (0.7476)	model_time 0.7804 (0.7430)	loss 3.6920 (3.3974)	grad_norm 1.5056 (1.3373/0.5447)	mem 34602MB
[2025-01-19 06:38:09 internimage_b_1k_224] (main.py 519): INFO EPOCH 92 training takes 0:03:53
[2025-01-19 06:38:09 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_92.pth saving......
[2025-01-19 06:38:12 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_92.pth saved !!!
[2025-01-19 06:38:20 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.308 (7.308)	Loss 0.8522 (0.8522)	Acc@1 81.323 (81.323)	Acc@5 96.191 (96.191)	Mem 34602MB
[2025-01-19 06:38:23 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.935)	Loss 1.1914 (1.0159)	Acc@1 74.194 (78.105)	Acc@5 92.651 (94.376)	Mem 34602MB
[2025-01-19 06:38:23 internimage_b_1k_224] (main.py 575): INFO [Epoch:92] * Acc@1 78.061 Acc@5 94.424
[2025-01-19 06:38:23 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.1%
[2025-01-19 06:38:23 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 78.10%
[2025-01-19 06:38:35 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 12.509 (12.509)	Loss 0.8041 (0.8041)	Acc@1 80.811 (80.811)	Acc@5 95.850 (95.850)	Mem 34602MB
[2025-01-19 06:38:45 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.974)	Loss 1.2198 (0.9731)	Acc@1 70.752 (76.978)	Acc@5 91.284 (93.759)	Mem 34602MB
[2025-01-19 06:38:45 internimage_b_1k_224] (main.py 575): INFO [Epoch:92] * Acc@1 76.977 Acc@5 93.832
[2025-01-19 06:38:45 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 77.0%
[2025-01-19 06:38:45 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 06:38:49 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 06:38:49 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 76.98%
[2025-01-19 06:38:51 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][0/312]	eta 0:11:52 lr 0.003133	time 2.2821 (2.2821)	model_time 0.7472 (0.7472)	loss 3.8510 (3.8510)	grad_norm 1.1262 (1.1262/0.0000)	mem 34602MB
[2025-01-19 06:38:58 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][10/312]	eta 0:04:28 lr 0.003132	time 0.7235 (0.8894)	model_time 0.7234 (0.7496)	loss 3.6491 (3.4875)	grad_norm 0.9192 (1.1608/0.4452)	mem 34602MB
[2025-01-19 06:39:06 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][20/312]	eta 0:04:00 lr 0.003132	time 0.7243 (0.8245)	model_time 0.7241 (0.7511)	loss 2.9439 (3.4529)	grad_norm 1.3142 (1.2283/0.5095)	mem 34602MB
[2025-01-19 06:39:14 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][30/312]	eta 0:03:47 lr 0.003131	time 0.7210 (0.8060)	model_time 0.7208 (0.7562)	loss 3.5778 (3.4432)	grad_norm 1.1976 (1.2368/0.4589)	mem 34602MB
[2025-01-19 06:39:21 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][40/312]	eta 0:03:35 lr 0.003131	time 0.7189 (0.7934)	model_time 0.7187 (0.7556)	loss 2.7566 (3.4323)	grad_norm 1.3479 (1.4577/0.7826)	mem 34602MB
[2025-01-19 06:39:29 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][50/312]	eta 0:03:25 lr 0.003130	time 0.7097 (0.7836)	model_time 0.7092 (0.7532)	loss 2.7076 (3.4778)	grad_norm 0.6927 (1.4867/0.7597)	mem 34602MB
[2025-01-19 06:39:36 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][60/312]	eta 0:03:16 lr 0.003130	time 0.8154 (0.7796)	model_time 0.8153 (0.7542)	loss 3.2317 (3.4237)	grad_norm 0.7177 (1.4072/0.7294)	mem 34602MB
[2025-01-19 06:39:44 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][70/312]	eta 0:03:07 lr 0.003129	time 0.7468 (0.7757)	model_time 0.7466 (0.7538)	loss 4.2780 (3.4630)	grad_norm 1.2699 (1.3326/0.7040)	mem 34602MB
[2025-01-19 06:39:51 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][80/312]	eta 0:02:58 lr 0.003129	time 0.7168 (0.7714)	model_time 0.7166 (0.7522)	loss 3.2681 (3.4492)	grad_norm 1.7927 (1.3371/0.6753)	mem 34602MB
[2025-01-19 06:39:58 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][90/312]	eta 0:02:50 lr 0.003128	time 0.7197 (0.7673)	model_time 0.7195 (0.7501)	loss 2.2069 (3.4287)	grad_norm 2.1623 (1.3514/0.6473)	mem 34602MB
[2025-01-19 06:40:06 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][100/312]	eta 0:02:41 lr 0.003127	time 0.7570 (0.7638)	model_time 0.7569 (0.7483)	loss 2.2234 (3.4252)	grad_norm 1.1884 (1.3299/0.6274)	mem 34602MB
[2025-01-19 06:40:13 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][110/312]	eta 0:02:33 lr 0.003127	time 0.7234 (0.7606)	model_time 0.7229 (0.7464)	loss 3.3111 (3.4116)	grad_norm 0.8326 (1.3047/0.6157)	mem 34602MB
[2025-01-19 06:40:20 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][120/312]	eta 0:02:25 lr 0.003126	time 0.7194 (0.7585)	model_time 0.7191 (0.7455)	loss 3.5224 (3.4034)	grad_norm 3.0443 (1.3070/0.6172)	mem 34602MB
[2025-01-19 06:40:28 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][130/312]	eta 0:02:17 lr 0.003126	time 0.7273 (0.7576)	model_time 0.7269 (0.7456)	loss 3.8508 (3.4245)	grad_norm 0.9531 (1.3202/0.6040)	mem 34602MB
[2025-01-19 06:40:35 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][140/312]	eta 0:02:10 lr 0.003125	time 0.8157 (0.7570)	model_time 0.8156 (0.7457)	loss 3.8053 (3.4269)	grad_norm 0.9454 (1.3087/0.5859)	mem 34602MB
[2025-01-19 06:40:43 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][150/312]	eta 0:02:02 lr 0.003125	time 0.7386 (0.7571)	model_time 0.7382 (0.7466)	loss 3.5360 (3.4222)	grad_norm 0.8731 (1.3383/0.6060)	mem 34602MB
[2025-01-19 06:40:50 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][160/312]	eta 0:01:54 lr 0.003124	time 0.7188 (0.7561)	model_time 0.7187 (0.7463)	loss 3.4014 (3.4241)	grad_norm 1.0457 (1.3354/0.6010)	mem 34602MB
[2025-01-19 06:40:58 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][170/312]	eta 0:01:47 lr 0.003124	time 0.7218 (0.7562)	model_time 0.7217 (0.7469)	loss 4.0182 (3.4280)	grad_norm 1.8273 (1.3192/0.5915)	mem 34602MB
[2025-01-19 06:41:06 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][180/312]	eta 0:01:39 lr 0.003123	time 0.7968 (0.7560)	model_time 0.7967 (0.7472)	loss 3.4488 (3.4167)	grad_norm 1.7290 (1.3464/0.6106)	mem 34602MB
[2025-01-19 06:41:13 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][190/312]	eta 0:01:32 lr 0.003122	time 0.7161 (0.7548)	model_time 0.7156 (0.7464)	loss 3.5994 (3.4223)	grad_norm 1.4564 (1.3727/0.6235)	mem 34602MB
[2025-01-19 06:41:20 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][200/312]	eta 0:01:24 lr 0.003122	time 0.7173 (0.7541)	model_time 0.7172 (0.7461)	loss 3.6923 (3.4169)	grad_norm 0.7977 (1.3592/0.6174)	mem 34602MB
[2025-01-19 06:41:28 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][210/312]	eta 0:01:16 lr 0.003121	time 0.7094 (0.7533)	model_time 0.7093 (0.7456)	loss 3.7467 (3.4113)	grad_norm 1.2475 (1.3584/0.6065)	mem 34602MB
[2025-01-19 06:41:35 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][220/312]	eta 0:01:09 lr 0.003121	time 0.7316 (0.7523)	model_time 0.7314 (0.7450)	loss 3.6835 (3.4179)	grad_norm 0.8125 (1.3501/0.5981)	mem 34602MB
[2025-01-19 06:41:42 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][230/312]	eta 0:01:01 lr 0.003120	time 0.7185 (0.7511)	model_time 0.7184 (0.7441)	loss 3.8099 (3.4080)	grad_norm 1.4598 (1.3344/0.5928)	mem 34602MB
[2025-01-19 06:41:50 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][240/312]	eta 0:00:54 lr 0.003120	time 0.7275 (0.7505)	model_time 0.7274 (0.7438)	loss 3.6006 (3.4180)	grad_norm 1.5801 (1.3368/0.5856)	mem 34602MB
[2025-01-19 06:41:57 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][250/312]	eta 0:00:46 lr 0.003119	time 0.7185 (0.7501)	model_time 0.7184 (0.7436)	loss 3.3410 (3.4081)	grad_norm 1.9242 (1.3525/0.5970)	mem 34602MB
[2025-01-19 06:42:05 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][260/312]	eta 0:00:39 lr 0.003119	time 0.8056 (0.7503)	model_time 0.8054 (0.7441)	loss 4.0062 (3.4225)	grad_norm 2.0253 (1.3593/0.5987)	mem 34602MB
[2025-01-19 06:42:12 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][270/312]	eta 0:00:31 lr 0.003118	time 0.7592 (0.7504)	model_time 0.7587 (0.7444)	loss 3.9725 (3.4336)	grad_norm 1.0047 (1.3498/0.5936)	mem 34602MB
[2025-01-19 06:42:20 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][280/312]	eta 0:00:24 lr 0.003117	time 0.7940 (0.7503)	model_time 0.7938 (0.7445)	loss 4.1425 (3.4388)	grad_norm 1.8427 (1.3496/0.5893)	mem 34602MB
[2025-01-19 06:42:27 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][290/312]	eta 0:00:16 lr 0.003117	time 0.7394 (0.7506)	model_time 0.7393 (0.7449)	loss 3.3090 (3.4388)	grad_norm 1.4841 (1.3584/0.5939)	mem 34602MB
[2025-01-19 06:42:35 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][300/312]	eta 0:00:09 lr 0.003116	time 0.7144 (0.7508)	model_time 0.7143 (0.7454)	loss 3.0721 (3.4415)	grad_norm 0.8712 (1.3594/0.5896)	mem 34602MB
[2025-01-19 06:42:42 internimage_b_1k_224] (main.py 510): INFO Train: [93/300][310/312]	eta 0:00:01 lr 0.003116	time 0.7049 (0.7502)	model_time 0.7048 (0.7450)	loss 4.1767 (3.4404)	grad_norm 0.9073 (1.3636/0.5862)	mem 34602MB
[2025-01-19 06:42:43 internimage_b_1k_224] (main.py 519): INFO EPOCH 93 training takes 0:03:54
[2025-01-19 06:42:43 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_93.pth saving......
[2025-01-19 06:42:46 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_93.pth saved !!!
[2025-01-19 06:42:54 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.443 (7.443)	Loss 0.9241 (0.9241)	Acc@1 80.615 (80.615)	Acc@5 96.143 (96.143)	Mem 34602MB
[2025-01-19 06:42:56 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.935)	Loss 1.2592 (1.0670)	Acc@1 73.682 (77.608)	Acc@5 92.163 (94.329)	Mem 34602MB
[2025-01-19 06:42:57 internimage_b_1k_224] (main.py 575): INFO [Epoch:93] * Acc@1 77.623 Acc@5 94.392
[2025-01-19 06:42:57 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.6%
[2025-01-19 06:42:57 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 78.10%
[2025-01-19 06:43:06 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.208 (9.208)	Loss 0.7954 (0.7954)	Acc@1 80.957 (80.957)	Acc@5 95.898 (95.898)	Mem 34602MB
[2025-01-19 06:43:10 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.179 (1.231)	Loss 1.2082 (0.9641)	Acc@1 71.094 (77.164)	Acc@5 91.333 (93.839)	Mem 34602MB
[2025-01-19 06:43:10 internimage_b_1k_224] (main.py 575): INFO [Epoch:93] * Acc@1 77.149 Acc@5 93.910
[2025-01-19 06:43:10 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 77.1%
[2025-01-19 06:43:10 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 06:43:15 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 06:43:15 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 77.15%
[2025-01-19 06:43:17 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][0/312]	eta 0:11:21 lr 0.003116	time 2.1848 (2.1848)	model_time 0.7563 (0.7563)	loss 3.9047 (3.9047)	grad_norm 1.2164 (1.2164/0.0000)	mem 34602MB
[2025-01-19 06:43:24 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][10/312]	eta 0:04:25 lr 0.003115	time 0.7388 (0.8796)	model_time 0.7386 (0.7494)	loss 4.2603 (3.7058)	grad_norm 1.4027 (1.1949/0.2649)	mem 34602MB
[2025-01-19 06:43:32 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][20/312]	eta 0:03:56 lr 0.003115	time 0.7168 (0.8111)	model_time 0.7167 (0.7427)	loss 2.5094 (3.6341)	grad_norm 1.8682 (1.3399/0.4302)	mem 34602MB
[2025-01-19 06:43:39 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][30/312]	eta 0:03:42 lr 0.003114	time 0.7239 (0.7880)	model_time 0.7236 (0.7416)	loss 3.5910 (3.5452)	grad_norm 1.2595 (1.3150/0.4731)	mem 34602MB
[2025-01-19 06:43:46 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][40/312]	eta 0:03:30 lr 0.003114	time 0.7206 (0.7736)	model_time 0.7201 (0.7384)	loss 3.3793 (3.5094)	grad_norm 0.7932 (1.2791/0.4431)	mem 34602MB
[2025-01-19 06:43:54 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][50/312]	eta 0:03:20 lr 0.003113	time 0.7410 (0.7660)	model_time 0.7408 (0.7376)	loss 3.3208 (3.4942)	grad_norm 0.8853 (1.2572/0.4286)	mem 34602MB
[2025-01-19 06:44:01 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][60/312]	eta 0:03:12 lr 0.003112	time 0.7218 (0.7621)	model_time 0.7216 (0.7383)	loss 4.3291 (3.4636)	grad_norm 0.9048 (1.2281/0.4198)	mem 34602MB
[2025-01-19 06:44:09 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][70/312]	eta 0:03:04 lr 0.003112	time 0.7390 (0.7605)	model_time 0.7386 (0.7401)	loss 2.8172 (3.4896)	grad_norm 1.8316 (1.2469/0.4248)	mem 34602MB
[2025-01-19 06:44:16 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][80/312]	eta 0:02:56 lr 0.003111	time 0.7224 (0.7595)	model_time 0.7219 (0.7416)	loss 3.4931 (3.4642)	grad_norm 1.9189 (1.2854/0.4590)	mem 34602MB
[2025-01-19 06:44:24 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][90/312]	eta 0:02:48 lr 0.003111	time 0.8053 (0.7598)	model_time 0.8051 (0.7437)	loss 2.9989 (3.4586)	grad_norm 1.2773 (1.2822/0.4382)	mem 34602MB
[2025-01-19 06:44:31 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][100/312]	eta 0:02:41 lr 0.003110	time 0.8046 (0.7601)	model_time 0.8042 (0.7456)	loss 4.1147 (3.4614)	grad_norm 2.2689 (1.2896/0.4351)	mem 34602MB
[2025-01-19 06:44:39 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][110/312]	eta 0:02:33 lr 0.003110	time 0.7541 (0.7585)	model_time 0.7537 (0.7453)	loss 3.5976 (3.4552)	grad_norm 1.3334 (1.3481/0.5550)	mem 34602MB
[2025-01-19 06:44:46 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][120/312]	eta 0:02:25 lr 0.003109	time 0.7185 (0.7576)	model_time 0.7183 (0.7454)	loss 3.2711 (3.4242)	grad_norm 1.3240 (1.3240/0.5411)	mem 34602MB
[2025-01-19 06:44:54 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][130/312]	eta 0:02:17 lr 0.003109	time 0.7462 (0.7566)	model_time 0.7460 (0.7453)	loss 3.9603 (3.4239)	grad_norm 0.7960 (1.3181/0.5427)	mem 34602MB
[2025-01-19 06:45:01 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][140/312]	eta 0:02:09 lr 0.003108	time 0.7163 (0.7550)	model_time 0.7161 (0.7445)	loss 3.9275 (3.4289)	grad_norm 0.8234 (1.3056/0.5352)	mem 34602MB
[2025-01-19 06:45:08 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][150/312]	eta 0:02:01 lr 0.003107	time 0.7144 (0.7530)	model_time 0.7142 (0.7432)	loss 4.4091 (3.4397)	grad_norm 1.1195 (1.2975/0.5268)	mem 34602MB
[2025-01-19 06:45:16 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][160/312]	eta 0:01:54 lr 0.003107	time 0.7191 (0.7515)	model_time 0.7190 (0.7422)	loss 3.3780 (3.4333)	grad_norm 1.1296 (1.2799/0.5181)	mem 34602MB
[2025-01-19 06:45:23 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][170/312]	eta 0:01:46 lr 0.003106	time 0.7095 (0.7503)	model_time 0.7091 (0.7416)	loss 3.3000 (3.4523)	grad_norm 1.3760 (1.2879/0.5078)	mem 34602MB
[2025-01-19 06:45:30 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][180/312]	eta 0:01:38 lr 0.003106	time 0.7196 (0.7498)	model_time 0.7195 (0.7415)	loss 4.1037 (3.4559)	grad_norm 0.7362 (1.2866/0.5010)	mem 34602MB
[2025-01-19 06:45:38 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][190/312]	eta 0:01:31 lr 0.003105	time 0.7175 (0.7505)	model_time 0.7171 (0.7426)	loss 2.7344 (3.4475)	grad_norm 2.0315 (1.3465/0.6037)	mem 34602MB
[2025-01-19 06:45:45 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][200/312]	eta 0:01:24 lr 0.003105	time 0.7173 (0.7502)	model_time 0.7170 (0.7427)	loss 3.8504 (3.4419)	grad_norm 0.8479 (1.3331/0.5949)	mem 34602MB
[2025-01-19 06:45:53 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][210/312]	eta 0:01:16 lr 0.003104	time 0.8053 (0.7512)	model_time 0.8048 (0.7440)	loss 3.9287 (3.4406)	grad_norm 0.7239 (1.3129/0.5882)	mem 34602MB
[2025-01-19 06:46:01 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][220/312]	eta 0:01:09 lr 0.003104	time 0.7862 (0.7515)	model_time 0.7858 (0.7447)	loss 2.8726 (3.4334)	grad_norm 0.8172 (1.3004/0.5798)	mem 34602MB
[2025-01-19 06:46:08 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][230/312]	eta 0:01:01 lr 0.003103	time 0.7110 (0.7511)	model_time 0.7105 (0.7446)	loss 3.3441 (3.4358)	grad_norm 1.0152 (1.2958/0.5743)	mem 34602MB
[2025-01-19 06:46:16 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][240/312]	eta 0:00:54 lr 0.003102	time 0.7218 (0.7507)	model_time 0.7213 (0.7444)	loss 3.2585 (3.4350)	grad_norm 1.1449 (1.2912/0.5697)	mem 34602MB
[2025-01-19 06:46:23 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][250/312]	eta 0:00:46 lr 0.003102	time 0.7364 (0.7503)	model_time 0.7362 (0.7442)	loss 3.5819 (3.4421)	grad_norm 1.3524 (1.2818/0.5617)	mem 34602MB
[2025-01-19 06:46:30 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][260/312]	eta 0:00:38 lr 0.003101	time 0.7130 (0.7496)	model_time 0.7125 (0.7438)	loss 4.0654 (3.4395)	grad_norm 1.5989 (1.2833/0.5532)	mem 34602MB
[2025-01-19 06:46:38 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][270/312]	eta 0:00:31 lr 0.003101	time 0.7182 (0.7489)	model_time 0.7180 (0.7433)	loss 3.5430 (3.4325)	grad_norm 2.0131 (1.2947/0.5615)	mem 34602MB
[2025-01-19 06:46:45 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][280/312]	eta 0:00:23 lr 0.003100	time 0.7180 (0.7480)	model_time 0.7176 (0.7425)	loss 3.0475 (3.4277)	grad_norm 1.7431 (1.2968/0.5568)	mem 34602MB
[2025-01-19 06:46:52 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][290/312]	eta 0:00:16 lr 0.003100	time 0.7243 (0.7474)	model_time 0.7238 (0.7422)	loss 3.1835 (3.4197)	grad_norm 1.0527 (1.2983/0.5553)	mem 34602MB
[2025-01-19 06:46:59 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][300/312]	eta 0:00:08 lr 0.003099	time 0.7087 (0.7470)	model_time 0.7086 (0.7417)	loss 3.9742 (3.4132)	grad_norm 1.1932 (1.3191/0.5725)	mem 34602MB
[2025-01-19 06:47:07 internimage_b_1k_224] (main.py 510): INFO Train: [94/300][310/312]	eta 0:00:01 lr 0.003098	time 0.7151 (0.7469)	model_time 0.7150 (0.7418)	loss 3.7459 (3.4254)	grad_norm 0.8392 (1.3318/0.5854)	mem 34602MB
[2025-01-19 06:47:08 internimage_b_1k_224] (main.py 519): INFO EPOCH 94 training takes 0:03:53
[2025-01-19 06:47:08 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_94.pth saving......
[2025-01-19 06:47:11 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_94.pth saved !!!
[2025-01-19 06:47:18 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.184 (7.184)	Loss 0.8611 (0.8611)	Acc@1 81.738 (81.738)	Acc@5 96.631 (96.631)	Mem 34602MB
[2025-01-19 06:47:21 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.917)	Loss 1.2224 (1.0263)	Acc@1 72.998 (77.941)	Acc@5 91.943 (94.425)	Mem 34602MB
[2025-01-19 06:47:21 internimage_b_1k_224] (main.py 575): INFO [Epoch:94] * Acc@1 77.847 Acc@5 94.478
[2025-01-19 06:47:21 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.8%
[2025-01-19 06:47:21 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 78.10%
[2025-01-19 06:47:30 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.005 (9.005)	Loss 0.7871 (0.7871)	Acc@1 80.957 (80.957)	Acc@5 96.021 (96.021)	Mem 34602MB
[2025-01-19 06:47:35 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.223)	Loss 1.1972 (0.9556)	Acc@1 71.289 (77.293)	Acc@5 91.406 (93.925)	Mem 34602MB
[2025-01-19 06:47:35 internimage_b_1k_224] (main.py 575): INFO [Epoch:94] * Acc@1 77.289 Acc@5 93.996
[2025-01-19 06:47:35 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 77.3%
[2025-01-19 06:47:35 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 06:47:39 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 06:47:39 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 77.29%
[2025-01-19 06:47:41 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][0/312]	eta 0:11:50 lr 0.003098	time 2.2760 (2.2760)	model_time 0.7547 (0.7547)	loss 3.5565 (3.5565)	grad_norm 2.4108 (2.4108/0.0000)	mem 34602MB
[2025-01-19 06:47:49 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][10/312]	eta 0:04:28 lr 0.003098	time 0.7453 (0.8887)	model_time 0.7452 (0.7502)	loss 3.9408 (3.4773)	grad_norm 1.3781 (1.3516/0.5288)	mem 34602MB
[2025-01-19 06:47:56 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][20/312]	eta 0:04:02 lr 0.003097	time 0.8166 (0.8296)	model_time 0.8162 (0.7568)	loss 2.6826 (3.4302)	grad_norm 0.9601 (1.2054/0.4777)	mem 34602MB
[2025-01-19 06:48:04 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][30/312]	eta 0:03:46 lr 0.003097	time 0.7183 (0.8039)	model_time 0.7178 (0.7545)	loss 3.6799 (3.4410)	grad_norm 1.4714 (1.1626/0.4177)	mem 34602MB
[2025-01-19 06:48:11 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][40/312]	eta 0:03:35 lr 0.003096	time 0.7278 (0.7920)	model_time 0.7276 (0.7546)	loss 3.3661 (3.4628)	grad_norm 0.7952 (1.1038/0.3877)	mem 34602MB
[2025-01-19 06:48:19 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][50/312]	eta 0:03:24 lr 0.003096	time 0.7216 (0.7802)	model_time 0.7214 (0.7501)	loss 4.0068 (3.4907)	grad_norm 2.7183 (1.1915/0.5659)	mem 34602MB
[2025-01-19 06:48:26 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][60/312]	eta 0:03:15 lr 0.003095	time 0.7247 (0.7744)	model_time 0.7242 (0.7492)	loss 4.3733 (3.5053)	grad_norm 2.5136 (1.2438/0.5717)	mem 34602MB
[2025-01-19 06:48:34 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][70/312]	eta 0:03:06 lr 0.003094	time 0.7263 (0.7715)	model_time 0.7262 (0.7498)	loss 3.3453 (3.4935)	grad_norm 1.2502 (1.2601/0.5443)	mem 34602MB
[2025-01-19 06:48:41 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][80/312]	eta 0:02:57 lr 0.003094	time 0.7196 (0.7660)	model_time 0.7194 (0.7470)	loss 3.6507 (3.4946)	grad_norm 2.0761 (1.3098/0.5742)	mem 34602MB
[2025-01-19 06:48:48 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][90/312]	eta 0:02:49 lr 0.003093	time 0.7197 (0.7625)	model_time 0.7196 (0.7454)	loss 2.6043 (3.4804)	grad_norm 1.3383 (1.3400/0.5563)	mem 34602MB
[2025-01-19 06:48:56 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][100/312]	eta 0:02:41 lr 0.003093	time 0.7225 (0.7604)	model_time 0.7221 (0.7450)	loss 3.2499 (3.4631)	grad_norm 1.0105 (1.3217/0.5389)	mem 34602MB
[2025-01-19 06:49:03 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][110/312]	eta 0:02:33 lr 0.003092	time 0.7170 (0.7590)	model_time 0.7168 (0.7450)	loss 3.5469 (3.4593)	grad_norm 1.6048 (1.3331/0.5405)	mem 34602MB
[2025-01-19 06:49:11 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][120/312]	eta 0:02:25 lr 0.003092	time 0.8283 (0.7592)	model_time 0.8280 (0.7463)	loss 2.8698 (3.4499)	grad_norm 0.9865 (1.3023/0.5411)	mem 34602MB
[2025-01-19 06:49:18 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][130/312]	eta 0:02:18 lr 0.003091	time 0.7206 (0.7584)	model_time 0.7201 (0.7465)	loss 3.2408 (3.4481)	grad_norm 1.7084 (1.3037/0.5361)	mem 34602MB
[2025-01-19 06:49:26 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][140/312]	eta 0:02:10 lr 0.003091	time 0.8099 (0.7590)	model_time 0.8097 (0.7479)	loss 2.3649 (3.4205)	grad_norm 1.5555 (1.3016/0.5281)	mem 34602MB
[2025-01-19 06:49:34 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][150/312]	eta 0:02:03 lr 0.003090	time 0.7373 (0.7593)	model_time 0.7371 (0.7489)	loss 4.2967 (3.4274)	grad_norm 1.2635 (1.2883/0.5195)	mem 34602MB
[2025-01-19 06:49:41 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][160/312]	eta 0:01:55 lr 0.003089	time 0.7211 (0.7588)	model_time 0.7206 (0.7491)	loss 3.5679 (3.4395)	grad_norm 1.2430 (1.2769/0.5124)	mem 34602MB
[2025-01-19 06:49:48 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][170/312]	eta 0:01:47 lr 0.003089	time 0.7236 (0.7574)	model_time 0.7234 (0.7482)	loss 2.8750 (3.4474)	grad_norm 0.8766 (1.2862/0.5201)	mem 34602MB
[2025-01-19 06:49:56 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][180/312]	eta 0:01:39 lr 0.003088	time 0.7189 (0.7564)	model_time 0.7188 (0.7477)	loss 3.7269 (3.4410)	grad_norm 2.0159 (1.3265/0.5846)	mem 34602MB
[2025-01-19 06:50:03 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][190/312]	eta 0:01:32 lr 0.003088	time 0.8232 (0.7558)	model_time 0.8228 (0.7476)	loss 3.5324 (3.4440)	grad_norm 0.7350 (1.3274/0.5826)	mem 34602MB
[2025-01-19 06:50:11 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][200/312]	eta 0:01:24 lr 0.003087	time 0.7793 (0.7548)	model_time 0.7791 (0.7469)	loss 3.2752 (3.4451)	grad_norm 0.8911 (1.3068/0.5756)	mem 34602MB
[2025-01-19 06:50:18 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][210/312]	eta 0:01:16 lr 0.003087	time 0.7203 (0.7535)	model_time 0.7202 (0.7459)	loss 3.7099 (3.4439)	grad_norm 0.8750 (1.2918/0.5675)	mem 34602MB
[2025-01-19 06:50:25 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][220/312]	eta 0:01:09 lr 0.003086	time 0.7300 (0.7532)	model_time 0.7296 (0.7459)	loss 3.4677 (3.4430)	grad_norm 1.5759 (1.2846/0.5591)	mem 34602MB
[2025-01-19 06:50:33 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][230/312]	eta 0:01:01 lr 0.003086	time 0.8099 (0.7526)	model_time 0.8098 (0.7456)	loss 2.2827 (3.4357)	grad_norm 1.1797 (1.2892/0.5617)	mem 34602MB
[2025-01-19 06:50:40 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][240/312]	eta 0:00:54 lr 0.003085	time 0.8197 (0.7530)	model_time 0.8191 (0.7463)	loss 3.1922 (3.4378)	grad_norm 2.0048 (1.2948/0.5648)	mem 34602MB
[2025-01-19 06:50:48 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][250/312]	eta 0:00:46 lr 0.003084	time 0.7190 (0.7532)	model_time 0.7188 (0.7467)	loss 3.6172 (3.4272)	grad_norm 1.2333 (1.3087/0.5724)	mem 34602MB
[2025-01-19 06:50:56 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][260/312]	eta 0:00:39 lr 0.003084	time 0.8033 (0.7539)	model_time 0.8031 (0.7477)	loss 3.1652 (3.4182)	grad_norm 0.9454 (1.3058/0.5717)	mem 34602MB
[2025-01-19 06:51:03 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][270/312]	eta 0:00:31 lr 0.003083	time 0.7267 (0.7544)	model_time 0.7265 (0.7484)	loss 2.6607 (3.4221)	grad_norm 2.2321 (1.3105/0.5758)	mem 34602MB
[2025-01-19 06:51:11 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][280/312]	eta 0:00:24 lr 0.003083	time 0.7182 (0.7543)	model_time 0.7181 (0.7485)	loss 4.0280 (3.4150)	grad_norm 1.2477 (1.3101/0.5685)	mem 34602MB
[2025-01-19 06:51:18 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][290/312]	eta 0:00:16 lr 0.003082	time 0.7201 (0.7538)	model_time 0.7200 (0.7481)	loss 2.9022 (3.4124)	grad_norm 1.2041 (1.3191/0.5674)	mem 34602MB
[2025-01-19 06:51:26 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][300/312]	eta 0:00:09 lr 0.003082	time 0.7231 (0.7536)	model_time 0.7230 (0.7482)	loss 3.7852 (3.4144)	grad_norm 0.8138 (1.3113/0.5629)	mem 34602MB
[2025-01-19 06:51:33 internimage_b_1k_224] (main.py 510): INFO Train: [95/300][310/312]	eta 0:00:01 lr 0.003081	time 0.7230 (0.7528)	model_time 0.7229 (0.7475)	loss 3.9346 (3.4176)	grad_norm 0.9080 (1.3068/0.5574)	mem 34602MB
[2025-01-19 06:51:34 internimage_b_1k_224] (main.py 519): INFO EPOCH 95 training takes 0:03:54
[2025-01-19 06:51:34 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_95.pth saving......
[2025-01-19 06:51:37 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_95.pth saved !!!
[2025-01-19 06:51:44 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.349 (7.349)	Loss 0.8211 (0.8211)	Acc@1 81.616 (81.616)	Acc@5 96.143 (96.143)	Mem 34602MB
[2025-01-19 06:51:47 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.932)	Loss 1.1634 (1.0017)	Acc@1 74.487 (78.087)	Acc@5 92.578 (94.356)	Mem 34602MB
[2025-01-19 06:51:48 internimage_b_1k_224] (main.py 575): INFO [Epoch:95] * Acc@1 78.063 Acc@5 94.416
[2025-01-19 06:51:48 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.1%
[2025-01-19 06:51:48 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 78.10%
[2025-01-19 06:51:57 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.052 (9.052)	Loss 0.7791 (0.7791)	Acc@1 81.030 (81.030)	Acc@5 96.021 (96.021)	Mem 34602MB
[2025-01-19 06:52:01 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.221)	Loss 1.1865 (0.9475)	Acc@1 71.558 (77.399)	Acc@5 91.431 (93.999)	Mem 34602MB
[2025-01-19 06:52:01 internimage_b_1k_224] (main.py 575): INFO [Epoch:95] * Acc@1 77.393 Acc@5 94.070
[2025-01-19 06:52:01 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 77.4%
[2025-01-19 06:52:01 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 06:52:05 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 06:52:05 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 77.39%
[2025-01-19 06:52:07 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][0/312]	eta 0:11:18 lr 0.003081	time 2.1733 (2.1733)	model_time 0.7479 (0.7479)	loss 4.0412 (4.0412)	grad_norm 0.6937 (0.6937/0.0000)	mem 34602MB
[2025-01-19 06:52:15 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][10/312]	eta 0:04:20 lr 0.003080	time 0.7312 (0.8629)	model_time 0.7311 (0.7331)	loss 3.8044 (3.4764)	grad_norm 1.4001 (1.3624/0.5558)	mem 34602MB
[2025-01-19 06:52:22 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][20/312]	eta 0:03:53 lr 0.003080	time 0.7190 (0.8010)	model_time 0.7188 (0.7328)	loss 4.2348 (3.5593)	grad_norm 2.0722 (1.8184/0.7791)	mem 34602MB
[2025-01-19 06:52:29 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][30/312]	eta 0:03:40 lr 0.003079	time 0.7198 (0.7815)	model_time 0.7193 (0.7351)	loss 2.4303 (3.4350)	grad_norm 0.8937 (1.6188/0.7291)	mem 34602MB
[2025-01-19 06:52:37 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][40/312]	eta 0:03:30 lr 0.003079	time 0.7483 (0.7733)	model_time 0.7481 (0.7382)	loss 3.8552 (3.4429)	grad_norm 1.6795 (1.5534/0.6754)	mem 34602MB
[2025-01-19 06:52:45 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][50/312]	eta 0:03:22 lr 0.003078	time 0.7892 (0.7712)	model_time 0.7890 (0.7429)	loss 2.8620 (3.4836)	grad_norm 1.0093 (1.4694/0.6558)	mem 34602MB
[2025-01-19 06:52:52 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][60/312]	eta 0:03:13 lr 0.003078	time 0.7159 (0.7686)	model_time 0.7157 (0.7449)	loss 3.3737 (3.4652)	grad_norm 0.7501 (1.3920/0.6383)	mem 34602MB
[2025-01-19 06:53:00 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][70/312]	eta 0:03:06 lr 0.003077	time 0.8115 (0.7696)	model_time 0.8113 (0.7492)	loss 3.3209 (3.4500)	grad_norm 1.1846 (1.3627/0.6027)	mem 34602MB
[2025-01-19 06:53:07 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][80/312]	eta 0:02:58 lr 0.003076	time 0.7414 (0.7677)	model_time 0.7413 (0.7497)	loss 3.4781 (3.4342)	grad_norm 1.9446 (1.3520/0.5828)	mem 34602MB
[2025-01-19 06:53:15 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][90/312]	eta 0:02:50 lr 0.003076	time 0.7998 (0.7667)	model_time 0.7996 (0.7507)	loss 2.8238 (3.4168)	grad_norm 0.8300 (1.3722/0.5880)	mem 34602MB
[2025-01-19 06:53:22 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][100/312]	eta 0:02:41 lr 0.003075	time 0.7220 (0.7633)	model_time 0.7218 (0.7488)	loss 3.4637 (3.4212)	grad_norm 1.1687 (1.3620/0.5776)	mem 34602MB
[2025-01-19 06:53:30 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][110/312]	eta 0:02:33 lr 0.003075	time 0.7338 (0.7618)	model_time 0.7333 (0.7486)	loss 3.8927 (3.4414)	grad_norm 1.2468 (1.3481/0.5646)	mem 34602MB
[2025-01-19 06:53:37 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][120/312]	eta 0:02:25 lr 0.003074	time 0.7311 (0.7593)	model_time 0.7309 (0.7472)	loss 2.8487 (3.4292)	grad_norm 0.9059 (1.3489/0.5596)	mem 34602MB
[2025-01-19 06:53:44 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][130/312]	eta 0:02:17 lr 0.003074	time 0.7504 (0.7574)	model_time 0.7502 (0.7462)	loss 2.8895 (3.4170)	grad_norm 1.5683 (1.3464/0.5474)	mem 34602MB
[2025-01-19 06:53:52 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][140/312]	eta 0:02:09 lr 0.003073	time 0.7165 (0.7551)	model_time 0.7163 (0.7446)	loss 2.6482 (3.4126)	grad_norm 1.7608 (1.3586/0.5491)	mem 34602MB
[2025-01-19 06:53:59 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][150/312]	eta 0:02:02 lr 0.003073	time 0.7306 (0.7544)	model_time 0.7304 (0.7446)	loss 3.7979 (3.4341)	grad_norm 1.4715 (1.3534/0.5367)	mem 34602MB
[2025-01-19 06:54:07 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][160/312]	eta 0:01:54 lr 0.003072	time 0.8273 (0.7534)	model_time 0.8268 (0.7442)	loss 3.8196 (3.4428)	grad_norm 1.5672 (1.3495/0.5246)	mem 34602MB
[2025-01-19 06:54:14 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][170/312]	eta 0:01:46 lr 0.003071	time 0.7220 (0.7532)	model_time 0.7215 (0.7445)	loss 3.9972 (3.4473)	grad_norm 0.9266 (1.3434/0.5351)	mem 34602MB
[2025-01-19 06:54:22 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][180/312]	eta 0:01:39 lr 0.003071	time 0.7196 (0.7541)	model_time 0.7194 (0.7458)	loss 3.6422 (3.4600)	grad_norm 2.7336 (1.3448/0.5410)	mem 34602MB
[2025-01-19 06:54:30 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][190/312]	eta 0:01:32 lr 0.003070	time 0.8201 (0.7555)	model_time 0.8196 (0.7477)	loss 2.5182 (3.4575)	grad_norm 3.9652 (1.3703/0.5673)	mem 34602MB
[2025-01-19 06:54:37 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][200/312]	eta 0:01:24 lr 0.003070	time 0.7399 (0.7560)	model_time 0.7397 (0.7485)	loss 3.8665 (3.4627)	grad_norm 1.2804 (1.3753/0.5618)	mem 34602MB
[2025-01-19 06:54:45 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][210/312]	eta 0:01:17 lr 0.003069	time 0.8054 (0.7559)	model_time 0.8049 (0.7488)	loss 3.5072 (3.4631)	grad_norm 0.9841 (1.3722/0.5573)	mem 34602MB
[2025-01-19 06:54:52 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][220/312]	eta 0:01:09 lr 0.003069	time 0.7192 (0.7551)	model_time 0.7190 (0.7483)	loss 3.9296 (3.4633)	grad_norm 0.9523 (1.3579/0.5522)	mem 34602MB
[2025-01-19 06:55:00 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][230/312]	eta 0:01:01 lr 0.003068	time 0.7172 (0.7549)	model_time 0.7170 (0.7483)	loss 2.9873 (3.4593)	grad_norm 1.5184 (1.3403/0.5482)	mem 34602MB
[2025-01-19 06:55:07 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][240/312]	eta 0:00:54 lr 0.003067	time 0.7176 (0.7540)	model_time 0.7174 (0.7477)	loss 3.4263 (3.4702)	grad_norm 0.8882 (1.3587/0.5638)	mem 34602MB
[2025-01-19 06:55:14 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][250/312]	eta 0:00:46 lr 0.003067	time 0.7234 (0.7529)	model_time 0.7230 (0.7469)	loss 3.1741 (3.4669)	grad_norm 0.6421 (1.3666/0.5679)	mem 34602MB
[2025-01-19 06:55:21 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][260/312]	eta 0:00:39 lr 0.003066	time 0.7443 (0.7519)	model_time 0.7438 (0.7461)	loss 2.8053 (3.4718)	grad_norm 0.9479 (1.3658/0.5666)	mem 34602MB
[2025-01-19 06:55:29 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][270/312]	eta 0:00:31 lr 0.003066	time 0.7110 (0.7513)	model_time 0.7109 (0.7457)	loss 2.6195 (3.4583)	grad_norm 1.5225 (1.3614/0.5586)	mem 34602MB
[2025-01-19 06:55:36 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][280/312]	eta 0:00:24 lr 0.003065	time 0.7998 (0.7509)	model_time 0.7997 (0.7455)	loss 4.0505 (3.4477)	grad_norm 2.3279 (1.3594/0.5560)	mem 34602MB
[2025-01-19 06:55:44 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][290/312]	eta 0:00:16 lr 0.003065	time 0.7186 (0.7508)	model_time 0.7181 (0.7456)	loss 3.4704 (3.4451)	grad_norm 2.0591 (1.3534/0.5543)	mem 34602MB
[2025-01-19 06:55:51 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][300/312]	eta 0:00:09 lr 0.003064	time 0.7904 (0.7513)	model_time 0.7903 (0.7462)	loss 3.8561 (3.4538)	grad_norm 2.3970 (1.3549/0.5541)	mem 34602MB
[2025-01-19 06:55:59 internimage_b_1k_224] (main.py 510): INFO Train: [96/300][310/312]	eta 0:00:01 lr 0.003063	time 0.7146 (0.7507)	model_time 0.7145 (0.7457)	loss 3.5510 (3.4581)	grad_norm 1.6932 (1.3614/0.5572)	mem 34602MB
[2025-01-19 06:55:59 internimage_b_1k_224] (main.py 519): INFO EPOCH 96 training takes 0:03:54
[2025-01-19 06:55:59 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_96.pth saving......
[2025-01-19 06:56:03 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_96.pth saved !!!
[2025-01-19 06:56:10 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.505 (7.505)	Loss 0.8908 (0.8908)	Acc@1 81.519 (81.519)	Acc@5 96.265 (96.265)	Mem 34602MB
[2025-01-19 06:56:13 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.955)	Loss 1.2196 (1.0209)	Acc@1 73.853 (78.234)	Acc@5 92.163 (94.527)	Mem 34602MB
[2025-01-19 06:56:13 internimage_b_1k_224] (main.py 575): INFO [Epoch:96] * Acc@1 78.125 Acc@5 94.562
[2025-01-19 06:56:13 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.1%
[2025-01-19 06:56:13 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 06:56:17 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 06:56:17 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 78.13%
[2025-01-19 06:56:24 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.378 (7.378)	Loss 0.7715 (0.7715)	Acc@1 81.299 (81.299)	Acc@5 96.118 (96.118)	Mem 34602MB
[2025-01-19 06:56:27 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.929)	Loss 1.1764 (0.9398)	Acc@1 71.680 (77.539)	Acc@5 91.504 (94.052)	Mem 34602MB
[2025-01-19 06:56:27 internimage_b_1k_224] (main.py 575): INFO [Epoch:96] * Acc@1 77.533 Acc@5 94.114
[2025-01-19 06:56:27 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 77.5%
[2025-01-19 06:56:27 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 06:56:32 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 06:56:32 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 77.53%
[2025-01-19 06:56:34 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][0/312]	eta 0:11:49 lr 0.003063	time 2.2749 (2.2749)	model_time 0.7456 (0.7456)	loss 3.3594 (3.3594)	grad_norm 0.8045 (0.8045/0.0000)	mem 34602MB
[2025-01-19 06:56:42 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][10/312]	eta 0:04:31 lr 0.003063	time 0.7354 (0.9002)	model_time 0.7352 (0.7609)	loss 2.8820 (3.2800)	grad_norm 1.7083 (1.7607/0.8315)	mem 34602MB
[2025-01-19 06:56:49 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][20/312]	eta 0:04:01 lr 0.003062	time 0.8145 (0.8282)	model_time 0.8141 (0.7551)	loss 2.5819 (3.2961)	grad_norm 0.9022 (1.4448/0.7330)	mem 34602MB
[2025-01-19 06:56:57 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][30/312]	eta 0:03:45 lr 0.003062	time 0.7310 (0.7990)	model_time 0.7309 (0.7494)	loss 3.7113 (3.2897)	grad_norm 1.1988 (1.2899/0.6492)	mem 34602MB
[2025-01-19 06:57:04 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][40/312]	eta 0:03:33 lr 0.003061	time 0.7642 (0.7866)	model_time 0.7640 (0.7490)	loss 2.4355 (3.3791)	grad_norm 2.9460 (1.5286/0.8659)	mem 34602MB
[2025-01-19 06:57:11 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][50/312]	eta 0:03:23 lr 0.003061	time 0.7250 (0.7774)	model_time 0.7248 (0.7471)	loss 3.4920 (3.3907)	grad_norm 0.6927 (1.5021/0.8304)	mem 34602MB
[2025-01-19 06:57:19 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][60/312]	eta 0:03:13 lr 0.003060	time 0.7445 (0.7695)	model_time 0.7443 (0.7442)	loss 3.3342 (3.4142)	grad_norm 2.0586 (1.4667/0.7783)	mem 34602MB
[2025-01-19 06:57:26 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][70/312]	eta 0:03:04 lr 0.003059	time 0.7157 (0.7634)	model_time 0.7156 (0.7416)	loss 2.9836 (3.4174)	grad_norm 2.7546 (1.4801/0.7520)	mem 34602MB
[2025-01-19 06:57:33 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][80/312]	eta 0:02:56 lr 0.003059	time 0.7157 (0.7612)	model_time 0.7155 (0.7420)	loss 3.3275 (3.4246)	grad_norm 0.8076 (1.4421/0.7207)	mem 34602MB
[2025-01-19 06:57:41 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][90/312]	eta 0:02:48 lr 0.003058	time 0.7176 (0.7594)	model_time 0.7175 (0.7422)	loss 2.8383 (3.4110)	grad_norm 0.5487 (1.3804/0.7046)	mem 34602MB
[2025-01-19 06:57:48 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][100/312]	eta 0:02:40 lr 0.003058	time 0.7195 (0.7585)	model_time 0.7194 (0.7431)	loss 2.8107 (3.4289)	grad_norm 1.1958 (1.3939/0.6825)	mem 34602MB
[2025-01-19 06:57:56 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][110/312]	eta 0:02:33 lr 0.003057	time 0.7306 (0.7585)	model_time 0.7301 (0.7444)	loss 2.4841 (3.4138)	grad_norm 0.7173 (1.3943/0.6702)	mem 34602MB
[2025-01-19 06:58:04 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][120/312]	eta 0:02:25 lr 0.003057	time 0.8045 (0.7586)	model_time 0.8044 (0.7457)	loss 2.9038 (3.4150)	grad_norm 0.7657 (1.3695/0.6587)	mem 34602MB
[2025-01-19 06:58:11 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][130/312]	eta 0:02:18 lr 0.003056	time 0.7174 (0.7587)	model_time 0.7172 (0.7467)	loss 3.7830 (3.4191)	grad_norm 1.5687 (1.3668/0.6513)	mem 34602MB
[2025-01-19 06:58:19 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][140/312]	eta 0:02:10 lr 0.003055	time 0.8396 (0.7584)	model_time 0.8394 (0.7472)	loss 3.9013 (3.4086)	grad_norm 1.0116 (1.3789/0.6401)	mem 34602MB
[2025-01-19 06:58:26 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][150/312]	eta 0:02:02 lr 0.003055	time 0.7176 (0.7572)	model_time 0.7172 (0.7467)	loss 3.1529 (3.3960)	grad_norm 0.8295 (1.3703/0.6243)	mem 34602MB
[2025-01-19 06:58:34 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][160/312]	eta 0:01:54 lr 0.003054	time 0.7222 (0.7564)	model_time 0.7221 (0.7466)	loss 3.4721 (3.4102)	grad_norm 0.8261 (1.3426/0.6152)	mem 34602MB
[2025-01-19 06:58:41 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][170/312]	eta 0:01:47 lr 0.003054	time 0.7564 (0.7557)	model_time 0.7559 (0.7464)	loss 3.4535 (3.4145)	grad_norm 0.8325 (1.3228/0.6042)	mem 34602MB
[2025-01-19 06:58:48 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][180/312]	eta 0:01:39 lr 0.003053	time 0.7157 (0.7540)	model_time 0.7152 (0.7453)	loss 3.2623 (3.4224)	grad_norm 0.7730 (1.3139/0.5952)	mem 34602MB
[2025-01-19 06:58:56 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][190/312]	eta 0:01:31 lr 0.003053	time 0.7350 (0.7527)	model_time 0.7348 (0.7443)	loss 3.2617 (3.4053)	grad_norm 1.4878 (1.3062/0.5830)	mem 34602MB
[2025-01-19 06:59:03 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][200/312]	eta 0:01:24 lr 0.003052	time 0.7153 (0.7521)	model_time 0.7151 (0.7442)	loss 3.6343 (3.4075)	grad_norm 0.7930 (1.3093/0.5772)	mem 34602MB
[2025-01-19 06:59:10 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][210/312]	eta 0:01:16 lr 0.003051	time 0.7527 (0.7515)	model_time 0.7525 (0.7439)	loss 3.3904 (3.4093)	grad_norm 2.1456 (1.3243/0.5774)	mem 34602MB
[2025-01-19 06:59:18 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][220/312]	eta 0:01:09 lr 0.003051	time 0.7146 (0.7516)	model_time 0.7145 (0.7443)	loss 4.2535 (3.4207)	grad_norm 1.9246 (1.3197/0.5686)	mem 34602MB
[2025-01-19 06:59:26 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][230/312]	eta 0:01:01 lr 0.003050	time 0.7254 (0.7518)	model_time 0.7252 (0.7449)	loss 2.6837 (3.4249)	grad_norm 1.7748 (1.3372/0.5811)	mem 34602MB
[2025-01-19 06:59:33 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][240/312]	eta 0:00:54 lr 0.003050	time 0.8014 (0.7529)	model_time 0.8012 (0.7462)	loss 4.1666 (3.4211)	grad_norm 0.6502 (1.3216/0.5781)	mem 34602MB
[2025-01-19 06:59:41 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][250/312]	eta 0:00:46 lr 0.003049	time 0.7281 (0.7537)	model_time 0.7279 (0.7472)	loss 3.6720 (3.4072)	grad_norm 1.4278 (1.3162/0.5698)	mem 34602MB
[2025-01-19 06:59:49 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][260/312]	eta 0:00:39 lr 0.003049	time 0.9242 (0.7543)	model_time 0.9241 (0.7481)	loss 2.4767 (3.3974)	grad_norm 1.0450 (1.3322/0.5915)	mem 34602MB
[2025-01-19 06:59:56 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][270/312]	eta 0:00:31 lr 0.003048	time 0.7307 (0.7539)	model_time 0.7305 (0.7479)	loss 3.7316 (3.3869)	grad_norm 1.0666 (1.3182/0.5859)	mem 34602MB
[2025-01-19 07:00:04 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][280/312]	eta 0:00:24 lr 0.003048	time 0.7319 (0.7543)	model_time 0.7318 (0.7485)	loss 3.6130 (3.3891)	grad_norm 1.7706 (1.3239/0.5901)	mem 34602MB
[2025-01-19 07:00:11 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][290/312]	eta 0:00:16 lr 0.003047	time 0.7528 (0.7538)	model_time 0.7526 (0.7482)	loss 3.9306 (3.3926)	grad_norm 1.3073 (1.3198/0.5894)	mem 34602MB
[2025-01-19 07:00:18 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][300/312]	eta 0:00:09 lr 0.003046	time 0.7193 (0.7526)	model_time 0.7192 (0.7472)	loss 2.8793 (3.3820)	grad_norm 0.6068 (1.3202/0.5855)	mem 34602MB
[2025-01-19 07:00:26 internimage_b_1k_224] (main.py 510): INFO Train: [97/300][310/312]	eta 0:00:01 lr 0.003046	time 0.7074 (0.7514)	model_time 0.7072 (0.7461)	loss 3.6241 (3.3750)	grad_norm 2.3391 (1.3057/0.5629)	mem 34602MB
[2025-01-19 07:00:26 internimage_b_1k_224] (main.py 519): INFO EPOCH 97 training takes 0:03:54
[2025-01-19 07:00:26 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_97.pth saving......
[2025-01-19 07:00:29 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_97.pth saved !!!
[2025-01-19 07:00:37 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.347 (7.347)	Loss 0.8799 (0.8799)	Acc@1 81.372 (81.372)	Acc@5 96.509 (96.509)	Mem 34602MB
[2025-01-19 07:00:40 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.928)	Loss 1.1534 (1.0098)	Acc@1 74.512 (78.258)	Acc@5 92.920 (94.478)	Mem 34602MB
[2025-01-19 07:00:40 internimage_b_1k_224] (main.py 575): INFO [Epoch:97] * Acc@1 78.171 Acc@5 94.470
[2025-01-19 07:00:40 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.2%
[2025-01-19 07:00:40 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 07:00:44 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 07:00:44 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 78.17%
[2025-01-19 07:00:51 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.156 (7.156)	Loss 0.7646 (0.7646)	Acc@1 81.274 (81.274)	Acc@5 96.265 (96.265)	Mem 34602MB
[2025-01-19 07:00:53 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.907)	Loss 1.1668 (0.9325)	Acc@1 71.948 (77.650)	Acc@5 91.650 (94.138)	Mem 34602MB
[2025-01-19 07:00:54 internimage_b_1k_224] (main.py 575): INFO [Epoch:97] * Acc@1 77.653 Acc@5 94.198
[2025-01-19 07:00:54 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 77.7%
[2025-01-19 07:00:54 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 07:00:58 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 07:00:58 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 77.65%
[2025-01-19 07:01:00 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][0/312]	eta 0:11:40 lr 0.003046	time 2.2463 (2.2463)	model_time 0.7475 (0.7475)	loss 3.6378 (3.6378)	grad_norm 2.3586 (2.3586/0.0000)	mem 34602MB
[2025-01-19 07:01:08 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][10/312]	eta 0:04:26 lr 0.003045	time 0.7203 (0.8810)	model_time 0.7202 (0.7444)	loss 3.3254 (3.3481)	grad_norm 2.6910 (1.7279/0.8957)	mem 34602MB
[2025-01-19 07:01:15 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][20/312]	eta 0:03:59 lr 0.003045	time 0.8239 (0.8191)	model_time 0.8237 (0.7474)	loss 2.5815 (3.3746)	grad_norm 1.0186 (1.5247/0.7392)	mem 34602MB
[2025-01-19 07:01:23 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][30/312]	eta 0:03:45 lr 0.003044	time 0.7279 (0.7979)	model_time 0.7278 (0.7492)	loss 3.4522 (3.3646)	grad_norm 3.3933 (1.6242/0.8093)	mem 34602MB
[2025-01-19 07:01:30 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][40/312]	eta 0:03:33 lr 0.003043	time 0.7293 (0.7847)	model_time 0.7289 (0.7478)	loss 3.6536 (3.3839)	grad_norm 1.6897 (1.6135/0.8065)	mem 34602MB
[2025-01-19 07:01:38 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][50/312]	eta 0:03:24 lr 0.003043	time 0.7565 (0.7808)	model_time 0.7563 (0.7511)	loss 3.6569 (3.4153)	grad_norm 0.7018 (1.4989/0.7652)	mem 34602MB
[2025-01-19 07:01:46 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][60/312]	eta 0:03:16 lr 0.003042	time 0.7340 (0.7802)	model_time 0.7339 (0.7552)	loss 2.6649 (3.3957)	grad_norm 0.9345 (1.4042/0.7341)	mem 34602MB
[2025-01-19 07:01:53 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][70/312]	eta 0:03:07 lr 0.003042	time 0.7360 (0.7735)	model_time 0.7358 (0.7520)	loss 2.3174 (3.3924)	grad_norm 1.4767 (1.3796/0.6997)	mem 34602MB
[2025-01-19 07:02:01 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][80/312]	eta 0:02:58 lr 0.003041	time 0.8137 (0.7707)	model_time 0.8132 (0.7519)	loss 4.4719 (3.4337)	grad_norm 2.1310 (1.3969/0.6731)	mem 34602MB
[2025-01-19 07:02:08 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][90/312]	eta 0:02:50 lr 0.003041	time 0.7328 (0.7674)	model_time 0.7327 (0.7506)	loss 2.6674 (3.4479)	grad_norm 1.4471 (1.4081/0.6569)	mem 34602MB
[2025-01-19 07:02:15 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][100/312]	eta 0:02:41 lr 0.003040	time 0.7281 (0.7641)	model_time 0.7276 (0.7489)	loss 2.8619 (3.4354)	grad_norm 0.8916 (1.3626/0.6405)	mem 34602MB
[2025-01-19 07:02:23 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][110/312]	eta 0:02:33 lr 0.003039	time 0.7179 (0.7611)	model_time 0.7177 (0.7472)	loss 2.2989 (3.3984)	grad_norm 0.7957 (1.3930/0.6905)	mem 34602MB
[2025-01-19 07:02:30 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][120/312]	eta 0:02:25 lr 0.003039	time 0.7373 (0.7583)	model_time 0.7372 (0.7455)	loss 3.9572 (3.3992)	grad_norm 1.1696 (1.3842/0.6770)	mem 34602MB
[2025-01-19 07:02:37 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][130/312]	eta 0:02:17 lr 0.003038	time 0.7155 (0.7574)	model_time 0.7151 (0.7456)	loss 2.4644 (3.3879)	grad_norm 1.3060 (1.3688/0.6602)	mem 34602MB
[2025-01-19 07:02:45 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][140/312]	eta 0:02:10 lr 0.003038	time 0.8119 (0.7576)	model_time 0.8117 (0.7466)	loss 3.3159 (3.3955)	grad_norm 0.8739 (1.3746/0.6545)	mem 34602MB
[2025-01-19 07:02:52 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][150/312]	eta 0:02:02 lr 0.003037	time 0.7766 (0.7571)	model_time 0.7764 (0.7468)	loss 3.7570 (3.4078)	grad_norm 1.8501 (1.3859/0.6415)	mem 34602MB
[2025-01-19 07:03:00 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][160/312]	eta 0:01:55 lr 0.003037	time 0.7191 (0.7569)	model_time 0.7187 (0.7472)	loss 3.2458 (3.4041)	grad_norm 1.4112 (1.3943/0.6316)	mem 34602MB
[2025-01-19 07:03:08 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][170/312]	eta 0:01:47 lr 0.003036	time 0.8100 (0.7569)	model_time 0.8099 (0.7477)	loss 3.6157 (3.4029)	grad_norm 1.1386 (1.3916/0.6278)	mem 34602MB
[2025-01-19 07:03:15 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][180/312]	eta 0:01:39 lr 0.003035	time 0.7161 (0.7574)	model_time 0.7156 (0.7487)	loss 3.6679 (3.4129)	grad_norm 0.7872 (1.3828/0.6172)	mem 34602MB
[2025-01-19 07:03:23 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][190/312]	eta 0:01:32 lr 0.003035	time 0.7354 (0.7562)	model_time 0.7350 (0.7480)	loss 3.8572 (3.4193)	grad_norm 0.5047 (1.3631/0.6112)	mem 34602MB
[2025-01-19 07:03:30 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][200/312]	eta 0:01:24 lr 0.003034	time 0.8123 (0.7563)	model_time 0.8122 (0.7485)	loss 2.8752 (3.4194)	grad_norm 1.3502 (1.3548/0.6036)	mem 34602MB
[2025-01-19 07:03:37 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][210/312]	eta 0:01:17 lr 0.003034	time 0.7188 (0.7552)	model_time 0.7184 (0.7477)	loss 3.4016 (3.4171)	grad_norm 1.2869 (1.3663/0.5978)	mem 34602MB
[2025-01-19 07:03:45 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][220/312]	eta 0:01:09 lr 0.003033	time 0.7312 (0.7544)	model_time 0.7308 (0.7472)	loss 3.3177 (3.4234)	grad_norm 2.1793 (1.3644/0.5930)	mem 34602MB
[2025-01-19 07:03:52 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][230/312]	eta 0:01:01 lr 0.003033	time 0.7178 (0.7529)	model_time 0.7176 (0.7461)	loss 3.5013 (3.4284)	grad_norm 2.2266 (1.3977/0.6353)	mem 34602MB
[2025-01-19 07:03:59 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][240/312]	eta 0:00:54 lr 0.003032	time 0.7387 (0.7518)	model_time 0.7385 (0.7452)	loss 3.2666 (3.4454)	grad_norm 0.9546 (1.3956/0.6283)	mem 34602MB
[2025-01-19 07:04:07 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][250/312]	eta 0:00:46 lr 0.003031	time 0.8573 (0.7516)	model_time 0.8568 (0.7453)	loss 3.8616 (3.4504)	grad_norm 1.9013 (1.3944/0.6213)	mem 34602MB
[2025-01-19 07:04:14 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][260/312]	eta 0:00:39 lr 0.003031	time 0.8135 (0.7516)	model_time 0.8131 (0.7455)	loss 4.1259 (3.4489)	grad_norm 1.3678 (1.3930/0.6125)	mem 34602MB
[2025-01-19 07:04:22 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][270/312]	eta 0:00:31 lr 0.003030	time 0.7520 (0.7513)	model_time 0.7518 (0.7454)	loss 3.7362 (3.4491)	grad_norm 1.1105 (1.3844/0.6054)	mem 34602MB
[2025-01-19 07:04:29 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][280/312]	eta 0:00:24 lr 0.003030	time 0.7319 (0.7514)	model_time 0.7317 (0.7457)	loss 3.8978 (3.4519)	grad_norm 1.1233 (1.3789/0.5978)	mem 34602MB
[2025-01-19 07:04:37 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][290/312]	eta 0:00:16 lr 0.003029	time 0.8385 (0.7514)	model_time 0.8380 (0.7458)	loss 3.9095 (3.4621)	grad_norm 0.8737 (1.3654/0.5928)	mem 34602MB
[2025-01-19 07:04:44 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][300/312]	eta 0:00:09 lr 0.003029	time 0.7108 (0.7517)	model_time 0.7107 (0.7463)	loss 3.6984 (3.4650)	grad_norm 1.6463 (1.3652/0.5891)	mem 34602MB
[2025-01-19 07:04:52 internimage_b_1k_224] (main.py 510): INFO Train: [98/300][310/312]	eta 0:00:01 lr 0.003028	time 0.7108 (0.7508)	model_time 0.7107 (0.7456)	loss 2.6547 (3.4611)	grad_norm 0.6754 (1.3415/0.5683)	mem 34602MB
[2025-01-19 07:04:52 internimage_b_1k_224] (main.py 519): INFO EPOCH 98 training takes 0:03:54
[2025-01-19 07:04:52 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_98.pth saving......
[2025-01-19 07:04:55 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_98.pth saved !!!
[2025-01-19 07:05:03 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.283 (7.283)	Loss 0.8423 (0.8423)	Acc@1 81.616 (81.616)	Acc@5 96.362 (96.362)	Mem 34602MB
[2025-01-19 07:05:06 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.930)	Loss 1.1882 (1.0074)	Acc@1 74.121 (78.056)	Acc@5 92.065 (94.383)	Mem 34602MB
[2025-01-19 07:05:06 internimage_b_1k_224] (main.py 575): INFO [Epoch:98] * Acc@1 78.001 Acc@5 94.426
[2025-01-19 07:05:06 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.0%
[2025-01-19 07:05:06 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 78.17%
[2025-01-19 07:05:15 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.925 (8.925)	Loss 0.7576 (0.7576)	Acc@1 81.372 (81.372)	Acc@5 96.362 (96.362)	Mem 34602MB
[2025-01-19 07:05:19 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.218)	Loss 1.1574 (0.9254)	Acc@1 72.095 (77.788)	Acc@5 91.748 (94.196)	Mem 34602MB
[2025-01-19 07:05:20 internimage_b_1k_224] (main.py 575): INFO [Epoch:98] * Acc@1 77.783 Acc@5 94.268
[2025-01-19 07:05:20 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 77.8%
[2025-01-19 07:05:20 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 07:05:24 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 07:05:24 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 77.78%
[2025-01-19 07:05:26 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][0/312]	eta 0:11:14 lr 0.003028	time 2.1622 (2.1622)	model_time 0.7397 (0.7397)	loss 3.5377 (3.5377)	grad_norm 1.0975 (1.0975/0.0000)	mem 34602MB
[2025-01-19 07:05:34 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][10/312]	eta 0:04:27 lr 0.003027	time 0.8156 (0.8859)	model_time 0.8152 (0.7563)	loss 3.2499 (3.3138)	grad_norm 2.5499 (1.2881/0.4581)	mem 34602MB
[2025-01-19 07:05:41 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][20/312]	eta 0:03:57 lr 0.003027	time 0.7271 (0.8150)	model_time 0.7269 (0.7469)	loss 3.6649 (3.3951)	grad_norm 2.7678 (1.7936/0.8715)	mem 34602MB
[2025-01-19 07:05:48 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][30/312]	eta 0:03:42 lr 0.003026	time 0.8133 (0.7897)	model_time 0.8128 (0.7435)	loss 2.5368 (3.4400)	grad_norm 0.9138 (1.5583/0.8344)	mem 34602MB
[2025-01-19 07:05:56 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][40/312]	eta 0:03:30 lr 0.003026	time 0.7396 (0.7745)	model_time 0.7392 (0.7394)	loss 4.2491 (3.4087)	grad_norm 1.9480 (1.4481/0.7761)	mem 34602MB
[2025-01-19 07:06:03 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][50/312]	eta 0:03:20 lr 0.003025	time 0.7352 (0.7665)	model_time 0.7350 (0.7382)	loss 2.1654 (3.4165)	grad_norm 1.1128 (1.3866/0.7189)	mem 34602MB
[2025-01-19 07:06:10 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][60/312]	eta 0:03:11 lr 0.003024	time 0.7279 (0.7619)	model_time 0.7275 (0.7381)	loss 3.8917 (3.3965)	grad_norm 1.0115 (1.3714/0.6726)	mem 34602MB
[2025-01-19 07:06:18 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][70/312]	eta 0:03:03 lr 0.003024	time 0.8141 (0.7595)	model_time 0.8137 (0.7390)	loss 3.7117 (3.3670)	grad_norm 1.3579 (1.3429/0.6353)	mem 34602MB
[2025-01-19 07:06:25 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][80/312]	eta 0:02:55 lr 0.003023	time 0.7170 (0.7582)	model_time 0.7165 (0.7402)	loss 2.8974 (3.3616)	grad_norm 2.3818 (1.3931/0.6336)	mem 34602MB
[2025-01-19 07:06:33 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][90/312]	eta 0:02:48 lr 0.003023	time 0.7253 (0.7580)	model_time 0.7251 (0.7419)	loss 3.6358 (3.3666)	grad_norm 1.1460 (1.3819/0.6236)	mem 34602MB
[2025-01-19 07:06:40 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][100/312]	eta 0:02:40 lr 0.003022	time 0.7205 (0.7566)	model_time 0.7200 (0.7421)	loss 3.2448 (3.3615)	grad_norm 0.8942 (1.3545/0.6046)	mem 34602MB
[2025-01-19 07:06:48 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][110/312]	eta 0:02:33 lr 0.003022	time 0.7255 (0.7579)	model_time 0.7250 (0.7446)	loss 3.4550 (3.3550)	grad_norm 1.1386 (1.3263/0.5905)	mem 34602MB
[2025-01-19 07:06:55 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][120/312]	eta 0:02:25 lr 0.003021	time 0.7487 (0.7568)	model_time 0.7483 (0.7447)	loss 2.7340 (3.3373)	grad_norm 1.1058 (1.3115/0.5710)	mem 34602MB
[2025-01-19 07:07:03 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][130/312]	eta 0:02:17 lr 0.003020	time 0.7283 (0.7551)	model_time 0.7281 (0.7438)	loss 3.9703 (3.3505)	grad_norm 1.4580 (1.3294/0.5697)	mem 34602MB
[2025-01-19 07:07:10 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][140/312]	eta 0:02:09 lr 0.003020	time 0.7380 (0.7548)	model_time 0.7378 (0.7443)	loss 3.6091 (3.3529)	grad_norm 0.8098 (1.3221/0.5622)	mem 34602MB
[2025-01-19 07:07:18 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][150/312]	eta 0:02:02 lr 0.003019	time 0.8085 (0.7537)	model_time 0.8083 (0.7439)	loss 3.7941 (3.3602)	grad_norm 0.8407 (1.3325/0.5696)	mem 34602MB
[2025-01-19 07:07:25 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][160/312]	eta 0:01:54 lr 0.003019	time 0.7267 (0.7519)	model_time 0.7263 (0.7426)	loss 3.5098 (3.3922)	grad_norm 0.8315 (1.3575/0.6062)	mem 34602MB
[2025-01-19 07:07:32 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][170/312]	eta 0:01:46 lr 0.003018	time 0.7182 (0.7505)	model_time 0.7178 (0.7418)	loss 3.6698 (3.4010)	grad_norm 1.2717 (1.3557/0.6076)	mem 34602MB
[2025-01-19 07:07:40 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][180/312]	eta 0:01:38 lr 0.003018	time 0.7278 (0.7498)	model_time 0.7276 (0.7415)	loss 4.1617 (3.4146)	grad_norm 0.7970 (1.3572/0.6243)	mem 34602MB
[2025-01-19 07:07:47 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][190/312]	eta 0:01:31 lr 0.003017	time 0.8012 (0.7494)	model_time 0.8010 (0.7416)	loss 3.1272 (3.4160)	grad_norm 0.8718 (1.3399/0.6161)	mem 34602MB
[2025-01-19 07:07:55 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][200/312]	eta 0:01:23 lr 0.003016	time 0.7558 (0.7496)	model_time 0.7554 (0.7421)	loss 4.1509 (3.4239)	grad_norm 0.7534 (1.3561/0.6295)	mem 34602MB
[2025-01-19 07:08:02 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][210/312]	eta 0:01:16 lr 0.003016	time 0.7159 (0.7506)	model_time 0.7157 (0.7434)	loss 2.9579 (3.4328)	grad_norm 1.1637 (1.3505/0.6199)	mem 34602MB
[2025-01-19 07:08:10 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][220/312]	eta 0:01:09 lr 0.003015	time 0.7616 (0.7503)	model_time 0.7611 (0.7434)	loss 3.0678 (3.4403)	grad_norm 2.4433 (1.3529/0.6144)	mem 34602MB
[2025-01-19 07:08:18 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][230/312]	eta 0:01:01 lr 0.003015	time 0.8017 (0.7519)	model_time 0.8015 (0.7453)	loss 3.5321 (3.4434)	grad_norm 0.7745 (1.3529/0.6202)	mem 34602MB
[2025-01-19 07:08:25 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][240/312]	eta 0:00:54 lr 0.003014	time 0.7186 (0.7516)	model_time 0.7181 (0.7453)	loss 4.1738 (3.4515)	grad_norm 1.5433 (1.3415/0.6144)	mem 34602MB
[2025-01-19 07:08:32 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][250/312]	eta 0:00:46 lr 0.003014	time 0.7174 (0.7507)	model_time 0.7172 (0.7446)	loss 3.4441 (3.4606)	grad_norm 2.3732 (1.3410/0.6099)	mem 34602MB
[2025-01-19 07:08:40 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][260/312]	eta 0:00:39 lr 0.003013	time 0.7288 (0.7505)	model_time 0.7286 (0.7447)	loss 3.8042 (3.4612)	grad_norm 2.0832 (1.3503/0.6119)	mem 34602MB
[2025-01-19 07:08:47 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][270/312]	eta 0:00:31 lr 0.003012	time 0.8094 (0.7502)	model_time 0.8089 (0.7446)	loss 2.9373 (3.4644)	grad_norm 1.5167 (1.3564/0.6056)	mem 34602MB
[2025-01-19 07:08:54 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][280/312]	eta 0:00:23 lr 0.003012	time 0.7101 (0.7494)	model_time 0.7097 (0.7439)	loss 3.7835 (3.4550)	grad_norm 0.7210 (1.3484/0.6018)	mem 34602MB
[2025-01-19 07:09:02 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][290/312]	eta 0:00:16 lr 0.003011	time 0.7117 (0.7489)	model_time 0.7115 (0.7436)	loss 2.6024 (3.4516)	grad_norm 1.0551 (1.3443/0.5973)	mem 34602MB
[2025-01-19 07:09:09 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][300/312]	eta 0:00:08 lr 0.003011	time 0.7216 (0.7483)	model_time 0.7215 (0.7432)	loss 2.8605 (3.4480)	grad_norm 1.1686 (1.3504/0.5959)	mem 34602MB
[2025-01-19 07:09:16 internimage_b_1k_224] (main.py 510): INFO Train: [99/300][310/312]	eta 0:00:01 lr 0.003010	time 0.7132 (0.7472)	model_time 0.7131 (0.7423)	loss 3.7984 (3.4445)	grad_norm 1.7826 (1.3546/0.5973)	mem 34602MB
[2025-01-19 07:09:17 internimage_b_1k_224] (main.py 519): INFO EPOCH 99 training takes 0:03:53
[2025-01-19 07:09:17 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_99.pth saving......
[2025-01-19 07:09:20 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_99.pth saved !!!
[2025-01-19 07:09:28 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.173 (7.173)	Loss 0.8479 (0.8479)	Acc@1 81.665 (81.665)	Acc@5 96.362 (96.362)	Mem 34602MB
[2025-01-19 07:09:31 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.908)	Loss 1.1777 (1.0049)	Acc@1 74.463 (78.265)	Acc@5 92.407 (94.582)	Mem 34602MB
[2025-01-19 07:09:31 internimage_b_1k_224] (main.py 575): INFO [Epoch:99] * Acc@1 78.241 Acc@5 94.616
[2025-01-19 07:09:31 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.2%
[2025-01-19 07:09:31 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 07:09:34 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 07:09:34 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 78.24%
[2025-01-19 07:09:41 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.183 (7.183)	Loss 0.7510 (0.7510)	Acc@1 81.421 (81.421)	Acc@5 96.338 (96.338)	Mem 34602MB
[2025-01-19 07:09:44 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.940)	Loss 1.1487 (0.9187)	Acc@1 72.168 (77.903)	Acc@5 91.772 (94.229)	Mem 34602MB
[2025-01-19 07:09:44 internimage_b_1k_224] (main.py 575): INFO [Epoch:99] * Acc@1 77.891 Acc@5 94.300
[2025-01-19 07:09:44 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 77.9%
[2025-01-19 07:09:44 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 07:09:49 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 07:09:49 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 77.89%
[2025-01-19 07:09:51 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][0/312]	eta 0:11:29 lr 0.003010	time 2.2088 (2.2088)	model_time 0.7622 (0.7622)	loss 2.6366 (2.6366)	grad_norm 2.0101 (2.0101/0.0000)	mem 34602MB
[2025-01-19 07:09:58 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][10/312]	eta 0:04:28 lr 0.003009	time 0.7155 (0.8887)	model_time 0.7149 (0.7569)	loss 2.4690 (3.2267)	grad_norm 0.9473 (1.2284/0.3221)	mem 34602MB
[2025-01-19 07:10:06 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][20/312]	eta 0:04:02 lr 0.003009	time 0.7319 (0.8320)	model_time 0.7318 (0.7628)	loss 2.7995 (3.3080)	grad_norm 0.7339 (1.3647/0.4841)	mem 34602MB
[2025-01-19 07:10:14 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][30/312]	eta 0:03:47 lr 0.003008	time 0.7167 (0.8059)	model_time 0.7165 (0.7589)	loss 4.1182 (3.3521)	grad_norm 1.0594 (1.3595/0.4918)	mem 34602MB
[2025-01-19 07:10:21 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][40/312]	eta 0:03:36 lr 0.003008	time 0.7546 (0.7949)	model_time 0.7545 (0.7592)	loss 2.7328 (3.3761)	grad_norm 0.8358 (1.3424/0.4767)	mem 34602MB
[2025-01-19 07:10:29 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][50/312]	eta 0:03:25 lr 0.003007	time 0.7215 (0.7828)	model_time 0.7213 (0.7541)	loss 3.8182 (3.4056)	grad_norm 2.2993 (1.3040/0.4802)	mem 34602MB
[2025-01-19 07:10:36 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][60/312]	eta 0:03:15 lr 0.003007	time 0.7273 (0.7751)	model_time 0.7269 (0.7511)	loss 2.1442 (3.3965)	grad_norm 1.1287 (1.3036/0.4753)	mem 34602MB
[2025-01-19 07:10:43 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][70/312]	eta 0:03:06 lr 0.003006	time 0.7113 (0.7715)	model_time 0.7111 (0.7508)	loss 3.2399 (3.3907)	grad_norm 0.9790 (1.2861/0.4632)	mem 34602MB
[2025-01-19 07:10:51 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][80/312]	eta 0:02:58 lr 0.003005	time 0.7624 (0.7674)	model_time 0.7619 (0.7493)	loss 3.6129 (3.4074)	grad_norm 1.0485 (1.2972/0.4591)	mem 34602MB
[2025-01-19 07:10:58 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][90/312]	eta 0:02:49 lr 0.003005	time 0.7182 (0.7632)	model_time 0.7180 (0.7470)	loss 3.2747 (3.4030)	grad_norm 0.8919 (1.2791/0.4677)	mem 34602MB
[2025-01-19 07:11:05 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][100/312]	eta 0:02:41 lr 0.003004	time 0.7208 (0.7598)	model_time 0.7206 (0.7452)	loss 3.8590 (3.3673)	grad_norm 1.1032 (1.2699/0.4551)	mem 34602MB
[2025-01-19 07:11:13 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][110/312]	eta 0:02:33 lr 0.003004	time 0.7241 (0.7579)	model_time 0.7237 (0.7446)	loss 3.3970 (3.3684)	grad_norm 2.3675 (1.2966/0.4779)	mem 34602MB
[2025-01-19 07:11:20 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][120/312]	eta 0:02:25 lr 0.003003	time 0.7265 (0.7562)	model_time 0.7260 (0.7439)	loss 2.6834 (3.3380)	grad_norm 1.9513 (1.3553/0.5332)	mem 34602MB
[2025-01-19 07:11:28 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][130/312]	eta 0:02:17 lr 0.003003	time 0.7507 (0.7552)	model_time 0.7506 (0.7438)	loss 3.4335 (3.3508)	grad_norm 0.7257 (1.3407/0.5343)	mem 34602MB
[2025-01-19 07:11:35 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][140/312]	eta 0:02:10 lr 0.003002	time 0.8080 (0.7559)	model_time 0.8078 (0.7453)	loss 4.2051 (3.3788)	grad_norm 2.1846 (1.3725/0.5467)	mem 34602MB
[2025-01-19 07:11:43 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][150/312]	eta 0:02:02 lr 0.003001	time 0.7357 (0.7555)	model_time 0.7355 (0.7456)	loss 3.4458 (3.3659)	grad_norm 1.0241 (1.3636/0.5350)	mem 34602MB
[2025-01-19 07:11:50 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][160/312]	eta 0:01:54 lr 0.003001	time 0.7193 (0.7564)	model_time 0.7189 (0.7471)	loss 4.0308 (3.3732)	grad_norm 0.8389 (1.3363/0.5304)	mem 34602MB
[2025-01-19 07:11:58 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][170/312]	eta 0:01:47 lr 0.003000	time 0.7196 (0.7553)	model_time 0.7194 (0.7465)	loss 3.6895 (3.3757)	grad_norm 1.6223 (1.3532/0.5417)	mem 34602MB
[2025-01-19 07:12:05 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][180/312]	eta 0:01:39 lr 0.003000	time 0.7426 (0.7544)	model_time 0.7425 (0.7461)	loss 3.1165 (3.3760)	grad_norm 1.9880 (1.3415/0.5338)	mem 34602MB
[2025-01-19 07:12:13 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][190/312]	eta 0:01:31 lr 0.002999	time 0.7206 (0.7537)	model_time 0.7201 (0.7458)	loss 3.8592 (3.3956)	grad_norm 0.6869 (1.3747/0.5808)	mem 34602MB
[2025-01-19 07:12:20 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][200/312]	eta 0:01:24 lr 0.002998	time 0.7192 (0.7525)	model_time 0.7188 (0.7449)	loss 2.7302 (3.3868)	grad_norm 0.9000 (1.3565/0.5764)	mem 34602MB
[2025-01-19 07:12:27 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][210/312]	eta 0:01:16 lr 0.002998	time 0.7186 (0.7519)	model_time 0.7184 (0.7447)	loss 2.8550 (3.3829)	grad_norm 1.2461 (1.3548/0.5715)	mem 34602MB
[2025-01-19 07:12:35 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][220/312]	eta 0:01:09 lr 0.002997	time 0.7236 (0.7509)	model_time 0.7230 (0.7440)	loss 3.7482 (3.3888)	grad_norm 1.0262 (1.3570/0.5676)	mem 34602MB
[2025-01-19 07:12:42 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][230/312]	eta 0:01:01 lr 0.002997	time 0.7255 (0.7501)	model_time 0.7253 (0.7435)	loss 2.6304 (3.4002)	grad_norm 1.8393 (1.3754/0.6036)	mem 34602MB
[2025-01-19 07:12:49 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][240/312]	eta 0:00:53 lr 0.002996	time 0.7217 (0.7493)	model_time 0.7213 (0.7430)	loss 3.6449 (3.4110)	grad_norm 1.8060 (1.3731/0.5978)	mem 34602MB
[2025-01-19 07:12:57 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][250/312]	eta 0:00:46 lr 0.002996	time 0.7185 (0.7493)	model_time 0.7183 (0.7432)	loss 3.7229 (3.4097)	grad_norm 0.8602 (1.3607/0.5936)	mem 34602MB
[2025-01-19 07:13:04 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][260/312]	eta 0:00:39 lr 0.002995	time 0.7778 (0.7504)	model_time 0.7776 (0.7445)	loss 4.5404 (3.4163)	grad_norm 0.9829 (1.3507/0.5879)	mem 34602MB
[2025-01-19 07:13:12 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][270/312]	eta 0:00:31 lr 0.002994	time 0.7299 (0.7503)	model_time 0.7295 (0.7447)	loss 2.9603 (3.4125)	grad_norm 0.8554 (1.3592/0.5877)	mem 34602MB
[2025-01-19 07:13:20 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][280/312]	eta 0:00:24 lr 0.002994	time 0.7198 (0.7508)	model_time 0.7196 (0.7453)	loss 3.6394 (3.4156)	grad_norm 1.4440 (1.3650/0.5833)	mem 34602MB
[2025-01-19 07:13:27 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][290/312]	eta 0:00:16 lr 0.002993	time 0.7202 (0.7503)	model_time 0.7197 (0.7450)	loss 3.8942 (3.4117)	grad_norm 1.7684 (1.3682/0.5874)	mem 34602MB
[2025-01-19 07:13:34 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][300/312]	eta 0:00:08 lr 0.002993	time 0.7134 (0.7497)	model_time 0.7133 (0.7446)	loss 3.5411 (3.4134)	grad_norm 1.1282 (1.3570/0.5822)	mem 34602MB
[2025-01-19 07:13:42 internimage_b_1k_224] (main.py 510): INFO Train: [100/300][310/312]	eta 0:00:01 lr 0.002992	time 0.7087 (0.7495)	model_time 0.7086 (0.7445)	loss 4.1160 (3.4124)	grad_norm 1.0088 (1.3536/0.5840)	mem 34602MB
[2025-01-19 07:13:42 internimage_b_1k_224] (main.py 519): INFO EPOCH 100 training takes 0:03:53
[2025-01-19 07:13:42 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_100.pth saving......
[2025-01-19 07:13:45 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_100.pth saved !!!
[2025-01-19 07:13:53 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.272 (7.272)	Loss 0.8673 (0.8673)	Acc@1 82.129 (82.129)	Acc@5 96.362 (96.362)	Mem 34602MB
[2025-01-19 07:13:56 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.939)	Loss 1.2231 (1.0417)	Acc@1 73.828 (78.407)	Acc@5 92.920 (94.456)	Mem 34602MB
[2025-01-19 07:13:56 internimage_b_1k_224] (main.py 575): INFO [Epoch:100] * Acc@1 78.315 Acc@5 94.508
[2025-01-19 07:13:56 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.3%
[2025-01-19 07:13:56 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 07:13:59 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 07:13:59 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 78.31%
[2025-01-19 07:14:07 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.545 (7.545)	Loss 0.7452 (0.7452)	Acc@1 81.494 (81.494)	Acc@5 96.411 (96.411)	Mem 34602MB
[2025-01-19 07:14:10 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.968)	Loss 1.1407 (0.9125)	Acc@1 72.339 (77.967)	Acc@5 91.772 (94.276)	Mem 34602MB
[2025-01-19 07:14:10 internimage_b_1k_224] (main.py 575): INFO [Epoch:100] * Acc@1 77.959 Acc@5 94.344
[2025-01-19 07:14:10 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.0%
[2025-01-19 07:14:10 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 07:14:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 07:14:14 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 77.96%
[2025-01-19 07:14:16 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][0/312]	eta 0:10:49 lr 0.002992	time 2.0821 (2.0821)	model_time 0.7515 (0.7515)	loss 3.2776 (3.2776)	grad_norm 1.7013 (1.7013/0.0000)	mem 34602MB
[2025-01-19 07:14:24 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][10/312]	eta 0:04:19 lr 0.002991	time 0.7186 (0.8604)	model_time 0.7185 (0.7391)	loss 3.4697 (3.5890)	grad_norm 1.8738 (1.6541/0.5372)	mem 34602MB
[2025-01-19 07:14:31 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][20/312]	eta 0:03:53 lr 0.002991	time 0.7485 (0.8012)	model_time 0.7482 (0.7375)	loss 3.2807 (3.4904)	grad_norm 1.5508 (1.5770/0.5340)	mem 34602MB
[2025-01-19 07:14:39 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][30/312]	eta 0:03:39 lr 0.002990	time 0.7565 (0.7799)	model_time 0.7561 (0.7367)	loss 2.5235 (3.4090)	grad_norm 1.3967 (1.4128/0.5251)	mem 34602MB
[2025-01-19 07:14:46 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][40/312]	eta 0:03:29 lr 0.002990	time 0.7184 (0.7692)	model_time 0.7183 (0.7364)	loss 2.8020 (3.3720)	grad_norm 1.4788 (1.3978/0.5523)	mem 34602MB
[2025-01-19 07:14:53 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][50/312]	eta 0:03:20 lr 0.002989	time 0.7178 (0.7661)	model_time 0.7173 (0.7396)	loss 3.4539 (3.3480)	grad_norm 2.2655 (1.4419/0.5847)	mem 34602MB
[2025-01-19 07:15:01 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][60/312]	eta 0:03:12 lr 0.002989	time 0.7186 (0.7620)	model_time 0.7184 (0.7399)	loss 3.3475 (3.3680)	grad_norm 0.9739 (1.3761/0.5643)	mem 34602MB
[2025-01-19 07:15:08 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][70/312]	eta 0:03:04 lr 0.002988	time 0.7285 (0.7618)	model_time 0.7284 (0.7427)	loss 3.4470 (3.4129)	grad_norm 2.3840 (1.4102/0.5577)	mem 34602MB
[2025-01-19 07:15:16 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][80/312]	eta 0:02:56 lr 0.002987	time 0.7263 (0.7594)	model_time 0.7258 (0.7426)	loss 4.0274 (3.4253)	grad_norm 1.6951 (1.4589/0.6460)	mem 34602MB
[2025-01-19 07:15:24 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][90/312]	eta 0:02:48 lr 0.002987	time 0.7187 (0.7598)	model_time 0.7185 (0.7448)	loss 2.7169 (3.4205)	grad_norm 0.8743 (1.4265/0.6326)	mem 34602MB
[2025-01-19 07:15:31 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][100/312]	eta 0:02:40 lr 0.002986	time 0.7193 (0.7572)	model_time 0.7192 (0.7437)	loss 2.5925 (3.3923)	grad_norm 1.4857 (1.4015/0.6188)	mem 34602MB
[2025-01-19 07:15:38 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][110/312]	eta 0:02:32 lr 0.002986	time 0.7913 (0.7566)	model_time 0.7908 (0.7443)	loss 2.8244 (3.3883)	grad_norm 0.8202 (1.3663/0.6057)	mem 34602MB
[2025-01-19 07:15:46 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][120/312]	eta 0:02:25 lr 0.002985	time 0.7536 (0.7559)	model_time 0.7535 (0.7445)	loss 2.6241 (3.3858)	grad_norm 1.3377 (1.3405/0.5898)	mem 34602MB
[2025-01-19 07:15:53 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][130/312]	eta 0:02:17 lr 0.002984	time 0.7170 (0.7545)	model_time 0.7167 (0.7440)	loss 2.5283 (3.3921)	grad_norm 0.7800 (1.3208/0.5824)	mem 34602MB
[2025-01-19 07:16:00 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][140/312]	eta 0:02:09 lr 0.002984	time 0.7226 (0.7525)	model_time 0.7222 (0.7427)	loss 4.3080 (3.4082)	grad_norm 1.8168 (1.3090/0.5754)	mem 34602MB
[2025-01-19 07:16:08 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][150/312]	eta 0:02:01 lr 0.002983	time 0.7169 (0.7508)	model_time 0.7167 (0.7416)	loss 3.7548 (3.3957)	grad_norm 4.0738 (1.3633/0.6317)	mem 34602MB
[2025-01-19 07:16:15 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][160/312]	eta 0:01:53 lr 0.002983	time 0.7188 (0.7491)	model_time 0.7186 (0.7405)	loss 4.1141 (3.3973)	grad_norm 0.7566 (1.3732/0.6363)	mem 34602MB
[2025-01-19 07:16:22 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][170/312]	eta 0:01:46 lr 0.002982	time 0.7184 (0.7491)	model_time 0.7179 (0.7410)	loss 3.8196 (3.4142)	grad_norm 1.4063 (1.3512/0.6268)	mem 34602MB
[2025-01-19 07:16:30 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][180/312]	eta 0:01:38 lr 0.002982	time 0.7320 (0.7495)	model_time 0.7319 (0.7418)	loss 4.0282 (3.4051)	grad_norm 2.7869 (1.3623/0.6275)	mem 34602MB
[2025-01-19 07:16:38 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][190/312]	eta 0:01:31 lr 0.002981	time 0.7178 (0.7499)	model_time 0.7176 (0.7426)	loss 3.4518 (3.4192)	grad_norm 1.5243 (1.3723/0.6255)	mem 34602MB
[2025-01-19 07:16:45 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][200/312]	eta 0:01:23 lr 0.002980	time 0.7430 (0.7495)	model_time 0.7426 (0.7426)	loss 3.9351 (3.4223)	grad_norm 1.5012 (1.3844/0.6173)	mem 34602MB
[2025-01-19 07:16:53 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][210/312]	eta 0:01:16 lr 0.002980	time 0.8118 (0.7500)	model_time 0.8113 (0.7433)	loss 2.9788 (3.4254)	grad_norm 0.6966 (1.3898/0.6291)	mem 34602MB
[2025-01-19 07:17:00 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][220/312]	eta 0:01:08 lr 0.002979	time 0.7214 (0.7499)	model_time 0.7212 (0.7435)	loss 2.7800 (3.4195)	grad_norm 1.2217 (1.3783/0.6215)	mem 34602MB
[2025-01-19 07:17:08 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][230/312]	eta 0:01:01 lr 0.002979	time 0.8003 (0.7497)	model_time 0.8001 (0.7436)	loss 3.3077 (3.4134)	grad_norm 0.7604 (1.3652/0.6138)	mem 34602MB
[2025-01-19 07:17:15 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][240/312]	eta 0:00:53 lr 0.002978	time 0.7235 (0.7493)	model_time 0.7234 (0.7434)	loss 3.5483 (3.4160)	grad_norm 1.5212 (1.3537/0.6061)	mem 34602MB
[2025-01-19 07:17:22 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][250/312]	eta 0:00:46 lr 0.002977	time 0.7203 (0.7488)	model_time 0.7201 (0.7432)	loss 3.4613 (3.4207)	grad_norm 1.4080 (1.3582/0.5980)	mem 34602MB
[2025-01-19 07:17:30 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][260/312]	eta 0:00:38 lr 0.002977	time 0.7616 (0.7481)	model_time 0.7614 (0.7427)	loss 3.7109 (3.4267)	grad_norm 2.3563 (1.3683/0.5968)	mem 34602MB
[2025-01-19 07:17:37 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][270/312]	eta 0:00:31 lr 0.002976	time 0.7437 (0.7474)	model_time 0.7435 (0.7421)	loss 4.0258 (3.4270)	grad_norm 1.2017 (1.3810/0.5968)	mem 34602MB
[2025-01-19 07:17:44 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][280/312]	eta 0:00:23 lr 0.002976	time 0.7409 (0.7468)	model_time 0.7405 (0.7417)	loss 3.9993 (3.4312)	grad_norm 1.2471 (1.3663/0.5924)	mem 34602MB
[2025-01-19 07:17:52 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][290/312]	eta 0:00:16 lr 0.002975	time 0.7267 (0.7465)	model_time 0.7265 (0.7416)	loss 3.5391 (3.4330)	grad_norm 0.8001 (1.3700/0.5969)	mem 34602MB
[2025-01-19 07:17:59 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][300/312]	eta 0:00:08 lr 0.002975	time 0.7124 (0.7466)	model_time 0.7123 (0.7419)	loss 3.7034 (3.4289)	grad_norm 0.7800 (1.3665/0.5965)	mem 34602MB
[2025-01-19 07:18:07 internimage_b_1k_224] (main.py 510): INFO Train: [101/300][310/312]	eta 0:00:01 lr 0.002974	time 0.7055 (0.7470)	model_time 0.7054 (0.7424)	loss 4.0778 (3.4285)	grad_norm 1.1963 (1.3548/0.5923)	mem 34602MB
[2025-01-19 07:18:07 internimage_b_1k_224] (main.py 519): INFO EPOCH 101 training takes 0:03:53
[2025-01-19 07:18:07 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_101.pth saving......
[2025-01-19 07:18:11 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_101.pth saved !!!
[2025-01-19 07:18:18 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.337 (7.337)	Loss 0.8489 (0.8489)	Acc@1 82.397 (82.397)	Acc@5 96.289 (96.289)	Mem 34602MB
[2025-01-19 07:18:21 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.927)	Loss 1.1839 (1.0175)	Acc@1 73.755 (78.456)	Acc@5 92.651 (94.549)	Mem 34602MB
[2025-01-19 07:18:21 internimage_b_1k_224] (main.py 575): INFO [Epoch:101] * Acc@1 78.379 Acc@5 94.580
[2025-01-19 07:18:21 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.4%
[2025-01-19 07:18:21 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 07:18:25 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 07:18:25 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 78.38%
[2025-01-19 07:18:32 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.253 (7.253)	Loss 0.7396 (0.7396)	Acc@1 81.665 (81.665)	Acc@5 96.436 (96.436)	Mem 34602MB
[2025-01-19 07:18:35 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.927)	Loss 1.1329 (0.9065)	Acc@1 72.461 (78.103)	Acc@5 91.772 (94.338)	Mem 34602MB
[2025-01-19 07:18:35 internimage_b_1k_224] (main.py 575): INFO [Epoch:101] * Acc@1 78.095 Acc@5 94.398
[2025-01-19 07:18:35 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.1%
[2025-01-19 07:18:35 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 07:18:39 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 07:18:39 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 78.10%
[2025-01-19 07:18:42 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][0/312]	eta 0:11:42 lr 0.002974	time 2.2524 (2.2524)	model_time 0.7483 (0.7483)	loss 4.0856 (4.0856)	grad_norm 0.9639 (0.9639/0.0000)	mem 34602MB
[2025-01-19 07:18:49 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][10/312]	eta 0:04:27 lr 0.002973	time 0.7489 (0.8862)	model_time 0.7487 (0.7492)	loss 3.6905 (3.6397)	grad_norm 0.9521 (1.3952/0.4397)	mem 34602MB
[2025-01-19 07:18:57 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][20/312]	eta 0:04:01 lr 0.002973	time 0.7183 (0.8254)	model_time 0.7179 (0.7535)	loss 3.8840 (3.4619)	grad_norm 1.0795 (1.3869/0.4451)	mem 34602MB
[2025-01-19 07:19:04 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][30/312]	eta 0:03:44 lr 0.002972	time 0.7434 (0.7949)	model_time 0.7432 (0.7462)	loss 2.1951 (3.3505)	grad_norm 1.8531 (1.4960/0.4825)	mem 34602MB
[2025-01-19 07:19:11 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][40/312]	eta 0:03:33 lr 0.002972	time 0.7415 (0.7849)	model_time 0.7413 (0.7479)	loss 3.4798 (3.3412)	grad_norm 0.7909 (1.4806/0.4932)	mem 34602MB
[2025-01-19 07:19:19 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][50/312]	eta 0:03:23 lr 0.002971	time 0.7220 (0.7776)	model_time 0.7219 (0.7479)	loss 3.3849 (3.3536)	grad_norm 0.8663 (1.4043/0.4974)	mem 34602MB
[2025-01-19 07:19:26 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][60/312]	eta 0:03:14 lr 0.002970	time 0.7823 (0.7715)	model_time 0.7821 (0.7465)	loss 3.7768 (3.3437)	grad_norm 0.8467 (1.4457/0.5650)	mem 34602MB
[2025-01-19 07:19:34 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][70/312]	eta 0:03:05 lr 0.002970	time 0.7081 (0.7661)	model_time 0.7074 (0.7446)	loss 2.7684 (3.3321)	grad_norm 2.1476 (1.4400/0.5594)	mem 34602MB
[2025-01-19 07:19:41 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][80/312]	eta 0:02:56 lr 0.002969	time 0.7144 (0.7613)	model_time 0.7143 (0.7424)	loss 2.6100 (3.3405)	grad_norm 2.2847 (1.4096/0.5656)	mem 34602MB
[2025-01-19 07:19:48 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][90/312]	eta 0:02:48 lr 0.002969	time 0.7286 (0.7576)	model_time 0.7285 (0.7408)	loss 3.5838 (3.3530)	grad_norm 1.5046 (1.4241/0.5614)	mem 34602MB
[2025-01-19 07:19:56 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][100/312]	eta 0:02:40 lr 0.002968	time 0.8048 (0.7581)	model_time 0.8047 (0.7429)	loss 3.7531 (3.3795)	grad_norm 2.4866 (1.4051/0.5552)	mem 34602MB
[2025-01-19 07:20:03 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][110/312]	eta 0:02:32 lr 0.002967	time 0.7714 (0.7573)	model_time 0.7710 (0.7434)	loss 2.4219 (3.3900)	grad_norm 0.9337 (1.3878/0.5478)	mem 34602MB
[2025-01-19 07:20:11 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][120/312]	eta 0:02:25 lr 0.002967	time 0.7190 (0.7581)	model_time 0.7186 (0.7453)	loss 3.8317 (3.3982)	grad_norm 0.7049 (1.3670/0.5393)	mem 34602MB
[2025-01-19 07:20:19 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][130/312]	eta 0:02:17 lr 0.002966	time 0.7586 (0.7577)	model_time 0.7585 (0.7459)	loss 3.6399 (3.4054)	grad_norm 0.6689 (1.3415/0.5297)	mem 34602MB
[2025-01-19 07:20:26 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][140/312]	eta 0:02:10 lr 0.002966	time 0.8003 (0.7587)	model_time 0.8002 (0.7478)	loss 3.5350 (3.3955)	grad_norm 0.6451 (1.3376/0.5206)	mem 34602MB
[2025-01-19 07:20:34 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][150/312]	eta 0:02:02 lr 0.002965	time 0.7152 (0.7571)	model_time 0.7150 (0.7468)	loss 3.1999 (3.3921)	grad_norm 2.4195 (1.3948/0.5674)	mem 34602MB
[2025-01-19 07:20:41 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][160/312]	eta 0:01:54 lr 0.002965	time 0.7360 (0.7563)	model_time 0.7355 (0.7466)	loss 2.6334 (3.3677)	grad_norm 1.5322 (1.3942/0.5585)	mem 34602MB
[2025-01-19 07:20:49 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][170/312]	eta 0:01:47 lr 0.002964	time 0.8025 (0.7559)	model_time 0.8023 (0.7468)	loss 2.5799 (3.3709)	grad_norm 0.7630 (1.3853/0.5515)	mem 34602MB
[2025-01-19 07:20:56 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][180/312]	eta 0:01:39 lr 0.002963	time 0.8134 (0.7547)	model_time 0.8130 (0.7461)	loss 3.8991 (3.3757)	grad_norm 1.2991 (1.3855/0.5430)	mem 34602MB
[2025-01-19 07:21:03 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][190/312]	eta 0:01:31 lr 0.002963	time 0.7255 (0.7534)	model_time 0.7250 (0.7452)	loss 2.7432 (3.3665)	grad_norm 1.2171 (1.3768/0.5315)	mem 34602MB
[2025-01-19 07:21:10 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][200/312]	eta 0:01:24 lr 0.002962	time 0.7327 (0.7518)	model_time 0.7323 (0.7440)	loss 3.9666 (3.3732)	grad_norm 1.6471 (1.3780/0.5400)	mem 34602MB
[2025-01-19 07:21:18 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][210/312]	eta 0:01:16 lr 0.002962	time 0.7434 (0.7511)	model_time 0.7432 (0.7436)	loss 2.8016 (3.3729)	grad_norm 1.2308 (1.3650/0.5361)	mem 34602MB
[2025-01-19 07:21:25 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][220/312]	eta 0:01:09 lr 0.002961	time 0.8329 (0.7513)	model_time 0.8325 (0.7441)	loss 2.9598 (3.3648)	grad_norm 0.6947 (1.3450/0.5329)	mem 34602MB
[2025-01-19 07:21:33 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][230/312]	eta 0:01:01 lr 0.002960	time 0.7993 (0.7509)	model_time 0.7991 (0.7440)	loss 3.2863 (3.3664)	grad_norm 1.5638 (1.3402/0.5290)	mem 34602MB
[2025-01-19 07:21:40 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][240/312]	eta 0:00:54 lr 0.002960	time 0.7222 (0.7515)	model_time 0.7220 (0.7449)	loss 3.5636 (3.3697)	grad_norm 1.3604 (1.3851/0.5880)	mem 34602MB
[2025-01-19 07:21:48 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][250/312]	eta 0:00:46 lr 0.002959	time 0.8272 (0.7522)	model_time 0.8270 (0.7459)	loss 3.2899 (3.3723)	grad_norm 0.8413 (1.3863/0.5844)	mem 34602MB
[2025-01-19 07:21:56 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][260/312]	eta 0:00:39 lr 0.002959	time 0.7276 (0.7526)	model_time 0.7271 (0.7465)	loss 2.5441 (3.3743)	grad_norm 1.4604 (1.3847/0.5748)	mem 34602MB
[2025-01-19 07:22:03 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][270/312]	eta 0:00:31 lr 0.002958	time 0.7213 (0.7523)	model_time 0.7209 (0.7464)	loss 3.2963 (3.3741)	grad_norm 1.5605 (1.3964/0.5751)	mem 34602MB
[2025-01-19 07:22:11 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][280/312]	eta 0:00:24 lr 0.002958	time 0.7311 (0.7520)	model_time 0.7310 (0.7463)	loss 3.4748 (3.3786)	grad_norm 1.0131 (1.3966/0.5717)	mem 34602MB
[2025-01-19 07:22:18 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][290/312]	eta 0:00:16 lr 0.002957	time 0.7293 (0.7514)	model_time 0.7291 (0.7459)	loss 3.5395 (3.3811)	grad_norm 0.8611 (1.3792/0.5701)	mem 34602MB
[2025-01-19 07:22:25 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][300/312]	eta 0:00:09 lr 0.002956	time 0.7953 (0.7511)	model_time 0.7952 (0.7458)	loss 3.9769 (3.3956)	grad_norm 0.9315 (1.3718/0.5666)	mem 34602MB
[2025-01-19 07:22:32 internimage_b_1k_224] (main.py 510): INFO Train: [102/300][310/312]	eta 0:00:01 lr 0.002956	time 0.7135 (0.7499)	model_time 0.7134 (0.7448)	loss 3.4546 (3.3951)	grad_norm 0.9083 (1.3694/0.5670)	mem 34602MB
[2025-01-19 07:22:33 internimage_b_1k_224] (main.py 519): INFO EPOCH 102 training takes 0:03:53
[2025-01-19 07:22:33 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_102.pth saving......
[2025-01-19 07:22:36 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_102.pth saved !!!
[2025-01-19 07:22:44 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.657 (7.657)	Loss 0.8348 (0.8348)	Acc@1 82.202 (82.202)	Acc@5 96.606 (96.606)	Mem 34602MB
[2025-01-19 07:22:47 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.971)	Loss 1.2164 (1.0103)	Acc@1 73.242 (78.671)	Acc@5 92.407 (94.551)	Mem 34602MB
[2025-01-19 07:22:47 internimage_b_1k_224] (main.py 575): INFO [Epoch:102] * Acc@1 78.611 Acc@5 94.618
[2025-01-19 07:22:47 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.6%
[2025-01-19 07:22:47 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 07:22:51 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 07:22:51 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 78.61%
[2025-01-19 07:22:58 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.434 (7.434)	Loss 0.7341 (0.7341)	Acc@1 81.812 (81.812)	Acc@5 96.460 (96.460)	Mem 34602MB
[2025-01-19 07:23:01 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.955)	Loss 1.1252 (0.9007)	Acc@1 72.607 (78.218)	Acc@5 91.846 (94.385)	Mem 34602MB
[2025-01-19 07:23:02 internimage_b_1k_224] (main.py 575): INFO [Epoch:102] * Acc@1 78.199 Acc@5 94.444
[2025-01-19 07:23:02 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.2%
[2025-01-19 07:23:02 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 07:23:06 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 07:23:06 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 78.20%
[2025-01-19 07:23:09 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][0/312]	eta 0:12:54 lr 0.002956	time 2.4829 (2.4829)	model_time 0.7626 (0.7626)	loss 4.2895 (4.2895)	grad_norm 1.0721 (1.0721/0.0000)	mem 34602MB
[2025-01-19 07:23:16 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][10/312]	eta 0:04:26 lr 0.002955	time 0.7211 (0.8824)	model_time 0.7210 (0.7257)	loss 4.0240 (3.6543)	grad_norm 0.8851 (1.6842/0.8364)	mem 34602MB
[2025-01-19 07:23:23 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][20/312]	eta 0:03:56 lr 0.002954	time 0.7236 (0.8104)	model_time 0.7232 (0.7281)	loss 2.7444 (3.5403)	grad_norm 0.9759 (1.4411/0.7116)	mem 34602MB
[2025-01-19 07:23:31 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][30/312]	eta 0:03:43 lr 0.002954	time 0.8063 (0.7933)	model_time 0.8062 (0.7375)	loss 3.7607 (3.5405)	grad_norm 1.2929 (1.4177/0.6084)	mem 34602MB
[2025-01-19 07:23:38 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][40/312]	eta 0:03:32 lr 0.002953	time 0.7189 (0.7802)	model_time 0.7184 (0.7379)	loss 3.8125 (3.5418)	grad_norm 2.3211 (1.4422/0.6208)	mem 34602MB
[2025-01-19 07:23:46 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][50/312]	eta 0:03:23 lr 0.002953	time 0.7183 (0.7759)	model_time 0.7179 (0.7418)	loss 3.5875 (3.5400)	grad_norm 2.3968 (1.5401/0.6748)	mem 34602MB
[2025-01-19 07:23:53 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][60/312]	eta 0:03:15 lr 0.002952	time 0.8317 (0.7742)	model_time 0.8313 (0.7456)	loss 3.6022 (3.5322)	grad_norm 1.1149 (1.4518/0.6573)	mem 34602MB
[2025-01-19 07:24:01 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][70/312]	eta 0:03:07 lr 0.002952	time 0.8254 (0.7735)	model_time 0.8252 (0.7489)	loss 3.4654 (3.5104)	grad_norm 0.7298 (1.4097/0.6287)	mem 34602MB
[2025-01-19 07:24:08 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][80/312]	eta 0:02:58 lr 0.002951	time 0.7193 (0.7695)	model_time 0.7189 (0.7479)	loss 2.8513 (3.5211)	grad_norm 1.5107 (1.3857/0.6027)	mem 34602MB
[2025-01-19 07:24:16 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][90/312]	eta 0:02:50 lr 0.002950	time 0.7210 (0.7668)	model_time 0.7205 (0.7475)	loss 4.2058 (3.5054)	grad_norm 2.2158 (1.3920/0.5984)	mem 34602MB
[2025-01-19 07:24:23 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][100/312]	eta 0:02:41 lr 0.002950	time 0.7544 (0.7640)	model_time 0.7543 (0.7466)	loss 2.9290 (3.4718)	grad_norm 1.3244 (1.3884/0.5924)	mem 34602MB
[2025-01-19 07:24:31 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][110/312]	eta 0:02:33 lr 0.002949	time 0.7220 (0.7621)	model_time 0.7219 (0.7463)	loss 2.4025 (3.4785)	grad_norm 1.9597 (1.3629/0.5821)	mem 34602MB
[2025-01-19 07:24:38 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][120/312]	eta 0:02:25 lr 0.002949	time 0.7176 (0.7595)	model_time 0.7174 (0.7449)	loss 2.4400 (3.4685)	grad_norm 1.4330 (1.3891/0.5730)	mem 34602MB
[2025-01-19 07:24:45 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][130/312]	eta 0:02:17 lr 0.002948	time 0.7311 (0.7575)	model_time 0.7309 (0.7440)	loss 2.6575 (3.4710)	grad_norm 1.3761 (1.3967/0.5875)	mem 34602MB
[2025-01-19 07:24:53 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][140/312]	eta 0:02:09 lr 0.002947	time 0.7229 (0.7552)	model_time 0.7227 (0.7426)	loss 3.8394 (3.4728)	grad_norm 0.9973 (1.4119/0.5939)	mem 34602MB
[2025-01-19 07:25:00 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][150/312]	eta 0:02:02 lr 0.002947	time 0.8033 (0.7547)	model_time 0.8029 (0.7429)	loss 2.9273 (3.4668)	grad_norm 1.0290 (1.4003/0.5919)	mem 34602MB
[2025-01-19 07:25:08 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][160/312]	eta 0:01:54 lr 0.002946	time 0.7442 (0.7547)	model_time 0.7441 (0.7436)	loss 4.0724 (3.4601)	grad_norm 0.9287 (1.4015/0.5820)	mem 34602MB
[2025-01-19 07:25:15 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][170/312]	eta 0:01:47 lr 0.002946	time 0.7197 (0.7551)	model_time 0.7196 (0.7447)	loss 3.6763 (3.4702)	grad_norm 1.2676 (1.4095/0.5812)	mem 34602MB
[2025-01-19 07:25:23 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][180/312]	eta 0:01:39 lr 0.002945	time 0.8170 (0.7559)	model_time 0.8165 (0.7460)	loss 3.6021 (3.4717)	grad_norm 1.3694 (1.3913/0.5726)	mem 34602MB
[2025-01-19 07:25:31 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][190/312]	eta 0:01:32 lr 0.002945	time 0.8048 (0.7571)	model_time 0.8046 (0.7477)	loss 3.6295 (3.4677)	grad_norm 0.6326 (1.3835/0.5782)	mem 34602MB
[2025-01-19 07:25:38 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][200/312]	eta 0:01:24 lr 0.002944	time 0.7531 (0.7564)	model_time 0.7527 (0.7475)	loss 2.7508 (3.4787)	grad_norm 0.8012 (1.3791/0.5797)	mem 34602MB
[2025-01-19 07:25:46 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][210/312]	eta 0:01:17 lr 0.002943	time 0.7191 (0.7559)	model_time 0.7189 (0.7474)	loss 4.1929 (3.4906)	grad_norm 1.2934 (1.3760/0.5709)	mem 34602MB
[2025-01-19 07:25:53 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][220/312]	eta 0:01:09 lr 0.002943	time 0.7303 (0.7548)	model_time 0.7299 (0.7467)	loss 2.9287 (3.4815)	grad_norm 1.0837 (1.3608/0.5635)	mem 34602MB
[2025-01-19 07:26:00 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][230/312]	eta 0:01:01 lr 0.002942	time 0.7251 (0.7544)	model_time 0.7250 (0.7466)	loss 2.6049 (3.4712)	grad_norm 2.5755 (1.3716/0.5715)	mem 34602MB
[2025-01-19 07:26:08 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][240/312]	eta 0:00:54 lr 0.002942	time 0.7154 (0.7534)	model_time 0.7152 (0.7459)	loss 3.3266 (3.4666)	grad_norm 0.7068 (1.3602/0.5658)	mem 34602MB
[2025-01-19 07:26:15 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][250/312]	eta 0:00:46 lr 0.002941	time 0.7307 (0.7525)	model_time 0.7303 (0.7453)	loss 4.2713 (3.4697)	grad_norm 1.6948 (1.3743/0.5686)	mem 34602MB
[2025-01-19 07:26:22 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][260/312]	eta 0:00:39 lr 0.002940	time 0.7166 (0.7515)	model_time 0.7164 (0.7446)	loss 3.6922 (3.4676)	grad_norm 0.8492 (1.3596/0.5649)	mem 34602MB
[2025-01-19 07:26:30 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][270/312]	eta 0:00:31 lr 0.002940	time 0.8047 (0.7514)	model_time 0.8043 (0.7447)	loss 3.6446 (3.4687)	grad_norm 1.2866 (1.3488/0.5591)	mem 34602MB
[2025-01-19 07:26:37 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][280/312]	eta 0:00:24 lr 0.002939	time 0.7308 (0.7512)	model_time 0.7307 (0.7447)	loss 3.4266 (3.4597)	grad_norm 1.2495 (1.3442/0.5583)	mem 34602MB
[2025-01-19 07:26:45 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][290/312]	eta 0:00:16 lr 0.002939	time 0.7350 (0.7511)	model_time 0.7348 (0.7448)	loss 3.5216 (3.4598)	grad_norm 1.4144 (1.3504/0.5650)	mem 34602MB
[2025-01-19 07:26:52 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][300/312]	eta 0:00:09 lr 0.002938	time 0.8062 (0.7514)	model_time 0.8061 (0.7453)	loss 3.6134 (3.4545)	grad_norm 1.0012 (1.3560/0.5739)	mem 34602MB
[2025-01-19 07:27:00 internimage_b_1k_224] (main.py 510): INFO Train: [103/300][310/312]	eta 0:00:01 lr 0.002937	time 0.7144 (0.7512)	model_time 0.7143 (0.7453)	loss 2.7790 (3.4625)	grad_norm 1.6826 (1.3358/0.5530)	mem 34602MB
[2025-01-19 07:27:00 internimage_b_1k_224] (main.py 519): INFO EPOCH 103 training takes 0:03:54
[2025-01-19 07:27:00 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_103.pth saving......
[2025-01-19 07:27:04 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_103.pth saved !!!
[2025-01-19 07:27:11 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.353 (7.353)	Loss 0.8442 (0.8442)	Acc@1 82.227 (82.227)	Acc@5 96.851 (96.851)	Mem 34602MB
[2025-01-19 07:27:14 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.941)	Loss 1.1832 (1.0042)	Acc@1 74.170 (78.658)	Acc@5 93.066 (94.795)	Mem 34602MB
[2025-01-19 07:27:14 internimage_b_1k_224] (main.py 575): INFO [Epoch:103] * Acc@1 78.583 Acc@5 94.818
[2025-01-19 07:27:14 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.6%
[2025-01-19 07:27:14 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 78.61%
[2025-01-19 07:27:23 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.888 (8.888)	Loss 0.7287 (0.7287)	Acc@1 81.836 (81.836)	Acc@5 96.582 (96.582)	Mem 34602MB
[2025-01-19 07:27:28 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.227)	Loss 1.1180 (0.8950)	Acc@1 72.803 (78.329)	Acc@5 91.943 (94.436)	Mem 34602MB
[2025-01-19 07:27:28 internimage_b_1k_224] (main.py 575): INFO [Epoch:103] * Acc@1 78.299 Acc@5 94.496
[2025-01-19 07:27:28 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.3%
[2025-01-19 07:27:28 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 07:27:33 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 07:27:33 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 78.30%
[2025-01-19 07:27:35 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][0/312]	eta 0:13:40 lr 0.002937	time 2.6312 (2.6312)	model_time 0.7767 (0.7767)	loss 2.7903 (2.7903)	grad_norm 1.9858 (1.9858/0.0000)	mem 34602MB
[2025-01-19 07:27:43 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][10/312]	eta 0:04:36 lr 0.002937	time 0.7483 (0.9162)	model_time 0.7482 (0.7474)	loss 3.7379 (3.2338)	grad_norm 1.6713 (1.4204/0.3961)	mem 34602MB
[2025-01-19 07:27:50 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][20/312]	eta 0:04:04 lr 0.002936	time 0.7142 (0.8374)	model_time 0.7140 (0.7488)	loss 3.2248 (3.3342)	grad_norm 0.6991 (1.5094/0.6486)	mem 34602MB
[2025-01-19 07:27:58 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][30/312]	eta 0:03:47 lr 0.002936	time 0.7168 (0.8076)	model_time 0.7166 (0.7475)	loss 3.6240 (3.3575)	grad_norm 1.4259 (1.4667/0.5797)	mem 34602MB
[2025-01-19 07:28:05 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][40/312]	eta 0:03:34 lr 0.002935	time 0.7293 (0.7877)	model_time 0.7291 (0.7422)	loss 2.8303 (3.3253)	grad_norm 0.8032 (1.4791/0.5554)	mem 34602MB
[2025-01-19 07:28:12 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][50/312]	eta 0:03:23 lr 0.002934	time 0.7273 (0.7775)	model_time 0.7272 (0.7409)	loss 2.8391 (3.2986)	grad_norm 1.5914 (1.4565/0.5540)	mem 34602MB
[2025-01-19 07:28:20 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][60/312]	eta 0:03:14 lr 0.002934	time 0.7226 (0.7707)	model_time 0.7224 (0.7400)	loss 2.8240 (3.3265)	grad_norm 1.4973 (1.4064/0.5375)	mem 34602MB
[2025-01-19 07:28:27 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][70/312]	eta 0:03:05 lr 0.002933	time 0.7161 (0.7646)	model_time 0.7159 (0.7381)	loss 3.3503 (3.3247)	grad_norm 2.1146 (1.3875/0.5173)	mem 34602MB
[2025-01-19 07:28:34 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][80/312]	eta 0:02:56 lr 0.002933	time 0.7941 (0.7624)	model_time 0.7940 (0.7392)	loss 3.1812 (3.3228)	grad_norm 1.7441 (1.4107/0.5144)	mem 34602MB
[2025-01-19 07:28:42 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][90/312]	eta 0:02:48 lr 0.002932	time 0.7175 (0.7607)	model_time 0.7174 (0.7400)	loss 3.7503 (3.3239)	grad_norm 1.8137 (1.4923/0.5813)	mem 34602MB
[2025-01-19 07:28:49 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][100/312]	eta 0:02:41 lr 0.002931	time 0.7278 (0.7607)	model_time 0.7277 (0.7420)	loss 3.4291 (3.3110)	grad_norm 1.1269 (1.4564/0.5670)	mem 34602MB
[2025-01-19 07:28:57 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][110/312]	eta 0:02:33 lr 0.002931	time 0.8022 (0.7610)	model_time 0.8020 (0.7440)	loss 2.2228 (3.2943)	grad_norm 2.0844 (1.4421/0.5663)	mem 34602MB
[2025-01-19 07:29:05 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][120/312]	eta 0:02:26 lr 0.002930	time 0.8057 (0.7608)	model_time 0.8053 (0.7452)	loss 3.5415 (3.3202)	grad_norm 1.2734 (1.4497/0.5666)	mem 34602MB
[2025-01-19 07:29:12 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][130/312]	eta 0:02:18 lr 0.002930	time 0.7346 (0.7602)	model_time 0.7345 (0.7457)	loss 3.4571 (3.3371)	grad_norm 1.1929 (1.4429/0.5520)	mem 34602MB
[2025-01-19 07:29:20 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][140/312]	eta 0:02:10 lr 0.002929	time 0.7168 (0.7589)	model_time 0.7164 (0.7455)	loss 3.7729 (3.3427)	grad_norm 1.5512 (1.4458/0.5461)	mem 34602MB
[2025-01-19 07:29:27 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][150/312]	eta 0:02:02 lr 0.002928	time 0.7156 (0.7585)	model_time 0.7155 (0.7459)	loss 2.7995 (3.3361)	grad_norm 0.8139 (1.4345/0.5348)	mem 34602MB
[2025-01-19 07:29:34 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][160/312]	eta 0:01:55 lr 0.002928	time 0.7575 (0.7566)	model_time 0.7574 (0.7448)	loss 3.5241 (3.3317)	grad_norm 1.6050 (1.4186/0.5252)	mem 34602MB
[2025-01-19 07:29:42 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][170/312]	eta 0:01:47 lr 0.002927	time 0.7200 (0.7555)	model_time 0.7198 (0.7444)	loss 2.3206 (3.3277)	grad_norm 1.2142 (1.3998/0.5175)	mem 34602MB
[2025-01-19 07:29:49 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][180/312]	eta 0:01:39 lr 0.002927	time 0.7180 (0.7538)	model_time 0.7176 (0.7433)	loss 2.5296 (3.3296)	grad_norm 2.2104 (1.4182/0.5385)	mem 34602MB
[2025-01-19 07:29:56 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][190/312]	eta 0:01:31 lr 0.002926	time 0.7202 (0.7524)	model_time 0.7201 (0.7424)	loss 3.9150 (3.3465)	grad_norm 1.0382 (1.4037/0.5332)	mem 34602MB
[2025-01-19 07:30:04 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][200/312]	eta 0:01:24 lr 0.002926	time 0.8062 (0.7523)	model_time 0.8057 (0.7427)	loss 3.5015 (3.3505)	grad_norm 0.7696 (1.3818/0.5324)	mem 34602MB
[2025-01-19 07:30:11 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][210/312]	eta 0:01:16 lr 0.002925	time 0.7162 (0.7524)	model_time 0.7159 (0.7433)	loss 3.6905 (3.3460)	grad_norm 2.1768 (1.3779/0.5285)	mem 34602MB
[2025-01-19 07:30:19 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][220/312]	eta 0:01:09 lr 0.002924	time 0.7236 (0.7520)	model_time 0.7231 (0.7433)	loss 3.4634 (3.3478)	grad_norm 1.3639 (1.3860/0.5406)	mem 34602MB
[2025-01-19 07:30:26 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][230/312]	eta 0:01:01 lr 0.002924	time 0.8151 (0.7524)	model_time 0.8145 (0.7441)	loss 3.5903 (3.3484)	grad_norm 1.0662 (1.3752/0.5361)	mem 34602MB
[2025-01-19 07:30:34 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][240/312]	eta 0:00:54 lr 0.002923	time 0.8085 (0.7525)	model_time 0.8084 (0.7445)	loss 2.3656 (3.3479)	grad_norm 3.2351 (1.3793/0.5449)	mem 34602MB
[2025-01-19 07:30:41 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][250/312]	eta 0:00:46 lr 0.002923	time 0.7187 (0.7525)	model_time 0.7182 (0.7447)	loss 2.3309 (3.3427)	grad_norm 1.5144 (1.3811/0.5445)	mem 34602MB
[2025-01-19 07:30:49 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][260/312]	eta 0:00:39 lr 0.002922	time 0.7154 (0.7524)	model_time 0.7153 (0.7450)	loss 3.5644 (3.3382)	grad_norm 1.7165 (1.3745/0.5381)	mem 34602MB
[2025-01-19 07:30:56 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][270/312]	eta 0:00:31 lr 0.002921	time 0.7182 (0.7523)	model_time 0.7178 (0.7451)	loss 3.2660 (3.3466)	grad_norm 1.1021 (1.3754/0.5353)	mem 34602MB
[2025-01-19 07:31:04 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][280/312]	eta 0:00:24 lr 0.002921	time 0.7230 (0.7515)	model_time 0.7228 (0.7445)	loss 3.4567 (3.3548)	grad_norm 0.7282 (1.3794/0.5376)	mem 34602MB
[2025-01-19 07:31:11 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][290/312]	eta 0:00:16 lr 0.002920	time 0.7224 (0.7511)	model_time 0.7222 (0.7444)	loss 2.1229 (3.3601)	grad_norm 0.7229 (1.3620/0.5366)	mem 34602MB
[2025-01-19 07:31:18 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][300/312]	eta 0:00:09 lr 0.002920	time 0.7156 (0.7500)	model_time 0.7155 (0.7435)	loss 3.1134 (3.3588)	grad_norm 1.1931 (1.3644/0.5412)	mem 34602MB
[2025-01-19 07:31:25 internimage_b_1k_224] (main.py 510): INFO Train: [104/300][310/312]	eta 0:00:01 lr 0.002919	time 0.7117 (0.7489)	model_time 0.7116 (0.7426)	loss 3.7068 (3.3592)	grad_norm 1.0809 (1.3715/0.5434)	mem 34602MB
[2025-01-19 07:31:26 internimage_b_1k_224] (main.py 519): INFO EPOCH 104 training takes 0:03:53
[2025-01-19 07:31:26 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_104.pth saving......
[2025-01-19 07:31:29 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_104.pth saved !!!
[2025-01-19 07:31:37 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.217 (7.217)	Loss 0.8449 (0.8449)	Acc@1 81.445 (81.445)	Acc@5 96.680 (96.680)	Mem 34602MB
[2025-01-19 07:31:40 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.924)	Loss 1.1918 (1.0094)	Acc@1 74.243 (78.407)	Acc@5 92.969 (94.651)	Mem 34602MB
[2025-01-19 07:31:40 internimage_b_1k_224] (main.py 575): INFO [Epoch:104] * Acc@1 78.347 Acc@5 94.684
[2025-01-19 07:31:40 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.3%
[2025-01-19 07:31:40 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 78.61%
[2025-01-19 07:31:49 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.048 (9.048)	Loss 0.7241 (0.7241)	Acc@1 81.836 (81.836)	Acc@5 96.606 (96.606)	Mem 34602MB
[2025-01-19 07:31:53 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.217)	Loss 1.1105 (0.8898)	Acc@1 72.925 (78.420)	Acc@5 91.943 (94.489)	Mem 34602MB
[2025-01-19 07:31:54 internimage_b_1k_224] (main.py 575): INFO [Epoch:104] * Acc@1 78.387 Acc@5 94.548
[2025-01-19 07:31:54 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.4%
[2025-01-19 07:31:54 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 07:31:58 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 07:31:58 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 78.39%
[2025-01-19 07:32:00 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][0/312]	eta 0:10:24 lr 0.002919	time 2.0002 (2.0002)	model_time 0.7561 (0.7561)	loss 2.2443 (2.2443)	grad_norm 2.1633 (2.1633/0.0000)	mem 34602MB
[2025-01-19 07:32:07 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][10/312]	eta 0:04:21 lr 0.002918	time 0.7216 (0.8646)	model_time 0.7214 (0.7512)	loss 3.5772 (3.3259)	grad_norm 0.9670 (1.2327/0.5031)	mem 34602MB
[2025-01-19 07:32:15 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][20/312]	eta 0:03:57 lr 0.002918	time 0.8005 (0.8141)	model_time 0.8001 (0.7546)	loss 3.7161 (3.3899)	grad_norm 3.2059 (1.4633/0.6626)	mem 34602MB
[2025-01-19 07:32:22 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][30/312]	eta 0:03:44 lr 0.002917	time 0.7177 (0.7948)	model_time 0.7175 (0.7544)	loss 3.4699 (3.4192)	grad_norm 2.3637 (1.4899/0.6545)	mem 34602MB
[2025-01-19 07:32:30 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][40/312]	eta 0:03:33 lr 0.002917	time 0.8107 (0.7865)	model_time 0.8103 (0.7559)	loss 3.5364 (3.4032)	grad_norm 1.1006 (1.4723/0.6149)	mem 34602MB
[2025-01-19 07:32:37 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][50/312]	eta 0:03:24 lr 0.002916	time 0.7550 (0.7814)	model_time 0.7549 (0.7567)	loss 3.5914 (3.3900)	grad_norm 1.7447 (1.3943/0.5865)	mem 34602MB
[2025-01-19 07:32:45 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][60/312]	eta 0:03:15 lr 0.002915	time 0.7262 (0.7750)	model_time 0.7258 (0.7543)	loss 3.3826 (3.4101)	grad_norm 0.8466 (1.3454/0.5672)	mem 34602MB
[2025-01-19 07:32:52 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][70/312]	eta 0:03:06 lr 0.002915	time 0.8349 (0.7714)	model_time 0.8343 (0.7535)	loss 3.5309 (3.4668)	grad_norm 0.9658 (1.3460/0.5472)	mem 34602MB
[2025-01-19 07:33:00 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][80/312]	eta 0:02:58 lr 0.002914	time 0.8077 (0.7686)	model_time 0.8075 (0.7529)	loss 2.6004 (3.4422)	grad_norm 1.9705 (1.3675/0.5487)	mem 34602MB
[2025-01-19 07:33:07 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][90/312]	eta 0:02:49 lr 0.002914	time 0.7267 (0.7639)	model_time 0.7266 (0.7499)	loss 4.5771 (3.4821)	grad_norm 1.2474 (1.3824/0.5317)	mem 34602MB
[2025-01-19 07:33:14 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][100/312]	eta 0:02:41 lr 0.002913	time 0.7208 (0.7610)	model_time 0.7207 (0.7483)	loss 3.8024 (3.4911)	grad_norm 1.9978 (1.3919/0.5448)	mem 34602MB
[2025-01-19 07:33:22 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][110/312]	eta 0:02:33 lr 0.002912	time 0.7304 (0.7579)	model_time 0.7299 (0.7464)	loss 3.2934 (3.4774)	grad_norm 0.8429 (1.3956/0.5345)	mem 34602MB
[2025-01-19 07:33:29 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][120/312]	eta 0:02:25 lr 0.002912	time 0.7148 (0.7556)	model_time 0.7143 (0.7449)	loss 2.4241 (3.4556)	grad_norm 0.5470 (1.3984/0.5555)	mem 34602MB
[2025-01-19 07:33:37 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][130/312]	eta 0:02:17 lr 0.002911	time 0.8174 (0.7554)	model_time 0.8172 (0.7456)	loss 4.3567 (3.4430)	grad_norm 1.0339 (1.4126/0.5741)	mem 34602MB
[2025-01-19 07:33:44 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][140/312]	eta 0:02:09 lr 0.002911	time 0.8094 (0.7552)	model_time 0.8090 (0.7460)	loss 2.6309 (3.4334)	grad_norm 1.0163 (1.4138/0.5700)	mem 34602MB
[2025-01-19 07:33:52 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][150/312]	eta 0:02:02 lr 0.002910	time 0.7130 (0.7558)	model_time 0.7126 (0.7472)	loss 4.2742 (3.4314)	grad_norm 0.6844 (1.3926/0.5671)	mem 34602MB
[2025-01-19 07:33:59 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][160/312]	eta 0:01:54 lr 0.002909	time 0.7181 (0.7552)	model_time 0.7177 (0.7471)	loss 3.6105 (3.4315)	grad_norm 1.0063 (1.3653/0.5671)	mem 34602MB
[2025-01-19 07:34:07 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][170/312]	eta 0:01:47 lr 0.002909	time 0.7317 (0.7553)	model_time 0.7316 (0.7477)	loss 4.2869 (3.4208)	grad_norm 2.3183 (1.3925/0.5964)	mem 34602MB
[2025-01-19 07:34:14 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][180/312]	eta 0:01:39 lr 0.002908	time 0.7194 (0.7548)	model_time 0.7193 (0.7476)	loss 3.3915 (3.4399)	grad_norm 1.1985 (1.3976/0.6046)	mem 34602MB
[2025-01-19 07:34:22 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][190/312]	eta 0:01:32 lr 0.002908	time 0.8263 (0.7552)	model_time 0.8259 (0.7483)	loss 2.9233 (3.4334)	grad_norm 1.0769 (1.4039/0.6076)	mem 34602MB
[2025-01-19 07:34:29 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][200/312]	eta 0:01:24 lr 0.002907	time 0.8027 (0.7548)	model_time 0.8023 (0.7482)	loss 3.3846 (3.4161)	grad_norm 1.3135 (1.3923/0.5970)	mem 34602MB
[2025-01-19 07:34:37 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][210/312]	eta 0:01:16 lr 0.002906	time 0.7202 (0.7534)	model_time 0.7200 (0.7471)	loss 3.9827 (3.4148)	grad_norm 1.7580 (1.3714/0.5945)	mem 34602MB
[2025-01-19 07:34:44 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][220/312]	eta 0:01:09 lr 0.002906	time 0.7211 (0.7526)	model_time 0.7207 (0.7466)	loss 3.5110 (3.4054)	grad_norm 0.8960 (1.3857/0.6112)	mem 34602MB
[2025-01-19 07:34:51 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][230/312]	eta 0:01:01 lr 0.002905	time 0.7169 (0.7513)	model_time 0.7164 (0.7455)	loss 3.3287 (3.4020)	grad_norm 0.9105 (1.3967/0.6101)	mem 34602MB
[2025-01-19 07:34:58 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][240/312]	eta 0:00:54 lr 0.002905	time 0.7165 (0.7503)	model_time 0.7160 (0.7448)	loss 3.6915 (3.3959)	grad_norm 3.3044 (1.4082/0.6183)	mem 34602MB
[2025-01-19 07:35:06 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][250/312]	eta 0:00:46 lr 0.002904	time 0.7163 (0.7503)	model_time 0.7159 (0.7450)	loss 3.2109 (3.4042)	grad_norm 2.8874 (1.4186/0.6199)	mem 34602MB
[2025-01-19 07:35:13 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][260/312]	eta 0:00:39 lr 0.002903	time 0.8031 (0.7505)	model_time 0.8029 (0.7453)	loss 4.1781 (3.3988)	grad_norm 1.2223 (1.4112/0.6163)	mem 34602MB
[2025-01-19 07:35:21 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][270/312]	eta 0:00:31 lr 0.002903	time 0.7156 (0.7507)	model_time 0.7151 (0.7458)	loss 3.6095 (3.4069)	grad_norm 0.9145 (1.4084/0.6094)	mem 34602MB
[2025-01-19 07:35:29 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][280/312]	eta 0:00:24 lr 0.002902	time 0.7173 (0.7506)	model_time 0.7171 (0.7458)	loss 3.6976 (3.4066)	grad_norm 0.6853 (1.3999/0.6022)	mem 34602MB
[2025-01-19 07:35:36 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][290/312]	eta 0:00:16 lr 0.002902	time 0.7113 (0.7509)	model_time 0.7111 (0.7462)	loss 4.3486 (3.4208)	grad_norm 1.4991 (1.3859/0.5983)	mem 34602MB
[2025-01-19 07:35:44 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][300/312]	eta 0:00:09 lr 0.002901	time 0.7130 (0.7506)	model_time 0.7129 (0.7461)	loss 4.1654 (3.4286)	grad_norm 2.1177 (1.3951/0.6005)	mem 34602MB
[2025-01-19 07:35:51 internimage_b_1k_224] (main.py 510): INFO Train: [105/300][310/312]	eta 0:00:01 lr 0.002900	time 0.7172 (0.7497)	model_time 0.7171 (0.7453)	loss 2.8186 (3.4177)	grad_norm 0.8718 (1.3871/0.5997)	mem 34602MB
[2025-01-19 07:35:52 internimage_b_1k_224] (main.py 519): INFO EPOCH 105 training takes 0:03:53
[2025-01-19 07:35:52 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_105.pth saving......
[2025-01-19 07:35:55 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_105.pth saved !!!
[2025-01-19 07:36:02 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.320 (7.320)	Loss 0.8878 (0.8878)	Acc@1 82.300 (82.300)	Acc@5 96.582 (96.582)	Mem 34602MB
[2025-01-19 07:36:05 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.920)	Loss 1.2154 (1.0556)	Acc@1 74.854 (78.764)	Acc@5 92.896 (94.664)	Mem 34602MB
[2025-01-19 07:36:05 internimage_b_1k_224] (main.py 575): INFO [Epoch:105] * Acc@1 78.677 Acc@5 94.730
[2025-01-19 07:36:05 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.7%
[2025-01-19 07:36:05 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 07:36:08 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 07:36:08 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 78.68%
[2025-01-19 07:36:16 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.177 (7.177)	Loss 0.7197 (0.7197)	Acc@1 81.812 (81.812)	Acc@5 96.631 (96.631)	Mem 34602MB
[2025-01-19 07:36:18 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.911)	Loss 1.1039 (0.8847)	Acc@1 73.145 (78.509)	Acc@5 92.041 (94.527)	Mem 34602MB
[2025-01-19 07:36:19 internimage_b_1k_224] (main.py 575): INFO [Epoch:105] * Acc@1 78.459 Acc@5 94.588
[2025-01-19 07:36:19 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.5%
[2025-01-19 07:36:19 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 07:36:23 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 07:36:23 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 78.46%
[2025-01-19 07:36:25 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][0/312]	eta 0:11:44 lr 0.002900	time 2.2578 (2.2578)	model_time 0.7586 (0.7586)	loss 2.9618 (2.9618)	grad_norm 0.8698 (0.8698/0.0000)	mem 34602MB
[2025-01-19 07:36:32 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][10/312]	eta 0:04:25 lr 0.002900	time 0.8125 (0.8802)	model_time 0.8124 (0.7436)	loss 3.0527 (3.4476)	grad_norm 0.5854 (1.2230/0.4353)	mem 34602MB
[2025-01-19 07:36:40 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][20/312]	eta 0:03:55 lr 0.002899	time 0.7174 (0.8070)	model_time 0.7170 (0.7353)	loss 3.2923 (3.4673)	grad_norm 1.2736 (1.2986/0.5074)	mem 34602MB
[2025-01-19 07:36:47 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][30/312]	eta 0:03:41 lr 0.002899	time 0.7301 (0.7871)	model_time 0.7300 (0.7384)	loss 2.9732 (3.4389)	grad_norm 0.8796 (1.3705/0.5983)	mem 34602MB
[2025-01-19 07:36:54 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][40/312]	eta 0:03:30 lr 0.002898	time 0.7165 (0.7724)	model_time 0.7163 (0.7355)	loss 4.0997 (3.5081)	grad_norm 1.1787 (1.3610/0.5993)	mem 34602MB
[2025-01-19 07:37:02 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][50/312]	eta 0:03:20 lr 0.002897	time 0.7435 (0.7660)	model_time 0.7431 (0.7363)	loss 3.5617 (3.4870)	grad_norm 1.3609 (1.3802/0.6039)	mem 34602MB
[2025-01-19 07:37:09 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][60/312]	eta 0:03:12 lr 0.002897	time 0.8392 (0.7629)	model_time 0.8388 (0.7380)	loss 3.4021 (3.4561)	grad_norm 1.0736 (1.3920/0.6071)	mem 34602MB
[2025-01-19 07:37:17 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][70/312]	eta 0:03:04 lr 0.002896	time 0.7160 (0.7612)	model_time 0.7159 (0.7397)	loss 2.6008 (3.3797)	grad_norm 1.0658 (1.3535/0.5893)	mem 34602MB
[2025-01-19 07:37:24 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][80/312]	eta 0:02:56 lr 0.002896	time 0.7966 (0.7608)	model_time 0.7965 (0.7420)	loss 3.7078 (3.3480)	grad_norm 2.5873 (1.3953/0.6027)	mem 34602MB
[2025-01-19 07:37:32 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][90/312]	eta 0:02:49 lr 0.002895	time 0.7171 (0.7625)	model_time 0.7167 (0.7457)	loss 3.5460 (3.3696)	grad_norm 0.8661 (1.4037/0.6075)	mem 34602MB
[2025-01-19 07:37:40 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][100/312]	eta 0:02:41 lr 0.002894	time 0.7134 (0.7613)	model_time 0.7128 (0.7461)	loss 2.4776 (3.3723)	grad_norm 0.9937 (1.4164/0.5993)	mem 34602MB
[2025-01-19 07:37:47 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][110/312]	eta 0:02:33 lr 0.002894	time 0.7150 (0.7612)	model_time 0.7148 (0.7473)	loss 3.9916 (3.3710)	grad_norm 3.1498 (1.4195/0.6063)	mem 34602MB
[2025-01-19 07:37:55 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][120/312]	eta 0:02:25 lr 0.002893	time 0.8011 (0.7589)	model_time 0.8006 (0.7462)	loss 3.5331 (3.3772)	grad_norm 1.3027 (1.4518/0.6308)	mem 34602MB
[2025-01-19 07:38:02 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][130/312]	eta 0:02:17 lr 0.002893	time 0.7092 (0.7570)	model_time 0.7090 (0.7452)	loss 3.2816 (3.3718)	grad_norm 0.8265 (1.4235/0.6165)	mem 34602MB
[2025-01-19 07:38:09 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][140/312]	eta 0:02:09 lr 0.002892	time 0.7247 (0.7554)	model_time 0.7245 (0.7444)	loss 2.9633 (3.3588)	grad_norm 1.7738 (1.4064/0.6037)	mem 34602MB
[2025-01-19 07:38:17 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][150/312]	eta 0:02:02 lr 0.002891	time 0.7248 (0.7539)	model_time 0.7243 (0.7436)	loss 3.0011 (3.3451)	grad_norm 2.9186 (1.4408/0.6394)	mem 34602MB
[2025-01-19 07:38:24 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][160/312]	eta 0:01:54 lr 0.002891	time 0.7178 (0.7522)	model_time 0.7173 (0.7425)	loss 3.1967 (3.3485)	grad_norm 0.6665 (1.4371/0.6289)	mem 34602MB
[2025-01-19 07:38:31 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][170/312]	eta 0:01:46 lr 0.002890	time 0.7525 (0.7511)	model_time 0.7520 (0.7419)	loss 4.1837 (3.3673)	grad_norm 0.8947 (1.4150/0.6185)	mem 34602MB
[2025-01-19 07:38:39 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][180/312]	eta 0:01:39 lr 0.002890	time 0.7993 (0.7507)	model_time 0.7989 (0.7420)	loss 3.6487 (3.3618)	grad_norm 2.4863 (1.4265/0.6188)	mem 34602MB
[2025-01-19 07:38:46 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][190/312]	eta 0:01:31 lr 0.002889	time 0.7174 (0.7510)	model_time 0.7172 (0.7428)	loss 3.8774 (3.3693)	grad_norm 3.6195 (1.4494/0.6348)	mem 34602MB
[2025-01-19 07:38:54 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][200/312]	eta 0:01:24 lr 0.002888	time 0.7976 (0.7516)	model_time 0.7972 (0.7438)	loss 2.9702 (3.3716)	grad_norm 0.8642 (1.4568/0.6478)	mem 34602MB
[2025-01-19 07:39:01 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][210/312]	eta 0:01:16 lr 0.002888	time 0.7338 (0.7517)	model_time 0.7337 (0.7442)	loss 4.2585 (3.3733)	grad_norm 1.7828 (1.4454/0.6431)	mem 34602MB
[2025-01-19 07:39:09 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][220/312]	eta 0:01:09 lr 0.002887	time 0.7167 (0.7523)	model_time 0.7166 (0.7452)	loss 2.9804 (3.3795)	grad_norm 1.7324 (1.4341/0.6350)	mem 34602MB
[2025-01-19 07:39:17 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][230/312]	eta 0:01:01 lr 0.002887	time 0.7208 (0.7526)	model_time 0.7203 (0.7457)	loss 3.9037 (3.3891)	grad_norm 2.4050 (1.4374/0.6322)	mem 34602MB
[2025-01-19 07:39:24 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][240/312]	eta 0:00:54 lr 0.002886	time 0.7945 (0.7520)	model_time 0.7943 (0.7454)	loss 3.4723 (3.3876)	grad_norm 1.5540 (1.4412/0.6225)	mem 34602MB
[2025-01-19 07:39:31 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][250/312]	eta 0:00:46 lr 0.002885	time 0.7419 (0.7515)	model_time 0.7418 (0.7452)	loss 3.8723 (3.3977)	grad_norm 1.8087 (1.4328/0.6161)	mem 34602MB
[2025-01-19 07:39:39 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][260/312]	eta 0:00:39 lr 0.002885	time 0.7187 (0.7508)	model_time 0.7182 (0.7447)	loss 2.8450 (3.4065)	grad_norm 1.6293 (1.4341/0.6173)	mem 34602MB
[2025-01-19 07:39:46 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][270/312]	eta 0:00:31 lr 0.002884	time 0.7222 (0.7502)	model_time 0.7221 (0.7443)	loss 3.0252 (3.4039)	grad_norm 1.5120 (1.4229/0.6107)	mem 34602MB
[2025-01-19 07:39:53 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][280/312]	eta 0:00:23 lr 0.002884	time 0.7172 (0.7492)	model_time 0.7167 (0.7435)	loss 3.5643 (3.4111)	grad_norm 2.2154 (1.4286/0.6074)	mem 34602MB
[2025-01-19 07:40:01 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][290/312]	eta 0:00:16 lr 0.002883	time 0.7281 (0.7486)	model_time 0.7279 (0.7431)	loss 4.4426 (3.4072)	grad_norm 2.9693 (1.4484/0.6191)	mem 34602MB
[2025-01-19 07:40:08 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][300/312]	eta 0:00:08 lr 0.002882	time 0.7960 (0.7483)	model_time 0.7959 (0.7430)	loss 2.7624 (3.3984)	grad_norm 1.7109 (1.4582/0.6160)	mem 34602MB
[2025-01-19 07:40:15 internimage_b_1k_224] (main.py 510): INFO Train: [106/300][310/312]	eta 0:00:01 lr 0.002882	time 0.7122 (0.7482)	model_time 0.7121 (0.7430)	loss 3.2342 (3.4025)	grad_norm 0.7843 (1.4633/0.6220)	mem 34602MB
[2025-01-19 07:40:16 internimage_b_1k_224] (main.py 519): INFO EPOCH 106 training takes 0:03:53
[2025-01-19 07:40:16 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_106.pth saving......
[2025-01-19 07:40:19 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_106.pth saved !!!
[2025-01-19 07:40:27 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.163 (7.163)	Loss 0.8149 (0.8149)	Acc@1 82.227 (82.227)	Acc@5 96.558 (96.558)	Mem 34602MB
[2025-01-19 07:40:29 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.897)	Loss 1.1329 (0.9732)	Acc@1 74.878 (78.964)	Acc@5 92.920 (94.767)	Mem 34602MB
[2025-01-19 07:40:30 internimage_b_1k_224] (main.py 575): INFO [Epoch:106] * Acc@1 78.865 Acc@5 94.818
[2025-01-19 07:40:30 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.9%
[2025-01-19 07:40:30 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 07:40:33 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 07:40:33 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 78.86%
[2025-01-19 07:40:40 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.175 (7.175)	Loss 0.7151 (0.7151)	Acc@1 81.958 (81.958)	Acc@5 96.704 (96.704)	Mem 34602MB
[2025-01-19 07:40:43 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.904)	Loss 1.0976 (0.8799)	Acc@1 73.267 (78.609)	Acc@5 92.065 (94.580)	Mem 34602MB
[2025-01-19 07:40:43 internimage_b_1k_224] (main.py 575): INFO [Epoch:106] * Acc@1 78.549 Acc@5 94.642
[2025-01-19 07:40:43 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.5%
[2025-01-19 07:40:43 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 07:40:48 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 07:40:48 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 78.55%
[2025-01-19 07:40:50 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][0/312]	eta 0:12:12 lr 0.002882	time 2.3479 (2.3479)	model_time 0.7693 (0.7693)	loss 3.5958 (3.5958)	grad_norm 0.8114 (0.8114/0.0000)	mem 34602MB
[2025-01-19 07:40:58 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][10/312]	eta 0:04:32 lr 0.002881	time 0.8297 (0.9011)	model_time 0.8293 (0.7572)	loss 2.7133 (3.4176)	grad_norm 1.5266 (1.0612/0.2064)	mem 34602MB
[2025-01-19 07:41:05 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][20/312]	eta 0:04:02 lr 0.002881	time 0.7186 (0.8303)	model_time 0.7182 (0.7548)	loss 2.8647 (3.3342)	grad_norm 0.9112 (1.0806/0.2419)	mem 34602MB
[2025-01-19 07:41:13 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][30/312]	eta 0:03:47 lr 0.002880	time 0.8153 (0.8079)	model_time 0.8149 (0.7566)	loss 2.2502 (3.2004)	grad_norm 0.7962 (1.3127/0.6047)	mem 34602MB
[2025-01-19 07:41:20 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][40/312]	eta 0:03:35 lr 0.002879	time 0.7204 (0.7934)	model_time 0.7197 (0.7546)	loss 3.0592 (3.2317)	grad_norm 2.5361 (1.3604/0.5941)	mem 34602MB
[2025-01-19 07:41:28 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][50/312]	eta 0:03:24 lr 0.002879	time 0.7174 (0.7820)	model_time 0.7173 (0.7507)	loss 3.3216 (3.2578)	grad_norm 0.9243 (1.3160/0.5649)	mem 34602MB
[2025-01-19 07:41:35 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][60/312]	eta 0:03:15 lr 0.002878	time 0.7332 (0.7759)	model_time 0.7330 (0.7496)	loss 3.5897 (3.2718)	grad_norm 1.7188 (1.3063/0.5420)	mem 34602MB
[2025-01-19 07:41:42 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][70/312]	eta 0:03:06 lr 0.002878	time 0.7436 (0.7699)	model_time 0.7431 (0.7473)	loss 3.9889 (3.2749)	grad_norm 1.8988 (1.3487/0.6200)	mem 34602MB
[2025-01-19 07:41:50 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][80/312]	eta 0:02:57 lr 0.002877	time 0.7287 (0.7656)	model_time 0.7285 (0.7458)	loss 4.3022 (3.2934)	grad_norm 1.0985 (1.3352/0.5964)	mem 34602MB
[2025-01-19 07:41:57 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][90/312]	eta 0:02:49 lr 0.002876	time 0.7358 (0.7615)	model_time 0.7356 (0.7438)	loss 3.7703 (3.3443)	grad_norm 0.7504 (1.3628/0.6132)	mem 34602MB
[2025-01-19 07:42:04 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][100/312]	eta 0:02:40 lr 0.002876	time 0.7112 (0.7589)	model_time 0.7110 (0.7429)	loss 3.6594 (3.3745)	grad_norm 1.1977 (1.3312/0.5972)	mem 34602MB
[2025-01-19 07:42:12 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][110/312]	eta 0:02:33 lr 0.002875	time 0.7172 (0.7582)	model_time 0.7170 (0.7436)	loss 3.8020 (3.3562)	grad_norm 1.0319 (1.3422/0.5911)	mem 34602MB
[2025-01-19 07:42:19 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][120/312]	eta 0:02:25 lr 0.002875	time 0.7155 (0.7578)	model_time 0.7154 (0.7444)	loss 3.6090 (3.3807)	grad_norm 1.8743 (1.3562/0.5867)	mem 34602MB
[2025-01-19 07:42:27 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][130/312]	eta 0:02:17 lr 0.002874	time 0.7215 (0.7576)	model_time 0.7213 (0.7452)	loss 3.7259 (3.3886)	grad_norm 1.6506 (1.3628/0.5772)	mem 34602MB
[2025-01-19 07:42:35 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][140/312]	eta 0:02:10 lr 0.002873	time 0.8092 (0.7583)	model_time 0.8090 (0.7468)	loss 3.5126 (3.3919)	grad_norm 2.2514 (1.3811/0.5788)	mem 34602MB
[2025-01-19 07:42:42 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][150/312]	eta 0:02:02 lr 0.002873	time 0.8166 (0.7584)	model_time 0.8164 (0.7476)	loss 3.6781 (3.3930)	grad_norm 1.1875 (1.3724/0.5687)	mem 34602MB
[2025-01-19 07:42:50 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][160/312]	eta 0:01:55 lr 0.002872	time 0.7258 (0.7576)	model_time 0.7256 (0.7475)	loss 3.8531 (3.3990)	grad_norm 1.3513 (1.3649/0.5583)	mem 34602MB
[2025-01-19 07:42:57 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][170/312]	eta 0:01:47 lr 0.002872	time 0.7150 (0.7562)	model_time 0.7149 (0.7466)	loss 3.3546 (3.3940)	grad_norm 0.9305 (1.3568/0.5563)	mem 34602MB
[2025-01-19 07:43:04 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][180/312]	eta 0:01:39 lr 0.002871	time 0.7170 (0.7556)	model_time 0.7169 (0.7465)	loss 3.4071 (3.4066)	grad_norm 0.5950 (1.3580/0.5598)	mem 34602MB
[2025-01-19 07:43:12 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][190/312]	eta 0:01:32 lr 0.002870	time 0.7267 (0.7545)	model_time 0.7262 (0.7459)	loss 3.4278 (3.4046)	grad_norm 1.5153 (1.3447/0.5506)	mem 34602MB
[2025-01-19 07:43:19 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][200/312]	eta 0:01:24 lr 0.002870	time 0.7511 (0.7534)	model_time 0.7507 (0.7452)	loss 3.2152 (3.4095)	grad_norm 0.9847 (1.3440/0.5463)	mem 34602MB
[2025-01-19 07:43:26 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][210/312]	eta 0:01:16 lr 0.002869	time 0.7578 (0.7523)	model_time 0.7576 (0.7445)	loss 3.2656 (3.4142)	grad_norm 0.9948 (1.3548/0.5729)	mem 34602MB
[2025-01-19 07:43:34 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][220/312]	eta 0:01:09 lr 0.002869	time 0.7189 (0.7516)	model_time 0.7185 (0.7441)	loss 2.2460 (3.4151)	grad_norm 1.4259 (1.3783/0.5798)	mem 34602MB
[2025-01-19 07:43:41 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][230/312]	eta 0:01:01 lr 0.002868	time 0.7081 (0.7515)	model_time 0.7079 (0.7443)	loss 3.3400 (3.4277)	grad_norm 1.0798 (1.3768/0.5880)	mem 34602MB
[2025-01-19 07:43:49 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][240/312]	eta 0:00:54 lr 0.002867	time 0.7178 (0.7512)	model_time 0.7172 (0.7443)	loss 3.7718 (3.4254)	grad_norm 1.1203 (1.3708/0.5814)	mem 34602MB
[2025-01-19 07:43:56 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][250/312]	eta 0:00:46 lr 0.002867	time 0.7086 (0.7515)	model_time 0.7085 (0.7448)	loss 2.6240 (3.4254)	grad_norm 1.3451 (1.3584/0.5744)	mem 34602MB
[2025-01-19 07:44:04 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][260/312]	eta 0:00:39 lr 0.002866	time 0.8177 (0.7515)	model_time 0.8175 (0.7451)	loss 2.4403 (3.4064)	grad_norm 1.2294 (1.3484/0.5688)	mem 34602MB
[2025-01-19 07:44:11 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][270/312]	eta 0:00:31 lr 0.002866	time 0.8044 (0.7513)	model_time 0.8043 (0.7451)	loss 2.8314 (3.4023)	grad_norm 2.3392 (1.3540/0.5698)	mem 34602MB
[2025-01-19 07:44:19 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][280/312]	eta 0:00:24 lr 0.002865	time 0.7295 (0.7512)	model_time 0.7293 (0.7452)	loss 3.3503 (3.4041)	grad_norm 0.8401 (1.3600/0.5704)	mem 34602MB
[2025-01-19 07:44:26 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][290/312]	eta 0:00:16 lr 0.002864	time 0.7165 (0.7502)	model_time 0.7162 (0.7444)	loss 3.4594 (3.4045)	grad_norm 1.0730 (1.3479/0.5658)	mem 34602MB
[2025-01-19 07:44:33 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][300/312]	eta 0:00:09 lr 0.002864	time 0.7118 (0.7502)	model_time 0.7117 (0.7446)	loss 2.1518 (3.3989)	grad_norm 1.1118 (1.3485/0.5586)	mem 34602MB
[2025-01-19 07:44:41 internimage_b_1k_224] (main.py 510): INFO Train: [107/300][310/312]	eta 0:00:01 lr 0.002863	time 0.7243 (0.7495)	model_time 0.7242 (0.7441)	loss 3.4364 (3.3953)	grad_norm 1.4095 (1.3676/0.5674)	mem 34602MB
[2025-01-19 07:44:41 internimage_b_1k_224] (main.py 519): INFO EPOCH 107 training takes 0:03:53
[2025-01-19 07:44:41 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_107.pth saving......
[2025-01-19 07:44:44 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_107.pth saved !!!
[2025-01-19 07:44:52 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.400 (7.400)	Loss 0.8560 (0.8560)	Acc@1 81.958 (81.958)	Acc@5 96.680 (96.680)	Mem 34602MB
[2025-01-19 07:44:55 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.939)	Loss 1.1853 (1.0113)	Acc@1 74.146 (78.613)	Acc@5 92.529 (94.689)	Mem 34602MB
[2025-01-19 07:44:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:107] * Acc@1 78.471 Acc@5 94.700
[2025-01-19 07:44:55 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.5%
[2025-01-19 07:44:55 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 78.86%
[2025-01-19 07:45:04 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.940 (8.940)	Loss 0.7109 (0.7109)	Acc@1 82.080 (82.080)	Acc@5 96.704 (96.704)	Mem 34602MB
[2025-01-19 07:45:09 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.226)	Loss 1.0911 (0.8753)	Acc@1 73.413 (78.722)	Acc@5 92.261 (94.649)	Mem 34602MB
[2025-01-19 07:45:09 internimage_b_1k_224] (main.py 575): INFO [Epoch:107] * Acc@1 78.655 Acc@5 94.716
[2025-01-19 07:45:09 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.7%
[2025-01-19 07:45:09 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 07:45:13 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 07:45:13 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 78.65%
[2025-01-19 07:45:15 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][0/312]	eta 0:12:06 lr 0.002863	time 2.3295 (2.3295)	model_time 0.7426 (0.7426)	loss 3.6929 (3.6929)	grad_norm 1.7525 (1.7525/0.0000)	mem 34602MB
[2025-01-19 07:45:22 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][10/312]	eta 0:04:25 lr 0.002862	time 0.7441 (0.8804)	model_time 0.7437 (0.7358)	loss 3.6426 (3.2887)	grad_norm 0.7729 (1.3019/0.4304)	mem 34602MB
[2025-01-19 07:45:30 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][20/312]	eta 0:03:55 lr 0.002862	time 0.7256 (0.8056)	model_time 0.7255 (0.7297)	loss 3.1953 (3.3068)	grad_norm 0.8838 (1.2281/0.4467)	mem 34602MB
[2025-01-19 07:45:37 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][30/312]	eta 0:03:40 lr 0.002861	time 0.7122 (0.7803)	model_time 0.7120 (0.7288)	loss 3.5516 (3.2023)	grad_norm 1.3696 (1.2525/0.4277)	mem 34602MB
[2025-01-19 07:45:44 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][40/312]	eta 0:03:29 lr 0.002861	time 0.7239 (0.7718)	model_time 0.7237 (0.7327)	loss 3.4951 (3.2351)	grad_norm 1.1221 (1.3066/0.4648)	mem 34602MB
[2025-01-19 07:45:52 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][50/312]	eta 0:03:20 lr 0.002860	time 0.7173 (0.7655)	model_time 0.7171 (0.7340)	loss 3.5095 (3.3405)	grad_norm 1.3093 (1.3793/0.4930)	mem 34602MB
[2025-01-19 07:45:59 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][60/312]	eta 0:03:12 lr 0.002859	time 0.7247 (0.7649)	model_time 0.7240 (0.7385)	loss 3.3910 (3.3112)	grad_norm 1.1180 (1.3984/0.5531)	mem 34602MB
[2025-01-19 07:46:07 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][70/312]	eta 0:03:04 lr 0.002859	time 0.7045 (0.7634)	model_time 0.7043 (0.7407)	loss 2.7047 (3.3007)	grad_norm 2.4991 (1.3870/0.5479)	mem 34602MB
[2025-01-19 07:46:14 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][80/312]	eta 0:02:56 lr 0.002858	time 0.8100 (0.7627)	model_time 0.8098 (0.7428)	loss 3.5151 (3.3041)	grad_norm 1.4873 (1.3836/0.5565)	mem 34602MB
[2025-01-19 07:46:22 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][90/312]	eta 0:02:49 lr 0.002858	time 0.7208 (0.7617)	model_time 0.7203 (0.7439)	loss 3.7534 (3.2867)	grad_norm 1.8484 (1.3718/0.5384)	mem 34602MB
[2025-01-19 07:46:29 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][100/312]	eta 0:02:41 lr 0.002857	time 0.8288 (0.7603)	model_time 0.8286 (0.7442)	loss 4.0270 (3.2815)	grad_norm 1.1239 (1.4214/0.6062)	mem 34602MB
[2025-01-19 07:46:37 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][110/312]	eta 0:02:33 lr 0.002856	time 0.7144 (0.7596)	model_time 0.7143 (0.7449)	loss 3.6483 (3.3231)	grad_norm 0.7751 (1.4590/0.6572)	mem 34602MB
[2025-01-19 07:46:44 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][120/312]	eta 0:02:25 lr 0.002856	time 0.7206 (0.7578)	model_time 0.7204 (0.7443)	loss 3.6262 (3.3276)	grad_norm 0.8668 (1.4228/0.6440)	mem 34602MB
[2025-01-19 07:46:52 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][130/312]	eta 0:02:17 lr 0.002855	time 0.7160 (0.7557)	model_time 0.7158 (0.7432)	loss 3.7174 (3.3351)	grad_norm 0.9320 (1.3930/0.6307)	mem 34602MB
[2025-01-19 07:46:59 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][140/312]	eta 0:02:09 lr 0.002855	time 0.7358 (0.7540)	model_time 0.7356 (0.7424)	loss 3.8071 (3.3378)	grad_norm 2.2877 (1.3931/0.6301)	mem 34602MB
[2025-01-19 07:47:06 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][150/312]	eta 0:02:01 lr 0.002854	time 0.7174 (0.7524)	model_time 0.7172 (0.7416)	loss 3.8234 (3.3415)	grad_norm 1.1018 (1.3951/0.6168)	mem 34602MB
[2025-01-19 07:47:14 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][160/312]	eta 0:01:54 lr 0.002853	time 0.7237 (0.7515)	model_time 0.7235 (0.7413)	loss 3.2912 (3.3499)	grad_norm 1.0043 (1.3854/0.6078)	mem 34602MB
[2025-01-19 07:47:21 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][170/312]	eta 0:01:46 lr 0.002853	time 0.7134 (0.7513)	model_time 0.7132 (0.7417)	loss 3.1465 (3.3673)	grad_norm 0.8879 (1.3752/0.6032)	mem 34602MB
[2025-01-19 07:47:29 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][180/312]	eta 0:01:39 lr 0.002852	time 0.7178 (0.7508)	model_time 0.7176 (0.7416)	loss 3.3105 (3.3752)	grad_norm 1.0699 (1.3603/0.5992)	mem 34602MB
[2025-01-19 07:47:36 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][190/312]	eta 0:01:31 lr 0.002852	time 0.7164 (0.7514)	model_time 0.7163 (0.7427)	loss 3.6076 (3.3750)	grad_norm 3.1597 (1.3678/0.6054)	mem 34602MB
[2025-01-19 07:47:44 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][200/312]	eta 0:01:24 lr 0.002851	time 0.8017 (0.7514)	model_time 0.8016 (0.7431)	loss 3.7163 (3.3841)	grad_norm 1.0698 (1.3791/0.5974)	mem 34602MB
[2025-01-19 07:47:51 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][210/312]	eta 0:01:16 lr 0.002850	time 0.7191 (0.7518)	model_time 0.7189 (0.7439)	loss 2.0491 (3.3735)	grad_norm 1.2185 (1.3796/0.5969)	mem 34602MB
[2025-01-19 07:47:59 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][220/312]	eta 0:01:09 lr 0.002850	time 0.7133 (0.7508)	model_time 0.7131 (0.7432)	loss 3.1350 (3.3613)	grad_norm 1.3355 (1.3714/0.5952)	mem 34602MB
[2025-01-19 07:48:06 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][230/312]	eta 0:01:01 lr 0.002849	time 0.7642 (0.7507)	model_time 0.7640 (0.7435)	loss 3.9860 (3.3609)	grad_norm 1.0998 (1.3819/0.5926)	mem 34602MB
[2025-01-19 07:48:13 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][240/312]	eta 0:00:54 lr 0.002849	time 0.7162 (0.7501)	model_time 0.7161 (0.7432)	loss 2.8098 (3.3636)	grad_norm 1.2091 (1.3740/0.5848)	mem 34602MB
[2025-01-19 07:48:21 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][250/312]	eta 0:00:46 lr 0.002848	time 0.7242 (0.7498)	model_time 0.7239 (0.7431)	loss 3.4376 (3.3516)	grad_norm 1.2803 (1.3962/0.5874)	mem 34602MB
[2025-01-19 07:48:28 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][260/312]	eta 0:00:38 lr 0.002847	time 0.7156 (0.7487)	model_time 0.7154 (0.7422)	loss 2.3924 (3.3353)	grad_norm 1.4005 (1.3928/0.5897)	mem 34602MB
[2025-01-19 07:48:35 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][270/312]	eta 0:00:31 lr 0.002847	time 0.7272 (0.7481)	model_time 0.7267 (0.7419)	loss 2.7710 (3.3428)	grad_norm 1.7955 (1.3943/0.5827)	mem 34602MB
[2025-01-19 07:48:43 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][280/312]	eta 0:00:23 lr 0.002846	time 0.7251 (0.7479)	model_time 0.7249 (0.7419)	loss 4.0832 (3.3473)	grad_norm 1.4409 (1.3870/0.5795)	mem 34602MB
[2025-01-19 07:48:50 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][290/312]	eta 0:00:16 lr 0.002846	time 0.7496 (0.7480)	model_time 0.7493 (0.7422)	loss 3.5612 (3.3430)	grad_norm 1.3220 (1.3851/0.5720)	mem 34602MB
[2025-01-19 07:48:58 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][300/312]	eta 0:00:08 lr 0.002845	time 0.7108 (0.7475)	model_time 0.7107 (0.7419)	loss 2.5935 (3.3411)	grad_norm 2.5324 (1.3836/0.5746)	mem 34602MB
[2025-01-19 07:49:05 internimage_b_1k_224] (main.py 510): INFO Train: [108/300][310/312]	eta 0:00:01 lr 0.002844	time 0.7148 (0.7483)	model_time 0.7147 (0.7429)	loss 3.3660 (3.3496)	grad_norm 0.9888 (1.3915/0.5877)	mem 34602MB
[2025-01-19 07:49:06 internimage_b_1k_224] (main.py 519): INFO EPOCH 108 training takes 0:03:53
[2025-01-19 07:49:06 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_108.pth saving......
[2025-01-19 07:49:09 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_108.pth saved !!!
[2025-01-19 07:49:17 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.435 (7.435)	Loss 0.8415 (0.8415)	Acc@1 82.056 (82.056)	Acc@5 96.680 (96.680)	Mem 34602MB
[2025-01-19 07:49:20 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.947)	Loss 1.1598 (0.9862)	Acc@1 73.975 (78.596)	Acc@5 92.896 (94.742)	Mem 34602MB
[2025-01-19 07:49:20 internimage_b_1k_224] (main.py 575): INFO [Epoch:108] * Acc@1 78.561 Acc@5 94.806
[2025-01-19 07:49:20 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.6%
[2025-01-19 07:49:20 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 78.86%
[2025-01-19 07:49:29 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.144 (9.144)	Loss 0.7068 (0.7068)	Acc@1 82.202 (82.202)	Acc@5 96.753 (96.753)	Mem 34602MB
[2025-01-19 07:49:33 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.225)	Loss 1.0848 (0.8707)	Acc@1 73.657 (78.844)	Acc@5 92.358 (94.676)	Mem 34602MB
[2025-01-19 07:49:34 internimage_b_1k_224] (main.py 575): INFO [Epoch:108] * Acc@1 78.775 Acc@5 94.740
[2025-01-19 07:49:34 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.8%
[2025-01-19 07:49:34 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 07:49:37 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 07:49:37 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 78.77%
[2025-01-19 07:49:40 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][0/312]	eta 0:11:47 lr 0.002844	time 2.2691 (2.2691)	model_time 0.7499 (0.7499)	loss 2.9056 (2.9056)	grad_norm 1.4900 (1.4900/0.0000)	mem 34602MB
[2025-01-19 07:49:47 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][10/312]	eta 0:04:29 lr 0.002844	time 0.8039 (0.8926)	model_time 0.8037 (0.7542)	loss 2.8847 (3.2281)	grad_norm 2.7531 (2.1348/0.6871)	mem 34602MB
[2025-01-19 07:49:55 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][20/312]	eta 0:04:03 lr 0.002843	time 0.7451 (0.8333)	model_time 0.7449 (0.7606)	loss 2.7927 (3.2489)	grad_norm 1.0191 (1.7481/0.7807)	mem 34602MB
[2025-01-19 07:50:02 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][30/312]	eta 0:03:46 lr 0.002842	time 0.7131 (0.8017)	model_time 0.7129 (0.7524)	loss 2.8344 (3.3004)	grad_norm 1.1438 (1.5061/0.7525)	mem 34602MB
[2025-01-19 07:50:10 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][40/312]	eta 0:03:34 lr 0.002842	time 0.7556 (0.7887)	model_time 0.7551 (0.7513)	loss 3.4804 (3.3058)	grad_norm 0.9413 (1.3991/0.6976)	mem 34602MB
[2025-01-19 07:50:17 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][50/312]	eta 0:03:24 lr 0.002841	time 0.7292 (0.7790)	model_time 0.7290 (0.7488)	loss 4.1653 (3.3107)	grad_norm 1.0716 (1.3646/0.6422)	mem 34602MB
[2025-01-19 07:50:24 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][60/312]	eta 0:03:14 lr 0.002841	time 0.7396 (0.7724)	model_time 0.7391 (0.7471)	loss 3.1133 (3.3283)	grad_norm 1.2779 (1.3534/0.6209)	mem 34602MB
[2025-01-19 07:50:32 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][70/312]	eta 0:03:05 lr 0.002840	time 0.7226 (0.7660)	model_time 0.7224 (0.7442)	loss 3.1977 (3.3411)	grad_norm 0.9028 (1.2969/0.5955)	mem 34602MB
[2025-01-19 07:50:39 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][80/312]	eta 0:02:56 lr 0.002839	time 0.7272 (0.7607)	model_time 0.7269 (0.7416)	loss 3.7343 (3.3143)	grad_norm 2.9655 (1.3143/0.6117)	mem 34602MB
[2025-01-19 07:50:46 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][90/312]	eta 0:02:48 lr 0.002839	time 0.7980 (0.7598)	model_time 0.7975 (0.7427)	loss 4.1581 (3.3354)	grad_norm 0.7870 (1.3572/0.6529)	mem 34602MB
[2025-01-19 07:50:54 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][100/312]	eta 0:02:40 lr 0.002838	time 0.7968 (0.7577)	model_time 0.7963 (0.7423)	loss 3.2292 (3.3084)	grad_norm 1.7354 (1.4246/0.7198)	mem 34602MB
[2025-01-19 07:51:01 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][110/312]	eta 0:02:33 lr 0.002838	time 0.8257 (0.7576)	model_time 0.8255 (0.7435)	loss 3.7771 (3.3175)	grad_norm 1.2055 (1.4039/0.6971)	mem 34602MB
[2025-01-19 07:51:09 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][120/312]	eta 0:02:25 lr 0.002837	time 0.8056 (0.7575)	model_time 0.8055 (0.7446)	loss 2.8749 (3.3110)	grad_norm 1.3348 (1.3704/0.6812)	mem 34602MB
[2025-01-19 07:51:16 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][130/312]	eta 0:02:17 lr 0.002836	time 0.7964 (0.7569)	model_time 0.7963 (0.7450)	loss 3.4746 (3.3297)	grad_norm 2.1088 (1.3729/0.6610)	mem 34602MB
[2025-01-19 07:51:24 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][140/312]	eta 0:02:10 lr 0.002836	time 0.7198 (0.7574)	model_time 0.7196 (0.7463)	loss 2.8730 (3.3159)	grad_norm 0.8129 (1.3550/0.6494)	mem 34602MB
[2025-01-19 07:51:31 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][150/312]	eta 0:02:02 lr 0.002835	time 0.7469 (0.7557)	model_time 0.7465 (0.7453)	loss 3.9922 (3.3298)	grad_norm 0.7566 (1.3321/0.6357)	mem 34602MB
[2025-01-19 07:51:39 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][160/312]	eta 0:01:54 lr 0.002835	time 0.7435 (0.7555)	model_time 0.7433 (0.7458)	loss 2.1332 (3.3240)	grad_norm 1.3609 (1.3188/0.6217)	mem 34602MB
[2025-01-19 07:51:46 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][170/312]	eta 0:01:47 lr 0.002834	time 0.7178 (0.7543)	model_time 0.7173 (0.7451)	loss 3.5332 (3.3112)	grad_norm 2.3132 (1.3287/0.6190)	mem 34602MB
[2025-01-19 07:51:54 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][180/312]	eta 0:01:39 lr 0.002833	time 0.7178 (0.7538)	model_time 0.7176 (0.7451)	loss 3.3942 (3.3326)	grad_norm 1.0228 (1.3284/0.6192)	mem 34602MB
[2025-01-19 07:52:01 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][190/312]	eta 0:01:31 lr 0.002833	time 0.7062 (0.7523)	model_time 0.7058 (0.7440)	loss 2.1148 (3.3151)	grad_norm 2.9520 (1.3592/0.6419)	mem 34602MB
[2025-01-19 07:52:08 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][200/312]	eta 0:01:24 lr 0.002832	time 0.7178 (0.7511)	model_time 0.7176 (0.7432)	loss 4.0638 (3.3124)	grad_norm 0.9024 (1.3615/0.6379)	mem 34602MB
[2025-01-19 07:52:16 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][210/312]	eta 0:01:16 lr 0.002832	time 0.7514 (0.7507)	model_time 0.7512 (0.7431)	loss 3.4482 (3.3118)	grad_norm 1.1124 (1.3491/0.6281)	mem 34602MB
[2025-01-19 07:52:23 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][220/312]	eta 0:01:09 lr 0.002831	time 0.8532 (0.7511)	model_time 0.8530 (0.7439)	loss 3.3689 (3.2920)	grad_norm 0.7388 (1.3484/0.6261)	mem 34602MB
[2025-01-19 07:52:31 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][230/312]	eta 0:01:01 lr 0.002830	time 0.8315 (0.7515)	model_time 0.8313 (0.7446)	loss 3.3805 (3.3023)	grad_norm 0.6961 (1.3412/0.6207)	mem 34602MB
[2025-01-19 07:52:38 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][240/312]	eta 0:00:54 lr 0.002830	time 0.8068 (0.7514)	model_time 0.8066 (0.7447)	loss 3.5796 (3.3017)	grad_norm 0.9898 (1.3294/0.6124)	mem 34602MB
[2025-01-19 07:52:46 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][250/312]	eta 0:00:46 lr 0.002829	time 0.7297 (0.7512)	model_time 0.7295 (0.7448)	loss 3.2051 (3.3016)	grad_norm 0.7149 (1.3125/0.6069)	mem 34602MB
[2025-01-19 07:52:54 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][260/312]	eta 0:00:39 lr 0.002828	time 0.7093 (0.7520)	model_time 0.7091 (0.7459)	loss 4.1947 (3.3050)	grad_norm 0.8635 (1.3261/0.6081)	mem 34602MB
[2025-01-19 07:53:01 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][270/312]	eta 0:00:31 lr 0.002828	time 0.7191 (0.7516)	model_time 0.7189 (0.7456)	loss 3.5039 (3.3116)	grad_norm 2.6442 (1.3528/0.6431)	mem 34602MB
[2025-01-19 07:53:09 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][280/312]	eta 0:00:24 lr 0.002827	time 0.7181 (0.7523)	model_time 0.7179 (0.7465)	loss 3.6666 (3.3156)	grad_norm 1.4394 (1.3562/0.6402)	mem 34602MB
[2025-01-19 07:53:16 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][290/312]	eta 0:00:16 lr 0.002827	time 0.7226 (0.7518)	model_time 0.7222 (0.7462)	loss 3.2878 (3.3139)	grad_norm 1.8150 (1.3566/0.6326)	mem 34602MB
[2025-01-19 07:53:23 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][300/312]	eta 0:00:09 lr 0.002826	time 0.7139 (0.7513)	model_time 0.7138 (0.7459)	loss 2.5442 (3.3201)	grad_norm 4.5983 (1.3762/0.6677)	mem 34602MB
[2025-01-19 07:53:31 internimage_b_1k_224] (main.py 510): INFO Train: [109/300][310/312]	eta 0:00:01 lr 0.002825	time 0.7176 (0.7502)	model_time 0.7158 (0.7449)	loss 3.8515 (3.3278)	grad_norm 0.7022 (1.3512/0.6577)	mem 34602MB
[2025-01-19 07:53:31 internimage_b_1k_224] (main.py 519): INFO EPOCH 109 training takes 0:03:54
[2025-01-19 07:53:31 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_109.pth saving......
[2025-01-19 07:53:34 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_109.pth saved !!!
[2025-01-19 07:53:42 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.311 (7.311)	Loss 0.8506 (0.8506)	Acc@1 81.348 (81.348)	Acc@5 96.655 (96.655)	Mem 34602MB
[2025-01-19 07:53:45 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.188 (0.933)	Loss 1.1671 (0.9805)	Acc@1 74.194 (78.915)	Acc@5 92.554 (94.678)	Mem 34602MB
[2025-01-19 07:53:45 internimage_b_1k_224] (main.py 575): INFO [Epoch:109] * Acc@1 78.777 Acc@5 94.692
[2025-01-19 07:53:45 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.8%
[2025-01-19 07:53:45 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 78.86%
[2025-01-19 07:53:54 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.165 (9.165)	Loss 0.7029 (0.7029)	Acc@1 82.227 (82.227)	Acc@5 96.802 (96.802)	Mem 34602MB
[2025-01-19 07:53:59 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.233)	Loss 1.0791 (0.8664)	Acc@1 73.755 (78.944)	Acc@5 92.407 (94.709)	Mem 34602MB
[2025-01-19 07:53:59 internimage_b_1k_224] (main.py 575): INFO [Epoch:109] * Acc@1 78.871 Acc@5 94.776
[2025-01-19 07:53:59 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.9%
[2025-01-19 07:53:59 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 07:54:03 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 07:54:03 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 78.87%
[2025-01-19 07:54:05 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][0/312]	eta 0:11:00 lr 0.002825	time 2.1163 (2.1163)	model_time 0.7425 (0.7425)	loss 3.6250 (3.6250)	grad_norm 1.4804 (1.4804/0.0000)	mem 34602MB
[2025-01-19 07:54:12 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][10/312]	eta 0:04:17 lr 0.002825	time 0.7254 (0.8538)	model_time 0.7253 (0.7285)	loss 3.1749 (3.4976)	grad_norm 0.6787 (1.1195/0.4634)	mem 34602MB
[2025-01-19 07:54:20 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][20/312]	eta 0:03:54 lr 0.002824	time 0.8138 (0.8018)	model_time 0.8136 (0.7360)	loss 2.6009 (3.2967)	grad_norm 1.4665 (1.0488/0.4303)	mem 34602MB
[2025-01-19 07:54:27 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][30/312]	eta 0:03:41 lr 0.002824	time 0.7241 (0.7846)	model_time 0.7237 (0.7400)	loss 3.5649 (3.2714)	grad_norm 2.1257 (1.1394/0.4504)	mem 34602MB
[2025-01-19 07:54:35 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][40/312]	eta 0:03:31 lr 0.002823	time 0.7196 (0.7788)	model_time 0.7191 (0.7450)	loss 3.4713 (3.3294)	grad_norm 1.0483 (1.1815/0.4412)	mem 34602MB
[2025-01-19 07:54:42 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][50/312]	eta 0:03:23 lr 0.002822	time 0.7256 (0.7756)	model_time 0.7254 (0.7483)	loss 3.5483 (3.3750)	grad_norm 0.7357 (1.2074/0.4533)	mem 34602MB
[2025-01-19 07:54:50 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][60/312]	eta 0:03:14 lr 0.002822	time 0.8014 (0.7735)	model_time 0.8010 (0.7506)	loss 3.3852 (3.3874)	grad_norm 1.8418 (1.2617/0.4633)	mem 34602MB
[2025-01-19 07:54:58 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][70/312]	eta 0:03:06 lr 0.002821	time 0.7409 (0.7714)	model_time 0.7407 (0.7517)	loss 2.7114 (3.3845)	grad_norm 3.7424 (1.3484/0.5977)	mem 34602MB
[2025-01-19 07:55:05 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][80/312]	eta 0:02:57 lr 0.002820	time 0.7261 (0.7665)	model_time 0.7256 (0.7492)	loss 3.4183 (3.3958)	grad_norm 1.1331 (1.3795/0.6082)	mem 34602MB
[2025-01-19 07:55:12 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][90/312]	eta 0:02:49 lr 0.002820	time 0.7164 (0.7647)	model_time 0.7162 (0.7493)	loss 3.2620 (3.3994)	grad_norm 0.9782 (1.3402/0.5878)	mem 34602MB
[2025-01-19 07:55:20 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][100/312]	eta 0:02:41 lr 0.002819	time 0.7234 (0.7614)	model_time 0.7232 (0.7474)	loss 4.0445 (3.3807)	grad_norm 1.2980 (1.3440/0.5710)	mem 34602MB
[2025-01-19 07:55:27 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][110/312]	eta 0:02:33 lr 0.002819	time 0.7171 (0.7593)	model_time 0.7166 (0.7466)	loss 3.4461 (3.3690)	grad_norm 1.0115 (1.3406/0.5538)	mem 34602MB
[2025-01-19 07:55:34 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][120/312]	eta 0:02:25 lr 0.002818	time 0.7207 (0.7564)	model_time 0.7205 (0.7447)	loss 3.6593 (3.3678)	grad_norm 1.2291 (1.3231/0.5440)	mem 34602MB
[2025-01-19 07:55:42 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][130/312]	eta 0:02:17 lr 0.002817	time 0.8499 (0.7550)	model_time 0.8494 (0.7442)	loss 3.7334 (3.3782)	grad_norm 0.9759 (1.3336/0.5399)	mem 34602MB
[2025-01-19 07:55:49 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][140/312]	eta 0:02:09 lr 0.002817	time 0.8002 (0.7539)	model_time 0.8000 (0.7438)	loss 2.6422 (3.3615)	grad_norm 1.0379 (1.3445/0.5350)	mem 34602MB
[2025-01-19 07:55:56 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][150/312]	eta 0:02:01 lr 0.002816	time 0.7238 (0.7528)	model_time 0.7236 (0.7434)	loss 3.3322 (3.3516)	grad_norm 0.8619 (1.3130/0.5315)	mem 34602MB
[2025-01-19 07:56:04 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][160/312]	eta 0:01:54 lr 0.002816	time 0.7175 (0.7538)	model_time 0.7170 (0.7449)	loss 3.5761 (3.3601)	grad_norm 1.7926 (1.3241/0.5441)	mem 34602MB
[2025-01-19 07:56:12 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][170/312]	eta 0:01:47 lr 0.002815	time 0.7316 (0.7543)	model_time 0.7312 (0.7459)	loss 4.0737 (3.3788)	grad_norm 1.6058 (1.3348/0.5412)	mem 34602MB
[2025-01-19 07:56:19 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][180/312]	eta 0:01:39 lr 0.002814	time 0.8008 (0.7544)	model_time 0.8006 (0.7464)	loss 3.0248 (3.3796)	grad_norm 0.6850 (1.3521/0.5536)	mem 34602MB
[2025-01-19 07:56:27 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][190/312]	eta 0:01:32 lr 0.002814	time 0.7356 (0.7548)	model_time 0.7351 (0.7472)	loss 3.1488 (3.3651)	grad_norm 1.2880 (1.3600/0.5469)	mem 34602MB
[2025-01-19 07:56:34 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][200/312]	eta 0:01:24 lr 0.002813	time 0.7201 (0.7535)	model_time 0.7199 (0.7463)	loss 2.7941 (3.3681)	grad_norm 0.5153 (1.3480/0.5464)	mem 34602MB
[2025-01-19 07:56:42 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][210/312]	eta 0:01:16 lr 0.002813	time 0.7163 (0.7532)	model_time 0.7162 (0.7463)	loss 3.7056 (3.3592)	grad_norm 1.1597 (1.3305/0.5410)	mem 34602MB
[2025-01-19 07:56:49 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][220/312]	eta 0:01:09 lr 0.002812	time 0.7283 (0.7519)	model_time 0.7279 (0.7453)	loss 2.9438 (3.3604)	grad_norm 2.6768 (1.3602/0.5934)	mem 34602MB
[2025-01-19 07:56:56 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][230/312]	eta 0:01:01 lr 0.002811	time 0.7238 (0.7510)	model_time 0.7234 (0.7447)	loss 4.0421 (3.3641)	grad_norm 0.8743 (1.3490/0.5872)	mem 34602MB
[2025-01-19 07:57:04 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][240/312]	eta 0:00:54 lr 0.002811	time 0.7546 (0.7501)	model_time 0.7541 (0.7440)	loss 3.4967 (3.3583)	grad_norm 1.4179 (1.3501/0.5874)	mem 34602MB
[2025-01-19 07:57:11 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][250/312]	eta 0:00:46 lr 0.002810	time 0.8190 (0.7495)	model_time 0.8188 (0.7436)	loss 3.6708 (3.3561)	grad_norm 1.0672 (1.3543/0.5877)	mem 34602MB
[2025-01-19 07:57:18 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][260/312]	eta 0:00:38 lr 0.002810	time 0.7323 (0.7487)	model_time 0.7319 (0.7431)	loss 3.3943 (3.3569)	grad_norm 0.9185 (1.3606/0.5955)	mem 34602MB
[2025-01-19 07:57:26 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][270/312]	eta 0:00:31 lr 0.002809	time 0.7328 (0.7487)	model_time 0.7323 (0.7432)	loss 3.4965 (3.3638)	grad_norm 0.8531 (1.3456/0.5921)	mem 34602MB
[2025-01-19 07:57:33 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][280/312]	eta 0:00:23 lr 0.002808	time 0.7295 (0.7486)	model_time 0.7291 (0.7433)	loss 2.5373 (3.3598)	grad_norm 0.9812 (1.3439/0.5844)	mem 34602MB
[2025-01-19 07:57:41 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][290/312]	eta 0:00:16 lr 0.002808	time 0.7220 (0.7491)	model_time 0.7216 (0.7440)	loss 3.0368 (3.3582)	grad_norm 1.5730 (1.3384/0.5797)	mem 34602MB
[2025-01-19 07:57:48 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][300/312]	eta 0:00:08 lr 0.002807	time 0.8033 (0.7492)	model_time 0.8032 (0.7442)	loss 3.4369 (3.3479)	grad_norm 1.2348 (1.3371/0.5771)	mem 34602MB
[2025-01-19 07:57:56 internimage_b_1k_224] (main.py 510): INFO Train: [110/300][310/312]	eta 0:00:01 lr 0.002806	time 0.7115 (0.7496)	model_time 0.7114 (0.7448)	loss 3.3208 (3.3443)	grad_norm 1.1338 (1.3500/0.5757)	mem 34602MB
[2025-01-19 07:57:57 internimage_b_1k_224] (main.py 519): INFO EPOCH 110 training takes 0:03:53
[2025-01-19 07:57:57 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_110.pth saving......
[2025-01-19 07:58:00 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_110.pth saved !!!
[2025-01-19 07:58:07 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.275 (7.275)	Loss 0.8453 (0.8453)	Acc@1 81.543 (81.543)	Acc@5 96.509 (96.509)	Mem 34602MB
[2025-01-19 07:58:10 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.918)	Loss 1.1821 (0.9827)	Acc@1 73.608 (78.897)	Acc@5 92.773 (94.818)	Mem 34602MB
[2025-01-19 07:58:10 internimage_b_1k_224] (main.py 575): INFO [Epoch:110] * Acc@1 78.795 Acc@5 94.874
[2025-01-19 07:58:10 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.8%
[2025-01-19 07:58:10 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 78.86%
[2025-01-19 07:58:19 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.991 (8.991)	Loss 0.6991 (0.6991)	Acc@1 82.422 (82.422)	Acc@5 96.826 (96.826)	Mem 34602MB
[2025-01-19 07:58:24 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.220)	Loss 1.0736 (0.8623)	Acc@1 73.828 (79.046)	Acc@5 92.456 (94.760)	Mem 34602MB
[2025-01-19 07:58:24 internimage_b_1k_224] (main.py 575): INFO [Epoch:110] * Acc@1 78.957 Acc@5 94.826
[2025-01-19 07:58:24 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.0%
[2025-01-19 07:58:24 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 07:58:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 07:58:28 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 78.96%
[2025-01-19 07:58:30 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][0/312]	eta 0:11:03 lr 0.002806	time 2.1273 (2.1273)	model_time 0.7363 (0.7363)	loss 3.3813 (3.3813)	grad_norm 1.6976 (1.6976/0.0000)	mem 34602MB
[2025-01-19 07:58:37 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][10/312]	eta 0:04:19 lr 0.002806	time 0.7343 (0.8601)	model_time 0.7342 (0.7334)	loss 3.6946 (3.0418)	grad_norm 1.2706 (1.1136/0.2403)	mem 34602MB
[2025-01-19 07:58:45 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][20/312]	eta 0:03:58 lr 0.002805	time 0.7176 (0.8156)	model_time 0.7175 (0.7491)	loss 3.5166 (3.1393)	grad_norm 2.1051 (1.3064/0.4188)	mem 34602MB
[2025-01-19 07:58:52 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][30/312]	eta 0:03:42 lr 0.002805	time 0.7206 (0.7884)	model_time 0.7204 (0.7432)	loss 3.7028 (3.1510)	grad_norm 0.9193 (1.3281/0.4499)	mem 34602MB
[2025-01-19 07:59:00 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][40/312]	eta 0:03:30 lr 0.002804	time 0.7185 (0.7741)	model_time 0.7181 (0.7399)	loss 3.2069 (3.2395)	grad_norm 2.4959 (1.3754/0.5304)	mem 34602MB
[2025-01-19 07:59:07 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][50/312]	eta 0:03:20 lr 0.002803	time 0.7270 (0.7648)	model_time 0.7267 (0.7372)	loss 3.3933 (3.2136)	grad_norm 1.3117 (1.3581/0.5217)	mem 34602MB
[2025-01-19 07:59:14 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][60/312]	eta 0:03:11 lr 0.002803	time 0.7272 (0.7588)	model_time 0.7267 (0.7356)	loss 3.6658 (3.3081)	grad_norm 1.6369 (1.3583/0.4957)	mem 34602MB
[2025-01-19 07:59:22 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][70/312]	eta 0:03:02 lr 0.002802	time 0.7179 (0.7551)	model_time 0.7175 (0.7352)	loss 4.2978 (3.3564)	grad_norm 1.6220 (1.4463/0.6338)	mem 34602MB
[2025-01-19 07:59:29 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][80/312]	eta 0:02:55 lr 0.002801	time 0.7203 (0.7548)	model_time 0.7201 (0.7373)	loss 3.8273 (3.4113)	grad_norm 1.3024 (1.4088/0.6224)	mem 34602MB
[2025-01-19 07:59:37 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][90/312]	eta 0:02:47 lr 0.002801	time 0.7204 (0.7555)	model_time 0.7203 (0.7399)	loss 3.0440 (3.3976)	grad_norm 0.9725 (1.3809/0.5979)	mem 34602MB
[2025-01-19 07:59:44 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][100/312]	eta 0:02:40 lr 0.002800	time 0.7294 (0.7548)	model_time 0.7290 (0.7407)	loss 3.7598 (3.3934)	grad_norm 2.1787 (1.3947/0.6161)	mem 34602MB
[2025-01-19 07:59:52 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][110/312]	eta 0:02:32 lr 0.002800	time 0.8196 (0.7551)	model_time 0.8194 (0.7422)	loss 3.4251 (3.3674)	grad_norm 1.3037 (1.3659/0.5999)	mem 34602MB
[2025-01-19 07:59:59 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][120/312]	eta 0:02:25 lr 0.002799	time 0.7971 (0.7560)	model_time 0.7967 (0.7442)	loss 4.1531 (3.3753)	grad_norm 1.4578 (1.3663/0.5881)	mem 34602MB
[2025-01-19 08:00:07 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][130/312]	eta 0:02:17 lr 0.002798	time 0.7152 (0.7543)	model_time 0.7151 (0.7434)	loss 3.4406 (3.3871)	grad_norm 1.2453 (1.3801/0.5902)	mem 34602MB
[2025-01-19 08:00:14 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][140/312]	eta 0:02:09 lr 0.002798	time 0.7198 (0.7538)	model_time 0.7196 (0.7436)	loss 4.2388 (3.4035)	grad_norm 2.4246 (1.3941/0.5835)	mem 34602MB
[2025-01-19 08:00:21 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][150/312]	eta 0:02:01 lr 0.002797	time 0.7264 (0.7522)	model_time 0.7260 (0.7426)	loss 3.5233 (3.4134)	grad_norm 0.8081 (1.3772/0.5720)	mem 34602MB
[2025-01-19 08:00:29 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][160/312]	eta 0:01:54 lr 0.002797	time 0.7175 (0.7509)	model_time 0.7170 (0.7420)	loss 3.1613 (3.4001)	grad_norm 1.7075 (1.3945/0.5783)	mem 34602MB
[2025-01-19 08:00:36 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][170/312]	eta 0:01:46 lr 0.002796	time 0.7453 (0.7496)	model_time 0.7451 (0.7411)	loss 3.4829 (3.3879)	grad_norm 1.4149 (1.3850/0.5672)	mem 34602MB
[2025-01-19 08:00:43 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][180/312]	eta 0:01:38 lr 0.002795	time 0.7466 (0.7483)	model_time 0.7465 (0.7403)	loss 4.0271 (3.3936)	grad_norm 1.8081 (1.3759/0.5564)	mem 34602MB
[2025-01-19 08:00:51 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][190/312]	eta 0:01:31 lr 0.002795	time 0.7208 (0.7474)	model_time 0.7206 (0.7398)	loss 2.7435 (3.3877)	grad_norm 2.6847 (1.4085/0.5942)	mem 34602MB
[2025-01-19 08:00:58 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][200/312]	eta 0:01:23 lr 0.002794	time 0.7202 (0.7478)	model_time 0.7201 (0.7406)	loss 3.7212 (3.3924)	grad_norm 1.1626 (1.3969/0.5859)	mem 34602MB
[2025-01-19 08:01:06 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][210/312]	eta 0:01:16 lr 0.002794	time 0.8103 (0.7481)	model_time 0.8099 (0.7412)	loss 3.8631 (3.3946)	grad_norm 1.1100 (1.3900/0.5817)	mem 34602MB
[2025-01-19 08:01:13 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][220/312]	eta 0:01:08 lr 0.002793	time 0.7170 (0.7482)	model_time 0.7166 (0.7416)	loss 4.0885 (3.3924)	grad_norm 0.8991 (1.3890/0.5743)	mem 34602MB
[2025-01-19 08:01:21 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][230/312]	eta 0:01:01 lr 0.002792	time 0.8348 (0.7487)	model_time 0.8344 (0.7423)	loss 3.4856 (3.3985)	grad_norm 0.6682 (1.3829/0.5696)	mem 34602MB
[2025-01-19 08:01:29 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][240/312]	eta 0:00:53 lr 0.002792	time 0.7924 (0.7494)	model_time 0.7922 (0.7433)	loss 3.4183 (3.4019)	grad_norm 1.1528 (1.3778/0.5660)	mem 34602MB
[2025-01-19 08:01:36 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][250/312]	eta 0:00:46 lr 0.002791	time 0.7335 (0.7485)	model_time 0.7331 (0.7426)	loss 3.1015 (3.3953)	grad_norm 2.2728 (1.3781/0.5670)	mem 34602MB
[2025-01-19 08:01:43 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][260/312]	eta 0:00:38 lr 0.002790	time 0.7311 (0.7487)	model_time 0.7306 (0.7431)	loss 3.8084 (3.3878)	grad_norm 1.0946 (1.3876/0.5661)	mem 34602MB
[2025-01-19 08:01:51 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][270/312]	eta 0:00:31 lr 0.002790	time 0.7176 (0.7481)	model_time 0.7175 (0.7426)	loss 4.0952 (3.3914)	grad_norm 0.9190 (1.3883/0.5635)	mem 34602MB
[2025-01-19 08:01:58 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][280/312]	eta 0:00:23 lr 0.002789	time 0.7405 (0.7475)	model_time 0.7404 (0.7422)	loss 4.1286 (3.3872)	grad_norm 1.7014 (1.3837/0.5582)	mem 34602MB
[2025-01-19 08:02:05 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][290/312]	eta 0:00:16 lr 0.002789	time 0.7240 (0.7469)	model_time 0.7235 (0.7417)	loss 3.1110 (3.3885)	grad_norm 1.1566 (1.3780/0.5539)	mem 34602MB
[2025-01-19 08:02:12 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][300/312]	eta 0:00:08 lr 0.002788	time 0.7119 (0.7460)	model_time 0.7117 (0.7411)	loss 3.1161 (3.3950)	grad_norm 1.1580 (1.3680/0.5480)	mem 34602MB
[2025-01-19 08:02:20 internimage_b_1k_224] (main.py 510): INFO Train: [111/300][310/312]	eta 0:00:01 lr 0.002787	time 0.7196 (0.7451)	model_time 0.7195 (0.7403)	loss 3.7566 (3.3869)	grad_norm 0.8070 (1.3654/0.5498)	mem 34602MB
[2025-01-19 08:02:20 internimage_b_1k_224] (main.py 519): INFO EPOCH 111 training takes 0:03:52
[2025-01-19 08:02:20 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_111.pth saving......
[2025-01-19 08:02:23 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_111.pth saved !!!
[2025-01-19 08:02:31 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.367 (7.367)	Loss 0.8254 (0.8254)	Acc@1 82.788 (82.788)	Acc@5 96.924 (96.924)	Mem 34602MB
[2025-01-19 08:02:34 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.933)	Loss 1.1714 (0.9784)	Acc@1 74.365 (79.264)	Acc@5 93.286 (95.046)	Mem 34602MB
[2025-01-19 08:02:34 internimage_b_1k_224] (main.py 575): INFO [Epoch:111] * Acc@1 79.157 Acc@5 95.052
[2025-01-19 08:02:34 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.2%
[2025-01-19 08:02:34 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 08:02:37 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 08:02:37 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.16%
[2025-01-19 08:02:45 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.406 (7.406)	Loss 0.6956 (0.6956)	Acc@1 82.495 (82.495)	Acc@5 96.826 (96.826)	Mem 34602MB
[2025-01-19 08:02:48 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.957)	Loss 1.0686 (0.8584)	Acc@1 73.926 (79.155)	Acc@5 92.456 (94.786)	Mem 34602MB
[2025-01-19 08:02:48 internimage_b_1k_224] (main.py 575): INFO [Epoch:111] * Acc@1 79.053 Acc@5 94.844
[2025-01-19 08:02:48 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.1%
[2025-01-19 08:02:48 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 08:02:52 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 08:02:52 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 79.05%
[2025-01-19 08:02:54 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][0/312]	eta 0:10:30 lr 0.002787	time 2.0217 (2.0217)	model_time 0.7541 (0.7541)	loss 3.5736 (3.5736)	grad_norm 0.8396 (0.8396/0.0000)	mem 34602MB
[2025-01-19 08:03:02 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][10/312]	eta 0:04:22 lr 0.002787	time 0.7263 (0.8700)	model_time 0.7262 (0.7545)	loss 4.1387 (3.5893)	grad_norm 1.8172 (1.5221/0.5160)	mem 34602MB
[2025-01-19 08:03:09 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][20/312]	eta 0:04:00 lr 0.002786	time 0.7326 (0.8232)	model_time 0.7324 (0.7625)	loss 3.8726 (3.5925)	grad_norm 1.3654 (1.5601/0.5929)	mem 34602MB
[2025-01-19 08:03:17 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][30/312]	eta 0:03:46 lr 0.002785	time 0.7211 (0.8033)	model_time 0.7207 (0.7621)	loss 3.3082 (3.5552)	grad_norm 1.1315 (1.4820/0.5760)	mem 34602MB
[2025-01-19 08:03:25 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][40/312]	eta 0:03:36 lr 0.002785	time 0.7176 (0.7948)	model_time 0.7174 (0.7636)	loss 3.4771 (3.4084)	grad_norm 1.8151 (1.4335/0.5514)	mem 34602MB
[2025-01-19 08:03:32 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][50/312]	eta 0:03:26 lr 0.002784	time 0.7229 (0.7883)	model_time 0.7224 (0.7632)	loss 4.0646 (3.3754)	grad_norm 0.9431 (1.3477/0.5322)	mem 34602MB
[2025-01-19 08:03:39 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][60/312]	eta 0:03:16 lr 0.002784	time 0.7287 (0.7795)	model_time 0.7282 (0.7585)	loss 3.2686 (3.3919)	grad_norm 1.1154 (1.3761/0.5489)	mem 34602MB
[2025-01-19 08:03:47 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][70/312]	eta 0:03:07 lr 0.002783	time 0.8027 (0.7756)	model_time 0.8023 (0.7574)	loss 3.6613 (3.3520)	grad_norm 1.0146 (1.4347/0.6231)	mem 34602MB
[2025-01-19 08:03:54 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][80/312]	eta 0:02:58 lr 0.002782	time 0.7220 (0.7696)	model_time 0.7216 (0.7536)	loss 3.5255 (3.3332)	grad_norm 0.5599 (1.4067/0.5948)	mem 34602MB
[2025-01-19 08:04:02 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][90/312]	eta 0:02:50 lr 0.002782	time 0.7167 (0.7661)	model_time 0.7165 (0.7519)	loss 3.7746 (3.3175)	grad_norm 0.6702 (1.3604/0.5803)	mem 34602MB
[2025-01-19 08:04:09 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][100/312]	eta 0:02:41 lr 0.002781	time 0.7137 (0.7615)	model_time 0.7133 (0.7486)	loss 2.2599 (3.3117)	grad_norm 1.7591 (1.3400/0.5622)	mem 34602MB
[2025-01-19 08:04:16 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][110/312]	eta 0:02:33 lr 0.002781	time 0.7163 (0.7581)	model_time 0.7158 (0.7464)	loss 3.2837 (3.3141)	grad_norm 1.9259 (1.4120/0.6264)	mem 34602MB
[2025-01-19 08:04:23 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][120/312]	eta 0:02:25 lr 0.002780	time 0.7218 (0.7553)	model_time 0.7216 (0.7445)	loss 2.2495 (3.3073)	grad_norm 0.8585 (1.4051/0.6084)	mem 34602MB
[2025-01-19 08:04:31 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][130/312]	eta 0:02:17 lr 0.002779	time 0.8022 (0.7562)	model_time 0.8017 (0.7462)	loss 2.5097 (3.3271)	grad_norm 1.2551 (1.4020/0.6143)	mem 34602MB
[2025-01-19 08:04:39 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][140/312]	eta 0:02:10 lr 0.002779	time 0.7159 (0.7568)	model_time 0.7155 (0.7475)	loss 2.8765 (3.3083)	grad_norm 1.4361 (1.3867/0.6038)	mem 34602MB
[2025-01-19 08:04:46 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][150/312]	eta 0:02:02 lr 0.002778	time 0.7184 (0.7557)	model_time 0.7179 (0.7470)	loss 4.1074 (3.3284)	grad_norm 1.9691 (1.3695/0.5928)	mem 34602MB
[2025-01-19 08:04:54 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][160/312]	eta 0:01:54 lr 0.002777	time 0.7257 (0.7562)	model_time 0.7253 (0.7480)	loss 2.9179 (3.3213)	grad_norm 0.6170 (1.3742/0.5984)	mem 34602MB
[2025-01-19 08:05:01 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][170/312]	eta 0:01:47 lr 0.002777	time 0.7280 (0.7566)	model_time 0.7276 (0.7488)	loss 3.6220 (3.3290)	grad_norm 0.6004 (1.4130/0.6437)	mem 34602MB
[2025-01-19 08:05:09 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][180/312]	eta 0:01:39 lr 0.002776	time 0.7161 (0.7550)	model_time 0.7156 (0.7476)	loss 3.4088 (3.3505)	grad_norm 1.3221 (1.4198/0.6470)	mem 34602MB
[2025-01-19 08:05:16 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][190/312]	eta 0:01:32 lr 0.002776	time 0.8133 (0.7547)	model_time 0.8131 (0.7477)	loss 3.1097 (3.3663)	grad_norm 2.1512 (1.4247/0.6416)	mem 34602MB
[2025-01-19 08:05:23 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][200/312]	eta 0:01:24 lr 0.002775	time 0.7183 (0.7532)	model_time 0.7179 (0.7466)	loss 3.4267 (3.3677)	grad_norm 1.0720 (1.4062/0.6324)	mem 34602MB
[2025-01-19 08:05:31 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][210/312]	eta 0:01:16 lr 0.002774	time 0.7166 (0.7525)	model_time 0.7165 (0.7462)	loss 3.6224 (3.3742)	grad_norm 1.6316 (1.3936/0.6233)	mem 34602MB
[2025-01-19 08:05:38 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][220/312]	eta 0:01:09 lr 0.002774	time 0.7715 (0.7516)	model_time 0.7713 (0.7455)	loss 3.5155 (3.3774)	grad_norm 1.4283 (1.3947/0.6219)	mem 34602MB
[2025-01-19 08:05:45 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][230/312]	eta 0:01:01 lr 0.002773	time 0.7216 (0.7506)	model_time 0.7212 (0.7447)	loss 4.1957 (3.3839)	grad_norm 1.3358 (1.3939/0.6180)	mem 34602MB
[2025-01-19 08:05:53 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][240/312]	eta 0:00:53 lr 0.002773	time 0.7171 (0.7495)	model_time 0.7166 (0.7438)	loss 4.0309 (3.3941)	grad_norm 1.8922 (1.4094/0.6400)	mem 34602MB
[2025-01-19 08:06:00 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][250/312]	eta 0:00:46 lr 0.002772	time 0.7946 (0.7499)	model_time 0.7944 (0.7445)	loss 3.2281 (3.3997)	grad_norm 1.2460 (1.4077/0.6370)	mem 34602MB
[2025-01-19 08:06:08 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][260/312]	eta 0:00:38 lr 0.002771	time 0.7450 (0.7499)	model_time 0.7445 (0.7447)	loss 4.1124 (3.4056)	grad_norm 0.9768 (1.3955/0.6328)	mem 34602MB
[2025-01-19 08:06:15 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][270/312]	eta 0:00:31 lr 0.002771	time 0.7277 (0.7497)	model_time 0.7273 (0.7446)	loss 3.8105 (3.4029)	grad_norm 1.6743 (1.3841/0.6266)	mem 34602MB
[2025-01-19 08:06:23 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][280/312]	eta 0:00:24 lr 0.002770	time 0.7176 (0.7501)	model_time 0.7171 (0.7452)	loss 3.4465 (3.3988)	grad_norm 2.6353 (1.3862/0.6294)	mem 34602MB
[2025-01-19 08:06:30 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][290/312]	eta 0:00:16 lr 0.002769	time 0.7146 (0.7508)	model_time 0.7144 (0.7461)	loss 3.5319 (3.3997)	grad_norm 2.2850 (1.3956/0.6267)	mem 34602MB
[2025-01-19 08:06:38 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][300/312]	eta 0:00:09 lr 0.002769	time 0.7140 (0.7503)	model_time 0.7139 (0.7457)	loss 4.2853 (3.4052)	grad_norm 1.0957 (1.4006/0.6270)	mem 34602MB
[2025-01-19 08:06:45 internimage_b_1k_224] (main.py 510): INFO Train: [112/300][310/312]	eta 0:00:01 lr 0.002768	time 0.7263 (0.7497)	model_time 0.7262 (0.7453)	loss 3.6721 (3.4161)	grad_norm 1.0488 (1.3952/0.6255)	mem 34602MB
[2025-01-19 08:06:46 internimage_b_1k_224] (main.py 519): INFO EPOCH 112 training takes 0:03:53
[2025-01-19 08:06:46 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_112.pth saving......
[2025-01-19 08:06:49 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_112.pth saved !!!
[2025-01-19 08:06:56 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.232 (7.232)	Loss 0.8746 (0.8746)	Acc@1 82.080 (82.080)	Acc@5 96.680 (96.680)	Mem 34602MB
[2025-01-19 08:06:59 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.188 (0.919)	Loss 1.1857 (1.0072)	Acc@1 74.585 (78.855)	Acc@5 92.896 (94.864)	Mem 34602MB
[2025-01-19 08:06:59 internimage_b_1k_224] (main.py 575): INFO [Epoch:112] * Acc@1 78.851 Acc@5 94.900
[2025-01-19 08:06:59 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.9%
[2025-01-19 08:06:59 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.16%
[2025-01-19 08:07:09 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.072 (9.072)	Loss 0.6924 (0.6924)	Acc@1 82.593 (82.593)	Acc@5 96.948 (96.948)	Mem 34602MB
[2025-01-19 08:07:13 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.218)	Loss 1.0636 (0.8548)	Acc@1 74.048 (79.230)	Acc@5 92.603 (94.835)	Mem 34602MB
[2025-01-19 08:07:13 internimage_b_1k_224] (main.py 575): INFO [Epoch:112] * Acc@1 79.123 Acc@5 94.890
[2025-01-19 08:07:13 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.1%
[2025-01-19 08:07:13 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 08:07:17 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 08:07:17 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 79.12%
[2025-01-19 08:07:19 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][0/312]	eta 0:11:21 lr 0.002768	time 2.1832 (2.1832)	model_time 0.7467 (0.7467)	loss 3.8207 (3.8207)	grad_norm 1.2918 (1.2918/0.0000)	mem 34602MB
[2025-01-19 08:07:27 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][10/312]	eta 0:04:21 lr 0.002768	time 0.7284 (0.8651)	model_time 0.7283 (0.7342)	loss 3.4414 (3.2720)	grad_norm 0.9219 (1.1005/0.2737)	mem 34602MB
[2025-01-19 08:07:34 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][20/312]	eta 0:03:54 lr 0.002767	time 0.7206 (0.8033)	model_time 0.7201 (0.7346)	loss 2.5290 (3.2526)	grad_norm 0.6353 (1.1043/0.3045)	mem 34602MB
[2025-01-19 08:07:41 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][30/312]	eta 0:03:39 lr 0.002766	time 0.7203 (0.7786)	model_time 0.7201 (0.7319)	loss 2.6465 (3.2313)	grad_norm 0.7865 (1.3182/0.6441)	mem 34602MB
[2025-01-19 08:07:48 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][40/312]	eta 0:03:28 lr 0.002766	time 0.7210 (0.7648)	model_time 0.7205 (0.7294)	loss 3.2390 (3.2303)	grad_norm 1.4109 (1.2912/0.5817)	mem 34602MB
[2025-01-19 08:07:56 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][50/312]	eta 0:03:18 lr 0.002765	time 0.7289 (0.7572)	model_time 0.7288 (0.7287)	loss 2.1591 (3.2400)	grad_norm 0.7894 (1.2330/0.5417)	mem 34602MB
[2025-01-19 08:08:03 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][60/312]	eta 0:03:10 lr 0.002764	time 0.7444 (0.7578)	model_time 0.7439 (0.7339)	loss 3.4522 (3.2728)	grad_norm 0.9412 (1.3026/0.5792)	mem 34602MB
[2025-01-19 08:08:11 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][70/312]	eta 0:03:03 lr 0.002764	time 0.7214 (0.7586)	model_time 0.7212 (0.7380)	loss 3.3964 (3.2643)	grad_norm 1.1290 (1.3071/0.5639)	mem 34602MB
[2025-01-19 08:08:18 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][80/312]	eta 0:02:55 lr 0.002763	time 0.7170 (0.7579)	model_time 0.7169 (0.7398)	loss 2.5975 (3.2659)	grad_norm 1.4118 (1.2654/0.5448)	mem 34602MB
[2025-01-19 08:08:26 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][90/312]	eta 0:02:48 lr 0.002763	time 0.7243 (0.7577)	model_time 0.7242 (0.7416)	loss 3.2636 (3.2599)	grad_norm 0.7897 (1.3147/0.5789)	mem 34602MB
[2025-01-19 08:08:33 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][100/312]	eta 0:02:40 lr 0.002762	time 0.7146 (0.7567)	model_time 0.7142 (0.7422)	loss 2.7784 (3.2429)	grad_norm 1.5142 (1.3640/0.6209)	mem 34602MB
[2025-01-19 08:08:41 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][110/312]	eta 0:02:32 lr 0.002761	time 0.8015 (0.7555)	model_time 0.8013 (0.7422)	loss 4.2056 (3.2454)	grad_norm 1.9507 (1.3836/0.6198)	mem 34602MB
[2025-01-19 08:08:48 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][120/312]	eta 0:02:24 lr 0.002761	time 0.7156 (0.7552)	model_time 0.7152 (0.7429)	loss 3.0847 (3.2391)	grad_norm 1.1892 (1.3777/0.6042)	mem 34602MB
[2025-01-19 08:08:56 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][130/312]	eta 0:02:17 lr 0.002760	time 0.8496 (0.7550)	model_time 0.8495 (0.7436)	loss 4.0499 (3.2490)	grad_norm 1.1390 (1.3887/0.6021)	mem 34602MB
[2025-01-19 08:09:03 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][140/312]	eta 0:02:09 lr 0.002760	time 0.7193 (0.7532)	model_time 0.7189 (0.7426)	loss 2.4280 (3.2192)	grad_norm 0.5699 (1.3751/0.5903)	mem 34602MB
[2025-01-19 08:09:11 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][150/312]	eta 0:02:01 lr 0.002759	time 0.7383 (0.7515)	model_time 0.7378 (0.7417)	loss 2.3156 (3.2220)	grad_norm 0.8423 (1.3748/0.5773)	mem 34602MB
[2025-01-19 08:09:18 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][160/312]	eta 0:01:53 lr 0.002758	time 0.7410 (0.7499)	model_time 0.7409 (0.7407)	loss 3.4571 (3.2330)	grad_norm 1.3378 (1.3660/0.5660)	mem 34602MB
[2025-01-19 08:09:25 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][170/312]	eta 0:01:46 lr 0.002758	time 0.7219 (0.7488)	model_time 0.7217 (0.7401)	loss 2.9625 (3.2453)	grad_norm 0.8557 (1.3637/0.5639)	mem 34602MB
[2025-01-19 08:09:33 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][180/312]	eta 0:01:38 lr 0.002757	time 0.7262 (0.7490)	model_time 0.7257 (0.7407)	loss 3.1603 (3.2567)	grad_norm 0.9307 (1.3493/0.5578)	mem 34602MB
[2025-01-19 08:09:40 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][190/312]	eta 0:01:31 lr 0.002756	time 0.7152 (0.7497)	model_time 0.7149 (0.7418)	loss 3.9237 (3.2645)	grad_norm 1.2012 (1.3457/0.5448)	mem 34602MB
[2025-01-19 08:09:48 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][200/312]	eta 0:01:23 lr 0.002756	time 0.8101 (0.7497)	model_time 0.8096 (0.7422)	loss 2.0502 (3.2561)	grad_norm 0.8897 (1.3474/0.5393)	mem 34602MB
[2025-01-19 08:09:55 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][210/312]	eta 0:01:16 lr 0.002755	time 0.7166 (0.7496)	model_time 0.7162 (0.7424)	loss 3.5299 (3.2637)	grad_norm 0.9541 (1.3295/0.5339)	mem 34602MB
[2025-01-19 08:10:03 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][220/312]	eta 0:01:08 lr 0.002755	time 0.7158 (0.7498)	model_time 0.7157 (0.7429)	loss 3.7527 (3.2747)	grad_norm 0.7335 (1.3363/0.5411)	mem 34602MB
[2025-01-19 08:10:10 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][230/312]	eta 0:01:01 lr 0.002754	time 0.7971 (0.7493)	model_time 0.7966 (0.7427)	loss 3.7993 (3.2791)	grad_norm 1.6921 (1.3331/0.5349)	mem 34602MB
[2025-01-19 08:10:18 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][240/312]	eta 0:00:53 lr 0.002753	time 0.6678 (0.7489)	model_time 0.6677 (0.7426)	loss 3.3491 (3.2780)	grad_norm inf (1.3615/0.5549)	mem 34602MB
[2025-01-19 08:10:25 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][250/312]	eta 0:00:46 lr 0.002753	time 0.8219 (0.7493)	model_time 0.8215 (0.7432)	loss 2.3622 (3.2731)	grad_norm 1.5812 (1.3705/0.5622)	mem 34602MB
[2025-01-19 08:10:32 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][260/312]	eta 0:00:38 lr 0.002752	time 0.7224 (0.7484)	model_time 0.7222 (0.7426)	loss 3.2634 (3.2803)	grad_norm 1.4814 (1.3660/0.5608)	mem 34602MB
[2025-01-19 08:10:40 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][270/312]	eta 0:00:31 lr 0.002751	time 0.7160 (0.7476)	model_time 0.7156 (0.7419)	loss 3.7130 (3.2872)	grad_norm 0.7807 (1.3538/0.5566)	mem 34602MB
[2025-01-19 08:10:47 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][280/312]	eta 0:00:23 lr 0.002751	time 0.7291 (0.7467)	model_time 0.7287 (0.7412)	loss 2.4856 (3.2756)	grad_norm 1.0262 (1.3510/0.5522)	mem 34602MB
[2025-01-19 08:10:54 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][290/312]	eta 0:00:16 lr 0.002750	time 0.7348 (0.7461)	model_time 0.7343 (0.7408)	loss 3.6740 (3.2832)	grad_norm 1.5952 (1.3532/0.5518)	mem 34602MB
[2025-01-19 08:11:02 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][300/312]	eta 0:00:08 lr 0.002750	time 0.7137 (0.7461)	model_time 0.7136 (0.7410)	loss 3.9297 (3.2850)	grad_norm 1.5397 (1.3596/0.5739)	mem 34602MB
[2025-01-19 08:11:09 internimage_b_1k_224] (main.py 510): INFO Train: [113/300][310/312]	eta 0:00:01 lr 0.002749	time 0.8002 (0.7464)	model_time 0.8002 (0.7414)	loss 3.7010 (3.2887)	grad_norm 1.4473 (1.3854/0.5939)	mem 34602MB
[2025-01-19 08:11:10 internimage_b_1k_224] (main.py 519): INFO EPOCH 113 training takes 0:03:52
[2025-01-19 08:11:10 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_113.pth saving......
[2025-01-19 08:11:13 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_113.pth saved !!!
[2025-01-19 08:11:20 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.257 (7.257)	Loss 0.8419 (0.8419)	Acc@1 81.885 (81.885)	Acc@5 96.655 (96.655)	Mem 34602MB
[2025-01-19 08:11:24 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.937)	Loss 1.1889 (1.0036)	Acc@1 73.682 (79.053)	Acc@5 92.700 (94.806)	Mem 34602MB
[2025-01-19 08:11:24 internimage_b_1k_224] (main.py 575): INFO [Epoch:113] * Acc@1 78.997 Acc@5 94.866
[2025-01-19 08:11:24 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.0%
[2025-01-19 08:11:24 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.16%
[2025-01-19 08:11:33 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.969 (8.969)	Loss 0.6894 (0.6894)	Acc@1 82.690 (82.690)	Acc@5 96.973 (96.973)	Mem 34602MB
[2025-01-19 08:11:37 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.218)	Loss 1.0588 (0.8513)	Acc@1 74.146 (79.319)	Acc@5 92.651 (94.873)	Mem 34602MB
[2025-01-19 08:11:37 internimage_b_1k_224] (main.py 575): INFO [Epoch:113] * Acc@1 79.221 Acc@5 94.930
[2025-01-19 08:11:37 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.2%
[2025-01-19 08:11:37 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 08:11:42 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 08:11:42 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 79.22%
[2025-01-19 08:11:44 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][0/312]	eta 0:10:19 lr 0.002749	time 1.9858 (1.9858)	model_time 0.7526 (0.7526)	loss 2.7989 (2.7989)	grad_norm 1.4458 (1.4458/0.0000)	mem 34602MB
[2025-01-19 08:11:51 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][10/312]	eta 0:04:21 lr 0.002748	time 0.7199 (0.8657)	model_time 0.7194 (0.7532)	loss 3.5493 (3.4350)	grad_norm 1.1023 (1.1949/0.2431)	mem 34602MB
[2025-01-19 08:11:59 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][20/312]	eta 0:03:59 lr 0.002748	time 0.7850 (0.8193)	model_time 0.7848 (0.7603)	loss 2.8570 (3.3979)	grad_norm 1.2437 (1.1422/0.2949)	mem 34602MB
[2025-01-19 08:12:07 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][30/312]	eta 0:03:45 lr 0.002747	time 0.7896 (0.7979)	model_time 0.7891 (0.7578)	loss 3.4038 (3.3982)	grad_norm 1.1912 (1.2177/0.3241)	mem 34602MB
[2025-01-19 08:12:14 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][40/312]	eta 0:03:32 lr 0.002746	time 0.7357 (0.7826)	model_time 0.7352 (0.7522)	loss 3.5681 (3.4786)	grad_norm 1.6777 (1.3021/0.4162)	mem 34602MB
[2025-01-19 08:12:22 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][50/312]	eta 0:03:23 lr 0.002746	time 0.8049 (0.7765)	model_time 0.8047 (0.7520)	loss 3.7222 (3.4387)	grad_norm 2.0834 (1.4596/0.5497)	mem 34602MB
[2025-01-19 08:12:29 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][60/312]	eta 0:03:13 lr 0.002745	time 0.7320 (0.7693)	model_time 0.7315 (0.7487)	loss 3.5436 (3.4830)	grad_norm 2.4884 (1.4607/0.5469)	mem 34602MB
[2025-01-19 08:12:36 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][70/312]	eta 0:03:04 lr 0.002745	time 0.7166 (0.7636)	model_time 0.7161 (0.7458)	loss 3.8162 (3.4520)	grad_norm 0.9656 (1.4242/0.5636)	mem 34602MB
[2025-01-19 08:12:43 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][80/312]	eta 0:02:56 lr 0.002744	time 0.7172 (0.7592)	model_time 0.7168 (0.7436)	loss 3.4929 (3.3858)	grad_norm 1.6413 (1.3983/0.5445)	mem 34602MB
[2025-01-19 08:12:51 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][90/312]	eta 0:02:47 lr 0.002743	time 0.7194 (0.7554)	model_time 0.7192 (0.7414)	loss 3.9709 (3.3952)	grad_norm 1.9800 (1.4059/0.5404)	mem 34602MB
[2025-01-19 08:12:58 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][100/312]	eta 0:02:39 lr 0.002743	time 0.7236 (0.7531)	model_time 0.7234 (0.7405)	loss 2.6452 (3.3515)	grad_norm 1.7076 (1.3723/0.5306)	mem 34602MB
[2025-01-19 08:13:06 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][110/312]	eta 0:02:32 lr 0.002742	time 0.7398 (0.7527)	model_time 0.7393 (0.7412)	loss 2.7694 (3.3435)	grad_norm 2.0490 (1.4044/0.5350)	mem 34602MB
[2025-01-19 08:13:13 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][120/312]	eta 0:02:24 lr 0.002741	time 0.7140 (0.7532)	model_time 0.7138 (0.7427)	loss 2.3864 (3.3329)	grad_norm 1.9631 (1.4331/0.5392)	mem 34602MB
[2025-01-19 08:13:21 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][130/312]	eta 0:02:17 lr 0.002741	time 0.7283 (0.7538)	model_time 0.7281 (0.7440)	loss 2.9620 (3.3419)	grad_norm 1.3529 (1.4327/0.5246)	mem 34602MB
[2025-01-19 08:13:28 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][140/312]	eta 0:02:09 lr 0.002740	time 0.9488 (0.7550)	model_time 0.9484 (0.7459)	loss 3.4147 (3.3329)	grad_norm 2.5530 (1.4426/0.5357)	mem 34602MB
[2025-01-19 08:13:36 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][150/312]	eta 0:02:02 lr 0.002740	time 0.7379 (0.7550)	model_time 0.7375 (0.7465)	loss 2.4985 (3.3092)	grad_norm 2.0682 (1.4586/0.5401)	mem 34602MB
[2025-01-19 08:13:43 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][160/312]	eta 0:01:54 lr 0.002739	time 0.7230 (0.7539)	model_time 0.7229 (0.7459)	loss 3.4077 (3.3173)	grad_norm 1.5636 (1.4765/0.5498)	mem 34602MB
[2025-01-19 08:13:51 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][170/312]	eta 0:01:47 lr 0.002738	time 0.8143 (0.7541)	model_time 0.8138 (0.7466)	loss 3.4143 (3.3058)	grad_norm 1.0337 (1.4414/0.5533)	mem 34602MB
[2025-01-19 08:13:58 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][180/312]	eta 0:01:39 lr 0.002738	time 0.7166 (0.7534)	model_time 0.7162 (0.7462)	loss 3.3790 (3.3136)	grad_norm 1.7963 (1.4190/0.5505)	mem 34602MB
[2025-01-19 08:14:06 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][190/312]	eta 0:01:31 lr 0.002737	time 0.7162 (0.7521)	model_time 0.7157 (0.7453)	loss 2.8775 (3.3354)	grad_norm 2.0488 (1.4200/0.5493)	mem 34602MB
[2025-01-19 08:14:13 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][200/312]	eta 0:01:24 lr 0.002737	time 0.7198 (0.7507)	model_time 0.7197 (0.7442)	loss 2.7235 (3.3067)	grad_norm 1.5198 (1.4107/0.5465)	mem 34602MB
[2025-01-19 08:14:20 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][210/312]	eta 0:01:16 lr 0.002736	time 0.7199 (0.7495)	model_time 0.7195 (0.7432)	loss 3.2410 (3.3074)	grad_norm 0.9843 (1.4244/0.5610)	mem 34602MB
[2025-01-19 08:14:27 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][220/312]	eta 0:01:08 lr 0.002735	time 0.7157 (0.7486)	model_time 0.7155 (0.7426)	loss 3.3361 (3.3152)	grad_norm 1.6414 (1.4294/0.5651)	mem 34602MB
[2025-01-19 08:14:35 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][230/312]	eta 0:01:01 lr 0.002735	time 0.7254 (0.7483)	model_time 0.7250 (0.7426)	loss 4.0243 (3.3292)	grad_norm 1.2808 (1.4106/0.5631)	mem 34602MB
[2025-01-19 08:14:42 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][240/312]	eta 0:00:53 lr 0.002734	time 0.7150 (0.7489)	model_time 0.7146 (0.7434)	loss 3.6125 (3.3295)	grad_norm 0.7765 (1.3830/0.5681)	mem 34602MB
[2025-01-19 08:14:50 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][250/312]	eta 0:00:46 lr 0.002733	time 0.7148 (0.7491)	model_time 0.7144 (0.7438)	loss 3.1561 (3.3281)	grad_norm 1.9838 (1.3926/0.5680)	mem 34602MB
[2025-01-19 08:14:58 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][260/312]	eta 0:00:38 lr 0.002733	time 0.8274 (0.7494)	model_time 0.8272 (0.7443)	loss 3.5958 (3.3321)	grad_norm 0.8359 (1.3900/0.5639)	mem 34602MB
[2025-01-19 08:15:05 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][270/312]	eta 0:00:31 lr 0.002732	time 0.7540 (0.7497)	model_time 0.7536 (0.7448)	loss 3.6193 (3.3342)	grad_norm 1.2598 (1.3816/0.5569)	mem 34602MB
[2025-01-19 08:15:12 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][280/312]	eta 0:00:23 lr 0.002732	time 0.7172 (0.7491)	model_time 0.7170 (0.7443)	loss 2.7281 (3.3348)	grad_norm 1.0721 (1.3946/0.5705)	mem 34602MB
[2025-01-19 08:15:20 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][290/312]	eta 0:00:16 lr 0.002731	time 0.8112 (0.7490)	model_time 0.8111 (0.7444)	loss 3.4241 (3.3275)	grad_norm 1.6020 (1.3900/0.5671)	mem 34602MB
[2025-01-19 08:15:27 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][300/312]	eta 0:00:08 lr 0.002730	time 0.7130 (0.7484)	model_time 0.7129 (0.7439)	loss 2.6408 (3.3215)	grad_norm 1.5292 (1.3923/0.5677)	mem 34602MB
[2025-01-19 08:15:34 internimage_b_1k_224] (main.py 510): INFO Train: [114/300][310/312]	eta 0:00:01 lr 0.002730	time 0.7149 (0.7477)	model_time 0.7148 (0.7433)	loss 2.7557 (3.3255)	grad_norm 2.3435 (1.4175/0.5981)	mem 34602MB
[2025-01-19 08:15:35 internimage_b_1k_224] (main.py 519): INFO EPOCH 114 training takes 0:03:53
[2025-01-19 08:15:35 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_114.pth saving......
[2025-01-19 08:15:38 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_114.pth saved !!!
[2025-01-19 08:15:46 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.178 (7.178)	Loss 0.8905 (0.8905)	Acc@1 81.982 (81.982)	Acc@5 96.704 (96.704)	Mem 34602MB
[2025-01-19 08:15:49 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.920)	Loss 1.1723 (1.0229)	Acc@1 74.829 (78.831)	Acc@5 93.359 (94.869)	Mem 34602MB
[2025-01-19 08:15:49 internimage_b_1k_224] (main.py 575): INFO [Epoch:114] * Acc@1 78.801 Acc@5 94.954
[2025-01-19 08:15:49 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.8%
[2025-01-19 08:15:49 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.16%
[2025-01-19 08:15:58 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.107 (9.107)	Loss 0.6865 (0.6865)	Acc@1 82.788 (82.788)	Acc@5 96.973 (96.973)	Mem 34602MB
[2025-01-19 08:16:02 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.226)	Loss 1.0541 (0.8480)	Acc@1 74.341 (79.408)	Acc@5 92.676 (94.913)	Mem 34602MB
[2025-01-19 08:16:03 internimage_b_1k_224] (main.py 575): INFO [Epoch:114] * Acc@1 79.301 Acc@5 94.964
[2025-01-19 08:16:03 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.3%
[2025-01-19 08:16:03 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 08:16:06 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 08:16:06 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 79.30%
[2025-01-19 08:16:09 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][0/312]	eta 0:11:03 lr 0.002730	time 2.1260 (2.1260)	model_time 0.7365 (0.7365)	loss 2.5876 (2.5876)	grad_norm 2.3234 (2.3234/0.0000)	mem 34602MB
[2025-01-19 08:16:16 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][10/312]	eta 0:04:18 lr 0.002729	time 0.7214 (0.8554)	model_time 0.7212 (0.7288)	loss 2.1081 (2.9159)	grad_norm 1.3169 (1.4654/0.5102)	mem 34602MB
[2025-01-19 08:16:23 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][20/312]	eta 0:03:53 lr 0.002728	time 0.7444 (0.7981)	model_time 0.7442 (0.7317)	loss 2.8850 (3.0415)	grad_norm 1.2684 (1.5431/0.5546)	mem 34602MB
[2025-01-19 08:16:30 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][30/312]	eta 0:03:38 lr 0.002728	time 0.7295 (0.7749)	model_time 0.7294 (0.7297)	loss 3.3406 (3.1761)	grad_norm 2.1190 (1.5368/0.5587)	mem 34602MB
[2025-01-19 08:16:38 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][40/312]	eta 0:03:29 lr 0.002727	time 0.7253 (0.7692)	model_time 0.7249 (0.7350)	loss 3.7067 (3.2011)	grad_norm 1.5124 (1.4609/0.5504)	mem 34602MB
[2025-01-19 08:16:46 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][50/312]	eta 0:03:21 lr 0.002726	time 0.8042 (0.7680)	model_time 0.8040 (0.7404)	loss 2.6899 (3.1908)	grad_norm 1.4626 (1.4133/0.5240)	mem 34602MB
[2025-01-19 08:16:53 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][60/312]	eta 0:03:12 lr 0.002726	time 0.7157 (0.7656)	model_time 0.7155 (0.7425)	loss 3.6699 (3.2457)	grad_norm 0.5530 (1.3974/0.5206)	mem 34602MB
[2025-01-19 08:17:01 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][70/312]	eta 0:03:05 lr 0.002725	time 0.7290 (0.7645)	model_time 0.7289 (0.7446)	loss 2.4090 (3.2503)	grad_norm 1.3053 (1.4624/0.5608)	mem 34602MB
[2025-01-19 08:17:08 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][80/312]	eta 0:02:56 lr 0.002725	time 0.7168 (0.7624)	model_time 0.7166 (0.7449)	loss 3.5839 (3.3060)	grad_norm 1.3887 (1.4892/0.5970)	mem 34602MB
[2025-01-19 08:17:16 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][90/312]	eta 0:02:48 lr 0.002724	time 0.7146 (0.7597)	model_time 0.7145 (0.7441)	loss 2.3377 (3.2812)	grad_norm 1.3537 (1.4740/0.5780)	mem 34602MB
[2025-01-19 08:17:23 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][100/312]	eta 0:02:40 lr 0.002723	time 0.7250 (0.7575)	model_time 0.7249 (0.7434)	loss 2.5523 (3.2434)	grad_norm 2.3574 (1.4948/0.5979)	mem 34602MB
[2025-01-19 08:17:30 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][110/312]	eta 0:02:32 lr 0.002723	time 0.7213 (0.7551)	model_time 0.7211 (0.7423)	loss 3.8847 (3.2605)	grad_norm 0.9301 (1.4567/0.5935)	mem 34602MB
[2025-01-19 08:17:38 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][120/312]	eta 0:02:25 lr 0.002722	time 0.7166 (0.7557)	model_time 0.7162 (0.7439)	loss 2.3102 (3.2406)	grad_norm 1.3459 (1.4402/0.5854)	mem 34602MB
[2025-01-19 08:17:45 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][130/312]	eta 0:02:17 lr 0.002721	time 0.7177 (0.7534)	model_time 0.7175 (0.7425)	loss 3.4422 (3.2431)	grad_norm 1.3727 (1.4397/0.5845)	mem 34602MB
[2025-01-19 08:17:52 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][140/312]	eta 0:02:09 lr 0.002721	time 0.7135 (0.7517)	model_time 0.7130 (0.7415)	loss 2.3837 (3.2370)	grad_norm 1.3694 (1.4448/0.5855)	mem 34602MB
[2025-01-19 08:18:00 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][150/312]	eta 0:02:01 lr 0.002720	time 0.7183 (0.7498)	model_time 0.7179 (0.7402)	loss 3.7777 (3.2620)	grad_norm 0.8999 (1.4327/0.5784)	mem 34602MB
[2025-01-19 08:18:07 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][160/312]	eta 0:01:53 lr 0.002720	time 0.7187 (0.7495)	model_time 0.7186 (0.7405)	loss 4.1176 (3.2714)	grad_norm 0.9336 (1.4220/0.5745)	mem 34602MB
[2025-01-19 08:18:15 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][170/312]	eta 0:01:46 lr 0.002719	time 0.8236 (0.7499)	model_time 0.8232 (0.7415)	loss 2.5575 (3.2851)	grad_norm 0.8631 (1.3940/0.5712)	mem 34602MB
[2025-01-19 08:18:22 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][180/312]	eta 0:01:39 lr 0.002718	time 0.7173 (0.7503)	model_time 0.7169 (0.7423)	loss 3.9462 (3.2849)	grad_norm 1.8519 (1.3805/0.5691)	mem 34602MB
[2025-01-19 08:18:30 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][190/312]	eta 0:01:31 lr 0.002718	time 0.7200 (0.7504)	model_time 0.7196 (0.7428)	loss 3.3122 (3.2858)	grad_norm 1.3694 (1.3892/0.5806)	mem 34602MB
[2025-01-19 08:18:37 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][200/312]	eta 0:01:24 lr 0.002717	time 0.7158 (0.7504)	model_time 0.7156 (0.7431)	loss 2.1177 (3.2675)	grad_norm 0.9373 (1.3786/0.5757)	mem 34602MB
[2025-01-19 08:18:45 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][210/312]	eta 0:01:16 lr 0.002717	time 0.7352 (0.7496)	model_time 0.7351 (0.7426)	loss 3.0650 (3.2737)	grad_norm 1.3299 (1.3547/0.5745)	mem 34602MB
[2025-01-19 08:18:52 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][220/312]	eta 0:01:08 lr 0.002716	time 0.7220 (0.7495)	model_time 0.7219 (0.7429)	loss 3.0853 (3.2676)	grad_norm 1.9173 (1.3585/0.5753)	mem 34602MB
[2025-01-19 08:18:59 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][230/312]	eta 0:01:01 lr 0.002715	time 0.7266 (0.7493)	model_time 0.7261 (0.7429)	loss 3.5005 (3.2715)	grad_norm 2.0644 (1.3695/0.5763)	mem 34602MB
[2025-01-19 08:19:07 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][240/312]	eta 0:00:53 lr 0.002715	time 0.7345 (0.7486)	model_time 0.7344 (0.7425)	loss 3.7423 (3.2695)	grad_norm 1.6588 (1.3783/0.5764)	mem 34602MB
[2025-01-19 08:19:14 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][250/312]	eta 0:00:46 lr 0.002714	time 0.7211 (0.7477)	model_time 0.7209 (0.7418)	loss 2.4780 (3.2640)	grad_norm 1.1229 (1.3755/0.5698)	mem 34602MB
[2025-01-19 08:19:21 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][260/312]	eta 0:00:38 lr 0.002713	time 0.7250 (0.7468)	model_time 0.7248 (0.7411)	loss 2.4819 (3.2671)	grad_norm 1.0761 (1.3854/0.5652)	mem 34602MB
[2025-01-19 08:19:29 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][270/312]	eta 0:00:31 lr 0.002713	time 0.7139 (0.7460)	model_time 0.7135 (0.7405)	loss 3.4119 (3.2672)	grad_norm 0.8233 (1.3732/0.5612)	mem 34602MB
[2025-01-19 08:19:36 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][280/312]	eta 0:00:23 lr 0.002712	time 0.7176 (0.7461)	model_time 0.7175 (0.7408)	loss 3.8961 (3.2785)	grad_norm 1.6065 (1.3692/0.5537)	mem 34602MB
[2025-01-19 08:19:44 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][290/312]	eta 0:00:16 lr 0.002712	time 0.7955 (0.7464)	model_time 0.7953 (0.7413)	loss 3.8892 (3.2773)	grad_norm 1.2167 (1.3695/0.5460)	mem 34602MB
[2025-01-19 08:19:51 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][300/312]	eta 0:00:08 lr 0.002711	time 0.7145 (0.7467)	model_time 0.7144 (0.7418)	loss 2.4837 (3.2757)	grad_norm 1.0370 (1.3662/0.5397)	mem 34602MB
[2025-01-19 08:19:59 internimage_b_1k_224] (main.py 510): INFO Train: [115/300][310/312]	eta 0:00:01 lr 0.002710	time 0.8196 (0.7463)	model_time 0.8195 (0.7415)	loss 3.3541 (3.2822)	grad_norm 0.9696 (1.3717/0.5508)	mem 34602MB
[2025-01-19 08:19:59 internimage_b_1k_224] (main.py 519): INFO EPOCH 115 training takes 0:03:52
[2025-01-19 08:19:59 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_115.pth saving......
[2025-01-19 08:20:02 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_115.pth saved !!!
[2025-01-19 08:20:10 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.523 (7.523)	Loss 0.8391 (0.8391)	Acc@1 83.081 (83.081)	Acc@5 96.436 (96.436)	Mem 34602MB
[2025-01-19 08:20:13 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.962)	Loss 1.1575 (0.9911)	Acc@1 75.000 (79.348)	Acc@5 92.896 (94.838)	Mem 34602MB
[2025-01-19 08:20:13 internimage_b_1k_224] (main.py 575): INFO [Epoch:115] * Acc@1 79.207 Acc@5 94.856
[2025-01-19 08:20:13 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.2%
[2025-01-19 08:20:13 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 08:20:16 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 08:20:16 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.21%
[2025-01-19 08:20:24 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.778 (7.778)	Loss 0.6839 (0.6839)	Acc@1 82.837 (82.837)	Acc@5 96.973 (96.973)	Mem 34602MB
[2025-01-19 08:20:27 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.976)	Loss 1.0494 (0.8447)	Acc@1 74.365 (79.450)	Acc@5 92.773 (94.946)	Mem 34602MB
[2025-01-19 08:20:27 internimage_b_1k_224] (main.py 575): INFO [Epoch:115] * Acc@1 79.335 Acc@5 95.002
[2025-01-19 08:20:27 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.3%
[2025-01-19 08:20:27 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 08:20:31 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 08:20:31 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 79.33%
[2025-01-19 08:20:34 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][0/312]	eta 0:11:22 lr 0.002710	time 2.1881 (2.1881)	model_time 0.7560 (0.7560)	loss 3.3947 (3.3947)	grad_norm 1.0668 (1.0668/0.0000)	mem 34602MB
[2025-01-19 08:20:41 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][10/312]	eta 0:04:29 lr 0.002710	time 0.7271 (0.8919)	model_time 0.7269 (0.7615)	loss 3.1061 (3.2082)	grad_norm 1.8059 (1.5256/0.5109)	mem 34602MB
[2025-01-19 08:20:49 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][20/312]	eta 0:03:57 lr 0.002709	time 0.7179 (0.8145)	model_time 0.7174 (0.7460)	loss 4.1062 (3.3007)	grad_norm 1.2076 (1.5585/0.5806)	mem 34602MB
[2025-01-19 08:20:56 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][30/312]	eta 0:03:44 lr 0.002708	time 0.7154 (0.7944)	model_time 0.7153 (0.7479)	loss 3.1554 (3.3076)	grad_norm 2.1597 (1.5802/0.6077)	mem 34602MB
[2025-01-19 08:21:04 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][40/312]	eta 0:03:33 lr 0.002708	time 0.7173 (0.7865)	model_time 0.7172 (0.7513)	loss 3.4798 (3.2675)	grad_norm 1.4492 (1.5605/0.5759)	mem 34602MB
[2025-01-19 08:21:11 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][50/312]	eta 0:03:24 lr 0.002707	time 0.7353 (0.7797)	model_time 0.7352 (0.7513)	loss 2.5978 (3.2800)	grad_norm 1.5040 (1.4505/0.5732)	mem 34602MB
[2025-01-19 08:21:18 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][60/312]	eta 0:03:14 lr 0.002706	time 0.7364 (0.7713)	model_time 0.7360 (0.7475)	loss 2.9139 (3.2862)	grad_norm 0.9867 (1.4485/0.6069)	mem 34602MB
[2025-01-19 08:21:26 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][70/312]	eta 0:03:04 lr 0.002706	time 0.7139 (0.7642)	model_time 0.7138 (0.7436)	loss 3.0905 (3.3161)	grad_norm 1.3586 (1.4432/0.5793)	mem 34602MB
[2025-01-19 08:21:33 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][80/312]	eta 0:02:56 lr 0.002705	time 0.7211 (0.7600)	model_time 0.7206 (0.7420)	loss 3.5493 (3.3391)	grad_norm 0.7682 (1.4191/0.5636)	mem 34602MB
[2025-01-19 08:21:40 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][90/312]	eta 0:02:48 lr 0.002705	time 0.7210 (0.7580)	model_time 0.7206 (0.7419)	loss 3.0526 (3.3513)	grad_norm 1.1776 (1.4239/0.5686)	mem 34602MB
[2025-01-19 08:21:48 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][100/312]	eta 0:02:40 lr 0.002704	time 0.8020 (0.7591)	model_time 0.8016 (0.7445)	loss 2.3008 (3.3497)	grad_norm 1.6212 (1.3897/0.5640)	mem 34602MB
[2025-01-19 08:21:56 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][110/312]	eta 0:02:33 lr 0.002703	time 0.7171 (0.7588)	model_time 0.7169 (0.7456)	loss 3.8010 (3.3486)	grad_norm 1.0679 (1.3822/0.5508)	mem 34602MB
[2025-01-19 08:22:03 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][120/312]	eta 0:02:25 lr 0.002703	time 0.7970 (0.7600)	model_time 0.7965 (0.7478)	loss 3.1378 (3.3307)	grad_norm 1.0640 (1.4017/0.5862)	mem 34602MB
[2025-01-19 08:22:11 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][130/312]	eta 0:02:18 lr 0.002702	time 0.7202 (0.7606)	model_time 0.7201 (0.7493)	loss 3.6216 (3.3183)	grad_norm 0.8577 (1.3912/0.5880)	mem 34602MB
[2025-01-19 08:22:18 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][140/312]	eta 0:02:10 lr 0.002701	time 0.7163 (0.7585)	model_time 0.7159 (0.7479)	loss 2.6588 (3.3200)	grad_norm 1.4115 (1.3784/0.5810)	mem 34602MB
[2025-01-19 08:22:26 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][150/312]	eta 0:02:02 lr 0.002701	time 0.7140 (0.7570)	model_time 0.7138 (0.7471)	loss 3.0250 (3.2978)	grad_norm 1.0337 (1.3731/0.5679)	mem 34602MB
[2025-01-19 08:22:33 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][160/312]	eta 0:01:54 lr 0.002700	time 0.7163 (0.7559)	model_time 0.7161 (0.7466)	loss 3.7224 (3.3026)	grad_norm 1.5781 (1.3823/0.5745)	mem 34602MB
[2025-01-19 08:22:40 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][170/312]	eta 0:01:47 lr 0.002700	time 0.7162 (0.7545)	model_time 0.7158 (0.7458)	loss 3.2647 (3.3012)	grad_norm 1.3477 (1.4138/0.6094)	mem 34602MB
[2025-01-19 08:22:48 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][180/312]	eta 0:01:39 lr 0.002699	time 0.7375 (0.7531)	model_time 0.7374 (0.7448)	loss 3.4551 (3.3097)	grad_norm 2.2590 (1.4130/0.6130)	mem 34602MB
[2025-01-19 08:22:55 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][190/312]	eta 0:01:31 lr 0.002698	time 0.7181 (0.7519)	model_time 0.7179 (0.7440)	loss 4.0806 (3.3159)	grad_norm 1.3090 (1.4121/0.6021)	mem 34602MB
[2025-01-19 08:23:02 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][200/312]	eta 0:01:24 lr 0.002698	time 0.7148 (0.7506)	model_time 0.7146 (0.7432)	loss 3.2774 (3.3048)	grad_norm 1.4815 (1.3985/0.5928)	mem 34602MB
[2025-01-19 08:23:10 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][210/312]	eta 0:01:16 lr 0.002697	time 0.7404 (0.7503)	model_time 0.7399 (0.7432)	loss 2.3441 (3.3067)	grad_norm 1.2314 (1.4111/0.5951)	mem 34602MB
[2025-01-19 08:23:17 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][220/312]	eta 0:01:09 lr 0.002696	time 0.8039 (0.7505)	model_time 0.8035 (0.7436)	loss 2.5520 (3.3096)	grad_norm 1.3178 (1.4104/0.5896)	mem 34602MB
[2025-01-19 08:23:25 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][230/312]	eta 0:01:01 lr 0.002696	time 0.8021 (0.7516)	model_time 0.8020 (0.7450)	loss 2.4344 (3.3136)	grad_norm 1.4172 (1.4090/0.5789)	mem 34602MB
[2025-01-19 08:23:33 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][240/312]	eta 0:00:54 lr 0.002695	time 0.7963 (0.7513)	model_time 0.7962 (0.7450)	loss 3.6501 (3.3186)	grad_norm 1.5202 (1.3964/0.5726)	mem 34602MB
[2025-01-19 08:23:40 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][250/312]	eta 0:00:46 lr 0.002695	time 0.7159 (0.7521)	model_time 0.7155 (0.7460)	loss 3.4202 (3.3242)	grad_norm 1.2715 (1.3926/0.5660)	mem 34602MB
[2025-01-19 08:23:47 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][260/312]	eta 0:00:39 lr 0.002694	time 0.7157 (0.7510)	model_time 0.7156 (0.7451)	loss 2.9713 (3.3246)	grad_norm 1.1221 (1.4085/0.5903)	mem 34602MB
[2025-01-19 08:23:55 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][270/312]	eta 0:00:31 lr 0.002693	time 0.7095 (0.7506)	model_time 0.7093 (0.7450)	loss 3.9255 (3.3269)	grad_norm 1.1187 (1.4182/0.5939)	mem 34602MB
[2025-01-19 08:24:03 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][280/312]	eta 0:00:24 lr 0.002693	time 0.7174 (0.7512)	model_time 0.7170 (0.7457)	loss 4.0870 (3.3224)	grad_norm 1.7430 (1.4087/0.5893)	mem 34602MB
[2025-01-19 08:24:10 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][290/312]	eta 0:00:16 lr 0.002692	time 0.7213 (0.7505)	model_time 0.7212 (0.7452)	loss 3.3510 (3.3158)	grad_norm 2.0872 (1.4182/0.5898)	mem 34602MB
[2025-01-19 08:24:17 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][300/312]	eta 0:00:08 lr 0.002691	time 0.7166 (0.7495)	model_time 0.7165 (0.7444)	loss 2.7723 (3.3196)	grad_norm 1.2202 (1.4308/0.6024)	mem 34602MB
[2025-01-19 08:24:24 internimage_b_1k_224] (main.py 510): INFO Train: [116/300][310/312]	eta 0:00:01 lr 0.002691	time 0.7133 (0.7484)	model_time 0.7132 (0.7435)	loss 3.5404 (3.3227)	grad_norm 1.5872 (1.4224/0.6012)	mem 34602MB
[2025-01-19 08:24:25 internimage_b_1k_224] (main.py 519): INFO EPOCH 116 training takes 0:03:53
[2025-01-19 08:24:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_116.pth saving......
[2025-01-19 08:24:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_116.pth saved !!!
[2025-01-19 08:24:36 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.364 (7.364)	Loss 0.8436 (0.8436)	Acc@1 82.349 (82.349)	Acc@5 96.533 (96.533)	Mem 34602MB
[2025-01-19 08:24:39 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.938)	Loss 1.1939 (0.9993)	Acc@1 74.658 (79.233)	Acc@5 92.871 (94.973)	Mem 34602MB
[2025-01-19 08:24:39 internimage_b_1k_224] (main.py 575): INFO [Epoch:116] * Acc@1 79.149 Acc@5 94.984
[2025-01-19 08:24:39 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.1%
[2025-01-19 08:24:39 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.21%
[2025-01-19 08:24:48 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.332 (9.332)	Loss 0.6813 (0.6813)	Acc@1 83.057 (83.057)	Acc@5 96.997 (96.997)	Mem 34602MB
[2025-01-19 08:24:53 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.249)	Loss 1.0446 (0.8416)	Acc@1 74.561 (79.543)	Acc@5 92.871 (94.991)	Mem 34602MB
[2025-01-19 08:24:53 internimage_b_1k_224] (main.py 575): INFO [Epoch:116] * Acc@1 79.423 Acc@5 95.042
[2025-01-19 08:24:53 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.4%
[2025-01-19 08:24:53 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 08:24:57 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 08:24:57 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 79.42%
[2025-01-19 08:24:59 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][0/312]	eta 0:12:05 lr 0.002691	time 2.3238 (2.3238)	model_time 0.7519 (0.7519)	loss 3.9260 (3.9260)	grad_norm 1.1488 (1.1488/0.0000)	mem 34602MB
[2025-01-19 08:25:06 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][10/312]	eta 0:04:25 lr 0.002690	time 0.7469 (0.8779)	model_time 0.7465 (0.7347)	loss 2.3363 (3.4002)	grad_norm 1.0823 (1.0262/0.2432)	mem 34602MB
[2025-01-19 08:25:14 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][20/312]	eta 0:03:58 lr 0.002689	time 0.7246 (0.8174)	model_time 0.7245 (0.7422)	loss 2.7455 (3.4699)	grad_norm 1.4420 (1.1875/0.3825)	mem 34602MB
[2025-01-19 08:25:21 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][30/312]	eta 0:03:44 lr 0.002689	time 0.7508 (0.7953)	model_time 0.7504 (0.7442)	loss 1.9291 (3.3297)	grad_norm 2.1830 (1.4086/0.7504)	mem 34602MB
[2025-01-19 08:25:29 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][40/312]	eta 0:03:34 lr 0.002688	time 0.7209 (0.7894)	model_time 0.7207 (0.7507)	loss 3.4786 (3.3658)	grad_norm 0.8802 (1.3179/0.6984)	mem 34602MB
[2025-01-19 08:25:37 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][50/312]	eta 0:03:25 lr 0.002688	time 0.7286 (0.7841)	model_time 0.7284 (0.7530)	loss 3.3482 (3.3499)	grad_norm 2.3453 (1.3858/0.7230)	mem 34602MB
[2025-01-19 08:25:44 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][60/312]	eta 0:03:16 lr 0.002687	time 0.7950 (0.7812)	model_time 0.7948 (0.7551)	loss 4.0612 (3.3225)	grad_norm 2.0179 (1.3938/0.7067)	mem 34602MB
[2025-01-19 08:25:52 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][70/312]	eta 0:03:07 lr 0.002686	time 0.8007 (0.7753)	model_time 0.8006 (0.7528)	loss 3.5703 (3.3650)	grad_norm 1.8300 (1.3976/0.6688)	mem 34602MB
[2025-01-19 08:25:59 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][80/312]	eta 0:02:59 lr 0.002686	time 0.7222 (0.7724)	model_time 0.7220 (0.7526)	loss 3.8329 (3.3559)	grad_norm 0.8568 (1.4461/0.6931)	mem 34602MB
[2025-01-19 08:26:07 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][90/312]	eta 0:02:50 lr 0.002685	time 0.7247 (0.7701)	model_time 0.7242 (0.7525)	loss 3.3523 (3.3738)	grad_norm 0.8353 (1.4198/0.6667)	mem 34602MB
[2025-01-19 08:26:14 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][100/312]	eta 0:02:42 lr 0.002684	time 0.7160 (0.7659)	model_time 0.7156 (0.7500)	loss 3.5795 (3.3877)	grad_norm 1.2867 (1.3985/0.6380)	mem 34602MB
[2025-01-19 08:26:21 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][110/312]	eta 0:02:34 lr 0.002684	time 0.7334 (0.7625)	model_time 0.7329 (0.7481)	loss 3.4325 (3.3771)	grad_norm 2.0207 (1.3794/0.6337)	mem 34602MB
[2025-01-19 08:26:29 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][120/312]	eta 0:02:25 lr 0.002683	time 0.7259 (0.7598)	model_time 0.7257 (0.7465)	loss 3.3091 (3.3624)	grad_norm 1.7525 (1.3831/0.6213)	mem 34602MB
[2025-01-19 08:26:36 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][130/312]	eta 0:02:17 lr 0.002683	time 0.7188 (0.7575)	model_time 0.7184 (0.7452)	loss 3.4665 (3.3371)	grad_norm 0.7254 (1.3370/0.6191)	mem 34602MB
[2025-01-19 08:26:43 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][140/312]	eta 0:02:10 lr 0.002682	time 0.7194 (0.7565)	model_time 0.7193 (0.7450)	loss 2.3458 (3.3367)	grad_norm 1.0415 (1.3104/0.6053)	mem 34602MB
[2025-01-19 08:26:51 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][150/312]	eta 0:02:02 lr 0.002681	time 0.7272 (0.7568)	model_time 0.7270 (0.7460)	loss 3.4798 (3.3464)	grad_norm 4.5702 (1.3545/0.6820)	mem 34602MB
[2025-01-19 08:26:59 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][160/312]	eta 0:01:55 lr 0.002681	time 0.8033 (0.7577)	model_time 0.8028 (0.7476)	loss 2.9240 (3.3610)	grad_norm 0.7563 (1.3469/0.6691)	mem 34602MB
[2025-01-19 08:27:06 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][170/312]	eta 0:01:47 lr 0.002680	time 0.7185 (0.7587)	model_time 0.7183 (0.7492)	loss 4.1106 (3.3657)	grad_norm 2.3552 (1.3475/0.6694)	mem 34602MB
[2025-01-19 08:27:14 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][180/312]	eta 0:01:40 lr 0.002679	time 0.8086 (0.7588)	model_time 0.8085 (0.7498)	loss 3.5405 (3.3514)	grad_norm 1.6540 (1.3602/0.6744)	mem 34602MB
[2025-01-19 08:27:21 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][190/312]	eta 0:01:32 lr 0.002679	time 0.7964 (0.7580)	model_time 0.7962 (0.7495)	loss 2.7688 (3.3507)	grad_norm 1.3328 (1.3817/0.6706)	mem 34602MB
[2025-01-19 08:27:29 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][200/312]	eta 0:01:24 lr 0.002678	time 0.7183 (0.7574)	model_time 0.7178 (0.7492)	loss 3.3712 (3.3444)	grad_norm 2.4362 (1.3745/0.6616)	mem 34602MB
[2025-01-19 08:27:36 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][210/312]	eta 0:01:17 lr 0.002678	time 0.7149 (0.7568)	model_time 0.7147 (0.7490)	loss 2.4784 (3.3344)	grad_norm 1.1587 (1.3806/0.6570)	mem 34602MB
[2025-01-19 08:27:44 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][220/312]	eta 0:01:09 lr 0.002677	time 0.7158 (0.7553)	model_time 0.7153 (0.7479)	loss 3.6658 (3.3470)	grad_norm 1.8497 (1.3691/0.6481)	mem 34602MB
[2025-01-19 08:27:51 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][230/312]	eta 0:01:01 lr 0.002676	time 0.7212 (0.7546)	model_time 0.7211 (0.7474)	loss 2.5826 (3.3279)	grad_norm 1.9333 (1.3692/0.6407)	mem 34602MB
[2025-01-19 08:27:58 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][240/312]	eta 0:00:54 lr 0.002676	time 0.7148 (0.7533)	model_time 0.7147 (0.7465)	loss 3.2852 (3.3269)	grad_norm 1.0822 (1.3608/0.6303)	mem 34602MB
[2025-01-19 08:28:05 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][250/312]	eta 0:00:46 lr 0.002675	time 0.7346 (0.7525)	model_time 0.7344 (0.7459)	loss 4.0070 (3.3384)	grad_norm 1.0931 (1.3589/0.6208)	mem 34602MB
[2025-01-19 08:28:13 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][260/312]	eta 0:00:39 lr 0.002674	time 0.7170 (0.7522)	model_time 0.7168 (0.7458)	loss 3.2606 (3.3481)	grad_norm 2.7617 (1.3567/0.6196)	mem 34602MB
[2025-01-19 08:28:20 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][270/312]	eta 0:00:31 lr 0.002674	time 0.7142 (0.7522)	model_time 0.7141 (0.7460)	loss 3.0928 (3.3513)	grad_norm 0.8898 (1.3756/0.6403)	mem 34602MB
[2025-01-19 08:28:28 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][280/312]	eta 0:00:24 lr 0.002673	time 0.8034 (0.7528)	model_time 0.8032 (0.7469)	loss 3.6313 (3.3430)	grad_norm 0.9463 (1.3903/0.6459)	mem 34602MB
[2025-01-19 08:28:36 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][290/312]	eta 0:00:16 lr 0.002673	time 0.7265 (0.7524)	model_time 0.7261 (0.7466)	loss 3.3100 (3.3457)	grad_norm 0.6667 (1.3714/0.6446)	mem 34602MB
[2025-01-19 08:28:43 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][300/312]	eta 0:00:09 lr 0.002672	time 0.7873 (0.7526)	model_time 0.7872 (0.7471)	loss 2.9882 (3.3423)	grad_norm 0.8187 (1.3694/0.6443)	mem 34602MB
[2025-01-19 08:28:50 internimage_b_1k_224] (main.py 510): INFO Train: [117/300][310/312]	eta 0:00:01 lr 0.002671	time 0.7134 (0.7521)	model_time 0.7132 (0.7467)	loss 3.5002 (3.3352)	grad_norm 0.5064 (1.3886/0.6492)	mem 34602MB
[2025-01-19 08:28:51 internimage_b_1k_224] (main.py 519): INFO EPOCH 117 training takes 0:03:54
[2025-01-19 08:28:51 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_117.pth saving......
[2025-01-19 08:28:54 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_117.pth saved !!!
[2025-01-19 08:29:02 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.447 (7.447)	Loss 0.8358 (0.8358)	Acc@1 82.153 (82.153)	Acc@5 96.484 (96.484)	Mem 34602MB
[2025-01-19 08:29:05 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.943)	Loss 1.0935 (0.9573)	Acc@1 74.829 (79.124)	Acc@5 93.579 (95.033)	Mem 34602MB
[2025-01-19 08:29:05 internimage_b_1k_224] (main.py 575): INFO [Epoch:117] * Acc@1 79.037 Acc@5 95.032
[2025-01-19 08:29:05 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.0%
[2025-01-19 08:29:05 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.21%
[2025-01-19 08:29:14 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.044 (9.044)	Loss 0.6786 (0.6786)	Acc@1 83.057 (83.057)	Acc@5 97.021 (97.021)	Mem 34602MB
[2025-01-19 08:29:18 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.225)	Loss 1.0397 (0.8386)	Acc@1 74.634 (79.579)	Acc@5 92.944 (95.028)	Mem 34602MB
[2025-01-19 08:29:19 internimage_b_1k_224] (main.py 575): INFO [Epoch:117] * Acc@1 79.463 Acc@5 95.074
[2025-01-19 08:29:19 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.5%
[2025-01-19 08:29:19 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 08:29:22 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 08:29:22 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 79.46%
[2025-01-19 08:29:25 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][0/312]	eta 0:11:41 lr 0.002671	time 2.2476 (2.2476)	model_time 0.7320 (0.7320)	loss 3.8905 (3.8905)	grad_norm 1.9895 (1.9895/0.0000)	mem 34602MB
[2025-01-19 08:29:32 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][10/312]	eta 0:04:30 lr 0.002671	time 0.7165 (0.8944)	model_time 0.7163 (0.7564)	loss 3.4038 (3.4220)	grad_norm 1.1627 (1.3994/0.5368)	mem 34602MB
[2025-01-19 08:29:40 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][20/312]	eta 0:04:00 lr 0.002670	time 0.7216 (0.8249)	model_time 0.7212 (0.7524)	loss 3.8704 (3.2760)	grad_norm 1.1269 (1.3132/0.4424)	mem 34602MB
[2025-01-19 08:29:47 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][30/312]	eta 0:03:44 lr 0.002669	time 0.7965 (0.7958)	model_time 0.7963 (0.7466)	loss 2.4162 (3.3577)	grad_norm 1.1585 (1.4076/0.4611)	mem 34602MB
[2025-01-19 08:29:54 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][40/312]	eta 0:03:32 lr 0.002669	time 0.7238 (0.7814)	model_time 0.7233 (0.7441)	loss 3.7510 (3.3137)	grad_norm 1.1612 (1.4034/0.4310)	mem 34602MB
[2025-01-19 08:30:02 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][50/312]	eta 0:03:21 lr 0.002668	time 0.7225 (0.7702)	model_time 0.7223 (0.7401)	loss 3.5585 (3.3630)	grad_norm 1.2831 (1.3630/0.4242)	mem 34602MB
[2025-01-19 08:30:09 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][60/312]	eta 0:03:12 lr 0.002667	time 0.7216 (0.7631)	model_time 0.7211 (0.7379)	loss 3.3395 (3.3608)	grad_norm 2.6141 (1.3853/0.4672)	mem 34602MB
[2025-01-19 08:30:16 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][70/312]	eta 0:03:03 lr 0.002667	time 0.7178 (0.7595)	model_time 0.7176 (0.7378)	loss 3.3837 (3.3601)	grad_norm 1.1057 (1.3596/0.4617)	mem 34602MB
[2025-01-19 08:30:24 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][80/312]	eta 0:02:55 lr 0.002666	time 0.7196 (0.7582)	model_time 0.7192 (0.7391)	loss 3.8135 (3.3698)	grad_norm 1.3771 (1.4089/0.5033)	mem 34602MB
[2025-01-19 08:30:32 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][90/312]	eta 0:02:48 lr 0.002666	time 0.7888 (0.7597)	model_time 0.7887 (0.7427)	loss 2.3979 (3.3427)	grad_norm 1.6490 (1.4433/0.5159)	mem 34602MB
[2025-01-19 08:30:39 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][100/312]	eta 0:02:41 lr 0.002665	time 0.8167 (0.7595)	model_time 0.8162 (0.7441)	loss 3.6962 (3.3600)	grad_norm 1.4670 (1.4410/0.5273)	mem 34602MB
[2025-01-19 08:30:47 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][110/312]	eta 0:02:33 lr 0.002664	time 0.8025 (0.7595)	model_time 0.8023 (0.7455)	loss 2.7923 (3.3404)	grad_norm 1.8842 (1.4190/0.5186)	mem 34602MB
[2025-01-19 08:30:54 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][120/312]	eta 0:02:25 lr 0.002664	time 0.7169 (0.7566)	model_time 0.7168 (0.7437)	loss 4.0001 (3.3833)	grad_norm 1.4320 (1.4169/0.5123)	mem 34602MB
[2025-01-19 08:31:01 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][130/312]	eta 0:02:17 lr 0.002663	time 0.8213 (0.7560)	model_time 0.8208 (0.7441)	loss 3.4439 (3.3619)	grad_norm 0.7572 (1.4212/0.5086)	mem 34602MB
[2025-01-19 08:31:09 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][140/312]	eta 0:02:09 lr 0.002662	time 0.7202 (0.7546)	model_time 0.7200 (0.7435)	loss 3.1157 (3.3542)	grad_norm 0.6783 (1.4030/0.5058)	mem 34602MB
[2025-01-19 08:31:16 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][150/312]	eta 0:02:01 lr 0.002662	time 0.7237 (0.7527)	model_time 0.7233 (0.7423)	loss 3.3232 (3.3710)	grad_norm 2.0231 (1.4037/0.4985)	mem 34602MB
[2025-01-19 08:31:23 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][160/312]	eta 0:01:54 lr 0.002661	time 0.7334 (0.7516)	model_time 0.7329 (0.7418)	loss 4.1322 (3.3627)	grad_norm 1.6608 (1.4156/0.5060)	mem 34602MB
[2025-01-19 08:31:31 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][170/312]	eta 0:01:46 lr 0.002660	time 0.7151 (0.7504)	model_time 0.7149 (0.7412)	loss 3.2698 (3.3716)	grad_norm 0.8838 (1.3905/0.5036)	mem 34602MB
[2025-01-19 08:31:38 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][180/312]	eta 0:01:38 lr 0.002660	time 0.7270 (0.7490)	model_time 0.7269 (0.7403)	loss 3.7694 (3.3790)	grad_norm 2.4532 (1.3971/0.5093)	mem 34602MB
[2025-01-19 08:31:45 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][190/312]	eta 0:01:31 lr 0.002659	time 0.7178 (0.7485)	model_time 0.7177 (0.7402)	loss 2.2725 (3.3771)	grad_norm 1.0302 (1.3929/0.5011)	mem 34602MB
[2025-01-19 08:31:53 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][200/312]	eta 0:01:23 lr 0.002659	time 0.7950 (0.7485)	model_time 0.7945 (0.7406)	loss 3.4649 (3.3660)	grad_norm 1.8427 (1.3833/0.4960)	mem 34602MB
[2025-01-19 08:32:00 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][210/312]	eta 0:01:16 lr 0.002658	time 0.7926 (0.7489)	model_time 0.7924 (0.7413)	loss 2.8654 (3.3528)	grad_norm 2.2160 (1.3833/0.4917)	mem 34602MB
[2025-01-19 08:32:08 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][220/312]	eta 0:01:08 lr 0.002657	time 0.8042 (0.7498)	model_time 0.8038 (0.7426)	loss 3.5353 (3.3537)	grad_norm 2.2839 (1.4032/0.5036)	mem 34602MB
[2025-01-19 08:32:16 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][230/312]	eta 0:01:01 lr 0.002657	time 0.8044 (0.7498)	model_time 0.8042 (0.7429)	loss 2.9459 (3.3436)	grad_norm 1.4580 (1.4094/0.5031)	mem 34602MB
[2025-01-19 08:32:23 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][240/312]	eta 0:00:53 lr 0.002656	time 0.7264 (0.7492)	model_time 0.7260 (0.7426)	loss 3.6618 (3.3466)	grad_norm 0.9886 (1.4050/0.5024)	mem 34602MB
[2025-01-19 08:32:31 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][250/312]	eta 0:00:46 lr 0.002655	time 0.8565 (0.7493)	model_time 0.8563 (0.7430)	loss 3.4871 (3.3463)	grad_norm 3.7936 (1.4257/0.5325)	mem 34602MB
[2025-01-19 08:32:38 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][260/312]	eta 0:00:38 lr 0.002655	time 0.7234 (0.7491)	model_time 0.7230 (0.7430)	loss 4.0245 (3.3501)	grad_norm 1.1950 (1.4420/0.5515)	mem 34602MB
[2025-01-19 08:32:45 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][270/312]	eta 0:00:31 lr 0.002654	time 0.7139 (0.7482)	model_time 0.7137 (0.7422)	loss 3.0140 (3.3462)	grad_norm 1.3223 (1.4399/0.5472)	mem 34602MB
[2025-01-19 08:32:53 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][280/312]	eta 0:00:23 lr 0.002654	time 0.7224 (0.7479)	model_time 0.7220 (0.7421)	loss 3.6311 (3.3410)	grad_norm 2.1400 (1.4400/0.5432)	mem 34602MB
[2025-01-19 08:33:00 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][290/312]	eta 0:00:16 lr 0.002653	time 0.7294 (0.7471)	model_time 0.7156 (0.7415)	loss 2.9140 (3.3363)	grad_norm 1.0906 (1.4377/0.5395)	mem 34602MB
[2025-01-19 08:33:07 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][300/312]	eta 0:00:08 lr 0.002652	time 0.7135 (0.7464)	model_time 0.7134 (0.7409)	loss 3.3995 (3.3420)	grad_norm 0.8817 (1.4252/0.5348)	mem 34602MB
[2025-01-19 08:33:15 internimage_b_1k_224] (main.py 510): INFO Train: [118/300][310/312]	eta 0:00:01 lr 0.002652	time 0.7119 (0.7462)	model_time 0.7118 (0.7410)	loss 2.0804 (3.3301)	grad_norm 0.7967 (1.4222/0.5319)	mem 34602MB
[2025-01-19 08:33:15 internimage_b_1k_224] (main.py 519): INFO EPOCH 118 training takes 0:03:52
[2025-01-19 08:33:15 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_118.pth saving......
[2025-01-19 08:33:18 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_118.pth saved !!!
[2025-01-19 08:33:26 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.530 (7.530)	Loss 0.8452 (0.8452)	Acc@1 82.422 (82.422)	Acc@5 96.533 (96.533)	Mem 34602MB
[2025-01-19 08:33:29 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.964)	Loss 1.1546 (0.9939)	Acc@1 75.513 (79.142)	Acc@5 93.335 (94.955)	Mem 34602MB
[2025-01-19 08:33:29 internimage_b_1k_224] (main.py 575): INFO [Epoch:118] * Acc@1 79.141 Acc@5 95.010
[2025-01-19 08:33:29 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.1%
[2025-01-19 08:33:29 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.21%
[2025-01-19 08:33:38 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.167 (9.167)	Loss 0.6761 (0.6761)	Acc@1 83.105 (83.105)	Acc@5 97.070 (97.070)	Mem 34602MB
[2025-01-19 08:33:43 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.243)	Loss 1.0353 (0.8357)	Acc@1 74.658 (79.650)	Acc@5 93.042 (95.059)	Mem 34602MB
[2025-01-19 08:33:43 internimage_b_1k_224] (main.py 575): INFO [Epoch:118] * Acc@1 79.533 Acc@5 95.108
[2025-01-19 08:33:43 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.5%
[2025-01-19 08:33:43 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 08:33:47 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 08:33:47 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 79.53%
[2025-01-19 08:33:50 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][0/312]	eta 0:12:40 lr 0.002652	time 2.4385 (2.4385)	model_time 0.7712 (0.7712)	loss 3.5114 (3.5114)	grad_norm 0.9984 (0.9984/0.0000)	mem 34602MB
[2025-01-19 08:33:57 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][10/312]	eta 0:04:34 lr 0.002651	time 0.8000 (0.9077)	model_time 0.7999 (0.7558)	loss 4.1159 (3.5734)	grad_norm 0.8855 (1.3642/0.4121)	mem 34602MB
[2025-01-19 08:34:05 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][20/312]	eta 0:04:05 lr 0.002650	time 0.7932 (0.8415)	model_time 0.7929 (0.7617)	loss 3.2662 (3.4091)	grad_norm 1.4093 (1.2688/0.4489)	mem 34602MB
[2025-01-19 08:34:12 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][30/312]	eta 0:03:48 lr 0.002650	time 0.7159 (0.8116)	model_time 0.7155 (0.7575)	loss 3.7699 (3.4242)	grad_norm 2.0151 (1.3101/0.4270)	mem 34602MB
[2025-01-19 08:34:20 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][40/312]	eta 0:03:36 lr 0.002649	time 0.7342 (0.7964)	model_time 0.7337 (0.7554)	loss 2.4134 (3.3662)	grad_norm 1.1226 (1.2998/0.4073)	mem 34602MB
[2025-01-19 08:34:27 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][50/312]	eta 0:03:25 lr 0.002648	time 0.7337 (0.7839)	model_time 0.7333 (0.7509)	loss 3.1062 (3.4129)	grad_norm 0.8849 (1.3012/0.4103)	mem 34602MB
[2025-01-19 08:34:35 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][60/312]	eta 0:03:16 lr 0.002648	time 0.7253 (0.7791)	model_time 0.7251 (0.7514)	loss 2.8701 (3.3949)	grad_norm 1.2315 (1.2405/0.4092)	mem 34602MB
[2025-01-19 08:34:42 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][70/312]	eta 0:03:07 lr 0.002647	time 0.7181 (0.7739)	model_time 0.7177 (0.7500)	loss 3.5530 (3.3369)	grad_norm 1.6248 (1.2287/0.3949)	mem 34602MB
[2025-01-19 08:34:50 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][80/312]	eta 0:02:58 lr 0.002646	time 0.7186 (0.7698)	model_time 0.7184 (0.7489)	loss 3.1215 (3.3057)	grad_norm 0.9776 (1.2932/0.4971)	mem 34602MB
[2025-01-19 08:34:57 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][90/312]	eta 0:02:49 lr 0.002646	time 0.7172 (0.7651)	model_time 0.7168 (0.7464)	loss 3.6464 (3.3165)	grad_norm 0.8825 (1.2852/0.4832)	mem 34602MB
[2025-01-19 08:35:04 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][100/312]	eta 0:02:41 lr 0.002645	time 0.7278 (0.7614)	model_time 0.7276 (0.7445)	loss 2.8808 (3.3140)	grad_norm 1.2161 (1.3084/0.4947)	mem 34602MB
[2025-01-19 08:35:11 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][110/312]	eta 0:02:33 lr 0.002645	time 0.7221 (0.7583)	model_time 0.7217 (0.7429)	loss 3.4247 (3.3259)	grad_norm 1.4259 (1.3040/0.4852)	mem 34602MB
[2025-01-19 08:35:19 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][120/312]	eta 0:02:25 lr 0.002644	time 0.8023 (0.7568)	model_time 0.8021 (0.7427)	loss 3.4348 (3.3116)	grad_norm 2.8428 (1.3305/0.5004)	mem 34602MB
[2025-01-19 08:35:26 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][130/312]	eta 0:02:17 lr 0.002643	time 0.7947 (0.7574)	model_time 0.7943 (0.7443)	loss 3.3198 (3.3081)	grad_norm 0.9657 (1.3496/0.5111)	mem 34602MB
[2025-01-19 08:35:34 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][140/312]	eta 0:02:10 lr 0.002643	time 0.7937 (0.7582)	model_time 0.7935 (0.7460)	loss 2.6374 (3.3130)	grad_norm 1.2302 (1.3474/0.5210)	mem 34602MB
[2025-01-19 08:35:42 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][150/312]	eta 0:02:02 lr 0.002642	time 0.7299 (0.7572)	model_time 0.7295 (0.7458)	loss 3.3923 (3.3190)	grad_norm 2.0268 (1.3662/0.5212)	mem 34602MB
[2025-01-19 08:35:49 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][160/312]	eta 0:01:55 lr 0.002641	time 0.7126 (0.7578)	model_time 0.7124 (0.7471)	loss 2.5800 (3.3277)	grad_norm 1.5698 (1.4000/0.5338)	mem 34602MB
[2025-01-19 08:35:57 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][170/312]	eta 0:01:47 lr 0.002641	time 0.7228 (0.7567)	model_time 0.7227 (0.7466)	loss 4.0608 (3.3225)	grad_norm 3.6534 (1.4228/0.5658)	mem 34602MB
[2025-01-19 08:36:04 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][180/312]	eta 0:01:39 lr 0.002640	time 0.7168 (0.7562)	model_time 0.7167 (0.7466)	loss 3.7693 (3.3287)	grad_norm 1.2604 (1.4254/0.5598)	mem 34602MB
[2025-01-19 08:36:11 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][190/312]	eta 0:01:32 lr 0.002640	time 0.7361 (0.7553)	model_time 0.7356 (0.7462)	loss 3.6649 (3.3382)	grad_norm 0.7629 (1.4068/0.5555)	mem 34602MB
[2025-01-19 08:36:19 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][200/312]	eta 0:01:24 lr 0.002639	time 0.7250 (0.7543)	model_time 0.7245 (0.7456)	loss 3.3363 (3.3456)	grad_norm 0.7906 (1.3950/0.5526)	mem 34602MB
[2025-01-19 08:36:26 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][210/312]	eta 0:01:16 lr 0.002638	time 0.7145 (0.7530)	model_time 0.7140 (0.7448)	loss 2.5913 (3.3357)	grad_norm 2.2460 (1.3937/0.5465)	mem 34602MB
[2025-01-19 08:36:33 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][220/312]	eta 0:01:09 lr 0.002638	time 0.7283 (0.7518)	model_time 0.7281 (0.7439)	loss 3.3098 (3.3423)	grad_norm 1.3240 (1.3933/0.5395)	mem 34602MB
[2025-01-19 08:36:41 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][230/312]	eta 0:01:01 lr 0.002637	time 0.7162 (0.7506)	model_time 0.7161 (0.7430)	loss 3.2571 (3.3438)	grad_norm 2.8970 (1.4270/0.5622)	mem 34602MB
[2025-01-19 08:36:48 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][240/312]	eta 0:00:54 lr 0.002636	time 0.8054 (0.7506)	model_time 0.8050 (0.7433)	loss 2.9874 (3.3414)	grad_norm 0.6256 (1.4274/0.5592)	mem 34602MB
[2025-01-19 08:36:56 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][250/312]	eta 0:00:46 lr 0.002636	time 0.8175 (0.7508)	model_time 0.8173 (0.7438)	loss 3.6204 (3.3347)	grad_norm 0.7037 (1.4062/0.5603)	mem 34602MB
[2025-01-19 08:37:03 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][260/312]	eta 0:00:39 lr 0.002635	time 0.7162 (0.7515)	model_time 0.7158 (0.7447)	loss 3.5131 (3.3411)	grad_norm 0.9616 (1.4115/0.5677)	mem 34602MB
[2025-01-19 08:37:11 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][270/312]	eta 0:00:31 lr 0.002635	time 0.7178 (0.7513)	model_time 0.7174 (0.7448)	loss 4.0859 (3.3493)	grad_norm 1.2682 (1.3953/0.5654)	mem 34602MB
[2025-01-19 08:37:18 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][280/312]	eta 0:00:24 lr 0.002634	time 0.7151 (0.7517)	model_time 0.7150 (0.7454)	loss 3.7650 (3.3443)	grad_norm 0.9820 (1.3946/0.5637)	mem 34602MB
[2025-01-19 08:37:26 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][290/312]	eta 0:00:16 lr 0.002633	time 0.7166 (0.7510)	model_time 0.7164 (0.7449)	loss 3.6607 (3.3470)	grad_norm 1.3320 (1.3870/0.5584)	mem 34602MB
[2025-01-19 08:37:33 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][300/312]	eta 0:00:09 lr 0.002633	time 0.7098 (0.7508)	model_time 0.7097 (0.7449)	loss 2.9044 (3.3458)	grad_norm 1.8512 (1.3879/0.5553)	mem 34602MB
[2025-01-19 08:37:41 internimage_b_1k_224] (main.py 510): INFO Train: [119/300][310/312]	eta 0:00:01 lr 0.002632	time 0.9681 (0.7507)	model_time 0.9680 (0.7450)	loss 2.9446 (3.3379)	grad_norm 1.4293 (1.3848/0.5543)	mem 34602MB
[2025-01-19 08:37:41 internimage_b_1k_224] (main.py 519): INFO EPOCH 119 training takes 0:03:54
[2025-01-19 08:37:41 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_119.pth saving......
[2025-01-19 08:37:44 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_119.pth saved !!!
[2025-01-19 08:37:52 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.411 (7.411)	Loss 0.8227 (0.8227)	Acc@1 82.153 (82.153)	Acc@5 96.606 (96.606)	Mem 34602MB
[2025-01-19 08:37:55 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.935)	Loss 1.1220 (0.9523)	Acc@1 75.146 (79.188)	Acc@5 92.969 (94.984)	Mem 34602MB
[2025-01-19 08:37:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:119] * Acc@1 79.069 Acc@5 95.010
[2025-01-19 08:37:55 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.1%
[2025-01-19 08:37:55 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.21%
[2025-01-19 08:38:04 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.902 (8.902)	Loss 0.6737 (0.6737)	Acc@1 83.154 (83.154)	Acc@5 97.144 (97.144)	Mem 34602MB
[2025-01-19 08:38:08 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.210)	Loss 1.0311 (0.8329)	Acc@1 74.756 (79.732)	Acc@5 93.091 (95.108)	Mem 34602MB
[2025-01-19 08:38:09 internimage_b_1k_224] (main.py 575): INFO [Epoch:119] * Acc@1 79.607 Acc@5 95.154
[2025-01-19 08:38:09 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.6%
[2025-01-19 08:38:09 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 08:38:13 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 08:38:13 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 79.61%
[2025-01-19 08:38:15 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][0/312]	eta 0:12:02 lr 0.002632	time 2.3150 (2.3150)	model_time 0.7487 (0.7487)	loss 3.9008 (3.9008)	grad_norm 0.9687 (0.9687/0.0000)	mem 34602MB
[2025-01-19 08:38:22 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][10/312]	eta 0:04:25 lr 0.002631	time 0.7209 (0.8796)	model_time 0.7208 (0.7368)	loss 3.8236 (3.2784)	grad_norm 1.1611 (1.5558/0.5961)	mem 34602MB
[2025-01-19 08:38:30 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][20/312]	eta 0:03:56 lr 0.002631	time 0.7318 (0.8083)	model_time 0.7317 (0.7333)	loss 3.3004 (3.2443)	grad_norm 1.3698 (1.7289/0.6938)	mem 34602MB
[2025-01-19 08:38:37 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][30/312]	eta 0:03:40 lr 0.002630	time 0.7188 (0.7817)	model_time 0.7186 (0.7308)	loss 2.1322 (3.2264)	grad_norm 1.1377 (1.6455/0.7043)	mem 34602MB
[2025-01-19 08:38:44 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][40/312]	eta 0:03:28 lr 0.002629	time 0.7183 (0.7679)	model_time 0.7179 (0.7293)	loss 3.2552 (3.2537)	grad_norm 1.3544 (1.4820/0.6821)	mem 34602MB
[2025-01-19 08:38:52 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][50/312]	eta 0:03:20 lr 0.002629	time 0.7322 (0.7635)	model_time 0.7320 (0.7324)	loss 3.2545 (3.2476)	grad_norm 2.8247 (1.4869/0.6834)	mem 34602MB
[2025-01-19 08:38:59 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][60/312]	eta 0:03:12 lr 0.002628	time 0.7174 (0.7639)	model_time 0.7169 (0.7378)	loss 3.8839 (3.2303)	grad_norm 1.1195 (1.4825/0.6612)	mem 34602MB
[2025-01-19 08:39:07 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][70/312]	eta 0:03:05 lr 0.002627	time 0.8085 (0.7658)	model_time 0.8081 (0.7434)	loss 4.1089 (3.2566)	grad_norm 1.0576 (1.4503/0.6406)	mem 34602MB
[2025-01-19 08:39:15 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][80/312]	eta 0:02:57 lr 0.002627	time 0.7218 (0.7640)	model_time 0.7216 (0.7443)	loss 3.5811 (3.2479)	grad_norm 2.9897 (1.4382/0.6444)	mem 34602MB
[2025-01-19 08:39:22 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][90/312]	eta 0:02:49 lr 0.002626	time 0.8012 (0.7642)	model_time 0.8010 (0.7466)	loss 3.8176 (3.2626)	grad_norm 1.0797 (1.4322/0.6379)	mem 34602MB
[2025-01-19 08:39:30 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][100/312]	eta 0:02:41 lr 0.002626	time 0.7285 (0.7623)	model_time 0.7284 (0.7464)	loss 3.9252 (3.2690)	grad_norm 3.7018 (1.4345/0.6723)	mem 34602MB
[2025-01-19 08:39:37 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][110/312]	eta 0:02:33 lr 0.002625	time 0.7323 (0.7616)	model_time 0.7319 (0.7471)	loss 3.2784 (3.2725)	grad_norm 1.8261 (1.4332/0.6637)	mem 34602MB
[2025-01-19 08:39:45 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][120/312]	eta 0:02:25 lr 0.002624	time 0.7152 (0.7602)	model_time 0.7151 (0.7469)	loss 3.4608 (3.2744)	grad_norm 2.2414 (1.4255/0.6481)	mem 34602MB
[2025-01-19 08:39:52 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][130/312]	eta 0:02:17 lr 0.002624	time 0.7141 (0.7581)	model_time 0.7137 (0.7457)	loss 2.8664 (3.2723)	grad_norm 2.2239 (1.4617/0.6451)	mem 34602MB
[2025-01-19 08:39:59 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][140/312]	eta 0:02:09 lr 0.002623	time 0.7137 (0.7556)	model_time 0.7135 (0.7441)	loss 3.5564 (3.2853)	grad_norm 1.1780 (1.4578/0.6301)	mem 34602MB
[2025-01-19 08:40:06 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][150/312]	eta 0:02:02 lr 0.002622	time 0.7339 (0.7535)	model_time 0.7334 (0.7428)	loss 4.0777 (3.3036)	grad_norm 1.2519 (1.4627/0.6209)	mem 34602MB
[2025-01-19 08:40:14 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][160/312]	eta 0:01:54 lr 0.002622	time 0.7160 (0.7517)	model_time 0.7156 (0.7416)	loss 3.1195 (3.2813)	grad_norm 1.0888 (1.4761/0.6237)	mem 34602MB
[2025-01-19 08:40:21 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][170/312]	eta 0:01:46 lr 0.002621	time 0.7238 (0.7511)	model_time 0.7237 (0.7416)	loss 3.3501 (3.2894)	grad_norm 0.9245 (1.4485/0.6173)	mem 34602MB
[2025-01-19 08:40:29 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][180/312]	eta 0:01:39 lr 0.002620	time 0.7212 (0.7518)	model_time 0.7211 (0.7428)	loss 3.2074 (3.2825)	grad_norm 2.7405 (1.4761/0.6575)	mem 34602MB
[2025-01-19 08:40:36 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][190/312]	eta 0:01:31 lr 0.002620	time 0.8114 (0.7526)	model_time 0.8112 (0.7440)	loss 2.4556 (3.2804)	grad_norm 0.7363 (1.4964/0.6648)	mem 34602MB
[2025-01-19 08:40:44 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][200/312]	eta 0:01:24 lr 0.002619	time 0.7190 (0.7522)	model_time 0.7186 (0.7440)	loss 3.4400 (3.2976)	grad_norm 1.1639 (1.5030/0.6613)	mem 34602MB
[2025-01-19 08:40:52 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][210/312]	eta 0:01:16 lr 0.002619	time 0.8043 (0.7528)	model_time 0.8041 (0.7450)	loss 2.2800 (3.3115)	grad_norm 1.7203 (1.4995/0.6510)	mem 34602MB
[2025-01-19 08:40:59 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][220/312]	eta 0:01:09 lr 0.002618	time 0.7224 (0.7524)	model_time 0.7220 (0.7450)	loss 3.4462 (3.3135)	grad_norm 3.3614 (1.5079/0.6530)	mem 34602MB
[2025-01-19 08:41:07 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][230/312]	eta 0:01:01 lr 0.002617	time 0.7350 (0.7524)	model_time 0.7348 (0.7453)	loss 3.3726 (3.3158)	grad_norm 0.7708 (1.5094/0.6678)	mem 34602MB
[2025-01-19 08:41:14 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][240/312]	eta 0:00:54 lr 0.002617	time 0.7176 (0.7524)	model_time 0.7174 (0.7455)	loss 2.4924 (3.3076)	grad_norm 0.7598 (1.5015/0.6613)	mem 34602MB
[2025-01-19 08:41:21 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][250/312]	eta 0:00:46 lr 0.002616	time 0.8442 (0.7519)	model_time 0.8440 (0.7453)	loss 3.2118 (3.3172)	grad_norm 1.4631 (1.4934/0.6513)	mem 34602MB
[2025-01-19 08:41:29 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][260/312]	eta 0:00:39 lr 0.002615	time 0.7146 (0.7509)	model_time 0.7142 (0.7445)	loss 3.6065 (3.3180)	grad_norm 0.6533 (1.4987/0.6474)	mem 34602MB
[2025-01-19 08:41:36 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][270/312]	eta 0:00:31 lr 0.002615	time 0.7259 (0.7500)	model_time 0.7255 (0.7438)	loss 2.5145 (3.3169)	grad_norm 0.8637 (1.4888/0.6405)	mem 34602MB
[2025-01-19 08:41:43 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][280/312]	eta 0:00:23 lr 0.002614	time 0.7157 (0.7491)	model_time 0.7155 (0.7432)	loss 2.8389 (3.3263)	grad_norm 1.4379 (1.4854/0.6353)	mem 34602MB
[2025-01-19 08:41:51 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][290/312]	eta 0:00:16 lr 0.002613	time 0.7181 (0.7488)	model_time 0.7177 (0.7430)	loss 3.8231 (3.3283)	grad_norm 1.5560 (1.4991/0.6525)	mem 34602MB
[2025-01-19 08:41:58 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][300/312]	eta 0:00:08 lr 0.002613	time 0.7149 (0.7488)	model_time 0.7148 (0.7432)	loss 2.4407 (3.3246)	grad_norm 1.3391 (1.4840/0.6476)	mem 34602MB
[2025-01-19 08:42:06 internimage_b_1k_224] (main.py 510): INFO Train: [120/300][310/312]	eta 0:00:01 lr 0.002612	time 0.7201 (0.7488)	model_time 0.7201 (0.7434)	loss 2.2660 (3.3100)	grad_norm 0.6362 (1.4777/0.6510)	mem 34602MB
[2025-01-19 08:42:06 internimage_b_1k_224] (main.py 519): INFO EPOCH 120 training takes 0:03:53
[2025-01-19 08:42:06 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_120.pth saving......
[2025-01-19 08:42:10 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_120.pth saved !!!
[2025-01-19 08:42:17 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.468 (7.468)	Loss 0.8287 (0.8287)	Acc@1 82.983 (82.983)	Acc@5 96.826 (96.826)	Mem 34602MB
[2025-01-19 08:42:20 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.950)	Loss 1.1479 (0.9755)	Acc@1 75.342 (79.548)	Acc@5 93.237 (95.148)	Mem 34602MB
[2025-01-19 08:42:20 internimage_b_1k_224] (main.py 575): INFO [Epoch:120] * Acc@1 79.453 Acc@5 95.196
[2025-01-19 08:42:20 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.5%
[2025-01-19 08:42:20 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 08:42:24 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 08:42:24 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.45%
[2025-01-19 08:42:31 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.452 (7.452)	Loss 0.6716 (0.6716)	Acc@1 83.252 (83.252)	Acc@5 97.119 (97.119)	Mem 34602MB
[2025-01-19 08:42:34 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.952)	Loss 1.0271 (0.8302)	Acc@1 74.854 (79.816)	Acc@5 93.115 (95.137)	Mem 34602MB
[2025-01-19 08:42:34 internimage_b_1k_224] (main.py 575): INFO [Epoch:120] * Acc@1 79.685 Acc@5 95.188
[2025-01-19 08:42:34 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.7%
[2025-01-19 08:42:34 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 08:42:38 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 08:42:38 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 79.68%
[2025-01-19 08:42:40 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][0/312]	eta 0:10:45 lr 0.002612	time 2.0676 (2.0676)	model_time 0.7499 (0.7499)	loss 3.3212 (3.3212)	grad_norm 0.7247 (0.7247/0.0000)	mem 34602MB
[2025-01-19 08:42:48 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][10/312]	eta 0:04:23 lr 0.002611	time 0.7289 (0.8728)	model_time 0.7288 (0.7526)	loss 3.8851 (3.4482)	grad_norm 1.3043 (1.2110/0.3503)	mem 34602MB
[2025-01-19 08:42:56 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][20/312]	eta 0:04:01 lr 0.002611	time 0.7208 (0.8268)	model_time 0.7206 (0.7637)	loss 3.6095 (3.3637)	grad_norm 1.1753 (1.2725/0.3780)	mem 34602MB
[2025-01-19 08:43:03 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][30/312]	eta 0:03:44 lr 0.002610	time 0.7172 (0.7973)	model_time 0.7171 (0.7544)	loss 3.4645 (3.3037)	grad_norm 1.7307 (1.3801/0.5057)	mem 34602MB
[2025-01-19 08:43:11 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][40/312]	eta 0:03:34 lr 0.002610	time 0.7450 (0.7876)	model_time 0.7445 (0.7551)	loss 3.1695 (3.2931)	grad_norm 2.6435 (1.4499/0.5323)	mem 34602MB
[2025-01-19 08:43:18 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][50/312]	eta 0:03:24 lr 0.002609	time 0.7172 (0.7793)	model_time 0.7170 (0.7530)	loss 2.9378 (3.3365)	grad_norm 0.8240 (1.4999/0.5775)	mem 34602MB
[2025-01-19 08:43:26 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][60/312]	eta 0:03:14 lr 0.002608	time 0.7212 (0.7727)	model_time 0.7211 (0.7507)	loss 2.4452 (3.2878)	grad_norm 1.6532 (1.4690/0.5643)	mem 34602MB
[2025-01-19 08:43:33 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][70/312]	eta 0:03:05 lr 0.002608	time 0.7263 (0.7660)	model_time 0.7261 (0.7470)	loss 3.3243 (3.2909)	grad_norm 1.9520 (1.4396/0.5489)	mem 34602MB
[2025-01-19 08:43:40 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][80/312]	eta 0:02:56 lr 0.002607	time 0.7225 (0.7612)	model_time 0.7223 (0.7445)	loss 3.8608 (3.2718)	grad_norm 1.9023 (1.4147/0.5289)	mem 34602MB
[2025-01-19 08:43:47 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][90/312]	eta 0:02:48 lr 0.002606	time 0.7453 (0.7577)	model_time 0.7448 (0.7428)	loss 2.6027 (3.2610)	grad_norm 1.9002 (1.3893/0.5173)	mem 34602MB
[2025-01-19 08:43:55 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][100/312]	eta 0:02:40 lr 0.002606	time 0.7201 (0.7562)	model_time 0.7196 (0.7428)	loss 3.7711 (3.2881)	grad_norm 0.6911 (1.3852/0.5183)	mem 34602MB
[2025-01-19 08:44:02 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][110/312]	eta 0:02:32 lr 0.002605	time 0.8004 (0.7567)	model_time 0.8003 (0.7445)	loss 2.5301 (3.2875)	grad_norm 0.7435 (1.3744/0.5050)	mem 34602MB
[2025-01-19 08:44:10 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][120/312]	eta 0:02:25 lr 0.002604	time 0.8131 (0.7577)	model_time 0.8126 (0.7465)	loss 3.7420 (3.2967)	grad_norm 0.8717 (1.3574/0.5090)	mem 34602MB
[2025-01-19 08:44:18 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][130/312]	eta 0:02:17 lr 0.002604	time 0.7378 (0.7575)	model_time 0.7377 (0.7471)	loss 3.6779 (3.3207)	grad_norm 1.7227 (1.3434/0.4983)	mem 34602MB
[2025-01-19 08:44:25 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][140/312]	eta 0:02:10 lr 0.002603	time 0.7157 (0.7583)	model_time 0.7152 (0.7485)	loss 4.0920 (3.3166)	grad_norm 0.9431 (1.3398/0.4947)	mem 34602MB
[2025-01-19 08:44:33 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][150/312]	eta 0:02:02 lr 0.002603	time 0.7164 (0.7569)	model_time 0.7162 (0.7478)	loss 3.7108 (3.3037)	grad_norm 1.3903 (1.3464/0.5148)	mem 34602MB
[2025-01-19 08:44:40 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][160/312]	eta 0:01:55 lr 0.002602	time 0.7900 (0.7568)	model_time 0.7898 (0.7482)	loss 2.0496 (3.3036)	grad_norm 2.5118 (1.3499/0.5126)	mem 34602MB
[2025-01-19 08:44:48 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][170/312]	eta 0:01:47 lr 0.002601	time 0.7186 (0.7559)	model_time 0.7185 (0.7479)	loss 3.4489 (3.3039)	grad_norm 2.7984 (1.3772/0.5286)	mem 34602MB
[2025-01-19 08:44:55 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][180/312]	eta 0:01:39 lr 0.002601	time 0.7147 (0.7546)	model_time 0.7145 (0.7470)	loss 2.9004 (3.3038)	grad_norm 1.9276 (1.3840/0.5247)	mem 34602MB
[2025-01-19 08:45:02 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][190/312]	eta 0:01:31 lr 0.002600	time 0.7216 (0.7531)	model_time 0.7212 (0.7459)	loss 3.6203 (3.2934)	grad_norm 1.1949 (1.3796/0.5182)	mem 34602MB
[2025-01-19 08:45:10 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][200/312]	eta 0:01:24 lr 0.002599	time 0.7154 (0.7518)	model_time 0.7153 (0.7449)	loss 3.0705 (3.2753)	grad_norm 1.8764 (1.3900/0.5205)	mem 34602MB
[2025-01-19 08:45:17 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][210/312]	eta 0:01:16 lr 0.002599	time 0.7426 (0.7508)	model_time 0.7424 (0.7442)	loss 3.7471 (3.2888)	grad_norm 3.5434 (1.4127/0.5379)	mem 34602MB
[2025-01-19 08:45:24 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][220/312]	eta 0:01:09 lr 0.002598	time 0.7306 (0.7504)	model_time 0.7304 (0.7441)	loss 2.4879 (3.2824)	grad_norm 1.7128 (1.4157/0.5383)	mem 34602MB
[2025-01-19 08:45:32 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][230/312]	eta 0:01:01 lr 0.002597	time 0.7163 (0.7505)	model_time 0.7159 (0.7444)	loss 3.7066 (3.2801)	grad_norm 0.7981 (1.4114/0.5399)	mem 34602MB
[2025-01-19 08:45:40 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][240/312]	eta 0:00:54 lr 0.002597	time 0.8066 (0.7516)	model_time 0.8064 (0.7457)	loss 3.2645 (3.2789)	grad_norm 0.5919 (1.4064/0.5347)	mem 34602MB
[2025-01-19 08:45:47 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][250/312]	eta 0:00:46 lr 0.002596	time 0.7148 (0.7514)	model_time 0.7146 (0.7458)	loss 4.1616 (3.2850)	grad_norm 1.2215 (1.4039/0.5296)	mem 34602MB
[2025-01-19 08:45:55 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][260/312]	eta 0:00:39 lr 0.002596	time 0.7168 (0.7525)	model_time 0.7164 (0.7471)	loss 3.0510 (3.2745)	grad_norm 1.5615 (1.4025/0.5246)	mem 34602MB
[2025-01-19 08:46:02 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][270/312]	eta 0:00:31 lr 0.002595	time 0.7263 (0.7524)	model_time 0.7261 (0.7472)	loss 3.3988 (3.2790)	grad_norm 1.0621 (1.3979/0.5201)	mem 34602MB
[2025-01-19 08:46:10 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][280/312]	eta 0:00:24 lr 0.002594	time 0.7158 (0.7523)	model_time 0.7153 (0.7472)	loss 2.6210 (3.2752)	grad_norm 1.4350 (1.3982/0.5143)	mem 34602MB
[2025-01-19 08:46:17 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][290/312]	eta 0:00:16 lr 0.002594	time 0.7205 (0.7518)	model_time 0.7200 (0.7469)	loss 3.6544 (3.2784)	grad_norm 1.0135 (1.3939/0.5146)	mem 34602MB
[2025-01-19 08:46:24 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][300/312]	eta 0:00:09 lr 0.002593	time 0.7132 (0.7509)	model_time 0.7131 (0.7462)	loss 3.2139 (3.2745)	grad_norm 0.6854 (1.3891/0.5143)	mem 34602MB
[2025-01-19 08:46:32 internimage_b_1k_224] (main.py 510): INFO Train: [121/300][310/312]	eta 0:00:01 lr 0.002592	time 0.7158 (0.7502)	model_time 0.7157 (0.7457)	loss 2.8776 (3.2764)	grad_norm 0.5954 (1.3859/0.5161)	mem 34602MB
[2025-01-19 08:46:32 internimage_b_1k_224] (main.py 519): INFO EPOCH 121 training takes 0:03:54
[2025-01-19 08:46:32 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_121.pth saving......
[2025-01-19 08:46:35 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_121.pth saved !!!
[2025-01-19 08:46:43 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.479 (7.479)	Loss 0.8456 (0.8456)	Acc@1 82.275 (82.275)	Acc@5 96.460 (96.460)	Mem 34602MB
[2025-01-19 08:46:46 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.953)	Loss 1.1985 (0.9928)	Acc@1 74.072 (79.219)	Acc@5 92.993 (94.917)	Mem 34602MB
[2025-01-19 08:46:46 internimage_b_1k_224] (main.py 575): INFO [Epoch:121] * Acc@1 79.245 Acc@5 94.980
[2025-01-19 08:46:46 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.2%
[2025-01-19 08:46:46 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.45%
[2025-01-19 08:46:55 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.126 (9.126)	Loss 0.6696 (0.6696)	Acc@1 83.325 (83.325)	Acc@5 97.144 (97.144)	Mem 34602MB
[2025-01-19 08:47:00 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.239)	Loss 1.0232 (0.8277)	Acc@1 75.049 (79.867)	Acc@5 93.115 (95.153)	Mem 34602MB
[2025-01-19 08:47:00 internimage_b_1k_224] (main.py 575): INFO [Epoch:121] * Acc@1 79.728 Acc@5 95.210
[2025-01-19 08:47:00 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.7%
[2025-01-19 08:47:00 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 08:47:04 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 08:47:04 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 79.73%
[2025-01-19 08:47:07 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][0/312]	eta 0:11:18 lr 0.002592	time 2.1733 (2.1733)	model_time 0.7422 (0.7422)	loss 3.8154 (3.8154)	grad_norm 1.4098 (1.4098/0.0000)	mem 34602MB
[2025-01-19 08:47:14 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][10/312]	eta 0:04:19 lr 0.002592	time 0.7182 (0.8582)	model_time 0.7180 (0.7278)	loss 3.5563 (3.1670)	grad_norm 1.6512 (1.7377/0.7148)	mem 34602MB
[2025-01-19 08:47:21 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][20/312]	eta 0:03:51 lr 0.002591	time 0.7311 (0.7937)	model_time 0.7309 (0.7253)	loss 3.5785 (3.1661)	grad_norm 1.1266 (1.5025/0.6070)	mem 34602MB
[2025-01-19 08:47:29 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][30/312]	eta 0:03:39 lr 0.002590	time 0.7258 (0.7790)	model_time 0.7253 (0.7325)	loss 3.4733 (3.2471)	grad_norm 0.9579 (1.4859/0.5534)	mem 34602MB
[2025-01-19 08:47:36 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][40/312]	eta 0:03:30 lr 0.002590	time 0.7976 (0.7745)	model_time 0.7975 (0.7392)	loss 3.6521 (3.3443)	grad_norm 1.2751 (1.4304/0.4995)	mem 34602MB
[2025-01-19 08:47:44 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][50/312]	eta 0:03:22 lr 0.002589	time 0.7163 (0.7743)	model_time 0.7161 (0.7459)	loss 3.6935 (3.3413)	grad_norm 1.9633 (1.3830/0.4789)	mem 34602MB
[2025-01-19 08:47:51 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][60/312]	eta 0:03:14 lr 0.002588	time 0.7195 (0.7708)	model_time 0.7191 (0.7470)	loss 3.6255 (3.3585)	grad_norm 0.9536 (1.3429/0.4623)	mem 34602MB
[2025-01-19 08:47:59 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][70/312]	eta 0:03:06 lr 0.002588	time 0.7146 (0.7700)	model_time 0.7144 (0.7495)	loss 2.3911 (3.3527)	grad_norm 1.5402 (1.3143/0.4610)	mem 34602MB
[2025-01-19 08:48:06 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][80/312]	eta 0:02:57 lr 0.002587	time 0.7169 (0.7661)	model_time 0.7165 (0.7481)	loss 3.7591 (3.3511)	grad_norm 1.1267 (1.3176/0.4502)	mem 34602MB
[2025-01-19 08:48:14 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][90/312]	eta 0:02:49 lr 0.002587	time 0.7258 (0.7639)	model_time 0.7257 (0.7478)	loss 3.7293 (3.3760)	grad_norm 1.4769 (1.3110/0.4378)	mem 34602MB
[2025-01-19 08:48:21 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][100/312]	eta 0:02:41 lr 0.002586	time 0.8030 (0.7613)	model_time 0.8028 (0.7467)	loss 3.9234 (3.3693)	grad_norm 1.2625 (1.3368/0.4771)	mem 34602MB
[2025-01-19 08:48:29 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][110/312]	eta 0:02:33 lr 0.002585	time 0.7162 (0.7592)	model_time 0.7157 (0.7459)	loss 3.6570 (3.3682)	grad_norm 0.9033 (1.3365/0.4875)	mem 34602MB
[2025-01-19 08:48:36 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][120/312]	eta 0:02:25 lr 0.002585	time 0.7163 (0.7572)	model_time 0.7162 (0.7450)	loss 3.9610 (3.3498)	grad_norm 1.6265 (1.3670/0.5448)	mem 34602MB
[2025-01-19 08:48:43 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][130/312]	eta 0:02:17 lr 0.002584	time 0.7187 (0.7549)	model_time 0.7182 (0.7436)	loss 2.4167 (3.3437)	grad_norm 1.8049 (1.3936/0.5429)	mem 34602MB
[2025-01-19 08:48:51 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][140/312]	eta 0:02:09 lr 0.002583	time 0.7226 (0.7527)	model_time 0.7224 (0.7422)	loss 4.0463 (3.3462)	grad_norm 0.9109 (1.3754/0.5394)	mem 34602MB
[2025-01-19 08:48:58 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][150/312]	eta 0:02:01 lr 0.002583	time 0.7225 (0.7520)	model_time 0.7221 (0.7422)	loss 3.7062 (3.3575)	grad_norm 1.3502 (1.3682/0.5357)	mem 34602MB
[2025-01-19 08:49:05 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][160/312]	eta 0:01:54 lr 0.002582	time 0.7995 (0.7521)	model_time 0.7990 (0.7429)	loss 2.4679 (3.3484)	grad_norm 0.8111 (1.3801/0.5388)	mem 34602MB
[2025-01-19 08:49:13 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][170/312]	eta 0:01:47 lr 0.002581	time 0.7285 (0.7537)	model_time 0.7283 (0.7448)	loss 3.8314 (3.3547)	grad_norm 3.0804 (1.3770/0.5475)	mem 34602MB
[2025-01-19 08:49:21 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][180/312]	eta 0:01:39 lr 0.002581	time 0.7148 (0.7545)	model_time 0.7146 (0.7460)	loss 4.0148 (3.3550)	grad_norm 1.1170 (1.3798/0.5502)	mem 34602MB
[2025-01-19 08:49:29 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][190/312]	eta 0:01:32 lr 0.002580	time 0.7359 (0.7548)	model_time 0.7354 (0.7468)	loss 4.0313 (3.3563)	grad_norm 0.6915 (1.3851/0.5472)	mem 34602MB
[2025-01-19 08:49:36 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][200/312]	eta 0:01:24 lr 0.002580	time 0.7195 (0.7540)	model_time 0.7187 (0.7463)	loss 3.1581 (3.3570)	grad_norm 1.7588 (1.3736/0.5393)	mem 34602MB
[2025-01-19 08:49:43 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][210/312]	eta 0:01:16 lr 0.002579	time 0.7971 (0.7530)	model_time 0.7966 (0.7457)	loss 3.4912 (3.3644)	grad_norm 2.0793 (1.3862/0.5396)	mem 34602MB
[2025-01-19 08:49:51 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][220/312]	eta 0:01:09 lr 0.002578	time 0.8456 (0.7535)	model_time 0.8455 (0.7465)	loss 3.7560 (3.3600)	grad_norm 1.0142 (1.3778/0.5342)	mem 34602MB
[2025-01-19 08:49:58 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][230/312]	eta 0:01:01 lr 0.002578	time 0.7154 (0.7529)	model_time 0.7149 (0.7462)	loss 3.6386 (3.3518)	grad_norm 1.6682 (1.3772/0.5271)	mem 34602MB
[2025-01-19 08:50:06 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][240/312]	eta 0:00:54 lr 0.002577	time 0.7167 (0.7520)	model_time 0.7165 (0.7455)	loss 2.1816 (3.3407)	grad_norm 0.7712 (1.3720/0.5232)	mem 34602MB
[2025-01-19 08:50:13 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][250/312]	eta 0:00:46 lr 0.002576	time 0.7185 (0.7507)	model_time 0.7180 (0.7445)	loss 3.5599 (3.3359)	grad_norm 2.3162 (1.3774/0.5240)	mem 34602MB
[2025-01-19 08:50:20 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][260/312]	eta 0:00:38 lr 0.002576	time 0.7191 (0.7497)	model_time 0.7186 (0.7437)	loss 3.2332 (3.3258)	grad_norm 1.6158 (1.3724/0.5190)	mem 34602MB
[2025-01-19 08:50:27 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][270/312]	eta 0:00:31 lr 0.002575	time 0.7159 (0.7493)	model_time 0.7155 (0.7435)	loss 2.3727 (3.3192)	grad_norm 1.9891 (1.3842/0.5228)	mem 34602MB
[2025-01-19 08:50:35 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][280/312]	eta 0:00:23 lr 0.002574	time 0.7148 (0.7495)	model_time 0.7146 (0.7439)	loss 2.6972 (3.3154)	grad_norm 0.8955 (1.3746/0.5197)	mem 34602MB
[2025-01-19 08:50:43 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][290/312]	eta 0:00:16 lr 0.002574	time 0.7272 (0.7502)	model_time 0.7270 (0.7447)	loss 4.0496 (3.3175)	grad_norm 0.8411 (1.3643/0.5170)	mem 34602MB
[2025-01-19 08:50:50 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][300/312]	eta 0:00:09 lr 0.002573	time 0.7127 (0.7503)	model_time 0.7126 (0.7451)	loss 3.2518 (3.3184)	grad_norm 1.5175 (1.3676/0.5147)	mem 34602MB
[2025-01-19 08:50:58 internimage_b_1k_224] (main.py 510): INFO Train: [122/300][310/312]	eta 0:00:01 lr 0.002573	time 0.7926 (0.7497)	model_time 0.7924 (0.7446)	loss 3.8508 (3.3204)	grad_norm 1.1268 (1.3524/0.5040)	mem 34602MB
[2025-01-19 08:50:58 internimage_b_1k_224] (main.py 519): INFO EPOCH 122 training takes 0:03:53
[2025-01-19 08:50:58 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_122.pth saving......
[2025-01-19 08:51:01 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_122.pth saved !!!
[2025-01-19 08:51:09 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.371 (7.371)	Loss 0.8078 (0.8078)	Acc@1 82.568 (82.568)	Acc@5 96.606 (96.606)	Mem 34602MB
[2025-01-19 08:51:12 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.184 (0.929)	Loss 1.1326 (0.9394)	Acc@1 74.390 (79.463)	Acc@5 93.140 (95.071)	Mem 34602MB
[2025-01-19 08:51:12 internimage_b_1k_224] (main.py 575): INFO [Epoch:122] * Acc@1 79.413 Acc@5 95.094
[2025-01-19 08:51:12 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.4%
[2025-01-19 08:51:12 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.45%
[2025-01-19 08:51:21 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.989 (8.989)	Loss 0.6677 (0.6677)	Acc@1 83.398 (83.398)	Acc@5 97.144 (97.144)	Mem 34602MB
[2025-01-19 08:51:25 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.212)	Loss 1.0193 (0.8253)	Acc@1 74.976 (79.918)	Acc@5 93.164 (95.170)	Mem 34602MB
[2025-01-19 08:51:26 internimage_b_1k_224] (main.py 575): INFO [Epoch:122] * Acc@1 79.784 Acc@5 95.224
[2025-01-19 08:51:26 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.8%
[2025-01-19 08:51:26 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 08:51:29 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 08:51:29 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 79.78%
[2025-01-19 08:51:32 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][0/312]	eta 0:11:06 lr 0.002572	time 2.1355 (2.1355)	model_time 0.7508 (0.7508)	loss 2.9690 (2.9690)	grad_norm 0.8782 (0.8782/0.0000)	mem 34602MB
[2025-01-19 08:51:39 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][10/312]	eta 0:04:22 lr 0.002572	time 0.7227 (0.8700)	model_time 0.7223 (0.7437)	loss 3.3556 (3.1674)	grad_norm 1.0084 (1.1352/0.3616)	mem 34602MB
[2025-01-19 08:51:47 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][20/312]	eta 0:03:59 lr 0.002571	time 0.7964 (0.8192)	model_time 0.7959 (0.7529)	loss 3.0915 (3.2360)	grad_norm 1.0830 (1.4131/0.6106)	mem 34602MB
[2025-01-19 08:51:54 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][30/312]	eta 0:03:43 lr 0.002570	time 0.7220 (0.7941)	model_time 0.7218 (0.7491)	loss 2.9075 (3.1783)	grad_norm 0.8815 (1.5543/0.7701)	mem 34602MB
[2025-01-19 08:52:01 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][40/312]	eta 0:03:31 lr 0.002570	time 0.7215 (0.7792)	model_time 0.7210 (0.7450)	loss 3.4950 (3.1744)	grad_norm 1.6589 (1.5647/0.7141)	mem 34602MB
[2025-01-19 08:52:09 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][50/312]	eta 0:03:21 lr 0.002569	time 0.7235 (0.7683)	model_time 0.7233 (0.7407)	loss 3.4662 (3.2253)	grad_norm 3.9455 (1.6403/0.7668)	mem 34602MB
[2025-01-19 08:52:16 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][60/312]	eta 0:03:11 lr 0.002569	time 0.7152 (0.7612)	model_time 0.7151 (0.7382)	loss 3.5597 (3.2598)	grad_norm 0.9209 (1.6278/0.7826)	mem 34602MB
[2025-01-19 08:52:23 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][70/312]	eta 0:03:03 lr 0.002568	time 0.7278 (0.7568)	model_time 0.7273 (0.7369)	loss 2.4076 (3.2422)	grad_norm 1.3285 (1.5538/0.7546)	mem 34602MB
[2025-01-19 08:52:31 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][80/312]	eta 0:02:55 lr 0.002567	time 0.7313 (0.7553)	model_time 0.7312 (0.7378)	loss 3.6524 (3.2350)	grad_norm 0.8978 (1.5213/0.7325)	mem 34602MB
[2025-01-19 08:52:38 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][90/312]	eta 0:02:47 lr 0.002567	time 0.7144 (0.7546)	model_time 0.7142 (0.7390)	loss 2.6560 (3.2347)	grad_norm 1.2096 (1.5235/0.7031)	mem 34602MB
[2025-01-19 08:52:46 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][100/312]	eta 0:02:40 lr 0.002566	time 0.7152 (0.7576)	model_time 0.7147 (0.7435)	loss 2.6724 (3.2516)	grad_norm 2.2882 (1.4981/0.6873)	mem 34602MB
[2025-01-19 08:52:54 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][110/312]	eta 0:02:32 lr 0.002565	time 0.7157 (0.7573)	model_time 0.7155 (0.7445)	loss 4.1138 (3.2415)	grad_norm 1.5952 (1.5242/0.6875)	mem 34602MB
[2025-01-19 08:53:01 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][120/312]	eta 0:02:25 lr 0.002565	time 0.7165 (0.7569)	model_time 0.7160 (0.7451)	loss 3.1872 (3.2389)	grad_norm 0.9718 (1.5083/0.6720)	mem 34602MB
[2025-01-19 08:53:08 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][130/312]	eta 0:02:17 lr 0.002564	time 0.7169 (0.7557)	model_time 0.7165 (0.7447)	loss 4.0699 (3.2559)	grad_norm 1.6630 (1.5049/0.6503)	mem 34602MB
[2025-01-19 08:53:16 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][140/312]	eta 0:02:09 lr 0.002563	time 0.7821 (0.7543)	model_time 0.7820 (0.7441)	loss 4.1203 (3.2650)	grad_norm 1.1378 (1.4880/0.6348)	mem 34602MB
[2025-01-19 08:53:23 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][150/312]	eta 0:02:02 lr 0.002563	time 0.7294 (0.7540)	model_time 0.7289 (0.7444)	loss 3.5018 (3.2677)	grad_norm 1.7379 (1.4752/0.6238)	mem 34602MB
[2025-01-19 08:53:31 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][160/312]	eta 0:01:54 lr 0.002562	time 0.7301 (0.7526)	model_time 0.7299 (0.7437)	loss 1.9413 (3.2591)	grad_norm 0.9802 (1.4778/0.6154)	mem 34602MB
[2025-01-19 08:53:38 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][170/312]	eta 0:01:46 lr 0.002562	time 0.7277 (0.7515)	model_time 0.7276 (0.7430)	loss 2.7288 (3.2525)	grad_norm 1.4953 (1.4755/0.6051)	mem 34602MB
[2025-01-19 08:53:45 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][180/312]	eta 0:01:38 lr 0.002561	time 0.7233 (0.7500)	model_time 0.7231 (0.7420)	loss 3.5344 (3.2475)	grad_norm 0.8129 (1.4541/0.6048)	mem 34602MB
[2025-01-19 08:53:53 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][190/312]	eta 0:01:31 lr 0.002560	time 0.7214 (0.7489)	model_time 0.7212 (0.7412)	loss 2.8480 (3.2471)	grad_norm 1.1706 (1.4548/0.5969)	mem 34602MB
[2025-01-19 08:54:00 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][200/312]	eta 0:01:23 lr 0.002560	time 0.8127 (0.7486)	model_time 0.8122 (0.7413)	loss 3.6883 (3.2524)	grad_norm 1.7844 (1.4847/0.6158)	mem 34602MB
[2025-01-19 08:54:07 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][210/312]	eta 0:01:16 lr 0.002559	time 0.7216 (0.7487)	model_time 0.7214 (0.7417)	loss 2.8700 (3.2488)	grad_norm 1.7352 (1.4853/0.6067)	mem 34602MB
[2025-01-19 08:54:15 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][220/312]	eta 0:01:09 lr 0.002558	time 0.7164 (0.7500)	model_time 0.7163 (0.7434)	loss 3.3101 (3.2452)	grad_norm 0.7611 (1.4758/0.6038)	mem 34602MB
[2025-01-19 08:54:23 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][230/312]	eta 0:01:01 lr 0.002558	time 0.8100 (0.7501)	model_time 0.8096 (0.7437)	loss 2.9080 (3.2519)	grad_norm 1.1472 (1.4709/0.6056)	mem 34602MB
[2025-01-19 08:54:30 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][240/312]	eta 0:00:54 lr 0.002557	time 0.7159 (0.7501)	model_time 0.7158 (0.7440)	loss 3.6317 (3.2562)	grad_norm 1.2560 (1.4614/0.6013)	mem 34602MB
[2025-01-19 08:54:38 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][250/312]	eta 0:00:46 lr 0.002556	time 0.7157 (0.7497)	model_time 0.7152 (0.7438)	loss 2.2078 (3.2570)	grad_norm 2.6751 (1.4556/0.5994)	mem 34602MB
[2025-01-19 08:54:45 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][260/312]	eta 0:00:38 lr 0.002556	time 0.8023 (0.7493)	model_time 0.8018 (0.7436)	loss 3.6540 (3.2619)	grad_norm 1.0976 (1.4711/0.6047)	mem 34602MB
[2025-01-19 08:54:53 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][270/312]	eta 0:00:31 lr 0.002555	time 0.7175 (0.7500)	model_time 0.7173 (0.7445)	loss 4.2288 (3.2561)	grad_norm 1.0972 (1.4795/0.6147)	mem 34602MB
[2025-01-19 08:55:00 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][280/312]	eta 0:00:23 lr 0.002555	time 0.7173 (0.7492)	model_time 0.7169 (0.7439)	loss 4.2283 (3.2601)	grad_norm 1.9572 (1.4963/0.6216)	mem 34602MB
[2025-01-19 08:55:07 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][290/312]	eta 0:00:16 lr 0.002554	time 0.7298 (0.7485)	model_time 0.7296 (0.7434)	loss 3.3013 (3.2566)	grad_norm 1.2475 (1.4892/0.6147)	mem 34602MB
[2025-01-19 08:55:15 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][300/312]	eta 0:00:08 lr 0.002553	time 0.7056 (0.7476)	model_time 0.7055 (0.7426)	loss 2.5614 (3.2597)	grad_norm 1.0793 (1.4945/0.6154)	mem 34602MB
[2025-01-19 08:55:22 internimage_b_1k_224] (main.py 510): INFO Train: [123/300][310/312]	eta 0:00:01 lr 0.002553	time 0.7111 (0.7466)	model_time 0.7110 (0.7418)	loss 3.5868 (3.2610)	grad_norm 1.4843 (1.5108/0.6162)	mem 34602MB
[2025-01-19 08:55:22 internimage_b_1k_224] (main.py 519): INFO EPOCH 123 training takes 0:03:52
[2025-01-19 08:55:22 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_123.pth saving......
[2025-01-19 08:55:26 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_123.pth saved !!!
[2025-01-19 08:55:33 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.258 (7.258)	Loss 0.8655 (0.8655)	Acc@1 82.910 (82.910)	Acc@5 96.509 (96.509)	Mem 34602MB
[2025-01-19 08:55:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.919)	Loss 1.1988 (1.0083)	Acc@1 74.561 (79.359)	Acc@5 93.140 (94.864)	Mem 34602MB
[2025-01-19 08:55:36 internimage_b_1k_224] (main.py 575): INFO [Epoch:123] * Acc@1 79.303 Acc@5 94.950
[2025-01-19 08:55:36 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.3%
[2025-01-19 08:55:36 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.45%
[2025-01-19 08:55:45 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.158 (9.158)	Loss 0.6658 (0.6658)	Acc@1 83.325 (83.325)	Acc@5 97.119 (97.119)	Mem 34602MB
[2025-01-19 08:55:50 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.238)	Loss 1.0156 (0.8229)	Acc@1 75.073 (79.960)	Acc@5 93.213 (95.195)	Mem 34602MB
[2025-01-19 08:55:50 internimage_b_1k_224] (main.py 575): INFO [Epoch:123] * Acc@1 79.836 Acc@5 95.250
[2025-01-19 08:55:50 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.8%
[2025-01-19 08:55:50 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 08:55:54 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 08:55:54 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 79.84%
[2025-01-19 08:55:56 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][0/312]	eta 0:10:36 lr 0.002552	time 2.0402 (2.0402)	model_time 0.7379 (0.7379)	loss 2.5342 (2.5342)	grad_norm 1.6517 (1.6517/0.0000)	mem 34602MB
[2025-01-19 08:56:03 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][10/312]	eta 0:04:18 lr 0.002552	time 0.7183 (0.8563)	model_time 0.7181 (0.7377)	loss 3.9697 (3.2088)	grad_norm 1.3193 (1.3036/0.5219)	mem 34602MB
[2025-01-19 08:56:11 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][20/312]	eta 0:03:57 lr 0.002551	time 0.7139 (0.8127)	model_time 0.7137 (0.7503)	loss 3.3282 (3.2707)	grad_norm 2.4676 (1.2988/0.5005)	mem 34602MB
[2025-01-19 08:56:19 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][30/312]	eta 0:03:45 lr 0.002551	time 0.8053 (0.8000)	model_time 0.8051 (0.7576)	loss 3.4151 (3.2727)	grad_norm 1.2031 (1.4451/0.5758)	mem 34602MB
[2025-01-19 08:56:26 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][40/312]	eta 0:03:34 lr 0.002550	time 0.7670 (0.7883)	model_time 0.7665 (0.7561)	loss 2.8642 (3.2521)	grad_norm 1.7384 (1.4060/0.5592)	mem 34602MB
[2025-01-19 08:56:34 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][50/312]	eta 0:03:25 lr 0.002549	time 0.8028 (0.7840)	model_time 0.8026 (0.7581)	loss 3.0371 (3.3436)	grad_norm 1.0475 (1.4707/0.5657)	mem 34602MB
[2025-01-19 08:56:41 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][60/312]	eta 0:03:16 lr 0.002549	time 0.8249 (0.7787)	model_time 0.8247 (0.7570)	loss 3.6266 (3.3398)	grad_norm 1.6014 (1.4478/0.5392)	mem 34602MB
[2025-01-19 08:56:49 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][70/312]	eta 0:03:06 lr 0.002548	time 0.7167 (0.7707)	model_time 0.7165 (0.7520)	loss 3.0403 (3.3256)	grad_norm 2.4965 (1.4737/0.5896)	mem 34602MB
[2025-01-19 08:56:56 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][80/312]	eta 0:02:58 lr 0.002547	time 0.7183 (0.7680)	model_time 0.7182 (0.7516)	loss 2.2085 (3.2706)	grad_norm 0.9467 (1.4971/0.6133)	mem 34602MB
[2025-01-19 08:57:03 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][90/312]	eta 0:02:49 lr 0.002547	time 0.7165 (0.7632)	model_time 0.7163 (0.7486)	loss 3.5603 (3.2720)	grad_norm 2.3318 (1.4699/0.6044)	mem 34602MB
[2025-01-19 08:57:11 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][100/312]	eta 0:02:41 lr 0.002546	time 0.7162 (0.7612)	model_time 0.7161 (0.7480)	loss 3.8329 (3.2699)	grad_norm 1.1130 (1.4680/0.5937)	mem 34602MB
[2025-01-19 08:57:18 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][110/312]	eta 0:02:33 lr 0.002545	time 0.7343 (0.7577)	model_time 0.7341 (0.7457)	loss 3.8191 (3.2861)	grad_norm 1.2434 (1.4646/0.5888)	mem 34602MB
[2025-01-19 08:57:25 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][120/312]	eta 0:02:24 lr 0.002545	time 0.7232 (0.7547)	model_time 0.7227 (0.7435)	loss 3.7568 (3.2822)	grad_norm 1.7193 (1.4579/0.5755)	mem 34602MB
[2025-01-19 08:57:33 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][130/312]	eta 0:02:17 lr 0.002544	time 0.7145 (0.7532)	model_time 0.7143 (0.7429)	loss 2.9278 (3.2482)	grad_norm 1.1483 (1.4992/0.6309)	mem 34602MB
[2025-01-19 08:57:40 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][140/312]	eta 0:02:09 lr 0.002543	time 0.7169 (0.7537)	model_time 0.7168 (0.7441)	loss 3.1955 (3.2316)	grad_norm 0.8119 (1.4679/0.6277)	mem 34602MB
[2025-01-19 08:57:48 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][150/312]	eta 0:02:02 lr 0.002543	time 0.7997 (0.7545)	model_time 0.7995 (0.7455)	loss 3.4591 (3.2412)	grad_norm 1.1216 (1.4318/0.6237)	mem 34602MB
[2025-01-19 08:57:55 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][160/312]	eta 0:01:54 lr 0.002542	time 0.7192 (0.7538)	model_time 0.7187 (0.7454)	loss 3.5369 (3.2330)	grad_norm 1.4527 (1.4277/0.6104)	mem 34602MB
[2025-01-19 08:58:03 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][170/312]	eta 0:01:47 lr 0.002542	time 0.7941 (0.7538)	model_time 0.7940 (0.7459)	loss 3.3949 (3.2258)	grad_norm 0.7608 (1.4167/0.6055)	mem 34602MB
[2025-01-19 08:58:10 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][180/312]	eta 0:01:39 lr 0.002541	time 0.8223 (0.7536)	model_time 0.8221 (0.7461)	loss 4.1550 (3.2376)	grad_norm 2.4140 (1.4083/0.5992)	mem 34602MB
[2025-01-19 08:58:18 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][190/312]	eta 0:01:31 lr 0.002540	time 0.7180 (0.7521)	model_time 0.7179 (0.7450)	loss 3.8207 (3.2529)	grad_norm 1.6888 (1.3982/0.5926)	mem 34602MB
[2025-01-19 08:58:25 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][200/312]	eta 0:01:24 lr 0.002540	time 0.7347 (0.7523)	model_time 0.7342 (0.7455)	loss 4.2210 (3.2658)	grad_norm 0.8481 (1.4051/0.6009)	mem 34602MB
[2025-01-19 08:58:32 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][210/312]	eta 0:01:16 lr 0.002539	time 0.7098 (0.7512)	model_time 0.7096 (0.7447)	loss 3.5004 (3.2767)	grad_norm 1.7782 (1.4072/0.5991)	mem 34602MB
[2025-01-19 08:58:40 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][220/312]	eta 0:01:09 lr 0.002538	time 0.7216 (0.7512)	model_time 0.7215 (0.7450)	loss 3.6609 (3.2865)	grad_norm 1.4835 (1.4158/0.6011)	mem 34602MB
[2025-01-19 08:58:47 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][230/312]	eta 0:01:01 lr 0.002538	time 0.7214 (0.7501)	model_time 0.7210 (0.7441)	loss 3.6684 (3.2861)	grad_norm 2.0513 (1.4529/0.6512)	mem 34602MB
[2025-01-19 08:58:54 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][240/312]	eta 0:00:53 lr 0.002537	time 0.7225 (0.7492)	model_time 0.7221 (0.7435)	loss 4.2276 (3.2787)	grad_norm 2.2847 (1.4632/0.6515)	mem 34602MB
[2025-01-19 08:59:02 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][250/312]	eta 0:00:46 lr 0.002536	time 0.7224 (0.7485)	model_time 0.7223 (0.7430)	loss 3.0605 (3.2743)	grad_norm 0.9243 (1.4450/0.6464)	mem 34602MB
[2025-01-19 08:59:10 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][260/312]	eta 0:00:38 lr 0.002536	time 0.7203 (0.7494)	model_time 0.7197 (0.7441)	loss 2.8855 (3.2728)	grad_norm 1.2636 (1.4312/0.6422)	mem 34602MB
[2025-01-19 08:59:17 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][270/312]	eta 0:00:31 lr 0.002535	time 0.8288 (0.7501)	model_time 0.8286 (0.7449)	loss 3.6154 (3.2885)	grad_norm 0.8614 (1.4328/0.6420)	mem 34602MB
[2025-01-19 08:59:25 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][280/312]	eta 0:00:23 lr 0.002535	time 0.7889 (0.7498)	model_time 0.7887 (0.7448)	loss 2.9000 (3.2799)	grad_norm 1.6285 (1.4311/0.6352)	mem 34602MB
[2025-01-19 08:59:32 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][290/312]	eta 0:00:16 lr 0.002534	time 0.7218 (0.7502)	model_time 0.7213 (0.7454)	loss 3.8890 (3.2777)	grad_norm 1.3891 (1.4280/0.6283)	mem 34602MB
[2025-01-19 08:59:40 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][300/312]	eta 0:00:09 lr 0.002533	time 0.7216 (0.7500)	model_time 0.7215 (0.7453)	loss 3.3367 (3.2853)	grad_norm 1.4229 (1.4204/0.6215)	mem 34602MB
[2025-01-19 08:59:47 internimage_b_1k_224] (main.py 510): INFO Train: [124/300][310/312]	eta 0:00:01 lr 0.002533	time 0.7160 (0.7493)	model_time 0.7159 (0.7447)	loss 3.2883 (3.2836)	grad_norm 0.7771 (1.4210/0.6214)	mem 34602MB
[2025-01-19 08:59:48 internimage_b_1k_224] (main.py 519): INFO EPOCH 124 training takes 0:03:53
[2025-01-19 08:59:48 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_124.pth saving......
[2025-01-19 08:59:51 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_124.pth saved !!!
[2025-01-19 08:59:59 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.771 (7.771)	Loss 0.8160 (0.8160)	Acc@1 83.032 (83.032)	Acc@5 96.851 (96.851)	Mem 34602MB
[2025-01-19 09:00:02 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.990)	Loss 1.1003 (0.9569)	Acc@1 75.244 (79.481)	Acc@5 93.481 (95.044)	Mem 34602MB
[2025-01-19 09:00:02 internimage_b_1k_224] (main.py 575): INFO [Epoch:124] * Acc@1 79.411 Acc@5 95.096
[2025-01-19 09:00:02 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.4%
[2025-01-19 09:00:02 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.45%
[2025-01-19 09:00:11 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.137 (9.137)	Loss 0.6642 (0.6642)	Acc@1 83.374 (83.374)	Acc@5 97.119 (97.119)	Mem 34602MB
[2025-01-19 09:00:16 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.245)	Loss 1.0120 (0.8207)	Acc@1 75.146 (80.040)	Acc@5 93.213 (95.215)	Mem 34602MB
[2025-01-19 09:00:16 internimage_b_1k_224] (main.py 575): INFO [Epoch:124] * Acc@1 79.908 Acc@5 95.272
[2025-01-19 09:00:16 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.9%
[2025-01-19 09:00:16 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 09:00:20 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 09:00:20 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 79.91%
[2025-01-19 09:00:22 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][0/312]	eta 0:10:28 lr 0.002532	time 2.0155 (2.0155)	model_time 0.7412 (0.7412)	loss 3.8786 (3.8786)	grad_norm 1.0132 (1.0132/0.0000)	mem 34602MB
[2025-01-19 09:00:29 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][10/312]	eta 0:04:20 lr 0.002532	time 0.7964 (0.8626)	model_time 0.7960 (0.7464)	loss 3.6219 (3.2808)	grad_norm 1.0376 (1.5964/0.7815)	mem 34602MB
[2025-01-19 09:00:37 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][20/312]	eta 0:03:55 lr 0.002531	time 0.8267 (0.8078)	model_time 0.8263 (0.7467)	loss 2.9930 (3.1610)	grad_norm 0.9148 (1.3111/0.6598)	mem 34602MB
[2025-01-19 09:00:44 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][30/312]	eta 0:03:40 lr 0.002531	time 0.7453 (0.7814)	model_time 0.7449 (0.7399)	loss 3.4254 (3.1939)	grad_norm 0.9715 (1.2357/0.5688)	mem 34602MB
[2025-01-19 09:00:51 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][40/312]	eta 0:03:28 lr 0.002530	time 0.7200 (0.7682)	model_time 0.7195 (0.7367)	loss 1.9777 (3.2199)	grad_norm 1.1633 (1.3705/0.5988)	mem 34602MB
[2025-01-19 09:00:59 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][50/312]	eta 0:03:18 lr 0.002529	time 0.7268 (0.7595)	model_time 0.7267 (0.7342)	loss 2.4972 (3.2976)	grad_norm 1.3164 (1.4073/0.5842)	mem 34602MB
[2025-01-19 09:01:06 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][60/312]	eta 0:03:11 lr 0.002529	time 0.7984 (0.7583)	model_time 0.7980 (0.7370)	loss 3.5335 (3.2773)	grad_norm 1.1261 (1.3330/0.5661)	mem 34602MB
[2025-01-19 09:01:14 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][70/312]	eta 0:03:03 lr 0.002528	time 0.7995 (0.7589)	model_time 0.7990 (0.7406)	loss 2.7240 (3.2921)	grad_norm 1.3826 (1.3262/0.5650)	mem 34602MB
[2025-01-19 09:01:21 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][80/312]	eta 0:02:56 lr 0.002527	time 0.7312 (0.7589)	model_time 0.7308 (0.7428)	loss 3.2044 (3.3266)	grad_norm 0.7535 (1.3634/0.5890)	mem 34602MB
[2025-01-19 09:01:29 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][90/312]	eta 0:02:48 lr 0.002527	time 0.7254 (0.7582)	model_time 0.7253 (0.7438)	loss 3.4312 (3.3313)	grad_norm 1.4965 (1.4112/0.6148)	mem 34602MB
[2025-01-19 09:01:36 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][100/312]	eta 0:02:40 lr 0.002526	time 0.8250 (0.7568)	model_time 0.8249 (0.7438)	loss 3.0332 (3.3116)	grad_norm 1.4539 (1.4000/0.5989)	mem 34602MB
[2025-01-19 09:01:44 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][110/312]	eta 0:02:32 lr 0.002525	time 0.7231 (0.7559)	model_time 0.7229 (0.7440)	loss 4.0470 (3.3348)	grad_norm 3.0793 (1.4028/0.6119)	mem 34602MB
[2025-01-19 09:01:51 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][120/312]	eta 0:02:24 lr 0.002525	time 0.7161 (0.7532)	model_time 0.7156 (0.7423)	loss 2.4671 (3.3370)	grad_norm 1.8397 (1.4455/0.6487)	mem 34602MB
[2025-01-19 09:01:58 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][130/312]	eta 0:02:17 lr 0.002524	time 0.7981 (0.7532)	model_time 0.7977 (0.7431)	loss 2.8455 (3.3297)	grad_norm 1.0673 (1.4311/0.6381)	mem 34602MB
[2025-01-19 09:02:06 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][140/312]	eta 0:02:09 lr 0.002523	time 0.7160 (0.7511)	model_time 0.7156 (0.7417)	loss 3.6788 (3.3095)	grad_norm 1.3675 (1.4159/0.6322)	mem 34602MB
[2025-01-19 09:02:13 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][150/312]	eta 0:02:01 lr 0.002523	time 0.7222 (0.7497)	model_time 0.7220 (0.7409)	loss 3.7417 (3.2983)	grad_norm 1.3133 (1.4105/0.6182)	mem 34602MB
[2025-01-19 09:02:20 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][160/312]	eta 0:01:53 lr 0.002522	time 0.7325 (0.7482)	model_time 0.7323 (0.7399)	loss 3.5776 (3.2938)	grad_norm 1.1778 (1.4033/0.6079)	mem 34602MB
[2025-01-19 09:02:27 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][170/312]	eta 0:01:46 lr 0.002522	time 0.7191 (0.7467)	model_time 0.7189 (0.7389)	loss 3.1480 (3.2925)	grad_norm 1.4432 (1.4149/0.5985)	mem 34602MB
[2025-01-19 09:02:35 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][180/312]	eta 0:01:38 lr 0.002521	time 0.7354 (0.7463)	model_time 0.7353 (0.7389)	loss 4.2990 (3.3139)	grad_norm 0.6635 (1.4103/0.5913)	mem 34602MB
[2025-01-19 09:02:43 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][190/312]	eta 0:01:31 lr 0.002520	time 0.8104 (0.7479)	model_time 0.8102 (0.7409)	loss 2.6742 (3.3105)	grad_norm 1.2113 (1.4096/0.5851)	mem 34602MB
[2025-01-19 09:02:50 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][200/312]	eta 0:01:23 lr 0.002520	time 0.7157 (0.7481)	model_time 0.7153 (0.7414)	loss 2.8473 (3.3189)	grad_norm 1.6677 (1.4076/0.5765)	mem 34602MB
[2025-01-19 09:02:58 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][210/312]	eta 0:01:16 lr 0.002519	time 0.7239 (0.7484)	model_time 0.7238 (0.7420)	loss 3.3072 (3.3200)	grad_norm 2.6861 (1.4343/0.5835)	mem 34602MB
[2025-01-19 09:03:05 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][220/312]	eta 0:01:08 lr 0.002518	time 0.8012 (0.7482)	model_time 0.8010 (0.7421)	loss 4.0151 (3.3252)	grad_norm 1.1386 (1.4367/0.5836)	mem 34602MB
[2025-01-19 09:03:13 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][230/312]	eta 0:01:01 lr 0.002518	time 0.7167 (0.7486)	model_time 0.7162 (0.7427)	loss 3.4871 (3.3251)	grad_norm 1.6762 (1.4461/0.5823)	mem 34602MB
[2025-01-19 09:03:20 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][240/312]	eta 0:00:53 lr 0.002517	time 0.7229 (0.7477)	model_time 0.7227 (0.7420)	loss 3.3470 (3.3223)	grad_norm 1.9482 (1.4429/0.5738)	mem 34602MB
[2025-01-19 09:03:28 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][250/312]	eta 0:00:46 lr 0.002516	time 0.7984 (0.7481)	model_time 0.7982 (0.7427)	loss 3.7631 (3.3168)	grad_norm 1.0660 (1.4505/0.5771)	mem 34602MB
[2025-01-19 09:03:35 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][260/312]	eta 0:00:38 lr 0.002516	time 0.7168 (0.7475)	model_time 0.7167 (0.7422)	loss 3.5319 (3.3262)	grad_norm 0.7208 (1.4561/0.5780)	mem 34602MB
[2025-01-19 09:03:42 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][270/312]	eta 0:00:31 lr 0.002515	time 0.7161 (0.7468)	model_time 0.7160 (0.7417)	loss 3.3761 (3.3161)	grad_norm 1.8928 (1.4504/0.5712)	mem 34602MB
[2025-01-19 09:03:49 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][280/312]	eta 0:00:23 lr 0.002514	time 0.7389 (0.7462)	model_time 0.7388 (0.7413)	loss 3.1465 (3.3139)	grad_norm 2.3377 (1.4555/0.5741)	mem 34602MB
[2025-01-19 09:03:57 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][290/312]	eta 0:00:16 lr 0.002514	time 0.7273 (0.7454)	model_time 0.7269 (0.7406)	loss 2.2051 (3.3076)	grad_norm 0.8498 (1.4509/0.5669)	mem 34602MB
[2025-01-19 09:04:04 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][300/312]	eta 0:00:08 lr 0.002513	time 0.7951 (0.7448)	model_time 0.7950 (0.7402)	loss 3.4037 (3.3023)	grad_norm 1.1062 (1.4471/0.5607)	mem 34602MB
[2025-01-19 09:04:12 internimage_b_1k_224] (main.py 510): INFO Train: [125/300][310/312]	eta 0:00:01 lr 0.002513	time 0.7234 (0.7451)	model_time 0.7233 (0.7406)	loss 3.1142 (3.3068)	grad_norm 2.0599 (1.4522/0.5528)	mem 34602MB
[2025-01-19 09:04:12 internimage_b_1k_224] (main.py 519): INFO EPOCH 125 training takes 0:03:52
[2025-01-19 09:04:12 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_125.pth saving......
[2025-01-19 09:04:15 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_125.pth saved !!!
[2025-01-19 09:04:23 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.549 (7.549)	Loss 0.8161 (0.8161)	Acc@1 82.983 (82.983)	Acc@5 96.851 (96.851)	Mem 34602MB
[2025-01-19 09:04:26 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.954)	Loss 1.1347 (0.9689)	Acc@1 75.000 (79.559)	Acc@5 93.481 (95.097)	Mem 34602MB
[2025-01-19 09:04:26 internimage_b_1k_224] (main.py 575): INFO [Epoch:125] * Acc@1 79.519 Acc@5 95.126
[2025-01-19 09:04:26 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.5%
[2025-01-19 09:04:26 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 09:04:30 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 09:04:30 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.52%
[2025-01-19 09:04:37 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.539 (7.539)	Loss 0.6626 (0.6626)	Acc@1 83.350 (83.350)	Acc@5 97.144 (97.144)	Mem 34602MB
[2025-01-19 09:04:40 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.948)	Loss 1.0087 (0.8186)	Acc@1 75.269 (80.071)	Acc@5 93.237 (95.228)	Mem 34602MB
[2025-01-19 09:04:40 internimage_b_1k_224] (main.py 575): INFO [Epoch:125] * Acc@1 79.940 Acc@5 95.288
[2025-01-19 09:04:40 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.9%
[2025-01-19 09:04:40 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 09:04:44 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 09:04:44 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 79.94%
[2025-01-19 09:04:46 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][0/312]	eta 0:11:56 lr 0.002512	time 2.2960 (2.2960)	model_time 0.7422 (0.7422)	loss 2.9920 (2.9920)	grad_norm 1.0249 (1.0249/0.0000)	mem 34602MB
[2025-01-19 09:04:54 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][10/312]	eta 0:04:37 lr 0.002512	time 0.7228 (0.9187)	model_time 0.7227 (0.7771)	loss 3.8946 (3.4611)	grad_norm 0.8640 (1.4264/0.3584)	mem 34602MB
[2025-01-19 09:05:02 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][20/312]	eta 0:04:05 lr 0.002511	time 0.8398 (0.8405)	model_time 0.8394 (0.7662)	loss 4.0277 (3.2139)	grad_norm 1.4012 (1.3906/0.4405)	mem 34602MB
[2025-01-19 09:05:09 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][30/312]	eta 0:03:48 lr 0.002510	time 0.7216 (0.8112)	model_time 0.7211 (0.7607)	loss 2.9502 (3.1785)	grad_norm 1.1383 (1.4337/0.5329)	mem 34602MB
[2025-01-19 09:05:17 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][40/312]	eta 0:03:36 lr 0.002510	time 0.7156 (0.7974)	model_time 0.7154 (0.7592)	loss 4.1544 (3.2615)	grad_norm 1.2997 (1.4137/0.5225)	mem 34602MB
[2025-01-19 09:05:24 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][50/312]	eta 0:03:26 lr 0.002509	time 1.0234 (0.7901)	model_time 1.0229 (0.7593)	loss 3.7915 (3.2828)	grad_norm 1.5219 (1.4443/0.5810)	mem 34602MB
[2025-01-19 09:05:32 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][60/312]	eta 0:03:16 lr 0.002509	time 0.7090 (0.7806)	model_time 0.7088 (0.7548)	loss 2.7643 (3.2826)	grad_norm 1.8628 (1.4647/0.5794)	mem 34602MB
[2025-01-19 09:05:39 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][70/312]	eta 0:03:07 lr 0.002508	time 0.7166 (0.7740)	model_time 0.7165 (0.7517)	loss 3.9349 (3.2932)	grad_norm 1.7590 (1.4767/0.5547)	mem 34602MB
[2025-01-19 09:05:46 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][80/312]	eta 0:02:58 lr 0.002507	time 0.7205 (0.7690)	model_time 0.7200 (0.7495)	loss 3.3794 (3.2802)	grad_norm 1.2534 (1.4536/0.5318)	mem 34602MB
[2025-01-19 09:05:54 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][90/312]	eta 0:02:49 lr 0.002507	time 0.7197 (0.7647)	model_time 0.7195 (0.7473)	loss 3.3101 (3.3158)	grad_norm 0.8598 (1.4282/0.5294)	mem 34602MB
[2025-01-19 09:06:01 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][100/312]	eta 0:02:41 lr 0.002506	time 0.7149 (0.7615)	model_time 0.7144 (0.7458)	loss 2.2433 (3.3103)	grad_norm 2.9235 (1.4272/0.5394)	mem 34602MB
[2025-01-19 09:06:08 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][110/312]	eta 0:02:33 lr 0.002505	time 0.7410 (0.7592)	model_time 0.7409 (0.7449)	loss 3.3607 (3.3255)	grad_norm 1.0857 (1.3990/0.5334)	mem 34602MB
[2025-01-19 09:06:16 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][120/312]	eta 0:02:25 lr 0.002505	time 0.8014 (0.7601)	model_time 0.8012 (0.7469)	loss 3.5588 (3.3198)	grad_norm 0.9097 (1.4136/0.5386)	mem 34602MB
[2025-01-19 09:06:24 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][130/312]	eta 0:02:18 lr 0.002504	time 0.7149 (0.7602)	model_time 0.7144 (0.7480)	loss 3.3208 (3.3077)	grad_norm 1.1040 (1.3686/0.5418)	mem 34602MB
[2025-01-19 09:06:31 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][140/312]	eta 0:02:10 lr 0.002503	time 0.8143 (0.7601)	model_time 0.8142 (0.7487)	loss 3.6027 (3.3110)	grad_norm 1.3573 (1.3623/0.5366)	mem 34602MB
[2025-01-19 09:06:39 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][150/312]	eta 0:02:02 lr 0.002503	time 0.7156 (0.7592)	model_time 0.7151 (0.7485)	loss 3.2019 (3.3024)	grad_norm 2.1750 (1.3785/0.5646)	mem 34602MB
[2025-01-19 09:06:46 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][160/312]	eta 0:01:55 lr 0.002502	time 0.7313 (0.7586)	model_time 0.7312 (0.7486)	loss 3.1110 (3.2995)	grad_norm 1.0759 (1.4131/0.6032)	mem 34602MB
[2025-01-19 09:06:54 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][170/312]	eta 0:01:47 lr 0.002501	time 0.8344 (0.7582)	model_time 0.8342 (0.7487)	loss 3.3258 (3.3142)	grad_norm 1.3649 (1.4508/0.6333)	mem 34602MB
[2025-01-19 09:07:01 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][180/312]	eta 0:01:40 lr 0.002501	time 0.7744 (0.7587)	model_time 0.7743 (0.7498)	loss 3.4951 (3.3040)	grad_norm 1.3240 (1.4321/0.6250)	mem 34602MB
[2025-01-19 09:07:09 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][190/312]	eta 0:01:32 lr 0.002500	time 0.7219 (0.7572)	model_time 0.7214 (0.7487)	loss 3.1283 (3.3126)	grad_norm 1.1669 (1.4186/0.6143)	mem 34602MB
[2025-01-19 09:07:16 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][200/312]	eta 0:01:24 lr 0.002500	time 0.7341 (0.7562)	model_time 0.7339 (0.7481)	loss 3.7748 (3.3117)	grad_norm 0.5506 (1.4183/0.6147)	mem 34602MB
[2025-01-19 09:07:23 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][210/312]	eta 0:01:17 lr 0.002499	time 0.7543 (0.7555)	model_time 0.7541 (0.7478)	loss 4.2027 (3.3293)	grad_norm 1.6870 (1.4415/0.6244)	mem 34602MB
[2025-01-19 09:07:31 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][220/312]	eta 0:01:09 lr 0.002498	time 0.7562 (0.7542)	model_time 0.7560 (0.7468)	loss 2.1568 (3.3214)	grad_norm 1.7990 (1.4397/0.6196)	mem 34602MB
[2025-01-19 09:07:38 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][230/312]	eta 0:01:01 lr 0.002498	time 0.7160 (0.7532)	model_time 0.7158 (0.7461)	loss 2.9068 (3.3132)	grad_norm 0.8537 (1.4327/0.6093)	mem 34602MB
[2025-01-19 09:07:46 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][240/312]	eta 0:00:54 lr 0.002497	time 0.7940 (0.7540)	model_time 0.7939 (0.7472)	loss 3.5347 (3.3000)	grad_norm 1.8198 (1.4414/0.6126)	mem 34602MB
[2025-01-19 09:07:53 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][250/312]	eta 0:00:46 lr 0.002496	time 0.7165 (0.7544)	model_time 0.7164 (0.7479)	loss 3.7222 (3.2937)	grad_norm 0.8109 (1.4619/0.6259)	mem 34602MB
[2025-01-19 09:08:01 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][260/312]	eta 0:00:39 lr 0.002496	time 0.7982 (0.7544)	model_time 0.7981 (0.7481)	loss 3.4400 (3.2954)	grad_norm 1.3110 (1.4622/0.6221)	mem 34602MB
[2025-01-19 09:08:08 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][270/312]	eta 0:00:31 lr 0.002495	time 0.7224 (0.7543)	model_time 0.7219 (0.7482)	loss 3.7834 (3.3075)	grad_norm 1.9676 (1.4583/0.6135)	mem 34602MB
[2025-01-19 09:08:16 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][280/312]	eta 0:00:24 lr 0.002494	time 0.7309 (0.7548)	model_time 0.7308 (0.7489)	loss 3.9908 (3.3146)	grad_norm 0.6605 (1.4509/0.6088)	mem 34602MB
[2025-01-19 09:08:24 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][290/312]	eta 0:00:16 lr 0.002494	time 0.8256 (0.7546)	model_time 0.8254 (0.7489)	loss 3.4713 (3.3169)	grad_norm 0.9292 (1.4521/0.6108)	mem 34602MB
[2025-01-19 09:08:31 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][300/312]	eta 0:00:09 lr 0.002493	time 0.7124 (0.7539)	model_time 0.7123 (0.7483)	loss 3.5536 (3.3114)	grad_norm 0.9302 (1.4554/0.6079)	mem 34602MB
[2025-01-19 09:08:38 internimage_b_1k_224] (main.py 510): INFO Train: [126/300][310/312]	eta 0:00:01 lr 0.002492	time 0.7087 (0.7529)	model_time 0.7086 (0.7476)	loss 3.3464 (3.3133)	grad_norm 1.7580 (1.4509/0.6080)	mem 34602MB
[2025-01-19 09:08:39 internimage_b_1k_224] (main.py 519): INFO EPOCH 126 training takes 0:03:54
[2025-01-19 09:08:39 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_126.pth saving......
[2025-01-19 09:08:42 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_126.pth saved !!!
[2025-01-19 09:08:50 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.748 (7.748)	Loss 0.8600 (0.8600)	Acc@1 82.812 (82.812)	Acc@5 96.729 (96.729)	Mem 34602MB
[2025-01-19 09:08:53 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.975)	Loss 1.0947 (0.9803)	Acc@1 76.318 (79.825)	Acc@5 94.043 (95.206)	Mem 34602MB
[2025-01-19 09:08:53 internimage_b_1k_224] (main.py 575): INFO [Epoch:126] * Acc@1 79.685 Acc@5 95.240
[2025-01-19 09:08:53 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.7%
[2025-01-19 09:08:53 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 09:08:56 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 09:08:56 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.68%
[2025-01-19 09:09:04 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.601 (7.601)	Loss 0.6611 (0.6611)	Acc@1 83.350 (83.350)	Acc@5 97.144 (97.144)	Mem 34602MB
[2025-01-19 09:09:07 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.974)	Loss 1.0055 (0.8165)	Acc@1 75.244 (80.116)	Acc@5 93.335 (95.268)	Mem 34602MB
[2025-01-19 09:09:07 internimage_b_1k_224] (main.py 575): INFO [Epoch:126] * Acc@1 79.986 Acc@5 95.325
[2025-01-19 09:09:07 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.0%
[2025-01-19 09:09:07 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 09:09:11 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 09:09:11 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 79.99%
[2025-01-19 09:09:13 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][0/312]	eta 0:10:24 lr 0.002492	time 2.0002 (2.0002)	model_time 0.7560 (0.7560)	loss 3.4775 (3.4775)	grad_norm 1.1374 (1.1374/0.0000)	mem 34602MB
[2025-01-19 09:09:21 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][10/312]	eta 0:04:18 lr 0.002492	time 0.7268 (0.8550)	model_time 0.7266 (0.7416)	loss 3.1738 (3.2861)	grad_norm 2.6958 (1.7016/0.5630)	mem 34602MB
[2025-01-19 09:09:28 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][20/312]	eta 0:03:53 lr 0.002491	time 0.8350 (0.7995)	model_time 0.8349 (0.7398)	loss 3.5122 (3.3180)	grad_norm 1.5132 (1.7459/0.5097)	mem 34602MB
[2025-01-19 09:09:35 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][30/312]	eta 0:03:38 lr 0.002490	time 0.7187 (0.7760)	model_time 0.7186 (0.7355)	loss 2.4039 (3.3240)	grad_norm 1.9206 (1.6449/0.5091)	mem 34602MB
[2025-01-19 09:09:43 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][40/312]	eta 0:03:28 lr 0.002490	time 0.7214 (0.7655)	model_time 0.7210 (0.7348)	loss 2.2023 (3.2812)	grad_norm 0.8748 (1.5203/0.5119)	mem 34602MB
[2025-01-19 09:09:50 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][50/312]	eta 0:03:20 lr 0.002489	time 0.7164 (0.7666)	model_time 0.7162 (0.7419)	loss 2.5906 (3.2868)	grad_norm 1.1980 (1.5151/0.5338)	mem 34602MB
[2025-01-19 09:09:58 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][60/312]	eta 0:03:12 lr 0.002488	time 0.7345 (0.7652)	model_time 0.7341 (0.7444)	loss 3.5007 (3.3069)	grad_norm 1.3977 (1.4982/0.5401)	mem 34602MB
[2025-01-19 09:10:06 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][70/312]	eta 0:03:04 lr 0.002488	time 0.7226 (0.7627)	model_time 0.7223 (0.7448)	loss 3.1491 (3.3034)	grad_norm 1.1853 (1.4261/0.5376)	mem 34602MB
[2025-01-19 09:10:13 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][80/312]	eta 0:02:57 lr 0.002487	time 0.8050 (0.7637)	model_time 0.8046 (0.7480)	loss 2.6253 (3.2931)	grad_norm 1.7590 (1.4413/0.5633)	mem 34602MB
[2025-01-19 09:10:21 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][90/312]	eta 0:02:48 lr 0.002486	time 0.7155 (0.7606)	model_time 0.7150 (0.7466)	loss 3.6473 (3.2885)	grad_norm 0.8409 (1.4169/0.5524)	mem 34602MB
[2025-01-19 09:10:28 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][100/312]	eta 0:02:40 lr 0.002486	time 0.8183 (0.7580)	model_time 0.8181 (0.7453)	loss 3.5176 (3.3093)	grad_norm 2.1657 (1.4116/0.5431)	mem 34602MB
[2025-01-19 09:10:35 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][110/312]	eta 0:02:32 lr 0.002485	time 0.7293 (0.7567)	model_time 0.7291 (0.7452)	loss 3.8670 (3.3121)	grad_norm 1.5232 (1.4098/0.5322)	mem 34602MB
[2025-01-19 09:10:43 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][120/312]	eta 0:02:24 lr 0.002485	time 0.7197 (0.7542)	model_time 0.7195 (0.7436)	loss 3.6719 (3.3093)	grad_norm 0.7446 (1.4257/0.5271)	mem 34602MB
[2025-01-19 09:10:50 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][130/312]	eta 0:02:17 lr 0.002484	time 0.7366 (0.7530)	model_time 0.7361 (0.7431)	loss 3.7986 (3.3107)	grad_norm 0.7023 (1.4112/0.5225)	mem 34602MB
[2025-01-19 09:10:57 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][140/312]	eta 0:02:09 lr 0.002483	time 0.8182 (0.7519)	model_time 0.8176 (0.7427)	loss 2.7051 (3.3066)	grad_norm 2.3370 (1.4431/0.5652)	mem 34602MB
[2025-01-19 09:11:05 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][150/312]	eta 0:02:01 lr 0.002483	time 0.7371 (0.7500)	model_time 0.7369 (0.7414)	loss 2.7071 (3.2993)	grad_norm 1.5701 (1.5038/0.6663)	mem 34602MB
[2025-01-19 09:11:12 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][160/312]	eta 0:01:53 lr 0.002482	time 0.7254 (0.7487)	model_time 0.7253 (0.7406)	loss 2.8214 (3.2881)	grad_norm 1.1523 (1.5095/0.6673)	mem 34602MB
[2025-01-19 09:11:20 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][170/312]	eta 0:01:46 lr 0.002481	time 0.7167 (0.7498)	model_time 0.7163 (0.7422)	loss 3.8034 (3.2837)	grad_norm 0.7750 (1.4765/0.6634)	mem 34602MB
[2025-01-19 09:11:27 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][180/312]	eta 0:01:39 lr 0.002481	time 0.7292 (0.7503)	model_time 0.7291 (0.7431)	loss 2.3952 (3.2866)	grad_norm 1.3204 (1.4849/0.6568)	mem 34602MB
[2025-01-19 09:11:35 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][190/312]	eta 0:01:31 lr 0.002480	time 0.7967 (0.7504)	model_time 0.7962 (0.7435)	loss 3.5560 (3.3023)	grad_norm 2.0075 (1.4998/0.6515)	mem 34602MB
[2025-01-19 09:11:42 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][200/312]	eta 0:01:24 lr 0.002479	time 0.8149 (0.7517)	model_time 0.8147 (0.7452)	loss 2.2375 (3.2988)	grad_norm 1.1680 (1.5029/0.6451)	mem 34602MB
[2025-01-19 09:11:50 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][210/312]	eta 0:01:16 lr 0.002479	time 0.7186 (0.7511)	model_time 0.7184 (0.7448)	loss 3.1602 (3.2993)	grad_norm 0.7841 (1.4967/0.6435)	mem 34602MB
[2025-01-19 09:11:57 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][220/312]	eta 0:01:09 lr 0.002478	time 0.8080 (0.7505)	model_time 0.8078 (0.7445)	loss 2.5505 (3.2896)	grad_norm 1.8744 (1.4986/0.6372)	mem 34602MB
[2025-01-19 09:12:05 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][230/312]	eta 0:01:01 lr 0.002477	time 0.7209 (0.7507)	model_time 0.7208 (0.7449)	loss 3.5752 (3.2961)	grad_norm 0.8960 (1.5051/0.6321)	mem 34602MB
[2025-01-19 09:12:12 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][240/312]	eta 0:00:53 lr 0.002477	time 0.7264 (0.7500)	model_time 0.7260 (0.7444)	loss 3.3480 (3.2965)	grad_norm 0.7371 (1.4973/0.6311)	mem 34602MB
[2025-01-19 09:12:20 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][250/312]	eta 0:00:46 lr 0.002476	time 0.7157 (0.7495)	model_time 0.7155 (0.7442)	loss 3.4098 (3.3052)	grad_norm 0.8963 (1.5170/0.6662)	mem 34602MB
[2025-01-19 09:12:27 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][260/312]	eta 0:00:38 lr 0.002475	time 0.7630 (0.7486)	model_time 0.7628 (0.7435)	loss 3.0272 (3.2939)	grad_norm 0.8342 (1.4974/0.6633)	mem 34602MB
[2025-01-19 09:12:34 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][270/312]	eta 0:00:31 lr 0.002475	time 0.7366 (0.7482)	model_time 0.7364 (0.7433)	loss 2.9039 (3.2900)	grad_norm 2.9242 (1.5017/0.6592)	mem 34602MB
[2025-01-19 09:12:41 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][280/312]	eta 0:00:23 lr 0.002474	time 0.7183 (0.7477)	model_time 0.7182 (0.7430)	loss 3.5499 (3.2884)	grad_norm 1.1869 (1.4983/0.6616)	mem 34602MB
[2025-01-19 09:12:49 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][290/312]	eta 0:00:16 lr 0.002474	time 0.7434 (0.7480)	model_time 0.7433 (0.7433)	loss 3.4436 (3.2887)	grad_norm 1.3987 (1.4831/0.6566)	mem 34602MB
[2025-01-19 09:12:57 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][300/312]	eta 0:00:08 lr 0.002473	time 0.7133 (0.7482)	model_time 0.7132 (0.7438)	loss 3.3124 (3.2883)	grad_norm 1.5202 (1.4940/0.6648)	mem 34602MB
[2025-01-19 09:13:04 internimage_b_1k_224] (main.py 510): INFO Train: [127/300][310/312]	eta 0:00:01 lr 0.002472	time 0.7124 (0.7478)	model_time 0.7123 (0.7434)	loss 3.3222 (3.2822)	grad_norm 1.6752 (1.4921/0.6657)	mem 34602MB
[2025-01-19 09:13:05 internimage_b_1k_224] (main.py 519): INFO EPOCH 127 training takes 0:03:53
[2025-01-19 09:13:05 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_127.pth saving......
[2025-01-19 09:13:08 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_127.pth saved !!!
[2025-01-19 09:13:15 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.354 (7.354)	Loss 0.7641 (0.7641)	Acc@1 83.325 (83.325)	Acc@5 96.753 (96.753)	Mem 34602MB
[2025-01-19 09:13:18 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.950)	Loss 1.1081 (0.9461)	Acc@1 75.708 (79.650)	Acc@5 93.604 (95.197)	Mem 34602MB
[2025-01-19 09:13:19 internimage_b_1k_224] (main.py 575): INFO [Epoch:127] * Acc@1 79.585 Acc@5 95.240
[2025-01-19 09:13:19 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.6%
[2025-01-19 09:13:19 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.68%
[2025-01-19 09:13:28 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.125 (9.125)	Loss 0.6597 (0.6597)	Acc@1 83.374 (83.374)	Acc@5 97.144 (97.144)	Mem 34602MB
[2025-01-19 09:13:32 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.241)	Loss 1.0023 (0.8144)	Acc@1 75.342 (80.165)	Acc@5 93.384 (95.293)	Mem 34602MB
[2025-01-19 09:13:33 internimage_b_1k_224] (main.py 575): INFO [Epoch:127] * Acc@1 80.044 Acc@5 95.349
[2025-01-19 09:13:33 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.0%
[2025-01-19 09:13:33 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 09:13:37 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 09:13:37 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.04%
[2025-01-19 09:13:39 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][0/312]	eta 0:10:23 lr 0.002472	time 1.9973 (1.9973)	model_time 0.7331 (0.7331)	loss 3.5549 (3.5549)	grad_norm 2.3671 (2.3671/0.0000)	mem 34602MB
[2025-01-19 09:13:46 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][10/312]	eta 0:04:23 lr 0.002471	time 0.8083 (0.8728)	model_time 0.8081 (0.7575)	loss 4.0483 (3.6264)	grad_norm 1.0596 (1.6032/0.5555)	mem 34602MB
[2025-01-19 09:13:53 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][20/312]	eta 0:03:55 lr 0.002471	time 0.7140 (0.8071)	model_time 0.7136 (0.7466)	loss 2.7588 (3.4863)	grad_norm 1.0669 (1.3633/0.4981)	mem 34602MB
[2025-01-19 09:14:01 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][30/312]	eta 0:03:40 lr 0.002470	time 0.7146 (0.7826)	model_time 0.7143 (0.7415)	loss 2.8190 (3.3814)	grad_norm 0.8793 (1.3138/0.4555)	mem 34602MB
[2025-01-19 09:14:08 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][40/312]	eta 0:03:31 lr 0.002470	time 0.7200 (0.7762)	model_time 0.7196 (0.7450)	loss 4.0632 (3.3328)	grad_norm 1.3003 (1.3168/0.4385)	mem 34602MB
[2025-01-19 09:14:16 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][50/312]	eta 0:03:20 lr 0.002469	time 0.7302 (0.7670)	model_time 0.7301 (0.7419)	loss 3.3669 (3.3780)	grad_norm 1.7768 (1.2840/0.4212)	mem 34602MB
[2025-01-19 09:14:23 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][60/312]	eta 0:03:11 lr 0.002468	time 0.7240 (0.7612)	model_time 0.7238 (0.7401)	loss 3.2503 (3.3840)	grad_norm 2.6836 (1.3949/0.5600)	mem 34602MB
[2025-01-19 09:14:30 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][70/312]	eta 0:03:03 lr 0.002468	time 0.7243 (0.7564)	model_time 0.7241 (0.7382)	loss 4.0311 (3.3615)	grad_norm 1.1787 (1.4040/0.5540)	mem 34602MB
[2025-01-19 09:14:37 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][80/312]	eta 0:02:54 lr 0.002467	time 0.7251 (0.7521)	model_time 0.7246 (0.7362)	loss 3.2620 (3.3385)	grad_norm 1.2686 (1.3606/0.5353)	mem 34602MB
[2025-01-19 09:14:45 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][90/312]	eta 0:02:46 lr 0.002466	time 0.8040 (0.7514)	model_time 0.8039 (0.7371)	loss 2.7722 (3.3036)	grad_norm 1.1611 (1.3668/0.5201)	mem 34602MB
[2025-01-19 09:14:53 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][100/312]	eta 0:02:39 lr 0.002466	time 0.7209 (0.7523)	model_time 0.7204 (0.7395)	loss 4.1374 (3.3014)	grad_norm 2.7500 (1.3863/0.5569)	mem 34602MB
[2025-01-19 09:15:00 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][110/312]	eta 0:02:31 lr 0.002465	time 0.7177 (0.7520)	model_time 0.7172 (0.7403)	loss 3.8618 (3.2832)	grad_norm 2.5116 (1.4111/0.5718)	mem 34602MB
[2025-01-19 09:15:08 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][120/312]	eta 0:02:24 lr 0.002464	time 0.7965 (0.7528)	model_time 0.7961 (0.7420)	loss 3.0959 (3.2821)	grad_norm 0.8067 (1.4040/0.5591)	mem 34602MB
[2025-01-19 09:15:15 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][130/312]	eta 0:02:17 lr 0.002464	time 0.8089 (0.7533)	model_time 0.8088 (0.7433)	loss 3.4698 (3.2899)	grad_norm 3.1433 (1.4271/0.5775)	mem 34602MB
[2025-01-19 09:15:23 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][140/312]	eta 0:02:09 lr 0.002463	time 0.7520 (0.7530)	model_time 0.7518 (0.7437)	loss 2.3033 (3.2942)	grad_norm 1.0909 (1.4302/0.5695)	mem 34602MB
[2025-01-19 09:15:30 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][150/312]	eta 0:02:01 lr 0.002462	time 0.7146 (0.7513)	model_time 0.7142 (0.7425)	loss 2.4367 (3.2843)	grad_norm 1.9595 (1.4441/0.5650)	mem 34602MB
[2025-01-19 09:15:38 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][160/312]	eta 0:01:54 lr 0.002462	time 0.8047 (0.7517)	model_time 0.8046 (0.7435)	loss 3.5656 (3.2994)	grad_norm 0.8388 (1.4330/0.5623)	mem 34602MB
[2025-01-19 09:15:45 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][170/312]	eta 0:01:46 lr 0.002461	time 0.7218 (0.7504)	model_time 0.7217 (0.7427)	loss 3.9788 (3.2931)	grad_norm 1.2180 (1.4089/0.5582)	mem 34602MB
[2025-01-19 09:15:52 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][180/312]	eta 0:01:38 lr 0.002460	time 0.7258 (0.7496)	model_time 0.7254 (0.7423)	loss 3.6123 (3.2960)	grad_norm 1.3986 (1.4112/0.5490)	mem 34602MB
[2025-01-19 09:15:59 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][190/312]	eta 0:01:31 lr 0.002460	time 0.7289 (0.7484)	model_time 0.7288 (0.7414)	loss 2.8034 (3.2832)	grad_norm 2.3466 (1.4241/0.5580)	mem 34602MB
[2025-01-19 09:16:07 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][200/312]	eta 0:01:23 lr 0.002459	time 0.7405 (0.7474)	model_time 0.7403 (0.7407)	loss 3.9912 (3.2804)	grad_norm 1.0292 (1.4208/0.5489)	mem 34602MB
[2025-01-19 09:16:14 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][210/312]	eta 0:01:16 lr 0.002459	time 0.8127 (0.7470)	model_time 0.8122 (0.7407)	loss 3.5311 (3.2906)	grad_norm 1.1439 (1.4116/0.5440)	mem 34602MB
[2025-01-19 09:16:22 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][220/312]	eta 0:01:08 lr 0.002458	time 0.7160 (0.7477)	model_time 0.7158 (0.7416)	loss 2.9637 (3.2902)	grad_norm 2.3082 (1.4118/0.5386)	mem 34602MB
[2025-01-19 09:16:29 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][230/312]	eta 0:01:01 lr 0.002457	time 0.7251 (0.7481)	model_time 0.7247 (0.7423)	loss 3.9720 (3.2885)	grad_norm 1.2495 (1.4099/0.5309)	mem 34602MB
[2025-01-19 09:16:37 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][240/312]	eta 0:00:53 lr 0.002457	time 0.7913 (0.7493)	model_time 0.7908 (0.7437)	loss 2.6166 (3.2930)	grad_norm 1.3779 (1.4014/0.5285)	mem 34602MB
[2025-01-19 09:16:45 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][250/312]	eta 0:00:46 lr 0.002456	time 0.8233 (0.7495)	model_time 0.8232 (0.7441)	loss 2.7275 (3.2874)	grad_norm 2.4206 (1.4121/0.5354)	mem 34602MB
[2025-01-19 09:16:52 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][260/312]	eta 0:00:38 lr 0.002455	time 0.7238 (0.7495)	model_time 0.7233 (0.7443)	loss 3.9434 (3.2873)	grad_norm 0.9242 (1.4223/0.5520)	mem 34602MB
[2025-01-19 09:16:59 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][270/312]	eta 0:00:31 lr 0.002455	time 0.7215 (0.7485)	model_time 0.7213 (0.7435)	loss 3.0466 (3.2898)	grad_norm 2.5403 (1.4240/0.5562)	mem 34602MB
[2025-01-19 09:17:07 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][280/312]	eta 0:00:23 lr 0.002454	time 0.8137 (0.7492)	model_time 0.8132 (0.7443)	loss 3.5957 (3.2872)	grad_norm 0.9189 (1.4198/0.5492)	mem 34602MB
[2025-01-19 09:17:14 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][290/312]	eta 0:00:16 lr 0.002453	time 0.7257 (0.7483)	model_time 0.7252 (0.7436)	loss 3.5781 (3.2859)	grad_norm 1.1590 (1.4283/0.5562)	mem 34602MB
[2025-01-19 09:17:22 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][300/312]	eta 0:00:08 lr 0.002453	time 0.7129 (0.7477)	model_time 0.7128 (0.7432)	loss 2.4515 (3.2805)	grad_norm 2.6158 (1.4308/0.5550)	mem 34602MB
[2025-01-19 09:17:29 internimage_b_1k_224] (main.py 510): INFO Train: [128/300][310/312]	eta 0:00:01 lr 0.002452	time 0.7136 (0.7468)	model_time 0.7135 (0.7423)	loss 3.7330 (3.2770)	grad_norm 0.5830 (1.4455/0.5688)	mem 34602MB
[2025-01-19 09:17:30 internimage_b_1k_224] (main.py 519): INFO EPOCH 128 training takes 0:03:52
[2025-01-19 09:17:30 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_128.pth saving......
[2025-01-19 09:17:33 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_128.pth saved !!!
[2025-01-19 09:17:40 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.301 (7.301)	Loss 0.8185 (0.8185)	Acc@1 82.837 (82.837)	Acc@5 96.704 (96.704)	Mem 34602MB
[2025-01-19 09:17:43 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.934)	Loss 1.1284 (0.9726)	Acc@1 75.781 (79.634)	Acc@5 93.164 (95.040)	Mem 34602MB
[2025-01-19 09:17:43 internimage_b_1k_224] (main.py 575): INFO [Epoch:128] * Acc@1 79.611 Acc@5 95.110
[2025-01-19 09:17:43 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.6%
[2025-01-19 09:17:43 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.68%
[2025-01-19 09:17:52 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.109 (9.109)	Loss 0.6582 (0.6582)	Acc@1 83.350 (83.350)	Acc@5 97.119 (97.119)	Mem 34602MB
[2025-01-19 09:17:57 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.229)	Loss 0.9992 (0.8125)	Acc@1 75.293 (80.185)	Acc@5 93.457 (95.321)	Mem 34602MB
[2025-01-19 09:17:57 internimage_b_1k_224] (main.py 575): INFO [Epoch:128] * Acc@1 80.056 Acc@5 95.381
[2025-01-19 09:17:57 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.1%
[2025-01-19 09:17:57 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 09:18:01 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 09:18:01 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.06%
[2025-01-19 09:18:03 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][0/312]	eta 0:10:13 lr 0.002452	time 1.9648 (1.9648)	model_time 0.7342 (0.7342)	loss 3.5062 (3.5062)	grad_norm 0.9517 (0.9517/0.0000)	mem 34602MB
[2025-01-19 09:18:10 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][10/312]	eta 0:04:13 lr 0.002451	time 0.7428 (0.8384)	model_time 0.7427 (0.7262)	loss 3.1507 (3.3723)	grad_norm 0.9839 (1.1632/0.4422)	mem 34602MB
[2025-01-19 09:18:18 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][20/312]	eta 0:03:51 lr 0.002451	time 0.8274 (0.7935)	model_time 0.8270 (0.7346)	loss 3.7163 (3.4636)	grad_norm 0.7258 (1.0828/0.3768)	mem 34602MB
[2025-01-19 09:18:25 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][30/312]	eta 0:03:40 lr 0.002450	time 0.7963 (0.7836)	model_time 0.7962 (0.7435)	loss 3.8582 (3.4149)	grad_norm 1.2182 (1.1716/0.4340)	mem 34602MB
[2025-01-19 09:18:33 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][40/312]	eta 0:03:30 lr 0.002449	time 0.7177 (0.7729)	model_time 0.7173 (0.7425)	loss 3.7117 (3.4569)	grad_norm 1.1456 (1.2253/0.4519)	mem 34602MB
[2025-01-19 09:18:40 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][50/312]	eta 0:03:21 lr 0.002449	time 0.7560 (0.7689)	model_time 0.7559 (0.7444)	loss 3.2666 (3.4464)	grad_norm 2.7568 (1.2831/0.5000)	mem 34602MB
[2025-01-19 09:18:48 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][60/312]	eta 0:03:13 lr 0.002448	time 0.7167 (0.7660)	model_time 0.7164 (0.7455)	loss 3.9814 (3.4564)	grad_norm 1.2936 (1.4187/0.6188)	mem 34602MB
[2025-01-19 09:18:55 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][70/312]	eta 0:03:04 lr 0.002447	time 0.7279 (0.7629)	model_time 0.7277 (0.7452)	loss 3.2660 (3.4315)	grad_norm 0.9052 (1.4451/0.6070)	mem 34602MB
[2025-01-19 09:19:03 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][80/312]	eta 0:02:56 lr 0.002447	time 0.7171 (0.7593)	model_time 0.7165 (0.7437)	loss 3.6363 (3.4003)	grad_norm 1.0746 (1.4528/0.5959)	mem 34602MB
[2025-01-19 09:19:10 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][90/312]	eta 0:02:48 lr 0.002446	time 0.7252 (0.7585)	model_time 0.7251 (0.7447)	loss 3.0592 (3.3642)	grad_norm 2.0306 (1.4344/0.5810)	mem 34602MB
[2025-01-19 09:19:18 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][100/312]	eta 0:02:40 lr 0.002445	time 0.7258 (0.7560)	model_time 0.7254 (0.7434)	loss 2.3864 (3.3376)	grad_norm 0.7994 (1.4549/0.5779)	mem 34602MB
[2025-01-19 09:19:25 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][110/312]	eta 0:02:32 lr 0.002445	time 0.7263 (0.7538)	model_time 0.7258 (0.7423)	loss 3.1230 (3.3203)	grad_norm 0.7355 (1.4495/0.5727)	mem 34602MB
[2025-01-19 09:19:32 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][120/312]	eta 0:02:24 lr 0.002444	time 0.7268 (0.7516)	model_time 0.7267 (0.7410)	loss 3.1172 (3.3114)	grad_norm 1.4653 (1.4213/0.5591)	mem 34602MB
[2025-01-19 09:19:39 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][130/312]	eta 0:02:16 lr 0.002443	time 0.7164 (0.7500)	model_time 0.7160 (0.7403)	loss 2.8955 (3.3156)	grad_norm 1.6891 (1.4357/0.5770)	mem 34602MB
[2025-01-19 09:19:47 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][140/312]	eta 0:02:08 lr 0.002443	time 0.7938 (0.7491)	model_time 0.7937 (0.7400)	loss 3.4176 (3.3214)	grad_norm 0.9302 (1.4316/0.5682)	mem 34602MB
[2025-01-19 09:19:54 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][150/312]	eta 0:02:01 lr 0.002442	time 0.7983 (0.7494)	model_time 0.7979 (0.7409)	loss 2.7931 (3.3183)	grad_norm 1.0650 (1.4346/0.5646)	mem 34602MB
[2025-01-19 09:20:02 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][160/312]	eta 0:01:54 lr 0.002442	time 0.7306 (0.7502)	model_time 0.7302 (0.7422)	loss 3.6277 (3.2972)	grad_norm 2.0712 (1.4372/0.5587)	mem 34602MB
[2025-01-19 09:20:10 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][170/312]	eta 0:01:46 lr 0.002441	time 0.7179 (0.7512)	model_time 0.7178 (0.7437)	loss 4.2006 (3.2950)	grad_norm 2.0607 (1.4500/0.5568)	mem 34602MB
[2025-01-19 09:20:17 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][180/312]	eta 0:01:39 lr 0.002440	time 0.7206 (0.7517)	model_time 0.7202 (0.7445)	loss 3.1864 (3.2944)	grad_norm 0.8297 (1.4356/0.5468)	mem 34602MB
[2025-01-19 09:20:25 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][190/312]	eta 0:01:31 lr 0.002440	time 0.7374 (0.7511)	model_time 0.7372 (0.7443)	loss 2.3832 (3.2872)	grad_norm 1.0137 (1.4330/0.5399)	mem 34602MB
[2025-01-19 09:20:32 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][200/312]	eta 0:01:24 lr 0.002439	time 0.7183 (0.7501)	model_time 0.7178 (0.7436)	loss 3.6870 (3.2940)	grad_norm 2.6189 (1.4516/0.5643)	mem 34602MB
[2025-01-19 09:20:39 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][210/312]	eta 0:01:16 lr 0.002438	time 0.7262 (0.7500)	model_time 0.7257 (0.7438)	loss 3.2665 (3.3011)	grad_norm 2.1340 (1.4583/0.5677)	mem 34602MB
[2025-01-19 09:20:47 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][220/312]	eta 0:01:08 lr 0.002438	time 0.7152 (0.7493)	model_time 0.7150 (0.7434)	loss 2.7234 (3.3165)	grad_norm 1.3989 (1.4527/0.5629)	mem 34602MB
[2025-01-19 09:20:54 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][230/312]	eta 0:01:01 lr 0.002437	time 0.7456 (0.7487)	model_time 0.7452 (0.7430)	loss 4.0728 (3.3201)	grad_norm 0.7521 (1.4387/0.5565)	mem 34602MB
[2025-01-19 09:21:01 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][240/312]	eta 0:00:53 lr 0.002436	time 0.7230 (0.7478)	model_time 0.7228 (0.7423)	loss 3.0156 (3.3269)	grad_norm 1.9491 (1.4400/0.5618)	mem 34602MB
[2025-01-19 09:21:09 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][250/312]	eta 0:00:46 lr 0.002436	time 0.7182 (0.7469)	model_time 0.7180 (0.7416)	loss 2.9123 (3.3303)	grad_norm 0.8482 (1.4334/0.5597)	mem 34602MB
[2025-01-19 09:21:16 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][260/312]	eta 0:00:38 lr 0.002435	time 0.7966 (0.7464)	model_time 0.7965 (0.7413)	loss 3.7032 (3.3320)	grad_norm 1.9033 (1.4320/0.5529)	mem 34602MB
[2025-01-19 09:21:23 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][270/312]	eta 0:00:31 lr 0.002434	time 0.7974 (0.7466)	model_time 0.7972 (0.7416)	loss 3.5431 (3.3341)	grad_norm 0.9666 (1.4391/0.5511)	mem 34602MB
[2025-01-19 09:21:31 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][280/312]	eta 0:00:23 lr 0.002434	time 0.7161 (0.7478)	model_time 0.7157 (0.7430)	loss 3.5162 (3.3370)	grad_norm 1.6635 (1.4361/0.5542)	mem 34602MB
[2025-01-19 09:21:39 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][290/312]	eta 0:00:16 lr 0.002433	time 0.7178 (0.7478)	model_time 0.7176 (0.7432)	loss 3.1580 (3.3325)	grad_norm 0.7538 (1.4242/0.5525)	mem 34602MB
[2025-01-19 09:21:46 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][300/312]	eta 0:00:08 lr 0.002432	time 0.7156 (0.7479)	model_time 0.7155 (0.7434)	loss 2.7522 (3.3251)	grad_norm 1.0011 (1.4224/0.5493)	mem 34602MB
[2025-01-19 09:21:54 internimage_b_1k_224] (main.py 510): INFO Train: [129/300][310/312]	eta 0:00:01 lr 0.002432	time 0.7140 (0.7477)	model_time 0.7139 (0.7434)	loss 3.0804 (3.3167)	grad_norm 0.7041 (1.4238/0.5468)	mem 34602MB
[2025-01-19 09:21:54 internimage_b_1k_224] (main.py 519): INFO EPOCH 129 training takes 0:03:53
[2025-01-19 09:21:54 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_129.pth saving......
[2025-01-19 09:21:58 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_129.pth saved !!!
[2025-01-19 09:22:05 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.296 (7.296)	Loss 0.8147 (0.8147)	Acc@1 83.105 (83.105)	Acc@5 96.899 (96.899)	Mem 34602MB
[2025-01-19 09:22:08 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.929)	Loss 1.1507 (0.9676)	Acc@1 73.926 (79.672)	Acc@5 93.457 (95.199)	Mem 34602MB
[2025-01-19 09:22:08 internimage_b_1k_224] (main.py 575): INFO [Epoch:129] * Acc@1 79.619 Acc@5 95.232
[2025-01-19 09:22:08 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.6%
[2025-01-19 09:22:08 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.68%
[2025-01-19 09:22:17 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.110 (9.110)	Loss 0.6571 (0.6571)	Acc@1 83.398 (83.398)	Acc@5 97.119 (97.119)	Mem 34602MB
[2025-01-19 09:22:22 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.234)	Loss 0.9963 (0.8107)	Acc@1 75.415 (80.253)	Acc@5 93.506 (95.337)	Mem 34602MB
[2025-01-19 09:22:22 internimage_b_1k_224] (main.py 575): INFO [Epoch:129] * Acc@1 80.130 Acc@5 95.397
[2025-01-19 09:22:22 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.1%
[2025-01-19 09:22:22 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 09:22:26 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 09:22:26 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.13%
[2025-01-19 09:22:28 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][0/312]	eta 0:12:02 lr 0.002432	time 2.3145 (2.3145)	model_time 0.7424 (0.7424)	loss 3.2153 (3.2153)	grad_norm 0.7091 (0.7091/0.0000)	mem 34602MB
[2025-01-19 09:22:35 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][10/312]	eta 0:04:25 lr 0.002431	time 0.7171 (0.8805)	model_time 0.7170 (0.7374)	loss 4.1089 (3.5078)	grad_norm 1.5641 (1.7095/0.7170)	mem 34602MB
[2025-01-19 09:22:43 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][20/312]	eta 0:03:59 lr 0.002430	time 0.7338 (0.8194)	model_time 0.7334 (0.7442)	loss 3.3950 (3.4678)	grad_norm 0.9930 (1.7496/0.8292)	mem 34602MB
[2025-01-19 09:22:50 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][30/312]	eta 0:03:43 lr 0.002430	time 0.7209 (0.7914)	model_time 0.7208 (0.7404)	loss 3.2776 (3.3624)	grad_norm 2.1696 (1.7033/0.7719)	mem 34602MB
[2025-01-19 09:22:58 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][40/312]	eta 0:03:31 lr 0.002429	time 0.7168 (0.7788)	model_time 0.7163 (0.7401)	loss 3.3837 (3.3325)	grad_norm 0.9905 (1.6434/0.7339)	mem 34602MB
[2025-01-19 09:23:05 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][50/312]	eta 0:03:21 lr 0.002428	time 0.7267 (0.7683)	model_time 0.7265 (0.7371)	loss 3.3413 (3.2983)	grad_norm 2.8048 (1.7330/0.7886)	mem 34602MB
[2025-01-19 09:23:12 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][60/312]	eta 0:03:11 lr 0.002428	time 0.7490 (0.7618)	model_time 0.7486 (0.7356)	loss 3.2441 (3.3018)	grad_norm 1.4538 (1.6701/0.7395)	mem 34602MB
[2025-01-19 09:23:20 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][70/312]	eta 0:03:03 lr 0.002427	time 0.7167 (0.7572)	model_time 0.7165 (0.7347)	loss 2.9364 (3.2755)	grad_norm 1.6284 (1.6105/0.7117)	mem 34602MB
[2025-01-19 09:23:27 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][80/312]	eta 0:02:55 lr 0.002426	time 0.8017 (0.7579)	model_time 0.8013 (0.7382)	loss 3.1402 (3.2750)	grad_norm 1.0180 (1.6199/0.7125)	mem 34602MB
[2025-01-19 09:23:35 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][90/312]	eta 0:02:48 lr 0.002426	time 0.7203 (0.7585)	model_time 0.7202 (0.7409)	loss 3.7396 (3.2761)	grad_norm 1.3461 (1.5903/0.6855)	mem 34602MB
[2025-01-19 09:23:42 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][100/312]	eta 0:02:40 lr 0.002425	time 0.7201 (0.7576)	model_time 0.7196 (0.7417)	loss 3.4245 (3.2667)	grad_norm 2.1257 (1.6230/0.6826)	mem 34602MB
[2025-01-19 09:23:50 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][110/312]	eta 0:02:33 lr 0.002425	time 0.8169 (0.7578)	model_time 0.8168 (0.7433)	loss 3.5576 (3.2893)	grad_norm 0.7918 (1.5609/0.6851)	mem 34602MB
[2025-01-19 09:23:57 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][120/312]	eta 0:02:25 lr 0.002424	time 0.7374 (0.7566)	model_time 0.7370 (0.7433)	loss 3.1374 (3.2773)	grad_norm 2.4399 (1.5418/0.6759)	mem 34602MB
[2025-01-19 09:24:05 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][130/312]	eta 0:02:17 lr 0.002423	time 0.7623 (0.7546)	model_time 0.7622 (0.7423)	loss 3.9068 (3.2584)	grad_norm 1.2123 (1.5485/0.6680)	mem 34602MB
[2025-01-19 09:24:12 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][140/312]	eta 0:02:09 lr 0.002423	time 0.7187 (0.7556)	model_time 0.7185 (0.7441)	loss 2.3357 (3.2516)	grad_norm 1.9216 (1.5521/0.6899)	mem 34602MB
[2025-01-19 09:24:20 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][150/312]	eta 0:02:02 lr 0.002422	time 0.7247 (0.7534)	model_time 0.7245 (0.7426)	loss 3.2180 (3.2565)	grad_norm 1.7969 (1.5258/0.6826)	mem 34602MB
[2025-01-19 09:24:27 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][160/312]	eta 0:01:54 lr 0.002421	time 0.7165 (0.7525)	model_time 0.7163 (0.7423)	loss 3.1483 (3.2618)	grad_norm 0.7625 (1.5079/0.6773)	mem 34602MB
[2025-01-19 09:24:34 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][170/312]	eta 0:01:46 lr 0.002421	time 0.7182 (0.7508)	model_time 0.7177 (0.7412)	loss 2.7574 (3.2719)	grad_norm 0.9812 (1.4946/0.6677)	mem 34602MB
[2025-01-19 09:24:41 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][180/312]	eta 0:01:38 lr 0.002420	time 0.7161 (0.7494)	model_time 0.7159 (0.7403)	loss 2.3225 (3.2675)	grad_norm 1.5327 (1.5075/0.6597)	mem 34602MB
[2025-01-19 09:24:49 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][190/312]	eta 0:01:31 lr 0.002419	time 0.7402 (0.7482)	model_time 0.7397 (0.7395)	loss 3.5557 (3.2742)	grad_norm 2.1554 (1.5155/0.6493)	mem 34602MB
[2025-01-19 09:24:56 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][200/312]	eta 0:01:23 lr 0.002419	time 0.8049 (0.7486)	model_time 0.8047 (0.7404)	loss 3.1171 (3.2677)	grad_norm 2.1351 (1.5101/0.6423)	mem 34602MB
[2025-01-19 09:25:04 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][210/312]	eta 0:01:16 lr 0.002418	time 0.7331 (0.7494)	model_time 0.7330 (0.7416)	loss 2.8430 (3.2611)	grad_norm 0.9209 (1.4885/0.6374)	mem 34602MB
[2025-01-19 09:25:11 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][220/312]	eta 0:01:08 lr 0.002417	time 0.7155 (0.7493)	model_time 0.7150 (0.7418)	loss 2.6840 (3.2604)	grad_norm 1.4824 (1.4811/0.6389)	mem 34602MB
[2025-01-19 09:25:19 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][230/312]	eta 0:01:01 lr 0.002417	time 0.8556 (0.7504)	model_time 0.8555 (0.7432)	loss 3.2140 (3.2567)	grad_norm 1.3608 (1.4777/0.6368)	mem 34602MB
[2025-01-19 09:25:27 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][240/312]	eta 0:00:54 lr 0.002416	time 0.7323 (0.7502)	model_time 0.7321 (0.7433)	loss 3.0880 (3.2521)	grad_norm 1.0308 (1.5108/0.6746)	mem 34602MB
[2025-01-19 09:25:34 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][250/312]	eta 0:00:46 lr 0.002415	time 0.7228 (0.7492)	model_time 0.7224 (0.7425)	loss 3.8003 (3.2538)	grad_norm 1.8984 (1.5361/0.6904)	mem 34602MB
[2025-01-19 09:25:42 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][260/312]	eta 0:00:38 lr 0.002415	time 0.7148 (0.7499)	model_time 0.7147 (0.7435)	loss 3.2082 (3.2554)	grad_norm 2.1398 (1.5302/0.6815)	mem 34602MB
[2025-01-19 09:25:49 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][270/312]	eta 0:00:31 lr 0.002414	time 0.7252 (0.7492)	model_time 0.7247 (0.7431)	loss 3.6399 (3.2468)	grad_norm 2.2522 (1.5287/0.6740)	mem 34602MB
[2025-01-19 09:25:56 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][280/312]	eta 0:00:23 lr 0.002413	time 0.7302 (0.7486)	model_time 0.7301 (0.7426)	loss 3.2508 (3.2407)	grad_norm 0.9157 (1.5354/0.6720)	mem 34602MB
[2025-01-19 09:26:03 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][290/312]	eta 0:00:16 lr 0.002413	time 0.7177 (0.7477)	model_time 0.7173 (0.7419)	loss 3.1104 (3.2346)	grad_norm 1.2331 (1.5181/0.6687)	mem 34602MB
[2025-01-19 09:26:11 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][300/312]	eta 0:00:08 lr 0.002412	time 0.7266 (0.7469)	model_time 0.7265 (0.7413)	loss 3.2555 (3.2421)	grad_norm 1.7757 (1.5174/0.6607)	mem 34602MB
[2025-01-19 09:26:18 internimage_b_1k_224] (main.py 510): INFO Train: [130/300][310/312]	eta 0:00:01 lr 0.002411	time 0.7142 (0.7460)	model_time 0.7141 (0.7406)	loss 3.7104 (3.2480)	grad_norm 1.6775 (1.5146/0.6624)	mem 34602MB
[2025-01-19 09:26:19 internimage_b_1k_224] (main.py 519): INFO EPOCH 130 training takes 0:03:52
[2025-01-19 09:26:19 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_130.pth saving......
[2025-01-19 09:26:22 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_130.pth saved !!!
[2025-01-19 09:26:29 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.563 (7.563)	Loss 0.8232 (0.8232)	Acc@1 82.544 (82.544)	Acc@5 96.680 (96.680)	Mem 34602MB
[2025-01-19 09:26:32 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.946)	Loss 1.1205 (0.9665)	Acc@1 76.147 (79.836)	Acc@5 93.677 (95.146)	Mem 34602MB
[2025-01-19 09:26:32 internimage_b_1k_224] (main.py 575): INFO [Epoch:130] * Acc@1 79.746 Acc@5 95.182
[2025-01-19 09:26:32 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.7%
[2025-01-19 09:26:32 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 09:26:36 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 09:26:36 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.75%
[2025-01-19 09:26:43 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.309 (7.309)	Loss 0.6563 (0.6563)	Acc@1 83.472 (83.472)	Acc@5 97.095 (97.095)	Mem 34602MB
[2025-01-19 09:26:46 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.928)	Loss 0.9937 (0.8090)	Acc@1 75.415 (80.302)	Acc@5 93.506 (95.368)	Mem 34602MB
[2025-01-19 09:26:46 internimage_b_1k_224] (main.py 575): INFO [Epoch:130] * Acc@1 80.186 Acc@5 95.427
[2025-01-19 09:26:46 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.2%
[2025-01-19 09:26:46 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 09:26:50 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 09:26:50 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.19%
[2025-01-19 09:26:52 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][0/312]	eta 0:11:36 lr 0.002411	time 2.2308 (2.2308)	model_time 0.7459 (0.7459)	loss 2.3893 (2.3893)	grad_norm 0.8874 (0.8874/0.0000)	mem 34602MB
[2025-01-19 09:27:00 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][10/312]	eta 0:04:31 lr 0.002411	time 0.7205 (0.8976)	model_time 0.7204 (0.7624)	loss 3.5639 (3.1570)	grad_norm 1.6006 (1.2881/0.3827)	mem 34602MB
[2025-01-19 09:27:08 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][20/312]	eta 0:04:03 lr 0.002410	time 0.7179 (0.8328)	model_time 0.7178 (0.7618)	loss 3.1447 (3.0512)	grad_norm 0.9557 (1.5988/0.6979)	mem 34602MB
[2025-01-19 09:27:15 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][30/312]	eta 0:03:47 lr 0.002409	time 0.7350 (0.8072)	model_time 0.7348 (0.7590)	loss 4.3419 (3.1993)	grad_norm 1.6811 (1.4958/0.6592)	mem 34602MB
[2025-01-19 09:27:23 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][40/312]	eta 0:03:36 lr 0.002409	time 0.7201 (0.7955)	model_time 0.7199 (0.7590)	loss 3.4929 (3.1360)	grad_norm 1.3728 (1.5442/0.6527)	mem 34602MB
[2025-01-19 09:27:30 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][50/312]	eta 0:03:26 lr 0.002408	time 0.7277 (0.7877)	model_time 0.7276 (0.7583)	loss 3.1677 (3.1716)	grad_norm 2.2174 (1.5390/0.6308)	mem 34602MB
[2025-01-19 09:27:38 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][60/312]	eta 0:03:16 lr 0.002407	time 0.7163 (0.7800)	model_time 0.7159 (0.7553)	loss 3.5622 (3.1636)	grad_norm 1.2026 (1.5124/0.5904)	mem 34602MB
[2025-01-19 09:27:45 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][70/312]	eta 0:03:08 lr 0.002407	time 0.7149 (0.7782)	model_time 0.7147 (0.7569)	loss 3.0609 (3.1505)	grad_norm 1.4748 (1.5055/0.5835)	mem 34602MB
[2025-01-19 09:27:53 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][80/312]	eta 0:02:59 lr 0.002406	time 0.7311 (0.7725)	model_time 0.7307 (0.7539)	loss 3.4408 (3.1492)	grad_norm 0.9025 (1.4640/0.5675)	mem 34602MB
[2025-01-19 09:28:00 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][90/312]	eta 0:02:50 lr 0.002405	time 0.7246 (0.7683)	model_time 0.7245 (0.7517)	loss 3.8438 (3.1559)	grad_norm 1.4725 (1.4751/0.5608)	mem 34602MB
[2025-01-19 09:28:07 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][100/312]	eta 0:02:42 lr 0.002405	time 0.7626 (0.7647)	model_time 0.7624 (0.7497)	loss 3.6476 (3.1683)	grad_norm 0.8139 (1.5128/0.6167)	mem 34602MB
[2025-01-19 09:28:15 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][110/312]	eta 0:02:33 lr 0.002404	time 0.7154 (0.7615)	model_time 0.7152 (0.7478)	loss 4.0552 (3.1898)	grad_norm 1.8725 (1.5155/0.6059)	mem 34602MB
[2025-01-19 09:28:22 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][120/312]	eta 0:02:25 lr 0.002404	time 0.7177 (0.7590)	model_time 0.7172 (0.7464)	loss 3.7349 (3.2021)	grad_norm 1.6970 (1.5260/0.5964)	mem 34602MB
[2025-01-19 09:28:30 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][130/312]	eta 0:02:18 lr 0.002403	time 0.8205 (0.7598)	model_time 0.8200 (0.7482)	loss 3.6124 (3.2054)	grad_norm 1.0470 (1.5062/0.5826)	mem 34602MB
[2025-01-19 09:28:37 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][140/312]	eta 0:02:10 lr 0.002402	time 0.7261 (0.7589)	model_time 0.7259 (0.7481)	loss 3.2932 (3.2085)	grad_norm 2.7903 (1.5278/0.5869)	mem 34602MB
[2025-01-19 09:28:45 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][150/312]	eta 0:02:02 lr 0.002402	time 0.7172 (0.7591)	model_time 0.7170 (0.7489)	loss 3.5370 (3.2202)	grad_norm 1.7927 (1.5219/0.5805)	mem 34602MB
[2025-01-19 09:28:52 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][160/312]	eta 0:01:55 lr 0.002401	time 0.7159 (0.7591)	model_time 0.7157 (0.7495)	loss 3.2685 (3.2381)	grad_norm 1.1701 (1.5039/0.5713)	mem 34602MB
[2025-01-19 09:29:00 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][170/312]	eta 0:01:47 lr 0.002400	time 0.7250 (0.7584)	model_time 0.7246 (0.7494)	loss 3.5984 (3.2409)	grad_norm 2.0073 (1.4896/0.5651)	mem 34602MB
[2025-01-19 09:29:07 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][180/312]	eta 0:01:39 lr 0.002400	time 0.7406 (0.7575)	model_time 0.7404 (0.7490)	loss 2.7294 (3.2454)	grad_norm 0.7026 (1.4766/0.5616)	mem 34602MB
[2025-01-19 09:29:15 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][190/312]	eta 0:01:32 lr 0.002399	time 0.7155 (0.7578)	model_time 0.7153 (0.7497)	loss 3.4623 (3.2458)	grad_norm 1.4054 (1.4751/0.5651)	mem 34602MB
[2025-01-19 09:29:22 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][200/312]	eta 0:01:24 lr 0.002398	time 0.7266 (0.7563)	model_time 0.7265 (0.7485)	loss 3.1201 (3.2538)	grad_norm 1.8730 (1.4980/0.5870)	mem 34602MB
[2025-01-19 09:29:30 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][210/312]	eta 0:01:17 lr 0.002398	time 0.7205 (0.7553)	model_time 0.7204 (0.7479)	loss 2.2639 (3.2558)	grad_norm 3.3581 (1.5369/0.6196)	mem 34602MB
[2025-01-19 09:29:37 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][220/312]	eta 0:01:09 lr 0.002397	time 0.7217 (0.7537)	model_time 0.7216 (0.7467)	loss 3.5592 (3.2651)	grad_norm 0.7035 (1.5541/0.6305)	mem 34602MB
[2025-01-19 09:29:44 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][230/312]	eta 0:01:01 lr 0.002396	time 0.7192 (0.7527)	model_time 0.7187 (0.7459)	loss 2.6724 (3.2718)	grad_norm 1.5789 (1.5387/0.6244)	mem 34602MB
[2025-01-19 09:29:51 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][240/312]	eta 0:00:54 lr 0.002396	time 0.7175 (0.7517)	model_time 0.7173 (0.7452)	loss 3.7349 (3.2751)	grad_norm 0.8148 (1.5288/0.6193)	mem 34602MB
[2025-01-19 09:29:59 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][250/312]	eta 0:00:46 lr 0.002395	time 0.8168 (0.7523)	model_time 0.8166 (0.7461)	loss 2.6036 (3.2825)	grad_norm 0.9916 (1.5136/0.6135)	mem 34602MB
[2025-01-19 09:30:07 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][260/312]	eta 0:00:39 lr 0.002394	time 0.7172 (0.7526)	model_time 0.7167 (0.7466)	loss 3.5100 (3.2890)	grad_norm 0.7423 (1.5046/0.6089)	mem 34602MB
[2025-01-19 09:30:14 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][270/312]	eta 0:00:31 lr 0.002394	time 0.7953 (0.7526)	model_time 0.7951 (0.7468)	loss 2.1970 (3.3011)	grad_norm 1.1972 (1.5040/0.6050)	mem 34602MB
[2025-01-19 09:30:22 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][280/312]	eta 0:00:24 lr 0.002393	time 0.7492 (0.7532)	model_time 0.7490 (0.7476)	loss 3.5713 (3.3080)	grad_norm 2.0188 (1.5022/0.6024)	mem 34602MB
[2025-01-19 09:30:29 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][290/312]	eta 0:00:16 lr 0.002392	time 0.7219 (0.7532)	model_time 0.7215 (0.7477)	loss 3.7136 (3.3057)	grad_norm 1.8691 (1.5028/0.5989)	mem 34602MB
[2025-01-19 09:30:37 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][300/312]	eta 0:00:09 lr 0.002392	time 0.7046 (0.7524)	model_time 0.7045 (0.7471)	loss 2.6297 (3.3065)	grad_norm 1.3831 (1.5007/0.5919)	mem 34602MB
[2025-01-19 09:30:44 internimage_b_1k_224] (main.py 510): INFO Train: [131/300][310/312]	eta 0:00:01 lr 0.002391	time 0.7134 (0.7526)	model_time 0.7133 (0.7475)	loss 3.1586 (3.3072)	grad_norm 1.6445 (1.5086/0.5988)	mem 34602MB
[2025-01-19 09:30:45 internimage_b_1k_224] (main.py 519): INFO EPOCH 131 training takes 0:03:54
[2025-01-19 09:30:45 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_131.pth saving......
[2025-01-19 09:30:48 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_131.pth saved !!!
[2025-01-19 09:30:56 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.544 (7.544)	Loss 0.8434 (0.8434)	Acc@1 82.251 (82.251)	Acc@5 96.777 (96.777)	Mem 34602MB
[2025-01-19 09:30:59 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.953)	Loss 1.1147 (0.9723)	Acc@1 75.366 (79.710)	Acc@5 93.628 (95.184)	Mem 34602MB
[2025-01-19 09:30:59 internimage_b_1k_224] (main.py 575): INFO [Epoch:131] * Acc@1 79.607 Acc@5 95.220
[2025-01-19 09:30:59 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.6%
[2025-01-19 09:30:59 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.75%
[2025-01-19 09:31:08 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.903 (8.903)	Loss 0.6554 (0.6554)	Acc@1 83.545 (83.545)	Acc@5 97.192 (97.192)	Mem 34602MB
[2025-01-19 09:31:12 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.223)	Loss 0.9910 (0.8073)	Acc@1 75.488 (80.336)	Acc@5 93.506 (95.399)	Mem 34602MB
[2025-01-19 09:31:13 internimage_b_1k_224] (main.py 575): INFO [Epoch:131] * Acc@1 80.224 Acc@5 95.463
[2025-01-19 09:31:13 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.2%
[2025-01-19 09:31:13 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 09:31:17 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 09:31:17 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.22%
[2025-01-19 09:31:19 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][0/312]	eta 0:10:27 lr 0.002391	time 2.0099 (2.0099)	model_time 0.7544 (0.7544)	loss 2.5502 (2.5502)	grad_norm 1.9729 (1.9729/0.0000)	mem 34602MB
[2025-01-19 09:31:26 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][10/312]	eta 0:04:14 lr 0.002390	time 0.7607 (0.8430)	model_time 0.7605 (0.7286)	loss 3.0817 (3.2380)	grad_norm 1.1045 (1.6905/0.5890)	mem 34602MB
[2025-01-19 09:31:33 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][20/312]	eta 0:03:51 lr 0.002390	time 0.7194 (0.7921)	model_time 0.7192 (0.7320)	loss 4.0879 (3.2972)	grad_norm 1.1470 (1.6283/0.5661)	mem 34602MB
[2025-01-19 09:31:41 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][30/312]	eta 0:03:37 lr 0.002389	time 0.7228 (0.7718)	model_time 0.7223 (0.7309)	loss 3.4242 (3.3118)	grad_norm 2.0581 (1.5571/0.5485)	mem 34602MB
[2025-01-19 09:31:48 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][40/312]	eta 0:03:27 lr 0.002388	time 0.7181 (0.7620)	model_time 0.7176 (0.7310)	loss 2.5801 (3.2445)	grad_norm 1.0831 (1.4944/0.5373)	mem 34602MB
[2025-01-19 09:31:55 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][50/312]	eta 0:03:18 lr 0.002388	time 0.7184 (0.7560)	model_time 0.7183 (0.7311)	loss 3.4057 (3.2253)	grad_norm 3.0503 (1.5557/0.6355)	mem 34602MB
[2025-01-19 09:32:03 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][60/312]	eta 0:03:10 lr 0.002387	time 0.8092 (0.7554)	model_time 0.8090 (0.7344)	loss 3.6693 (3.2221)	grad_norm 1.5505 (1.5765/0.6086)	mem 34602MB
[2025-01-19 09:32:10 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][70/312]	eta 0:03:02 lr 0.002386	time 0.7204 (0.7553)	model_time 0.7202 (0.7373)	loss 2.7480 (3.2124)	grad_norm 0.9365 (1.5183/0.5948)	mem 34602MB
[2025-01-19 09:32:18 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][80/312]	eta 0:02:55 lr 0.002386	time 0.7170 (0.7546)	model_time 0.7168 (0.7388)	loss 2.1323 (3.2092)	grad_norm 1.4638 (1.5227/0.5741)	mem 34602MB
[2025-01-19 09:32:25 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][90/312]	eta 0:02:47 lr 0.002385	time 0.7172 (0.7548)	model_time 0.7170 (0.7407)	loss 2.7626 (3.2330)	grad_norm 1.1209 (1.5278/0.5763)	mem 34602MB
[2025-01-19 09:32:33 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][100/312]	eta 0:02:39 lr 0.002384	time 0.7190 (0.7527)	model_time 0.7186 (0.7399)	loss 3.6828 (3.2708)	grad_norm 1.0874 (1.5149/0.5599)	mem 34602MB
[2025-01-19 09:32:40 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][110/312]	eta 0:02:31 lr 0.002384	time 0.8113 (0.7511)	model_time 0.8111 (0.7395)	loss 4.0542 (3.2852)	grad_norm 1.6991 (1.4949/0.5524)	mem 34602MB
[2025-01-19 09:32:48 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][120/312]	eta 0:02:24 lr 0.002383	time 0.8104 (0.7527)	model_time 0.8102 (0.7420)	loss 2.7042 (3.2848)	grad_norm 2.6487 (1.5246/0.6023)	mem 34602MB
[2025-01-19 09:32:55 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][130/312]	eta 0:02:16 lr 0.002383	time 0.7179 (0.7509)	model_time 0.7177 (0.7410)	loss 3.2699 (3.2808)	grad_norm 0.8453 (1.5129/0.5961)	mem 34602MB
[2025-01-19 09:33:02 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][140/312]	eta 0:02:08 lr 0.002382	time 0.7404 (0.7499)	model_time 0.7402 (0.7406)	loss 3.4358 (3.2666)	grad_norm 1.0173 (1.4937/0.5850)	mem 34602MB
[2025-01-19 09:33:10 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][150/312]	eta 0:02:01 lr 0.002381	time 0.7170 (0.7482)	model_time 0.7166 (0.7396)	loss 3.4080 (3.2639)	grad_norm 1.7595 (1.4919/0.5723)	mem 34602MB
[2025-01-19 09:33:17 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][160/312]	eta 0:01:53 lr 0.002381	time 0.7302 (0.7473)	model_time 0.7300 (0.7392)	loss 3.3620 (3.2468)	grad_norm 1.4109 (1.4865/0.5669)	mem 34602MB
[2025-01-19 09:33:24 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][170/312]	eta 0:01:46 lr 0.002380	time 0.7243 (0.7466)	model_time 0.7242 (0.7389)	loss 2.4561 (3.2431)	grad_norm 0.7246 (1.4885/0.5650)	mem 34602MB
[2025-01-19 09:33:32 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][180/312]	eta 0:01:38 lr 0.002379	time 0.8062 (0.7468)	model_time 0.8058 (0.7395)	loss 2.2131 (3.2591)	grad_norm 0.9306 (1.4851/0.5559)	mem 34602MB
[2025-01-19 09:33:39 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][190/312]	eta 0:01:31 lr 0.002379	time 0.7261 (0.7474)	model_time 0.7258 (0.7404)	loss 3.3444 (3.2705)	grad_norm 0.7989 (1.4648/0.5530)	mem 34602MB
[2025-01-19 09:33:47 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][200/312]	eta 0:01:23 lr 0.002378	time 0.7373 (0.7473)	model_time 0.7372 (0.7407)	loss 3.1490 (3.2723)	grad_norm 1.3994 (1.4495/0.5522)	mem 34602MB
[2025-01-19 09:33:55 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][210/312]	eta 0:01:16 lr 0.002377	time 0.8069 (0.7483)	model_time 0.8068 (0.7420)	loss 3.1554 (3.2761)	grad_norm 1.3366 (1.4527/0.5467)	mem 34602MB
[2025-01-19 09:34:02 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][220/312]	eta 0:01:08 lr 0.002377	time 0.7178 (0.7481)	model_time 0.7176 (0.7420)	loss 2.6884 (3.2763)	grad_norm 0.9565 (1.4576/0.5510)	mem 34602MB
[2025-01-19 09:34:09 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][230/312]	eta 0:01:01 lr 0.002376	time 0.8093 (0.7477)	model_time 0.8088 (0.7419)	loss 3.5679 (3.2796)	grad_norm 1.9712 (1.4506/0.5440)	mem 34602MB
[2025-01-19 09:34:17 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][240/312]	eta 0:00:53 lr 0.002375	time 1.0105 (0.7488)	model_time 1.0101 (0.7432)	loss 2.4287 (3.2639)	grad_norm 1.4325 (1.4898/0.5893)	mem 34602MB
[2025-01-19 09:34:24 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][250/312]	eta 0:00:46 lr 0.002375	time 0.7164 (0.7479)	model_time 0.7162 (0.7426)	loss 2.3681 (3.2643)	grad_norm 1.1522 (1.5045/0.6247)	mem 34602MB
[2025-01-19 09:34:32 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][260/312]	eta 0:00:38 lr 0.002374	time 0.7174 (0.7473)	model_time 0.7172 (0.7421)	loss 3.7908 (3.2707)	grad_norm 0.8239 (1.5077/0.6228)	mem 34602MB
[2025-01-19 09:34:39 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][270/312]	eta 0:00:31 lr 0.002373	time 0.7173 (0.7465)	model_time 0.7169 (0.7415)	loss 3.3365 (3.2673)	grad_norm 2.2674 (1.5088/0.6199)	mem 34602MB
[2025-01-19 09:34:46 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][280/312]	eta 0:00:23 lr 0.002373	time 0.7250 (0.7459)	model_time 0.7248 (0.7410)	loss 1.9058 (3.2556)	grad_norm 2.2357 (1.4988/0.6154)	mem 34602MB
[2025-01-19 09:34:54 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][290/312]	eta 0:00:16 lr 0.002372	time 0.7265 (0.7453)	model_time 0.7263 (0.7406)	loss 3.4701 (3.2586)	grad_norm 0.9614 (1.4871/0.6117)	mem 34602MB
[2025-01-19 09:35:01 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][300/312]	eta 0:00:08 lr 0.002371	time 0.7910 (0.7453)	model_time 0.7909 (0.7408)	loss 3.9374 (3.2606)	grad_norm 0.9748 (1.4813/0.6111)	mem 34602MB
[2025-01-19 09:35:09 internimage_b_1k_224] (main.py 510): INFO Train: [132/300][310/312]	eta 0:00:01 lr 0.002371	time 0.7946 (0.7456)	model_time 0.7945 (0.7412)	loss 3.4531 (3.2574)	grad_norm 1.2645 (1.4829/0.6040)	mem 34602MB
[2025-01-19 09:35:09 internimage_b_1k_224] (main.py 519): INFO EPOCH 132 training takes 0:03:52
[2025-01-19 09:35:09 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_132.pth saving......
[2025-01-19 09:35:12 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_132.pth saved !!!
[2025-01-19 09:35:20 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.292 (7.292)	Loss 0.8212 (0.8212)	Acc@1 83.447 (83.447)	Acc@5 97.021 (97.021)	Mem 34602MB
[2025-01-19 09:35:23 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.920)	Loss 1.1348 (0.9750)	Acc@1 76.489 (80.003)	Acc@5 93.481 (95.299)	Mem 34602MB
[2025-01-19 09:35:23 internimage_b_1k_224] (main.py 575): INFO [Epoch:132] * Acc@1 79.902 Acc@5 95.335
[2025-01-19 09:35:23 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.9%
[2025-01-19 09:35:23 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 09:35:26 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 09:35:26 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.90%
[2025-01-19 09:35:33 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.114 (7.114)	Loss 0.6547 (0.6547)	Acc@1 83.569 (83.569)	Acc@5 97.192 (97.192)	Mem 34602MB
[2025-01-19 09:35:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.910)	Loss 0.9885 (0.8058)	Acc@1 75.562 (80.378)	Acc@5 93.555 (95.390)	Mem 34602MB
[2025-01-19 09:35:37 internimage_b_1k_224] (main.py 575): INFO [Epoch:132] * Acc@1 80.272 Acc@5 95.459
[2025-01-19 09:35:37 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.3%
[2025-01-19 09:35:37 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 09:35:40 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 09:35:40 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.27%
[2025-01-19 09:35:43 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][0/312]	eta 0:11:39 lr 0.002371	time 2.2410 (2.2410)	model_time 0.7419 (0.7419)	loss 2.2122 (2.2122)	grad_norm 1.2335 (1.2335/0.0000)	mem 34602MB
[2025-01-19 09:35:50 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][10/312]	eta 0:04:29 lr 0.002370	time 0.7196 (0.8908)	model_time 0.7195 (0.7543)	loss 3.5044 (3.0400)	grad_norm 1.5323 (1.5935/0.8811)	mem 34602MB
[2025-01-19 09:35:58 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][20/312]	eta 0:04:02 lr 0.002369	time 0.7623 (0.8293)	model_time 0.7619 (0.7576)	loss 3.3327 (3.1582)	grad_norm 1.1410 (1.5488/0.7702)	mem 34602MB
[2025-01-19 09:36:05 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][30/312]	eta 0:03:47 lr 0.002369	time 0.7263 (0.8054)	model_time 0.7261 (0.7568)	loss 3.7602 (3.0970)	grad_norm 2.0477 (1.5834/0.6721)	mem 34602MB
[2025-01-19 09:36:13 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][40/312]	eta 0:03:34 lr 0.002368	time 0.7185 (0.7901)	model_time 0.7180 (0.7532)	loss 3.5923 (3.1235)	grad_norm 1.1705 (1.5572/0.6298)	mem 34602MB
[2025-01-19 09:36:20 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][50/312]	eta 0:03:25 lr 0.002367	time 0.7197 (0.7832)	model_time 0.7196 (0.7535)	loss 2.2172 (3.1339)	grad_norm 1.1716 (1.5015/0.5870)	mem 34602MB
[2025-01-19 09:36:28 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][60/312]	eta 0:03:15 lr 0.002367	time 0.7439 (0.7750)	model_time 0.7438 (0.7501)	loss 4.2583 (3.1636)	grad_norm 2.3441 (1.4692/0.5668)	mem 34602MB
[2025-01-19 09:36:35 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][70/312]	eta 0:03:06 lr 0.002366	time 0.7198 (0.7696)	model_time 0.7197 (0.7482)	loss 3.5329 (3.2332)	grad_norm 1.2202 (1.4648/0.5721)	mem 34602MB
[2025-01-19 09:36:42 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][80/312]	eta 0:02:57 lr 0.002365	time 0.7176 (0.7651)	model_time 0.7171 (0.7463)	loss 3.0923 (3.2453)	grad_norm 1.2568 (1.5188/0.5989)	mem 34602MB
[2025-01-19 09:36:50 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][90/312]	eta 0:02:48 lr 0.002365	time 0.7180 (0.7611)	model_time 0.7178 (0.7443)	loss 3.6026 (3.2636)	grad_norm 1.0439 (1.5501/0.5953)	mem 34602MB
[2025-01-19 09:36:57 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][100/312]	eta 0:02:40 lr 0.002364	time 0.7927 (0.7584)	model_time 0.7923 (0.7432)	loss 3.3253 (3.2700)	grad_norm 1.7772 (1.5335/0.5757)	mem 34602MB
[2025-01-19 09:37:05 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][110/312]	eta 0:02:33 lr 0.002363	time 0.8060 (0.7582)	model_time 0.8058 (0.7443)	loss 2.5354 (3.2450)	grad_norm 0.9762 (1.5156/0.5666)	mem 34602MB
[2025-01-19 09:37:12 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][120/312]	eta 0:02:25 lr 0.002363	time 0.8137 (0.7591)	model_time 0.8132 (0.7464)	loss 3.8777 (3.2522)	grad_norm 1.3344 (1.5229/0.5573)	mem 34602MB
[2025-01-19 09:37:20 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][130/312]	eta 0:02:17 lr 0.002362	time 0.7162 (0.7580)	model_time 0.7160 (0.7462)	loss 3.3173 (3.2546)	grad_norm 0.9350 (1.5162/0.5482)	mem 34602MB
[2025-01-19 09:37:27 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][140/312]	eta 0:02:10 lr 0.002361	time 0.7180 (0.7586)	model_time 0.7179 (0.7476)	loss 3.4909 (3.2407)	grad_norm 2.1561 (1.5199/0.5375)	mem 34602MB
[2025-01-19 09:37:35 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][150/312]	eta 0:02:03 lr 0.002361	time 0.7430 (0.7594)	model_time 0.7429 (0.7491)	loss 2.3781 (3.2191)	grad_norm 1.2824 (1.5089/0.5406)	mem 34602MB
[2025-01-19 09:37:43 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][160/312]	eta 0:01:55 lr 0.002360	time 0.7384 (0.7585)	model_time 0.7382 (0.7488)	loss 4.0435 (3.2283)	grad_norm 2.3264 (1.4963/0.5363)	mem 34602MB
[2025-01-19 09:37:50 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][170/312]	eta 0:01:47 lr 0.002360	time 0.7232 (0.7579)	model_time 0.7227 (0.7487)	loss 3.5738 (3.2269)	grad_norm 1.3385 (1.4905/0.5395)	mem 34602MB
[2025-01-19 09:37:57 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][180/312]	eta 0:01:39 lr 0.002359	time 0.7174 (0.7564)	model_time 0.7172 (0.7477)	loss 2.9173 (3.2292)	grad_norm 2.4851 (1.5109/0.5419)	mem 34602MB
[2025-01-19 09:38:05 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][190/312]	eta 0:01:32 lr 0.002358	time 0.7247 (0.7557)	model_time 0.7243 (0.7474)	loss 3.1035 (3.2241)	grad_norm 0.9654 (1.4956/0.5393)	mem 34602MB
[2025-01-19 09:38:12 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][200/312]	eta 0:01:24 lr 0.002358	time 0.7535 (0.7544)	model_time 0.7533 (0.7465)	loss 3.4440 (3.2301)	grad_norm 1.4317 (1.5231/0.5757)	mem 34602MB
[2025-01-19 09:38:19 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][210/312]	eta 0:01:16 lr 0.002357	time 0.7222 (0.7531)	model_time 0.7220 (0.7456)	loss 4.2485 (3.2216)	grad_norm 0.9487 (1.5368/0.5803)	mem 34602MB
[2025-01-19 09:38:27 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][220/312]	eta 0:01:09 lr 0.002356	time 0.8021 (0.7524)	model_time 0.8017 (0.7452)	loss 2.8460 (3.2203)	grad_norm 0.9353 (1.5134/0.5782)	mem 34602MB
[2025-01-19 09:38:34 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][230/312]	eta 0:01:01 lr 0.002356	time 0.7865 (0.7524)	model_time 0.7863 (0.7455)	loss 3.5376 (3.2178)	grad_norm 1.6673 (1.5100/0.5887)	mem 34602MB
[2025-01-19 09:38:42 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][240/312]	eta 0:00:54 lr 0.002355	time 0.8082 (0.7529)	model_time 0.8079 (0.7462)	loss 3.4097 (3.2159)	grad_norm 0.9644 (1.5013/0.5837)	mem 34602MB
[2025-01-19 09:38:49 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][250/312]	eta 0:00:46 lr 0.002354	time 0.7186 (0.7521)	model_time 0.7185 (0.7458)	loss 3.2232 (3.2171)	grad_norm 1.2505 (1.4795/0.5830)	mem 34602MB
[2025-01-19 09:38:57 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][260/312]	eta 0:00:39 lr 0.002354	time 0.7199 (0.7530)	model_time 0.7198 (0.7468)	loss 3.1531 (3.2071)	grad_norm 1.5421 (1.4778/0.5761)	mem 34602MB
[2025-01-19 09:39:05 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][270/312]	eta 0:00:31 lr 0.002353	time 0.7163 (0.7533)	model_time 0.7158 (0.7474)	loss 3.8079 (3.2106)	grad_norm 0.7515 (1.4896/0.5870)	mem 34602MB
[2025-01-19 09:39:12 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][280/312]	eta 0:00:24 lr 0.002352	time 0.7208 (0.7526)	model_time 0.7204 (0.7469)	loss 3.4445 (3.2061)	grad_norm 1.8628 (1.4826/0.5823)	mem 34602MB
[2025-01-19 09:39:19 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][290/312]	eta 0:00:16 lr 0.002352	time 0.7198 (0.7523)	model_time 0.7196 (0.7468)	loss 3.6729 (3.2106)	grad_norm 1.7033 (1.5091/0.6066)	mem 34602MB
[2025-01-19 09:39:27 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][300/312]	eta 0:00:09 lr 0.002351	time 0.7140 (0.7517)	model_time 0.7139 (0.7463)	loss 3.8654 (3.2147)	grad_norm 0.9803 (1.5057/0.6072)	mem 34602MB
[2025-01-19 09:39:34 internimage_b_1k_224] (main.py 510): INFO Train: [133/300][310/312]	eta 0:00:01 lr 0.002350	time 0.7159 (0.7508)	model_time 0.7158 (0.7456)	loss 3.3454 (3.2122)	grad_norm 1.4791 (1.4953/0.5874)	mem 34602MB
[2025-01-19 09:39:35 internimage_b_1k_224] (main.py 519): INFO EPOCH 133 training takes 0:03:54
[2025-01-19 09:39:35 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_133.pth saving......
[2025-01-19 09:39:38 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_133.pth saved !!!
[2025-01-19 09:39:45 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.115 (7.115)	Loss 0.8321 (0.8321)	Acc@1 82.837 (82.837)	Acc@5 96.826 (96.826)	Mem 34602MB
[2025-01-19 09:39:48 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.924)	Loss 1.0910 (0.9561)	Acc@1 75.610 (79.656)	Acc@5 94.019 (95.301)	Mem 34602MB
[2025-01-19 09:39:48 internimage_b_1k_224] (main.py 575): INFO [Epoch:133] * Acc@1 79.593 Acc@5 95.333
[2025-01-19 09:39:48 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.6%
[2025-01-19 09:39:48 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.90%
[2025-01-19 09:39:58 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.208 (9.208)	Loss 0.6539 (0.6539)	Acc@1 83.569 (83.569)	Acc@5 97.192 (97.192)	Mem 34602MB
[2025-01-19 09:40:02 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.211 (1.237)	Loss 0.9861 (0.8044)	Acc@1 75.708 (80.427)	Acc@5 93.604 (95.410)	Mem 34602MB
[2025-01-19 09:40:02 internimage_b_1k_224] (main.py 575): INFO [Epoch:133] * Acc@1 80.318 Acc@5 95.479
[2025-01-19 09:40:02 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.3%
[2025-01-19 09:40:02 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 09:40:06 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 09:40:06 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.32%
[2025-01-19 09:40:08 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][0/312]	eta 0:11:09 lr 0.002350	time 2.1454 (2.1454)	model_time 0.7511 (0.7511)	loss 4.1500 (4.1500)	grad_norm 1.1151 (1.1151/0.0000)	mem 34602MB
[2025-01-19 09:40:16 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][10/312]	eta 0:04:17 lr 0.002350	time 0.7280 (0.8536)	model_time 0.7279 (0.7265)	loss 3.5089 (3.2703)	grad_norm 1.1927 (1.1430/0.1804)	mem 34602MB
[2025-01-19 09:40:23 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][20/312]	eta 0:03:51 lr 0.002349	time 0.7183 (0.7944)	model_time 0.7178 (0.7277)	loss 4.1740 (3.1607)	grad_norm 0.8837 (1.2738/0.3236)	mem 34602MB
[2025-01-19 09:40:30 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][30/312]	eta 0:03:38 lr 0.002348	time 0.7364 (0.7761)	model_time 0.7363 (0.7307)	loss 2.1508 (3.0939)	grad_norm 1.0407 (1.2936/0.3806)	mem 34602MB
[2025-01-19 09:40:38 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][40/312]	eta 0:03:29 lr 0.002348	time 0.8148 (0.7702)	model_time 0.8147 (0.7359)	loss 3.3898 (3.1672)	grad_norm 1.4532 (1.3383/0.3833)	mem 34602MB
[2025-01-19 09:40:45 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][50/312]	eta 0:03:21 lr 0.002347	time 0.7199 (0.7695)	model_time 0.7195 (0.7418)	loss 3.1571 (3.1941)	grad_norm 1.9143 (1.2835/0.3936)	mem 34602MB
[2025-01-19 09:40:53 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][60/312]	eta 0:03:12 lr 0.002346	time 0.7205 (0.7648)	model_time 0.7203 (0.7416)	loss 2.7174 (3.1881)	grad_norm 3.0839 (1.3565/0.4750)	mem 34602MB
[2025-01-19 09:41:00 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][70/312]	eta 0:03:04 lr 0.002346	time 0.7427 (0.7641)	model_time 0.7422 (0.7441)	loss 3.3792 (3.2073)	grad_norm 0.7718 (1.4175/0.6601)	mem 34602MB
[2025-01-19 09:41:08 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][80/312]	eta 0:02:56 lr 0.002345	time 0.7283 (0.7611)	model_time 0.7278 (0.7435)	loss 3.0547 (3.2070)	grad_norm 1.2032 (1.4143/0.6444)	mem 34602MB
[2025-01-19 09:41:15 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][90/312]	eta 0:02:48 lr 0.002344	time 0.7168 (0.7602)	model_time 0.7166 (0.7445)	loss 3.3811 (3.2091)	grad_norm 0.8855 (1.3940/0.6217)	mem 34602MB
[2025-01-19 09:41:23 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][100/312]	eta 0:02:40 lr 0.002344	time 0.8074 (0.7582)	model_time 0.8072 (0.7441)	loss 3.1964 (3.2482)	grad_norm 1.0721 (1.3625/0.6154)	mem 34602MB
[2025-01-19 09:41:30 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][110/312]	eta 0:02:32 lr 0.002343	time 0.7167 (0.7557)	model_time 0.7163 (0.7428)	loss 3.2934 (3.2452)	grad_norm 0.9634 (1.3269/0.6001)	mem 34602MB
[2025-01-19 09:41:37 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][120/312]	eta 0:02:24 lr 0.002342	time 0.7236 (0.7549)	model_time 0.7232 (0.7431)	loss 2.0490 (3.2377)	grad_norm 2.2231 (1.3457/0.6030)	mem 34602MB
[2025-01-19 09:41:45 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][130/312]	eta 0:02:17 lr 0.002342	time 0.7271 (0.7531)	model_time 0.7269 (0.7421)	loss 3.4007 (3.2239)	grad_norm 1.8086 (1.3872/0.6272)	mem 34602MB
[2025-01-19 09:41:52 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][140/312]	eta 0:02:09 lr 0.002341	time 0.7267 (0.7516)	model_time 0.7262 (0.7414)	loss 3.4944 (3.2407)	grad_norm 2.6491 (1.4366/0.6379)	mem 34602MB
[2025-01-19 09:42:00 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][150/312]	eta 0:02:01 lr 0.002340	time 0.7268 (0.7514)	model_time 0.7264 (0.7418)	loss 3.4269 (3.2622)	grad_norm 1.5866 (1.4176/0.6285)	mem 34602MB
[2025-01-19 09:42:07 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][160/312]	eta 0:01:54 lr 0.002340	time 0.7256 (0.7512)	model_time 0.7252 (0.7422)	loss 3.7102 (3.2609)	grad_norm 1.5312 (1.3987/0.6177)	mem 34602MB
[2025-01-19 09:42:15 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][170/312]	eta 0:01:46 lr 0.002339	time 0.7171 (0.7517)	model_time 0.7166 (0.7432)	loss 4.0529 (3.2523)	grad_norm 0.9087 (1.3992/0.6176)	mem 34602MB
[2025-01-19 09:42:22 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][180/312]	eta 0:01:39 lr 0.002338	time 0.7213 (0.7513)	model_time 0.7209 (0.7432)	loss 3.5424 (3.2761)	grad_norm 2.2172 (1.4337/0.6416)	mem 34602MB
[2025-01-19 09:42:30 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][190/312]	eta 0:01:31 lr 0.002338	time 0.8121 (0.7532)	model_time 0.8119 (0.7455)	loss 3.6326 (3.2736)	grad_norm 1.5632 (1.4427/0.6409)	mem 34602MB
[2025-01-19 09:42:37 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][200/312]	eta 0:01:24 lr 0.002337	time 0.7198 (0.7525)	model_time 0.7194 (0.7452)	loss 3.2305 (3.2777)	grad_norm 1.0605 (1.4423/0.6317)	mem 34602MB
[2025-01-19 09:42:45 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][210/312]	eta 0:01:16 lr 0.002336	time 0.7174 (0.7518)	model_time 0.7170 (0.7448)	loss 3.7936 (3.2728)	grad_norm 1.1802 (1.4269/0.6234)	mem 34602MB
[2025-01-19 09:42:52 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][220/312]	eta 0:01:09 lr 0.002336	time 0.8092 (0.7515)	model_time 0.8090 (0.7448)	loss 1.9479 (3.2695)	grad_norm 2.6481 (1.4334/0.6200)	mem 34602MB
[2025-01-19 09:43:00 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][230/312]	eta 0:01:01 lr 0.002335	time 0.7187 (0.7505)	model_time 0.7185 (0.7441)	loss 4.0214 (3.2793)	grad_norm 2.1802 (1.4570/0.6460)	mem 34602MB
[2025-01-19 09:43:07 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][240/312]	eta 0:00:54 lr 0.002334	time 0.7206 (0.7502)	model_time 0.7205 (0.7440)	loss 3.3301 (3.2818)	grad_norm 0.8981 (1.4632/0.6486)	mem 34602MB
[2025-01-19 09:43:14 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][250/312]	eta 0:00:46 lr 0.002334	time 0.7166 (0.7494)	model_time 0.7164 (0.7434)	loss 3.2286 (3.2811)	grad_norm 1.3054 (1.4465/0.6418)	mem 34602MB
[2025-01-19 09:43:22 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][260/312]	eta 0:00:38 lr 0.002333	time 0.7159 (0.7486)	model_time 0.7157 (0.7429)	loss 2.9171 (3.2796)	grad_norm 1.2635 (1.4392/0.6407)	mem 34602MB
[2025-01-19 09:43:29 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][270/312]	eta 0:00:31 lr 0.002332	time 0.7176 (0.7485)	model_time 0.7174 (0.7430)	loss 2.9659 (3.2756)	grad_norm 2.9156 (1.4349/0.6382)	mem 34602MB
[2025-01-19 09:43:36 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][280/312]	eta 0:00:23 lr 0.002332	time 0.7461 (0.7483)	model_time 0.7459 (0.7430)	loss 3.5852 (3.2737)	grad_norm 1.0087 (1.4457/0.6390)	mem 34602MB
[2025-01-19 09:43:44 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][290/312]	eta 0:00:16 lr 0.002331	time 0.7153 (0.7489)	model_time 0.7152 (0.7438)	loss 3.3451 (3.2683)	grad_norm 1.2975 (1.4671/0.6548)	mem 34602MB
[2025-01-19 09:43:52 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][300/312]	eta 0:00:08 lr 0.002331	time 0.7146 (0.7491)	model_time 0.7144 (0.7441)	loss 2.7268 (3.2665)	grad_norm 1.2442 (1.4657/0.6487)	mem 34602MB
[2025-01-19 09:43:59 internimage_b_1k_224] (main.py 510): INFO Train: [134/300][310/312]	eta 0:00:01 lr 0.002330	time 0.7107 (0.7486)	model_time 0.7106 (0.7437)	loss 3.7141 (3.2759)	grad_norm 1.7296 (1.4780/0.6489)	mem 34602MB
[2025-01-19 09:44:00 internimage_b_1k_224] (main.py 519): INFO EPOCH 134 training takes 0:03:53
[2025-01-19 09:44:00 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_134.pth saving......
[2025-01-19 09:44:03 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_134.pth saved !!!
[2025-01-19 09:44:10 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.486 (7.486)	Loss 0.8454 (0.8454)	Acc@1 82.617 (82.617)	Acc@5 96.436 (96.436)	Mem 34602MB
[2025-01-19 09:44:13 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.947)	Loss 1.1484 (0.9801)	Acc@1 75.464 (79.821)	Acc@5 93.530 (95.159)	Mem 34602MB
[2025-01-19 09:44:14 internimage_b_1k_224] (main.py 575): INFO [Epoch:134] * Acc@1 79.788 Acc@5 95.216
[2025-01-19 09:44:14 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.8%
[2025-01-19 09:44:14 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.90%
[2025-01-19 09:44:23 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.105 (9.105)	Loss 0.6531 (0.6531)	Acc@1 83.618 (83.618)	Acc@5 97.168 (97.168)	Mem 34602MB
[2025-01-19 09:44:27 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.230)	Loss 0.9838 (0.8031)	Acc@1 75.684 (80.453)	Acc@5 93.628 (95.430)	Mem 34602MB
[2025-01-19 09:44:27 internimage_b_1k_224] (main.py 575): INFO [Epoch:134] * Acc@1 80.356 Acc@5 95.495
[2025-01-19 09:44:27 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.4%
[2025-01-19 09:44:27 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 09:44:32 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 09:44:32 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.36%
[2025-01-19 09:44:34 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][0/312]	eta 0:11:17 lr 0.002330	time 2.1712 (2.1712)	model_time 0.7403 (0.7403)	loss 4.1591 (4.1591)	grad_norm 2.2813 (2.2813/0.0000)	mem 34602MB
[2025-01-19 09:44:41 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][10/312]	eta 0:04:27 lr 0.002329	time 0.7628 (0.8873)	model_time 0.7626 (0.7569)	loss 2.8750 (3.1250)	grad_norm 1.1515 (1.3700/0.4164)	mem 34602MB
[2025-01-19 09:44:49 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][20/312]	eta 0:03:57 lr 0.002328	time 0.7201 (0.8149)	model_time 0.7200 (0.7464)	loss 2.8107 (3.2902)	grad_norm 3.1463 (1.6123/0.8704)	mem 34602MB
[2025-01-19 09:44:56 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][30/312]	eta 0:03:43 lr 0.002328	time 0.7244 (0.7927)	model_time 0.7240 (0.7462)	loss 2.9218 (3.2515)	grad_norm 0.8886 (1.6702/0.8747)	mem 34602MB
[2025-01-19 09:45:03 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][40/312]	eta 0:03:31 lr 0.002327	time 0.7334 (0.7770)	model_time 0.7332 (0.7417)	loss 2.5286 (3.2046)	grad_norm 1.7950 (1.5903/0.8046)	mem 34602MB
[2025-01-19 09:45:11 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][50/312]	eta 0:03:21 lr 0.002326	time 0.7252 (0.7694)	model_time 0.7251 (0.7410)	loss 4.0328 (3.1920)	grad_norm 0.9245 (1.6129/0.7901)	mem 34602MB
[2025-01-19 09:45:18 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][60/312]	eta 0:03:12 lr 0.002326	time 0.7286 (0.7633)	model_time 0.7284 (0.7395)	loss 3.7833 (3.2552)	grad_norm 0.9587 (1.5545/0.7529)	mem 34602MB
[2025-01-19 09:45:25 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][70/312]	eta 0:03:03 lr 0.002325	time 0.7247 (0.7592)	model_time 0.7245 (0.7387)	loss 3.4059 (3.2512)	grad_norm 1.3105 (1.5529/0.7217)	mem 34602MB
[2025-01-19 09:45:33 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][80/312]	eta 0:02:55 lr 0.002324	time 0.7399 (0.7576)	model_time 0.7394 (0.7396)	loss 2.5300 (3.2830)	grad_norm 1.3821 (1.5485/0.7025)	mem 34602MB
[2025-01-19 09:45:40 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][90/312]	eta 0:02:47 lr 0.002324	time 0.8050 (0.7566)	model_time 0.8048 (0.7405)	loss 2.2970 (3.2681)	grad_norm 1.6573 (1.5072/0.6795)	mem 34602MB
[2025-01-19 09:45:48 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][100/312]	eta 0:02:40 lr 0.002323	time 0.7147 (0.7577)	model_time 0.7144 (0.7432)	loss 2.9646 (3.2811)	grad_norm 1.3646 (1.4810/0.6541)	mem 34602MB
[2025-01-19 09:45:56 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][110/312]	eta 0:02:32 lr 0.002323	time 0.7255 (0.7569)	model_time 0.7251 (0.7437)	loss 3.1797 (3.2808)	grad_norm 1.0987 (1.4755/0.6402)	mem 34602MB
[2025-01-19 09:46:03 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][120/312]	eta 0:02:25 lr 0.002322	time 0.7174 (0.7559)	model_time 0.7172 (0.7437)	loss 2.8074 (3.2880)	grad_norm 2.9650 (1.4682/0.6442)	mem 34602MB
[2025-01-19 09:46:11 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][130/312]	eta 0:02:17 lr 0.002321	time 0.7203 (0.7552)	model_time 0.7199 (0.7439)	loss 4.2587 (3.2734)	grad_norm 1.3621 (1.4851/0.6506)	mem 34602MB
[2025-01-19 09:46:18 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][140/312]	eta 0:02:09 lr 0.002321	time 0.7202 (0.7540)	model_time 0.7197 (0.7435)	loss 3.3533 (3.3058)	grad_norm 1.8827 (1.4828/0.6372)	mem 34602MB
[2025-01-19 09:46:25 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][150/312]	eta 0:02:02 lr 0.002320	time 0.7956 (0.7540)	model_time 0.7955 (0.7442)	loss 2.4901 (3.2833)	grad_norm 0.8164 (1.4978/0.6378)	mem 34602MB
[2025-01-19 09:46:33 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][160/312]	eta 0:01:54 lr 0.002319	time 0.7434 (0.7528)	model_time 0.7432 (0.7436)	loss 3.6220 (3.2832)	grad_norm 1.2251 (1.4887/0.6394)	mem 34602MB
[2025-01-19 09:46:40 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][170/312]	eta 0:01:46 lr 0.002319	time 0.7193 (0.7520)	model_time 0.7191 (0.7432)	loss 2.4657 (3.2666)	grad_norm 1.7236 (1.4774/0.6281)	mem 34602MB
[2025-01-19 09:46:47 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][180/312]	eta 0:01:39 lr 0.002318	time 0.7244 (0.7505)	model_time 0.7240 (0.7422)	loss 3.6645 (3.2661)	grad_norm 1.9578 (1.4916/0.6283)	mem 34602MB
[2025-01-19 09:46:55 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][190/312]	eta 0:01:31 lr 0.002317	time 0.7207 (0.7493)	model_time 0.7203 (0.7415)	loss 2.6848 (3.2709)	grad_norm 0.9577 (1.4717/0.6210)	mem 34602MB
[2025-01-19 09:47:02 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][200/312]	eta 0:01:23 lr 0.002317	time 0.7233 (0.7490)	model_time 0.7231 (0.7415)	loss 3.5158 (3.2753)	grad_norm 3.3562 (1.4731/0.6344)	mem 34602MB
[2025-01-19 09:47:10 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][210/312]	eta 0:01:16 lr 0.002316	time 0.8237 (0.7489)	model_time 0.8235 (0.7417)	loss 3.3073 (3.2861)	grad_norm 1.3048 (1.4962/0.6758)	mem 34602MB
[2025-01-19 09:47:17 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][220/312]	eta 0:01:08 lr 0.002315	time 0.7202 (0.7497)	model_time 0.7200 (0.7428)	loss 3.6822 (3.2864)	grad_norm 0.9498 (1.4960/0.6665)	mem 34602MB
[2025-01-19 09:47:25 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][230/312]	eta 0:01:01 lr 0.002315	time 0.7374 (0.7503)	model_time 0.7373 (0.7438)	loss 3.3999 (3.2843)	grad_norm 0.9745 (1.4868/0.6589)	mem 34602MB
[2025-01-19 09:47:33 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][240/312]	eta 0:00:54 lr 0.002314	time 0.7179 (0.7508)	model_time 0.7178 (0.7446)	loss 2.7834 (3.2807)	grad_norm 2.2224 (1.4824/0.6540)	mem 34602MB
[2025-01-19 09:47:40 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][250/312]	eta 0:00:46 lr 0.002313	time 0.7592 (0.7513)	model_time 0.7588 (0.7452)	loss 3.2917 (3.2759)	grad_norm 0.8618 (1.4815/0.6483)	mem 34602MB
[2025-01-19 09:47:48 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][260/312]	eta 0:00:39 lr 0.002313	time 0.8291 (0.7510)	model_time 0.8289 (0.7451)	loss 3.5162 (3.2698)	grad_norm 2.0499 (1.4797/0.6535)	mem 34602MB
[2025-01-19 09:47:55 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][270/312]	eta 0:00:31 lr 0.002312	time 0.8267 (0.7508)	model_time 0.8266 (0.7451)	loss 3.2622 (3.2672)	grad_norm 1.5752 (1.4856/0.6528)	mem 34602MB
[2025-01-19 09:48:02 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][280/312]	eta 0:00:24 lr 0.002311	time 0.7187 (0.7503)	model_time 0.7185 (0.7448)	loss 3.4505 (3.2672)	grad_norm 1.9672 (1.4860/0.6483)	mem 34602MB
[2025-01-19 09:48:10 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][290/312]	eta 0:00:16 lr 0.002311	time 0.7253 (0.7497)	model_time 0.7252 (0.7444)	loss 4.1736 (3.2731)	grad_norm 1.2753 (1.4802/0.6424)	mem 34602MB
[2025-01-19 09:48:17 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][300/312]	eta 0:00:08 lr 0.002310	time 0.7105 (0.7488)	model_time 0.7104 (0.7437)	loss 3.3243 (3.2684)	grad_norm 1.0634 (1.4737/0.6338)	mem 34602MB
[2025-01-19 09:48:24 internimage_b_1k_224] (main.py 510): INFO Train: [135/300][310/312]	eta 0:00:01 lr 0.002309	time 0.7193 (0.7478)	model_time 0.7192 (0.7428)	loss 2.6618 (3.2685)	grad_norm 1.9469 (1.4895/0.6417)	mem 34602MB
[2025-01-19 09:48:25 internimage_b_1k_224] (main.py 519): INFO EPOCH 135 training takes 0:03:53
[2025-01-19 09:48:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_135.pth saving......
[2025-01-19 09:48:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_135.pth saved !!!
[2025-01-19 09:48:35 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.286 (7.286)	Loss 0.8470 (0.8470)	Acc@1 82.544 (82.544)	Acc@5 96.729 (96.729)	Mem 34602MB
[2025-01-19 09:48:38 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.934)	Loss 1.1355 (0.9758)	Acc@1 74.951 (79.965)	Acc@5 93.213 (95.199)	Mem 34602MB
[2025-01-19 09:48:39 internimage_b_1k_224] (main.py 575): INFO [Epoch:135] * Acc@1 79.844 Acc@5 95.254
[2025-01-19 09:48:39 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.8%
[2025-01-19 09:48:39 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.90%
[2025-01-19 09:48:48 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.944 (8.944)	Loss 0.6525 (0.6525)	Acc@1 83.643 (83.643)	Acc@5 97.241 (97.241)	Mem 34602MB
[2025-01-19 09:48:52 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.220)	Loss 0.9818 (0.8018)	Acc@1 75.757 (80.513)	Acc@5 93.726 (95.470)	Mem 34602MB
[2025-01-19 09:48:52 internimage_b_1k_224] (main.py 575): INFO [Epoch:135] * Acc@1 80.414 Acc@5 95.541
[2025-01-19 09:48:52 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.4%
[2025-01-19 09:48:52 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 09:48:56 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 09:48:56 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.41%
[2025-01-19 09:48:58 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][0/312]	eta 0:11:19 lr 0.002309	time 2.1771 (2.1771)	model_time 0.7589 (0.7589)	loss 3.3487 (3.3487)	grad_norm 2.0067 (2.0067/0.0000)	mem 34602MB
[2025-01-19 09:49:06 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][10/312]	eta 0:04:25 lr 0.002309	time 0.7402 (0.8782)	model_time 0.7400 (0.7489)	loss 2.2615 (3.0255)	grad_norm 1.1961 (1.2865/0.4757)	mem 34602MB
[2025-01-19 09:49:13 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][20/312]	eta 0:03:58 lr 0.002308	time 0.8072 (0.8179)	model_time 0.8070 (0.7501)	loss 2.3783 (3.2096)	grad_norm 1.4471 (1.2407/0.4151)	mem 34602MB
[2025-01-19 09:49:21 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][30/312]	eta 0:03:45 lr 0.002307	time 0.7159 (0.8008)	model_time 0.7154 (0.7547)	loss 3.5758 (3.2134)	grad_norm 1.2778 (1.2434/0.3731)	mem 34602MB
[2025-01-19 09:49:28 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][40/312]	eta 0:03:34 lr 0.002307	time 0.7204 (0.7868)	model_time 0.7203 (0.7518)	loss 3.0692 (3.2024)	grad_norm 1.9307 (1.4176/0.6045)	mem 34602MB
[2025-01-19 09:49:36 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][50/312]	eta 0:03:24 lr 0.002306	time 0.8142 (0.7810)	model_time 0.8137 (0.7529)	loss 3.2858 (3.2425)	grad_norm 2.5388 (1.4944/0.6270)	mem 34602MB
[2025-01-19 09:49:43 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][60/312]	eta 0:03:15 lr 0.002305	time 0.7224 (0.7763)	model_time 0.7219 (0.7527)	loss 3.9653 (3.2572)	grad_norm 0.9994 (1.5017/0.6111)	mem 34602MB
[2025-01-19 09:49:51 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][70/312]	eta 0:03:06 lr 0.002305	time 0.8634 (0.7724)	model_time 0.8632 (0.7521)	loss 3.6607 (3.3001)	grad_norm 1.4397 (1.4729/0.5878)	mem 34602MB
[2025-01-19 09:49:59 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][80/312]	eta 0:02:59 lr 0.002304	time 0.9749 (0.7718)	model_time 0.9745 (0.7539)	loss 3.1228 (3.3017)	grad_norm 0.7179 (1.4683/0.5712)	mem 34602MB
[2025-01-19 09:50:06 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][90/312]	eta 0:02:50 lr 0.002303	time 0.7555 (0.7683)	model_time 0.7550 (0.7524)	loss 3.0369 (3.3017)	grad_norm 2.8854 (1.4754/0.5959)	mem 34602MB
[2025-01-19 09:50:13 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][100/312]	eta 0:02:42 lr 0.002303	time 0.7150 (0.7649)	model_time 0.7145 (0.7505)	loss 3.0605 (3.2895)	grad_norm 1.7915 (1.4575/0.5858)	mem 34602MB
[2025-01-19 09:50:21 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][110/312]	eta 0:02:33 lr 0.002302	time 0.7199 (0.7620)	model_time 0.7197 (0.7489)	loss 4.0314 (3.2881)	grad_norm 2.3511 (1.4813/0.6011)	mem 34602MB
[2025-01-19 09:50:28 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][120/312]	eta 0:02:25 lr 0.002301	time 0.7178 (0.7593)	model_time 0.7174 (0.7472)	loss 2.3407 (3.2781)	grad_norm 1.1280 (1.4627/0.5891)	mem 34602MB
[2025-01-19 09:50:35 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][130/312]	eta 0:02:17 lr 0.002301	time 0.7158 (0.7573)	model_time 0.7153 (0.7461)	loss 2.0952 (3.2313)	grad_norm 2.1209 (1.4415/0.5833)	mem 34602MB
[2025-01-19 09:50:43 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][140/312]	eta 0:02:10 lr 0.002300	time 0.8140 (0.7566)	model_time 0.8139 (0.7462)	loss 3.5532 (3.2521)	grad_norm 2.6438 (1.4378/0.5785)	mem 34602MB
[2025-01-19 09:50:50 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][150/312]	eta 0:02:02 lr 0.002299	time 0.7195 (0.7570)	model_time 0.7190 (0.7472)	loss 3.5398 (3.2460)	grad_norm 1.5740 (1.4282/0.5709)	mem 34602MB
[2025-01-19 09:50:58 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][160/312]	eta 0:01:55 lr 0.002299	time 0.7209 (0.7570)	model_time 0.7208 (0.7478)	loss 3.0643 (3.2384)	grad_norm 1.3301 (1.4018/0.5666)	mem 34602MB
[2025-01-19 09:51:06 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][170/312]	eta 0:01:47 lr 0.002298	time 0.7596 (0.7579)	model_time 0.7592 (0.7492)	loss 3.4086 (3.2271)	grad_norm 0.8066 (1.3987/0.5629)	mem 34602MB
[2025-01-19 09:51:13 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][180/312]	eta 0:01:39 lr 0.002297	time 0.7165 (0.7570)	model_time 0.7163 (0.7488)	loss 2.8321 (3.2184)	grad_norm 1.9123 (1.4029/0.5563)	mem 34602MB
[2025-01-19 09:51:21 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][190/312]	eta 0:01:32 lr 0.002297	time 0.7189 (0.7566)	model_time 0.7187 (0.7488)	loss 2.8413 (3.2228)	grad_norm 1.0807 (1.3960/0.5484)	mem 34602MB
[2025-01-19 09:51:28 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][200/312]	eta 0:01:24 lr 0.002296	time 0.7181 (0.7562)	model_time 0.7176 (0.7488)	loss 2.9544 (3.2210)	grad_norm 1.1417 (1.3995/0.5398)	mem 34602MB
[2025-01-19 09:51:36 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][210/312]	eta 0:01:17 lr 0.002295	time 0.7271 (0.7559)	model_time 0.7269 (0.7489)	loss 2.4694 (3.2328)	grad_norm 1.1898 (1.4195/0.5559)	mem 34602MB
[2025-01-19 09:51:43 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][220/312]	eta 0:01:09 lr 0.002295	time 0.7278 (0.7551)	model_time 0.7277 (0.7483)	loss 3.7294 (3.2429)	grad_norm 1.2281 (1.4086/0.5484)	mem 34602MB
[2025-01-19 09:51:50 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][230/312]	eta 0:01:01 lr 0.002294	time 0.7539 (0.7538)	model_time 0.7537 (0.7474)	loss 3.1855 (3.2337)	grad_norm 0.8568 (1.4069/0.5463)	mem 34602MB
[2025-01-19 09:51:57 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][240/312]	eta 0:00:54 lr 0.002293	time 0.7197 (0.7525)	model_time 0.7195 (0.7462)	loss 3.2473 (3.2312)	grad_norm 1.1399 (1.3919/0.5413)	mem 34602MB
[2025-01-19 09:52:05 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][250/312]	eta 0:00:46 lr 0.002293	time 0.7215 (0.7519)	model_time 0.7211 (0.7459)	loss 2.8184 (3.2331)	grad_norm 3.0536 (1.4047/0.5563)	mem 34602MB
[2025-01-19 09:52:12 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][260/312]	eta 0:00:39 lr 0.002292	time 0.8330 (0.7519)	model_time 0.8328 (0.7461)	loss 3.1188 (3.2280)	grad_norm 1.4098 (1.4218/0.5638)	mem 34602MB
[2025-01-19 09:52:20 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][270/312]	eta 0:00:31 lr 0.002291	time 0.7202 (0.7526)	model_time 0.7198 (0.7470)	loss 3.7212 (3.2243)	grad_norm 0.9641 (1.4220/0.5568)	mem 34602MB
[2025-01-19 09:52:27 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][280/312]	eta 0:00:24 lr 0.002291	time 0.7175 (0.7523)	model_time 0.7171 (0.7469)	loss 2.8558 (3.2189)	grad_norm 1.6122 (1.4254/0.5619)	mem 34602MB
[2025-01-19 09:52:35 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][290/312]	eta 0:00:16 lr 0.002290	time 0.8136 (0.7522)	model_time 0.8135 (0.7470)	loss 2.5828 (3.2237)	grad_norm 0.9662 (1.4238/0.5566)	mem 34602MB
[2025-01-19 09:52:42 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][300/312]	eta 0:00:09 lr 0.002290	time 0.7129 (0.7518)	model_time 0.7127 (0.7467)	loss 3.4929 (3.2286)	grad_norm 1.4958 (1.4177/0.5591)	mem 34602MB
[2025-01-19 09:52:50 internimage_b_1k_224] (main.py 510): INFO Train: [136/300][310/312]	eta 0:00:01 lr 0.002289	time 0.7145 (0.7513)	model_time 0.7144 (0.7464)	loss 3.9159 (3.2336)	grad_norm 4.2394 (1.4499/0.5962)	mem 34602MB
[2025-01-19 09:52:50 internimage_b_1k_224] (main.py 519): INFO EPOCH 136 training takes 0:03:54
[2025-01-19 09:52:50 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_136.pth saving......
[2025-01-19 09:52:53 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_136.pth saved !!!
[2025-01-19 09:53:01 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.514 (7.514)	Loss 0.8398 (0.8398)	Acc@1 83.545 (83.545)	Acc@5 97.070 (97.070)	Mem 34602MB
[2025-01-19 09:53:04 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.944)	Loss 1.1032 (0.9612)	Acc@1 75.439 (79.976)	Acc@5 93.530 (95.250)	Mem 34602MB
[2025-01-19 09:53:04 internimage_b_1k_224] (main.py 575): INFO [Epoch:136] * Acc@1 79.908 Acc@5 95.268
[2025-01-19 09:53:04 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.9%
[2025-01-19 09:53:04 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 09:53:07 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 09:53:07 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 79.91%
[2025-01-19 09:53:15 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.249 (7.249)	Loss 0.6519 (0.6519)	Acc@1 83.691 (83.691)	Acc@5 97.363 (97.363)	Mem 34602MB
[2025-01-19 09:53:18 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.927)	Loss 0.9795 (0.8006)	Acc@1 75.806 (80.571)	Acc@5 93.726 (95.510)	Mem 34602MB
[2025-01-19 09:53:18 internimage_b_1k_224] (main.py 575): INFO [Epoch:136] * Acc@1 80.470 Acc@5 95.579
[2025-01-19 09:53:18 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.5%
[2025-01-19 09:53:18 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 09:53:22 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 09:53:22 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.47%
[2025-01-19 09:53:24 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][0/312]	eta 0:11:17 lr 0.002289	time 2.1725 (2.1725)	model_time 0.8794 (0.8794)	loss 3.6124 (3.6124)	grad_norm 2.3250 (2.3250/0.0000)	mem 34602MB
[2025-01-19 09:53:31 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][10/312]	eta 0:04:23 lr 0.002288	time 0.7168 (0.8736)	model_time 0.7166 (0.7544)	loss 2.3917 (3.1328)	grad_norm 0.6684 (1.6063/0.6427)	mem 34602MB
[2025-01-19 09:53:39 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][20/312]	eta 0:03:59 lr 0.002287	time 0.7169 (0.8190)	model_time 0.7165 (0.7564)	loss 3.6767 (3.1911)	grad_norm 1.1257 (1.6823/0.6147)	mem 34602MB
[2025-01-19 09:53:46 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][30/312]	eta 0:03:43 lr 0.002287	time 0.7222 (0.7933)	model_time 0.7221 (0.7508)	loss 3.6905 (3.1936)	grad_norm 0.9953 (1.5630/0.5741)	mem 34602MB
[2025-01-19 09:53:54 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][40/312]	eta 0:03:31 lr 0.002286	time 0.7318 (0.7790)	model_time 0.7314 (0.7468)	loss 3.8082 (3.1652)	grad_norm 1.2470 (1.4648/0.5488)	mem 34602MB
[2025-01-19 09:54:01 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][50/312]	eta 0:03:21 lr 0.002285	time 0.7172 (0.7691)	model_time 0.7171 (0.7431)	loss 3.0006 (3.1690)	grad_norm 1.1913 (1.4026/0.5208)	mem 34602MB
[2025-01-19 09:54:09 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][60/312]	eta 0:03:12 lr 0.002285	time 0.7294 (0.7656)	model_time 0.7289 (0.7439)	loss 3.5657 (3.2072)	grad_norm 2.1448 (1.4017/0.5143)	mem 34602MB
[2025-01-19 09:54:16 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][70/312]	eta 0:03:04 lr 0.002284	time 0.8017 (0.7643)	model_time 0.8014 (0.7455)	loss 2.4889 (3.1829)	grad_norm 2.3915 (1.3784/0.5080)	mem 34602MB
[2025-01-19 09:54:24 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][80/312]	eta 0:02:58 lr 0.002283	time 0.7915 (0.7682)	model_time 0.7914 (0.7517)	loss 3.2973 (3.2112)	grad_norm 2.3658 (1.4966/0.6342)	mem 34602MB
[2025-01-19 09:54:32 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][90/312]	eta 0:02:50 lr 0.002283	time 0.7153 (0.7664)	model_time 0.7151 (0.7517)	loss 3.3685 (3.2042)	grad_norm 1.6838 (1.5336/0.7309)	mem 34602MB
[2025-01-19 09:54:39 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][100/312]	eta 0:02:42 lr 0.002282	time 0.8075 (0.7655)	model_time 0.8070 (0.7523)	loss 3.5798 (3.2142)	grad_norm 2.7406 (1.5391/0.7384)	mem 34602MB
[2025-01-19 09:54:47 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][110/312]	eta 0:02:34 lr 0.002281	time 0.7181 (0.7642)	model_time 0.7179 (0.7521)	loss 3.4900 (3.2075)	grad_norm 1.1239 (1.5404/0.7386)	mem 34602MB
[2025-01-19 09:54:54 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][120/312]	eta 0:02:26 lr 0.002281	time 0.8194 (0.7621)	model_time 0.8192 (0.7509)	loss 3.1987 (3.2347)	grad_norm 0.6011 (1.4933/0.7293)	mem 34602MB
[2025-01-19 09:55:02 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][130/312]	eta 0:02:18 lr 0.002280	time 0.7618 (0.7605)	model_time 0.7614 (0.7501)	loss 3.6906 (3.2467)	grad_norm 0.9958 (1.5340/0.7514)	mem 34602MB
[2025-01-19 09:55:09 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][140/312]	eta 0:02:10 lr 0.002279	time 0.7178 (0.7603)	model_time 0.7173 (0.7507)	loss 3.3773 (3.2385)	grad_norm 2.0635 (1.5339/0.7387)	mem 34602MB
[2025-01-19 09:55:16 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][150/312]	eta 0:02:02 lr 0.002279	time 0.7641 (0.7590)	model_time 0.7639 (0.7500)	loss 2.6558 (3.2163)	grad_norm 1.8582 (1.5210/0.7232)	mem 34602MB
[2025-01-19 09:55:24 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][160/312]	eta 0:01:55 lr 0.002278	time 0.7578 (0.7571)	model_time 0.7574 (0.7487)	loss 3.8077 (3.2226)	grad_norm 1.0548 (1.5038/0.7085)	mem 34602MB
[2025-01-19 09:55:31 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][170/312]	eta 0:01:47 lr 0.002278	time 0.7240 (0.7553)	model_time 0.7235 (0.7474)	loss 4.0922 (3.2343)	grad_norm 1.7434 (1.5047/0.7030)	mem 34602MB
[2025-01-19 09:55:38 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][180/312]	eta 0:01:39 lr 0.002277	time 0.7175 (0.7546)	model_time 0.7170 (0.7471)	loss 3.9040 (3.2210)	grad_norm 1.4549 (1.4946/0.6866)	mem 34602MB
[2025-01-19 09:55:46 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][190/312]	eta 0:01:32 lr 0.002276	time 0.8046 (0.7546)	model_time 0.8045 (0.7474)	loss 2.6389 (3.2143)	grad_norm 0.7045 (1.4885/0.6797)	mem 34602MB
[2025-01-19 09:55:54 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][200/312]	eta 0:01:24 lr 0.002276	time 0.7955 (0.7550)	model_time 0.7954 (0.7481)	loss 2.5704 (3.1947)	grad_norm 1.6827 (1.4946/0.6713)	mem 34602MB
[2025-01-19 09:56:01 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][210/312]	eta 0:01:16 lr 0.002275	time 0.7614 (0.7547)	model_time 0.7613 (0.7481)	loss 3.4649 (3.2000)	grad_norm 1.1176 (1.4922/0.6632)	mem 34602MB
[2025-01-19 09:56:09 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][220/312]	eta 0:01:09 lr 0.002274	time 0.7195 (0.7546)	model_time 0.7191 (0.7483)	loss 2.9704 (3.1938)	grad_norm 1.2321 (1.4949/0.6606)	mem 34602MB
[2025-01-19 09:56:16 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][230/312]	eta 0:01:01 lr 0.002274	time 0.7221 (0.7546)	model_time 0.7217 (0.7486)	loss 2.1780 (3.1942)	grad_norm 2.3687 (1.4855/0.6555)	mem 34602MB
[2025-01-19 09:56:24 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][240/312]	eta 0:00:54 lr 0.002273	time 0.8177 (0.7538)	model_time 0.8173 (0.7480)	loss 2.7695 (3.1991)	grad_norm 0.8268 (1.4868/0.6503)	mem 34602MB
[2025-01-19 09:56:31 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][250/312]	eta 0:00:46 lr 0.002272	time 0.7191 (0.7528)	model_time 0.7187 (0.7472)	loss 2.1573 (3.1897)	grad_norm 1.8327 (1.4869/0.6497)	mem 34602MB
[2025-01-19 09:56:39 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][260/312]	eta 0:00:39 lr 0.002272	time 0.7150 (0.7534)	model_time 0.7146 (0.7481)	loss 2.6399 (3.1945)	grad_norm 1.1288 (1.4722/0.6445)	mem 34602MB
[2025-01-19 09:56:46 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][270/312]	eta 0:00:31 lr 0.002271	time 0.7249 (0.7527)	model_time 0.7247 (0.7475)	loss 3.5744 (3.1988)	grad_norm 0.9821 (1.4724/0.6448)	mem 34602MB
[2025-01-19 09:56:53 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][280/312]	eta 0:00:24 lr 0.002270	time 0.7237 (0.7516)	model_time 0.7233 (0.7466)	loss 3.5402 (3.1963)	grad_norm 1.5661 (1.4690/0.6364)	mem 34602MB
[2025-01-19 09:57:00 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][290/312]	eta 0:00:16 lr 0.002270	time 0.7191 (0.7508)	model_time 0.7187 (0.7459)	loss 3.3297 (3.2046)	grad_norm 3.3643 (1.4765/0.6376)	mem 34602MB
[2025-01-19 09:57:08 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][300/312]	eta 0:00:09 lr 0.002269	time 0.7173 (0.7503)	model_time 0.7172 (0.7456)	loss 3.3676 (3.2059)	grad_norm 1.3537 (1.4642/0.6335)	mem 34602MB
[2025-01-19 09:57:15 internimage_b_1k_224] (main.py 510): INFO Train: [137/300][310/312]	eta 0:00:01 lr 0.002268	time 0.7104 (0.7497)	model_time 0.7103 (0.7451)	loss 3.8702 (3.2079)	grad_norm 1.6683 (1.4726/0.6371)	mem 34602MB
[2025-01-19 09:57:16 internimage_b_1k_224] (main.py 519): INFO EPOCH 137 training takes 0:03:53
[2025-01-19 09:57:16 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_137.pth saving......
[2025-01-19 09:57:19 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_137.pth saved !!!
[2025-01-19 09:57:27 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.534 (7.534)	Loss 0.7616 (0.7616)	Acc@1 83.862 (83.862)	Acc@5 96.973 (96.973)	Mem 34602MB
[2025-01-19 09:57:30 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.950)	Loss 1.1010 (0.9249)	Acc@1 75.928 (80.229)	Acc@5 93.384 (95.368)	Mem 34602MB
[2025-01-19 09:57:30 internimage_b_1k_224] (main.py 575): INFO [Epoch:137] * Acc@1 80.160 Acc@5 95.379
[2025-01-19 09:57:30 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.2%
[2025-01-19 09:57:30 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 09:57:33 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 09:57:33 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.16%
[2025-01-19 09:57:41 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.463 (7.463)	Loss 0.6513 (0.6513)	Acc@1 83.618 (83.618)	Acc@5 97.363 (97.363)	Mem 34602MB
[2025-01-19 09:57:44 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.938)	Loss 0.9775 (0.7995)	Acc@1 75.781 (80.604)	Acc@5 93.921 (95.557)	Mem 34602MB
[2025-01-19 09:57:44 internimage_b_1k_224] (main.py 575): INFO [Epoch:137] * Acc@1 80.510 Acc@5 95.627
[2025-01-19 09:57:44 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.5%
[2025-01-19 09:57:44 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 09:57:48 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 09:57:48 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.51%
[2025-01-19 09:57:50 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][0/312]	eta 0:10:59 lr 0.002268	time 2.1153 (2.1153)	model_time 0.7713 (0.7713)	loss 3.3054 (3.3054)	grad_norm 1.1148 (1.1148/0.0000)	mem 34602MB
[2025-01-19 09:57:58 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][10/312]	eta 0:04:31 lr 0.002268	time 0.7930 (0.8989)	model_time 0.7929 (0.7764)	loss 2.9500 (3.3097)	grad_norm 1.2390 (1.5871/0.6384)	mem 34602MB
[2025-01-19 09:58:05 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][20/312]	eta 0:04:01 lr 0.002267	time 0.7172 (0.8287)	model_time 0.7168 (0.7644)	loss 3.7534 (3.3769)	grad_norm 1.0052 (1.5968/0.6354)	mem 34602MB
[2025-01-19 09:58:13 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][30/312]	eta 0:03:46 lr 0.002266	time 0.8090 (0.8046)	model_time 0.8088 (0.7610)	loss 4.0573 (3.3907)	grad_norm 0.7812 (1.4851/0.5787)	mem 34602MB
[2025-01-19 09:58:20 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][40/312]	eta 0:03:35 lr 0.002266	time 0.8270 (0.7926)	model_time 0.8268 (0.7595)	loss 3.9168 (3.4069)	grad_norm 1.0971 (1.4328/0.5292)	mem 34602MB
[2025-01-19 09:58:28 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][50/312]	eta 0:03:24 lr 0.002265	time 0.7164 (0.7792)	model_time 0.7162 (0.7525)	loss 3.5720 (3.3587)	grad_norm 1.7573 (1.5216/0.5684)	mem 34602MB
[2025-01-19 09:58:35 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][60/312]	eta 0:03:15 lr 0.002264	time 0.7175 (0.7760)	model_time 0.7171 (0.7537)	loss 3.6178 (3.3597)	grad_norm 1.4890 (1.5089/0.5707)	mem 34602MB
[2025-01-19 09:58:43 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][70/312]	eta 0:03:07 lr 0.002264	time 0.7652 (0.7750)	model_time 0.7646 (0.7557)	loss 3.5023 (3.3181)	grad_norm 1.8851 (1.5153/0.5549)	mem 34602MB
[2025-01-19 09:58:50 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][80/312]	eta 0:02:58 lr 0.002263	time 0.7244 (0.7700)	model_time 0.7242 (0.7531)	loss 2.1806 (3.2614)	grad_norm 0.9199 (1.4652/0.5495)	mem 34602MB
[2025-01-19 09:58:58 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][90/312]	eta 0:02:49 lr 0.002262	time 0.7161 (0.7655)	model_time 0.7159 (0.7504)	loss 3.7289 (3.2715)	grad_norm 0.8602 (1.4493/0.5393)	mem 34602MB
[2025-01-19 09:59:05 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][100/312]	eta 0:02:41 lr 0.002262	time 0.7232 (0.7616)	model_time 0.7228 (0.7479)	loss 3.2114 (3.2529)	grad_norm 1.5061 (1.4284/0.5252)	mem 34602MB
[2025-01-19 09:59:12 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][110/312]	eta 0:02:33 lr 0.002261	time 0.8032 (0.7595)	model_time 0.8031 (0.7471)	loss 3.3627 (3.2359)	grad_norm 2.1775 (1.4695/0.5533)	mem 34602MB
[2025-01-19 09:59:20 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][120/312]	eta 0:02:25 lr 0.002260	time 0.8097 (0.7590)	model_time 0.8093 (0.7475)	loss 3.8024 (3.2646)	grad_norm 0.7460 (1.4919/0.5584)	mem 34602MB
[2025-01-19 09:59:28 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][130/312]	eta 0:02:18 lr 0.002260	time 0.7163 (0.7597)	model_time 0.7161 (0.7491)	loss 3.8420 (3.2761)	grad_norm 1.8694 (1.5000/0.5472)	mem 34602MB
[2025-01-19 09:59:35 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][140/312]	eta 0:02:10 lr 0.002259	time 0.7575 (0.7591)	model_time 0.7573 (0.7492)	loss 3.2152 (3.2734)	grad_norm 1.3092 (1.4781/0.5430)	mem 34602MB
[2025-01-19 09:59:43 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][150/312]	eta 0:02:03 lr 0.002258	time 0.8081 (0.7595)	model_time 0.8080 (0.7503)	loss 2.6875 (3.2731)	grad_norm 0.8375 (1.4721/0.5439)	mem 34602MB
[2025-01-19 09:59:50 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][160/312]	eta 0:01:55 lr 0.002258	time 0.8171 (0.7587)	model_time 0.8169 (0.7500)	loss 3.0470 (3.2790)	grad_norm 1.0822 (1.4660/0.5385)	mem 34602MB
[2025-01-19 09:59:58 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][170/312]	eta 0:01:47 lr 0.002257	time 0.7766 (0.7575)	model_time 0.7765 (0.7493)	loss 2.1871 (3.2769)	grad_norm 1.0580 (1.4591/0.5416)	mem 34602MB
[2025-01-19 10:00:05 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][180/312]	eta 0:01:39 lr 0.002256	time 0.7279 (0.7565)	model_time 0.7277 (0.7488)	loss 3.8289 (3.2895)	grad_norm 0.7265 (1.4561/0.5475)	mem 34602MB
[2025-01-19 10:00:13 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][190/312]	eta 0:01:32 lr 0.002256	time 0.7162 (0.7566)	model_time 0.7157 (0.7492)	loss 2.7269 (3.2980)	grad_norm 2.2969 (1.4560/0.5476)	mem 34602MB
[2025-01-19 10:00:20 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][200/312]	eta 0:01:24 lr 0.002255	time 0.7324 (0.7557)	model_time 0.7319 (0.7486)	loss 3.8836 (3.3082)	grad_norm 1.5039 (1.4477/0.5396)	mem 34602MB
[2025-01-19 10:00:27 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][210/312]	eta 0:01:16 lr 0.002254	time 0.7447 (0.7545)	model_time 0.7445 (0.7478)	loss 3.1764 (3.3054)	grad_norm 0.7578 (1.4447/0.5392)	mem 34602MB
[2025-01-19 10:00:34 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][220/312]	eta 0:01:09 lr 0.002254	time 0.7160 (0.7532)	model_time 0.7158 (0.7468)	loss 3.6577 (3.3029)	grad_norm 1.4777 (1.4384/0.5381)	mem 34602MB
[2025-01-19 10:00:42 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][230/312]	eta 0:01:01 lr 0.002253	time 0.8041 (0.7527)	model_time 0.8035 (0.7466)	loss 3.1009 (3.3097)	grad_norm 1.5583 (1.4280/0.5328)	mem 34602MB
[2025-01-19 10:00:49 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][240/312]	eta 0:00:54 lr 0.002252	time 0.8140 (0.7527)	model_time 0.8135 (0.7468)	loss 3.5889 (3.3174)	grad_norm 1.1164 (1.4395/0.5403)	mem 34602MB
[2025-01-19 10:00:57 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][250/312]	eta 0:00:46 lr 0.002252	time 0.7157 (0.7534)	model_time 0.7156 (0.7477)	loss 3.4997 (3.3015)	grad_norm 1.1517 (1.4533/0.5568)	mem 34602MB
[2025-01-19 10:01:05 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][260/312]	eta 0:00:39 lr 0.002251	time 0.7174 (0.7535)	model_time 0.7170 (0.7479)	loss 2.5758 (3.3050)	grad_norm 2.3189 (1.4604/0.5546)	mem 34602MB
[2025-01-19 10:01:12 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][270/312]	eta 0:00:31 lr 0.002250	time 0.8083 (0.7538)	model_time 0.8079 (0.7485)	loss 3.4142 (3.2985)	grad_norm 1.4701 (1.4624/0.5469)	mem 34602MB
[2025-01-19 10:01:20 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][280/312]	eta 0:00:24 lr 0.002250	time 0.8158 (0.7536)	model_time 0.8157 (0.7485)	loss 3.5642 (3.2968)	grad_norm 1.4699 (1.4515/0.5438)	mem 34602MB
[2025-01-19 10:01:27 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][290/312]	eta 0:00:16 lr 0.002249	time 0.7357 (0.7531)	model_time 0.7355 (0.7481)	loss 3.2366 (3.2996)	grad_norm 0.9087 (1.4479/0.5392)	mem 34602MB
[2025-01-19 10:01:34 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][300/312]	eta 0:00:09 lr 0.002248	time 0.7158 (0.7525)	model_time 0.7157 (0.7476)	loss 3.4148 (3.2936)	grad_norm 2.8693 (1.4700/0.5660)	mem 34602MB
[2025-01-19 10:01:42 internimage_b_1k_224] (main.py 510): INFO Train: [138/300][310/312]	eta 0:00:01 lr 0.002248	time 0.7065 (0.7524)	model_time 0.7064 (0.7477)	loss 3.6454 (3.2902)	grad_norm 1.3075 (1.4696/0.5624)	mem 34602MB
[2025-01-19 10:01:43 internimage_b_1k_224] (main.py 519): INFO EPOCH 138 training takes 0:03:54
[2025-01-19 10:01:43 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_138.pth saving......
[2025-01-19 10:01:46 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_138.pth saved !!!
[2025-01-19 10:01:54 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.776 (7.776)	Loss 0.8159 (0.8159)	Acc@1 83.276 (83.276)	Acc@5 96.851 (96.851)	Mem 34602MB
[2025-01-19 10:01:57 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.975)	Loss 1.1178 (0.9252)	Acc@1 74.634 (80.151)	Acc@5 93.481 (95.421)	Mem 34602MB
[2025-01-19 10:01:57 internimage_b_1k_224] (main.py 575): INFO [Epoch:138] * Acc@1 80.050 Acc@5 95.449
[2025-01-19 10:01:57 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.1%
[2025-01-19 10:01:57 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.16%
[2025-01-19 10:02:06 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.206 (9.206)	Loss 0.6509 (0.6509)	Acc@1 83.667 (83.667)	Acc@5 97.412 (97.412)	Mem 34602MB
[2025-01-19 10:02:11 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.247)	Loss 0.9755 (0.7984)	Acc@1 75.806 (80.671)	Acc@5 93.945 (95.574)	Mem 34602MB
[2025-01-19 10:02:11 internimage_b_1k_224] (main.py 575): INFO [Epoch:138] * Acc@1 80.572 Acc@5 95.639
[2025-01-19 10:02:11 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.6%
[2025-01-19 10:02:11 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 10:02:15 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 10:02:15 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.57%
[2025-01-19 10:02:17 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][0/312]	eta 0:12:11 lr 0.002248	time 2.3456 (2.3456)	model_time 0.7714 (0.7714)	loss 4.0051 (4.0051)	grad_norm 1.7112 (1.7112/0.0000)	mem 34602MB
[2025-01-19 10:02:25 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][10/312]	eta 0:04:27 lr 0.002247	time 0.7272 (0.8849)	model_time 0.7271 (0.7416)	loss 3.6927 (3.2441)	grad_norm 0.6601 (1.6915/0.5457)	mem 34602MB
[2025-01-19 10:02:32 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][20/312]	eta 0:03:56 lr 0.002246	time 0.7241 (0.8091)	model_time 0.7239 (0.7338)	loss 2.7139 (3.3533)	grad_norm 1.3433 (1.7002/0.5513)	mem 34602MB
[2025-01-19 10:02:39 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][30/312]	eta 0:03:41 lr 0.002246	time 0.7187 (0.7837)	model_time 0.7186 (0.7327)	loss 3.6322 (3.2947)	grad_norm 1.3957 (1.6043/0.5166)	mem 34602MB
[2025-01-19 10:02:47 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][40/312]	eta 0:03:30 lr 0.002245	time 0.7158 (0.7743)	model_time 0.7153 (0.7356)	loss 3.2664 (3.2831)	grad_norm 5.1979 (1.6399/0.7691)	mem 34602MB
[2025-01-19 10:02:54 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][50/312]	eta 0:03:21 lr 0.002244	time 0.7211 (0.7699)	model_time 0.7207 (0.7387)	loss 3.5051 (3.2921)	grad_norm 0.8341 (1.6854/0.7842)	mem 34602MB
[2025-01-19 10:03:02 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][60/312]	eta 0:03:14 lr 0.002244	time 0.7998 (0.7708)	model_time 0.7996 (0.7447)	loss 3.3395 (3.3232)	grad_norm 1.4102 (1.6060/0.7445)	mem 34602MB
[2025-01-19 10:03:10 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][70/312]	eta 0:03:05 lr 0.002243	time 0.7510 (0.7677)	model_time 0.7505 (0.7452)	loss 3.3246 (3.3204)	grad_norm 2.2556 (1.6316/0.7033)	mem 34602MB
[2025-01-19 10:03:17 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][80/312]	eta 0:02:58 lr 0.002242	time 0.7186 (0.7677)	model_time 0.7184 (0.7479)	loss 2.7800 (3.3014)	grad_norm 1.1425 (1.6142/0.6855)	mem 34602MB
[2025-01-19 10:03:25 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][90/312]	eta 0:02:49 lr 0.002242	time 0.7178 (0.7650)	model_time 0.7177 (0.7474)	loss 3.3948 (3.3145)	grad_norm 1.1792 (1.5791/0.6644)	mem 34602MB
[2025-01-19 10:03:32 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][100/312]	eta 0:02:41 lr 0.002241	time 0.7337 (0.7619)	model_time 0.7333 (0.7459)	loss 4.1173 (3.3102)	grad_norm 1.4060 (1.5826/0.6398)	mem 34602MB
[2025-01-19 10:03:40 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][110/312]	eta 0:02:33 lr 0.002240	time 0.8312 (0.7607)	model_time 0.8311 (0.7461)	loss 3.2261 (3.3137)	grad_norm 1.2023 (1.5593/0.6230)	mem 34602MB
[2025-01-19 10:03:47 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][120/312]	eta 0:02:25 lr 0.002240	time 0.7304 (0.7599)	model_time 0.7302 (0.7465)	loss 3.2591 (3.2813)	grad_norm 0.6374 (1.5595/0.6105)	mem 34602MB
[2025-01-19 10:03:54 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][130/312]	eta 0:02:17 lr 0.002239	time 0.7166 (0.7580)	model_time 0.7164 (0.7456)	loss 2.6027 (3.2591)	grad_norm 1.7804 (1.5530/0.5986)	mem 34602MB
[2025-01-19 10:04:02 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][140/312]	eta 0:02:10 lr 0.002238	time 0.7274 (0.7564)	model_time 0.7269 (0.7449)	loss 3.2398 (3.2640)	grad_norm 1.7200 (1.5984/0.6594)	mem 34602MB
[2025-01-19 10:04:09 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][150/312]	eta 0:02:02 lr 0.002238	time 0.7213 (0.7545)	model_time 0.7211 (0.7437)	loss 2.3685 (3.2457)	grad_norm 2.1919 (1.6241/0.6757)	mem 34602MB
[2025-01-19 10:04:16 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][160/312]	eta 0:01:54 lr 0.002237	time 0.7261 (0.7535)	model_time 0.7256 (0.7434)	loss 2.3331 (3.2536)	grad_norm 1.1539 (1.6153/0.6599)	mem 34602MB
[2025-01-19 10:04:24 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][170/312]	eta 0:01:46 lr 0.002236	time 0.7186 (0.7533)	model_time 0.7184 (0.7437)	loss 3.6700 (3.2441)	grad_norm 1.1038 (1.5856/0.6529)	mem 34602MB
[2025-01-19 10:04:32 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][180/312]	eta 0:01:39 lr 0.002236	time 0.7961 (0.7553)	model_time 0.7959 (0.7463)	loss 3.7836 (3.2502)	grad_norm 1.0202 (1.5658/0.6439)	mem 34602MB
[2025-01-19 10:04:39 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][190/312]	eta 0:01:32 lr 0.002235	time 0.7348 (0.7553)	model_time 0.7343 (0.7467)	loss 2.8705 (3.2536)	grad_norm 1.3204 (1.5502/0.6344)	mem 34602MB
[2025-01-19 10:04:47 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][200/312]	eta 0:01:24 lr 0.002234	time 0.8116 (0.7554)	model_time 0.8114 (0.7472)	loss 3.2033 (3.2498)	grad_norm 1.1792 (1.5255/0.6290)	mem 34602MB
[2025-01-19 10:04:54 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][210/312]	eta 0:01:17 lr 0.002234	time 0.7191 (0.7552)	model_time 0.7189 (0.7474)	loss 2.8257 (3.2387)	grad_norm 1.8324 (1.5294/0.6242)	mem 34602MB
[2025-01-19 10:05:02 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][220/312]	eta 0:01:09 lr 0.002233	time 0.7245 (0.7552)	model_time 0.7242 (0.7477)	loss 3.5395 (3.2368)	grad_norm 2.1295 (1.5399/0.6187)	mem 34602MB
[2025-01-19 10:05:10 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][230/312]	eta 0:01:01 lr 0.002232	time 1.0013 (0.7555)	model_time 1.0008 (0.7484)	loss 3.5408 (3.2406)	grad_norm 1.1487 (1.5592/0.6367)	mem 34602MB
[2025-01-19 10:05:17 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][240/312]	eta 0:00:54 lr 0.002232	time 0.7223 (0.7553)	model_time 0.7219 (0.7485)	loss 3.7046 (3.2401)	grad_norm 1.1356 (1.5707/0.6559)	mem 34602MB
[2025-01-19 10:05:25 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][250/312]	eta 0:00:46 lr 0.002231	time 0.7198 (0.7546)	model_time 0.7196 (0.7479)	loss 2.8381 (3.2364)	grad_norm 0.7475 (1.5546/0.6578)	mem 34602MB
[2025-01-19 10:05:32 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][260/312]	eta 0:00:39 lr 0.002230	time 0.7230 (0.7539)	model_time 0.7227 (0.7475)	loss 3.5385 (3.2316)	grad_norm 0.9469 (1.5375/0.6535)	mem 34602MB
[2025-01-19 10:05:39 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][270/312]	eta 0:00:31 lr 0.002230	time 0.7228 (0.7532)	model_time 0.7224 (0.7470)	loss 2.4127 (3.2238)	grad_norm 2.4460 (1.5536/0.6633)	mem 34602MB
[2025-01-19 10:05:47 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][280/312]	eta 0:00:24 lr 0.002229	time 0.7162 (0.7525)	model_time 0.7158 (0.7465)	loss 2.8991 (3.2339)	grad_norm 1.7877 (1.5665/0.6665)	mem 34602MB
[2025-01-19 10:05:54 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][290/312]	eta 0:00:16 lr 0.002228	time 0.7305 (0.7521)	model_time 0.7303 (0.7463)	loss 3.0803 (3.2310)	grad_norm 2.2717 (1.5684/0.6662)	mem 34602MB
[2025-01-19 10:06:02 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][300/312]	eta 0:00:09 lr 0.002228	time 0.7947 (0.7524)	model_time 0.7946 (0.7468)	loss 3.2036 (3.2369)	grad_norm 0.6168 (1.5569/0.6654)	mem 34602MB
[2025-01-19 10:06:09 internimage_b_1k_224] (main.py 510): INFO Train: [139/300][310/312]	eta 0:00:01 lr 0.002227	time 0.7144 (0.7520)	model_time 0.7143 (0.7465)	loss 2.9454 (3.2330)	grad_norm 0.7366 (1.5364/0.6643)	mem 34602MB
[2025-01-19 10:06:10 internimage_b_1k_224] (main.py 519): INFO EPOCH 139 training takes 0:03:54
[2025-01-19 10:06:10 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_139.pth saving......
[2025-01-19 10:06:13 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_139.pth saved !!!
[2025-01-19 10:06:21 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.663 (7.663)	Loss 0.7802 (0.7802)	Acc@1 83.716 (83.716)	Acc@5 97.314 (97.314)	Mem 34602MB
[2025-01-19 10:06:24 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.984)	Loss 1.0641 (0.9329)	Acc@1 76.562 (80.216)	Acc@5 93.921 (95.415)	Mem 34602MB
[2025-01-19 10:06:24 internimage_b_1k_224] (main.py 575): INFO [Epoch:139] * Acc@1 80.088 Acc@5 95.429
[2025-01-19 10:06:24 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.1%
[2025-01-19 10:06:24 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.16%
[2025-01-19 10:06:35 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 11.155 (11.155)	Loss 0.6505 (0.6505)	Acc@1 83.740 (83.740)	Acc@5 97.412 (97.412)	Mem 34602MB
[2025-01-19 10:06:41 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.577)	Loss 0.9733 (0.7974)	Acc@1 75.928 (80.726)	Acc@5 93.945 (95.594)	Mem 34602MB
[2025-01-19 10:06:42 internimage_b_1k_224] (main.py 575): INFO [Epoch:139] * Acc@1 80.624 Acc@5 95.659
[2025-01-19 10:06:42 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.6%
[2025-01-19 10:06:42 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 10:06:46 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 10:06:46 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.62%
[2025-01-19 10:06:49 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][0/312]	eta 0:11:35 lr 0.002227	time 2.2293 (2.2293)	model_time 0.7469 (0.7469)	loss 2.7269 (2.7269)	grad_norm 1.3556 (1.3556/0.0000)	mem 34602MB
[2025-01-19 10:06:56 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][10/312]	eta 0:04:30 lr 0.002226	time 0.8363 (0.8964)	model_time 0.8362 (0.7613)	loss 3.3597 (3.4710)	grad_norm 0.8804 (1.2316/0.2732)	mem 34602MB
[2025-01-19 10:07:04 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][20/312]	eta 0:04:02 lr 0.002226	time 0.7072 (0.8289)	model_time 0.7070 (0.7580)	loss 2.6227 (3.4044)	grad_norm 1.1524 (1.2490/0.3015)	mem 34602MB
[2025-01-19 10:07:11 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][30/312]	eta 0:03:45 lr 0.002225	time 0.7443 (0.7986)	model_time 0.7438 (0.7505)	loss 3.4369 (3.2934)	grad_norm 0.6702 (1.5347/0.8308)	mem 34602MB
[2025-01-19 10:07:19 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][40/312]	eta 0:03:33 lr 0.002224	time 0.8240 (0.7861)	model_time 0.8238 (0.7496)	loss 3.4701 (3.3487)	grad_norm 2.2700 (1.5707/0.7894)	mem 34602MB
[2025-01-19 10:07:26 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][50/312]	eta 0:03:24 lr 0.002224	time 0.7229 (0.7786)	model_time 0.7227 (0.7492)	loss 3.8893 (3.2966)	grad_norm 1.5432 (1.5313/0.7329)	mem 34602MB
[2025-01-19 10:07:33 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][60/312]	eta 0:03:14 lr 0.002223	time 0.7172 (0.7722)	model_time 0.7171 (0.7476)	loss 3.5654 (3.2766)	grad_norm 0.7139 (1.5554/0.7134)	mem 34602MB
[2025-01-19 10:07:41 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][70/312]	eta 0:03:05 lr 0.002222	time 0.7235 (0.7656)	model_time 0.7230 (0.7444)	loss 2.7427 (3.2779)	grad_norm 1.2974 (1.5634/0.7004)	mem 34602MB
[2025-01-19 10:07:48 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][80/312]	eta 0:02:56 lr 0.002222	time 0.7172 (0.7616)	model_time 0.7169 (0.7429)	loss 3.2108 (3.2674)	grad_norm 1.9219 (1.5538/0.6921)	mem 34602MB
[2025-01-19 10:07:55 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][90/312]	eta 0:02:48 lr 0.002221	time 0.7199 (0.7596)	model_time 0.7194 (0.7430)	loss 3.6660 (3.2278)	grad_norm 2.3115 (1.5446/0.6644)	mem 34602MB
[2025-01-19 10:08:03 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][100/312]	eta 0:02:40 lr 0.002220	time 0.7185 (0.7579)	model_time 0.7183 (0.7428)	loss 3.2798 (3.2261)	grad_norm 1.9316 (1.5353/0.6400)	mem 34602MB
[2025-01-19 10:08:11 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][110/312]	eta 0:02:33 lr 0.002220	time 0.8227 (0.7599)	model_time 0.8224 (0.7462)	loss 3.6294 (3.2281)	grad_norm 1.2653 (1.5213/0.6291)	mem 34602MB
[2025-01-19 10:08:18 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][120/312]	eta 0:02:25 lr 0.002219	time 0.7170 (0.7585)	model_time 0.7168 (0.7459)	loss 2.7288 (3.2012)	grad_norm 2.3334 (1.5315/0.6355)	mem 34602MB
[2025-01-19 10:08:26 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][130/312]	eta 0:02:18 lr 0.002218	time 0.8317 (0.7588)	model_time 0.8315 (0.7471)	loss 2.9291 (3.1938)	grad_norm 2.9268 (1.5488/0.6582)	mem 34602MB
[2025-01-19 10:08:33 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][140/312]	eta 0:02:10 lr 0.002218	time 0.7268 (0.7585)	model_time 0.7267 (0.7476)	loss 3.5743 (3.2188)	grad_norm 1.5922 (1.5474/0.6413)	mem 34602MB
[2025-01-19 10:08:41 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][150/312]	eta 0:02:02 lr 0.002217	time 0.7125 (0.7564)	model_time 0.7120 (0.7462)	loss 3.5406 (3.2309)	grad_norm 2.8991 (1.5488/0.6392)	mem 34602MB
[2025-01-19 10:08:48 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][160/312]	eta 0:01:54 lr 0.002216	time 0.7508 (0.7551)	model_time 0.7506 (0.7455)	loss 3.7292 (3.2261)	grad_norm 1.2555 (1.5544/0.6371)	mem 34602MB
[2025-01-19 10:08:55 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][170/312]	eta 0:01:47 lr 0.002216	time 0.7280 (0.7547)	model_time 0.7278 (0.7457)	loss 3.3184 (3.2312)	grad_norm 1.5319 (1.5303/0.6339)	mem 34602MB
[2025-01-19 10:09:03 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][180/312]	eta 0:01:39 lr 0.002215	time 0.7612 (0.7546)	model_time 0.7608 (0.7461)	loss 4.0925 (3.2315)	grad_norm 1.2731 (1.5296/0.6242)	mem 34602MB
[2025-01-19 10:09:10 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][190/312]	eta 0:01:31 lr 0.002214	time 0.7179 (0.7533)	model_time 0.7177 (0.7452)	loss 3.1466 (3.2254)	grad_norm 1.9068 (1.5398/0.6238)	mem 34602MB
[2025-01-19 10:09:18 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][200/312]	eta 0:01:24 lr 0.002214	time 0.7192 (0.7521)	model_time 0.7190 (0.7444)	loss 2.7911 (3.2265)	grad_norm 0.7207 (1.5333/0.6215)	mem 34602MB
[2025-01-19 10:09:25 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][210/312]	eta 0:01:16 lr 0.002213	time 0.7480 (0.7518)	model_time 0.7478 (0.7444)	loss 2.2182 (3.2218)	grad_norm 0.9056 (1.5309/0.6145)	mem 34602MB
[2025-01-19 10:09:32 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][220/312]	eta 0:01:09 lr 0.002212	time 0.7191 (0.7514)	model_time 0.7186 (0.7444)	loss 2.5786 (3.2182)	grad_norm 1.5836 (1.5417/0.6338)	mem 34602MB
[2025-01-19 10:09:40 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][230/312]	eta 0:01:01 lr 0.002212	time 0.8509 (0.7522)	model_time 0.8505 (0.7454)	loss 3.6053 (3.2256)	grad_norm 0.8186 (1.5345/0.6258)	mem 34602MB
[2025-01-19 10:09:48 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][240/312]	eta 0:00:54 lr 0.002211	time 0.7189 (0.7526)	model_time 0.7185 (0.7461)	loss 3.5272 (3.2342)	grad_norm 2.3893 (1.5319/0.6201)	mem 34602MB
[2025-01-19 10:09:55 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][250/312]	eta 0:00:46 lr 0.002210	time 0.8080 (0.7529)	model_time 0.8078 (0.7467)	loss 3.0300 (3.2387)	grad_norm 1.0851 (1.5306/0.6177)	mem 34602MB
[2025-01-19 10:10:03 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][260/312]	eta 0:00:39 lr 0.002210	time 0.7154 (0.7537)	model_time 0.7152 (0.7477)	loss 2.6974 (3.2375)	grad_norm 1.0546 (1.5176/0.6149)	mem 34602MB
[2025-01-19 10:10:10 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][270/312]	eta 0:00:31 lr 0.002209	time 0.7199 (0.7529)	model_time 0.7197 (0.7471)	loss 3.2157 (3.2365)	grad_norm 1.4582 (1.5073/0.6105)	mem 34602MB
[2025-01-19 10:10:18 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][280/312]	eta 0:00:24 lr 0.002208	time 0.7439 (0.7523)	model_time 0.7437 (0.7467)	loss 3.1736 (3.2289)	grad_norm 4.0030 (1.5384/0.6536)	mem 34602MB
[2025-01-19 10:10:25 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][290/312]	eta 0:00:16 lr 0.002208	time 0.7212 (0.7520)	model_time 0.7209 (0.7466)	loss 4.0617 (3.2376)	grad_norm 2.7084 (1.5497/0.6735)	mem 34602MB
[2025-01-19 10:10:33 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][300/312]	eta 0:00:09 lr 0.002207	time 0.7123 (0.7514)	model_time 0.7122 (0.7461)	loss 3.9138 (3.2405)	grad_norm 1.3096 (1.5425/0.6681)	mem 34602MB
[2025-01-19 10:10:40 internimage_b_1k_224] (main.py 510): INFO Train: [140/300][310/312]	eta 0:00:01 lr 0.002206	time 0.7158 (0.7503)	model_time 0.7157 (0.7452)	loss 3.2983 (3.2370)	grad_norm 1.2099 (1.5447/0.6691)	mem 34602MB
[2025-01-19 10:10:40 internimage_b_1k_224] (main.py 519): INFO EPOCH 140 training takes 0:03:54
[2025-01-19 10:10:40 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_140.pth saving......
[2025-01-19 10:10:44 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_140.pth saved !!!
[2025-01-19 10:10:52 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.144 (8.144)	Loss 0.7931 (0.7931)	Acc@1 83.887 (83.887)	Acc@5 97.046 (97.046)	Mem 34602MB
[2025-01-19 10:10:55 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.012)	Loss 1.0669 (0.9271)	Acc@1 76.685 (80.238)	Acc@5 93.652 (95.377)	Mem 34602MB
[2025-01-19 10:10:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:140] * Acc@1 80.134 Acc@5 95.417
[2025-01-19 10:10:55 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.1%
[2025-01-19 10:10:55 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.16%
[2025-01-19 10:11:05 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.645 (9.645)	Loss 0.6504 (0.6504)	Acc@1 83.691 (83.691)	Acc@5 97.461 (97.461)	Mem 34602MB
[2025-01-19 10:11:10 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.320)	Loss 0.9711 (0.7965)	Acc@1 76.001 (80.768)	Acc@5 93.945 (95.630)	Mem 34602MB
[2025-01-19 10:11:10 internimage_b_1k_224] (main.py 575): INFO [Epoch:140] * Acc@1 80.666 Acc@5 95.689
[2025-01-19 10:11:10 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.7%
[2025-01-19 10:11:10 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 10:11:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 10:11:14 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.67%
[2025-01-19 10:11:16 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][0/312]	eta 0:11:13 lr 0.002206	time 2.1597 (2.1597)	model_time 0.7488 (0.7488)	loss 3.4972 (3.4972)	grad_norm 0.9853 (0.9853/0.0000)	mem 34602MB
[2025-01-19 10:11:24 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][10/312]	eta 0:04:20 lr 0.002206	time 0.7250 (0.8620)	model_time 0.7249 (0.7335)	loss 4.0013 (3.3668)	grad_norm 0.8810 (1.3855/0.5077)	mem 34602MB
[2025-01-19 10:11:31 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][20/312]	eta 0:03:54 lr 0.002205	time 0.7125 (0.8047)	model_time 0.7120 (0.7372)	loss 2.8215 (3.2420)	grad_norm 1.3733 (1.2090/0.4310)	mem 34602MB
[2025-01-19 10:11:39 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][30/312]	eta 0:03:43 lr 0.002204	time 0.7952 (0.7935)	model_time 0.7951 (0.7477)	loss 2.9933 (3.1771)	grad_norm 0.9768 (1.3004/0.5066)	mem 34602MB
[2025-01-19 10:11:46 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][40/312]	eta 0:03:33 lr 0.002204	time 0.7218 (0.7836)	model_time 0.7216 (0.7488)	loss 4.0764 (3.2413)	grad_norm 0.6520 (1.2704/0.4816)	mem 34602MB
[2025-01-19 10:11:54 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][50/312]	eta 0:03:23 lr 0.002203	time 0.7137 (0.7782)	model_time 0.7135 (0.7502)	loss 3.6034 (3.2914)	grad_norm 1.3728 (1.2577/0.4552)	mem 34602MB
[2025-01-19 10:12:01 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][60/312]	eta 0:03:15 lr 0.002202	time 0.8201 (0.7771)	model_time 0.8199 (0.7536)	loss 4.0787 (3.2978)	grad_norm 0.9101 (1.2892/0.4934)	mem 34602MB
[2025-01-19 10:12:09 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][70/312]	eta 0:03:07 lr 0.002202	time 0.7170 (0.7733)	model_time 0.7167 (0.7531)	loss 3.3251 (3.2792)	grad_norm 1.6451 (1.4703/0.8089)	mem 34602MB
[2025-01-19 10:12:16 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][80/312]	eta 0:02:58 lr 0.002201	time 0.7309 (0.7694)	model_time 0.7305 (0.7517)	loss 3.2993 (3.2764)	grad_norm 0.7762 (1.4702/0.7857)	mem 34602MB
[2025-01-19 10:12:24 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][90/312]	eta 0:02:50 lr 0.002200	time 0.7128 (0.7658)	model_time 0.7125 (0.7499)	loss 4.0295 (3.2738)	grad_norm 1.9254 (1.4653/0.7654)	mem 34602MB
[2025-01-19 10:12:31 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][100/312]	eta 0:02:42 lr 0.002200	time 0.7144 (0.7649)	model_time 0.7142 (0.7506)	loss 3.5142 (3.2598)	grad_norm 1.7641 (1.5121/0.7470)	mem 34602MB
[2025-01-19 10:12:39 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][110/312]	eta 0:02:33 lr 0.002199	time 0.7266 (0.7618)	model_time 0.7264 (0.7487)	loss 2.7938 (3.2608)	grad_norm 1.0836 (1.5211/0.7319)	mem 34602MB
[2025-01-19 10:12:46 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][120/312]	eta 0:02:25 lr 0.002198	time 0.7081 (0.7590)	model_time 0.7076 (0.7470)	loss 3.0520 (3.2756)	grad_norm 1.6250 (1.5167/0.7093)	mem 34602MB
[2025-01-19 10:12:53 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][130/312]	eta 0:02:17 lr 0.002198	time 0.7215 (0.7568)	model_time 0.7210 (0.7457)	loss 3.2862 (3.2904)	grad_norm 2.3278 (1.5256/0.6919)	mem 34602MB
[2025-01-19 10:13:01 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][140/312]	eta 0:02:10 lr 0.002197	time 0.7584 (0.7559)	model_time 0.7583 (0.7455)	loss 3.5126 (3.2847)	grad_norm 2.1475 (1.5395/0.6861)	mem 34602MB
[2025-01-19 10:13:09 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][150/312]	eta 0:02:02 lr 0.002196	time 0.7252 (0.7580)	model_time 0.7247 (0.7483)	loss 3.4421 (3.2744)	grad_norm 2.0766 (1.5297/0.6742)	mem 34602MB
[2025-01-19 10:13:16 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][160/312]	eta 0:01:55 lr 0.002196	time 0.7277 (0.7578)	model_time 0.7273 (0.7487)	loss 3.3436 (3.2780)	grad_norm 2.0680 (1.5407/0.6676)	mem 34602MB
[2025-01-19 10:13:24 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][170/312]	eta 0:01:47 lr 0.002195	time 0.7169 (0.7573)	model_time 0.7167 (0.7486)	loss 3.1052 (3.2885)	grad_norm 1.8876 (1.5326/0.6692)	mem 34602MB
[2025-01-19 10:13:32 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][180/312]	eta 0:01:40 lr 0.002194	time 0.9390 (0.7598)	model_time 0.9386 (0.7516)	loss 3.8559 (3.2905)	grad_norm 0.7694 (1.5238/0.6631)	mem 34602MB
[2025-01-19 10:13:39 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][190/312]	eta 0:01:32 lr 0.002194	time 0.8079 (0.7593)	model_time 0.8077 (0.7515)	loss 3.4908 (3.2914)	grad_norm 1.5046 (1.5302/0.6652)	mem 34602MB
[2025-01-19 10:13:46 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][200/312]	eta 0:01:24 lr 0.002193	time 0.7176 (0.7580)	model_time 0.7172 (0.7507)	loss 3.8495 (3.3030)	grad_norm 1.3217 (1.5492/0.6982)	mem 34602MB
[2025-01-19 10:13:54 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][210/312]	eta 0:01:17 lr 0.002192	time 0.7309 (0.7573)	model_time 0.7305 (0.7502)	loss 2.1958 (3.3114)	grad_norm 2.2548 (1.5591/0.6908)	mem 34602MB
[2025-01-19 10:14:01 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][220/312]	eta 0:01:09 lr 0.002192	time 0.7213 (0.7572)	model_time 0.7211 (0.7504)	loss 2.9396 (3.3016)	grad_norm 1.0826 (1.5497/0.6830)	mem 34602MB
[2025-01-19 10:14:09 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][230/312]	eta 0:01:02 lr 0.002191	time 0.7343 (0.7562)	model_time 0.7341 (0.7497)	loss 3.1560 (3.2973)	grad_norm 2.1412 (1.5422/0.6797)	mem 34602MB
[2025-01-19 10:14:16 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][240/312]	eta 0:00:54 lr 0.002190	time 0.7300 (0.7548)	model_time 0.7298 (0.7486)	loss 3.2024 (3.2927)	grad_norm 1.8546 (1.5343/0.6698)	mem 34602MB
[2025-01-19 10:14:23 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][250/312]	eta 0:00:46 lr 0.002190	time 0.7181 (0.7536)	model_time 0.7180 (0.7476)	loss 3.2303 (3.2971)	grad_norm 0.8805 (1.5221/0.6635)	mem 34602MB
[2025-01-19 10:14:31 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][260/312]	eta 0:00:39 lr 0.002189	time 0.7165 (0.7528)	model_time 0.7164 (0.7471)	loss 3.1609 (3.2943)	grad_norm 1.6386 (1.5133/0.6562)	mem 34602MB
[2025-01-19 10:14:38 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][270/312]	eta 0:00:31 lr 0.002188	time 0.7172 (0.7529)	model_time 0.7171 (0.7474)	loss 2.6068 (3.2908)	grad_norm 2.2233 (1.5063/0.6496)	mem 34602MB
[2025-01-19 10:14:46 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][280/312]	eta 0:00:24 lr 0.002188	time 0.7125 (0.7531)	model_time 0.7124 (0.7477)	loss 3.3073 (3.2937)	grad_norm 2.2825 (1.5092/0.6459)	mem 34602MB
[2025-01-19 10:14:53 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][290/312]	eta 0:00:16 lr 0.002187	time 0.7194 (0.7530)	model_time 0.7193 (0.7478)	loss 3.3688 (3.2836)	grad_norm 1.4605 (1.5222/0.6578)	mem 34602MB
[2025-01-19 10:15:01 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][300/312]	eta 0:00:09 lr 0.002186	time 0.8037 (0.7532)	model_time 0.8036 (0.7481)	loss 3.3148 (3.2804)	grad_norm 1.3395 (1.5162/0.6520)	mem 34602MB
[2025-01-19 10:15:08 internimage_b_1k_224] (main.py 665): INFO Full config saved to work_dirs/internimage_b_1k_224/config.json
[2025-01-19 10:15:08 internimage_b_1k_224] (main.py 668): INFO AMP_OPT_LEVEL: O1
AMP_TYPE: float16
AUG:
  AUTO_AUGMENT: rand-m9-mstd0.5-inc1
  COLOR_JITTER: 0.4
  CUTMIX: 1.0
  CUTMIX_MINMAX: null
  MEAN:
  - 0.485
  - 0.456
  - 0.406
  MIXUP: 0.8
  MIXUP_MODE: batch
  MIXUP_PROB: 1.0
  MIXUP_SWITCH_PROB: 0.5
  RANDOM_RESIZED_CROP: false
  RECOUNT: 1
  REMODE: pixel
  REPROB: 0.25
  STD:
  - 0.229
  - 0.224
  - 0.225
BASE:
- ''
DATA:
  BATCH_SIZE: 128
  CACHE_MODE: part
  DATASET: imagenet
  DATA_PATH: data/imagenet
  IMG_ON_MEMORY: true
  IMG_SIZE: 224
  INTERPOLATION: bicubic
  NUM_WORKERS: 8
  PIN_MEMORY: true
  ZIP_MODE: false
EVAL_22K_TO_1K: false
EVAL_FREQ: 1
EVAL_MODE: false
LOCAL_RANK: 0
MODEL:
  DROP_PATH_RATE: 0.5
  DROP_PATH_TYPE: linear
  DROP_RATE: 0.0
  INTERN_IMAGE:
    CENTER_FEATURE_SCALE: false
    CHANNELS: 112
    CORE_OP: DCNv3
    DEPTHS:
    - 4
    - 4
    - 21
    - 4
    DW_KERNEL_SIZE: null
    GROUPS:
    - 7
    - 14
    - 28
    - 56
    LAYER_SCALE: 1.0e-05
    LEVEL2_POST_NORM: false
    LEVEL2_POST_NORM_BLOCK_IDS: null
    MLP_RATIO: 4.0
    OFFSET_SCALE: 1.0
    POST_NORM: true
    REMOVE_CENTER: false
    RES_POST_NORM: false
    USE_CLIP_PROJECTOR: false
  LABEL_SMOOTHING: 0.1
  NAME: internimage_b_1k_224
  NUM_CLASSES: 1000
  PRETRAINED: ''
  RESUME: ''
  TYPE: intern_image
OUTPUT: work_dirs/internimage_b_1k_224
PRINT_FREQ: 10
SAVE_CKPT_NUM: 1
SAVE_FREQ: 1
SEED: 0
TAG: default
TEST:
  CROP: true
  SEQUENTIAL: false
THROUGHPUT_MODE: false
TRAIN:
  ACCUMULATION_STEPS: 1
  AUTO_RESUME: true
  BASE_LR: 0.004
  CLIP_GRAD: 5.0
  EMA:
    DECAY: 0.9999
    ENABLE: true
  EPOCHS: 300
  LR_LAYER_DECAY: false
  LR_LAYER_DECAY_RATIO: 0.875
  LR_SCHEDULER:
    DECAY_EPOCHS: 30
    DECAY_RATE: 0.1
    NAME: cosine
  MIN_LR: 4.0e-05
  OPTIMIZER:
    BETAS:
    - 0.9
    - 0.999
    DCN_LR_MUL: null
    EPS: 1.0e-08
    FREEZE_BACKBONE: null
    MOMENTUM: 0.9
    NAME: adamw
    USE_ZERO: false
  RAND_INIT_FT_HEAD: false
  START_EPOCH: 0
  USE_CHECKPOINT: false
  WARMUP_EPOCHS: 20
  WARMUP_LR: 4.0e-06
  WEIGHT_DECAY: 0.05

[2025-01-19 10:15:08 internimage_b_1k_224] (main.py 510): INFO Train: [141/300][310/312]	eta 0:00:01 lr 0.002186	time 0.7148 (0.7528)	model_time 0.7147 (0.7479)	loss 3.2795 (3.2833)	grad_norm 0.9172 (1.5007/0.6538)	mem 34602MB
[2025-01-19 10:15:09 internimage_b_1k_224] (main.py 519): INFO EPOCH 141 training takes 0:03:54
[2025-01-19 10:15:09 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_141.pth saving......
[2025-01-19 10:15:12 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_141.pth saved !!!
[2025-01-19 10:15:27 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.854 (14.854)	Loss 0.7919 (0.7919)	Acc@1 82.812 (82.812)	Acc@5 96.899 (96.899)	Mem 34602MB
[2025-01-19 10:15:34 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.978)	Loss 1.0416 (0.9086)	Acc@1 77.124 (80.289)	Acc@5 94.238 (95.372)	Mem 34602MB
[2025-01-19 10:15:35 internimage_b_1k_224] (main.py 575): INFO [Epoch:141] * Acc@1 80.156 Acc@5 95.371
[2025-01-19 10:15:35 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.2%
[2025-01-19 10:15:35 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.16%
[2025-01-19 10:15:51 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.604 (16.604)	Loss 0.6502 (0.6502)	Acc@1 83.740 (83.740)	Acc@5 97.485 (97.485)	Mem 34602MB
[2025-01-19 10:16:00 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.289)	Loss 0.9692 (0.7957)	Acc@1 76.099 (80.813)	Acc@5 94.019 (95.676)	Mem 34602MB
[2025-01-19 10:16:00 internimage_b_1k_224] (main.py 575): INFO [Epoch:141] * Acc@1 80.716 Acc@5 95.725
[2025-01-19 10:16:00 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.7%
[2025-01-19 10:16:00 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 10:16:04 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 10:16:04 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.72%
[2025-01-19 10:16:06 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][0/312]	eta 0:12:08 lr 0.002186	time 2.3338 (2.3338)	model_time 0.7394 (0.7394)	loss 2.3377 (2.3377)	grad_norm 1.7902 (1.7902/0.0000)	mem 34602MB
[2025-01-19 10:16:14 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][10/312]	eta 0:04:27 lr 0.002185	time 0.7361 (0.8844)	model_time 0.7360 (0.7392)	loss 3.1671 (3.1561)	grad_norm 1.9534 (1.5908/0.5703)	mem 34602MB
[2025-01-19 10:16:21 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][20/312]	eta 0:03:57 lr 0.002184	time 0.7215 (0.8137)	model_time 0.7213 (0.7375)	loss 2.6075 (3.1443)	grad_norm 0.9795 (1.4759/0.5590)	mem 34602MB
[2025-01-19 10:16:28 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][30/312]	eta 0:03:43 lr 0.002184	time 0.7224 (0.7932)	model_time 0.7222 (0.7415)	loss 3.1454 (3.2151)	grad_norm 1.4888 (1.4900/0.5340)	mem 34602MB
[2025-01-19 10:16:36 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][40/312]	eta 0:03:32 lr 0.002183	time 0.7262 (0.7801)	model_time 0.7260 (0.7409)	loss 3.5483 (3.2053)	grad_norm 1.7047 (1.5653/0.6194)	mem 34602MB
[2025-01-19 10:16:43 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][50/312]	eta 0:03:22 lr 0.002182	time 0.7160 (0.7713)	model_time 0.7159 (0.7397)	loss 3.7896 (3.2704)	grad_norm 0.7454 (1.6117/0.6554)	mem 34602MB
[2025-01-19 10:16:51 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][60/312]	eta 0:03:12 lr 0.002182	time 0.7419 (0.7647)	model_time 0.7415 (0.7382)	loss 3.7929 (3.2751)	grad_norm 0.8840 (1.6140/0.6812)	mem 34602MB
[2025-01-19 10:16:58 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][70/312]	eta 0:03:04 lr 0.002181	time 0.7168 (0.7616)	model_time 0.7163 (0.7389)	loss 3.3336 (3.2615)	grad_norm 0.9353 (1.6003/0.6619)	mem 34602MB
[2025-01-19 10:17:06 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][80/312]	eta 0:02:56 lr 0.002180	time 0.7175 (0.7620)	model_time 0.7170 (0.7420)	loss 3.3507 (3.2911)	grad_norm 1.0700 (1.5486/0.6452)	mem 34602MB
[2025-01-19 10:17:13 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][90/312]	eta 0:02:49 lr 0.002180	time 0.7960 (0.7618)	model_time 0.7958 (0.7438)	loss 3.4282 (3.2910)	grad_norm 0.7524 (1.5413/0.6240)	mem 34602MB
[2025-01-19 10:17:21 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][100/312]	eta 0:02:41 lr 0.002179	time 0.7318 (0.7602)	model_time 0.7313 (0.7440)	loss 3.4294 (3.2827)	grad_norm 0.9767 (1.5100/0.6166)	mem 34602MB
[2025-01-19 10:17:28 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][110/312]	eta 0:02:33 lr 0.002178	time 0.8002 (0.7607)	model_time 0.8000 (0.7459)	loss 2.5297 (3.2469)	grad_norm 1.7571 (1.5142/0.5993)	mem 34602MB
[2025-01-19 10:17:36 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][120/312]	eta 0:02:25 lr 0.002178	time 0.7155 (0.7593)	model_time 0.7153 (0.7457)	loss 2.7461 (3.2295)	grad_norm 2.1117 (1.5372/0.6180)	mem 34602MB
[2025-01-19 10:17:43 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][130/312]	eta 0:02:18 lr 0.002177	time 0.7092 (0.7587)	model_time 0.7089 (0.7461)	loss 2.7843 (3.2306)	grad_norm 2.2728 (1.5516/0.6132)	mem 34602MB
[2025-01-19 10:17:51 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][140/312]	eta 0:02:10 lr 0.002176	time 0.8013 (0.7571)	model_time 0.8011 (0.7454)	loss 3.0888 (3.2258)	grad_norm 1.5770 (1.5459/0.6175)	mem 34602MB
[2025-01-19 10:17:58 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][150/312]	eta 0:02:02 lr 0.002176	time 0.7145 (0.7565)	model_time 0.7140 (0.7456)	loss 3.2077 (3.2078)	grad_norm 1.2826 (1.5173/0.6124)	mem 34602MB
[2025-01-19 10:18:05 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][160/312]	eta 0:01:54 lr 0.002175	time 0.7423 (0.7551)	model_time 0.7420 (0.7448)	loss 3.5103 (3.2141)	grad_norm 0.8600 (1.4926/0.6037)	mem 34602MB
[2025-01-19 10:18:13 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][170/312]	eta 0:01:47 lr 0.002174	time 0.7116 (0.7551)	model_time 0.7114 (0.7454)	loss 2.2527 (3.2101)	grad_norm 0.6606 (1.5027/0.6046)	mem 34602MB
[2025-01-19 10:18:20 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][180/312]	eta 0:01:39 lr 0.002174	time 0.7158 (0.7538)	model_time 0.7157 (0.7446)	loss 2.3087 (3.2017)	grad_norm 0.7149 (1.4975/0.6076)	mem 34602MB
[2025-01-19 10:18:28 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][190/312]	eta 0:01:31 lr 0.002173	time 0.7147 (0.7531)	model_time 0.7145 (0.7444)	loss 3.2864 (3.2105)	grad_norm 0.9875 (1.5043/0.6209)	mem 34602MB
[2025-01-19 10:18:35 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][200/312]	eta 0:01:24 lr 0.002172	time 0.8213 (0.7537)	model_time 0.8210 (0.7453)	loss 2.3518 (3.2097)	grad_norm 1.2435 (1.5272/0.6441)	mem 34602MB
[2025-01-19 10:18:43 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][210/312]	eta 0:01:16 lr 0.002172	time 0.7934 (0.7541)	model_time 0.7932 (0.7461)	loss 3.6511 (3.2049)	grad_norm 0.6810 (1.5171/0.6432)	mem 34602MB
[2025-01-19 10:18:51 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][220/312]	eta 0:01:09 lr 0.002171	time 0.8220 (0.7542)	model_time 0.8219 (0.7465)	loss 2.6867 (3.2003)	grad_norm 0.8168 (1.5053/0.6334)	mem 34602MB
[2025-01-19 10:18:58 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][230/312]	eta 0:01:01 lr 0.002170	time 0.7925 (0.7546)	model_time 0.7920 (0.7473)	loss 3.4513 (3.1937)	grad_norm 0.6630 (1.4982/0.6311)	mem 34602MB
[2025-01-19 10:19:06 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][240/312]	eta 0:00:54 lr 0.002170	time 0.7224 (0.7540)	model_time 0.7223 (0.7470)	loss 3.4833 (3.2019)	grad_norm 1.4845 (1.4926/0.6227)	mem 34602MB
[2025-01-19 10:19:13 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][250/312]	eta 0:00:46 lr 0.002169	time 0.7298 (0.7532)	model_time 0.7293 (0.7465)	loss 2.6870 (3.1998)	grad_norm 1.1017 (1.4780/0.6199)	mem 34602MB
[2025-01-19 10:19:20 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][260/312]	eta 0:00:39 lr 0.002168	time 0.7391 (0.7522)	model_time 0.7389 (0.7457)	loss 2.6658 (3.1977)	grad_norm 2.5265 (1.5084/0.6531)	mem 34602MB
[2025-01-19 10:19:28 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][270/312]	eta 0:00:31 lr 0.002168	time 0.8033 (0.7528)	model_time 0.8031 (0.7466)	loss 3.2969 (3.2000)	grad_norm 1.4159 (1.5206/0.6592)	mem 34602MB
[2025-01-19 10:19:35 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][280/312]	eta 0:00:24 lr 0.002167	time 0.7789 (0.7525)	model_time 0.7784 (0.7465)	loss 3.9423 (3.2021)	grad_norm 0.7883 (1.5078/0.6533)	mem 34602MB
[2025-01-19 10:19:43 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][290/312]	eta 0:00:16 lr 0.002166	time 0.7170 (0.7521)	model_time 0.7168 (0.7462)	loss 3.3685 (3.2070)	grad_norm 1.0860 (1.4979/0.6475)	mem 34602MB
[2025-01-19 10:19:50 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][300/312]	eta 0:00:09 lr 0.002166	time 0.7066 (0.7509)	model_time 0.7065 (0.7453)	loss 3.4784 (3.2107)	grad_norm 2.0556 (1.4881/0.6433)	mem 34602MB
[2025-01-19 10:19:57 internimage_b_1k_224] (main.py 510): INFO Train: [142/300][310/312]	eta 0:00:01 lr 0.002165	time 0.7140 (0.7501)	model_time 0.7139 (0.7446)	loss 3.2168 (3.2139)	grad_norm 1.1168 (1.4806/0.6393)	mem 34602MB
[2025-01-19 10:19:58 internimage_b_1k_224] (main.py 519): INFO EPOCH 142 training takes 0:03:54
[2025-01-19 10:19:58 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_142.pth saving......
[2025-01-19 10:20:01 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_142.pth saved !!!
[2025-01-19 10:20:15 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 13.500 (13.500)	Loss 0.8148 (0.8148)	Acc@1 83.936 (83.936)	Acc@5 97.119 (97.119)	Mem 34602MB
[2025-01-19 10:20:21 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.770)	Loss 1.0940 (0.9353)	Acc@1 76.123 (80.265)	Acc@5 93.555 (95.241)	Mem 34602MB
[2025-01-19 10:20:21 internimage_b_1k_224] (main.py 575): INFO [Epoch:142] * Acc@1 80.112 Acc@5 95.252
[2025-01-19 10:20:21 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.1%
[2025-01-19 10:20:21 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.16%
[2025-01-19 10:20:36 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.882 (14.882)	Loss 0.6501 (0.6501)	Acc@1 83.740 (83.740)	Acc@5 97.485 (97.485)	Mem 34602MB
[2025-01-19 10:20:43 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.185 (2.028)	Loss 0.9672 (0.7949)	Acc@1 76.172 (80.882)	Acc@5 93.994 (95.710)	Mem 34602MB
[2025-01-19 10:20:43 internimage_b_1k_224] (main.py 575): INFO [Epoch:142] * Acc@1 80.770 Acc@5 95.759
[2025-01-19 10:20:43 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.8%
[2025-01-19 10:20:43 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 10:20:47 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 10:20:47 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.77%
[2025-01-19 10:20:49 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][0/312]	eta 0:11:06 lr 0.002165	time 2.1365 (2.1365)	model_time 0.7336 (0.7336)	loss 2.9239 (2.9239)	grad_norm 0.8358 (0.8358/0.0000)	mem 34602MB
[2025-01-19 10:20:57 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][10/312]	eta 0:04:32 lr 0.002164	time 0.8564 (0.9024)	model_time 0.8559 (0.7745)	loss 4.1080 (3.2810)	grad_norm 1.3331 (1.2428/0.4617)	mem 34602MB
[2025-01-19 10:21:05 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][20/312]	eta 0:04:08 lr 0.002164	time 0.8061 (0.8515)	model_time 0.8059 (0.7843)	loss 3.1880 (3.1840)	grad_norm 2.2110 (1.6226/0.7462)	mem 34602MB
[2025-01-19 10:21:13 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][30/312]	eta 0:03:50 lr 0.002163	time 0.7072 (0.8174)	model_time 0.7070 (0.7718)	loss 3.6856 (3.2517)	grad_norm 0.6641 (1.5638/0.7607)	mem 34602MB
[2025-01-19 10:21:20 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][40/312]	eta 0:03:39 lr 0.002162	time 0.7190 (0.8062)	model_time 0.7185 (0.7716)	loss 1.9690 (3.2147)	grad_norm 2.2884 (1.7031/0.8117)	mem 34602MB
[2025-01-19 10:21:28 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][50/312]	eta 0:03:29 lr 0.002162	time 0.7463 (0.7995)	model_time 0.7461 (0.7716)	loss 3.1708 (3.2404)	grad_norm 1.2000 (1.6430/0.7989)	mem 34602MB
[2025-01-19 10:21:35 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][60/312]	eta 0:03:18 lr 0.002161	time 0.7414 (0.7885)	model_time 0.7412 (0.7651)	loss 2.6989 (3.1847)	grad_norm 1.1899 (1.6631/0.8018)	mem 34602MB
[2025-01-19 10:21:43 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][70/312]	eta 0:03:08 lr 0.002160	time 0.7277 (0.7803)	model_time 0.7272 (0.7601)	loss 3.6646 (3.1834)	grad_norm 0.9678 (1.6145/0.7635)	mem 34602MB
[2025-01-19 10:21:50 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][80/312]	eta 0:03:00 lr 0.002160	time 0.7187 (0.7777)	model_time 0.7185 (0.7600)	loss 2.2134 (3.1632)	grad_norm 1.2451 (1.5996/0.7366)	mem 34602MB
[2025-01-19 10:21:58 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][90/312]	eta 0:02:51 lr 0.002159	time 0.7254 (0.7730)	model_time 0.7253 (0.7572)	loss 3.0235 (3.1794)	grad_norm 1.0697 (1.5895/0.7214)	mem 34602MB
[2025-01-19 10:22:05 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][100/312]	eta 0:02:43 lr 0.002158	time 0.7661 (0.7690)	model_time 0.7656 (0.7548)	loss 3.2913 (3.1957)	grad_norm 1.4556 (1.5680/0.6920)	mem 34602MB
[2025-01-19 10:22:05 internimage_b_1k_224] (main.py 174): INFO Creating model:intern_image/internimage_b_1k_224
[2025-01-19 10:22:12 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][110/312]	eta 0:02:34 lr 0.002158	time 0.7462 (0.7651)	model_time 0.7457 (0.7521)	loss 3.1156 (3.2106)	grad_norm 2.4207 (1.6335/0.7613)	mem 34602MB
[2025-01-19 10:22:20 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][120/312]	eta 0:02:26 lr 0.002157	time 0.7184 (0.7625)	model_time 0.7182 (0.7505)	loss 2.6768 (3.2184)	grad_norm 1.1529 (1.6435/0.7633)	mem 34602MB
[2025-01-19 10:22:27 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][130/312]	eta 0:02:18 lr 0.002156	time 0.7181 (0.7622)	model_time 0.7179 (0.7511)	loss 3.6091 (3.2279)	grad_norm 0.6821 (1.6229/0.7509)	mem 34602MB
[2025-01-19 10:22:34 internimage_b_1k_224] (main.py 177): INFO InternImage(
  (patch_embed): StemLayer(
    (conv1): Conv2d(3, 56, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
    (norm1): Sequential(
      (0): to_channels_last()
      (1): LayerNorm((56,), eps=1e-06, elementwise_affine=True)
      (2): to_channels_first()
    )
    (act): GELU()
    (conv2): Conv2d(56, 112, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
    (norm2): Sequential(
      (0): to_channels_last()
      (1): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
    )
  )
  (pos_drop): Dropout(p=0.0, inplace=False)
  (levels): ModuleList(
    (0): InternImageBlock(
      (blocks): ModuleList(
        (0): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=112)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=112, out_features=126, bias=True)
            (mask): Linear(in_features=112, out_features=63, bias=True)
            (input_proj): Linear(in_features=112, out_features=112, bias=True)
            (output_proj): Linear(in_features=112, out_features=112, bias=True)
          )
          (drop_path): Identity()
          (norm2): Sequential(
            (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=112, out_features=448, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=448, out_features=112, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (1): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=112)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=112, out_features=126, bias=True)
            (mask): Linear(in_features=112, out_features=63, bias=True)
            (input_proj): Linear(in_features=112, out_features=112, bias=True)
            (output_proj): Linear(in_features=112, out_features=112, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.016)
          (norm2): Sequential(
            (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=112, out_features=448, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=448, out_features=112, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (2): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=112)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=112, out_features=126, bias=True)
            (mask): Linear(in_features=112, out_features=63, bias=True)
            (input_proj): Linear(in_features=112, out_features=112, bias=True)
            (output_proj): Linear(in_features=112, out_features=112, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.031)
          (norm2): Sequential(
            (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=112, out_features=448, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=448, out_features=112, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (3): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=112)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=112, out_features=126, bias=True)
            (mask): Linear(in_features=112, out_features=63, bias=True)
            (input_proj): Linear(in_features=112, out_features=112, bias=True)
            (output_proj): Linear(in_features=112, out_features=112, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.047)
          (norm2): Sequential(
            (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=112, out_features=448, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=448, out_features=112, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
      )
      (downsample): DownsampleLayer(
        (conv): Conv2d(112, 224, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        (norm): Sequential(
          (0): to_channels_last()
          (1): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
        )
      )
    )
    (1): InternImageBlock(
      (blocks): ModuleList(
        (0): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(224, 224, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=224)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=224, out_features=252, bias=True)
            (mask): Linear(in_features=224, out_features=126, bias=True)
            (input_proj): Linear(in_features=224, out_features=224, bias=True)
            (output_proj): Linear(in_features=224, out_features=224, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.062)
          (norm2): Sequential(
            (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=224, out_features=896, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=896, out_features=224, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (1): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(224, 224, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=224)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=224, out_features=252, bias=True)
            (mask): Linear(in_features=224, out_features=126, bias=True)
            (input_proj): Linear(in_features=224, out_features=224, bias=True)
            (output_proj): Linear(in_features=224, out_features=224, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.078)
          (norm2): Sequential(
            (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=224, out_features=896, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=896, out_features=224, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (2): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(224, 224, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=224)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=224, out_features=252, bias=True)
            (mask): Linear(in_features=224, out_features=126, bias=True)
            (input_proj): Linear(in_features=224, out_features=224, bias=True)
            (output_proj): Linear(in_features=224, out_features=224, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.094)
          (norm2): Sequential(
            (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=224, out_features=896, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=896, out_features=224, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (3): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(224, 224, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=224)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=224, out_features=252, bias=True)
            (mask): Linear(in_features=224, out_features=126, bias=True)
            (input_proj): Linear(in_features=224, out_features=224, bias=True)
            (output_proj): Linear(in_features=224, out_features=224, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.109)
          (norm2): Sequential(
            (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=224, out_features=896, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=896, out_features=224, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
      )
      (downsample): DownsampleLayer(
        (conv): Conv2d(224, 448, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        (norm): Sequential(
          (0): to_channels_last()
          (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
        )
      )
    )
    (2): InternImageBlock(
      (blocks): ModuleList(
        (0): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.125)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (1): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.141)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (2): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.156)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (3): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.172)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (4): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.188)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (5): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.203)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (6): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.219)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (7): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.234)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (8): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.250)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (9): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.266)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (10): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.281)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (11): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.297)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (12): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.312)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (13): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.328)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (14): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.344)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (15): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.359)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (16): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.375)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (17): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.391)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (18): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.406)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (19): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.422)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (20): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=448, out_features=504, bias=True)
            (mask): Linear(in_features=448, out_features=252, bias=True)
            (input_proj): Linear(in_features=448, out_features=448, bias=True)
            (output_proj): Linear(in_features=448, out_features=448, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.438)
          (norm2): Sequential(
            (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=448, out_features=1792, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1792, out_features=448, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
      )
      (downsample): DownsampleLayer(
        (conv): Conv2d(448, 896, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        (norm): Sequential(
          (0): to_channels_last()
          (1): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
        )
      )
    )
    (3): InternImageBlock(
      (blocks): ModuleList(
        (0): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(896, 896, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=896)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=896, out_features=1008, bias=True)
            (mask): Linear(in_features=896, out_features=504, bias=True)
            (input_proj): Linear(in_features=896, out_features=896, bias=True)
            (output_proj): Linear(in_features=896, out_features=896, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.453)
          (norm2): Sequential(
            (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=896, out_features=3584, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=3584, out_features=896, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (1): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(896, 896, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=896)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=896, out_features=1008, bias=True)
            (mask): Linear(in_features=896, out_features=504, bias=True)
            (input_proj): Linear(in_features=896, out_features=896, bias=True)
            (output_proj): Linear(in_features=896, out_features=896, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.469)
          (norm2): Sequential(
            (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=896, out_features=3584, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=3584, out_features=896, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (2): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(896, 896, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=896)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=896, out_features=1008, bias=True)
            (mask): Linear(in_features=896, out_features=504, bias=True)
            (input_proj): Linear(in_features=896, out_features=896, bias=True)
            (output_proj): Linear(in_features=896, out_features=896, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.484)
          (norm2): Sequential(
            (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=896, out_features=3584, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=3584, out_features=896, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (3): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(896, 896, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=896)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=896, out_features=1008, bias=True)
            (mask): Linear(in_features=896, out_features=504, bias=True)
            (input_proj): Linear(in_features=896, out_features=896, bias=True)
            (output_proj): Linear(in_features=896, out_features=896, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.500)
          (norm2): Sequential(
            (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=896, out_features=3584, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=3584, out_features=896, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
      )
    )
  )
  (conv_head): Sequential(
    (0): Conv2d(896, 1344, kernel_size=(1, 1), stride=(1, 1), bias=False)
    (1): Sequential(
      (0): BatchNorm2d(1344, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (2): GELU()
  )
  (head): Linear(in_features=1344, out_features=1000, bias=True)
  (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
)
[2025-01-19 10:22:35 internimage_b_1k_224] (main.py 213): INFO Using native Torch AMP. Training in mixed precision.
[2025-01-19 10:22:35 internimage_b_1k_224] (main.py 225): INFO using fp16_compress_hook!
[2025-01-19 10:22:35 internimage_b_1k_224] (main.py 233): INFO number of params: 97461832
[2025-01-19 10:22:35 internimage_b_1k_224] (main.py 265): INFO auto resuming from work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth
[2025-01-19 10:22:35 internimage_b_1k_224] (utils.py 60): INFO ==============> Resuming form work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth....................
[2025-01-19 10:22:35 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][140/312]	eta 0:02:11 lr 0.002156	time 0.8086 (0.7633)	model_time 0.8085 (0.7529)	loss 3.9582 (3.2325)	grad_norm 0.9693 (1.6186/0.7458)	mem 34602MB
[2025-01-19 10:22:38 internimage_b_1k_224] (utils.py 92): INFO <All keys matched successfully>
[2025-01-19 10:22:39 internimage_b_1k_224] (utils.py 110): INFO => loaded successfully work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth (epoch 142)
[2025-01-19 10:22:42 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][150/312]	eta 0:02:03 lr 0.002155	time 0.7926 (0.7629)	model_time 0.7924 (0.7533)	loss 3.4762 (3.2281)	grad_norm 1.6399 (1.5973/0.7357)	mem 34602MB
[2025-01-19 10:22:50 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][160/312]	eta 0:01:56 lr 0.002154	time 0.7529 (0.7634)	model_time 0.7527 (0.7544)	loss 3.7034 (3.2318)	grad_norm 2.0425 (1.6305/0.7432)	mem 34602MB
[2025-01-19 10:22:57 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][170/312]	eta 0:01:48 lr 0.002154	time 0.7193 (0.7617)	model_time 0.7191 (0.7531)	loss 3.4466 (3.2337)	grad_norm 1.3855 (1.6123/0.7374)	mem 34602MB
[2025-01-19 10:23:05 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][180/312]	eta 0:01:40 lr 0.002153	time 0.7266 (0.7604)	model_time 0.7264 (0.7522)	loss 3.1919 (3.2334)	grad_norm 1.4474 (1.5854/0.7283)	mem 34602MB
[2025-01-19 10:23:07 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 28.878 (28.878)	Loss 0.8298 (0.8298)	Acc@1 83.887 (83.887)	Acc@5 97.119 (97.119)	Mem 3458MB
[2025-01-19 10:23:10 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.179 (2.877)	Loss 1.1067 (0.9483)	Acc@1 76.050 (80.262)	Acc@5 93.604 (95.264)	Mem 3458MB
[2025-01-19 10:23:11 internimage_b_1k_224] (main.py 579): INFO  * Acc@1 80.122 Acc@5 95.270
[2025-01-19 10:23:11 internimage_b_1k_224] (main.py 277): INFO Accuracy of the network on the 50000 test images: 80.1%
[2025-01-19 10:23:11 internimage_b_1k_224] (utils.py 24): INFO ==============> Resuming form work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth....................
[2025-01-19 10:23:12 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][190/312]	eta 0:01:32 lr 0.002152	time 0.7269 (0.7587)	model_time 0.7266 (0.7510)	loss 2.5130 (3.2396)	grad_norm 1.6918 (1.5677/0.7155)	mem 34602MB
[2025-01-19 10:23:14 internimage_b_1k_224] (utils.py 44): INFO <All keys matched successfully>
[2025-01-19 10:23:14 internimage_b_1k_224] (utils.py 45): INFO Loaded state_dict_ema
[2025-01-19 10:23:20 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][200/312]	eta 0:01:25 lr 0.002152	time 0.7667 (0.7593)	model_time 0.7663 (0.7520)	loss 3.4880 (3.2298)	grad_norm 0.8749 (1.5823/0.7360)	mem 34602MB
[2025-01-19 10:23:24 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 10.402 (10.402)	Loss 0.6504 (0.6504)	Acc@1 83.740 (83.740)	Acc@5 97.485 (97.485)	Mem 4206MB
[2025-01-19 10:23:27 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][210/312]	eta 0:01:17 lr 0.002151	time 0.7347 (0.7580)	model_time 0.7345 (0.7510)	loss 3.3617 (3.2216)	grad_norm 1.0872 (1.5688/0.7257)	mem 34602MB
[2025-01-19 10:23:28 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.179 (1.338)	Loss 0.9670 (0.7948)	Acc@1 76.172 (80.884)	Acc@5 93.994 (95.701)	Mem 4206MB
[2025-01-19 10:23:29 internimage_b_1k_224] (main.py 579): INFO  * Acc@1 80.776 Acc@5 95.751
[2025-01-19 10:23:29 internimage_b_1k_224] (main.py 297): INFO Accuracy of the ema network on the 50000 test images: 80.8%
[2025-01-19 10:23:29 internimage_b_1k_224] (main.py 308): INFO Start training
[2025-01-19 10:23:34 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][220/312]	eta 0:01:09 lr 0.002150	time 0.7215 (0.7565)	model_time 0.7213 (0.7498)	loss 2.2937 (3.2194)	grad_norm 1.2063 (1.5643/0.7195)	mem 34602MB
[2025-01-19 10:23:36 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][0/312]	eta 0:39:03 lr 0.002165	time 7.5109 (7.5109)	model_time 4.6858 (4.6858)	loss 4.0577 (4.0577)	grad_norm 0.8639 (0.8639/0.0000)	mem 34235MB
[2025-01-19 10:23:42 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][230/312]	eta 0:01:01 lr 0.002150	time 0.7176 (0.7555)	model_time 0.7172 (0.7490)	loss 3.3994 (3.2171)	grad_norm 1.5675 (1.5550/0.7073)	mem 34602MB
[2025-01-19 10:23:44 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][10/312]	eta 0:07:03 lr 0.002164	time 0.7432 (1.4028)	model_time 0.7430 (1.1457)	loss 3.0858 (3.5964)	grad_norm 1.0464 (1.7788/0.6154)	mem 34604MB
[2025-01-19 10:23:49 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][240/312]	eta 0:00:54 lr 0.002149	time 0.7193 (0.7544)	model_time 0.7191 (0.7482)	loss 2.9489 (3.2118)	grad_norm 1.5386 (1.5576/0.7031)	mem 34602MB
[2025-01-19 10:23:51 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][20/312]	eta 0:05:16 lr 0.002164	time 0.7207 (1.0842)	model_time 0.7201 (0.9493)	loss 3.5036 (3.5252)	grad_norm 0.9694 (1.6987/0.5725)	mem 34604MB
[2025-01-19 10:23:57 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][250/312]	eta 0:00:46 lr 0.002148	time 0.7092 (0.7542)	model_time 0.7089 (0.7483)	loss 2.3311 (3.2016)	grad_norm 1.0949 (1.5476/0.6957)	mem 34602MB
[2025-01-19 10:23:59 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][30/312]	eta 0:04:33 lr 0.002163	time 0.7190 (0.9702)	model_time 0.7188 (0.8788)	loss 2.4763 (3.5193)	grad_norm 1.7894 (1.7265/0.7272)	mem 34604MB
[2025-01-19 10:24:04 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][260/312]	eta 0:00:39 lr 0.002148	time 0.8046 (0.7550)	model_time 0.8041 (0.7492)	loss 3.4393 (3.2059)	grad_norm 1.6357 (1.5792/0.7263)	mem 34602MB
[2025-01-19 10:24:06 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][40/312]	eta 0:04:07 lr 0.002162	time 0.7194 (0.9113)	model_time 0.7192 (0.8421)	loss 3.0558 (3.4411)	grad_norm 2.7017 (1.7403/0.6876)	mem 34604MB
[2025-01-19 10:24:12 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][270/312]	eta 0:00:31 lr 0.002147	time 0.7214 (0.7550)	model_time 0.7210 (0.7495)	loss 2.9850 (3.2104)	grad_norm 0.7096 (1.5737/0.7275)	mem 34602MB
[2025-01-19 10:24:14 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][50/312]	eta 0:03:50 lr 0.002162	time 0.7178 (0.8806)	model_time 0.7173 (0.8249)	loss 3.7513 (3.4197)	grad_norm 1.0401 (1.7584/0.6722)	mem 34604MB
[2025-01-19 10:24:19 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][280/312]	eta 0:00:24 lr 0.002146	time 0.7164 (0.7552)	model_time 0.7163 (0.7498)	loss 2.2280 (3.2107)	grad_norm 0.6567 (1.5655/0.7196)	mem 34602MB
[2025-01-19 10:24:21 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][60/312]	eta 0:03:35 lr 0.002161	time 0.7468 (0.8563)	model_time 0.7464 (0.8097)	loss 3.1598 (3.3786)	grad_norm 1.4513 (1.7084/0.6813)	mem 34604MB
[2025-01-19 10:24:27 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][290/312]	eta 0:00:16 lr 0.002146	time 0.7246 (0.7549)	model_time 0.7244 (0.7497)	loss 2.7575 (3.2115)	grad_norm 2.4235 (1.5670/0.7161)	mem 34602MB
[2025-01-19 10:24:28 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][70/312]	eta 0:03:22 lr 0.002160	time 0.7194 (0.8376)	model_time 0.7189 (0.7976)	loss 3.1145 (3.3463)	grad_norm 1.3498 (1.6679/0.6525)	mem 34604MB
[2025-01-19 10:24:34 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][300/312]	eta 0:00:09 lr 0.002145	time 0.7155 (0.7543)	model_time 0.7154 (0.7493)	loss 3.7591 (3.2120)	grad_norm 1.2935 (1.5689/0.7198)	mem 34602MB
[2025-01-19 10:24:35 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][80/312]	eta 0:03:11 lr 0.002160	time 0.7271 (0.8241)	model_time 0.7266 (0.7889)	loss 2.8326 (3.3278)	grad_norm 0.6020 (1.6008/0.6507)	mem 34604MB
[2025-01-19 10:24:41 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][310/312]	eta 0:00:01 lr 0.002144	time 0.7151 (0.7531)	model_time 0.7150 (0.7482)	loss 2.8361 (3.2092)	grad_norm 1.3739 (1.5642/0.7184)	mem 34602MB
[2025-01-19 10:24:42 internimage_b_1k_224] (main.py 519): INFO EPOCH 143 training takes 0:03:54
[2025-01-19 10:24:42 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_143.pth saving......
[2025-01-19 10:24:43 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][90/312]	eta 0:03:00 lr 0.002159	time 0.7351 (0.8140)	model_time 0.7346 (0.7826)	loss 3.7534 (3.3163)	grad_norm 1.3537 (1.5819/0.6532)	mem 34604MB
[2025-01-19 10:24:45 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_143.pth saved !!!
[2025-01-19 10:24:50 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][100/312]	eta 0:02:50 lr 0.002158	time 0.7291 (0.8053)	model_time 0.7287 (0.7771)	loss 3.5974 (3.3246)	grad_norm 0.7032 (1.5311/0.6566)	mem 34604MB
[2025-01-19 10:24:53 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.153 (7.153)	Loss 0.8197 (0.8197)	Acc@1 83.276 (83.276)	Acc@5 96.826 (96.826)	Mem 34602MB
[2025-01-19 10:24:56 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.948)	Loss 1.0800 (0.9298)	Acc@1 76.123 (80.513)	Acc@5 93.994 (95.459)	Mem 34602MB
[2025-01-19 10:24:56 internimage_b_1k_224] (main.py 575): INFO [Epoch:143] * Acc@1 80.360 Acc@5 95.491
[2025-01-19 10:24:56 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.4%
[2025-01-19 10:24:56 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 10:24:57 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][110/312]	eta 0:02:41 lr 0.002158	time 0.7210 (0.7984)	model_time 0.7208 (0.7727)	loss 2.7783 (3.3209)	grad_norm 0.7955 (1.5056/0.6430)	mem 34604MB
[2025-01-19 10:25:00 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 10:25:00 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.36%
[2025-01-19 10:25:05 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][120/312]	eta 0:02:32 lr 0.002157	time 0.7298 (0.7932)	model_time 0.7297 (0.7696)	loss 2.0479 (3.3157)	grad_norm 2.0146 (1.5201/0.6346)	mem 34604MB
[2025-01-19 10:25:07 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.228 (7.228)	Loss 0.6502 (0.6502)	Acc@1 83.740 (83.740)	Acc@5 97.485 (97.485)	Mem 34602MB
[2025-01-19 10:25:10 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.959)	Loss 0.9655 (0.7942)	Acc@1 76.245 (80.939)	Acc@5 94.043 (95.734)	Mem 34602MB
[2025-01-19 10:25:10 internimage_b_1k_224] (main.py 575): INFO [Epoch:143] * Acc@1 80.832 Acc@5 95.781
[2025-01-19 10:25:10 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.8%
[2025-01-19 10:25:10 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 10:25:12 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][130/312]	eta 0:02:23 lr 0.002156	time 0.7238 (0.7880)	model_time 0.7237 (0.7661)	loss 3.4786 (3.3125)	grad_norm 1.3658 (1.5277/0.6256)	mem 34604MB
[2025-01-19 10:25:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 10:25:14 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.83%
[2025-01-19 10:25:17 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][0/312]	eta 0:11:18 lr 0.002144	time 2.1738 (2.1738)	model_time 0.7438 (0.7438)	loss 3.2000 (3.2000)	grad_norm 1.1942 (1.1942/0.0000)	mem 34602MB
[2025-01-19 10:25:19 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][140/312]	eta 0:02:14 lr 0.002156	time 0.7333 (0.7838)	model_time 0.7329 (0.7635)	loss 3.5297 (3.2964)	grad_norm 0.7476 (1.5272/0.6135)	mem 34604MB
[2025-01-19 10:25:24 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][10/312]	eta 0:04:29 lr 0.002144	time 0.7221 (0.8909)	model_time 0.7219 (0.7606)	loss 3.9517 (3.2300)	grad_norm 1.4937 (1.6901/0.4896)	mem 34602MB
[2025-01-19 10:25:26 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][150/312]	eta 0:02:06 lr 0.002155	time 0.7200 (0.7799)	model_time 0.7199 (0.7609)	loss 2.3709 (3.2851)	grad_norm 1.0200 (1.5247/0.6108)	mem 34604MB
[2025-01-19 10:25:32 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][20/312]	eta 0:03:58 lr 0.002143	time 0.7268 (0.8171)	model_time 0.7263 (0.7486)	loss 3.7132 (3.3039)	grad_norm 1.2748 (1.6928/0.4503)	mem 34602MB
[2025-01-19 10:25:34 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][160/312]	eta 0:01:58 lr 0.002154	time 0.7105 (0.7768)	model_time 0.7104 (0.7589)	loss 3.7551 (3.2879)	grad_norm 2.2231 (1.5136/0.6053)	mem 34604MB
[2025-01-19 10:25:39 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][30/312]	eta 0:03:42 lr 0.002142	time 0.7270 (0.7887)	model_time 0.7268 (0.7422)	loss 2.9238 (3.2777)	grad_norm 1.2019 (1.5990/0.4766)	mem 34602MB
[2025-01-19 10:25:41 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][170/312]	eta 0:01:49 lr 0.002154	time 0.7196 (0.7746)	model_time 0.7192 (0.7578)	loss 3.3297 (3.2824)	grad_norm 0.9524 (1.4989/0.5929)	mem 34604MB
[2025-01-19 10:25:46 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][40/312]	eta 0:03:30 lr 0.002142	time 0.7251 (0.7744)	model_time 0.7247 (0.7392)	loss 3.4138 (3.2528)	grad_norm 1.1278 (1.5131/0.4554)	mem 34602MB
[2025-01-19 10:25:48 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][180/312]	eta 0:01:41 lr 0.002153	time 0.7470 (0.7721)	model_time 0.7466 (0.7561)	loss 3.3471 (3.2695)	grad_norm 1.2180 (1.5255/0.6118)	mem 34604MB
[2025-01-19 10:25:54 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][50/312]	eta 0:03:21 lr 0.002141	time 0.7200 (0.7680)	model_time 0.7195 (0.7396)	loss 2.9476 (3.2381)	grad_norm 1.8148 (1.4192/0.4702)	mem 34602MB
[2025-01-19 10:25:56 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][190/312]	eta 0:01:33 lr 0.002152	time 0.7070 (0.7699)	model_time 0.7069 (0.7548)	loss 2.6931 (3.2662)	grad_norm 2.3593 (1.5557/0.6319)	mem 34604MB
[2025-01-19 10:26:01 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][60/312]	eta 0:03:13 lr 0.002140	time 0.7909 (0.7663)	model_time 0.7907 (0.7425)	loss 3.1958 (3.2019)	grad_norm 1.4328 (1.4782/0.5028)	mem 34602MB
[2025-01-19 10:26:03 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][200/312]	eta 0:01:25 lr 0.002152	time 0.7215 (0.7678)	model_time 0.7214 (0.7534)	loss 3.1553 (3.2541)	grad_norm 0.8254 (1.5626/0.6254)	mem 34604MB
[2025-01-19 10:26:09 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][70/312]	eta 0:03:05 lr 0.002140	time 0.7199 (0.7658)	model_time 0.7194 (0.7453)	loss 3.8043 (3.2204)	grad_norm 1.2043 (1.5412/0.5727)	mem 34602MB
[2025-01-19 10:26:10 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][210/312]	eta 0:01:18 lr 0.002151	time 0.7518 (0.7661)	model_time 0.7511 (0.7524)	loss 3.4058 (3.2471)	grad_norm 1.3827 (1.5629/0.6173)	mem 34604MB
[2025-01-19 10:26:16 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][80/312]	eta 0:02:57 lr 0.002139	time 0.8020 (0.7646)	model_time 0.8015 (0.7466)	loss 3.7736 (3.2401)	grad_norm 2.8484 (1.5712/0.6066)	mem 34602MB
[2025-01-19 10:26:18 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][220/312]	eta 0:01:10 lr 0.002150	time 0.7260 (0.7645)	model_time 0.7255 (0.7513)	loss 3.7007 (3.2431)	grad_norm 3.1481 (1.5736/0.6222)	mem 34604MB
[2025-01-19 10:26:24 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][90/312]	eta 0:02:50 lr 0.002138	time 0.7145 (0.7671)	model_time 0.7143 (0.7510)	loss 2.8566 (3.2387)	grad_norm 3.5814 (1.6542/0.7041)	mem 34602MB
[2025-01-19 10:26:25 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][230/312]	eta 0:01:02 lr 0.002150	time 0.7179 (0.7630)	model_time 0.7178 (0.7505)	loss 2.6506 (3.2440)	grad_norm 1.1186 (1.5805/0.6213)	mem 34604MB
[2025-01-19 10:26:32 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][100/312]	eta 0:02:42 lr 0.002138	time 0.7091 (0.7651)	model_time 0.7089 (0.7506)	loss 3.4352 (3.2363)	grad_norm 1.3128 (1.6462/0.7152)	mem 34602MB
[2025-01-19 10:26:32 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][240/312]	eta 0:00:54 lr 0.002149	time 0.7182 (0.7614)	model_time 0.7180 (0.7494)	loss 3.4330 (3.2405)	grad_norm 1.6562 (1.5986/0.6423)	mem 34604MB
[2025-01-19 10:26:39 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][110/312]	eta 0:02:33 lr 0.002137	time 0.7217 (0.7623)	model_time 0.7216 (0.7487)	loss 3.3378 (3.2467)	grad_norm 0.9431 (1.6002/0.7139)	mem 34602MB
[2025-01-19 10:26:39 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][250/312]	eta 0:00:47 lr 0.002148	time 0.7219 (0.7601)	model_time 0.7217 (0.7485)	loss 3.4616 (3.2325)	grad_norm 0.8363 (1.6037/0.6476)	mem 34604MB
[2025-01-19 10:26:46 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][120/312]	eta 0:02:25 lr 0.002136	time 0.7253 (0.7600)	model_time 0.7247 (0.7474)	loss 3.7770 (3.2468)	grad_norm 0.6943 (1.5643/0.7023)	mem 34602MB
[2025-01-19 10:26:47 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][260/312]	eta 0:00:39 lr 0.002148	time 0.7196 (0.7588)	model_time 0.7195 (0.7476)	loss 3.0843 (3.2267)	grad_norm 1.0461 (1.5924/0.6402)	mem 34604MB
[2025-01-19 10:26:54 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][270/312]	eta 0:00:31 lr 0.002147	time 0.7380 (0.7576)	model_time 0.7379 (0.7468)	loss 3.8167 (3.2223)	grad_norm 1.1221 (1.5694/0.6401)	mem 34604MB
[2025-01-19 10:26:54 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][130/312]	eta 0:02:18 lr 0.002136	time 0.7197 (0.7613)	model_time 0.7195 (0.7494)	loss 3.1622 (3.2320)	grad_norm 1.8378 (1.5421/0.6845)	mem 34602MB
[2025-01-19 10:27:01 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][280/312]	eta 0:00:24 lr 0.002146	time 0.7190 (0.7565)	model_time 0.7186 (0.7459)	loss 3.2930 (3.2286)	grad_norm 1.0120 (1.5721/0.6361)	mem 34604MB
[2025-01-19 10:27:01 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][140/312]	eta 0:02:10 lr 0.002135	time 0.7169 (0.7591)	model_time 0.7165 (0.7479)	loss 2.7387 (3.2336)	grad_norm 1.1553 (1.5634/0.6875)	mem 34602MB
[2025-01-19 10:27:09 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][150/312]	eta 0:02:02 lr 0.002134	time 0.7183 (0.7571)	model_time 0.7181 (0.7466)	loss 3.8128 (3.2495)	grad_norm 1.4559 (1.5511/0.6687)	mem 34602MB
[2025-01-19 10:27:09 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][290/312]	eta 0:00:16 lr 0.002146	time 0.8437 (0.7566)	model_time 0.8435 (0.7464)	loss 2.0682 (3.2212)	grad_norm 0.9402 (1.5587/0.6351)	mem 34604MB
[2025-01-19 10:27:16 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][160/312]	eta 0:01:54 lr 0.002134	time 0.7203 (0.7553)	model_time 0.7199 (0.7453)	loss 3.3239 (3.2619)	grad_norm 1.4597 (1.5429/0.6562)	mem 34602MB
[2025-01-19 10:27:16 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][300/312]	eta 0:00:09 lr 0.002145	time 0.7155 (0.7556)	model_time 0.7154 (0.7457)	loss 3.1439 (3.2160)	grad_norm 1.6015 (1.5531/0.6290)	mem 34604MB
[2025-01-19 10:27:23 internimage_b_1k_224] (main.py 510): INFO Train: [143/300][310/312]	eta 0:00:01 lr 0.002144	time 0.7192 (0.7546)	model_time 0.7191 (0.7449)	loss 3.3826 (3.2151)	grad_norm 1.3717 (1.5337/0.6223)	mem 34604MB
[2025-01-19 10:27:23 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][170/312]	eta 0:01:47 lr 0.002133	time 0.7271 (0.7547)	model_time 0.7267 (0.7451)	loss 3.9398 (3.2712)	grad_norm 2.6692 (1.5414/0.6536)	mem 34602MB
[2025-01-19 10:27:24 internimage_b_1k_224] (main.py 519): INFO EPOCH 143 training takes 0:03:55
[2025-01-19 10:27:24 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_143.pth saving......
[2025-01-19 10:27:27 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_143.pth saved !!!
[2025-01-19 10:27:31 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][180/312]	eta 0:01:39 lr 0.002132	time 0.8217 (0.7551)	model_time 0.8216 (0.7459)	loss 3.4299 (3.2658)	grad_norm 0.8777 (1.5463/0.6455)	mem 34602MB
[2025-01-19 10:27:35 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.336 (7.336)	Loss 0.7981 (0.7981)	Acc@1 83.569 (83.569)	Acc@5 96.948 (96.948)	Mem 34604MB
[2025-01-19 10:27:38 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (1.004)	Loss 1.0669 (0.9297)	Acc@1 75.513 (80.154)	Acc@5 93.970 (95.455)	Mem 34604MB
[2025-01-19 10:27:39 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][190/312]	eta 0:01:32 lr 0.002132	time 0.7191 (0.7548)	model_time 0.7190 (0.7460)	loss 3.4751 (3.2637)	grad_norm 1.1239 (1.5406/0.6378)	mem 34602MB
[2025-01-19 10:27:39 internimage_b_1k_224] (main.py 575): INFO [Epoch:143] * Acc@1 80.076 Acc@5 95.501
[2025-01-19 10:27:39 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.1%
[2025-01-19 10:27:39 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.16%
[2025-01-19 10:27:46 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][200/312]	eta 0:01:24 lr 0.002131	time 0.8058 (0.7555)	model_time 0.8057 (0.7471)	loss 3.4944 (3.2541)	grad_norm 1.7905 (1.5374/0.6284)	mem 34602MB
[2025-01-19 10:27:48 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.140 (9.140)	Loss 0.6503 (0.6503)	Acc@1 83.813 (83.813)	Acc@5 97.461 (97.461)	Mem 34604MB
[2025-01-19 10:27:53 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.281)	Loss 0.9654 (0.7941)	Acc@1 76.318 (80.944)	Acc@5 94.019 (95.730)	Mem 34604MB
[2025-01-19 10:27:53 internimage_b_1k_224] (main.py 575): INFO [Epoch:143] * Acc@1 80.832 Acc@5 95.779
[2025-01-19 10:27:53 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.8%
[2025-01-19 10:27:53 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 10:27:54 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][210/312]	eta 0:01:17 lr 0.002130	time 0.7204 (0.7572)	model_time 0.7199 (0.7491)	loss 2.5724 (3.2572)	grad_norm 1.5244 (1.5277/0.6213)	mem 34602MB
[2025-01-19 10:27:57 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 10:27:57 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.83%
[2025-01-19 10:27:59 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][0/312]	eta 0:11:38 lr 0.002144	time 2.2390 (2.2390)	model_time 0.8368 (0.8368)	loss 4.0655 (4.0655)	grad_norm 1.5967 (1.5967/0.0000)	mem 34604MB
[2025-01-19 10:28:02 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][220/312]	eta 0:01:09 lr 0.002130	time 0.7176 (0.7570)	model_time 0.7175 (0.7492)	loss 3.6962 (3.2647)	grad_norm 1.8581 (1.5132/0.6149)	mem 34602MB
[2025-01-19 10:28:07 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][10/312]	eta 0:04:21 lr 0.002144	time 0.7208 (0.8662)	model_time 0.7206 (0.7364)	loss 3.4847 (3.6473)	grad_norm 3.4051 (2.1318/0.9767)	mem 34604MB
[2025-01-19 10:28:09 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][230/312]	eta 0:01:01 lr 0.002129	time 0.7168 (0.7560)	model_time 0.7167 (0.7484)	loss 2.5634 (3.2527)	grad_norm 1.8903 (1.5311/0.6172)	mem 34602MB
[2025-01-19 10:28:14 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][20/312]	eta 0:03:54 lr 0.002143	time 0.7267 (0.8025)	model_time 0.7263 (0.7338)	loss 3.6601 (3.4419)	grad_norm 2.2534 (2.1155/0.9194)	mem 34604MB
[2025-01-19 10:28:16 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][240/312]	eta 0:00:54 lr 0.002128	time 0.7168 (0.7547)	model_time 0.7166 (0.7474)	loss 2.8852 (3.2513)	grad_norm 2.4094 (1.5374/0.6143)	mem 34602MB
[2025-01-19 10:28:21 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][30/312]	eta 0:03:40 lr 0.002142	time 0.7304 (0.7815)	model_time 0.7302 (0.7344)	loss 3.5473 (3.4131)	grad_norm 1.9179 (1.9144/0.8831)	mem 34604MB
[2025-01-19 10:28:24 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][250/312]	eta 0:00:46 lr 0.002128	time 0.7162 (0.7550)	model_time 0.7161 (0.7478)	loss 3.3509 (3.2579)	grad_norm 1.1899 (1.5402/0.6121)	mem 34602MB
[2025-01-19 10:28:29 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][40/312]	eta 0:03:29 lr 0.002142	time 0.7269 (0.7698)	model_time 0.7263 (0.7339)	loss 3.8566 (3.3941)	grad_norm 1.8707 (1.7989/0.8161)	mem 34604MB
[2025-01-19 10:28:31 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][260/312]	eta 0:00:39 lr 0.002127	time 0.7207 (0.7542)	model_time 0.7206 (0.7473)	loss 3.3546 (3.2601)	grad_norm 1.7779 (1.5478/0.6147)	mem 34602MB
[2025-01-19 10:28:36 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][50/312]	eta 0:03:19 lr 0.002141	time 0.7547 (0.7620)	model_time 0.7543 (0.7323)	loss 3.7359 (3.3661)	grad_norm 2.0377 (1.7457/0.7705)	mem 34604MB
[2025-01-19 10:28:39 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][270/312]	eta 0:00:31 lr 0.002126	time 0.7483 (0.7535)	model_time 0.7479 (0.7467)	loss 3.3912 (3.2523)	grad_norm 1.0548 (1.5553/0.6160)	mem 34602MB
[2025-01-19 10:28:43 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][60/312]	eta 0:03:10 lr 0.002140	time 0.7367 (0.7561)	model_time 0.7363 (0.7311)	loss 3.7975 (3.3138)	grad_norm 1.4053 (1.6698/0.7473)	mem 34604MB
[2025-01-19 10:28:46 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][280/312]	eta 0:00:24 lr 0.002126	time 0.7340 (0.7528)	model_time 0.7338 (0.7462)	loss 3.1117 (3.2513)	grad_norm 0.7916 (1.5527/0.6114)	mem 34602MB
[2025-01-19 10:28:51 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][70/312]	eta 0:03:02 lr 0.002140	time 0.7263 (0.7525)	model_time 0.7261 (0.7308)	loss 2.3402 (3.2774)	grad_norm 1.0078 (1.6042/0.7203)	mem 34604MB
[2025-01-19 10:28:53 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][290/312]	eta 0:00:16 lr 0.002125	time 0.7203 (0.7527)	model_time 0.7197 (0.7462)	loss 3.9541 (3.2484)	grad_norm 1.4392 (1.5488/0.6077)	mem 34602MB
[2025-01-19 10:28:58 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][80/312]	eta 0:02:53 lr 0.002139	time 0.7269 (0.7498)	model_time 0.7267 (0.7305)	loss 3.5795 (3.2569)	grad_norm 0.9043 (1.5472/0.7041)	mem 34604MB
[2025-01-19 10:29:01 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][300/312]	eta 0:00:09 lr 0.002124	time 0.7845 (0.7527)	model_time 0.7844 (0.7464)	loss 3.2290 (3.2488)	grad_norm 0.7623 (1.5453/0.6083)	mem 34602MB
[2025-01-19 10:29:05 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][90/312]	eta 0:02:45 lr 0.002138	time 0.7576 (0.7475)	model_time 0.7572 (0.7301)	loss 3.0936 (3.2702)	grad_norm 1.3464 (1.5782/0.7090)	mem 34604MB
[2025-01-19 10:29:08 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][310/312]	eta 0:00:01 lr 0.002124	time 0.7115 (0.7519)	model_time 0.7112 (0.7457)	loss 3.4489 (3.2509)	grad_norm 1.6667 (1.5379/0.6073)	mem 34602MB
[2025-01-19 10:29:09 internimage_b_1k_224] (main.py 519): INFO EPOCH 144 training takes 0:03:54
[2025-01-19 10:29:09 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_144.pth saving......
[2025-01-19 10:29:12 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_144.pth saved !!!
[2025-01-19 10:29:13 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][100/312]	eta 0:02:38 lr 0.002138	time 0.7175 (0.7495)	model_time 0.7170 (0.7336)	loss 3.1972 (3.2792)	grad_norm 1.6524 (1.5633/0.6890)	mem 34604MB
[2025-01-19 10:29:20 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][110/312]	eta 0:02:31 lr 0.002137	time 0.7466 (0.7475)	model_time 0.7464 (0.7329)	loss 2.5272 (3.2554)	grad_norm 1.3834 (1.6090/0.7035)	mem 34604MB
[2025-01-19 10:29:20 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.447 (7.447)	Loss 0.7993 (0.7993)	Acc@1 82.520 (82.520)	Acc@5 96.802 (96.802)	Mem 34602MB
[2025-01-19 10:29:24 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.014)	Loss 1.0932 (0.9369)	Acc@1 75.391 (80.269)	Acc@5 93.799 (95.441)	Mem 34602MB
[2025-01-19 10:29:24 internimage_b_1k_224] (main.py 575): INFO [Epoch:144] * Acc@1 80.078 Acc@5 95.479
[2025-01-19 10:29:24 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.1%
[2025-01-19 10:29:24 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.36%
[2025-01-19 10:29:27 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][120/312]	eta 0:02:23 lr 0.002136	time 0.8103 (0.7463)	model_time 0.8098 (0.7328)	loss 3.9467 (3.2850)	grad_norm 1.2183 (1.5753/0.6877)	mem 34604MB
[2025-01-19 10:29:33 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.049 (9.049)	Loss 0.6504 (0.6504)	Acc@1 83.789 (83.789)	Acc@5 97.559 (97.559)	Mem 34602MB
[2025-01-19 10:29:35 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][130/312]	eta 0:02:15 lr 0.002136	time 0.7185 (0.7455)	model_time 0.7180 (0.7328)	loss 3.1631 (3.2861)	grad_norm 0.8713 (1.5635/0.6871)	mem 34604MB
[2025-01-19 10:29:38 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.268)	Loss 0.9643 (0.7937)	Acc@1 76.294 (80.973)	Acc@5 94.067 (95.763)	Mem 34602MB
[2025-01-19 10:29:38 internimage_b_1k_224] (main.py 575): INFO [Epoch:144] * Acc@1 80.872 Acc@5 95.807
[2025-01-19 10:29:38 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.9%
[2025-01-19 10:29:38 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 10:29:42 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][140/312]	eta 0:02:08 lr 0.002135	time 0.7209 (0.7442)	model_time 0.7207 (0.7323)	loss 2.3556 (3.2680)	grad_norm 1.1659 (1.5429/0.6735)	mem 34604MB
[2025-01-19 10:29:42 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 10:29:42 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.87%
[2025-01-19 10:29:45 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][0/312]	eta 0:10:48 lr 0.002124	time 2.0785 (2.0785)	model_time 0.7421 (0.7421)	loss 2.3881 (2.3881)	grad_norm 1.0272 (1.0272/0.0000)	mem 34602MB
[2025-01-19 10:29:49 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][150/312]	eta 0:02:00 lr 0.002134	time 0.7241 (0.7430)	model_time 0.7239 (0.7318)	loss 2.8999 (3.2524)	grad_norm 2.0649 (1.5488/0.6653)	mem 34604MB
[2025-01-19 10:29:52 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][10/312]	eta 0:04:27 lr 0.002123	time 0.8111 (0.8855)	model_time 0.8109 (0.7624)	loss 2.4091 (2.9136)	grad_norm 1.0068 (1.1432/0.3563)	mem 34602MB
[2025-01-19 10:29:57 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][160/312]	eta 0:01:52 lr 0.002134	time 0.7180 (0.7421)	model_time 0.7178 (0.7315)	loss 3.0086 (3.2366)	grad_norm 0.8837 (1.5409/0.6553)	mem 34604MB
[2025-01-19 10:30:00 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][20/312]	eta 0:04:02 lr 0.002122	time 0.7208 (0.8316)	model_time 0.7203 (0.7665)	loss 2.3406 (3.0749)	grad_norm 0.8758 (1.2498/0.4308)	mem 34602MB
[2025-01-19 10:30:04 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][170/312]	eta 0:01:45 lr 0.002133	time 0.7309 (0.7418)	model_time 0.7307 (0.7317)	loss 4.2008 (3.2438)	grad_norm 2.0983 (1.5492/0.6489)	mem 34604MB
[2025-01-19 10:30:07 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][30/312]	eta 0:03:47 lr 0.002122	time 0.8568 (0.8050)	model_time 0.8566 (0.7604)	loss 3.5451 (3.1715)	grad_norm 1.0271 (1.3185/0.4591)	mem 34602MB
[2025-01-19 10:30:11 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][180/312]	eta 0:01:37 lr 0.002132	time 0.7176 (0.7409)	model_time 0.7174 (0.7313)	loss 2.6074 (3.2466)	grad_norm 0.7720 (1.5309/0.6379)	mem 34604MB
[2025-01-19 10:30:15 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][40/312]	eta 0:03:33 lr 0.002121	time 0.7174 (0.7859)	model_time 0.7168 (0.7521)	loss 3.6110 (3.1907)	grad_norm 1.0060 (1.3258/0.4628)	mem 34602MB
[2025-01-19 10:30:18 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][190/312]	eta 0:01:30 lr 0.002132	time 0.7204 (0.7402)	model_time 0.7199 (0.7311)	loss 2.6806 (3.2424)	grad_norm 0.8025 (1.5230/0.6398)	mem 34604MB
[2025-01-19 10:30:22 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][50/312]	eta 0:03:22 lr 0.002120	time 0.7228 (0.7746)	model_time 0.7226 (0.7473)	loss 3.1876 (3.2127)	grad_norm 0.9742 (1.3317/0.4564)	mem 34602MB
[2025-01-19 10:30:26 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][200/312]	eta 0:01:22 lr 0.002131	time 0.7462 (0.7396)	model_time 0.7460 (0.7309)	loss 3.8547 (3.2626)	grad_norm 1.9714 (1.5464/0.6531)	mem 34604MB
[2025-01-19 10:30:30 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][60/312]	eta 0:03:14 lr 0.002120	time 0.8403 (0.7737)	model_time 0.8402 (0.7509)	loss 3.7042 (3.2513)	grad_norm 2.0516 (1.3723/0.4625)	mem 34602MB
[2025-01-19 10:30:33 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][210/312]	eta 0:01:15 lr 0.002130	time 0.7275 (0.7389)	model_time 0.7271 (0.7307)	loss 3.1910 (3.2540)	grad_norm 0.9511 (1.5889/0.6984)	mem 34604MB
[2025-01-19 10:30:37 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][70/312]	eta 0:03:05 lr 0.002119	time 0.7183 (0.7679)	model_time 0.7181 (0.7482)	loss 3.3201 (3.2770)	grad_norm 2.1486 (1.4161/0.5497)	mem 34602MB
[2025-01-19 10:30:41 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][220/312]	eta 0:01:08 lr 0.002130	time 0.7278 (0.7403)	model_time 0.7277 (0.7324)	loss 3.8029 (3.2512)	grad_norm 0.6997 (1.5811/0.6904)	mem 34604MB
[2025-01-19 10:30:44 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][80/312]	eta 0:02:57 lr 0.002118	time 0.7358 (0.7632)	model_time 0.7354 (0.7459)	loss 2.7475 (3.2736)	grad_norm 1.2770 (1.3678/0.5408)	mem 34602MB
[2025-01-19 10:30:48 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][230/312]	eta 0:01:00 lr 0.002129	time 0.7158 (0.7395)	model_time 0.7157 (0.7320)	loss 3.3291 (3.2406)	grad_norm 1.2800 (1.5837/0.6832)	mem 34604MB
[2025-01-19 10:30:52 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][90/312]	eta 0:02:48 lr 0.002118	time 0.7181 (0.7588)	model_time 0.7180 (0.7434)	loss 3.4909 (3.2253)	grad_norm 1.2358 (1.4300/0.5730)	mem 34602MB
[2025-01-19 10:30:55 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][240/312]	eta 0:00:53 lr 0.002128	time 0.8078 (0.7392)	model_time 0.8074 (0.7319)	loss 3.8209 (3.2504)	grad_norm 1.5760 (1.5844/0.6755)	mem 34604MB
[2025-01-19 10:30:59 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][100/312]	eta 0:02:40 lr 0.002117	time 0.7275 (0.7560)	model_time 0.7273 (0.7421)	loss 3.5095 (3.2252)	grad_norm 1.7582 (1.4207/0.5538)	mem 34602MB
[2025-01-19 10:31:02 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][250/312]	eta 0:00:45 lr 0.002128	time 0.7168 (0.7385)	model_time 0.7164 (0.7315)	loss 3.4041 (3.2576)	grad_norm 1.1855 (1.5773/0.6652)	mem 34604MB
[2025-01-19 10:31:06 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][110/312]	eta 0:02:32 lr 0.002116	time 0.7179 (0.7554)	model_time 0.7175 (0.7427)	loss 2.4013 (3.2160)	grad_norm 1.2583 (1.4264/0.5406)	mem 34602MB
[2025-01-19 10:31:10 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][260/312]	eta 0:00:38 lr 0.002127	time 0.7233 (0.7377)	model_time 0.7232 (0.7310)	loss 3.0820 (3.2549)	grad_norm 1.2649 (1.5736/0.6663)	mem 34604MB
[2025-01-19 10:31:14 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][120/312]	eta 0:02:24 lr 0.002116	time 0.7999 (0.7547)	model_time 0.7997 (0.7430)	loss 3.7018 (3.2094)	grad_norm 1.9662 (1.4450/0.5306)	mem 34602MB
[2025-01-19 10:31:17 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][270/312]	eta 0:00:30 lr 0.002126	time 0.7374 (0.7373)	model_time 0.7370 (0.7307)	loss 3.4538 (3.2636)	grad_norm 1.3009 (1.5972/0.6957)	mem 34604MB
[2025-01-19 10:31:21 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][130/312]	eta 0:02:17 lr 0.002115	time 0.7309 (0.7556)	model_time 0.7307 (0.7448)	loss 3.9280 (3.2125)	grad_norm 2.5478 (1.4547/0.5255)	mem 34602MB
[2025-01-19 10:31:24 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][280/312]	eta 0:00:23 lr 0.002126	time 0.7340 (0.7369)	model_time 0.7339 (0.7306)	loss 2.8024 (3.2632)	grad_norm 0.8757 (1.5886/0.6936)	mem 34604MB
[2025-01-19 10:31:29 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][140/312]	eta 0:02:10 lr 0.002114	time 0.7955 (0.7571)	model_time 0.7953 (0.7471)	loss 2.7234 (3.1796)	grad_norm 1.2116 (1.4640/0.5204)	mem 34602MB
[2025-01-19 10:31:31 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][290/312]	eta 0:00:16 lr 0.002125	time 0.7182 (0.7366)	model_time 0.7177 (0.7305)	loss 2.3391 (3.2578)	grad_norm 0.8979 (1.5714/0.6889)	mem 34604MB
[2025-01-19 10:31:37 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][150/312]	eta 0:02:02 lr 0.002114	time 0.8183 (0.7566)	model_time 0.8179 (0.7472)	loss 2.7658 (3.2122)	grad_norm 0.9208 (1.4544/0.5145)	mem 34602MB
[2025-01-19 10:31:39 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][300/312]	eta 0:00:08 lr 0.002124	time 0.7136 (0.7361)	model_time 0.7135 (0.7302)	loss 3.5853 (3.2603)	grad_norm 1.3557 (1.5652/0.6848)	mem 34604MB
[2025-01-19 10:31:44 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][160/312]	eta 0:01:54 lr 0.002113	time 0.7192 (0.7552)	model_time 0.7187 (0.7460)	loss 3.6716 (3.2223)	grad_norm 1.7911 (1.4296/0.5141)	mem 34602MB
[2025-01-19 10:31:46 internimage_b_1k_224] (main.py 510): INFO Train: [144/300][310/312]	eta 0:00:01 lr 0.002124	time 0.7195 (0.7354)	model_time 0.7194 (0.7297)	loss 3.9577 (3.2679)	grad_norm 1.1070 (1.5345/0.6538)	mem 34604MB
[2025-01-19 10:31:47 internimage_b_1k_224] (main.py 519): INFO EPOCH 144 training takes 0:03:49
[2025-01-19 10:31:47 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_144.pth saving......
[2025-01-19 10:31:50 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_144.pth saved !!!
[2025-01-19 10:31:51 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][170/312]	eta 0:01:46 lr 0.002112	time 0.7181 (0.7534)	model_time 0.7180 (0.7448)	loss 3.0847 (3.2174)	grad_norm 1.1836 (1.4194/0.5148)	mem 34602MB
[2025-01-19 10:31:57 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.082 (7.082)	Loss 0.7996 (0.7996)	Acc@1 82.837 (82.837)	Acc@5 96.802 (96.802)	Mem 34604MB
[2025-01-19 10:31:59 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][180/312]	eta 0:01:39 lr 0.002112	time 0.8294 (0.7534)	model_time 0.8290 (0.7452)	loss 2.8572 (3.2254)	grad_norm 2.6467 (1.4523/0.5477)	mem 34602MB
[2025-01-19 10:32:00 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.928)	Loss 1.0675 (0.9369)	Acc@1 76.221 (80.091)	Acc@5 93.774 (95.335)	Mem 34604MB
[2025-01-19 10:32:00 internimage_b_1k_224] (main.py 575): INFO [Epoch:144] * Acc@1 80.020 Acc@5 95.381
[2025-01-19 10:32:00 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.0%
[2025-01-19 10:32:00 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.16%
[2025-01-19 10:32:06 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][190/312]	eta 0:01:31 lr 0.002111	time 0.7217 (0.7523)	model_time 0.7215 (0.7446)	loss 3.3402 (3.2307)	grad_norm 2.0028 (1.4722/0.5636)	mem 34602MB
[2025-01-19 10:32:09 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.997 (8.997)	Loss 0.6503 (0.6503)	Acc@1 83.838 (83.838)	Acc@5 97.510 (97.510)	Mem 34604MB
[2025-01-19 10:32:13 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][200/312]	eta 0:01:24 lr 0.002110	time 0.7388 (0.7511)	model_time 0.7387 (0.7437)	loss 3.0867 (3.2262)	grad_norm 1.4367 (1.4919/0.5727)	mem 34602MB
[2025-01-19 10:32:14 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (1.222)	Loss 0.9638 (0.7935)	Acc@1 76.440 (81.015)	Acc@5 94.067 (95.761)	Mem 34604MB
[2025-01-19 10:32:14 internimage_b_1k_224] (main.py 575): INFO [Epoch:144] * Acc@1 80.904 Acc@5 95.807
[2025-01-19 10:32:14 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.9%
[2025-01-19 10:32:14 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 10:32:18 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 10:32:18 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.90%
[2025-01-19 10:32:20 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][0/312]	eta 0:10:42 lr 0.002124	time 2.0586 (2.0586)	model_time 0.7448 (0.7448)	loss 3.4238 (3.4238)	grad_norm 1.3280 (1.3280/0.0000)	mem 34604MB
[2025-01-19 10:32:21 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][210/312]	eta 0:01:16 lr 0.002110	time 0.7249 (0.7497)	model_time 0.7245 (0.7426)	loss 2.7371 (3.2219)	grad_norm 1.6781 (1.4707/0.5708)	mem 34602MB
[2025-01-19 10:32:27 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][10/312]	eta 0:04:18 lr 0.002123	time 0.7500 (0.8553)	model_time 0.7496 (0.7354)	loss 2.9021 (3.2449)	grad_norm 1.5250 (1.5095/0.8234)	mem 34604MB
[2025-01-19 10:32:28 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][220/312]	eta 0:01:08 lr 0.002109	time 0.7249 (0.7491)	model_time 0.7245 (0.7424)	loss 3.0226 (3.2208)	grad_norm 2.1279 (1.5160/0.6593)	mem 34602MB
[2025-01-19 10:32:35 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][20/312]	eta 0:03:52 lr 0.002122	time 0.7452 (0.7977)	model_time 0.7450 (0.7347)	loss 2.7598 (3.0978)	grad_norm 0.9630 (1.4480/0.6546)	mem 34604MB
[2025-01-19 10:32:36 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][230/312]	eta 0:01:01 lr 0.002108	time 0.8055 (0.7492)	model_time 0.8053 (0.7427)	loss 2.7300 (3.2205)	grad_norm 1.7994 (1.5066/0.6673)	mem 34602MB
[2025-01-19 10:32:42 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][30/312]	eta 0:03:41 lr 0.002122	time 0.7257 (0.7870)	model_time 0.7256 (0.7442)	loss 3.2464 (3.1611)	grad_norm 1.9023 (1.5123/0.6530)	mem 34604MB
[2025-01-19 10:32:43 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][240/312]	eta 0:00:53 lr 0.002108	time 0.8036 (0.7493)	model_time 0.8032 (0.7431)	loss 3.1899 (3.2243)	grad_norm 1.8157 (1.5124/0.6627)	mem 34602MB
[2025-01-19 10:32:50 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][40/312]	eta 0:03:30 lr 0.002121	time 0.7210 (0.7730)	model_time 0.7208 (0.7406)	loss 3.3300 (3.0996)	grad_norm 1.3051 (1.5216/0.6145)	mem 34604MB
[2025-01-19 10:32:51 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][250/312]	eta 0:00:46 lr 0.002107	time 0.8164 (0.7505)	model_time 0.8163 (0.7445)	loss 1.9246 (3.2308)	grad_norm 1.6423 (1.5010/0.6586)	mem 34602MB
[2025-01-19 10:32:57 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][50/312]	eta 0:03:20 lr 0.002120	time 0.7164 (0.7642)	model_time 0.7160 (0.7380)	loss 3.3581 (3.1848)	grad_norm 0.8218 (1.4181/0.6032)	mem 34604MB
[2025-01-19 10:32:59 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][260/312]	eta 0:00:39 lr 0.002106	time 0.7929 (0.7511)	model_time 0.7924 (0.7453)	loss 3.8657 (3.2244)	grad_norm 0.8700 (1.5042/0.6574)	mem 34602MB
[2025-01-19 10:33:04 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][60/312]	eta 0:03:11 lr 0.002120	time 0.7288 (0.7585)	model_time 0.7284 (0.7366)	loss 3.6460 (3.1917)	grad_norm 1.6990 (1.4670/0.6623)	mem 34604MB
[2025-01-19 10:33:06 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][270/312]	eta 0:00:31 lr 0.002106	time 0.8206 (0.7519)	model_time 0.8201 (0.7463)	loss 2.6330 (3.2239)	grad_norm 3.2591 (1.5017/0.6599)	mem 34602MB
[2025-01-19 10:33:12 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][70/312]	eta 0:03:02 lr 0.002119	time 0.7199 (0.7541)	model_time 0.7197 (0.7352)	loss 3.0041 (3.1628)	grad_norm 1.1578 (1.5098/0.6565)	mem 34604MB
[2025-01-19 10:33:14 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][280/312]	eta 0:00:24 lr 0.002105	time 0.7398 (0.7514)	model_time 0.7395 (0.7460)	loss 2.7716 (3.2190)	grad_norm 1.4490 (1.5070/0.6598)	mem 34602MB
[2025-01-19 10:33:19 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][80/312]	eta 0:02:54 lr 0.002118	time 0.7151 (0.7521)	model_time 0.7150 (0.7355)	loss 4.0929 (3.1539)	grad_norm 1.8472 (1.5273/0.6495)	mem 34604MB
[2025-01-19 10:33:21 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][290/312]	eta 0:00:16 lr 0.002104	time 0.7299 (0.7505)	model_time 0.7294 (0.7452)	loss 3.3562 (3.2114)	grad_norm 1.1921 (1.5032/0.6564)	mem 34602MB
[2025-01-19 10:33:26 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][90/312]	eta 0:02:46 lr 0.002118	time 0.7207 (0.7489)	model_time 0.7203 (0.7341)	loss 3.3932 (3.1276)	grad_norm 0.9277 (1.5232/0.6482)	mem 34604MB
[2025-01-19 10:33:28 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][300/312]	eta 0:00:09 lr 0.002104	time 0.7953 (0.7504)	model_time 0.7952 (0.7453)	loss 3.0946 (3.1996)	grad_norm 1.5377 (1.4951/0.6497)	mem 34602MB
[2025-01-19 10:33:33 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][100/312]	eta 0:02:38 lr 0.002117	time 0.7177 (0.7465)	model_time 0.7173 (0.7331)	loss 3.1749 (3.1348)	grad_norm 1.0291 (1.4963/0.6278)	mem 34604MB
[2025-01-19 10:33:36 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][310/312]	eta 0:00:01 lr 0.002103	time 0.7185 (0.7497)	model_time 0.7184 (0.7448)	loss 2.4081 (3.2042)	grad_norm 0.9140 (1.4925/0.6504)	mem 34602MB
[2025-01-19 10:33:36 internimage_b_1k_224] (main.py 519): INFO EPOCH 145 training takes 0:03:53
[2025-01-19 10:33:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_145.pth saving......
[2025-01-19 10:33:40 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_145.pth saved !!!
[2025-01-19 10:33:41 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][110/312]	eta 0:02:30 lr 0.002116	time 0.7200 (0.7444)	model_time 0.7198 (0.7321)	loss 3.2887 (3.1454)	grad_norm 1.8581 (1.4932/0.6074)	mem 34604MB
[2025-01-19 10:33:47 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.263 (7.263)	Loss 0.8027 (0.8027)	Acc@1 83.447 (83.447)	Acc@5 96.851 (96.851)	Mem 34602MB
[2025-01-19 10:33:48 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][120/312]	eta 0:02:22 lr 0.002116	time 0.7103 (0.7425)	model_time 0.7098 (0.7312)	loss 3.4960 (3.1549)	grad_norm 0.9478 (1.4859/0.6025)	mem 34604MB
[2025-01-19 10:33:50 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.918)	Loss 1.0622 (0.9240)	Acc@1 77.026 (80.573)	Acc@5 94.141 (95.526)	Mem 34602MB
[2025-01-19 10:33:50 internimage_b_1k_224] (main.py 575): INFO [Epoch:145] * Acc@1 80.476 Acc@5 95.559
[2025-01-19 10:33:50 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.5%
[2025-01-19 10:33:50 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 10:33:53 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 10:33:53 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.48%
[2025-01-19 10:33:55 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][130/312]	eta 0:02:14 lr 0.002115	time 0.7214 (0.7407)	model_time 0.7210 (0.7303)	loss 2.3236 (3.1569)	grad_norm 1.0881 (1.4846/0.5878)	mem 34604MB
[2025-01-19 10:34:01 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.448 (7.448)	Loss 0.6506 (0.6506)	Acc@1 83.813 (83.813)	Acc@5 97.583 (97.583)	Mem 34602MB
[2025-01-19 10:34:02 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][140/312]	eta 0:02:07 lr 0.002114	time 0.7498 (0.7407)	model_time 0.7493 (0.7310)	loss 3.7239 (3.1822)	grad_norm 1.0317 (1.4798/0.5792)	mem 34604MB
[2025-01-19 10:34:04 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.958)	Loss 0.9633 (0.7931)	Acc@1 76.367 (81.030)	Acc@5 94.019 (95.781)	Mem 34602MB
[2025-01-19 10:34:04 internimage_b_1k_224] (main.py 575): INFO [Epoch:145] * Acc@1 80.926 Acc@5 95.825
[2025-01-19 10:34:04 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.9%
[2025-01-19 10:34:04 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 10:34:08 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 10:34:08 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.93%
[2025-01-19 10:34:10 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][150/312]	eta 0:02:00 lr 0.002114	time 0.7222 (0.7418)	model_time 0.7220 (0.7327)	loss 2.3604 (3.1884)	grad_norm 0.7536 (1.4551/0.5723)	mem 34604MB
[2025-01-19 10:34:10 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][0/312]	eta 0:11:31 lr 0.002103	time 2.2174 (2.2174)	model_time 0.7351 (0.7351)	loss 4.0499 (4.0499)	grad_norm 1.8181 (1.8181/0.0000)	mem 34602MB
[2025-01-19 10:34:17 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][160/312]	eta 0:01:52 lr 0.002113	time 0.7280 (0.7409)	model_time 0.7276 (0.7323)	loss 2.3199 (3.1908)	grad_norm 2.5032 (1.4572/0.5653)	mem 34604MB
[2025-01-19 10:34:18 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][10/312]	eta 0:04:21 lr 0.002102	time 0.7171 (0.8652)	model_time 0.7170 (0.7301)	loss 3.6599 (3.3386)	grad_norm 1.7969 (1.6921/0.6185)	mem 34602MB
[2025-01-19 10:34:24 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][170/312]	eta 0:01:45 lr 0.002112	time 0.7190 (0.7399)	model_time 0.7189 (0.7318)	loss 3.1850 (3.1988)	grad_norm 0.9863 (1.4551/0.5644)	mem 34604MB
[2025-01-19 10:34:25 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][20/312]	eta 0:03:53 lr 0.002102	time 0.7290 (0.8013)	model_time 0.7285 (0.7304)	loss 2.6632 (3.1335)	grad_norm 1.5802 (1.4570/0.5665)	mem 34602MB
[2025-01-19 10:34:32 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][180/312]	eta 0:01:37 lr 0.002112	time 0.7331 (0.7391)	model_time 0.7327 (0.7314)	loss 3.9463 (3.1969)	grad_norm 1.2571 (1.4546/0.5554)	mem 34604MB
[2025-01-19 10:34:32 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][30/312]	eta 0:03:39 lr 0.002101	time 0.7229 (0.7795)	model_time 0.7228 (0.7314)	loss 3.3410 (3.1459)	grad_norm 2.1743 (1.4803/0.5324)	mem 34602MB
[2025-01-19 10:34:39 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][190/312]	eta 0:01:30 lr 0.002111	time 0.7183 (0.7384)	model_time 0.7178 (0.7311)	loss 3.7292 (3.1811)	grad_norm 1.5150 (1.4678/0.5796)	mem 34604MB
[2025-01-19 10:34:40 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][40/312]	eta 0:03:30 lr 0.002100	time 0.7156 (0.7729)	model_time 0.7149 (0.7365)	loss 3.8020 (3.1925)	grad_norm 1.7361 (1.4693/0.5006)	mem 34602MB
[2025-01-19 10:34:46 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][200/312]	eta 0:01:22 lr 0.002110	time 0.7223 (0.7376)	model_time 0.7221 (0.7307)	loss 2.2741 (3.1804)	grad_norm 1.0900 (1.4790/0.5827)	mem 34604MB
[2025-01-19 10:34:47 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][50/312]	eta 0:03:21 lr 0.002100	time 0.7224 (0.7696)	model_time 0.7220 (0.7402)	loss 4.0008 (3.1764)	grad_norm 1.9005 (1.5261/0.5195)	mem 34602MB
[2025-01-19 10:34:54 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][210/312]	eta 0:01:15 lr 0.002110	time 0.7213 (0.7371)	model_time 0.7208 (0.7305)	loss 2.4662 (3.1739)	grad_norm 0.8108 (1.4776/0.5789)	mem 34604MB
[2025-01-19 10:34:55 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][60/312]	eta 0:03:13 lr 0.002099	time 0.7159 (0.7695)	model_time 0.7154 (0.7448)	loss 3.5657 (3.1892)	grad_norm 1.2862 (1.5624/0.5121)	mem 34602MB
[2025-01-19 10:35:01 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][220/312]	eta 0:01:07 lr 0.002109	time 0.7082 (0.7365)	model_time 0.7081 (0.7301)	loss 2.3987 (3.1720)	grad_norm 1.8104 (1.4724/0.5727)	mem 34604MB
[2025-01-19 10:35:03 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][70/312]	eta 0:03:06 lr 0.002098	time 0.8090 (0.7711)	model_time 0.8089 (0.7499)	loss 2.9387 (3.1695)	grad_norm 0.9877 (1.5514/0.5048)	mem 34602MB
[2025-01-19 10:35:08 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][230/312]	eta 0:01:00 lr 0.002108	time 0.7156 (0.7358)	model_time 0.7152 (0.7297)	loss 3.7253 (3.1847)	grad_norm 1.2009 (1.4574/0.5696)	mem 34604MB
[2025-01-19 10:35:10 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][80/312]	eta 0:02:58 lr 0.002098	time 0.7214 (0.7677)	model_time 0.7212 (0.7490)	loss 2.7698 (3.1590)	grad_norm 1.6886 (1.6165/0.5389)	mem 34602MB
[2025-01-19 10:35:15 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][240/312]	eta 0:00:52 lr 0.002108	time 0.7401 (0.7353)	model_time 0.7400 (0.7295)	loss 3.2759 (3.1815)	grad_norm 0.8886 (1.4617/0.5682)	mem 34604MB
[2025-01-19 10:35:18 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][90/312]	eta 0:02:49 lr 0.002097	time 0.7323 (0.7640)	model_time 0.7322 (0.7474)	loss 3.4438 (3.1529)	grad_norm 1.5517 (1.5863/0.5290)	mem 34602MB
[2025-01-19 10:35:22 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][250/312]	eta 0:00:45 lr 0.002107	time 0.7309 (0.7349)	model_time 0.7307 (0.7293)	loss 3.1550 (3.1857)	grad_norm 1.4820 (1.4542/0.5631)	mem 34604MB
[2025-01-19 10:35:25 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][100/312]	eta 0:02:41 lr 0.002096	time 0.7288 (0.7601)	model_time 0.7283 (0.7450)	loss 2.8889 (3.1284)	grad_norm 3.5244 (1.5923/0.5963)	mem 34602MB
[2025-01-19 10:35:30 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][260/312]	eta 0:00:38 lr 0.002106	time 0.7386 (0.7345)	model_time 0.7382 (0.7291)	loss 2.6444 (3.1799)	grad_norm 1.0763 (1.4630/0.5620)	mem 34604MB
[2025-01-19 10:35:32 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][110/312]	eta 0:02:33 lr 0.002096	time 0.7515 (0.7594)	model_time 0.7510 (0.7457)	loss 4.2822 (3.1462)	grad_norm 1.5193 (1.6127/0.6041)	mem 34602MB
[2025-01-19 10:35:37 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][270/312]	eta 0:00:30 lr 0.002106	time 0.7171 (0.7357)	model_time 0.7166 (0.7305)	loss 3.1841 (3.1781)	grad_norm 1.6122 (1.4711/0.5591)	mem 34604MB
[2025-01-19 10:35:40 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][120/312]	eta 0:02:25 lr 0.002095	time 0.7207 (0.7569)	model_time 0.7201 (0.7443)	loss 3.9770 (3.1818)	grad_norm 2.7653 (1.5984/0.5998)	mem 34602MB
[2025-01-19 10:35:45 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][280/312]	eta 0:00:23 lr 0.002105	time 0.7288 (0.7353)	model_time 0.7283 (0.7303)	loss 3.7639 (3.1816)	grad_norm 1.7929 (1.4684/0.5553)	mem 34604MB
[2025-01-19 10:35:47 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][130/312]	eta 0:02:17 lr 0.002094	time 0.7319 (0.7548)	model_time 0.7315 (0.7431)	loss 3.2417 (3.1891)	grad_norm 1.4907 (1.5785/0.5897)	mem 34602MB
[2025-01-19 10:35:52 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][290/312]	eta 0:00:16 lr 0.002104	time 0.7287 (0.7352)	model_time 0.7282 (0.7303)	loss 3.5999 (3.1796)	grad_norm 1.4914 (1.4647/0.5497)	mem 34604MB
[2025-01-19 10:35:54 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][140/312]	eta 0:02:09 lr 0.002094	time 0.7394 (0.7528)	model_time 0.7391 (0.7419)	loss 3.4426 (3.1888)	grad_norm 1.5105 (1.5721/0.5882)	mem 34602MB
[2025-01-19 10:35:59 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][300/312]	eta 0:00:08 lr 0.002104	time 0.7150 (0.7346)	model_time 0.7149 (0.7299)	loss 3.7440 (3.1905)	grad_norm 3.2050 (1.4916/0.5741)	mem 34604MB
[2025-01-19 10:36:02 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][150/312]	eta 0:02:01 lr 0.002093	time 0.7207 (0.7516)	model_time 0.7203 (0.7415)	loss 3.5399 (3.2109)	grad_norm 1.0275 (1.5742/0.5801)	mem 34602MB
[2025-01-19 10:36:06 internimage_b_1k_224] (main.py 510): INFO Train: [145/300][310/312]	eta 0:00:01 lr 0.002103	time 0.7138 (0.7340)	model_time 0.7137 (0.7295)	loss 2.2953 (3.1959)	grad_norm 2.0623 (1.4889/0.5576)	mem 34604MB
[2025-01-19 10:36:07 internimage_b_1k_224] (main.py 519): INFO EPOCH 145 training takes 0:03:49
[2025-01-19 10:36:07 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_145.pth saving......
[2025-01-19 10:36:09 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][160/312]	eta 0:01:54 lr 0.002092	time 0.7163 (0.7510)	model_time 0.7162 (0.7414)	loss 3.2896 (3.1945)	grad_norm 2.0124 (1.5736/0.5815)	mem 34602MB
[2025-01-19 10:36:10 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_145.pth saved !!!
[2025-01-19 10:36:17 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][170/312]	eta 0:01:46 lr 0.002092	time 0.7181 (0.7513)	model_time 0.7179 (0.7422)	loss 4.0551 (3.2146)	grad_norm 0.6684 (1.5430/0.5823)	mem 34602MB
[2025-01-19 10:36:17 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.095 (7.095)	Loss 0.7766 (0.7766)	Acc@1 83.032 (83.032)	Acc@5 97.021 (97.021)	Mem 34604MB
[2025-01-19 10:36:20 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.919)	Loss 1.0683 (0.9086)	Acc@1 76.001 (80.429)	Acc@5 93.750 (95.479)	Mem 34604MB
[2025-01-19 10:36:21 internimage_b_1k_224] (main.py 575): INFO [Epoch:145] * Acc@1 80.398 Acc@5 95.517
[2025-01-19 10:36:21 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.4%
[2025-01-19 10:36:21 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 10:36:24 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 10:36:24 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.40%
[2025-01-19 10:36:24 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][180/312]	eta 0:01:39 lr 0.002091	time 0.7183 (0.7513)	model_time 0.7181 (0.7427)	loss 2.9355 (3.2099)	grad_norm 1.2573 (1.5171/0.5801)	mem 34602MB
[2025-01-19 10:36:31 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.104 (7.104)	Loss 0.6503 (0.6503)	Acc@1 83.862 (83.862)	Acc@5 97.534 (97.534)	Mem 34604MB
[2025-01-19 10:36:32 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][190/312]	eta 0:01:31 lr 0.002090	time 0.8075 (0.7534)	model_time 0.8070 (0.7453)	loss 2.3120 (3.2054)	grad_norm 0.9307 (1.4990/0.5721)	mem 34602MB
[2025-01-19 10:36:34 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.930)	Loss 0.9624 (0.7931)	Acc@1 76.538 (81.050)	Acc@5 94.067 (95.770)	Mem 34604MB
[2025-01-19 10:36:34 internimage_b_1k_224] (main.py 575): INFO [Epoch:145] * Acc@1 80.936 Acc@5 95.811
[2025-01-19 10:36:34 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.9%
[2025-01-19 10:36:34 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 10:36:38 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 10:36:38 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.94%
[2025-01-19 10:36:40 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][200/312]	eta 0:01:24 lr 0.002090	time 0.7256 (0.7537)	model_time 0.7252 (0.7460)	loss 3.5898 (3.1976)	grad_norm 2.0463 (1.5049/0.5661)	mem 34602MB
[2025-01-19 10:36:40 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][0/312]	eta 0:10:58 lr 0.002103	time 2.1116 (2.1116)	model_time 0.7335 (0.7335)	loss 3.5190 (3.5190)	grad_norm 1.6417 (1.6417/0.0000)	mem 34604MB
[2025-01-19 10:36:47 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][210/312]	eta 0:01:16 lr 0.002089	time 0.7181 (0.7526)	model_time 0.7179 (0.7452)	loss 3.3264 (3.1985)	grad_norm 1.3721 (1.5087/0.5596)	mem 34602MB
[2025-01-19 10:36:47 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][10/312]	eta 0:04:19 lr 0.002102	time 0.7625 (0.8603)	model_time 0.7621 (0.7347)	loss 2.5064 (3.0192)	grad_norm 0.9879 (1.5574/0.3240)	mem 34604MB
[2025-01-19 10:36:54 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][220/312]	eta 0:01:09 lr 0.002088	time 0.7194 (0.7513)	model_time 0.7193 (0.7442)	loss 3.7462 (3.2000)	grad_norm 1.6395 (1.5099/0.5499)	mem 34602MB
[2025-01-19 10:36:55 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][20/312]	eta 0:03:52 lr 0.002102	time 0.7208 (0.7977)	model_time 0.7206 (0.7317)	loss 3.1085 (2.9604)	grad_norm 1.5214 (1.4405/0.4023)	mem 34604MB
[2025-01-19 10:37:02 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][230/312]	eta 0:01:01 lr 0.002088	time 0.7312 (0.7511)	model_time 0.7307 (0.7443)	loss 3.4049 (3.2058)	grad_norm 2.4618 (1.5169/0.5605)	mem 34602MB
[2025-01-19 10:37:02 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][30/312]	eta 0:03:38 lr 0.002101	time 0.7148 (0.7736)	model_time 0.7146 (0.7288)	loss 3.5083 (3.0520)	grad_norm 1.1655 (1.4285/0.3772)	mem 34604MB
[2025-01-19 10:37:09 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][240/312]	eta 0:00:54 lr 0.002087	time 0.7410 (0.7507)	model_time 0.7408 (0.7441)	loss 2.3934 (3.2015)	grad_norm 1.3476 (1.5559/0.6434)	mem 34602MB
[2025-01-19 10:37:09 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][40/312]	eta 0:03:27 lr 0.002100	time 0.7202 (0.7625)	model_time 0.7197 (0.7285)	loss 2.3041 (3.1225)	grad_norm 0.7899 (1.3176/0.3906)	mem 34604MB
[2025-01-19 10:37:16 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][250/312]	eta 0:00:46 lr 0.002086	time 0.7418 (0.7497)	model_time 0.7417 (0.7434)	loss 3.3846 (3.1987)	grad_norm 2.6231 (1.5692/0.6480)	mem 34602MB
[2025-01-19 10:37:17 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][50/312]	eta 0:03:17 lr 0.002100	time 0.7271 (0.7547)	model_time 0.7270 (0.7273)	loss 4.1372 (3.1366)	grad_norm 1.3418 (1.3405/0.4061)	mem 34604MB
[2025-01-19 10:37:23 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][260/312]	eta 0:00:38 lr 0.002086	time 0.7189 (0.7488)	model_time 0.7184 (0.7427)	loss 3.0015 (3.1942)	grad_norm 2.9544 (1.6088/0.7086)	mem 34602MB
[2025-01-19 10:37:24 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][60/312]	eta 0:03:08 lr 0.002099	time 0.7202 (0.7494)	model_time 0.7201 (0.7265)	loss 2.2494 (3.1308)	grad_norm 2.4426 (1.5045/0.6445)	mem 34604MB
[2025-01-19 10:37:31 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][270/312]	eta 0:00:31 lr 0.002085	time 0.7184 (0.7483)	model_time 0.7179 (0.7425)	loss 3.6845 (3.1962)	grad_norm 1.0369 (1.6009/0.7015)	mem 34602MB
[2025-01-19 10:37:31 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][70/312]	eta 0:03:00 lr 0.002098	time 0.7188 (0.7458)	model_time 0.7184 (0.7261)	loss 3.3000 (3.1447)	grad_norm 0.9787 (1.4597/0.6279)	mem 34604MB
[2025-01-19 10:37:38 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][280/312]	eta 0:00:23 lr 0.002084	time 0.8011 (0.7480)	model_time 0.8010 (0.7423)	loss 3.6164 (3.2002)	grad_norm 1.1485 (1.5878/0.6963)	mem 34602MB
[2025-01-19 10:37:39 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][80/312]	eta 0:02:53 lr 0.002098	time 0.8150 (0.7479)	model_time 0.8148 (0.7305)	loss 2.2411 (3.1816)	grad_norm 1.4193 (1.4371/0.6052)	mem 34604MB
[2025-01-19 10:37:46 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][290/312]	eta 0:00:16 lr 0.002084	time 0.7980 (0.7479)	model_time 0.7975 (0.7425)	loss 2.8640 (3.1966)	grad_norm 1.6010 (1.5941/0.6935)	mem 34602MB
[2025-01-19 10:37:46 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][90/312]	eta 0:02:45 lr 0.002097	time 0.7356 (0.7457)	model_time 0.7355 (0.7302)	loss 3.0825 (3.1536)	grad_norm 1.0278 (1.4763/0.6358)	mem 34604MB
[2025-01-19 10:37:53 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][100/312]	eta 0:02:37 lr 0.002096	time 0.7252 (0.7435)	model_time 0.7247 (0.7295)	loss 3.4465 (3.1564)	grad_norm 1.7053 (1.4603/0.6139)	mem 34604MB
[2025-01-19 10:37:53 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][300/312]	eta 0:00:08 lr 0.002083	time 0.7134 (0.7483)	model_time 0.7133 (0.7430)	loss 3.1301 (3.1983)	grad_norm 0.9836 (1.5747/0.6914)	mem 34602MB
[2025-01-19 10:38:00 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][110/312]	eta 0:02:29 lr 0.002096	time 0.7141 (0.7418)	model_time 0.7136 (0.7291)	loss 2.8872 (3.1674)	grad_norm 1.4051 (1.5017/0.6325)	mem 34604MB
[2025-01-19 10:38:01 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][310/312]	eta 0:00:01 lr 0.002082	time 0.7123 (0.7496)	model_time 0.7122 (0.7444)	loss 3.2448 (3.1913)	grad_norm 0.9792 (1.5591/0.6870)	mem 34602MB
[2025-01-19 10:38:02 internimage_b_1k_224] (main.py 519): INFO EPOCH 146 training takes 0:03:53
[2025-01-19 10:38:02 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_146.pth saving......
[2025-01-19 10:38:05 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_146.pth saved !!!
[2025-01-19 10:38:08 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][120/312]	eta 0:02:22 lr 0.002095	time 0.7196 (0.7405)	model_time 0.7191 (0.7288)	loss 3.5220 (3.1875)	grad_norm 0.7937 (1.4815/0.6208)	mem 34604MB
[2025-01-19 10:38:13 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.451 (7.451)	Loss 0.8234 (0.8234)	Acc@1 83.081 (83.081)	Acc@5 96.826 (96.826)	Mem 34602MB
[2025-01-19 10:38:15 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][130/312]	eta 0:02:14 lr 0.002094	time 0.7148 (0.7397)	model_time 0.7146 (0.7288)	loss 2.9628 (3.1906)	grad_norm 1.0344 (1.4566/0.6077)	mem 34604MB
[2025-01-19 10:38:16 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.959)	Loss 1.1016 (0.9483)	Acc@1 76.245 (80.440)	Acc@5 93.652 (95.468)	Mem 34602MB
[2025-01-19 10:38:16 internimage_b_1k_224] (main.py 575): INFO [Epoch:146] * Acc@1 80.424 Acc@5 95.533
[2025-01-19 10:38:16 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.4%
[2025-01-19 10:38:16 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.48%
[2025-01-19 10:38:22 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][140/312]	eta 0:02:07 lr 0.002094	time 0.7264 (0.7385)	model_time 0.7260 (0.7284)	loss 3.7035 (3.1736)	grad_norm 1.5929 (1.4495/0.5990)	mem 34604MB
[2025-01-19 10:38:25 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.228 (9.228)	Loss 0.6508 (0.6508)	Acc@1 83.936 (83.936)	Acc@5 97.559 (97.559)	Mem 34602MB
[2025-01-19 10:38:29 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][150/312]	eta 0:01:59 lr 0.002093	time 0.7199 (0.7376)	model_time 0.7194 (0.7282)	loss 3.1130 (3.1763)	grad_norm 0.9426 (1.4279/0.5932)	mem 34604MB
[2025-01-19 10:38:30 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.238)	Loss 0.9621 (0.7927)	Acc@1 76.489 (81.104)	Acc@5 94.116 (95.799)	Mem 34602MB
[2025-01-19 10:38:30 internimage_b_1k_224] (main.py 575): INFO [Epoch:146] * Acc@1 80.996 Acc@5 95.839
[2025-01-19 10:38:30 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.0%
[2025-01-19 10:38:30 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 10:38:34 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 10:38:34 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.00%
[2025-01-19 10:38:36 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][0/312]	eta 0:10:45 lr 0.002082	time 2.0681 (2.0681)	model_time 0.7369 (0.7369)	loss 2.5179 (2.5179)	grad_norm 2.2772 (2.2772/0.0000)	mem 34602MB
[2025-01-19 10:38:37 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][160/312]	eta 0:01:52 lr 0.002092	time 0.7141 (0.7369)	model_time 0.7140 (0.7280)	loss 4.1573 (3.1776)	grad_norm 1.0902 (1.4497/0.6051)	mem 34604MB
[2025-01-19 10:38:43 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][10/312]	eta 0:04:22 lr 0.002082	time 0.7174 (0.8694)	model_time 0.7172 (0.7481)	loss 3.3065 (2.8212)	grad_norm 1.4546 (1.6686/0.5577)	mem 34602MB
[2025-01-19 10:38:44 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][170/312]	eta 0:01:44 lr 0.002092	time 0.7544 (0.7361)	model_time 0.7540 (0.7277)	loss 3.6358 (3.1808)	grad_norm 0.9704 (1.4418/0.5962)	mem 34604MB
[2025-01-19 10:38:50 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][20/312]	eta 0:03:54 lr 0.002081	time 0.7229 (0.8032)	model_time 0.7228 (0.7395)	loss 3.5131 (3.0176)	grad_norm 1.6281 (1.5111/0.5720)	mem 34602MB
[2025-01-19 10:38:51 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][180/312]	eta 0:01:37 lr 0.002091	time 0.7198 (0.7359)	model_time 0.7197 (0.7279)	loss 3.4438 (3.1923)	grad_norm 1.4105 (1.4447/0.5915)	mem 34604MB
[2025-01-19 10:38:58 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][30/312]	eta 0:03:39 lr 0.002080	time 0.7072 (0.7787)	model_time 0.7067 (0.7354)	loss 3.3697 (3.0400)	grad_norm 2.3322 (1.4997/0.5530)	mem 34602MB
[2025-01-19 10:38:58 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][190/312]	eta 0:01:29 lr 0.002090	time 0.7143 (0.7353)	model_time 0.7138 (0.7277)	loss 3.3709 (3.1933)	grad_norm 1.4596 (1.4784/0.6204)	mem 34604MB
[2025-01-19 10:39:05 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][40/312]	eta 0:03:30 lr 0.002080	time 0.7304 (0.7745)	model_time 0.7302 (0.7417)	loss 3.4996 (3.0516)	grad_norm 2.0000 (1.5745/0.5766)	mem 34602MB
[2025-01-19 10:39:06 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][200/312]	eta 0:01:22 lr 0.002090	time 0.8168 (0.7363)	model_time 0.8163 (0.7291)	loss 2.6786 (3.1887)	grad_norm 0.9771 (1.5202/0.6806)	mem 34604MB
[2025-01-19 10:39:13 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][50/312]	eta 0:03:21 lr 0.002079	time 0.7716 (0.7693)	model_time 0.7714 (0.7428)	loss 3.2675 (3.0544)	grad_norm 2.3290 (1.5732/0.5703)	mem 34602MB
[2025-01-19 10:39:13 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][210/312]	eta 0:01:15 lr 0.002089	time 0.7192 (0.7358)	model_time 0.7190 (0.7289)	loss 3.7992 (3.1949)	grad_norm 1.2229 (1.5078/0.6694)	mem 34604MB
[2025-01-19 10:39:20 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][60/312]	eta 0:03:11 lr 0.002078	time 0.7183 (0.7618)	model_time 0.7178 (0.7396)	loss 2.1964 (3.0972)	grad_norm 1.4444 (1.5514/0.5581)	mem 34602MB
[2025-01-19 10:39:20 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][220/312]	eta 0:01:07 lr 0.002088	time 0.7153 (0.7351)	model_time 0.7149 (0.7285)	loss 3.0612 (3.1930)	grad_norm 1.3007 (1.4988/0.6572)	mem 34604MB
[2025-01-19 10:39:27 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][70/312]	eta 0:03:03 lr 0.002078	time 0.7218 (0.7573)	model_time 0.7216 (0.7382)	loss 3.2570 (3.1340)	grad_norm 1.7462 (1.5448/0.5345)	mem 34602MB
[2025-01-19 10:39:28 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][230/312]	eta 0:01:00 lr 0.002088	time 0.7644 (0.7348)	model_time 0.7643 (0.7284)	loss 3.3159 (3.1863)	grad_norm 1.1253 (1.5050/0.6518)	mem 34604MB
[2025-01-19 10:39:35 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][80/312]	eta 0:02:54 lr 0.002077	time 0.7295 (0.7539)	model_time 0.7290 (0.7371)	loss 3.3633 (3.1580)	grad_norm 0.9090 (1.5624/0.5578)	mem 34602MB
[2025-01-19 10:39:35 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][240/312]	eta 0:00:52 lr 0.002087	time 0.7291 (0.7344)	model_time 0.7286 (0.7283)	loss 3.7103 (3.2038)	grad_norm 1.5697 (1.5199/0.6580)	mem 34604MB
[2025-01-19 10:39:42 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][90/312]	eta 0:02:47 lr 0.002076	time 0.8072 (0.7537)	model_time 0.8067 (0.7387)	loss 2.9251 (3.1603)	grad_norm 1.3182 (1.5626/0.5544)	mem 34602MB
[2025-01-19 10:39:42 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][250/312]	eta 0:00:45 lr 0.002086	time 0.7070 (0.7342)	model_time 0.7066 (0.7284)	loss 3.4971 (3.2156)	grad_norm 2.3034 (1.5421/0.6813)	mem 34604MB
[2025-01-19 10:39:50 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][260/312]	eta 0:00:38 lr 0.002086	time 0.7181 (0.7340)	model_time 0.7176 (0.7284)	loss 3.8417 (3.2154)	grad_norm 1.3378 (1.5311/0.6737)	mem 34604MB
[2025-01-19 10:39:50 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][100/312]	eta 0:02:39 lr 0.002076	time 0.8038 (0.7529)	model_time 0.8036 (0.7393)	loss 3.4266 (3.1691)	grad_norm 1.1007 (1.5939/0.5963)	mem 34602MB
[2025-01-19 10:39:57 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][270/312]	eta 0:00:30 lr 0.002085	time 0.7128 (0.7336)	model_time 0.7126 (0.7282)	loss 3.5654 (3.2243)	grad_norm 0.9425 (1.5299/0.6677)	mem 34604MB
[2025-01-19 10:39:57 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][110/312]	eta 0:02:32 lr 0.002075	time 0.8074 (0.7530)	model_time 0.8069 (0.7406)	loss 4.2261 (3.1845)	grad_norm 1.2016 (1.5496/0.5913)	mem 34602MB
[2025-01-19 10:40:04 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][280/312]	eta 0:00:23 lr 0.002084	time 0.7161 (0.7331)	model_time 0.7157 (0.7278)	loss 3.8380 (3.2261)	grad_norm 1.2503 (1.5195/0.6622)	mem 34604MB
[2025-01-19 10:40:05 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][120/312]	eta 0:02:24 lr 0.002074	time 0.7211 (0.7535)	model_time 0.7207 (0.7422)	loss 3.0389 (3.1751)	grad_norm 1.5611 (1.5341/0.5804)	mem 34602MB
[2025-01-19 10:40:11 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][290/312]	eta 0:00:16 lr 0.002084	time 0.7265 (0.7330)	model_time 0.7264 (0.7279)	loss 3.2846 (3.2187)	grad_norm 1.5250 (1.5106/0.6534)	mem 34604MB
[2025-01-19 10:40:12 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][130/312]	eta 0:02:17 lr 0.002074	time 0.7223 (0.7536)	model_time 0.7222 (0.7431)	loss 2.4078 (3.1755)	grad_norm 0.8751 (1.5193/0.5738)	mem 34602MB
[2025-01-19 10:40:19 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][300/312]	eta 0:00:08 lr 0.002083	time 0.7139 (0.7326)	model_time 0.7138 (0.7277)	loss 3.3563 (3.2140)	grad_norm 2.1150 (1.5210/0.6517)	mem 34604MB
[2025-01-19 10:40:20 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][140/312]	eta 0:02:09 lr 0.002073	time 0.7618 (0.7520)	model_time 0.7616 (0.7421)	loss 3.3775 (3.1807)	grad_norm 1.6951 (1.4857/0.5750)	mem 34602MB
[2025-01-19 10:40:26 internimage_b_1k_224] (main.py 510): INFO Train: [146/300][310/312]	eta 0:00:01 lr 0.002082	time 0.7511 (0.7323)	model_time 0.7510 (0.7275)	loss 3.1801 (3.2156)	grad_norm 0.8549 (1.5111/0.6520)	mem 34604MB
[2025-01-19 10:40:26 internimage_b_1k_224] (main.py 519): INFO EPOCH 146 training takes 0:03:48
[2025-01-19 10:40:26 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_146.pth saving......
[2025-01-19 10:40:27 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][150/312]	eta 0:02:01 lr 0.002072	time 0.7188 (0.7509)	model_time 0.7184 (0.7417)	loss 3.8532 (3.1832)	grad_norm 2.0044 (1.5021/0.5830)	mem 34602MB
[2025-01-19 10:40:30 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_146.pth saved !!!
[2025-01-19 10:40:34 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][160/312]	eta 0:01:54 lr 0.002072	time 0.7204 (0.7511)	model_time 0.7199 (0.7424)	loss 2.5788 (3.1897)	grad_norm 0.9058 (1.5047/0.6023)	mem 34602MB
[2025-01-19 10:40:37 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.349 (7.349)	Loss 0.7967 (0.7967)	Acc@1 83.081 (83.081)	Acc@5 96.851 (96.851)	Mem 34604MB
[2025-01-19 10:40:40 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.946)	Loss 1.0498 (0.9191)	Acc@1 77.246 (80.123)	Acc@5 94.019 (95.452)	Mem 34604MB
[2025-01-19 10:40:40 internimage_b_1k_224] (main.py 575): INFO [Epoch:146] * Acc@1 80.114 Acc@5 95.481
[2025-01-19 10:40:40 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.1%
[2025-01-19 10:40:40 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.40%
[2025-01-19 10:40:42 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][170/312]	eta 0:01:46 lr 0.002071	time 0.7233 (0.7511)	model_time 0.7231 (0.7430)	loss 3.2826 (3.2013)	grad_norm 2.6757 (1.5006/0.6012)	mem 34602MB
[2025-01-19 10:40:49 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][180/312]	eta 0:01:38 lr 0.002070	time 0.7287 (0.7497)	model_time 0.7283 (0.7420)	loss 2.6992 (3.1824)	grad_norm 1.3807 (1.5015/0.5920)	mem 34602MB
[2025-01-19 10:40:49 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.996 (8.996)	Loss 0.6504 (0.6504)	Acc@1 83.911 (83.911)	Acc@5 97.534 (97.534)	Mem 34604MB
[2025-01-19 10:40:54 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.221)	Loss 0.9612 (0.7927)	Acc@1 76.514 (81.068)	Acc@5 94.165 (95.772)	Mem 34604MB
[2025-01-19 10:40:54 internimage_b_1k_224] (main.py 575): INFO [Epoch:146] * Acc@1 80.962 Acc@5 95.815
[2025-01-19 10:40:54 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.0%
[2025-01-19 10:40:54 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 10:40:56 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][190/312]	eta 0:01:31 lr 0.002070	time 0.7211 (0.7480)	model_time 0.7209 (0.7407)	loss 3.9167 (3.1871)	grad_norm 1.6936 (1.4829/0.5863)	mem 34602MB
[2025-01-19 10:40:58 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 10:40:58 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 80.96%
[2025-01-19 10:41:00 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][0/312]	eta 0:10:27 lr 0.002082	time 2.0097 (2.0097)	model_time 0.7471 (0.7471)	loss 2.0130 (2.0130)	grad_norm 0.7659 (0.7659/0.0000)	mem 34604MB
[2025-01-19 10:41:04 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][200/312]	eta 0:01:23 lr 0.002069	time 0.7251 (0.7473)	model_time 0.7249 (0.7403)	loss 3.0197 (3.1855)	grad_norm 1.7508 (1.5126/0.6198)	mem 34602MB
[2025-01-19 10:41:08 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][10/312]	eta 0:04:24 lr 0.002082	time 0.8067 (0.8757)	model_time 0.8063 (0.7605)	loss 3.4743 (3.0717)	grad_norm 0.7493 (1.3494/0.8608)	mem 34604MB
[2025-01-19 10:41:11 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][210/312]	eta 0:01:16 lr 0.002068	time 0.7911 (0.7476)	model_time 0.7909 (0.7409)	loss 3.1348 (3.1846)	grad_norm 2.0214 (1.5204/0.6180)	mem 34602MB
[2025-01-19 10:41:15 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][20/312]	eta 0:03:55 lr 0.002081	time 0.7131 (0.8071)	model_time 0.7126 (0.7466)	loss 3.4100 (3.2179)	grad_norm 1.0862 (1.5352/0.7601)	mem 34604MB
[2025-01-19 10:41:19 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][220/312]	eta 0:01:08 lr 0.002068	time 0.8032 (0.7476)	model_time 0.8027 (0.7412)	loss 2.5169 (3.1894)	grad_norm 2.6462 (1.5436/0.6287)	mem 34602MB
[2025-01-19 10:41:22 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][30/312]	eta 0:03:39 lr 0.002080	time 0.7236 (0.7799)	model_time 0.7234 (0.7388)	loss 2.9966 (3.2388)	grad_norm 1.0153 (1.5043/0.7648)	mem 34604MB
[2025-01-19 10:41:26 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][230/312]	eta 0:01:01 lr 0.002067	time 0.7977 (0.7480)	model_time 0.7975 (0.7419)	loss 2.5969 (3.1914)	grad_norm 1.2856 (1.5627/0.6389)	mem 34602MB
[2025-01-19 10:41:29 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][40/312]	eta 0:03:28 lr 0.002080	time 0.7284 (0.7675)	model_time 0.7282 (0.7364)	loss 2.7602 (3.2670)	grad_norm 2.4412 (1.6423/0.8123)	mem 34604MB
[2025-01-19 10:41:34 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][240/312]	eta 0:00:53 lr 0.002066	time 0.7768 (0.7485)	model_time 0.7763 (0.7426)	loss 3.0691 (3.1906)	grad_norm 0.6230 (1.5693/0.6356)	mem 34602MB
[2025-01-19 10:41:37 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][50/312]	eta 0:03:19 lr 0.002079	time 0.7473 (0.7602)	model_time 0.7468 (0.7351)	loss 3.2920 (3.2663)	grad_norm 0.7417 (1.5664/0.7711)	mem 34604MB
[2025-01-19 10:41:42 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][250/312]	eta 0:00:46 lr 0.002066	time 0.7169 (0.7493)	model_time 0.7167 (0.7436)	loss 3.9855 (3.1958)	grad_norm 1.6989 (1.5570/0.6312)	mem 34602MB
[2025-01-19 10:41:44 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][60/312]	eta 0:03:10 lr 0.002078	time 0.7143 (0.7545)	model_time 0.7139 (0.7335)	loss 2.5158 (3.2517)	grad_norm 1.6899 (1.6463/0.8050)	mem 34604MB
[2025-01-19 10:41:49 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][260/312]	eta 0:00:38 lr 0.002065	time 0.7179 (0.7489)	model_time 0.7177 (0.7434)	loss 3.0631 (3.1961)	grad_norm 1.2821 (1.5498/0.6233)	mem 34602MB
[2025-01-19 10:41:51 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][70/312]	eta 0:03:01 lr 0.002078	time 0.7193 (0.7502)	model_time 0.7191 (0.7321)	loss 3.0023 (3.2074)	grad_norm 2.5037 (1.7223/0.8114)	mem 34604MB
[2025-01-19 10:41:56 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][270/312]	eta 0:00:31 lr 0.002064	time 0.7146 (0.7480)	model_time 0.7141 (0.7428)	loss 3.3556 (3.1967)	grad_norm 0.9132 (1.5441/0.6152)	mem 34602MB
[2025-01-19 10:41:58 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][80/312]	eta 0:02:53 lr 0.002077	time 0.7268 (0.7467)	model_time 0.7267 (0.7308)	loss 3.0867 (3.2010)	grad_norm 1.7413 (1.6844/0.7859)	mem 34604MB
[2025-01-19 10:42:04 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][280/312]	eta 0:00:23 lr 0.002064	time 0.7310 (0.7480)	model_time 0.7309 (0.7429)	loss 3.3097 (3.2089)	grad_norm 1.2374 (1.5294/0.6106)	mem 34602MB
[2025-01-19 10:42:06 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][90/312]	eta 0:02:45 lr 0.002076	time 0.7161 (0.7440)	model_time 0.7157 (0.7298)	loss 3.8390 (3.2021)	grad_norm 1.7965 (1.6219/0.7725)	mem 34604MB
[2025-01-19 10:42:11 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][290/312]	eta 0:00:16 lr 0.002063	time 0.7199 (0.7481)	model_time 0.7197 (0.7432)	loss 2.9905 (3.2097)	grad_norm 2.9498 (1.5395/0.6178)	mem 34602MB
[2025-01-19 10:42:13 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][100/312]	eta 0:02:37 lr 0.002076	time 0.7128 (0.7416)	model_time 0.7123 (0.7288)	loss 3.6882 (3.2018)	grad_norm 1.0646 (1.5955/0.7459)	mem 34604MB
[2025-01-19 10:42:19 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][300/312]	eta 0:00:08 lr 0.002062	time 0.7152 (0.7475)	model_time 0.7151 (0.7427)	loss 3.9721 (3.2078)	grad_norm 1.3659 (1.5414/0.6153)	mem 34602MB
[2025-01-19 10:42:20 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][110/312]	eta 0:02:29 lr 0.002075	time 0.7458 (0.7406)	model_time 0.7453 (0.7289)	loss 2.9259 (3.2218)	grad_norm 0.9741 (1.6017/0.7288)	mem 34604MB
[2025-01-19 10:42:26 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][310/312]	eta 0:00:01 lr 0.002062	time 0.7115 (0.7466)	model_time 0.7114 (0.7419)	loss 3.4948 (3.2155)	grad_norm 0.6936 (1.5276/0.6123)	mem 34602MB
[2025-01-19 10:42:26 internimage_b_1k_224] (main.py 519): INFO EPOCH 147 training takes 0:03:52
[2025-01-19 10:42:26 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_147.pth saving......
[2025-01-19 10:42:27 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][120/312]	eta 0:02:22 lr 0.002074	time 0.7226 (0.7400)	model_time 0.7225 (0.7292)	loss 2.7421 (3.2351)	grad_norm 1.0901 (1.5876/0.7075)	mem 34604MB
[2025-01-19 10:42:30 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_147.pth saved !!!
[2025-01-19 10:42:35 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][130/312]	eta 0:02:14 lr 0.002074	time 0.7311 (0.7413)	model_time 0.7309 (0.7313)	loss 3.4208 (3.2374)	grad_norm 2.0679 (1.5984/0.7040)	mem 34604MB
[2025-01-19 10:42:37 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.217 (7.217)	Loss 0.7988 (0.7988)	Acc@1 83.105 (83.105)	Acc@5 96.997 (96.997)	Mem 34602MB
[2025-01-19 10:42:40 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.915)	Loss 1.0913 (0.9228)	Acc@1 76.831 (80.500)	Acc@5 94.263 (95.483)	Mem 34602MB
[2025-01-19 10:42:40 internimage_b_1k_224] (main.py 575): INFO [Epoch:147] * Acc@1 80.440 Acc@5 95.513
[2025-01-19 10:42:40 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.4%
[2025-01-19 10:42:40 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.48%
[2025-01-19 10:42:43 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][140/312]	eta 0:02:07 lr 0.002073	time 0.7758 (0.7416)	model_time 0.7756 (0.7324)	loss 4.0461 (3.2380)	grad_norm 3.6185 (1.6226/0.7228)	mem 34604MB
[2025-01-19 10:42:50 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.151 (9.151)	Loss 0.6510 (0.6510)	Acc@1 83.960 (83.960)	Acc@5 97.559 (97.559)	Mem 34602MB
[2025-01-19 10:42:50 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][150/312]	eta 0:01:59 lr 0.002072	time 0.7097 (0.7401)	model_time 0.7095 (0.7315)	loss 3.0556 (3.2375)	grad_norm 1.6041 (1.6305/0.7121)	mem 34604MB
[2025-01-19 10:42:54 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.254)	Loss 0.9610 (0.7924)	Acc@1 76.489 (81.137)	Acc@5 94.214 (95.814)	Mem 34602MB
[2025-01-19 10:42:54 internimage_b_1k_224] (main.py 575): INFO [Epoch:147] * Acc@1 81.032 Acc@5 95.857
[2025-01-19 10:42:54 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.0%
[2025-01-19 10:42:54 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 10:42:57 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][160/312]	eta 0:01:52 lr 0.002072	time 0.7206 (0.7391)	model_time 0.7205 (0.7309)	loss 2.9666 (3.2524)	grad_norm 0.7010 (1.5980/0.7050)	mem 34604MB
[2025-01-19 10:42:58 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 10:42:58 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.03%
[2025-01-19 10:43:00 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][0/312]	eta 0:10:44 lr 0.002061	time 2.0641 (2.0641)	model_time 0.7389 (0.7389)	loss 3.3134 (3.3134)	grad_norm 1.9051 (1.9051/0.0000)	mem 34602MB
[2025-01-19 10:43:04 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][170/312]	eta 0:01:44 lr 0.002071	time 0.7175 (0.7383)	model_time 0.7170 (0.7306)	loss 3.0892 (3.2481)	grad_norm 1.3518 (1.5700/0.6977)	mem 34604MB
[2025-01-19 10:43:08 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][10/312]	eta 0:04:21 lr 0.002061	time 0.7275 (0.8646)	model_time 0.7273 (0.7439)	loss 4.0321 (3.2962)	grad_norm 2.1615 (1.3692/0.4102)	mem 34602MB
[2025-01-19 10:43:11 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][180/312]	eta 0:01:37 lr 0.002070	time 0.7180 (0.7373)	model_time 0.7179 (0.7300)	loss 3.3159 (3.2450)	grad_norm 1.4247 (1.5940/0.7277)	mem 34604MB
[2025-01-19 10:43:16 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][20/312]	eta 0:03:59 lr 0.002060	time 0.8125 (0.8190)	model_time 0.8120 (0.7555)	loss 3.9193 (3.4537)	grad_norm 1.0922 (1.3875/0.4241)	mem 34602MB
[2025-01-19 10:43:19 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][190/312]	eta 0:01:29 lr 0.002070	time 0.7361 (0.7365)	model_time 0.7359 (0.7296)	loss 2.9084 (3.2436)	grad_norm 2.6555 (1.5972/0.7225)	mem 34604MB
[2025-01-19 10:43:23 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][30/312]	eta 0:03:44 lr 0.002059	time 0.7214 (0.7963)	model_time 0.7210 (0.7533)	loss 3.7357 (3.3206)	grad_norm 1.0398 (1.6101/0.7469)	mem 34602MB
[2025-01-19 10:43:26 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][200/312]	eta 0:01:22 lr 0.002069	time 0.7207 (0.7360)	model_time 0.7202 (0.7294)	loss 2.6806 (3.2471)	grad_norm 1.3045 (1.5918/0.7118)	mem 34604MB
[2025-01-19 10:43:31 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][40/312]	eta 0:03:34 lr 0.002059	time 0.7086 (0.7876)	model_time 0.7084 (0.7550)	loss 2.7843 (3.3050)	grad_norm 1.0996 (1.6110/0.7438)	mem 34602MB
[2025-01-19 10:43:33 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][210/312]	eta 0:01:14 lr 0.002068	time 0.7176 (0.7352)	model_time 0.7171 (0.7289)	loss 2.4837 (3.2506)	grad_norm 1.6822 (1.5759/0.7033)	mem 34604MB
[2025-01-19 10:43:38 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][50/312]	eta 0:03:25 lr 0.002058	time 0.7149 (0.7831)	model_time 0.7147 (0.7568)	loss 3.9596 (3.3236)	grad_norm 2.3724 (1.5828/0.7059)	mem 34602MB
[2025-01-19 10:43:40 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][220/312]	eta 0:01:07 lr 0.002068	time 0.7295 (0.7352)	model_time 0.7294 (0.7292)	loss 3.2074 (3.2541)	grad_norm 1.4369 (1.5597/0.6955)	mem 34604MB
[2025-01-19 10:43:46 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][60/312]	eta 0:03:17 lr 0.002057	time 0.8126 (0.7831)	model_time 0.8125 (0.7611)	loss 3.5077 (3.2966)	grad_norm 1.6505 (1.6721/0.7230)	mem 34602MB
[2025-01-19 10:43:48 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][230/312]	eta 0:01:00 lr 0.002067	time 0.7206 (0.7347)	model_time 0.7204 (0.7289)	loss 2.7987 (3.2386)	grad_norm 1.3852 (1.5620/0.6984)	mem 34604MB
[2025-01-19 10:43:54 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][70/312]	eta 0:03:07 lr 0.002057	time 0.7184 (0.7761)	model_time 0.7182 (0.7571)	loss 3.2261 (3.2599)	grad_norm 1.4600 (1.6271/0.6988)	mem 34602MB
[2025-01-19 10:43:55 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][240/312]	eta 0:00:52 lr 0.002066	time 0.7147 (0.7347)	model_time 0.7146 (0.7291)	loss 3.5469 (3.2228)	grad_norm 0.9664 (1.5581/0.6925)	mem 34604MB
[2025-01-19 10:44:01 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][80/312]	eta 0:02:58 lr 0.002056	time 0.7180 (0.7714)	model_time 0.7178 (0.7547)	loss 3.8034 (3.2634)	grad_norm 1.4215 (1.5733/0.6777)	mem 34602MB
[2025-01-19 10:44:03 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][250/312]	eta 0:00:45 lr 0.002066	time 0.7163 (0.7360)	model_time 0.7162 (0.7307)	loss 3.3058 (3.2163)	grad_norm 1.8281 (1.5551/0.6856)	mem 34604MB
[2025-01-19 10:44:08 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][90/312]	eta 0:02:50 lr 0.002055	time 0.7158 (0.7686)	model_time 0.7154 (0.7537)	loss 2.3330 (3.2594)	grad_norm 0.8695 (1.5294/0.6594)	mem 34602MB
[2025-01-19 10:44:10 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][260/312]	eta 0:00:38 lr 0.002065	time 0.7287 (0.7365)	model_time 0.7285 (0.7313)	loss 3.2175 (3.2226)	grad_norm 1.4441 (1.5553/0.6843)	mem 34604MB
[2025-01-19 10:44:16 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][100/312]	eta 0:02:42 lr 0.002055	time 0.7360 (0.7654)	model_time 0.7359 (0.7519)	loss 3.7820 (3.2489)	grad_norm 2.0118 (1.5210/0.6680)	mem 34602MB
[2025-01-19 10:44:17 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][270/312]	eta 0:00:30 lr 0.002064	time 0.7222 (0.7361)	model_time 0.7217 (0.7311)	loss 3.1750 (3.2278)	grad_norm 1.0272 (1.5587/0.6760)	mem 34604MB
[2025-01-19 10:44:23 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][110/312]	eta 0:02:34 lr 0.002054	time 0.7229 (0.7643)	model_time 0.7227 (0.7520)	loss 3.4962 (3.2631)	grad_norm 0.9472 (1.5215/0.6657)	mem 34602MB
[2025-01-19 10:44:25 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][280/312]	eta 0:00:23 lr 0.002064	time 0.7424 (0.7358)	model_time 0.7423 (0.7310)	loss 3.3315 (3.2334)	grad_norm 0.9012 (1.5485/0.6692)	mem 34604MB
[2025-01-19 10:44:31 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][120/312]	eta 0:02:26 lr 0.002053	time 0.7279 (0.7613)	model_time 0.7278 (0.7500)	loss 2.2223 (3.2711)	grad_norm 1.1037 (1.5002/0.6527)	mem 34602MB
[2025-01-19 10:44:32 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][290/312]	eta 0:00:16 lr 0.002063	time 0.7607 (0.7358)	model_time 0.7601 (0.7311)	loss 3.3324 (3.2302)	grad_norm 1.3813 (1.5629/0.6698)	mem 34604MB
[2025-01-19 10:44:38 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][130/312]	eta 0:02:18 lr 0.002053	time 0.7149 (0.7606)	model_time 0.7148 (0.7502)	loss 2.3901 (3.2497)	grad_norm 1.1206 (1.4973/0.6357)	mem 34602MB
[2025-01-19 10:44:39 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][300/312]	eta 0:00:08 lr 0.002062	time 0.7639 (0.7355)	model_time 0.7637 (0.7310)	loss 2.4015 (3.2254)	grad_norm 1.7865 (1.5784/0.6892)	mem 34604MB
[2025-01-19 10:44:46 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][140/312]	eta 0:02:10 lr 0.002052	time 0.7968 (0.7596)	model_time 0.7964 (0.7499)	loss 3.5362 (3.2592)	grad_norm 1.5930 (1.5213/0.6711)	mem 34602MB
[2025-01-19 10:44:47 internimage_b_1k_224] (main.py 510): INFO Train: [147/300][310/312]	eta 0:00:01 lr 0.002062	time 0.7136 (0.7355)	model_time 0.7135 (0.7311)	loss 3.2136 (3.2238)	grad_norm 1.7980 (1.5726/0.6764)	mem 34604MB
[2025-01-19 10:44:47 internimage_b_1k_224] (main.py 519): INFO EPOCH 147 training takes 0:03:49
[2025-01-19 10:44:47 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_147.pth saving......
[2025-01-19 10:44:51 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_147.pth saved !!!
[2025-01-19 10:44:53 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][150/312]	eta 0:02:02 lr 0.002051	time 0.7274 (0.7592)	model_time 0.7272 (0.7501)	loss 3.1808 (3.2529)	grad_norm 2.5997 (1.5318/0.6759)	mem 34602MB
[2025-01-19 10:44:58 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.977 (6.977)	Loss 0.8008 (0.8008)	Acc@1 83.447 (83.447)	Acc@5 97.070 (97.070)	Mem 34604MB
[2025-01-19 10:45:01 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.901)	Loss 1.0625 (0.9233)	Acc@1 77.148 (80.506)	Acc@5 93.970 (95.421)	Mem 34604MB
[2025-01-19 10:45:01 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][160/312]	eta 0:01:55 lr 0.002051	time 0.7178 (0.7596)	model_time 0.7174 (0.7510)	loss 3.1810 (3.2614)	grad_norm 1.8317 (1.5493/0.6990)	mem 34602MB
[2025-01-19 10:45:01 internimage_b_1k_224] (main.py 575): INFO [Epoch:147] * Acc@1 80.404 Acc@5 95.449
[2025-01-19 10:45:01 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.4%
[2025-01-19 10:45:01 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 10:45:04 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 10:45:04 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.40%
[2025-01-19 10:45:08 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][170/312]	eta 0:01:47 lr 0.002050	time 0.7172 (0.7597)	model_time 0.7170 (0.7516)	loss 3.1746 (3.2552)	grad_norm 1.5913 (1.5345/0.6845)	mem 34602MB
[2025-01-19 10:45:11 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.002 (7.002)	Loss 0.6506 (0.6506)	Acc@1 84.009 (84.009)	Acc@5 97.559 (97.559)	Mem 34604MB
[2025-01-19 10:45:14 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.898)	Loss 0.9600 (0.7924)	Acc@1 76.489 (81.119)	Acc@5 94.287 (95.790)	Mem 34604MB
[2025-01-19 10:45:14 internimage_b_1k_224] (main.py 575): INFO [Epoch:147] * Acc@1 81.008 Acc@5 95.835
[2025-01-19 10:45:14 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.0%
[2025-01-19 10:45:14 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 10:45:16 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][180/312]	eta 0:01:40 lr 0.002050	time 0.8198 (0.7596)	model_time 0.8194 (0.7519)	loss 3.4999 (3.2506)	grad_norm 1.1510 (1.5292/0.6756)	mem 34602MB
[2025-01-19 10:45:18 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 10:45:18 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.01%
[2025-01-19 10:45:20 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][0/312]	eta 0:10:25 lr 0.002061	time 2.0032 (2.0032)	model_time 0.7383 (0.7383)	loss 2.2969 (2.2969)	grad_norm 2.4062 (2.4062/0.0000)	mem 34604MB
[2025-01-19 10:45:23 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][190/312]	eta 0:01:32 lr 0.002049	time 0.7336 (0.7577)	model_time 0.7334 (0.7504)	loss 3.6993 (3.2594)	grad_norm 0.7852 (1.5145/0.6660)	mem 34602MB
[2025-01-19 10:45:28 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][10/312]	eta 0:04:14 lr 0.002061	time 0.7265 (0.8441)	model_time 0.7260 (0.7289)	loss 3.2478 (2.9173)	grad_norm 1.3418 (1.5610/0.6050)	mem 34604MB
[2025-01-19 10:45:30 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][200/312]	eta 0:01:24 lr 0.002048	time 0.7408 (0.7561)	model_time 0.7406 (0.7491)	loss 2.1398 (3.2641)	grad_norm 1.0539 (1.5310/0.6719)	mem 34602MB
[2025-01-19 10:45:35 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][20/312]	eta 0:03:50 lr 0.002060	time 0.7162 (0.7880)	model_time 0.7161 (0.7275)	loss 2.4471 (3.0182)	grad_norm 0.7085 (1.5739/0.6253)	mem 34604MB
[2025-01-19 10:45:38 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][210/312]	eta 0:01:17 lr 0.002048	time 0.7173 (0.7560)	model_time 0.7169 (0.7494)	loss 2.3938 (3.2565)	grad_norm 1.3571 (1.5255/0.6626)	mem 34602MB
[2025-01-19 10:45:42 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][30/312]	eta 0:03:37 lr 0.002059	time 0.8172 (0.7718)	model_time 0.8168 (0.7307)	loss 3.2595 (3.1734)	grad_norm 1.3861 (1.5194/0.6653)	mem 34604MB
[2025-01-19 10:45:45 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][220/312]	eta 0:01:09 lr 0.002047	time 0.7268 (0.7552)	model_time 0.7265 (0.7488)	loss 2.6630 (3.2567)	grad_norm 0.8193 (1.5147/0.6556)	mem 34602MB
[2025-01-19 10:45:50 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][40/312]	eta 0:03:26 lr 0.002059	time 0.7183 (0.7592)	model_time 0.7181 (0.7280)	loss 3.8395 (3.2247)	grad_norm 1.5761 (1.4841/0.6164)	mem 34604MB
[2025-01-19 10:45:53 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][230/312]	eta 0:01:01 lr 0.002046	time 0.7165 (0.7542)	model_time 0.7160 (0.7481)	loss 3.5246 (3.2605)	grad_norm 1.0689 (1.5264/0.6555)	mem 34602MB
[2025-01-19 10:45:57 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][50/312]	eta 0:03:17 lr 0.002058	time 0.7254 (0.7530)	model_time 0.7253 (0.7279)	loss 3.1139 (3.2628)	grad_norm 2.2409 (1.4838/0.5881)	mem 34604MB
[2025-01-19 10:46:00 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][240/312]	eta 0:00:54 lr 0.002046	time 0.7215 (0.7531)	model_time 0.7213 (0.7472)	loss 3.2782 (3.2590)	grad_norm 1.6573 (1.5185/0.6487)	mem 34602MB
[2025-01-19 10:46:05 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][60/312]	eta 0:03:10 lr 0.002057	time 0.7282 (0.7571)	model_time 0.7277 (0.7360)	loss 2.8229 (3.2512)	grad_norm 1.1203 (1.5359/0.6143)	mem 34604MB
[2025-01-19 10:46:07 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][250/312]	eta 0:00:46 lr 0.002045	time 0.7145 (0.7529)	model_time 0.7144 (0.7473)	loss 3.4614 (3.2526)	grad_norm 1.6121 (1.5380/0.6722)	mem 34602MB
[2025-01-19 10:46:12 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][70/312]	eta 0:03:02 lr 0.002057	time 0.7218 (0.7558)	model_time 0.7214 (0.7376)	loss 3.6229 (3.2636)	grad_norm 0.9213 (1.4825/0.5928)	mem 34604MB
[2025-01-19 10:46:15 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][260/312]	eta 0:00:39 lr 0.002044	time 0.7328 (0.7526)	model_time 0.7324 (0.7472)	loss 2.6739 (3.2432)	grad_norm 1.6555 (1.5397/0.6687)	mem 34602MB
[2025-01-19 10:46:19 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][80/312]	eta 0:02:54 lr 0.002056	time 0.7145 (0.7530)	model_time 0.7141 (0.7370)	loss 3.3638 (3.2644)	grad_norm 1.6531 (1.4504/0.5739)	mem 34604MB
[2025-01-19 10:46:22 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][270/312]	eta 0:00:31 lr 0.002044	time 0.7361 (0.7530)	model_time 0.7360 (0.7477)	loss 2.3248 (3.2377)	grad_norm 1.0734 (1.5520/0.6775)	mem 34602MB
[2025-01-19 10:46:27 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][90/312]	eta 0:02:46 lr 0.002055	time 0.7163 (0.7498)	model_time 0.7162 (0.7355)	loss 2.3577 (3.2040)	grad_norm 0.8388 (1.5552/0.6769)	mem 34604MB
[2025-01-19 10:46:30 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][280/312]	eta 0:00:24 lr 0.002043	time 0.7079 (0.7531)	model_time 0.7074 (0.7480)	loss 2.8159 (3.2459)	grad_norm 0.9126 (1.5507/0.6799)	mem 34602MB
[2025-01-19 10:46:34 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][100/312]	eta 0:02:38 lr 0.002055	time 0.7632 (0.7477)	model_time 0.7631 (0.7349)	loss 2.8048 (3.1727)	grad_norm 1.2491 (1.5898/0.6726)	mem 34604MB
[2025-01-19 10:46:38 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][290/312]	eta 0:00:16 lr 0.002042	time 0.7170 (0.7534)	model_time 0.7168 (0.7485)	loss 3.5317 (3.2447)	grad_norm 1.2126 (1.5415/0.6734)	mem 34602MB
[2025-01-19 10:46:41 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][110/312]	eta 0:02:30 lr 0.002054	time 0.7135 (0.7463)	model_time 0.7134 (0.7345)	loss 3.4996 (3.1845)	grad_norm 1.9917 (1.5654/0.6563)	mem 34604MB
[2025-01-19 10:46:45 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][300/312]	eta 0:00:09 lr 0.002042	time 0.7131 (0.7528)	model_time 0.7129 (0.7481)	loss 2.0274 (3.2387)	grad_norm 1.8014 (1.5410/0.6690)	mem 34602MB
[2025-01-19 10:46:49 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][120/312]	eta 0:02:23 lr 0.002053	time 0.7311 (0.7449)	model_time 0.7310 (0.7340)	loss 3.5829 (3.1824)	grad_norm 0.9589 (1.5621/0.6670)	mem 34604MB
[2025-01-19 10:46:52 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][310/312]	eta 0:00:01 lr 0.002041	time 0.7154 (0.7520)	model_time 0.7153 (0.7473)	loss 2.7732 (3.2366)	grad_norm 1.2570 (1.5347/0.6692)	mem 34602MB
[2025-01-19 10:46:53 internimage_b_1k_224] (main.py 519): INFO EPOCH 148 training takes 0:03:54
[2025-01-19 10:46:53 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_148.pth saving......
[2025-01-19 10:46:56 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][130/312]	eta 0:02:15 lr 0.002053	time 0.7096 (0.7433)	model_time 0.7094 (0.7333)	loss 3.0442 (3.1848)	grad_norm 0.7743 (1.5259/0.6582)	mem 34604MB
[2025-01-19 10:46:56 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_148.pth saved !!!
[2025-01-19 10:47:03 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][140/312]	eta 0:02:07 lr 0.002052	time 0.7204 (0.7419)	model_time 0.7200 (0.7325)	loss 3.6629 (3.2051)	grad_norm 1.4334 (1.5235/0.6459)	mem 34604MB
[2025-01-19 10:47:04 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.322 (7.322)	Loss 0.8092 (0.8092)	Acc@1 83.618 (83.618)	Acc@5 96.997 (96.997)	Mem 34602MB
[2025-01-19 10:47:07 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.921)	Loss 1.0746 (0.9178)	Acc@1 76.294 (80.597)	Acc@5 93.994 (95.461)	Mem 34602MB
[2025-01-19 10:47:07 internimage_b_1k_224] (main.py 575): INFO [Epoch:148] * Acc@1 80.530 Acc@5 95.507
[2025-01-19 10:47:07 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.5%
[2025-01-19 10:47:07 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 10:47:10 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 10:47:10 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.53%
[2025-01-19 10:47:10 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][150/312]	eta 0:02:00 lr 0.002051	time 0.7236 (0.7411)	model_time 0.7234 (0.7324)	loss 3.1428 (3.2009)	grad_norm 1.4399 (1.5364/0.6470)	mem 34604MB
[2025-01-19 10:47:17 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.272 (7.272)	Loss 0.6515 (0.6515)	Acc@1 84.058 (84.058)	Acc@5 97.583 (97.583)	Mem 34602MB
[2025-01-19 10:47:18 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][160/312]	eta 0:01:52 lr 0.002051	time 0.7130 (0.7406)	model_time 0.7128 (0.7324)	loss 2.4918 (3.1892)	grad_norm 1.1428 (1.5273/0.6359)	mem 34604MB
[2025-01-19 10:47:20 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.911)	Loss 0.9602 (0.7922)	Acc@1 76.440 (81.172)	Acc@5 94.238 (95.816)	Mem 34602MB
[2025-01-19 10:47:20 internimage_b_1k_224] (main.py 575): INFO [Epoch:148] * Acc@1 81.074 Acc@5 95.861
[2025-01-19 10:47:20 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.1%
[2025-01-19 10:47:20 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 10:47:24 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 10:47:24 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.07%
[2025-01-19 10:47:25 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][170/312]	eta 0:01:45 lr 0.002050	time 0.7154 (0.7399)	model_time 0.7152 (0.7321)	loss 3.6013 (3.2020)	grad_norm 1.6420 (1.5286/0.6249)	mem 34604MB
[2025-01-19 10:47:26 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][0/312]	eta 0:12:04 lr 0.002041	time 2.3222 (2.3222)	model_time 0.7493 (0.7493)	loss 3.6320 (3.6320)	grad_norm 1.2654 (1.2654/0.0000)	mem 34602MB
[2025-01-19 10:47:33 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][180/312]	eta 0:01:37 lr 0.002050	time 0.7228 (0.7416)	model_time 0.7224 (0.7343)	loss 2.6989 (3.1992)	grad_norm 0.8773 (1.5538/0.6545)	mem 34604MB
[2025-01-19 10:47:34 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][10/312]	eta 0:04:22 lr 0.002040	time 0.7290 (0.8689)	model_time 0.7289 (0.7257)	loss 2.5704 (3.0872)	grad_norm 0.8392 (1.6202/0.8076)	mem 34602MB
[2025-01-19 10:47:40 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][190/312]	eta 0:01:30 lr 0.002049	time 0.7244 (0.7422)	model_time 0.7240 (0.7352)	loss 3.1096 (3.1898)	grad_norm 2.4191 (1.5723/0.6597)	mem 34604MB
[2025-01-19 10:47:41 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][20/312]	eta 0:03:57 lr 0.002039	time 0.7175 (0.8135)	model_time 0.7174 (0.7384)	loss 2.5264 (3.0968)	grad_norm 1.4801 (1.4592/0.7115)	mem 34602MB
[2025-01-19 10:47:48 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][200/312]	eta 0:01:23 lr 0.002048	time 0.7317 (0.7416)	model_time 0.7316 (0.7350)	loss 4.1967 (3.1915)	grad_norm 2.1608 (1.5733/0.6636)	mem 34604MB
[2025-01-19 10:47:49 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][30/312]	eta 0:03:42 lr 0.002039	time 0.7185 (0.7888)	model_time 0.7180 (0.7378)	loss 3.6786 (3.1161)	grad_norm 0.9497 (1.3840/0.6556)	mem 34602MB
[2025-01-19 10:47:55 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][210/312]	eta 0:01:15 lr 0.002048	time 0.7545 (0.7409)	model_time 0.7541 (0.7345)	loss 3.3560 (3.1989)	grad_norm 1.4341 (1.5930/0.6698)	mem 34604MB
[2025-01-19 10:47:56 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][40/312]	eta 0:03:30 lr 0.002038	time 0.7175 (0.7756)	model_time 0.7170 (0.7369)	loss 3.2885 (3.1175)	grad_norm 1.0198 (1.4007/0.5989)	mem 34602MB
[2025-01-19 10:48:02 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][220/312]	eta 0:01:08 lr 0.002047	time 0.7159 (0.7406)	model_time 0.7158 (0.7345)	loss 3.9424 (3.2007)	grad_norm 1.4739 (1.6060/0.6632)	mem 34604MB
[2025-01-19 10:48:03 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][50/312]	eta 0:03:21 lr 0.002037	time 0.7228 (0.7676)	model_time 0.7226 (0.7364)	loss 3.2748 (3.0985)	grad_norm 2.5033 (1.4144/0.5952)	mem 34602MB
[2025-01-19 10:48:09 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][230/312]	eta 0:01:00 lr 0.002046	time 0.7198 (0.7399)	model_time 0.7197 (0.7340)	loss 3.5052 (3.1995)	grad_norm 1.0566 (1.5955/0.6555)	mem 34604MB
[2025-01-19 10:48:11 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][60/312]	eta 0:03:12 lr 0.002037	time 0.7268 (0.7630)	model_time 0.7263 (0.7369)	loss 3.7492 (3.1307)	grad_norm 1.3546 (1.4744/0.6369)	mem 34602MB
[2025-01-19 10:48:17 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][240/312]	eta 0:00:53 lr 0.002046	time 0.7179 (0.7391)	model_time 0.7177 (0.7335)	loss 2.7441 (3.2072)	grad_norm 1.2361 (1.5856/0.6485)	mem 34604MB
[2025-01-19 10:48:18 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][70/312]	eta 0:03:04 lr 0.002036	time 0.8073 (0.7609)	model_time 0.8068 (0.7384)	loss 2.2917 (3.1177)	grad_norm 1.0627 (1.4353/0.6199)	mem 34602MB
[2025-01-19 10:48:24 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][250/312]	eta 0:00:45 lr 0.002045	time 0.7162 (0.7384)	model_time 0.7158 (0.7330)	loss 2.5617 (3.2006)	grad_norm 2.3733 (1.5920/0.6437)	mem 34604MB
[2025-01-19 10:48:26 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][80/312]	eta 0:02:56 lr 0.002035	time 0.7190 (0.7610)	model_time 0.7185 (0.7412)	loss 2.4080 (3.1461)	grad_norm 1.4274 (1.4737/0.6413)	mem 34602MB
[2025-01-19 10:48:31 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][260/312]	eta 0:00:38 lr 0.002044	time 0.7241 (0.7379)	model_time 0.7240 (0.7327)	loss 3.6756 (3.2059)	grad_norm 2.4744 (1.6066/0.6436)	mem 34604MB
[2025-01-19 10:48:33 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][90/312]	eta 0:02:48 lr 0.002035	time 0.7214 (0.7603)	model_time 0.7212 (0.7427)	loss 3.2401 (3.1700)	grad_norm 0.7954 (1.4835/0.6546)	mem 34602MB
[2025-01-19 10:48:38 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][270/312]	eta 0:00:30 lr 0.002044	time 0.7176 (0.7376)	model_time 0.7171 (0.7326)	loss 3.5849 (3.2115)	grad_norm 0.7208 (1.6216/0.6660)	mem 34604MB
[2025-01-19 10:48:41 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][100/312]	eta 0:02:41 lr 0.002034	time 0.7901 (0.7611)	model_time 0.7899 (0.7452)	loss 3.5370 (3.1752)	grad_norm 1.7275 (1.4594/0.6369)	mem 34602MB
[2025-01-19 10:48:46 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][280/312]	eta 0:00:23 lr 0.002043	time 0.7232 (0.7372)	model_time 0.7231 (0.7324)	loss 2.4339 (3.2058)	grad_norm 1.4854 (1.6187/0.6553)	mem 34604MB
[2025-01-19 10:48:48 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][110/312]	eta 0:02:33 lr 0.002033	time 0.7310 (0.7591)	model_time 0.7309 (0.7446)	loss 2.1986 (3.1729)	grad_norm 1.2242 (1.4455/0.6159)	mem 34602MB
[2025-01-19 10:48:53 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][290/312]	eta 0:00:16 lr 0.002042	time 0.7198 (0.7369)	model_time 0.7194 (0.7322)	loss 2.4017 (3.1966)	grad_norm 0.8196 (1.6077/0.6508)	mem 34604MB
[2025-01-19 10:48:56 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][120/312]	eta 0:02:25 lr 0.002033	time 0.7326 (0.7571)	model_time 0.7321 (0.7437)	loss 3.5562 (3.1940)	grad_norm 0.9241 (1.4932/0.6462)	mem 34602MB
[2025-01-19 10:49:01 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][300/312]	eta 0:00:08 lr 0.002042	time 0.7117 (0.7378)	model_time 0.7115 (0.7333)	loss 3.1543 (3.1951)	grad_norm 1.0864 (1.5916/0.6448)	mem 34604MB
[2025-01-19 10:49:03 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][130/312]	eta 0:02:17 lr 0.002032	time 0.7262 (0.7551)	model_time 0.7261 (0.7427)	loss 2.6419 (3.1746)	grad_norm 1.1696 (1.4649/0.6353)	mem 34602MB
[2025-01-19 10:49:08 internimage_b_1k_224] (main.py 510): INFO Train: [148/300][310/312]	eta 0:00:01 lr 0.002041	time 0.7137 (0.7386)	model_time 0.7136 (0.7342)	loss 3.5948 (3.1897)	grad_norm 1.0619 (1.5907/0.6422)	mem 34604MB
[2025-01-19 10:49:09 internimage_b_1k_224] (main.py 519): INFO EPOCH 148 training takes 0:03:50
[2025-01-19 10:49:09 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_148.pth saving......
[2025-01-19 10:49:10 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][140/312]	eta 0:02:09 lr 0.002031	time 0.7228 (0.7548)	model_time 0.7226 (0.7433)	loss 2.8910 (3.1663)	grad_norm 1.6412 (1.4599/0.6221)	mem 34602MB
[2025-01-19 10:49:12 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_148.pth saved !!!
[2025-01-19 10:49:18 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][150/312]	eta 0:02:02 lr 0.002031	time 0.7185 (0.7537)	model_time 0.7183 (0.7430)	loss 3.8049 (3.1886)	grad_norm 3.1216 (1.4732/0.6269)	mem 34602MB
[2025-01-19 10:49:19 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.304 (7.304)	Loss 0.7808 (0.7808)	Acc@1 83.521 (83.521)	Acc@5 96.802 (96.802)	Mem 34604MB
[2025-01-19 10:49:22 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.931)	Loss 1.0849 (0.9117)	Acc@1 76.514 (80.686)	Acc@5 93.799 (95.612)	Mem 34604MB
[2025-01-19 10:49:23 internimage_b_1k_224] (main.py 575): INFO [Epoch:148] * Acc@1 80.574 Acc@5 95.645
[2025-01-19 10:49:23 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.6%
[2025-01-19 10:49:23 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 10:49:25 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][160/312]	eta 0:01:54 lr 0.002030	time 0.7372 (0.7524)	model_time 0.7367 (0.7423)	loss 3.4335 (3.1933)	grad_norm 2.0831 (1.5136/0.6735)	mem 34602MB
[2025-01-19 10:49:26 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 10:49:26 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.57%
[2025-01-19 10:49:33 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][170/312]	eta 0:01:46 lr 0.002029	time 0.7229 (0.7512)	model_time 0.7227 (0.7416)	loss 2.0142 (3.1769)	grad_norm 1.5077 (1.5018/0.6626)	mem 34602MB
[2025-01-19 10:49:33 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.042 (7.042)	Loss 0.6507 (0.6507)	Acc@1 84.033 (84.033)	Acc@5 97.607 (97.607)	Mem 34604MB
[2025-01-19 10:49:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.909)	Loss 0.9587 (0.7921)	Acc@1 76.611 (81.206)	Acc@5 94.287 (95.803)	Mem 34604MB
[2025-01-19 10:49:36 internimage_b_1k_224] (main.py 575): INFO [Epoch:148] * Acc@1 81.090 Acc@5 95.843
[2025-01-19 10:49:36 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.1%
[2025-01-19 10:49:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 10:49:40 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][180/312]	eta 0:01:39 lr 0.002029	time 0.7325 (0.7507)	model_time 0.7321 (0.7416)	loss 3.5386 (3.1844)	grad_norm 1.8844 (1.5095/0.6611)	mem 34602MB
[2025-01-19 10:49:40 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 10:49:40 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.09%
[2025-01-19 10:49:42 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][0/312]	eta 0:11:02 lr 0.002041	time 2.1221 (2.1221)	model_time 0.7365 (0.7365)	loss 4.0892 (4.0892)	grad_norm 1.3058 (1.3058/0.0000)	mem 34604MB
[2025-01-19 10:49:47 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][190/312]	eta 0:01:31 lr 0.002028	time 0.7960 (0.7503)	model_time 0.7956 (0.7417)	loss 3.3104 (3.1883)	grad_norm 3.3531 (1.5125/0.6673)	mem 34602MB
[2025-01-19 10:49:50 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][10/312]	eta 0:04:19 lr 0.002040	time 0.7276 (0.8589)	model_time 0.7274 (0.7326)	loss 2.1037 (3.4635)	grad_norm 1.0064 (1.5676/0.8205)	mem 34604MB
[2025-01-19 10:49:55 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][200/312]	eta 0:01:24 lr 0.002027	time 0.7997 (0.7511)	model_time 0.7993 (0.7429)	loss 3.6552 (3.1780)	grad_norm 1.0048 (1.5124/0.6618)	mem 34602MB
[2025-01-19 10:49:57 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][20/312]	eta 0:03:53 lr 0.002039	time 0.7209 (0.7980)	model_time 0.7208 (0.7317)	loss 4.0236 (3.3425)	grad_norm 1.8793 (1.6193/0.6686)	mem 34604MB
[2025-01-19 10:50:03 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][210/312]	eta 0:01:16 lr 0.002027	time 0.7308 (0.7514)	model_time 0.7306 (0.7436)	loss 2.7095 (3.1757)	grad_norm 1.8518 (1.5096/0.6521)	mem 34602MB
[2025-01-19 10:50:04 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][30/312]	eta 0:03:38 lr 0.002039	time 0.7225 (0.7742)	model_time 0.7221 (0.7292)	loss 3.4484 (3.2691)	grad_norm 1.0667 (1.4962/0.6011)	mem 34604MB
[2025-01-19 10:50:10 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][220/312]	eta 0:01:09 lr 0.002026	time 0.7927 (0.7523)	model_time 0.7923 (0.7448)	loss 2.7762 (3.1625)	grad_norm 1.6002 (1.5259/0.6579)	mem 34602MB
[2025-01-19 10:50:12 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][40/312]	eta 0:03:27 lr 0.002038	time 0.7579 (0.7629)	model_time 0.7577 (0.7288)	loss 2.5764 (3.2334)	grad_norm 3.0604 (1.5074/0.6209)	mem 34604MB
[2025-01-19 10:50:18 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][230/312]	eta 0:01:01 lr 0.002025	time 0.7200 (0.7523)	model_time 0.7195 (0.7452)	loss 4.2994 (3.1738)	grad_norm 1.4893 (1.5250/0.6479)	mem 34602MB
[2025-01-19 10:50:19 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][50/312]	eta 0:03:17 lr 0.002037	time 0.7228 (0.7545)	model_time 0.7227 (0.7271)	loss 2.7133 (3.1366)	grad_norm 1.3948 (1.4839/0.5965)	mem 34604MB
[2025-01-19 10:50:25 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][240/312]	eta 0:00:54 lr 0.002025	time 0.7216 (0.7517)	model_time 0.7212 (0.7448)	loss 3.8722 (3.1767)	grad_norm 2.1668 (1.5373/0.6496)	mem 34602MB
[2025-01-19 10:50:26 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][60/312]	eta 0:03:08 lr 0.002037	time 0.7192 (0.7494)	model_time 0.7188 (0.7263)	loss 3.3044 (3.1235)	grad_norm 1.1025 (1.4827/0.5959)	mem 34604MB
[2025-01-19 10:50:32 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][250/312]	eta 0:00:46 lr 0.002024	time 0.7296 (0.7507)	model_time 0.7295 (0.7441)	loss 3.1095 (3.1686)	grad_norm 1.2316 (1.5508/0.6590)	mem 34602MB
[2025-01-19 10:50:33 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][70/312]	eta 0:03:00 lr 0.002036	time 0.7157 (0.7462)	model_time 0.7153 (0.7263)	loss 2.9317 (3.1189)	grad_norm 0.9592 (1.5109/0.5994)	mem 34604MB
[2025-01-19 10:50:40 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][260/312]	eta 0:00:39 lr 0.002023	time 0.7163 (0.7508)	model_time 0.7158 (0.7444)	loss 3.6355 (3.1558)	grad_norm 1.0633 (1.5473/0.6526)	mem 34602MB
[2025-01-19 10:50:41 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][80/312]	eta 0:02:52 lr 0.002035	time 0.7551 (0.7455)	model_time 0.7549 (0.7281)	loss 2.2819 (3.0962)	grad_norm 1.5744 (1.4928/0.5781)	mem 34604MB
[2025-01-19 10:50:47 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][270/312]	eta 0:00:31 lr 0.002023	time 0.7199 (0.7502)	model_time 0.7198 (0.7440)	loss 3.5062 (3.1530)	grad_norm 1.6815 (1.5529/0.6494)	mem 34602MB
[2025-01-19 10:50:48 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][90/312]	eta 0:02:45 lr 0.002035	time 0.7177 (0.7438)	model_time 0.7172 (0.7282)	loss 2.3882 (3.1065)	grad_norm 1.1693 (1.4827/0.5769)	mem 34604MB
[2025-01-19 10:50:55 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][280/312]	eta 0:00:23 lr 0.002022	time 0.7185 (0.7496)	model_time 0.7180 (0.7436)	loss 2.4899 (3.1635)	grad_norm 1.3038 (1.5622/0.6497)	mem 34602MB
[2025-01-19 10:50:55 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][100/312]	eta 0:02:37 lr 0.002034	time 0.8306 (0.7429)	model_time 0.8301 (0.7288)	loss 3.4913 (3.1013)	grad_norm 1.3947 (1.4825/0.5697)	mem 34604MB
[2025-01-19 10:51:02 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][290/312]	eta 0:00:16 lr 0.002021	time 0.7435 (0.7492)	model_time 0.7433 (0.7434)	loss 3.5688 (3.1757)	grad_norm 0.7317 (1.5525/0.6504)	mem 34602MB
[2025-01-19 10:51:03 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][110/312]	eta 0:02:30 lr 0.002033	time 0.7896 (0.7461)	model_time 0.7891 (0.7333)	loss 3.7678 (3.0965)	grad_norm 1.1283 (1.5150/0.5917)	mem 34604MB
[2025-01-19 10:51:09 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][300/312]	eta 0:00:08 lr 0.002021	time 0.7090 (0.7484)	model_time 0.7088 (0.7428)	loss 3.6388 (3.1845)	grad_norm 0.7334 (1.5499/0.6565)	mem 34602MB
[2025-01-19 10:51:11 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][120/312]	eta 0:02:23 lr 0.002033	time 0.7217 (0.7462)	model_time 0.7216 (0.7344)	loss 2.8445 (3.1055)	grad_norm 1.1831 (1.5070/0.5871)	mem 34604MB
[2025-01-19 10:51:17 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][310/312]	eta 0:00:01 lr 0.002020	time 0.7177 (0.7476)	model_time 0.7176 (0.7422)	loss 3.6079 (3.1959)	grad_norm 2.0824 (1.5388/0.6455)	mem 34602MB
[2025-01-19 10:51:17 internimage_b_1k_224] (main.py 519): INFO EPOCH 149 training takes 0:03:53
[2025-01-19 10:51:17 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_149.pth saving......
[2025-01-19 10:51:18 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][130/312]	eta 0:02:15 lr 0.002032	time 0.7204 (0.7444)	model_time 0.7200 (0.7334)	loss 3.6377 (3.1125)	grad_norm 2.3991 (1.5104/0.5778)	mem 34604MB
[2025-01-19 10:51:20 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_149.pth saved !!!
[2025-01-19 10:51:25 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][140/312]	eta 0:02:07 lr 0.002031	time 0.7219 (0.7430)	model_time 0.7217 (0.7328)	loss 2.4391 (3.1346)	grad_norm 3.0146 (1.5454/0.6257)	mem 34604MB
[2025-01-19 10:51:28 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.511 (7.511)	Loss 0.7721 (0.7721)	Acc@1 83.350 (83.350)	Acc@5 96.924 (96.924)	Mem 34602MB
[2025-01-19 10:51:31 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.944)	Loss 1.0462 (0.9047)	Acc@1 76.636 (80.624)	Acc@5 94.092 (95.510)	Mem 34602MB
[2025-01-19 10:51:31 internimage_b_1k_224] (main.py 575): INFO [Epoch:149] * Acc@1 80.576 Acc@5 95.589
[2025-01-19 10:51:31 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.6%
[2025-01-19 10:51:31 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 10:51:32 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][150/312]	eta 0:02:00 lr 0.002031	time 0.7190 (0.7419)	model_time 0.7189 (0.7323)	loss 3.0748 (3.1404)	grad_norm 1.5277 (1.5597/0.6226)	mem 34604MB
[2025-01-19 10:51:34 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 10:51:34 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.58%
[2025-01-19 10:51:39 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][160/312]	eta 0:01:52 lr 0.002030	time 0.7328 (0.7407)	model_time 0.7327 (0.7318)	loss 3.4200 (3.1531)	grad_norm 1.5798 (1.5867/0.6952)	mem 34604MB
[2025-01-19 10:51:42 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.446 (7.446)	Loss 0.6520 (0.6520)	Acc@1 84.106 (84.106)	Acc@5 97.559 (97.559)	Mem 34602MB
[2025-01-19 10:51:45 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.950)	Loss 0.9595 (0.7919)	Acc@1 76.343 (81.186)	Acc@5 94.263 (95.832)	Mem 34602MB
[2025-01-19 10:51:45 internimage_b_1k_224] (main.py 575): INFO [Epoch:149] * Acc@1 81.086 Acc@5 95.875
[2025-01-19 10:51:45 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.1%
[2025-01-19 10:51:45 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 10:51:47 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][170/312]	eta 0:01:45 lr 0.002029	time 0.7203 (0.7401)	model_time 0.7199 (0.7316)	loss 3.2373 (3.1568)	grad_norm 1.7744 (1.5950/0.6881)	mem 34604MB
[2025-01-19 10:51:49 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 10:51:49 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.09%
[2025-01-19 10:51:51 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][0/312]	eta 0:11:01 lr 0.002020	time 2.1204 (2.1204)	model_time 0.7621 (0.7621)	loss 2.5802 (2.5802)	grad_norm 2.0968 (2.0968/0.0000)	mem 34602MB
[2025-01-19 10:51:54 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][180/312]	eta 0:01:37 lr 0.002029	time 0.7200 (0.7393)	model_time 0.7195 (0.7313)	loss 3.9674 (3.1571)	grad_norm 1.1686 (1.5720/0.6801)	mem 34604MB
[2025-01-19 10:51:59 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][10/312]	eta 0:04:35 lr 0.002019	time 0.7361 (0.9111)	model_time 0.7359 (0.7873)	loss 4.1694 (3.1529)	grad_norm 2.7061 (2.2684/1.0832)	mem 34602MB
[2025-01-19 10:52:01 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][190/312]	eta 0:01:30 lr 0.002028	time 0.7147 (0.7388)	model_time 0.7143 (0.7312)	loss 3.1221 (3.1489)	grad_norm 0.8199 (1.5629/0.6745)	mem 34604MB
[2025-01-19 10:52:07 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][20/312]	eta 0:04:03 lr 0.002019	time 0.7213 (0.8332)	model_time 0.7210 (0.7682)	loss 3.3322 (3.2630)	grad_norm 1.7070 (2.0124/0.9540)	mem 34602MB
[2025-01-19 10:52:09 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][200/312]	eta 0:01:22 lr 0.002027	time 0.7247 (0.7386)	model_time 0.7242 (0.7314)	loss 3.3475 (3.1610)	grad_norm 0.8995 (1.5802/0.7049)	mem 34604MB
[2025-01-19 10:52:14 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][30/312]	eta 0:03:49 lr 0.002018	time 0.8034 (0.8133)	model_time 0.8029 (0.7691)	loss 3.1195 (3.3150)	grad_norm 1.3740 (1.8171/0.8649)	mem 34602MB
[2025-01-19 10:52:16 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][210/312]	eta 0:01:15 lr 0.002027	time 0.7431 (0.7382)	model_time 0.7427 (0.7312)	loss 3.2730 (3.1514)	grad_norm 0.9443 (1.5809/0.7055)	mem 34604MB
[2025-01-19 10:52:22 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][40/312]	eta 0:03:36 lr 0.002017	time 0.7180 (0.7977)	model_time 0.7178 (0.7642)	loss 3.6643 (3.2897)	grad_norm 1.2501 (1.7191/0.7889)	mem 34602MB
[2025-01-19 10:52:23 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][220/312]	eta 0:01:07 lr 0.002026	time 0.7201 (0.7377)	model_time 0.7196 (0.7310)	loss 3.8899 (3.1640)	grad_norm 1.6715 (1.5632/0.6982)	mem 34604MB
[2025-01-19 10:52:29 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][50/312]	eta 0:03:25 lr 0.002017	time 0.7521 (0.7846)	model_time 0.7519 (0.7576)	loss 2.6027 (3.2690)	grad_norm 1.2769 (1.6148/0.7454)	mem 34602MB
[2025-01-19 10:52:31 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][230/312]	eta 0:01:00 lr 0.002025	time 0.8056 (0.7393)	model_time 0.8055 (0.7329)	loss 3.5981 (3.1647)	grad_norm 1.7742 (1.5572/0.6939)	mem 34604MB
[2025-01-19 10:52:37 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][60/312]	eta 0:03:15 lr 0.002016	time 0.8388 (0.7767)	model_time 0.8384 (0.7541)	loss 3.2131 (3.2738)	grad_norm 1.7376 (1.5496/0.7085)	mem 34602MB
[2025-01-19 10:52:39 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][240/312]	eta 0:00:53 lr 0.002025	time 0.7206 (0.7404)	model_time 0.7204 (0.7343)	loss 2.4416 (3.1630)	grad_norm 2.0474 (1.5769/0.6985)	mem 34604MB
[2025-01-19 10:52:44 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][70/312]	eta 0:03:07 lr 0.002015	time 0.7223 (0.7761)	model_time 0.7222 (0.7566)	loss 3.1732 (3.2358)	grad_norm 1.3354 (1.4982/0.6735)	mem 34602MB
[2025-01-19 10:52:46 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][250/312]	eta 0:00:45 lr 0.002024	time 0.7162 (0.7398)	model_time 0.7160 (0.7339)	loss 3.2234 (3.1643)	grad_norm 0.9008 (1.5819/0.6961)	mem 34604MB
[2025-01-19 10:52:52 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][80/312]	eta 0:02:58 lr 0.002015	time 0.7265 (0.7708)	model_time 0.7264 (0.7537)	loss 3.4164 (3.2153)	grad_norm 1.2616 (1.5340/0.7062)	mem 34602MB
[2025-01-19 10:52:53 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][260/312]	eta 0:00:38 lr 0.002023	time 0.7160 (0.7396)	model_time 0.7155 (0.7339)	loss 3.7031 (3.1730)	grad_norm 2.1522 (1.5773/0.6881)	mem 34604MB
[2025-01-19 10:52:59 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][90/312]	eta 0:02:50 lr 0.002014	time 0.7386 (0.7676)	model_time 0.7385 (0.7523)	loss 3.4945 (3.2420)	grad_norm 2.0984 (1.5256/0.6797)	mem 34602MB
[2025-01-19 10:53:00 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][270/312]	eta 0:00:31 lr 0.002023	time 0.7194 (0.7390)	model_time 0.7192 (0.7335)	loss 2.5706 (3.1765)	grad_norm 1.1585 (1.5770/0.6796)	mem 34604MB
[2025-01-19 10:53:06 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][100/312]	eta 0:02:41 lr 0.002013	time 0.7408 (0.7633)	model_time 0.7403 (0.7495)	loss 3.7959 (3.2237)	grad_norm 1.7147 (1.4743/0.6702)	mem 34602MB
[2025-01-19 10:53:08 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][280/312]	eta 0:00:23 lr 0.002022	time 0.7279 (0.7386)	model_time 0.7277 (0.7333)	loss 2.8168 (3.1773)	grad_norm 0.8257 (1.5704/0.6752)	mem 34604MB
[2025-01-19 10:53:14 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][110/312]	eta 0:02:33 lr 0.002013	time 0.7177 (0.7609)	model_time 0.7175 (0.7483)	loss 2.3862 (3.2181)	grad_norm 1.1158 (1.4743/0.6489)	mem 34602MB
[2025-01-19 10:53:15 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][290/312]	eta 0:00:16 lr 0.002021	time 0.7266 (0.7382)	model_time 0.7262 (0.7331)	loss 3.6542 (3.1833)	grad_norm 1.8154 (1.5687/0.6672)	mem 34604MB
[2025-01-19 10:53:21 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][120/312]	eta 0:02:25 lr 0.002012	time 0.7203 (0.7590)	model_time 0.7198 (0.7474)	loss 3.8596 (3.2039)	grad_norm 1.1257 (1.4751/0.6373)	mem 34602MB
[2025-01-19 10:53:22 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][300/312]	eta 0:00:08 lr 0.002021	time 0.7128 (0.7375)	model_time 0.7127 (0.7326)	loss 2.5766 (3.1885)	grad_norm 2.1285 (1.5839/0.6715)	mem 34604MB
[2025-01-19 10:53:29 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][130/312]	eta 0:02:18 lr 0.002011	time 0.7998 (0.7597)	model_time 0.7996 (0.7490)	loss 2.7940 (3.2091)	grad_norm 1.7514 (1.5041/0.6273)	mem 34602MB
[2025-01-19 10:53:29 internimage_b_1k_224] (main.py 510): INFO Train: [149/300][310/312]	eta 0:00:01 lr 0.002020	time 0.7144 (0.7368)	model_time 0.7143 (0.7320)	loss 2.9119 (3.1892)	grad_norm 1.0435 (1.5777/0.6629)	mem 34604MB
[2025-01-19 10:53:30 internimage_b_1k_224] (main.py 519): INFO EPOCH 149 training takes 0:03:49
[2025-01-19 10:53:30 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_149.pth saving......
[2025-01-19 10:53:33 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_149.pth saved !!!
[2025-01-19 10:53:36 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][140/312]	eta 0:02:10 lr 0.002011	time 0.8017 (0.7597)	model_time 0.8011 (0.7497)	loss 3.5537 (3.2309)	grad_norm 2.0720 (1.5645/0.6925)	mem 34602MB
[2025-01-19 10:53:41 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.246 (7.246)	Loss 0.7690 (0.7690)	Acc@1 83.447 (83.447)	Acc@5 97.070 (97.070)	Mem 34604MB
[2025-01-19 10:53:44 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.926)	Loss 1.0414 (0.8978)	Acc@1 76.416 (80.449)	Acc@5 94.092 (95.581)	Mem 34604MB
[2025-01-19 10:53:44 internimage_b_1k_224] (main.py 575): INFO [Epoch:149] * Acc@1 80.360 Acc@5 95.615
[2025-01-19 10:53:44 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.4%
[2025-01-19 10:53:44 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.57%
[2025-01-19 10:53:44 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][150/312]	eta 0:02:03 lr 0.002010	time 0.8062 (0.7609)	model_time 0.8060 (0.7515)	loss 2.3554 (3.2386)	grad_norm 2.6134 (1.5633/0.6885)	mem 34602MB
[2025-01-19 10:53:51 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][160/312]	eta 0:01:55 lr 0.002009	time 0.7183 (0.7594)	model_time 0.7178 (0.7506)	loss 3.9086 (3.2503)	grad_norm 1.2711 (1.5776/0.6873)	mem 34602MB
[2025-01-19 10:53:53 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.115 (9.115)	Loss 0.6510 (0.6510)	Acc@1 84.033 (84.033)	Acc@5 97.632 (97.632)	Mem 34604MB
[2025-01-19 10:53:58 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (1.241)	Loss 0.9577 (0.7917)	Acc@1 76.709 (81.226)	Acc@5 94.238 (95.819)	Mem 34604MB
[2025-01-19 10:53:58 internimage_b_1k_224] (main.py 575): INFO [Epoch:149] * Acc@1 81.120 Acc@5 95.861
[2025-01-19 10:53:58 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.1%
[2025-01-19 10:53:58 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 10:53:59 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][170/312]	eta 0:01:47 lr 0.002009	time 0.7220 (0.7584)	model_time 0.7218 (0.7501)	loss 3.1560 (3.2549)	grad_norm 0.8233 (1.5497/0.6803)	mem 34602MB
[2025-01-19 10:54:01 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 10:54:01 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.12%
[2025-01-19 10:54:04 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][0/312]	eta 0:10:58 lr 0.002020	time 2.1122 (2.1122)	model_time 0.7401 (0.7401)	loss 3.6434 (3.6434)	grad_norm 1.6983 (1.6983/0.0000)	mem 34604MB
[2025-01-19 10:54:06 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][180/312]	eta 0:01:39 lr 0.002008	time 0.7236 (0.7570)	model_time 0.7235 (0.7491)	loss 2.2542 (3.2428)	grad_norm 1.2382 (1.5455/0.6721)	mem 34602MB
[2025-01-19 10:54:11 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][10/312]	eta 0:04:18 lr 0.002019	time 0.7282 (0.8564)	model_time 0.7277 (0.7313)	loss 3.1725 (3.5348)	grad_norm 1.3765 (1.6136/0.4142)	mem 34604MB
[2025-01-19 10:54:14 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][190/312]	eta 0:01:32 lr 0.002007	time 0.7224 (0.7568)	model_time 0.7219 (0.7493)	loss 3.3991 (3.2364)	grad_norm 1.4058 (1.5295/0.6601)	mem 34602MB
[2025-01-19 10:54:18 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][20/312]	eta 0:03:52 lr 0.002019	time 0.7274 (0.7959)	model_time 0.7269 (0.7303)	loss 2.4873 (3.2330)	grad_norm 1.9715 (1.9986/0.7919)	mem 34604MB
[2025-01-19 10:54:21 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][200/312]	eta 0:01:24 lr 0.002007	time 0.7189 (0.7559)	model_time 0.7184 (0.7488)	loss 3.4866 (3.2424)	grad_norm 0.7873 (1.5320/0.6687)	mem 34602MB
[2025-01-19 10:54:25 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][30/312]	eta 0:03:38 lr 0.002018	time 0.7194 (0.7736)	model_time 0.7193 (0.7290)	loss 3.3309 (3.2339)	grad_norm 0.9883 (1.8235/0.7435)	mem 34604MB
[2025-01-19 10:54:29 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][210/312]	eta 0:01:17 lr 0.002006	time 0.7262 (0.7554)	model_time 0.7258 (0.7486)	loss 3.6393 (3.2526)	grad_norm 2.2082 (1.5547/0.6859)	mem 34602MB
[2025-01-19 10:54:33 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][40/312]	eta 0:03:31 lr 0.002017	time 0.8186 (0.7767)	model_time 0.8183 (0.7429)	loss 2.2684 (3.1388)	grad_norm 1.1219 (1.6482/0.7315)	mem 34604MB
[2025-01-19 10:54:36 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][220/312]	eta 0:01:09 lr 0.002005	time 0.7265 (0.7541)	model_time 0.7264 (0.7476)	loss 3.3765 (3.2542)	grad_norm 1.1396 (1.5590/0.6805)	mem 34602MB
[2025-01-19 10:54:41 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][50/312]	eta 0:03:22 lr 0.002017	time 0.7232 (0.7747)	model_time 0.7227 (0.7475)	loss 3.5057 (3.1383)	grad_norm 1.3923 (1.5570/0.6939)	mem 34604MB
[2025-01-19 10:54:43 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][230/312]	eta 0:01:01 lr 0.002005	time 0.7140 (0.7532)	model_time 0.7138 (0.7470)	loss 2.1562 (3.2499)	grad_norm 2.9724 (1.5667/0.6848)	mem 34602MB
[2025-01-19 10:54:48 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][60/312]	eta 0:03:13 lr 0.002016	time 0.7179 (0.7665)	model_time 0.7177 (0.7437)	loss 2.7735 (3.1364)	grad_norm 1.3311 (1.4936/0.6564)	mem 34604MB
[2025-01-19 10:54:51 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][240/312]	eta 0:00:54 lr 0.002004	time 0.7175 (0.7527)	model_time 0.7174 (0.7467)	loss 4.0459 (3.2599)	grad_norm 1.9310 (1.5590/0.6758)	mem 34602MB
[2025-01-19 10:54:55 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][70/312]	eta 0:03:04 lr 0.002015	time 0.7215 (0.7607)	model_time 0.7210 (0.7410)	loss 2.6691 (3.1324)	grad_norm 2.0566 (1.5710/0.7833)	mem 34604MB
[2025-01-19 10:54:58 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][250/312]	eta 0:00:46 lr 0.002003	time 0.7999 (0.7537)	model_time 0.7994 (0.7479)	loss 3.1113 (3.2569)	grad_norm 2.9901 (1.5651/0.6862)	mem 34602MB
[2025-01-19 10:55:03 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][80/312]	eta 0:02:55 lr 0.002015	time 0.7280 (0.7564)	model_time 0.7275 (0.7391)	loss 4.0339 (3.1634)	grad_norm 0.9494 (1.5227/0.7589)	mem 34604MB
[2025-01-19 10:55:06 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][260/312]	eta 0:00:39 lr 0.002003	time 0.8028 (0.7538)	model_time 0.8024 (0.7482)	loss 3.3835 (3.2451)	grad_norm 1.6021 (1.5692/0.6851)	mem 34602MB
[2025-01-19 10:55:10 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][90/312]	eta 0:02:47 lr 0.002014	time 0.7462 (0.7533)	model_time 0.7460 (0.7379)	loss 3.5213 (3.1809)	grad_norm 2.2073 (1.5155/0.7337)	mem 34604MB
[2025-01-19 10:55:14 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][270/312]	eta 0:00:31 lr 0.002002	time 0.8147 (0.7544)	model_time 0.8145 (0.7490)	loss 3.2840 (3.2344)	grad_norm 1.6000 (1.5830/0.6910)	mem 34602MB
[2025-01-19 10:55:17 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][100/312]	eta 0:02:39 lr 0.002013	time 0.7230 (0.7507)	model_time 0.7226 (0.7368)	loss 2.5358 (3.1631)	grad_norm 0.8085 (1.4829/0.7115)	mem 34604MB
[2025-01-19 10:55:21 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][280/312]	eta 0:00:24 lr 0.002001	time 0.7155 (0.7543)	model_time 0.7150 (0.7491)	loss 3.3444 (3.2372)	grad_norm 1.0270 (1.5801/0.6842)	mem 34602MB
[2025-01-19 10:55:25 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][110/312]	eta 0:02:31 lr 0.002013	time 0.7165 (0.7487)	model_time 0.7161 (0.7360)	loss 2.4992 (3.1679)	grad_norm 1.7626 (1.5043/0.7109)	mem 34604MB
[2025-01-19 10:55:28 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][290/312]	eta 0:00:16 lr 0.002001	time 0.7165 (0.7534)	model_time 0.7164 (0.7484)	loss 3.0272 (3.2360)	grad_norm 0.7472 (1.5673/0.6818)	mem 34602MB
[2025-01-19 10:55:32 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][120/312]	eta 0:02:23 lr 0.002012	time 0.7189 (0.7468)	model_time 0.7187 (0.7351)	loss 2.2872 (3.1652)	grad_norm 3.0491 (1.5075/0.7126)	mem 34604MB
[2025-01-19 10:55:36 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][300/312]	eta 0:00:09 lr 0.002000	time 0.7138 (0.7525)	model_time 0.7137 (0.7477)	loss 3.1523 (3.2347)	grad_norm 1.2671 (1.5576/0.6749)	mem 34602MB
[2025-01-19 10:55:39 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][130/312]	eta 0:02:15 lr 0.002011	time 0.7632 (0.7452)	model_time 0.7631 (0.7344)	loss 3.2270 (3.1661)	grad_norm 0.7504 (1.4966/0.6949)	mem 34604MB
[2025-01-19 10:55:43 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][310/312]	eta 0:00:01 lr 0.001999	time 0.7981 (0.7524)	model_time 0.7980 (0.7477)	loss 3.6402 (3.2344)	grad_norm 0.8296 (1.5229/0.6333)	mem 34602MB
[2025-01-19 10:55:44 internimage_b_1k_224] (main.py 519): INFO EPOCH 150 training takes 0:03:54
[2025-01-19 10:55:44 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_150.pth saving......
[2025-01-19 10:55:46 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][140/312]	eta 0:02:07 lr 0.002011	time 0.7360 (0.7438)	model_time 0.7359 (0.7338)	loss 3.4153 (3.1849)	grad_norm 2.2309 (1.4838/0.6811)	mem 34604MB
[2025-01-19 10:55:47 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_150.pth saved !!!
[2025-01-19 10:55:54 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][150/312]	eta 0:02:00 lr 0.002010	time 0.7152 (0.7427)	model_time 0.7147 (0.7332)	loss 3.5977 (3.1983)	grad_norm 1.5826 (1.5287/0.7537)	mem 34604MB
[2025-01-19 10:55:54 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.226 (7.226)	Loss 0.8071 (0.8071)	Acc@1 83.545 (83.545)	Acc@5 97.217 (97.217)	Mem 34602MB
[2025-01-19 10:55:57 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.919)	Loss 1.1011 (0.9432)	Acc@1 76.147 (80.564)	Acc@5 93.872 (95.517)	Mem 34602MB
[2025-01-19 10:55:58 internimage_b_1k_224] (main.py 575): INFO [Epoch:150] * Acc@1 80.434 Acc@5 95.563
[2025-01-19 10:55:58 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.4%
[2025-01-19 10:55:58 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.58%
[2025-01-19 10:56:01 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][160/312]	eta 0:01:53 lr 0.002009	time 0.7263 (0.7442)	model_time 0.7261 (0.7354)	loss 3.1308 (3.1936)	grad_norm 0.8582 (1.5334/0.7448)	mem 34604MB
[2025-01-19 10:56:07 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.163 (9.163)	Loss 0.6526 (0.6526)	Acc@1 84.131 (84.131)	Acc@5 97.583 (97.583)	Mem 34602MB
[2025-01-19 10:56:09 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][170/312]	eta 0:01:45 lr 0.002009	time 0.7064 (0.7456)	model_time 0.7060 (0.7372)	loss 2.8431 (3.1944)	grad_norm 1.1936 (1.5117/0.7334)	mem 34604MB
[2025-01-19 10:56:11 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.248)	Loss 0.9587 (0.7919)	Acc@1 76.489 (81.243)	Acc@5 94.360 (95.843)	Mem 34602MB
[2025-01-19 10:56:12 internimage_b_1k_224] (main.py 575): INFO [Epoch:150] * Acc@1 81.140 Acc@5 95.887
[2025-01-19 10:56:12 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.1%
[2025-01-19 10:56:12 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 10:56:15 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 10:56:15 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.14%
[2025-01-19 10:56:16 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][180/312]	eta 0:01:38 lr 0.002008	time 0.7263 (0.7442)	model_time 0.7261 (0.7363)	loss 3.1959 (3.1930)	grad_norm 0.9437 (1.5085/0.7235)	mem 34604MB
[2025-01-19 10:56:17 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][0/312]	eta 0:11:02 lr 0.001999	time 2.1241 (2.1241)	model_time 0.7432 (0.7432)	loss 2.8044 (2.8044)	grad_norm 0.9792 (0.9792/0.0000)	mem 34602MB
[2025-01-19 10:56:23 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][190/312]	eta 0:01:30 lr 0.002007	time 0.7214 (0.7431)	model_time 0.7210 (0.7356)	loss 2.1791 (3.1863)	grad_norm 1.0975 (1.5006/0.7099)	mem 34604MB
[2025-01-19 10:56:25 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][10/312]	eta 0:04:19 lr 0.001999	time 0.7170 (0.8604)	model_time 0.7169 (0.7346)	loss 3.7793 (3.0061)	grad_norm 2.0055 (1.6159/0.7248)	mem 34602MB
[2025-01-19 10:56:31 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][200/312]	eta 0:01:23 lr 0.002007	time 0.7195 (0.7424)	model_time 0.7193 (0.7352)	loss 3.9935 (3.1906)	grad_norm 1.1785 (1.4974/0.6941)	mem 34604MB
[2025-01-19 10:56:32 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][20/312]	eta 0:03:54 lr 0.001998	time 0.7442 (0.8025)	model_time 0.7438 (0.7365)	loss 2.3233 (2.9794)	grad_norm 2.5112 (2.0860/0.8636)	mem 34602MB
[2025-01-19 10:56:38 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][210/312]	eta 0:01:15 lr 0.002006	time 0.7224 (0.7419)	model_time 0.7219 (0.7350)	loss 2.8251 (3.1772)	grad_norm 0.9888 (1.4895/0.6863)	mem 34604MB
[2025-01-19 10:56:39 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][30/312]	eta 0:03:39 lr 0.001997	time 0.7286 (0.7785)	model_time 0.7285 (0.7336)	loss 2.9443 (3.1061)	grad_norm 1.5465 (1.8409/0.8130)	mem 34602MB
[2025-01-19 10:56:45 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][220/312]	eta 0:01:08 lr 0.002005	time 0.7427 (0.7413)	model_time 0.7423 (0.7348)	loss 3.4941 (3.1864)	grad_norm 1.4904 (1.4825/0.6758)	mem 34604MB
[2025-01-19 10:56:47 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][40/312]	eta 0:03:28 lr 0.001997	time 0.7205 (0.7682)	model_time 0.7200 (0.7342)	loss 3.6659 (3.1013)	grad_norm 0.7398 (1.8255/0.7759)	mem 34602MB
[2025-01-19 10:56:53 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][230/312]	eta 0:01:00 lr 0.002005	time 0.7231 (0.7410)	model_time 0.7229 (0.7347)	loss 3.5452 (3.1864)	grad_norm 1.2486 (1.4887/0.6674)	mem 34604MB
[2025-01-19 10:56:54 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][50/312]	eta 0:03:21 lr 0.001996	time 0.7907 (0.7675)	model_time 0.7905 (0.7401)	loss 3.7028 (3.1650)	grad_norm 1.8747 (1.8308/0.7317)	mem 34602MB
[2025-01-19 10:57:00 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][240/312]	eta 0:00:53 lr 0.002004	time 0.7249 (0.7405)	model_time 0.7244 (0.7344)	loss 3.2397 (3.1786)	grad_norm 3.0758 (1.5006/0.6707)	mem 34604MB
[2025-01-19 10:57:02 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][60/312]	eta 0:03:13 lr 0.001995	time 0.7198 (0.7667)	model_time 0.7197 (0.7437)	loss 3.2060 (3.1458)	grad_norm 1.2879 (1.7408/0.7075)	mem 34602MB
[2025-01-19 10:57:07 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][250/312]	eta 0:00:45 lr 0.002003	time 0.7161 (0.7397)	model_time 0.7156 (0.7338)	loss 3.1337 (3.1800)	grad_norm 2.2304 (1.5469/0.7432)	mem 34604MB
[2025-01-19 10:57:10 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][70/312]	eta 0:03:04 lr 0.001995	time 0.7200 (0.7644)	model_time 0.7198 (0.7446)	loss 3.5668 (3.1782)	grad_norm 1.6732 (1.6770/0.6898)	mem 34602MB
[2025-01-19 10:57:14 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][260/312]	eta 0:00:38 lr 0.002003	time 0.7246 (0.7391)	model_time 0.7245 (0.7335)	loss 3.5513 (3.1819)	grad_norm 2.2050 (1.5509/0.7358)	mem 34604MB
[2025-01-19 10:57:17 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][80/312]	eta 0:02:57 lr 0.001994	time 0.7161 (0.7656)	model_time 0.7160 (0.7483)	loss 3.1913 (3.1365)	grad_norm 3.3804 (1.6653/0.6915)	mem 34602MB
[2025-01-19 10:57:22 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][270/312]	eta 0:00:31 lr 0.002002	time 0.7310 (0.7387)	model_time 0.7306 (0.7333)	loss 3.2431 (3.1916)	grad_norm 1.1767 (1.5603/0.7328)	mem 34604MB
[2025-01-19 10:57:25 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][90/312]	eta 0:02:49 lr 0.001993	time 0.7172 (0.7643)	model_time 0.7167 (0.7488)	loss 3.5639 (3.1325)	grad_norm 2.6704 (1.7117/0.7251)	mem 34602MB
[2025-01-19 10:57:29 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][280/312]	eta 0:00:23 lr 0.002001	time 0.7388 (0.7399)	model_time 0.7384 (0.7347)	loss 3.8841 (3.1811)	grad_norm 2.3949 (1.5547/0.7287)	mem 34604MB
[2025-01-19 10:57:32 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][100/312]	eta 0:02:41 lr 0.001993	time 0.7199 (0.7618)	model_time 0.7198 (0.7478)	loss 2.8686 (3.1315)	grad_norm 1.0028 (1.6874/0.7140)	mem 34602MB
[2025-01-19 10:57:37 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][290/312]	eta 0:00:16 lr 0.002001	time 0.7407 (0.7415)	model_time 0.7406 (0.7364)	loss 3.3057 (3.1795)	grad_norm 2.0104 (1.5526/0.7273)	mem 34604MB
[2025-01-19 10:57:40 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][110/312]	eta 0:02:33 lr 0.001992	time 0.8308 (0.7594)	model_time 0.8307 (0.7466)	loss 3.3672 (3.1567)	grad_norm 2.2434 (1.6495/0.7042)	mem 34602MB
[2025-01-19 10:57:44 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][300/312]	eta 0:00:08 lr 0.002000	time 0.7122 (0.7408)	model_time 0.7121 (0.7359)	loss 3.4868 (3.1802)	grad_norm 1.7598 (1.5489/0.7283)	mem 34604MB
[2025-01-19 10:57:47 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][120/312]	eta 0:02:25 lr 0.001991	time 0.7253 (0.7589)	model_time 0.7249 (0.7472)	loss 2.4301 (3.1532)	grad_norm 0.9086 (1.6563/0.7052)	mem 34602MB
[2025-01-19 10:57:52 internimage_b_1k_224] (main.py 510): INFO Train: [150/300][310/312]	eta 0:00:01 lr 0.001999	time 0.7165 (0.7401)	model_time 0.7164 (0.7354)	loss 3.1936 (3.1848)	grad_norm 3.1550 (1.5482/0.7316)	mem 34604MB
[2025-01-19 10:57:52 internimage_b_1k_224] (main.py 519): INFO EPOCH 150 training takes 0:03:50
[2025-01-19 10:57:52 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_150.pth saving......
[2025-01-19 10:57:54 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][130/312]	eta 0:02:17 lr 0.001991	time 0.7234 (0.7571)	model_time 0.7232 (0.7462)	loss 2.2710 (3.1670)	grad_norm 1.6540 (1.6345/0.6892)	mem 34602MB
[2025-01-19 10:57:56 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_150.pth saved !!!
[2025-01-19 10:58:02 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][140/312]	eta 0:02:10 lr 0.001990	time 0.7520 (0.7558)	model_time 0.7516 (0.7457)	loss 4.0043 (3.1699)	grad_norm 1.4649 (1.6254/0.6761)	mem 34602MB
[2025-01-19 10:58:03 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.065 (7.065)	Loss 0.8038 (0.8038)	Acc@1 83.130 (83.130)	Acc@5 97.046 (97.046)	Mem 34604MB
[2025-01-19 10:58:06 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.911)	Loss 1.0708 (0.9150)	Acc@1 76.514 (80.697)	Acc@5 93.896 (95.581)	Mem 34604MB
[2025-01-19 10:58:06 internimage_b_1k_224] (main.py 575): INFO [Epoch:150] * Acc@1 80.494 Acc@5 95.603
[2025-01-19 10:58:06 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.5%
[2025-01-19 10:58:06 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.57%
[2025-01-19 10:58:09 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][150/312]	eta 0:02:02 lr 0.001989	time 0.7259 (0.7537)	model_time 0.7257 (0.7443)	loss 3.7748 (3.1788)	grad_norm 1.6632 (1.6075/0.6665)	mem 34602MB
[2025-01-19 10:58:15 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.901 (8.901)	Loss 0.6512 (0.6512)	Acc@1 84.033 (84.033)	Acc@5 97.632 (97.632)	Mem 34604MB
[2025-01-19 10:58:16 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][160/312]	eta 0:01:54 lr 0.001989	time 0.7575 (0.7531)	model_time 0.7571 (0.7442)	loss 3.4145 (3.1919)	grad_norm 1.3589 (1.5860/0.6565)	mem 34602MB
[2025-01-19 10:58:19 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (1.204)	Loss 0.9567 (0.7915)	Acc@1 76.733 (81.250)	Acc@5 94.336 (95.825)	Mem 34604MB
[2025-01-19 10:58:19 internimage_b_1k_224] (main.py 575): INFO [Epoch:150] * Acc@1 81.134 Acc@5 95.867
[2025-01-19 10:58:19 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.1%
[2025-01-19 10:58:19 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 10:58:23 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 10:58:23 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.13%
[2025-01-19 10:58:24 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][170/312]	eta 0:01:46 lr 0.001988	time 0.7497 (0.7534)	model_time 0.7495 (0.7450)	loss 3.1150 (3.1948)	grad_norm 1.5111 (1.5809/0.6440)	mem 34602MB
[2025-01-19 10:58:25 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][0/312]	eta 0:10:40 lr 0.001999	time 2.0540 (2.0540)	model_time 0.7411 (0.7411)	loss 2.8869 (2.8869)	grad_norm 2.0346 (2.0346/0.0000)	mem 34604MB
[2025-01-19 10:58:32 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][180/312]	eta 0:01:39 lr 0.001987	time 0.8012 (0.7542)	model_time 0.8010 (0.7462)	loss 3.2683 (3.2076)	grad_norm 1.0241 (1.5656/0.6377)	mem 34602MB
[2025-01-19 10:58:33 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][10/312]	eta 0:04:21 lr 0.001999	time 0.7297 (0.8645)	model_time 0.7293 (0.7448)	loss 2.6903 (3.0436)	grad_norm 0.8834 (1.5074/0.4735)	mem 34604MB
[2025-01-19 10:58:39 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][190/312]	eta 0:01:31 lr 0.001987	time 0.7179 (0.7533)	model_time 0.7175 (0.7458)	loss 3.4544 (3.1938)	grad_norm 1.9280 (1.5645/0.6365)	mem 34602MB
[2025-01-19 10:58:40 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][20/312]	eta 0:03:53 lr 0.001998	time 0.7528 (0.8004)	model_time 0.7524 (0.7375)	loss 4.0765 (3.2085)	grad_norm 1.2055 (1.3931/0.4190)	mem 34604MB
[2025-01-19 10:58:47 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][200/312]	eta 0:01:24 lr 0.001986	time 0.7238 (0.7545)	model_time 0.7232 (0.7473)	loss 2.2132 (3.1960)	grad_norm 1.3575 (1.5711/0.6355)	mem 34602MB
[2025-01-19 10:58:47 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][30/312]	eta 0:03:39 lr 0.001997	time 0.7209 (0.7770)	model_time 0.7207 (0.7343)	loss 3.3533 (3.2431)	grad_norm 1.0440 (1.3765/0.4475)	mem 34604MB
[2025-01-19 10:58:54 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][210/312]	eta 0:01:16 lr 0.001985	time 0.7159 (0.7538)	model_time 0.7157 (0.7469)	loss 3.1863 (3.1883)	grad_norm 2.1023 (1.5773/0.6294)	mem 34602MB
[2025-01-19 10:58:54 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][40/312]	eta 0:03:27 lr 0.001997	time 0.7449 (0.7642)	model_time 0.7447 (0.7319)	loss 3.4609 (3.2448)	grad_norm 1.3078 (1.3453/0.4107)	mem 34604MB
[2025-01-19 10:59:02 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][50/312]	eta 0:03:18 lr 0.001996	time 0.7161 (0.7560)	model_time 0.7157 (0.7299)	loss 3.6285 (3.2176)	grad_norm 0.9829 (1.3747/0.4426)	mem 34604MB
[2025-01-19 10:59:02 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][220/312]	eta 0:01:09 lr 0.001985	time 0.7273 (0.7530)	model_time 0.7269 (0.7464)	loss 2.8317 (3.1965)	grad_norm 2.6128 (1.5894/0.6247)	mem 34602MB
[2025-01-19 10:59:09 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][60/312]	eta 0:03:09 lr 0.001995	time 0.7156 (0.7520)	model_time 0.7155 (0.7301)	loss 3.2999 (3.2582)	grad_norm 1.3110 (1.3930/0.4628)	mem 34604MB
[2025-01-19 10:59:09 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][230/312]	eta 0:01:01 lr 0.001984	time 1.0002 (0.7531)	model_time 1.0000 (0.7468)	loss 3.7438 (3.1979)	grad_norm 1.9709 (1.5818/0.6191)	mem 34602MB
[2025-01-19 10:59:16 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][70/312]	eta 0:03:01 lr 0.001995	time 0.7176 (0.7481)	model_time 0.7171 (0.7293)	loss 3.2358 (3.2782)	grad_norm 2.2144 (1.4609/0.4865)	mem 34604MB
[2025-01-19 10:59:17 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][240/312]	eta 0:00:54 lr 0.001983	time 0.7187 (0.7525)	model_time 0.7185 (0.7464)	loss 3.8211 (3.2002)	grad_norm 1.0957 (1.5667/0.6194)	mem 34602MB
[2025-01-19 10:59:24 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][80/312]	eta 0:02:53 lr 0.001994	time 0.7148 (0.7471)	model_time 0.7144 (0.7305)	loss 2.1870 (3.2629)	grad_norm 2.6894 (1.5139/0.5292)	mem 34604MB
[2025-01-19 10:59:24 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][250/312]	eta 0:00:46 lr 0.001983	time 0.7164 (0.7524)	model_time 0.7160 (0.7465)	loss 3.1538 (3.2013)	grad_norm 1.2416 (1.5590/0.6196)	mem 34602MB
[2025-01-19 10:59:31 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][90/312]	eta 0:02:46 lr 0.001993	time 0.7245 (0.7506)	model_time 0.7241 (0.7358)	loss 3.4720 (3.2521)	grad_norm 1.0932 (1.5225/0.5432)	mem 34604MB
[2025-01-19 10:59:31 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][260/312]	eta 0:00:39 lr 0.001982	time 0.7192 (0.7516)	model_time 0.7191 (0.7459)	loss 3.7431 (3.1966)	grad_norm 2.4602 (1.5810/0.6331)	mem 34602MB
[2025-01-19 10:59:39 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][270/312]	eta 0:00:31 lr 0.001981	time 0.7375 (0.7507)	model_time 0.7371 (0.7452)	loss 3.4491 (3.1962)	grad_norm 1.3533 (1.5790/0.6254)	mem 34602MB
[2025-01-19 10:59:39 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][100/312]	eta 0:02:39 lr 0.001993	time 0.7373 (0.7526)	model_time 0.7372 (0.7393)	loss 3.0930 (3.2269)	grad_norm 2.6713 (1.6072/0.7229)	mem 34604MB
[2025-01-19 10:59:46 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][280/312]	eta 0:00:24 lr 0.001981	time 0.7177 (0.7504)	model_time 0.7172 (0.7451)	loss 4.0994 (3.1963)	grad_norm 2.6077 (1.5742/0.6223)	mem 34602MB
[2025-01-19 10:59:46 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][110/312]	eta 0:02:31 lr 0.001992	time 0.7180 (0.7505)	model_time 0.7176 (0.7383)	loss 3.4749 (3.2306)	grad_norm 1.2532 (1.5845/0.6979)	mem 34604MB
[2025-01-19 10:59:54 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][120/312]	eta 0:02:23 lr 0.001991	time 0.7160 (0.7484)	model_time 0.7158 (0.7372)	loss 3.5461 (3.2240)	grad_norm 1.6994 (1.5802/0.6866)	mem 34604MB
[2025-01-19 10:59:54 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][290/312]	eta 0:00:16 lr 0.001980	time 0.7173 (0.7506)	model_time 0.7169 (0.7455)	loss 3.4522 (3.2007)	grad_norm 2.5595 (1.5789/0.6258)	mem 34602MB
[2025-01-19 11:00:01 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][130/312]	eta 0:02:16 lr 0.001991	time 0.7195 (0.7475)	model_time 0.7191 (0.7372)	loss 4.0901 (3.2293)	grad_norm 0.9246 (1.5918/0.6856)	mem 34604MB
[2025-01-19 11:00:01 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][300/312]	eta 0:00:09 lr 0.001979	time 0.7957 (0.7512)	model_time 0.7955 (0.7463)	loss 3.8513 (3.2059)	grad_norm 1.1199 (1.5788/0.6227)	mem 34602MB
[2025-01-19 11:00:08 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][140/312]	eta 0:02:08 lr 0.001990	time 0.7236 (0.7466)	model_time 0.7231 (0.7369)	loss 2.7163 (3.2329)	grad_norm 1.6306 (1.5709/0.6674)	mem 34604MB
[2025-01-19 11:00:09 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][310/312]	eta 0:00:01 lr 0.001979	time 0.7221 (0.7504)	model_time 0.7219 (0.7456)	loss 2.8062 (3.2064)	grad_norm 2.0394 (1.5683/0.6142)	mem 34602MB
[2025-01-19 11:00:09 internimage_b_1k_224] (main.py 519): INFO EPOCH 151 training takes 0:03:54
[2025-01-19 11:00:09 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_151.pth saving......
[2025-01-19 11:00:12 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_151.pth saved !!!
[2025-01-19 11:00:16 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][150/312]	eta 0:02:00 lr 0.001989	time 0.7230 (0.7453)	model_time 0.7225 (0.7363)	loss 4.0557 (3.2446)	grad_norm 0.7865 (1.5387/0.6614)	mem 34604MB
[2025-01-19 11:00:20 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.289 (7.289)	Loss 0.7950 (0.7950)	Acc@1 84.253 (84.253)	Acc@5 97.168 (97.168)	Mem 34602MB
[2025-01-19 11:00:23 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][160/312]	eta 0:01:53 lr 0.001989	time 0.7220 (0.7442)	model_time 0.7218 (0.7357)	loss 3.4585 (3.2335)	grad_norm 2.1566 (1.5529/0.6697)	mem 34604MB
[2025-01-19 11:00:23 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.960)	Loss 1.0699 (0.9213)	Acc@1 75.903 (80.688)	Acc@5 94.067 (95.543)	Mem 34602MB
[2025-01-19 11:00:23 internimage_b_1k_224] (main.py 575): INFO [Epoch:151] * Acc@1 80.596 Acc@5 95.585
[2025-01-19 11:00:23 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.6%
[2025-01-19 11:00:23 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 11:00:27 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 11:00:27 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.60%
[2025-01-19 11:00:30 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][170/312]	eta 0:01:45 lr 0.001988	time 0.7385 (0.7431)	model_time 0.7380 (0.7351)	loss 3.1183 (3.2383)	grad_norm 0.9868 (1.5369/0.6591)	mem 34604MB
[2025-01-19 11:00:34 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.505 (7.505)	Loss 0.6531 (0.6531)	Acc@1 84.131 (84.131)	Acc@5 97.583 (97.583)	Mem 34602MB
[2025-01-19 11:00:37 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.972)	Loss 0.9580 (0.7918)	Acc@1 76.611 (81.330)	Acc@5 94.263 (95.843)	Mem 34602MB
[2025-01-19 11:00:37 internimage_b_1k_224] (main.py 575): INFO [Epoch:151] * Acc@1 81.222 Acc@5 95.889
[2025-01-19 11:00:37 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.2%
[2025-01-19 11:00:37 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:00:37 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][180/312]	eta 0:01:38 lr 0.001987	time 0.7318 (0.7426)	model_time 0.7317 (0.7350)	loss 3.3234 (3.2420)	grad_norm 1.6584 (1.5495/0.6725)	mem 34604MB
[2025-01-19 11:00:41 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:00:41 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.22%
[2025-01-19 11:00:43 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][0/312]	eta 0:10:39 lr 0.001979	time 2.0507 (2.0507)	model_time 0.7569 (0.7569)	loss 3.4890 (3.4890)	grad_norm 0.8798 (0.8798/0.0000)	mem 34602MB
[2025-01-19 11:00:45 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][190/312]	eta 0:01:30 lr 0.001987	time 0.7199 (0.7419)	model_time 0.7194 (0.7347)	loss 3.8877 (3.2430)	grad_norm 1.1952 (1.5627/0.6677)	mem 34604MB
[2025-01-19 11:00:51 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][10/312]	eta 0:04:27 lr 0.001978	time 0.7377 (0.8848)	model_time 0.7375 (0.7669)	loss 3.2083 (3.2763)	grad_norm 0.7271 (1.3706/0.5722)	mem 34602MB
[2025-01-19 11:00:52 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][200/312]	eta 0:01:23 lr 0.001986	time 0.7233 (0.7414)	model_time 0.7231 (0.7346)	loss 3.7808 (3.2488)	grad_norm 1.7233 (1.5785/0.6733)	mem 34604MB
[2025-01-19 11:00:59 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][20/312]	eta 0:03:58 lr 0.001977	time 0.7340 (0.8185)	model_time 0.7335 (0.7565)	loss 3.8801 (3.2478)	grad_norm 1.0732 (1.3083/0.4772)	mem 34602MB
[2025-01-19 11:01:00 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][210/312]	eta 0:01:15 lr 0.001985	time 0.7280 (0.7431)	model_time 0.7278 (0.7365)	loss 3.6646 (3.2610)	grad_norm 1.9699 (1.5895/0.6664)	mem 34604MB
[2025-01-19 11:01:06 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][30/312]	eta 0:03:43 lr 0.001977	time 0.7331 (0.7935)	model_time 0.7326 (0.7514)	loss 3.1839 (3.1893)	grad_norm 1.2549 (1.3714/0.4767)	mem 34602MB
[2025-01-19 11:01:08 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][220/312]	eta 0:01:08 lr 0.001985	time 0.7259 (0.7441)	model_time 0.7258 (0.7378)	loss 2.2178 (3.2588)	grad_norm 1.2895 (1.5929/0.6756)	mem 34604MB
[2025-01-19 11:01:13 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][40/312]	eta 0:03:32 lr 0.001976	time 0.7194 (0.7796)	model_time 0.7189 (0.7477)	loss 3.3206 (3.1643)	grad_norm 1.1254 (1.4402/0.5766)	mem 34602MB
[2025-01-19 11:01:15 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][230/312]	eta 0:01:00 lr 0.001984	time 0.7187 (0.7435)	model_time 0.7183 (0.7375)	loss 3.5932 (3.2626)	grad_norm 1.9638 (1.6073/0.6923)	mem 34604MB
[2025-01-19 11:01:21 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][50/312]	eta 0:03:22 lr 0.001975	time 0.7169 (0.7720)	model_time 0.7164 (0.7463)	loss 3.7291 (3.2299)	grad_norm 1.5355 (1.5482/0.6241)	mem 34602MB
[2025-01-19 11:01:22 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][240/312]	eta 0:00:53 lr 0.001983	time 0.7235 (0.7428)	model_time 0.7230 (0.7370)	loss 3.5280 (3.2571)	grad_norm 2.1016 (1.6065/0.6848)	mem 34604MB
[2025-01-19 11:01:28 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][60/312]	eta 0:03:13 lr 0.001975	time 0.7518 (0.7670)	model_time 0.7513 (0.7454)	loss 3.1157 (3.2358)	grad_norm 2.0708 (1.6496/0.6526)	mem 34602MB
[2025-01-19 11:01:29 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][250/312]	eta 0:00:46 lr 0.001983	time 0.7315 (0.7425)	model_time 0.7313 (0.7369)	loss 2.1183 (3.2473)	grad_norm 1.4907 (1.6107/0.6937)	mem 34604MB
[2025-01-19 11:01:35 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][70/312]	eta 0:03:04 lr 0.001974	time 0.7205 (0.7621)	model_time 0.7203 (0.7435)	loss 3.7542 (3.2447)	grad_norm 0.9209 (1.6562/0.6750)	mem 34602MB
[2025-01-19 11:01:37 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][260/312]	eta 0:00:38 lr 0.001982	time 0.7227 (0.7420)	model_time 0.7223 (0.7366)	loss 3.4752 (3.2400)	grad_norm 0.7798 (1.5961/0.6884)	mem 34604MB
[2025-01-19 11:01:43 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][80/312]	eta 0:02:55 lr 0.001973	time 0.7575 (0.7577)	model_time 0.7570 (0.7413)	loss 2.7861 (3.2261)	grad_norm 2.4854 (1.6281/0.6628)	mem 34602MB
[2025-01-19 11:01:44 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][270/312]	eta 0:00:31 lr 0.001981	time 0.7162 (0.7415)	model_time 0.7157 (0.7363)	loss 3.3352 (3.2426)	grad_norm 1.1501 (1.5869/0.6795)	mem 34604MB
[2025-01-19 11:01:50 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][90/312]	eta 0:02:47 lr 0.001973	time 0.7171 (0.7546)	model_time 0.7169 (0.7399)	loss 2.3032 (3.1929)	grad_norm 2.0010 (1.6248/0.6522)	mem 34602MB
[2025-01-19 11:01:51 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][280/312]	eta 0:00:23 lr 0.001981	time 0.7185 (0.7409)	model_time 0.7183 (0.7359)	loss 4.0195 (3.2445)	grad_norm 1.1179 (1.5744/0.6754)	mem 34604MB
[2025-01-19 11:01:58 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][100/312]	eta 0:02:40 lr 0.001972	time 0.8020 (0.7551)	model_time 0.8016 (0.7419)	loss 2.3493 (3.2103)	grad_norm 0.7125 (1.5860/0.6396)	mem 34602MB
[2025-01-19 11:01:59 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][290/312]	eta 0:00:16 lr 0.001980	time 0.7157 (0.7405)	model_time 0.7156 (0.7356)	loss 2.5314 (3.2337)	grad_norm 1.2393 (1.5674/0.6691)	mem 34604MB
[2025-01-19 11:02:05 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][110/312]	eta 0:02:32 lr 0.001971	time 0.7186 (0.7560)	model_time 0.7181 (0.7440)	loss 3.3186 (3.2195)	grad_norm 2.4786 (1.5616/0.6343)	mem 34602MB
[2025-01-19 11:02:06 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][300/312]	eta 0:00:08 lr 0.001979	time 0.7136 (0.7399)	model_time 0.7135 (0.7352)	loss 3.2644 (3.2290)	grad_norm 0.9877 (1.5785/0.6813)	mem 34604MB
[2025-01-19 11:02:13 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][120/312]	eta 0:02:25 lr 0.001971	time 0.8043 (0.7553)	model_time 0.8041 (0.7442)	loss 3.2777 (3.2248)	grad_norm 1.2388 (1.5840/0.6486)	mem 34602MB
[2025-01-19 11:02:13 internimage_b_1k_224] (main.py 510): INFO Train: [151/300][310/312]	eta 0:00:01 lr 0.001979	time 0.7141 (0.7392)	model_time 0.7141 (0.7347)	loss 3.1446 (3.2249)	grad_norm 2.6359 (1.5898/0.6844)	mem 34604MB
[2025-01-19 11:02:14 internimage_b_1k_224] (main.py 519): INFO EPOCH 151 training takes 0:03:50
[2025-01-19 11:02:14 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_151.pth saving......
[2025-01-19 11:02:17 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_151.pth saved !!!
[2025-01-19 11:02:21 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][130/312]	eta 0:02:17 lr 0.001970	time 0.7255 (0.7573)	model_time 0.7254 (0.7470)	loss 3.4853 (3.2177)	grad_norm 1.3192 (1.5565/0.6359)	mem 34602MB
[2025-01-19 11:02:24 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.325 (7.325)	Loss 0.8094 (0.8094)	Acc@1 83.325 (83.325)	Acc@5 97.021 (97.021)	Mem 34604MB
[2025-01-19 11:02:27 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.939)	Loss 1.0645 (0.9061)	Acc@1 75.659 (80.624)	Acc@5 94.019 (95.643)	Mem 34604MB
[2025-01-19 11:02:27 internimage_b_1k_224] (main.py 575): INFO [Epoch:151] * Acc@1 80.488 Acc@5 95.691
[2025-01-19 11:02:27 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.5%
[2025-01-19 11:02:27 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.57%
[2025-01-19 11:02:28 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][140/312]	eta 0:02:10 lr 0.001969	time 0.7352 (0.7560)	model_time 0.7348 (0.7465)	loss 3.0492 (3.2119)	grad_norm 1.3707 (1.5236/0.6278)	mem 34602MB
[2025-01-19 11:02:35 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][150/312]	eta 0:02:02 lr 0.001969	time 0.7294 (0.7553)	model_time 0.7289 (0.7463)	loss 3.2745 (3.1986)	grad_norm 0.8682 (1.4914/0.6205)	mem 34602MB
[2025-01-19 11:02:37 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.122 (9.122)	Loss 0.6519 (0.6519)	Acc@1 84.155 (84.155)	Acc@5 97.632 (97.632)	Mem 34604MB
[2025-01-19 11:02:41 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.239)	Loss 0.9558 (0.7913)	Acc@1 76.758 (81.308)	Acc@5 94.482 (95.856)	Mem 34604MB
[2025-01-19 11:02:41 internimage_b_1k_224] (main.py 575): INFO [Epoch:151] * Acc@1 81.192 Acc@5 95.897
[2025-01-19 11:02:41 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.2%
[2025-01-19 11:02:41 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:02:43 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][160/312]	eta 0:01:54 lr 0.001968	time 0.7182 (0.7551)	model_time 0.7178 (0.7467)	loss 3.3299 (3.2004)	grad_norm 1.3027 (1.5239/0.6624)	mem 34602MB
[2025-01-19 11:02:45 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:02:45 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.19%
[2025-01-19 11:02:47 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][0/312]	eta 0:10:13 lr 0.001979	time 1.9654 (1.9654)	model_time 0.7303 (0.7303)	loss 3.2221 (3.2221)	grad_norm 1.6407 (1.6407/0.0000)	mem 34604MB
[2025-01-19 11:02:50 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][170/312]	eta 0:01:47 lr 0.001967	time 0.7226 (0.7539)	model_time 0.7221 (0.7460)	loss 3.7344 (3.2009)	grad_norm 1.2476 (1.5656/0.6972)	mem 34602MB
[2025-01-19 11:02:55 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][10/312]	eta 0:04:18 lr 0.001978	time 0.8306 (0.8553)	model_time 0.8305 (0.7427)	loss 2.9711 (3.2667)	grad_norm 1.5483 (1.3518/0.3444)	mem 34604MB
[2025-01-19 11:02:58 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][180/312]	eta 0:01:39 lr 0.001967	time 0.7325 (0.7534)	model_time 0.7320 (0.7458)	loss 3.4139 (3.2043)	grad_norm 1.8671 (1.5684/0.6891)	mem 34602MB
[2025-01-19 11:03:02 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][20/312]	eta 0:03:58 lr 0.001977	time 0.7198 (0.8184)	model_time 0.7193 (0.7592)	loss 3.4293 (3.2427)	grad_norm 1.2165 (1.3980/0.4297)	mem 34604MB
[2025-01-19 11:03:05 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][190/312]	eta 0:01:31 lr 0.001966	time 0.7180 (0.7524)	model_time 0.7179 (0.7452)	loss 2.9624 (3.2041)	grad_norm 0.8115 (1.5546/0.6788)	mem 34602MB
[2025-01-19 11:03:10 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][30/312]	eta 0:03:46 lr 0.001977	time 0.7234 (0.8024)	model_time 0.7232 (0.7622)	loss 3.0535 (3.2240)	grad_norm 1.0246 (1.4067/0.3770)	mem 34604MB
[2025-01-19 11:03:12 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][200/312]	eta 0:01:24 lr 0.001965	time 0.7208 (0.7509)	model_time 0.7206 (0.7441)	loss 3.4532 (3.2031)	grad_norm 1.4161 (1.5332/0.6706)	mem 34602MB
[2025-01-19 11:03:17 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][40/312]	eta 0:03:33 lr 0.001976	time 0.7184 (0.7841)	model_time 0.7183 (0.7536)	loss 3.4915 (3.2008)	grad_norm 1.8936 (1.5261/0.4965)	mem 34604MB
[2025-01-19 11:03:20 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][210/312]	eta 0:01:16 lr 0.001965	time 0.7297 (0.7501)	model_time 0.7296 (0.7436)	loss 3.2357 (3.1952)	grad_norm 1.0979 (1.5217/0.6599)	mem 34602MB
[2025-01-19 11:03:25 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][50/312]	eta 0:03:22 lr 0.001975	time 0.7275 (0.7734)	model_time 0.7273 (0.7489)	loss 2.5507 (3.1368)	grad_norm 1.3721 (1.5876/0.5953)	mem 34604MB
[2025-01-19 11:03:27 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][220/312]	eta 0:01:09 lr 0.001964	time 0.8081 (0.7504)	model_time 0.8077 (0.7442)	loss 2.5702 (3.2009)	grad_norm 1.0422 (1.5094/0.6498)	mem 34602MB
[2025-01-19 11:03:32 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][60/312]	eta 0:03:12 lr 0.001975	time 0.7176 (0.7652)	model_time 0.7171 (0.7446)	loss 3.5312 (3.1050)	grad_norm 0.8825 (1.5124/0.5927)	mem 34604MB
[2025-01-19 11:03:35 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][230/312]	eta 0:01:01 lr 0.001963	time 0.7169 (0.7520)	model_time 0.7165 (0.7460)	loss 2.6270 (3.1924)	grad_norm 1.0042 (1.5004/0.6415)	mem 34602MB
[2025-01-19 11:03:39 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][70/312]	eta 0:03:04 lr 0.001974	time 0.7334 (0.7603)	model_time 0.7332 (0.7426)	loss 2.4220 (3.1091)	grad_norm 0.9089 (1.5007/0.5680)	mem 34604MB
[2025-01-19 11:03:42 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][240/312]	eta 0:00:54 lr 0.001963	time 0.8153 (0.7514)	model_time 0.8151 (0.7457)	loss 3.1208 (3.1985)	grad_norm 1.2257 (1.5019/0.6323)	mem 34602MB
[2025-01-19 11:03:47 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][80/312]	eta 0:02:55 lr 0.001973	time 0.7233 (0.7559)	model_time 0.7231 (0.7404)	loss 3.4525 (3.0866)	grad_norm 0.8677 (1.5787/0.6227)	mem 34604MB
[2025-01-19 11:03:50 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][250/312]	eta 0:00:46 lr 0.001962	time 0.7939 (0.7519)	model_time 0.7937 (0.7464)	loss 2.7259 (3.2034)	grad_norm 1.9435 (1.5114/0.6318)	mem 34602MB
[2025-01-19 11:03:54 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][90/312]	eta 0:02:47 lr 0.001973	time 0.7504 (0.7525)	model_time 0.7502 (0.7386)	loss 3.3428 (3.1179)	grad_norm 0.9663 (1.5808/0.6190)	mem 34604MB
[2025-01-19 11:03:57 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][260/312]	eta 0:00:39 lr 0.001961	time 0.7179 (0.7513)	model_time 0.7175 (0.7460)	loss 3.8821 (3.1951)	grad_norm 0.9887 (1.5163/0.6279)	mem 34602MB
[2025-01-19 11:04:01 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][100/312]	eta 0:02:39 lr 0.001972	time 0.7154 (0.7508)	model_time 0.7152 (0.7383)	loss 2.1081 (3.1023)	grad_norm 1.1959 (1.5508/0.6096)	mem 34604MB
[2025-01-19 11:04:05 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][270/312]	eta 0:00:31 lr 0.001961	time 0.7175 (0.7510)	model_time 0.7173 (0.7459)	loss 3.2788 (3.1986)	grad_norm 2.0914 (1.5170/0.6256)	mem 34602MB
[2025-01-19 11:04:08 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][110/312]	eta 0:02:31 lr 0.001971	time 0.7271 (0.7484)	model_time 0.7270 (0.7370)	loss 2.9317 (3.1167)	grad_norm 1.5707 (1.6333/0.7445)	mem 34604MB
[2025-01-19 11:04:12 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][280/312]	eta 0:00:24 lr 0.001960	time 0.7414 (0.7501)	model_time 0.7413 (0.7451)	loss 2.8081 (3.2014)	grad_norm 1.3784 (1.5171/0.6206)	mem 34602MB
[2025-01-19 11:04:16 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][120/312]	eta 0:02:23 lr 0.001971	time 0.7255 (0.7468)	model_time 0.7253 (0.7363)	loss 3.8089 (3.1248)	grad_norm 1.4497 (1.6637/0.7444)	mem 34604MB
[2025-01-19 11:04:20 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][290/312]	eta 0:00:16 lr 0.001959	time 0.8075 (0.7501)	model_time 0.8070 (0.7453)	loss 3.3170 (3.2061)	grad_norm 1.6477 (1.5123/0.6165)	mem 34602MB
[2025-01-19 11:04:23 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][130/312]	eta 0:02:15 lr 0.001970	time 0.8413 (0.7468)	model_time 0.8408 (0.7371)	loss 3.8764 (3.1496)	grad_norm 1.0688 (1.6559/0.7351)	mem 34604MB
[2025-01-19 11:04:27 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][300/312]	eta 0:00:08 lr 0.001959	time 0.7123 (0.7497)	model_time 0.7122 (0.7450)	loss 2.4125 (3.2072)	grad_norm 1.0205 (1.5044/0.6171)	mem 34602MB
[2025-01-19 11:04:31 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][140/312]	eta 0:02:08 lr 0.001969	time 0.7120 (0.7480)	model_time 0.7115 (0.7389)	loss 2.3618 (3.1367)	grad_norm 1.2353 (1.6231/0.7237)	mem 34604MB
[2025-01-19 11:04:34 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][310/312]	eta 0:00:01 lr 0.001958	time 0.7215 (0.7488)	model_time 0.7214 (0.7443)	loss 2.7011 (3.1990)	grad_norm 2.8193 (1.5104/0.6300)	mem 34602MB
[2025-01-19 11:04:35 internimage_b_1k_224] (main.py 519): INFO EPOCH 152 training takes 0:03:53
[2025-01-19 11:04:35 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_152.pth saving......
[2025-01-19 11:04:38 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_152.pth saved !!!
[2025-01-19 11:04:38 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][150/312]	eta 0:02:01 lr 0.001969	time 0.7565 (0.7490)	model_time 0.7564 (0.7405)	loss 2.9178 (3.1349)	grad_norm 0.7713 (1.5713/0.7265)	mem 34604MB
[2025-01-19 11:04:46 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.297 (7.297)	Loss 0.7883 (0.7883)	Acc@1 83.496 (83.496)	Acc@5 97.021 (97.021)	Mem 34602MB
[2025-01-19 11:04:46 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][160/312]	eta 0:01:53 lr 0.001968	time 0.7279 (0.7473)	model_time 0.7277 (0.7393)	loss 3.6663 (3.1387)	grad_norm 1.0633 (1.5508/0.7106)	mem 34604MB
[2025-01-19 11:04:49 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.938)	Loss 1.0873 (0.9235)	Acc@1 75.610 (80.682)	Acc@5 94.043 (95.435)	Mem 34602MB
[2025-01-19 11:04:49 internimage_b_1k_224] (main.py 575): INFO [Epoch:152] * Acc@1 80.616 Acc@5 95.499
[2025-01-19 11:04:49 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.6%
[2025-01-19 11:04:49 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 11:04:52 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 11:04:52 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.62%
[2025-01-19 11:04:53 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][170/312]	eta 0:01:45 lr 0.001967	time 0.7212 (0.7460)	model_time 0.7211 (0.7384)	loss 2.7424 (3.1492)	grad_norm 1.4911 (1.5620/0.6993)	mem 34604MB
[2025-01-19 11:04:59 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.442 (7.442)	Loss 0.6536 (0.6536)	Acc@1 84.106 (84.106)	Acc@5 97.583 (97.583)	Mem 34602MB
[2025-01-19 11:05:00 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][180/312]	eta 0:01:38 lr 0.001967	time 0.7085 (0.7447)	model_time 0.7083 (0.7376)	loss 3.3890 (3.1406)	grad_norm 1.3535 (1.5569/0.6863)	mem 34604MB
[2025-01-19 11:05:03 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.965)	Loss 0.9571 (0.7918)	Acc@1 76.636 (81.350)	Acc@5 94.312 (95.852)	Mem 34602MB
[2025-01-19 11:05:03 internimage_b_1k_224] (main.py 575): INFO [Epoch:152] * Acc@1 81.246 Acc@5 95.899
[2025-01-19 11:05:03 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.2%
[2025-01-19 11:05:03 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:05:07 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:05:07 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.25%
[2025-01-19 11:05:07 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][190/312]	eta 0:01:30 lr 0.001966	time 0.7529 (0.7440)	model_time 0.7527 (0.7372)	loss 2.4916 (3.1508)	grad_norm 0.9489 (1.5403/0.6738)	mem 34604MB
[2025-01-19 11:05:09 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][0/312]	eta 0:13:54 lr 0.001958	time 2.6744 (2.6744)	model_time 0.7541 (0.7541)	loss 3.0636 (3.0636)	grad_norm 1.2325 (1.2325/0.0000)	mem 34602MB
[2025-01-19 11:05:15 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][200/312]	eta 0:01:23 lr 0.001965	time 0.7256 (0.7431)	model_time 0.7254 (0.7366)	loss 2.9938 (3.1499)	grad_norm 1.9249 (1.5261/0.6653)	mem 34604MB
[2025-01-19 11:05:17 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][10/312]	eta 0:04:33 lr 0.001957	time 0.7140 (0.9060)	model_time 0.7139 (0.7312)	loss 3.2242 (3.3182)	grad_norm 1.8694 (2.0035/0.8306)	mem 34602MB
[2025-01-19 11:05:22 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][210/312]	eta 0:01:15 lr 0.001965	time 0.7376 (0.7424)	model_time 0.7375 (0.7362)	loss 3.2830 (3.1599)	grad_norm 0.9084 (1.5093/0.6559)	mem 34604MB
[2025-01-19 11:05:24 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][20/312]	eta 0:04:02 lr 0.001956	time 0.7513 (0.8313)	model_time 0.7509 (0.7395)	loss 2.5933 (3.3683)	grad_norm 1.3474 (1.8007/0.7438)	mem 34602MB
[2025-01-19 11:05:29 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][220/312]	eta 0:01:08 lr 0.001964	time 0.7193 (0.7419)	model_time 0.7189 (0.7360)	loss 3.3911 (3.1532)	grad_norm 2.3556 (1.5114/0.6488)	mem 34604MB
[2025-01-19 11:05:32 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][30/312]	eta 0:03:46 lr 0.001956	time 0.7225 (0.8039)	model_time 0.7223 (0.7416)	loss 2.2344 (3.3279)	grad_norm 0.9654 (1.6236/0.6940)	mem 34602MB
[2025-01-19 11:05:37 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][230/312]	eta 0:01:00 lr 0.001963	time 0.7179 (0.7412)	model_time 0.7177 (0.7355)	loss 3.2268 (3.1646)	grad_norm 1.1263 (1.5004/0.6393)	mem 34604MB
[2025-01-19 11:05:39 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][40/312]	eta 0:03:37 lr 0.001955	time 0.7173 (0.7987)	model_time 0.7168 (0.7515)	loss 3.1112 (3.3325)	grad_norm 1.0734 (1.5927/0.6560)	mem 34602MB
[2025-01-19 11:05:44 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][240/312]	eta 0:00:53 lr 0.001963	time 0.7276 (0.7405)	model_time 0.7275 (0.7351)	loss 3.9867 (3.1633)	grad_norm 2.3450 (1.5083/0.6368)	mem 34604MB
[2025-01-19 11:05:47 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][50/312]	eta 0:03:26 lr 0.001954	time 0.7411 (0.7870)	model_time 0.7407 (0.7490)	loss 2.9516 (3.3179)	grad_norm 1.2361 (1.6078/0.6767)	mem 34602MB
[2025-01-19 11:05:51 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][250/312]	eta 0:00:45 lr 0.001962	time 0.7137 (0.7401)	model_time 0.7136 (0.7349)	loss 2.4865 (3.1629)	grad_norm 1.0800 (1.4912/0.6322)	mem 34604MB
[2025-01-19 11:05:55 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][60/312]	eta 0:03:18 lr 0.001954	time 0.8067 (0.7861)	model_time 0.8066 (0.7543)	loss 3.4147 (3.3577)	grad_norm 1.6099 (1.5467/0.6452)	mem 34602MB
[2025-01-19 11:05:59 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][260/312]	eta 0:00:38 lr 0.001961	time 0.8101 (0.7412)	model_time 0.8100 (0.7361)	loss 3.4609 (3.1541)	grad_norm 1.1996 (1.4802/0.6248)	mem 34604MB
[2025-01-19 11:06:02 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][70/312]	eta 0:03:08 lr 0.001953	time 0.7162 (0.7803)	model_time 0.7160 (0.7529)	loss 3.5905 (3.3104)	grad_norm 0.8897 (1.4724/0.6298)	mem 34602MB
[2025-01-19 11:06:06 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][270/312]	eta 0:00:31 lr 0.001961	time 0.7174 (0.7420)	model_time 0.7172 (0.7372)	loss 3.4294 (3.1508)	grad_norm 0.8975 (1.4824/0.6380)	mem 34604MB
[2025-01-19 11:06:09 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][80/312]	eta 0:02:59 lr 0.001952	time 0.7190 (0.7756)	model_time 0.7186 (0.7516)	loss 2.5147 (3.2701)	grad_norm 0.8195 (1.4643/0.6086)	mem 34602MB
[2025-01-19 11:06:14 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][280/312]	eta 0:00:23 lr 0.001960	time 0.7235 (0.7416)	model_time 0.7234 (0.7369)	loss 2.5798 (3.1411)	grad_norm 2.1771 (1.5049/0.6451)	mem 34604MB
[2025-01-19 11:06:17 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][90/312]	eta 0:02:51 lr 0.001952	time 0.7235 (0.7717)	model_time 0.7231 (0.7502)	loss 3.7873 (3.2656)	grad_norm 0.7479 (1.4593/0.6096)	mem 34602MB
[2025-01-19 11:06:21 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][290/312]	eta 0:00:16 lr 0.001959	time 0.7179 (0.7410)	model_time 0.7174 (0.7364)	loss 2.7629 (3.1503)	grad_norm 1.3216 (1.5131/0.6443)	mem 34604MB
[2025-01-19 11:06:24 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][100/312]	eta 0:02:43 lr 0.001951	time 0.7178 (0.7691)	model_time 0.7177 (0.7498)	loss 3.0210 (3.2454)	grad_norm 1.0173 (1.4476/0.6037)	mem 34602MB
[2025-01-19 11:06:28 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][300/312]	eta 0:00:08 lr 0.001959	time 0.7163 (0.7404)	model_time 0.7162 (0.7360)	loss 2.7645 (3.1461)	grad_norm 1.4829 (1.5176/0.6425)	mem 34604MB
[2025-01-19 11:06:32 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][110/312]	eta 0:02:34 lr 0.001951	time 0.7225 (0.7669)	model_time 0.7221 (0.7493)	loss 3.4414 (3.2387)	grad_norm 2.0112 (1.4381/0.5835)	mem 34602MB
[2025-01-19 11:06:35 internimage_b_1k_224] (main.py 510): INFO Train: [152/300][310/312]	eta 0:00:01 lr 0.001958	time 0.7136 (0.7396)	model_time 0.7135 (0.7353)	loss 2.9043 (3.1478)	grad_norm 1.8607 (1.5276/0.6430)	mem 34604MB
[2025-01-19 11:06:36 internimage_b_1k_224] (main.py 519): INFO EPOCH 152 training takes 0:03:50
[2025-01-19 11:06:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_152.pth saving......
[2025-01-19 11:06:39 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][120/312]	eta 0:02:26 lr 0.001950	time 0.7195 (0.7645)	model_time 0.7193 (0.7482)	loss 3.2418 (3.2458)	grad_norm 1.8380 (1.5008/0.6565)	mem 34602MB
[2025-01-19 11:06:39 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_152.pth saved !!!
[2025-01-19 11:06:46 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][130/312]	eta 0:02:18 lr 0.001949	time 0.7390 (0.7617)	model_time 0.7388 (0.7467)	loss 3.8107 (3.2471)	grad_norm 0.9134 (1.5015/0.6661)	mem 34602MB
[2025-01-19 11:06:47 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.350 (7.350)	Loss 0.7939 (0.7939)	Acc@1 83.496 (83.496)	Acc@5 97.241 (97.241)	Mem 34604MB
[2025-01-19 11:06:50 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.938)	Loss 1.1000 (0.9307)	Acc@1 76.440 (80.715)	Acc@5 93.945 (95.634)	Mem 34604MB
[2025-01-19 11:06:50 internimage_b_1k_224] (main.py 575): INFO [Epoch:152] * Acc@1 80.656 Acc@5 95.655
[2025-01-19 11:06:50 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.7%
[2025-01-19 11:06:50 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 11:06:53 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 11:06:53 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.66%
[2025-01-19 11:06:54 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][140/312]	eta 0:02:10 lr 0.001949	time 0.7176 (0.7604)	model_time 0.7172 (0.7464)	loss 3.5335 (3.2577)	grad_norm 1.6516 (1.5071/0.6520)	mem 34602MB
[2025-01-19 11:07:00 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.247 (7.247)	Loss 0.6525 (0.6525)	Acc@1 84.302 (84.302)	Acc@5 97.632 (97.632)	Mem 34604MB
[2025-01-19 11:07:01 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][150/312]	eta 0:02:03 lr 0.001948	time 0.7191 (0.7600)	model_time 0.7187 (0.7469)	loss 3.8760 (3.2532)	grad_norm 2.8880 (1.5444/0.6768)	mem 34602MB
[2025-01-19 11:07:04 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.942)	Loss 0.9550 (0.7912)	Acc@1 76.904 (81.365)	Acc@5 94.482 (95.865)	Mem 34604MB
[2025-01-19 11:07:04 internimage_b_1k_224] (main.py 575): INFO [Epoch:152] * Acc@1 81.254 Acc@5 95.911
[2025-01-19 11:07:04 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.3%
[2025-01-19 11:07:04 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:07:08 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:07:08 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.25%
[2025-01-19 11:07:09 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][160/312]	eta 0:01:55 lr 0.001947	time 0.8054 (0.7612)	model_time 0.8053 (0.7489)	loss 3.7408 (3.2462)	grad_norm 3.3341 (1.6153/0.7467)	mem 34602MB
[2025-01-19 11:07:10 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][0/312]	eta 0:13:15 lr 0.001958	time 2.5504 (2.5504)	model_time 0.7491 (0.7491)	loss 3.1686 (3.1686)	grad_norm 0.9293 (0.9293/0.0000)	mem 34604MB
[2025-01-19 11:07:17 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][170/312]	eta 0:01:47 lr 0.001947	time 0.7184 (0.7600)	model_time 0.7182 (0.7483)	loss 3.3591 (3.2549)	grad_norm 1.4327 (1.5981/0.7365)	mem 34602MB
[2025-01-19 11:07:17 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][10/312]	eta 0:04:29 lr 0.001957	time 0.7165 (0.8939)	model_time 0.7163 (0.7298)	loss 3.1062 (3.1402)	grad_norm 1.6926 (1.2708/0.2863)	mem 34604MB
[2025-01-19 11:07:24 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][180/312]	eta 0:01:40 lr 0.001946	time 0.8046 (0.7608)	model_time 0.8045 (0.7498)	loss 3.0069 (3.2520)	grad_norm 0.7494 (1.5899/0.7238)	mem 34602MB
[2025-01-19 11:07:25 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][20/312]	eta 0:03:57 lr 0.001956	time 0.7187 (0.8117)	model_time 0.7183 (0.7256)	loss 2.8156 (3.0230)	grad_norm 0.9716 (1.2838/0.3591)	mem 34604MB
[2025-01-19 11:07:32 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][190/312]	eta 0:01:32 lr 0.001945	time 0.7167 (0.7601)	model_time 0.7162 (0.7496)	loss 3.6494 (3.2350)	grad_norm 0.9203 (1.5893/0.7156)	mem 34602MB
[2025-01-19 11:07:32 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][30/312]	eta 0:03:41 lr 0.001956	time 0.7232 (0.7870)	model_time 0.7231 (0.7286)	loss 2.2401 (3.0717)	grad_norm 1.2239 (1.3164/0.3829)	mem 34604MB
[2025-01-19 11:07:39 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][200/312]	eta 0:01:25 lr 0.001945	time 0.7550 (0.7591)	model_time 0.7545 (0.7491)	loss 4.0701 (3.2371)	grad_norm 1.7449 (1.5785/0.7048)	mem 34602MB
[2025-01-19 11:07:39 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][40/312]	eta 0:03:30 lr 0.001955	time 0.7228 (0.7726)	model_time 0.7227 (0.7283)	loss 2.5905 (3.0868)	grad_norm 1.7434 (1.4007/0.4243)	mem 34604MB
[2025-01-19 11:07:47 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][210/312]	eta 0:01:17 lr 0.001944	time 0.7200 (0.7582)	model_time 0.7198 (0.7487)	loss 2.9973 (3.2343)	grad_norm 1.4954 (1.5597/0.6949)	mem 34602MB
[2025-01-19 11:07:47 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][50/312]	eta 0:03:20 lr 0.001954	time 0.7184 (0.7650)	model_time 0.7180 (0.7293)	loss 3.3596 (3.1113)	grad_norm 0.8005 (1.3738/0.4281)	mem 34604MB
[2025-01-19 11:07:54 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][60/312]	eta 0:03:11 lr 0.001954	time 0.8060 (0.7606)	model_time 0.8058 (0.7307)	loss 3.6191 (3.1290)	grad_norm 2.2358 (1.3845/0.4409)	mem 34604MB
[2025-01-19 11:07:54 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][220/312]	eta 0:01:09 lr 0.001943	time 0.7177 (0.7582)	model_time 0.7173 (0.7491)	loss 2.9224 (3.2316)	grad_norm 1.9211 (1.5581/0.6847)	mem 34602MB
[2025-01-19 11:08:02 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][70/312]	eta 0:03:04 lr 0.001953	time 0.8067 (0.7628)	model_time 0.8066 (0.7371)	loss 3.1942 (3.1061)	grad_norm 1.1541 (1.4645/0.5840)	mem 34604MB
[2025-01-19 11:08:02 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][230/312]	eta 0:01:02 lr 0.001943	time 0.7218 (0.7583)	model_time 0.7214 (0.7496)	loss 3.3034 (3.2296)	grad_norm 3.0182 (1.5752/0.6970)	mem 34602MB
[2025-01-19 11:08:09 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][240/312]	eta 0:00:54 lr 0.001942	time 0.7463 (0.7571)	model_time 0.7459 (0.7487)	loss 2.7204 (3.2198)	grad_norm 1.2815 (1.5724/0.6880)	mem 34602MB
[2025-01-19 11:08:10 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][80/312]	eta 0:02:57 lr 0.001952	time 0.7167 (0.7644)	model_time 0.7166 (0.7418)	loss 3.9593 (3.1329)	grad_norm 1.6770 (1.4989/0.6221)	mem 34604MB
[2025-01-19 11:08:16 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][250/312]	eta 0:00:46 lr 0.001941	time 0.7251 (0.7562)	model_time 0.7247 (0.7482)	loss 3.3808 (3.2196)	grad_norm 2.4265 (1.5682/0.6800)	mem 34602MB
[2025-01-19 11:08:17 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][90/312]	eta 0:02:48 lr 0.001952	time 0.7560 (0.7609)	model_time 0.7555 (0.7408)	loss 3.5802 (3.1343)	grad_norm 1.3749 (1.4692/0.6062)	mem 34604MB
[2025-01-19 11:08:24 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][260/312]	eta 0:00:39 lr 0.001941	time 0.9091 (0.7557)	model_time 0.9087 (0.7479)	loss 2.3785 (3.2221)	grad_norm 1.9737 (1.5841/0.6798)	mem 34602MB
[2025-01-19 11:08:24 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][100/312]	eta 0:02:40 lr 0.001951	time 0.7201 (0.7572)	model_time 0.7199 (0.7390)	loss 4.0624 (3.1534)	grad_norm 2.2088 (1.4735/0.6012)	mem 34604MB
[2025-01-19 11:08:31 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][270/312]	eta 0:00:31 lr 0.001940	time 0.7184 (0.7553)	model_time 0.7180 (0.7478)	loss 3.8004 (3.2261)	grad_norm 3.3204 (1.5928/0.6930)	mem 34602MB
[2025-01-19 11:08:31 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][110/312]	eta 0:02:32 lr 0.001951	time 0.7297 (0.7544)	model_time 0.7292 (0.7378)	loss 3.4992 (3.1727)	grad_norm 1.0921 (1.4712/0.5964)	mem 34604MB
[2025-01-19 11:08:39 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][120/312]	eta 0:02:24 lr 0.001950	time 0.7225 (0.7523)	model_time 0.7221 (0.7370)	loss 3.5018 (3.2051)	grad_norm 1.1988 (1.4671/0.5790)	mem 34604MB
[2025-01-19 11:08:39 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][280/312]	eta 0:00:24 lr 0.001939	time 0.8056 (0.7558)	model_time 0.8054 (0.7485)	loss 3.5874 (3.2323)	grad_norm 2.0749 (1.5861/0.6858)	mem 34602MB
[2025-01-19 11:08:46 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][130/312]	eta 0:02:16 lr 0.001949	time 0.7219 (0.7502)	model_time 0.7217 (0.7361)	loss 3.9201 (3.2121)	grad_norm 2.9797 (1.5445/0.6554)	mem 34604MB
[2025-01-19 11:08:46 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][290/312]	eta 0:00:16 lr 0.001939	time 0.7169 (0.7553)	model_time 0.7168 (0.7483)	loss 3.9161 (3.2293)	grad_norm 1.3413 (1.5965/0.6867)	mem 34602MB
[2025-01-19 11:08:53 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][140/312]	eta 0:02:08 lr 0.001949	time 0.7160 (0.7484)	model_time 0.7156 (0.7353)	loss 2.6651 (3.2168)	grad_norm 0.7057 (1.5706/0.6719)	mem 34604MB
[2025-01-19 11:08:54 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][300/312]	eta 0:00:09 lr 0.001938	time 0.7986 (0.7560)	model_time 0.7985 (0.7492)	loss 3.7511 (3.2314)	grad_norm 0.8899 (1.6005/0.6811)	mem 34602MB
[2025-01-19 11:09:01 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][150/312]	eta 0:02:01 lr 0.001948	time 0.7581 (0.7477)	model_time 0.7579 (0.7354)	loss 2.9403 (3.2115)	grad_norm 1.1862 (1.5568/0.6739)	mem 34604MB
[2025-01-19 11:09:02 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][310/312]	eta 0:00:01 lr 0.001937	time 0.7198 (0.7555)	model_time 0.7197 (0.7490)	loss 4.0864 (3.2332)	grad_norm 1.0236 (1.5794/0.6644)	mem 34602MB
[2025-01-19 11:09:02 internimage_b_1k_224] (main.py 519): INFO EPOCH 153 training takes 0:03:55
[2025-01-19 11:09:02 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_153.pth saving......
[2025-01-19 11:09:05 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_153.pth saved !!!
[2025-01-19 11:09:08 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][160/312]	eta 0:01:53 lr 0.001947	time 0.7135 (0.7462)	model_time 0.7131 (0.7346)	loss 3.6083 (3.2090)	grad_norm 1.0963 (1.5493/0.6705)	mem 34604MB
[2025-01-19 11:09:13 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.489 (7.489)	Loss 0.7533 (0.7533)	Acc@1 83.472 (83.472)	Acc@5 97.021 (97.021)	Mem 34602MB
[2025-01-19 11:09:15 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][170/312]	eta 0:01:45 lr 0.001947	time 0.7168 (0.7451)	model_time 0.7166 (0.7342)	loss 3.3282 (3.2077)	grad_norm 0.8771 (1.5437/0.6681)	mem 34604MB
[2025-01-19 11:09:16 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.973)	Loss 1.0443 (0.8845)	Acc@1 76.685 (80.808)	Acc@5 94.092 (95.648)	Mem 34602MB
[2025-01-19 11:09:16 internimage_b_1k_224] (main.py 575): INFO [Epoch:153] * Acc@1 80.718 Acc@5 95.681
[2025-01-19 11:09:16 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.7%
[2025-01-19 11:09:17 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 11:09:20 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 11:09:20 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.72%
[2025-01-19 11:09:22 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][180/312]	eta 0:01:38 lr 0.001946	time 0.8001 (0.7446)	model_time 0.7999 (0.7343)	loss 2.2331 (3.2080)	grad_norm 1.0947 (1.5449/0.6710)	mem 34604MB
[2025-01-19 11:09:27 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.556 (7.556)	Loss 0.6542 (0.6542)	Acc@1 84.106 (84.106)	Acc@5 97.559 (97.559)	Mem 34602MB
[2025-01-19 11:09:30 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][190/312]	eta 0:01:31 lr 0.001945	time 0.8538 (0.7463)	model_time 0.8533 (0.7365)	loss 3.8602 (3.2167)	grad_norm 1.6935 (1.5374/0.6616)	mem 34604MB
[2025-01-19 11:09:30 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.963)	Loss 0.9566 (0.7919)	Acc@1 76.733 (81.390)	Acc@5 94.336 (95.878)	Mem 34602MB
[2025-01-19 11:09:31 internimage_b_1k_224] (main.py 575): INFO [Epoch:153] * Acc@1 81.290 Acc@5 95.923
[2025-01-19 11:09:31 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.3%
[2025-01-19 11:09:31 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:09:35 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:09:35 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.29%
[2025-01-19 11:09:37 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][0/312]	eta 0:10:30 lr 0.001937	time 2.0210 (2.0210)	model_time 0.7328 (0.7328)	loss 3.4202 (3.4202)	grad_norm 0.8925 (0.8925/0.0000)	mem 34602MB
[2025-01-19 11:09:38 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][200/312]	eta 0:01:23 lr 0.001945	time 0.8181 (0.7483)	model_time 0.8179 (0.7390)	loss 3.5177 (3.2218)	grad_norm 0.9739 (1.5374/0.6545)	mem 34604MB
[2025-01-19 11:09:44 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][10/312]	eta 0:04:19 lr 0.001936	time 0.7167 (0.8603)	model_time 0.7165 (0.7428)	loss 4.0439 (3.2214)	grad_norm 2.5017 (1.7724/0.5938)	mem 34602MB
[2025-01-19 11:09:45 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][210/312]	eta 0:01:16 lr 0.001944	time 0.7332 (0.7473)	model_time 0.7328 (0.7385)	loss 2.8083 (3.2027)	grad_norm 1.8873 (1.5382/0.6425)	mem 34604MB
[2025-01-19 11:09:52 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][20/312]	eta 0:03:53 lr 0.001936	time 0.7208 (0.7994)	model_time 0.7207 (0.7377)	loss 4.0704 (3.2229)	grad_norm 4.2794 (1.7883/0.7590)	mem 34602MB
[2025-01-19 11:09:53 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][220/312]	eta 0:01:08 lr 0.001943	time 0.7223 (0.7463)	model_time 0.7219 (0.7378)	loss 3.7010 (3.1911)	grad_norm 3.3830 (1.5616/0.6591)	mem 34604MB
[2025-01-19 11:09:59 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][30/312]	eta 0:03:40 lr 0.001935	time 0.7227 (0.7833)	model_time 0.7225 (0.7414)	loss 2.3306 (3.1398)	grad_norm 2.5817 (1.9374/0.9709)	mem 34602MB
[2025-01-19 11:10:00 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][230/312]	eta 0:01:01 lr 0.001943	time 0.7252 (0.7452)	model_time 0.7250 (0.7371)	loss 3.2926 (3.1920)	grad_norm 1.0994 (1.5663/0.6533)	mem 34604MB
[2025-01-19 11:10:07 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][40/312]	eta 0:03:30 lr 0.001934	time 0.7288 (0.7754)	model_time 0.7284 (0.7436)	loss 2.5917 (3.1435)	grad_norm 2.2353 (1.8316/0.9126)	mem 34602MB
[2025-01-19 11:10:07 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][240/312]	eta 0:00:53 lr 0.001942	time 0.7326 (0.7444)	model_time 0.7322 (0.7366)	loss 3.1939 (3.1928)	grad_norm 1.6304 (1.5974/0.6690)	mem 34604MB
[2025-01-19 11:10:14 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][50/312]	eta 0:03:20 lr 0.001934	time 0.7185 (0.7651)	model_time 0.7183 (0.7395)	loss 2.3201 (3.0661)	grad_norm 1.9373 (1.8157/0.8461)	mem 34602MB
[2025-01-19 11:10:14 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][250/312]	eta 0:00:46 lr 0.001941	time 0.7230 (0.7438)	model_time 0.7226 (0.7362)	loss 3.2956 (3.1931)	grad_norm 0.8897 (1.5915/0.6700)	mem 34604MB
[2025-01-19 11:10:21 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][60/312]	eta 0:03:11 lr 0.001933	time 0.7521 (0.7601)	model_time 0.7520 (0.7386)	loss 3.3338 (3.0883)	grad_norm 1.9775 (1.7713/0.8057)	mem 34602MB
[2025-01-19 11:10:22 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][260/312]	eta 0:00:38 lr 0.001941	time 0.7205 (0.7431)	model_time 0.7204 (0.7358)	loss 3.2067 (3.1979)	grad_norm 1.0027 (1.5977/0.6654)	mem 34604MB
[2025-01-19 11:10:29 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][70/312]	eta 0:03:03 lr 0.001932	time 0.8067 (0.7571)	model_time 0.8065 (0.7387)	loss 3.7533 (3.0960)	grad_norm 1.1518 (1.6931/0.7854)	mem 34602MB
[2025-01-19 11:10:29 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][270/312]	eta 0:00:31 lr 0.001940	time 0.7221 (0.7427)	model_time 0.7219 (0.7357)	loss 3.6115 (3.1998)	grad_norm 1.3589 (1.6134/0.6681)	mem 34604MB
[2025-01-19 11:10:36 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][80/312]	eta 0:02:55 lr 0.001932	time 0.7207 (0.7557)	model_time 0.7203 (0.7395)	loss 2.9861 (3.1265)	grad_norm 1.8018 (1.6656/0.7500)	mem 34602MB
[2025-01-19 11:10:36 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][280/312]	eta 0:00:23 lr 0.001939	time 0.7278 (0.7420)	model_time 0.7274 (0.7352)	loss 2.2832 (3.1888)	grad_norm 1.3664 (1.6039/0.6619)	mem 34604MB
[2025-01-19 11:10:43 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][290/312]	eta 0:00:16 lr 0.001939	time 0.7231 (0.7415)	model_time 0.7227 (0.7350)	loss 3.7381 (3.1957)	grad_norm 2.0599 (1.5937/0.6565)	mem 34604MB
[2025-01-19 11:10:43 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][90/312]	eta 0:02:47 lr 0.001931	time 0.7195 (0.7550)	model_time 0.7193 (0.7405)	loss 3.9571 (3.1333)	grad_norm 1.2771 (1.6218/0.7336)	mem 34602MB
[2025-01-19 11:10:51 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][300/312]	eta 0:00:08 lr 0.001938	time 0.7915 (0.7413)	model_time 0.7914 (0.7349)	loss 2.5828 (3.1951)	grad_norm 0.9203 (1.5817/0.6535)	mem 34604MB
[2025-01-19 11:10:51 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][100/312]	eta 0:02:39 lr 0.001930	time 0.8034 (0.7544)	model_time 0.8032 (0.7413)	loss 3.3817 (3.1281)	grad_norm 3.6320 (1.6114/0.7383)	mem 34602MB
[2025-01-19 11:10:58 internimage_b_1k_224] (main.py 510): INFO Train: [153/300][310/312]	eta 0:00:01 lr 0.001937	time 0.7118 (0.7417)	model_time 0.7117 (0.7355)	loss 3.1702 (3.1936)	grad_norm 1.2674 (1.5837/0.6596)	mem 34604MB
[2025-01-19 11:10:59 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][110/312]	eta 0:02:32 lr 0.001930	time 0.8091 (0.7548)	model_time 0.8087 (0.7428)	loss 3.8570 (3.1700)	grad_norm 2.0277 (1.6425/0.7348)	mem 34602MB
[2025-01-19 11:10:59 internimage_b_1k_224] (main.py 519): INFO EPOCH 153 training takes 0:03:51
[2025-01-19 11:10:59 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_153.pth saving......
[2025-01-19 11:11:02 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_153.pth saved !!!
[2025-01-19 11:11:06 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][120/312]	eta 0:02:25 lr 0.001929	time 1.0306 (0.7558)	model_time 1.0301 (0.7448)	loss 3.5231 (3.1744)	grad_norm 1.5139 (1.6659/0.7273)	mem 34602MB
[2025-01-19 11:11:10 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.208 (7.208)	Loss 0.7701 (0.7701)	Acc@1 83.569 (83.569)	Acc@5 97.290 (97.290)	Mem 34604MB
[2025-01-19 11:11:13 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.930)	Loss 1.0675 (0.9202)	Acc@1 76.245 (80.775)	Acc@5 94.092 (95.663)	Mem 34604MB
[2025-01-19 11:11:13 internimage_b_1k_224] (main.py 575): INFO [Epoch:153] * Acc@1 80.664 Acc@5 95.665
[2025-01-19 11:11:13 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.7%
[2025-01-19 11:11:13 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 11:11:14 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][130/312]	eta 0:02:17 lr 0.001928	time 0.7207 (0.7544)	model_time 0.7202 (0.7442)	loss 2.6989 (3.1613)	grad_norm 1.7890 (1.6601/0.7203)	mem 34602MB
[2025-01-19 11:11:16 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 11:11:16 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.66%
[2025-01-19 11:11:21 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][140/312]	eta 0:02:09 lr 0.001928	time 0.7245 (0.7533)	model_time 0.7243 (0.7438)	loss 3.7173 (3.1750)	grad_norm 0.7636 (1.6503/0.7115)	mem 34602MB
[2025-01-19 11:11:23 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.237 (7.237)	Loss 0.6532 (0.6532)	Acc@1 84.302 (84.302)	Acc@5 97.632 (97.632)	Mem 34604MB
[2025-01-19 11:11:26 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.920)	Loss 0.9543 (0.7912)	Acc@1 77.002 (81.408)	Acc@5 94.507 (95.887)	Mem 34604MB
[2025-01-19 11:11:27 internimage_b_1k_224] (main.py 575): INFO [Epoch:153] * Acc@1 81.294 Acc@5 95.933
[2025-01-19 11:11:27 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.3%
[2025-01-19 11:11:27 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:11:28 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][150/312]	eta 0:02:01 lr 0.001927	time 0.7171 (0.7525)	model_time 0.7167 (0.7436)	loss 2.9798 (3.1490)	grad_norm 2.1139 (1.6417/0.7003)	mem 34602MB
[2025-01-19 11:11:31 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:11:31 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.29%
[2025-01-19 11:11:33 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][0/312]	eta 0:10:15 lr 0.001937	time 1.9714 (1.9714)	model_time 0.7373 (0.7373)	loss 3.5028 (3.5028)	grad_norm 0.9499 (0.9499/0.0000)	mem 34604MB
[2025-01-19 11:11:36 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][160/312]	eta 0:01:54 lr 0.001926	time 0.7183 (0.7522)	model_time 0.7179 (0.7438)	loss 3.2075 (3.1556)	grad_norm 1.0834 (1.6256/0.6936)	mem 34602MB
[2025-01-19 11:11:40 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][10/312]	eta 0:04:25 lr 0.001936	time 0.7161 (0.8798)	model_time 0.7157 (0.7673)	loss 3.4784 (3.0021)	grad_norm 0.7815 (1.3855/0.4396)	mem 34604MB
[2025-01-19 11:11:43 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][170/312]	eta 0:01:46 lr 0.001926	time 0.7199 (0.7507)	model_time 0.7198 (0.7428)	loss 2.2657 (3.1742)	grad_norm 0.7434 (1.6309/0.7118)	mem 34602MB
[2025-01-19 11:11:48 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][20/312]	eta 0:03:56 lr 0.001936	time 0.7496 (0.8084)	model_time 0.7495 (0.7493)	loss 3.5746 (3.0512)	grad_norm 1.6005 (1.5650/0.5398)	mem 34604MB
[2025-01-19 11:11:50 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][180/312]	eta 0:01:38 lr 0.001925	time 0.7233 (0.7499)	model_time 0.7232 (0.7424)	loss 2.9938 (3.1795)	grad_norm 1.6216 (1.6432/0.7246)	mem 34602MB
[2025-01-19 11:11:55 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][30/312]	eta 0:03:40 lr 0.001935	time 0.7310 (0.7829)	model_time 0.7309 (0.7428)	loss 3.8231 (3.1259)	grad_norm 1.1073 (1.5333/0.5470)	mem 34604MB
[2025-01-19 11:11:58 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][190/312]	eta 0:01:31 lr 0.001924	time 0.7217 (0.7484)	model_time 0.7212 (0.7413)	loss 3.7546 (3.1977)	grad_norm 1.7597 (1.6534/0.7105)	mem 34602MB
[2025-01-19 11:12:02 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][40/312]	eta 0:03:29 lr 0.001934	time 0.7314 (0.7700)	model_time 0.7312 (0.7396)	loss 3.1409 (3.0752)	grad_norm 1.9811 (1.4704/0.5473)	mem 34604MB
[2025-01-19 11:12:05 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][200/312]	eta 0:01:23 lr 0.001924	time 0.7212 (0.7489)	model_time 0.7210 (0.7422)	loss 3.3377 (3.2049)	grad_norm 1.8601 (1.6554/0.7009)	mem 34602MB
[2025-01-19 11:12:09 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][50/312]	eta 0:03:19 lr 0.001934	time 0.7331 (0.7624)	model_time 0.7329 (0.7379)	loss 2.3621 (3.0756)	grad_norm 2.1401 (1.4350/0.5281)	mem 34604MB
[2025-01-19 11:12:13 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][210/312]	eta 0:01:16 lr 0.001923	time 0.7183 (0.7489)	model_time 0.7182 (0.7425)	loss 3.6019 (3.1972)	grad_norm 2.0818 (1.6715/0.7172)	mem 34602MB
[2025-01-19 11:12:17 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][60/312]	eta 0:03:10 lr 0.001933	time 0.7223 (0.7568)	model_time 0.7218 (0.7362)	loss 3.7224 (3.1106)	grad_norm 0.8805 (1.4879/0.5952)	mem 34604MB
[2025-01-19 11:12:20 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][220/312]	eta 0:01:08 lr 0.001922	time 0.8076 (0.7490)	model_time 0.8071 (0.7428)	loss 4.1851 (3.1917)	grad_norm 1.1217 (1.6434/0.7158)	mem 34602MB
[2025-01-19 11:12:24 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][70/312]	eta 0:03:02 lr 0.001932	time 0.7184 (0.7528)	model_time 0.7179 (0.7351)	loss 3.7672 (3.1039)	grad_norm 2.6329 (1.5348/0.6210)	mem 34604MB
[2025-01-19 11:12:28 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][230/312]	eta 0:01:01 lr 0.001922	time 0.8055 (0.7504)	model_time 0.8054 (0.7444)	loss 2.5345 (3.1879)	grad_norm 1.1057 (1.6262/0.7071)	mem 34602MB
[2025-01-19 11:12:31 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][80/312]	eta 0:02:53 lr 0.001932	time 0.7119 (0.7500)	model_time 0.7115 (0.7344)	loss 3.7057 (3.1243)	grad_norm 1.5735 (1.5591/0.6369)	mem 34604MB
[2025-01-19 11:12:36 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][240/312]	eta 0:00:54 lr 0.001921	time 0.8402 (0.7505)	model_time 0.8397 (0.7448)	loss 3.9640 (3.2050)	grad_norm 1.1346 (1.6305/0.7004)	mem 34602MB
[2025-01-19 11:12:39 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][90/312]	eta 0:02:45 lr 0.001931	time 0.7215 (0.7477)	model_time 0.7213 (0.7338)	loss 3.8531 (3.1153)	grad_norm 1.7425 (1.5688/0.6347)	mem 34604MB
[2025-01-19 11:12:43 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][250/312]	eta 0:00:46 lr 0.001920	time 0.7173 (0.7501)	model_time 0.7171 (0.7446)	loss 2.4836 (3.1968)	grad_norm 2.3797 (1.6314/0.6913)	mem 34602MB
[2025-01-19 11:12:46 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][100/312]	eta 0:02:38 lr 0.001930	time 0.7353 (0.7463)	model_time 0.7349 (0.7338)	loss 3.6182 (3.1251)	grad_norm 1.0378 (1.5784/0.6406)	mem 34604MB
[2025-01-19 11:12:50 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][260/312]	eta 0:00:38 lr 0.001920	time 0.7208 (0.7494)	model_time 0.7203 (0.7441)	loss 3.1964 (3.1895)	grad_norm 1.4936 (1.6268/0.6862)	mem 34602MB
[2025-01-19 11:12:53 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][110/312]	eta 0:02:30 lr 0.001930	time 0.8271 (0.7459)	model_time 0.8266 (0.7344)	loss 2.4742 (3.1115)	grad_norm 1.2473 (1.6228/0.6773)	mem 34604MB
[2025-01-19 11:12:58 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][270/312]	eta 0:00:31 lr 0.001919	time 0.7328 (0.7492)	model_time 0.7326 (0.7440)	loss 3.0168 (3.1785)	grad_norm 0.9213 (1.6158/0.6808)	mem 34602MB
[2025-01-19 11:13:01 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][120/312]	eta 0:02:23 lr 0.001929	time 0.8042 (0.7482)	model_time 0.8038 (0.7377)	loss 3.8789 (3.1185)	grad_norm 1.8586 (1.6342/0.7155)	mem 34604MB
[2025-01-19 11:13:05 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][280/312]	eta 0:00:23 lr 0.001918	time 0.7229 (0.7489)	model_time 0.7227 (0.7439)	loss 2.5814 (3.1763)	grad_norm 1.3076 (1.6088/0.6718)	mem 34602MB
[2025-01-19 11:13:09 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][130/312]	eta 0:02:16 lr 0.001928	time 0.7128 (0.7511)	model_time 0.7124 (0.7413)	loss 3.6384 (3.1429)	grad_norm 0.9535 (1.5918/0.7077)	mem 34604MB
[2025-01-19 11:13:13 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][290/312]	eta 0:00:16 lr 0.001918	time 0.7463 (0.7483)	model_time 0.7459 (0.7435)	loss 3.1692 (3.1867)	grad_norm 1.0140 (1.6169/0.6692)	mem 34602MB
[2025-01-19 11:13:16 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][140/312]	eta 0:02:08 lr 0.001928	time 0.7337 (0.7497)	model_time 0.7335 (0.7406)	loss 3.3257 (3.1427)	grad_norm 1.8532 (1.5965/0.7023)	mem 34604MB
[2025-01-19 11:13:20 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][300/312]	eta 0:00:08 lr 0.001917	time 0.7127 (0.7477)	model_time 0.7126 (0.7431)	loss 2.3658 (3.1849)	grad_norm 2.3178 (1.6113/0.6638)	mem 34602MB
[2025-01-19 11:13:23 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][150/312]	eta 0:02:01 lr 0.001927	time 0.7097 (0.7481)	model_time 0.7096 (0.7395)	loss 3.2356 (3.1544)	grad_norm 0.7892 (1.6025/0.6984)	mem 34604MB
[2025-01-19 11:13:27 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][310/312]	eta 0:00:01 lr 0.001917	time 0.7132 (0.7467)	model_time 0.7131 (0.7422)	loss 3.0462 (3.1836)	grad_norm 1.1911 (1.5979/0.6586)	mem 34602MB
[2025-01-19 11:13:28 internimage_b_1k_224] (main.py 519): INFO EPOCH 154 training takes 0:03:52
[2025-01-19 11:13:28 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_154.pth saving......
[2025-01-19 11:13:31 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][160/312]	eta 0:01:53 lr 0.001926	time 0.7202 (0.7467)	model_time 0.7198 (0.7387)	loss 2.5648 (3.1592)	grad_norm 1.2805 (1.6086/0.6947)	mem 34604MB
[2025-01-19 11:13:31 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_154.pth saved !!!
[2025-01-19 11:13:38 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][170/312]	eta 0:01:45 lr 0.001926	time 0.7197 (0.7454)	model_time 0.7195 (0.7378)	loss 1.9611 (3.1493)	grad_norm 1.2176 (1.6304/0.7123)	mem 34604MB
[2025-01-19 11:13:38 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.471 (7.471)	Loss 0.7887 (0.7887)	Acc@1 84.033 (84.033)	Acc@5 97.070 (97.070)	Mem 34602MB
[2025-01-19 11:13:41 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.954)	Loss 1.0726 (0.9256)	Acc@1 76.147 (80.617)	Acc@5 94.092 (95.603)	Mem 34602MB
[2025-01-19 11:13:42 internimage_b_1k_224] (main.py 575): INFO [Epoch:154] * Acc@1 80.546 Acc@5 95.665
[2025-01-19 11:13:42 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.5%
[2025-01-19 11:13:42 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.72%
[2025-01-19 11:13:45 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][180/312]	eta 0:01:38 lr 0.001925	time 0.7204 (0.7442)	model_time 0.7200 (0.7370)	loss 3.2946 (3.1629)	grad_norm 1.2180 (1.6377/0.7053)	mem 34604MB
[2025-01-19 11:13:51 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.299 (9.299)	Loss 0.6550 (0.6550)	Acc@1 84.106 (84.106)	Acc@5 97.534 (97.534)	Mem 34602MB
[2025-01-19 11:13:52 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][190/312]	eta 0:01:30 lr 0.001924	time 0.7225 (0.7431)	model_time 0.7224 (0.7363)	loss 2.8216 (3.1684)	grad_norm 0.8422 (1.6385/0.7004)	mem 34604MB
[2025-01-19 11:13:56 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.259)	Loss 0.9561 (0.7920)	Acc@1 76.880 (81.432)	Acc@5 94.336 (95.881)	Mem 34602MB
[2025-01-19 11:13:56 internimage_b_1k_224] (main.py 575): INFO [Epoch:154] * Acc@1 81.326 Acc@5 95.925
[2025-01-19 11:13:56 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.3%
[2025-01-19 11:13:56 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:14:00 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:14:00 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.33%
[2025-01-19 11:14:00 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][200/312]	eta 0:01:23 lr 0.001924	time 0.7214 (0.7421)	model_time 0.7212 (0.7356)	loss 2.9643 (3.1829)	grad_norm 1.0467 (1.6200/0.6898)	mem 34604MB
[2025-01-19 11:14:02 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][0/312]	eta 0:10:29 lr 0.001916	time 2.0178 (2.0178)	model_time 0.7415 (0.7415)	loss 3.1853 (3.1853)	grad_norm 1.2900 (1.2900/0.0000)	mem 34602MB
[2025-01-19 11:14:07 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][210/312]	eta 0:01:15 lr 0.001923	time 0.7170 (0.7418)	model_time 0.7168 (0.7356)	loss 3.8625 (3.1826)	grad_norm 1.4339 (1.5947/0.6841)	mem 34604MB
[2025-01-19 11:14:09 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][10/312]	eta 0:04:22 lr 0.001916	time 0.7312 (0.8694)	model_time 0.7311 (0.7530)	loss 3.4715 (3.3373)	grad_norm 1.5547 (1.2799/0.2869)	mem 34602MB
[2025-01-19 11:14:14 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][220/312]	eta 0:01:08 lr 0.001922	time 0.7160 (0.7409)	model_time 0.7155 (0.7350)	loss 3.7318 (3.1935)	grad_norm 1.7698 (1.5911/0.6794)	mem 34604MB
[2025-01-19 11:14:17 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][20/312]	eta 0:03:59 lr 0.001915	time 0.7532 (0.8187)	model_time 0.7527 (0.7575)	loss 2.8290 (3.3467)	grad_norm 0.9607 (1.3048/0.3514)	mem 34602MB
[2025-01-19 11:14:22 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][230/312]	eta 0:01:00 lr 0.001922	time 0.8291 (0.7412)	model_time 0.8287 (0.7355)	loss 3.4140 (3.1894)	grad_norm 2.0814 (1.5975/0.6825)	mem 34604MB
[2025-01-19 11:14:25 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][30/312]	eta 0:03:46 lr 0.001914	time 0.8135 (0.8020)	model_time 0.8134 (0.7604)	loss 2.8258 (3.3084)	grad_norm 1.8511 (1.4658/0.4821)	mem 34602MB
[2025-01-19 11:14:29 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][240/312]	eta 0:00:53 lr 0.001921	time 0.7209 (0.7418)	model_time 0.7208 (0.7363)	loss 2.9099 (3.1912)	grad_norm 1.4682 (1.5952/0.6738)	mem 34604MB
[2025-01-19 11:14:32 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][40/312]	eta 0:03:36 lr 0.001914	time 0.7174 (0.7978)	model_time 0.7170 (0.7663)	loss 3.5083 (3.3619)	grad_norm 2.0488 (1.7278/0.7797)	mem 34602MB
[2025-01-19 11:14:37 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][250/312]	eta 0:00:46 lr 0.001920	time 0.7226 (0.7435)	model_time 0.7225 (0.7383)	loss 3.6058 (3.1951)	grad_norm 1.2695 (1.5838/0.6643)	mem 34604MB
[2025-01-19 11:14:40 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][50/312]	eta 0:03:26 lr 0.001913	time 0.7582 (0.7890)	model_time 0.7581 (0.7636)	loss 3.6780 (3.2955)	grad_norm 0.7271 (1.7109/0.7571)	mem 34602MB
[2025-01-19 11:14:44 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][260/312]	eta 0:00:38 lr 0.001920	time 0.7183 (0.7430)	model_time 0.7178 (0.7379)	loss 2.8843 (3.1936)	grad_norm 1.0599 (1.5943/0.6669)	mem 34604MB
[2025-01-19 11:14:47 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][60/312]	eta 0:03:17 lr 0.001912	time 0.7186 (0.7821)	model_time 0.7181 (0.7608)	loss 3.7926 (3.2935)	grad_norm 0.6401 (1.5950/0.7526)	mem 34602MB
[2025-01-19 11:14:52 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][270/312]	eta 0:00:31 lr 0.001919	time 0.7180 (0.7423)	model_time 0.7176 (0.7374)	loss 3.3851 (3.1906)	grad_norm 1.6329 (1.5882/0.6617)	mem 34604MB
[2025-01-19 11:14:55 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][70/312]	eta 0:03:07 lr 0.001912	time 0.7173 (0.7755)	model_time 0.7171 (0.7572)	loss 3.3858 (3.2584)	grad_norm 1.4771 (1.5505/0.7231)	mem 34602MB
[2025-01-19 11:14:59 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][280/312]	eta 0:00:23 lr 0.001918	time 0.7146 (0.7417)	model_time 0.7144 (0.7370)	loss 3.8434 (3.1898)	grad_norm 0.7864 (1.5956/0.6676)	mem 34604MB
[2025-01-19 11:15:02 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][80/312]	eta 0:02:59 lr 0.001911	time 0.8385 (0.7723)	model_time 0.8381 (0.7562)	loss 4.0483 (3.3002)	grad_norm 1.0700 (1.5184/0.6949)	mem 34602MB
[2025-01-19 11:15:06 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][290/312]	eta 0:00:16 lr 0.001918	time 0.7324 (0.7412)	model_time 0.7320 (0.7366)	loss 3.4374 (3.1958)	grad_norm 1.1197 (1.5993/0.6626)	mem 34604MB
[2025-01-19 11:15:10 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][90/312]	eta 0:02:50 lr 0.001910	time 0.7317 (0.7687)	model_time 0.7315 (0.7543)	loss 2.8269 (3.3001)	grad_norm 4.8992 (1.5758/0.8074)	mem 34602MB
[2025-01-19 11:15:13 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][300/312]	eta 0:00:08 lr 0.001917	time 0.7149 (0.7406)	model_time 0.7148 (0.7361)	loss 2.9943 (3.2010)	grad_norm 1.7779 (1.6108/0.6776)	mem 34604MB
[2025-01-19 11:15:17 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][100/312]	eta 0:02:42 lr 0.001910	time 0.7173 (0.7655)	model_time 0.7171 (0.7525)	loss 3.5945 (3.2911)	grad_norm 0.8787 (1.5891/0.8070)	mem 34602MB
[2025-01-19 11:15:21 internimage_b_1k_224] (main.py 510): INFO Train: [154/300][310/312]	eta 0:00:01 lr 0.001917	time 0.7133 (0.7401)	model_time 0.7132 (0.7357)	loss 3.3112 (3.2045)	grad_norm 1.3457 (1.6129/0.6850)	mem 34604MB
[2025-01-19 11:15:21 internimage_b_1k_224] (main.py 519): INFO EPOCH 154 training takes 0:03:50
[2025-01-19 11:15:21 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_154.pth saving......
[2025-01-19 11:15:24 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][110/312]	eta 0:02:33 lr 0.001909	time 0.7178 (0.7619)	model_time 0.7177 (0.7500)	loss 2.1126 (3.2632)	grad_norm 1.3229 (1.5445/0.7881)	mem 34602MB
[2025-01-19 11:15:25 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_154.pth saved !!!
[2025-01-19 11:15:32 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][120/312]	eta 0:02:25 lr 0.001908	time 0.7240 (0.7587)	model_time 0.7238 (0.7478)	loss 3.5643 (3.2726)	grad_norm 1.2236 (1.5215/0.7676)	mem 34602MB
[2025-01-19 11:15:32 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.150 (7.150)	Loss 0.7939 (0.7939)	Acc@1 83.765 (83.765)	Acc@5 97.095 (97.095)	Mem 34604MB
[2025-01-19 11:15:35 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.923)	Loss 1.0585 (0.9130)	Acc@1 75.732 (80.662)	Acc@5 93.677 (95.610)	Mem 34604MB
[2025-01-19 11:15:35 internimage_b_1k_224] (main.py 575): INFO [Epoch:154] * Acc@1 80.572 Acc@5 95.659
[2025-01-19 11:15:35 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.6%
[2025-01-19 11:15:35 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.66%
[2025-01-19 11:15:39 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][130/312]	eta 0:02:17 lr 0.001908	time 0.7238 (0.7575)	model_time 0.7237 (0.7474)	loss 3.0043 (3.2710)	grad_norm 0.8925 (1.5024/0.7465)	mem 34602MB
[2025-01-19 11:15:44 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.958 (8.958)	Loss 0.6538 (0.6538)	Acc@1 84.302 (84.302)	Acc@5 97.656 (97.656)	Mem 34604MB
[2025-01-19 11:15:47 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][140/312]	eta 0:02:10 lr 0.001907	time 0.7192 (0.7579)	model_time 0.7188 (0.7485)	loss 3.1464 (3.2648)	grad_norm 1.3863 (1.5026/0.7374)	mem 34602MB
[2025-01-19 11:15:49 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.230)	Loss 0.9537 (0.7912)	Acc@1 77.051 (81.448)	Acc@5 94.629 (95.930)	Mem 34604MB
[2025-01-19 11:15:49 internimage_b_1k_224] (main.py 575): INFO [Epoch:154] * Acc@1 81.336 Acc@5 95.967
[2025-01-19 11:15:49 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.3%
[2025-01-19 11:15:49 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:15:53 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:15:53 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.34%
[2025-01-19 11:15:54 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][150/312]	eta 0:02:02 lr 0.001906	time 0.7500 (0.7576)	model_time 0.7498 (0.7487)	loss 2.9324 (3.2653)	grad_norm 1.0454 (1.5157/0.7261)	mem 34602MB
[2025-01-19 11:15:55 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][0/312]	eta 0:10:49 lr 0.001916	time 2.0814 (2.0814)	model_time 0.7442 (0.7442)	loss 3.1817 (3.1817)	grad_norm 1.3077 (1.3077/0.0000)	mem 34604MB
[2025-01-19 11:16:02 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][160/312]	eta 0:01:55 lr 0.001906	time 0.7223 (0.7596)	model_time 0.7218 (0.7513)	loss 2.7125 (3.2536)	grad_norm 1.0156 (1.4979/0.7124)	mem 34602MB
[2025-01-19 11:16:02 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][10/312]	eta 0:04:17 lr 0.001916	time 0.7415 (0.8537)	model_time 0.7411 (0.7318)	loss 3.2742 (3.0407)	grad_norm 2.0918 (1.7121/0.3342)	mem 34604MB
[2025-01-19 11:16:09 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][170/312]	eta 0:01:47 lr 0.001905	time 0.7174 (0.7584)	model_time 0.7173 (0.7506)	loss 3.2690 (3.2433)	grad_norm 2.1889 (1.4878/0.7040)	mem 34602MB
[2025-01-19 11:16:10 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][20/312]	eta 0:03:51 lr 0.001915	time 0.7414 (0.7941)	model_time 0.7410 (0.7300)	loss 2.6297 (3.2151)	grad_norm 1.3401 (1.5484/0.4137)	mem 34604MB
[2025-01-19 11:16:17 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][180/312]	eta 0:01:39 lr 0.001904	time 0.7167 (0.7575)	model_time 0.7165 (0.7501)	loss 2.0100 (3.2270)	grad_norm 1.8989 (1.4944/0.7069)	mem 34602MB
[2025-01-19 11:16:17 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][30/312]	eta 0:03:37 lr 0.001914	time 0.7206 (0.7725)	model_time 0.7202 (0.7290)	loss 3.4516 (3.2226)	grad_norm 1.4395 (1.5088/0.4335)	mem 34604MB
[2025-01-19 11:16:24 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][190/312]	eta 0:01:32 lr 0.001904	time 0.7437 (0.7566)	model_time 0.7436 (0.7496)	loss 2.6691 (3.2133)	grad_norm 1.7719 (1.5042/0.6980)	mem 34602MB
[2025-01-19 11:16:25 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][40/312]	eta 0:03:28 lr 0.001914	time 0.7169 (0.7661)	model_time 0.7168 (0.7332)	loss 3.2222 (3.2071)	grad_norm 1.2259 (1.4521/0.4092)	mem 34604MB
[2025-01-19 11:16:32 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][200/312]	eta 0:01:24 lr 0.001903	time 0.8147 (0.7562)	model_time 0.8143 (0.7495)	loss 3.5487 (3.2246)	grad_norm 1.1337 (1.5177/0.6986)	mem 34602MB
[2025-01-19 11:16:32 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][50/312]	eta 0:03:20 lr 0.001913	time 0.8082 (0.7671)	model_time 0.8081 (0.7404)	loss 2.8926 (3.2069)	grad_norm 2.8373 (1.4586/0.4471)	mem 34604MB
[2025-01-19 11:16:39 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][210/312]	eta 0:01:17 lr 0.001902	time 0.7238 (0.7554)	model_time 0.7237 (0.7490)	loss 3.8063 (3.2188)	grad_norm 2.1120 (1.5185/0.6897)	mem 34602MB
[2025-01-19 11:16:40 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][60/312]	eta 0:03:14 lr 0.001912	time 0.8082 (0.7717)	model_time 0.8081 (0.7494)	loss 2.2128 (3.1962)	grad_norm 3.2429 (1.5549/0.6081)	mem 34604MB
[2025-01-19 11:16:46 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][220/312]	eta 0:01:09 lr 0.001902	time 0.7161 (0.7545)	model_time 0.7157 (0.7484)	loss 2.7747 (3.2138)	grad_norm 2.8069 (1.5351/0.6936)	mem 34602MB
[2025-01-19 11:16:47 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][70/312]	eta 0:03:05 lr 0.001912	time 0.7168 (0.7655)	model_time 0.7167 (0.7463)	loss 2.3680 (3.1602)	grad_norm 2.7292 (1.6415/0.6791)	mem 34604MB
[2025-01-19 11:16:54 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][230/312]	eta 0:01:01 lr 0.001901	time 0.7250 (0.7533)	model_time 0.7249 (0.7474)	loss 3.1528 (3.2137)	grad_norm 1.7618 (1.5240/0.6840)	mem 34602MB
[2025-01-19 11:16:55 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][80/312]	eta 0:02:56 lr 0.001911	time 0.7185 (0.7605)	model_time 0.7184 (0.7436)	loss 3.7832 (3.1890)	grad_norm 1.3080 (1.6229/0.6615)	mem 34604MB
[2025-01-19 11:17:01 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][240/312]	eta 0:00:54 lr 0.001900	time 0.7180 (0.7520)	model_time 0.7175 (0.7464)	loss 3.4023 (3.2102)	grad_norm 1.0122 (1.5275/0.6825)	mem 34602MB
[2025-01-19 11:17:02 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][90/312]	eta 0:02:48 lr 0.001910	time 0.7603 (0.7575)	model_time 0.7601 (0.7424)	loss 3.1863 (3.1871)	grad_norm 0.9706 (1.6183/0.6398)	mem 34604MB
[2025-01-19 11:17:08 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][250/312]	eta 0:00:46 lr 0.001900	time 0.7187 (0.7516)	model_time 0.7183 (0.7461)	loss 3.3707 (3.2083)	grad_norm 1.5239 (1.5312/0.6755)	mem 34602MB
[2025-01-19 11:17:09 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][100/312]	eta 0:02:40 lr 0.001910	time 0.7145 (0.7549)	model_time 0.7140 (0.7413)	loss 4.0207 (3.1767)	grad_norm 1.9269 (1.6631/0.6920)	mem 34604MB
[2025-01-19 11:17:16 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][260/312]	eta 0:00:39 lr 0.001899	time 0.7166 (0.7521)	model_time 0.7164 (0.7468)	loss 2.9734 (3.2110)	grad_norm 1.3610 (1.5264/0.6664)	mem 34602MB
[2025-01-19 11:17:17 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][110/312]	eta 0:02:31 lr 0.001909	time 0.7222 (0.7523)	model_time 0.7220 (0.7399)	loss 2.1279 (3.1850)	grad_norm 2.2223 (1.6356/0.6762)	mem 34604MB
[2025-01-19 11:17:24 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][270/312]	eta 0:00:31 lr 0.001898	time 0.7203 (0.7520)	model_time 0.7199 (0.7470)	loss 3.2900 (3.2171)	grad_norm 1.6500 (1.5284/0.6575)	mem 34602MB
[2025-01-19 11:17:24 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][120/312]	eta 0:02:24 lr 0.001908	time 0.7238 (0.7505)	model_time 0.7234 (0.7391)	loss 2.7440 (3.1735)	grad_norm 1.1478 (1.5916/0.6673)	mem 34604MB
[2025-01-19 11:17:31 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][130/312]	eta 0:02:16 lr 0.001908	time 0.7158 (0.7483)	model_time 0.7156 (0.7377)	loss 3.9040 (3.1767)	grad_norm 1.1834 (1.5822/0.6530)	mem 34604MB
[2025-01-19 11:17:31 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][280/312]	eta 0:00:24 lr 0.001898	time 0.7191 (0.7533)	model_time 0.7187 (0.7484)	loss 3.8824 (3.2099)	grad_norm 1.3383 (1.5176/0.6526)	mem 34602MB
[2025-01-19 11:17:38 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][140/312]	eta 0:02:08 lr 0.001907	time 0.7287 (0.7470)	model_time 0.7283 (0.7371)	loss 3.6543 (3.1642)	grad_norm 1.6207 (1.5622/0.6420)	mem 34604MB
[2025-01-19 11:17:39 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][290/312]	eta 0:00:16 lr 0.001897	time 0.7418 (0.7529)	model_time 0.7416 (0.7482)	loss 3.9737 (3.2156)	grad_norm 1.0067 (1.5007/0.6482)	mem 34602MB
[2025-01-19 11:17:46 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][150/312]	eta 0:02:00 lr 0.001906	time 0.7271 (0.7458)	model_time 0.7266 (0.7366)	loss 3.2438 (3.1567)	grad_norm 2.4602 (1.5943/0.6630)	mem 34604MB
[2025-01-19 11:17:46 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][300/312]	eta 0:00:09 lr 0.001896	time 0.7126 (0.7524)	model_time 0.7125 (0.7478)	loss 3.0648 (3.2056)	grad_norm 0.8419 (1.5010/0.6441)	mem 34602MB
[2025-01-19 11:17:53 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][160/312]	eta 0:01:53 lr 0.001906	time 0.7284 (0.7457)	model_time 0.7283 (0.7371)	loss 2.7888 (3.1448)	grad_norm 2.3937 (1.6347/0.7249)	mem 34604MB
[2025-01-19 11:17:53 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][310/312]	eta 0:00:01 lr 0.001896	time 0.7179 (0.7512)	model_time 0.7178 (0.7468)	loss 3.6478 (3.1957)	grad_norm 1.9362 (1.5117/0.6461)	mem 34602MB
[2025-01-19 11:17:54 internimage_b_1k_224] (main.py 519): INFO EPOCH 155 training takes 0:03:54
[2025-01-19 11:17:54 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_155.pth saving......
[2025-01-19 11:17:57 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_155.pth saved !!!
[2025-01-19 11:18:01 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][170/312]	eta 0:01:45 lr 0.001905	time 0.7470 (0.7462)	model_time 0.7465 (0.7380)	loss 3.8104 (3.1527)	grad_norm 1.2805 (1.6316/0.7134)	mem 34604MB
[2025-01-19 11:18:05 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.630 (7.630)	Loss 0.7954 (0.7954)	Acc@1 84.204 (84.204)	Acc@5 97.266 (97.266)	Mem 34602MB
[2025-01-19 11:18:08 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.981)	Loss 1.0754 (0.9218)	Acc@1 76.465 (80.848)	Acc@5 94.263 (95.661)	Mem 34602MB
[2025-01-19 11:18:08 internimage_b_1k_224] (main.py 575): INFO [Epoch:155] * Acc@1 80.788 Acc@5 95.693
[2025-01-19 11:18:08 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.8%
[2025-01-19 11:18:08 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 11:18:09 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][180/312]	eta 0:01:38 lr 0.001904	time 0.8047 (0.7488)	model_time 0.8045 (0.7411)	loss 3.0484 (3.1504)	grad_norm 1.5996 (1.6156/0.7005)	mem 34604MB
[2025-01-19 11:18:12 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 11:18:12 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.79%
[2025-01-19 11:18:16 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][190/312]	eta 0:01:31 lr 0.001904	time 0.7235 (0.7477)	model_time 0.7234 (0.7404)	loss 2.7320 (3.1486)	grad_norm 2.1501 (1.5993/0.6920)	mem 34604MB
[2025-01-19 11:18:19 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.393 (7.393)	Loss 0.6555 (0.6555)	Acc@1 84.106 (84.106)	Acc@5 97.534 (97.534)	Mem 34602MB
[2025-01-19 11:18:22 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.951)	Loss 0.9556 (0.7921)	Acc@1 76.904 (81.463)	Acc@5 94.336 (95.894)	Mem 34602MB
[2025-01-19 11:18:22 internimage_b_1k_224] (main.py 575): INFO [Epoch:155] * Acc@1 81.356 Acc@5 95.943
[2025-01-19 11:18:22 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.4%
[2025-01-19 11:18:22 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:18:23 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][200/312]	eta 0:01:23 lr 0.001903	time 0.7237 (0.7471)	model_time 0.7236 (0.7401)	loss 3.3140 (3.1410)	grad_norm 1.0602 (1.5816/0.6872)	mem 34604MB
[2025-01-19 11:18:26 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:18:26 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.36%
[2025-01-19 11:18:29 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][0/312]	eta 0:11:06 lr 0.001896	time 2.1352 (2.1352)	model_time 0.7436 (0.7436)	loss 3.4527 (3.4527)	grad_norm 1.2195 (1.2195/0.0000)	mem 34602MB
[2025-01-19 11:18:31 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][210/312]	eta 0:01:16 lr 0.001902	time 0.7182 (0.7461)	model_time 0.7180 (0.7394)	loss 3.3353 (3.1358)	grad_norm 1.7849 (1.5847/0.7040)	mem 34604MB
[2025-01-19 11:18:36 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][10/312]	eta 0:04:20 lr 0.001895	time 0.7269 (0.8634)	model_time 0.7267 (0.7367)	loss 3.9332 (3.4308)	grad_norm 1.2884 (2.3290/0.8495)	mem 34602MB
[2025-01-19 11:18:38 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][220/312]	eta 0:01:08 lr 0.001902	time 0.7168 (0.7452)	model_time 0.7166 (0.7387)	loss 3.4467 (3.1426)	grad_norm 1.3888 (1.5891/0.6978)	mem 34604MB
[2025-01-19 11:18:43 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][20/312]	eta 0:03:56 lr 0.001894	time 0.7436 (0.8093)	model_time 0.7434 (0.7428)	loss 2.6725 (3.2295)	grad_norm 1.6113 (2.1404/0.7205)	mem 34602MB
[2025-01-19 11:18:45 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][230/312]	eta 0:01:01 lr 0.001901	time 0.7201 (0.7441)	model_time 0.7199 (0.7379)	loss 3.2616 (3.1519)	grad_norm 1.4556 (1.5865/0.6904)	mem 34604MB
[2025-01-19 11:18:51 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][30/312]	eta 0:03:41 lr 0.001894	time 0.7251 (0.7865)	model_time 0.7249 (0.7413)	loss 3.0408 (3.1397)	grad_norm 0.8201 (1.9367/0.7352)	mem 34602MB
[2025-01-19 11:18:52 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][240/312]	eta 0:00:53 lr 0.001900	time 0.7139 (0.7432)	model_time 0.7135 (0.7373)	loss 2.2894 (3.1514)	grad_norm 0.9115 (1.5933/0.6854)	mem 34604MB
[2025-01-19 11:18:58 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][40/312]	eta 0:03:30 lr 0.001893	time 0.7191 (0.7723)	model_time 0.7189 (0.7381)	loss 3.0270 (3.1343)	grad_norm 1.0914 (1.8410/0.7310)	mem 34602MB
[2025-01-19 11:18:59 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][250/312]	eta 0:00:46 lr 0.001900	time 0.7259 (0.7423)	model_time 0.7255 (0.7367)	loss 2.2259 (3.1564)	grad_norm 1.3657 (1.5816/0.6755)	mem 34604MB
[2025-01-19 11:19:05 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][50/312]	eta 0:03:20 lr 0.001892	time 0.7309 (0.7639)	model_time 0.7307 (0.7363)	loss 3.7794 (3.1030)	grad_norm 2.5599 (1.7660/0.7133)	mem 34602MB
[2025-01-19 11:19:07 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][260/312]	eta 0:00:38 lr 0.001899	time 0.7309 (0.7417)	model_time 0.7304 (0.7363)	loss 3.0534 (3.1564)	grad_norm 1.7142 (1.5705/0.6686)	mem 34604MB
[2025-01-19 11:19:13 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][60/312]	eta 0:03:11 lr 0.001892	time 0.7380 (0.7613)	model_time 0.7374 (0.7382)	loss 3.2632 (3.0994)	grad_norm 0.8858 (1.7516/0.7115)	mem 34602MB
[2025-01-19 11:19:14 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][270/312]	eta 0:00:31 lr 0.001898	time 0.7505 (0.7411)	model_time 0.7504 (0.7358)	loss 2.4828 (3.1532)	grad_norm 0.8784 (1.5606/0.6607)	mem 34604MB
[2025-01-19 11:19:21 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][70/312]	eta 0:03:04 lr 0.001891	time 0.8074 (0.7631)	model_time 0.8072 (0.7431)	loss 3.0467 (3.1052)	grad_norm 1.4091 (1.8118/0.7721)	mem 34602MB
[2025-01-19 11:19:21 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][280/312]	eta 0:00:23 lr 0.001898	time 0.7172 (0.7409)	model_time 0.7170 (0.7357)	loss 3.7916 (3.1589)	grad_norm 3.0177 (1.5801/0.6669)	mem 34604MB
[2025-01-19 11:19:28 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][80/312]	eta 0:02:56 lr 0.001890	time 0.7187 (0.7608)	model_time 0.7183 (0.7433)	loss 2.8942 (3.1235)	grad_norm 1.4423 (1.8170/0.7842)	mem 34602MB
[2025-01-19 11:19:29 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][290/312]	eta 0:00:16 lr 0.001897	time 0.7355 (0.7419)	model_time 0.7350 (0.7370)	loss 3.4245 (3.1578)	grad_norm 1.7647 (1.5786/0.6739)	mem 34604MB
[2025-01-19 11:19:36 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][90/312]	eta 0:02:49 lr 0.001890	time 0.8156 (0.7652)	model_time 0.8152 (0.7496)	loss 3.6883 (3.1501)	grad_norm 1.0672 (1.7442/0.7755)	mem 34602MB
[2025-01-19 11:19:37 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][300/312]	eta 0:00:08 lr 0.001896	time 0.8357 (0.7436)	model_time 0.8356 (0.7388)	loss 3.4976 (3.1696)	grad_norm 2.2552 (1.5738/0.6670)	mem 34604MB
[2025-01-19 11:19:44 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][100/312]	eta 0:02:41 lr 0.001889	time 0.7186 (0.7639)	model_time 0.7184 (0.7498)	loss 2.8572 (3.1398)	grad_norm 1.0827 (1.6911/0.7626)	mem 34602MB
[2025-01-19 11:19:44 internimage_b_1k_224] (main.py 510): INFO Train: [155/300][310/312]	eta 0:00:01 lr 0.001896	time 0.7141 (0.7429)	model_time 0.7140 (0.7383)	loss 3.9662 (3.1775)	grad_norm 1.5455 (1.5643/0.6705)	mem 34604MB
[2025-01-19 11:19:45 internimage_b_1k_224] (main.py 519): INFO EPOCH 155 training takes 0:03:51
[2025-01-19 11:19:45 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_155.pth saving......
[2025-01-19 11:19:48 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_155.pth saved !!!
[2025-01-19 11:19:51 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][110/312]	eta 0:02:33 lr 0.001888	time 0.7188 (0.7617)	model_time 0.7184 (0.7488)	loss 2.4211 (3.1450)	grad_norm 1.2978 (1.6751/0.7330)	mem 34602MB
[2025-01-19 11:19:55 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.232 (7.232)	Loss 0.7967 (0.7967)	Acc@1 83.618 (83.618)	Acc@5 97.046 (97.046)	Mem 34604MB
[2025-01-19 11:19:58 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][120/312]	eta 0:02:25 lr 0.001888	time 0.7182 (0.7595)	model_time 0.7178 (0.7477)	loss 3.5132 (3.1354)	grad_norm 0.9551 (1.6669/0.7136)	mem 34602MB
[2025-01-19 11:19:59 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.948)	Loss 1.0402 (0.9151)	Acc@1 77.368 (80.837)	Acc@5 94.141 (95.628)	Mem 34604MB
[2025-01-19 11:19:59 internimage_b_1k_224] (main.py 575): INFO [Epoch:155] * Acc@1 80.746 Acc@5 95.663
[2025-01-19 11:19:59 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.7%
[2025-01-19 11:19:59 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 11:20:02 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 11:20:02 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.75%
[2025-01-19 11:20:06 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][130/312]	eta 0:02:17 lr 0.001887	time 0.8096 (0.7578)	model_time 0.8095 (0.7469)	loss 3.2533 (3.1500)	grad_norm 3.2423 (1.6869/0.7212)	mem 34602MB
[2025-01-19 11:20:10 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.329 (7.329)	Loss 0.6543 (0.6543)	Acc@1 84.399 (84.399)	Acc@5 97.681 (97.681)	Mem 34604MB
[2025-01-19 11:20:13 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.940)	Loss 0.9531 (0.7912)	Acc@1 77.075 (81.494)	Acc@5 94.653 (95.945)	Mem 34604MB
[2025-01-19 11:20:13 internimage_b_1k_224] (main.py 575): INFO [Epoch:155] * Acc@1 81.380 Acc@5 95.987
[2025-01-19 11:20:13 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.4%
[2025-01-19 11:20:13 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:20:13 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][140/312]	eta 0:02:10 lr 0.001886	time 0.7419 (0.7576)	model_time 0.7418 (0.7474)	loss 3.4274 (3.1653)	grad_norm 2.5428 (1.7029/0.7247)	mem 34602MB
[2025-01-19 11:20:17 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:20:17 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.38%
[2025-01-19 11:20:19 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][0/312]	eta 0:10:42 lr 0.001896	time 2.0599 (2.0599)	model_time 0.7254 (0.7254)	loss 3.4621 (3.4621)	grad_norm 1.4493 (1.4493/0.0000)	mem 34604MB
[2025-01-19 11:20:21 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][150/312]	eta 0:02:02 lr 0.001886	time 0.7265 (0.7559)	model_time 0.7260 (0.7464)	loss 2.4964 (3.1641)	grad_norm 2.5457 (1.7187/0.7225)	mem 34602MB
[2025-01-19 11:20:26 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][10/312]	eta 0:04:16 lr 0.001895	time 0.7349 (0.8481)	model_time 0.7344 (0.7264)	loss 2.3390 (2.8971)	grad_norm 0.9126 (1.5363/0.4523)	mem 34604MB
[2025-01-19 11:20:28 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][160/312]	eta 0:01:54 lr 0.001885	time 0.7212 (0.7544)	model_time 0.7211 (0.7454)	loss 3.5532 (3.1590)	grad_norm 2.2616 (1.7120/0.7101)	mem 34602MB
[2025-01-19 11:20:34 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][20/312]	eta 0:03:50 lr 0.001894	time 0.7146 (0.7888)	model_time 0.7144 (0.7249)	loss 3.8493 (2.9728)	grad_norm 2.4784 (1.4902/0.4973)	mem 34604MB
[2025-01-19 11:20:35 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][170/312]	eta 0:01:46 lr 0.001884	time 0.7158 (0.7527)	model_time 0.7156 (0.7442)	loss 2.4753 (3.1442)	grad_norm 1.5788 (1.7001/0.6937)	mem 34602MB
[2025-01-19 11:20:41 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][30/312]	eta 0:03:36 lr 0.001894	time 0.7072 (0.7687)	model_time 0.7071 (0.7253)	loss 3.4558 (2.9288)	grad_norm 1.6937 (1.6957/0.7447)	mem 34604MB
[2025-01-19 11:20:42 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][180/312]	eta 0:01:39 lr 0.001884	time 0.7219 (0.7515)	model_time 0.7215 (0.7435)	loss 2.6863 (3.1395)	grad_norm 0.9644 (1.7140/0.6931)	mem 34602MB
[2025-01-19 11:20:48 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][40/312]	eta 0:03:26 lr 0.001893	time 0.7520 (0.7587)	model_time 0.7518 (0.7258)	loss 2.8494 (2.9945)	grad_norm 2.5077 (1.7916/0.8116)	mem 34604MB
[2025-01-19 11:20:50 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][190/312]	eta 0:01:31 lr 0.001883	time 0.8064 (0.7523)	model_time 0.8063 (0.7446)	loss 2.7963 (3.1444)	grad_norm 2.3624 (1.7058/0.6817)	mem 34602MB
[2025-01-19 11:20:55 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][50/312]	eta 0:03:17 lr 0.001892	time 0.7358 (0.7529)	model_time 0.7354 (0.7263)	loss 3.7484 (2.9753)	grad_norm 0.7936 (1.7826/0.8100)	mem 34604MB
[2025-01-19 11:20:58 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][200/312]	eta 0:01:24 lr 0.001882	time 0.7179 (0.7523)	model_time 0.7175 (0.7450)	loss 3.7254 (3.1443)	grad_norm 1.5882 (1.7161/0.6793)	mem 34602MB
[2025-01-19 11:21:03 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][60/312]	eta 0:03:08 lr 0.001892	time 0.7256 (0.7483)	model_time 0.7254 (0.7261)	loss 3.0853 (3.0143)	grad_norm 0.9427 (1.6913/0.7912)	mem 34604MB
[2025-01-19 11:21:05 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][210/312]	eta 0:01:16 lr 0.001882	time 0.8034 (0.7535)	model_time 0.8030 (0.7465)	loss 3.4607 (3.1582)	grad_norm 1.4880 (1.7091/0.6806)	mem 34602MB
[2025-01-19 11:21:10 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][70/312]	eta 0:03:00 lr 0.001891	time 0.7350 (0.7453)	model_time 0.7345 (0.7261)	loss 4.0370 (3.0410)	grad_norm 1.3795 (1.6202/0.7597)	mem 34604MB
[2025-01-19 11:21:13 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][220/312]	eta 0:01:09 lr 0.001881	time 0.7183 (0.7528)	model_time 0.7181 (0.7462)	loss 3.7090 (3.1690)	grad_norm 1.2129 (1.6939/0.6713)	mem 34602MB
[2025-01-19 11:21:17 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][80/312]	eta 0:02:52 lr 0.001890	time 0.7494 (0.7438)	model_time 0.7492 (0.7270)	loss 3.3830 (3.0363)	grad_norm 1.4286 (1.5976/0.7262)	mem 34604MB
[2025-01-19 11:21:20 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][230/312]	eta 0:01:01 lr 0.001880	time 0.7167 (0.7524)	model_time 0.7163 (0.7460)	loss 3.4762 (3.1728)	grad_norm 1.2244 (1.6726/0.6655)	mem 34602MB
[2025-01-19 11:21:25 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][90/312]	eta 0:02:45 lr 0.001890	time 0.7165 (0.7436)	model_time 0.7164 (0.7286)	loss 3.2869 (3.0368)	grad_norm 3.1042 (1.6259/0.7688)	mem 34604MB
[2025-01-19 11:21:27 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][240/312]	eta 0:00:54 lr 0.001880	time 0.7174 (0.7514)	model_time 0.7170 (0.7453)	loss 3.3715 (3.1847)	grad_norm 1.2821 (1.6656/0.6672)	mem 34602MB
[2025-01-19 11:21:32 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][100/312]	eta 0:02:38 lr 0.001889	time 0.7177 (0.7461)	model_time 0.7172 (0.7326)	loss 3.8228 (3.0742)	grad_norm 2.6888 (1.6453/0.7620)	mem 34604MB
[2025-01-19 11:21:35 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][250/312]	eta 0:00:46 lr 0.001879	time 0.8105 (0.7506)	model_time 0.8103 (0.7447)	loss 3.8644 (3.1961)	grad_norm 2.2595 (1.6808/0.6844)	mem 34602MB
[2025-01-19 11:21:40 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][110/312]	eta 0:02:31 lr 0.001888	time 0.8011 (0.7512)	model_time 0.7991 (0.7388)	loss 3.3577 (3.0783)	grad_norm 1.9754 (1.6420/0.7390)	mem 34604MB
[2025-01-19 11:21:42 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][260/312]	eta 0:00:39 lr 0.001878	time 0.7201 (0.7506)	model_time 0.7196 (0.7449)	loss 3.5404 (3.1962)	grad_norm 1.1864 (1.6935/0.6911)	mem 34602MB
[2025-01-19 11:21:48 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][120/312]	eta 0:02:23 lr 0.001888	time 0.7345 (0.7500)	model_time 0.7340 (0.7386)	loss 3.6229 (3.1100)	grad_norm 1.2773 (1.6465/0.7264)	mem 34604MB
[2025-01-19 11:21:50 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][270/312]	eta 0:00:31 lr 0.001878	time 0.8092 (0.7499)	model_time 0.8091 (0.7445)	loss 3.4436 (3.2001)	grad_norm 0.9260 (1.7039/0.6932)	mem 34602MB
[2025-01-19 11:21:55 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][130/312]	eta 0:02:16 lr 0.001887	time 0.7174 (0.7481)	model_time 0.7173 (0.7375)	loss 2.4043 (3.1074)	grad_norm 0.7868 (1.6194/0.7215)	mem 34604MB
[2025-01-19 11:21:57 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][280/312]	eta 0:00:23 lr 0.001877	time 0.7176 (0.7490)	model_time 0.7175 (0.7437)	loss 2.4800 (3.1869)	grad_norm 1.0733 (1.6807/0.6927)	mem 34602MB
[2025-01-19 11:22:02 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][140/312]	eta 0:02:08 lr 0.001886	time 0.7125 (0.7465)	model_time 0.7121 (0.7367)	loss 3.9141 (3.1070)	grad_norm 1.7600 (1.6050/0.7035)	mem 34604MB
[2025-01-19 11:22:04 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][290/312]	eta 0:00:16 lr 0.001876	time 0.7206 (0.7482)	model_time 0.7205 (0.7431)	loss 2.7391 (3.1902)	grad_norm 1.7911 (1.6862/0.6921)	mem 34602MB
[2025-01-19 11:22:09 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][150/312]	eta 0:02:00 lr 0.001886	time 0.7225 (0.7448)	model_time 0.7220 (0.7356)	loss 3.1552 (3.1056)	grad_norm 1.3836 (1.6146/0.6989)	mem 34604MB
[2025-01-19 11:22:11 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][300/312]	eta 0:00:08 lr 0.001876	time 0.7139 (0.7475)	model_time 0.7138 (0.7426)	loss 2.7291 (3.1914)	grad_norm 1.0919 (1.6835/0.6964)	mem 34602MB
[2025-01-19 11:22:17 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][160/312]	eta 0:01:53 lr 0.001885	time 0.7156 (0.7438)	model_time 0.7151 (0.7351)	loss 3.6389 (3.1183)	grad_norm 1.5543 (1.6138/0.6858)	mem 34604MB
[2025-01-19 11:22:19 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][310/312]	eta 0:00:01 lr 0.001875	time 0.7114 (0.7475)	model_time 0.7113 (0.7427)	loss 3.6686 (3.2004)	grad_norm 2.4818 (1.6494/0.6749)	mem 34602MB
[2025-01-19 11:22:20 internimage_b_1k_224] (main.py 519): INFO EPOCH 156 training takes 0:03:53
[2025-01-19 11:22:20 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_156.pth saving......
[2025-01-19 11:22:23 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_156.pth saved !!!
[2025-01-19 11:22:24 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][170/312]	eta 0:01:45 lr 0.001884	time 0.7179 (0.7427)	model_time 0.7177 (0.7346)	loss 3.3042 (3.1192)	grad_norm 3.0445 (1.6188/0.6831)	mem 34604MB
[2025-01-19 11:22:31 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.631 (7.631)	Loss 0.7523 (0.7523)	Acc@1 84.106 (84.106)	Acc@5 97.339 (97.339)	Mem 34602MB
[2025-01-19 11:22:31 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][180/312]	eta 0:01:37 lr 0.001884	time 0.7209 (0.7420)	model_time 0.7207 (0.7342)	loss 3.3330 (3.1092)	grad_norm 1.8055 (1.6089/0.6764)	mem 34604MB
[2025-01-19 11:22:34 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.981)	Loss 1.0291 (0.8984)	Acc@1 77.710 (81.006)	Acc@5 94.434 (95.748)	Mem 34602MB
[2025-01-19 11:22:34 internimage_b_1k_224] (main.py 575): INFO [Epoch:156] * Acc@1 80.816 Acc@5 95.765
[2025-01-19 11:22:34 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.8%
[2025-01-19 11:22:34 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 11:22:37 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 11:22:37 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.82%
[2025-01-19 11:22:39 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][190/312]	eta 0:01:30 lr 0.001883	time 0.7163 (0.7409)	model_time 0.7162 (0.7336)	loss 3.7982 (3.1179)	grad_norm 2.3933 (1.6016/0.6751)	mem 34604MB
[2025-01-19 11:22:45 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.887 (7.887)	Loss 0.6559 (0.6559)	Acc@1 84.106 (84.106)	Acc@5 97.583 (97.583)	Mem 34602MB
[2025-01-19 11:22:46 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][200/312]	eta 0:01:22 lr 0.001882	time 0.7114 (0.7404)	model_time 0.7113 (0.7333)	loss 3.6359 (3.1310)	grad_norm 1.5147 (1.6163/0.6695)	mem 34604MB
[2025-01-19 11:22:48 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.003)	Loss 0.9551 (0.7921)	Acc@1 77.002 (81.472)	Acc@5 94.385 (95.914)	Mem 34602MB
[2025-01-19 11:22:48 internimage_b_1k_224] (main.py 575): INFO [Epoch:156] * Acc@1 81.362 Acc@5 95.965
[2025-01-19 11:22:48 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.4%
[2025-01-19 11:22:48 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:22:53 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:22:53 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.36%
[2025-01-19 11:22:53 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][210/312]	eta 0:01:15 lr 0.001882	time 0.7146 (0.7406)	model_time 0.7144 (0.7339)	loss 2.6579 (3.1263)	grad_norm 0.8994 (1.6247/0.6876)	mem 34604MB
[2025-01-19 11:22:55 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][0/312]	eta 0:10:23 lr 0.001875	time 1.9976 (1.9976)	model_time 0.7405 (0.7405)	loss 3.6050 (3.6050)	grad_norm 1.8802 (1.8802/0.0000)	mem 34602MB
[2025-01-19 11:23:01 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][220/312]	eta 0:01:08 lr 0.001881	time 0.7197 (0.7421)	model_time 0.7196 (0.7357)	loss 2.4749 (3.1238)	grad_norm 1.4754 (1.6290/0.6968)	mem 34604MB
[2025-01-19 11:23:02 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][10/312]	eta 0:04:21 lr 0.001874	time 0.7181 (0.8671)	model_time 0.7179 (0.7526)	loss 3.4780 (3.1457)	grad_norm 1.4606 (1.7800/0.4153)	mem 34602MB
[2025-01-19 11:23:09 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][230/312]	eta 0:01:01 lr 0.001880	time 0.7179 (0.7443)	model_time 0.7175 (0.7382)	loss 3.6528 (3.1259)	grad_norm 3.0921 (1.6146/0.6990)	mem 34604MB
[2025-01-19 11:23:10 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][20/312]	eta 0:04:03 lr 0.001874	time 0.7541 (0.8330)	model_time 0.7537 (0.7728)	loss 3.8777 (3.0624)	grad_norm 0.8623 (1.4753/0.4645)	mem 34602MB
[2025-01-19 11:23:16 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][240/312]	eta 0:00:53 lr 0.001880	time 0.7520 (0.7442)	model_time 0.7519 (0.7383)	loss 3.9249 (3.1297)	grad_norm 0.8448 (1.6003/0.6924)	mem 34604MB
[2025-01-19 11:23:18 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][30/312]	eta 0:03:46 lr 0.001873	time 0.8383 (0.8042)	model_time 0.8379 (0.7634)	loss 3.5545 (3.2063)	grad_norm 2.9722 (1.5201/0.5046)	mem 34602MB
[2025-01-19 11:23:24 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][250/312]	eta 0:00:46 lr 0.001879	time 0.7163 (0.7437)	model_time 0.7158 (0.7381)	loss 3.2301 (3.1180)	grad_norm 3.2236 (1.6019/0.6888)	mem 34604MB
[2025-01-19 11:23:25 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][40/312]	eta 0:03:34 lr 0.001872	time 0.7261 (0.7888)	model_time 0.7259 (0.7578)	loss 3.0853 (3.2076)	grad_norm 1.0096 (1.4718/0.4942)	mem 34602MB
[2025-01-19 11:23:31 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][260/312]	eta 0:00:38 lr 0.001878	time 0.7200 (0.7430)	model_time 0.7195 (0.7375)	loss 3.5789 (3.1284)	grad_norm 2.7309 (1.6122/0.6863)	mem 34604MB
[2025-01-19 11:23:32 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][50/312]	eta 0:03:24 lr 0.001872	time 0.7425 (0.7788)	model_time 0.7421 (0.7538)	loss 3.0302 (3.1715)	grad_norm 1.1464 (1.5056/0.4775)	mem 34602MB
[2025-01-19 11:23:38 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][270/312]	eta 0:00:31 lr 0.001878	time 0.7168 (0.7422)	model_time 0.7167 (0.7370)	loss 2.1137 (3.1316)	grad_norm 1.1734 (1.5994/0.6824)	mem 34604MB
[2025-01-19 11:23:40 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][60/312]	eta 0:03:14 lr 0.001871	time 0.7200 (0.7714)	model_time 0.7199 (0.7504)	loss 3.3467 (3.1571)	grad_norm 2.1613 (1.5638/0.5123)	mem 34602MB
[2025-01-19 11:23:45 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][280/312]	eta 0:00:23 lr 0.001877	time 0.7251 (0.7415)	model_time 0.7249 (0.7364)	loss 2.0898 (3.1269)	grad_norm 1.2375 (1.5997/0.6877)	mem 34604MB
[2025-01-19 11:23:47 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][70/312]	eta 0:03:05 lr 0.001870	time 0.7165 (0.7685)	model_time 0.7163 (0.7504)	loss 2.9437 (3.1709)	grad_norm 1.0188 (1.6222/0.5842)	mem 34602MB
[2025-01-19 11:23:53 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][290/312]	eta 0:00:16 lr 0.001876	time 0.7218 (0.7410)	model_time 0.7214 (0.7360)	loss 3.3434 (3.1209)	grad_norm 3.1524 (1.6107/0.6914)	mem 34604MB
[2025-01-19 11:23:54 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][80/312]	eta 0:02:57 lr 0.001870	time 0.7186 (0.7642)	model_time 0.7182 (0.7483)	loss 3.7233 (3.1765)	grad_norm 1.6937 (1.7084/0.6476)	mem 34602MB
[2025-01-19 11:24:00 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][300/312]	eta 0:00:08 lr 0.001876	time 0.7128 (0.7404)	model_time 0.7127 (0.7356)	loss 3.5279 (3.1232)	grad_norm 1.1371 (1.6036/0.6847)	mem 34604MB
[2025-01-19 11:24:02 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][90/312]	eta 0:02:48 lr 0.001869	time 0.7418 (0.7602)	model_time 0.7414 (0.7461)	loss 2.9001 (3.1549)	grad_norm 1.0918 (1.6627/0.6427)	mem 34602MB
[2025-01-19 11:24:07 internimage_b_1k_224] (main.py 510): INFO Train: [156/300][310/312]	eta 0:00:01 lr 0.001875	time 0.7167 (0.7398)	model_time 0.7166 (0.7351)	loss 3.4527 (3.1223)	grad_norm 1.3891 (1.5965/0.6869)	mem 34604MB
[2025-01-19 11:24:08 internimage_b_1k_224] (main.py 519): INFO EPOCH 156 training takes 0:03:50
[2025-01-19 11:24:08 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_156.pth saving......
[2025-01-19 11:24:09 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][100/312]	eta 0:02:40 lr 0.001868	time 0.7220 (0.7569)	model_time 0.7218 (0.7441)	loss 2.8508 (3.1576)	grad_norm 0.9393 (1.6355/0.6257)	mem 34602MB
[2025-01-19 11:24:11 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_156.pth saved !!!
[2025-01-19 11:24:16 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][110/312]	eta 0:02:32 lr 0.001868	time 0.7235 (0.7551)	model_time 0.7231 (0.7434)	loss 3.5120 (3.1758)	grad_norm 1.7366 (1.6495/0.6100)	mem 34602MB
[2025-01-19 11:24:19 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.503 (7.503)	Loss 0.7816 (0.7816)	Acc@1 84.180 (84.180)	Acc@5 97.070 (97.070)	Mem 34604MB
[2025-01-19 11:24:22 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.953)	Loss 1.0643 (0.9102)	Acc@1 76.562 (80.915)	Acc@5 94.360 (95.739)	Mem 34604MB
[2025-01-19 11:24:22 internimage_b_1k_224] (main.py 575): INFO [Epoch:156] * Acc@1 80.786 Acc@5 95.777
[2025-01-19 11:24:22 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.8%
[2025-01-19 11:24:22 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 11:24:24 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][120/312]	eta 0:02:25 lr 0.001867	time 0.8711 (0.7570)	model_time 0.8710 (0.7462)	loss 3.2259 (3.1714)	grad_norm 2.1235 (1.6650/0.6005)	mem 34602MB
[2025-01-19 11:24:26 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 11:24:26 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.79%
[2025-01-19 11:24:32 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][130/312]	eta 0:02:17 lr 0.001866	time 0.8078 (0.7563)	model_time 0.8073 (0.7463)	loss 3.2603 (3.1858)	grad_norm 1.7528 (1.6734/0.6034)	mem 34602MB
[2025-01-19 11:24:33 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.510 (7.510)	Loss 0.6552 (0.6552)	Acc@1 84.375 (84.375)	Acc@5 97.656 (97.656)	Mem 34604MB
[2025-01-19 11:24:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.953)	Loss 0.9523 (0.7914)	Acc@1 77.197 (81.543)	Acc@5 94.629 (95.972)	Mem 34604MB
[2025-01-19 11:24:36 internimage_b_1k_224] (main.py 575): INFO [Epoch:156] * Acc@1 81.426 Acc@5 96.015
[2025-01-19 11:24:36 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.4%
[2025-01-19 11:24:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:24:39 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][140/312]	eta 0:02:10 lr 0.001866	time 0.8109 (0.7582)	model_time 0.8108 (0.7489)	loss 3.4473 (3.1659)	grad_norm 1.9228 (1.6691/0.5923)	mem 34602MB
[2025-01-19 11:24:40 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:24:40 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.43%
[2025-01-19 11:24:42 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][0/312]	eta 0:11:07 lr 0.001875	time 2.1402 (2.1402)	model_time 0.7227 (0.7227)	loss 3.4061 (3.4061)	grad_norm 1.8742 (1.8742/0.0000)	mem 34604MB
[2025-01-19 11:24:47 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][150/312]	eta 0:02:02 lr 0.001865	time 0.8083 (0.7586)	model_time 0.8078 (0.7499)	loss 3.3679 (3.1632)	grad_norm 0.9293 (1.6419/0.5846)	mem 34602MB
[2025-01-19 11:24:50 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][10/312]	eta 0:04:20 lr 0.001874	time 0.7162 (0.8640)	model_time 0.7158 (0.7347)	loss 2.1922 (3.0493)	grad_norm 2.6296 (1.9308/1.3768)	mem 34604MB
[2025-01-19 11:24:55 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][160/312]	eta 0:01:55 lr 0.001864	time 0.7192 (0.7575)	model_time 0.7191 (0.7493)	loss 2.5388 (3.1652)	grad_norm 2.0976 (1.6184/0.5821)	mem 34602MB
[2025-01-19 11:24:57 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][20/312]	eta 0:03:55 lr 0.001874	time 0.7228 (0.8066)	model_time 0.7227 (0.7388)	loss 3.2723 (3.0451)	grad_norm 2.0059 (1.9287/1.2154)	mem 34604MB
[2025-01-19 11:25:02 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][170/312]	eta 0:01:47 lr 0.001864	time 0.8110 (0.7566)	model_time 0.8106 (0.7489)	loss 3.6357 (3.1607)	grad_norm 1.0899 (1.6122/0.5900)	mem 34602MB
[2025-01-19 11:25:05 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][30/312]	eta 0:03:43 lr 0.001873	time 0.8029 (0.7935)	model_time 0.8027 (0.7474)	loss 3.4460 (3.1569)	grad_norm 0.8082 (1.7127/1.0879)	mem 34604MB
[2025-01-19 11:25:09 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][180/312]	eta 0:01:39 lr 0.001863	time 0.7379 (0.7556)	model_time 0.7375 (0.7483)	loss 3.7149 (3.1646)	grad_norm 0.8827 (1.6004/0.5887)	mem 34602MB
[2025-01-19 11:25:13 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][40/312]	eta 0:03:35 lr 0.001872	time 0.7219 (0.7907)	model_time 0.7218 (0.7557)	loss 3.3558 (3.1974)	grad_norm 1.0162 (1.5410/1.0003)	mem 34604MB
[2025-01-19 11:25:17 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][190/312]	eta 0:01:32 lr 0.001862	time 0.7259 (0.7559)	model_time 0.7255 (0.7489)	loss 3.3941 (3.1685)	grad_norm 1.6758 (1.6227/0.6455)	mem 34602MB
[2025-01-19 11:25:20 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][50/312]	eta 0:03:24 lr 0.001872	time 0.7191 (0.7810)	model_time 0.7190 (0.7528)	loss 3.0010 (3.1536)	grad_norm 0.9088 (1.4762/0.9179)	mem 34604MB
[2025-01-19 11:25:24 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][200/312]	eta 0:01:24 lr 0.001862	time 0.7203 (0.7547)	model_time 0.7201 (0.7481)	loss 3.7944 (3.1712)	grad_norm 1.0411 (1.6169/0.6348)	mem 34602MB
[2025-01-19 11:25:27 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][60/312]	eta 0:03:14 lr 0.001871	time 0.7267 (0.7720)	model_time 0.7266 (0.7485)	loss 3.3787 (3.1255)	grad_norm 1.3564 (1.5216/0.8676)	mem 34604MB
[2025-01-19 11:25:32 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][210/312]	eta 0:01:16 lr 0.001861	time 0.7205 (0.7536)	model_time 0.7204 (0.7473)	loss 3.2068 (3.1855)	grad_norm 0.9583 (1.5915/0.6318)	mem 34602MB
[2025-01-19 11:25:35 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][70/312]	eta 0:03:05 lr 0.001870	time 0.7180 (0.7655)	model_time 0.7179 (0.7452)	loss 3.1692 (3.1496)	grad_norm 1.7770 (1.4823/0.8218)	mem 34604MB
[2025-01-19 11:25:39 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][220/312]	eta 0:01:09 lr 0.001860	time 0.7263 (0.7524)	model_time 0.7259 (0.7463)	loss 3.9343 (3.1853)	grad_norm 1.4539 (1.5877/0.6330)	mem 34602MB
[2025-01-19 11:25:42 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][80/312]	eta 0:02:56 lr 0.001870	time 0.7414 (0.7622)	model_time 0.7412 (0.7444)	loss 3.4676 (3.1665)	grad_norm 0.6703 (1.5011/0.8120)	mem 34604MB
[2025-01-19 11:25:46 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][230/312]	eta 0:01:01 lr 0.001860	time 0.7219 (0.7520)	model_time 0.7218 (0.7462)	loss 3.4182 (3.1968)	grad_norm 1.1412 (1.5864/0.6430)	mem 34602MB
[2025-01-19 11:25:49 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][90/312]	eta 0:02:48 lr 0.001869	time 0.7235 (0.7590)	model_time 0.7230 (0.7431)	loss 3.0882 (3.1386)	grad_norm 2.3288 (1.4925/0.7810)	mem 34604MB
[2025-01-19 11:25:54 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][240/312]	eta 0:00:54 lr 0.001859	time 0.7910 (0.7517)	model_time 0.7906 (0.7461)	loss 3.7099 (3.1999)	grad_norm 1.2766 (1.6112/0.6779)	mem 34602MB
[2025-01-19 11:25:57 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][100/312]	eta 0:02:40 lr 0.001868	time 0.7212 (0.7557)	model_time 0.7207 (0.7413)	loss 2.9520 (3.1640)	grad_norm 3.5001 (1.5604/0.8333)	mem 34604MB
[2025-01-19 11:26:01 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][250/312]	eta 0:00:46 lr 0.001858	time 0.8059 (0.7524)	model_time 0.8054 (0.7471)	loss 3.6080 (3.1967)	grad_norm 1.1825 (1.5961/0.6719)	mem 34602MB
[2025-01-19 11:26:04 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][110/312]	eta 0:02:32 lr 0.001868	time 0.7124 (0.7534)	model_time 0.7122 (0.7403)	loss 2.6862 (3.1648)	grad_norm 1.7670 (1.5940/0.8517)	mem 34604MB
[2025-01-19 11:26:09 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][260/312]	eta 0:00:39 lr 0.001858	time 0.8227 (0.7530)	model_time 0.8225 (0.7479)	loss 3.7021 (3.1865)	grad_norm 1.9031 (1.5959/0.6634)	mem 34602MB
[2025-01-19 11:26:11 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][120/312]	eta 0:02:24 lr 0.001867	time 0.7197 (0.7510)	model_time 0.7193 (0.7390)	loss 2.3500 (3.1592)	grad_norm 1.8714 (1.6341/0.8334)	mem 34604MB
[2025-01-19 11:26:17 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][270/312]	eta 0:00:31 lr 0.001857	time 0.8073 (0.7532)	model_time 0.8068 (0.7482)	loss 3.6181 (3.1836)	grad_norm 1.1912 (1.6075/0.6644)	mem 34602MB
[2025-01-19 11:26:18 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][130/312]	eta 0:02:16 lr 0.001866	time 0.7243 (0.7495)	model_time 0.7242 (0.7384)	loss 2.7635 (3.1653)	grad_norm 2.2218 (1.6337/0.8126)	mem 34604MB
[2025-01-19 11:26:24 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][280/312]	eta 0:00:24 lr 0.001856	time 0.7206 (0.7530)	model_time 0.7201 (0.7482)	loss 3.9427 (3.1877)	grad_norm 1.8309 (1.6061/0.6620)	mem 34602MB
[2025-01-19 11:26:26 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][140/312]	eta 0:02:08 lr 0.001866	time 0.7214 (0.7493)	model_time 0.7213 (0.7389)	loss 3.2809 (3.1686)	grad_norm 1.9706 (1.6249/0.7924)	mem 34604MB
[2025-01-19 11:26:32 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][290/312]	eta 0:00:16 lr 0.001856	time 0.8084 (0.7525)	model_time 0.8080 (0.7478)	loss 3.2374 (3.1952)	grad_norm 1.2065 (1.6053/0.6641)	mem 34602MB
[2025-01-19 11:26:34 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][150/312]	eta 0:02:01 lr 0.001865	time 0.8050 (0.7505)	model_time 0.8049 (0.7408)	loss 4.0077 (3.1709)	grad_norm 0.8815 (1.6289/0.7799)	mem 34604MB
[2025-01-19 11:26:39 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][300/312]	eta 0:00:09 lr 0.001855	time 0.7126 (0.7516)	model_time 0.7126 (0.7471)	loss 2.1386 (3.1883)	grad_norm 1.9985 (1.5991/0.6581)	mem 34602MB
[2025-01-19 11:26:41 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][160/312]	eta 0:01:54 lr 0.001864	time 0.7177 (0.7521)	model_time 0.7175 (0.7430)	loss 3.7582 (3.1770)	grad_norm 1.3081 (1.6283/0.7597)	mem 34604MB
[2025-01-19 11:26:46 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][310/312]	eta 0:00:01 lr 0.001854	time 0.7135 (0.7517)	model_time 0.7134 (0.7473)	loss 2.4945 (3.1873)	grad_norm 0.8615 (1.5889/0.6584)	mem 34602MB
[2025-01-19 11:26:47 internimage_b_1k_224] (main.py 519): INFO EPOCH 157 training takes 0:03:54
[2025-01-19 11:26:47 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_157.pth saving......
[2025-01-19 11:26:49 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][170/312]	eta 0:01:46 lr 0.001864	time 0.7165 (0.7514)	model_time 0.7160 (0.7428)	loss 2.3748 (3.1687)	grad_norm 1.0700 (1.6160/0.7474)	mem 34604MB
[2025-01-19 11:26:50 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_157.pth saved !!!
[2025-01-19 11:26:56 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][180/312]	eta 0:01:39 lr 0.001863	time 0.7195 (0.7500)	model_time 0.7191 (0.7419)	loss 3.4996 (3.1727)	grad_norm 1.4177 (1.6169/0.7355)	mem 34604MB
[2025-01-19 11:26:58 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.449 (7.449)	Loss 0.7455 (0.7455)	Acc@1 83.936 (83.936)	Acc@5 97.168 (97.168)	Mem 34602MB
[2025-01-19 11:27:01 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.943)	Loss 1.0397 (0.8851)	Acc@1 76.489 (80.853)	Acc@5 94.238 (95.619)	Mem 34602MB
[2025-01-19 11:27:01 internimage_b_1k_224] (main.py 575): INFO [Epoch:157] * Acc@1 80.706 Acc@5 95.681
[2025-01-19 11:27:01 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.7%
[2025-01-19 11:27:01 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.82%
[2025-01-19 11:27:03 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][190/312]	eta 0:01:31 lr 0.001862	time 0.7303 (0.7488)	model_time 0.7301 (0.7411)	loss 3.0858 (3.1819)	grad_norm 2.1197 (1.5896/0.7308)	mem 34604MB
[2025-01-19 11:27:10 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][200/312]	eta 0:01:23 lr 0.001862	time 0.7219 (0.7475)	model_time 0.7217 (0.7401)	loss 3.4991 (3.1823)	grad_norm 3.0334 (1.6070/0.7334)	mem 34604MB
[2025-01-19 11:27:11 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.314 (9.314)	Loss 0.6565 (0.6565)	Acc@1 84.204 (84.204)	Acc@5 97.583 (97.583)	Mem 34602MB
[2025-01-19 11:27:15 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.265)	Loss 0.9543 (0.7922)	Acc@1 77.148 (81.541)	Acc@5 94.458 (95.934)	Mem 34602MB
[2025-01-19 11:27:15 internimage_b_1k_224] (main.py 575): INFO [Epoch:157] * Acc@1 81.430 Acc@5 95.981
[2025-01-19 11:27:15 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.4%
[2025-01-19 11:27:15 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:27:18 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][210/312]	eta 0:01:16 lr 0.001861	time 0.7202 (0.7468)	model_time 0.7201 (0.7398)	loss 3.3972 (3.1868)	grad_norm 1.1349 (1.5955/0.7244)	mem 34604MB
[2025-01-19 11:27:20 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:27:20 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.43%
[2025-01-19 11:27:22 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][0/312]	eta 0:11:15 lr 0.001854	time 2.1649 (2.1649)	model_time 0.7568 (0.7568)	loss 3.7780 (3.7780)	grad_norm 1.3844 (1.3844/0.0000)	mem 34602MB
[2025-01-19 11:27:25 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][220/312]	eta 0:01:08 lr 0.001860	time 0.7196 (0.7458)	model_time 0.7191 (0.7391)	loss 3.3098 (3.1934)	grad_norm 1.0062 (1.5788/0.7153)	mem 34604MB
[2025-01-19 11:27:29 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][10/312]	eta 0:04:21 lr 0.001854	time 0.7356 (0.8669)	model_time 0.7354 (0.7386)	loss 3.1934 (3.4385)	grad_norm 1.4753 (1.2228/0.2995)	mem 34602MB
[2025-01-19 11:27:32 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][230/312]	eta 0:01:01 lr 0.001860	time 0.7329 (0.7451)	model_time 0.7327 (0.7386)	loss 3.1873 (3.1967)	grad_norm 1.0432 (1.5654/0.7049)	mem 34604MB
[2025-01-19 11:27:37 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][20/312]	eta 0:03:54 lr 0.001853	time 0.7153 (0.8025)	model_time 0.7148 (0.7351)	loss 3.1029 (3.1932)	grad_norm 1.2697 (1.2016/0.3740)	mem 34602MB
[2025-01-19 11:27:40 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][240/312]	eta 0:00:53 lr 0.001859	time 0.7249 (0.7445)	model_time 0.7244 (0.7382)	loss 2.9239 (3.1857)	grad_norm 1.1213 (1.5557/0.6945)	mem 34604MB
[2025-01-19 11:27:44 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][30/312]	eta 0:03:39 lr 0.001852	time 0.7295 (0.7781)	model_time 0.7293 (0.7324)	loss 2.7211 (3.1492)	grad_norm 1.1232 (1.3336/0.4785)	mem 34602MB
[2025-01-19 11:27:47 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][250/312]	eta 0:00:46 lr 0.001858	time 0.7289 (0.7441)	model_time 0.7285 (0.7381)	loss 3.2906 (3.1962)	grad_norm 2.5894 (1.5654/0.6936)	mem 34604MB
[2025-01-19 11:27:51 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][40/312]	eta 0:03:28 lr 0.001852	time 0.7219 (0.7671)	model_time 0.7215 (0.7324)	loss 2.6281 (3.1658)	grad_norm 1.5042 (1.4406/0.5907)	mem 34602MB
[2025-01-19 11:27:54 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][260/312]	eta 0:00:38 lr 0.001858	time 0.7226 (0.7443)	model_time 0.7222 (0.7385)	loss 3.2371 (3.1961)	grad_norm 1.0940 (1.5721/0.6927)	mem 34604MB
[2025-01-19 11:27:59 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][50/312]	eta 0:03:21 lr 0.001851	time 0.8035 (0.7679)	model_time 0.8034 (0.7400)	loss 3.4522 (3.2128)	grad_norm 0.7472 (1.4419/0.5864)	mem 34602MB
[2025-01-19 11:28:02 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][270/312]	eta 0:00:31 lr 0.001857	time 0.7992 (0.7453)	model_time 0.7990 (0.7397)	loss 2.9805 (3.1987)	grad_norm 1.0140 (1.5824/0.7018)	mem 34604MB
[2025-01-19 11:28:07 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][60/312]	eta 0:03:13 lr 0.001850	time 0.7180 (0.7689)	model_time 0.7175 (0.7455)	loss 3.7706 (3.2228)	grad_norm 1.7037 (1.5408/0.6397)	mem 34602MB
[2025-01-19 11:28:10 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][280/312]	eta 0:00:23 lr 0.001856	time 0.7170 (0.7468)	model_time 0.7169 (0.7414)	loss 2.7691 (3.1986)	grad_norm 2.5189 (1.5816/0.6944)	mem 34604MB
[2025-01-19 11:28:14 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][70/312]	eta 0:03:06 lr 0.001850	time 0.7210 (0.7701)	model_time 0.7205 (0.7500)	loss 3.7323 (3.2280)	grad_norm 1.1567 (1.5645/0.6287)	mem 34602MB
[2025-01-19 11:28:17 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][290/312]	eta 0:00:16 lr 0.001856	time 0.7245 (0.7466)	model_time 0.7240 (0.7414)	loss 3.2000 (3.2045)	grad_norm 2.0351 (1.5926/0.7010)	mem 34604MB
[2025-01-19 11:28:22 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][80/312]	eta 0:02:58 lr 0.001849	time 0.7319 (0.7684)	model_time 0.7314 (0.7506)	loss 2.1578 (3.2445)	grad_norm 1.3167 (1.5552/0.6384)	mem 34602MB
[2025-01-19 11:28:25 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][300/312]	eta 0:00:08 lr 0.001855	time 0.7141 (0.7457)	model_time 0.7140 (0.7407)	loss 3.0162 (3.2093)	grad_norm 1.5298 (1.5915/0.6947)	mem 34604MB
[2025-01-19 11:28:30 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][90/312]	eta 0:02:50 lr 0.001848	time 0.7229 (0.7673)	model_time 0.7227 (0.7515)	loss 3.1100 (3.2496)	grad_norm 1.4018 (1.5485/0.6206)	mem 34602MB
[2025-01-19 11:28:32 internimage_b_1k_224] (main.py 510): INFO Train: [157/300][310/312]	eta 0:00:01 lr 0.001854	time 0.7129 (0.7449)	model_time 0.7128 (0.7400)	loss 3.6868 (3.2085)	grad_norm 1.5975 (1.5766/0.6421)	mem 34604MB
[2025-01-19 11:28:33 internimage_b_1k_224] (main.py 519): INFO EPOCH 157 training takes 0:03:52
[2025-01-19 11:28:33 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_157.pth saving......
[2025-01-19 11:28:36 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_157.pth saved !!!
[2025-01-19 11:28:37 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][100/312]	eta 0:02:41 lr 0.001848	time 0.8054 (0.7641)	model_time 0.8049 (0.7498)	loss 3.5593 (3.2829)	grad_norm 0.7737 (1.4797/0.6266)	mem 34602MB
[2025-01-19 11:28:43 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.455 (7.455)	Loss 0.7880 (0.7880)	Acc@1 83.667 (83.667)	Acc@5 97.095 (97.095)	Mem 34604MB
[2025-01-19 11:28:44 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][110/312]	eta 0:02:33 lr 0.001847	time 0.7154 (0.7619)	model_time 0.7152 (0.7489)	loss 2.7391 (3.2753)	grad_norm 1.8833 (1.4817/0.6203)	mem 34602MB
[2025-01-19 11:28:46 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.952)	Loss 1.0774 (0.9238)	Acc@1 76.172 (80.617)	Acc@5 93.872 (95.568)	Mem 34604MB
[2025-01-19 11:28:47 internimage_b_1k_224] (main.py 575): INFO [Epoch:157] * Acc@1 80.528 Acc@5 95.613
[2025-01-19 11:28:47 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.5%
[2025-01-19 11:28:47 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.79%
[2025-01-19 11:28:52 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][120/312]	eta 0:02:26 lr 0.001846	time 0.7174 (0.7610)	model_time 0.7172 (0.7491)	loss 3.3710 (3.2535)	grad_norm 3.2416 (1.4958/0.6237)	mem 34602MB
[2025-01-19 11:28:56 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.247 (9.247)	Loss 0.6561 (0.6561)	Acc@1 84.424 (84.424)	Acc@5 97.632 (97.632)	Mem 34604MB
[2025-01-19 11:28:59 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][130/312]	eta 0:02:18 lr 0.001846	time 0.7213 (0.7598)	model_time 0.7207 (0.7487)	loss 3.2431 (3.2434)	grad_norm 1.5143 (1.5522/0.7021)	mem 34602MB
[2025-01-19 11:29:00 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.256)	Loss 0.9517 (0.7915)	Acc@1 77.246 (81.576)	Acc@5 94.653 (95.983)	Mem 34604MB
[2025-01-19 11:29:01 internimage_b_1k_224] (main.py 575): INFO [Epoch:157] * Acc@1 81.454 Acc@5 96.027
[2025-01-19 11:29:01 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.5%
[2025-01-19 11:29:01 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:29:05 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:29:05 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.45%
[2025-01-19 11:29:07 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][140/312]	eta 0:02:10 lr 0.001845	time 0.7375 (0.7579)	model_time 0.7373 (0.7476)	loss 2.6156 (3.2360)	grad_norm 1.5673 (1.5451/0.6975)	mem 34602MB
[2025-01-19 11:29:07 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][0/312]	eta 0:11:36 lr 0.001854	time 2.2334 (2.2334)	model_time 0.7414 (0.7414)	loss 3.1775 (3.1775)	grad_norm 1.0256 (1.0256/0.0000)	mem 34604MB
[2025-01-19 11:29:14 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][150/312]	eta 0:02:02 lr 0.001844	time 0.7212 (0.7557)	model_time 0.7207 (0.7460)	loss 2.0908 (3.2304)	grad_norm 1.5554 (1.5184/0.6836)	mem 34602MB
[2025-01-19 11:29:14 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][10/312]	eta 0:04:21 lr 0.001854	time 0.7267 (0.8649)	model_time 0.7266 (0.7290)	loss 3.1752 (3.2199)	grad_norm 1.4812 (1.4607/0.3580)	mem 34604MB
[2025-01-19 11:29:21 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][160/312]	eta 0:01:54 lr 0.001844	time 0.7304 (0.7545)	model_time 0.7299 (0.7454)	loss 3.0426 (3.2374)	grad_norm 2.9913 (1.5301/0.6861)	mem 34602MB
[2025-01-19 11:29:21 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][20/312]	eta 0:03:53 lr 0.001853	time 0.7208 (0.8013)	model_time 0.7206 (0.7300)	loss 4.0118 (3.3459)	grad_norm 0.8134 (1.3631/0.3952)	mem 34604MB
[2025-01-19 11:29:29 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][30/312]	eta 0:03:39 lr 0.001852	time 0.7446 (0.7776)	model_time 0.7445 (0.7291)	loss 3.0198 (3.2770)	grad_norm 1.1764 (1.4418/0.5767)	mem 34604MB
[2025-01-19 11:29:29 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][170/312]	eta 0:01:47 lr 0.001843	time 0.8061 (0.7544)	model_time 0.8059 (0.7458)	loss 3.4684 (3.2340)	grad_norm 2.3049 (1.5409/0.6759)	mem 34602MB
[2025-01-19 11:29:36 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][40/312]	eta 0:03:28 lr 0.001852	time 0.7365 (0.7665)	model_time 0.7364 (0.7298)	loss 3.7120 (3.2731)	grad_norm 2.5555 (1.6275/0.7670)	mem 34604MB
[2025-01-19 11:29:36 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][180/312]	eta 0:01:39 lr 0.001842	time 0.8181 (0.7553)	model_time 0.8176 (0.7472)	loss 3.4524 (3.2228)	grad_norm 1.7575 (1.5325/0.6639)	mem 34602MB
[2025-01-19 11:29:43 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][50/312]	eta 0:03:18 lr 0.001851	time 0.7260 (0.7584)	model_time 0.7259 (0.7289)	loss 2.4578 (3.2198)	grad_norm 2.0063 (1.7065/0.7892)	mem 34604MB
[2025-01-19 11:29:44 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][190/312]	eta 0:01:32 lr 0.001842	time 0.7255 (0.7557)	model_time 0.7250 (0.7480)	loss 3.1218 (3.2102)	grad_norm 0.8129 (1.5400/0.6750)	mem 34602MB
[2025-01-19 11:29:51 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][60/312]	eta 0:03:10 lr 0.001850	time 0.7256 (0.7546)	model_time 0.7254 (0.7298)	loss 3.3469 (3.2371)	grad_norm 0.8590 (1.7135/0.7716)	mem 34604MB
[2025-01-19 11:29:52 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][200/312]	eta 0:01:24 lr 0.001841	time 0.7189 (0.7557)	model_time 0.7188 (0.7484)	loss 3.5403 (3.2022)	grad_norm 1.7966 (1.5717/0.7059)	mem 34602MB
[2025-01-19 11:29:58 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][70/312]	eta 0:03:02 lr 0.001850	time 0.7164 (0.7538)	model_time 0.7162 (0.7325)	loss 2.9652 (3.2233)	grad_norm 1.0752 (1.6947/0.7538)	mem 34604MB
[2025-01-19 11:29:59 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][210/312]	eta 0:01:17 lr 0.001840	time 0.7246 (0.7561)	model_time 0.7245 (0.7490)	loss 2.7203 (3.2030)	grad_norm 1.6972 (1.5676/0.6977)	mem 34602MB
[2025-01-19 11:30:06 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][80/312]	eta 0:02:55 lr 0.001849	time 0.8526 (0.7571)	model_time 0.8522 (0.7383)	loss 2.9570 (3.1961)	grad_norm 1.9351 (1.6637/0.7376)	mem 34604MB
[2025-01-19 11:30:07 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][220/312]	eta 0:01:09 lr 0.001840	time 0.7327 (0.7549)	model_time 0.7325 (0.7482)	loss 3.2255 (3.2087)	grad_norm 1.0363 (1.5441/0.6922)	mem 34602MB
[2025-01-19 11:30:14 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][90/312]	eta 0:02:48 lr 0.001848	time 0.7263 (0.7593)	model_time 0.7261 (0.7426)	loss 3.3315 (3.1893)	grad_norm 1.3485 (1.6781/0.7197)	mem 34604MB
[2025-01-19 11:30:14 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][230/312]	eta 0:01:01 lr 0.001839	time 0.7181 (0.7544)	model_time 0.7179 (0.7480)	loss 2.4736 (3.1990)	grad_norm 2.9810 (1.5429/0.6915)	mem 34602MB
[2025-01-19 11:30:21 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][100/312]	eta 0:02:40 lr 0.001848	time 0.7222 (0.7567)	model_time 0.7220 (0.7416)	loss 3.3762 (3.1866)	grad_norm 1.3076 (1.6357/0.7021)	mem 34604MB
[2025-01-19 11:30:21 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][240/312]	eta 0:00:54 lr 0.001838	time 0.7234 (0.7543)	model_time 0.7230 (0.7481)	loss 2.6763 (3.1896)	grad_norm 1.2716 (1.5434/0.6862)	mem 34602MB
[2025-01-19 11:30:28 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][110/312]	eta 0:02:32 lr 0.001847	time 0.7175 (0.7543)	model_time 0.7171 (0.7406)	loss 3.8818 (3.1932)	grad_norm 2.3810 (1.6382/0.6887)	mem 34604MB
[2025-01-19 11:30:29 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][250/312]	eta 0:00:46 lr 0.001838	time 0.7505 (0.7538)	model_time 0.7501 (0.7479)	loss 2.2619 (3.1900)	grad_norm 1.1671 (1.5361/0.6795)	mem 34602MB
[2025-01-19 11:30:36 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][120/312]	eta 0:02:24 lr 0.001846	time 0.7203 (0.7528)	model_time 0.7201 (0.7401)	loss 3.5267 (3.1929)	grad_norm 0.9593 (1.6914/0.7643)	mem 34604MB
[2025-01-19 11:30:36 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][260/312]	eta 0:00:39 lr 0.001837	time 0.7600 (0.7531)	model_time 0.7598 (0.7474)	loss 3.0131 (3.1905)	grad_norm 1.0292 (1.5315/0.6707)	mem 34602MB
[2025-01-19 11:30:43 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][130/312]	eta 0:02:16 lr 0.001846	time 0.7221 (0.7509)	model_time 0.7217 (0.7392)	loss 2.7442 (3.1930)	grad_norm 1.5443 (1.6832/0.7447)	mem 34604MB
[2025-01-19 11:30:44 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][270/312]	eta 0:00:31 lr 0.001836	time 0.7362 (0.7522)	model_time 0.7361 (0.7467)	loss 3.8681 (3.1831)	grad_norm 2.1448 (1.5564/0.6876)	mem 34602MB
[2025-01-19 11:30:50 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][140/312]	eta 0:02:08 lr 0.001845	time 0.7233 (0.7493)	model_time 0.7232 (0.7384)	loss 2.2461 (3.1940)	grad_norm 2.5320 (1.6657/0.7377)	mem 34604MB
[2025-01-19 11:30:51 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][280/312]	eta 0:00:24 lr 0.001836	time 0.7385 (0.7519)	model_time 0.7383 (0.7465)	loss 3.6335 (3.1857)	grad_norm 1.5279 (1.5638/0.6836)	mem 34602MB
[2025-01-19 11:30:58 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][150/312]	eta 0:02:01 lr 0.001844	time 0.7224 (0.7479)	model_time 0.7220 (0.7377)	loss 3.0949 (3.1829)	grad_norm 2.0652 (1.6530/0.7224)	mem 34604MB
[2025-01-19 11:30:58 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][290/312]	eta 0:00:16 lr 0.001835	time 0.8046 (0.7518)	model_time 0.8045 (0.7467)	loss 2.6299 (3.1812)	grad_norm 0.9996 (1.5544/0.6760)	mem 34602MB
[2025-01-19 11:31:05 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][160/312]	eta 0:01:53 lr 0.001844	time 0.7287 (0.7465)	model_time 0.7286 (0.7369)	loss 3.3983 (3.1897)	grad_norm 2.8676 (1.6566/0.7221)	mem 34604MB
[2025-01-19 11:31:06 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][300/312]	eta 0:00:09 lr 0.001834	time 0.8203 (0.7524)	model_time 0.8202 (0.7474)	loss 3.0636 (3.1860)	grad_norm 2.4706 (1.5741/0.6893)	mem 34602MB
[2025-01-19 11:31:12 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][170/312]	eta 0:01:45 lr 0.001843	time 0.7263 (0.7456)	model_time 0.7261 (0.7365)	loss 3.2795 (3.1857)	grad_norm 3.2169 (1.6578/0.7169)	mem 34604MB
[2025-01-19 11:31:14 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][310/312]	eta 0:00:01 lr 0.001834	time 0.7984 (0.7524)	model_time 0.7983 (0.7475)	loss 2.9669 (3.1807)	grad_norm 2.1893 (1.5894/0.6899)	mem 34602MB
[2025-01-19 11:31:15 internimage_b_1k_224] (main.py 519): INFO EPOCH 158 training takes 0:03:54
[2025-01-19 11:31:15 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_158.pth saving......
[2025-01-19 11:31:18 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_158.pth saved !!!
[2025-01-19 11:31:19 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][180/312]	eta 0:01:38 lr 0.001842	time 0.7414 (0.7447)	model_time 0.7410 (0.7361)	loss 3.0650 (3.1693)	grad_norm 0.9919 (1.6399/0.7049)	mem 34604MB
[2025-01-19 11:31:26 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.942 (7.942)	Loss 0.7956 (0.7956)	Acc@1 84.131 (84.131)	Acc@5 97.095 (97.095)	Mem 34602MB
[2025-01-19 11:31:27 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][190/312]	eta 0:01:30 lr 0.001842	time 0.7080 (0.7447)	model_time 0.7077 (0.7365)	loss 2.3598 (3.1526)	grad_norm 0.7663 (1.6271/0.6996)	mem 34604MB
[2025-01-19 11:31:29 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.017)	Loss 1.0716 (0.9166)	Acc@1 76.416 (81.026)	Acc@5 94.019 (95.685)	Mem 34602MB
[2025-01-19 11:31:29 internimage_b_1k_224] (main.py 575): INFO [Epoch:158] * Acc@1 80.906 Acc@5 95.747
[2025-01-19 11:31:29 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.9%
[2025-01-19 11:31:29 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 11:31:32 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 11:31:32 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.91%
[2025-01-19 11:31:35 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][200/312]	eta 0:01:23 lr 0.001841	time 0.8272 (0.7459)	model_time 0.8271 (0.7382)	loss 3.8753 (3.1535)	grad_norm 0.9301 (1.6173/0.7018)	mem 34604MB
[2025-01-19 11:31:40 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.441 (7.441)	Loss 0.6572 (0.6572)	Acc@1 84.204 (84.204)	Acc@5 97.583 (97.583)	Mem 34602MB
[2025-01-19 11:31:42 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][210/312]	eta 0:01:16 lr 0.001840	time 0.7188 (0.7475)	model_time 0.7186 (0.7401)	loss 3.3542 (3.1522)	grad_norm 1.2636 (1.6196/0.6958)	mem 34604MB
[2025-01-19 11:31:43 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.961)	Loss 0.9539 (0.7923)	Acc@1 77.344 (81.570)	Acc@5 94.482 (95.961)	Mem 34602MB
[2025-01-19 11:31:43 internimage_b_1k_224] (main.py 575): INFO [Epoch:158] * Acc@1 81.454 Acc@5 96.007
[2025-01-19 11:31:43 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.5%
[2025-01-19 11:31:43 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:31:47 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:31:47 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.45%
[2025-01-19 11:31:49 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][0/312]	eta 0:11:34 lr 0.001834	time 2.2247 (2.2247)	model_time 0.7595 (0.7595)	loss 4.0190 (4.0190)	grad_norm 1.9817 (1.9817/0.0000)	mem 34602MB
[2025-01-19 11:31:50 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][220/312]	eta 0:01:08 lr 0.001840	time 0.7126 (0.7468)	model_time 0.7125 (0.7397)	loss 2.5473 (3.1427)	grad_norm 1.3894 (1.6457/0.7122)	mem 34604MB
[2025-01-19 11:31:57 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][10/312]	eta 0:04:26 lr 0.001833	time 0.7209 (0.8823)	model_time 0.7208 (0.7488)	loss 2.2825 (3.2410)	grad_norm 4.7557 (2.0977/0.9941)	mem 34602MB
[2025-01-19 11:31:57 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][230/312]	eta 0:01:01 lr 0.001839	time 0.7089 (0.7458)	model_time 0.7087 (0.7390)	loss 2.2801 (3.1414)	grad_norm 0.9393 (1.6576/0.7167)	mem 34604MB
[2025-01-19 11:32:04 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][240/312]	eta 0:00:53 lr 0.001838	time 0.7202 (0.7451)	model_time 0.7201 (0.7386)	loss 2.8919 (3.1474)	grad_norm 1.7627 (1.6524/0.7123)	mem 34604MB
[2025-01-19 11:32:04 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][20/312]	eta 0:03:59 lr 0.001832	time 0.7325 (0.8185)	model_time 0.7324 (0.7484)	loss 3.1103 (3.1394)	grad_norm 1.4452 (1.9855/0.9582)	mem 34602MB
[2025-01-19 11:32:11 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][250/312]	eta 0:00:46 lr 0.001838	time 0.7200 (0.7443)	model_time 0.7195 (0.7380)	loss 3.3055 (3.1484)	grad_norm 1.4910 (1.6371/0.7056)	mem 34604MB
[2025-01-19 11:32:12 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][30/312]	eta 0:03:42 lr 0.001832	time 0.7462 (0.7899)	model_time 0.7459 (0.7423)	loss 2.5352 (3.0995)	grad_norm 1.8486 (1.9592/0.8779)	mem 34602MB
[2025-01-19 11:32:19 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][260/312]	eta 0:00:38 lr 0.001837	time 0.7422 (0.7436)	model_time 0.7417 (0.7376)	loss 3.9427 (3.1642)	grad_norm 1.3968 (1.6466/0.7086)	mem 34604MB
[2025-01-19 11:32:19 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][40/312]	eta 0:03:31 lr 0.001831	time 0.7362 (0.7781)	model_time 0.7361 (0.7420)	loss 3.2920 (3.1428)	grad_norm 0.9897 (1.7930/0.8374)	mem 34602MB
[2025-01-19 11:32:26 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][270/312]	eta 0:00:31 lr 0.001836	time 0.7165 (0.7430)	model_time 0.7161 (0.7371)	loss 3.0245 (3.1655)	grad_norm 1.4041 (1.6294/0.7018)	mem 34604MB
[2025-01-19 11:32:27 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][50/312]	eta 0:03:22 lr 0.001830	time 0.7452 (0.7731)	model_time 0.7451 (0.7440)	loss 3.8584 (3.1353)	grad_norm 1.4316 (1.6435/0.8130)	mem 34602MB
[2025-01-19 11:32:33 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][280/312]	eta 0:00:23 lr 0.001836	time 0.7223 (0.7424)	model_time 0.7221 (0.7368)	loss 2.4046 (3.1685)	grad_norm 1.9343 (1.6189/0.6958)	mem 34604MB
[2025-01-19 11:32:34 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][60/312]	eta 0:03:13 lr 0.001830	time 0.8285 (0.7683)	model_time 0.8283 (0.7439)	loss 2.6138 (3.1229)	grad_norm 1.1917 (1.5974/0.7976)	mem 34602MB
[2025-01-19 11:32:41 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][290/312]	eta 0:00:16 lr 0.001835	time 0.7324 (0.7420)	model_time 0.7322 (0.7365)	loss 3.6989 (3.1641)	grad_norm 1.0828 (1.6610/0.7487)	mem 34604MB
[2025-01-19 11:32:41 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][70/312]	eta 0:03:04 lr 0.001829	time 0.7238 (0.7630)	model_time 0.7233 (0.7421)	loss 2.2516 (3.1362)	grad_norm 1.0542 (1.5416/0.7698)	mem 34602MB
[2025-01-19 11:32:48 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][300/312]	eta 0:00:08 lr 0.001834	time 0.7122 (0.7413)	model_time 0.7120 (0.7360)	loss 3.4441 (3.1750)	grad_norm 2.1967 (1.6606/0.7529)	mem 34604MB
[2025-01-19 11:32:49 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][80/312]	eta 0:02:56 lr 0.001828	time 0.7196 (0.7593)	model_time 0.7192 (0.7408)	loss 3.3849 (3.1656)	grad_norm 1.0979 (1.5055/0.7465)	mem 34602MB
[2025-01-19 11:32:55 internimage_b_1k_224] (main.py 510): INFO Train: [158/300][310/312]	eta 0:00:01 lr 0.001834	time 0.7893 (0.7408)	model_time 0.7892 (0.7356)	loss 3.1344 (3.1770)	grad_norm 1.9363 (1.6517/0.7559)	mem 34604MB
[2025-01-19 11:32:56 internimage_b_1k_224] (main.py 519): INFO EPOCH 158 training takes 0:03:51
[2025-01-19 11:32:56 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_158.pth saving......
[2025-01-19 11:32:56 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][90/312]	eta 0:02:48 lr 0.001828	time 0.7270 (0.7572)	model_time 0.7268 (0.7407)	loss 3.3693 (3.1610)	grad_norm 2.0631 (1.5084/0.7266)	mem 34602MB
[2025-01-19 11:32:59 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_158.pth saved !!!
[2025-01-19 11:33:04 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][100/312]	eta 0:02:40 lr 0.001827	time 0.8060 (0.7575)	model_time 0.8058 (0.7426)	loss 2.9887 (3.1430)	grad_norm 2.2543 (1.5430/0.7371)	mem 34602MB
[2025-01-19 11:33:07 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.313 (7.313)	Loss 0.8091 (0.8091)	Acc@1 83.984 (83.984)	Acc@5 97.192 (97.192)	Mem 34604MB
[2025-01-19 11:33:10 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.946)	Loss 1.0494 (0.9174)	Acc@1 76.978 (80.919)	Acc@5 94.141 (95.654)	Mem 34604MB
[2025-01-19 11:33:10 internimage_b_1k_224] (main.py 575): INFO [Epoch:158] * Acc@1 80.830 Acc@5 95.685
[2025-01-19 11:33:10 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.8%
[2025-01-19 11:33:10 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 11:33:11 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][110/312]	eta 0:02:32 lr 0.001826	time 0.7196 (0.7573)	model_time 0.7192 (0.7438)	loss 3.6374 (3.1333)	grad_norm 1.1615 (1.5794/0.7619)	mem 34602MB
[2025-01-19 11:33:13 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 11:33:13 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.83%
[2025-01-19 11:33:19 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][120/312]	eta 0:02:25 lr 0.001826	time 0.8130 (0.7579)	model_time 0.8129 (0.7455)	loss 2.4565 (3.1326)	grad_norm 1.4045 (1.6024/0.7664)	mem 34602MB
[2025-01-19 11:33:20 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.268 (7.268)	Loss 0.6568 (0.6568)	Acc@1 84.497 (84.497)	Acc@5 97.656 (97.656)	Mem 34604MB
[2025-01-19 11:33:24 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.935)	Loss 0.9512 (0.7917)	Acc@1 77.295 (81.627)	Acc@5 94.678 (96.001)	Mem 34604MB
[2025-01-19 11:33:24 internimage_b_1k_224] (main.py 575): INFO [Epoch:158] * Acc@1 81.500 Acc@5 96.043
[2025-01-19 11:33:24 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.5%
[2025-01-19 11:33:24 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:33:26 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][130/312]	eta 0:02:17 lr 0.001825	time 0.7260 (0.7573)	model_time 0.7258 (0.7458)	loss 3.7502 (3.1476)	grad_norm 1.1616 (1.6055/0.7475)	mem 34602MB
[2025-01-19 11:33:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:33:28 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.50%
[2025-01-19 11:33:30 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][0/312]	eta 0:11:33 lr 0.001834	time 2.2242 (2.2242)	model_time 0.7288 (0.7288)	loss 3.1262 (3.1262)	grad_norm 1.4847 (1.4847/0.0000)	mem 34604MB
[2025-01-19 11:33:34 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][140/312]	eta 0:02:10 lr 0.001824	time 0.7303 (0.7563)	model_time 0.7301 (0.7456)	loss 3.3347 (3.1431)	grad_norm 1.9198 (1.5765/0.7387)	mem 34602MB
[2025-01-19 11:33:38 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][10/312]	eta 0:04:33 lr 0.001833	time 0.8265 (0.9051)	model_time 0.8263 (0.7689)	loss 2.5909 (3.1905)	grad_norm 0.7697 (1.5199/0.4138)	mem 34604MB
[2025-01-19 11:33:41 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][150/312]	eta 0:02:02 lr 0.001824	time 0.7157 (0.7546)	model_time 0.7155 (0.7446)	loss 2.7100 (3.1315)	grad_norm 1.5781 (1.5794/0.7217)	mem 34602MB
[2025-01-19 11:33:45 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][20/312]	eta 0:04:06 lr 0.001832	time 0.7237 (0.8434)	model_time 0.7236 (0.7719)	loss 3.7634 (3.2223)	grad_norm 2.9467 (1.5965/0.4970)	mem 34604MB
[2025-01-19 11:33:48 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][160/312]	eta 0:01:54 lr 0.001823	time 0.7326 (0.7534)	model_time 0.7324 (0.7439)	loss 3.8610 (3.1458)	grad_norm 2.0067 (1.6072/0.7337)	mem 34602MB
[2025-01-19 11:33:53 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][30/312]	eta 0:03:47 lr 0.001832	time 0.7262 (0.8079)	model_time 0.7258 (0.7594)	loss 2.7458 (3.1593)	grad_norm 1.2622 (1.6630/0.5419)	mem 34604MB
[2025-01-19 11:33:56 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][170/312]	eta 0:01:47 lr 0.001822	time 0.7171 (0.7539)	model_time 0.7170 (0.7450)	loss 3.3402 (3.1358)	grad_norm 2.1616 (1.6193/0.7264)	mem 34602MB
[2025-01-19 11:34:00 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][40/312]	eta 0:03:34 lr 0.001831	time 0.7094 (0.7880)	model_time 0.7090 (0.7512)	loss 2.4860 (3.1346)	grad_norm 1.6729 (1.5794/0.5115)	mem 34604MB
[2025-01-19 11:34:03 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][180/312]	eta 0:01:39 lr 0.001822	time 0.8116 (0.7530)	model_time 0.8114 (0.7446)	loss 2.2748 (3.1416)	grad_norm 3.1410 (1.6291/0.7375)	mem 34602MB
[2025-01-19 11:34:07 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][50/312]	eta 0:03:23 lr 0.001830	time 0.7425 (0.7785)	model_time 0.7423 (0.7488)	loss 2.7231 (3.1291)	grad_norm 1.9639 (1.5280/0.5203)	mem 34604MB
[2025-01-19 11:34:11 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][190/312]	eta 0:01:31 lr 0.001821	time 0.7213 (0.7517)	model_time 0.7211 (0.7437)	loss 3.1426 (3.1438)	grad_norm 1.5581 (1.6266/0.7289)	mem 34602MB
[2025-01-19 11:34:15 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][60/312]	eta 0:03:13 lr 0.001830	time 0.7156 (0.7696)	model_time 0.7152 (0.7447)	loss 3.1598 (3.1170)	grad_norm 1.4228 (1.4978/0.5036)	mem 34604MB
[2025-01-19 11:34:18 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][200/312]	eta 0:01:24 lr 0.001820	time 0.7339 (0.7510)	model_time 0.7337 (0.7433)	loss 3.5655 (3.1511)	grad_norm 2.0644 (1.6279/0.7156)	mem 34602MB
[2025-01-19 11:34:22 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][70/312]	eta 0:03:04 lr 0.001829	time 0.7177 (0.7641)	model_time 0.7173 (0.7427)	loss 2.8005 (3.1458)	grad_norm 0.9703 (1.4911/0.5138)	mem 34604MB
[2025-01-19 11:34:25 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][210/312]	eta 0:01:16 lr 0.001820	time 0.7198 (0.7506)	model_time 0.7196 (0.7433)	loss 3.1796 (3.1628)	grad_norm 1.3506 (1.6360/0.7202)	mem 34602MB
[2025-01-19 11:34:29 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][80/312]	eta 0:02:56 lr 0.001828	time 0.7287 (0.7592)	model_time 0.7282 (0.7404)	loss 2.3700 (3.1210)	grad_norm 1.4372 (1.4778/0.5114)	mem 34604MB
[2025-01-19 11:34:33 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][220/312]	eta 0:01:09 lr 0.001819	time 0.8009 (0.7509)	model_time 0.8008 (0.7439)	loss 2.8376 (3.1627)	grad_norm 0.8692 (1.6341/0.7158)	mem 34602MB
[2025-01-19 11:34:36 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][90/312]	eta 0:02:47 lr 0.001828	time 0.7189 (0.7559)	model_time 0.7183 (0.7391)	loss 3.7640 (3.1329)	grad_norm 2.8401 (1.5262/0.5884)	mem 34604MB
[2025-01-19 11:34:41 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][230/312]	eta 0:01:01 lr 0.001818	time 0.8055 (0.7515)	model_time 0.8053 (0.7448)	loss 2.9826 (3.1622)	grad_norm 0.7957 (1.6097/0.7123)	mem 34602MB
[2025-01-19 11:34:44 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][100/312]	eta 0:02:39 lr 0.001827	time 0.7224 (0.7534)	model_time 0.7220 (0.7383)	loss 2.6368 (3.1186)	grad_norm 0.6460 (1.5483/0.6310)	mem 34604MB
[2025-01-19 11:34:48 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][240/312]	eta 0:00:54 lr 0.001818	time 0.8636 (0.7525)	model_time 0.8634 (0.7461)	loss 3.4695 (3.1618)	grad_norm 2.9995 (1.6172/0.7209)	mem 34602MB
[2025-01-19 11:34:51 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][110/312]	eta 0:02:31 lr 0.001826	time 0.7188 (0.7506)	model_time 0.7184 (0.7367)	loss 3.6472 (3.1221)	grad_norm 3.3952 (1.5546/0.6472)	mem 34604MB
[2025-01-19 11:34:56 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][250/312]	eta 0:00:46 lr 0.001817	time 0.7238 (0.7523)	model_time 0.7236 (0.7461)	loss 3.1298 (3.1487)	grad_norm 1.1418 (1.6133/0.7162)	mem 34602MB
[2025-01-19 11:34:58 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][120/312]	eta 0:02:23 lr 0.001826	time 0.7161 (0.7498)	model_time 0.7156 (0.7371)	loss 3.4749 (3.1294)	grad_norm 1.4972 (1.5719/0.6381)	mem 34604MB
[2025-01-19 11:35:03 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][260/312]	eta 0:00:39 lr 0.001816	time 0.7254 (0.7521)	model_time 0.7252 (0.7461)	loss 3.1724 (3.1539)	grad_norm 1.5523 (1.6089/0.7085)	mem 34602MB
[2025-01-19 11:35:06 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][130/312]	eta 0:02:16 lr 0.001825	time 0.8107 (0.7513)	model_time 0.8105 (0.7395)	loss 2.9437 (3.1211)	grad_norm 0.8559 (1.5633/0.6325)	mem 34604MB
[2025-01-19 11:35:11 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][270/312]	eta 0:00:31 lr 0.001816	time 0.7228 (0.7511)	model_time 0.7226 (0.7454)	loss 3.4628 (3.1621)	grad_norm 1.5762 (1.5951/0.7017)	mem 34602MB
[2025-01-19 11:35:14 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][140/312]	eta 0:02:09 lr 0.001824	time 0.8335 (0.7540)	model_time 0.8331 (0.7431)	loss 3.2897 (3.1406)	grad_norm 1.5998 (1.5630/0.6288)	mem 34604MB
[2025-01-19 11:35:18 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][280/312]	eta 0:00:24 lr 0.001815	time 0.7279 (0.7506)	model_time 0.7274 (0.7451)	loss 3.3446 (3.1631)	grad_norm 1.1885 (1.5804/0.6943)	mem 34602MB
[2025-01-19 11:35:21 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][150/312]	eta 0:02:01 lr 0.001824	time 0.7192 (0.7524)	model_time 0.7188 (0.7421)	loss 3.2315 (3.1531)	grad_norm 2.4348 (1.5897/0.6327)	mem 34604MB
[2025-01-19 11:35:26 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][290/312]	eta 0:00:16 lr 0.001814	time 0.7156 (0.7514)	model_time 0.7155 (0.7461)	loss 3.3530 (3.1670)	grad_norm 1.4387 (1.5687/0.6877)	mem 34602MB
[2025-01-19 11:35:29 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][160/312]	eta 0:01:54 lr 0.001823	time 0.7656 (0.7509)	model_time 0.7654 (0.7412)	loss 2.7378 (3.1457)	grad_norm 1.5986 (1.6072/0.6623)	mem 34604MB
[2025-01-19 11:35:33 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][300/312]	eta 0:00:09 lr 0.001814	time 0.8009 (0.7513)	model_time 0.8008 (0.7461)	loss 2.5318 (3.1690)	grad_norm 2.2869 (1.5745/0.6950)	mem 34602MB
[2025-01-19 11:35:36 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][170/312]	eta 0:01:46 lr 0.001822	time 0.7272 (0.7496)	model_time 0.7271 (0.7405)	loss 3.5786 (3.1573)	grad_norm 1.7689 (1.6307/0.6644)	mem 34604MB
[2025-01-19 11:35:40 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][310/312]	eta 0:00:01 lr 0.001813	time 0.7149 (0.7505)	model_time 0.7148 (0.7455)	loss 3.8218 (3.1783)	grad_norm 1.9291 (1.5647/0.6771)	mem 34602MB
[2025-01-19 11:35:41 internimage_b_1k_224] (main.py 519): INFO EPOCH 159 training takes 0:03:54
[2025-01-19 11:35:41 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_159.pth saving......
[2025-01-19 11:35:43 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][180/312]	eta 0:01:38 lr 0.001822	time 0.7142 (0.7486)	model_time 0.7137 (0.7399)	loss 3.4583 (3.1498)	grad_norm 0.9371 (1.6366/0.6691)	mem 34604MB
[2025-01-19 11:35:44 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_159.pth saved !!!
[2025-01-19 11:35:50 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][190/312]	eta 0:01:31 lr 0.001821	time 0.7209 (0.7472)	model_time 0.7208 (0.7390)	loss 3.5008 (3.1622)	grad_norm 2.7528 (1.6579/0.6803)	mem 34604MB
[2025-01-19 11:35:52 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.755 (7.755)	Loss 0.7762 (0.7762)	Acc@1 83.960 (83.960)	Acc@5 97.192 (97.192)	Mem 34602MB
[2025-01-19 11:35:56 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.008)	Loss 1.0693 (0.8996)	Acc@1 76.538 (80.922)	Acc@5 93.872 (95.732)	Mem 34602MB
[2025-01-19 11:35:56 internimage_b_1k_224] (main.py 575): INFO [Epoch:159] * Acc@1 80.778 Acc@5 95.781
[2025-01-19 11:35:56 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.8%
[2025-01-19 11:35:56 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.91%
[2025-01-19 11:35:58 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][200/312]	eta 0:01:23 lr 0.001820	time 0.7229 (0.7460)	model_time 0.7225 (0.7382)	loss 2.9187 (3.1567)	grad_norm 3.0179 (1.6696/0.6768)	mem 34604MB
[2025-01-19 11:36:05 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][210/312]	eta 0:01:16 lr 0.001820	time 0.7183 (0.7452)	model_time 0.7181 (0.7378)	loss 3.5286 (3.1641)	grad_norm 1.7460 (1.6584/0.6721)	mem 34604MB
[2025-01-19 11:36:06 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 10.108 (10.108)	Loss 0.6579 (0.6579)	Acc@1 84.277 (84.277)	Acc@5 97.583 (97.583)	Mem 34602MB
[2025-01-19 11:36:11 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.380)	Loss 0.9536 (0.7925)	Acc@1 77.271 (81.612)	Acc@5 94.580 (95.965)	Mem 34602MB
[2025-01-19 11:36:11 internimage_b_1k_224] (main.py 575): INFO [Epoch:159] * Acc@1 81.490 Acc@5 96.015
[2025-01-19 11:36:11 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.5%
[2025-01-19 11:36:11 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:36:12 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][220/312]	eta 0:01:08 lr 0.001819	time 0.7217 (0.7443)	model_time 0.7213 (0.7371)	loss 3.0847 (3.1618)	grad_norm 3.7729 (1.6784/0.6829)	mem 34604MB
[2025-01-19 11:36:15 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:36:15 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.49%
[2025-01-19 11:36:17 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][0/312]	eta 0:10:39 lr 0.001813	time 2.0503 (2.0503)	model_time 0.7313 (0.7313)	loss 2.6908 (2.6908)	grad_norm 2.8099 (2.8099/0.0000)	mem 34602MB
[2025-01-19 11:36:19 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][230/312]	eta 0:01:00 lr 0.001818	time 0.7066 (0.7435)	model_time 0.7064 (0.7367)	loss 3.1926 (3.1723)	grad_norm 1.0184 (1.7081/0.7119)	mem 34604MB
[2025-01-19 11:36:25 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][10/312]	eta 0:04:22 lr 0.001812	time 0.8067 (0.8686)	model_time 0.7894 (0.7468)	loss 3.7911 (3.2974)	grad_norm 1.0496 (1.5801/0.7833)	mem 34602MB
[2025-01-19 11:36:27 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][240/312]	eta 0:00:53 lr 0.001818	time 0.7916 (0.7429)	model_time 0.7915 (0.7363)	loss 3.4433 (3.1697)	grad_norm 1.2987 (1.7139/0.7119)	mem 34604MB
[2025-01-19 11:36:32 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][20/312]	eta 0:03:55 lr 0.001812	time 0.7235 (0.8060)	model_time 0.7234 (0.7420)	loss 3.9999 (3.3909)	grad_norm 1.2161 (1.5463/0.6904)	mem 34602MB
[2025-01-19 11:36:34 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][250/312]	eta 0:00:46 lr 0.001817	time 0.8121 (0.7441)	model_time 0.8120 (0.7378)	loss 2.9653 (3.1724)	grad_norm 1.0122 (1.6943/0.7062)	mem 34604MB
[2025-01-19 11:36:40 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][30/312]	eta 0:03:42 lr 0.001811	time 0.7430 (0.7902)	model_time 0.7429 (0.7468)	loss 3.1667 (3.3675)	grad_norm 2.4675 (1.5237/0.6129)	mem 34602MB
[2025-01-19 11:36:42 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][260/312]	eta 0:00:38 lr 0.001816	time 0.8236 (0.7460)	model_time 0.8232 (0.7399)	loss 2.7035 (3.1770)	grad_norm 1.8485 (1.6887/0.6981)	mem 34604MB
[2025-01-19 11:36:47 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][40/312]	eta 0:03:33 lr 0.001810	time 0.7387 (0.7842)	model_time 0.7383 (0.7513)	loss 3.3657 (3.2885)	grad_norm 2.5242 (1.5386/0.6464)	mem 34602MB
[2025-01-19 11:36:50 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][270/312]	eta 0:00:31 lr 0.001816	time 0.7390 (0.7455)	model_time 0.7388 (0.7397)	loss 2.6092 (3.1757)	grad_norm 0.6699 (1.6693/0.6964)	mem 34604MB
[2025-01-19 11:36:55 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][50/312]	eta 0:03:25 lr 0.001810	time 0.7414 (0.7839)	model_time 0.7412 (0.7574)	loss 3.3178 (3.2202)	grad_norm 0.8053 (1.5135/0.6516)	mem 34602MB
[2025-01-19 11:36:57 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][280/312]	eta 0:00:23 lr 0.001815	time 0.7193 (0.7447)	model_time 0.7191 (0.7390)	loss 3.4079 (3.1765)	grad_norm 1.5604 (1.6623/0.6947)	mem 34604MB
[2025-01-19 11:37:03 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][60/312]	eta 0:03:16 lr 0.001809	time 0.7181 (0.7798)	model_time 0.7179 (0.7576)	loss 2.9634 (3.2629)	grad_norm 1.1465 (1.4703/0.6249)	mem 34602MB
[2025-01-19 11:37:04 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][290/312]	eta 0:00:16 lr 0.001814	time 0.7194 (0.7443)	model_time 0.7193 (0.7388)	loss 3.1686 (3.1727)	grad_norm 3.1513 (1.6713/0.7026)	mem 34604MB
[2025-01-19 11:37:10 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][70/312]	eta 0:03:07 lr 0.001808	time 0.8139 (0.7746)	model_time 0.8138 (0.7554)	loss 2.9545 (3.2689)	grad_norm 1.3299 (1.5406/0.7069)	mem 34602MB
[2025-01-19 11:37:12 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][300/312]	eta 0:00:08 lr 0.001814	time 0.7138 (0.7436)	model_time 0.7136 (0.7382)	loss 3.7005 (3.1790)	grad_norm 1.0078 (1.6729/0.7162)	mem 34604MB
[2025-01-19 11:37:18 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][80/312]	eta 0:02:58 lr 0.001808	time 0.7324 (0.7686)	model_time 0.7319 (0.7518)	loss 2.2072 (3.2184)	grad_norm 0.9154 (1.5499/0.6918)	mem 34602MB
[2025-01-19 11:37:19 internimage_b_1k_224] (main.py 510): INFO Train: [159/300][310/312]	eta 0:00:01 lr 0.001813	time 0.7147 (0.7427)	model_time 0.7146 (0.7375)	loss 3.5256 (3.1849)	grad_norm 1.6225 (1.6629/0.7199)	mem 34604MB
[2025-01-19 11:37:19 internimage_b_1k_224] (main.py 519): INFO EPOCH 159 training takes 0:03:51
[2025-01-19 11:37:19 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_159.pth saving......
[2025-01-19 11:37:23 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_159.pth saved !!!
[2025-01-19 11:37:25 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][90/312]	eta 0:02:49 lr 0.001807	time 0.7170 (0.7653)	model_time 0.7168 (0.7503)	loss 2.8624 (3.1924)	grad_norm 2.2037 (1.5459/0.6786)	mem 34602MB
[2025-01-19 11:37:30 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.385 (7.385)	Loss 0.7812 (0.7812)	Acc@1 83.472 (83.472)	Acc@5 97.339 (97.339)	Mem 34604MB
[2025-01-19 11:37:32 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][100/312]	eta 0:02:41 lr 0.001806	time 0.7514 (0.7636)	model_time 0.7513 (0.7501)	loss 2.1321 (3.1728)	grad_norm 2.0674 (1.5926/0.6785)	mem 34602MB
[2025-01-19 11:37:33 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.949)	Loss 1.0235 (0.9150)	Acc@1 77.881 (80.846)	Acc@5 94.727 (95.785)	Mem 34604MB
[2025-01-19 11:37:34 internimage_b_1k_224] (main.py 575): INFO [Epoch:159] * Acc@1 80.782 Acc@5 95.829
[2025-01-19 11:37:34 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.8%
[2025-01-19 11:37:34 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.83%
[2025-01-19 11:37:40 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][110/312]	eta 0:02:33 lr 0.001806	time 0.7179 (0.7602)	model_time 0.7177 (0.7478)	loss 2.5305 (3.1761)	grad_norm 1.6734 (1.5991/0.6635)	mem 34602MB
[2025-01-19 11:37:43 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.448 (9.448)	Loss 0.6576 (0.6576)	Acc@1 84.521 (84.521)	Acc@5 97.681 (97.681)	Mem 34604MB
[2025-01-19 11:37:47 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][120/312]	eta 0:02:25 lr 0.001805	time 0.7263 (0.7585)	model_time 0.7262 (0.7472)	loss 2.2266 (3.1370)	grad_norm 1.3502 (1.5815/0.6441)	mem 34602MB
[2025-01-19 11:37:48 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (1.296)	Loss 0.9509 (0.7920)	Acc@1 77.368 (81.650)	Acc@5 94.604 (96.016)	Mem 34604MB
[2025-01-19 11:37:48 internimage_b_1k_224] (main.py 575): INFO [Epoch:159] * Acc@1 81.516 Acc@5 96.063
[2025-01-19 11:37:48 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.5%
[2025-01-19 11:37:48 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:37:52 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:37:52 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.52%
[2025-01-19 11:37:54 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][0/312]	eta 0:11:09 lr 0.001813	time 2.1461 (2.1461)	model_time 0.7381 (0.7381)	loss 2.9700 (2.9700)	grad_norm 1.9335 (1.9335/0.0000)	mem 34604MB
[2025-01-19 11:37:55 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][130/312]	eta 0:02:17 lr 0.001804	time 0.8171 (0.7577)	model_time 0.8170 (0.7472)	loss 3.1432 (3.1377)	grad_norm 1.5722 (1.5803/0.6303)	mem 34602MB
[2025-01-19 11:38:01 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][10/312]	eta 0:04:19 lr 0.001812	time 0.7222 (0.8591)	model_time 0.7220 (0.7308)	loss 3.3085 (2.9784)	grad_norm 1.2989 (1.6695/0.6920)	mem 34604MB
[2025-01-19 11:38:02 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][140/312]	eta 0:02:10 lr 0.001804	time 0.7261 (0.7564)	model_time 0.7259 (0.7466)	loss 3.1121 (3.1486)	grad_norm 0.8934 (1.5737/0.6280)	mem 34602MB
[2025-01-19 11:38:09 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][20/312]	eta 0:03:53 lr 0.001812	time 0.7198 (0.7995)	model_time 0.7197 (0.7321)	loss 3.5198 (3.0408)	grad_norm 1.2675 (1.9288/1.0187)	mem 34604MB
[2025-01-19 11:38:10 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][150/312]	eta 0:02:02 lr 0.001803	time 0.7381 (0.7567)	model_time 0.7379 (0.7475)	loss 2.9362 (3.1619)	grad_norm 1.6021 (1.5797/0.6149)	mem 34602MB
[2025-01-19 11:38:16 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][30/312]	eta 0:03:39 lr 0.001811	time 0.7325 (0.7769)	model_time 0.7324 (0.7311)	loss 2.4679 (3.0099)	grad_norm 1.2295 (1.7180/0.9204)	mem 34604MB
[2025-01-19 11:38:17 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][160/312]	eta 0:01:55 lr 0.001802	time 0.7192 (0.7569)	model_time 0.7191 (0.7482)	loss 3.6714 (3.1579)	grad_norm 3.8693 (1.6091/0.6591)	mem 34602MB
[2025-01-19 11:38:23 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][40/312]	eta 0:03:28 lr 0.001810	time 0.7161 (0.7660)	model_time 0.7159 (0.7313)	loss 3.2755 (3.0616)	grad_norm 1.6276 (1.6310/0.8287)	mem 34604MB
[2025-01-19 11:38:25 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][170/312]	eta 0:01:47 lr 0.001802	time 0.7170 (0.7568)	model_time 0.7166 (0.7486)	loss 2.2920 (3.1567)	grad_norm 1.7463 (1.6201/0.6568)	mem 34602MB
[2025-01-19 11:38:31 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][50/312]	eta 0:03:19 lr 0.001810	time 0.8394 (0.7602)	model_time 0.8393 (0.7322)	loss 3.4284 (3.0751)	grad_norm 1.5545 (1.6579/0.7675)	mem 34604MB
[2025-01-19 11:38:32 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][180/312]	eta 0:01:39 lr 0.001801	time 0.7999 (0.7568)	model_time 0.7998 (0.7491)	loss 2.0590 (3.1564)	grad_norm 1.6755 (1.6089/0.6462)	mem 34602MB
[2025-01-19 11:38:38 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][60/312]	eta 0:03:11 lr 0.001809	time 0.8268 (0.7617)	model_time 0.8267 (0.7382)	loss 2.8499 (3.0672)	grad_norm 1.6015 (1.6358/0.7308)	mem 34604MB
[2025-01-19 11:38:40 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][190/312]	eta 0:01:32 lr 0.001800	time 0.8107 (0.7564)	model_time 0.8105 (0.7491)	loss 3.2984 (3.1397)	grad_norm 2.8587 (1.6164/0.6494)	mem 34602MB
[2025-01-19 11:38:47 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][70/312]	eta 0:03:06 lr 0.001808	time 0.8118 (0.7696)	model_time 0.8116 (0.7494)	loss 3.0656 (3.0683)	grad_norm 2.0368 (1.6640/0.7277)	mem 34604MB
[2025-01-19 11:38:47 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][200/312]	eta 0:01:24 lr 0.001800	time 0.7229 (0.7549)	model_time 0.7227 (0.7479)	loss 3.2604 (3.1451)	grad_norm 1.5273 (1.5993/0.6392)	mem 34602MB
[2025-01-19 11:38:54 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][80/312]	eta 0:02:57 lr 0.001808	time 0.7209 (0.7661)	model_time 0.7205 (0.7484)	loss 3.3599 (3.0690)	grad_norm 1.0867 (1.6209/0.6950)	mem 34604MB
[2025-01-19 11:38:54 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][210/312]	eta 0:01:16 lr 0.001799	time 0.7234 (0.7543)	model_time 0.7233 (0.7477)	loss 3.2972 (3.1299)	grad_norm 1.3362 (1.5961/0.6284)	mem 34602MB
[2025-01-19 11:39:01 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][90/312]	eta 0:02:49 lr 0.001807	time 0.7344 (0.7623)	model_time 0.7342 (0.7464)	loss 3.5207 (3.0915)	grad_norm 3.2193 (1.6604/0.7031)	mem 34604MB
[2025-01-19 11:39:02 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][220/312]	eta 0:01:09 lr 0.001798	time 0.7252 (0.7541)	model_time 0.7250 (0.7477)	loss 3.4915 (3.1296)	grad_norm 1.5527 (1.6132/0.6395)	mem 34602MB
[2025-01-19 11:39:09 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][100/312]	eta 0:02:40 lr 0.001806	time 0.7285 (0.7585)	model_time 0.7283 (0.7442)	loss 3.5754 (3.1206)	grad_norm 1.5593 (1.7136/0.7313)	mem 34604MB
[2025-01-19 11:39:09 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][230/312]	eta 0:01:01 lr 0.001798	time 0.7186 (0.7530)	model_time 0.7182 (0.7469)	loss 2.2548 (3.1276)	grad_norm 1.2933 (1.5995/0.6392)	mem 34602MB
[2025-01-19 11:39:16 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][110/312]	eta 0:02:32 lr 0.001806	time 0.7417 (0.7557)	model_time 0.7412 (0.7427)	loss 3.5087 (3.1302)	grad_norm 0.9892 (1.7119/0.7220)	mem 34604MB
[2025-01-19 11:39:17 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][240/312]	eta 0:00:54 lr 0.001797	time 0.7120 (0.7521)	model_time 0.7118 (0.7463)	loss 3.7759 (3.1331)	grad_norm 1.1911 (1.5979/0.6363)	mem 34602MB
[2025-01-19 11:39:23 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][120/312]	eta 0:02:24 lr 0.001805	time 0.7228 (0.7532)	model_time 0.7227 (0.7411)	loss 2.8887 (3.1097)	grad_norm 1.4187 (1.6777/0.7130)	mem 34604MB
[2025-01-19 11:39:24 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][250/312]	eta 0:00:46 lr 0.001797	time 0.7819 (0.7515)	model_time 0.7814 (0.7458)	loss 2.7094 (3.1315)	grad_norm 0.9927 (1.5907/0.6344)	mem 34602MB
[2025-01-19 11:39:30 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][130/312]	eta 0:02:16 lr 0.001804	time 0.7200 (0.7509)	model_time 0.7196 (0.7397)	loss 3.3276 (3.1198)	grad_norm 2.8723 (1.6800/0.7066)	mem 34604MB
[2025-01-19 11:39:31 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][260/312]	eta 0:00:39 lr 0.001796	time 0.7227 (0.7514)	model_time 0.7225 (0.7460)	loss 3.4103 (3.1306)	grad_norm 0.8640 (1.6069/0.6443)	mem 34602MB
[2025-01-19 11:39:38 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][140/312]	eta 0:02:09 lr 0.001804	time 0.7355 (0.7500)	model_time 0.7350 (0.7397)	loss 3.3249 (3.1141)	grad_norm 2.0429 (1.6920/0.6938)	mem 34604MB
[2025-01-19 11:39:39 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][270/312]	eta 0:00:31 lr 0.001795	time 0.8124 (0.7516)	model_time 0.8119 (0.7463)	loss 3.4286 (3.1368)	grad_norm 1.6065 (1.6056/0.6356)	mem 34602MB
[2025-01-19 11:39:45 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][150/312]	eta 0:02:01 lr 0.001803	time 0.7169 (0.7481)	model_time 0.7167 (0.7384)	loss 2.9922 (3.1226)	grad_norm 1.3589 (1.6768/0.6848)	mem 34604MB
[2025-01-19 11:39:47 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][280/312]	eta 0:00:24 lr 0.001795	time 0.7304 (0.7520)	model_time 0.7299 (0.7469)	loss 3.5587 (3.1314)	grad_norm 1.6956 (1.6109/0.6314)	mem 34602MB
[2025-01-19 11:39:52 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][160/312]	eta 0:01:53 lr 0.001802	time 0.7450 (0.7470)	model_time 0.7445 (0.7379)	loss 3.2626 (3.1334)	grad_norm 1.3508 (1.6703/0.6754)	mem 34604MB
[2025-01-19 11:39:54 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][290/312]	eta 0:00:16 lr 0.001794	time 0.7466 (0.7521)	model_time 0.7464 (0.7471)	loss 3.5137 (3.1365)	grad_norm 1.5016 (1.6293/0.6487)	mem 34602MB
[2025-01-19 11:40:00 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][170/312]	eta 0:01:45 lr 0.001802	time 0.8334 (0.7462)	model_time 0.8329 (0.7376)	loss 3.4609 (3.1388)	grad_norm 1.7245 (1.6511/0.6645)	mem 34604MB
[2025-01-19 11:40:02 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][300/312]	eta 0:00:09 lr 0.001793	time 0.8114 (0.7526)	model_time 0.8113 (0.7478)	loss 2.6738 (3.1360)	grad_norm 3.6894 (1.6377/0.6612)	mem 34602MB
[2025-01-19 11:40:07 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][180/312]	eta 0:01:38 lr 0.001801	time 0.8034 (0.7471)	model_time 0.8033 (0.7390)	loss 2.2823 (3.1296)	grad_norm 1.2776 (1.6264/0.6573)	mem 34604MB
[2025-01-19 11:40:09 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][310/312]	eta 0:00:01 lr 0.001793	time 0.7223 (0.7518)	model_time 0.7222 (0.7471)	loss 2.9932 (3.1361)	grad_norm 1.5524 (1.6353/0.6546)	mem 34602MB
[2025-01-19 11:40:10 internimage_b_1k_224] (main.py 519): INFO EPOCH 160 training takes 0:03:54
[2025-01-19 11:40:10 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_160.pth saving......
[2025-01-19 11:40:13 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_160.pth saved !!!
[2025-01-19 11:40:15 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][190/312]	eta 0:01:31 lr 0.001800	time 0.7231 (0.7489)	model_time 0.7226 (0.7412)	loss 3.4239 (3.1380)	grad_norm 3.1496 (1.6464/0.6653)	mem 34604MB
[2025-01-19 11:40:21 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.777 (7.777)	Loss 0.7627 (0.7627)	Acc@1 83.813 (83.813)	Acc@5 97.314 (97.314)	Mem 34602MB
[2025-01-19 11:40:22 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][200/312]	eta 0:01:23 lr 0.001800	time 0.7199 (0.7487)	model_time 0.7197 (0.7414)	loss 3.8344 (3.1359)	grad_norm 2.0963 (1.6461/0.6526)	mem 34604MB
[2025-01-19 11:40:24 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.986)	Loss 1.0394 (0.8955)	Acc@1 77.173 (81.139)	Acc@5 94.507 (95.725)	Mem 34602MB
[2025-01-19 11:40:24 internimage_b_1k_224] (main.py 575): INFO [Epoch:160] * Acc@1 80.944 Acc@5 95.755
[2025-01-19 11:40:24 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.9%
[2025-01-19 11:40:24 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 11:40:27 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 11:40:27 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.94%
[2025-01-19 11:40:30 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][210/312]	eta 0:01:16 lr 0.001799	time 0.7361 (0.7478)	model_time 0.7357 (0.7407)	loss 3.1037 (3.1316)	grad_norm 1.0091 (1.6408/0.6482)	mem 34604MB
[2025-01-19 11:40:35 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.590 (7.590)	Loss 0.6588 (0.6588)	Acc@1 84.302 (84.302)	Acc@5 97.607 (97.607)	Mem 34602MB
[2025-01-19 11:40:37 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][220/312]	eta 0:01:08 lr 0.001798	time 0.7262 (0.7468)	model_time 0.7260 (0.7401)	loss 3.7833 (3.1407)	grad_norm 3.8115 (1.6408/0.6609)	mem 34604MB
[2025-01-19 11:40:38 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.980)	Loss 0.9534 (0.7928)	Acc@1 77.393 (81.663)	Acc@5 94.653 (95.989)	Mem 34602MB
[2025-01-19 11:40:38 internimage_b_1k_224] (main.py 575): INFO [Epoch:160] * Acc@1 81.538 Acc@5 96.035
[2025-01-19 11:40:38 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.5%
[2025-01-19 11:40:38 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:40:42 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:40:42 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.54%
[2025-01-19 11:40:44 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][230/312]	eta 0:01:01 lr 0.001798	time 0.7201 (0.7459)	model_time 0.7199 (0.7394)	loss 2.0884 (3.1292)	grad_norm 0.9368 (1.6293/0.6562)	mem 34604MB
[2025-01-19 11:40:45 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][0/312]	eta 0:11:42 lr 0.001792	time 2.2512 (2.2512)	model_time 0.7397 (0.7397)	loss 2.5075 (2.5075)	grad_norm 0.8915 (0.8915/0.0000)	mem 34602MB
[2025-01-19 11:40:52 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][240/312]	eta 0:00:53 lr 0.001797	time 0.7362 (0.7451)	model_time 0.7360 (0.7389)	loss 2.5169 (3.1303)	grad_norm 3.0155 (1.6187/0.6609)	mem 34604MB
[2025-01-19 11:40:52 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][10/312]	eta 0:04:21 lr 0.001792	time 0.7245 (0.8644)	model_time 0.7244 (0.7268)	loss 3.4317 (3.0191)	grad_norm 1.0784 (1.3300/0.2304)	mem 34602MB
[2025-01-19 11:40:59 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][250/312]	eta 0:00:46 lr 0.001797	time 0.7170 (0.7442)	model_time 0.7169 (0.7383)	loss 3.3781 (3.1250)	grad_norm 1.1898 (1.6110/0.6524)	mem 34604MB
[2025-01-19 11:40:59 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][20/312]	eta 0:03:56 lr 0.001791	time 0.7197 (0.8095)	model_time 0.7196 (0.7373)	loss 2.5346 (3.0543)	grad_norm 1.1079 (1.3073/0.3379)	mem 34602MB
[2025-01-19 11:41:06 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][260/312]	eta 0:00:38 lr 0.001796	time 0.7138 (0.7438)	model_time 0.7137 (0.7380)	loss 2.7389 (3.1303)	grad_norm 0.9660 (1.6011/0.6477)	mem 34604MB
[2025-01-19 11:41:07 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][30/312]	eta 0:03:42 lr 0.001790	time 0.7274 (0.7879)	model_time 0.7273 (0.7388)	loss 2.6740 (3.0637)	grad_norm 2.4208 (1.3540/0.3908)	mem 34602MB
[2025-01-19 11:41:13 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][270/312]	eta 0:00:31 lr 0.001795	time 0.7341 (0.7432)	model_time 0.7337 (0.7376)	loss 2.5408 (3.1248)	grad_norm 1.2200 (1.5897/0.6440)	mem 34604MB
[2025-01-19 11:41:14 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][40/312]	eta 0:03:30 lr 0.001790	time 0.7400 (0.7735)	model_time 0.7395 (0.7363)	loss 3.3855 (3.1305)	grad_norm 3.3347 (1.4962/0.5670)	mem 34602MB
[2025-01-19 11:41:21 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][280/312]	eta 0:00:23 lr 0.001795	time 0.7426 (0.7426)	model_time 0.7424 (0.7373)	loss 3.2912 (3.1237)	grad_norm 2.7548 (1.5889/0.6443)	mem 34604MB
[2025-01-19 11:41:21 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][50/312]	eta 0:03:20 lr 0.001789	time 0.7225 (0.7662)	model_time 0.7223 (0.7362)	loss 2.8765 (3.1354)	grad_norm 1.1759 (1.4930/0.5546)	mem 34602MB
[2025-01-19 11:41:28 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][290/312]	eta 0:00:16 lr 0.001794	time 0.8416 (0.7426)	model_time 0.8412 (0.7374)	loss 3.8329 (3.1300)	grad_norm 1.3087 (1.5946/0.6438)	mem 34604MB
[2025-01-19 11:41:29 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][60/312]	eta 0:03:12 lr 0.001788	time 0.8168 (0.7630)	model_time 0.8164 (0.7378)	loss 3.1809 (3.1604)	grad_norm 3.6637 (1.6078/0.7346)	mem 34602MB
[2025-01-19 11:41:36 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][300/312]	eta 0:00:08 lr 0.001793	time 0.7976 (0.7434)	model_time 0.7975 (0.7383)	loss 2.4782 (3.1266)	grad_norm 2.4981 (1.5958/0.6494)	mem 34604MB
[2025-01-19 11:41:36 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][70/312]	eta 0:03:03 lr 0.001788	time 0.7249 (0.7595)	model_time 0.7244 (0.7379)	loss 2.0396 (3.1346)	grad_norm 0.8434 (1.5434/0.7107)	mem 34602MB
[2025-01-19 11:41:43 internimage_b_1k_224] (main.py 510): INFO Train: [160/300][310/312]	eta 0:00:01 lr 0.001793	time 0.7900 (0.7444)	model_time 0.7899 (0.7395)	loss 3.6729 (3.1269)	grad_norm 0.8983 (1.5983/0.6500)	mem 34604MB
[2025-01-19 11:41:44 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][80/312]	eta 0:02:56 lr 0.001787	time 0.8161 (0.7595)	model_time 0.8159 (0.7405)	loss 2.8135 (3.1135)	grad_norm 1.1171 (1.5532/0.6888)	mem 34602MB
[2025-01-19 11:41:44 internimage_b_1k_224] (main.py 519): INFO EPOCH 160 training takes 0:03:52
[2025-01-19 11:41:44 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_160.pth saving......
[2025-01-19 11:41:48 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_160.pth saved !!!
[2025-01-19 11:41:51 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][90/312]	eta 0:02:48 lr 0.001786	time 0.8158 (0.7601)	model_time 0.8156 (0.7432)	loss 3.2762 (3.1106)	grad_norm 1.8320 (1.5193/0.6649)	mem 34602MB
[2025-01-19 11:41:55 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.580 (7.580)	Loss 0.7720 (0.7720)	Acc@1 83.838 (83.838)	Acc@5 96.948 (96.948)	Mem 34604MB
[2025-01-19 11:41:58 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.984)	Loss 1.0311 (0.8837)	Acc@1 77.368 (81.308)	Acc@5 94.604 (95.825)	Mem 34604MB
[2025-01-19 11:41:59 internimage_b_1k_224] (main.py 575): INFO [Epoch:160] * Acc@1 81.192 Acc@5 95.841
[2025-01-19 11:41:59 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.2%
[2025-01-19 11:41:59 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 11:41:59 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][100/312]	eta 0:02:41 lr 0.001786	time 0.8053 (0.7608)	model_time 0.8051 (0.7455)	loss 3.0223 (3.1349)	grad_norm 2.4740 (1.5653/0.6993)	mem 34602MB
[2025-01-19 11:42:02 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 11:42:02 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.19%
[2025-01-19 11:42:07 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][110/312]	eta 0:02:34 lr 0.001785	time 0.8060 (0.7637)	model_time 0.8055 (0.7498)	loss 3.1967 (3.1402)	grad_norm 1.7828 (1.6157/0.7382)	mem 34602MB
[2025-01-19 11:42:09 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.108 (7.108)	Loss 0.6582 (0.6582)	Acc@1 84.521 (84.521)	Acc@5 97.681 (97.681)	Mem 34604MB
[2025-01-19 11:42:12 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.947)	Loss 0.9506 (0.7920)	Acc@1 77.368 (81.665)	Acc@5 94.629 (96.036)	Mem 34604MB
[2025-01-19 11:42:13 internimage_b_1k_224] (main.py 575): INFO [Epoch:160] * Acc@1 81.530 Acc@5 96.085
[2025-01-19 11:42:13 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.5%
[2025-01-19 11:42:13 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:42:14 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][120/312]	eta 0:02:26 lr 0.001785	time 0.7250 (0.7612)	model_time 0.7245 (0.7484)	loss 2.6876 (3.1465)	grad_norm 1.0701 (1.6275/0.7413)	mem 34602MB
[2025-01-19 11:42:16 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:42:16 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.53%
[2025-01-19 11:42:19 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][0/312]	eta 0:11:27 lr 0.001792	time 2.2039 (2.2039)	model_time 0.7432 (0.7432)	loss 2.4081 (2.4081)	grad_norm 1.0111 (1.0111/0.0000)	mem 34604MB
[2025-01-19 11:42:22 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][130/312]	eta 0:02:18 lr 0.001784	time 0.7238 (0.7594)	model_time 0.7234 (0.7475)	loss 3.8040 (3.1323)	grad_norm 1.2887 (1.6152/0.7248)	mem 34602MB
[2025-01-19 11:42:26 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][10/312]	eta 0:04:28 lr 0.001792	time 0.7292 (0.8875)	model_time 0.7291 (0.7544)	loss 4.0210 (3.1949)	grad_norm 1.4478 (1.6874/0.8402)	mem 34604MB
[2025-01-19 11:42:29 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][140/312]	eta 0:02:10 lr 0.001783	time 0.7151 (0.7582)	model_time 0.7149 (0.7471)	loss 3.6366 (3.1420)	grad_norm 1.5663 (1.6605/0.7755)	mem 34602MB
[2025-01-19 11:42:34 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][20/312]	eta 0:03:56 lr 0.001791	time 0.7314 (0.8115)	model_time 0.7310 (0.7417)	loss 2.5599 (3.2907)	grad_norm 1.9150 (1.5857/0.6805)	mem 34604MB
[2025-01-19 11:42:37 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][150/312]	eta 0:02:02 lr 0.001783	time 0.7255 (0.7570)	model_time 0.7251 (0.7466)	loss 2.3361 (3.1484)	grad_norm 1.1019 (1.6405/0.7615)	mem 34602MB
[2025-01-19 11:42:41 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][30/312]	eta 0:03:41 lr 0.001790	time 0.7159 (0.7841)	model_time 0.7157 (0.7367)	loss 2.5358 (3.2145)	grad_norm 0.9973 (1.5026/0.6235)	mem 34604MB
[2025-01-19 11:42:44 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][160/312]	eta 0:01:54 lr 0.001782	time 0.7878 (0.7559)	model_time 0.7877 (0.7462)	loss 3.2795 (3.1517)	grad_norm 1.3304 (1.6143/0.7469)	mem 34602MB
[2025-01-19 11:42:48 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][40/312]	eta 0:03:29 lr 0.001790	time 0.7238 (0.7697)	model_time 0.7234 (0.7337)	loss 2.0471 (3.1738)	grad_norm 2.1437 (1.4768/0.5745)	mem 34604MB
[2025-01-19 11:42:51 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][170/312]	eta 0:01:47 lr 0.001781	time 0.7171 (0.7553)	model_time 0.7170 (0.7461)	loss 3.7798 (3.1715)	grad_norm 2.7453 (1.6184/0.7329)	mem 34602MB
[2025-01-19 11:42:55 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][50/312]	eta 0:03:19 lr 0.001789	time 0.7223 (0.7622)	model_time 0.7221 (0.7333)	loss 2.9840 (3.1943)	grad_norm 1.2460 (1.5302/0.7587)	mem 34604MB
[2025-01-19 11:42:59 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][180/312]	eta 0:01:39 lr 0.001781	time 0.8082 (0.7547)	model_time 0.8080 (0.7460)	loss 3.7912 (3.1822)	grad_norm 1.7236 (1.6177/0.7221)	mem 34602MB
[2025-01-19 11:43:03 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][60/312]	eta 0:03:10 lr 0.001788	time 0.7247 (0.7567)	model_time 0.7246 (0.7324)	loss 3.3823 (3.1765)	grad_norm 1.3084 (1.5646/0.7600)	mem 34604MB
[2025-01-19 11:43:06 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][190/312]	eta 0:01:31 lr 0.001780	time 0.7247 (0.7541)	model_time 0.7246 (0.7458)	loss 3.6978 (3.1905)	grad_norm 1.2762 (1.6290/0.7235)	mem 34602MB
[2025-01-19 11:43:10 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][70/312]	eta 0:03:02 lr 0.001788	time 0.7268 (0.7531)	model_time 0.7266 (0.7322)	loss 3.2501 (3.1836)	grad_norm 1.7779 (1.5501/0.7255)	mem 34604MB
[2025-01-19 11:43:14 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][200/312]	eta 0:01:24 lr 0.001779	time 0.7224 (0.7541)	model_time 0.7222 (0.7462)	loss 3.5404 (3.2022)	grad_norm 1.3118 (1.6256/0.7135)	mem 34602MB
[2025-01-19 11:43:17 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][80/312]	eta 0:02:54 lr 0.001787	time 0.7297 (0.7501)	model_time 0.7293 (0.7317)	loss 3.6456 (3.1884)	grad_norm 1.0329 (1.6097/0.7927)	mem 34604MB
[2025-01-19 11:43:22 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][210/312]	eta 0:01:17 lr 0.001779	time 0.8105 (0.7552)	model_time 0.8104 (0.7477)	loss 2.4503 (3.2060)	grad_norm 1.2216 (1.6016/0.7088)	mem 34602MB
[2025-01-19 11:43:24 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][90/312]	eta 0:02:45 lr 0.001786	time 0.7160 (0.7470)	model_time 0.7159 (0.7307)	loss 2.5676 (3.1961)	grad_norm 1.7068 (1.5981/0.7659)	mem 34604MB
[2025-01-19 11:43:29 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][220/312]	eta 0:01:09 lr 0.001778	time 0.8062 (0.7561)	model_time 0.8061 (0.7490)	loss 3.5149 (3.2133)	grad_norm 1.5783 (1.5787/0.7022)	mem 34602MB
[2025-01-19 11:43:32 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][100/312]	eta 0:02:38 lr 0.001786	time 0.7207 (0.7455)	model_time 0.7202 (0.7308)	loss 2.3712 (3.1734)	grad_norm 1.3065 (1.5684/0.7393)	mem 34604MB
[2025-01-19 11:43:37 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][230/312]	eta 0:01:02 lr 0.001777	time 0.8068 (0.7562)	model_time 0.8063 (0.7493)	loss 3.3878 (3.2190)	grad_norm 0.8623 (1.5594/0.6935)	mem 34602MB
[2025-01-19 11:43:40 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][110/312]	eta 0:02:31 lr 0.001785	time 0.8254 (0.7490)	model_time 0.8248 (0.7355)	loss 3.3910 (3.1678)	grad_norm 1.2199 (1.6058/0.7849)	mem 34604MB
[2025-01-19 11:43:44 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][240/312]	eta 0:00:54 lr 0.001777	time 0.7185 (0.7554)	model_time 0.7181 (0.7488)	loss 2.7522 (3.2197)	grad_norm 2.2552 (1.5594/0.6940)	mem 34602MB
[2025-01-19 11:43:47 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][120/312]	eta 0:02:24 lr 0.001785	time 0.8020 (0.7513)	model_time 0.8018 (0.7389)	loss 2.7219 (3.1500)	grad_norm 1.0220 (1.5634/0.7679)	mem 34604MB
[2025-01-19 11:43:52 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][250/312]	eta 0:00:46 lr 0.001776	time 0.7326 (0.7546)	model_time 0.7324 (0.7482)	loss 2.1413 (3.2148)	grad_norm 3.1348 (1.5765/0.7047)	mem 34602MB
[2025-01-19 11:43:55 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][130/312]	eta 0:02:16 lr 0.001784	time 0.7192 (0.7513)	model_time 0.7190 (0.7398)	loss 3.4138 (3.1556)	grad_norm 1.3484 (1.5444/0.7438)	mem 34604MB
[2025-01-19 11:43:59 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][260/312]	eta 0:00:39 lr 0.001775	time 0.7199 (0.7541)	model_time 0.7195 (0.7480)	loss 3.7785 (3.2067)	grad_norm 1.3207 (1.5671/0.6989)	mem 34602MB
[2025-01-19 11:44:02 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][140/312]	eta 0:02:08 lr 0.001783	time 0.7193 (0.7500)	model_time 0.7191 (0.7393)	loss 3.4305 (3.1566)	grad_norm 0.9401 (1.5566/0.7461)	mem 34604MB
[2025-01-19 11:44:07 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][270/312]	eta 0:00:31 lr 0.001775	time 0.7178 (0.7536)	model_time 0.7173 (0.7477)	loss 3.3882 (3.2086)	grad_norm 1.1881 (1.5773/0.6958)	mem 34602MB
[2025-01-19 11:44:10 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][150/312]	eta 0:02:01 lr 0.001783	time 0.7133 (0.7488)	model_time 0.7131 (0.7388)	loss 2.8220 (3.1603)	grad_norm 2.2351 (1.5510/0.7315)	mem 34604MB
[2025-01-19 11:44:14 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][280/312]	eta 0:00:24 lr 0.001774	time 0.7250 (0.7527)	model_time 0.7248 (0.7470)	loss 3.4100 (3.2070)	grad_norm 1.2670 (1.5820/0.6905)	mem 34602MB
[2025-01-19 11:44:17 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][160/312]	eta 0:01:53 lr 0.001782	time 0.7201 (0.7478)	model_time 0.7199 (0.7384)	loss 3.1141 (3.1512)	grad_norm 2.5587 (1.5518/0.7211)	mem 34604MB
[2025-01-19 11:44:21 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][290/312]	eta 0:00:16 lr 0.001773	time 0.7169 (0.7525)	model_time 0.7167 (0.7469)	loss 2.7953 (3.1998)	grad_norm 1.2188 (1.5787/0.6860)	mem 34602MB
[2025-01-19 11:44:24 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][170/312]	eta 0:01:46 lr 0.001781	time 0.7244 (0.7469)	model_time 0.7242 (0.7381)	loss 2.1851 (3.1424)	grad_norm 1.4590 (1.5820/0.7340)	mem 34604MB
[2025-01-19 11:44:29 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][300/312]	eta 0:00:09 lr 0.001773	time 0.7136 (0.7519)	model_time 0.7135 (0.7465)	loss 2.7951 (3.1995)	grad_norm 1.0347 (1.5842/0.6817)	mem 34602MB
[2025-01-19 11:44:31 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][180/312]	eta 0:01:38 lr 0.001781	time 0.7150 (0.7455)	model_time 0.7146 (0.7371)	loss 3.1813 (3.1410)	grad_norm 4.3293 (1.6468/0.8229)	mem 34604MB
[2025-01-19 11:44:36 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][310/312]	eta 0:00:01 lr 0.001772	time 0.7137 (0.7518)	model_time 0.7136 (0.7466)	loss 3.7802 (3.2077)	grad_norm 2.8000 (1.5939/0.6897)	mem 34602MB
[2025-01-19 11:44:37 internimage_b_1k_224] (main.py 519): INFO EPOCH 161 training takes 0:03:54
[2025-01-19 11:44:37 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_161.pth saving......
[2025-01-19 11:44:39 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][190/312]	eta 0:01:30 lr 0.001780	time 0.7526 (0.7449)	model_time 0.7524 (0.7369)	loss 3.7999 (3.1495)	grad_norm 1.1872 (1.6313/0.8049)	mem 34604MB
[2025-01-19 11:44:40 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_161.pth saved !!!
[2025-01-19 11:44:46 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][200/312]	eta 0:01:23 lr 0.001779	time 0.7229 (0.7443)	model_time 0.7223 (0.7367)	loss 3.2980 (3.1403)	grad_norm 1.7846 (1.6248/0.7907)	mem 34604MB
[2025-01-19 11:44:48 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.943 (7.943)	Loss 0.7697 (0.7697)	Acc@1 83.862 (83.862)	Acc@5 97.266 (97.266)	Mem 34602MB
[2025-01-19 11:44:51 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.994)	Loss 1.0476 (0.9010)	Acc@1 76.440 (80.953)	Acc@5 94.141 (95.703)	Mem 34602MB
[2025-01-19 11:44:51 internimage_b_1k_224] (main.py 575): INFO [Epoch:161] * Acc@1 80.842 Acc@5 95.727
[2025-01-19 11:44:51 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.8%
[2025-01-19 11:44:51 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 80.94%
[2025-01-19 11:44:53 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][210/312]	eta 0:01:15 lr 0.001779	time 0.7153 (0.7433)	model_time 0.7148 (0.7360)	loss 3.2437 (3.1561)	grad_norm 0.9296 (1.6218/0.7932)	mem 34604MB
[2025-01-19 11:45:01 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.414 (9.414)	Loss 0.6596 (0.6596)	Acc@1 84.375 (84.375)	Acc@5 97.632 (97.632)	Mem 34602MB
[2025-01-19 11:45:01 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][220/312]	eta 0:01:08 lr 0.001778	time 0.7179 (0.7432)	model_time 0.7177 (0.7362)	loss 3.7173 (3.1662)	grad_norm 1.1886 (1.6194/0.7814)	mem 34604MB
[2025-01-19 11:45:05 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.268)	Loss 0.9533 (0.7930)	Acc@1 77.466 (81.703)	Acc@5 94.604 (95.985)	Mem 34602MB
[2025-01-19 11:45:05 internimage_b_1k_224] (main.py 575): INFO [Epoch:161] * Acc@1 81.568 Acc@5 96.033
[2025-01-19 11:45:05 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.6%
[2025-01-19 11:45:05 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:45:08 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][230/312]	eta 0:01:01 lr 0.001777	time 0.8065 (0.7443)	model_time 0.8063 (0.7376)	loss 3.1569 (3.1614)	grad_norm 2.0145 (1.6072/0.7723)	mem 34604MB
[2025-01-19 11:45:09 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:45:09 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.57%
[2025-01-19 11:45:11 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][0/312]	eta 0:11:37 lr 0.001772	time 2.2346 (2.2346)	model_time 0.7910 (0.7910)	loss 3.5122 (3.5122)	grad_norm 2.4127 (2.4127/0.0000)	mem 34602MB
[2025-01-19 11:45:16 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][240/312]	eta 0:00:53 lr 0.001777	time 0.8020 (0.7457)	model_time 0.8019 (0.7393)	loss 3.1469 (3.1576)	grad_norm 2.4319 (1.6269/0.7735)	mem 34604MB
[2025-01-19 11:45:19 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][10/312]	eta 0:04:31 lr 0.001771	time 0.7199 (0.8992)	model_time 0.7195 (0.7675)	loss 3.1773 (3.3257)	grad_norm 2.2905 (1.8992/0.8064)	mem 34602MB
[2025-01-19 11:45:24 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][250/312]	eta 0:00:46 lr 0.001776	time 0.7175 (0.7462)	model_time 0.7170 (0.7400)	loss 3.4625 (3.1737)	grad_norm 2.1336 (1.6202/0.7632)	mem 34604MB
[2025-01-19 11:45:26 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][20/312]	eta 0:04:04 lr 0.001771	time 0.8083 (0.8371)	model_time 0.8082 (0.7681)	loss 2.6326 (3.1956)	grad_norm 1.8687 (1.7150/0.7303)	mem 34602MB
[2025-01-19 11:45:31 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][260/312]	eta 0:00:38 lr 0.001775	time 0.7622 (0.7455)	model_time 0.7620 (0.7396)	loss 3.5530 (3.1890)	grad_norm 1.3438 (1.6098/0.7560)	mem 34604MB
[2025-01-19 11:45:34 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][30/312]	eta 0:03:50 lr 0.001770	time 0.8077 (0.8174)	model_time 0.8073 (0.7705)	loss 3.3023 (3.2382)	grad_norm 1.1985 (1.6864/0.6645)	mem 34602MB
[2025-01-19 11:45:38 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][270/312]	eta 0:00:31 lr 0.001775	time 0.7166 (0.7449)	model_time 0.7164 (0.7391)	loss 3.9450 (3.1930)	grad_norm 2.2401 (1.6308/0.7612)	mem 34604MB
[2025-01-19 11:45:42 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][40/312]	eta 0:03:38 lr 0.001769	time 0.7164 (0.8042)	model_time 0.7160 (0.7686)	loss 3.8788 (3.2093)	grad_norm 1.0771 (1.6593/0.6197)	mem 34602MB
[2025-01-19 11:45:46 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][280/312]	eta 0:00:23 lr 0.001774	time 0.7273 (0.7442)	model_time 0.7272 (0.7387)	loss 2.3566 (3.1803)	grad_norm 0.9795 (1.6368/0.7606)	mem 34604MB
[2025-01-19 11:45:49 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][50/312]	eta 0:03:27 lr 0.001769	time 0.7178 (0.7916)	model_time 0.7174 (0.7629)	loss 2.6189 (3.1717)	grad_norm 1.1214 (1.7012/0.6506)	mem 34602MB
[2025-01-19 11:45:53 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][290/312]	eta 0:00:16 lr 0.001773	time 0.7242 (0.7439)	model_time 0.7240 (0.7386)	loss 3.8688 (3.1782)	grad_norm 1.0592 (1.6362/0.7579)	mem 34604MB
[2025-01-19 11:45:57 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][60/312]	eta 0:03:16 lr 0.001768	time 0.7209 (0.7804)	model_time 0.7207 (0.7564)	loss 3.6443 (3.1257)	grad_norm 0.7503 (1.6582/0.6534)	mem 34602MB
[2025-01-19 11:46:00 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][300/312]	eta 0:00:08 lr 0.001773	time 0.7161 (0.7432)	model_time 0.7160 (0.7380)	loss 2.3270 (3.1780)	grad_norm 2.1380 (1.6476/0.7509)	mem 34604MB
[2025-01-19 11:46:04 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][70/312]	eta 0:03:07 lr 0.001767	time 0.8152 (0.7757)	model_time 0.8150 (0.7551)	loss 3.0821 (3.1209)	grad_norm 2.0422 (1.6000/0.6463)	mem 34602MB
[2025-01-19 11:46:07 internimage_b_1k_224] (main.py 510): INFO Train: [161/300][310/312]	eta 0:00:01 lr 0.001772	time 0.7133 (0.7422)	model_time 0.7132 (0.7372)	loss 2.6221 (3.1825)	grad_norm 1.1085 (1.6251/0.7432)	mem 34604MB
[2025-01-19 11:46:08 internimage_b_1k_224] (main.py 519): INFO EPOCH 161 training takes 0:03:51
[2025-01-19 11:46:08 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_161.pth saving......
[2025-01-19 11:46:11 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_161.pth saved !!!
[2025-01-19 11:46:11 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][80/312]	eta 0:02:58 lr 0.001767	time 0.7201 (0.7706)	model_time 0.7197 (0.7524)	loss 2.6409 (3.1012)	grad_norm 1.8250 (1.5731/0.6299)	mem 34602MB
[2025-01-19 11:46:19 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][90/312]	eta 0:02:50 lr 0.001766	time 0.7441 (0.7671)	model_time 0.7436 (0.7509)	loss 2.6149 (3.0805)	grad_norm 1.3149 (1.6884/0.7482)	mem 34602MB
[2025-01-19 11:46:20 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.748 (8.748)	Loss 0.7799 (0.7799)	Acc@1 83.789 (83.789)	Acc@5 97.119 (97.119)	Mem 34604MB
[2025-01-19 11:46:23 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.068)	Loss 1.0633 (0.9230)	Acc@1 77.002 (81.013)	Acc@5 94.458 (95.776)	Mem 34604MB
[2025-01-19 11:46:23 internimage_b_1k_224] (main.py 575): INFO [Epoch:161] * Acc@1 80.898 Acc@5 95.819
[2025-01-19 11:46:23 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.9%
[2025-01-19 11:46:23 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.19%
[2025-01-19 11:46:26 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][100/312]	eta 0:02:41 lr 0.001765	time 0.7217 (0.7638)	model_time 0.7216 (0.7492)	loss 3.4607 (3.1090)	grad_norm 1.8176 (1.7136/0.7387)	mem 34602MB
[2025-01-19 11:46:32 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.106 (9.106)	Loss 0.6589 (0.6589)	Acc@1 84.619 (84.619)	Acc@5 97.681 (97.681)	Mem 34604MB
[2025-01-19 11:46:33 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][110/312]	eta 0:02:33 lr 0.001765	time 0.7277 (0.7613)	model_time 0.7275 (0.7479)	loss 2.9153 (3.0762)	grad_norm 1.1084 (1.6947/0.7198)	mem 34602MB
[2025-01-19 11:46:37 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (1.235)	Loss 0.9506 (0.7922)	Acc@1 77.368 (81.694)	Acc@5 94.629 (96.052)	Mem 34604MB
[2025-01-19 11:46:37 internimage_b_1k_224] (main.py 575): INFO [Epoch:161] * Acc@1 81.562 Acc@5 96.097
[2025-01-19 11:46:37 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.6%
[2025-01-19 11:46:37 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:46:41 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][120/312]	eta 0:02:25 lr 0.001764	time 0.7166 (0.7593)	model_time 0.7165 (0.7470)	loss 3.3830 (3.0951)	grad_norm 1.1788 (1.6962/0.7239)	mem 34602MB
[2025-01-19 11:46:41 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:46:41 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.56%
[2025-01-19 11:46:43 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][0/312]	eta 0:11:20 lr 0.001772	time 2.1811 (2.1811)	model_time 0.7385 (0.7385)	loss 3.7003 (3.7003)	grad_norm 1.3690 (1.3690/0.0000)	mem 34604MB
[2025-01-19 11:46:48 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][130/312]	eta 0:02:18 lr 0.001763	time 0.7217 (0.7590)	model_time 0.7213 (0.7476)	loss 3.5491 (3.1085)	grad_norm 0.9618 (1.6814/0.7142)	mem 34602MB
[2025-01-19 11:46:51 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][10/312]	eta 0:04:18 lr 0.001771	time 0.7181 (0.8571)	model_time 0.7180 (0.7257)	loss 3.3961 (3.3456)	grad_norm 3.0163 (1.4913/0.5712)	mem 34604MB
[2025-01-19 11:46:56 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][140/312]	eta 0:02:10 lr 0.001763	time 0.8165 (0.7603)	model_time 0.8163 (0.7497)	loss 3.7616 (3.1097)	grad_norm 1.1679 (1.6380/0.7098)	mem 34602MB
[2025-01-19 11:46:58 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][20/312]	eta 0:03:52 lr 0.001771	time 0.7247 (0.7970)	model_time 0.7243 (0.7280)	loss 3.5958 (3.2699)	grad_norm 1.7168 (1.4613/0.5323)	mem 34604MB
[2025-01-19 11:47:04 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][150/312]	eta 0:02:03 lr 0.001762	time 0.8448 (0.7615)	model_time 0.8444 (0.7515)	loss 3.7495 (3.1314)	grad_norm 1.9236 (1.6300/0.6945)	mem 34602MB
[2025-01-19 11:47:05 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][30/312]	eta 0:03:39 lr 0.001770	time 0.7958 (0.7768)	model_time 0.7957 (0.7300)	loss 2.6103 (3.1215)	grad_norm 2.3564 (1.5287/0.5026)	mem 34604MB
[2025-01-19 11:47:11 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][160/312]	eta 0:01:55 lr 0.001761	time 0.7186 (0.7612)	model_time 0.7181 (0.7519)	loss 2.7420 (3.1435)	grad_norm 1.3111 (1.6208/0.6807)	mem 34602MB
[2025-01-19 11:47:13 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][40/312]	eta 0:03:32 lr 0.001769	time 0.7149 (0.7797)	model_time 0.7147 (0.7443)	loss 3.6996 (3.1560)	grad_norm 0.7724 (1.5747/0.5477)	mem 34604MB
[2025-01-19 11:47:19 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][170/312]	eta 0:01:47 lr 0.001761	time 0.7225 (0.7600)	model_time 0.7224 (0.7512)	loss 3.6176 (3.1502)	grad_norm 0.8980 (1.6429/0.6883)	mem 34602MB
[2025-01-19 11:47:21 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][50/312]	eta 0:03:25 lr 0.001769	time 0.8092 (0.7826)	model_time 0.8087 (0.7540)	loss 3.4994 (3.1652)	grad_norm 4.3797 (1.6392/0.7456)	mem 34604MB
[2025-01-19 11:47:26 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][180/312]	eta 0:01:40 lr 0.001760	time 0.7225 (0.7591)	model_time 0.7221 (0.7508)	loss 3.6576 (3.1655)	grad_norm 1.7667 (1.6378/0.6833)	mem 34602MB
[2025-01-19 11:47:29 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][60/312]	eta 0:03:16 lr 0.001768	time 0.7154 (0.7799)	model_time 0.7153 (0.7560)	loss 3.4308 (3.1810)	grad_norm 2.6026 (1.6514/0.7398)	mem 34604MB
[2025-01-19 11:47:34 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][190/312]	eta 0:01:32 lr 0.001759	time 0.8230 (0.7585)	model_time 0.8228 (0.7506)	loss 3.3058 (3.1638)	grad_norm 0.9397 (1.6328/0.6779)	mem 34602MB
[2025-01-19 11:47:36 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][70/312]	eta 0:03:06 lr 0.001767	time 0.7482 (0.7724)	model_time 0.7480 (0.7518)	loss 2.4172 (3.1766)	grad_norm 1.7078 (1.7152/0.7321)	mem 34604MB
[2025-01-19 11:47:41 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][200/312]	eta 0:01:24 lr 0.001759	time 0.7232 (0.7576)	model_time 0.7228 (0.7501)	loss 3.7160 (3.1705)	grad_norm 1.0589 (1.6288/0.6796)	mem 34602MB
[2025-01-19 11:47:43 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][80/312]	eta 0:02:57 lr 0.001767	time 0.7276 (0.7666)	model_time 0.7275 (0.7484)	loss 3.5212 (3.1901)	grad_norm 2.4582 (1.7163/0.7272)	mem 34604MB
[2025-01-19 11:47:48 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][210/312]	eta 0:01:17 lr 0.001758	time 0.7236 (0.7563)	model_time 0.7235 (0.7491)	loss 3.5532 (3.1593)	grad_norm 1.9134 (1.6185/0.6696)	mem 34602MB
[2025-01-19 11:47:51 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][90/312]	eta 0:02:49 lr 0.001766	time 0.7399 (0.7627)	model_time 0.7397 (0.7465)	loss 2.9891 (3.2016)	grad_norm 2.0753 (1.7773/0.7708)	mem 34604MB
[2025-01-19 11:47:56 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][220/312]	eta 0:01:09 lr 0.001757	time 0.7583 (0.7552)	model_time 0.7581 (0.7483)	loss 3.0222 (3.1461)	grad_norm 3.1623 (1.6293/0.6749)	mem 34602MB
[2025-01-19 11:47:58 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][100/312]	eta 0:02:41 lr 0.001765	time 0.7141 (0.7602)	model_time 0.7140 (0.7456)	loss 2.6021 (3.1800)	grad_norm 1.0902 (1.7326/0.7544)	mem 34604MB
[2025-01-19 11:48:03 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][230/312]	eta 0:01:01 lr 0.001757	time 0.7261 (0.7549)	model_time 0.7260 (0.7483)	loss 2.7674 (3.1417)	grad_norm 1.8596 (1.6407/0.6727)	mem 34602MB
[2025-01-19 11:48:05 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][110/312]	eta 0:02:32 lr 0.001765	time 0.7297 (0.7570)	model_time 0.7296 (0.7437)	loss 3.3556 (3.1606)	grad_norm 1.2755 (1.6878/0.7367)	mem 34604MB
[2025-01-19 11:48:11 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][240/312]	eta 0:00:54 lr 0.001756	time 0.7423 (0.7544)	model_time 0.7421 (0.7481)	loss 2.4187 (3.1259)	grad_norm 2.5828 (1.6405/0.6631)	mem 34602MB
[2025-01-19 11:48:13 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][120/312]	eta 0:02:24 lr 0.001764	time 0.7083 (0.7548)	model_time 0.7081 (0.7425)	loss 2.4712 (3.1545)	grad_norm 2.2182 (1.6803/0.7119)	mem 34604MB
[2025-01-19 11:48:18 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][250/312]	eta 0:00:46 lr 0.001755	time 0.7180 (0.7545)	model_time 0.7176 (0.7484)	loss 2.8837 (3.1215)	grad_norm 1.6280 (1.6389/0.6640)	mem 34602MB
[2025-01-19 11:48:20 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][130/312]	eta 0:02:16 lr 0.001763	time 0.7241 (0.7527)	model_time 0.7237 (0.7414)	loss 2.6524 (3.1592)	grad_norm 0.8395 (1.6553/0.6987)	mem 34604MB
[2025-01-19 11:48:26 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][260/312]	eta 0:00:39 lr 0.001755	time 0.8049 (0.7550)	model_time 0.8047 (0.7491)	loss 3.4544 (3.1198)	grad_norm 1.2312 (1.6470/0.6646)	mem 34602MB
[2025-01-19 11:48:27 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][140/312]	eta 0:02:09 lr 0.001763	time 0.7244 (0.7517)	model_time 0.7243 (0.7411)	loss 3.2657 (3.1815)	grad_norm 3.7134 (1.6691/0.7040)	mem 34604MB
[2025-01-19 11:48:34 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][270/312]	eta 0:00:31 lr 0.001754	time 0.8147 (0.7556)	model_time 0.8144 (0.7499)	loss 3.2029 (3.1221)	grad_norm 2.4801 (1.6549/0.6682)	mem 34602MB
[2025-01-19 11:48:35 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][150/312]	eta 0:02:01 lr 0.001762	time 0.7988 (0.7503)	model_time 0.7983 (0.7404)	loss 3.6898 (3.1883)	grad_norm 1.4415 (1.6511/0.6927)	mem 34604MB
[2025-01-19 11:48:41 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][280/312]	eta 0:00:24 lr 0.001753	time 0.7157 (0.7556)	model_time 0.7156 (0.7501)	loss 3.7447 (3.1181)	grad_norm 0.9558 (1.6538/0.6658)	mem 34602MB
[2025-01-19 11:48:42 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][160/312]	eta 0:01:54 lr 0.001761	time 0.7182 (0.7517)	model_time 0.7180 (0.7425)	loss 2.5389 (3.1872)	grad_norm 1.7183 (1.6530/0.6953)	mem 34604MB
[2025-01-19 11:48:49 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][290/312]	eta 0:00:16 lr 0.001753	time 0.7254 (0.7549)	model_time 0.7253 (0.7496)	loss 3.0449 (3.1260)	grad_norm 1.5078 (1.6637/0.6699)	mem 34602MB
[2025-01-19 11:48:50 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][170/312]	eta 0:01:47 lr 0.001761	time 0.7189 (0.7546)	model_time 0.7187 (0.7459)	loss 2.5147 (3.1835)	grad_norm 0.9590 (1.6368/0.6890)	mem 34604MB
[2025-01-19 11:48:56 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][300/312]	eta 0:00:09 lr 0.001752	time 0.7140 (0.7540)	model_time 0.7139 (0.7489)	loss 3.3258 (3.1309)	grad_norm 1.7873 (1.6448/0.6668)	mem 34602MB
[2025-01-19 11:48:58 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][180/312]	eta 0:01:39 lr 0.001760	time 0.7215 (0.7556)	model_time 0.7211 (0.7473)	loss 2.4062 (3.1751)	grad_norm 1.3627 (1.6223/0.6767)	mem 34604MB
[2025-01-19 11:49:03 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][310/312]	eta 0:00:01 lr 0.001751	time 0.7177 (0.7530)	model_time 0.7176 (0.7480)	loss 3.3927 (3.1390)	grad_norm 1.3004 (1.6235/0.6544)	mem 34602MB
[2025-01-19 11:49:04 internimage_b_1k_224] (main.py 519): INFO EPOCH 162 training takes 0:03:55
[2025-01-19 11:49:04 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_162.pth saving......
[2025-01-19 11:49:05 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][190/312]	eta 0:01:31 lr 0.001759	time 0.7254 (0.7540)	model_time 0.7253 (0.7461)	loss 3.5486 (3.1700)	grad_norm 0.7616 (1.6178/0.6739)	mem 34604MB
[2025-01-19 11:49:07 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_162.pth saved !!!
[2025-01-19 11:49:12 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][200/312]	eta 0:01:24 lr 0.001759	time 0.7087 (0.7525)	model_time 0.7083 (0.7450)	loss 3.5391 (3.1632)	grad_norm 2.2419 (1.6361/0.6757)	mem 34604MB
[2025-01-19 11:49:15 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.734 (7.734)	Loss 0.7870 (0.7870)	Acc@1 83.911 (83.911)	Acc@5 97.119 (97.119)	Mem 34602MB
[2025-01-19 11:49:18 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.979)	Loss 1.0468 (0.9072)	Acc@1 76.440 (81.288)	Acc@5 94.556 (95.830)	Mem 34602MB
[2025-01-19 11:49:18 internimage_b_1k_224] (main.py 575): INFO [Epoch:162] * Acc@1 81.142 Acc@5 95.859
[2025-01-19 11:49:18 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.1%
[2025-01-19 11:49:18 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 11:49:20 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][210/312]	eta 0:01:16 lr 0.001758	time 0.7236 (0.7512)	model_time 0.7235 (0.7441)	loss 2.6605 (3.1574)	grad_norm 1.1611 (1.6421/0.6792)	mem 34604MB
[2025-01-19 11:49:21 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 11:49:21 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.14%
[2025-01-19 11:49:27 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][220/312]	eta 0:01:09 lr 0.001757	time 0.7211 (0.7502)	model_time 0.7210 (0.7434)	loss 3.5786 (3.1530)	grad_norm 0.7900 (1.6186/0.6754)	mem 34604MB
[2025-01-19 11:49:29 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.774 (7.774)	Loss 0.6604 (0.6604)	Acc@1 84.351 (84.351)	Acc@5 97.632 (97.632)	Mem 34602MB
[2025-01-19 11:49:32 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.995)	Loss 0.9527 (0.7933)	Acc@1 77.393 (81.718)	Acc@5 94.629 (96.007)	Mem 34602MB
[2025-01-19 11:49:33 internimage_b_1k_224] (main.py 575): INFO [Epoch:162] * Acc@1 81.580 Acc@5 96.057
[2025-01-19 11:49:33 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.6%
[2025-01-19 11:49:33 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:49:34 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][230/312]	eta 0:01:01 lr 0.001757	time 0.7451 (0.7492)	model_time 0.7449 (0.7427)	loss 2.1141 (3.1483)	grad_norm 2.0702 (1.5993/0.6752)	mem 34604MB
[2025-01-19 11:49:36 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:49:36 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.58%
[2025-01-19 11:49:38 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][0/312]	eta 0:10:28 lr 0.001751	time 2.0131 (2.0131)	model_time 0.7422 (0.7422)	loss 2.9543 (2.9543)	grad_norm 1.2016 (1.2016/0.0000)	mem 34602MB
[2025-01-19 11:49:42 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][240/312]	eta 0:00:53 lr 0.001756	time 0.7219 (0.7483)	model_time 0.7217 (0.7420)	loss 2.8022 (3.1507)	grad_norm 0.8386 (1.6064/0.6803)	mem 34604MB
[2025-01-19 11:49:46 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][10/312]	eta 0:04:19 lr 0.001751	time 0.7211 (0.8581)	model_time 0.7207 (0.7422)	loss 3.4148 (3.4725)	grad_norm 1.3284 (1.3631/0.2892)	mem 34602MB
[2025-01-19 11:49:49 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][250/312]	eta 0:00:46 lr 0.001755	time 0.7282 (0.7472)	model_time 0.7278 (0.7412)	loss 2.8128 (3.1535)	grad_norm 1.5155 (1.6095/0.6818)	mem 34604MB
[2025-01-19 11:49:53 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][20/312]	eta 0:03:52 lr 0.001750	time 0.7165 (0.7978)	model_time 0.7160 (0.7370)	loss 3.8573 (3.3714)	grad_norm 1.8392 (1.4341/0.3835)	mem 34602MB
[2025-01-19 11:49:56 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][260/312]	eta 0:00:38 lr 0.001755	time 0.7405 (0.7466)	model_time 0.7401 (0.7408)	loss 3.9728 (3.1545)	grad_norm 1.0227 (1.6061/0.6765)	mem 34604MB
[2025-01-19 11:50:00 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][30/312]	eta 0:03:38 lr 0.001749	time 0.7309 (0.7761)	model_time 0.7308 (0.7348)	loss 3.5938 (3.3375)	grad_norm 0.9964 (1.4605/0.5359)	mem 34602MB
[2025-01-19 11:50:03 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][270/312]	eta 0:00:31 lr 0.001754	time 0.8111 (0.7461)	model_time 0.8106 (0.7405)	loss 3.2754 (3.1564)	grad_norm 2.8778 (1.6340/0.7118)	mem 34604MB
[2025-01-19 11:50:08 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][40/312]	eta 0:03:29 lr 0.001749	time 0.7161 (0.7705)	model_time 0.7159 (0.7392)	loss 3.6402 (3.3589)	grad_norm 1.1203 (1.6069/0.6776)	mem 34602MB
[2025-01-19 11:50:11 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][280/312]	eta 0:00:23 lr 0.001753	time 0.8001 (0.7470)	model_time 0.8000 (0.7415)	loss 2.3217 (3.1500)	grad_norm 1.0050 (1.6521/0.7222)	mem 34604MB
[2025-01-19 11:50:15 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][50/312]	eta 0:03:20 lr 0.001748	time 0.7216 (0.7636)	model_time 0.7212 (0.7383)	loss 3.4758 (3.3235)	grad_norm 3.1248 (1.6689/0.6828)	mem 34602MB
[2025-01-19 11:50:19 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][290/312]	eta 0:00:16 lr 0.001753	time 0.8089 (0.7484)	model_time 0.8087 (0.7432)	loss 3.0478 (3.1443)	grad_norm 0.7756 (1.6549/0.7206)	mem 34604MB
[2025-01-19 11:50:23 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][60/312]	eta 0:03:11 lr 0.001747	time 0.8017 (0.7617)	model_time 0.8013 (0.7405)	loss 3.4160 (3.3265)	grad_norm 1.9727 (1.7057/0.7317)	mem 34602MB
[2025-01-19 11:50:27 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][300/312]	eta 0:00:08 lr 0.001752	time 0.7166 (0.7492)	model_time 0.7165 (0.7441)	loss 3.1835 (3.1433)	grad_norm 1.0683 (1.6557/0.7120)	mem 34604MB
[2025-01-19 11:50:30 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][70/312]	eta 0:03:04 lr 0.001747	time 0.8062 (0.7619)	model_time 0.8061 (0.7436)	loss 2.7811 (3.3249)	grad_norm 1.6395 (1.8584/0.8082)	mem 34602MB
[2025-01-19 11:50:34 internimage_b_1k_224] (main.py 510): INFO Train: [162/300][310/312]	eta 0:00:01 lr 0.001751	time 0.7216 (0.7482)	model_time 0.7215 (0.7432)	loss 3.2499 (3.1498)	grad_norm 1.8541 (1.6498/0.7094)	mem 34604MB
[2025-01-19 11:50:35 internimage_b_1k_224] (main.py 519): INFO EPOCH 162 training takes 0:03:53
[2025-01-19 11:50:35 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_162.pth saving......
[2025-01-19 11:50:38 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_162.pth saved !!!
[2025-01-19 11:50:38 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][80/312]	eta 0:02:56 lr 0.001746	time 0.7149 (0.7623)	model_time 0.7145 (0.7462)	loss 2.6870 (3.2906)	grad_norm 0.8354 (1.8663/0.8056)	mem 34602MB
[2025-01-19 11:50:45 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.508 (7.508)	Loss 0.7621 (0.7621)	Acc@1 83.838 (83.838)	Acc@5 97.168 (97.168)	Mem 34604MB
[2025-01-19 11:50:46 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][90/312]	eta 0:02:49 lr 0.001745	time 0.7960 (0.7637)	model_time 0.7956 (0.7493)	loss 2.6077 (3.2723)	grad_norm 1.0940 (1.8107/0.7844)	mem 34602MB
[2025-01-19 11:50:49 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.974)	Loss 1.0373 (0.8851)	Acc@1 76.465 (81.163)	Acc@5 94.336 (95.787)	Mem 34604MB
[2025-01-19 11:50:49 internimage_b_1k_224] (main.py 575): INFO [Epoch:162] * Acc@1 81.066 Acc@5 95.841
[2025-01-19 11:50:49 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.1%
[2025-01-19 11:50:49 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.19%
[2025-01-19 11:50:53 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][100/312]	eta 0:02:41 lr 0.001745	time 0.7203 (0.7622)	model_time 0.7201 (0.7492)	loss 3.0506 (3.2757)	grad_norm 1.2895 (1.7282/0.7874)	mem 34602MB
[2025-01-19 11:50:58 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.324 (9.324)	Loss 0.6595 (0.6595)	Acc@1 84.644 (84.644)	Acc@5 97.681 (97.681)	Mem 34604MB
[2025-01-19 11:51:01 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][110/312]	eta 0:02:33 lr 0.001744	time 0.7228 (0.7593)	model_time 0.7226 (0.7475)	loss 2.1343 (3.2515)	grad_norm 0.8309 (1.6823/0.7695)	mem 34602MB
[2025-01-19 11:51:03 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (1.260)	Loss 0.9505 (0.7923)	Acc@1 77.393 (81.732)	Acc@5 94.556 (96.047)	Mem 34604MB
[2025-01-19 11:51:03 internimage_b_1k_224] (main.py 575): INFO [Epoch:162] * Acc@1 81.596 Acc@5 96.093
[2025-01-19 11:51:03 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.6%
[2025-01-19 11:51:03 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:51:07 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:51:07 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.60%
[2025-01-19 11:51:08 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][120/312]	eta 0:02:25 lr 0.001743	time 0.7179 (0.7582)	model_time 0.7175 (0.7473)	loss 3.3169 (3.2568)	grad_norm 1.8106 (1.6425/0.7584)	mem 34602MB
[2025-01-19 11:51:09 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][0/312]	eta 0:10:21 lr 0.001751	time 1.9920 (1.9920)	model_time 0.7367 (0.7367)	loss 3.2291 (3.2291)	grad_norm 2.0549 (2.0549/0.0000)	mem 34604MB
[2025-01-19 11:51:16 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][130/312]	eta 0:02:17 lr 0.001743	time 0.7161 (0.7577)	model_time 0.7159 (0.7476)	loss 2.3933 (3.2210)	grad_norm 1.1823 (1.6096/0.7449)	mem 34602MB
[2025-01-19 11:51:17 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][10/312]	eta 0:04:13 lr 0.001751	time 0.7407 (0.8401)	model_time 0.7406 (0.7257)	loss 3.9441 (3.4520)	grad_norm 2.2069 (2.0332/0.6639)	mem 34604MB
[2025-01-19 11:51:23 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][140/312]	eta 0:02:10 lr 0.001742	time 0.7196 (0.7559)	model_time 0.7194 (0.7465)	loss 4.0249 (3.2111)	grad_norm 2.7664 (1.6642/0.8042)	mem 34602MB
[2025-01-19 11:51:24 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][20/312]	eta 0:03:49 lr 0.001750	time 0.7237 (0.7844)	model_time 0.7233 (0.7244)	loss 3.8058 (3.3155)	grad_norm 1.5512 (1.8371/0.7236)	mem 34604MB
[2025-01-19 11:51:30 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][150/312]	eta 0:02:02 lr 0.001741	time 0.7311 (0.7545)	model_time 0.7307 (0.7457)	loss 2.6075 (3.2099)	grad_norm 1.2586 (1.6473/0.7906)	mem 34602MB
[2025-01-19 11:51:31 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][30/312]	eta 0:03:36 lr 0.001749	time 0.7198 (0.7667)	model_time 0.7193 (0.7259)	loss 3.5189 (3.3589)	grad_norm 1.4950 (1.6668/0.6716)	mem 34604MB
[2025-01-19 11:51:38 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][160/312]	eta 0:01:54 lr 0.001741	time 0.7212 (0.7540)	model_time 0.7207 (0.7458)	loss 3.4205 (3.2058)	grad_norm 1.5690 (1.6407/0.7724)	mem 34602MB
[2025-01-19 11:51:38 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][40/312]	eta 0:03:25 lr 0.001749	time 0.7193 (0.7572)	model_time 0.7188 (0.7263)	loss 3.8200 (3.3050)	grad_norm 2.3538 (1.5975/0.6353)	mem 34604MB
[2025-01-19 11:51:45 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][170/312]	eta 0:01:46 lr 0.001740	time 0.8056 (0.7532)	model_time 0.8052 (0.7454)	loss 3.2825 (3.1998)	grad_norm 0.9759 (1.6177/0.7598)	mem 34602MB
[2025-01-19 11:51:46 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][50/312]	eta 0:03:16 lr 0.001748	time 0.7254 (0.7517)	model_time 0.7250 (0.7268)	loss 3.8167 (3.2986)	grad_norm 1.9543 (1.5720/0.6119)	mem 34604MB
[2025-01-19 11:51:53 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][180/312]	eta 0:01:39 lr 0.001739	time 0.7935 (0.7531)	model_time 0.7934 (0.7457)	loss 3.2070 (3.2039)	grad_norm 1.5027 (1.6315/0.7510)	mem 34602MB
[2025-01-19 11:51:53 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][60/312]	eta 0:03:08 lr 0.001747	time 0.7227 (0.7479)	model_time 0.7226 (0.7270)	loss 3.5253 (3.3185)	grad_norm 2.0044 (1.4976/0.6012)	mem 34604MB
[2025-01-19 11:52:00 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][70/312]	eta 0:03:00 lr 0.001747	time 0.7237 (0.7452)	model_time 0.7233 (0.7272)	loss 4.2099 (3.3521)	grad_norm 1.2145 (1.5476/0.6549)	mem 34604MB
[2025-01-19 11:52:00 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][190/312]	eta 0:01:31 lr 0.001739	time 0.8119 (0.7533)	model_time 0.8114 (0.7463)	loss 3.3817 (3.2028)	grad_norm 1.6943 (1.6214/0.7346)	mem 34602MB
[2025-01-19 11:52:08 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][80/312]	eta 0:02:52 lr 0.001746	time 0.7205 (0.7451)	model_time 0.7204 (0.7292)	loss 2.7979 (3.3059)	grad_norm 2.5227 (1.6829/0.9215)	mem 34604MB
[2025-01-19 11:52:08 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][200/312]	eta 0:01:24 lr 0.001738	time 0.8020 (0.7543)	model_time 0.8015 (0.7476)	loss 3.4515 (3.2021)	grad_norm 1.6394 (1.6153/0.7241)	mem 34602MB
[2025-01-19 11:52:16 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][90/312]	eta 0:02:46 lr 0.001745	time 0.9890 (0.7507)	model_time 0.9888 (0.7366)	loss 3.5205 (3.2886)	grad_norm 1.4920 (1.6862/0.9160)	mem 34604MB
[2025-01-19 11:52:16 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][210/312]	eta 0:01:16 lr 0.001737	time 0.8043 (0.7547)	model_time 0.8042 (0.7483)	loss 3.1961 (3.2013)	grad_norm 2.6506 (1.6013/0.7197)	mem 34602MB
[2025-01-19 11:52:23 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][220/312]	eta 0:01:09 lr 0.001737	time 0.7149 (0.7542)	model_time 0.7144 (0.7481)	loss 2.0166 (3.1910)	grad_norm 1.0253 (1.5932/0.7116)	mem 34602MB
[2025-01-19 11:52:24 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][100/312]	eta 0:02:39 lr 0.001745	time 0.8080 (0.7545)	model_time 0.8076 (0.7417)	loss 2.2651 (3.2745)	grad_norm 1.2845 (1.6442/0.8834)	mem 34604MB
[2025-01-19 11:52:30 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][230/312]	eta 0:01:01 lr 0.001736	time 0.7205 (0.7529)	model_time 0.7200 (0.7471)	loss 2.4538 (3.1891)	grad_norm 1.1404 (1.6008/0.7054)	mem 34602MB
[2025-01-19 11:52:31 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][110/312]	eta 0:02:32 lr 0.001744	time 0.7247 (0.7572)	model_time 0.7246 (0.7456)	loss 2.5191 (3.2544)	grad_norm 1.6289 (1.6365/0.8525)	mem 34604MB
[2025-01-19 11:52:38 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][240/312]	eta 0:00:54 lr 0.001735	time 0.7236 (0.7526)	model_time 0.7235 (0.7470)	loss 3.4773 (3.1950)	grad_norm 1.5374 (1.6172/0.7027)	mem 34602MB
[2025-01-19 11:52:39 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][120/312]	eta 0:02:25 lr 0.001743	time 0.7231 (0.7555)	model_time 0.7229 (0.7448)	loss 3.9919 (3.2458)	grad_norm 1.4090 (1.6297/0.8355)	mem 34604MB
[2025-01-19 11:52:45 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][250/312]	eta 0:00:46 lr 0.001735	time 0.7225 (0.7526)	model_time 0.7224 (0.7471)	loss 3.3410 (3.1940)	grad_norm 1.3306 (1.6192/0.6970)	mem 34602MB
[2025-01-19 11:52:46 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][130/312]	eta 0:02:17 lr 0.001743	time 0.7180 (0.7537)	model_time 0.7176 (0.7438)	loss 3.3102 (3.2345)	grad_norm 1.3761 (1.6170/0.8078)	mem 34604MB
[2025-01-19 11:52:53 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][260/312]	eta 0:00:39 lr 0.001734	time 0.7609 (0.7518)	model_time 0.7604 (0.7466)	loss 4.1535 (3.1944)	grad_norm 1.1676 (1.6357/0.7144)	mem 34602MB
[2025-01-19 11:52:53 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][140/312]	eta 0:02:09 lr 0.001742	time 0.7167 (0.7516)	model_time 0.7163 (0.7424)	loss 3.9253 (3.2415)	grad_norm 0.8701 (1.5856/0.7888)	mem 34604MB
[2025-01-19 11:53:00 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][270/312]	eta 0:00:31 lr 0.001734	time 0.7277 (0.7511)	model_time 0.7276 (0.7460)	loss 3.3941 (3.1921)	grad_norm 1.2680 (1.6414/0.7136)	mem 34602MB
[2025-01-19 11:53:01 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][150/312]	eta 0:02:01 lr 0.001741	time 0.7266 (0.7501)	model_time 0.7262 (0.7414)	loss 3.5603 (3.2278)	grad_norm 0.8216 (1.5885/0.7707)	mem 34604MB
[2025-01-19 11:53:07 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][280/312]	eta 0:00:24 lr 0.001733	time 0.7837 (0.7512)	model_time 0.7832 (0.7463)	loss 2.1670 (3.1722)	grad_norm 1.7021 (1.6390/0.7049)	mem 34602MB
[2025-01-19 11:53:08 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][160/312]	eta 0:01:53 lr 0.001741	time 0.7194 (0.7487)	model_time 0.7192 (0.7406)	loss 2.2113 (3.2256)	grad_norm 1.3846 (1.5767/0.7536)	mem 34604MB
[2025-01-19 11:53:15 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][290/312]	eta 0:00:16 lr 0.001732	time 0.8041 (0.7507)	model_time 0.8037 (0.7459)	loss 2.6081 (3.1696)	grad_norm 0.8146 (1.6335/0.7022)	mem 34602MB
[2025-01-19 11:53:15 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][170/312]	eta 0:01:46 lr 0.001740	time 0.7289 (0.7474)	model_time 0.7288 (0.7397)	loss 2.3218 (3.2173)	grad_norm 1.2845 (1.5534/0.7390)	mem 34604MB
[2025-01-19 11:53:22 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][300/312]	eta 0:00:08 lr 0.001732	time 0.7158 (0.7500)	model_time 0.7157 (0.7454)	loss 3.8457 (3.1750)	grad_norm 0.9214 (1.6399/0.7125)	mem 34602MB
[2025-01-19 11:53:22 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][180/312]	eta 0:01:38 lr 0.001739	time 0.7669 (0.7464)	model_time 0.7664 (0.7392)	loss 3.7457 (3.2277)	grad_norm 1.3398 (1.6115/0.8221)	mem 34604MB
[2025-01-19 11:53:30 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][310/312]	eta 0:00:01 lr 0.001731	time 0.7151 (0.7497)	model_time 0.7150 (0.7452)	loss 3.4449 (3.1828)	grad_norm 1.3582 (1.6507/0.7200)	mem 34602MB
[2025-01-19 11:53:30 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][190/312]	eta 0:01:30 lr 0.001739	time 0.7106 (0.7451)	model_time 0.7101 (0.7381)	loss 3.2795 (3.2179)	grad_norm 1.2836 (1.6044/0.8061)	mem 34604MB
[2025-01-19 11:53:30 internimage_b_1k_224] (main.py 519): INFO EPOCH 163 training takes 0:03:53
[2025-01-19 11:53:30 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_163.pth saving......
[2025-01-19 11:53:33 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_163.pth saved !!!
[2025-01-19 11:53:37 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][200/312]	eta 0:01:23 lr 0.001738	time 0.7183 (0.7445)	model_time 0.7178 (0.7379)	loss 3.4486 (3.2159)	grad_norm 1.0252 (1.5897/0.7920)	mem 34604MB
[2025-01-19 11:53:42 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.870 (7.870)	Loss 0.7537 (0.7537)	Acc@1 83.765 (83.765)	Acc@5 97.046 (97.046)	Mem 34602MB
[2025-01-19 11:53:45 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.990)	Loss 1.0311 (0.8753)	Acc@1 77.490 (81.443)	Acc@5 94.238 (95.814)	Mem 34602MB
[2025-01-19 11:53:45 internimage_b_1k_224] (main.py 575): INFO [Epoch:163] * Acc@1 81.236 Acc@5 95.839
[2025-01-19 11:53:45 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.2%
[2025-01-19 11:53:45 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 11:53:45 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][210/312]	eta 0:01:16 lr 0.001737	time 0.8406 (0.7465)	model_time 0.8401 (0.7402)	loss 3.7122 (3.2022)	grad_norm 0.9980 (1.5833/0.7787)	mem 34604MB
[2025-01-19 11:53:48 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 11:53:48 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.24%
[2025-01-19 11:53:53 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][220/312]	eta 0:01:08 lr 0.001737	time 0.8005 (0.7483)	model_time 0.8001 (0.7422)	loss 2.3846 (3.1907)	grad_norm 2.3166 (1.5819/0.7684)	mem 34604MB
[2025-01-19 11:53:57 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.261 (8.261)	Loss 0.6611 (0.6611)	Acc@1 84.302 (84.302)	Acc@5 97.681 (97.681)	Mem 34602MB
[2025-01-19 11:54:00 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.031)	Loss 0.9519 (0.7935)	Acc@1 77.368 (81.723)	Acc@5 94.629 (96.036)	Mem 34602MB
[2025-01-19 11:54:00 internimage_b_1k_224] (main.py 575): INFO [Epoch:163] * Acc@1 81.586 Acc@5 96.089
[2025-01-19 11:54:00 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.6%
[2025-01-19 11:54:00 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:54:00 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][230/312]	eta 0:01:01 lr 0.001736	time 0.7157 (0.7489)	model_time 0.7156 (0.7431)	loss 2.1037 (3.1776)	grad_norm 0.9104 (1.5863/0.7607)	mem 34604MB
[2025-01-19 11:54:04 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:54:04 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.59%
[2025-01-19 11:54:06 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][0/312]	eta 0:10:20 lr 0.001731	time 1.9879 (1.9879)	model_time 0.7538 (0.7538)	loss 3.6461 (3.6461)	grad_norm 0.9197 (0.9197/0.0000)	mem 34602MB
[2025-01-19 11:54:08 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][240/312]	eta 0:00:53 lr 0.001735	time 0.7166 (0.7483)	model_time 0.7162 (0.7428)	loss 3.5342 (3.1675)	grad_norm 1.1974 (1.5946/0.7581)	mem 34604MB
[2025-01-19 11:54:13 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][10/312]	eta 0:04:30 lr 0.001730	time 0.7241 (0.8941)	model_time 0.7239 (0.7815)	loss 2.7845 (2.9911)	grad_norm 1.2231 (1.0386/0.1717)	mem 34602MB
[2025-01-19 11:54:15 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][250/312]	eta 0:00:46 lr 0.001735	time 0.7196 (0.7478)	model_time 0.7191 (0.7424)	loss 3.7896 (3.1651)	grad_norm 2.0529 (1.5850/0.7480)	mem 34604MB
[2025-01-19 11:54:21 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][20/312]	eta 0:04:01 lr 0.001729	time 0.8077 (0.8282)	model_time 0.8073 (0.7692)	loss 2.3109 (3.0964)	grad_norm 0.9411 (1.1675/0.3007)	mem 34602MB
[2025-01-19 11:54:22 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][260/312]	eta 0:00:38 lr 0.001734	time 0.7229 (0.7470)	model_time 0.7228 (0.7419)	loss 3.3572 (3.1589)	grad_norm 1.1768 (1.5768/0.7378)	mem 34604MB
[2025-01-19 11:54:28 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][30/312]	eta 0:03:45 lr 0.001729	time 0.8114 (0.8004)	model_time 0.8112 (0.7602)	loss 3.3944 (3.1351)	grad_norm 1.2258 (1.2898/0.4702)	mem 34602MB
[2025-01-19 11:54:30 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][270/312]	eta 0:00:31 lr 0.001734	time 0.7317 (0.7462)	model_time 0.7313 (0.7412)	loss 3.2618 (3.1657)	grad_norm 1.3969 (1.5929/0.7578)	mem 34604MB
[2025-01-19 11:54:36 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][40/312]	eta 0:03:32 lr 0.001728	time 0.7224 (0.7829)	model_time 0.7221 (0.7525)	loss 3.3630 (3.0684)	grad_norm 3.0350 (1.5355/0.7284)	mem 34602MB
[2025-01-19 11:54:37 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][280/312]	eta 0:00:23 lr 0.001733	time 0.7089 (0.7453)	model_time 0.7087 (0.7405)	loss 2.4695 (3.1628)	grad_norm 1.3682 (1.5783/0.7489)	mem 34604MB
[2025-01-19 11:54:43 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][50/312]	eta 0:03:23 lr 0.001727	time 0.7158 (0.7750)	model_time 0.7154 (0.7505)	loss 3.5166 (3.0179)	grad_norm 1.8553 (1.5713/0.6948)	mem 34602MB
[2025-01-19 11:54:44 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][290/312]	eta 0:00:16 lr 0.001732	time 0.7236 (0.7445)	model_time 0.7232 (0.7398)	loss 2.5782 (3.1638)	grad_norm 1.0177 (1.5815/0.7449)	mem 34604MB
[2025-01-19 11:54:51 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][60/312]	eta 0:03:14 lr 0.001727	time 0.8182 (0.7718)	model_time 0.8180 (0.7512)	loss 3.4868 (3.0053)	grad_norm 1.2885 (1.5242/0.6768)	mem 34602MB
[2025-01-19 11:54:51 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][300/312]	eta 0:00:08 lr 0.001732	time 0.7130 (0.7437)	model_time 0.7129 (0.7392)	loss 3.8355 (3.1694)	grad_norm 1.3542 (1.5950/0.7577)	mem 34604MB
[2025-01-19 11:54:58 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][70/312]	eta 0:03:05 lr 0.001726	time 0.7174 (0.7656)	model_time 0.7169 (0.7479)	loss 3.8370 (2.9841)	grad_norm 3.2842 (1.5667/0.6794)	mem 34602MB
[2025-01-19 11:54:58 internimage_b_1k_224] (main.py 510): INFO Train: [163/300][310/312]	eta 0:00:01 lr 0.001731	time 0.7149 (0.7429)	model_time 0.7148 (0.7385)	loss 3.7056 (3.1711)	grad_norm 2.4317 (1.5745/0.7496)	mem 34604MB
[2025-01-19 11:54:59 internimage_b_1k_224] (main.py 519): INFO EPOCH 163 training takes 0:03:51
[2025-01-19 11:54:59 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_163.pth saving......
[2025-01-19 11:55:02 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_163.pth saved !!!
[2025-01-19 11:55:05 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][80/312]	eta 0:02:56 lr 0.001725	time 0.7168 (0.7612)	model_time 0.7164 (0.7456)	loss 2.8150 (2.9656)	grad_norm 1.0955 (1.5808/0.6675)	mem 34602MB
[2025-01-19 11:55:10 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.696 (7.696)	Loss 0.7617 (0.7617)	Acc@1 83.887 (83.887)	Acc@5 97.388 (97.388)	Mem 34604MB
[2025-01-19 11:55:13 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][90/312]	eta 0:02:48 lr 0.001725	time 0.8083 (0.7611)	model_time 0.8081 (0.7471)	loss 3.4787 (2.9819)	grad_norm 1.6623 (1.5763/0.6493)	mem 34602MB
[2025-01-19 11:55:13 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.972)	Loss 1.0374 (0.9017)	Acc@1 76.929 (81.155)	Acc@5 94.849 (95.881)	Mem 34604MB
[2025-01-19 11:55:13 internimage_b_1k_224] (main.py 575): INFO [Epoch:163] * Acc@1 81.082 Acc@5 95.891
[2025-01-19 11:55:13 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.1%
[2025-01-19 11:55:13 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.19%
[2025-01-19 11:55:20 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][100/312]	eta 0:02:40 lr 0.001724	time 0.7289 (0.7582)	model_time 0.7284 (0.7456)	loss 3.4627 (3.0138)	grad_norm 0.7678 (1.5680/0.6385)	mem 34602MB
[2025-01-19 11:55:23 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.338 (9.338)	Loss 0.6603 (0.6603)	Acc@1 84.717 (84.717)	Acc@5 97.681 (97.681)	Mem 34604MB
[2025-01-19 11:55:27 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.274)	Loss 0.9506 (0.7926)	Acc@1 77.441 (81.774)	Acc@5 94.629 (96.069)	Mem 34604MB
[2025-01-19 11:55:28 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][110/312]	eta 0:02:32 lr 0.001724	time 0.7208 (0.7560)	model_time 0.7204 (0.7446)	loss 3.3134 (3.0197)	grad_norm 1.5826 (1.5861/0.6429)	mem 34602MB
[2025-01-19 11:55:28 internimage_b_1k_224] (main.py 575): INFO [Epoch:163] * Acc@1 81.638 Acc@5 96.113
[2025-01-19 11:55:28 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.6%
[2025-01-19 11:55:28 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:55:32 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:55:32 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.64%
[2025-01-19 11:55:34 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][0/312]	eta 0:10:33 lr 0.001731	time 2.0318 (2.0318)	model_time 0.7477 (0.7477)	loss 2.9679 (2.9679)	grad_norm 1.0199 (1.0199/0.0000)	mem 34604MB
[2025-01-19 11:55:35 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][120/312]	eta 0:02:25 lr 0.001723	time 0.8109 (0.7570)	model_time 0.8108 (0.7464)	loss 3.7187 (3.0290)	grad_norm 1.5575 (1.5716/0.6208)	mem 34602MB
[2025-01-19 11:55:41 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][10/312]	eta 0:04:22 lr 0.001730	time 0.8368 (0.8679)	model_time 0.8367 (0.7509)	loss 2.6190 (3.0835)	grad_norm 1.4206 (1.3882/0.3687)	mem 34604MB
[2025-01-19 11:55:43 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][130/312]	eta 0:02:18 lr 0.001722	time 0.7206 (0.7586)	model_time 0.7205 (0.7488)	loss 3.2314 (3.0624)	grad_norm 1.4139 (1.5555/0.6058)	mem 34602MB
[2025-01-19 11:55:49 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][20/312]	eta 0:04:00 lr 0.001729	time 0.8004 (0.8234)	model_time 0.7999 (0.7619)	loss 3.7084 (3.2339)	grad_norm 1.6341 (1.8921/0.7988)	mem 34604MB
[2025-01-19 11:55:51 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][140/312]	eta 0:02:10 lr 0.001722	time 0.8062 (0.7584)	model_time 0.8061 (0.7493)	loss 3.1870 (3.0498)	grad_norm 2.0309 (1.5516/0.5975)	mem 34602MB
[2025-01-19 11:55:57 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][30/312]	eta 0:03:48 lr 0.001729	time 0.7169 (0.8118)	model_time 0.7167 (0.7700)	loss 3.2546 (3.1364)	grad_norm 1.4413 (1.7611/0.7443)	mem 34604MB
[2025-01-19 11:55:58 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][150/312]	eta 0:02:02 lr 0.001721	time 0.8136 (0.7579)	model_time 0.8134 (0.7494)	loss 1.9721 (3.0357)	grad_norm 1.8028 (1.6033/0.6463)	mem 34602MB
[2025-01-19 11:56:05 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][40/312]	eta 0:03:38 lr 0.001728	time 0.7981 (0.8049)	model_time 0.7977 (0.7732)	loss 3.1711 (3.1685)	grad_norm 1.2853 (1.6773/0.7145)	mem 34604MB
[2025-01-19 11:56:05 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][160/312]	eta 0:01:54 lr 0.001720	time 0.7358 (0.7560)	model_time 0.7354 (0.7480)	loss 2.7885 (3.0431)	grad_norm 2.0416 (1.6514/0.7017)	mem 34602MB
[2025-01-19 11:56:12 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][50/312]	eta 0:03:27 lr 0.001727	time 0.7187 (0.7903)	model_time 0.7185 (0.7648)	loss 2.2947 (3.1443)	grad_norm 1.0352 (1.5621/0.6884)	mem 34604MB
[2025-01-19 11:56:13 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][170/312]	eta 0:01:47 lr 0.001720	time 0.8089 (0.7552)	model_time 0.8087 (0.7476)	loss 3.1624 (3.0471)	grad_norm 1.0903 (1.6335/0.6909)	mem 34602MB
[2025-01-19 11:56:19 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][60/312]	eta 0:03:16 lr 0.001727	time 0.7200 (0.7802)	model_time 0.7196 (0.7588)	loss 2.7428 (3.1147)	grad_norm 1.8572 (1.6901/0.7570)	mem 34604MB
[2025-01-19 11:56:20 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][180/312]	eta 0:01:39 lr 0.001719	time 0.8149 (0.7550)	model_time 0.8148 (0.7478)	loss 3.6833 (3.0606)	grad_norm 2.5411 (1.6173/0.6911)	mem 34602MB
[2025-01-19 11:56:27 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][70/312]	eta 0:03:07 lr 0.001726	time 0.7239 (0.7732)	model_time 0.7235 (0.7547)	loss 3.4698 (3.1502)	grad_norm 1.9540 (1.6969/0.7272)	mem 34604MB
[2025-01-19 11:56:28 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][190/312]	eta 0:01:31 lr 0.001718	time 0.7210 (0.7537)	model_time 0.7205 (0.7469)	loss 3.6103 (3.0748)	grad_norm 1.2681 (1.6051/0.6775)	mem 34602MB
[2025-01-19 11:56:34 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][80/312]	eta 0:02:58 lr 0.001725	time 0.7252 (0.7676)	model_time 0.7250 (0.7513)	loss 2.8621 (3.1279)	grad_norm 2.6139 (1.6687/0.7112)	mem 34604MB
[2025-01-19 11:56:35 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][200/312]	eta 0:01:24 lr 0.001718	time 0.7179 (0.7525)	model_time 0.7178 (0.7460)	loss 3.6061 (3.0776)	grad_norm 1.4327 (1.5875/0.6673)	mem 34602MB
[2025-01-19 11:56:41 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][90/312]	eta 0:02:49 lr 0.001725	time 0.7084 (0.7639)	model_time 0.7079 (0.7494)	loss 3.7328 (3.1240)	grad_norm 1.2797 (1.7139/0.7265)	mem 34604MB
[2025-01-19 11:56:42 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][210/312]	eta 0:01:16 lr 0.001717	time 0.7972 (0.7525)	model_time 0.7971 (0.7463)	loss 3.2207 (3.0681)	grad_norm 1.8916 (1.5865/0.6641)	mem 34602MB
[2025-01-19 11:56:48 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][100/312]	eta 0:02:41 lr 0.001724	time 0.7244 (0.7602)	model_time 0.7242 (0.7471)	loss 3.0211 (3.1273)	grad_norm 0.9831 (1.7033/0.7158)	mem 34604MB
[2025-01-19 11:56:50 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][220/312]	eta 0:01:09 lr 0.001716	time 0.7178 (0.7513)	model_time 0.7173 (0.7454)	loss 3.5992 (3.0814)	grad_norm 1.7836 (1.5891/0.6572)	mem 34602MB
[2025-01-19 11:56:56 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][110/312]	eta 0:02:32 lr 0.001724	time 0.7240 (0.7571)	model_time 0.7239 (0.7451)	loss 2.2209 (3.1217)	grad_norm 1.9143 (1.7374/0.7293)	mem 34604MB
[2025-01-19 11:56:57 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][230/312]	eta 0:01:01 lr 0.001716	time 0.7164 (0.7514)	model_time 0.7160 (0.7457)	loss 3.1289 (3.0849)	grad_norm 1.5811 (1.5882/0.6516)	mem 34602MB
[2025-01-19 11:57:03 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][120/312]	eta 0:02:24 lr 0.001723	time 0.7190 (0.7545)	model_time 0.7189 (0.7435)	loss 3.0824 (3.1055)	grad_norm 1.0080 (1.7597/0.7547)	mem 34604MB
[2025-01-19 11:57:05 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][240/312]	eta 0:00:54 lr 0.001715	time 0.8000 (0.7520)	model_time 0.7998 (0.7465)	loss 3.2096 (3.0842)	grad_norm 1.1016 (1.6020/0.6528)	mem 34602MB
[2025-01-19 11:57:10 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][130/312]	eta 0:02:17 lr 0.001722	time 0.8509 (0.7538)	model_time 0.8508 (0.7437)	loss 3.3369 (3.0930)	grad_norm 1.5033 (1.7382/0.7363)	mem 34604MB
[2025-01-19 11:57:13 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][250/312]	eta 0:00:46 lr 0.001714	time 0.7171 (0.7540)	model_time 0.7166 (0.7487)	loss 3.3058 (3.0964)	grad_norm 3.0690 (1.6003/0.6527)	mem 34602MB
[2025-01-19 11:57:18 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][140/312]	eta 0:02:09 lr 0.001722	time 0.8074 (0.7556)	model_time 0.8069 (0.7461)	loss 3.3342 (3.0816)	grad_norm 1.2015 (1.6947/0.7320)	mem 34604MB
[2025-01-19 11:57:20 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][260/312]	eta 0:00:39 lr 0.001714	time 0.7188 (0.7537)	model_time 0.7186 (0.7486)	loss 2.5440 (3.1047)	grad_norm 1.8802 (1.6027/0.6441)	mem 34602MB
[2025-01-19 11:57:26 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][150/312]	eta 0:02:03 lr 0.001721	time 0.9864 (0.7595)	model_time 0.9859 (0.7507)	loss 3.4878 (3.0992)	grad_norm 1.3484 (1.6862/0.7158)	mem 34604MB
[2025-01-19 11:57:28 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][270/312]	eta 0:00:31 lr 0.001713	time 0.8117 (0.7538)	model_time 0.8112 (0.7489)	loss 3.2782 (3.1029)	grad_norm 1.3253 (1.5982/0.6359)	mem 34602MB
[2025-01-19 11:57:34 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][160/312]	eta 0:01:55 lr 0.001720	time 0.8034 (0.7605)	model_time 0.8029 (0.7521)	loss 3.2926 (3.1048)	grad_norm 3.1728 (1.6844/0.7171)	mem 34604MB
[2025-01-19 11:57:35 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][280/312]	eta 0:00:24 lr 0.001712	time 0.7224 (0.7530)	model_time 0.7223 (0.7482)	loss 3.1791 (3.1092)	grad_norm 1.1271 (1.5967/0.6310)	mem 34602MB
[2025-01-19 11:57:41 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][170/312]	eta 0:01:47 lr 0.001720	time 0.7205 (0.7584)	model_time 0.7203 (0.7505)	loss 3.3258 (3.1254)	grad_norm 1.9709 (1.6753/0.7101)	mem 34604MB
[2025-01-19 11:57:43 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][290/312]	eta 0:00:16 lr 0.001712	time 0.8125 (0.7525)	model_time 0.8120 (0.7479)	loss 2.8526 (3.1072)	grad_norm 3.7138 (1.6026/0.6383)	mem 34602MB
[2025-01-19 11:57:49 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][180/312]	eta 0:01:39 lr 0.001719	time 0.7245 (0.7568)	model_time 0.7244 (0.7493)	loss 2.6332 (3.1289)	grad_norm 1.0223 (1.6750/0.7200)	mem 34604MB
[2025-01-19 11:57:50 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][300/312]	eta 0:00:09 lr 0.001711	time 0.7128 (0.7521)	model_time 0.7127 (0.7476)	loss 2.9669 (3.1121)	grad_norm 1.3102 (1.5994/0.6387)	mem 34602MB
[2025-01-19 11:57:56 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][190/312]	eta 0:01:32 lr 0.001718	time 0.7183 (0.7554)	model_time 0.7179 (0.7484)	loss 2.5695 (3.1229)	grad_norm 1.4512 (1.6690/0.7086)	mem 34604MB
[2025-01-19 11:57:57 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][310/312]	eta 0:00:01 lr 0.001710	time 0.7151 (0.7513)	model_time 0.7150 (0.7470)	loss 2.4301 (3.1086)	grad_norm 2.0969 (1.6093/0.6344)	mem 34602MB
[2025-01-19 11:57:58 internimage_b_1k_224] (main.py 519): INFO EPOCH 164 training takes 0:03:54
[2025-01-19 11:57:58 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_164.pth saving......
[2025-01-19 11:58:01 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_164.pth saved !!!
[2025-01-19 11:58:03 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][200/312]	eta 0:01:24 lr 0.001718	time 0.7408 (0.7542)	model_time 0.7406 (0.7474)	loss 3.5636 (3.1075)	grad_norm 1.9278 (1.6745/0.6981)	mem 34604MB
[2025-01-19 11:58:09 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.105 (8.105)	Loss 0.7818 (0.7818)	Acc@1 83.521 (83.521)	Acc@5 96.973 (96.973)	Mem 34602MB
[2025-01-19 11:58:11 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][210/312]	eta 0:01:16 lr 0.001717	time 0.7099 (0.7531)	model_time 0.7095 (0.7467)	loss 4.0105 (3.1057)	grad_norm 2.3478 (1.6776/0.6886)	mem 34604MB
[2025-01-19 11:58:13 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.013)	Loss 1.0594 (0.8928)	Acc@1 76.758 (81.270)	Acc@5 94.263 (95.843)	Mem 34602MB
[2025-01-19 11:58:13 internimage_b_1k_224] (main.py 575): INFO [Epoch:164] * Acc@1 81.122 Acc@5 95.869
[2025-01-19 11:58:13 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.1%
[2025-01-19 11:58:13 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.24%
[2025-01-19 11:58:18 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][220/312]	eta 0:01:09 lr 0.001716	time 0.7260 (0.7518)	model_time 0.7256 (0.7456)	loss 3.5074 (3.1002)	grad_norm 1.1254 (1.6885/0.6991)	mem 34604MB
[2025-01-19 11:58:22 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.672 (9.672)	Loss 0.6620 (0.6620)	Acc@1 84.351 (84.351)	Acc@5 97.681 (97.681)	Mem 34602MB
[2025-01-19 11:58:25 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][230/312]	eta 0:01:01 lr 0.001716	time 0.7104 (0.7508)	model_time 0.7100 (0.7449)	loss 2.1310 (3.1027)	grad_norm 1.5151 (1.6939/0.6949)	mem 34604MB
[2025-01-19 11:58:27 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.308)	Loss 0.9515 (0.7937)	Acc@1 77.417 (81.747)	Acc@5 94.629 (96.047)	Mem 34602MB
[2025-01-19 11:58:27 internimage_b_1k_224] (main.py 575): INFO [Epoch:164] * Acc@1 81.608 Acc@5 96.105
[2025-01-19 11:58:27 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.6%
[2025-01-19 11:58:27 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:58:31 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:58:31 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.61%
[2025-01-19 11:58:32 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][240/312]	eta 0:00:53 lr 0.001715	time 0.7341 (0.7498)	model_time 0.7339 (0.7441)	loss 3.4696 (3.1165)	grad_norm 1.5106 (1.6885/0.6833)	mem 34604MB
[2025-01-19 11:58:33 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][0/312]	eta 0:10:14 lr 0.001710	time 1.9689 (1.9689)	model_time 0.7538 (0.7538)	loss 2.5773 (2.5773)	grad_norm 2.1601 (2.1601/0.0000)	mem 34602MB
[2025-01-19 11:58:40 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][250/312]	eta 0:00:46 lr 0.001714	time 0.7179 (0.7491)	model_time 0.7177 (0.7436)	loss 3.1593 (3.1165)	grad_norm 0.8839 (1.6763/0.6801)	mem 34604MB
[2025-01-19 11:58:40 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][10/312]	eta 0:04:16 lr 0.001710	time 0.7359 (0.8484)	model_time 0.7358 (0.7376)	loss 2.3766 (2.9540)	grad_norm 0.7434 (1.6734/0.5184)	mem 34602MB
[2025-01-19 11:58:47 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][260/312]	eta 0:00:39 lr 0.001714	time 0.8068 (0.7500)	model_time 0.8064 (0.7447)	loss 2.2335 (3.1156)	grad_norm 2.3780 (1.7014/0.7281)	mem 34604MB
[2025-01-19 11:58:48 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][20/312]	eta 0:03:54 lr 0.001709	time 0.7285 (0.8015)	model_time 0.7283 (0.7433)	loss 3.4602 (3.1386)	grad_norm 0.9162 (1.5725/0.5663)	mem 34602MB
[2025-01-19 11:58:55 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][270/312]	eta 0:00:31 lr 0.001713	time 0.8337 (0.7521)	model_time 0.8335 (0.7470)	loss 2.2188 (3.1166)	grad_norm 2.7016 (1.7053/0.7344)	mem 34604MB
[2025-01-19 11:58:55 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][30/312]	eta 0:03:41 lr 0.001708	time 0.7505 (0.7852)	model_time 0.7503 (0.7457)	loss 3.4028 (3.1464)	grad_norm 1.3210 (1.5361/0.5468)	mem 34602MB
[2025-01-19 11:59:03 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][40/312]	eta 0:03:30 lr 0.001708	time 0.7218 (0.7740)	model_time 0.7214 (0.7440)	loss 3.0168 (3.1505)	grad_norm 1.2338 (1.4551/0.5241)	mem 34602MB
[2025-01-19 11:59:03 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][280/312]	eta 0:00:24 lr 0.001712	time 0.8046 (0.7535)	model_time 0.8042 (0.7485)	loss 2.4525 (3.1157)	grad_norm 0.9439 (1.6842/0.7336)	mem 34604MB
[2025-01-19 11:59:10 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][50/312]	eta 0:03:21 lr 0.001707	time 0.7921 (0.7709)	model_time 0.7919 (0.7467)	loss 3.9707 (3.2038)	grad_norm 2.1758 (1.5058/0.5785)	mem 34602MB
[2025-01-19 11:59:11 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][290/312]	eta 0:00:16 lr 0.001712	time 0.7256 (0.7525)	model_time 0.7251 (0.7477)	loss 3.7926 (3.1209)	grad_norm 2.7302 (1.6803/0.7317)	mem 34604MB
[2025-01-19 11:59:18 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][300/312]	eta 0:00:09 lr 0.001711	time 0.7592 (0.7517)	model_time 0.7591 (0.7471)	loss 2.8554 (3.1134)	grad_norm 1.1502 (1.6770/0.7275)	mem 34604MB
[2025-01-19 11:59:18 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][60/312]	eta 0:03:13 lr 0.001706	time 0.8115 (0.7697)	model_time 0.8111 (0.7495)	loss 2.9502 (3.2218)	grad_norm 0.9645 (1.5665/0.6643)	mem 34602MB
[2025-01-19 11:59:25 internimage_b_1k_224] (main.py 510): INFO Train: [164/300][310/312]	eta 0:00:01 lr 0.001710	time 0.7159 (0.7507)	model_time 0.7158 (0.7462)	loss 3.3045 (3.1112)	grad_norm 0.8318 (1.6709/0.7305)	mem 34604MB
[2025-01-19 11:59:26 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][70/312]	eta 0:03:05 lr 0.001706	time 0.7268 (0.7681)	model_time 0.7264 (0.7506)	loss 2.7227 (3.1794)	grad_norm 2.6180 (1.5700/0.6514)	mem 34602MB
[2025-01-19 11:59:26 internimage_b_1k_224] (main.py 519): INFO EPOCH 164 training takes 0:03:54
[2025-01-19 11:59:26 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_164.pth saving......
[2025-01-19 11:59:29 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_164.pth saved !!!
[2025-01-19 11:59:33 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][80/312]	eta 0:02:57 lr 0.001705	time 0.7156 (0.7658)	model_time 0.7154 (0.7504)	loss 2.2090 (3.1960)	grad_norm 1.3047 (1.5486/0.6239)	mem 34602MB
[2025-01-19 11:59:37 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.494 (7.494)	Loss 0.7720 (0.7720)	Acc@1 84.326 (84.326)	Acc@5 97.021 (97.021)	Mem 34604MB
[2025-01-19 11:59:40 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.963)	Loss 1.0268 (0.8871)	Acc@1 76.758 (81.223)	Acc@5 94.434 (95.861)	Mem 34604MB
[2025-01-19 11:59:40 internimage_b_1k_224] (main.py 575): INFO [Epoch:164] * Acc@1 81.106 Acc@5 95.855
[2025-01-19 11:59:40 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.1%
[2025-01-19 11:59:40 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.19%
[2025-01-19 11:59:40 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][90/312]	eta 0:02:49 lr 0.001704	time 0.7275 (0.7617)	model_time 0.7274 (0.7480)	loss 2.2019 (3.1621)	grad_norm 1.6014 (1.6241/0.6792)	mem 34602MB
[2025-01-19 11:59:48 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][100/312]	eta 0:02:41 lr 0.001704	time 0.7210 (0.7598)	model_time 0.7206 (0.7474)	loss 3.2905 (3.1689)	grad_norm 1.6555 (1.6052/0.6724)	mem 34602MB
[2025-01-19 11:59:49 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.426 (9.426)	Loss 0.6610 (0.6610)	Acc@1 84.692 (84.692)	Acc@5 97.705 (97.705)	Mem 34604MB
[2025-01-19 11:59:54 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.293)	Loss 0.9505 (0.7929)	Acc@1 77.441 (81.772)	Acc@5 94.653 (96.107)	Mem 34604MB
[2025-01-19 11:59:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:164] * Acc@1 81.640 Acc@5 96.151
[2025-01-19 11:59:55 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.6%
[2025-01-19 11:59:55 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 11:59:55 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][110/312]	eta 0:02:33 lr 0.001703	time 0.7159 (0.7586)	model_time 0.7157 (0.7473)	loss 4.0655 (3.1681)	grad_norm 1.2881 (1.5858/0.6544)	mem 34602MB
[2025-01-19 11:59:58 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 11:59:58 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.64%
[2025-01-19 12:00:00 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][0/312]	eta 0:10:06 lr 0.001710	time 1.9434 (1.9434)	model_time 0.7407 (0.7407)	loss 3.0821 (3.0821)	grad_norm 2.4245 (2.4245/0.0000)	mem 34604MB
[2025-01-19 12:00:03 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][120/312]	eta 0:02:25 lr 0.001702	time 0.7303 (0.7566)	model_time 0.7299 (0.7462)	loss 3.5732 (3.1744)	grad_norm 2.6718 (1.5938/0.6560)	mem 34602MB
[2025-01-19 12:00:08 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][10/312]	eta 0:04:15 lr 0.001710	time 0.7263 (0.8465)	model_time 0.7259 (0.7367)	loss 3.5959 (3.2307)	grad_norm 3.1693 (1.9645/0.5805)	mem 34604MB
[2025-01-19 12:00:10 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][130/312]	eta 0:02:17 lr 0.001702	time 0.7474 (0.7546)	model_time 0.7472 (0.7449)	loss 3.6901 (3.1892)	grad_norm 1.4193 (1.5890/0.6488)	mem 34602MB
[2025-01-19 12:00:15 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][20/312]	eta 0:03:50 lr 0.001709	time 0.7140 (0.7905)	model_time 0.7138 (0.7329)	loss 2.3129 (3.1503)	grad_norm 2.7190 (1.8981/0.5733)	mem 34604MB
[2025-01-19 12:00:18 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][140/312]	eta 0:02:09 lr 0.001701	time 0.7201 (0.7546)	model_time 0.7197 (0.7456)	loss 2.9444 (3.1961)	grad_norm 3.2582 (1.5933/0.6538)	mem 34602MB
[2025-01-19 12:00:22 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][30/312]	eta 0:03:37 lr 0.001708	time 0.7206 (0.7729)	model_time 0.7202 (0.7338)	loss 3.5211 (3.1308)	grad_norm 1.9746 (1.9200/0.6691)	mem 34604MB
[2025-01-19 12:00:25 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][150/312]	eta 0:02:02 lr 0.001700	time 0.7179 (0.7534)	model_time 0.7174 (0.7450)	loss 3.5128 (3.1779)	grad_norm 2.0988 (1.5979/0.6607)	mem 34602MB
[2025-01-19 12:00:30 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][40/312]	eta 0:03:27 lr 0.001708	time 0.7368 (0.7624)	model_time 0.7366 (0.7327)	loss 2.4079 (3.0764)	grad_norm 1.2637 (1.7715/0.6719)	mem 34604MB
[2025-01-19 12:00:32 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][160/312]	eta 0:01:54 lr 0.001700	time 0.7175 (0.7528)	model_time 0.7173 (0.7449)	loss 3.7920 (3.1931)	grad_norm 1.6095 (1.5963/0.6454)	mem 34602MB
[2025-01-19 12:00:37 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][50/312]	eta 0:03:18 lr 0.001707	time 0.7196 (0.7565)	model_time 0.7194 (0.7326)	loss 3.9918 (3.0914)	grad_norm 1.2396 (1.7110/0.6331)	mem 34604MB
[2025-01-19 12:00:40 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][170/312]	eta 0:01:46 lr 0.001699	time 0.8054 (0.7530)	model_time 0.8052 (0.7455)	loss 2.9614 (3.1826)	grad_norm 0.9554 (1.5738/0.6360)	mem 34602MB
[2025-01-19 12:00:44 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][60/312]	eta 0:03:10 lr 0.001706	time 0.8002 (0.7540)	model_time 0.7997 (0.7340)	loss 2.8300 (3.0845)	grad_norm 3.1531 (1.6472/0.6590)	mem 34604MB
[2025-01-19 12:00:48 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][180/312]	eta 0:01:39 lr 0.001698	time 0.8088 (0.7544)	model_time 0.8087 (0.7473)	loss 2.5876 (3.1678)	grad_norm 2.3293 (1.5875/0.6367)	mem 34602MB
[2025-01-19 12:00:52 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][70/312]	eta 0:03:03 lr 0.001706	time 0.7149 (0.7573)	model_time 0.7147 (0.7400)	loss 2.9932 (3.1071)	grad_norm 0.8381 (1.6631/0.6415)	mem 34604MB
[2025-01-19 12:00:55 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][190/312]	eta 0:01:32 lr 0.001698	time 0.8112 (0.7546)	model_time 0.8108 (0.7479)	loss 2.5475 (3.1746)	grad_norm 1.2649 (1.6059/0.6437)	mem 34602MB
[2025-01-19 12:01:00 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][80/312]	eta 0:02:56 lr 0.001705	time 0.8054 (0.7604)	model_time 0.8053 (0.7452)	loss 2.3554 (3.0845)	grad_norm 0.9536 (1.7004/0.6801)	mem 34604MB
[2025-01-19 12:01:03 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][200/312]	eta 0:01:24 lr 0.001697	time 0.7194 (0.7545)	model_time 0.7190 (0.7481)	loss 3.1542 (3.1737)	grad_norm 1.7128 (1.6206/0.6377)	mem 34602MB
[2025-01-19 12:01:08 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][90/312]	eta 0:02:48 lr 0.001704	time 0.7272 (0.7597)	model_time 0.7270 (0.7461)	loss 2.5097 (3.0694)	grad_norm 1.7178 (1.7321/0.6713)	mem 34604MB
[2025-01-19 12:01:10 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][210/312]	eta 0:01:16 lr 0.001696	time 0.7235 (0.7530)	model_time 0.7230 (0.7469)	loss 2.7333 (3.1713)	grad_norm 1.0718 (1.6134/0.6281)	mem 34602MB
[2025-01-19 12:01:15 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][100/312]	eta 0:02:40 lr 0.001704	time 0.7171 (0.7561)	model_time 0.7169 (0.7439)	loss 3.7529 (3.0940)	grad_norm 0.9927 (1.6864/0.6617)	mem 34604MB
[2025-01-19 12:01:17 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][220/312]	eta 0:01:09 lr 0.001696	time 0.7180 (0.7524)	model_time 0.7175 (0.7465)	loss 3.2891 (3.1573)	grad_norm 1.8103 (1.6233/0.6461)	mem 34602MB
[2025-01-19 12:01:22 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][110/312]	eta 0:02:32 lr 0.001703	time 0.7209 (0.7534)	model_time 0.7207 (0.7422)	loss 2.1687 (3.0831)	grad_norm 2.6064 (1.6718/0.6696)	mem 34604MB
[2025-01-19 12:01:25 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][230/312]	eta 0:01:01 lr 0.001695	time 0.7213 (0.7528)	model_time 0.7212 (0.7472)	loss 3.5541 (3.1602)	grad_norm 0.9662 (1.6478/0.6700)	mem 34602MB
[2025-01-19 12:01:29 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][120/312]	eta 0:02:24 lr 0.001702	time 0.7209 (0.7514)	model_time 0.7208 (0.7411)	loss 3.6226 (3.0887)	grad_norm 2.0622 (1.6789/0.6782)	mem 34604MB
[2025-01-19 12:01:32 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][240/312]	eta 0:00:54 lr 0.001695	time 0.7168 (0.7521)	model_time 0.7167 (0.7466)	loss 2.7065 (3.1590)	grad_norm 0.7336 (1.6330/0.6674)	mem 34602MB
[2025-01-19 12:01:37 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][130/312]	eta 0:02:16 lr 0.001702	time 0.7413 (0.7499)	model_time 0.7409 (0.7404)	loss 2.7790 (3.0916)	grad_norm 3.2223 (1.7027/0.6845)	mem 34604MB
[2025-01-19 12:01:40 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][250/312]	eta 0:00:46 lr 0.001694	time 0.7269 (0.7513)	model_time 0.7268 (0.7461)	loss 2.8063 (3.1467)	grad_norm 2.2742 (1.6351/0.6612)	mem 34602MB
[2025-01-19 12:01:44 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][140/312]	eta 0:02:08 lr 0.001701	time 0.7163 (0.7482)	model_time 0.7158 (0.7394)	loss 2.9279 (3.0669)	grad_norm 1.3688 (1.7203/0.6971)	mem 34604MB
[2025-01-19 12:01:47 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][260/312]	eta 0:00:39 lr 0.001693	time 0.7203 (0.7510)	model_time 0.7202 (0.7460)	loss 3.6791 (3.1542)	grad_norm 1.8365 (1.6389/0.6542)	mem 34602MB
[2025-01-19 12:01:51 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][150/312]	eta 0:02:00 lr 0.001700	time 0.7437 (0.7468)	model_time 0.7436 (0.7385)	loss 3.5434 (3.0699)	grad_norm 2.0670 (1.7349/0.7009)	mem 34604MB
[2025-01-19 12:01:55 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][270/312]	eta 0:00:31 lr 0.001693	time 0.7230 (0.7508)	model_time 0.7226 (0.7459)	loss 3.5628 (3.1582)	grad_norm 2.1917 (1.6301/0.6475)	mem 34602MB
[2025-01-19 12:01:59 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][160/312]	eta 0:01:53 lr 0.001700	time 0.7168 (0.7457)	model_time 0.7166 (0.7379)	loss 2.1092 (3.0710)	grad_norm 0.9592 (1.6985/0.6951)	mem 34604MB
[2025-01-19 12:02:02 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][280/312]	eta 0:00:24 lr 0.001692	time 0.7265 (0.7503)	model_time 0.7263 (0.7456)	loss 2.5720 (3.1558)	grad_norm 1.3901 (1.6336/0.6511)	mem 34602MB
[2025-01-19 12:02:06 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][170/312]	eta 0:01:45 lr 0.001699	time 0.7147 (0.7446)	model_time 0.7142 (0.7372)	loss 3.4592 (3.0806)	grad_norm 2.2273 (1.6799/0.6916)	mem 34604MB
[2025-01-19 12:02:10 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][290/312]	eta 0:00:16 lr 0.001691	time 0.8298 (0.7510)	model_time 0.8294 (0.7464)	loss 2.4929 (3.1417)	grad_norm 1.0760 (1.6322/0.6538)	mem 34602MB
[2025-01-19 12:02:13 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][180/312]	eta 0:01:38 lr 0.001698	time 0.8057 (0.7444)	model_time 0.8056 (0.7375)	loss 3.3305 (3.0718)	grad_norm 1.6404 (1.6542/0.6864)	mem 34604MB
[2025-01-19 12:02:17 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][300/312]	eta 0:00:09 lr 0.001691	time 0.7981 (0.7514)	model_time 0.7981 (0.7470)	loss 2.6563 (3.1426)	grad_norm 1.0507 (1.6240/0.6472)	mem 34602MB
[2025-01-19 12:02:21 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][190/312]	eta 0:01:31 lr 0.001698	time 0.8075 (0.7477)	model_time 0.8070 (0.7411)	loss 2.0643 (3.0673)	grad_norm 1.0117 (1.6360/0.6842)	mem 34604MB
[2025-01-19 12:02:25 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][310/312]	eta 0:00:01 lr 0.001690	time 0.7156 (0.7509)	model_time 0.7155 (0.7466)	loss 3.5042 (3.1449)	grad_norm 1.4837 (1.6150/0.6449)	mem 34602MB
[2025-01-19 12:02:26 internimage_b_1k_224] (main.py 519): INFO EPOCH 165 training takes 0:03:54
[2025-01-19 12:02:26 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_165.pth saving......
[2025-01-19 12:02:29 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_165.pth saved !!!
[2025-01-19 12:02:29 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][200/312]	eta 0:01:24 lr 0.001697	time 0.8051 (0.7506)	model_time 0.8047 (0.7442)	loss 3.0635 (3.0790)	grad_norm 2.4852 (1.6396/0.6770)	mem 34604MB
[2025-01-19 12:02:37 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.134 (8.134)	Loss 0.7993 (0.7993)	Acc@1 83.716 (83.716)	Acc@5 97.314 (97.314)	Mem 34602MB
[2025-01-19 12:02:37 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][210/312]	eta 0:01:16 lr 0.001696	time 0.7203 (0.7513)	model_time 0.7202 (0.7452)	loss 2.5265 (3.0723)	grad_norm 1.7928 (1.6676/0.7050)	mem 34604MB
[2025-01-19 12:02:40 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.028)	Loss 1.0526 (0.9129)	Acc@1 77.026 (81.283)	Acc@5 94.507 (95.823)	Mem 34602MB
[2025-01-19 12:02:40 internimage_b_1k_224] (main.py 575): INFO [Epoch:165] * Acc@1 81.188 Acc@5 95.839
[2025-01-19 12:02:40 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.2%
[2025-01-19 12:02:40 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.24%
[2025-01-19 12:02:44 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][220/312]	eta 0:01:09 lr 0.001696	time 0.7167 (0.7504)	model_time 0.7163 (0.7447)	loss 3.3763 (3.0650)	grad_norm 0.9125 (1.6620/0.7019)	mem 34604MB
[2025-01-19 12:02:50 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.414 (9.414)	Loss 0.6627 (0.6627)	Acc@1 84.375 (84.375)	Acc@5 97.632 (97.632)	Mem 34602MB
[2025-01-19 12:02:52 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][230/312]	eta 0:01:01 lr 0.001695	time 0.7429 (0.7496)	model_time 0.7425 (0.7440)	loss 2.0355 (3.0741)	grad_norm 2.2518 (1.6827/0.7226)	mem 34604MB
[2025-01-19 12:02:54 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.288)	Loss 0.9511 (0.7939)	Acc@1 77.490 (81.745)	Acc@5 94.653 (96.056)	Mem 34602MB
[2025-01-19 12:02:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:165] * Acc@1 81.612 Acc@5 96.117
[2025-01-19 12:02:55 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.6%
[2025-01-19 12:02:55 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:02:58 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:02:58 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.61%
[2025-01-19 12:02:59 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][240/312]	eta 0:00:53 lr 0.001695	time 0.7182 (0.7486)	model_time 0.7178 (0.7432)	loss 3.2552 (3.0789)	grad_norm 0.8532 (1.6818/0.7264)	mem 34604MB
[2025-01-19 12:03:01 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][0/312]	eta 0:11:55 lr 0.001690	time 2.2927 (2.2927)	model_time 0.7434 (0.7434)	loss 3.0342 (3.0342)	grad_norm 1.2046 (1.2046/0.0000)	mem 34602MB
[2025-01-19 12:03:06 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][250/312]	eta 0:00:46 lr 0.001694	time 0.7321 (0.7477)	model_time 0.7319 (0.7425)	loss 3.3000 (3.0751)	grad_norm 1.9559 (1.6850/0.7224)	mem 34604MB
[2025-01-19 12:03:08 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][10/312]	eta 0:04:29 lr 0.001689	time 0.7181 (0.8937)	model_time 0.7176 (0.7525)	loss 3.4577 (3.0412)	grad_norm 1.2172 (1.3912/0.4197)	mem 34602MB
[2025-01-19 12:03:13 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][260/312]	eta 0:00:38 lr 0.001693	time 0.7334 (0.7469)	model_time 0.7333 (0.7419)	loss 3.2810 (3.0794)	grad_norm 1.2604 (1.6776/0.7154)	mem 34604MB
[2025-01-19 12:03:15 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][20/312]	eta 0:03:57 lr 0.001688	time 0.7196 (0.8142)	model_time 0.7195 (0.7401)	loss 3.3165 (3.1047)	grad_norm 0.9666 (1.5766/0.6972)	mem 34602MB
[2025-01-19 12:03:21 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][270/312]	eta 0:00:31 lr 0.001693	time 0.7232 (0.7462)	model_time 0.7230 (0.7414)	loss 2.2098 (3.0849)	grad_norm 1.1418 (1.6549/0.7131)	mem 34604MB
[2025-01-19 12:03:23 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][30/312]	eta 0:03:41 lr 0.001688	time 0.7311 (0.7854)	model_time 0.7307 (0.7351)	loss 4.0694 (3.1299)	grad_norm 1.4235 (1.5156/0.5972)	mem 34602MB
[2025-01-19 12:03:28 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][280/312]	eta 0:00:23 lr 0.001692	time 0.7466 (0.7457)	model_time 0.7461 (0.7411)	loss 3.7603 (3.0865)	grad_norm 2.0553 (1.6479/0.7050)	mem 34604MB
[2025-01-19 12:03:30 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][40/312]	eta 0:03:31 lr 0.001687	time 0.7280 (0.7785)	model_time 0.7276 (0.7404)	loss 3.2312 (3.1159)	grad_norm 0.6722 (1.4615/0.5970)	mem 34602MB
[2025-01-19 12:03:35 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][290/312]	eta 0:00:16 lr 0.001691	time 0.7195 (0.7451)	model_time 0.7193 (0.7406)	loss 3.9499 (3.1051)	grad_norm 0.9660 (1.6612/0.7144)	mem 34604MB
[2025-01-19 12:03:38 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][50/312]	eta 0:03:21 lr 0.001687	time 0.7297 (0.7692)	model_time 0.7293 (0.7384)	loss 3.2275 (3.1071)	grad_norm 1.2092 (1.6678/0.7977)	mem 34602MB
[2025-01-19 12:03:43 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][300/312]	eta 0:00:08 lr 0.001691	time 0.7889 (0.7448)	model_time 0.7889 (0.7405)	loss 3.2304 (3.1146)	grad_norm 2.7139 (1.6606/0.7138)	mem 34604MB
[2025-01-19 12:03:45 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][60/312]	eta 0:03:12 lr 0.001686	time 0.8021 (0.7632)	model_time 0.8016 (0.7374)	loss 2.8913 (3.0923)	grad_norm 1.0503 (1.6820/0.7798)	mem 34602MB
[2025-01-19 12:03:50 internimage_b_1k_224] (main.py 510): INFO Train: [165/300][310/312]	eta 0:00:01 lr 0.001690	time 0.8157 (0.7453)	model_time 0.8156 (0.7411)	loss 3.4246 (3.1171)	grad_norm 1.3977 (1.6460/0.7112)	mem 34604MB
[2025-01-19 12:03:51 internimage_b_1k_224] (main.py 519): INFO EPOCH 165 training takes 0:03:52
[2025-01-19 12:03:51 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_165.pth saving......
[2025-01-19 12:03:52 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][70/312]	eta 0:03:04 lr 0.001685	time 0.7394 (0.7608)	model_time 0.7393 (0.7386)	loss 2.5936 (3.0826)	grad_norm 1.4143 (1.6334/0.7433)	mem 34602MB
[2025-01-19 12:03:54 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_165.pth saved !!!
[2025-01-19 12:04:00 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][80/312]	eta 0:02:55 lr 0.001685	time 0.8162 (0.7580)	model_time 0.8158 (0.7385)	loss 3.0714 (3.0909)	grad_norm 2.1705 (1.6028/0.7133)	mem 34602MB
[2025-01-19 12:04:02 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.604 (7.604)	Loss 0.7484 (0.7484)	Acc@1 84.326 (84.326)	Acc@5 97.266 (97.266)	Mem 34604MB
[2025-01-19 12:04:05 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.977)	Loss 1.0178 (0.8729)	Acc@1 77.539 (81.381)	Acc@5 94.556 (95.958)	Mem 34604MB
[2025-01-19 12:04:05 internimage_b_1k_224] (main.py 575): INFO [Epoch:165] * Acc@1 81.284 Acc@5 95.967
[2025-01-19 12:04:05 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.3%
[2025-01-19 12:04:05 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 12:04:07 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][90/312]	eta 0:02:47 lr 0.001684	time 0.8026 (0.7562)	model_time 0.8025 (0.7388)	loss 2.4441 (3.0789)	grad_norm 1.2453 (1.6146/0.7180)	mem 34602MB
[2025-01-19 12:04:09 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 12:04:09 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.28%
[2025-01-19 12:04:15 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][100/312]	eta 0:02:40 lr 0.001683	time 0.7961 (0.7555)	model_time 0.7960 (0.7397)	loss 3.6589 (3.1237)	grad_norm 1.1386 (1.6080/0.7117)	mem 34602MB
[2025-01-19 12:04:16 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.352 (7.352)	Loss 0.6618 (0.6618)	Acc@1 84.790 (84.790)	Acc@5 97.705 (97.705)	Mem 34604MB
[2025-01-19 12:04:19 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.965)	Loss 0.9501 (0.7931)	Acc@1 77.466 (81.820)	Acc@5 94.653 (96.114)	Mem 34604MB
[2025-01-19 12:04:19 internimage_b_1k_224] (main.py 575): INFO [Epoch:165] * Acc@1 81.686 Acc@5 96.161
[2025-01-19 12:04:19 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.7%
[2025-01-19 12:04:19 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:04:22 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][110/312]	eta 0:02:32 lr 0.001683	time 0.7243 (0.7574)	model_time 0.7239 (0.7430)	loss 2.9048 (3.1266)	grad_norm 1.9594 (1.6089/0.6834)	mem 34602MB
[2025-01-19 12:04:23 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:04:23 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.69%
[2025-01-19 12:04:26 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][0/312]	eta 0:11:41 lr 0.001690	time 2.2475 (2.2475)	model_time 0.7301 (0.7301)	loss 3.0854 (3.0854)	grad_norm 2.5023 (2.5023/0.0000)	mem 34604MB
[2025-01-19 12:04:30 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][120/312]	eta 0:02:25 lr 0.001682	time 0.7321 (0.7568)	model_time 0.7317 (0.7436)	loss 3.8336 (3.1455)	grad_norm 1.9989 (1.6352/0.6850)	mem 34602MB
[2025-01-19 12:04:34 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][10/312]	eta 0:04:39 lr 0.001689	time 0.8049 (0.9271)	model_time 0.8048 (0.7889)	loss 2.4492 (2.7977)	grad_norm 1.4384 (1.6597/0.5389)	mem 34604MB
[2025-01-19 12:04:37 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][130/312]	eta 0:02:17 lr 0.001681	time 0.7233 (0.7561)	model_time 0.7232 (0.7439)	loss 2.8718 (3.1424)	grad_norm 1.2736 (1.6379/0.6889)	mem 34602MB
[2025-01-19 12:04:41 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][20/312]	eta 0:04:09 lr 0.001688	time 0.7194 (0.8548)	model_time 0.7193 (0.7823)	loss 3.5589 (3.0367)	grad_norm 3.1918 (1.8496/0.6812)	mem 34604MB
[2025-01-19 12:04:45 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][140/312]	eta 0:02:09 lr 0.001681	time 0.7254 (0.7544)	model_time 0.7250 (0.7430)	loss 3.3175 (3.1588)	grad_norm 1.6836 (1.6267/0.6744)	mem 34602MB
[2025-01-19 12:04:49 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][30/312]	eta 0:03:49 lr 0.001688	time 0.7217 (0.8135)	model_time 0.7212 (0.7643)	loss 2.5505 (3.0157)	grad_norm 2.6526 (2.0076/0.7115)	mem 34604MB
[2025-01-19 12:04:52 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][150/312]	eta 0:02:01 lr 0.001680	time 0.7276 (0.7523)	model_time 0.7273 (0.7416)	loss 3.1038 (3.1619)	grad_norm 1.7324 (1.6438/0.6682)	mem 34602MB
[2025-01-19 12:04:56 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][40/312]	eta 0:03:35 lr 0.001687	time 0.7261 (0.7930)	model_time 0.7260 (0.7557)	loss 3.7312 (3.0916)	grad_norm 1.7211 (1.8754/0.6803)	mem 34604MB
[2025-01-19 12:05:00 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][160/312]	eta 0:01:54 lr 0.001679	time 0.7197 (0.7524)	model_time 0.7193 (0.7423)	loss 2.8943 (3.1577)	grad_norm 2.4138 (1.6588/0.6682)	mem 34602MB
[2025-01-19 12:05:03 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][50/312]	eta 0:03:24 lr 0.001687	time 0.7378 (0.7798)	model_time 0.7377 (0.7497)	loss 2.8168 (3.0864)	grad_norm 1.7227 (1.7763/0.6490)	mem 34604MB
[2025-01-19 12:05:07 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][170/312]	eta 0:01:46 lr 0.001679	time 0.7211 (0.7512)	model_time 0.7207 (0.7417)	loss 3.0629 (3.1664)	grad_norm 1.4050 (1.6410/0.6648)	mem 34602MB
[2025-01-19 12:05:10 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][60/312]	eta 0:03:14 lr 0.001686	time 0.7345 (0.7712)	model_time 0.7343 (0.7459)	loss 3.4636 (3.1024)	grad_norm 1.9717 (1.7287/0.6399)	mem 34604MB
[2025-01-19 12:05:14 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][180/312]	eta 0:01:38 lr 0.001678	time 0.7231 (0.7498)	model_time 0.7230 (0.7408)	loss 3.4899 (3.1650)	grad_norm 0.8344 (1.6467/0.6622)	mem 34602MB
[2025-01-19 12:05:18 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][70/312]	eta 0:03:05 lr 0.001685	time 0.7342 (0.7649)	model_time 0.7338 (0.7432)	loss 2.6376 (3.1141)	grad_norm 1.3270 (1.7079/0.6043)	mem 34604MB
[2025-01-19 12:05:22 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][190/312]	eta 0:01:31 lr 0.001677	time 0.7146 (0.7498)	model_time 0.7141 (0.7413)	loss 2.8380 (3.1632)	grad_norm 1.7463 (1.6573/0.6624)	mem 34602MB
[2025-01-19 12:05:25 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][80/312]	eta 0:02:56 lr 0.001685	time 0.7169 (0.7604)	model_time 0.7168 (0.7413)	loss 3.5492 (3.1269)	grad_norm 2.3170 (1.7161/0.6162)	mem 34604MB
[2025-01-19 12:05:29 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][200/312]	eta 0:01:23 lr 0.001677	time 0.8053 (0.7489)	model_time 0.8052 (0.7408)	loss 3.4022 (3.1593)	grad_norm 1.5497 (1.6877/0.6709)	mem 34602MB
[2025-01-19 12:05:32 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][90/312]	eta 0:02:48 lr 0.001684	time 0.7209 (0.7568)	model_time 0.7207 (0.7398)	loss 3.3326 (3.1568)	grad_norm 1.1107 (1.7475/0.6412)	mem 34604MB
[2025-01-19 12:05:36 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][210/312]	eta 0:01:16 lr 0.001676	time 0.8012 (0.7486)	model_time 0.8008 (0.7409)	loss 3.9749 (3.1614)	grad_norm 1.0889 (1.6780/0.6660)	mem 34602MB
[2025-01-19 12:05:40 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][100/312]	eta 0:02:40 lr 0.001683	time 0.7114 (0.7548)	model_time 0.7110 (0.7394)	loss 3.8399 (3.1633)	grad_norm 1.6006 (1.7324/0.6234)	mem 34604MB
[2025-01-19 12:05:44 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][220/312]	eta 0:01:08 lr 0.001675	time 0.7370 (0.7487)	model_time 0.7369 (0.7413)	loss 2.7669 (3.1606)	grad_norm 1.3542 (1.6673/0.6559)	mem 34602MB
[2025-01-19 12:05:47 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][110/312]	eta 0:02:32 lr 0.001683	time 0.7199 (0.7538)	model_time 0.7195 (0.7398)	loss 3.2143 (3.1325)	grad_norm 1.1053 (1.7569/0.6497)	mem 34604MB
[2025-01-19 12:05:52 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][230/312]	eta 0:01:01 lr 0.001675	time 0.7157 (0.7505)	model_time 0.7152 (0.7433)	loss 3.2764 (3.1606)	grad_norm 1.0950 (1.6769/0.6686)	mem 34602MB
[2025-01-19 12:05:55 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][120/312]	eta 0:02:25 lr 0.001682	time 0.8109 (0.7556)	model_time 0.8108 (0.7427)	loss 3.2852 (3.1308)	grad_norm 1.2485 (1.7544/0.6415)	mem 34604MB
[2025-01-19 12:05:59 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][240/312]	eta 0:00:53 lr 0.001674	time 0.7175 (0.7499)	model_time 0.7171 (0.7431)	loss 3.0626 (3.1553)	grad_norm 1.7967 (1.6732/0.6726)	mem 34602MB
[2025-01-19 12:06:03 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][130/312]	eta 0:02:17 lr 0.001681	time 0.7994 (0.7576)	model_time 0.7992 (0.7456)	loss 2.8845 (3.1298)	grad_norm 1.1969 (1.7362/0.6344)	mem 34604MB
[2025-01-19 12:06:07 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][250/312]	eta 0:00:46 lr 0.001673	time 0.7185 (0.7499)	model_time 0.7183 (0.7433)	loss 3.9154 (3.1657)	grad_norm 1.5668 (1.6678/0.6764)	mem 34602MB
[2025-01-19 12:06:10 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][140/312]	eta 0:02:10 lr 0.001681	time 0.7388 (0.7588)	model_time 0.7387 (0.7477)	loss 2.9862 (3.1372)	grad_norm 1.6459 (1.7300/0.6207)	mem 34604MB
[2025-01-19 12:06:14 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][260/312]	eta 0:00:38 lr 0.001673	time 0.7247 (0.7492)	model_time 0.7245 (0.7428)	loss 3.2502 (3.1528)	grad_norm 1.3669 (1.6570/0.6703)	mem 34602MB
[2025-01-19 12:06:18 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][150/312]	eta 0:02:02 lr 0.001680	time 0.7236 (0.7568)	model_time 0.7231 (0.7464)	loss 2.9137 (3.1331)	grad_norm 2.6983 (1.7443/0.6190)	mem 34604MB
[2025-01-19 12:06:21 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][270/312]	eta 0:00:31 lr 0.001672	time 0.7294 (0.7484)	model_time 0.7293 (0.7423)	loss 3.9159 (3.1551)	grad_norm 0.8150 (1.6466/0.6641)	mem 34602MB
[2025-01-19 12:06:25 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][160/312]	eta 0:01:54 lr 0.001679	time 0.7156 (0.7549)	model_time 0.7154 (0.7451)	loss 3.1459 (3.1237)	grad_norm 2.1856 (1.7458/0.6225)	mem 34604MB
[2025-01-19 12:06:29 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][280/312]	eta 0:00:23 lr 0.001671	time 0.7259 (0.7489)	model_time 0.7258 (0.7429)	loss 4.1202 (3.1508)	grad_norm 1.1406 (1.6352/0.6573)	mem 34602MB
[2025-01-19 12:06:32 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][170/312]	eta 0:01:46 lr 0.001679	time 0.7378 (0.7532)	model_time 0.7371 (0.7440)	loss 3.7733 (3.1442)	grad_norm 1.1711 (1.7526/0.6667)	mem 34604MB
[2025-01-19 12:06:36 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][290/312]	eta 0:00:16 lr 0.001671	time 0.7154 (0.7482)	model_time 0.7150 (0.7425)	loss 3.2368 (3.1546)	grad_norm 1.0700 (1.6659/0.7195)	mem 34602MB
[2025-01-19 12:06:40 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][180/312]	eta 0:01:39 lr 0.001678	time 0.7141 (0.7520)	model_time 0.7136 (0.7432)	loss 3.8900 (3.1424)	grad_norm 1.3967 (1.7388/0.6583)	mem 34604MB
[2025-01-19 12:06:43 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][300/312]	eta 0:00:08 lr 0.001670	time 0.7133 (0.7473)	model_time 0.7132 (0.7418)	loss 3.6578 (3.1525)	grad_norm 1.6305 (1.6667/0.7239)	mem 34602MB
[2025-01-19 12:06:47 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][190/312]	eta 0:01:31 lr 0.001677	time 0.7189 (0.7509)	model_time 0.7185 (0.7425)	loss 3.1078 (3.1425)	grad_norm 2.4617 (1.7478/0.6507)	mem 34604MB
[2025-01-19 12:06:51 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][310/312]	eta 0:00:01 lr 0.001670	time 0.7110 (0.7472)	model_time 0.7109 (0.7418)	loss 3.3903 (3.1533)	grad_norm 2.1279 (1.6655/0.7246)	mem 34602MB
[2025-01-19 12:06:52 internimage_b_1k_224] (main.py 519): INFO EPOCH 166 training takes 0:03:53
[2025-01-19 12:06:52 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_166.pth saving......
[2025-01-19 12:06:54 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][200/312]	eta 0:01:23 lr 0.001677	time 0.7166 (0.7498)	model_time 0.7162 (0.7419)	loss 3.7298 (3.1467)	grad_norm 2.5440 (1.7501/0.6422)	mem 34604MB
[2025-01-19 12:06:55 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_166.pth saved !!!
[2025-01-19 12:07:01 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][210/312]	eta 0:01:16 lr 0.001676	time 0.7203 (0.7487)	model_time 0.7199 (0.7411)	loss 4.0860 (3.1478)	grad_norm 1.3235 (1.7393/0.6380)	mem 34604MB
[2025-01-19 12:07:02 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.507 (7.507)	Loss 0.7924 (0.7924)	Acc@1 83.691 (83.691)	Acc@5 97.412 (97.412)	Mem 34602MB
[2025-01-19 12:07:05 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.960)	Loss 1.0487 (0.8983)	Acc@1 76.953 (81.277)	Acc@5 94.702 (95.878)	Mem 34602MB
[2025-01-19 12:07:06 internimage_b_1k_224] (main.py 575): INFO [Epoch:166] * Acc@1 81.124 Acc@5 95.919
[2025-01-19 12:07:06 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.1%
[2025-01-19 12:07:06 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.24%
[2025-01-19 12:07:09 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][220/312]	eta 0:01:08 lr 0.001675	time 0.7097 (0.7480)	model_time 0.7093 (0.7408)	loss 2.9695 (3.1403)	grad_norm 2.6887 (1.7415/0.6417)	mem 34604MB
[2025-01-19 12:07:15 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.400 (9.400)	Loss 0.6635 (0.6635)	Acc@1 84.424 (84.424)	Acc@5 97.632 (97.632)	Mem 34602MB
[2025-01-19 12:07:16 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][230/312]	eta 0:01:01 lr 0.001675	time 0.7175 (0.7478)	model_time 0.7170 (0.7409)	loss 3.0523 (3.1294)	grad_norm 1.5151 (1.7279/0.6346)	mem 34604MB
[2025-01-19 12:07:20 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.274)	Loss 0.9508 (0.7942)	Acc@1 77.466 (81.760)	Acc@5 94.702 (96.080)	Mem 34602MB
[2025-01-19 12:07:20 internimage_b_1k_224] (main.py 575): INFO [Epoch:166] * Acc@1 81.624 Acc@5 96.137
[2025-01-19 12:07:20 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.6%
[2025-01-19 12:07:20 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:07:24 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:07:24 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.62%
[2025-01-19 12:07:24 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][240/312]	eta 0:00:53 lr 0.001674	time 0.9722 (0.7488)	model_time 0.9720 (0.7421)	loss 3.1750 (3.1253)	grad_norm 2.7565 (1.7462/0.6538)	mem 34604MB
[2025-01-19 12:07:26 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][0/312]	eta 0:12:14 lr 0.001669	time 2.3530 (2.3530)	model_time 0.7517 (0.7517)	loss 3.0980 (3.0980)	grad_norm 3.0966 (3.0966/0.0000)	mem 34602MB
[2025-01-19 12:07:32 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][250/312]	eta 0:00:46 lr 0.001673	time 0.7997 (0.7500)	model_time 0.7996 (0.7436)	loss 3.3212 (3.1317)	grad_norm 0.9524 (1.7507/0.6609)	mem 34604MB
[2025-01-19 12:07:33 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][10/312]	eta 0:04:27 lr 0.001669	time 0.8054 (0.8869)	model_time 0.8053 (0.7410)	loss 2.8732 (3.1848)	grad_norm 0.8532 (1.5447/0.6772)	mem 34602MB
[2025-01-19 12:07:39 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][260/312]	eta 0:00:39 lr 0.001673	time 0.7313 (0.7507)	model_time 0.7311 (0.7445)	loss 2.5203 (3.1276)	grad_norm 1.9182 (1.7474/0.6664)	mem 34604MB
[2025-01-19 12:07:41 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][20/312]	eta 0:03:56 lr 0.001668	time 0.7297 (0.8096)	model_time 0.7295 (0.7331)	loss 3.8046 (3.2715)	grad_norm 0.8575 (1.5749/0.6050)	mem 34602MB
[2025-01-19 12:07:47 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][270/312]	eta 0:00:31 lr 0.001672	time 0.7135 (0.7498)	model_time 0.7131 (0.7438)	loss 3.9491 (3.1230)	grad_norm 1.1185 (1.7308/0.6618)	mem 34604MB
[2025-01-19 12:07:48 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][30/312]	eta 0:03:43 lr 0.001667	time 0.7325 (0.7933)	model_time 0.7320 (0.7413)	loss 3.3810 (3.3139)	grad_norm 0.8628 (1.4670/0.5414)	mem 34602MB
[2025-01-19 12:07:54 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][280/312]	eta 0:00:23 lr 0.001671	time 0.7195 (0.7490)	model_time 0.7190 (0.7433)	loss 2.4239 (3.1213)	grad_norm 1.2419 (1.7199/0.6546)	mem 34604MB
[2025-01-19 12:07:56 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][40/312]	eta 0:03:33 lr 0.001667	time 0.7217 (0.7867)	model_time 0.7213 (0.7473)	loss 2.5405 (3.2879)	grad_norm 1.6790 (1.5647/0.6529)	mem 34602MB
[2025-01-19 12:08:01 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][290/312]	eta 0:00:16 lr 0.001671	time 0.7442 (0.7484)	model_time 0.7436 (0.7428)	loss 3.9377 (3.1301)	grad_norm 0.9373 (1.7028/0.6534)	mem 34604MB
[2025-01-19 12:08:03 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][50/312]	eta 0:03:24 lr 0.001666	time 0.7164 (0.7801)	model_time 0.7162 (0.7484)	loss 3.4219 (3.2981)	grad_norm 0.8950 (1.5373/0.6588)	mem 34602MB
[2025-01-19 12:08:08 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][300/312]	eta 0:00:08 lr 0.001670	time 0.7128 (0.7475)	model_time 0.7127 (0.7421)	loss 3.0755 (3.1329)	grad_norm 2.1131 (1.6986/0.6456)	mem 34604MB
[2025-01-19 12:08:11 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][60/312]	eta 0:03:15 lr 0.001665	time 0.7161 (0.7742)	model_time 0.7160 (0.7475)	loss 3.1251 (3.2894)	grad_norm 1.6642 (1.5468/0.6292)	mem 34602MB
[2025-01-19 12:08:16 internimage_b_1k_224] (main.py 510): INFO Train: [166/300][310/312]	eta 0:00:01 lr 0.001670	time 0.7206 (0.7465)	model_time 0.7205 (0.7413)	loss 2.6183 (3.1333)	grad_norm 1.0041 (1.6819/0.6501)	mem 34604MB
[2025-01-19 12:08:16 internimage_b_1k_224] (main.py 519): INFO EPOCH 166 training takes 0:03:52
[2025-01-19 12:08:16 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_166.pth saving......
[2025-01-19 12:08:18 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][70/312]	eta 0:03:05 lr 0.001665	time 0.7233 (0.7685)	model_time 0.7229 (0.7456)	loss 3.9330 (3.2931)	grad_norm 1.3444 (1.5938/0.6638)	mem 34602MB
[2025-01-19 12:08:20 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_166.pth saved !!!
[2025-01-19 12:08:26 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][80/312]	eta 0:02:57 lr 0.001664	time 0.7182 (0.7644)	model_time 0.7178 (0.7442)	loss 2.3690 (3.2558)	grad_norm 1.4663 (1.5696/0.6527)	mem 34602MB
[2025-01-19 12:08:27 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.644 (7.644)	Loss 0.7999 (0.7999)	Acc@1 83.862 (83.862)	Acc@5 97.241 (97.241)	Mem 34604MB
[2025-01-19 12:08:30 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.980)	Loss 1.0416 (0.9120)	Acc@1 77.905 (81.172)	Acc@5 94.043 (95.772)	Mem 34604MB
[2025-01-19 12:08:31 internimage_b_1k_224] (main.py 575): INFO [Epoch:166] * Acc@1 81.038 Acc@5 95.805
[2025-01-19 12:08:31 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.0%
[2025-01-19 12:08:31 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.28%
[2025-01-19 12:08:33 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][90/312]	eta 0:02:49 lr 0.001663	time 0.7409 (0.7628)	model_time 0.7407 (0.7449)	loss 2.2274 (3.2339)	grad_norm 1.6847 (1.5997/0.6361)	mem 34602MB
[2025-01-19 12:08:40 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.406 (9.406)	Loss 0.6627 (0.6627)	Acc@1 84.790 (84.790)	Acc@5 97.705 (97.705)	Mem 34604MB
[2025-01-19 12:08:40 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][100/312]	eta 0:02:41 lr 0.001663	time 0.7163 (0.7598)	model_time 0.7159 (0.7436)	loss 3.7372 (3.2217)	grad_norm 2.3195 (1.6768/0.7646)	mem 34602MB
[2025-01-19 12:08:45 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.183 (1.273)	Loss 0.9502 (0.7934)	Acc@1 77.393 (81.860)	Acc@5 94.702 (96.123)	Mem 34604MB
[2025-01-19 12:08:45 internimage_b_1k_224] (main.py 575): INFO [Epoch:166] * Acc@1 81.738 Acc@5 96.169
[2025-01-19 12:08:45 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.7%
[2025-01-19 12:08:45 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:08:48 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][110/312]	eta 0:02:32 lr 0.001662	time 0.7152 (0.7567)	model_time 0.7148 (0.7419)	loss 3.6841 (3.2214)	grad_norm 1.3492 (1.6783/0.7457)	mem 34602MB
[2025-01-19 12:08:49 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:08:49 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.74%
[2025-01-19 12:08:51 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][0/312]	eta 0:11:30 lr 0.001669	time 2.2140 (2.2140)	model_time 0.7275 (0.7275)	loss 3.3634 (3.3634)	grad_norm 1.9021 (1.9021/0.0000)	mem 34604MB
[2025-01-19 12:08:55 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][120/312]	eta 0:02:25 lr 0.001662	time 0.7164 (0.7561)	model_time 0.7159 (0.7425)	loss 2.7425 (3.2281)	grad_norm 0.9224 (1.6297/0.7359)	mem 34602MB
[2025-01-19 12:08:58 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][10/312]	eta 0:04:20 lr 0.001669	time 0.7295 (0.8630)	model_time 0.7291 (0.7275)	loss 3.1413 (3.1938)	grad_norm 0.8015 (1.8585/0.7295)	mem 34604MB
[2025-01-19 12:09:02 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][130/312]	eta 0:02:17 lr 0.001661	time 0.7220 (0.7548)	model_time 0.7219 (0.7422)	loss 3.0938 (3.2292)	grad_norm 1.2461 (1.6503/0.8074)	mem 34602MB
[2025-01-19 12:09:05 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][20/312]	eta 0:03:53 lr 0.001668	time 0.7228 (0.7994)	model_time 0.7226 (0.7283)	loss 3.2369 (3.0652)	grad_norm 3.3434 (2.2798/1.0329)	mem 34604MB
[2025-01-19 12:09:10 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][140/312]	eta 0:02:09 lr 0.001660	time 0.7291 (0.7536)	model_time 0.7289 (0.7418)	loss 3.4554 (3.2251)	grad_norm 1.1585 (1.6951/0.8241)	mem 34602MB
[2025-01-19 12:09:13 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][30/312]	eta 0:03:39 lr 0.001667	time 0.7325 (0.7779)	model_time 0.7320 (0.7296)	loss 3.3211 (3.0790)	grad_norm 1.4335 (2.1238/0.9602)	mem 34604MB
[2025-01-19 12:09:17 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][150/312]	eta 0:02:02 lr 0.001660	time 0.7188 (0.7539)	model_time 0.7186 (0.7429)	loss 2.4374 (3.2301)	grad_norm 1.5421 (1.6689/0.8037)	mem 34602MB
[2025-01-19 12:09:20 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][40/312]	eta 0:03:29 lr 0.001667	time 0.8404 (0.7702)	model_time 0.8399 (0.7335)	loss 3.4236 (3.0809)	grad_norm 3.0455 (1.9856/0.9106)	mem 34604MB
[2025-01-19 12:09:25 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][160/312]	eta 0:01:54 lr 0.001659	time 0.7515 (0.7558)	model_time 0.7509 (0.7455)	loss 2.7814 (3.2083)	grad_norm 1.4512 (1.6784/0.7991)	mem 34602MB
[2025-01-19 12:09:28 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][50/312]	eta 0:03:21 lr 0.001666	time 0.8374 (0.7698)	model_time 0.8370 (0.7402)	loss 3.2705 (3.0730)	grad_norm 1.4587 (1.9585/0.8370)	mem 34604MB
[2025-01-19 12:09:33 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][170/312]	eta 0:01:47 lr 0.001658	time 0.7208 (0.7548)	model_time 0.7207 (0.7451)	loss 2.5688 (3.2001)	grad_norm 3.9590 (1.7006/0.8121)	mem 34602MB
[2025-01-19 12:09:36 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][60/312]	eta 0:03:14 lr 0.001665	time 0.7194 (0.7723)	model_time 0.7192 (0.7475)	loss 3.5216 (3.1124)	grad_norm 1.6221 (1.8615/0.8040)	mem 34604MB
[2025-01-19 12:09:40 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][180/312]	eta 0:01:39 lr 0.001658	time 0.7301 (0.7539)	model_time 0.7297 (0.7447)	loss 3.1115 (3.2002)	grad_norm 1.8805 (1.7162/0.8180)	mem 34602MB
[2025-01-19 12:09:43 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][70/312]	eta 0:03:06 lr 0.001665	time 0.7151 (0.7717)	model_time 0.7150 (0.7504)	loss 3.5108 (3.0771)	grad_norm 1.4127 (1.7750/0.7909)	mem 34604MB
[2025-01-19 12:09:47 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][190/312]	eta 0:01:31 lr 0.001657	time 0.7135 (0.7529)	model_time 0.7133 (0.7441)	loss 3.1686 (3.1948)	grad_norm 1.7227 (1.7039/0.8089)	mem 34602MB
[2025-01-19 12:09:51 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][80/312]	eta 0:02:57 lr 0.001664	time 0.7194 (0.7657)	model_time 0.7190 (0.7470)	loss 3.5210 (3.0452)	grad_norm 0.9207 (1.6903/0.7770)	mem 34604MB
[2025-01-19 12:09:55 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][200/312]	eta 0:01:24 lr 0.001656	time 0.7153 (0.7519)	model_time 0.7151 (0.7436)	loss 3.1809 (3.1970)	grad_norm 3.0100 (1.7132/0.8135)	mem 34602MB
[2025-01-19 12:09:58 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][90/312]	eta 0:02:49 lr 0.001663	time 0.7204 (0.7629)	model_time 0.7202 (0.7462)	loss 3.3066 (3.0578)	grad_norm 1.6429 (1.6272/0.7593)	mem 34604MB
[2025-01-19 12:10:02 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][210/312]	eta 0:01:16 lr 0.001656	time 0.7186 (0.7517)	model_time 0.7182 (0.7437)	loss 2.4248 (3.2002)	grad_norm 2.0050 (1.7079/0.8079)	mem 34602MB
[2025-01-19 12:10:05 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][100/312]	eta 0:02:40 lr 0.001663	time 0.7064 (0.7589)	model_time 0.7062 (0.7438)	loss 2.2559 (3.0751)	grad_norm 2.3323 (1.6569/0.7540)	mem 34604MB
[2025-01-19 12:10:10 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][220/312]	eta 0:01:09 lr 0.001655	time 0.7684 (0.7509)	model_time 0.7682 (0.7433)	loss 3.2664 (3.1996)	grad_norm 1.1472 (1.6932/0.8006)	mem 34602MB
[2025-01-19 12:10:13 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][110/312]	eta 0:02:32 lr 0.001662	time 0.7205 (0.7559)	model_time 0.7201 (0.7421)	loss 3.3722 (3.0767)	grad_norm 2.0136 (1.6264/0.7316)	mem 34604MB
[2025-01-19 12:10:17 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][230/312]	eta 0:01:01 lr 0.001654	time 0.7481 (0.7499)	model_time 0.7476 (0.7426)	loss 3.4655 (3.2037)	grad_norm 1.2298 (1.6859/0.7882)	mem 34602MB
[2025-01-19 12:10:20 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][120/312]	eta 0:02:24 lr 0.001662	time 0.7293 (0.7534)	model_time 0.7289 (0.7408)	loss 3.1589 (3.0869)	grad_norm 1.2313 (1.6435/0.7663)	mem 34604MB
[2025-01-19 12:10:24 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][240/312]	eta 0:00:53 lr 0.001654	time 0.7350 (0.7498)	model_time 0.7346 (0.7428)	loss 3.8448 (3.1884)	grad_norm 1.4890 (1.6780/0.7770)	mem 34602MB
[2025-01-19 12:10:27 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][130/312]	eta 0:02:16 lr 0.001661	time 0.7093 (0.7515)	model_time 0.7089 (0.7398)	loss 3.4456 (3.0817)	grad_norm 1.0226 (1.6632/0.7681)	mem 34604MB
[2025-01-19 12:10:32 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][250/312]	eta 0:00:46 lr 0.001653	time 0.7194 (0.7493)	model_time 0.7193 (0.7425)	loss 3.5907 (3.1755)	grad_norm 2.1414 (1.6791/0.7695)	mem 34602MB
[2025-01-19 12:10:34 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][140/312]	eta 0:02:08 lr 0.001660	time 0.7370 (0.7499)	model_time 0.7365 (0.7389)	loss 3.3982 (3.0867)	grad_norm 1.3082 (1.6449/0.7513)	mem 34604MB
[2025-01-19 12:10:39 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][260/312]	eta 0:00:38 lr 0.001652	time 0.7486 (0.7487)	model_time 0.7485 (0.7422)	loss 3.2153 (3.1785)	grad_norm 1.0122 (1.6703/0.7600)	mem 34602MB
[2025-01-19 12:10:42 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][150/312]	eta 0:02:01 lr 0.001660	time 0.7060 (0.7488)	model_time 0.7056 (0.7386)	loss 3.3758 (3.0855)	grad_norm 1.0793 (1.6234/0.7354)	mem 34604MB
[2025-01-19 12:10:47 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][270/312]	eta 0:00:31 lr 0.001652	time 0.7326 (0.7493)	model_time 0.7325 (0.7430)	loss 2.6301 (3.1792)	grad_norm 1.1884 (1.6686/0.7521)	mem 34602MB
[2025-01-19 12:10:49 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][160/312]	eta 0:01:53 lr 0.001659	time 0.8279 (0.7491)	model_time 0.8278 (0.7395)	loss 2.9795 (3.0904)	grad_norm 1.4593 (1.6314/0.7315)	mem 34604MB
[2025-01-19 12:10:54 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][280/312]	eta 0:00:24 lr 0.001651	time 0.8146 (0.7501)	model_time 0.8145 (0.7441)	loss 3.4581 (3.1866)	grad_norm 1.4748 (1.6665/0.7476)	mem 34602MB
[2025-01-19 12:10:57 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][170/312]	eta 0:01:46 lr 0.001658	time 0.8077 (0.7501)	model_time 0.8075 (0.7410)	loss 3.5607 (3.0975)	grad_norm 1.8241 (1.6562/0.7280)	mem 34604MB
[2025-01-19 12:11:02 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][290/312]	eta 0:00:16 lr 0.001650	time 0.7361 (0.7500)	model_time 0.7357 (0.7441)	loss 3.4994 (3.1887)	grad_norm 1.7389 (1.6772/0.7486)	mem 34602MB
[2025-01-19 12:11:05 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][180/312]	eta 0:01:39 lr 0.001658	time 0.7465 (0.7524)	model_time 0.7461 (0.7438)	loss 3.6557 (3.1175)	grad_norm 2.3102 (1.6601/0.7200)	mem 34604MB
[2025-01-19 12:11:09 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][300/312]	eta 0:00:08 lr 0.001650	time 0.7123 (0.7495)	model_time 0.7122 (0.7438)	loss 3.2114 (3.1837)	grad_norm 1.0428 (1.6642/0.7397)	mem 34602MB
[2025-01-19 12:11:13 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][190/312]	eta 0:01:31 lr 0.001657	time 0.7164 (0.7537)	model_time 0.7159 (0.7456)	loss 3.3848 (3.1056)	grad_norm 0.8384 (1.6589/0.7092)	mem 34604MB
[2025-01-19 12:11:16 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][310/312]	eta 0:00:01 lr 0.001649	time 0.7148 (0.7487)	model_time 0.7147 (0.7431)	loss 3.5194 (3.1864)	grad_norm 3.4462 (1.6820/0.7554)	mem 34602MB
[2025-01-19 12:11:17 internimage_b_1k_224] (main.py 519): INFO EPOCH 167 training takes 0:03:53
[2025-01-19 12:11:17 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_167.pth saving......
[2025-01-19 12:11:20 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][200/312]	eta 0:01:24 lr 0.001656	time 0.7081 (0.7528)	model_time 0.7080 (0.7450)	loss 3.6370 (3.1106)	grad_norm 2.1492 (1.6474/0.7000)	mem 34604MB
[2025-01-19 12:11:20 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_167.pth saved !!!
[2025-01-19 12:11:27 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][210/312]	eta 0:01:16 lr 0.001656	time 0.7152 (0.7514)	model_time 0.7150 (0.7440)	loss 2.8797 (3.1183)	grad_norm 1.7507 (1.6700/0.7221)	mem 34604MB
[2025-01-19 12:11:28 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.583 (7.583)	Loss 0.7971 (0.7971)	Acc@1 84.229 (84.229)	Acc@5 97.070 (97.070)	Mem 34602MB
[2025-01-19 12:11:31 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.973)	Loss 1.0799 (0.9137)	Acc@1 76.807 (81.381)	Acc@5 94.727 (95.885)	Mem 34602MB
[2025-01-19 12:11:31 internimage_b_1k_224] (main.py 575): INFO [Epoch:167] * Acc@1 81.246 Acc@5 95.897
[2025-01-19 12:11:31 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.2%
[2025-01-19 12:11:31 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 12:11:34 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][220/312]	eta 0:01:09 lr 0.001655	time 0.7208 (0.7503)	model_time 0.7206 (0.7432)	loss 3.2923 (3.1305)	grad_norm 1.1451 (1.6871/0.7338)	mem 34604MB
[2025-01-19 12:11:35 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 12:11:35 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.25%
[2025-01-19 12:11:42 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][230/312]	eta 0:01:01 lr 0.001654	time 0.7269 (0.7495)	model_time 0.7267 (0.7427)	loss 2.1649 (3.1185)	grad_norm 1.1960 (1.6715/0.7271)	mem 34604MB
[2025-01-19 12:11:42 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.461 (7.461)	Loss 0.6643 (0.6643)	Acc@1 84.351 (84.351)	Acc@5 97.656 (97.656)	Mem 34602MB
[2025-01-19 12:11:45 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.966)	Loss 0.9507 (0.7944)	Acc@1 77.490 (81.787)	Acc@5 94.727 (96.105)	Mem 34602MB
[2025-01-19 12:11:45 internimage_b_1k_224] (main.py 575): INFO [Epoch:167] * Acc@1 81.656 Acc@5 96.159
[2025-01-19 12:11:45 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.7%
[2025-01-19 12:11:46 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:11:49 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][240/312]	eta 0:00:53 lr 0.001654	time 0.7199 (0.7488)	model_time 0.7197 (0.7423)	loss 2.9526 (3.1087)	grad_norm 1.1428 (1.6529/0.7197)	mem 34604MB
[2025-01-19 12:11:49 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:11:49 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.66%
[2025-01-19 12:11:51 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][0/312]	eta 0:11:11 lr 0.001649	time 2.1538 (2.1538)	model_time 0.7366 (0.7366)	loss 3.1498 (3.1498)	grad_norm 1.7711 (1.7711/0.0000)	mem 34602MB
[2025-01-19 12:11:56 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][250/312]	eta 0:00:46 lr 0.001653	time 0.7173 (0.7478)	model_time 0.7168 (0.7415)	loss 3.4549 (3.1102)	grad_norm 1.0888 (1.6571/0.7253)	mem 34604MB
[2025-01-19 12:11:59 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][10/312]	eta 0:04:22 lr 0.001648	time 0.7166 (0.8707)	model_time 0.7162 (0.7415)	loss 2.4173 (3.0839)	grad_norm 0.9048 (1.9132/0.6269)	mem 34602MB
[2025-01-19 12:12:04 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][260/312]	eta 0:00:38 lr 0.001652	time 0.7183 (0.7469)	model_time 0.7181 (0.7408)	loss 2.8015 (3.1105)	grad_norm 0.6239 (1.6541/0.7366)	mem 34604MB
[2025-01-19 12:12:06 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][20/312]	eta 0:03:54 lr 0.001648	time 0.7196 (0.8044)	model_time 0.7191 (0.7366)	loss 2.9237 (3.0300)	grad_norm 1.3621 (1.8782/0.7127)	mem 34602MB
[2025-01-19 12:12:11 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][270/312]	eta 0:00:31 lr 0.001652	time 0.7345 (0.7463)	model_time 0.7343 (0.7404)	loss 3.3108 (3.1093)	grad_norm 1.1004 (1.6435/0.7281)	mem 34604MB
[2025-01-19 12:12:13 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][30/312]	eta 0:03:40 lr 0.001647	time 0.7286 (0.7820)	model_time 0.7282 (0.7359)	loss 3.3050 (3.0711)	grad_norm 1.0322 (1.7732/0.6481)	mem 34602MB
[2025-01-19 12:12:18 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][280/312]	eta 0:00:23 lr 0.001651	time 0.8269 (0.7463)	model_time 0.8264 (0.7407)	loss 2.9084 (3.1077)	grad_norm 2.0524 (1.6382/0.7211)	mem 34604MB
[2025-01-19 12:12:21 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][40/312]	eta 0:03:29 lr 0.001646	time 0.7191 (0.7697)	model_time 0.7186 (0.7347)	loss 3.3841 (3.0669)	grad_norm 1.0098 (1.6522/0.6276)	mem 34602MB
[2025-01-19 12:12:26 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][290/312]	eta 0:00:16 lr 0.001650	time 0.8191 (0.7467)	model_time 0.8186 (0.7412)	loss 2.6592 (3.1048)	grad_norm 1.7082 (1.6343/0.7138)	mem 34604MB
[2025-01-19 12:12:28 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][50/312]	eta 0:03:20 lr 0.001646	time 0.7249 (0.7640)	model_time 0.7248 (0.7358)	loss 3.4766 (3.1173)	grad_norm 0.9144 (1.6102/0.5907)	mem 34602MB
[2025-01-19 12:12:34 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][300/312]	eta 0:00:08 lr 0.001650	time 0.7121 (0.7476)	model_time 0.7120 (0.7423)	loss 3.9399 (3.1072)	grad_norm 2.0836 (1.6306/0.7120)	mem 34604MB
[2025-01-19 12:12:36 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][60/312]	eta 0:03:11 lr 0.001645	time 0.8048 (0.7601)	model_time 0.8043 (0.7365)	loss 3.4909 (3.1253)	grad_norm 1.6039 (1.6613/0.5898)	mem 34602MB
[2025-01-19 12:12:42 internimage_b_1k_224] (main.py 510): INFO Train: [167/300][310/312]	eta 0:00:01 lr 0.001649	time 0.7039 (0.7489)	model_time 0.7038 (0.7438)	loss 1.9264 (3.1021)	grad_norm 1.6550 (1.6161/0.7024)	mem 34604MB
[2025-01-19 12:12:42 internimage_b_1k_224] (main.py 519): INFO EPOCH 167 training takes 0:03:53
[2025-01-19 12:12:42 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_167.pth saving......
[2025-01-19 12:12:43 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][70/312]	eta 0:03:03 lr 0.001644	time 0.7176 (0.7578)	model_time 0.7171 (0.7374)	loss 3.1831 (3.0964)	grad_norm 2.2666 (1.7436/0.6244)	mem 34602MB
[2025-01-19 12:12:45 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_167.pth saved !!!
[2025-01-19 12:12:51 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][80/312]	eta 0:02:55 lr 0.001644	time 0.7331 (0.7578)	model_time 0.7327 (0.7399)	loss 3.9037 (3.1005)	grad_norm 1.7820 (1.7330/0.6142)	mem 34602MB
[2025-01-19 12:12:53 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.387 (7.387)	Loss 0.7767 (0.7767)	Acc@1 84.033 (84.033)	Acc@5 97.388 (97.388)	Mem 34604MB
[2025-01-19 12:12:56 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.964)	Loss 1.0253 (0.8771)	Acc@1 76.538 (81.365)	Acc@5 94.409 (95.978)	Mem 34604MB
[2025-01-19 12:12:56 internimage_b_1k_224] (main.py 575): INFO [Epoch:167] * Acc@1 81.228 Acc@5 96.009
[2025-01-19 12:12:56 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.2%
[2025-01-19 12:12:56 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.28%
[2025-01-19 12:12:58 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][90/312]	eta 0:02:48 lr 0.001643	time 0.7172 (0.7577)	model_time 0.7167 (0.7418)	loss 2.4723 (3.0886)	grad_norm 1.0379 (1.7043/0.6162)	mem 34602MB
[2025-01-19 12:13:06 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][100/312]	eta 0:02:40 lr 0.001642	time 0.8120 (0.7569)	model_time 0.8119 (0.7425)	loss 2.0476 (3.1016)	grad_norm 0.6735 (1.6810/0.6051)	mem 34602MB
[2025-01-19 12:13:06 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.458 (9.458)	Loss 0.6636 (0.6636)	Acc@1 84.790 (84.790)	Acc@5 97.705 (97.705)	Mem 34604MB
[2025-01-19 12:13:10 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.275)	Loss 0.9500 (0.7938)	Acc@1 77.441 (81.891)	Acc@5 94.702 (96.127)	Mem 34604MB
[2025-01-19 12:13:11 internimage_b_1k_224] (main.py 575): INFO [Epoch:167] * Acc@1 81.766 Acc@5 96.173
[2025-01-19 12:13:11 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.8%
[2025-01-19 12:13:11 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:13:13 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][110/312]	eta 0:02:32 lr 0.001642	time 0.7177 (0.7550)	model_time 0.7173 (0.7418)	loss 3.3272 (3.1051)	grad_norm 1.2681 (1.6365/0.5998)	mem 34602MB
[2025-01-19 12:13:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:13:14 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.77%
[2025-01-19 12:13:16 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][0/312]	eta 0:11:28 lr 0.001649	time 2.2069 (2.2069)	model_time 0.7460 (0.7460)	loss 3.7382 (3.7382)	grad_norm 1.7702 (1.7702/0.0000)	mem 34604MB
[2025-01-19 12:13:20 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][120/312]	eta 0:02:24 lr 0.001641	time 0.7165 (0.7530)	model_time 0.7160 (0.7409)	loss 2.6431 (3.1078)	grad_norm 1.7418 (1.6183/0.5927)	mem 34602MB
[2025-01-19 12:13:24 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][10/312]	eta 0:04:20 lr 0.001648	time 0.7279 (0.8623)	model_time 0.7278 (0.7292)	loss 3.2851 (3.2099)	grad_norm 1.9169 (2.0575/0.7352)	mem 34604MB
[2025-01-19 12:13:28 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][130/312]	eta 0:02:16 lr 0.001641	time 0.7155 (0.7520)	model_time 0.7153 (0.7408)	loss 3.2219 (3.1262)	grad_norm 1.4478 (1.6013/0.5834)	mem 34602MB
[2025-01-19 12:13:31 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][20/312]	eta 0:03:53 lr 0.001648	time 0.7400 (0.8011)	model_time 0.7398 (0.7312)	loss 3.3327 (3.2180)	grad_norm 1.3438 (2.0326/0.8376)	mem 34604MB
[2025-01-19 12:13:35 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][140/312]	eta 0:02:09 lr 0.001640	time 0.7305 (0.7511)	model_time 0.7303 (0.7407)	loss 3.3361 (3.1457)	grad_norm 1.3435 (1.5972/0.5731)	mem 34602MB
[2025-01-19 12:13:38 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][30/312]	eta 0:03:40 lr 0.001647	time 0.7069 (0.7816)	model_time 0.7067 (0.7341)	loss 2.6431 (3.1221)	grad_norm 1.3718 (1.8651/0.7522)	mem 34604MB
[2025-01-19 12:13:42 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][150/312]	eta 0:02:01 lr 0.001639	time 0.7279 (0.7498)	model_time 0.7278 (0.7400)	loss 3.2604 (3.1523)	grad_norm 1.7000 (1.6596/0.6283)	mem 34602MB
[2025-01-19 12:13:46 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][40/312]	eta 0:03:28 lr 0.001646	time 0.7237 (0.7678)	model_time 0.7233 (0.7318)	loss 4.0216 (3.1254)	grad_norm 1.1646 (1.7211/0.7064)	mem 34604MB
[2025-01-19 12:13:50 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][160/312]	eta 0:01:53 lr 0.001639	time 0.7376 (0.7486)	model_time 0.7375 (0.7394)	loss 3.2063 (3.1637)	grad_norm 0.6599 (1.6349/0.6244)	mem 34602MB
[2025-01-19 12:13:53 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][50/312]	eta 0:03:18 lr 0.001646	time 0.7194 (0.7590)	model_time 0.7189 (0.7300)	loss 2.1557 (3.1491)	grad_norm 1.1749 (1.6964/0.6633)	mem 34604MB
[2025-01-19 12:13:57 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][170/312]	eta 0:01:46 lr 0.001638	time 0.7082 (0.7482)	model_time 0.7080 (0.7395)	loss 2.6784 (3.1708)	grad_norm 1.4370 (1.6024/0.6209)	mem 34602MB
[2025-01-19 12:14:00 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][60/312]	eta 0:03:09 lr 0.001645	time 0.7284 (0.7533)	model_time 0.7279 (0.7290)	loss 2.5562 (3.1164)	grad_norm 1.9946 (1.6727/0.6354)	mem 34604MB
[2025-01-19 12:14:05 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][180/312]	eta 0:01:38 lr 0.001637	time 0.8111 (0.7480)	model_time 0.8107 (0.7398)	loss 2.5195 (3.1596)	grad_norm 0.8073 (1.5867/0.6216)	mem 34602MB
[2025-01-19 12:14:07 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][70/312]	eta 0:03:01 lr 0.001644	time 0.7283 (0.7502)	model_time 0.7281 (0.7293)	loss 3.1632 (3.1466)	grad_norm 1.7765 (1.6593/0.6161)	mem 34604MB
[2025-01-19 12:14:12 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][190/312]	eta 0:01:31 lr 0.001637	time 0.7185 (0.7475)	model_time 0.7181 (0.7397)	loss 3.4489 (3.1567)	grad_norm 1.0576 (1.5951/0.6344)	mem 34602MB
[2025-01-19 12:14:15 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][80/312]	eta 0:02:53 lr 0.001644	time 0.7353 (0.7473)	model_time 0.7351 (0.7289)	loss 3.0315 (3.1379)	grad_norm 0.9886 (1.6236/0.6022)	mem 34604MB
[2025-01-19 12:14:20 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][200/312]	eta 0:01:23 lr 0.001636	time 0.7229 (0.7480)	model_time 0.7228 (0.7405)	loss 3.2084 (3.1624)	grad_norm 1.4612 (1.5996/0.6381)	mem 34602MB
[2025-01-19 12:14:22 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][90/312]	eta 0:02:46 lr 0.001643	time 0.8978 (0.7483)	model_time 0.8976 (0.7319)	loss 3.3175 (3.1305)	grad_norm 4.6114 (1.6757/0.7119)	mem 34604MB
[2025-01-19 12:14:27 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][210/312]	eta 0:01:16 lr 0.001635	time 0.7157 (0.7485)	model_time 0.7153 (0.7414)	loss 2.6726 (3.1510)	grad_norm 2.0803 (1.5985/0.6300)	mem 34602MB
[2025-01-19 12:14:30 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][100/312]	eta 0:02:38 lr 0.001642	time 0.7132 (0.7485)	model_time 0.7130 (0.7337)	loss 3.5249 (3.1462)	grad_norm 1.3326 (1.6874/0.7138)	mem 34604MB
[2025-01-19 12:14:35 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][220/312]	eta 0:01:08 lr 0.001635	time 0.8130 (0.7496)	model_time 0.8125 (0.7428)	loss 2.7851 (3.1502)	grad_norm 0.8296 (1.5953/0.6261)	mem 34602MB
[2025-01-19 12:14:38 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][110/312]	eta 0:02:32 lr 0.001642	time 0.8010 (0.7527)	model_time 0.8008 (0.7392)	loss 2.9934 (3.1581)	grad_norm 1.3786 (1.6778/0.7204)	mem 34604MB
[2025-01-19 12:14:42 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][230/312]	eta 0:01:01 lr 0.001634	time 0.7208 (0.7491)	model_time 0.7206 (0.7426)	loss 2.8784 (3.1486)	grad_norm 1.8893 (1.5810/0.6219)	mem 34602MB
[2025-01-19 12:14:45 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][120/312]	eta 0:02:25 lr 0.001641	time 0.8015 (0.7554)	model_time 0.8011 (0.7429)	loss 2.8040 (3.1405)	grad_norm 2.0361 (1.6799/0.7079)	mem 34604MB
[2025-01-19 12:14:50 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][240/312]	eta 0:00:53 lr 0.001633	time 0.7208 (0.7484)	model_time 0.7204 (0.7422)	loss 2.6237 (3.1393)	grad_norm 1.4129 (1.5917/0.6401)	mem 34602MB
[2025-01-19 12:14:53 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][130/312]	eta 0:02:17 lr 0.001641	time 0.7153 (0.7536)	model_time 0.7148 (0.7421)	loss 2.9786 (3.1428)	grad_norm 0.7084 (1.6647/0.6969)	mem 34604MB
[2025-01-19 12:14:57 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][250/312]	eta 0:00:46 lr 0.001633	time 0.8107 (0.7482)	model_time 0.8103 (0.7421)	loss 1.9941 (3.1266)	grad_norm 2.1572 (1.6006/0.6388)	mem 34602MB
[2025-01-19 12:15:00 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][140/312]	eta 0:02:09 lr 0.001640	time 0.7656 (0.7521)	model_time 0.7650 (0.7414)	loss 3.9017 (3.1471)	grad_norm 0.7657 (1.6166/0.6975)	mem 34604MB
[2025-01-19 12:15:04 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][260/312]	eta 0:00:38 lr 0.001632	time 0.7412 (0.7479)	model_time 0.7408 (0.7421)	loss 2.9526 (3.1156)	grad_norm 3.0173 (1.6070/0.6407)	mem 34602MB
[2025-01-19 12:15:08 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][150/312]	eta 0:02:01 lr 0.001639	time 0.7074 (0.7513)	model_time 0.7072 (0.7413)	loss 2.7564 (3.1533)	grad_norm 2.0551 (1.6238/0.6805)	mem 34604MB
[2025-01-19 12:15:12 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][270/312]	eta 0:00:31 lr 0.001631	time 0.7151 (0.7472)	model_time 0.7146 (0.7416)	loss 2.5801 (3.1137)	grad_norm 1.9182 (1.6090/0.6327)	mem 34602MB
[2025-01-19 12:15:15 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][160/312]	eta 0:01:53 lr 0.001639	time 0.7229 (0.7498)	model_time 0.7225 (0.7404)	loss 3.2754 (3.1444)	grad_norm 2.2067 (1.6124/0.6695)	mem 34604MB
[2025-01-19 12:15:19 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][280/312]	eta 0:00:23 lr 0.001631	time 0.7346 (0.7466)	model_time 0.7341 (0.7412)	loss 3.3871 (3.1242)	grad_norm 1.0754 (1.6041/0.6344)	mem 34602MB
[2025-01-19 12:15:22 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][170/312]	eta 0:01:46 lr 0.001638	time 0.7252 (0.7483)	model_time 0.7248 (0.7394)	loss 2.3798 (3.1238)	grad_norm 0.7836 (1.6006/0.6570)	mem 34604MB
[2025-01-19 12:15:26 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][290/312]	eta 0:00:16 lr 0.001630	time 0.7226 (0.7462)	model_time 0.7221 (0.7410)	loss 2.9201 (3.1244)	grad_norm 3.2016 (1.6362/0.6623)	mem 34602MB
[2025-01-19 12:15:29 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][180/312]	eta 0:01:38 lr 0.001637	time 0.7126 (0.7471)	model_time 0.7124 (0.7387)	loss 3.4650 (3.1229)	grad_norm 0.9277 (1.5901/0.6471)	mem 34604MB
[2025-01-19 12:15:34 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][300/312]	eta 0:00:08 lr 0.001629	time 0.7919 (0.7460)	model_time 0.7918 (0.7409)	loss 3.7801 (3.1295)	grad_norm 0.8997 (1.6357/0.6585)	mem 34602MB
[2025-01-19 12:15:37 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][190/312]	eta 0:01:31 lr 0.001637	time 0.7211 (0.7460)	model_time 0.7209 (0.7380)	loss 1.9796 (3.1140)	grad_norm 2.4508 (1.5970/0.6515)	mem 34604MB
[2025-01-19 12:15:41 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][310/312]	eta 0:00:01 lr 0.001629	time 0.7124 (0.7453)	model_time 0.7123 (0.7404)	loss 2.9663 (3.1318)	grad_norm 1.2759 (1.6187/0.6480)	mem 34602MB
[2025-01-19 12:15:42 internimage_b_1k_224] (main.py 519): INFO EPOCH 168 training takes 0:03:52
[2025-01-19 12:15:42 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_168.pth saving......
[2025-01-19 12:15:44 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][200/312]	eta 0:01:23 lr 0.001636	time 0.7239 (0.7449)	model_time 0.7237 (0.7373)	loss 3.3663 (3.1117)	grad_norm 1.2424 (1.6145/0.6558)	mem 34604MB
[2025-01-19 12:15:45 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_168.pth saved !!!
[2025-01-19 12:15:51 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][210/312]	eta 0:01:15 lr 0.001635	time 0.8173 (0.7450)	model_time 0.8168 (0.7377)	loss 3.1064 (3.1083)	grad_norm 1.3643 (1.6180/0.6645)	mem 34604MB
[2025-01-19 12:15:53 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.518 (7.518)	Loss 0.7370 (0.7370)	Acc@1 84.229 (84.229)	Acc@5 97.168 (97.168)	Mem 34602MB
[2025-01-19 12:15:56 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.955)	Loss 1.0232 (0.8785)	Acc@1 77.417 (81.343)	Acc@5 94.873 (95.874)	Mem 34602MB
[2025-01-19 12:15:56 internimage_b_1k_224] (main.py 575): INFO [Epoch:168] * Acc@1 81.282 Acc@5 95.935
[2025-01-19 12:15:56 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.3%
[2025-01-19 12:15:56 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 12:15:59 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][220/312]	eta 0:01:08 lr 0.001635	time 0.7196 (0.7451)	model_time 0.7194 (0.7382)	loss 2.5158 (3.1121)	grad_norm 1.9365 (1.6162/0.6618)	mem 34604MB
[2025-01-19 12:15:59 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 12:15:59 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.28%
[2025-01-19 12:16:07 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.569 (7.569)	Loss 0.6651 (0.6651)	Acc@1 84.399 (84.399)	Acc@5 97.705 (97.705)	Mem 34602MB
[2025-01-19 12:16:07 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][230/312]	eta 0:01:01 lr 0.001634	time 0.8250 (0.7474)	model_time 0.8248 (0.7407)	loss 2.2185 (3.1041)	grad_norm 1.6487 (1.6470/0.7029)	mem 34604MB
[2025-01-19 12:16:10 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.975)	Loss 0.9503 (0.7946)	Acc@1 77.637 (81.836)	Acc@5 94.678 (96.116)	Mem 34602MB
[2025-01-19 12:16:10 internimage_b_1k_224] (main.py 575): INFO [Epoch:168] * Acc@1 81.696 Acc@5 96.171
[2025-01-19 12:16:10 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.7%
[2025-01-19 12:16:10 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:16:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:16:14 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.70%
[2025-01-19 12:16:14 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][240/312]	eta 0:00:53 lr 0.001633	time 0.8194 (0.7482)	model_time 0.8192 (0.7418)	loss 2.9275 (3.1050)	grad_norm 1.1203 (1.6727/0.7396)	mem 34604MB
[2025-01-19 12:16:16 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][0/312]	eta 0:11:13 lr 0.001629	time 2.1576 (2.1576)	model_time 0.7346 (0.7346)	loss 3.1844 (3.1844)	grad_norm 1.4811 (1.4811/0.0000)	mem 34602MB
[2025-01-19 12:16:22 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][250/312]	eta 0:00:46 lr 0.001633	time 0.7218 (0.7478)	model_time 0.7212 (0.7416)	loss 2.9950 (3.0978)	grad_norm 0.9479 (1.6805/0.7433)	mem 34604MB
[2025-01-19 12:16:24 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][10/312]	eta 0:04:31 lr 0.001628	time 0.8138 (0.8997)	model_time 0.8137 (0.7700)	loss 2.6865 (2.9078)	grad_norm 2.6167 (1.5995/0.5290)	mem 34602MB
[2025-01-19 12:16:29 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][260/312]	eta 0:00:38 lr 0.001632	time 0.7131 (0.7472)	model_time 0.7126 (0.7412)	loss 3.1487 (3.0964)	grad_norm 2.0484 (1.6790/0.7335)	mem 34604MB
[2025-01-19 12:16:31 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][20/312]	eta 0:04:04 lr 0.001627	time 0.8100 (0.8358)	model_time 0.8099 (0.7677)	loss 3.4087 (2.9822)	grad_norm 2.6636 (1.8968/0.6970)	mem 34602MB
[2025-01-19 12:16:36 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][270/312]	eta 0:00:31 lr 0.001631	time 0.6646 (0.7466)	model_time 0.6642 (0.7408)	loss 3.8551 (3.1068)	grad_norm inf (1.6671/0.7265)	mem 34604MB
[2025-01-19 12:16:39 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][30/312]	eta 0:03:49 lr 0.001627	time 0.7214 (0.8142)	model_time 0.7212 (0.7679)	loss 3.3225 (3.1177)	grad_norm 1.0419 (1.7442/0.6769)	mem 34602MB
[2025-01-19 12:16:44 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][280/312]	eta 0:00:23 lr 0.001631	time 0.7323 (0.7464)	model_time 0.7321 (0.7408)	loss 3.2140 (3.1085)	grad_norm 1.1854 (1.6611/0.7192)	mem 34604MB
[2025-01-19 12:16:46 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][40/312]	eta 0:03:36 lr 0.001626	time 0.7238 (0.7977)	model_time 0.7236 (0.7626)	loss 2.8856 (3.0951)	grad_norm 0.8639 (1.6468/0.6339)	mem 34602MB
[2025-01-19 12:16:51 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][290/312]	eta 0:00:16 lr 0.001630	time 0.7416 (0.7456)	model_time 0.7414 (0.7403)	loss 3.6992 (3.1144)	grad_norm 2.5368 (1.6583/0.7123)	mem 34604MB
[2025-01-19 12:16:54 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][50/312]	eta 0:03:25 lr 0.001625	time 0.7254 (0.7853)	model_time 0.7250 (0.7571)	loss 3.5331 (3.0308)	grad_norm 1.2932 (1.5701/0.6016)	mem 34602MB
[2025-01-19 12:16:58 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][300/312]	eta 0:00:08 lr 0.001629	time 0.7140 (0.7447)	model_time 0.7139 (0.7395)	loss 3.2429 (3.1112)	grad_norm 1.5541 (1.6449/0.7098)	mem 34604MB
[2025-01-19 12:17:01 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][60/312]	eta 0:03:16 lr 0.001625	time 0.8403 (0.7793)	model_time 0.8401 (0.7557)	loss 3.5105 (3.0303)	grad_norm 2.7678 (1.5927/0.6268)	mem 34602MB
[2025-01-19 12:17:05 internimage_b_1k_224] (main.py 510): INFO Train: [168/300][310/312]	eta 0:00:01 lr 0.001629	time 0.7203 (0.7438)	model_time 0.7202 (0.7388)	loss 2.6773 (3.1097)	grad_norm 1.1302 (1.6359/0.7037)	mem 34604MB
[2025-01-19 12:17:06 internimage_b_1k_224] (main.py 519): INFO EPOCH 168 training takes 0:03:52
[2025-01-19 12:17:06 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_168.pth saving......
[2025-01-19 12:17:09 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][70/312]	eta 0:03:07 lr 0.001624	time 0.7375 (0.7744)	model_time 0.7374 (0.7540)	loss 2.9318 (3.0649)	grad_norm 2.1844 (1.7416/0.7457)	mem 34602MB
[2025-01-19 12:17:09 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_168.pth saved !!!
[2025-01-19 12:17:16 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][80/312]	eta 0:02:58 lr 0.001623	time 0.7356 (0.7696)	model_time 0.7352 (0.7517)	loss 3.9102 (3.0693)	grad_norm 2.4773 (1.7783/0.7464)	mem 34602MB
[2025-01-19 12:17:17 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.529 (7.529)	Loss 0.7521 (0.7521)	Acc@1 84.033 (84.033)	Acc@5 97.241 (97.241)	Mem 34604MB
[2025-01-19 12:17:20 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.953)	Loss 1.0151 (0.8604)	Acc@1 76.318 (81.681)	Acc@5 94.336 (96.003)	Mem 34604MB
[2025-01-19 12:17:20 internimage_b_1k_224] (main.py 575): INFO [Epoch:168] * Acc@1 81.508 Acc@5 96.009
[2025-01-19 12:17:20 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.5%
[2025-01-19 12:17:20 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 12:17:23 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][90/312]	eta 0:02:49 lr 0.001623	time 0.7179 (0.7646)	model_time 0.7178 (0.7486)	loss 3.6372 (3.0558)	grad_norm 1.0074 (1.7516/0.7348)	mem 34602MB
[2025-01-19 12:17:24 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 12:17:24 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.51%
[2025-01-19 12:17:31 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][100/312]	eta 0:02:41 lr 0.001622	time 0.7212 (0.7626)	model_time 0.7208 (0.7482)	loss 3.3375 (3.0659)	grad_norm 2.2766 (1.7209/0.7143)	mem 34602MB
[2025-01-19 12:17:31 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.367 (7.367)	Loss 0.6645 (0.6645)	Acc@1 84.839 (84.839)	Acc@5 97.729 (97.729)	Mem 34604MB
[2025-01-19 12:17:34 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.932)	Loss 0.9498 (0.7941)	Acc@1 77.466 (81.931)	Acc@5 94.702 (96.154)	Mem 34604MB
[2025-01-19 12:17:34 internimage_b_1k_224] (main.py 575): INFO [Epoch:168] * Acc@1 81.804 Acc@5 96.201
[2025-01-19 12:17:34 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.8%
[2025-01-19 12:17:34 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:17:38 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:17:38 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.80%
[2025-01-19 12:17:38 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][110/312]	eta 0:02:34 lr 0.001621	time 0.8861 (0.7626)	model_time 0.8860 (0.7494)	loss 2.8072 (3.0659)	grad_norm 2.3104 (1.7049/0.7024)	mem 34602MB
[2025-01-19 12:17:40 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][0/312]	eta 0:11:04 lr 0.001629	time 2.1308 (2.1308)	model_time 0.7373 (0.7373)	loss 3.4338 (3.4338)	grad_norm 1.3004 (1.3004/0.0000)	mem 34604MB
[2025-01-19 12:17:46 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][120/312]	eta 0:02:26 lr 0.001621	time 0.8288 (0.7609)	model_time 0.8287 (0.7487)	loss 2.5766 (3.0557)	grad_norm 0.9549 (1.7158/0.7153)	mem 34602MB
[2025-01-19 12:17:47 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][10/312]	eta 0:04:19 lr 0.001628	time 0.7577 (0.8589)	model_time 0.7576 (0.7319)	loss 3.2356 (3.0842)	grad_norm 3.0916 (1.6380/1.0571)	mem 34604MB
[2025-01-19 12:17:53 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][130/312]	eta 0:02:18 lr 0.001620	time 0.8115 (0.7600)	model_time 0.8113 (0.7487)	loss 3.3365 (3.0728)	grad_norm 1.6016 (1.7302/0.7191)	mem 34602MB
[2025-01-19 12:17:55 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][20/312]	eta 0:03:54 lr 0.001627	time 0.8149 (0.8043)	model_time 0.8144 (0.7376)	loss 2.5127 (3.0927)	grad_norm 2.6786 (1.9057/0.9458)	mem 34604MB
[2025-01-19 12:18:01 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][140/312]	eta 0:02:10 lr 0.001620	time 0.8094 (0.7614)	model_time 0.8093 (0.7509)	loss 2.4080 (3.0783)	grad_norm 1.2128 (1.7067/0.7051)	mem 34602MB
[2025-01-19 12:18:02 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][30/312]	eta 0:03:43 lr 0.001627	time 0.8257 (0.7937)	model_time 0.8255 (0.7484)	loss 3.1102 (3.0840)	grad_norm 1.9848 (1.8388/0.9291)	mem 34604MB
[2025-01-19 12:18:09 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][150/312]	eta 0:02:03 lr 0.001619	time 0.7163 (0.7614)	model_time 0.7161 (0.7516)	loss 3.2510 (3.0825)	grad_norm 0.8794 (1.7028/0.6967)	mem 34602MB
[2025-01-19 12:18:10 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][40/312]	eta 0:03:36 lr 0.001626	time 0.8244 (0.7942)	model_time 0.8243 (0.7599)	loss 2.2885 (3.0747)	grad_norm 2.2149 (1.7303/0.8485)	mem 34604MB
[2025-01-19 12:18:16 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][160/312]	eta 0:01:55 lr 0.001618	time 0.7278 (0.7611)	model_time 0.7273 (0.7519)	loss 2.1714 (3.0876)	grad_norm 1.8318 (1.7015/0.6804)	mem 34602MB
[2025-01-19 12:18:18 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][50/312]	eta 0:03:25 lr 0.001625	time 0.7090 (0.7852)	model_time 0.7088 (0.7575)	loss 2.1534 (3.0598)	grad_norm 0.9897 (1.6344/0.8076)	mem 34604MB
[2025-01-19 12:18:24 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][170/312]	eta 0:01:47 lr 0.001618	time 0.7197 (0.7596)	model_time 0.7193 (0.7509)	loss 2.3052 (3.0777)	grad_norm 0.7715 (1.6784/0.6756)	mem 34602MB
[2025-01-19 12:18:25 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][60/312]	eta 0:03:16 lr 0.001625	time 0.7348 (0.7788)	model_time 0.7346 (0.7556)	loss 2.2058 (3.0838)	grad_norm 1.6053 (1.5908/0.7615)	mem 34604MB
[2025-01-19 12:18:31 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][180/312]	eta 0:01:40 lr 0.001617	time 0.7967 (0.7588)	model_time 0.7966 (0.7506)	loss 2.8541 (3.0592)	grad_norm 1.2844 (1.6661/0.6718)	mem 34602MB
[2025-01-19 12:18:33 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][70/312]	eta 0:03:06 lr 0.001624	time 0.7378 (0.7716)	model_time 0.7376 (0.7516)	loss 2.1142 (3.0905)	grad_norm 1.0741 (1.5506/0.7364)	mem 34604MB
[2025-01-19 12:18:38 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][190/312]	eta 0:01:32 lr 0.001616	time 0.7143 (0.7576)	model_time 0.7139 (0.7497)	loss 2.4303 (3.0632)	grad_norm 1.9029 (1.6451/0.6663)	mem 34602MB
[2025-01-19 12:18:40 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][80/312]	eta 0:02:57 lr 0.001623	time 0.7304 (0.7659)	model_time 0.7302 (0.7483)	loss 3.3376 (3.0968)	grad_norm 1.4158 (1.5784/0.7296)	mem 34604MB
[2025-01-19 12:18:46 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][200/312]	eta 0:01:24 lr 0.001616	time 0.7260 (0.7564)	model_time 0.7258 (0.7489)	loss 3.3624 (3.0702)	grad_norm 1.7154 (1.6471/0.6616)	mem 34602MB
[2025-01-19 12:18:47 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][90/312]	eta 0:02:49 lr 0.001623	time 0.7162 (0.7625)	model_time 0.7158 (0.7469)	loss 3.4477 (3.1038)	grad_norm 2.6045 (1.5729/0.7204)	mem 34604MB
[2025-01-19 12:18:53 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][210/312]	eta 0:01:16 lr 0.001615	time 0.7172 (0.7549)	model_time 0.7170 (0.7478)	loss 3.1782 (3.0749)	grad_norm 1.2144 (1.6234/0.6573)	mem 34602MB
[2025-01-19 12:18:55 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][100/312]	eta 0:02:40 lr 0.001622	time 0.7239 (0.7589)	model_time 0.7236 (0.7447)	loss 2.1920 (3.1069)	grad_norm 4.1847 (1.6409/0.7798)	mem 34604MB
[2025-01-19 12:19:00 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][220/312]	eta 0:01:09 lr 0.001614	time 0.7164 (0.7539)	model_time 0.7163 (0.7471)	loss 3.6662 (3.0837)	grad_norm 3.0669 (1.6281/0.6673)	mem 34602MB
[2025-01-19 12:19:02 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][110/312]	eta 0:02:32 lr 0.001621	time 0.7274 (0.7556)	model_time 0.7273 (0.7427)	loss 3.2617 (3.1038)	grad_norm 2.1207 (1.6466/0.7727)	mem 34604MB
[2025-01-19 12:19:08 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][230/312]	eta 0:01:01 lr 0.001614	time 0.8178 (0.7537)	model_time 0.8174 (0.7472)	loss 3.3066 (3.0743)	grad_norm 1.3792 (1.6457/0.6989)	mem 34602MB
[2025-01-19 12:19:09 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][120/312]	eta 0:02:24 lr 0.001621	time 0.7228 (0.7530)	model_time 0.7226 (0.7411)	loss 2.4211 (3.0805)	grad_norm 1.6670 (1.6284/0.7498)	mem 34604MB
[2025-01-19 12:19:15 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][240/312]	eta 0:00:54 lr 0.001613	time 0.8127 (0.7530)	model_time 0.8123 (0.7468)	loss 2.9741 (3.0737)	grad_norm 1.1230 (1.6413/0.6907)	mem 34602MB
[2025-01-19 12:19:16 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][130/312]	eta 0:02:16 lr 0.001620	time 0.7335 (0.7510)	model_time 0.7332 (0.7400)	loss 2.1498 (3.0840)	grad_norm 2.0545 (1.6201/0.7394)	mem 34604MB
[2025-01-19 12:19:23 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][250/312]	eta 0:00:46 lr 0.001612	time 0.7160 (0.7527)	model_time 0.7156 (0.7467)	loss 3.7881 (3.0772)	grad_norm 3.1751 (1.6505/0.6862)	mem 34602MB
[2025-01-19 12:19:24 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][140/312]	eta 0:02:08 lr 0.001620	time 0.7233 (0.7500)	model_time 0.7231 (0.7397)	loss 3.4070 (3.0913)	grad_norm 1.0468 (1.6110/0.7276)	mem 34604MB
[2025-01-19 12:19:30 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][260/312]	eta 0:00:39 lr 0.001612	time 0.7173 (0.7536)	model_time 0.7171 (0.7478)	loss 2.4691 (3.0809)	grad_norm 2.8271 (1.6799/0.7003)	mem 34602MB
[2025-01-19 12:19:31 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][150/312]	eta 0:02:01 lr 0.001619	time 0.8204 (0.7515)	model_time 0.8198 (0.7419)	loss 3.4125 (3.1061)	grad_norm 3.3646 (1.6512/0.7730)	mem 34604MB
[2025-01-19 12:19:38 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][270/312]	eta 0:00:31 lr 0.001611	time 0.7137 (0.7542)	model_time 0.7135 (0.7486)	loss 2.1273 (3.0816)	grad_norm 1.3338 (1.6605/0.6973)	mem 34602MB
[2025-01-19 12:19:39 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][160/312]	eta 0:01:54 lr 0.001618	time 0.8177 (0.7547)	model_time 0.8172 (0.7457)	loss 3.4682 (3.1226)	grad_norm 3.1283 (1.6650/0.7712)	mem 34604MB
[2025-01-19 12:19:46 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][280/312]	eta 0:00:24 lr 0.001610	time 0.7203 (0.7540)	model_time 0.7198 (0.7486)	loss 2.5383 (3.0854)	grad_norm 2.2073 (1.6643/0.6978)	mem 34602MB
[2025-01-19 12:19:47 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][170/312]	eta 0:01:47 lr 0.001618	time 0.7177 (0.7543)	model_time 0.7171 (0.7458)	loss 3.3899 (3.1207)	grad_norm 2.2745 (1.6728/0.7600)	mem 34604MB
[2025-01-19 12:19:53 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][290/312]	eta 0:00:16 lr 0.001610	time 0.7292 (0.7535)	model_time 0.7290 (0.7482)	loss 3.3994 (3.0886)	grad_norm 1.8408 (1.6669/0.6922)	mem 34602MB
[2025-01-19 12:19:54 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][180/312]	eta 0:01:39 lr 0.001617	time 0.7646 (0.7539)	model_time 0.7644 (0.7458)	loss 3.3430 (3.1259)	grad_norm 1.2036 (1.6687/0.7555)	mem 34604MB
[2025-01-19 12:20:00 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][300/312]	eta 0:00:09 lr 0.001609	time 0.7970 (0.7529)	model_time 0.7969 (0.7478)	loss 2.6856 (3.0914)	grad_norm 1.3206 (1.6604/0.6860)	mem 34602MB
[2025-01-19 12:20:02 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][190/312]	eta 0:01:31 lr 0.001616	time 0.7190 (0.7524)	model_time 0.7185 (0.7447)	loss 2.5757 (3.1209)	grad_norm 1.6946 (1.6566/0.7442)	mem 34604MB
[2025-01-19 12:20:08 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][310/312]	eta 0:00:01 lr 0.001608	time 0.7131 (0.7521)	model_time 0.7130 (0.7471)	loss 3.0754 (3.0972)	grad_norm 1.3724 (1.6553/0.6851)	mem 34602MB
[2025-01-19 12:20:08 internimage_b_1k_224] (main.py 519): INFO EPOCH 169 training takes 0:03:54
[2025-01-19 12:20:08 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_169.pth saving......
[2025-01-19 12:20:09 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][200/312]	eta 0:01:24 lr 0.001616	time 0.7256 (0.7513)	model_time 0.7254 (0.7440)	loss 3.2156 (3.1157)	grad_norm 0.8894 (1.6431/0.7332)	mem 34604MB
[2025-01-19 12:20:11 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_169.pth saved !!!
[2025-01-19 12:20:16 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][210/312]	eta 0:01:16 lr 0.001615	time 0.7166 (0.7510)	model_time 0.7161 (0.7440)	loss 4.0696 (3.1181)	grad_norm 2.0756 (1.6392/0.7307)	mem 34604MB
[2025-01-19 12:20:19 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.480 (7.480)	Loss 0.7479 (0.7479)	Acc@1 84.180 (84.180)	Acc@5 97.217 (97.217)	Mem 34602MB
[2025-01-19 12:20:22 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.964)	Loss 1.0147 (0.8757)	Acc@1 77.026 (81.452)	Acc@5 94.580 (95.949)	Mem 34602MB
[2025-01-19 12:20:22 internimage_b_1k_224] (main.py 575): INFO [Epoch:169] * Acc@1 81.316 Acc@5 95.971
[2025-01-19 12:20:22 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.3%
[2025-01-19 12:20:22 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 12:20:24 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][220/312]	eta 0:01:08 lr 0.001614	time 0.7201 (0.7499)	model_time 0.7196 (0.7432)	loss 3.0134 (3.1142)	grad_norm 2.5939 (1.6695/0.7486)	mem 34604MB
[2025-01-19 12:20:26 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 12:20:26 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.32%
[2025-01-19 12:20:31 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][230/312]	eta 0:01:01 lr 0.001614	time 0.7088 (0.7486)	model_time 0.7085 (0.7422)	loss 3.5446 (3.1183)	grad_norm 2.3380 (1.6946/0.7691)	mem 34604MB
[2025-01-19 12:20:33 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.749 (7.749)	Loss 0.6657 (0.6657)	Acc@1 84.424 (84.424)	Acc@5 97.705 (97.705)	Mem 34602MB
[2025-01-19 12:20:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.974)	Loss 0.9500 (0.7949)	Acc@1 77.637 (81.885)	Acc@5 94.727 (96.138)	Mem 34602MB
[2025-01-19 12:20:37 internimage_b_1k_224] (main.py 575): INFO [Epoch:169] * Acc@1 81.738 Acc@5 96.193
[2025-01-19 12:20:37 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.7%
[2025-01-19 12:20:37 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:20:38 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][240/312]	eta 0:00:53 lr 0.001613	time 0.7253 (0.7477)	model_time 0.7252 (0.7416)	loss 3.2710 (3.1134)	grad_norm 2.5419 (1.6897/0.7598)	mem 34604MB
[2025-01-19 12:20:41 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:20:41 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.74%
[2025-01-19 12:20:43 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][0/312]	eta 0:10:45 lr 0.001608	time 2.0691 (2.0691)	model_time 0.7484 (0.7484)	loss 2.0519 (2.0519)	grad_norm 0.9669 (0.9669/0.0000)	mem 34602MB
[2025-01-19 12:20:45 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][250/312]	eta 0:00:46 lr 0.001612	time 0.7202 (0.7470)	model_time 0.7200 (0.7410)	loss 3.7910 (3.1245)	grad_norm 1.6839 (1.6844/0.7511)	mem 34604MB
[2025-01-19 12:20:50 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][10/312]	eta 0:04:19 lr 0.001608	time 0.7168 (0.8576)	model_time 0.7164 (0.7372)	loss 3.2141 (3.0091)	grad_norm 1.5276 (1.6382/0.4294)	mem 34602MB
[2025-01-19 12:20:53 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][260/312]	eta 0:00:38 lr 0.001612	time 0.7260 (0.7465)	model_time 0.7258 (0.7408)	loss 3.4938 (3.1186)	grad_norm 2.5289 (1.6897/0.7529)	mem 34604MB
[2025-01-19 12:20:57 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][20/312]	eta 0:03:53 lr 0.001607	time 0.7323 (0.7990)	model_time 0.7319 (0.7357)	loss 3.3013 (3.1003)	grad_norm 1.9566 (1.5358/0.4557)	mem 34602MB
[2025-01-19 12:21:00 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][270/312]	eta 0:00:31 lr 0.001611	time 0.8048 (0.7473)	model_time 0.8043 (0.7418)	loss 2.9277 (3.1197)	grad_norm 3.3240 (1.7058/0.7686)	mem 34604MB
[2025-01-19 12:21:05 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][30/312]	eta 0:03:39 lr 0.001606	time 0.7189 (0.7784)	model_time 0.7187 (0.7355)	loss 2.1535 (3.0581)	grad_norm 2.0710 (1.6243/0.4624)	mem 34602MB
[2025-01-19 12:21:09 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][280/312]	eta 0:00:23 lr 0.001610	time 0.8644 (0.7495)	model_time 0.8640 (0.7442)	loss 3.0270 (3.1286)	grad_norm 1.8593 (1.7192/0.7734)	mem 34604MB
[2025-01-19 12:21:12 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][40/312]	eta 0:03:30 lr 0.001606	time 0.7312 (0.7753)	model_time 0.7310 (0.7428)	loss 3.5800 (3.0559)	grad_norm 1.4775 (1.8304/0.7168)	mem 34602MB
[2025-01-19 12:21:16 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][290/312]	eta 0:00:16 lr 0.001610	time 0.7263 (0.7495)	model_time 0.7261 (0.7443)	loss 4.0120 (3.1321)	grad_norm 2.2448 (1.7196/0.7693)	mem 34604MB
[2025-01-19 12:21:20 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][50/312]	eta 0:03:21 lr 0.001605	time 0.7221 (0.7705)	model_time 0.7217 (0.7443)	loss 2.0642 (3.0543)	grad_norm 1.9861 (1.8146/0.6765)	mem 34602MB
[2025-01-19 12:21:23 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][300/312]	eta 0:00:08 lr 0.001609	time 0.7135 (0.7489)	model_time 0.7134 (0.7439)	loss 2.6006 (3.1312)	grad_norm 1.5707 (1.7122/0.7637)	mem 34604MB
[2025-01-19 12:21:27 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][60/312]	eta 0:03:12 lr 0.001604	time 0.7292 (0.7656)	model_time 0.7290 (0.7435)	loss 3.2388 (3.0693)	grad_norm 1.2048 (1.7199/0.6644)	mem 34602MB
[2025-01-19 12:21:31 internimage_b_1k_224] (main.py 510): INFO Train: [169/300][310/312]	eta 0:00:01 lr 0.001608	time 0.7137 (0.7479)	model_time 0.7136 (0.7431)	loss 3.2057 (3.1221)	grad_norm 1.4104 (1.7116/0.7392)	mem 34604MB
[2025-01-19 12:21:31 internimage_b_1k_224] (main.py 519): INFO EPOCH 169 training takes 0:03:53
[2025-01-19 12:21:31 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_169.pth saving......
[2025-01-19 12:21:35 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_169.pth saved !!!
[2025-01-19 12:21:35 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][70/312]	eta 0:03:05 lr 0.001604	time 0.7244 (0.7649)	model_time 0.7240 (0.7460)	loss 2.8184 (3.0659)	grad_norm 1.1181 (1.6986/0.6806)	mem 34602MB
[2025-01-19 12:21:42 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.281 (7.281)	Loss 0.7915 (0.7915)	Acc@1 84.204 (84.204)	Acc@5 97.559 (97.559)	Mem 34604MB
[2025-01-19 12:21:42 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][80/312]	eta 0:02:57 lr 0.001603	time 0.7302 (0.7643)	model_time 0.7298 (0.7477)	loss 3.2596 (3.0939)	grad_norm 2.2028 (1.7087/0.6656)	mem 34602MB
[2025-01-19 12:21:45 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.956)	Loss 1.0415 (0.8992)	Acc@1 77.148 (81.525)	Acc@5 94.556 (96.009)	Mem 34604MB
[2025-01-19 12:21:45 internimage_b_1k_224] (main.py 575): INFO [Epoch:169] * Acc@1 81.430 Acc@5 96.019
[2025-01-19 12:21:45 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.4%
[2025-01-19 12:21:45 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.51%
[2025-01-19 12:21:50 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][90/312]	eta 0:02:49 lr 0.001602	time 0.7176 (0.7636)	model_time 0.7175 (0.7487)	loss 3.3972 (3.0808)	grad_norm 0.8523 (1.7121/0.6685)	mem 34602MB
[2025-01-19 12:21:54 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.156 (9.156)	Loss 0.6653 (0.6653)	Acc@1 84.814 (84.814)	Acc@5 97.729 (97.729)	Mem 34604MB
[2025-01-19 12:21:57 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][100/312]	eta 0:02:41 lr 0.001602	time 0.7157 (0.7608)	model_time 0.7155 (0.7473)	loss 3.6564 (3.0861)	grad_norm 1.4697 (1.6921/0.6526)	mem 34602MB
[2025-01-19 12:21:59 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (1.256)	Loss 0.9497 (0.7944)	Acc@1 77.588 (81.985)	Acc@5 94.751 (96.180)	Mem 34604MB
[2025-01-19 12:21:59 internimage_b_1k_224] (main.py 575): INFO [Epoch:169] * Acc@1 81.858 Acc@5 96.223
[2025-01-19 12:21:59 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.9%
[2025-01-19 12:21:59 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:22:03 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:22:03 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.86%
[2025-01-19 12:22:05 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][110/312]	eta 0:02:33 lr 0.001601	time 0.7436 (0.7595)	model_time 0.7432 (0.7472)	loss 2.6991 (3.0931)	grad_norm 1.5430 (1.7137/0.6896)	mem 34602MB
[2025-01-19 12:22:05 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][0/312]	eta 0:10:51 lr 0.001608	time 2.0894 (2.0894)	model_time 0.7688 (0.7688)	loss 2.8646 (2.8646)	grad_norm 1.1617 (1.1617/0.0000)	mem 34604MB
[2025-01-19 12:22:12 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][120/312]	eta 0:02:25 lr 0.001601	time 0.7314 (0.7573)	model_time 0.7309 (0.7460)	loss 4.0965 (3.1180)	grad_norm 1.1922 (1.7279/0.6882)	mem 34602MB
[2025-01-19 12:22:12 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][10/312]	eta 0:04:17 lr 0.001608	time 0.7586 (0.8532)	model_time 0.7581 (0.7327)	loss 2.5809 (2.9216)	grad_norm 2.5169 (1.8912/0.8461)	mem 34604MB
[2025-01-19 12:22:20 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][130/312]	eta 0:02:17 lr 0.001600	time 0.7191 (0.7558)	model_time 0.7190 (0.7453)	loss 3.6902 (3.1031)	grad_norm 2.0754 (1.7409/0.6731)	mem 34602MB
[2025-01-19 12:22:20 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][20/312]	eta 0:03:51 lr 0.001607	time 0.7372 (0.7926)	model_time 0.7371 (0.7293)	loss 3.3835 (3.1192)	grad_norm 2.9838 (1.7859/0.8449)	mem 34604MB
[2025-01-19 12:22:27 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][140/312]	eta 0:02:09 lr 0.001599	time 0.7594 (0.7537)	model_time 0.7592 (0.7440)	loss 3.3766 (3.0857)	grad_norm 1.2801 (1.7314/0.6716)	mem 34602MB
[2025-01-19 12:22:27 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][30/312]	eta 0:03:37 lr 0.001606	time 0.7333 (0.7724)	model_time 0.7329 (0.7294)	loss 3.0627 (3.1636)	grad_norm 0.7819 (1.6589/0.7841)	mem 34604MB
[2025-01-19 12:22:34 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][150/312]	eta 0:02:01 lr 0.001599	time 0.7202 (0.7522)	model_time 0.7201 (0.7431)	loss 3.1832 (3.0937)	grad_norm 1.4635 (1.7260/0.6696)	mem 34602MB
[2025-01-19 12:22:34 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][40/312]	eta 0:03:27 lr 0.001606	time 0.7283 (0.7611)	model_time 0.7280 (0.7284)	loss 2.4961 (3.1746)	grad_norm 0.8804 (1.5389/0.7257)	mem 34604MB
[2025-01-19 12:22:41 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][50/312]	eta 0:03:17 lr 0.001605	time 0.7218 (0.7540)	model_time 0.7216 (0.7276)	loss 3.6237 (3.1390)	grad_norm 1.0304 (1.4658/0.6739)	mem 34604MB
[2025-01-19 12:22:42 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][160/312]	eta 0:01:54 lr 0.001598	time 0.7213 (0.7519)	model_time 0.7208 (0.7434)	loss 2.9741 (3.0891)	grad_norm 0.8056 (1.7067/0.6676)	mem 34602MB
[2025-01-19 12:22:49 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][60/312]	eta 0:03:09 lr 0.001604	time 0.7247 (0.7510)	model_time 0.7242 (0.7289)	loss 2.7080 (3.1033)	grad_norm 0.5946 (1.4182/0.6400)	mem 34604MB
[2025-01-19 12:22:49 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][170/312]	eta 0:01:46 lr 0.001597	time 0.7416 (0.7517)	model_time 0.7415 (0.7436)	loss 1.9899 (3.0743)	grad_norm 1.0293 (1.6729/0.6646)	mem 34602MB
[2025-01-19 12:22:56 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][70/312]	eta 0:03:01 lr 0.001604	time 0.8472 (0.7491)	model_time 0.8469 (0.7300)	loss 3.4442 (3.1382)	grad_norm 1.1481 (1.4054/0.6138)	mem 34604MB
[2025-01-19 12:22:56 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][180/312]	eta 0:01:39 lr 0.001597	time 0.7166 (0.7510)	model_time 0.7165 (0.7433)	loss 3.5105 (3.0773)	grad_norm 1.7480 (1.6556/0.6554)	mem 34602MB
[2025-01-19 12:23:04 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][80/312]	eta 0:02:54 lr 0.001603	time 0.7208 (0.7509)	model_time 0.7206 (0.7342)	loss 3.1738 (3.1457)	grad_norm 1.0801 (1.3784/0.6051)	mem 34604MB
[2025-01-19 12:23:04 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][190/312]	eta 0:01:31 lr 0.001596	time 0.7159 (0.7511)	model_time 0.7158 (0.7438)	loss 2.9710 (3.0790)	grad_norm 0.8253 (1.6538/0.6594)	mem 34602MB
[2025-01-19 12:23:12 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][200/312]	eta 0:01:24 lr 0.001595	time 0.7261 (0.7519)	model_time 0.7257 (0.7450)	loss 2.0754 (3.0724)	grad_norm 1.1550 (1.6655/0.6551)	mem 34602MB
[2025-01-19 12:23:12 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][90/312]	eta 0:02:47 lr 0.001602	time 0.8203 (0.7567)	model_time 0.8201 (0.7418)	loss 2.6902 (3.1472)	grad_norm 2.3471 (1.4149/0.6082)	mem 34604MB
[2025-01-19 12:23:19 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][210/312]	eta 0:01:16 lr 0.001595	time 0.7207 (0.7527)	model_time 0.7202 (0.7460)	loss 2.0885 (3.0709)	grad_norm 1.4828 (1.6570/0.6539)	mem 34602MB
[2025-01-19 12:23:19 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][100/312]	eta 0:02:40 lr 0.001602	time 0.7185 (0.7565)	model_time 0.7183 (0.7431)	loss 3.5367 (3.1496)	grad_norm 1.2571 (1.4383/0.6065)	mem 34604MB
[2025-01-19 12:23:27 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][220/312]	eta 0:01:09 lr 0.001594	time 0.7225 (0.7520)	model_time 0.7224 (0.7457)	loss 3.1259 (3.0671)	grad_norm 1.3103 (1.6562/0.6610)	mem 34602MB
[2025-01-19 12:23:27 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][110/312]	eta 0:02:32 lr 0.001601	time 0.7166 (0.7547)	model_time 0.7164 (0.7424)	loss 2.9871 (3.1555)	grad_norm 1.2746 (1.4838/0.6391)	mem 34604MB
[2025-01-19 12:23:34 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][120/312]	eta 0:02:24 lr 0.001601	time 0.7241 (0.7524)	model_time 0.7239 (0.7411)	loss 2.7953 (3.1681)	grad_norm 2.9845 (1.5408/0.6823)	mem 34604MB
[2025-01-19 12:23:34 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][230/312]	eta 0:01:01 lr 0.001593	time 0.7619 (0.7516)	model_time 0.7618 (0.7455)	loss 3.6251 (3.0563)	grad_norm 2.9291 (1.6577/0.6576)	mem 34602MB
[2025-01-19 12:23:41 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][130/312]	eta 0:02:16 lr 0.001600	time 0.7166 (0.7501)	model_time 0.7163 (0.7396)	loss 2.4190 (3.1775)	grad_norm 4.5753 (1.5700/0.7260)	mem 34604MB
[2025-01-19 12:23:42 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][240/312]	eta 0:00:54 lr 0.001593	time 0.7249 (0.7515)	model_time 0.7247 (0.7456)	loss 3.8486 (3.0664)	grad_norm 1.6028 (1.6448/0.6507)	mem 34602MB
[2025-01-19 12:23:49 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][140/312]	eta 0:02:08 lr 0.001599	time 0.7158 (0.7482)	model_time 0.7156 (0.7384)	loss 3.4089 (3.1758)	grad_norm 1.7543 (1.5755/0.7165)	mem 34604MB
[2025-01-19 12:23:49 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][250/312]	eta 0:00:46 lr 0.001592	time 0.7339 (0.7511)	model_time 0.7335 (0.7454)	loss 2.3159 (3.0638)	grad_norm 0.7086 (1.6258/0.6455)	mem 34602MB
[2025-01-19 12:23:56 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][150/312]	eta 0:02:00 lr 0.001599	time 0.7184 (0.7466)	model_time 0.7178 (0.7375)	loss 3.8042 (3.1742)	grad_norm 1.5607 (1.5645/0.7024)	mem 34604MB
[2025-01-19 12:23:56 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][260/312]	eta 0:00:39 lr 0.001591	time 0.7215 (0.7502)	model_time 0.7211 (0.7448)	loss 2.6625 (3.0653)	grad_norm 2.6062 (1.6361/0.6426)	mem 34602MB
[2025-01-19 12:24:03 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][160/312]	eta 0:01:53 lr 0.001598	time 0.7204 (0.7453)	model_time 0.7203 (0.7368)	loss 2.0897 (3.1572)	grad_norm 1.7098 (1.5694/0.6908)	mem 34604MB
[2025-01-19 12:24:04 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][270/312]	eta 0:00:31 lr 0.001591	time 0.7313 (0.7496)	model_time 0.7311 (0.7443)	loss 2.7605 (3.0643)	grad_norm 1.5786 (1.6336/0.6331)	mem 34602MB
[2025-01-19 12:24:10 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][170/312]	eta 0:01:45 lr 0.001597	time 0.7148 (0.7439)	model_time 0.7146 (0.7358)	loss 3.7386 (3.1717)	grad_norm 1.5446 (1.5623/0.6732)	mem 34604MB
[2025-01-19 12:24:11 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][280/312]	eta 0:00:23 lr 0.001590	time 0.7517 (0.7496)	model_time 0.7515 (0.7445)	loss 2.2230 (3.0599)	grad_norm 1.4753 (1.6242/0.6309)	mem 34602MB
[2025-01-19 12:24:18 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][180/312]	eta 0:01:38 lr 0.001597	time 0.7227 (0.7438)	model_time 0.7223 (0.7362)	loss 3.6243 (3.1753)	grad_norm 1.5736 (1.5778/0.6658)	mem 34604MB
[2025-01-19 12:24:19 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][290/312]	eta 0:00:16 lr 0.001590	time 0.7148 (0.7497)	model_time 0.7147 (0.7448)	loss 3.4369 (3.0629)	grad_norm 1.4101 (1.6114/0.6305)	mem 34602MB
[2025-01-19 12:24:25 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][190/312]	eta 0:01:30 lr 0.001596	time 0.8428 (0.7436)	model_time 0.8424 (0.7363)	loss 3.2343 (3.1682)	grad_norm 1.9282 (1.6116/0.6940)	mem 34604MB
[2025-01-19 12:24:26 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][300/312]	eta 0:00:08 lr 0.001589	time 0.7180 (0.7494)	model_time 0.7179 (0.7447)	loss 3.1662 (3.0664)	grad_norm 3.0685 (1.6329/0.6410)	mem 34602MB
[2025-01-19 12:24:33 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][200/312]	eta 0:01:23 lr 0.001595	time 0.8109 (0.7440)	model_time 0.8107 (0.7371)	loss 2.4221 (3.1743)	grad_norm 2.0796 (1.6140/0.6911)	mem 34604MB
[2025-01-19 12:24:34 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][310/312]	eta 0:00:01 lr 0.001588	time 0.7897 (0.7496)	model_time 0.7896 (0.7450)	loss 3.2155 (3.0678)	grad_norm 1.4271 (1.6170/0.6424)	mem 34602MB
[2025-01-19 12:24:34 internimage_b_1k_224] (main.py 519): INFO EPOCH 170 training takes 0:03:53
[2025-01-19 12:24:34 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_170.pth saving......
[2025-01-19 12:24:38 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_170.pth saved !!!
[2025-01-19 12:24:41 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][210/312]	eta 0:01:16 lr 0.001595	time 0.8024 (0.7465)	model_time 0.8022 (0.7399)	loss 2.1435 (3.1676)	grad_norm 1.0433 (1.6082/0.6898)	mem 34604MB
[2025-01-19 12:24:45 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.670 (7.670)	Loss 0.7709 (0.7709)	Acc@1 83.765 (83.765)	Acc@5 97.168 (97.168)	Mem 34602MB
[2025-01-19 12:24:48 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][220/312]	eta 0:01:08 lr 0.001594	time 0.7166 (0.7466)	model_time 0.7164 (0.7403)	loss 3.1864 (3.1705)	grad_norm 1.4189 (1.6032/0.6879)	mem 34604MB
[2025-01-19 12:24:49 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.983)	Loss 1.0284 (0.8968)	Acc@1 77.368 (81.479)	Acc@5 94.946 (95.994)	Mem 34602MB
[2025-01-19 12:24:49 internimage_b_1k_224] (main.py 575): INFO [Epoch:170] * Acc@1 81.332 Acc@5 96.029
[2025-01-19 12:24:49 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.3%
[2025-01-19 12:24:49 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 12:24:52 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 12:24:52 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.33%
[2025-01-19 12:24:55 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][230/312]	eta 0:01:01 lr 0.001593	time 0.7248 (0.7461)	model_time 0.7246 (0.7400)	loss 3.3312 (3.1637)	grad_norm 1.9378 (1.6100/0.6820)	mem 34604MB
[2025-01-19 12:25:00 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.453 (7.453)	Loss 0.6667 (0.6667)	Acc@1 84.448 (84.448)	Acc@5 97.705 (97.705)	Mem 34602MB
[2025-01-19 12:25:03 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][240/312]	eta 0:00:53 lr 0.001593	time 0.7225 (0.7454)	model_time 0.7224 (0.7395)	loss 1.8658 (3.1467)	grad_norm 1.7458 (1.6220/0.6806)	mem 34604MB
[2025-01-19 12:25:03 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.966)	Loss 0.9498 (0.7952)	Acc@1 77.734 (81.911)	Acc@5 94.800 (96.149)	Mem 34602MB
[2025-01-19 12:25:03 internimage_b_1k_224] (main.py 575): INFO [Epoch:170] * Acc@1 81.768 Acc@5 96.205
[2025-01-19 12:25:03 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.8%
[2025-01-19 12:25:03 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:25:07 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:25:07 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.77%
[2025-01-19 12:25:09 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][0/312]	eta 0:11:39 lr 0.001588	time 2.2429 (2.2429)	model_time 0.7504 (0.7504)	loss 2.9478 (2.9478)	grad_norm 1.3296 (1.3296/0.0000)	mem 34602MB
[2025-01-19 12:25:10 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][250/312]	eta 0:00:46 lr 0.001592	time 0.7183 (0.7446)	model_time 0.7181 (0.7389)	loss 3.2052 (3.1487)	grad_norm 1.4102 (1.6208/0.6789)	mem 34604MB
[2025-01-19 12:25:17 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][10/312]	eta 0:04:30 lr 0.001587	time 0.7166 (0.8951)	model_time 0.7164 (0.7591)	loss 3.2995 (3.2107)	grad_norm 0.9649 (1.0633/0.1869)	mem 34602MB
[2025-01-19 12:25:17 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][260/312]	eta 0:00:38 lr 0.001591	time 0.7287 (0.7438)	model_time 0.7286 (0.7384)	loss 2.5026 (3.1385)	grad_norm 1.6418 (1.6176/0.6701)	mem 34604MB
[2025-01-19 12:25:24 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][20/312]	eta 0:04:01 lr 0.001587	time 0.7398 (0.8286)	model_time 0.7393 (0.7572)	loss 3.3928 (3.2046)	grad_norm 0.9598 (1.2586/0.4225)	mem 34602MB
[2025-01-19 12:25:24 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][270/312]	eta 0:00:31 lr 0.001591	time 0.7144 (0.7432)	model_time 0.7143 (0.7380)	loss 2.5123 (3.1347)	grad_norm 3.4216 (1.6200/0.6703)	mem 34604MB
[2025-01-19 12:25:32 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][30/312]	eta 0:03:45 lr 0.001586	time 0.7154 (0.7998)	model_time 0.7152 (0.7514)	loss 2.5238 (3.1080)	grad_norm 2.9083 (1.5760/0.9701)	mem 34602MB
[2025-01-19 12:25:32 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][280/312]	eta 0:00:23 lr 0.001590	time 0.7256 (0.7424)	model_time 0.7254 (0.7373)	loss 3.3272 (3.1384)	grad_norm 1.3801 (1.6226/0.6635)	mem 34604MB
[2025-01-19 12:25:39 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][290/312]	eta 0:00:16 lr 0.001590	time 0.7283 (0.7418)	model_time 0.7282 (0.7369)	loss 3.1084 (3.1360)	grad_norm 1.3247 (1.6243/0.6607)	mem 34604MB
[2025-01-19 12:25:39 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][40/312]	eta 0:03:33 lr 0.001585	time 0.7199 (0.7866)	model_time 0.7195 (0.7499)	loss 3.0831 (3.0833)	grad_norm 1.1293 (1.6564/0.9523)	mem 34602MB
[2025-01-19 12:25:46 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][300/312]	eta 0:00:08 lr 0.001589	time 0.7104 (0.7416)	model_time 0.7103 (0.7369)	loss 3.7675 (3.1401)	grad_norm 2.7537 (1.6273/0.6558)	mem 34604MB
[2025-01-19 12:25:46 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][50/312]	eta 0:03:23 lr 0.001585	time 0.7208 (0.7779)	model_time 0.7202 (0.7483)	loss 2.5705 (3.0950)	grad_norm 1.2294 (1.6641/0.9305)	mem 34602MB
[2025-01-19 12:25:54 internimage_b_1k_224] (main.py 510): INFO Train: [170/300][310/312]	eta 0:00:01 lr 0.001588	time 0.7895 (0.7411)	model_time 0.7894 (0.7365)	loss 2.8034 (3.1409)	grad_norm 1.9474 (1.6235/0.6547)	mem 34604MB
[2025-01-19 12:25:54 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][60/312]	eta 0:03:14 lr 0.001584	time 0.7513 (0.7712)	model_time 0.7512 (0.7464)	loss 3.1316 (3.1033)	grad_norm 1.4190 (1.6334/0.8654)	mem 34602MB
[2025-01-19 12:25:54 internimage_b_1k_224] (main.py 519): INFO EPOCH 170 training takes 0:03:51
[2025-01-19 12:25:54 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_170.pth saving......
[2025-01-19 12:25:57 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_170.pth saved !!!
[2025-01-19 12:26:01 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][70/312]	eta 0:03:05 lr 0.001584	time 0.7292 (0.7652)	model_time 0.7290 (0.7438)	loss 3.0845 (3.0979)	grad_norm 0.7669 (1.6178/0.8235)	mem 34602MB
[2025-01-19 12:26:05 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.619 (7.619)	Loss 0.7834 (0.7834)	Acc@1 84.009 (84.009)	Acc@5 97.363 (97.363)	Mem 34604MB
[2025-01-19 12:26:08 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.968)	Loss 1.0225 (0.8841)	Acc@1 77.832 (81.594)	Acc@5 94.531 (95.934)	Mem 34604MB
[2025-01-19 12:26:08 internimage_b_1k_224] (main.py 575): INFO [Epoch:170] * Acc@1 81.430 Acc@5 95.949
[2025-01-19 12:26:08 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.4%
[2025-01-19 12:26:08 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.51%
[2025-01-19 12:26:08 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][80/312]	eta 0:02:56 lr 0.001583	time 0.7462 (0.7617)	model_time 0.7461 (0.7430)	loss 3.0699 (3.0944)	grad_norm 1.0475 (1.7121/0.8517)	mem 34602MB
[2025-01-19 12:26:16 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][90/312]	eta 0:02:48 lr 0.001582	time 0.7247 (0.7603)	model_time 0.7243 (0.7435)	loss 3.8438 (3.1049)	grad_norm 2.3475 (1.6630/0.8292)	mem 34602MB
[2025-01-19 12:26:18 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.301 (9.301)	Loss 0.6661 (0.6661)	Acc@1 84.814 (84.814)	Acc@5 97.778 (97.778)	Mem 34604MB
[2025-01-19 12:26:22 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (1.248)	Loss 0.9498 (0.7947)	Acc@1 77.588 (82.002)	Acc@5 94.727 (96.169)	Mem 34604MB
[2025-01-19 12:26:22 internimage_b_1k_224] (main.py 575): INFO [Epoch:170] * Acc@1 81.884 Acc@5 96.223
[2025-01-19 12:26:22 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.9%
[2025-01-19 12:26:22 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:26:23 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][100/312]	eta 0:02:40 lr 0.001582	time 0.7187 (0.7592)	model_time 0.7183 (0.7440)	loss 3.2927 (3.1090)	grad_norm 1.3386 (1.6770/0.8450)	mem 34602MB
[2025-01-19 12:26:26 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:26:26 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.88%
[2025-01-19 12:26:28 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][0/312]	eta 0:11:38 lr 0.001588	time 2.2392 (2.2392)	model_time 0.7486 (0.7486)	loss 3.6244 (3.6244)	grad_norm 1.7537 (1.7537/0.0000)	mem 34604MB
[2025-01-19 12:26:31 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][110/312]	eta 0:02:32 lr 0.001581	time 0.7168 (0.7574)	model_time 0.7164 (0.7436)	loss 3.9494 (3.0821)	grad_norm 2.6456 (1.7154/0.8295)	mem 34602MB
[2025-01-19 12:26:36 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][10/312]	eta 0:04:34 lr 0.001587	time 0.8076 (0.9085)	model_time 0.8074 (0.7728)	loss 3.5128 (3.2959)	grad_norm 1.6808 (1.7926/0.6769)	mem 34604MB
[2025-01-19 12:26:38 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][120/312]	eta 0:02:25 lr 0.001580	time 0.7228 (0.7576)	model_time 0.7226 (0.7449)	loss 3.0374 (3.0861)	grad_norm 1.7053 (1.7089/0.8323)	mem 34602MB
[2025-01-19 12:26:44 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][20/312]	eta 0:04:12 lr 0.001587	time 0.9771 (0.8645)	model_time 0.9769 (0.7933)	loss 3.4836 (3.2876)	grad_norm 1.5685 (1.7837/0.5975)	mem 34604MB
[2025-01-19 12:26:46 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][130/312]	eta 0:02:17 lr 0.001580	time 0.7154 (0.7569)	model_time 0.7150 (0.7451)	loss 2.6995 (3.0722)	grad_norm 0.8546 (1.7034/0.8167)	mem 34602MB
[2025-01-19 12:26:51 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][30/312]	eta 0:03:53 lr 0.001586	time 0.8094 (0.8296)	model_time 0.8089 (0.7812)	loss 3.9320 (3.2839)	grad_norm 0.9341 (1.6282/0.5794)	mem 34604MB
[2025-01-19 12:26:54 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][140/312]	eta 0:02:10 lr 0.001579	time 0.7436 (0.7580)	model_time 0.7431 (0.7470)	loss 3.9640 (3.0896)	grad_norm 1.3039 (1.7103/0.8008)	mem 34602MB
[2025-01-19 12:26:59 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][40/312]	eta 0:03:39 lr 0.001585	time 0.7158 (0.8054)	model_time 0.7157 (0.7688)	loss 2.7438 (3.2466)	grad_norm 2.9056 (1.7337/0.6221)	mem 34604MB
[2025-01-19 12:27:01 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][150/312]	eta 0:02:02 lr 0.001578	time 0.7301 (0.7563)	model_time 0.7294 (0.7461)	loss 3.0411 (3.0929)	grad_norm 0.9981 (1.7141/0.8015)	mem 34602MB
[2025-01-19 12:27:06 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][50/312]	eta 0:03:26 lr 0.001585	time 0.7170 (0.7891)	model_time 0.7168 (0.7596)	loss 3.5462 (3.2299)	grad_norm 1.9395 (1.6801/0.5941)	mem 34604MB
[2025-01-19 12:27:08 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][160/312]	eta 0:01:54 lr 0.001578	time 0.7170 (0.7554)	model_time 0.7166 (0.7458)	loss 3.3650 (3.0973)	grad_norm 3.0612 (1.7381/0.8126)	mem 34602MB
[2025-01-19 12:27:13 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][60/312]	eta 0:03:16 lr 0.001584	time 0.7423 (0.7787)	model_time 0.7418 (0.7539)	loss 2.5578 (3.2209)	grad_norm 2.4516 (1.7293/0.6092)	mem 34604MB
[2025-01-19 12:27:16 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][170/312]	eta 0:01:47 lr 0.001577	time 0.7423 (0.7544)	model_time 0.7422 (0.7453)	loss 3.7186 (3.1066)	grad_norm 2.1387 (1.7412/0.8010)	mem 34602MB
[2025-01-19 12:27:20 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][70/312]	eta 0:03:06 lr 0.001584	time 0.7183 (0.7716)	model_time 0.7178 (0.7503)	loss 3.0654 (3.1872)	grad_norm 1.6566 (1.7437/0.5980)	mem 34604MB
[2025-01-19 12:27:23 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][180/312]	eta 0:01:39 lr 0.001576	time 0.7168 (0.7533)	model_time 0.7163 (0.7447)	loss 3.4077 (3.1151)	grad_norm 2.3670 (1.7318/0.8015)	mem 34602MB
[2025-01-19 12:27:28 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][80/312]	eta 0:02:57 lr 0.001583	time 0.7156 (0.7654)	model_time 0.7154 (0.7467)	loss 3.2963 (3.1733)	grad_norm 1.4226 (1.7312/0.6026)	mem 34604MB
[2025-01-19 12:27:30 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][190/312]	eta 0:01:31 lr 0.001576	time 0.7332 (0.7518)	model_time 0.7330 (0.7436)	loss 2.4498 (3.1050)	grad_norm 2.4816 (1.7330/0.7883)	mem 34602MB
[2025-01-19 12:27:35 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][90/312]	eta 0:02:49 lr 0.001582	time 0.7230 (0.7614)	model_time 0.7226 (0.7447)	loss 3.2085 (3.1746)	grad_norm 0.8473 (1.7416/0.6610)	mem 34604MB
[2025-01-19 12:27:38 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][200/312]	eta 0:01:24 lr 0.001575	time 0.7208 (0.7509)	model_time 0.7206 (0.7431)	loss 3.7322 (3.1093)	grad_norm 4.2583 (1.7765/0.8283)	mem 34602MB
[2025-01-19 12:27:42 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][100/312]	eta 0:02:40 lr 0.001582	time 0.7279 (0.7582)	model_time 0.7277 (0.7431)	loss 3.4141 (3.1769)	grad_norm 1.3355 (1.7663/0.7013)	mem 34604MB
[2025-01-19 12:27:45 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][210/312]	eta 0:01:16 lr 0.001574	time 0.7177 (0.7511)	model_time 0.7176 (0.7437)	loss 3.5373 (3.1059)	grad_norm 2.1842 (1.7544/0.8181)	mem 34602MB
[2025-01-19 12:27:50 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][110/312]	eta 0:02:32 lr 0.001581	time 0.7178 (0.7554)	model_time 0.7173 (0.7416)	loss 3.5595 (3.1872)	grad_norm 1.6623 (1.7553/0.6783)	mem 34604MB
[2025-01-19 12:27:53 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][220/312]	eta 0:01:09 lr 0.001574	time 0.7161 (0.7508)	model_time 0.7156 (0.7437)	loss 2.9566 (3.1076)	grad_norm 1.3012 (1.7392/0.8063)	mem 34602MB
[2025-01-19 12:27:57 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][120/312]	eta 0:02:24 lr 0.001580	time 0.7165 (0.7538)	model_time 0.7163 (0.7411)	loss 3.2286 (3.1708)	grad_norm 1.3979 (1.7482/0.7214)	mem 34604MB
[2025-01-19 12:28:00 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][230/312]	eta 0:01:01 lr 0.001573	time 0.7333 (0.7507)	model_time 0.7332 (0.7439)	loss 2.6377 (3.1065)	grad_norm 1.2823 (1.7209/0.7948)	mem 34602MB
[2025-01-19 12:28:04 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][130/312]	eta 0:02:17 lr 0.001580	time 0.7162 (0.7537)	model_time 0.7161 (0.7419)	loss 2.1755 (3.1690)	grad_norm 2.1172 (1.7378/0.7338)	mem 34604MB
[2025-01-19 12:28:08 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][240/312]	eta 0:00:54 lr 0.001573	time 0.7163 (0.7506)	model_time 0.7161 (0.7441)	loss 3.3829 (3.1186)	grad_norm 1.2078 (1.7037/0.7838)	mem 34602MB
[2025-01-19 12:28:12 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][140/312]	eta 0:02:10 lr 0.001579	time 0.8115 (0.7570)	model_time 0.8113 (0.7461)	loss 2.1951 (3.1678)	grad_norm 2.1761 (1.7684/0.7297)	mem 34604MB
[2025-01-19 12:28:15 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][250/312]	eta 0:00:46 lr 0.001572	time 0.7165 (0.7514)	model_time 0.7163 (0.7451)	loss 3.7490 (3.1209)	grad_norm 1.5175 (1.6957/0.7741)	mem 34602MB
[2025-01-19 12:28:20 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][150/312]	eta 0:02:02 lr 0.001578	time 0.8100 (0.7563)	model_time 0.8098 (0.7460)	loss 2.3172 (3.1629)	grad_norm 0.7290 (1.7692/0.7359)	mem 34604MB
[2025-01-19 12:28:23 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][260/312]	eta 0:00:39 lr 0.001571	time 0.7166 (0.7515)	model_time 0.7162 (0.7454)	loss 2.8717 (3.1218)	grad_norm 2.1439 (1.7007/0.7744)	mem 34602MB
[2025-01-19 12:28:27 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][160/312]	eta 0:01:54 lr 0.001578	time 0.7251 (0.7550)	model_time 0.7249 (0.7453)	loss 3.2170 (3.1522)	grad_norm 1.9626 (1.7558/0.7241)	mem 34604MB
[2025-01-19 12:28:30 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][270/312]	eta 0:00:31 lr 0.001571	time 0.7155 (0.7509)	model_time 0.7153 (0.7450)	loss 3.3429 (3.1131)	grad_norm 1.5243 (1.6927/0.7653)	mem 34602MB
[2025-01-19 12:28:34 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][170/312]	eta 0:01:46 lr 0.001577	time 0.7245 (0.7532)	model_time 0.7244 (0.7441)	loss 3.1754 (3.1425)	grad_norm 1.4934 (1.7315/0.7153)	mem 34604MB
[2025-01-19 12:28:38 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][280/312]	eta 0:00:24 lr 0.001570	time 0.7167 (0.7505)	model_time 0.7166 (0.7449)	loss 3.2022 (3.1079)	grad_norm 0.9045 (1.6702/0.7618)	mem 34602MB
[2025-01-19 12:28:42 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][180/312]	eta 0:01:39 lr 0.001576	time 0.7276 (0.7516)	model_time 0.7271 (0.7430)	loss 2.2957 (3.1472)	grad_norm 1.2521 (1.7342/0.7126)	mem 34604MB
[2025-01-19 12:28:45 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][290/312]	eta 0:00:16 lr 0.001569	time 0.7244 (0.7501)	model_time 0.7242 (0.7446)	loss 3.2104 (3.0974)	grad_norm 2.8618 (1.6691/0.7594)	mem 34602MB
[2025-01-19 12:28:49 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][190/312]	eta 0:01:31 lr 0.001576	time 0.7242 (0.7503)	model_time 0.7237 (0.7421)	loss 3.4526 (3.1499)	grad_norm 1.1559 (1.7056/0.7072)	mem 34604MB
[2025-01-19 12:28:52 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][300/312]	eta 0:00:08 lr 0.001569	time 0.7128 (0.7497)	model_time 0.7127 (0.7444)	loss 3.3437 (3.0978)	grad_norm 3.8818 (1.6882/0.7890)	mem 34602MB
[2025-01-19 12:28:56 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][200/312]	eta 0:01:23 lr 0.001575	time 0.7238 (0.7488)	model_time 0.7237 (0.7410)	loss 3.5405 (3.1585)	grad_norm 2.9542 (1.7032/0.7058)	mem 34604MB
[2025-01-19 12:29:00 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][310/312]	eta 0:00:01 lr 0.001568	time 0.7158 (0.7487)	model_time 0.7157 (0.7436)	loss 2.3628 (3.0883)	grad_norm 1.4287 (1.7121/0.7931)	mem 34602MB
[2025-01-19 12:29:00 internimage_b_1k_224] (main.py 519): INFO EPOCH 171 training takes 0:03:53
[2025-01-19 12:29:00 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_171.pth saving......
[2025-01-19 12:29:04 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][210/312]	eta 0:01:16 lr 0.001574	time 0.7531 (0.7480)	model_time 0.7526 (0.7406)	loss 2.6967 (3.1452)	grad_norm 1.2631 (1.6972/0.6996)	mem 34604MB
[2025-01-19 12:29:04 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_171.pth saved !!!
[2025-01-19 12:29:11 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][220/312]	eta 0:01:08 lr 0.001574	time 0.7187 (0.7468)	model_time 0.7182 (0.7397)	loss 3.6078 (3.1440)	grad_norm 2.2059 (1.6972/0.6987)	mem 34604MB
[2025-01-19 12:29:12 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.764 (7.764)	Loss 0.7898 (0.7898)	Acc@1 83.960 (83.960)	Acc@5 97.314 (97.314)	Mem 34602MB
[2025-01-19 12:29:14 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.969)	Loss 1.0557 (0.9061)	Acc@1 77.661 (81.587)	Acc@5 94.800 (96.016)	Mem 34602MB
[2025-01-19 12:29:15 internimage_b_1k_224] (main.py 575): INFO [Epoch:171] * Acc@1 81.424 Acc@5 96.025
[2025-01-19 12:29:15 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.4%
[2025-01-19 12:29:15 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 12:29:18 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 12:29:18 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.42%
[2025-01-19 12:29:18 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][230/312]	eta 0:01:01 lr 0.001573	time 0.7182 (0.7459)	model_time 0.7180 (0.7390)	loss 3.3685 (3.1570)	grad_norm 1.1401 (1.6964/0.6921)	mem 34604MB
[2025-01-19 12:29:25 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][240/312]	eta 0:00:53 lr 0.001573	time 0.7229 (0.7450)	model_time 0.7225 (0.7384)	loss 1.9757 (3.1482)	grad_norm 1.7658 (1.6732/0.6891)	mem 34604MB
[2025-01-19 12:29:26 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.759 (7.759)	Loss 0.6678 (0.6678)	Acc@1 84.473 (84.473)	Acc@5 97.729 (97.729)	Mem 34602MB
[2025-01-19 12:29:29 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.997)	Loss 0.9497 (0.7956)	Acc@1 77.808 (81.945)	Acc@5 94.800 (96.174)	Mem 34602MB
[2025-01-19 12:29:29 internimage_b_1k_224] (main.py 575): INFO [Epoch:171] * Acc@1 81.798 Acc@5 96.229
[2025-01-19 12:29:29 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.8%
[2025-01-19 12:29:29 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:29:33 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:29:33 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.80%
[2025-01-19 12:29:33 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][250/312]	eta 0:00:46 lr 0.001572	time 0.7159 (0.7460)	model_time 0.7155 (0.7397)	loss 3.7007 (3.1449)	grad_norm 2.1859 (1.6666/0.6870)	mem 34604MB
[2025-01-19 12:29:35 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][0/312]	eta 0:11:17 lr 0.001568	time 2.1701 (2.1701)	model_time 0.7446 (0.7446)	loss 3.2289 (3.2289)	grad_norm 2.0329 (2.0329/0.0000)	mem 34602MB
[2025-01-19 12:29:41 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][260/312]	eta 0:00:38 lr 0.001571	time 0.8156 (0.7483)	model_time 0.8154 (0.7422)	loss 3.4401 (3.1444)	grad_norm 1.8310 (1.6693/0.6798)	mem 34604MB
[2025-01-19 12:29:42 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][10/312]	eta 0:04:22 lr 0.001567	time 0.7279 (0.8676)	model_time 0.7278 (0.7377)	loss 3.2721 (2.9752)	grad_norm 1.6961 (1.7046/0.6727)	mem 34602MB
[2025-01-19 12:29:49 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][270/312]	eta 0:00:31 lr 0.001571	time 0.8149 (0.7486)	model_time 0.8145 (0.7427)	loss 3.1481 (3.1284)	grad_norm 1.1423 (1.6502/0.6774)	mem 34604MB
[2025-01-19 12:29:50 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][20/312]	eta 0:03:59 lr 0.001567	time 0.8024 (0.8197)	model_time 0.8019 (0.7516)	loss 3.4567 (3.0670)	grad_norm 1.0917 (1.4875/0.5722)	mem 34602MB
[2025-01-19 12:29:56 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][280/312]	eta 0:00:23 lr 0.001570	time 0.7344 (0.7481)	model_time 0.7340 (0.7424)	loss 3.5987 (3.1245)	grad_norm 1.3300 (1.6503/0.6705)	mem 34604MB
[2025-01-19 12:29:57 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][30/312]	eta 0:03:43 lr 0.001566	time 0.7331 (0.7941)	model_time 0.7329 (0.7478)	loss 2.8141 (3.0580)	grad_norm 2.3894 (1.5552/0.6463)	mem 34602MB
[2025-01-19 12:30:03 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][290/312]	eta 0:00:16 lr 0.001569	time 0.7255 (0.7472)	model_time 0.7253 (0.7417)	loss 3.3925 (3.1291)	grad_norm 1.7464 (1.6379/0.6654)	mem 34604MB
[2025-01-19 12:30:05 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][40/312]	eta 0:03:32 lr 0.001565	time 0.7221 (0.7815)	model_time 0.7216 (0.7465)	loss 3.5122 (3.1389)	grad_norm 0.7794 (1.7051/0.7781)	mem 34602MB
[2025-01-19 12:30:10 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][300/312]	eta 0:00:08 lr 0.001569	time 0.7138 (0.7464)	model_time 0.7137 (0.7410)	loss 2.9123 (3.1284)	grad_norm 2.0289 (1.6625/0.6991)	mem 34604MB
[2025-01-19 12:30:13 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][50/312]	eta 0:03:24 lr 0.001565	time 0.7168 (0.7801)	model_time 0.7166 (0.7519)	loss 2.8613 (3.1237)	grad_norm 1.8971 (1.6659/0.7259)	mem 34602MB
[2025-01-19 12:30:18 internimage_b_1k_224] (main.py 510): INFO Train: [171/300][310/312]	eta 0:00:01 lr 0.001568	time 0.7157 (0.7455)	model_time 0.7156 (0.7403)	loss 3.4998 (3.1258)	grad_norm 1.1540 (1.6740/0.7070)	mem 34604MB
[2025-01-19 12:30:18 internimage_b_1k_224] (main.py 519): INFO EPOCH 171 training takes 0:03:52
[2025-01-19 12:30:18 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_171.pth saving......
[2025-01-19 12:30:20 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][60/312]	eta 0:03:16 lr 0.001564	time 0.7206 (0.7779)	model_time 0.7204 (0.7542)	loss 3.1898 (3.1206)	grad_norm 1.2934 (1.6201/0.6813)	mem 34602MB
[2025-01-19 12:30:22 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_171.pth saved !!!
[2025-01-19 12:30:28 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][70/312]	eta 0:03:07 lr 0.001563	time 0.7231 (0.7742)	model_time 0.7227 (0.7538)	loss 2.9026 (3.0983)	grad_norm 3.2742 (1.6202/0.6920)	mem 34602MB
[2025-01-19 12:30:29 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.679 (7.679)	Loss 0.7523 (0.7523)	Acc@1 83.154 (83.154)	Acc@5 97.314 (97.314)	Mem 34604MB
[2025-01-19 12:30:32 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.974)	Loss 1.0301 (0.8695)	Acc@1 77.783 (81.479)	Acc@5 94.580 (95.916)	Mem 34604MB
[2025-01-19 12:30:32 internimage_b_1k_224] (main.py 575): INFO [Epoch:171] * Acc@1 81.308 Acc@5 95.899
[2025-01-19 12:30:32 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.3%
[2025-01-19 12:30:32 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.51%
[2025-01-19 12:30:35 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][80/312]	eta 0:02:58 lr 0.001563	time 0.7180 (0.7692)	model_time 0.7175 (0.7513)	loss 2.9848 (3.1132)	grad_norm 1.5278 (1.6067/0.6668)	mem 34602MB
[2025-01-19 12:30:42 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.262 (9.262)	Loss 0.6670 (0.6670)	Acc@1 84.912 (84.912)	Acc@5 97.778 (97.778)	Mem 34604MB
[2025-01-19 12:30:43 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][90/312]	eta 0:02:50 lr 0.001562	time 0.8129 (0.7668)	model_time 0.8128 (0.7508)	loss 3.6663 (3.1059)	grad_norm 2.4345 (1.6316/0.6681)	mem 34602MB
[2025-01-19 12:30:46 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (1.262)	Loss 0.9498 (0.7951)	Acc@1 77.734 (82.062)	Acc@5 94.824 (96.180)	Mem 34604MB
[2025-01-19 12:30:47 internimage_b_1k_224] (main.py 575): INFO [Epoch:171] * Acc@1 81.930 Acc@5 96.235
[2025-01-19 12:30:47 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.9%
[2025-01-19 12:30:47 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:30:50 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][100/312]	eta 0:02:41 lr 0.001561	time 0.8114 (0.7635)	model_time 0.8110 (0.7490)	loss 1.8547 (3.1023)	grad_norm 1.1033 (1.6572/0.6882)	mem 34602MB
[2025-01-19 12:30:50 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:30:50 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.93%
[2025-01-19 12:30:53 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][0/312]	eta 0:11:49 lr 0.001568	time 2.2746 (2.2746)	model_time 0.7566 (0.7566)	loss 2.6160 (2.6160)	grad_norm 1.7628 (1.7628/0.0000)	mem 34604MB
[2025-01-19 12:30:57 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][110/312]	eta 0:02:33 lr 0.001561	time 0.7273 (0.7612)	model_time 0.7272 (0.7480)	loss 2.8469 (3.0888)	grad_norm 1.9031 (1.6272/0.6745)	mem 34602MB
[2025-01-19 12:31:00 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][10/312]	eta 0:04:21 lr 0.001567	time 0.7103 (0.8672)	model_time 0.7102 (0.7288)	loss 2.5340 (3.0769)	grad_norm 1.3133 (1.6741/0.4483)	mem 34604MB
[2025-01-19 12:31:05 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][120/312]	eta 0:02:25 lr 0.001560	time 0.7286 (0.7585)	model_time 0.7281 (0.7463)	loss 3.1893 (3.0976)	grad_norm 0.7526 (1.5907/0.6658)	mem 34602MB
[2025-01-19 12:31:07 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][20/312]	eta 0:03:53 lr 0.001567	time 0.7238 (0.8012)	model_time 0.7236 (0.7286)	loss 2.3085 (3.0243)	grad_norm 2.6884 (1.5686/0.4922)	mem 34604MB
[2025-01-19 12:31:12 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][130/312]	eta 0:02:17 lr 0.001559	time 0.7144 (0.7561)	model_time 0.7143 (0.7449)	loss 3.1373 (3.0820)	grad_norm 1.1930 (1.5590/0.6523)	mem 34602MB
[2025-01-19 12:31:15 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][30/312]	eta 0:03:39 lr 0.001566	time 0.7161 (0.7778)	model_time 0.7157 (0.7285)	loss 2.3610 (3.0577)	grad_norm 1.3137 (1.8022/0.7006)	mem 34604MB
[2025-01-19 12:31:20 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][140/312]	eta 0:02:10 lr 0.001559	time 0.8065 (0.7576)	model_time 0.8060 (0.7471)	loss 3.6909 (3.0941)	grad_norm 1.6419 (1.5444/0.6373)	mem 34602MB
[2025-01-19 12:31:22 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][40/312]	eta 0:03:28 lr 0.001565	time 0.7185 (0.7655)	model_time 0.7183 (0.7282)	loss 3.2078 (3.0741)	grad_norm 1.0846 (1.7121/0.6825)	mem 34604MB
[2025-01-19 12:31:27 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][150/312]	eta 0:02:02 lr 0.001558	time 0.7161 (0.7553)	model_time 0.7159 (0.7455)	loss 3.4329 (3.0899)	grad_norm 1.8508 (1.5970/0.7069)	mem 34602MB
[2025-01-19 12:31:29 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][50/312]	eta 0:03:18 lr 0.001565	time 0.7176 (0.7590)	model_time 0.7171 (0.7289)	loss 3.8111 (3.0951)	grad_norm 0.9832 (1.7281/0.8333)	mem 34604MB
[2025-01-19 12:31:34 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][160/312]	eta 0:01:54 lr 0.001558	time 0.7245 (0.7545)	model_time 0.7240 (0.7453)	loss 2.2177 (3.1006)	grad_norm 0.7678 (1.5878/0.6968)	mem 34602MB
[2025-01-19 12:31:37 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][60/312]	eta 0:03:11 lr 0.001564	time 0.8118 (0.7610)	model_time 0.8116 (0.7358)	loss 3.2970 (3.1352)	grad_norm 1.6429 (1.8653/0.9981)	mem 34604MB
[2025-01-19 12:31:42 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][170/312]	eta 0:01:47 lr 0.001557	time 0.7255 (0.7568)	model_time 0.7254 (0.7481)	loss 3.1139 (3.1078)	grad_norm 1.6745 (1.6095/0.6996)	mem 34602MB
[2025-01-19 12:31:45 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][70/312]	eta 0:03:05 lr 0.001563	time 0.8095 (0.7657)	model_time 0.8094 (0.7440)	loss 2.6161 (3.0791)	grad_norm 2.2677 (1.7885/0.9692)	mem 34604MB
[2025-01-19 12:31:50 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][180/312]	eta 0:01:39 lr 0.001556	time 0.7221 (0.7571)	model_time 0.7216 (0.7488)	loss 3.5163 (3.1149)	grad_norm 2.3639 (1.6298/0.7036)	mem 34602MB
[2025-01-19 12:31:52 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][80/312]	eta 0:02:57 lr 0.001563	time 0.7969 (0.7637)	model_time 0.7968 (0.7446)	loss 2.8438 (3.0750)	grad_norm 1.6966 (1.7787/0.9317)	mem 34604MB
[2025-01-19 12:31:57 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][190/312]	eta 0:01:32 lr 0.001556	time 0.7254 (0.7571)	model_time 0.7252 (0.7492)	loss 3.6321 (3.1179)	grad_norm 1.6652 (1.6406/0.6948)	mem 34602MB
[2025-01-19 12:32:00 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][90/312]	eta 0:02:49 lr 0.001562	time 0.7316 (0.7616)	model_time 0.7311 (0.7446)	loss 3.0963 (3.0692)	grad_norm 1.6100 (1.7488/0.8982)	mem 34604MB
[2025-01-19 12:32:05 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][200/312]	eta 0:01:24 lr 0.001555	time 0.7362 (0.7560)	model_time 0.7358 (0.7485)	loss 2.8200 (3.1093)	grad_norm 1.3866 (1.6705/0.7252)	mem 34602MB
[2025-01-19 12:32:07 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][100/312]	eta 0:02:40 lr 0.001561	time 0.7274 (0.7578)	model_time 0.7270 (0.7424)	loss 1.9490 (3.0702)	grad_norm 1.3406 (1.7426/0.8673)	mem 34604MB
[2025-01-19 12:32:12 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][210/312]	eta 0:01:16 lr 0.001554	time 0.7431 (0.7545)	model_time 0.7429 (0.7474)	loss 3.5463 (3.1157)	grad_norm 0.6299 (1.6630/0.7170)	mem 34602MB
[2025-01-19 12:32:14 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][110/312]	eta 0:02:32 lr 0.001561	time 0.7172 (0.7554)	model_time 0.7171 (0.7413)	loss 2.1446 (3.0545)	grad_norm 1.1303 (1.6935/0.8448)	mem 34604MB
[2025-01-19 12:32:20 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][220/312]	eta 0:01:09 lr 0.001554	time 0.8106 (0.7543)	model_time 0.8102 (0.7475)	loss 2.8411 (3.1238)	grad_norm 1.4659 (1.6702/0.7168)	mem 34602MB
[2025-01-19 12:32:22 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][120/312]	eta 0:02:24 lr 0.001560	time 0.7163 (0.7537)	model_time 0.7161 (0.7408)	loss 1.9699 (3.0681)	grad_norm 1.3454 (1.7019/0.8369)	mem 34604MB
[2025-01-19 12:32:27 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][230/312]	eta 0:01:01 lr 0.001553	time 0.7176 (0.7533)	model_time 0.7174 (0.7468)	loss 3.2208 (3.1259)	grad_norm 1.3816 (1.6562/0.7065)	mem 34602MB
[2025-01-19 12:32:29 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][130/312]	eta 0:02:16 lr 0.001559	time 0.7179 (0.7514)	model_time 0.7177 (0.7395)	loss 3.0378 (3.0507)	grad_norm 2.5815 (1.7228/0.8179)	mem 34604MB
[2025-01-19 12:32:34 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][240/312]	eta 0:00:54 lr 0.001552	time 0.7452 (0.7524)	model_time 0.7448 (0.7461)	loss 3.3297 (3.1265)	grad_norm 0.8661 (1.6469/0.7005)	mem 34602MB
[2025-01-19 12:32:36 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][140/312]	eta 0:02:09 lr 0.001559	time 0.7220 (0.7503)	model_time 0.7218 (0.7391)	loss 3.6471 (3.0540)	grad_norm 0.7507 (1.7010/0.8110)	mem 34604MB
[2025-01-19 12:32:41 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][250/312]	eta 0:00:46 lr 0.001552	time 0.7160 (0.7514)	model_time 0.7158 (0.7454)	loss 2.1536 (3.1161)	grad_norm 2.0869 (1.6492/0.6922)	mem 34602MB
[2025-01-19 12:32:43 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][150/312]	eta 0:02:01 lr 0.001558	time 0.7371 (0.7487)	model_time 0.7366 (0.7383)	loss 2.7420 (3.0606)	grad_norm 2.0939 (1.6925/0.7941)	mem 34604MB
[2025-01-19 12:32:49 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][260/312]	eta 0:00:39 lr 0.001551	time 0.9018 (0.7523)	model_time 0.9016 (0.7465)	loss 3.2327 (3.1132)	grad_norm 1.2233 (1.6589/0.6882)	mem 34602MB
[2025-01-19 12:32:51 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][160/312]	eta 0:01:53 lr 0.001558	time 0.7160 (0.7474)	model_time 0.7159 (0.7376)	loss 3.7382 (3.0584)	grad_norm 1.6502 (1.7162/0.8058)	mem 34604MB
[2025-01-19 12:32:56 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][270/312]	eta 0:00:31 lr 0.001550	time 0.7320 (0.7513)	model_time 0.7318 (0.7456)	loss 3.4456 (3.1165)	grad_norm 0.9910 (1.6650/0.6894)	mem 34602MB
[2025-01-19 12:32:58 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][170/312]	eta 0:01:46 lr 0.001557	time 0.7138 (0.7467)	model_time 0.7133 (0.7374)	loss 3.5680 (3.0768)	grad_norm 1.8403 (1.7522/0.8377)	mem 34604MB
[2025-01-19 12:33:04 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][280/312]	eta 0:00:24 lr 0.001550	time 0.7226 (0.7512)	model_time 0.7222 (0.7458)	loss 2.8343 (3.1243)	grad_norm 1.5916 (1.6728/0.6925)	mem 34602MB
[2025-01-19 12:33:06 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][180/312]	eta 0:01:38 lr 0.001556	time 0.8069 (0.7473)	model_time 0.8067 (0.7385)	loss 3.0159 (3.0791)	grad_norm 1.5365 (1.7669/0.8289)	mem 34604MB
[2025-01-19 12:33:12 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][290/312]	eta 0:00:16 lr 0.001549	time 0.7169 (0.7521)	model_time 0.7167 (0.7469)	loss 2.8005 (3.1266)	grad_norm 1.2665 (1.6936/0.7149)	mem 34602MB
[2025-01-19 12:33:14 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][190/312]	eta 0:01:31 lr 0.001556	time 0.8409 (0.7508)	model_time 0.8407 (0.7425)	loss 3.4066 (3.0784)	grad_norm 0.8953 (1.7468/0.8188)	mem 34604MB
[2025-01-19 12:33:19 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][300/312]	eta 0:00:09 lr 0.001548	time 0.7980 (0.7525)	model_time 0.7979 (0.7474)	loss 3.4522 (3.1242)	grad_norm 3.5045 (1.7278/0.7589)	mem 34602MB
[2025-01-19 12:33:22 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][200/312]	eta 0:01:24 lr 0.001555	time 0.8154 (0.7521)	model_time 0.8150 (0.7441)	loss 3.3379 (3.0681)	grad_norm 2.7733 (1.7176/0.8195)	mem 34604MB
[2025-01-19 12:33:27 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][310/312]	eta 0:00:01 lr 0.001548	time 0.7117 (0.7519)	model_time 0.7116 (0.7470)	loss 3.7046 (3.1180)	grad_norm 1.8042 (1.7244/0.7507)	mem 34602MB
[2025-01-19 12:33:28 internimage_b_1k_224] (main.py 519): INFO EPOCH 172 training takes 0:03:54
[2025-01-19 12:33:28 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_172.pth saving......
[2025-01-19 12:33:29 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][210/312]	eta 0:01:16 lr 0.001554	time 0.7245 (0.7517)	model_time 0.7243 (0.7441)	loss 3.2785 (3.0743)	grad_norm 1.6646 (1.7351/0.8150)	mem 34604MB
[2025-01-19 12:33:31 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_172.pth saved !!!
[2025-01-19 12:33:36 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][220/312]	eta 0:01:09 lr 0.001554	time 0.7395 (0.7506)	model_time 0.7391 (0.7433)	loss 2.4566 (3.0842)	grad_norm 2.4716 (1.7499/0.8078)	mem 34604MB
[2025-01-19 12:33:40 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.826 (8.826)	Loss 0.8047 (0.8047)	Acc@1 83.960 (83.960)	Acc@5 97.290 (97.290)	Mem 34602MB
[2025-01-19 12:33:43 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.092)	Loss 1.0143 (0.8913)	Acc@1 77.466 (81.485)	Acc@5 94.751 (96.023)	Mem 34602MB
[2025-01-19 12:33:43 internimage_b_1k_224] (main.py 575): INFO [Epoch:172] * Acc@1 81.368 Acc@5 96.025
[2025-01-19 12:33:43 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.4%
[2025-01-19 12:33:43 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.42%
[2025-01-19 12:33:44 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][230/312]	eta 0:01:01 lr 0.001553	time 0.7279 (0.7496)	model_time 0.7276 (0.7426)	loss 3.8024 (3.0931)	grad_norm 1.5518 (1.7472/0.7968)	mem 34604MB
[2025-01-19 12:33:51 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][240/312]	eta 0:00:53 lr 0.001552	time 0.7312 (0.7490)	model_time 0.7311 (0.7423)	loss 3.3637 (3.0877)	grad_norm 1.1672 (1.7270/0.7877)	mem 34604MB
[2025-01-19 12:33:52 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.312 (9.312)	Loss 0.6688 (0.6688)	Acc@1 84.546 (84.546)	Acc@5 97.754 (97.754)	Mem 34602MB
[2025-01-19 12:33:57 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.263)	Loss 0.9496 (0.7961)	Acc@1 77.930 (82.005)	Acc@5 94.824 (96.200)	Mem 34602MB
[2025-01-19 12:33:57 internimage_b_1k_224] (main.py 575): INFO [Epoch:172] * Acc@1 81.850 Acc@5 96.257
[2025-01-19 12:33:57 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.8%
[2025-01-19 12:33:57 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:33:58 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][250/312]	eta 0:00:46 lr 0.001552	time 0.7136 (0.7482)	model_time 0.7134 (0.7418)	loss 3.6043 (3.0797)	grad_norm 1.2660 (1.7140/0.7770)	mem 34604MB
[2025-01-19 12:34:01 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:34:01 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.85%
[2025-01-19 12:34:04 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][0/312]	eta 0:11:52 lr 0.001548	time 2.2828 (2.2828)	model_time 0.7346 (0.7346)	loss 3.7632 (3.7632)	grad_norm 0.8186 (0.8186/0.0000)	mem 34602MB
[2025-01-19 12:34:05 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][260/312]	eta 0:00:38 lr 0.001551	time 0.7236 (0.7473)	model_time 0.7234 (0.7411)	loss 3.3196 (3.0879)	grad_norm 1.1977 (1.7103/0.7680)	mem 34604MB
[2025-01-19 12:34:11 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][10/312]	eta 0:04:24 lr 0.001547	time 0.7152 (0.8770)	model_time 0.7151 (0.7360)	loss 3.3931 (3.0057)	grad_norm 1.6638 (1.7267/0.7751)	mem 34602MB
[2025-01-19 12:34:13 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][270/312]	eta 0:00:31 lr 0.001550	time 0.7221 (0.7467)	model_time 0.7219 (0.7407)	loss 3.8008 (3.0827)	grad_norm 1.2823 (1.7129/0.7679)	mem 34604MB
[2025-01-19 12:34:18 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][20/312]	eta 0:03:55 lr 0.001546	time 0.7242 (0.8050)	model_time 0.7238 (0.7310)	loss 2.2650 (2.9678)	grad_norm 1.4605 (1.7275/0.6602)	mem 34602MB
[2025-01-19 12:34:20 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][280/312]	eta 0:00:23 lr 0.001550	time 0.7141 (0.7459)	model_time 0.7139 (0.7401)	loss 3.2143 (3.0772)	grad_norm 0.8689 (1.7133/0.7696)	mem 34604MB
[2025-01-19 12:34:26 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][30/312]	eta 0:03:43 lr 0.001546	time 0.7433 (0.7908)	model_time 0.7429 (0.7406)	loss 3.0582 (2.9626)	grad_norm 1.7260 (1.6274/0.5931)	mem 34602MB
[2025-01-19 12:34:27 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][290/312]	eta 0:00:16 lr 0.001549	time 0.7168 (0.7456)	model_time 0.7164 (0.7400)	loss 3.2319 (3.0722)	grad_norm 1.4290 (1.7166/0.7651)	mem 34604MB
[2025-01-19 12:34:33 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][40/312]	eta 0:03:31 lr 0.001545	time 0.7235 (0.7774)	model_time 0.7233 (0.7393)	loss 3.5960 (2.9913)	grad_norm 2.2612 (1.6646/0.5704)	mem 34602MB
[2025-01-19 12:34:35 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][300/312]	eta 0:00:08 lr 0.001548	time 0.7974 (0.7462)	model_time 0.7973 (0.7407)	loss 2.5877 (3.0685)	grad_norm 1.7125 (1.7169/0.7577)	mem 34604MB
[2025-01-19 12:34:40 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][50/312]	eta 0:03:21 lr 0.001544	time 0.7179 (0.7681)	model_time 0.7177 (0.7375)	loss 3.8800 (3.0448)	grad_norm 2.9457 (1.6975/0.5557)	mem 34602MB
[2025-01-19 12:34:43 internimage_b_1k_224] (main.py 510): INFO Train: [172/300][310/312]	eta 0:00:01 lr 0.001548	time 0.8116 (0.7480)	model_time 0.8115 (0.7428)	loss 3.3273 (3.0717)	grad_norm 1.1158 (1.7088/0.7659)	mem 34604MB
[2025-01-19 12:34:44 internimage_b_1k_224] (main.py 519): INFO EPOCH 172 training takes 0:03:53
[2025-01-19 12:34:44 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_172.pth saving......
[2025-01-19 12:34:47 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_172.pth saved !!!
[2025-01-19 12:34:48 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][60/312]	eta 0:03:12 lr 0.001544	time 0.7172 (0.7639)	model_time 0.7168 (0.7381)	loss 2.6159 (3.0785)	grad_norm 2.3064 (1.7023/0.5378)	mem 34602MB
[2025-01-19 12:34:55 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.360 (7.360)	Loss 0.7287 (0.7287)	Acc@1 84.473 (84.473)	Acc@5 97.388 (97.388)	Mem 34604MB
[2025-01-19 12:34:55 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][70/312]	eta 0:03:04 lr 0.001543	time 0.7157 (0.7631)	model_time 0.7156 (0.7410)	loss 3.2790 (3.0671)	grad_norm 1.6919 (1.6956/0.5307)	mem 34602MB
[2025-01-19 12:34:57 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.938)	Loss 1.0444 (0.8761)	Acc@1 76.270 (81.441)	Acc@5 94.556 (95.867)	Mem 34604MB
[2025-01-19 12:34:58 internimage_b_1k_224] (main.py 575): INFO [Epoch:172] * Acc@1 81.380 Acc@5 95.903
[2025-01-19 12:34:58 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.4%
[2025-01-19 12:34:58 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.51%
[2025-01-19 12:35:03 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][80/312]	eta 0:02:56 lr 0.001543	time 0.8102 (0.7598)	model_time 0.8097 (0.7404)	loss 3.8401 (3.0928)	grad_norm 1.7105 (1.6570/0.5269)	mem 34602MB
[2025-01-19 12:35:07 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.261 (9.261)	Loss 0.6681 (0.6681)	Acc@1 84.839 (84.839)	Acc@5 97.778 (97.778)	Mem 34604MB
[2025-01-19 12:35:10 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][90/312]	eta 0:02:48 lr 0.001542	time 1.0017 (0.7607)	model_time 1.0012 (0.7434)	loss 3.0811 (3.1060)	grad_norm 0.7340 (1.6100/0.5341)	mem 34602MB
[2025-01-19 12:35:12 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.257)	Loss 0.9500 (0.7955)	Acc@1 77.759 (82.100)	Acc@5 94.849 (96.211)	Mem 34604MB
[2025-01-19 12:35:12 internimage_b_1k_224] (main.py 575): INFO [Epoch:172] * Acc@1 81.970 Acc@5 96.267
[2025-01-19 12:35:12 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.0%
[2025-01-19 12:35:12 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:35:16 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:35:16 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.97%
[2025-01-19 12:35:18 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][0/312]	eta 0:11:42 lr 0.001548	time 2.2528 (2.2528)	model_time 0.7362 (0.7362)	loss 3.6884 (3.6884)	grad_norm 1.6196 (1.6196/0.0000)	mem 34604MB
[2025-01-19 12:35:18 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][100/312]	eta 0:02:41 lr 0.001541	time 0.7835 (0.7607)	model_time 0.7834 (0.7450)	loss 3.3212 (3.1056)	grad_norm 2.7275 (1.5815/0.5442)	mem 34602MB
[2025-01-19 12:35:25 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][10/312]	eta 0:04:30 lr 0.001547	time 0.7307 (0.8948)	model_time 0.7306 (0.7566)	loss 3.3676 (3.3764)	grad_norm 1.7580 (1.5369/0.4728)	mem 34604MB
[2025-01-19 12:35:26 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][110/312]	eta 0:02:33 lr 0.001541	time 0.7168 (0.7611)	model_time 0.7164 (0.7468)	loss 3.4735 (3.1194)	grad_norm 1.9451 (1.5673/0.5532)	mem 34602MB
[2025-01-19 12:35:33 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][20/312]	eta 0:04:01 lr 0.001546	time 0.7262 (0.8266)	model_time 0.7260 (0.7540)	loss 3.7388 (3.2036)	grad_norm 1.1304 (1.3922/0.4786)	mem 34604MB
[2025-01-19 12:35:33 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][120/312]	eta 0:02:26 lr 0.001540	time 0.7166 (0.7608)	model_time 0.7164 (0.7477)	loss 2.3843 (3.1128)	grad_norm 1.0843 (1.5722/0.5498)	mem 34602MB
[2025-01-19 12:35:40 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][30/312]	eta 0:03:44 lr 0.001546	time 0.7362 (0.7948)	model_time 0.7360 (0.7455)	loss 3.4165 (3.1970)	grad_norm 3.3053 (1.5958/0.6060)	mem 34604MB
[2025-01-19 12:35:41 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][130/312]	eta 0:02:18 lr 0.001539	time 0.7480 (0.7590)	model_time 0.7478 (0.7468)	loss 3.0038 (3.0828)	grad_norm 1.2358 (1.5658/0.5442)	mem 34602MB
[2025-01-19 12:35:48 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][40/312]	eta 0:03:31 lr 0.001545	time 0.7170 (0.7791)	model_time 0.7168 (0.7417)	loss 3.4124 (3.1744)	grad_norm 0.9205 (1.6773/0.7217)	mem 34604MB
[2025-01-19 12:35:48 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][140/312]	eta 0:02:10 lr 0.001539	time 0.7227 (0.7567)	model_time 0.7223 (0.7453)	loss 3.3839 (3.0982)	grad_norm 0.7741 (1.5695/0.5539)	mem 34602MB
[2025-01-19 12:35:55 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][50/312]	eta 0:03:21 lr 0.001544	time 0.7300 (0.7694)	model_time 0.7298 (0.7392)	loss 3.3714 (3.1911)	grad_norm 1.9805 (1.6762/0.7028)	mem 34604MB
[2025-01-19 12:35:56 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][150/312]	eta 0:02:02 lr 0.001538	time 0.7164 (0.7566)	model_time 0.7162 (0.7460)	loss 2.7190 (3.0716)	grad_norm 2.0596 (1.6016/0.6141)	mem 34602MB
[2025-01-19 12:36:02 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][60/312]	eta 0:03:12 lr 0.001544	time 0.7192 (0.7623)	model_time 0.7191 (0.7370)	loss 3.3429 (3.2117)	grad_norm 1.4287 (1.6246/0.6683)	mem 34604MB
[2025-01-19 12:36:03 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][160/312]	eta 0:01:54 lr 0.001537	time 0.7289 (0.7552)	model_time 0.7285 (0.7452)	loss 3.4206 (3.0711)	grad_norm 2.0402 (1.6141/0.6351)	mem 34602MB
[2025-01-19 12:36:09 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][70/312]	eta 0:03:03 lr 0.001543	time 0.7115 (0.7567)	model_time 0.7114 (0.7349)	loss 3.3271 (3.2241)	grad_norm 2.5215 (1.6264/0.6501)	mem 34604MB
[2025-01-19 12:36:10 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][170/312]	eta 0:01:47 lr 0.001537	time 0.7159 (0.7538)	model_time 0.7155 (0.7444)	loss 3.3494 (3.0695)	grad_norm 0.8259 (1.6077/0.6394)	mem 34602MB
[2025-01-19 12:36:17 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][80/312]	eta 0:02:54 lr 0.001543	time 0.7159 (0.7539)	model_time 0.7154 (0.7348)	loss 3.6455 (3.2089)	grad_norm 1.4790 (1.6611/0.6505)	mem 34604MB
[2025-01-19 12:36:18 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][180/312]	eta 0:01:39 lr 0.001536	time 0.7570 (0.7530)	model_time 0.7568 (0.7441)	loss 3.2888 (3.0753)	grad_norm 4.1722 (1.6245/0.6650)	mem 34602MB
[2025-01-19 12:36:24 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][90/312]	eta 0:02:46 lr 0.001542	time 0.7214 (0.7507)	model_time 0.7212 (0.7336)	loss 2.8066 (3.2033)	grad_norm 1.1770 (1.6421/0.6567)	mem 34604MB
[2025-01-19 12:36:25 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][190/312]	eta 0:01:31 lr 0.001535	time 0.7426 (0.7532)	model_time 0.7425 (0.7447)	loss 2.5915 (3.0658)	grad_norm 2.2264 (1.6560/0.6748)	mem 34602MB
[2025-01-19 12:36:31 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][100/312]	eta 0:02:38 lr 0.001541	time 0.8428 (0.7492)	model_time 0.8426 (0.7338)	loss 2.6282 (3.1723)	grad_norm 0.9888 (1.6531/0.6919)	mem 34604MB
[2025-01-19 12:36:32 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][200/312]	eta 0:01:24 lr 0.001535	time 0.7992 (0.7523)	model_time 0.7988 (0.7442)	loss 3.7230 (3.0737)	grad_norm 0.8705 (1.6429/0.6680)	mem 34602MB
[2025-01-19 12:36:39 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][110/312]	eta 0:02:31 lr 0.001541	time 0.9710 (0.7520)	model_time 0.9708 (0.7379)	loss 3.2954 (3.1748)	grad_norm 1.7382 (1.6773/0.6852)	mem 34604MB
[2025-01-19 12:36:40 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][210/312]	eta 0:01:16 lr 0.001534	time 0.7998 (0.7521)	model_time 0.7996 (0.7444)	loss 3.7705 (3.0800)	grad_norm 1.1482 (1.6311/0.6596)	mem 34602MB
[2025-01-19 12:36:47 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][120/312]	eta 0:02:24 lr 0.001540	time 0.8293 (0.7546)	model_time 0.8291 (0.7417)	loss 3.2970 (3.1787)	grad_norm 1.1132 (1.6466/0.6787)	mem 34604MB
[2025-01-19 12:36:48 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][220/312]	eta 0:01:09 lr 0.001534	time 0.8005 (0.7523)	model_time 0.8001 (0.7449)	loss 3.6365 (3.0811)	grad_norm 1.5873 (1.6297/0.6574)	mem 34602MB
[2025-01-19 12:36:55 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][130/312]	eta 0:02:17 lr 0.001539	time 0.7242 (0.7560)	model_time 0.7237 (0.7440)	loss 1.8418 (3.1831)	grad_norm 0.8659 (1.6485/0.6753)	mem 34604MB
[2025-01-19 12:36:55 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][230/312]	eta 0:01:01 lr 0.001533	time 0.8049 (0.7528)	model_time 0.8045 (0.7457)	loss 3.8162 (3.0871)	grad_norm 3.6250 (1.6610/0.6831)	mem 34602MB
[2025-01-19 12:37:02 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][140/312]	eta 0:02:09 lr 0.001539	time 0.7155 (0.7553)	model_time 0.7153 (0.7441)	loss 2.8246 (3.1813)	grad_norm 2.6637 (1.6557/0.6717)	mem 34604MB
[2025-01-19 12:37:03 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][240/312]	eta 0:00:54 lr 0.001532	time 0.7220 (0.7531)	model_time 0.7215 (0.7463)	loss 3.7573 (3.0867)	grad_norm 1.6338 (1.6701/0.6783)	mem 34602MB
[2025-01-19 12:37:09 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][150/312]	eta 0:02:02 lr 0.001538	time 0.7353 (0.7535)	model_time 0.7350 (0.7430)	loss 2.9131 (3.1452)	grad_norm 1.6028 (1.6596/0.6756)	mem 34604MB
[2025-01-19 12:37:10 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][250/312]	eta 0:00:46 lr 0.001532	time 0.7314 (0.7522)	model_time 0.7312 (0.7457)	loss 3.3452 (3.0869)	grad_norm 1.5303 (1.6560/0.6753)	mem 34602MB
[2025-01-19 12:37:17 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][160/312]	eta 0:01:54 lr 0.001537	time 0.7252 (0.7518)	model_time 0.7250 (0.7420)	loss 3.2605 (3.1341)	grad_norm 1.6524 (1.6570/0.6749)	mem 34604MB
[2025-01-19 12:37:17 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][260/312]	eta 0:00:39 lr 0.001531	time 0.7288 (0.7511)	model_time 0.7281 (0.7448)	loss 3.5351 (3.0943)	grad_norm 0.9057 (1.6452/0.6736)	mem 34602MB
[2025-01-19 12:37:24 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][170/312]	eta 0:01:46 lr 0.001537	time 0.7202 (0.7503)	model_time 0.7197 (0.7410)	loss 3.1139 (3.1361)	grad_norm 1.1648 (1.6948/0.7208)	mem 34604MB
[2025-01-19 12:37:25 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][270/312]	eta 0:00:31 lr 0.001530	time 0.7414 (0.7511)	model_time 0.7410 (0.7450)	loss 2.7333 (3.0946)	grad_norm 1.1494 (1.6415/0.6685)	mem 34602MB
[2025-01-19 12:37:31 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][180/312]	eta 0:01:38 lr 0.001536	time 0.7131 (0.7490)	model_time 0.7125 (0.7402)	loss 3.1789 (3.1486)	grad_norm 0.9879 (1.7068/0.7308)	mem 34604MB
[2025-01-19 12:37:32 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][280/312]	eta 0:00:24 lr 0.001530	time 0.7243 (0.7504)	model_time 0.7239 (0.7445)	loss 3.3681 (3.0978)	grad_norm 1.1563 (1.6434/0.6690)	mem 34602MB
[2025-01-19 12:37:39 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][190/312]	eta 0:01:31 lr 0.001535	time 0.7240 (0.7479)	model_time 0.7237 (0.7396)	loss 2.9088 (3.1374)	grad_norm 2.1507 (1.6993/0.7166)	mem 34604MB
[2025-01-19 12:37:39 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][290/312]	eta 0:00:16 lr 0.001529	time 0.7227 (0.7495)	model_time 0.7226 (0.7438)	loss 3.8917 (3.1100)	grad_norm 1.2481 (1.6320/0.6634)	mem 34602MB
[2025-01-19 12:37:46 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][200/312]	eta 0:01:23 lr 0.001535	time 0.7149 (0.7470)	model_time 0.7148 (0.7390)	loss 2.0685 (3.1362)	grad_norm 0.9993 (1.6751/0.7104)	mem 34604MB
[2025-01-19 12:37:47 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][300/312]	eta 0:00:08 lr 0.001528	time 0.7123 (0.7488)	model_time 0.7122 (0.7433)	loss 2.6291 (3.1078)	grad_norm 1.0905 (1.6314/0.6571)	mem 34602MB
[2025-01-19 12:37:53 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][210/312]	eta 0:01:16 lr 0.001534	time 0.7445 (0.7459)	model_time 0.7443 (0.7383)	loss 2.8049 (3.1377)	grad_norm 3.1945 (1.6796/0.7066)	mem 34604MB
[2025-01-19 12:37:54 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][310/312]	eta 0:00:01 lr 0.001528	time 0.7993 (0.7486)	model_time 0.7992 (0.7433)	loss 2.3073 (3.1058)	grad_norm 1.1965 (1.6251/0.6497)	mem 34602MB
[2025-01-19 12:37:55 internimage_b_1k_224] (main.py 519): INFO EPOCH 173 training takes 0:03:53
[2025-01-19 12:37:55 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_173.pth saving......
[2025-01-19 12:37:58 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_173.pth saved !!!
[2025-01-19 12:38:00 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][220/312]	eta 0:01:08 lr 0.001534	time 0.8275 (0.7454)	model_time 0.8270 (0.7381)	loss 2.5149 (3.1320)	grad_norm 1.2802 (1.6728/0.7058)	mem 34604MB
[2025-01-19 12:38:06 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.776 (7.776)	Loss 0.8028 (0.8028)	Acc@1 84.619 (84.619)	Acc@5 97.363 (97.363)	Mem 34602MB
[2025-01-19 12:38:08 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][230/312]	eta 0:01:01 lr 0.001533	time 0.8223 (0.7459)	model_time 0.8221 (0.7390)	loss 3.4532 (3.1296)	grad_norm 1.5971 (1.6870/0.7062)	mem 34604MB
[2025-01-19 12:38:09 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.989)	Loss 1.0782 (0.9121)	Acc@1 76.831 (81.547)	Acc@5 94.727 (95.983)	Mem 34602MB
[2025-01-19 12:38:09 internimage_b_1k_224] (main.py 575): INFO [Epoch:173] * Acc@1 81.418 Acc@5 95.997
[2025-01-19 12:38:09 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.4%
[2025-01-19 12:38:09 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.42%
[2025-01-19 12:38:16 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][240/312]	eta 0:00:53 lr 0.001532	time 0.9318 (0.7483)	model_time 0.9316 (0.7416)	loss 3.7602 (3.1250)	grad_norm 0.8918 (1.6992/0.7366)	mem 34604MB
[2025-01-19 12:38:19 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.316 (9.316)	Loss 0.6700 (0.6700)	Acc@1 84.595 (84.595)	Acc@5 97.729 (97.729)	Mem 34602MB
[2025-01-19 12:38:23 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.281)	Loss 0.9496 (0.7966)	Acc@1 78.027 (82.067)	Acc@5 94.800 (96.207)	Mem 34602MB
[2025-01-19 12:38:24 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][250/312]	eta 0:00:46 lr 0.001532	time 0.7143 (0.7487)	model_time 0.7141 (0.7423)	loss 3.7011 (3.1284)	grad_norm 1.0547 (1.6845/0.7296)	mem 34604MB
[2025-01-19 12:38:24 internimage_b_1k_224] (main.py 575): INFO [Epoch:173] * Acc@1 81.906 Acc@5 96.265
[2025-01-19 12:38:24 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.9%
[2025-01-19 12:38:24 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:38:27 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:38:27 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.91%
[2025-01-19 12:38:30 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][0/312]	eta 0:10:38 lr 0.001528	time 2.0456 (2.0456)	model_time 0.7532 (0.7532)	loss 2.9562 (2.9562)	grad_norm 1.5770 (1.5770/0.0000)	mem 34602MB
[2025-01-19 12:38:31 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][260/312]	eta 0:00:38 lr 0.001531	time 0.7194 (0.7484)	model_time 0.7192 (0.7422)	loss 3.5602 (3.1207)	grad_norm 1.3109 (1.6823/0.7248)	mem 34604MB
[2025-01-19 12:38:37 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][10/312]	eta 0:04:15 lr 0.001527	time 0.7218 (0.8464)	model_time 0.7214 (0.7286)	loss 3.0281 (3.1186)	grad_norm 1.0356 (1.9037/1.0021)	mem 34602MB
[2025-01-19 12:38:38 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][270/312]	eta 0:00:31 lr 0.001530	time 0.7186 (0.7474)	model_time 0.7185 (0.7414)	loss 3.3819 (3.1271)	grad_norm 1.2918 (1.6632/0.7208)	mem 34604MB
[2025-01-19 12:38:44 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][20/312]	eta 0:03:55 lr 0.001526	time 0.7284 (0.8060)	model_time 0.7280 (0.7441)	loss 2.4274 (3.1280)	grad_norm 2.0236 (2.2104/1.2922)	mem 34602MB
[2025-01-19 12:38:45 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][280/312]	eta 0:00:23 lr 0.001530	time 0.7235 (0.7466)	model_time 0.7233 (0.7408)	loss 2.4842 (3.1128)	grad_norm 1.4418 (1.6502/0.7134)	mem 34604MB
[2025-01-19 12:38:52 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][30/312]	eta 0:03:43 lr 0.001526	time 0.7202 (0.7929)	model_time 0.7198 (0.7508)	loss 2.0983 (3.0808)	grad_norm 2.0772 (2.0289/1.1168)	mem 34602MB
[2025-01-19 12:38:53 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][290/312]	eta 0:00:16 lr 0.001529	time 0.7204 (0.7459)	model_time 0.7199 (0.7403)	loss 3.6585 (3.1184)	grad_norm 1.8800 (1.6570/0.7138)	mem 34604MB
[2025-01-19 12:39:00 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][40/312]	eta 0:03:34 lr 0.001525	time 0.7238 (0.7869)	model_time 0.7234 (0.7550)	loss 2.6004 (3.0978)	grad_norm 1.1614 (1.8842/1.0389)	mem 34602MB
[2025-01-19 12:39:00 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][300/312]	eta 0:00:08 lr 0.001528	time 0.7119 (0.7452)	model_time 0.7118 (0.7397)	loss 3.5733 (3.1190)	grad_norm 0.9698 (1.6390/0.7110)	mem 34604MB
[2025-01-19 12:39:07 internimage_b_1k_224] (main.py 510): INFO Train: [173/300][310/312]	eta 0:00:01 lr 0.001528	time 0.7121 (0.7444)	model_time 0.7120 (0.7391)	loss 3.2793 (3.1282)	grad_norm 1.1374 (1.6419/0.7101)	mem 34604MB
[2025-01-19 12:39:07 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][50/312]	eta 0:03:24 lr 0.001524	time 0.7173 (0.7787)	model_time 0.7171 (0.7530)	loss 3.3513 (3.0889)	grad_norm 1.3489 (1.8368/0.9645)	mem 34602MB
[2025-01-19 12:39:08 internimage_b_1k_224] (main.py 519): INFO EPOCH 173 training takes 0:03:52
[2025-01-19 12:39:08 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_173.pth saving......
[2025-01-19 12:39:11 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_173.pth saved !!!
[2025-01-19 12:39:15 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][60/312]	eta 0:03:14 lr 0.001524	time 0.7249 (0.7715)	model_time 0.7244 (0.7499)	loss 3.3350 (3.0579)	grad_norm 2.1733 (1.8254/0.9145)	mem 34602MB
[2025-01-19 12:39:19 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.496 (7.496)	Loss 0.7821 (0.7821)	Acc@1 84.326 (84.326)	Acc@5 97.290 (97.290)	Mem 34604MB
[2025-01-19 12:39:22 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.958)	Loss 1.0622 (0.9044)	Acc@1 77.148 (81.667)	Acc@5 94.702 (95.992)	Mem 34604MB
[2025-01-19 12:39:22 internimage_b_1k_224] (main.py 575): INFO [Epoch:173] * Acc@1 81.596 Acc@5 96.009
[2025-01-19 12:39:22 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.6%
[2025-01-19 12:39:22 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 12:39:22 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][70/312]	eta 0:03:05 lr 0.001523	time 0.7229 (0.7669)	model_time 0.7225 (0.7484)	loss 3.1487 (3.0128)	grad_norm 0.9454 (1.8067/0.8826)	mem 34602MB
[2025-01-19 12:39:25 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 12:39:25 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.60%
[2025-01-19 12:39:29 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][80/312]	eta 0:02:57 lr 0.001522	time 0.7179 (0.7639)	model_time 0.7178 (0.7476)	loss 1.9484 (3.0011)	grad_norm 1.4670 (1.7531/0.8560)	mem 34602MB
[2025-01-19 12:39:33 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.492 (7.492)	Loss 0.6691 (0.6691)	Acc@1 84.790 (84.790)	Acc@5 97.803 (97.803)	Mem 34604MB
[2025-01-19 12:39:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.957)	Loss 0.9501 (0.7959)	Acc@1 77.954 (82.153)	Acc@5 94.824 (96.225)	Mem 34604MB
[2025-01-19 12:39:36 internimage_b_1k_224] (main.py 575): INFO [Epoch:173] * Acc@1 82.022 Acc@5 96.281
[2025-01-19 12:39:36 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.0%
[2025-01-19 12:39:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:39:37 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][90/312]	eta 0:02:48 lr 0.001522	time 0.7244 (0.7607)	model_time 0.7242 (0.7462)	loss 3.3820 (3.0229)	grad_norm 1.0761 (1.6893/0.8341)	mem 34602MB
[2025-01-19 12:39:39 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:39:39 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.02%
[2025-01-19 12:39:42 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][0/312]	eta 0:10:38 lr 0.001528	time 2.0451 (2.0451)	model_time 0.7501 (0.7501)	loss 2.9366 (2.9366)	grad_norm 1.5795 (1.5795/0.0000)	mem 34604MB
[2025-01-19 12:39:44 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][100/312]	eta 0:02:40 lr 0.001521	time 0.7176 (0.7572)	model_time 0.7174 (0.7440)	loss 3.9382 (3.0594)	grad_norm 1.2589 (1.6667/0.8002)	mem 34602MB
[2025-01-19 12:39:49 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][10/312]	eta 0:04:22 lr 0.001527	time 0.7219 (0.8686)	model_time 0.7217 (0.7507)	loss 3.5919 (3.2636)	grad_norm 1.0187 (1.4573/0.3848)	mem 34604MB
[2025-01-19 12:39:51 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][110/312]	eta 0:02:32 lr 0.001521	time 0.7175 (0.7551)	model_time 0.7171 (0.7431)	loss 3.3574 (3.0631)	grad_norm 1.6063 (1.6555/0.7731)	mem 34602MB
[2025-01-19 12:39:56 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][20/312]	eta 0:03:54 lr 0.001526	time 0.7170 (0.8042)	model_time 0.7168 (0.7423)	loss 3.1210 (3.1881)	grad_norm 1.3655 (1.5107/0.6137)	mem 34604MB
[2025-01-19 12:39:59 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][120/312]	eta 0:02:24 lr 0.001520	time 0.7246 (0.7548)	model_time 0.7242 (0.7438)	loss 2.0508 (3.0207)	grad_norm 1.5108 (1.6639/0.7498)	mem 34602MB
[2025-01-19 12:40:04 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][30/312]	eta 0:03:40 lr 0.001526	time 0.7191 (0.7819)	model_time 0.7189 (0.7398)	loss 3.0867 (3.1869)	grad_norm 1.2167 (1.5563/0.6224)	mem 34604MB
[2025-01-19 12:40:06 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][130/312]	eta 0:02:16 lr 0.001519	time 0.7150 (0.7524)	model_time 0.7144 (0.7422)	loss 2.9845 (3.0256)	grad_norm 1.3781 (1.6583/0.7322)	mem 34602MB
[2025-01-19 12:40:11 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][40/312]	eta 0:03:31 lr 0.001525	time 0.7143 (0.7763)	model_time 0.7138 (0.7444)	loss 3.4048 (3.2086)	grad_norm 1.3567 (1.6608/0.6398)	mem 34604MB
[2025-01-19 12:40:14 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][140/312]	eta 0:02:09 lr 0.001519	time 0.7190 (0.7527)	model_time 0.7189 (0.7431)	loss 3.5215 (3.0251)	grad_norm 1.2937 (1.6334/0.7139)	mem 34602MB
[2025-01-19 12:40:19 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][50/312]	eta 0:03:25 lr 0.001524	time 0.8262 (0.7829)	model_time 0.8257 (0.7572)	loss 3.4875 (3.1418)	grad_norm 1.8912 (1.6591/0.5935)	mem 34604MB
[2025-01-19 12:40:21 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][150/312]	eta 0:02:02 lr 0.001518	time 0.7149 (0.7537)	model_time 0.7144 (0.7448)	loss 2.7882 (3.0342)	grad_norm 2.2476 (1.6057/0.7080)	mem 34602MB
[2025-01-19 12:40:27 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][60/312]	eta 0:03:16 lr 0.001524	time 0.8138 (0.7789)	model_time 0.8136 (0.7573)	loss 3.3620 (3.1498)	grad_norm 1.2008 (1.6806/0.5937)	mem 34604MB
[2025-01-19 12:40:29 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][160/312]	eta 0:01:54 lr 0.001517	time 0.8171 (0.7545)	model_time 0.8166 (0.7461)	loss 2.6054 (3.0223)	grad_norm 1.2221 (1.6116/0.7037)	mem 34602MB
[2025-01-19 12:40:34 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][70/312]	eta 0:03:07 lr 0.001523	time 0.7165 (0.7735)	model_time 0.7163 (0.7549)	loss 2.6463 (3.1337)	grad_norm 1.6325 (1.7562/0.6907)	mem 34604MB
[2025-01-19 12:40:37 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][170/312]	eta 0:01:47 lr 0.001517	time 0.7216 (0.7549)	model_time 0.7214 (0.7469)	loss 2.1871 (3.0232)	grad_norm 1.0214 (1.5843/0.6946)	mem 34602MB
[2025-01-19 12:40:42 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][80/312]	eta 0:02:58 lr 0.001522	time 0.7329 (0.7674)	model_time 0.7326 (0.7511)	loss 2.2886 (3.1202)	grad_norm 1.2861 (1.6979/0.6712)	mem 34604MB
[2025-01-19 12:40:44 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][180/312]	eta 0:01:39 lr 0.001516	time 0.7157 (0.7537)	model_time 0.7152 (0.7462)	loss 2.8097 (3.0199)	grad_norm 1.0031 (1.5750/0.6850)	mem 34602MB
[2025-01-19 12:40:49 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][90/312]	eta 0:02:49 lr 0.001522	time 0.7290 (0.7624)	model_time 0.7288 (0.7478)	loss 3.6819 (3.1280)	grad_norm 0.8736 (1.6784/0.6483)	mem 34604MB
[2025-01-19 12:40:51 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][190/312]	eta 0:01:31 lr 0.001515	time 0.7161 (0.7529)	model_time 0.7159 (0.7458)	loss 3.5913 (3.0409)	grad_norm 1.7727 (1.5710/0.6724)	mem 34602MB
[2025-01-19 12:40:56 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][100/312]	eta 0:02:40 lr 0.001521	time 0.7224 (0.7586)	model_time 0.7220 (0.7455)	loss 3.3210 (3.1044)	grad_norm 1.1074 (1.6543/0.6628)	mem 34604MB
[2025-01-19 12:40:59 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][200/312]	eta 0:01:24 lr 0.001515	time 0.7216 (0.7530)	model_time 0.7212 (0.7463)	loss 3.3407 (3.0369)	grad_norm 1.0533 (1.5623/0.6655)	mem 34602MB
[2025-01-19 12:41:03 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][110/312]	eta 0:02:32 lr 0.001521	time 0.7161 (0.7556)	model_time 0.7156 (0.7436)	loss 3.4006 (3.1072)	grad_norm 0.9523 (1.6579/0.6593)	mem 34604MB
[2025-01-19 12:41:06 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][210/312]	eta 0:01:16 lr 0.001514	time 0.7151 (0.7524)	model_time 0.7149 (0.7459)	loss 2.6470 (3.0452)	grad_norm 1.0124 (1.5544/0.6594)	mem 34602MB
[2025-01-19 12:41:11 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][120/312]	eta 0:02:24 lr 0.001520	time 0.7199 (0.7536)	model_time 0.7197 (0.7426)	loss 2.7873 (3.1099)	grad_norm 2.5060 (1.6543/0.6683)	mem 34604MB
[2025-01-19 12:41:13 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][220/312]	eta 0:01:09 lr 0.001513	time 0.7189 (0.7512)	model_time 0.7185 (0.7450)	loss 3.4189 (3.0514)	grad_norm 2.1106 (1.6003/0.7462)	mem 34602MB
[2025-01-19 12:41:18 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][130/312]	eta 0:02:16 lr 0.001519	time 0.7195 (0.7525)	model_time 0.7193 (0.7422)	loss 2.0471 (3.1036)	grad_norm 1.0838 (1.6165/0.6636)	mem 34604MB
[2025-01-19 12:41:21 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][230/312]	eta 0:01:01 lr 0.001513	time 0.7269 (0.7505)	model_time 0.7268 (0.7446)	loss 1.9456 (3.0518)	grad_norm 3.0286 (1.6437/0.7786)	mem 34602MB
[2025-01-19 12:41:25 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][140/312]	eta 0:02:09 lr 0.001519	time 0.7093 (0.7504)	model_time 0.7088 (0.7408)	loss 2.3700 (3.0926)	grad_norm 1.5692 (1.6092/0.6475)	mem 34604MB
[2025-01-19 12:41:28 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][240/312]	eta 0:00:54 lr 0.001512	time 0.7156 (0.7509)	model_time 0.7154 (0.7451)	loss 2.6477 (3.0543)	grad_norm 2.4258 (1.6610/0.7914)	mem 34602MB
[2025-01-19 12:41:33 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][150/312]	eta 0:02:01 lr 0.001518	time 0.7185 (0.7491)	model_time 0.7183 (0.7401)	loss 2.2107 (3.0913)	grad_norm 1.1573 (1.5920/0.6439)	mem 34604MB
[2025-01-19 12:41:36 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][250/312]	eta 0:00:46 lr 0.001512	time 0.7250 (0.7498)	model_time 0.7249 (0.7443)	loss 3.2121 (3.0484)	grad_norm 1.2628 (1.6495/0.7807)	mem 34602MB
[2025-01-19 12:41:40 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][160/312]	eta 0:01:54 lr 0.001517	time 0.8019 (0.7504)	model_time 0.8017 (0.7420)	loss 3.2036 (3.0840)	grad_norm 1.6632 (1.5776/0.6304)	mem 34604MB
[2025-01-19 12:41:43 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][260/312]	eta 0:00:38 lr 0.001511	time 0.7208 (0.7499)	model_time 0.7206 (0.7446)	loss 3.3052 (3.0483)	grad_norm 1.1447 (1.6464/0.7725)	mem 34602MB
[2025-01-19 12:41:48 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][170/312]	eta 0:01:46 lr 0.001517	time 0.8074 (0.7528)	model_time 0.8072 (0.7449)	loss 2.6756 (3.0846)	grad_norm 1.6130 (1.5970/0.6463)	mem 34604MB
[2025-01-19 12:41:51 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][270/312]	eta 0:00:31 lr 0.001510	time 0.8065 (0.7503)	model_time 0.8064 (0.7451)	loss 3.5744 (3.0517)	grad_norm 1.1825 (1.6359/0.7625)	mem 34602MB
[2025-01-19 12:41:56 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][180/312]	eta 0:01:39 lr 0.001516	time 0.8103 (0.7532)	model_time 0.8101 (0.7457)	loss 2.6132 (3.0715)	grad_norm 1.0654 (1.6039/0.6436)	mem 34604MB
[2025-01-19 12:41:58 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][280/312]	eta 0:00:24 lr 0.001510	time 0.8193 (0.7507)	model_time 0.8192 (0.7458)	loss 2.9581 (3.0627)	grad_norm 2.0302 (1.6664/0.7909)	mem 34602MB
[2025-01-19 12:42:03 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][190/312]	eta 0:01:31 lr 0.001515	time 0.7825 (0.7529)	model_time 0.7820 (0.7457)	loss 3.0453 (3.0742)	grad_norm 1.7012 (1.6190/0.6641)	mem 34604MB
[2025-01-19 12:42:06 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][290/312]	eta 0:00:16 lr 0.001509	time 0.8100 (0.7511)	model_time 0.8098 (0.7463)	loss 1.9118 (3.0661)	grad_norm 0.8487 (1.6583/0.7856)	mem 34602MB
[2025-01-19 12:42:11 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][200/312]	eta 0:01:24 lr 0.001515	time 0.7098 (0.7515)	model_time 0.7095 (0.7447)	loss 2.2698 (3.0728)	grad_norm 2.8592 (1.6385/0.6642)	mem 34604MB
[2025-01-19 12:42:13 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][300/312]	eta 0:00:09 lr 0.001508	time 0.7140 (0.7505)	model_time 0.7139 (0.7459)	loss 2.7428 (3.0704)	grad_norm 2.9021 (1.6493/0.7813)	mem 34602MB
[2025-01-19 12:42:18 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][210/312]	eta 0:01:16 lr 0.001514	time 0.7201 (0.7503)	model_time 0.7199 (0.7438)	loss 3.2815 (3.0763)	grad_norm 1.7744 (1.6713/0.6790)	mem 34604MB
[2025-01-19 12:42:21 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][310/312]	eta 0:00:01 lr 0.001508	time 0.7151 (0.7496)	model_time 0.7150 (0.7451)	loss 3.0328 (3.0762)	grad_norm 1.2670 (1.6491/0.7686)	mem 34602MB
[2025-01-19 12:42:21 internimage_b_1k_224] (main.py 519): INFO EPOCH 174 training takes 0:03:53
[2025-01-19 12:42:21 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_174.pth saving......
[2025-01-19 12:42:24 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_174.pth saved !!!
[2025-01-19 12:42:25 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][220/312]	eta 0:01:08 lr 0.001513	time 0.7100 (0.7493)	model_time 0.7098 (0.7430)	loss 2.7412 (3.0808)	grad_norm 1.0092 (1.6631/0.6713)	mem 34604MB
[2025-01-19 12:42:32 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][230/312]	eta 0:01:01 lr 0.001513	time 0.7194 (0.7482)	model_time 0.7193 (0.7423)	loss 2.9237 (3.0705)	grad_norm 1.6969 (1.6686/0.6656)	mem 34604MB
[2025-01-19 12:42:32 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.708 (7.708)	Loss 0.7687 (0.7687)	Acc@1 84.961 (84.961)	Acc@5 97.412 (97.412)	Mem 34602MB
[2025-01-19 12:42:35 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.187 (0.975)	Loss 1.0568 (0.8894)	Acc@1 77.490 (81.716)	Acc@5 94.434 (96.005)	Mem 34602MB
[2025-01-19 12:42:36 internimage_b_1k_224] (main.py 575): INFO [Epoch:174] * Acc@1 81.588 Acc@5 96.045
[2025-01-19 12:42:36 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.6%
[2025-01-19 12:42:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 12:42:39 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 12:42:39 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.59%
[2025-01-19 12:42:40 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][240/312]	eta 0:00:53 lr 0.001512	time 0.7275 (0.7475)	model_time 0.7270 (0.7418)	loss 3.4280 (3.0755)	grad_norm 2.0306 (1.6538/0.6631)	mem 34604MB
[2025-01-19 12:42:46 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.674 (7.674)	Loss 0.6711 (0.6711)	Acc@1 84.546 (84.546)	Acc@5 97.778 (97.778)	Mem 34602MB
[2025-01-19 12:42:47 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][250/312]	eta 0:00:46 lr 0.001512	time 0.7123 (0.7479)	model_time 0.7121 (0.7424)	loss 3.3699 (3.0772)	grad_norm 0.9011 (1.6309/0.6627)	mem 34604MB
[2025-01-19 12:42:50 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.992)	Loss 0.9499 (0.7972)	Acc@1 78.003 (82.096)	Acc@5 94.824 (96.240)	Mem 34602MB
[2025-01-19 12:42:50 internimage_b_1k_224] (main.py 575): INFO [Epoch:174] * Acc@1 81.932 Acc@5 96.293
[2025-01-19 12:42:50 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.9%
[2025-01-19 12:42:50 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:42:54 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:42:54 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.93%
[2025-01-19 12:42:54 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][260/312]	eta 0:00:38 lr 0.001511	time 0.7342 (0.7470)	model_time 0.7340 (0.7417)	loss 3.5554 (3.0825)	grad_norm 1.8322 (1.6415/0.6711)	mem 34604MB
[2025-01-19 12:42:56 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][0/312]	eta 0:10:11 lr 0.001508	time 1.9593 (1.9593)	model_time 0.7417 (0.7417)	loss 3.6659 (3.6659)	grad_norm 1.2094 (1.2094/0.0000)	mem 34602MB
[2025-01-19 12:43:02 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][270/312]	eta 0:00:31 lr 0.001510	time 0.7141 (0.7460)	model_time 0.7136 (0.7409)	loss 3.0053 (3.0797)	grad_norm 1.1992 (1.6337/0.6675)	mem 34604MB
[2025-01-19 12:43:04 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][10/312]	eta 0:04:23 lr 0.001507	time 0.7186 (0.8741)	model_time 0.7185 (0.7631)	loss 2.2740 (2.8736)	grad_norm 1.9610 (1.4702/0.4094)	mem 34602MB
[2025-01-19 12:43:09 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][280/312]	eta 0:00:23 lr 0.001510	time 0.7916 (0.7469)	model_time 0.7911 (0.7419)	loss 3.0939 (3.0801)	grad_norm 1.4642 (1.6248/0.6619)	mem 34604MB
[2025-01-19 12:43:11 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][20/312]	eta 0:03:55 lr 0.001506	time 0.7333 (0.8081)	model_time 0.7331 (0.7499)	loss 2.9751 (2.9975)	grad_norm 2.3413 (1.4855/0.4013)	mem 34602MB
[2025-01-19 12:43:17 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][290/312]	eta 0:00:16 lr 0.001509	time 0.8123 (0.7487)	model_time 0.8119 (0.7439)	loss 2.8527 (3.0725)	grad_norm 1.5434 (1.6188/0.6530)	mem 34604MB
[2025-01-19 12:43:18 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][30/312]	eta 0:03:40 lr 0.001506	time 0.7206 (0.7831)	model_time 0.7204 (0.7435)	loss 3.9617 (3.0986)	grad_norm 2.4861 (1.7237/0.6773)	mem 34602MB
[2025-01-19 12:43:25 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][300/312]	eta 0:00:08 lr 0.001508	time 0.8029 (0.7491)	model_time 0.8028 (0.7445)	loss 2.3093 (3.0736)	grad_norm 1.5731 (1.6247/0.6476)	mem 34604MB
[2025-01-19 12:43:26 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][40/312]	eta 0:03:30 lr 0.001505	time 0.7210 (0.7722)	model_time 0.7206 (0.7421)	loss 3.1700 (3.0846)	grad_norm 1.1873 (1.6321/0.6366)	mem 34602MB
[2025-01-19 12:43:32 internimage_b_1k_224] (main.py 510): INFO Train: [174/300][310/312]	eta 0:00:01 lr 0.001508	time 0.7144 (0.7486)	model_time 0.7143 (0.7441)	loss 3.4113 (3.0784)	grad_norm 2.5486 (1.6255/0.6491)	mem 34604MB
[2025-01-19 12:43:33 internimage_b_1k_224] (main.py 519): INFO EPOCH 174 training takes 0:03:53
[2025-01-19 12:43:33 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_174.pth saving......
[2025-01-19 12:43:33 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][50/312]	eta 0:03:21 lr 0.001504	time 0.7213 (0.7675)	model_time 0.7212 (0.7433)	loss 3.9328 (3.0675)	grad_norm 2.7590 (1.6559/0.6207)	mem 34602MB
[2025-01-19 12:43:36 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_174.pth saved !!!
[2025-01-19 12:43:40 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][60/312]	eta 0:03:12 lr 0.001504	time 0.7166 (0.7623)	model_time 0.7162 (0.7420)	loss 3.0225 (3.0642)	grad_norm 2.3185 (1.6766/0.5945)	mem 34602MB
[2025-01-19 12:43:44 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.594 (7.594)	Loss 0.7273 (0.7273)	Acc@1 83.984 (83.984)	Acc@5 97.485 (97.485)	Mem 34604MB
[2025-01-19 12:43:47 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.969)	Loss 0.9769 (0.8478)	Acc@1 78.906 (81.838)	Acc@5 94.629 (95.987)	Mem 34604MB
[2025-01-19 12:43:47 internimage_b_1k_224] (main.py 575): INFO [Epoch:174] * Acc@1 81.684 Acc@5 96.033
[2025-01-19 12:43:47 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.7%
[2025-01-19 12:43:47 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 12:43:48 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][70/312]	eta 0:03:04 lr 0.001503	time 0.7476 (0.7609)	model_time 0.7471 (0.7434)	loss 3.1136 (3.0447)	grad_norm 2.0455 (1.7513/0.6826)	mem 34602MB
[2025-01-19 12:43:51 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 12:43:51 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.68%
[2025-01-19 12:43:56 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][80/312]	eta 0:02:56 lr 0.001502	time 0.8046 (0.7602)	model_time 0.8045 (0.7448)	loss 2.5765 (3.0724)	grad_norm 2.0758 (1.7453/0.6540)	mem 34602MB
[2025-01-19 12:43:58 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.610 (7.610)	Loss 0.6701 (0.6701)	Acc@1 84.814 (84.814)	Acc@5 97.803 (97.803)	Mem 34604MB
[2025-01-19 12:44:01 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.969)	Loss 0.9503 (0.7964)	Acc@1 78.003 (82.198)	Acc@5 94.849 (96.236)	Mem 34604MB
[2025-01-19 12:44:02 internimage_b_1k_224] (main.py 575): INFO [Epoch:174] * Acc@1 82.066 Acc@5 96.289
[2025-01-19 12:44:02 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.1%
[2025-01-19 12:44:02 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:44:03 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][90/312]	eta 0:02:48 lr 0.001502	time 0.7296 (0.7600)	model_time 0.7295 (0.7462)	loss 2.4741 (3.0688)	grad_norm 0.8099 (1.7809/0.6992)	mem 34602MB
[2025-01-19 12:44:05 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:44:05 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.07%
[2025-01-19 12:44:07 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][0/312]	eta 0:10:27 lr 0.001508	time 2.0110 (2.0110)	model_time 0.7281 (0.7281)	loss 2.8236 (2.8236)	grad_norm 1.5011 (1.5011/0.0000)	mem 34604MB
[2025-01-19 12:44:11 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][100/312]	eta 0:02:41 lr 0.001501	time 0.7283 (0.7598)	model_time 0.7279 (0.7474)	loss 3.5987 (3.0416)	grad_norm 2.6480 (1.8239/0.7470)	mem 34602MB
[2025-01-19 12:44:14 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][10/312]	eta 0:04:15 lr 0.001507	time 0.7134 (0.8467)	model_time 0.7129 (0.7297)	loss 2.8482 (2.9776)	grad_norm 1.0533 (1.2025/0.4059)	mem 34604MB
[2025-01-19 12:44:18 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][110/312]	eta 0:02:32 lr 0.001500	time 0.7225 (0.7573)	model_time 0.7224 (0.7459)	loss 3.3755 (3.0219)	grad_norm 1.4746 (1.7983/0.7276)	mem 34602MB
[2025-01-19 12:44:22 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][20/312]	eta 0:03:51 lr 0.001506	time 0.7256 (0.7923)	model_time 0.7255 (0.7308)	loss 3.6829 (3.0424)	grad_norm 1.3108 (1.2501/0.4393)	mem 34604MB
[2025-01-19 12:44:25 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][120/312]	eta 0:02:25 lr 0.001500	time 0.8144 (0.7556)	model_time 0.8140 (0.7452)	loss 2.4577 (3.0326)	grad_norm 2.2122 (1.8124/0.7485)	mem 34602MB
[2025-01-19 12:44:29 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][30/312]	eta 0:03:37 lr 0.001506	time 0.7225 (0.7721)	model_time 0.7223 (0.7304)	loss 3.5491 (3.1264)	grad_norm 2.1571 (1.3473/0.4601)	mem 34604MB
[2025-01-19 12:44:33 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][130/312]	eta 0:02:17 lr 0.001499	time 0.7183 (0.7550)	model_time 0.7178 (0.7454)	loss 3.4872 (3.0225)	grad_norm 1.9512 (1.8044/0.7328)	mem 34602MB
[2025-01-19 12:44:36 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][40/312]	eta 0:03:27 lr 0.001505	time 0.7111 (0.7630)	model_time 0.7106 (0.7314)	loss 3.4324 (3.1418)	grad_norm 4.5389 (1.4493/0.6705)	mem 34604MB
[2025-01-19 12:44:40 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][140/312]	eta 0:02:09 lr 0.001499	time 0.7313 (0.7542)	model_time 0.7312 (0.7452)	loss 2.5545 (3.0183)	grad_norm 1.2526 (1.7570/0.7309)	mem 34602MB
[2025-01-19 12:44:44 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][50/312]	eta 0:03:18 lr 0.001504	time 0.7157 (0.7558)	model_time 0.7155 (0.7303)	loss 3.2927 (3.1870)	grad_norm 2.0532 (1.6216/0.9533)	mem 34604MB
[2025-01-19 12:44:48 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][150/312]	eta 0:02:01 lr 0.001498	time 0.7369 (0.7522)	model_time 0.7365 (0.7438)	loss 3.6242 (3.0228)	grad_norm 1.0458 (1.7209/0.7222)	mem 34602MB
[2025-01-19 12:44:51 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][60/312]	eta 0:03:09 lr 0.001504	time 0.7254 (0.7510)	model_time 0.7253 (0.7296)	loss 2.8354 (3.1780)	grad_norm 1.4419 (1.6817/0.9365)	mem 34604MB
[2025-01-19 12:44:55 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][160/312]	eta 0:01:54 lr 0.001497	time 0.7278 (0.7512)	model_time 0.7276 (0.7432)	loss 3.2003 (3.0231)	grad_norm 0.9482 (1.7323/0.7293)	mem 34602MB
[2025-01-19 12:44:58 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][70/312]	eta 0:03:01 lr 0.001503	time 0.7243 (0.7492)	model_time 0.7241 (0.7308)	loss 3.7465 (3.1540)	grad_norm 2.4784 (1.6756/0.8877)	mem 34604MB
[2025-01-19 12:45:02 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][170/312]	eta 0:01:46 lr 0.001497	time 0.7165 (0.7510)	model_time 0.7164 (0.7435)	loss 2.9088 (3.0114)	grad_norm 1.2849 (1.7437/0.7321)	mem 34602MB
[2025-01-19 12:45:05 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][80/312]	eta 0:02:53 lr 0.001502	time 0.7362 (0.7464)	model_time 0.7360 (0.7302)	loss 3.5730 (3.1817)	grad_norm 0.8249 (1.6693/0.8604)	mem 34604MB
[2025-01-19 12:45:10 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][180/312]	eta 0:01:39 lr 0.001496	time 0.7214 (0.7504)	model_time 0.7209 (0.7433)	loss 3.7428 (3.0214)	grad_norm 4.4399 (1.7683/0.7663)	mem 34602MB
[2025-01-19 12:45:13 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][90/312]	eta 0:02:46 lr 0.001502	time 0.7995 (0.7498)	model_time 0.7992 (0.7353)	loss 3.4823 (3.1807)	grad_norm 2.7441 (1.7362/0.8849)	mem 34604MB
[2025-01-19 12:45:17 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][190/312]	eta 0:01:31 lr 0.001495	time 0.7229 (0.7506)	model_time 0.7225 (0.7438)	loss 3.0231 (3.0228)	grad_norm 1.7881 (1.7650/0.7617)	mem 34602MB
[2025-01-19 12:45:21 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][100/312]	eta 0:02:39 lr 0.001501	time 0.8091 (0.7526)	model_time 0.8086 (0.7395)	loss 2.7939 (3.1856)	grad_norm 1.5634 (1.7538/0.8453)	mem 34604MB
[2025-01-19 12:45:25 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][200/312]	eta 0:01:24 lr 0.001495	time 0.7992 (0.7511)	model_time 0.7987 (0.7446)	loss 3.1174 (3.0255)	grad_norm 1.7865 (1.7411/0.7552)	mem 34602MB
[2025-01-19 12:45:29 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][110/312]	eta 0:02:32 lr 0.001500	time 0.7239 (0.7539)	model_time 0.7237 (0.7421)	loss 3.6898 (3.1825)	grad_norm 1.4549 (1.7458/0.8355)	mem 34604MB
[2025-01-19 12:45:33 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][210/312]	eta 0:01:16 lr 0.001494	time 0.7445 (0.7516)	model_time 0.7444 (0.7454)	loss 2.9468 (3.0247)	grad_norm 1.1243 (1.7126/0.7533)	mem 34602MB
[2025-01-19 12:45:36 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][120/312]	eta 0:02:24 lr 0.001500	time 0.8111 (0.7534)	model_time 0.8107 (0.7424)	loss 3.3277 (3.1601)	grad_norm 2.0143 (1.7139/0.8155)	mem 34604MB
[2025-01-19 12:45:40 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][220/312]	eta 0:01:09 lr 0.001493	time 0.7160 (0.7522)	model_time 0.7156 (0.7464)	loss 3.9662 (3.0270)	grad_norm 1.4349 (1.6907/0.7447)	mem 34602MB
[2025-01-19 12:45:43 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][130/312]	eta 0:02:16 lr 0.001499	time 0.7243 (0.7514)	model_time 0.7241 (0.7413)	loss 3.2361 (3.1667)	grad_norm 0.9771 (1.6836/0.7942)	mem 34604MB
[2025-01-19 12:45:48 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][230/312]	eta 0:01:01 lr 0.001493	time 0.7251 (0.7514)	model_time 0.7246 (0.7458)	loss 3.7761 (3.0292)	grad_norm 1.4602 (1.6940/0.7404)	mem 34602MB
[2025-01-19 12:45:51 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][140/312]	eta 0:02:08 lr 0.001499	time 0.7338 (0.7497)	model_time 0.7333 (0.7402)	loss 3.3231 (3.1712)	grad_norm 1.7293 (1.6412/0.7881)	mem 34604MB
[2025-01-19 12:45:55 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][240/312]	eta 0:00:54 lr 0.001492	time 0.7903 (0.7507)	model_time 0.7901 (0.7453)	loss 2.3101 (3.0229)	grad_norm 1.7443 (1.6824/0.7338)	mem 34602MB
[2025-01-19 12:45:58 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][150/312]	eta 0:02:01 lr 0.001498	time 0.7341 (0.7478)	model_time 0.7340 (0.7390)	loss 3.1647 (3.1651)	grad_norm 1.6183 (1.6501/0.7689)	mem 34604MB
[2025-01-19 12:46:02 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][250/312]	eta 0:00:46 lr 0.001492	time 0.7193 (0.7507)	model_time 0.7192 (0.7455)	loss 3.1061 (3.0372)	grad_norm 1.0546 (1.6735/0.7229)	mem 34602MB
[2025-01-19 12:46:05 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][160/312]	eta 0:01:53 lr 0.001497	time 0.7212 (0.7470)	model_time 0.7210 (0.7387)	loss 3.6005 (3.1595)	grad_norm 2.1814 (1.6661/0.7596)	mem 34604MB
[2025-01-19 12:46:10 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][260/312]	eta 0:00:39 lr 0.001491	time 0.7300 (0.7504)	model_time 0.7296 (0.7454)	loss 3.7747 (3.0309)	grad_norm 1.6583 (1.6582/0.7150)	mem 34602MB
[2025-01-19 12:46:13 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][170/312]	eta 0:01:45 lr 0.001497	time 0.7375 (0.7457)	model_time 0.7373 (0.7379)	loss 2.3017 (3.1486)	grad_norm 1.2599 (1.6703/0.7454)	mem 34604MB
[2025-01-19 12:46:17 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][270/312]	eta 0:00:31 lr 0.001490	time 0.7244 (0.7495)	model_time 0.7243 (0.7446)	loss 2.9252 (3.0387)	grad_norm 1.6917 (1.6512/0.7097)	mem 34602MB
[2025-01-19 12:46:20 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][180/312]	eta 0:01:38 lr 0.001496	time 0.7425 (0.7446)	model_time 0.7423 (0.7372)	loss 3.2697 (3.1358)	grad_norm 0.9480 (1.6949/0.7632)	mem 34604MB
[2025-01-19 12:46:24 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][280/312]	eta 0:00:23 lr 0.001490	time 0.7208 (0.7488)	model_time 0.7203 (0.7441)	loss 3.3283 (3.0463)	grad_norm 1.4136 (1.6393/0.7041)	mem 34602MB
[2025-01-19 12:46:27 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][190/312]	eta 0:01:30 lr 0.001495	time 0.7209 (0.7443)	model_time 0.7202 (0.7372)	loss 3.8683 (3.1470)	grad_norm 1.0798 (1.6795/0.7518)	mem 34604MB
[2025-01-19 12:46:32 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][290/312]	eta 0:00:16 lr 0.001489	time 0.7896 (0.7491)	model_time 0.7894 (0.7446)	loss 3.3443 (3.0459)	grad_norm 2.1507 (1.6546/0.7091)	mem 34602MB
[2025-01-19 12:46:35 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][200/312]	eta 0:01:23 lr 0.001495	time 0.7179 (0.7438)	model_time 0.7177 (0.7371)	loss 3.4230 (3.1385)	grad_norm 1.0716 (1.6744/0.7445)	mem 34604MB
[2025-01-19 12:46:39 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][300/312]	eta 0:00:08 lr 0.001488	time 0.7103 (0.7485)	model_time 0.7102 (0.7441)	loss 3.0003 (3.0588)	grad_norm 1.9033 (1.6843/0.7351)	mem 34602MB
[2025-01-19 12:46:42 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][210/312]	eta 0:01:16 lr 0.001494	time 0.8037 (0.7455)	model_time 0.8035 (0.7391)	loss 2.9697 (3.1414)	grad_norm 1.5332 (1.6693/0.7340)	mem 34604MB
[2025-01-19 12:46:47 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][310/312]	eta 0:00:01 lr 0.001488	time 0.7127 (0.7481)	model_time 0.7126 (0.7438)	loss 2.8474 (3.0608)	grad_norm 2.3892 (1.6992/0.7421)	mem 34602MB
[2025-01-19 12:46:47 internimage_b_1k_224] (main.py 519): INFO EPOCH 175 training takes 0:03:53
[2025-01-19 12:46:47 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_175.pth saving......
[2025-01-19 12:46:50 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][220/312]	eta 0:01:08 lr 0.001493	time 0.7145 (0.7469)	model_time 0.7144 (0.7407)	loss 2.9799 (3.1458)	grad_norm 0.9097 (1.6816/0.7418)	mem 34604MB
[2025-01-19 12:46:50 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_175.pth saved !!!
[2025-01-19 12:46:58 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][230/312]	eta 0:01:01 lr 0.001493	time 0.7352 (0.7477)	model_time 0.7350 (0.7418)	loss 2.1745 (3.1368)	grad_norm 1.4713 (1.6734/0.7287)	mem 34604MB
[2025-01-19 12:46:58 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.454 (7.454)	Loss 0.7552 (0.7552)	Acc@1 83.862 (83.862)	Acc@5 97.485 (97.485)	Mem 34602MB
[2025-01-19 12:47:01 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.962)	Loss 1.0125 (0.8711)	Acc@1 78.198 (81.705)	Acc@5 94.702 (95.974)	Mem 34602MB
[2025-01-19 12:47:01 internimage_b_1k_224] (main.py 575): INFO [Epoch:175] * Acc@1 81.622 Acc@5 96.021
[2025-01-19 12:47:01 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.6%
[2025-01-19 12:47:01 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 12:47:05 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 12:47:05 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.62%
[2025-01-19 12:47:05 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][240/312]	eta 0:00:53 lr 0.001492	time 0.7183 (0.7474)	model_time 0.7181 (0.7417)	loss 3.3931 (3.1310)	grad_norm 2.5530 (1.6871/0.7288)	mem 34604MB
[2025-01-19 12:47:12 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.448 (7.448)	Loss 0.6720 (0.6720)	Acc@1 84.570 (84.570)	Acc@5 97.778 (97.778)	Mem 34602MB
[2025-01-19 12:47:12 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][250/312]	eta 0:00:46 lr 0.001492	time 0.7265 (0.7469)	model_time 0.7263 (0.7415)	loss 3.4818 (3.1260)	grad_norm 0.9626 (1.6982/0.7279)	mem 34604MB
[2025-01-19 12:47:15 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.947)	Loss 0.9497 (0.7977)	Acc@1 78.101 (82.124)	Acc@5 94.873 (96.251)	Mem 34602MB
[2025-01-19 12:47:16 internimage_b_1k_224] (main.py 575): INFO [Epoch:175] * Acc@1 81.966 Acc@5 96.305
[2025-01-19 12:47:16 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.0%
[2025-01-19 12:47:16 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:47:19 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:47:19 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 81.97%
[2025-01-19 12:47:20 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][260/312]	eta 0:00:38 lr 0.001491	time 0.7296 (0.7462)	model_time 0.7294 (0.7409)	loss 3.5085 (3.1228)	grad_norm 1.1685 (1.7025/0.7228)	mem 34604MB
[2025-01-19 12:47:21 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][0/312]	eta 0:10:56 lr 0.001488	time 2.1026 (2.1026)	model_time 0.7477 (0.7477)	loss 3.5263 (3.5263)	grad_norm 2.9391 (2.9391/0.0000)	mem 34602MB
[2025-01-19 12:47:27 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][270/312]	eta 0:00:31 lr 0.001490	time 0.7104 (0.7456)	model_time 0.7102 (0.7406)	loss 3.3859 (3.1363)	grad_norm 1.0538 (1.6852/0.7165)	mem 34604MB
[2025-01-19 12:47:29 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][10/312]	eta 0:04:25 lr 0.001487	time 0.8021 (0.8788)	model_time 0.8019 (0.7553)	loss 3.5792 (3.0172)	grad_norm 1.0549 (1.4372/0.5653)	mem 34602MB
[2025-01-19 12:47:34 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][280/312]	eta 0:00:23 lr 0.001490	time 0.7279 (0.7449)	model_time 0.7277 (0.7400)	loss 3.8436 (3.1422)	grad_norm 1.6574 (1.6951/0.7196)	mem 34604MB
[2025-01-19 12:47:37 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][20/312]	eta 0:04:01 lr 0.001486	time 0.7212 (0.8278)	model_time 0.7210 (0.7629)	loss 3.3643 (3.0670)	grad_norm 1.7859 (1.3984/0.4800)	mem 34602MB
[2025-01-19 12:47:42 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][290/312]	eta 0:00:16 lr 0.001489	time 0.7149 (0.7443)	model_time 0.7147 (0.7396)	loss 2.7102 (3.1309)	grad_norm 1.6963 (1.6879/0.7102)	mem 34604MB
[2025-01-19 12:47:44 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][30/312]	eta 0:03:47 lr 0.001486	time 0.7438 (0.8085)	model_time 0.7433 (0.7644)	loss 3.0031 (3.0991)	grad_norm 1.0256 (1.5561/0.6012)	mem 34602MB
[2025-01-19 12:47:49 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][300/312]	eta 0:00:08 lr 0.001488	time 0.7141 (0.7438)	model_time 0.7140 (0.7392)	loss 3.2797 (3.1369)	grad_norm 2.6250 (1.6857/0.7043)	mem 34604MB
[2025-01-19 12:47:52 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][40/312]	eta 0:03:34 lr 0.001485	time 0.7157 (0.7898)	model_time 0.7155 (0.7564)	loss 3.1262 (3.0545)	grad_norm 0.9223 (1.6438/0.6979)	mem 34602MB
[2025-01-19 12:47:56 internimage_b_1k_224] (main.py 510): INFO Train: [175/300][310/312]	eta 0:00:01 lr 0.001488	time 0.7133 (0.7434)	model_time 0.7132 (0.7390)	loss 2.0857 (3.1319)	grad_norm 3.2768 (1.7052/0.7029)	mem 34604MB
[2025-01-19 12:47:57 internimage_b_1k_224] (main.py 519): INFO EPOCH 175 training takes 0:03:51
[2025-01-19 12:47:57 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_175.pth saving......
[2025-01-19 12:47:59 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][50/312]	eta 0:03:24 lr 0.001484	time 0.7157 (0.7792)	model_time 0.7151 (0.7522)	loss 3.2194 (3.0541)	grad_norm 1.2195 (1.5961/0.6485)	mem 34602MB
[2025-01-19 12:48:00 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_175.pth saved !!!
[2025-01-19 12:48:07 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][60/312]	eta 0:03:15 lr 0.001484	time 0.8944 (0.7760)	model_time 0.8943 (0.7534)	loss 3.3903 (3.0145)	grad_norm 1.0317 (1.6085/0.6701)	mem 34602MB
[2025-01-19 12:48:08 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.649 (7.649)	Loss 0.7724 (0.7724)	Acc@1 84.204 (84.204)	Acc@5 97.412 (97.412)	Mem 34604MB
[2025-01-19 12:48:11 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.977)	Loss 1.0223 (0.8828)	Acc@1 78.345 (81.698)	Acc@5 94.409 (96.080)	Mem 34604MB
[2025-01-19 12:48:11 internimage_b_1k_224] (main.py 575): INFO [Epoch:175] * Acc@1 81.632 Acc@5 96.103
[2025-01-19 12:48:11 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.6%
[2025-01-19 12:48:11 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.68%
[2025-01-19 12:48:14 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][70/312]	eta 0:03:06 lr 0.001483	time 0.7676 (0.7704)	model_time 0.7674 (0.7510)	loss 3.3766 (3.0200)	grad_norm 0.9216 (1.6001/0.6430)	mem 34602MB
[2025-01-19 12:48:20 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.164 (9.164)	Loss 0.6713 (0.6713)	Acc@1 84.839 (84.839)	Acc@5 97.852 (97.852)	Mem 34604MB
[2025-01-19 12:48:21 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][80/312]	eta 0:02:57 lr 0.001482	time 0.7356 (0.7652)	model_time 0.7354 (0.7481)	loss 3.0082 (3.0210)	grad_norm 1.0603 (1.6295/0.6514)	mem 34602MB
[2025-01-19 12:48:25 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.260)	Loss 0.9500 (0.7969)	Acc@1 78.149 (82.218)	Acc@5 94.824 (96.258)	Mem 34604MB
[2025-01-19 12:48:25 internimage_b_1k_224] (main.py 575): INFO [Epoch:175] * Acc@1 82.084 Acc@5 96.307
[2025-01-19 12:48:25 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.1%
[2025-01-19 12:48:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:48:29 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:48:29 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.08%
[2025-01-19 12:48:29 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][90/312]	eta 0:02:49 lr 0.001482	time 0.7250 (0.7620)	model_time 0.7248 (0.7467)	loss 2.9040 (3.0194)	grad_norm 2.5363 (1.6275/0.6470)	mem 34602MB
[2025-01-19 12:48:31 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][0/312]	eta 0:11:08 lr 0.001488	time 2.1413 (2.1413)	model_time 0.7267 (0.7267)	loss 2.8644 (2.8644)	grad_norm 4.0718 (4.0718/0.0000)	mem 34604MB
[2025-01-19 12:48:36 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][100/312]	eta 0:02:41 lr 0.001481	time 0.8024 (0.7613)	model_time 0.8022 (0.7475)	loss 2.3794 (3.0158)	grad_norm 1.1309 (1.6315/0.6529)	mem 34602MB
[2025-01-19 12:48:38 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][10/312]	eta 0:04:19 lr 0.001487	time 0.7289 (0.8598)	model_time 0.7288 (0.7309)	loss 3.9882 (3.3763)	grad_norm 1.4140 (1.7987/0.8055)	mem 34604MB
[2025-01-19 12:48:44 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][110/312]	eta 0:02:33 lr 0.001481	time 0.7171 (0.7589)	model_time 0.7169 (0.7464)	loss 3.5832 (3.0359)	grad_norm 1.2635 (1.6254/0.6324)	mem 34602MB
[2025-01-19 12:48:46 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][20/312]	eta 0:04:00 lr 0.001486	time 0.8075 (0.8249)	model_time 0.8074 (0.7572)	loss 3.1976 (3.0905)	grad_norm 1.4402 (1.6895/0.7018)	mem 34604MB
[2025-01-19 12:48:51 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][120/312]	eta 0:02:25 lr 0.001480	time 0.7170 (0.7579)	model_time 0.7166 (0.7463)	loss 4.1254 (3.0494)	grad_norm 1.0674 (1.5855/0.6295)	mem 34602MB
[2025-01-19 12:48:54 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][30/312]	eta 0:03:48 lr 0.001486	time 0.7182 (0.8090)	model_time 0.7180 (0.7630)	loss 3.1342 (3.0607)	grad_norm 1.4531 (1.5693/0.6396)	mem 34604MB
[2025-01-19 12:48:59 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][130/312]	eta 0:02:17 lr 0.001479	time 0.8012 (0.7577)	model_time 0.8008 (0.7469)	loss 2.8388 (3.0341)	grad_norm 1.5174 (1.6138/0.6330)	mem 34602MB
[2025-01-19 12:49:01 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][40/312]	eta 0:03:37 lr 0.001485	time 0.7082 (0.7990)	model_time 0.7077 (0.7641)	loss 3.4731 (3.0707)	grad_norm 4.3292 (1.7287/0.7535)	mem 34604MB
[2025-01-19 12:49:06 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][140/312]	eta 0:02:10 lr 0.001479	time 0.7212 (0.7583)	model_time 0.7211 (0.7483)	loss 3.5637 (3.0451)	grad_norm 1.3661 (1.6378/0.6598)	mem 34602MB
[2025-01-19 12:49:09 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][50/312]	eta 0:03:26 lr 0.001484	time 0.7191 (0.7886)	model_time 0.7189 (0.7605)	loss 2.9012 (3.0952)	grad_norm 3.7450 (1.8792/0.8976)	mem 34604MB
[2025-01-19 12:49:14 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][150/312]	eta 0:02:02 lr 0.001478	time 0.7930 (0.7581)	model_time 0.7925 (0.7488)	loss 2.7385 (3.0504)	grad_norm 1.7779 (1.6521/0.6628)	mem 34602MB
[2025-01-19 12:49:16 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][60/312]	eta 0:03:16 lr 0.001484	time 0.7258 (0.7804)	model_time 0.7256 (0.7569)	loss 3.2935 (3.1120)	grad_norm 2.2449 (1.8529/0.8565)	mem 34604MB
[2025-01-19 12:49:21 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][160/312]	eta 0:01:55 lr 0.001477	time 0.7275 (0.7570)	model_time 0.7270 (0.7482)	loss 3.0823 (3.0631)	grad_norm 1.9514 (1.6673/0.6750)	mem 34602MB
[2025-01-19 12:49:24 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][70/312]	eta 0:03:07 lr 0.001483	time 0.7260 (0.7729)	model_time 0.7254 (0.7527)	loss 3.8238 (3.1086)	grad_norm 2.1321 (1.8501/0.8875)	mem 34604MB
[2025-01-19 12:49:29 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][170/312]	eta 0:01:47 lr 0.001477	time 0.7155 (0.7559)	model_time 0.7153 (0.7476)	loss 2.8402 (3.0560)	grad_norm 1.3469 (1.6756/0.6797)	mem 34602MB
[2025-01-19 12:49:31 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][80/312]	eta 0:02:57 lr 0.001482	time 0.7274 (0.7667)	model_time 0.7272 (0.7489)	loss 2.7558 (3.0802)	grad_norm 0.9201 (1.8707/0.8662)	mem 34604MB
[2025-01-19 12:49:36 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][180/312]	eta 0:01:39 lr 0.001476	time 0.8159 (0.7558)	model_time 0.8154 (0.7480)	loss 2.9430 (3.0641)	grad_norm 1.3480 (1.6695/0.6938)	mem 34602MB
[2025-01-19 12:49:38 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][90/312]	eta 0:02:49 lr 0.001482	time 0.7427 (0.7625)	model_time 0.7426 (0.7466)	loss 2.3400 (3.0556)	grad_norm 1.5026 (1.8839/0.8742)	mem 34604MB
[2025-01-19 12:49:44 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][190/312]	eta 0:01:32 lr 0.001475	time 0.7288 (0.7549)	model_time 0.7284 (0.7475)	loss 4.1195 (3.0637)	grad_norm 1.5216 (1.6613/0.6889)	mem 34602MB
[2025-01-19 12:49:45 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][100/312]	eta 0:02:40 lr 0.001481	time 0.7546 (0.7591)	model_time 0.7545 (0.7447)	loss 2.6446 (3.0698)	grad_norm 1.5338 (1.8891/0.8521)	mem 34604MB
[2025-01-19 12:49:51 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][200/312]	eta 0:01:24 lr 0.001475	time 0.7212 (0.7534)	model_time 0.7210 (0.7463)	loss 3.1289 (3.0659)	grad_norm 2.1743 (1.6818/0.7041)	mem 34602MB
[2025-01-19 12:49:53 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][110/312]	eta 0:02:32 lr 0.001481	time 0.7287 (0.7561)	model_time 0.7282 (0.7430)	loss 2.8148 (3.0464)	grad_norm 1.4387 (1.8511/0.8350)	mem 34604MB
[2025-01-19 12:49:58 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][210/312]	eta 0:01:16 lr 0.001474	time 0.7174 (0.7527)	model_time 0.7173 (0.7459)	loss 3.1044 (3.0688)	grad_norm 1.3408 (1.6828/0.6963)	mem 34602MB
[2025-01-19 12:50:00 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][120/312]	eta 0:02:24 lr 0.001480	time 0.7124 (0.7532)	model_time 0.7122 (0.7411)	loss 2.8808 (3.0577)	grad_norm 2.3442 (1.8610/0.8280)	mem 34604MB
[2025-01-19 12:50:06 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][220/312]	eta 0:01:09 lr 0.001473	time 0.8281 (0.7532)	model_time 0.8276 (0.7467)	loss 2.6069 (3.0731)	grad_norm 1.2193 (1.6672/0.6847)	mem 34602MB
[2025-01-19 12:50:07 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][130/312]	eta 0:02:16 lr 0.001479	time 0.7244 (0.7513)	model_time 0.7240 (0.7401)	loss 2.7307 (3.0564)	grad_norm 1.0372 (1.8391/0.8119)	mem 34604MB
[2025-01-19 12:50:13 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][230/312]	eta 0:01:01 lr 0.001473	time 0.8078 (0.7529)	model_time 0.8077 (0.7467)	loss 2.6479 (3.0707)	grad_norm 1.6339 (1.6808/0.6885)	mem 34602MB
[2025-01-19 12:50:15 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][140/312]	eta 0:02:09 lr 0.001479	time 0.7901 (0.7529)	model_time 0.7896 (0.7425)	loss 2.8230 (3.0531)	grad_norm 1.7079 (1.8452/0.8042)	mem 34604MB
[2025-01-19 12:50:21 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][240/312]	eta 0:00:54 lr 0.001472	time 0.7160 (0.7524)	model_time 0.7159 (0.7464)	loss 2.7885 (3.0673)	grad_norm 1.0607 (1.6704/0.6820)	mem 34602MB
[2025-01-19 12:50:23 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][150/312]	eta 0:02:02 lr 0.001478	time 0.8076 (0.7553)	model_time 0.8075 (0.7456)	loss 3.3996 (3.0539)	grad_norm 2.1203 (1.8512/0.8034)	mem 34604MB
[2025-01-19 12:50:28 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][250/312]	eta 0:00:46 lr 0.001472	time 0.7962 (0.7526)	model_time 0.7960 (0.7469)	loss 2.4375 (3.0647)	grad_norm 0.8840 (1.6540/0.6757)	mem 34602MB
[2025-01-19 12:50:30 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][160/312]	eta 0:01:54 lr 0.001477	time 0.7198 (0.7556)	model_time 0.7193 (0.7464)	loss 2.1524 (3.0570)	grad_norm 1.8070 (1.8520/0.7891)	mem 34604MB
[2025-01-19 12:50:36 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][260/312]	eta 0:00:39 lr 0.001471	time 0.7163 (0.7530)	model_time 0.7161 (0.7474)	loss 3.4615 (3.0653)	grad_norm 1.0968 (1.6517/0.6807)	mem 34602MB
[2025-01-19 12:50:38 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][170/312]	eta 0:01:47 lr 0.001477	time 0.7118 (0.7548)	model_time 0.7113 (0.7461)	loss 3.1205 (3.0511)	grad_norm 0.7701 (1.8336/0.7833)	mem 34604MB
[2025-01-19 12:50:44 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][270/312]	eta 0:00:31 lr 0.001470	time 0.7955 (0.7539)	model_time 0.7951 (0.7485)	loss 3.2168 (3.0704)	grad_norm 1.5968 (1.6531/0.6715)	mem 34602MB
[2025-01-19 12:50:45 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][180/312]	eta 0:01:39 lr 0.001476	time 0.7457 (0.7537)	model_time 0.7455 (0.7456)	loss 3.1579 (3.0635)	grad_norm 0.8209 (1.7933/0.7840)	mem 34604MB
[2025-01-19 12:50:51 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][280/312]	eta 0:00:24 lr 0.001470	time 0.7237 (0.7534)	model_time 0.7233 (0.7482)	loss 2.5412 (3.0688)	grad_norm 1.3145 (1.6517/0.6649)	mem 34602MB
[2025-01-19 12:50:52 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][190/312]	eta 0:01:31 lr 0.001475	time 0.7109 (0.7523)	model_time 0.7107 (0.7446)	loss 3.4858 (3.0676)	grad_norm 1.0035 (1.7935/0.7812)	mem 34604MB
[2025-01-19 12:50:58 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][290/312]	eta 0:00:16 lr 0.001469	time 0.7275 (0.7526)	model_time 0.7273 (0.7476)	loss 3.6363 (3.0730)	grad_norm 0.8410 (1.6390/0.6700)	mem 34602MB
[2025-01-19 12:51:00 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][200/312]	eta 0:01:24 lr 0.001475	time 0.7187 (0.7511)	model_time 0.7183 (0.7437)	loss 2.4405 (3.0587)	grad_norm 3.3416 (1.8055/0.7797)	mem 34604MB
[2025-01-19 12:51:06 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][300/312]	eta 0:00:09 lr 0.001468	time 0.7136 (0.7526)	model_time 0.7135 (0.7477)	loss 2.5826 (3.0737)	grad_norm 1.9685 (1.6426/0.6681)	mem 34602MB
[2025-01-19 12:51:07 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][210/312]	eta 0:01:16 lr 0.001474	time 0.7281 (0.7503)	model_time 0.7278 (0.7433)	loss 3.2052 (3.0683)	grad_norm 1.5697 (1.8283/0.7966)	mem 34604MB
[2025-01-19 12:51:13 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][310/312]	eta 0:00:01 lr 0.001468	time 0.7136 (0.7519)	model_time 0.7135 (0.7472)	loss 2.9438 (3.0772)	grad_norm 1.0110 (1.6686/0.6779)	mem 34602MB
[2025-01-19 12:51:14 internimage_b_1k_224] (main.py 519): INFO EPOCH 176 training takes 0:03:54
[2025-01-19 12:51:14 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_176.pth saving......
[2025-01-19 12:51:14 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][220/312]	eta 0:01:08 lr 0.001473	time 0.7157 (0.7491)	model_time 0.7155 (0.7424)	loss 2.9678 (3.0710)	grad_norm 1.8370 (1.8252/0.7850)	mem 34604MB
[2025-01-19 12:51:17 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_176.pth saved !!!
[2025-01-19 12:51:22 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][230/312]	eta 0:01:01 lr 0.001473	time 0.7249 (0.7483)	model_time 0.7247 (0.7418)	loss 2.6205 (3.0709)	grad_norm 1.6305 (1.8065/0.7748)	mem 34604MB
[2025-01-19 12:51:25 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.633 (7.633)	Loss 0.7550 (0.7550)	Acc@1 84.351 (84.351)	Acc@5 97.241 (97.241)	Mem 34602MB
[2025-01-19 12:51:28 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.007)	Loss 1.0196 (0.8750)	Acc@1 78.149 (81.896)	Acc@5 94.287 (95.974)	Mem 34602MB
[2025-01-19 12:51:28 internimage_b_1k_224] (main.py 575): INFO [Epoch:176] * Acc@1 81.702 Acc@5 95.981
[2025-01-19 12:51:28 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.7%
[2025-01-19 12:51:28 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 12:51:29 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][240/312]	eta 0:00:53 lr 0.001472	time 0.7457 (0.7473)	model_time 0.7455 (0.7411)	loss 3.4748 (3.0719)	grad_norm 1.3551 (1.7986/0.7658)	mem 34604MB
[2025-01-19 12:51:32 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 12:51:32 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.70%
[2025-01-19 12:51:36 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][250/312]	eta 0:00:46 lr 0.001472	time 0.7196 (0.7467)	model_time 0.7191 (0.7407)	loss 2.6617 (3.0666)	grad_norm 1.6619 (1.7976/0.7726)	mem 34604MB
[2025-01-19 12:51:39 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.733 (7.733)	Loss 0.6731 (0.6731)	Acc@1 84.619 (84.619)	Acc@5 97.778 (97.778)	Mem 34602MB
[2025-01-19 12:51:43 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.994)	Loss 0.9495 (0.7983)	Acc@1 78.174 (82.158)	Acc@5 94.849 (96.265)	Mem 34602MB
[2025-01-19 12:51:43 internimage_b_1k_224] (main.py 575): INFO [Epoch:176] * Acc@1 81.998 Acc@5 96.319
[2025-01-19 12:51:43 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.0%
[2025-01-19 12:51:43 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:51:44 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][260/312]	eta 0:00:38 lr 0.001471	time 0.7145 (0.7476)	model_time 0.7143 (0.7418)	loss 3.5496 (3.0698)	grad_norm 0.7504 (1.7791/0.7680)	mem 34604MB
[2025-01-19 12:51:47 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:51:47 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.00%
[2025-01-19 12:51:49 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][0/312]	eta 0:10:21 lr 0.001468	time 1.9919 (1.9919)	model_time 0.7416 (0.7416)	loss 3.1601 (3.1601)	grad_norm 1.3108 (1.3108/0.0000)	mem 34602MB
[2025-01-19 12:51:52 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][270/312]	eta 0:00:31 lr 0.001470	time 0.8060 (0.7494)	model_time 0.8056 (0.7438)	loss 1.9558 (3.0511)	grad_norm 1.3952 (1.7613/0.7623)	mem 34604MB
[2025-01-19 12:51:56 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][10/312]	eta 0:04:13 lr 0.001467	time 0.7184 (0.8409)	model_time 0.7180 (0.7268)	loss 3.0133 (3.1078)	grad_norm 1.2490 (1.6349/0.4665)	mem 34602MB
[2025-01-19 12:51:59 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][280/312]	eta 0:00:23 lr 0.001470	time 0.7471 (0.7498)	model_time 0.7469 (0.7444)	loss 3.0339 (3.0524)	grad_norm 0.9403 (1.7510/0.7521)	mem 34604MB
[2025-01-19 12:52:03 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][20/312]	eta 0:03:51 lr 0.001466	time 0.8247 (0.7926)	model_time 0.8245 (0.7327)	loss 2.1582 (2.9737)	grad_norm 1.1234 (1.5386/0.4618)	mem 34602MB
[2025-01-19 12:52:07 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][290/312]	eta 0:00:16 lr 0.001469	time 0.7215 (0.7492)	model_time 0.7210 (0.7440)	loss 2.7096 (3.0553)	grad_norm 1.6426 (1.7532/0.7547)	mem 34604MB
[2025-01-19 12:52:11 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][30/312]	eta 0:03:40 lr 0.001466	time 0.7180 (0.7814)	model_time 0.7179 (0.7407)	loss 2.7980 (3.0510)	grad_norm 1.4123 (1.5066/0.4974)	mem 34602MB
[2025-01-19 12:52:14 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][300/312]	eta 0:00:08 lr 0.001468	time 0.7194 (0.7486)	model_time 0.7193 (0.7436)	loss 2.3662 (3.0485)	grad_norm 0.8936 (1.7433/0.7428)	mem 34604MB
[2025-01-19 12:52:18 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][40/312]	eta 0:03:29 lr 0.001465	time 0.7258 (0.7704)	model_time 0.7253 (0.7395)	loss 2.3895 (2.9686)	grad_norm 0.9668 (1.4835/0.5702)	mem 34602MB
[2025-01-19 12:52:21 internimage_b_1k_224] (main.py 510): INFO Train: [176/300][310/312]	eta 0:00:01 lr 0.001468	time 0.7186 (0.7476)	model_time 0.7185 (0.7427)	loss 3.0807 (3.0472)	grad_norm 1.9571 (1.7526/0.7438)	mem 34604MB
[2025-01-19 12:52:22 internimage_b_1k_224] (main.py 519): INFO EPOCH 176 training takes 0:03:53
[2025-01-19 12:52:22 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_176.pth saving......
[2025-01-19 12:52:25 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_176.pth saved !!!
[2025-01-19 12:52:26 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][50/312]	eta 0:03:20 lr 0.001464	time 0.7206 (0.7655)	model_time 0.7204 (0.7406)	loss 3.4637 (2.9903)	grad_norm 0.8450 (1.4924/0.5996)	mem 34602MB
[2025-01-19 12:52:33 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.519 (7.519)	Loss 0.7565 (0.7565)	Acc@1 84.033 (84.033)	Acc@5 97.363 (97.363)	Mem 34604MB
[2025-01-19 12:52:34 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][60/312]	eta 0:03:13 lr 0.001464	time 0.7164 (0.7670)	model_time 0.7160 (0.7462)	loss 3.2758 (2.9970)	grad_norm 2.1082 (1.5449/0.6054)	mem 34602MB
[2025-01-19 12:52:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.972)	Loss 0.9780 (0.8630)	Acc@1 79.321 (81.931)	Acc@5 95.117 (96.016)	Mem 34604MB
[2025-01-19 12:52:36 internimage_b_1k_224] (main.py 575): INFO [Epoch:176] * Acc@1 81.778 Acc@5 95.989
[2025-01-19 12:52:36 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.8%
[2025-01-19 12:52:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 12:52:39 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 12:52:39 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.78%
[2025-01-19 12:52:41 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][70/312]	eta 0:03:05 lr 0.001463	time 0.7981 (0.7647)	model_time 0.7976 (0.7467)	loss 2.5889 (3.0009)	grad_norm 1.0043 (1.5632/0.6116)	mem 34602MB
[2025-01-19 12:52:47 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.560 (7.560)	Loss 0.6722 (0.6722)	Acc@1 84.863 (84.863)	Acc@5 97.827 (97.827)	Mem 34604MB
[2025-01-19 12:52:49 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][80/312]	eta 0:02:56 lr 0.001462	time 0.7197 (0.7627)	model_time 0.7195 (0.7469)	loss 3.6819 (3.0240)	grad_norm 1.3172 (1.5764/0.6064)	mem 34602MB
[2025-01-19 12:52:50 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.965)	Loss 0.9499 (0.7973)	Acc@1 78.223 (82.251)	Acc@5 94.824 (96.260)	Mem 34604MB
[2025-01-19 12:52:50 internimage_b_1k_224] (main.py 575): INFO [Epoch:176] * Acc@1 82.118 Acc@5 96.307
[2025-01-19 12:52:50 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.1%
[2025-01-19 12:52:50 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:52:54 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:52:54 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.12%
[2025-01-19 12:52:56 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][0/312]	eta 0:10:18 lr 0.001468	time 1.9835 (1.9835)	model_time 0.7447 (0.7447)	loss 3.2396 (3.2396)	grad_norm 1.2174 (1.2174/0.0000)	mem 34604MB
[2025-01-19 12:52:56 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][90/312]	eta 0:02:48 lr 0.001462	time 0.7217 (0.7603)	model_time 0.7212 (0.7462)	loss 2.8521 (3.0299)	grad_norm 3.0870 (1.6031/0.6211)	mem 34602MB
[2025-01-19 12:53:03 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][10/312]	eta 0:04:15 lr 0.001467	time 0.7195 (0.8450)	model_time 0.7191 (0.7320)	loss 3.1847 (2.9675)	grad_norm 1.4141 (1.1526/0.2673)	mem 34604MB
[2025-01-19 12:53:03 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][100/312]	eta 0:02:40 lr 0.001461	time 0.7209 (0.7577)	model_time 0.7205 (0.7449)	loss 3.1419 (3.0236)	grad_norm 2.2701 (1.6282/0.6360)	mem 34602MB
[2025-01-19 12:53:11 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][20/312]	eta 0:03:50 lr 0.001466	time 0.7197 (0.7907)	model_time 0.7196 (0.7314)	loss 3.4885 (3.0017)	grad_norm 1.4859 (1.5211/0.6802)	mem 34604MB
[2025-01-19 12:53:11 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][110/312]	eta 0:02:32 lr 0.001461	time 0.7170 (0.7568)	model_time 0.7168 (0.7451)	loss 3.2403 (3.0433)	grad_norm 1.2751 (1.6129/0.6415)	mem 34602MB
[2025-01-19 12:53:18 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][30/312]	eta 0:03:37 lr 0.001466	time 0.7078 (0.7716)	model_time 0.7077 (0.7313)	loss 2.7559 (3.1180)	grad_norm 1.2548 (1.8868/1.1074)	mem 34604MB
[2025-01-19 12:53:18 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][120/312]	eta 0:02:25 lr 0.001460	time 0.7429 (0.7566)	model_time 0.7428 (0.7459)	loss 3.1541 (3.0492)	grad_norm 1.6382 (1.6313/0.6587)	mem 34602MB
[2025-01-19 12:53:25 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][40/312]	eta 0:03:27 lr 0.001465	time 0.7191 (0.7611)	model_time 0.7186 (0.7305)	loss 3.5962 (3.0683)	grad_norm 1.0898 (1.8159/0.9976)	mem 34604MB
[2025-01-19 12:53:26 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][130/312]	eta 0:02:17 lr 0.001459	time 0.7286 (0.7544)	model_time 0.7282 (0.7445)	loss 3.1490 (3.0567)	grad_norm 0.8414 (1.6411/0.6571)	mem 34602MB
[2025-01-19 12:53:32 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][50/312]	eta 0:03:17 lr 0.001464	time 0.7251 (0.7548)	model_time 0.7249 (0.7302)	loss 2.7421 (3.0377)	grad_norm 1.3038 (1.8130/0.9564)	mem 34604MB
[2025-01-19 12:53:33 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][140/312]	eta 0:02:09 lr 0.001459	time 0.8140 (0.7531)	model_time 0.8138 (0.7438)	loss 3.1552 (3.0609)	grad_norm 1.8065 (1.6461/0.6445)	mem 34602MB
[2025-01-19 12:53:40 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][60/312]	eta 0:03:09 lr 0.001464	time 0.8361 (0.7522)	model_time 0.8357 (0.7315)	loss 3.0851 (3.0425)	grad_norm 1.7456 (1.9133/0.9658)	mem 34604MB
[2025-01-19 12:53:40 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][150/312]	eta 0:02:02 lr 0.001458	time 0.7191 (0.7531)	model_time 0.7190 (0.7445)	loss 3.9081 (3.0774)	grad_norm 1.5758 (1.6322/0.6339)	mem 34602MB
[2025-01-19 12:53:48 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][70/312]	eta 0:03:02 lr 0.001463	time 0.8062 (0.7547)	model_time 0.8060 (0.7369)	loss 3.3024 (3.0575)	grad_norm 1.8126 (1.9442/0.9761)	mem 34604MB
[2025-01-19 12:53:48 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][160/312]	eta 0:01:54 lr 0.001457	time 0.7284 (0.7522)	model_time 0.7279 (0.7441)	loss 2.5174 (3.0636)	grad_norm 1.7424 (1.6344/0.6345)	mem 34602MB
[2025-01-19 12:53:55 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][170/312]	eta 0:01:46 lr 0.001457	time 0.7270 (0.7518)	model_time 0.7268 (0.7442)	loss 2.8494 (3.0646)	grad_norm 1.7127 (1.6252/0.6238)	mem 34602MB
[2025-01-19 12:53:55 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][80/312]	eta 0:02:56 lr 0.001462	time 0.7241 (0.7588)	model_time 0.7239 (0.7432)	loss 3.3783 (3.0910)	grad_norm 1.1747 (1.9189/0.9520)	mem 34604MB
[2025-01-19 12:54:03 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][180/312]	eta 0:01:39 lr 0.001456	time 0.7181 (0.7530)	model_time 0.7176 (0.7457)	loss 2.8092 (3.0518)	grad_norm 1.5257 (1.6323/0.6507)	mem 34602MB
[2025-01-19 12:54:03 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][90/312]	eta 0:02:48 lr 0.001462	time 0.8115 (0.7610)	model_time 0.8113 (0.7470)	loss 3.3545 (3.0963)	grad_norm 0.8625 (1.8653/0.9229)	mem 34604MB
[2025-01-19 12:54:10 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][100/312]	eta 0:02:40 lr 0.001461	time 0.7235 (0.7580)	model_time 0.7234 (0.7454)	loss 2.4858 (3.0967)	grad_norm 1.0507 (1.8058/0.8983)	mem 34604MB
[2025-01-19 12:54:11 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][190/312]	eta 0:01:31 lr 0.001455	time 0.8035 (0.7531)	model_time 0.8033 (0.7461)	loss 3.7735 (3.0656)	grad_norm 1.7044 (1.6761/0.7077)	mem 34602MB
[2025-01-19 12:54:18 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][110/312]	eta 0:02:32 lr 0.001461	time 0.7214 (0.7558)	model_time 0.7209 (0.7443)	loss 2.0731 (3.0931)	grad_norm 1.9449 (1.8182/0.8790)	mem 34604MB
[2025-01-19 12:54:18 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][200/312]	eta 0:01:24 lr 0.001455	time 0.7168 (0.7529)	model_time 0.7167 (0.7464)	loss 3.0401 (3.0767)	grad_norm 2.1807 (1.7060/0.7397)	mem 34602MB
[2025-01-19 12:54:25 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][120/312]	eta 0:02:24 lr 0.001460	time 0.7407 (0.7532)	model_time 0.7402 (0.7426)	loss 3.2197 (3.0823)	grad_norm 3.6731 (1.8615/0.8918)	mem 34604MB
[2025-01-19 12:54:26 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][210/312]	eta 0:01:16 lr 0.001454	time 0.7519 (0.7528)	model_time 0.7517 (0.7465)	loss 3.4193 (3.0731)	grad_norm 0.9512 (1.6983/0.7375)	mem 34602MB
[2025-01-19 12:54:32 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][130/312]	eta 0:02:16 lr 0.001459	time 0.7218 (0.7509)	model_time 0.7213 (0.7411)	loss 3.8869 (3.0995)	grad_norm 1.2237 (1.8566/0.8740)	mem 34604MB
[2025-01-19 12:54:33 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][220/312]	eta 0:01:09 lr 0.001454	time 0.7182 (0.7521)	model_time 0.7177 (0.7461)	loss 3.1459 (3.0746)	grad_norm 0.8838 (1.6781/0.7324)	mem 34602MB
[2025-01-19 12:54:40 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][140/312]	eta 0:02:08 lr 0.001459	time 0.7369 (0.7493)	model_time 0.7367 (0.7401)	loss 2.5818 (3.1026)	grad_norm 1.4358 (1.8392/0.8674)	mem 34604MB
[2025-01-19 12:54:40 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][230/312]	eta 0:01:01 lr 0.001453	time 0.7179 (0.7517)	model_time 0.7175 (0.7459)	loss 3.4828 (3.0778)	grad_norm 0.8654 (1.6589/0.7273)	mem 34602MB
[2025-01-19 12:54:47 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][150/312]	eta 0:02:01 lr 0.001458	time 0.7235 (0.7478)	model_time 0.7234 (0.7393)	loss 2.5020 (3.1032)	grad_norm 1.4196 (1.8463/0.8537)	mem 34604MB
[2025-01-19 12:54:48 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][240/312]	eta 0:00:54 lr 0.001452	time 0.7205 (0.7512)	model_time 0.7203 (0.7457)	loss 3.0508 (3.0763)	grad_norm 2.0713 (1.6959/0.7624)	mem 34602MB
[2025-01-19 12:54:54 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][160/312]	eta 0:01:53 lr 0.001457	time 0.7312 (0.7467)	model_time 0.7310 (0.7387)	loss 2.9340 (3.0953)	grad_norm 1.8749 (1.8181/0.8372)	mem 34604MB
[2025-01-19 12:54:55 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][250/312]	eta 0:00:46 lr 0.001452	time 0.7179 (0.7502)	model_time 0.7177 (0.7449)	loss 3.4692 (3.0786)	grad_norm 1.6691 (1.7095/0.7628)	mem 34602MB
[2025-01-19 12:55:01 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][170/312]	eta 0:01:45 lr 0.001457	time 0.7147 (0.7453)	model_time 0.7145 (0.7377)	loss 2.9446 (3.0877)	grad_norm 2.3641 (1.7885/0.8275)	mem 34604MB
[2025-01-19 12:55:02 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][260/312]	eta 0:00:38 lr 0.001451	time 0.8105 (0.7497)	model_time 0.8103 (0.7445)	loss 3.6164 (3.0867)	grad_norm 1.1316 (1.6961/0.7547)	mem 34602MB
[2025-01-19 12:55:09 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][180/312]	eta 0:01:38 lr 0.001456	time 0.8433 (0.7450)	model_time 0.8429 (0.7378)	loss 3.1214 (3.0943)	grad_norm 1.4697 (1.7947/0.8307)	mem 34604MB
[2025-01-19 12:55:10 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][270/312]	eta 0:00:31 lr 0.001450	time 0.7182 (0.7496)	model_time 0.7180 (0.7447)	loss 2.1932 (3.0869)	grad_norm 1.4025 (1.6877/0.7460)	mem 34602MB
[2025-01-19 12:55:16 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][190/312]	eta 0:01:31 lr 0.001455	time 0.8071 (0.7462)	model_time 0.8067 (0.7394)	loss 2.5238 (3.0785)	grad_norm 2.2431 (1.8099/0.8245)	mem 34604MB
[2025-01-19 12:55:17 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][280/312]	eta 0:00:23 lr 0.001450	time 0.7195 (0.7490)	model_time 0.7193 (0.7441)	loss 3.5180 (3.0802)	grad_norm 1.2605 (1.7026/0.7592)	mem 34602MB
[2025-01-19 12:55:24 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][200/312]	eta 0:01:23 lr 0.001455	time 0.7167 (0.7478)	model_time 0.7165 (0.7413)	loss 3.1240 (3.0771)	grad_norm 1.7530 (1.8270/0.8181)	mem 34604MB
[2025-01-19 12:55:25 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][290/312]	eta 0:00:16 lr 0.001449	time 0.7206 (0.7488)	model_time 0.7205 (0.7442)	loss 3.3046 (3.0848)	grad_norm 1.1474 (1.7100/0.7633)	mem 34602MB
[2025-01-19 12:55:32 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][210/312]	eta 0:01:16 lr 0.001454	time 0.8140 (0.7491)	model_time 0.8139 (0.7428)	loss 3.3511 (3.0752)	grad_norm 2.2161 (1.8173/0.8076)	mem 34604MB
[2025-01-19 12:55:32 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][300/312]	eta 0:00:08 lr 0.001448	time 0.7887 (0.7488)	model_time 0.7886 (0.7443)	loss 3.1481 (3.0928)	grad_norm 1.0294 (1.7072/0.7563)	mem 34602MB
[2025-01-19 12:55:39 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][220/312]	eta 0:01:08 lr 0.001454	time 0.7177 (0.7483)	model_time 0.7175 (0.7424)	loss 2.6031 (3.0663)	grad_norm 0.8042 (1.8042/0.8050)	mem 34604MB
[2025-01-19 12:55:40 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][310/312]	eta 0:00:01 lr 0.001448	time 0.7963 (0.7488)	model_time 0.7961 (0.7445)	loss 2.7506 (3.0946)	grad_norm 1.4303 (1.6975/0.7555)	mem 34602MB
[2025-01-19 12:55:40 internimage_b_1k_224] (main.py 519): INFO EPOCH 177 training takes 0:03:53
[2025-01-19 12:55:40 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_177.pth saving......
[2025-01-19 12:55:44 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_177.pth saved !!!
[2025-01-19 12:55:47 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][230/312]	eta 0:01:01 lr 0.001453	time 0.7192 (0.7478)	model_time 0.7187 (0.7421)	loss 3.1550 (3.0730)	grad_norm 1.3508 (1.7931/0.7981)	mem 34604MB
[2025-01-19 12:55:51 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.560 (7.560)	Loss 0.7299 (0.7299)	Acc@1 84.473 (84.473)	Acc@5 97.363 (97.363)	Mem 34602MB
[2025-01-19 12:55:54 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][240/312]	eta 0:00:53 lr 0.001452	time 0.7081 (0.7470)	model_time 0.7079 (0.7415)	loss 3.5438 (3.0729)	grad_norm 2.0370 (1.7795/0.7862)	mem 34604MB
[2025-01-19 12:55:54 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.957)	Loss 0.9850 (0.8474)	Acc@1 78.369 (81.669)	Acc@5 94.824 (95.989)	Mem 34602MB
[2025-01-19 12:55:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:177] * Acc@1 81.580 Acc@5 96.001
[2025-01-19 12:55:55 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.6%
[2025-01-19 12:55:55 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.70%
[2025-01-19 12:56:01 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][250/312]	eta 0:00:46 lr 0.001452	time 0.7218 (0.7461)	model_time 0.7213 (0.7408)	loss 3.3303 (3.0756)	grad_norm 1.0946 (1.7820/0.7791)	mem 34604MB
[2025-01-19 12:56:04 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.303 (9.303)	Loss 0.6740 (0.6740)	Acc@1 84.668 (84.668)	Acc@5 97.778 (97.778)	Mem 34602MB
[2025-01-19 12:56:08 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.259)	Loss 0.9494 (0.7987)	Acc@1 78.149 (82.198)	Acc@5 94.849 (96.274)	Mem 34602MB
[2025-01-19 12:56:08 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][260/312]	eta 0:00:38 lr 0.001451	time 0.7250 (0.7455)	model_time 0.7245 (0.7403)	loss 2.6980 (3.0812)	grad_norm 1.9562 (1.7839/0.7743)	mem 34604MB
[2025-01-19 12:56:09 internimage_b_1k_224] (main.py 575): INFO [Epoch:177] * Acc@1 82.036 Acc@5 96.329
[2025-01-19 12:56:09 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.0%
[2025-01-19 12:56:09 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:56:12 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:56:12 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.04%
[2025-01-19 12:56:15 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][0/312]	eta 0:11:36 lr 0.001448	time 2.2323 (2.2323)	model_time 0.7508 (0.7508)	loss 3.2607 (3.2607)	grad_norm 0.8500 (0.8500/0.0000)	mem 34602MB
[2025-01-19 12:56:16 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][270/312]	eta 0:00:31 lr 0.001450	time 0.7262 (0.7448)	model_time 0.7258 (0.7399)	loss 3.8996 (3.0858)	grad_norm 1.9762 (1.7698/0.7695)	mem 34604MB
[2025-01-19 12:56:22 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][10/312]	eta 0:04:29 lr 0.001447	time 0.7198 (0.8925)	model_time 0.7197 (0.7576)	loss 3.1626 (2.9301)	grad_norm 1.4915 (1.5587/0.6007)	mem 34602MB
[2025-01-19 12:56:23 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][280/312]	eta 0:00:23 lr 0.001450	time 0.7296 (0.7443)	model_time 0.7291 (0.7395)	loss 3.0933 (3.0874)	grad_norm 1.2601 (1.7734/0.7625)	mem 34604MB
[2025-01-19 12:56:30 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][20/312]	eta 0:04:00 lr 0.001446	time 0.7270 (0.8235)	model_time 0.7266 (0.7527)	loss 3.7927 (3.0777)	grad_norm 0.9758 (1.7556/0.7426)	mem 34602MB
[2025-01-19 12:56:30 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][290/312]	eta 0:00:16 lr 0.001449	time 0.7277 (0.7435)	model_time 0.7275 (0.7389)	loss 2.8841 (3.0806)	grad_norm 2.4309 (1.7687/0.7612)	mem 34604MB
[2025-01-19 12:56:37 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][30/312]	eta 0:03:44 lr 0.001446	time 0.8116 (0.7948)	model_time 0.8110 (0.7467)	loss 2.8645 (3.1454)	grad_norm 1.1902 (1.8258/0.7173)	mem 34602MB
[2025-01-19 12:56:37 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][300/312]	eta 0:00:08 lr 0.001448	time 0.7149 (0.7428)	model_time 0.7148 (0.7383)	loss 2.9502 (3.0827)	grad_norm 1.9440 (1.7760/0.7530)	mem 34604MB
[2025-01-19 12:56:45 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][40/312]	eta 0:03:32 lr 0.001445	time 0.7234 (0.7819)	model_time 0.7232 (0.7455)	loss 2.5849 (3.0659)	grad_norm 1.8624 (1.9585/0.7496)	mem 34602MB
[2025-01-19 12:56:45 internimage_b_1k_224] (main.py 510): INFO Train: [177/300][310/312]	eta 0:00:01 lr 0.001448	time 0.8050 (0.7432)	model_time 0.8049 (0.7388)	loss 3.2856 (3.0759)	grad_norm 1.0685 (1.7894/0.7454)	mem 34604MB
[2025-01-19 12:56:46 internimage_b_1k_224] (main.py 519): INFO EPOCH 177 training takes 0:03:51
[2025-01-19 12:56:46 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_177.pth saving......
[2025-01-19 12:56:49 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_177.pth saved !!!
[2025-01-19 12:56:52 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][50/312]	eta 0:03:22 lr 0.001445	time 0.7173 (0.7745)	model_time 0.7168 (0.7451)	loss 3.2417 (3.0934)	grad_norm 1.1654 (1.7704/0.7755)	mem 34602MB
[2025-01-19 12:56:57 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.502 (7.502)	Loss 0.7884 (0.7884)	Acc@1 84.253 (84.253)	Acc@5 97.559 (97.559)	Mem 34604MB
[2025-01-19 12:56:59 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][60/312]	eta 0:03:13 lr 0.001444	time 0.7173 (0.7676)	model_time 0.7172 (0.7429)	loss 2.8443 (3.0938)	grad_norm 1.1239 (1.7544/0.7740)	mem 34602MB
[2025-01-19 12:57:00 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.953)	Loss 1.0430 (0.9046)	Acc@1 78.003 (81.607)	Acc@5 94.678 (95.938)	Mem 34604MB
[2025-01-19 12:57:00 internimage_b_1k_224] (main.py 575): INFO [Epoch:177] * Acc@1 81.472 Acc@5 95.911
[2025-01-19 12:57:00 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.5%
[2025-01-19 12:57:00 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.78%
[2025-01-19 12:57:07 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][70/312]	eta 0:03:04 lr 0.001443	time 0.7613 (0.7637)	model_time 0.7609 (0.7425)	loss 3.1776 (3.1131)	grad_norm 1.1466 (1.6886/0.7510)	mem 34602MB
[2025-01-19 12:57:09 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.501 (9.501)	Loss 0.6733 (0.6733)	Acc@1 84.912 (84.912)	Acc@5 97.827 (97.827)	Mem 34604MB
[2025-01-19 12:57:14 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.277)	Loss 0.9498 (0.7979)	Acc@1 78.198 (82.262)	Acc@5 94.849 (96.267)	Mem 34604MB
[2025-01-19 12:57:14 internimage_b_1k_224] (main.py 575): INFO [Epoch:177] * Acc@1 82.124 Acc@5 96.315
[2025-01-19 12:57:14 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.1%
[2025-01-19 12:57:14 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 12:57:14 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][80/312]	eta 0:02:57 lr 0.001443	time 0.7149 (0.7631)	model_time 0.7144 (0.7444)	loss 2.9444 (3.1033)	grad_norm 1.2812 (1.6841/0.7409)	mem 34602MB
[2025-01-19 12:57:18 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 12:57:18 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.12%
[2025-01-19 12:57:20 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][0/312]	eta 0:11:30 lr 0.001448	time 2.2143 (2.2143)	model_time 0.7408 (0.7408)	loss 2.8255 (2.8255)	grad_norm 1.6014 (1.6014/0.0000)	mem 34604MB
[2025-01-19 12:57:22 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][90/312]	eta 0:02:48 lr 0.001442	time 0.7193 (0.7607)	model_time 0.7188 (0.7441)	loss 3.3057 (3.1189)	grad_norm 1.1829 (1.6716/0.7362)	mem 34602MB
[2025-01-19 12:57:28 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][10/312]	eta 0:04:40 lr 0.001447	time 0.8123 (0.9279)	model_time 0.8118 (0.7937)	loss 2.5226 (2.9347)	grad_norm 1.0086 (1.5000/0.4811)	mem 34604MB
[2025-01-19 12:57:29 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][100/312]	eta 0:02:40 lr 0.001441	time 0.7214 (0.7585)	model_time 0.7213 (0.7435)	loss 3.4194 (3.1162)	grad_norm 1.0098 (1.6967/0.7338)	mem 34602MB
[2025-01-19 12:57:35 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][20/312]	eta 0:04:07 lr 0.001446	time 0.7346 (0.8467)	model_time 0.7344 (0.7762)	loss 2.8897 (2.9730)	grad_norm 0.7172 (1.4909/0.5518)	mem 34604MB
[2025-01-19 12:57:37 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][110/312]	eta 0:02:33 lr 0.001441	time 0.8049 (0.7590)	model_time 0.8044 (0.7453)	loss 2.1653 (3.0882)	grad_norm 0.7718 (1.6640/0.7177)	mem 34602MB
[2025-01-19 12:57:43 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][30/312]	eta 0:03:48 lr 0.001446	time 0.7274 (0.8111)	model_time 0.7272 (0.7632)	loss 3.5410 (3.0777)	grad_norm 2.1234 (1.5201/0.5322)	mem 34604MB
[2025-01-19 12:57:44 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][120/312]	eta 0:02:25 lr 0.001440	time 0.8133 (0.7591)	model_time 0.8129 (0.7465)	loss 3.0141 (3.0623)	grad_norm 2.1169 (1.7067/0.7105)	mem 34602MB
[2025-01-19 12:57:50 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][40/312]	eta 0:03:35 lr 0.001445	time 0.7309 (0.7923)	model_time 0.7308 (0.7561)	loss 3.4521 (3.0489)	grad_norm 2.0325 (1.6128/0.5863)	mem 34604MB
[2025-01-19 12:57:52 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][130/312]	eta 0:02:18 lr 0.001439	time 0.7158 (0.7589)	model_time 0.7156 (0.7472)	loss 3.3340 (3.0710)	grad_norm 4.0123 (1.7298/0.7187)	mem 34602MB
[2025-01-19 12:57:57 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][50/312]	eta 0:03:24 lr 0.001445	time 0.7349 (0.7792)	model_time 0.7345 (0.7500)	loss 2.4085 (3.0663)	grad_norm 1.0727 (1.5954/0.5518)	mem 34604MB
[2025-01-19 12:57:59 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][140/312]	eta 0:02:10 lr 0.001439	time 0.7207 (0.7579)	model_time 0.7202 (0.7470)	loss 3.1651 (3.0621)	grad_norm 1.6910 (1.7204/0.7147)	mem 34602MB
[2025-01-19 12:58:05 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][60/312]	eta 0:03:14 lr 0.001444	time 0.7160 (0.7705)	model_time 0.7159 (0.7460)	loss 3.3373 (3.0930)	grad_norm 1.8196 (1.5915/0.5731)	mem 34604MB
[2025-01-19 12:58:07 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][150/312]	eta 0:02:02 lr 0.001438	time 0.8089 (0.7566)	model_time 0.8088 (0.7464)	loss 3.6764 (3.0590)	grad_norm 1.3318 (1.7377/0.7018)	mem 34602MB
[2025-01-19 12:58:12 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][70/312]	eta 0:03:05 lr 0.001443	time 0.7305 (0.7663)	model_time 0.7304 (0.7452)	loss 1.9393 (3.0652)	grad_norm 2.5544 (1.6048/0.5890)	mem 34604MB
[2025-01-19 12:58:14 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][160/312]	eta 0:01:54 lr 0.001438	time 0.7201 (0.7560)	model_time 0.7199 (0.7464)	loss 3.7753 (3.0750)	grad_norm 1.2223 (1.7058/0.6939)	mem 34602MB
[2025-01-19 12:58:19 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][80/312]	eta 0:02:56 lr 0.001443	time 0.7491 (0.7619)	model_time 0.7487 (0.7434)	loss 3.1598 (3.0700)	grad_norm 2.8071 (1.6313/0.5871)	mem 34604MB
[2025-01-19 12:58:22 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][170/312]	eta 0:01:47 lr 0.001437	time 0.7225 (0.7554)	model_time 0.7223 (0.7464)	loss 2.2000 (3.0741)	grad_norm 1.1541 (1.6985/0.6902)	mem 34602MB
[2025-01-19 12:58:27 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][90/312]	eta 0:02:48 lr 0.001442	time 0.7271 (0.7586)	model_time 0.7269 (0.7421)	loss 3.3270 (3.0973)	grad_norm 1.6546 (1.6280/0.5701)	mem 34604MB
[2025-01-19 12:58:29 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][180/312]	eta 0:01:39 lr 0.001436	time 0.7168 (0.7541)	model_time 0.7163 (0.7456)	loss 2.4277 (3.0608)	grad_norm 0.8549 (1.6925/0.6824)	mem 34602MB
[2025-01-19 12:58:34 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][100/312]	eta 0:02:40 lr 0.001441	time 0.7155 (0.7553)	model_time 0.7151 (0.7404)	loss 2.9402 (3.1036)	grad_norm 3.1958 (1.6469/0.5944)	mem 34604MB
[2025-01-19 12:58:36 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][190/312]	eta 0:01:31 lr 0.001436	time 0.7257 (0.7526)	model_time 0.7252 (0.7445)	loss 3.4550 (3.0599)	grad_norm 1.1278 (1.6950/0.6907)	mem 34602MB
[2025-01-19 12:58:41 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][110/312]	eta 0:02:32 lr 0.001441	time 0.7127 (0.7530)	model_time 0.7122 (0.7394)	loss 3.2890 (3.1063)	grad_norm 1.0783 (1.7240/0.7413)	mem 34604MB
[2025-01-19 12:58:44 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][200/312]	eta 0:01:24 lr 0.001435	time 0.8268 (0.7534)	model_time 0.8264 (0.7457)	loss 3.0917 (3.0517)	grad_norm 4.3654 (1.7009/0.7146)	mem 34602MB
[2025-01-19 12:58:49 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][120/312]	eta 0:02:25 lr 0.001440	time 0.8139 (0.7560)	model_time 0.8138 (0.7435)	loss 3.0101 (3.0961)	grad_norm 1.7796 (1.7540/0.7527)	mem 34604MB
[2025-01-19 12:58:51 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][210/312]	eta 0:01:16 lr 0.001434	time 0.7191 (0.7529)	model_time 0.7189 (0.7455)	loss 3.7583 (3.0532)	grad_norm 1.5939 (1.7153/0.7092)	mem 34602MB
[2025-01-19 12:58:57 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][130/312]	eta 0:02:18 lr 0.001439	time 0.8094 (0.7590)	model_time 0.8092 (0.7474)	loss 2.3746 (3.0979)	grad_norm 1.1438 (1.7272/0.7383)	mem 34604MB
[2025-01-19 12:58:59 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][220/312]	eta 0:01:09 lr 0.001434	time 0.7287 (0.7519)	model_time 0.7282 (0.7448)	loss 1.7730 (3.0589)	grad_norm 2.7685 (1.7143/0.7077)	mem 34602MB
[2025-01-19 12:59:05 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][140/312]	eta 0:02:10 lr 0.001439	time 0.7445 (0.7601)	model_time 0.7441 (0.7493)	loss 3.6382 (3.0948)	grad_norm 1.7896 (1.7008/0.7245)	mem 34604MB
[2025-01-19 12:59:06 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][230/312]	eta 0:01:01 lr 0.001433	time 0.8089 (0.7520)	model_time 0.8087 (0.7453)	loss 3.2233 (3.0556)	grad_norm 1.6543 (1.7092/0.7021)	mem 34602MB
[2025-01-19 12:59:12 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][150/312]	eta 0:02:02 lr 0.001438	time 0.7180 (0.7589)	model_time 0.7176 (0.7488)	loss 3.3707 (3.0996)	grad_norm 1.1052 (1.6799/0.7071)	mem 34604MB
[2025-01-19 12:59:14 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][240/312]	eta 0:00:54 lr 0.001432	time 0.7165 (0.7519)	model_time 0.7160 (0.7454)	loss 3.2491 (3.0552)	grad_norm 1.5769 (1.6957/0.6938)	mem 34602MB
[2025-01-19 12:59:20 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][160/312]	eta 0:01:55 lr 0.001438	time 0.7215 (0.7575)	model_time 0.7214 (0.7480)	loss 2.8279 (3.0902)	grad_norm 1.9472 (1.6663/0.7035)	mem 34604MB
[2025-01-19 12:59:21 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][250/312]	eta 0:00:46 lr 0.001432	time 0.7192 (0.7527)	model_time 0.7191 (0.7465)	loss 3.5285 (3.0528)	grad_norm 1.0654 (1.6799/0.6889)	mem 34602MB
[2025-01-19 12:59:27 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][170/312]	eta 0:01:47 lr 0.001437	time 0.7164 (0.7556)	model_time 0.7160 (0.7467)	loss 3.3430 (3.0872)	grad_norm 2.8751 (1.6938/0.7106)	mem 34604MB
[2025-01-19 12:59:29 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][260/312]	eta 0:00:39 lr 0.001431	time 0.7145 (0.7525)	model_time 0.7141 (0.7465)	loss 2.6736 (3.0525)	grad_norm 1.3591 (1.6675/0.6836)	mem 34602MB
[2025-01-19 12:59:34 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][180/312]	eta 0:01:39 lr 0.001436	time 0.7148 (0.7540)	model_time 0.7147 (0.7455)	loss 2.0657 (3.0924)	grad_norm 0.9531 (1.6990/0.7128)	mem 34604MB
[2025-01-19 12:59:36 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][270/312]	eta 0:00:31 lr 0.001431	time 0.8211 (0.7518)	model_time 0.8206 (0.7460)	loss 3.1140 (3.0564)	grad_norm 2.6815 (1.6568/0.6835)	mem 34602MB
[2025-01-19 12:59:41 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][190/312]	eta 0:01:31 lr 0.001436	time 0.7167 (0.7531)	model_time 0.7163 (0.7451)	loss 2.9652 (3.0863)	grad_norm 1.6753 (1.7067/0.7057)	mem 34604MB
[2025-01-19 12:59:44 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][280/312]	eta 0:00:24 lr 0.001430	time 0.8096 (0.7514)	model_time 0.8095 (0.7458)	loss 3.0590 (3.0595)	grad_norm 2.8206 (1.6642/0.6822)	mem 34602MB
[2025-01-19 12:59:49 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][200/312]	eta 0:01:24 lr 0.001435	time 0.7194 (0.7520)	model_time 0.7190 (0.7443)	loss 3.1983 (3.0800)	grad_norm 1.2961 (1.6977/0.6952)	mem 34604MB
[2025-01-19 12:59:51 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][290/312]	eta 0:00:16 lr 0.001429	time 0.7197 (0.7510)	model_time 0.7196 (0.7455)	loss 2.7828 (3.0465)	grad_norm 2.4613 (1.6782/0.6830)	mem 34602MB
[2025-01-19 12:59:56 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][210/312]	eta 0:01:16 lr 0.001434	time 0.7263 (0.7506)	model_time 0.7258 (0.7433)	loss 3.9952 (3.0892)	grad_norm 1.0332 (1.7027/0.6915)	mem 34604MB
[2025-01-19 12:59:58 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][300/312]	eta 0:00:09 lr 0.001429	time 0.7164 (0.7502)	model_time 0.7163 (0.7449)	loss 3.4027 (3.0478)	grad_norm 1.3630 (1.6799/0.6864)	mem 34602MB
[2025-01-19 13:00:03 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][220/312]	eta 0:01:08 lr 0.001434	time 0.7188 (0.7494)	model_time 0.7187 (0.7424)	loss 2.8881 (3.0839)	grad_norm 0.9183 (1.7196/0.7313)	mem 34604MB
[2025-01-19 13:00:05 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][310/312]	eta 0:00:01 lr 0.001428	time 0.7119 (0.7491)	model_time 0.7118 (0.7439)	loss 1.8617 (3.0422)	grad_norm 1.6221 (1.6728/0.6801)	mem 34602MB
[2025-01-19 13:00:06 internimage_b_1k_224] (main.py 519): INFO EPOCH 178 training takes 0:03:53
[2025-01-19 13:00:06 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_178.pth saving......
[2025-01-19 13:00:09 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_178.pth saved !!!
[2025-01-19 13:00:11 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][230/312]	eta 0:01:01 lr 0.001433	time 0.7778 (0.7490)	model_time 0.7773 (0.7422)	loss 3.1999 (3.0968)	grad_norm 2.1743 (1.7102/0.7215)	mem 34604MB
[2025-01-19 13:00:17 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.545 (7.545)	Loss 0.7677 (0.7677)	Acc@1 84.473 (84.473)	Acc@5 97.168 (97.168)	Mem 34602MB
[2025-01-19 13:00:18 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][240/312]	eta 0:00:53 lr 0.001432	time 0.8045 (0.7498)	model_time 0.8041 (0.7434)	loss 3.0908 (3.0935)	grad_norm 1.6489 (1.6975/0.7124)	mem 34604MB
[2025-01-19 13:00:20 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.975)	Loss 1.0421 (0.8822)	Acc@1 76.709 (81.805)	Acc@5 94.653 (95.992)	Mem 34602MB
[2025-01-19 13:00:21 internimage_b_1k_224] (main.py 575): INFO [Epoch:178] * Acc@1 81.698 Acc@5 95.993
[2025-01-19 13:00:21 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.7%
[2025-01-19 13:00:21 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.70%
[2025-01-19 13:00:26 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][250/312]	eta 0:00:46 lr 0.001432	time 0.8305 (0.7520)	model_time 0.8303 (0.7457)	loss 3.4101 (3.0889)	grad_norm 0.8768 (1.6887/0.7075)	mem 34604MB
[2025-01-19 13:00:30 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.279 (9.279)	Loss 0.6750 (0.6750)	Acc@1 84.692 (84.692)	Acc@5 97.778 (97.778)	Mem 34602MB
[2025-01-19 13:00:34 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][260/312]	eta 0:00:39 lr 0.001431	time 0.7224 (0.7519)	model_time 0.7220 (0.7459)	loss 2.4603 (3.0855)	grad_norm 3.2913 (1.7058/0.7159)	mem 34604MB
[2025-01-19 13:00:34 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.255)	Loss 0.9494 (0.7992)	Acc@1 78.223 (82.213)	Acc@5 94.873 (96.285)	Mem 34602MB
[2025-01-19 13:00:35 internimage_b_1k_224] (main.py 575): INFO [Epoch:178] * Acc@1 82.058 Acc@5 96.343
[2025-01-19 13:00:35 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.1%
[2025-01-19 13:00:35 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:00:38 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:00:38 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.06%
[2025-01-19 13:00:41 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][0/312]	eta 0:12:32 lr 0.001428	time 2.4109 (2.4109)	model_time 0.7918 (0.7918)	loss 3.2544 (3.2544)	grad_norm 1.3642 (1.3642/0.0000)	mem 34602MB
[2025-01-19 13:00:41 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][270/312]	eta 0:00:31 lr 0.001431	time 0.7262 (0.7517)	model_time 0.7258 (0.7459)	loss 3.3227 (3.0780)	grad_norm 1.6643 (1.7164/0.7112)	mem 34604MB
[2025-01-19 13:00:48 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][10/312]	eta 0:04:34 lr 0.001427	time 0.7935 (0.9085)	model_time 0.7930 (0.7609)	loss 3.2651 (3.0950)	grad_norm 1.3870 (2.3069/1.1509)	mem 34602MB
[2025-01-19 13:00:49 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][280/312]	eta 0:00:24 lr 0.001430	time 0.7230 (0.7511)	model_time 0.7225 (0.7455)	loss 3.5558 (3.0822)	grad_norm 1.0604 (1.7222/0.7230)	mem 34604MB
[2025-01-19 13:00:56 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][20/312]	eta 0:04:01 lr 0.001427	time 0.7266 (0.8285)	model_time 0.7265 (0.7511)	loss 3.3426 (3.1622)	grad_norm 2.6412 (2.4340/1.0046)	mem 34602MB
[2025-01-19 13:00:56 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][290/312]	eta 0:00:16 lr 0.001429	time 0.7288 (0.7504)	model_time 0.7286 (0.7449)	loss 3.2374 (3.0762)	grad_norm 2.0642 (1.7425/0.7451)	mem 34604MB
[2025-01-19 13:01:03 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][300/312]	eta 0:00:08 lr 0.001429	time 0.7159 (0.7493)	model_time 0.7158 (0.7441)	loss 2.7150 (3.0785)	grad_norm 0.8956 (1.7425/0.7467)	mem 34604MB
[2025-01-19 13:01:03 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][30/312]	eta 0:03:45 lr 0.001426	time 0.7248 (0.7994)	model_time 0.7244 (0.7468)	loss 3.0854 (3.1109)	grad_norm 1.0085 (2.1458/1.0041)	mem 34602MB
[2025-01-19 13:01:10 internimage_b_1k_224] (main.py 510): INFO Train: [178/300][310/312]	eta 0:00:01 lr 0.001428	time 0.8131 (0.7488)	model_time 0.8130 (0.7437)	loss 3.6740 (3.0845)	grad_norm 1.2336 (1.7328/0.7476)	mem 34604MB
[2025-01-19 13:01:11 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][40/312]	eta 0:03:34 lr 0.001425	time 0.7251 (0.7900)	model_time 0.7246 (0.7501)	loss 3.1619 (3.0916)	grad_norm 1.4120 (1.9898/0.9445)	mem 34602MB
[2025-01-19 13:01:11 internimage_b_1k_224] (main.py 519): INFO EPOCH 178 training takes 0:03:53
[2025-01-19 13:01:11 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_178.pth saving......
[2025-01-19 13:01:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_178.pth saved !!!
[2025-01-19 13:01:18 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][50/312]	eta 0:03:25 lr 0.001425	time 0.7161 (0.7855)	model_time 0.7159 (0.7534)	loss 3.5048 (3.1247)	grad_norm 1.4727 (1.8173/0.9228)	mem 34602MB
[2025-01-19 13:01:22 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.600 (7.600)	Loss 0.7495 (0.7495)	Acc@1 84.521 (84.521)	Acc@5 97.559 (97.559)	Mem 34604MB
[2025-01-19 13:01:25 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.985)	Loss 1.0288 (0.8776)	Acc@1 77.832 (82.031)	Acc@5 94.409 (96.016)	Mem 34604MB
[2025-01-19 13:01:25 internimage_b_1k_224] (main.py 575): INFO [Epoch:178] * Acc@1 81.874 Acc@5 96.043
[2025-01-19 13:01:25 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.9%
[2025-01-19 13:01:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 13:01:26 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][60/312]	eta 0:03:17 lr 0.001424	time 0.7759 (0.7818)	model_time 0.7758 (0.7549)	loss 3.2406 (3.0559)	grad_norm 0.8578 (1.7173/0.8848)	mem 34602MB
[2025-01-19 13:01:29 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 13:01:29 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.87%
[2025-01-19 13:01:34 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][70/312]	eta 0:03:08 lr 0.001423	time 0.7187 (0.7770)	model_time 0.7183 (0.7538)	loss 3.2376 (3.0743)	grad_norm 1.3150 (1.7022/0.8367)	mem 34602MB
[2025-01-19 13:01:36 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.216 (7.216)	Loss 0.6742 (0.6742)	Acc@1 84.912 (84.912)	Acc@5 97.852 (97.852)	Mem 34604MB
[2025-01-19 13:01:39 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.929)	Loss 0.9497 (0.7983)	Acc@1 78.320 (82.324)	Acc@5 94.849 (96.289)	Mem 34604MB
[2025-01-19 13:01:39 internimage_b_1k_224] (main.py 575): INFO [Epoch:178] * Acc@1 82.186 Acc@5 96.339
[2025-01-19 13:01:39 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.2%
[2025-01-19 13:01:39 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:01:41 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][80/312]	eta 0:02:58 lr 0.001423	time 0.7319 (0.7708)	model_time 0.7314 (0.7504)	loss 3.3818 (3.0874)	grad_norm 1.6459 (1.6684/0.7965)	mem 34602MB
[2025-01-19 13:01:43 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:01:43 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.19%
[2025-01-19 13:01:45 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][0/312]	eta 0:11:34 lr 0.001428	time 2.2244 (2.2244)	model_time 0.7251 (0.7251)	loss 3.1970 (3.1970)	grad_norm 0.9381 (0.9381/0.0000)	mem 34604MB
[2025-01-19 13:01:48 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][90/312]	eta 0:02:50 lr 0.001422	time 0.7324 (0.7686)	model_time 0.7322 (0.7504)	loss 3.8216 (3.0833)	grad_norm 1.4417 (1.7108/0.8313)	mem 34602MB
[2025-01-19 13:01:52 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][10/312]	eta 0:04:23 lr 0.001427	time 0.7279 (0.8724)	model_time 0.7277 (0.7358)	loss 3.2580 (2.9035)	grad_norm 1.1059 (1.8855/0.6474)	mem 34604MB
[2025-01-19 13:01:56 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][100/312]	eta 0:02:42 lr 0.001422	time 0.8043 (0.7664)	model_time 0.8039 (0.7500)	loss 2.6279 (3.0832)	grad_norm 3.1247 (1.7587/0.8319)	mem 34602MB
[2025-01-19 13:02:00 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][20/312]	eta 0:03:54 lr 0.001427	time 0.7299 (0.8015)	model_time 0.7295 (0.7298)	loss 2.8546 (2.8916)	grad_norm 1.3835 (1.7809/0.6257)	mem 34604MB
[2025-01-19 13:02:03 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][110/312]	eta 0:02:34 lr 0.001421	time 0.7238 (0.7628)	model_time 0.7236 (0.7478)	loss 2.3762 (3.0966)	grad_norm 1.5742 (1.7342/0.8072)	mem 34602MB
[2025-01-19 13:02:07 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][30/312]	eta 0:03:39 lr 0.001426	time 0.7358 (0.7785)	model_time 0.7356 (0.7298)	loss 2.3417 (2.9181)	grad_norm 2.7114 (1.7529/0.5789)	mem 34604MB
[2025-01-19 13:02:10 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][120/312]	eta 0:02:25 lr 0.001420	time 0.7317 (0.7602)	model_time 0.7315 (0.7465)	loss 2.6564 (3.0944)	grad_norm 1.3511 (1.7155/0.7974)	mem 34602MB
[2025-01-19 13:02:14 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][40/312]	eta 0:03:28 lr 0.001425	time 0.7415 (0.7660)	model_time 0.7410 (0.7291)	loss 3.6575 (2.9568)	grad_norm 0.9119 (1.8057/0.7600)	mem 34604MB
[2025-01-19 13:02:18 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][130/312]	eta 0:02:18 lr 0.001420	time 0.7245 (0.7593)	model_time 0.7241 (0.7465)	loss 3.2407 (3.1191)	grad_norm 2.3131 (1.7083/0.7795)	mem 34602MB
[2025-01-19 13:02:22 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][50/312]	eta 0:03:21 lr 0.001425	time 0.7908 (0.7694)	model_time 0.7906 (0.7396)	loss 3.2154 (2.9240)	grad_norm 2.3529 (1.7948/0.7469)	mem 34604MB
[2025-01-19 13:02:25 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][140/312]	eta 0:02:10 lr 0.001419	time 0.7348 (0.7586)	model_time 0.7346 (0.7467)	loss 2.3730 (3.1146)	grad_norm 2.7192 (1.7303/0.8097)	mem 34602MB
[2025-01-19 13:02:30 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][60/312]	eta 0:03:14 lr 0.001424	time 0.8079 (0.7727)	model_time 0.8075 (0.7477)	loss 3.5216 (2.9727)	grad_norm 1.3266 (1.7567/0.7157)	mem 34604MB
[2025-01-19 13:02:33 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][150/312]	eta 0:02:02 lr 0.001418	time 0.7352 (0.7569)	model_time 0.7347 (0.7458)	loss 2.6631 (3.1122)	grad_norm 1.6366 (1.7119/0.7946)	mem 34602MB
[2025-01-19 13:02:37 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][70/312]	eta 0:03:06 lr 0.001423	time 0.7186 (0.7709)	model_time 0.7185 (0.7494)	loss 3.6631 (3.0110)	grad_norm 1.5355 (1.7714/0.7368)	mem 34604MB
[2025-01-19 13:02:40 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][160/312]	eta 0:01:55 lr 0.001418	time 0.7195 (0.7567)	model_time 0.7194 (0.7463)	loss 3.3134 (3.1111)	grad_norm 1.6627 (1.7444/0.8524)	mem 34602MB
[2025-01-19 13:02:45 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][80/312]	eta 0:02:57 lr 0.001423	time 0.7237 (0.7672)	model_time 0.7235 (0.7483)	loss 3.1289 (3.0247)	grad_norm 1.0410 (1.7679/0.7295)	mem 34604MB
[2025-01-19 13:02:48 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][170/312]	eta 0:01:47 lr 0.001417	time 0.7167 (0.7570)	model_time 0.7162 (0.7471)	loss 3.3400 (3.1140)	grad_norm 1.7366 (1.7435/0.8314)	mem 34602MB
[2025-01-19 13:02:52 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][90/312]	eta 0:02:49 lr 0.001422	time 0.7198 (0.7632)	model_time 0.7197 (0.7463)	loss 3.3626 (3.0301)	grad_norm 1.7830 (1.7505/0.7055)	mem 34604MB
[2025-01-19 13:02:56 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][180/312]	eta 0:01:40 lr 0.001416	time 0.7951 (0.7576)	model_time 0.7949 (0.7483)	loss 2.7771 (3.0982)	grad_norm 3.4267 (1.7614/0.8282)	mem 34602MB
[2025-01-19 13:03:00 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][100/312]	eta 0:02:41 lr 0.001422	time 0.7568 (0.7601)	model_time 0.7567 (0.7449)	loss 3.5277 (3.0325)	grad_norm 1.5107 (1.7501/0.7057)	mem 34604MB
[2025-01-19 13:03:03 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][190/312]	eta 0:01:32 lr 0.001416	time 0.7410 (0.7570)	model_time 0.7406 (0.7482)	loss 2.2545 (3.0961)	grad_norm 3.3991 (1.7748/0.8409)	mem 34602MB
[2025-01-19 13:03:07 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][110/312]	eta 0:02:32 lr 0.001421	time 0.7197 (0.7571)	model_time 0.7192 (0.7433)	loss 3.1038 (3.0535)	grad_norm 2.4297 (1.7759/0.7227)	mem 34604MB
[2025-01-19 13:03:10 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][200/312]	eta 0:01:24 lr 0.001415	time 0.7178 (0.7554)	model_time 0.7174 (0.7469)	loss 2.3044 (3.0959)	grad_norm 1.1099 (1.7634/0.8319)	mem 34602MB
[2025-01-19 13:03:14 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][120/312]	eta 0:02:24 lr 0.001420	time 0.7310 (0.7545)	model_time 0.7308 (0.7417)	loss 2.0028 (3.0676)	grad_norm 1.8624 (1.8388/0.7794)	mem 34604MB
[2025-01-19 13:03:18 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][210/312]	eta 0:01:17 lr 0.001415	time 0.7283 (0.7560)	model_time 0.7279 (0.7480)	loss 3.5681 (3.1033)	grad_norm 1.8262 (1.7617/0.8282)	mem 34602MB
[2025-01-19 13:03:21 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][130/312]	eta 0:02:16 lr 0.001420	time 0.7293 (0.7527)	model_time 0.7291 (0.7409)	loss 3.3485 (3.0673)	grad_norm 2.4151 (1.8611/0.7819)	mem 34604MB
[2025-01-19 13:03:25 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][220/312]	eta 0:01:09 lr 0.001414	time 0.8068 (0.7554)	model_time 0.8066 (0.7477)	loss 2.0685 (3.1008)	grad_norm 1.8605 (1.7638/0.8172)	mem 34602MB
[2025-01-19 13:03:29 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][140/312]	eta 0:02:09 lr 0.001419	time 0.7335 (0.7504)	model_time 0.7333 (0.7394)	loss 3.8155 (3.0726)	grad_norm 1.3297 (1.8224/0.7732)	mem 34604MB
[2025-01-19 13:03:33 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][230/312]	eta 0:01:01 lr 0.001413	time 0.7459 (0.7542)	model_time 0.7454 (0.7468)	loss 2.8832 (3.0887)	grad_norm 0.8416 (1.7620/0.8116)	mem 34602MB
[2025-01-19 13:03:36 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][150/312]	eta 0:02:01 lr 0.001418	time 0.7281 (0.7492)	model_time 0.7277 (0.7390)	loss 2.6779 (3.0728)	grad_norm 1.5961 (1.8031/0.7609)	mem 34604MB
[2025-01-19 13:03:40 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][240/312]	eta 0:00:54 lr 0.001413	time 0.7364 (0.7531)	model_time 0.7359 (0.7460)	loss 2.8871 (3.0903)	grad_norm 1.0291 (1.7543/0.8067)	mem 34602MB
[2025-01-19 13:03:43 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][160/312]	eta 0:01:53 lr 0.001418	time 0.7281 (0.7479)	model_time 0.7277 (0.7382)	loss 2.9833 (3.0701)	grad_norm 1.7352 (1.8057/0.7499)	mem 34604MB
[2025-01-19 13:03:47 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][250/312]	eta 0:00:46 lr 0.001412	time 0.7284 (0.7527)	model_time 0.7280 (0.7458)	loss 3.1515 (3.0872)	grad_norm 2.8858 (1.7806/0.8220)	mem 34602MB
[2025-01-19 13:03:51 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][170/312]	eta 0:01:46 lr 0.001417	time 0.7924 (0.7498)	model_time 0.7922 (0.7406)	loss 2.1714 (3.0672)	grad_norm 1.5698 (1.8091/0.7417)	mem 34604MB
[2025-01-19 13:03:55 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][260/312]	eta 0:00:39 lr 0.001411	time 0.7187 (0.7525)	model_time 0.7183 (0.7459)	loss 3.0338 (3.0888)	grad_norm 0.7953 (1.7724/0.8225)	mem 34602MB
[2025-01-19 13:03:59 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][180/312]	eta 0:01:39 lr 0.001416	time 0.8087 (0.7526)	model_time 0.8085 (0.7440)	loss 3.4572 (3.0655)	grad_norm 4.5280 (1.8221/0.7618)	mem 34604MB
[2025-01-19 13:04:02 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][270/312]	eta 0:00:31 lr 0.001411	time 0.7237 (0.7516)	model_time 0.7235 (0.7453)	loss 2.0498 (3.0882)	grad_norm 3.6899 (1.7586/0.8253)	mem 34602MB
[2025-01-19 13:04:07 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][190/312]	eta 0:01:31 lr 0.001416	time 0.7153 (0.7535)	model_time 0.7148 (0.7453)	loss 2.5177 (3.0802)	grad_norm 2.2321 (1.8256/0.7621)	mem 34604MB
[2025-01-19 13:04:10 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][280/312]	eta 0:00:24 lr 0.001410	time 0.7177 (0.7516)	model_time 0.7172 (0.7455)	loss 3.2935 (3.0813)	grad_norm 3.0354 (1.7580/0.8219)	mem 34602MB
[2025-01-19 13:04:14 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][200/312]	eta 0:01:24 lr 0.001415	time 0.7121 (0.7529)	model_time 0.7118 (0.7451)	loss 3.9907 (3.0820)	grad_norm 3.0915 (1.8301/0.7539)	mem 34604MB
[2025-01-19 13:04:17 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][290/312]	eta 0:00:16 lr 0.001410	time 0.7157 (0.7519)	model_time 0.7153 (0.7459)	loss 2.8966 (3.0781)	grad_norm 1.8370 (1.7447/0.8147)	mem 34602MB
[2025-01-19 13:04:21 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][210/312]	eta 0:01:16 lr 0.001415	time 0.7144 (0.7516)	model_time 0.7143 (0.7441)	loss 2.3990 (3.0800)	grad_norm 2.0535 (1.8231/0.7434)	mem 34604MB
[2025-01-19 13:04:25 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][300/312]	eta 0:00:09 lr 0.001409	time 0.7848 (0.7520)	model_time 0.7847 (0.7462)	loss 3.2737 (3.0732)	grad_norm 2.2971 (1.7449/0.8102)	mem 34602MB
[2025-01-19 13:04:29 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][220/312]	eta 0:01:09 lr 0.001414	time 0.7228 (0.7509)	model_time 0.7227 (0.7438)	loss 2.3883 (3.0861)	grad_norm 2.0714 (1.8132/0.7321)	mem 34604MB
[2025-01-19 13:04:32 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][310/312]	eta 0:00:01 lr 0.001408	time 0.8141 (0.7514)	model_time 0.8139 (0.7458)	loss 3.5980 (3.0706)	grad_norm 1.2300 (1.7285/0.7894)	mem 34602MB
[2025-01-19 13:04:33 internimage_b_1k_224] (main.py 519): INFO EPOCH 179 training takes 0:03:54
[2025-01-19 13:04:33 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_179.pth saving......
[2025-01-19 13:04:36 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][230/312]	eta 0:01:01 lr 0.001413	time 0.7440 (0.7500)	model_time 0.7434 (0.7431)	loss 3.1717 (3.0901)	grad_norm 1.7150 (1.8097/0.7179)	mem 34604MB
[2025-01-19 13:04:36 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_179.pth saved !!!
[2025-01-19 13:04:43 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][240/312]	eta 0:00:53 lr 0.001413	time 0.7208 (0.7490)	model_time 0.7203 (0.7424)	loss 3.6835 (3.0880)	grad_norm 1.1158 (1.8085/0.7241)	mem 34604MB
[2025-01-19 13:04:44 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.495 (7.495)	Loss 0.7575 (0.7575)	Acc@1 84.204 (84.204)	Acc@5 97.339 (97.339)	Mem 34602MB
[2025-01-19 13:04:47 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.958)	Loss 1.0146 (0.8699)	Acc@1 77.124 (81.812)	Acc@5 94.824 (96.007)	Mem 34602MB
[2025-01-19 13:04:47 internimage_b_1k_224] (main.py 575): INFO [Epoch:179] * Acc@1 81.644 Acc@5 96.031
[2025-01-19 13:04:47 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.6%
[2025-01-19 13:04:47 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.70%
[2025-01-19 13:04:51 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][250/312]	eta 0:00:46 lr 0.001412	time 0.7283 (0.7484)	model_time 0.7282 (0.7421)	loss 3.6570 (3.0915)	grad_norm 0.9342 (1.7875/0.7211)	mem 34604MB
[2025-01-19 13:04:56 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.207 (9.207)	Loss 0.6760 (0.6760)	Acc@1 84.741 (84.741)	Acc@5 97.803 (97.803)	Mem 34602MB
[2025-01-19 13:04:58 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][260/312]	eta 0:00:38 lr 0.001411	time 0.7167 (0.7476)	model_time 0.7166 (0.7415)	loss 3.1635 (3.0970)	grad_norm 1.7886 (1.7790/0.7133)	mem 34604MB
[2025-01-19 13:05:01 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.260)	Loss 0.9494 (0.7997)	Acc@1 78.271 (82.253)	Acc@5 94.873 (96.302)	Mem 34602MB
[2025-01-19 13:05:01 internimage_b_1k_224] (main.py 575): INFO [Epoch:179] * Acc@1 82.090 Acc@5 96.359
[2025-01-19 13:05:01 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.1%
[2025-01-19 13:05:01 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:05:05 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][270/312]	eta 0:00:31 lr 0.001411	time 0.7195 (0.7468)	model_time 0.7191 (0.7409)	loss 3.4992 (3.1092)	grad_norm 3.6774 (1.7903/0.7189)	mem 34604MB
[2025-01-19 13:05:05 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:05:05 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.09%
[2025-01-19 13:05:07 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][0/312]	eta 0:10:34 lr 0.001408	time 2.0327 (2.0327)	model_time 0.7508 (0.7508)	loss 3.5571 (3.5571)	grad_norm 1.9838 (1.9838/0.0000)	mem 34602MB
[2025-01-19 13:05:13 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][280/312]	eta 0:00:23 lr 0.001410	time 0.7207 (0.7465)	model_time 0.7205 (0.7408)	loss 3.4256 (3.1173)	grad_norm 1.2041 (1.7852/0.7099)	mem 34604MB
[2025-01-19 13:05:15 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][10/312]	eta 0:04:20 lr 0.001408	time 0.7574 (0.8627)	model_time 0.7573 (0.7459)	loss 2.6002 (3.1445)	grad_norm 2.2671 (2.1625/0.9008)	mem 34602MB
[2025-01-19 13:05:20 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][290/312]	eta 0:00:16 lr 0.001410	time 0.7907 (0.7477)	model_time 0.7906 (0.7422)	loss 3.2999 (3.1082)	grad_norm 1.4141 (1.7683/0.7054)	mem 34604MB
[2025-01-19 13:05:22 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][20/312]	eta 0:03:58 lr 0.001407	time 0.7329 (0.8154)	model_time 0.7324 (0.7541)	loss 3.0318 (3.0485)	grad_norm 1.1994 (2.1344/0.9356)	mem 34602MB
[2025-01-19 13:05:28 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][300/312]	eta 0:00:08 lr 0.001409	time 0.7150 (0.7485)	model_time 0.7149 (0.7431)	loss 4.0201 (3.1029)	grad_norm 1.9264 (1.7854/0.7175)	mem 34604MB
[2025-01-19 13:05:30 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][30/312]	eta 0:03:42 lr 0.001406	time 0.7588 (0.7906)	model_time 0.7586 (0.7490)	loss 3.2793 (3.1363)	grad_norm 1.0505 (2.0037/0.8594)	mem 34602MB
[2025-01-19 13:05:36 internimage_b_1k_224] (main.py 510): INFO Train: [179/300][310/312]	eta 0:00:01 lr 0.001408	time 0.7927 (0.7487)	model_time 0.7926 (0.7436)	loss 2.9181 (3.1060)	grad_norm 2.0925 (1.8033/0.7503)	mem 34604MB
[2025-01-19 13:05:36 internimage_b_1k_224] (main.py 519): INFO EPOCH 179 training takes 0:03:53
[2025-01-19 13:05:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_179.pth saving......
[2025-01-19 13:05:37 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][40/312]	eta 0:03:30 lr 0.001406	time 0.7222 (0.7741)	model_time 0.7221 (0.7425)	loss 2.9244 (3.0935)	grad_norm 1.2321 (1.8776/0.8071)	mem 34602MB
[2025-01-19 13:05:40 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_179.pth saved !!!
[2025-01-19 13:05:44 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][50/312]	eta 0:03:20 lr 0.001405	time 0.7409 (0.7656)	model_time 0.7408 (0.7401)	loss 3.6109 (3.0434)	grad_norm 0.7491 (1.7225/0.7986)	mem 34602MB
[2025-01-19 13:05:47 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.701 (7.701)	Loss 0.7645 (0.7645)	Acc@1 84.741 (84.741)	Acc@5 97.437 (97.437)	Mem 34604MB
[2025-01-19 13:05:51 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.997)	Loss 1.0120 (0.8777)	Acc@1 78.442 (81.894)	Acc@5 94.165 (95.930)	Mem 34604MB
[2025-01-19 13:05:51 internimage_b_1k_224] (main.py 575): INFO [Epoch:179] * Acc@1 81.692 Acc@5 95.931
[2025-01-19 13:05:51 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.7%
[2025-01-19 13:05:51 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.87%
[2025-01-19 13:05:52 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][60/312]	eta 0:03:11 lr 0.001404	time 0.7165 (0.7618)	model_time 0.7161 (0.7404)	loss 2.3981 (3.0714)	grad_norm 2.3927 (1.6453/0.7814)	mem 34602MB
[2025-01-19 13:05:59 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][70/312]	eta 0:03:04 lr 0.001404	time 0.8029 (0.7611)	model_time 0.8027 (0.7427)	loss 2.6932 (3.0414)	grad_norm 1.1279 (1.6698/0.7743)	mem 34602MB
[2025-01-19 13:06:00 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.399 (9.399)	Loss 0.6752 (0.6752)	Acc@1 84.863 (84.863)	Acc@5 97.876 (97.876)	Mem 34604MB
[2025-01-19 13:06:05 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.281)	Loss 0.9497 (0.7988)	Acc@1 78.369 (82.346)	Acc@5 94.800 (96.300)	Mem 34604MB
[2025-01-19 13:06:05 internimage_b_1k_224] (main.py 575): INFO [Epoch:179] * Acc@1 82.212 Acc@5 96.343
[2025-01-19 13:06:05 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.2%
[2025-01-19 13:06:05 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:06:07 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][80/312]	eta 0:02:56 lr 0.001403	time 0.7401 (0.7592)	model_time 0.7396 (0.7430)	loss 3.7746 (3.0822)	grad_norm 0.8734 (1.7420/0.8773)	mem 34602MB
[2025-01-19 13:06:09 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:06:09 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.21%
[2025-01-19 13:06:11 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][0/312]	eta 0:10:27 lr 0.001408	time 2.0123 (2.0123)	model_time 0.7410 (0.7410)	loss 3.8420 (3.8420)	grad_norm 1.4706 (1.4706/0.0000)	mem 34604MB
[2025-01-19 13:06:14 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][90/312]	eta 0:02:48 lr 0.001402	time 0.7236 (0.7582)	model_time 0.7235 (0.7437)	loss 3.1009 (3.0985)	grad_norm 1.0815 (1.6796/0.8521)	mem 34602MB
[2025-01-19 13:06:18 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][10/312]	eta 0:04:17 lr 0.001408	time 0.7252 (0.8538)	model_time 0.7247 (0.7378)	loss 2.4455 (3.2231)	grad_norm 1.3962 (1.4333/0.3817)	mem 34604MB
[2025-01-19 13:06:22 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][100/312]	eta 0:02:40 lr 0.001402	time 0.8092 (0.7578)	model_time 0.8087 (0.7447)	loss 2.8902 (3.0705)	grad_norm 1.5669 (1.7312/0.9330)	mem 34602MB
[2025-01-19 13:06:25 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][20/312]	eta 0:03:53 lr 0.001407	time 0.7162 (0.7987)	model_time 0.7158 (0.7378)	loss 3.3244 (3.0765)	grad_norm 3.3461 (1.5078/0.5293)	mem 34604MB
[2025-01-19 13:06:30 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][110/312]	eta 0:02:33 lr 0.001401	time 0.7189 (0.7589)	model_time 0.7185 (0.7470)	loss 2.6843 (3.0763)	grad_norm 0.9587 (1.7771/0.9530)	mem 34602MB
[2025-01-19 13:06:33 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][30/312]	eta 0:03:38 lr 0.001406	time 0.7200 (0.7765)	model_time 0.7196 (0.7351)	loss 2.9384 (3.0705)	grad_norm 2.3489 (1.6027/0.5743)	mem 34604MB
[2025-01-19 13:06:37 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][120/312]	eta 0:02:25 lr 0.001401	time 0.7246 (0.7574)	model_time 0.7244 (0.7464)	loss 2.2474 (3.0868)	grad_norm 1.7312 (1.7552/0.9199)	mem 34602MB
[2025-01-19 13:06:40 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][40/312]	eta 0:03:27 lr 0.001406	time 0.7240 (0.7646)	model_time 0.7239 (0.7332)	loss 2.9248 (2.9766)	grad_norm 0.8755 (1.7096/0.7771)	mem 34604MB
[2025-01-19 13:06:44 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][130/312]	eta 0:02:17 lr 0.001400	time 0.7200 (0.7565)	model_time 0.7196 (0.7464)	loss 2.8735 (3.0829)	grad_norm 1.4789 (1.7218/0.9005)	mem 34602MB
[2025-01-19 13:06:47 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][50/312]	eta 0:03:18 lr 0.001405	time 0.7159 (0.7574)	model_time 0.7158 (0.7321)	loss 1.9735 (2.9829)	grad_norm 1.2935 (1.8190/0.8711)	mem 34604MB
[2025-01-19 13:06:52 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][140/312]	eta 0:02:10 lr 0.001399	time 0.7334 (0.7560)	model_time 0.7332 (0.7466)	loss 2.7731 (3.0875)	grad_norm 0.8178 (1.7124/0.8808)	mem 34602MB
[2025-01-19 13:06:55 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][60/312]	eta 0:03:09 lr 0.001404	time 0.7056 (0.7527)	model_time 0.7051 (0.7314)	loss 3.1728 (3.0144)	grad_norm 1.9052 (1.7567/0.8222)	mem 34604MB
[2025-01-19 13:06:59 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][150/312]	eta 0:02:02 lr 0.001399	time 0.7476 (0.7558)	model_time 0.7474 (0.7470)	loss 3.2700 (3.0883)	grad_norm 1.7955 (1.7038/0.8672)	mem 34602MB
[2025-01-19 13:07:02 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][70/312]	eta 0:03:01 lr 0.001404	time 0.7320 (0.7491)	model_time 0.7316 (0.7308)	loss 3.1271 (3.0179)	grad_norm 1.3219 (1.7092/0.7817)	mem 34604MB
[2025-01-19 13:07:07 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][160/312]	eta 0:01:54 lr 0.001398	time 0.7373 (0.7541)	model_time 0.7368 (0.7458)	loss 3.2491 (3.1162)	grad_norm 3.2805 (1.7100/0.8696)	mem 34602MB
[2025-01-19 13:07:09 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][80/312]	eta 0:02:53 lr 0.001403	time 0.7237 (0.7467)	model_time 0.7233 (0.7306)	loss 3.5519 (3.0041)	grad_norm 1.2398 (1.7024/0.7608)	mem 34604MB
[2025-01-19 13:07:14 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][170/312]	eta 0:01:46 lr 0.001397	time 0.7298 (0.7530)	model_time 0.7296 (0.7451)	loss 3.0491 (3.1193)	grad_norm 1.5716 (1.7230/0.8639)	mem 34602MB
[2025-01-19 13:07:17 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][90/312]	eta 0:02:45 lr 0.001402	time 0.7629 (0.7459)	model_time 0.7625 (0.7315)	loss 3.2552 (3.0047)	grad_norm 1.7071 (1.7181/0.7484)	mem 34604MB
[2025-01-19 13:07:22 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][180/312]	eta 0:01:39 lr 0.001397	time 0.7584 (0.7532)	model_time 0.7582 (0.7457)	loss 2.1994 (3.1202)	grad_norm 0.9968 (1.7359/0.8589)	mem 34602MB
[2025-01-19 13:07:24 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][100/312]	eta 0:02:38 lr 0.001402	time 0.8322 (0.7483)	model_time 0.8318 (0.7353)	loss 2.7663 (3.0185)	grad_norm 1.0432 (1.6733/0.7300)	mem 34604MB
[2025-01-19 13:07:29 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][190/312]	eta 0:01:31 lr 0.001396	time 0.7137 (0.7522)	model_time 0.7132 (0.7451)	loss 2.9949 (3.1073)	grad_norm 2.5098 (1.7597/0.8604)	mem 34602MB
[2025-01-19 13:07:32 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][110/312]	eta 0:02:32 lr 0.001401	time 0.8237 (0.7534)	model_time 0.8232 (0.7416)	loss 3.2581 (3.0087)	grad_norm 1.8846 (1.6468/0.7080)	mem 34604MB
[2025-01-19 13:07:36 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][200/312]	eta 0:01:24 lr 0.001396	time 0.7519 (0.7522)	model_time 0.7517 (0.7454)	loss 3.5660 (3.1171)	grad_norm 0.8340 (1.7762/0.8709)	mem 34602MB
[2025-01-19 13:07:40 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][120/312]	eta 0:02:24 lr 0.001401	time 0.8130 (0.7546)	model_time 0.8129 (0.7437)	loss 3.9256 (3.0387)	grad_norm 1.3475 (1.6203/0.6892)	mem 34604MB
[2025-01-19 13:07:44 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][210/312]	eta 0:01:16 lr 0.001395	time 0.7173 (0.7522)	model_time 0.7171 (0.7458)	loss 2.9936 (3.1184)	grad_norm 1.6655 (1.7817/0.8586)	mem 34602MB
[2025-01-19 13:07:47 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][130/312]	eta 0:02:17 lr 0.001400	time 0.7219 (0.7534)	model_time 0.7217 (0.7433)	loss 3.3531 (3.0278)	grad_norm 3.6104 (1.6419/0.7114)	mem 34604MB
[2025-01-19 13:07:51 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][220/312]	eta 0:01:09 lr 0.001394	time 0.7951 (0.7517)	model_time 0.7949 (0.7456)	loss 3.6483 (3.1277)	grad_norm 1.4200 (1.7689/0.8494)	mem 34602MB
[2025-01-19 13:07:55 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][140/312]	eta 0:02:09 lr 0.001399	time 0.7164 (0.7525)	model_time 0.7160 (0.7431)	loss 2.7277 (3.0322)	grad_norm 0.9916 (1.6521/0.7049)	mem 34604MB
[2025-01-19 13:07:59 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][230/312]	eta 0:01:01 lr 0.001394	time 0.7923 (0.7528)	model_time 0.7919 (0.7469)	loss 3.5111 (3.1330)	grad_norm 1.4471 (1.7590/0.8372)	mem 34602MB
[2025-01-19 13:08:02 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][150/312]	eta 0:02:01 lr 0.001399	time 0.7249 (0.7511)	model_time 0.7244 (0.7423)	loss 3.0251 (3.0393)	grad_norm 2.5780 (1.6589/0.7000)	mem 34604MB
[2025-01-19 13:08:07 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][240/312]	eta 0:00:54 lr 0.001393	time 0.7465 (0.7523)	model_time 0.7464 (0.7466)	loss 2.6510 (3.1337)	grad_norm 2.6041 (1.7461/0.8300)	mem 34602MB
[2025-01-19 13:08:09 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][160/312]	eta 0:01:53 lr 0.001398	time 0.7207 (0.7495)	model_time 0.7205 (0.7412)	loss 2.3813 (3.0372)	grad_norm 1.9306 (1.6732/0.6946)	mem 34604MB
[2025-01-19 13:08:14 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][250/312]	eta 0:00:46 lr 0.001392	time 0.7167 (0.7525)	model_time 0.7165 (0.7470)	loss 2.9507 (3.1335)	grad_norm 1.0249 (1.7301/0.8220)	mem 34602MB
[2025-01-19 13:08:17 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][170/312]	eta 0:01:46 lr 0.001397	time 0.7318 (0.7481)	model_time 0.7313 (0.7402)	loss 2.4734 (3.0426)	grad_norm 2.2566 (1.7118/0.7029)	mem 34604MB
[2025-01-19 13:08:22 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][260/312]	eta 0:00:39 lr 0.001392	time 0.7272 (0.7526)	model_time 0.7271 (0.7473)	loss 3.4927 (3.1360)	grad_norm 1.5091 (1.7274/0.8124)	mem 34602MB
[2025-01-19 13:08:24 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][180/312]	eta 0:01:38 lr 0.001397	time 0.7579 (0.7469)	model_time 0.7578 (0.7395)	loss 2.7316 (3.0227)	grad_norm 0.8861 (1.7114/0.7105)	mem 34604MB
[2025-01-19 13:08:29 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][270/312]	eta 0:00:31 lr 0.001391	time 0.7359 (0.7520)	model_time 0.7355 (0.7469)	loss 2.6786 (3.1287)	grad_norm 0.9899 (1.7109/0.8041)	mem 34602MB
[2025-01-19 13:08:31 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][190/312]	eta 0:01:30 lr 0.001396	time 0.7489 (0.7459)	model_time 0.7488 (0.7388)	loss 3.1612 (3.0202)	grad_norm 1.0942 (1.7211/0.7078)	mem 34604MB
[2025-01-19 13:08:36 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][280/312]	eta 0:00:24 lr 0.001390	time 0.7243 (0.7514)	model_time 0.7241 (0.7465)	loss 2.8404 (3.1236)	grad_norm 1.3580 (1.7011/0.7926)	mem 34602MB
[2025-01-19 13:08:38 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][200/312]	eta 0:01:23 lr 0.001396	time 0.7250 (0.7453)	model_time 0.7248 (0.7386)	loss 3.8938 (3.0300)	grad_norm 1.6588 (1.7360/0.7129)	mem 34604MB
[2025-01-19 13:08:44 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][290/312]	eta 0:00:16 lr 0.001390	time 0.7270 (0.7507)	model_time 0.7268 (0.7459)	loss 2.2421 (3.1260)	grad_norm 1.1825 (1.7237/0.8105)	mem 34602MB
[2025-01-19 13:08:46 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][210/312]	eta 0:01:15 lr 0.001395	time 0.7263 (0.7444)	model_time 0.7258 (0.7380)	loss 2.4758 (3.0190)	grad_norm 1.6528 (1.7304/0.7023)	mem 34604MB
[2025-01-19 13:08:51 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][300/312]	eta 0:00:09 lr 0.001389	time 0.7131 (0.7505)	model_time 0.7130 (0.7459)	loss 2.6619 (3.1158)	grad_norm 2.5914 (1.7216/0.8017)	mem 34602MB
[2025-01-19 13:08:53 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][220/312]	eta 0:01:08 lr 0.001394	time 0.8374 (0.7452)	model_time 0.8373 (0.7391)	loss 3.1493 (3.0261)	grad_norm 1.8549 (1.7366/0.7036)	mem 34604MB
[2025-01-19 13:08:58 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][310/312]	eta 0:00:01 lr 0.001389	time 0.7140 (0.7499)	model_time 0.7139 (0.7454)	loss 3.0818 (3.1142)	grad_norm 0.9347 (1.6944/0.7841)	mem 34602MB
[2025-01-19 13:08:59 internimage_b_1k_224] (main.py 519): INFO EPOCH 180 training takes 0:03:53
[2025-01-19 13:08:59 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_180.pth saving......
[2025-01-19 13:09:01 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][230/312]	eta 0:01:01 lr 0.001394	time 0.8342 (0.7471)	model_time 0.8338 (0.7412)	loss 3.9646 (3.0244)	grad_norm 0.8320 (1.7309/0.6986)	mem 34604MB
[2025-01-19 13:09:02 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_180.pth saved !!!
[2025-01-19 13:09:09 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][240/312]	eta 0:00:53 lr 0.001393	time 0.8119 (0.7486)	model_time 0.8117 (0.7429)	loss 3.3337 (3.0297)	grad_norm 1.5323 (1.7129/0.6924)	mem 34604MB
[2025-01-19 13:09:10 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.394 (7.394)	Loss 0.7510 (0.7510)	Acc@1 84.497 (84.497)	Acc@5 97.388 (97.388)	Mem 34602MB
[2025-01-19 13:09:13 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.957)	Loss 1.0129 (0.8628)	Acc@1 77.100 (82.005)	Acc@5 94.946 (96.045)	Mem 34602MB
[2025-01-19 13:09:13 internimage_b_1k_224] (main.py 575): INFO [Epoch:180] * Acc@1 81.856 Acc@5 96.057
[2025-01-19 13:09:13 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.9%
[2025-01-19 13:09:13 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 13:09:16 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][250/312]	eta 0:00:46 lr 0.001392	time 0.7205 (0.7483)	model_time 0.7200 (0.7428)	loss 3.2341 (3.0275)	grad_norm 1.4340 (1.6993/0.6855)	mem 34604MB
[2025-01-19 13:09:17 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 13:09:17 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.86%
[2025-01-19 13:09:24 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][260/312]	eta 0:00:38 lr 0.001392	time 0.7237 (0.7476)	model_time 0.7232 (0.7424)	loss 3.6666 (3.0325)	grad_norm 1.0429 (1.7099/0.6902)	mem 34604MB
[2025-01-19 13:09:25 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.003 (8.003)	Loss 0.6771 (0.6771)	Acc@1 84.717 (84.717)	Acc@5 97.803 (97.803)	Mem 34602MB
[2025-01-19 13:09:28 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.072)	Loss 0.9492 (0.8001)	Acc@1 78.296 (82.291)	Acc@5 94.922 (96.309)	Mem 34602MB
[2025-01-19 13:09:29 internimage_b_1k_224] (main.py 575): INFO [Epoch:180] * Acc@1 82.126 Acc@5 96.367
[2025-01-19 13:09:29 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.1%
[2025-01-19 13:09:29 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:09:31 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][270/312]	eta 0:00:31 lr 0.001391	time 0.7507 (0.7472)	model_time 0.7503 (0.7421)	loss 3.3397 (3.0411)	grad_norm 3.1292 (1.7420/0.7298)	mem 34604MB
[2025-01-19 13:09:33 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:09:33 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.13%
[2025-01-19 13:09:35 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][0/312]	eta 0:10:30 lr 0.001388	time 2.0200 (2.0200)	model_time 0.7482 (0.7482)	loss 3.4955 (3.4955)	grad_norm 1.4225 (1.4225/0.0000)	mem 34602MB
[2025-01-19 13:09:38 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][280/312]	eta 0:00:23 lr 0.001390	time 0.7180 (0.7465)	model_time 0.7178 (0.7416)	loss 2.1867 (3.0417)	grad_norm 1.0390 (1.7321/0.7289)	mem 34604MB
[2025-01-19 13:09:42 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][10/312]	eta 0:04:24 lr 0.001388	time 0.7175 (0.8756)	model_time 0.7171 (0.7596)	loss 3.1099 (3.1071)	grad_norm 2.2446 (1.5090/0.4361)	mem 34602MB
[2025-01-19 13:09:46 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][290/312]	eta 0:00:16 lr 0.001390	time 0.7277 (0.7459)	model_time 0.7276 (0.7412)	loss 3.1750 (3.0408)	grad_norm 1.6718 (1.7445/0.7381)	mem 34604MB
[2025-01-19 13:09:50 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][20/312]	eta 0:03:57 lr 0.001387	time 0.7159 (0.8131)	model_time 0.7158 (0.7523)	loss 3.1263 (3.1202)	grad_norm 2.6472 (1.6432/0.5622)	mem 34602MB
[2025-01-19 13:09:53 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][300/312]	eta 0:00:08 lr 0.001389	time 0.7149 (0.7451)	model_time 0.7148 (0.7404)	loss 3.2250 (3.0432)	grad_norm 1.6762 (1.7414/0.7332)	mem 34604MB
[2025-01-19 13:09:57 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][30/312]	eta 0:03:43 lr 0.001387	time 0.7190 (0.7920)	model_time 0.7188 (0.7507)	loss 3.0389 (3.1234)	grad_norm 1.1293 (1.7938/0.6750)	mem 34602MB
[2025-01-19 13:10:00 internimage_b_1k_224] (main.py 510): INFO Train: [180/300][310/312]	eta 0:00:01 lr 0.001389	time 0.7198 (0.7443)	model_time 0.7197 (0.7399)	loss 3.7305 (3.0495)	grad_norm 1.4735 (1.7374/0.7337)	mem 34604MB
[2025-01-19 13:10:01 internimage_b_1k_224] (main.py 519): INFO EPOCH 180 training takes 0:03:52
[2025-01-19 13:10:01 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_180.pth saving......
[2025-01-19 13:10:04 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_180.pth saved !!!
[2025-01-19 13:10:05 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][40/312]	eta 0:03:34 lr 0.001386	time 0.7236 (0.7882)	model_time 0.7232 (0.7568)	loss 3.6803 (3.1275)	grad_norm 2.0249 (1.8681/0.7184)	mem 34602MB
[2025-01-19 13:10:12 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.561 (7.561)	Loss 0.7643 (0.7643)	Acc@1 84.229 (84.229)	Acc@5 97.192 (97.192)	Mem 34604MB
[2025-01-19 13:10:12 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][50/312]	eta 0:03:24 lr 0.001385	time 0.7201 (0.7800)	model_time 0.7197 (0.7548)	loss 2.4372 (3.1113)	grad_norm 1.1788 (1.8065/0.6829)	mem 34602MB
[2025-01-19 13:10:15 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.968)	Loss 0.9914 (0.8642)	Acc@1 77.832 (81.798)	Acc@5 95.361 (96.067)	Mem 34604MB
[2025-01-19 13:10:15 internimage_b_1k_224] (main.py 575): INFO [Epoch:180] * Acc@1 81.696 Acc@5 96.063
[2025-01-19 13:10:15 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.7%
[2025-01-19 13:10:15 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.87%
[2025-01-19 13:10:20 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][60/312]	eta 0:03:15 lr 0.001385	time 0.7225 (0.7749)	model_time 0.7224 (0.7537)	loss 1.8419 (3.0693)	grad_norm 1.2026 (1.7066/0.6712)	mem 34602MB
[2025-01-19 13:10:24 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.126 (9.126)	Loss 0.6762 (0.6762)	Acc@1 84.839 (84.839)	Acc@5 97.876 (97.876)	Mem 34604MB
[2025-01-19 13:10:27 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][70/312]	eta 0:03:06 lr 0.001384	time 0.7179 (0.7726)	model_time 0.7177 (0.7543)	loss 2.9289 (3.0630)	grad_norm 1.7407 (1.7566/0.7265)	mem 34602MB
[2025-01-19 13:10:29 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.239)	Loss 0.9498 (0.7992)	Acc@1 78.491 (82.382)	Acc@5 94.849 (96.305)	Mem 34604MB
[2025-01-19 13:10:29 internimage_b_1k_224] (main.py 575): INFO [Epoch:180] * Acc@1 82.240 Acc@5 96.351
[2025-01-19 13:10:29 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.2%
[2025-01-19 13:10:29 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:10:32 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:10:32 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.24%
[2025-01-19 13:10:35 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][0/312]	eta 0:10:35 lr 0.001388	time 2.0354 (2.0354)	model_time 0.7336 (0.7336)	loss 2.2800 (2.2800)	grad_norm 1.4543 (1.4543/0.0000)	mem 34604MB
[2025-01-19 13:10:35 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][80/312]	eta 0:02:58 lr 0.001383	time 0.7190 (0.7684)	model_time 0.7186 (0.7524)	loss 3.0118 (3.0810)	grad_norm 1.0782 (1.7293/0.7046)	mem 34602MB
[2025-01-19 13:10:42 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][10/312]	eta 0:04:16 lr 0.001388	time 0.7221 (0.8490)	model_time 0.7217 (0.7304)	loss 2.3614 (2.8916)	grad_norm 2.2410 (1.7175/0.5909)	mem 34604MB
[2025-01-19 13:10:42 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][90/312]	eta 0:02:49 lr 0.001383	time 0.7341 (0.7642)	model_time 0.7340 (0.7499)	loss 2.5206 (3.0789)	grad_norm 0.9068 (1.6873/0.6918)	mem 34602MB
[2025-01-19 13:10:49 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][20/312]	eta 0:03:51 lr 0.001387	time 0.7224 (0.7920)	model_time 0.7223 (0.7296)	loss 2.6842 (2.9755)	grad_norm 2.8978 (1.7495/0.6239)	mem 34604MB
[2025-01-19 13:10:49 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][100/312]	eta 0:02:41 lr 0.001382	time 0.7186 (0.7603)	model_time 0.7184 (0.7474)	loss 2.7399 (3.0448)	grad_norm 3.0075 (1.7326/0.7041)	mem 34602MB
[2025-01-19 13:10:57 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][110/312]	eta 0:02:33 lr 0.001382	time 0.7346 (0.7594)	model_time 0.7344 (0.7476)	loss 3.5164 (3.0458)	grad_norm 1.6380 (1.7465/0.7154)	mem 34602MB
[2025-01-19 13:10:57 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][30/312]	eta 0:03:42 lr 0.001387	time 0.8041 (0.7897)	model_time 0.8037 (0.7474)	loss 2.3948 (2.9709)	grad_norm 1.2352 (1.8806/0.8374)	mem 34604MB
[2025-01-19 13:11:04 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][120/312]	eta 0:02:25 lr 0.001381	time 0.7230 (0.7574)	model_time 0.7228 (0.7465)	loss 2.4914 (3.0448)	grad_norm 1.4406 (1.7381/0.6983)	mem 34602MB
[2025-01-19 13:11:05 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][40/312]	eta 0:03:35 lr 0.001386	time 0.8222 (0.7910)	model_time 0.8221 (0.7589)	loss 3.3473 (3.0036)	grad_norm 1.7981 (1.9172/0.8258)	mem 34604MB
[2025-01-19 13:11:12 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][130/312]	eta 0:02:17 lr 0.001380	time 0.7227 (0.7575)	model_time 0.7226 (0.7475)	loss 2.1074 (3.0566)	grad_norm 2.4324 (1.7342/0.6869)	mem 34602MB
[2025-01-19 13:11:13 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][50/312]	eta 0:03:26 lr 0.001385	time 0.7161 (0.7865)	model_time 0.7156 (0.7606)	loss 1.9840 (3.0317)	grad_norm 1.0993 (1.8362/0.7879)	mem 34604MB
[2025-01-19 13:11:19 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][140/312]	eta 0:02:10 lr 0.001380	time 0.7990 (0.7572)	model_time 0.7985 (0.7479)	loss 3.6405 (3.0587)	grad_norm 1.1085 (1.7128/0.6776)	mem 34602MB
[2025-01-19 13:11:20 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][60/312]	eta 0:03:16 lr 0.001385	time 0.7218 (0.7795)	model_time 0.7214 (0.7577)	loss 3.2382 (3.0218)	grad_norm 1.6469 (1.8102/0.7778)	mem 34604MB
[2025-01-19 13:11:27 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][150/312]	eta 0:02:02 lr 0.001379	time 0.7175 (0.7562)	model_time 0.7174 (0.7474)	loss 2.6738 (3.0665)	grad_norm 1.1995 (1.7130/0.6670)	mem 34602MB
[2025-01-19 13:11:28 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][70/312]	eta 0:03:07 lr 0.001384	time 0.8085 (0.7749)	model_time 0.8083 (0.7562)	loss 3.2736 (3.0366)	grad_norm 0.7961 (1.8891/0.8689)	mem 34604MB
[2025-01-19 13:11:34 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][160/312]	eta 0:01:55 lr 0.001378	time 0.7179 (0.7574)	model_time 0.7174 (0.7491)	loss 3.2347 (3.0589)	grad_norm 1.7975 (1.7304/0.6811)	mem 34602MB
[2025-01-19 13:11:35 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][80/312]	eta 0:02:58 lr 0.001383	time 0.7287 (0.7690)	model_time 0.7285 (0.7526)	loss 2.1348 (3.0078)	grad_norm 2.5465 (1.9200/0.8896)	mem 34604MB
[2025-01-19 13:11:42 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][170/312]	eta 0:01:47 lr 0.001378	time 0.7287 (0.7567)	model_time 0.7283 (0.7489)	loss 2.9269 (3.0555)	grad_norm 1.0516 (1.7220/0.6823)	mem 34602MB
[2025-01-19 13:11:42 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][90/312]	eta 0:02:49 lr 0.001383	time 0.7174 (0.7646)	model_time 0.7173 (0.7499)	loss 3.0011 (3.0198)	grad_norm 1.7072 (1.8899/0.8692)	mem 34604MB
[2025-01-19 13:11:49 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][100/312]	eta 0:02:41 lr 0.001382	time 0.7172 (0.7605)	model_time 0.7171 (0.7473)	loss 2.4529 (3.0194)	grad_norm 0.9535 (1.8308/0.8489)	mem 34604MB
[2025-01-19 13:11:49 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][180/312]	eta 0:01:39 lr 0.001377	time 0.7210 (0.7560)	model_time 0.7206 (0.7486)	loss 3.3934 (3.0673)	grad_norm 2.1727 (1.7297/0.6844)	mem 34602MB
[2025-01-19 13:11:57 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][110/312]	eta 0:02:33 lr 0.001382	time 0.7403 (0.7580)	model_time 0.7402 (0.7459)	loss 3.2205 (3.0313)	grad_norm 1.5465 (1.8193/0.8334)	mem 34604MB
[2025-01-19 13:11:57 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][190/312]	eta 0:01:32 lr 0.001377	time 0.7175 (0.7560)	model_time 0.7173 (0.7490)	loss 2.8035 (3.0644)	grad_norm 2.2938 (1.7676/0.7242)	mem 34602MB
[2025-01-19 13:12:04 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][120/312]	eta 0:02:25 lr 0.001381	time 0.7235 (0.7555)	model_time 0.7230 (0.7444)	loss 2.4574 (3.0354)	grad_norm 1.5022 (1.7901/0.8093)	mem 34604MB
[2025-01-19 13:12:04 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][200/312]	eta 0:01:24 lr 0.001376	time 0.7271 (0.7551)	model_time 0.7266 (0.7484)	loss 3.2541 (3.0654)	grad_norm 1.7190 (1.7822/0.7334)	mem 34602MB
[2025-01-19 13:12:11 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][130/312]	eta 0:02:17 lr 0.001380	time 0.7209 (0.7532)	model_time 0.7207 (0.7429)	loss 3.0063 (3.0185)	grad_norm 1.2078 (1.7528/0.7916)	mem 34604MB
[2025-01-19 13:12:12 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][210/312]	eta 0:01:16 lr 0.001375	time 0.7174 (0.7539)	model_time 0.7172 (0.7475)	loss 2.2692 (3.0745)	grad_norm 2.0147 (1.7816/0.7258)	mem 34602MB
[2025-01-19 13:12:18 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][140/312]	eta 0:02:09 lr 0.001380	time 0.7182 (0.7513)	model_time 0.7178 (0.7417)	loss 3.4669 (3.0076)	grad_norm 0.9517 (1.7724/0.8145)	mem 34604MB
[2025-01-19 13:12:19 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][220/312]	eta 0:01:09 lr 0.001375	time 0.7204 (0.7525)	model_time 0.7199 (0.7464)	loss 3.4527 (3.0744)	grad_norm 0.8518 (1.7795/0.7246)	mem 34602MB
[2025-01-19 13:12:26 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][150/312]	eta 0:02:01 lr 0.001379	time 0.8021 (0.7528)	model_time 0.8017 (0.7438)	loss 2.1543 (3.0221)	grad_norm 1.6055 (1.7499/0.8001)	mem 34604MB
[2025-01-19 13:12:26 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][230/312]	eta 0:01:01 lr 0.001374	time 0.7255 (0.7524)	model_time 0.7253 (0.7465)	loss 3.0330 (3.0715)	grad_norm 1.3945 (1.7692/0.7136)	mem 34602MB
[2025-01-19 13:12:34 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][240/312]	eta 0:00:54 lr 0.001373	time 0.7261 (0.7516)	model_time 0.7257 (0.7460)	loss 2.4848 (3.0676)	grad_norm 0.9317 (1.7563/0.7087)	mem 34602MB
[2025-01-19 13:12:34 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][160/312]	eta 0:01:55 lr 0.001378	time 0.8315 (0.7567)	model_time 0.8311 (0.7483)	loss 3.5866 (3.0277)	grad_norm 1.0898 (1.7613/0.8101)	mem 34604MB
[2025-01-19 13:12:41 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][250/312]	eta 0:00:46 lr 0.001373	time 0.7167 (0.7518)	model_time 0.7165 (0.7464)	loss 3.3474 (3.0691)	grad_norm 2.9313 (1.7682/0.7166)	mem 34602MB
[2025-01-19 13:12:42 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][170/312]	eta 0:01:47 lr 0.001378	time 0.8049 (0.7587)	model_time 0.8047 (0.7507)	loss 3.3520 (3.0262)	grad_norm 1.5661 (1.7486/0.7938)	mem 34604MB
[2025-01-19 13:12:49 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][260/312]	eta 0:00:39 lr 0.001372	time 0.8015 (0.7518)	model_time 0.8011 (0.7466)	loss 3.3413 (3.0714)	grad_norm 2.1900 (1.7831/0.7240)	mem 34602MB
[2025-01-19 13:12:50 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][180/312]	eta 0:01:40 lr 0.001377	time 0.7440 (0.7581)	model_time 0.7438 (0.7505)	loss 3.4510 (3.0302)	grad_norm 1.0375 (1.7542/0.8037)	mem 34604MB
[2025-01-19 13:12:56 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][270/312]	eta 0:00:31 lr 0.001371	time 0.7185 (0.7515)	model_time 0.7184 (0.7465)	loss 3.2169 (3.0682)	grad_norm 1.6842 (1.7849/0.7244)	mem 34602MB
[2025-01-19 13:12:57 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][190/312]	eta 0:01:32 lr 0.001377	time 0.8057 (0.7573)	model_time 0.8055 (0.7501)	loss 2.4999 (3.0342)	grad_norm 1.8900 (1.7551/0.7895)	mem 34604MB
[2025-01-19 13:13:04 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][280/312]	eta 0:00:24 lr 0.001371	time 0.7186 (0.7520)	model_time 0.7184 (0.7472)	loss 2.7802 (3.0659)	grad_norm 1.3671 (1.7718/0.7188)	mem 34602MB
[2025-01-19 13:13:04 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][200/312]	eta 0:01:24 lr 0.001376	time 0.7372 (0.7556)	model_time 0.7370 (0.7488)	loss 3.3434 (3.0390)	grad_norm 1.9560 (1.7675/0.7899)	mem 34604MB
[2025-01-19 13:13:11 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][290/312]	eta 0:00:16 lr 0.001370	time 0.8207 (0.7521)	model_time 0.8205 (0.7474)	loss 3.7356 (3.0613)	grad_norm 1.2960 (1.7595/0.7129)	mem 34602MB
[2025-01-19 13:13:12 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][210/312]	eta 0:01:16 lr 0.001375	time 0.7170 (0.7541)	model_time 0.7169 (0.7475)	loss 2.8844 (3.0464)	grad_norm 1.4845 (1.7724/0.8005)	mem 34604MB
[2025-01-19 13:13:19 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][300/312]	eta 0:00:09 lr 0.001370	time 0.7137 (0.7512)	model_time 0.7136 (0.7467)	loss 3.7423 (3.0638)	grad_norm 1.5758 (1.7627/0.7104)	mem 34602MB
[2025-01-19 13:13:19 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][220/312]	eta 0:01:09 lr 0.001375	time 0.7099 (0.7526)	model_time 0.7095 (0.7464)	loss 2.5293 (3.0600)	grad_norm 0.8957 (1.7439/0.7954)	mem 34604MB
[2025-01-19 13:13:26 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][310/312]	eta 0:00:01 lr 0.001369	time 0.8020 (0.7511)	model_time 0.8019 (0.7466)	loss 3.1190 (3.0658)	grad_norm 0.8446 (1.7541/0.7147)	mem 34602MB
[2025-01-19 13:13:26 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][230/312]	eta 0:01:01 lr 0.001374	time 0.7164 (0.7515)	model_time 0.7162 (0.7455)	loss 3.0252 (3.0552)	grad_norm 3.4374 (1.7717/0.8541)	mem 34604MB
[2025-01-19 13:13:27 internimage_b_1k_224] (main.py 519): INFO EPOCH 181 training takes 0:03:54
[2025-01-19 13:13:27 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_181.pth saving......
[2025-01-19 13:13:30 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_181.pth saved !!!
[2025-01-19 13:13:33 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][240/312]	eta 0:00:54 lr 0.001373	time 0.7361 (0.7507)	model_time 0.7357 (0.7449)	loss 2.1481 (3.0424)	grad_norm 1.4974 (1.8040/0.8798)	mem 34604MB
[2025-01-19 13:13:38 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.618 (7.618)	Loss 0.7716 (0.7716)	Acc@1 84.253 (84.253)	Acc@5 97.144 (97.144)	Mem 34602MB
[2025-01-19 13:13:41 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][250/312]	eta 0:00:46 lr 0.001373	time 0.7238 (0.7499)	model_time 0.7236 (0.7444)	loss 2.9855 (3.0378)	grad_norm 1.1984 (1.7983/0.8690)	mem 34604MB
[2025-01-19 13:13:41 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.975)	Loss 1.0103 (0.8638)	Acc@1 77.417 (81.816)	Acc@5 94.800 (96.032)	Mem 34602MB
[2025-01-19 13:13:41 internimage_b_1k_224] (main.py 575): INFO [Epoch:181] * Acc@1 81.662 Acc@5 96.045
[2025-01-19 13:13:41 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.7%
[2025-01-19 13:13:41 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.86%
[2025-01-19 13:13:48 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][260/312]	eta 0:00:38 lr 0.001372	time 0.7293 (0.7490)	model_time 0.7288 (0.7437)	loss 2.1328 (3.0401)	grad_norm 1.6391 (1.7788/0.8607)	mem 34604MB
[2025-01-19 13:13:50 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.387 (9.387)	Loss 0.6784 (0.6784)	Acc@1 84.717 (84.717)	Acc@5 97.803 (97.803)	Mem 34602MB
[2025-01-19 13:13:55 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.260)	Loss 0.9494 (0.8007)	Acc@1 78.369 (82.311)	Acc@5 94.922 (96.316)	Mem 34602MB
[2025-01-19 13:13:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:181] * Acc@1 82.144 Acc@5 96.371
[2025-01-19 13:13:55 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.1%
[2025-01-19 13:13:55 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:13:56 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][270/312]	eta 0:00:31 lr 0.001371	time 0.8116 (0.7496)	model_time 0.8111 (0.7445)	loss 2.6661 (3.0356)	grad_norm 1.9598 (1.7990/0.8754)	mem 34604MB
[2025-01-19 13:13:59 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:13:59 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.14%
[2025-01-19 13:14:01 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][0/312]	eta 0:11:34 lr 0.001369	time 2.2249 (2.2249)	model_time 0.7530 (0.7530)	loss 3.6718 (3.6718)	grad_norm 0.9645 (0.9645/0.0000)	mem 34602MB
[2025-01-19 13:14:04 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][280/312]	eta 0:00:24 lr 0.001371	time 0.8207 (0.7513)	model_time 0.8205 (0.7463)	loss 1.9296 (3.0260)	grad_norm 1.2714 (1.7994/0.8645)	mem 34604MB
[2025-01-19 13:14:09 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][10/312]	eta 0:04:24 lr 0.001368	time 0.7377 (0.8744)	model_time 0.7376 (0.7404)	loss 3.3392 (3.2621)	grad_norm 2.0556 (1.6489/0.6457)	mem 34602MB
[2025-01-19 13:14:12 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][290/312]	eta 0:00:16 lr 0.001370	time 0.8043 (0.7527)	model_time 0.8041 (0.7479)	loss 3.5822 (3.0269)	grad_norm 1.7690 (1.8053/0.8601)	mem 34604MB
[2025-01-19 13:14:16 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][20/312]	eta 0:03:56 lr 0.001368	time 0.7178 (0.8088)	model_time 0.7177 (0.7385)	loss 2.5166 (3.0805)	grad_norm 3.0663 (1.7822/0.6598)	mem 34602MB
[2025-01-19 13:14:19 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][300/312]	eta 0:00:09 lr 0.001370	time 0.7906 (0.7525)	model_time 0.7905 (0.7478)	loss 3.2164 (3.0240)	grad_norm 0.8842 (1.8100/0.8617)	mem 34604MB
[2025-01-19 13:14:23 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][30/312]	eta 0:03:40 lr 0.001367	time 0.7277 (0.7829)	model_time 0.7276 (0.7352)	loss 2.0265 (3.0118)	grad_norm 0.9999 (1.8170/0.6783)	mem 34602MB
[2025-01-19 13:14:26 internimage_b_1k_224] (main.py 510): INFO Train: [181/300][310/312]	eta 0:00:01 lr 0.001369	time 0.7167 (0.7516)	model_time 0.7166 (0.7470)	loss 2.8864 (3.0264)	grad_norm 0.8458 (1.8009/0.8613)	mem 34604MB
[2025-01-19 13:14:27 internimage_b_1k_224] (main.py 519): INFO EPOCH 181 training takes 0:03:54
[2025-01-19 13:14:27 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_181.pth saving......
[2025-01-19 13:14:30 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_181.pth saved !!!
[2025-01-19 13:14:31 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][40/312]	eta 0:03:31 lr 0.001366	time 0.7200 (0.7762)	model_time 0.7198 (0.7400)	loss 3.5936 (3.0661)	grad_norm 2.4891 (1.8706/0.7730)	mem 34602MB
[2025-01-19 13:14:38 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.371 (7.371)	Loss 0.7747 (0.7747)	Acc@1 84.180 (84.180)	Acc@5 97.290 (97.290)	Mem 34604MB
[2025-01-19 13:14:39 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][50/312]	eta 0:03:22 lr 0.001366	time 0.8113 (0.7728)	model_time 0.8111 (0.7436)	loss 3.6538 (3.0922)	grad_norm 2.0051 (1.8455/0.7030)	mem 34602MB
[2025-01-19 13:14:41 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.953)	Loss 1.0123 (0.8816)	Acc@1 78.369 (81.969)	Acc@5 94.824 (96.049)	Mem 34604MB
[2025-01-19 13:14:41 internimage_b_1k_224] (main.py 575): INFO [Epoch:181] * Acc@1 81.854 Acc@5 96.057
[2025-01-19 13:14:41 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.9%
[2025-01-19 13:14:41 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.87%
[2025-01-19 13:14:46 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][60/312]	eta 0:03:13 lr 0.001365	time 0.8189 (0.7689)	model_time 0.8188 (0.7444)	loss 3.4564 (3.1269)	grad_norm 3.0810 (1.8498/0.6825)	mem 34602MB
[2025-01-19 13:14:50 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.164 (9.164)	Loss 0.6772 (0.6772)	Acc@1 84.937 (84.937)	Acc@5 97.852 (97.852)	Mem 34604MB
[2025-01-19 13:14:54 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][70/312]	eta 0:03:05 lr 0.001364	time 0.7248 (0.7666)	model_time 0.7246 (0.7455)	loss 2.9419 (3.1198)	grad_norm 2.2903 (1.8336/0.6463)	mem 34602MB
[2025-01-19 13:14:55 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.256)	Loss 0.9500 (0.7998)	Acc@1 78.516 (82.413)	Acc@5 94.824 (96.302)	Mem 34604MB
[2025-01-19 13:14:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:181] * Acc@1 82.264 Acc@5 96.351
[2025-01-19 13:14:55 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.3%
[2025-01-19 13:14:55 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:14:58 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:14:58 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.26%
[2025-01-19 13:15:01 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][0/312]	eta 0:11:06 lr 0.001369	time 2.1376 (2.1376)	model_time 0.7458 (0.7458)	loss 3.1505 (3.1505)	grad_norm 3.3832 (3.3832/0.0000)	mem 34604MB
[2025-01-19 13:15:01 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][80/312]	eta 0:02:57 lr 0.001364	time 0.7173 (0.7639)	model_time 0.7171 (0.7454)	loss 3.3176 (3.1156)	grad_norm 4.7637 (1.9276/0.7460)	mem 34602MB
[2025-01-19 13:15:08 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][10/312]	eta 0:04:18 lr 0.001368	time 0.7369 (0.8554)	model_time 0.7365 (0.7285)	loss 3.8399 (2.9094)	grad_norm 1.1310 (1.3767/0.7254)	mem 34604MB
[2025-01-19 13:15:09 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][90/312]	eta 0:02:49 lr 0.001363	time 0.7950 (0.7653)	model_time 0.7945 (0.7488)	loss 2.4271 (3.0829)	grad_norm 1.0243 (1.8892/0.7470)	mem 34602MB
[2025-01-19 13:15:15 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][20/312]	eta 0:03:51 lr 0.001368	time 0.7254 (0.7932)	model_time 0.7252 (0.7265)	loss 2.2451 (2.8610)	grad_norm 1.1593 (1.2813/0.5629)	mem 34604MB
[2025-01-19 13:15:16 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][100/312]	eta 0:02:41 lr 0.001363	time 0.7180 (0.7621)	model_time 0.7178 (0.7472)	loss 3.6332 (3.0957)	grad_norm 1.9342 (1.8504/0.7317)	mem 34602MB
[2025-01-19 13:15:22 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][30/312]	eta 0:03:38 lr 0.001367	time 0.7241 (0.7747)	model_time 0.7239 (0.7295)	loss 2.1535 (2.8739)	grad_norm 1.1693 (1.2713/0.5046)	mem 34604MB
[2025-01-19 13:15:24 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][110/312]	eta 0:02:34 lr 0.001362	time 1.0884 (0.7628)	model_time 1.0879 (0.7492)	loss 2.8226 (3.0687)	grad_norm 1.1174 (1.8455/0.7160)	mem 34602MB
[2025-01-19 13:15:30 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][40/312]	eta 0:03:27 lr 0.001366	time 0.7228 (0.7642)	model_time 0.7223 (0.7299)	loss 2.1498 (2.8691)	grad_norm 2.9441 (1.3984/0.5793)	mem 34604MB
[2025-01-19 13:15:31 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][120/312]	eta 0:02:26 lr 0.001361	time 0.8396 (0.7615)	model_time 0.8394 (0.7490)	loss 3.4209 (3.0859)	grad_norm 0.7463 (1.8568/0.7266)	mem 34602MB
[2025-01-19 13:15:37 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][50/312]	eta 0:03:18 lr 0.001366	time 0.7217 (0.7570)	model_time 0.7212 (0.7294)	loss 3.0536 (2.9108)	grad_norm 1.7278 (1.4438/0.5641)	mem 34604MB
[2025-01-19 13:15:39 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][130/312]	eta 0:02:18 lr 0.001361	time 0.7242 (0.7597)	model_time 0.7240 (0.7481)	loss 2.5197 (3.0848)	grad_norm 1.6103 (1.8584/0.7275)	mem 34602MB
[2025-01-19 13:15:44 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][60/312]	eta 0:03:09 lr 0.001365	time 0.7252 (0.7522)	model_time 0.7250 (0.7290)	loss 3.2855 (2.9232)	grad_norm 1.0835 (1.4471/0.5392)	mem 34604MB
[2025-01-19 13:15:46 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][140/312]	eta 0:02:10 lr 0.001360	time 0.7338 (0.7578)	model_time 0.7336 (0.7470)	loss 3.2570 (3.0849)	grad_norm 1.4481 (1.8722/0.7277)	mem 34602MB
[2025-01-19 13:15:52 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][70/312]	eta 0:03:01 lr 0.001364	time 0.7253 (0.7497)	model_time 0.7249 (0.7297)	loss 2.3433 (2.9509)	grad_norm 1.8420 (1.5057/0.5493)	mem 34604MB
[2025-01-19 13:15:53 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][150/312]	eta 0:02:02 lr 0.001359	time 0.7194 (0.7556)	model_time 0.7190 (0.7455)	loss 3.2027 (3.0699)	grad_norm 1.7890 (1.8882/0.7206)	mem 34602MB
[2025-01-19 13:15:59 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][80/312]	eta 0:02:54 lr 0.001364	time 0.8208 (0.7525)	model_time 0.8204 (0.7349)	loss 3.5672 (2.9653)	grad_norm 3.2893 (1.6731/0.7731)	mem 34604MB
[2025-01-19 13:16:01 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][160/312]	eta 0:01:54 lr 0.001359	time 0.7288 (0.7556)	model_time 0.7287 (0.7461)	loss 3.2817 (3.0679)	grad_norm 1.3790 (1.8430/0.7229)	mem 34602MB
[2025-01-19 13:16:07 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][90/312]	eta 0:02:48 lr 0.001363	time 0.8059 (0.7592)	model_time 0.8057 (0.7436)	loss 2.9054 (2.9873)	grad_norm 2.8840 (1.7494/0.8283)	mem 34604MB
[2025-01-19 13:16:08 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][170/312]	eta 0:01:47 lr 0.001358	time 0.8077 (0.7551)	model_time 0.8073 (0.7461)	loss 3.3533 (3.0551)	grad_norm 2.4369 (1.8646/0.7464)	mem 34602MB
[2025-01-19 13:16:15 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][100/312]	eta 0:02:41 lr 0.001363	time 0.8049 (0.7607)	model_time 0.8045 (0.7466)	loss 2.9384 (3.0055)	grad_norm 1.5971 (1.7302/0.8203)	mem 34604MB
[2025-01-19 13:16:16 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][180/312]	eta 0:01:39 lr 0.001358	time 0.8155 (0.7551)	model_time 0.8150 (0.7467)	loss 3.7330 (3.0567)	grad_norm 1.6754 (1.8333/0.7391)	mem 34602MB
[2025-01-19 13:16:23 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][110/312]	eta 0:02:33 lr 0.001362	time 0.7369 (0.7592)	model_time 0.7367 (0.7463)	loss 3.4734 (2.9907)	grad_norm 2.3235 (1.7307/0.7985)	mem 34604MB
[2025-01-19 13:16:23 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][190/312]	eta 0:01:32 lr 0.001357	time 0.7187 (0.7548)	model_time 0.7182 (0.7467)	loss 3.3467 (3.0577)	grad_norm 0.7932 (1.8140/0.7299)	mem 34602MB
[2025-01-19 13:16:30 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][120/312]	eta 0:02:25 lr 0.001361	time 0.7285 (0.7571)	model_time 0.7283 (0.7453)	loss 2.9081 (3.0149)	grad_norm 1.2362 (1.7042/0.7762)	mem 34604MB
[2025-01-19 13:16:31 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][200/312]	eta 0:01:24 lr 0.001356	time 0.7167 (0.7546)	model_time 0.7163 (0.7470)	loss 3.3280 (3.0626)	grad_norm 1.4312 (1.7992/0.7187)	mem 34602MB
[2025-01-19 13:16:37 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][130/312]	eta 0:02:17 lr 0.001361	time 0.7285 (0.7553)	model_time 0.7281 (0.7443)	loss 3.4965 (3.0216)	grad_norm 0.8804 (1.6510/0.7703)	mem 34604MB
[2025-01-19 13:16:39 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][210/312]	eta 0:01:17 lr 0.001356	time 0.7914 (0.7554)	model_time 0.7912 (0.7481)	loss 3.3067 (3.0624)	grad_norm 1.2210 (1.7937/0.7061)	mem 34602MB
[2025-01-19 13:16:45 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][140/312]	eta 0:02:09 lr 0.001360	time 0.7232 (0.7533)	model_time 0.7231 (0.7431)	loss 3.6286 (3.0208)	grad_norm 3.0391 (1.6861/0.7846)	mem 34604MB
[2025-01-19 13:16:46 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][220/312]	eta 0:01:09 lr 0.001355	time 0.7189 (0.7546)	model_time 0.7187 (0.7476)	loss 1.9905 (3.0532)	grad_norm 1.3247 (1.7751/0.7008)	mem 34602MB
[2025-01-19 13:16:52 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][150/312]	eta 0:02:01 lr 0.001359	time 0.7679 (0.7523)	model_time 0.7678 (0.7427)	loss 2.7522 (3.0252)	grad_norm 1.7760 (1.7341/0.8145)	mem 34604MB
[2025-01-19 13:16:53 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][230/312]	eta 0:01:01 lr 0.001354	time 0.8164 (0.7540)	model_time 0.8160 (0.7473)	loss 3.1404 (3.0613)	grad_norm 1.5088 (1.7727/0.6919)	mem 34602MB
[2025-01-19 13:16:59 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][160/312]	eta 0:01:54 lr 0.001359	time 0.7232 (0.7508)	model_time 0.7231 (0.7418)	loss 1.9909 (3.0281)	grad_norm 1.4860 (1.7492/0.8152)	mem 34604MB
[2025-01-19 13:17:01 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][240/312]	eta 0:00:54 lr 0.001354	time 0.8134 (0.7537)	model_time 0.8133 (0.7473)	loss 2.0246 (3.0474)	grad_norm 2.2895 (1.7801/0.6832)	mem 34602MB
[2025-01-19 13:17:07 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][170/312]	eta 0:01:46 lr 0.001358	time 0.7171 (0.7495)	model_time 0.7170 (0.7410)	loss 3.6192 (3.0198)	grad_norm 1.9620 (1.7545/0.7942)	mem 34604MB
[2025-01-19 13:17:08 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][250/312]	eta 0:00:46 lr 0.001353	time 0.8069 (0.7531)	model_time 0.8067 (0.7469)	loss 2.6558 (3.0421)	grad_norm 1.7157 (1.7822/0.6845)	mem 34602MB
[2025-01-19 13:17:14 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][180/312]	eta 0:01:38 lr 0.001358	time 0.7389 (0.7484)	model_time 0.7385 (0.7403)	loss 2.4527 (3.0263)	grad_norm 1.0225 (1.7402/0.7820)	mem 34604MB
[2025-01-19 13:17:16 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][260/312]	eta 0:00:39 lr 0.001353	time 0.7193 (0.7526)	model_time 0.7188 (0.7466)	loss 3.0486 (3.0424)	grad_norm 1.2368 (1.7922/0.6875)	mem 34602MB
[2025-01-19 13:17:21 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][190/312]	eta 0:01:31 lr 0.001357	time 0.7188 (0.7474)	model_time 0.7183 (0.7397)	loss 3.0650 (3.0232)	grad_norm 2.8734 (1.7294/0.7741)	mem 34604MB
[2025-01-19 13:17:23 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][270/312]	eta 0:00:31 lr 0.001352	time 0.7221 (0.7515)	model_time 0.7220 (0.7458)	loss 2.9888 (3.0507)	grad_norm 1.1320 (1.7926/0.6858)	mem 34602MB
[2025-01-19 13:17:29 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][200/312]	eta 0:01:23 lr 0.001356	time 0.7151 (0.7483)	model_time 0.7147 (0.7410)	loss 2.1528 (3.0130)	grad_norm 2.5512 (1.7304/0.7810)	mem 34604MB
[2025-01-19 13:17:30 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][280/312]	eta 0:00:24 lr 0.001351	time 0.7250 (0.7518)	model_time 0.7248 (0.7462)	loss 3.5068 (3.0610)	grad_norm 2.6465 (1.7939/0.6866)	mem 34602MB
[2025-01-19 13:17:37 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][210/312]	eta 0:01:16 lr 0.001356	time 0.8250 (0.7514)	model_time 0.8246 (0.7444)	loss 3.3892 (3.0069)	grad_norm 1.2046 (1.7231/0.7716)	mem 34604MB
[2025-01-19 13:17:38 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][290/312]	eta 0:00:16 lr 0.001351	time 0.7395 (0.7514)	model_time 0.7391 (0.7460)	loss 1.9590 (3.0513)	grad_norm 1.2687 (1.7804/0.6802)	mem 34602MB
[2025-01-19 13:17:45 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][220/312]	eta 0:01:09 lr 0.001355	time 0.7210 (0.7525)	model_time 0.7206 (0.7458)	loss 2.4655 (3.0070)	grad_norm 1.1990 (1.7081/0.7620)	mem 34604MB
[2025-01-19 13:17:45 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][300/312]	eta 0:00:09 lr 0.001350	time 0.8185 (0.7520)	model_time 0.8184 (0.7468)	loss 2.9901 (3.0491)	grad_norm 1.7743 (1.7872/0.6773)	mem 34602MB
[2025-01-19 13:17:52 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][230/312]	eta 0:01:01 lr 0.001354	time 0.7292 (0.7525)	model_time 0.7288 (0.7461)	loss 3.1371 (2.9978)	grad_norm 1.5938 (1.6944/0.7504)	mem 34604MB
[2025-01-19 13:17:53 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][310/312]	eta 0:00:01 lr 0.001349	time 0.7565 (0.7523)	model_time 0.7564 (0.7472)	loss 3.2424 (3.0490)	grad_norm 2.0892 (1.7916/0.6763)	mem 34602MB
[2025-01-19 13:17:54 internimage_b_1k_224] (main.py 519): INFO EPOCH 182 training takes 0:03:54
[2025-01-19 13:17:54 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_182.pth saving......
[2025-01-19 13:17:57 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_182.pth saved !!!
[2025-01-19 13:18:00 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][240/312]	eta 0:00:54 lr 0.001354	time 0.7206 (0.7516)	model_time 0.7202 (0.7454)	loss 3.5550 (3.0027)	grad_norm 1.0703 (1.6796/0.7453)	mem 34604MB
[2025-01-19 13:18:05 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.887 (7.887)	Loss 0.7532 (0.7532)	Acc@1 84.839 (84.839)	Acc@5 97.437 (97.437)	Mem 34602MB
[2025-01-19 13:18:07 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][250/312]	eta 0:00:46 lr 0.001353	time 0.7206 (0.7506)	model_time 0.7201 (0.7447)	loss 4.0427 (2.9965)	grad_norm 1.5240 (1.6737/0.7334)	mem 34604MB
[2025-01-19 13:18:08 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.992)	Loss 1.0290 (0.8661)	Acc@1 77.930 (82.169)	Acc@5 94.800 (96.145)	Mem 34602MB
[2025-01-19 13:18:08 internimage_b_1k_224] (main.py 575): INFO [Epoch:182] * Acc@1 81.998 Acc@5 96.141
[2025-01-19 13:18:08 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.0%
[2025-01-19 13:18:08 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 13:18:11 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 13:18:11 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.00%
[2025-01-19 13:18:14 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][260/312]	eta 0:00:38 lr 0.001353	time 0.7227 (0.7497)	model_time 0.7225 (0.7439)	loss 3.0190 (3.0034)	grad_norm 1.4717 (1.7063/0.7613)	mem 34604MB
[2025-01-19 13:18:19 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.602 (7.602)	Loss 0.6795 (0.6795)	Acc@1 84.692 (84.692)	Acc@5 97.803 (97.803)	Mem 34602MB
[2025-01-19 13:18:21 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][270/312]	eta 0:00:31 lr 0.001352	time 0.7415 (0.7490)	model_time 0.7411 (0.7435)	loss 2.9719 (2.9943)	grad_norm 0.9323 (1.7186/0.7690)	mem 34604MB
[2025-01-19 13:18:22 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.971)	Loss 0.9496 (0.8012)	Acc@1 78.296 (82.338)	Acc@5 94.971 (96.320)	Mem 34602MB
[2025-01-19 13:18:22 internimage_b_1k_224] (main.py 575): INFO [Epoch:182] * Acc@1 82.176 Acc@5 96.375
[2025-01-19 13:18:22 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.2%
[2025-01-19 13:18:22 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:18:26 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:18:26 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.18%
[2025-01-19 13:18:28 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][0/312]	eta 0:11:08 lr 0.001349	time 2.1417 (2.1417)	model_time 0.7330 (0.7330)	loss 2.3323 (2.3323)	grad_norm 1.9934 (1.9934/0.0000)	mem 34602MB
[2025-01-19 13:18:29 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][280/312]	eta 0:00:23 lr 0.001351	time 0.7164 (0.7482)	model_time 0.7163 (0.7428)	loss 3.0683 (2.9960)	grad_norm 1.9001 (1.7173/0.7625)	mem 34604MB
[2025-01-19 13:18:36 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][290/312]	eta 0:00:16 lr 0.001351	time 0.7232 (0.7476)	model_time 0.7227 (0.7424)	loss 3.3773 (2.9917)	grad_norm 1.7196 (1.7235/0.7622)	mem 34604MB
[2025-01-19 13:18:36 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][10/312]	eta 0:04:25 lr 0.001349	time 0.7174 (0.8778)	model_time 0.7173 (0.7495)	loss 3.0226 (3.0532)	grad_norm 1.8565 (1.8247/0.5675)	mem 34602MB
[2025-01-19 13:18:43 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][300/312]	eta 0:00:08 lr 0.001350	time 0.7151 (0.7471)	model_time 0.7150 (0.7420)	loss 3.4631 (2.9983)	grad_norm 3.5218 (1.7411/0.7734)	mem 34604MB
[2025-01-19 13:18:44 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][20/312]	eta 0:04:01 lr 0.001348	time 0.8080 (0.8273)	model_time 0.8078 (0.7600)	loss 2.3539 (2.9664)	grad_norm 2.1649 (1.7713/0.5620)	mem 34602MB
[2025-01-19 13:18:50 internimage_b_1k_224] (main.py 510): INFO Train: [182/300][310/312]	eta 0:00:01 lr 0.001349	time 0.7167 (0.7461)	model_time 0.7166 (0.7413)	loss 3.0959 (3.0000)	grad_norm 1.2558 (1.7776/0.7813)	mem 34604MB
[2025-01-19 13:18:51 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][30/312]	eta 0:03:45 lr 0.001347	time 0.7272 (0.7985)	model_time 0.7268 (0.7528)	loss 3.2906 (3.1109)	grad_norm 3.9884 (1.8416/0.6957)	mem 34602MB
[2025-01-19 13:18:51 internimage_b_1k_224] (main.py 519): INFO EPOCH 182 training takes 0:03:52
[2025-01-19 13:18:51 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_182.pth saving......
[2025-01-19 13:18:54 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_182.pth saved !!!
[2025-01-19 13:18:59 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][40/312]	eta 0:03:33 lr 0.001347	time 0.8117 (0.7861)	model_time 0.8115 (0.7514)	loss 2.1224 (2.9981)	grad_norm 1.4386 (1.8833/0.7226)	mem 34602MB
[2025-01-19 13:19:02 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.322 (7.322)	Loss 0.7686 (0.7686)	Acc@1 84.229 (84.229)	Acc@5 97.339 (97.339)	Mem 34604MB
[2025-01-19 13:19:05 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.962)	Loss 1.0258 (0.8835)	Acc@1 77.661 (82.036)	Acc@5 94.800 (96.120)	Mem 34604MB
[2025-01-19 13:19:05 internimage_b_1k_224] (main.py 575): INFO [Epoch:182] * Acc@1 81.834 Acc@5 96.075
[2025-01-19 13:19:05 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.8%
[2025-01-19 13:19:05 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 81.87%
[2025-01-19 13:19:06 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][50/312]	eta 0:03:24 lr 0.001346	time 0.7166 (0.7798)	model_time 0.7164 (0.7518)	loss 3.3342 (3.0392)	grad_norm 2.2014 (1.8728/0.7013)	mem 34602MB
[2025-01-19 13:19:14 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][60/312]	eta 0:03:14 lr 0.001346	time 0.7179 (0.7737)	model_time 0.7174 (0.7503)	loss 3.4250 (3.0536)	grad_norm 3.1522 (1.9539/0.8184)	mem 34602MB
[2025-01-19 13:19:14 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.224 (9.224)	Loss 0.6784 (0.6784)	Acc@1 84.912 (84.912)	Acc@5 97.827 (97.827)	Mem 34604MB
[2025-01-19 13:19:19 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.255)	Loss 0.9499 (0.8003)	Acc@1 78.540 (82.455)	Acc@5 94.873 (96.302)	Mem 34604MB
[2025-01-19 13:19:19 internimage_b_1k_224] (main.py 575): INFO [Epoch:182] * Acc@1 82.306 Acc@5 96.351
[2025-01-19 13:19:19 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.3%
[2025-01-19 13:19:19 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:19:21 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][70/312]	eta 0:03:05 lr 0.001345	time 0.7188 (0.7677)	model_time 0.7186 (0.7476)	loss 3.4469 (3.0540)	grad_norm 2.9814 (1.9807/0.8546)	mem 34602MB
[2025-01-19 13:19:23 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:19:23 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.31%
[2025-01-19 13:19:25 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][0/312]	eta 0:11:01 lr 0.001349	time 2.1198 (2.1198)	model_time 0.7238 (0.7238)	loss 2.7716 (2.7716)	grad_norm 1.9925 (1.9925/0.0000)	mem 34604MB
[2025-01-19 13:19:28 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][80/312]	eta 0:02:57 lr 0.001344	time 0.8065 (0.7646)	model_time 0.8064 (0.7469)	loss 2.7273 (3.0330)	grad_norm 1.0389 (1.9491/0.8256)	mem 34602MB
[2025-01-19 13:19:32 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][10/312]	eta 0:04:26 lr 0.001349	time 0.7175 (0.8825)	model_time 0.7173 (0.7553)	loss 2.1414 (2.8777)	grad_norm 0.8548 (1.6839/0.5690)	mem 34604MB
[2025-01-19 13:19:36 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][90/312]	eta 0:02:49 lr 0.001344	time 0.7292 (0.7627)	model_time 0.7290 (0.7469)	loss 3.3448 (3.0101)	grad_norm 1.2199 (1.8840/0.8105)	mem 34602MB
[2025-01-19 13:19:41 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][20/312]	eta 0:04:09 lr 0.001348	time 0.9701 (0.8536)	model_time 0.9699 (0.7868)	loss 3.5390 (2.9732)	grad_norm 1.5601 (1.8026/0.6459)	mem 34604MB
[2025-01-19 13:19:43 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][100/312]	eta 0:02:41 lr 0.001343	time 0.7220 (0.7615)	model_time 0.7219 (0.7472)	loss 3.3205 (3.0002)	grad_norm 1.4360 (1.8223/0.7972)	mem 34602MB
[2025-01-19 13:19:48 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][30/312]	eta 0:03:52 lr 0.001347	time 0.8168 (0.8239)	model_time 0.8163 (0.7786)	loss 3.3201 (3.0424)	grad_norm 1.8399 (1.7986/0.6215)	mem 34604MB
[2025-01-19 13:19:51 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][110/312]	eta 0:02:33 lr 0.001342	time 0.7245 (0.7609)	model_time 0.7244 (0.7479)	loss 2.1806 (3.0154)	grad_norm 1.5853 (1.8173/0.7709)	mem 34602MB
[2025-01-19 13:19:56 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][40/312]	eta 0:03:39 lr 0.001347	time 0.7168 (0.8054)	model_time 0.7167 (0.7710)	loss 3.2307 (3.0947)	grad_norm 1.5259 (1.7027/0.5891)	mem 34604MB
[2025-01-19 13:19:58 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][120/312]	eta 0:02:25 lr 0.001342	time 0.7206 (0.7594)	model_time 0.7204 (0.7475)	loss 3.0345 (3.0134)	grad_norm 1.6984 (1.8078/0.7579)	mem 34602MB
[2025-01-19 13:20:03 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][50/312]	eta 0:03:27 lr 0.001346	time 0.7363 (0.7923)	model_time 0.7362 (0.7646)	loss 2.4378 (3.1010)	grad_norm 1.3993 (1.6208/0.5926)	mem 34604MB
[2025-01-19 13:20:06 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][130/312]	eta 0:02:18 lr 0.001341	time 0.7185 (0.7592)	model_time 0.7184 (0.7482)	loss 1.9294 (2.9953)	grad_norm 0.9301 (1.7573/0.7518)	mem 34602MB
[2025-01-19 13:20:10 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][60/312]	eta 0:03:17 lr 0.001346	time 0.7310 (0.7819)	model_time 0.7306 (0.7586)	loss 4.0301 (3.0883)	grad_norm 1.0195 (1.7095/0.7630)	mem 34604MB
[2025-01-19 13:20:13 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][140/312]	eta 0:02:10 lr 0.001341	time 0.7923 (0.7594)	model_time 0.7922 (0.7491)	loss 2.4204 (2.9891)	grad_norm 1.0156 (1.7444/0.7433)	mem 34602MB
[2025-01-19 13:20:18 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][70/312]	eta 0:03:07 lr 0.001345	time 0.7170 (0.7738)	model_time 0.7165 (0.7538)	loss 3.5480 (3.0920)	grad_norm 1.3954 (1.7154/0.7617)	mem 34604MB
[2025-01-19 13:20:21 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][150/312]	eta 0:02:02 lr 0.001340	time 0.7190 (0.7577)	model_time 0.7189 (0.7481)	loss 2.6307 (2.9734)	grad_norm 1.5842 (1.7512/0.7445)	mem 34602MB
[2025-01-19 13:20:25 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][80/312]	eta 0:02:58 lr 0.001344	time 0.7267 (0.7688)	model_time 0.7266 (0.7511)	loss 2.5325 (3.0807)	grad_norm 1.5228 (1.7453/0.7350)	mem 34604MB
[2025-01-19 13:20:28 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][160/312]	eta 0:01:54 lr 0.001339	time 0.7468 (0.7563)	model_time 0.7466 (0.7472)	loss 3.5737 (2.9849)	grad_norm 1.4869 (1.7369/0.7338)	mem 34602MB
[2025-01-19 13:20:32 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][90/312]	eta 0:02:49 lr 0.001344	time 0.7213 (0.7643)	model_time 0.7208 (0.7486)	loss 3.1227 (3.0666)	grad_norm 2.1820 (1.7511/0.7475)	mem 34604MB
[2025-01-19 13:20:36 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][170/312]	eta 0:01:47 lr 0.001339	time 0.7199 (0.7565)	model_time 0.7195 (0.7479)	loss 2.7387 (2.9934)	grad_norm 2.9216 (1.7879/0.7635)	mem 34602MB
[2025-01-19 13:20:40 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][100/312]	eta 0:02:41 lr 0.001343	time 0.7296 (0.7611)	model_time 0.7292 (0.7469)	loss 2.3854 (3.0813)	grad_norm 2.4677 (1.7771/0.7329)	mem 34604MB
[2025-01-19 13:20:43 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][180/312]	eta 0:01:39 lr 0.001338	time 0.7386 (0.7559)	model_time 0.7384 (0.7478)	loss 3.2389 (3.0020)	grad_norm 1.1549 (1.8172/0.7734)	mem 34602MB
[2025-01-19 13:20:47 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][110/312]	eta 0:02:33 lr 0.001342	time 0.7196 (0.7577)	model_time 0.7194 (0.7448)	loss 2.9526 (3.0951)	grad_norm 0.9674 (1.7954/0.7419)	mem 34604MB
[2025-01-19 13:20:50 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][190/312]	eta 0:01:32 lr 0.001337	time 0.7250 (0.7546)	model_time 0.7249 (0.7469)	loss 3.5241 (3.0051)	grad_norm 1.0537 (1.8221/0.7786)	mem 34602MB
[2025-01-19 13:20:54 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][120/312]	eta 0:02:24 lr 0.001342	time 0.7253 (0.7552)	model_time 0.7252 (0.7433)	loss 3.0791 (3.0813)	grad_norm 2.0786 (1.7758/0.7247)	mem 34604MB
[2025-01-19 13:20:58 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][200/312]	eta 0:01:24 lr 0.001337	time 0.8043 (0.7535)	model_time 0.8042 (0.7461)	loss 1.9282 (2.9879)	grad_norm 1.5636 (1.7930/0.7727)	mem 34602MB
[2025-01-19 13:21:02 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][130/312]	eta 0:02:17 lr 0.001341	time 0.8152 (0.7566)	model_time 0.8151 (0.7456)	loss 2.9108 (3.0747)	grad_norm 2.3585 (1.7892/0.7116)	mem 34604MB
[2025-01-19 13:21:05 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][210/312]	eta 0:01:16 lr 0.001336	time 0.7169 (0.7525)	model_time 0.7167 (0.7455)	loss 3.3311 (2.9997)	grad_norm 1.2642 (1.7712/0.7642)	mem 34602MB
[2025-01-19 13:21:10 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][140/312]	eta 0:02:10 lr 0.001341	time 0.8339 (0.7590)	model_time 0.8335 (0.7488)	loss 2.4299 (3.0758)	grad_norm 2.0229 (1.7751/0.6991)	mem 34604MB
[2025-01-19 13:21:13 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][220/312]	eta 0:01:09 lr 0.001336	time 0.7161 (0.7526)	model_time 0.7159 (0.7459)	loss 2.1437 (3.0044)	grad_norm 2.2167 (1.7782/0.7642)	mem 34602MB
[2025-01-19 13:21:17 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][150/312]	eta 0:02:02 lr 0.001340	time 0.8513 (0.7587)	model_time 0.8511 (0.7491)	loss 3.3268 (3.0814)	grad_norm 1.1916 (1.7354/0.6938)	mem 34604MB
[2025-01-19 13:21:20 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][230/312]	eta 0:01:01 lr 0.001335	time 0.7285 (0.7525)	model_time 0.7281 (0.7461)	loss 3.0172 (3.0221)	grad_norm 1.1487 (1.7871/0.7708)	mem 34602MB
[2025-01-19 13:21:25 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][160/312]	eta 0:01:55 lr 0.001339	time 0.7182 (0.7588)	model_time 0.7178 (0.7497)	loss 3.4069 (3.0790)	grad_norm 2.7262 (1.7225/0.6916)	mem 34604MB
[2025-01-19 13:21:28 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][240/312]	eta 0:00:54 lr 0.001334	time 0.7204 (0.7525)	model_time 0.7202 (0.7463)	loss 3.8280 (3.0212)	grad_norm 1.3518 (1.7920/0.7644)	mem 34602MB
[2025-01-19 13:21:32 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][170/312]	eta 0:01:47 lr 0.001339	time 0.7245 (0.7567)	model_time 0.7241 (0.7482)	loss 2.9713 (3.0813)	grad_norm 0.8180 (1.7136/0.6824)	mem 34604MB
[2025-01-19 13:21:35 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][250/312]	eta 0:00:46 lr 0.001334	time 0.8228 (0.7524)	model_time 0.8223 (0.7465)	loss 2.4615 (3.0206)	grad_norm 2.0590 (1.7790/0.7573)	mem 34602MB
[2025-01-19 13:21:39 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][180/312]	eta 0:01:39 lr 0.001338	time 0.7221 (0.7553)	model_time 0.7220 (0.7472)	loss 3.2241 (3.0815)	grad_norm 1.1607 (1.6939/0.6734)	mem 34604MB
[2025-01-19 13:21:43 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][260/312]	eta 0:00:39 lr 0.001333	time 0.7599 (0.7525)	model_time 0.7598 (0.7468)	loss 2.2060 (3.0137)	grad_norm 1.2965 (1.7637/0.7493)	mem 34602MB
[2025-01-19 13:21:47 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][190/312]	eta 0:01:32 lr 0.001337	time 0.7312 (0.7542)	model_time 0.7307 (0.7465)	loss 3.3321 (3.0853)	grad_norm 1.9971 (1.6924/0.6616)	mem 34604MB
[2025-01-19 13:21:50 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][270/312]	eta 0:00:31 lr 0.001332	time 0.7173 (0.7522)	model_time 0.7169 (0.7467)	loss 2.8281 (3.0135)	grad_norm 2.5525 (1.7567/0.7417)	mem 34602MB
[2025-01-19 13:21:54 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][200/312]	eta 0:01:24 lr 0.001337	time 0.7659 (0.7535)	model_time 0.7655 (0.7462)	loss 3.4421 (3.0927)	grad_norm 1.5500 (1.6869/0.6529)	mem 34604MB
[2025-01-19 13:21:57 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][280/312]	eta 0:00:24 lr 0.001332	time 0.7315 (0.7515)	model_time 0.7313 (0.7462)	loss 2.4847 (3.0109)	grad_norm 1.4262 (1.7483/0.7336)	mem 34602MB
[2025-01-19 13:22:02 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][210/312]	eta 0:01:16 lr 0.001336	time 0.7354 (0.7524)	model_time 0.7349 (0.7454)	loss 3.3945 (3.0906)	grad_norm 2.9520 (1.7220/0.7163)	mem 34604MB
[2025-01-19 13:22:05 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][290/312]	eta 0:00:16 lr 0.001331	time 0.7193 (0.7514)	model_time 0.7189 (0.7463)	loss 3.2580 (3.0161)	grad_norm 1.2875 (1.7517/0.7289)	mem 34602MB
[2025-01-19 13:22:09 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][220/312]	eta 0:01:09 lr 0.001336	time 0.7175 (0.7515)	model_time 0.7170 (0.7448)	loss 3.3124 (3.0905)	grad_norm 2.7776 (1.7545/0.7399)	mem 34604MB
[2025-01-19 13:22:12 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][300/312]	eta 0:00:09 lr 0.001331	time 0.7111 (0.7510)	model_time 0.7110 (0.7460)	loss 2.2498 (3.0095)	grad_norm 1.0153 (1.7390/0.7235)	mem 34602MB
[2025-01-19 13:22:16 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][230/312]	eta 0:01:01 lr 0.001335	time 0.7293 (0.7504)	model_time 0.7288 (0.7440)	loss 3.2513 (3.0858)	grad_norm 0.9167 (1.7579/0.7371)	mem 34604MB
[2025-01-19 13:22:20 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][310/312]	eta 0:00:01 lr 0.001330	time 0.7156 (0.7498)	model_time 0.7155 (0.7450)	loss 3.1696 (3.0096)	grad_norm 1.9920 (1.7320/0.7191)	mem 34602MB
[2025-01-19 13:22:20 internimage_b_1k_224] (main.py 519): INFO EPOCH 183 training takes 0:03:53
[2025-01-19 13:22:20 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_183.pth saving......
[2025-01-19 13:22:23 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_183.pth saved !!!
[2025-01-19 13:22:23 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][240/312]	eta 0:00:53 lr 0.001334	time 0.7229 (0.7495)	model_time 0.7227 (0.7434)	loss 3.8300 (3.0935)	grad_norm 1.1473 (1.7399/0.7293)	mem 34604MB
[2025-01-19 13:22:31 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][250/312]	eta 0:00:46 lr 0.001334	time 0.8687 (0.7502)	model_time 0.8682 (0.7442)	loss 2.7161 (3.0955)	grad_norm 2.5231 (1.7281/0.7217)	mem 34604MB
[2025-01-19 13:22:31 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.631 (7.631)	Loss 0.7565 (0.7565)	Acc@1 84.521 (84.521)	Acc@5 97.412 (97.412)	Mem 34602MB
[2025-01-19 13:22:34 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.979)	Loss 1.0067 (0.8741)	Acc@1 77.954 (82.047)	Acc@5 94.824 (96.023)	Mem 34602MB
[2025-01-19 13:22:35 internimage_b_1k_224] (main.py 575): INFO [Epoch:183] * Acc@1 81.854 Acc@5 96.057
[2025-01-19 13:22:35 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.9%
[2025-01-19 13:22:35 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.00%
[2025-01-19 13:22:39 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][260/312]	eta 0:00:39 lr 0.001333	time 0.8132 (0.7520)	model_time 0.8130 (0.7463)	loss 3.7070 (3.0931)	grad_norm 2.7818 (1.7419/0.7431)	mem 34604MB
[2025-01-19 13:22:44 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.279 (9.279)	Loss 0.6806 (0.6806)	Acc@1 84.692 (84.692)	Acc@5 97.803 (97.803)	Mem 34602MB
[2025-01-19 13:22:47 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][270/312]	eta 0:00:31 lr 0.001332	time 0.7220 (0.7522)	model_time 0.7219 (0.7467)	loss 2.5796 (3.0824)	grad_norm 2.0693 (1.7714/0.7623)	mem 34604MB
[2025-01-19 13:22:48 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.262)	Loss 0.9497 (0.8018)	Acc@1 78.394 (82.382)	Acc@5 95.020 (96.327)	Mem 34602MB
[2025-01-19 13:22:49 internimage_b_1k_224] (main.py 575): INFO [Epoch:183] * Acc@1 82.226 Acc@5 96.375
[2025-01-19 13:22:49 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.2%
[2025-01-19 13:22:49 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:22:53 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:22:53 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.23%
[2025-01-19 13:22:54 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][280/312]	eta 0:00:24 lr 0.001332	time 0.7283 (0.7532)	model_time 0.7279 (0.7478)	loss 2.6564 (3.0837)	grad_norm 1.2515 (1.7636/0.7575)	mem 34604MB
[2025-01-19 13:22:55 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][0/312]	eta 0:11:25 lr 0.001330	time 2.1979 (2.1979)	model_time 0.7363 (0.7363)	loss 3.4358 (3.4358)	grad_norm 1.6877 (1.6877/0.0000)	mem 34602MB
[2025-01-19 13:23:02 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][290/312]	eta 0:00:16 lr 0.001331	time 0.7347 (0.7522)	model_time 0.7343 (0.7470)	loss 3.8835 (3.0919)	grad_norm 1.4458 (1.7696/0.7578)	mem 34604MB
[2025-01-19 13:23:02 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][10/312]	eta 0:04:23 lr 0.001329	time 0.7174 (0.8709)	model_time 0.7172 (0.7377)	loss 2.9851 (3.1559)	grad_norm 1.3629 (1.7976/0.9729)	mem 34602MB
[2025-01-19 13:23:09 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][300/312]	eta 0:00:09 lr 0.001331	time 0.7125 (0.7514)	model_time 0.7124 (0.7463)	loss 2.8218 (3.0849)	grad_norm 1.4849 (1.7783/0.7612)	mem 34604MB
[2025-01-19 13:23:10 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][20/312]	eta 0:03:55 lr 0.001329	time 0.7472 (0.8060)	model_time 0.7470 (0.7361)	loss 3.0606 (2.9920)	grad_norm 1.6119 (1.7731/0.7397)	mem 34602MB
[2025-01-19 13:23:16 internimage_b_1k_224] (main.py 510): INFO Train: [183/300][310/312]	eta 0:00:01 lr 0.001330	time 0.7141 (0.7503)	model_time 0.7140 (0.7454)	loss 3.1513 (3.0798)	grad_norm 2.0048 (1.7742/0.7581)	mem 34604MB
[2025-01-19 13:23:17 internimage_b_1k_224] (main.py 519): INFO EPOCH 183 training takes 0:03:54
[2025-01-19 13:23:17 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_183.pth saving......
[2025-01-19 13:23:17 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][30/312]	eta 0:03:42 lr 0.001328	time 0.7193 (0.7905)	model_time 0.7191 (0.7430)	loss 2.6616 (3.0126)	grad_norm 1.7313 (1.7200/0.6654)	mem 34602MB
[2025-01-19 13:23:20 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_183.pth saved !!!
[2025-01-19 13:23:25 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][40/312]	eta 0:03:32 lr 0.001327	time 0.7187 (0.7814)	model_time 0.7182 (0.7454)	loss 3.6989 (3.0377)	grad_norm 1.8787 (1.8048/0.7059)	mem 34602MB
[2025-01-19 13:23:28 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.809 (7.809)	Loss 0.7265 (0.7265)	Acc@1 84.521 (84.521)	Acc@5 97.363 (97.363)	Mem 34604MB
[2025-01-19 13:23:31 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.000)	Loss 1.0099 (0.8641)	Acc@1 78.223 (82.131)	Acc@5 94.775 (96.065)	Mem 34604MB
[2025-01-19 13:23:31 internimage_b_1k_224] (main.py 575): INFO [Epoch:183] * Acc@1 82.000 Acc@5 96.107
[2025-01-19 13:23:31 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.0%
[2025-01-19 13:23:31 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 13:23:32 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][50/312]	eta 0:03:23 lr 0.001327	time 0.8245 (0.7751)	model_time 0.8243 (0.7461)	loss 2.9417 (3.0492)	grad_norm 1.0645 (1.7820/0.7550)	mem 34602MB
[2025-01-19 13:23:35 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 13:23:35 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.00%
[2025-01-19 13:23:40 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][60/312]	eta 0:03:14 lr 0.001326	time 0.7217 (0.7701)	model_time 0.7213 (0.7458)	loss 2.0942 (2.9961)	grad_norm 3.0288 (1.7726/0.7516)	mem 34602MB
[2025-01-19 13:23:43 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.750 (7.750)	Loss 0.6794 (0.6794)	Acc@1 84.937 (84.937)	Acc@5 97.827 (97.827)	Mem 34604MB
[2025-01-19 13:23:46 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.001)	Loss 0.9500 (0.8007)	Acc@1 78.662 (82.511)	Acc@5 94.873 (96.309)	Mem 34604MB
[2025-01-19 13:23:46 internimage_b_1k_224] (main.py 575): INFO [Epoch:183] * Acc@1 82.354 Acc@5 96.363
[2025-01-19 13:23:46 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.4%
[2025-01-19 13:23:46 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:23:47 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][70/312]	eta 0:03:05 lr 0.001325	time 0.7208 (0.7683)	model_time 0.7204 (0.7474)	loss 3.7329 (2.9962)	grad_norm 0.8496 (1.7402/0.7541)	mem 34602MB
[2025-01-19 13:23:50 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:23:50 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.35%
[2025-01-19 13:23:52 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][0/312]	eta 0:11:54 lr 0.001330	time 2.2888 (2.2888)	model_time 0.7306 (0.7306)	loss 2.3704 (2.3704)	grad_norm 1.1516 (1.1516/0.0000)	mem 34604MB
[2025-01-19 13:23:55 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][80/312]	eta 0:02:57 lr 0.001325	time 0.7594 (0.7660)	model_time 0.7593 (0.7476)	loss 2.0715 (2.9828)	grad_norm 0.8805 (1.7003/0.7388)	mem 34602MB
[2025-01-19 13:23:59 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][10/312]	eta 0:04:22 lr 0.001329	time 0.7486 (0.8702)	model_time 0.7484 (0.7283)	loss 2.4804 (2.8375)	grad_norm 1.3980 (1.4391/0.2762)	mem 34604MB
[2025-01-19 13:24:02 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][90/312]	eta 0:02:49 lr 0.001324	time 0.7334 (0.7626)	model_time 0.7333 (0.7462)	loss 2.6817 (2.9864)	grad_norm 1.0718 (1.6882/0.7107)	mem 34602MB
[2025-01-19 13:24:06 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][20/312]	eta 0:03:54 lr 0.001329	time 0.7527 (0.8037)	model_time 0.7525 (0.7291)	loss 2.8654 (2.9602)	grad_norm 1.1170 (1.5818/0.4405)	mem 34604MB
[2025-01-19 13:24:10 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][100/312]	eta 0:02:41 lr 0.001324	time 0.8216 (0.7626)	model_time 0.8212 (0.7478)	loss 3.3125 (2.9830)	grad_norm 1.5361 (1.6706/0.6895)	mem 34602MB
[2025-01-19 13:24:14 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][30/312]	eta 0:03:40 lr 0.001328	time 0.7244 (0.7805)	model_time 0.7240 (0.7299)	loss 2.9165 (2.9623)	grad_norm 1.5518 (1.6448/0.4801)	mem 34604MB
[2025-01-19 13:24:17 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][110/312]	eta 0:02:33 lr 0.001323	time 0.7375 (0.7604)	model_time 0.7374 (0.7468)	loss 2.3426 (3.0013)	grad_norm 0.9588 (1.6555/0.6732)	mem 34602MB
[2025-01-19 13:24:21 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][40/312]	eta 0:03:28 lr 0.001327	time 0.7271 (0.7682)	model_time 0.7269 (0.7298)	loss 3.8126 (3.0469)	grad_norm 1.7952 (1.7186/0.5869)	mem 34604MB
[2025-01-19 13:24:25 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][120/312]	eta 0:02:25 lr 0.001322	time 0.7165 (0.7574)	model_time 0.7161 (0.7450)	loss 3.1572 (2.9979)	grad_norm 1.0911 (1.6634/0.6674)	mem 34602MB
[2025-01-19 13:24:28 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][50/312]	eta 0:03:19 lr 0.001327	time 0.7253 (0.7622)	model_time 0.7248 (0.7312)	loss 3.0835 (3.0148)	grad_norm 2.3745 (1.7569/0.5604)	mem 34604MB
[2025-01-19 13:24:32 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][130/312]	eta 0:02:17 lr 0.001322	time 0.7143 (0.7557)	model_time 0.7142 (0.7442)	loss 3.4703 (3.0035)	grad_norm 3.9997 (1.7068/0.6959)	mem 34602MB
[2025-01-19 13:24:36 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][60/312]	eta 0:03:11 lr 0.001326	time 0.8017 (0.7614)	model_time 0.8016 (0.7355)	loss 3.3365 (3.0575)	grad_norm 1.2612 (1.7275/0.5485)	mem 34604MB
[2025-01-19 13:24:39 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][140/312]	eta 0:02:09 lr 0.001321	time 0.7197 (0.7552)	model_time 0.7195 (0.7445)	loss 2.1022 (2.9915)	grad_norm 1.3254 (1.7085/0.6875)	mem 34602MB
[2025-01-19 13:24:44 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][70/312]	eta 0:03:05 lr 0.001325	time 0.8140 (0.7669)	model_time 0.8139 (0.7446)	loss 2.7844 (3.0183)	grad_norm 1.0336 (1.7059/0.5555)	mem 34604MB
[2025-01-19 13:24:47 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][150/312]	eta 0:02:02 lr 0.001320	time 0.7247 (0.7554)	model_time 0.7246 (0.7454)	loss 2.3622 (2.9976)	grad_norm 0.9796 (1.7030/0.6864)	mem 34602MB
[2025-01-19 13:24:52 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][80/312]	eta 0:02:58 lr 0.001325	time 0.7234 (0.7680)	model_time 0.7230 (0.7484)	loss 2.6715 (3.0429)	grad_norm 1.1139 (1.7088/0.5638)	mem 34604MB
[2025-01-19 13:24:54 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][160/312]	eta 0:01:54 lr 0.001320	time 0.7903 (0.7550)	model_time 0.7899 (0.7456)	loss 3.0200 (3.0016)	grad_norm 1.8920 (1.7168/0.7015)	mem 34602MB
[2025-01-19 13:24:59 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][90/312]	eta 0:02:50 lr 0.001324	time 0.7988 (0.7668)	model_time 0.7987 (0.7493)	loss 3.3139 (3.0500)	grad_norm 2.3995 (1.6648/0.5650)	mem 34604MB
[2025-01-19 13:25:02 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][170/312]	eta 0:01:47 lr 0.001319	time 0.8055 (0.7544)	model_time 0.8051 (0.7455)	loss 3.3203 (3.0048)	grad_norm 0.9488 (1.7345/0.7129)	mem 34602MB
[2025-01-19 13:25:07 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][100/312]	eta 0:02:41 lr 0.001324	time 0.7192 (0.7634)	model_time 0.7188 (0.7476)	loss 3.6630 (3.0453)	grad_norm 0.8652 (1.6309/0.5581)	mem 34604MB
[2025-01-19 13:25:09 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][180/312]	eta 0:01:39 lr 0.001319	time 0.7276 (0.7538)	model_time 0.7275 (0.7454)	loss 3.4010 (3.0268)	grad_norm 2.5292 (1.7375/0.7017)	mem 34602MB
[2025-01-19 13:25:14 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][110/312]	eta 0:02:33 lr 0.001323	time 0.7413 (0.7600)	model_time 0.7409 (0.7456)	loss 3.7425 (3.0553)	grad_norm 2.0375 (1.6703/0.6190)	mem 34604MB
[2025-01-19 13:25:17 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][190/312]	eta 0:01:32 lr 0.001318	time 0.8141 (0.7544)	model_time 0.8139 (0.7464)	loss 3.7793 (3.0315)	grad_norm 1.1947 (1.7583/0.7373)	mem 34602MB
[2025-01-19 13:25:21 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][120/312]	eta 0:02:25 lr 0.001322	time 0.7149 (0.7578)	model_time 0.7148 (0.7445)	loss 3.8567 (3.0637)	grad_norm 1.6231 (1.6584/0.5994)	mem 34604MB
[2025-01-19 13:25:24 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][200/312]	eta 0:01:24 lr 0.001317	time 0.7252 (0.7532)	model_time 0.7248 (0.7456)	loss 2.9029 (3.0406)	grad_norm 1.2619 (1.7312/0.7325)	mem 34602MB
[2025-01-19 13:25:29 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][130/312]	eta 0:02:17 lr 0.001322	time 0.7500 (0.7556)	model_time 0.7499 (0.7434)	loss 3.3971 (3.0871)	grad_norm 1.8620 (1.6348/0.5905)	mem 34604MB
[2025-01-19 13:25:32 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][210/312]	eta 0:01:16 lr 0.001317	time 0.7213 (0.7527)	model_time 0.7211 (0.7454)	loss 3.6400 (3.0499)	grad_norm 3.0390 (1.7278/0.7415)	mem 34602MB
[2025-01-19 13:25:36 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][140/312]	eta 0:02:09 lr 0.001321	time 0.7191 (0.7536)	model_time 0.7186 (0.7422)	loss 2.8711 (3.0728)	grad_norm 1.9904 (1.6502/0.5847)	mem 34604MB
[2025-01-19 13:25:39 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][220/312]	eta 0:01:09 lr 0.001316	time 0.8060 (0.7531)	model_time 0.8059 (0.7461)	loss 3.1185 (3.0518)	grad_norm 1.1095 (1.7172/0.7301)	mem 34602MB
[2025-01-19 13:25:43 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][150/312]	eta 0:02:01 lr 0.001320	time 0.7361 (0.7523)	model_time 0.7359 (0.7416)	loss 3.8874 (3.0792)	grad_norm 1.8874 (1.6524/0.5787)	mem 34604MB
[2025-01-19 13:25:47 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][230/312]	eta 0:01:01 lr 0.001316	time 0.7180 (0.7523)	model_time 0.7179 (0.7456)	loss 2.3775 (3.0585)	grad_norm 3.0685 (1.7242/0.7231)	mem 34602MB
[2025-01-19 13:25:50 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][160/312]	eta 0:01:54 lr 0.001320	time 0.7210 (0.7509)	model_time 0.7205 (0.7408)	loss 2.7465 (3.0727)	grad_norm 2.1022 (1.7303/0.7148)	mem 34604MB
[2025-01-19 13:25:54 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][240/312]	eta 0:00:54 lr 0.001315	time 0.7333 (0.7511)	model_time 0.7329 (0.7447)	loss 2.3793 (3.0534)	grad_norm 1.6057 (1.7353/0.7251)	mem 34602MB
[2025-01-19 13:25:58 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][170/312]	eta 0:01:46 lr 0.001319	time 0.7192 (0.7500)	model_time 0.7190 (0.7406)	loss 3.2123 (3.0765)	grad_norm 1.6668 (1.7214/0.7073)	mem 34604MB
[2025-01-19 13:26:01 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][250/312]	eta 0:00:46 lr 0.001314	time 0.7179 (0.7506)	model_time 0.7178 (0.7444)	loss 3.4933 (3.0503)	grad_norm 2.7867 (1.7345/0.7179)	mem 34602MB
[2025-01-19 13:26:05 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][180/312]	eta 0:01:39 lr 0.001319	time 0.8083 (0.7504)	model_time 0.8079 (0.7414)	loss 3.1880 (3.0759)	grad_norm 1.5102 (1.7221/0.6995)	mem 34604MB
[2025-01-19 13:26:09 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][260/312]	eta 0:00:39 lr 0.001314	time 0.7452 (0.7505)	model_time 0.7448 (0.7446)	loss 3.2682 (3.0515)	grad_norm 1.0029 (1.7287/0.7170)	mem 34602MB
[2025-01-19 13:26:13 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][190/312]	eta 0:01:31 lr 0.001318	time 0.8154 (0.7521)	model_time 0.8152 (0.7436)	loss 2.5371 (3.0657)	grad_norm 1.6661 (1.7517/0.7468)	mem 34604MB
[2025-01-19 13:26:17 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][270/312]	eta 0:00:31 lr 0.001313	time 0.8088 (0.7514)	model_time 0.8084 (0.7456)	loss 3.5752 (3.0530)	grad_norm 4.8040 (1.7577/0.7631)	mem 34602MB
[2025-01-19 13:26:21 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][200/312]	eta 0:01:24 lr 0.001317	time 0.7233 (0.7534)	model_time 0.7232 (0.7453)	loss 3.4969 (3.0595)	grad_norm 0.8703 (1.7694/0.7589)	mem 34604MB
[2025-01-19 13:26:24 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][280/312]	eta 0:00:24 lr 0.001312	time 0.7965 (0.7515)	model_time 0.7963 (0.7459)	loss 3.2538 (3.0605)	grad_norm 3.2163 (1.7967/0.8161)	mem 34602MB
[2025-01-19 13:26:29 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][210/312]	eta 0:01:16 lr 0.001317	time 0.7998 (0.7536)	model_time 0.7994 (0.7458)	loss 2.4471 (3.0455)	grad_norm 1.4285 (1.7533/0.7474)	mem 34604MB
[2025-01-19 13:26:32 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][290/312]	eta 0:00:16 lr 0.001312	time 0.8074 (0.7513)	model_time 0.8072 (0.7459)	loss 3.5044 (3.0639)	grad_norm 1.4322 (1.8047/0.8123)	mem 34602MB
[2025-01-19 13:26:36 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][220/312]	eta 0:01:09 lr 0.001316	time 0.7161 (0.7530)	model_time 0.7156 (0.7455)	loss 1.9887 (3.0545)	grad_norm 1.0525 (1.7355/0.7383)	mem 34604MB
[2025-01-19 13:26:39 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][300/312]	eta 0:00:09 lr 0.001311	time 0.7152 (0.7511)	model_time 0.7151 (0.7458)	loss 3.0102 (3.0608)	grad_norm 1.9314 (1.8005/0.8044)	mem 34602MB
[2025-01-19 13:26:43 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][230/312]	eta 0:01:01 lr 0.001316	time 0.7211 (0.7520)	model_time 0.7209 (0.7449)	loss 3.7811 (3.0744)	grad_norm 1.1340 (1.7199/0.7301)	mem 34604MB
[2025-01-19 13:26:47 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][310/312]	eta 0:00:01 lr 0.001311	time 0.7955 (0.7511)	model_time 0.7953 (0.7460)	loss 3.2094 (3.0536)	grad_norm 1.1657 (1.7891/0.7876)	mem 34602MB
[2025-01-19 13:26:47 internimage_b_1k_224] (main.py 519): INFO EPOCH 184 training takes 0:03:54
[2025-01-19 13:26:47 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_184.pth saving......
[2025-01-19 13:26:50 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_184.pth saved !!!
[2025-01-19 13:26:51 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][240/312]	eta 0:00:54 lr 0.001315	time 0.7261 (0.7512)	model_time 0.7257 (0.7444)	loss 3.7054 (3.0769)	grad_norm 1.5147 (1.7280/0.7301)	mem 34604MB
[2025-01-19 13:26:58 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][250/312]	eta 0:00:46 lr 0.001314	time 0.7313 (0.7506)	model_time 0.7309 (0.7440)	loss 3.9362 (3.0769)	grad_norm 1.0417 (1.7138/0.7220)	mem 34604MB
[2025-01-19 13:26:58 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.404 (7.404)	Loss 0.7744 (0.7744)	Acc@1 84.717 (84.717)	Acc@5 97.461 (97.461)	Mem 34602MB
[2025-01-19 13:27:01 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.968)	Loss 0.9905 (0.8732)	Acc@1 78.540 (82.076)	Acc@5 95.435 (96.265)	Mem 34602MB
[2025-01-19 13:27:02 internimage_b_1k_224] (main.py 575): INFO [Epoch:184] * Acc@1 82.028 Acc@5 96.305
[2025-01-19 13:27:02 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.0%
[2025-01-19 13:27:02 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 13:27:05 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 13:27:05 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.03%
[2025-01-19 13:27:05 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][260/312]	eta 0:00:38 lr 0.001314	time 0.7220 (0.7498)	model_time 0.7218 (0.7434)	loss 2.9215 (3.0845)	grad_norm 2.2189 (1.7283/0.7309)	mem 34604MB
[2025-01-19 13:27:12 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.429 (7.429)	Loss 0.6816 (0.6816)	Acc@1 84.717 (84.717)	Acc@5 97.827 (97.827)	Mem 34602MB
[2025-01-19 13:27:13 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][270/312]	eta 0:00:31 lr 0.001313	time 0.7195 (0.7491)	model_time 0.7191 (0.7429)	loss 3.5625 (3.0825)	grad_norm 3.0518 (1.7303/0.7270)	mem 34604MB
[2025-01-19 13:27:15 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.948)	Loss 0.9497 (0.8023)	Acc@1 78.394 (82.420)	Acc@5 95.020 (96.336)	Mem 34602MB
[2025-01-19 13:27:15 internimage_b_1k_224] (main.py 575): INFO [Epoch:184] * Acc@1 82.258 Acc@5 96.385
[2025-01-19 13:27:15 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.3%
[2025-01-19 13:27:15 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:27:19 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:27:19 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.26%
[2025-01-19 13:27:20 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][280/312]	eta 0:00:23 lr 0.001312	time 0.7340 (0.7484)	model_time 0.7338 (0.7425)	loss 2.1470 (3.0718)	grad_norm 1.6110 (1.7282/0.7188)	mem 34604MB
[2025-01-19 13:27:22 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][0/312]	eta 0:11:25 lr 0.001310	time 2.1977 (2.1977)	model_time 0.7457 (0.7457)	loss 2.4403 (2.4403)	grad_norm 1.4189 (1.4189/0.0000)	mem 34602MB
[2025-01-19 13:27:27 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][290/312]	eta 0:00:16 lr 0.001312	time 0.7182 (0.7482)	model_time 0.7180 (0.7424)	loss 3.3742 (3.0676)	grad_norm 2.2231 (1.7405/0.7313)	mem 34604MB
[2025-01-19 13:27:29 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][10/312]	eta 0:04:23 lr 0.001310	time 0.7496 (0.8726)	model_time 0.7492 (0.7402)	loss 2.9210 (3.0968)	grad_norm 1.6252 (1.4485/0.4996)	mem 34602MB
[2025-01-19 13:27:35 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][300/312]	eta 0:00:08 lr 0.001311	time 0.7975 (0.7483)	model_time 0.7974 (0.7428)	loss 2.9680 (3.0736)	grad_norm 1.6594 (1.7511/0.7359)	mem 34604MB
[2025-01-19 13:27:37 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][20/312]	eta 0:03:56 lr 0.001309	time 0.7470 (0.8116)	model_time 0.7469 (0.7421)	loss 3.4591 (2.9982)	grad_norm 1.0896 (1.6271/0.7115)	mem 34602MB
[2025-01-19 13:27:42 internimage_b_1k_224] (main.py 510): INFO Train: [184/300][310/312]	eta 0:00:01 lr 0.001311	time 0.7142 (0.7488)	model_time 0.7141 (0.7434)	loss 3.5009 (3.0786)	grad_norm 2.0282 (1.7707/0.7447)	mem 34604MB
[2025-01-19 13:27:43 internimage_b_1k_224] (main.py 519): INFO EPOCH 184 training takes 0:03:53
[2025-01-19 13:27:43 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_184.pth saving......
[2025-01-19 13:27:44 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][30/312]	eta 0:03:43 lr 0.001309	time 0.7151 (0.7925)	model_time 0.7149 (0.7453)	loss 3.0072 (3.0422)	grad_norm 1.2544 (1.6006/0.6804)	mem 34602MB
[2025-01-19 13:27:47 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_184.pth saved !!!
[2025-01-19 13:27:51 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][40/312]	eta 0:03:31 lr 0.001308	time 0.7248 (0.7789)	model_time 0.7244 (0.7431)	loss 3.1669 (3.0266)	grad_norm 1.4778 (1.5863/0.6493)	mem 34602MB
[2025-01-19 13:27:54 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.333 (7.333)	Loss 0.7542 (0.7542)	Acc@1 84.888 (84.888)	Acc@5 97.290 (97.290)	Mem 34604MB
[2025-01-19 13:27:57 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.941)	Loss 1.0070 (0.8644)	Acc@1 77.930 (82.067)	Acc@5 95.020 (96.218)	Mem 34604MB
[2025-01-19 13:27:57 internimage_b_1k_224] (main.py 575): INFO [Epoch:184] * Acc@1 81.922 Acc@5 96.219
[2025-01-19 13:27:57 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.9%
[2025-01-19 13:27:57 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.00%
[2025-01-19 13:27:59 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][50/312]	eta 0:03:21 lr 0.001307	time 0.7237 (0.7684)	model_time 0.7235 (0.7396)	loss 2.7224 (3.0593)	grad_norm 1.5904 (1.5215/0.6217)	mem 34602MB
[2025-01-19 13:28:06 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][60/312]	eta 0:03:11 lr 0.001307	time 0.7187 (0.7619)	model_time 0.7183 (0.7377)	loss 2.1435 (3.0664)	grad_norm 1.0404 (1.5713/0.6671)	mem 34602MB
[2025-01-19 13:28:06 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.178 (9.178)	Loss 0.6802 (0.6802)	Acc@1 84.937 (84.937)	Acc@5 97.900 (97.900)	Mem 34604MB
[2025-01-19 13:28:11 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.184 (1.250)	Loss 0.9502 (0.8011)	Acc@1 78.687 (82.551)	Acc@5 94.873 (96.327)	Mem 34604MB
[2025-01-19 13:28:11 internimage_b_1k_224] (main.py 575): INFO [Epoch:184] * Acc@1 82.392 Acc@5 96.387
[2025-01-19 13:28:11 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.4%
[2025-01-19 13:28:11 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:28:13 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][70/312]	eta 0:03:04 lr 0.001306	time 0.7218 (0.7604)	model_time 0.7216 (0.7396)	loss 3.2573 (3.0807)	grad_norm 1.9009 (1.5298/0.6429)	mem 34602MB
[2025-01-19 13:28:15 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:28:15 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.39%
[2025-01-19 13:28:17 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][0/312]	eta 0:11:26 lr 0.001310	time 2.1993 (2.1993)	model_time 0.7292 (0.7292)	loss 3.7539 (3.7539)	grad_norm 2.4410 (2.4410/0.0000)	mem 34604MB
[2025-01-19 13:28:21 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][80/312]	eta 0:02:56 lr 0.001305	time 0.7184 (0.7607)	model_time 0.7182 (0.7424)	loss 3.2977 (3.0964)	grad_norm 1.9058 (1.5454/0.6277)	mem 34602MB
[2025-01-19 13:28:25 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][10/312]	eta 0:04:37 lr 0.001310	time 0.7200 (0.9182)	model_time 0.7196 (0.7842)	loss 3.1139 (3.0070)	grad_norm 2.2181 (1.9485/0.7706)	mem 34604MB
[2025-01-19 13:28:29 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][90/312]	eta 0:02:48 lr 0.001305	time 0.8217 (0.7597)	model_time 0.8216 (0.7434)	loss 3.1446 (3.0738)	grad_norm 1.4761 (1.5579/0.6148)	mem 34602MB
[2025-01-19 13:28:32 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][20/312]	eta 0:04:05 lr 0.001309	time 0.8001 (0.8403)	model_time 0.7999 (0.7699)	loss 3.7141 (3.0227)	grad_norm 2.8626 (1.7105/0.7126)	mem 34604MB
[2025-01-19 13:28:36 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][100/312]	eta 0:02:40 lr 0.001304	time 0.7360 (0.7576)	model_time 0.7355 (0.7428)	loss 3.4469 (3.0609)	grad_norm 1.3985 (1.5936/0.6399)	mem 34602MB
[2025-01-19 13:28:40 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][30/312]	eta 0:03:47 lr 0.001309	time 0.7914 (0.8071)	model_time 0.7912 (0.7593)	loss 3.0515 (2.9786)	grad_norm 1.5746 (1.6027/0.6273)	mem 34604MB
[2025-01-19 13:28:44 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][110/312]	eta 0:02:33 lr 0.001304	time 0.7972 (0.7580)	model_time 0.7970 (0.7446)	loss 3.1490 (3.0410)	grad_norm 1.4083 (1.6360/0.6877)	mem 34602MB
[2025-01-19 13:28:47 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][40/312]	eta 0:03:34 lr 0.001308	time 0.7169 (0.7876)	model_time 0.7168 (0.7514)	loss 3.2670 (3.0107)	grad_norm 1.8813 (1.6559/0.7476)	mem 34604MB
[2025-01-19 13:28:51 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][120/312]	eta 0:02:25 lr 0.001303	time 0.7229 (0.7576)	model_time 0.7228 (0.7453)	loss 3.7560 (3.0345)	grad_norm 1.1352 (1.6525/0.6907)	mem 34602MB
[2025-01-19 13:28:54 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][50/312]	eta 0:03:23 lr 0.001307	time 0.7168 (0.7767)	model_time 0.7164 (0.7475)	loss 2.9737 (3.0825)	grad_norm 2.5035 (1.7083/0.8368)	mem 34604MB
[2025-01-19 13:28:59 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][130/312]	eta 0:02:17 lr 0.001302	time 0.8145 (0.7578)	model_time 0.8141 (0.7463)	loss 3.1666 (3.0455)	grad_norm 1.3084 (1.6811/0.7155)	mem 34602MB
[2025-01-19 13:29:02 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][60/312]	eta 0:03:13 lr 0.001307	time 0.7149 (0.7690)	model_time 0.7145 (0.7446)	loss 3.3610 (3.0518)	grad_norm 2.5211 (1.7820/0.8049)	mem 34604MB
[2025-01-19 13:29:06 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][140/312]	eta 0:02:10 lr 0.001302	time 0.7726 (0.7565)	model_time 0.7724 (0.7458)	loss 3.2147 (3.0340)	grad_norm 1.2909 (1.6967/0.7174)	mem 34602MB
[2025-01-19 13:29:09 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][70/312]	eta 0:03:04 lr 0.001306	time 0.7306 (0.7635)	model_time 0.7301 (0.7424)	loss 3.7544 (3.0453)	grad_norm 2.1782 (1.7606/0.7797)	mem 34604MB
[2025-01-19 13:29:14 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][150/312]	eta 0:02:02 lr 0.001301	time 0.8147 (0.7562)	model_time 0.8143 (0.7462)	loss 3.4426 (3.0184)	grad_norm 0.7872 (1.6944/0.7272)	mem 34602MB
[2025-01-19 13:29:16 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][80/312]	eta 0:02:56 lr 0.001305	time 0.7120 (0.7594)	model_time 0.7119 (0.7409)	loss 3.1437 (3.0648)	grad_norm 1.2872 (1.7508/0.7528)	mem 34604MB
[2025-01-19 13:29:21 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][160/312]	eta 0:01:54 lr 0.001301	time 0.8060 (0.7553)	model_time 0.8058 (0.7459)	loss 3.1866 (3.0014)	grad_norm 1.6731 (1.6892/0.7195)	mem 34602MB
[2025-01-19 13:29:24 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][90/312]	eta 0:02:47 lr 0.001305	time 0.7210 (0.7565)	model_time 0.7208 (0.7400)	loss 2.9331 (3.0325)	grad_norm 1.3558 (1.6968/0.7335)	mem 34604MB
[2025-01-19 13:29:28 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][170/312]	eta 0:01:47 lr 0.001300	time 0.7676 (0.7539)	model_time 0.7674 (0.7450)	loss 2.5342 (3.0105)	grad_norm 1.0289 (1.7112/0.7323)	mem 34602MB
[2025-01-19 13:29:31 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][100/312]	eta 0:02:39 lr 0.001304	time 0.7172 (0.7540)	model_time 0.7168 (0.7391)	loss 2.9120 (3.0309)	grad_norm 4.3084 (1.7157/0.7680)	mem 34604MB
[2025-01-19 13:29:36 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][180/312]	eta 0:01:39 lr 0.001299	time 0.7223 (0.7521)	model_time 0.7222 (0.7438)	loss 1.9822 (3.0062)	grad_norm 1.5048 (1.6848/0.7222)	mem 34602MB
[2025-01-19 13:29:38 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][110/312]	eta 0:02:32 lr 0.001304	time 0.7086 (0.7534)	model_time 0.7084 (0.7398)	loss 3.3613 (3.0616)	grad_norm 1.7106 (1.7244/0.7630)	mem 34604MB
[2025-01-19 13:29:43 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][190/312]	eta 0:01:31 lr 0.001299	time 0.7211 (0.7525)	model_time 0.7207 (0.7445)	loss 3.1783 (3.0008)	grad_norm 1.0754 (1.6557/0.7161)	mem 34602MB
[2025-01-19 13:29:46 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][120/312]	eta 0:02:24 lr 0.001303	time 0.7199 (0.7547)	model_time 0.7194 (0.7422)	loss 3.3622 (3.0678)	grad_norm 1.4711 (1.7309/0.7603)	mem 34604MB
[2025-01-19 13:29:51 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][200/312]	eta 0:01:24 lr 0.001298	time 0.8050 (0.7527)	model_time 0.8049 (0.7451)	loss 3.0043 (2.9994)	grad_norm 2.6493 (1.6857/0.7417)	mem 34602MB
[2025-01-19 13:29:54 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][130/312]	eta 0:02:17 lr 0.001302	time 0.7147 (0.7582)	model_time 0.7145 (0.7466)	loss 2.7950 (3.0686)	grad_norm 1.6009 (1.7781/0.7738)	mem 34604MB
[2025-01-19 13:29:58 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][210/312]	eta 0:01:16 lr 0.001297	time 0.8129 (0.7529)	model_time 0.8128 (0.7457)	loss 1.9417 (2.9913)	grad_norm 1.8400 (1.6964/0.7311)	mem 34602MB
[2025-01-19 13:30:02 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][140/312]	eta 0:02:10 lr 0.001302	time 0.7239 (0.7581)	model_time 0.7237 (0.7473)	loss 2.8743 (3.0449)	grad_norm 2.6402 (1.7856/0.7744)	mem 34604MB
[2025-01-19 13:30:06 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][220/312]	eta 0:01:09 lr 0.001297	time 0.7178 (0.7522)	model_time 0.7174 (0.7453)	loss 1.8958 (2.9921)	grad_norm 0.9091 (1.6881/0.7234)	mem 34602MB
[2025-01-19 13:30:09 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][150/312]	eta 0:02:02 lr 0.001301	time 0.8053 (0.7568)	model_time 0.8048 (0.7467)	loss 2.9733 (3.0448)	grad_norm 1.9624 (1.7439/0.7702)	mem 34604MB
[2025-01-19 13:30:13 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][230/312]	eta 0:01:01 lr 0.001296	time 0.8105 (0.7527)	model_time 0.8100 (0.7460)	loss 2.6962 (3.0031)	grad_norm 3.3271 (1.6835/0.7231)	mem 34602MB
[2025-01-19 13:30:16 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][160/312]	eta 0:01:54 lr 0.001301	time 0.7263 (0.7553)	model_time 0.7262 (0.7458)	loss 3.2827 (3.0453)	grad_norm 1.4178 (1.7380/0.7665)	mem 34604MB
[2025-01-19 13:30:21 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][240/312]	eta 0:00:54 lr 0.001296	time 0.7221 (0.7526)	model_time 0.7219 (0.7462)	loss 3.2618 (3.0067)	grad_norm 1.1517 (1.6816/0.7217)	mem 34602MB
[2025-01-19 13:30:24 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][170/312]	eta 0:01:47 lr 0.001300	time 0.7235 (0.7538)	model_time 0.7233 (0.7448)	loss 2.5669 (3.0290)	grad_norm 2.8621 (1.7545/0.7771)	mem 34604MB
[2025-01-19 13:30:28 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][250/312]	eta 0:00:46 lr 0.001295	time 0.7289 (0.7527)	model_time 0.7288 (0.7466)	loss 2.0812 (3.0086)	grad_norm 2.1377 (1.6765/0.7159)	mem 34602MB
[2025-01-19 13:30:31 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][180/312]	eta 0:01:39 lr 0.001299	time 0.7247 (0.7521)	model_time 0.7243 (0.7436)	loss 2.1125 (3.0237)	grad_norm 1.7834 (1.7829/0.7813)	mem 34604MB
[2025-01-19 13:30:36 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][260/312]	eta 0:00:39 lr 0.001294	time 0.7572 (0.7526)	model_time 0.7570 (0.7467)	loss 3.0421 (3.0065)	grad_norm 1.9360 (1.7035/0.7383)	mem 34602MB
[2025-01-19 13:30:38 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][190/312]	eta 0:01:31 lr 0.001299	time 0.7393 (0.7510)	model_time 0.7389 (0.7430)	loss 2.1912 (3.0317)	grad_norm 1.9485 (1.7681/0.7698)	mem 34604MB
[2025-01-19 13:30:43 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][270/312]	eta 0:00:31 lr 0.001294	time 0.8050 (0.7526)	model_time 0.8044 (0.7469)	loss 3.1915 (3.0047)	grad_norm 1.8762 (1.7015/0.7289)	mem 34602MB
[2025-01-19 13:30:46 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][200/312]	eta 0:01:23 lr 0.001298	time 0.7180 (0.7499)	model_time 0.7178 (0.7422)	loss 2.0177 (3.0196)	grad_norm 1.4031 (1.7619/0.7595)	mem 34604MB
[2025-01-19 13:30:51 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][280/312]	eta 0:00:24 lr 0.001293	time 0.7173 (0.7521)	model_time 0.7172 (0.7466)	loss 3.5675 (3.0011)	grad_norm 0.8456 (1.6957/0.7250)	mem 34602MB
[2025-01-19 13:30:53 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][210/312]	eta 0:01:16 lr 0.001297	time 0.7754 (0.7492)	model_time 0.7753 (0.7418)	loss 3.4925 (3.0079)	grad_norm 2.0422 (1.7620/0.7469)	mem 34604MB
[2025-01-19 13:30:58 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][290/312]	eta 0:00:16 lr 0.001292	time 0.7255 (0.7515)	model_time 0.7253 (0.7462)	loss 2.7831 (3.0033)	grad_norm 1.2294 (1.6841/0.7172)	mem 34602MB
[2025-01-19 13:31:00 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][220/312]	eta 0:01:08 lr 0.001297	time 0.7665 (0.7484)	model_time 0.7663 (0.7414)	loss 3.2301 (3.0104)	grad_norm 1.8154 (1.7686/0.7342)	mem 34604MB
[2025-01-19 13:31:05 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][300/312]	eta 0:00:09 lr 0.001292	time 0.7073 (0.7506)	model_time 0.7072 (0.7454)	loss 2.9379 (3.0050)	grad_norm 2.0561 (1.6891/0.7096)	mem 34602MB
[2025-01-19 13:31:08 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][230/312]	eta 0:01:01 lr 0.001296	time 0.7228 (0.7482)	model_time 0.7227 (0.7415)	loss 3.6947 (3.0074)	grad_norm 2.7842 (1.7695/0.7245)	mem 34604MB
[2025-01-19 13:31:13 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][310/312]	eta 0:00:01 lr 0.001291	time 0.7860 (0.7505)	model_time 0.7859 (0.7455)	loss 3.3755 (3.0062)	grad_norm 2.4319 (1.7245/0.7426)	mem 34602MB
[2025-01-19 13:31:14 internimage_b_1k_224] (main.py 519): INFO EPOCH 185 training takes 0:03:54
[2025-01-19 13:31:14 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_185.pth saving......
[2025-01-19 13:31:15 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][240/312]	eta 0:00:53 lr 0.001296	time 0.7203 (0.7487)	model_time 0.7201 (0.7422)	loss 3.4771 (3.0096)	grad_norm 1.5075 (1.7729/0.7241)	mem 34604MB
[2025-01-19 13:31:17 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_185.pth saved !!!
[2025-01-19 13:31:23 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][250/312]	eta 0:00:46 lr 0.001295	time 0.7103 (0.7508)	model_time 0.7101 (0.7446)	loss 3.5105 (3.0130)	grad_norm 1.2854 (1.7713/0.7233)	mem 34604MB
[2025-01-19 13:31:24 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.447 (7.447)	Loss 0.7459 (0.7459)	Acc@1 84.937 (84.937)	Acc@5 97.266 (97.266)	Mem 34602MB
[2025-01-19 13:31:27 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.944)	Loss 1.0053 (0.8724)	Acc@1 78.223 (82.180)	Acc@5 95.044 (96.171)	Mem 34602MB
[2025-01-19 13:31:28 internimage_b_1k_224] (main.py 575): INFO [Epoch:185] * Acc@1 82.026 Acc@5 96.217
[2025-01-19 13:31:28 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.0%
[2025-01-19 13:31:28 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.03%
[2025-01-19 13:31:31 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][260/312]	eta 0:00:39 lr 0.001294	time 0.7531 (0.7514)	model_time 0.7527 (0.7454)	loss 3.2484 (3.0113)	grad_norm 0.8882 (1.7577/0.7159)	mem 34604MB
[2025-01-19 13:31:37 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.221 (9.221)	Loss 0.6826 (0.6826)	Acc@1 84.790 (84.790)	Acc@5 97.852 (97.852)	Mem 34602MB
[2025-01-19 13:31:38 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][270/312]	eta 0:00:31 lr 0.001294	time 0.8047 (0.7514)	model_time 0.8042 (0.7456)	loss 3.2933 (3.0244)	grad_norm 2.8243 (1.7606/0.7201)	mem 34604MB
[2025-01-19 13:31:42 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.264)	Loss 0.9494 (0.8028)	Acc@1 78.516 (82.506)	Acc@5 94.995 (96.345)	Mem 34602MB
[2025-01-19 13:31:42 internimage_b_1k_224] (main.py 575): INFO [Epoch:185] * Acc@1 82.344 Acc@5 96.397
[2025-01-19 13:31:42 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.3%
[2025-01-19 13:31:42 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:31:46 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:31:46 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.34%
[2025-01-19 13:31:46 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][280/312]	eta 0:00:24 lr 0.001293	time 0.7269 (0.7508)	model_time 0.7265 (0.7452)	loss 2.4712 (3.0286)	grad_norm 1.6230 (1.7783/0.7288)	mem 34604MB
[2025-01-19 13:31:48 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][0/312]	eta 0:10:46 lr 0.001291	time 2.0710 (2.0710)	model_time 0.7562 (0.7562)	loss 3.4821 (3.4821)	grad_norm 1.0359 (1.0359/0.0000)	mem 34602MB
[2025-01-19 13:31:53 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][290/312]	eta 0:00:16 lr 0.001292	time 0.7335 (0.7503)	model_time 0.7331 (0.7449)	loss 2.7047 (3.0217)	grad_norm 1.9967 (1.7697/0.7219)	mem 34604MB
[2025-01-19 13:31:55 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][10/312]	eta 0:04:24 lr 0.001290	time 0.8060 (0.8773)	model_time 0.8058 (0.7575)	loss 3.2074 (3.2659)	grad_norm 1.6700 (1.6511/0.9077)	mem 34602MB
[2025-01-19 13:32:00 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][300/312]	eta 0:00:08 lr 0.001292	time 0.7143 (0.7494)	model_time 0.7142 (0.7442)	loss 2.6011 (3.0070)	grad_norm 0.8775 (1.7650/0.7203)	mem 34604MB
[2025-01-19 13:32:03 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][20/312]	eta 0:03:59 lr 0.001290	time 0.7202 (0.8190)	model_time 0.7198 (0.7561)	loss 3.1879 (3.2877)	grad_norm 1.3041 (1.5567/0.7137)	mem 34602MB
[2025-01-19 13:32:08 internimage_b_1k_224] (main.py 510): INFO Train: [185/300][310/312]	eta 0:00:01 lr 0.001291	time 0.7160 (0.7485)	model_time 0.7159 (0.7434)	loss 3.8291 (3.0066)	grad_norm 1.4430 (1.7477/0.7138)	mem 34604MB
[2025-01-19 13:32:08 internimage_b_1k_224] (main.py 519): INFO EPOCH 185 training takes 0:03:53
[2025-01-19 13:32:08 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_185.pth saving......
[2025-01-19 13:32:10 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][30/312]	eta 0:03:45 lr 0.001289	time 0.7238 (0.7981)	model_time 0.7236 (0.7554)	loss 3.4139 (3.2843)	grad_norm 2.4110 (1.9616/1.0672)	mem 34602MB
[2025-01-19 13:32:12 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_185.pth saved !!!
[2025-01-19 13:32:18 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][40/312]	eta 0:03:34 lr 0.001289	time 0.7234 (0.7888)	model_time 0.7229 (0.7564)	loss 3.4811 (3.2744)	grad_norm 1.1205 (1.8232/0.9963)	mem 34602MB
[2025-01-19 13:32:19 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.222 (7.222)	Loss 0.7508 (0.7508)	Acc@1 84.521 (84.521)	Acc@5 97.583 (97.583)	Mem 34604MB
[2025-01-19 13:32:22 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.942)	Loss 1.0100 (0.8616)	Acc@1 77.759 (82.073)	Acc@5 95.044 (96.216)	Mem 34604MB
[2025-01-19 13:32:22 internimage_b_1k_224] (main.py 575): INFO [Epoch:185] * Acc@1 81.918 Acc@5 96.241
[2025-01-19 13:32:22 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.9%
[2025-01-19 13:32:22 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.00%
[2025-01-19 13:32:26 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][50/312]	eta 0:03:24 lr 0.001288	time 0.7398 (0.7810)	model_time 0.7396 (0.7549)	loss 3.3892 (3.1988)	grad_norm 1.3810 (1.7424/0.9170)	mem 34602MB
[2025-01-19 13:32:32 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.327 (9.327)	Loss 0.6813 (0.6813)	Acc@1 84.961 (84.961)	Acc@5 97.876 (97.876)	Mem 34604MB
[2025-01-19 13:32:33 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][60/312]	eta 0:03:15 lr 0.001287	time 0.7372 (0.7758)	model_time 0.7371 (0.7540)	loss 3.6842 (3.1505)	grad_norm 1.3598 (1.6549/0.8697)	mem 34602MB
[2025-01-19 13:32:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.258)	Loss 0.9503 (0.8017)	Acc@1 78.882 (82.631)	Acc@5 94.897 (96.342)	Mem 34604MB
[2025-01-19 13:32:36 internimage_b_1k_224] (main.py 575): INFO [Epoch:185] * Acc@1 82.464 Acc@5 96.401
[2025-01-19 13:32:36 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.5%
[2025-01-19 13:32:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:32:40 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:32:40 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.46%
[2025-01-19 13:32:41 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][70/312]	eta 0:03:06 lr 0.001287	time 0.7477 (0.7723)	model_time 0.7476 (0.7535)	loss 3.3927 (3.1791)	grad_norm 1.9623 (1.6080/0.8217)	mem 34602MB
[2025-01-19 13:32:42 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][0/312]	eta 0:11:00 lr 0.001291	time 2.1185 (2.1185)	model_time 0.7417 (0.7417)	loss 3.1893 (3.1893)	grad_norm 0.8868 (0.8868/0.0000)	mem 34604MB
[2025-01-19 13:32:48 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][80/312]	eta 0:02:58 lr 0.001286	time 0.7272 (0.7683)	model_time 0.7271 (0.7517)	loss 3.4464 (3.1788)	grad_norm 1.0276 (1.6272/0.8048)	mem 34602MB
[2025-01-19 13:32:49 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][10/312]	eta 0:04:17 lr 0.001290	time 0.7378 (0.8523)	model_time 0.7377 (0.7269)	loss 3.3718 (2.8370)	grad_norm 2.6478 (2.4586/0.9531)	mem 34604MB
[2025-01-19 13:32:55 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][90/312]	eta 0:02:49 lr 0.001286	time 0.7463 (0.7650)	model_time 0.7460 (0.7503)	loss 1.9879 (3.1482)	grad_norm 2.2992 (1.6126/0.7726)	mem 34602MB
[2025-01-19 13:32:57 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][20/312]	eta 0:03:52 lr 0.001290	time 0.7199 (0.7965)	model_time 0.7194 (0.7307)	loss 3.8449 (3.0790)	grad_norm 2.7668 (2.1610/0.8708)	mem 34604MB
[2025-01-19 13:33:03 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][100/312]	eta 0:02:41 lr 0.001285	time 0.7228 (0.7621)	model_time 0.7227 (0.7487)	loss 3.5365 (3.1520)	grad_norm 2.4468 (1.6318/0.7809)	mem 34602MB
[2025-01-19 13:33:04 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][30/312]	eta 0:03:38 lr 0.001289	time 0.7360 (0.7759)	model_time 0.7355 (0.7311)	loss 3.3115 (3.1247)	grad_norm 1.4274 (2.1917/0.8262)	mem 34604MB
[2025-01-19 13:33:10 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][110/312]	eta 0:02:33 lr 0.001284	time 0.7234 (0.7590)	model_time 0.7229 (0.7468)	loss 3.5616 (3.1434)	grad_norm 0.9923 (1.6676/0.8047)	mem 34602MB
[2025-01-19 13:33:11 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][40/312]	eta 0:03:28 lr 0.001289	time 0.7200 (0.7669)	model_time 0.7196 (0.7330)	loss 2.8936 (3.0942)	grad_norm 2.2576 (2.0574/0.8075)	mem 34604MB
[2025-01-19 13:33:17 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][120/312]	eta 0:02:25 lr 0.001284	time 0.7173 (0.7580)	model_time 0.7172 (0.7468)	loss 2.5889 (3.0935)	grad_norm 3.3048 (1.7244/0.8207)	mem 34602MB
[2025-01-19 13:33:19 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][50/312]	eta 0:03:21 lr 0.001288	time 0.7944 (0.7681)	model_time 0.7942 (0.7407)	loss 3.0821 (3.1015)	grad_norm 0.9005 (1.8957/0.8091)	mem 34604MB
[2025-01-19 13:33:25 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][130/312]	eta 0:02:18 lr 0.001283	time 0.7164 (0.7584)	model_time 0.7163 (0.7480)	loss 2.4429 (3.0909)	grad_norm 1.0354 (1.7225/0.8127)	mem 34602MB
[2025-01-19 13:33:27 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][60/312]	eta 0:03:15 lr 0.001287	time 0.8055 (0.7743)	model_time 0.8053 (0.7514)	loss 2.6793 (3.0774)	grad_norm 2.6071 (1.8715/0.7747)	mem 34604MB
[2025-01-19 13:33:33 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][140/312]	eta 0:02:10 lr 0.001282	time 0.7176 (0.7588)	model_time 0.7175 (0.7492)	loss 3.0440 (3.0750)	grad_norm 3.0335 (1.7228/0.8001)	mem 34602MB
[2025-01-19 13:33:34 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][70/312]	eta 0:03:06 lr 0.001287	time 0.7306 (0.7688)	model_time 0.7304 (0.7490)	loss 2.8079 (3.0566)	grad_norm 1.5400 (1.9027/0.8772)	mem 34604MB
[2025-01-19 13:33:40 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][150/312]	eta 0:02:03 lr 0.001282	time 0.7154 (0.7599)	model_time 0.7153 (0.7508)	loss 3.6963 (3.0736)	grad_norm 1.3516 (1.7613/0.8121)	mem 34602MB
[2025-01-19 13:33:42 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][80/312]	eta 0:02:57 lr 0.001286	time 0.7178 (0.7654)	model_time 0.7177 (0.7480)	loss 2.6321 (3.0674)	grad_norm 3.1082 (2.0086/0.9924)	mem 34604MB
[2025-01-19 13:33:48 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][160/312]	eta 0:01:55 lr 0.001281	time 0.7295 (0.7599)	model_time 0.7293 (0.7514)	loss 3.1882 (3.0787)	grad_norm 2.2508 (1.7768/0.8195)	mem 34602MB
[2025-01-19 13:33:49 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][90/312]	eta 0:02:48 lr 0.001286	time 0.7174 (0.7612)	model_time 0.7172 (0.7458)	loss 3.2854 (3.0600)	grad_norm 2.3884 (1.9916/0.9644)	mem 34604MB
[2025-01-19 13:33:56 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][170/312]	eta 0:01:47 lr 0.001281	time 0.8226 (0.7594)	model_time 0.8224 (0.7514)	loss 3.7834 (3.0864)	grad_norm 2.4959 (1.7782/0.8034)	mem 34602MB
[2025-01-19 13:33:56 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][100/312]	eta 0:02:40 lr 0.001285	time 0.7330 (0.7583)	model_time 0.7325 (0.7443)	loss 3.1702 (3.0461)	grad_norm 1.1269 (1.9308/0.9395)	mem 34604MB
[2025-01-19 13:34:03 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][180/312]	eta 0:01:40 lr 0.001280	time 0.7331 (0.7593)	model_time 0.7327 (0.7517)	loss 2.9761 (3.0764)	grad_norm 1.1336 (1.7677/0.7927)	mem 34602MB
[2025-01-19 13:34:04 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][110/312]	eta 0:02:32 lr 0.001284	time 0.7264 (0.7554)	model_time 0.7263 (0.7426)	loss 3.0717 (3.0026)	grad_norm 0.9037 (1.9577/0.9388)	mem 34604MB
[2025-01-19 13:34:11 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][190/312]	eta 0:01:32 lr 0.001279	time 0.7465 (0.7584)	model_time 0.7464 (0.7511)	loss 3.0968 (3.0769)	grad_norm 0.8645 (1.7830/0.7892)	mem 34602MB
[2025-01-19 13:34:11 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][120/312]	eta 0:02:24 lr 0.001284	time 0.7505 (0.7536)	model_time 0.7504 (0.7418)	loss 3.1487 (3.0127)	grad_norm 2.3167 (1.8991/0.9282)	mem 34604MB
[2025-01-19 13:34:18 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][200/312]	eta 0:01:24 lr 0.001279	time 0.7175 (0.7575)	model_time 0.7174 (0.7506)	loss 3.1853 (3.0738)	grad_norm 1.0038 (1.7506/0.7842)	mem 34602MB
[2025-01-19 13:34:18 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][130/312]	eta 0:02:16 lr 0.001283	time 0.7306 (0.7519)	model_time 0.7305 (0.7411)	loss 3.4659 (3.0097)	grad_norm 3.4909 (1.8982/0.9258)	mem 34604MB
[2025-01-19 13:34:25 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][210/312]	eta 0:01:17 lr 0.001278	time 0.7201 (0.7571)	model_time 0.7197 (0.7506)	loss 2.9513 (3.0784)	grad_norm 1.4190 (1.7459/0.7714)	mem 34602MB
[2025-01-19 13:34:26 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][140/312]	eta 0:02:09 lr 0.001282	time 0.7256 (0.7503)	model_time 0.7252 (0.7402)	loss 2.1632 (3.0046)	grad_norm 2.3392 (1.9149/0.9315)	mem 34604MB
[2025-01-19 13:34:33 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][220/312]	eta 0:01:09 lr 0.001278	time 0.7202 (0.7562)	model_time 0.7200 (0.7499)	loss 3.2138 (3.0730)	grad_norm 1.9084 (1.7365/0.7605)	mem 34602MB
[2025-01-19 13:34:33 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][150/312]	eta 0:02:01 lr 0.001282	time 0.7259 (0.7490)	model_time 0.7255 (0.7395)	loss 2.9780 (2.9961)	grad_norm 1.7981 (1.8747/0.9174)	mem 34604MB
[2025-01-19 13:34:40 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][230/312]	eta 0:01:01 lr 0.001277	time 0.7322 (0.7549)	model_time 0.7320 (0.7489)	loss 2.6982 (3.0738)	grad_norm 1.0178 (1.7305/0.7475)	mem 34602MB
[2025-01-19 13:34:40 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][160/312]	eta 0:01:53 lr 0.001281	time 0.7171 (0.7491)	model_time 0.7169 (0.7402)	loss 3.3988 (2.9972)	grad_norm 0.9826 (1.8630/0.9111)	mem 34604MB
[2025-01-19 13:34:48 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][240/312]	eta 0:00:54 lr 0.001276	time 0.7248 (0.7546)	model_time 0.7244 (0.7488)	loss 3.3319 (3.0747)	grad_norm 2.3207 (1.7138/0.7414)	mem 34602MB
[2025-01-19 13:34:48 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][170/312]	eta 0:01:46 lr 0.001281	time 0.8012 (0.7501)	model_time 0.8007 (0.7417)	loss 3.6013 (2.9951)	grad_norm 1.1987 (1.8742/0.9191)	mem 34604MB
[2025-01-19 13:34:55 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][250/312]	eta 0:00:46 lr 0.001276	time 0.7215 (0.7543)	model_time 0.7213 (0.7488)	loss 3.0260 (3.0764)	grad_norm 1.4279 (1.7234/0.7309)	mem 34602MB
[2025-01-19 13:34:56 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][180/312]	eta 0:01:39 lr 0.001280	time 0.8086 (0.7529)	model_time 0.8081 (0.7449)	loss 3.5297 (2.9871)	grad_norm 2.4448 (1.8651/0.9032)	mem 34604MB
[2025-01-19 13:35:02 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][260/312]	eta 0:00:39 lr 0.001275	time 0.7100 (0.7540)	model_time 0.7098 (0.7487)	loss 3.5611 (3.0583)	grad_norm 1.4666 (1.7192/0.7274)	mem 34602MB
[2025-01-19 13:35:03 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][190/312]	eta 0:01:31 lr 0.001279	time 0.7268 (0.7522)	model_time 0.7264 (0.7446)	loss 1.9943 (2.9820)	grad_norm 2.0657 (1.8727/0.9067)	mem 34604MB
[2025-01-19 13:35:10 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][270/312]	eta 0:00:31 lr 0.001274	time 0.8191 (0.7548)	model_time 0.8187 (0.7496)	loss 3.1081 (3.0640)	grad_norm 1.7705 (1.7314/0.7214)	mem 34602MB
[2025-01-19 13:35:11 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][200/312]	eta 0:01:24 lr 0.001279	time 0.7186 (0.7516)	model_time 0.7184 (0.7444)	loss 2.3967 (2.9915)	grad_norm 3.4646 (1.9247/0.9378)	mem 34604MB
[2025-01-19 13:35:18 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][280/312]	eta 0:00:24 lr 0.001274	time 0.7269 (0.7543)	model_time 0.7267 (0.7493)	loss 3.9107 (3.0650)	grad_norm 1.5913 (1.7381/0.7155)	mem 34602MB
[2025-01-19 13:35:18 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][210/312]	eta 0:01:16 lr 0.001278	time 0.7223 (0.7507)	model_time 0.7219 (0.7438)	loss 3.4809 (2.9979)	grad_norm 1.2170 (1.9326/0.9328)	mem 34604MB
[2025-01-19 13:35:25 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][290/312]	eta 0:00:16 lr 0.001273	time 0.7953 (0.7541)	model_time 0.7950 (0.7493)	loss 3.0694 (3.0710)	grad_norm 1.2686 (1.7447/0.7168)	mem 34602MB
[2025-01-19 13:35:25 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][220/312]	eta 0:01:08 lr 0.001278	time 0.7200 (0.7496)	model_time 0.7196 (0.7430)	loss 3.6218 (2.9956)	grad_norm 1.8650 (1.9206/0.9230)	mem 34604MB
[2025-01-19 13:35:33 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][300/312]	eta 0:00:09 lr 0.001273	time 0.7129 (0.7541)	model_time 0.7128 (0.7494)	loss 2.7628 (3.0657)	grad_norm 1.3361 (1.7386/0.7212)	mem 34602MB
[2025-01-19 13:35:33 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][230/312]	eta 0:01:01 lr 0.001277	time 0.7082 (0.7488)	model_time 0.7081 (0.7424)	loss 3.4823 (2.9834)	grad_norm 3.1463 (1.9501/0.9250)	mem 34604MB
[2025-01-19 13:35:40 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][310/312]	eta 0:00:01 lr 0.001272	time 0.7137 (0.7531)	model_time 0.7136 (0.7486)	loss 3.0834 (3.0641)	grad_norm 1.2893 (1.7321/0.7082)	mem 34602MB
[2025-01-19 13:35:40 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][240/312]	eta 0:00:53 lr 0.001276	time 0.7250 (0.7479)	model_time 0.7246 (0.7419)	loss 3.0296 (2.9705)	grad_norm 1.7155 (1.9369/0.9137)	mem 34604MB
[2025-01-19 13:35:41 internimage_b_1k_224] (main.py 519): INFO EPOCH 186 training takes 0:03:55
[2025-01-19 13:35:41 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_186.pth saving......
[2025-01-19 13:35:44 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_186.pth saved !!!
[2025-01-19 13:35:47 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][250/312]	eta 0:00:46 lr 0.001276	time 0.7236 (0.7472)	model_time 0.7232 (0.7413)	loss 3.2593 (2.9747)	grad_norm 2.2977 (1.9164/0.9056)	mem 34604MB
[2025-01-19 13:35:52 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.988 (7.988)	Loss 0.7493 (0.7493)	Acc@1 84.619 (84.619)	Acc@5 97.314 (97.314)	Mem 34602MB
[2025-01-19 13:35:55 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][260/312]	eta 0:00:38 lr 0.001275	time 0.7211 (0.7466)	model_time 0.7209 (0.7410)	loss 2.4193 (2.9787)	grad_norm 2.0650 (1.9128/0.9052)	mem 34604MB
[2025-01-19 13:35:55 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.031)	Loss 1.0252 (0.8551)	Acc@1 77.197 (82.147)	Acc@5 94.531 (96.116)	Mem 34602MB
[2025-01-19 13:35:56 internimage_b_1k_224] (main.py 575): INFO [Epoch:186] * Acc@1 82.068 Acc@5 96.145
[2025-01-19 13:35:56 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.1%
[2025-01-19 13:35:56 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 13:35:59 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 13:35:59 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.07%
[2025-01-19 13:36:02 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][270/312]	eta 0:00:31 lr 0.001274	time 0.7160 (0.7461)	model_time 0.7155 (0.7406)	loss 2.5173 (2.9852)	grad_norm 1.3935 (1.9016/0.8943)	mem 34604MB
[2025-01-19 13:36:07 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.015 (8.015)	Loss 0.6838 (0.6838)	Acc@1 84.937 (84.937)	Acc@5 97.852 (97.852)	Mem 34602MB
[2025-01-19 13:36:10 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][280/312]	eta 0:00:23 lr 0.001274	time 0.7145 (0.7464)	model_time 0.7144 (0.7411)	loss 3.3242 (2.9855)	grad_norm 1.1415 (1.8965/0.8821)	mem 34604MB
[2025-01-19 13:36:10 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.038)	Loss 0.9490 (0.8032)	Acc@1 78.613 (82.537)	Acc@5 95.020 (96.373)	Mem 34602MB
[2025-01-19 13:36:11 internimage_b_1k_224] (main.py 575): INFO [Epoch:186] * Acc@1 82.372 Acc@5 96.423
[2025-01-19 13:36:11 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.4%
[2025-01-19 13:36:11 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:36:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:36:14 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.37%
[2025-01-19 13:36:16 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][0/312]	eta 0:10:07 lr 0.001272	time 1.9462 (1.9462)	model_time 0.7438 (0.7438)	loss 2.7408 (2.7408)	grad_norm 1.7009 (1.7009/0.0000)	mem 34602MB
[2025-01-19 13:36:17 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][290/312]	eta 0:00:16 lr 0.001273	time 0.7989 (0.7476)	model_time 0.7987 (0.7425)	loss 2.5846 (2.9811)	grad_norm 1.4771 (1.8837/0.8717)	mem 34604MB
[2025-01-19 13:36:24 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][10/312]	eta 0:04:19 lr 0.001271	time 0.7161 (0.8594)	model_time 0.7160 (0.7497)	loss 2.1803 (2.8698)	grad_norm 2.1316 (2.1140/0.7185)	mem 34602MB
[2025-01-19 13:36:25 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][300/312]	eta 0:00:08 lr 0.001273	time 0.8116 (0.7489)	model_time 0.8115 (0.7439)	loss 3.7556 (2.9894)	grad_norm 2.2130 (1.8751/0.8629)	mem 34604MB
[2025-01-19 13:36:31 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][20/312]	eta 0:03:54 lr 0.001271	time 0.7219 (0.8035)	model_time 0.7215 (0.7458)	loss 3.1502 (2.9384)	grad_norm 3.8327 (2.1535/0.7890)	mem 34602MB
[2025-01-19 13:36:33 internimage_b_1k_224] (main.py 510): INFO Train: [186/300][310/312]	eta 0:00:01 lr 0.001272	time 0.7156 (0.7486)	model_time 0.7155 (0.7438)	loss 3.2852 (2.9937)	grad_norm 1.5846 (1.8577/0.8514)	mem 34604MB
[2025-01-19 13:36:33 internimage_b_1k_224] (main.py 519): INFO EPOCH 186 training takes 0:03:53
[2025-01-19 13:36:33 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_186.pth saving......
[2025-01-19 13:36:37 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_186.pth saved !!!
[2025-01-19 13:36:39 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][30/312]	eta 0:03:40 lr 0.001270	time 0.7254 (0.7805)	model_time 0.7250 (0.7413)	loss 2.7583 (2.9230)	grad_norm 0.8993 (1.9829/0.7626)	mem 34602MB
[2025-01-19 13:36:44 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.684 (7.684)	Loss 0.7076 (0.7076)	Acc@1 84.497 (84.497)	Acc@5 97.461 (97.461)	Mem 34604MB
[2025-01-19 13:36:46 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][40/312]	eta 0:03:28 lr 0.001269	time 0.7664 (0.7684)	model_time 0.7662 (0.7387)	loss 2.8827 (2.9218)	grad_norm 1.2350 (1.8146/0.7469)	mem 34602MB
[2025-01-19 13:36:48 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.994)	Loss 0.9951 (0.8457)	Acc@1 78.149 (82.107)	Acc@5 95.117 (96.183)	Mem 34604MB
[2025-01-19 13:36:48 internimage_b_1k_224] (main.py 575): INFO [Epoch:186] * Acc@1 81.960 Acc@5 96.223
[2025-01-19 13:36:48 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.0%
[2025-01-19 13:36:48 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.00%
[2025-01-19 13:36:53 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][50/312]	eta 0:03:20 lr 0.001269	time 0.7155 (0.7644)	model_time 0.7153 (0.7405)	loss 2.2215 (2.8937)	grad_norm 2.2397 (1.7135/0.7169)	mem 34602MB
[2025-01-19 13:36:58 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.918 (9.918)	Loss 0.6823 (0.6823)	Acc@1 84.912 (84.912)	Acc@5 97.900 (97.900)	Mem 34604MB
[2025-01-19 13:37:01 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][60/312]	eta 0:03:11 lr 0.001268	time 0.7924 (0.7613)	model_time 0.7922 (0.7413)	loss 2.2326 (2.9003)	grad_norm 1.0555 (1.6610/0.6826)	mem 34602MB
[2025-01-19 13:37:02 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.313)	Loss 0.9502 (0.8021)	Acc@1 78.906 (82.635)	Acc@5 94.897 (96.349)	Mem 34604MB
[2025-01-19 13:37:02 internimage_b_1k_224] (main.py 575): INFO [Epoch:186] * Acc@1 82.468 Acc@5 96.409
[2025-01-19 13:37:02 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.5%
[2025-01-19 13:37:03 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:37:06 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:37:06 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.47%
[2025-01-19 13:37:08 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][0/312]	eta 0:09:59 lr 0.001272	time 1.9214 (1.9214)	model_time 0.7300 (0.7300)	loss 3.0079 (3.0079)	grad_norm 1.7416 (1.7416/0.0000)	mem 34604MB
[2025-01-19 13:37:09 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][70/312]	eta 0:03:04 lr 0.001268	time 0.7200 (0.7606)	model_time 0.7198 (0.7433)	loss 2.0440 (2.9090)	grad_norm 1.3318 (1.6844/0.6982)	mem 34602MB
[2025-01-19 13:37:15 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][10/312]	eta 0:04:16 lr 0.001271	time 0.7220 (0.8496)	model_time 0.7216 (0.7409)	loss 2.9708 (2.9895)	grad_norm 1.1787 (1.7699/0.6534)	mem 34604MB
[2025-01-19 13:37:16 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][80/312]	eta 0:02:55 lr 0.001267	time 0.7299 (0.7580)	model_time 0.7293 (0.7428)	loss 2.7709 (2.9098)	grad_norm 3.0267 (1.7392/0.7237)	mem 34602MB
[2025-01-19 13:37:23 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][20/312]	eta 0:03:51 lr 0.001271	time 0.7260 (0.7913)	model_time 0.7256 (0.7342)	loss 2.9383 (3.0623)	grad_norm 2.2994 (2.1758/0.8128)	mem 34604MB
[2025-01-19 13:37:24 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][90/312]	eta 0:02:48 lr 0.001266	time 0.8069 (0.7593)	model_time 0.8065 (0.7457)	loss 3.5039 (2.9763)	grad_norm 2.3177 (1.7475/0.7397)	mem 34602MB
[2025-01-19 13:37:30 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][30/312]	eta 0:03:37 lr 0.001270	time 0.7226 (0.7724)	model_time 0.7225 (0.7336)	loss 3.2625 (3.0566)	grad_norm 1.0897 (2.0046/0.8035)	mem 34604MB
[2025-01-19 13:37:31 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][100/312]	eta 0:02:40 lr 0.001266	time 0.7359 (0.7575)	model_time 0.7357 (0.7452)	loss 3.2828 (2.9902)	grad_norm 1.5027 (1.7462/0.7180)	mem 34602MB
[2025-01-19 13:37:37 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][40/312]	eta 0:03:27 lr 0.001269	time 0.7200 (0.7617)	model_time 0.7199 (0.7323)	loss 3.2269 (3.0712)	grad_norm 0.8678 (1.8132/0.7870)	mem 34604MB
[2025-01-19 13:37:38 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][110/312]	eta 0:02:32 lr 0.001265	time 0.7913 (0.7566)	model_time 0.7909 (0.7454)	loss 2.9537 (2.9821)	grad_norm 1.0216 (1.7663/0.7267)	mem 34602MB
[2025-01-19 13:37:45 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][50/312]	eta 0:03:18 lr 0.001269	time 0.7227 (0.7559)	model_time 0.7222 (0.7321)	loss 3.6096 (3.1202)	grad_norm 1.1967 (1.7511/0.7446)	mem 34604MB
[2025-01-19 13:37:46 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][120/312]	eta 0:02:25 lr 0.001264	time 0.7152 (0.7556)	model_time 0.7148 (0.7453)	loss 2.8572 (3.0032)	grad_norm 1.0750 (1.7553/0.7076)	mem 34602MB
[2025-01-19 13:37:52 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][60/312]	eta 0:03:09 lr 0.001268	time 0.7291 (0.7521)	model_time 0.7286 (0.7322)	loss 3.8664 (3.0978)	grad_norm 0.9712 (1.6992/0.7229)	mem 34604MB
[2025-01-19 13:37:53 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][130/312]	eta 0:02:17 lr 0.001264	time 0.7203 (0.7540)	model_time 0.7199 (0.7445)	loss 2.8442 (3.0209)	grad_norm 2.2129 (1.7407/0.6925)	mem 34602MB
[2025-01-19 13:37:59 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][70/312]	eta 0:03:01 lr 0.001268	time 0.7577 (0.7504)	model_time 0.7572 (0.7333)	loss 3.4829 (3.0919)	grad_norm 1.7415 (1.6354/0.6994)	mem 34604MB
[2025-01-19 13:38:01 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][140/312]	eta 0:02:09 lr 0.001263	time 0.7354 (0.7535)	model_time 0.7350 (0.7446)	loss 2.9492 (3.0130)	grad_norm 1.9389 (1.7581/0.6966)	mem 34602MB
[2025-01-19 13:38:07 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][80/312]	eta 0:02:53 lr 0.001267	time 0.7229 (0.7481)	model_time 0.7225 (0.7330)	loss 1.9357 (3.0469)	grad_norm 1.4484 (1.6906/0.7012)	mem 34604MB
[2025-01-19 13:38:08 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][150/312]	eta 0:02:01 lr 0.001263	time 0.7200 (0.7523)	model_time 0.7198 (0.7440)	loss 3.5612 (3.0268)	grad_norm 2.2470 (1.7837/0.7162)	mem 34602MB
[2025-01-19 13:38:14 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][90/312]	eta 0:02:46 lr 0.001266	time 0.8021 (0.7494)	model_time 0.8016 (0.7359)	loss 3.0959 (3.0309)	grad_norm 1.5196 (1.6780/0.6863)	mem 34604MB
[2025-01-19 13:38:15 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][160/312]	eta 0:01:54 lr 0.001262	time 0.7233 (0.7505)	model_time 0.7232 (0.7427)	loss 3.8699 (3.0284)	grad_norm 1.5703 (1.7786/0.7171)	mem 34602MB
[2025-01-19 13:38:22 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][100/312]	eta 0:02:39 lr 0.001266	time 0.7239 (0.7513)	model_time 0.7237 (0.7392)	loss 2.6462 (3.0143)	grad_norm 1.0305 (1.7121/0.7187)	mem 34604MB
[2025-01-19 13:38:23 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][170/312]	eta 0:01:46 lr 0.001261	time 0.7232 (0.7504)	model_time 0.7230 (0.7430)	loss 2.2715 (3.0291)	grad_norm 1.6385 (1.7508/0.7121)	mem 34602MB
[2025-01-19 13:38:30 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][110/312]	eta 0:02:32 lr 0.001265	time 0.8196 (0.7561)	model_time 0.8194 (0.7450)	loss 3.3261 (3.0187)	grad_norm 2.8369 (1.7707/0.7355)	mem 34604MB
[2025-01-19 13:38:30 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][180/312]	eta 0:01:39 lr 0.001261	time 0.8056 (0.7506)	model_time 0.8051 (0.7436)	loss 3.2189 (3.0204)	grad_norm 1.0771 (1.7343/0.7145)	mem 34602MB
[2025-01-19 13:38:37 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][120/312]	eta 0:02:25 lr 0.001264	time 0.7244 (0.7560)	model_time 0.7240 (0.7458)	loss 2.7926 (3.0238)	grad_norm 2.1112 (1.8012/0.7871)	mem 34604MB
[2025-01-19 13:38:38 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][190/312]	eta 0:01:31 lr 0.001260	time 0.7128 (0.7506)	model_time 0.7126 (0.7440)	loss 2.9081 (3.0184)	grad_norm 0.8528 (1.7124/0.7073)	mem 34602MB
[2025-01-19 13:38:45 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][130/312]	eta 0:02:17 lr 0.001264	time 0.7167 (0.7548)	model_time 0.7162 (0.7453)	loss 2.9104 (3.0387)	grad_norm 1.1587 (1.7887/0.7748)	mem 34604MB
[2025-01-19 13:38:45 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][200/312]	eta 0:01:24 lr 0.001260	time 0.7276 (0.7506)	model_time 0.7272 (0.7443)	loss 2.8070 (3.0162)	grad_norm 1.1101 (1.7106/0.7089)	mem 34602MB
[2025-01-19 13:38:52 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][140/312]	eta 0:02:09 lr 0.001263	time 0.7198 (0.7528)	model_time 0.7197 (0.7440)	loss 3.5780 (3.0330)	grad_norm 1.2322 (1.7681/0.7586)	mem 34604MB
[2025-01-19 13:38:53 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][210/312]	eta 0:01:16 lr 0.001259	time 0.7159 (0.7511)	model_time 0.7158 (0.7450)	loss 3.1743 (3.0012)	grad_norm 3.5099 (1.7424/0.7404)	mem 34602MB
[2025-01-19 13:38:59 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][150/312]	eta 0:02:01 lr 0.001263	time 0.7175 (0.7509)	model_time 0.7174 (0.7426)	loss 3.2071 (3.0279)	grad_norm 1.5361 (1.7350/0.7465)	mem 34604MB
[2025-01-19 13:39:00 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][220/312]	eta 0:01:09 lr 0.001258	time 0.7233 (0.7510)	model_time 0.7231 (0.7452)	loss 2.4957 (2.9954)	grad_norm 2.6028 (1.7519/0.7364)	mem 34602MB
[2025-01-19 13:39:07 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][160/312]	eta 0:01:53 lr 0.001262	time 0.7207 (0.7493)	model_time 0.7202 (0.7415)	loss 3.3547 (3.0163)	grad_norm 1.7778 (1.7383/0.7342)	mem 34604MB
[2025-01-19 13:39:08 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][230/312]	eta 0:01:01 lr 0.001258	time 0.8073 (0.7516)	model_time 0.8071 (0.7461)	loss 3.3079 (2.9966)	grad_norm 3.2643 (1.7891/0.7668)	mem 34602MB
[2025-01-19 13:39:14 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][170/312]	eta 0:01:46 lr 0.001261	time 0.7261 (0.7481)	model_time 0.7257 (0.7408)	loss 3.3181 (3.0218)	grad_norm 0.9087 (1.7406/0.7369)	mem 34604MB
[2025-01-19 13:39:16 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][240/312]	eta 0:00:54 lr 0.001257	time 0.7240 (0.7512)	model_time 0.7236 (0.7458)	loss 3.0023 (2.9949)	grad_norm 3.1632 (1.8037/0.7662)	mem 34602MB
[2025-01-19 13:39:21 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][180/312]	eta 0:01:38 lr 0.001261	time 0.7148 (0.7469)	model_time 0.7144 (0.7399)	loss 3.3061 (3.0172)	grad_norm 2.7326 (1.7302/0.7289)	mem 34604MB
[2025-01-19 13:39:23 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][250/312]	eta 0:00:46 lr 0.001257	time 0.7298 (0.7508)	model_time 0.7296 (0.7456)	loss 3.2801 (2.9893)	grad_norm 1.0627 (1.8033/0.7628)	mem 34602MB
[2025-01-19 13:39:28 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][190/312]	eta 0:01:30 lr 0.001260	time 0.7143 (0.7458)	model_time 0.7141 (0.7392)	loss 2.0739 (3.0153)	grad_norm 2.6716 (1.7261/0.7219)	mem 34604MB
[2025-01-19 13:39:30 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][260/312]	eta 0:00:39 lr 0.001256	time 0.7230 (0.7506)	model_time 0.7225 (0.7456)	loss 3.6586 (2.9859)	grad_norm 2.5329 (1.7963/0.7558)	mem 34602MB
[2025-01-19 13:39:36 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][200/312]	eta 0:01:23 lr 0.001260	time 0.7203 (0.7448)	model_time 0.7199 (0.7385)	loss 3.1750 (3.0108)	grad_norm 1.5618 (1.7409/0.7213)	mem 34604MB
[2025-01-19 13:39:38 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][270/312]	eta 0:00:31 lr 0.001255	time 0.7233 (0.7500)	model_time 0.7229 (0.7452)	loss 2.0674 (2.9921)	grad_norm 2.5962 (1.7998/0.7485)	mem 34602MB
[2025-01-19 13:39:43 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][210/312]	eta 0:01:16 lr 0.001259	time 0.8048 (0.7454)	model_time 0.8046 (0.7394)	loss 3.1187 (3.0085)	grad_norm 1.3633 (1.7582/0.7248)	mem 34604MB
[2025-01-19 13:39:45 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][280/312]	eta 0:00:23 lr 0.001255	time 0.7493 (0.7493)	model_time 0.7489 (0.7446)	loss 2.7195 (2.9763)	grad_norm 2.8512 (1.7982/0.7462)	mem 34602MB
[2025-01-19 13:39:51 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][220/312]	eta 0:01:08 lr 0.001258	time 0.7192 (0.7466)	model_time 0.7190 (0.7408)	loss 3.0809 (3.0067)	grad_norm 0.8771 (1.7441/0.7283)	mem 34604MB
[2025-01-19 13:39:53 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][290/312]	eta 0:00:16 lr 0.001254	time 0.7216 (0.7492)	model_time 0.7215 (0.7447)	loss 3.4024 (2.9749)	grad_norm 1.4763 (1.7838/0.7429)	mem 34602MB
[2025-01-19 13:39:59 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][230/312]	eta 0:01:01 lr 0.001258	time 0.8059 (0.7498)	model_time 0.8058 (0.7443)	loss 2.8218 (3.0038)	grad_norm 2.0433 (1.7499/0.7333)	mem 34604MB
[2025-01-19 13:40:00 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][300/312]	eta 0:00:08 lr 0.001253	time 0.7127 (0.7488)	model_time 0.7127 (0.7445)	loss 2.8348 (2.9758)	grad_norm 0.9571 (1.7811/0.7440)	mem 34602MB
[2025-01-19 13:40:07 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][240/312]	eta 0:00:53 lr 0.001257	time 0.7408 (0.7496)	model_time 0.7407 (0.7443)	loss 3.2696 (3.0056)	grad_norm 3.2170 (1.7569/0.7311)	mem 34604MB
[2025-01-19 13:40:08 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][310/312]	eta 0:00:01 lr 0.001253	time 0.7848 (0.7494)	model_time 0.7847 (0.7452)	loss 3.2293 (2.9754)	grad_norm 1.5780 (1.7824/0.7517)	mem 34602MB
[2025-01-19 13:40:08 internimage_b_1k_224] (main.py 519): INFO EPOCH 187 training takes 0:03:53
[2025-01-19 13:40:08 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_187.pth saving......
[2025-01-19 13:40:11 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_187.pth saved !!!
[2025-01-19 13:40:14 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][250/312]	eta 0:00:46 lr 0.001257	time 0.7236 (0.7495)	model_time 0.7231 (0.7444)	loss 3.0659 (3.0013)	grad_norm 2.2026 (1.7585/0.7265)	mem 34604MB
[2025-01-19 13:40:20 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.872 (7.872)	Loss 0.7332 (0.7332)	Acc@1 85.181 (85.181)	Acc@5 97.485 (97.485)	Mem 34602MB
[2025-01-19 13:40:21 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][260/312]	eta 0:00:38 lr 0.001256	time 0.7260 (0.7484)	model_time 0.7258 (0.7435)	loss 3.4371 (3.0129)	grad_norm 2.7771 (1.7804/0.7836)	mem 34604MB
[2025-01-19 13:40:23 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.014)	Loss 1.0048 (0.8505)	Acc@1 77.686 (82.224)	Acc@5 94.727 (96.234)	Mem 34602MB
[2025-01-19 13:40:23 internimage_b_1k_224] (main.py 575): INFO [Epoch:187] * Acc@1 82.060 Acc@5 96.237
[2025-01-19 13:40:23 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.1%
[2025-01-19 13:40:23 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.07%
[2025-01-19 13:40:29 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][270/312]	eta 0:00:31 lr 0.001255	time 0.7268 (0.7475)	model_time 0.7266 (0.7428)	loss 2.9897 (3.0246)	grad_norm 2.3826 (1.7862/0.7906)	mem 34604MB
[2025-01-19 13:40:32 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.453 (9.453)	Loss 0.6849 (0.6849)	Acc@1 84.961 (84.961)	Acc@5 97.900 (97.900)	Mem 34602MB
[2025-01-19 13:40:36 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][280/312]	eta 0:00:23 lr 0.001255	time 0.7231 (0.7471)	model_time 0.7229 (0.7425)	loss 3.2185 (3.0259)	grad_norm 2.2776 (1.7754/0.7827)	mem 34604MB
[2025-01-19 13:40:37 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.291)	Loss 0.9489 (0.8036)	Acc@1 78.638 (82.575)	Acc@5 95.020 (96.382)	Mem 34602MB
[2025-01-19 13:40:37 internimage_b_1k_224] (main.py 575): INFO [Epoch:187] * Acc@1 82.410 Acc@5 96.433
[2025-01-19 13:40:37 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.4%
[2025-01-19 13:40:37 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:40:41 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:40:41 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.41%
[2025-01-19 13:40:43 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][290/312]	eta 0:00:16 lr 0.001254	time 0.7221 (0.7462)	model_time 0.7217 (0.7418)	loss 3.6645 (3.0309)	grad_norm 2.1174 (1.7754/0.7753)	mem 34604MB
[2025-01-19 13:40:44 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][0/312]	eta 0:12:36 lr 0.001253	time 2.4233 (2.4233)	model_time 0.7574 (0.7574)	loss 2.9444 (2.9444)	grad_norm 1.2681 (1.2681/0.0000)	mem 34602MB
[2025-01-19 13:40:50 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][300/312]	eta 0:00:08 lr 0.001253	time 0.7144 (0.7454)	model_time 0.7143 (0.7411)	loss 2.9810 (3.0333)	grad_norm 2.7052 (1.7834/0.7703)	mem 34604MB
[2025-01-19 13:40:51 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][10/312]	eta 0:04:31 lr 0.001252	time 0.7088 (0.9006)	model_time 0.7084 (0.7488)	loss 3.0811 (3.0747)	grad_norm 1.5579 (1.5706/0.7935)	mem 34602MB
[2025-01-19 13:40:58 internimage_b_1k_224] (main.py 510): INFO Train: [187/300][310/312]	eta 0:00:01 lr 0.001253	time 0.7210 (0.7446)	model_time 0.7209 (0.7404)	loss 2.5888 (3.0328)	grad_norm 1.9517 (1.8004/0.7804)	mem 34604MB
[2025-01-19 13:40:58 internimage_b_1k_224] (main.py 519): INFO EPOCH 187 training takes 0:03:52
[2025-01-19 13:40:58 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_187.pth saving......
[2025-01-19 13:40:59 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][20/312]	eta 0:04:03 lr 0.001251	time 0.7279 (0.8325)	model_time 0.7277 (0.7528)	loss 3.0502 (3.1810)	grad_norm 1.7562 (1.6150/0.6568)	mem 34602MB
[2025-01-19 13:41:02 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_187.pth saved !!!
[2025-01-19 13:41:06 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][30/312]	eta 0:03:48 lr 0.001251	time 0.7973 (0.8104)	model_time 0.7971 (0.7563)	loss 3.3598 (3.1264)	grad_norm 1.9592 (1.6472/0.6009)	mem 34602MB
[2025-01-19 13:41:09 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.565 (7.565)	Loss 0.7355 (0.7355)	Acc@1 84.546 (84.546)	Acc@5 97.510 (97.510)	Mem 34604MB
[2025-01-19 13:41:12 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.958)	Loss 1.0030 (0.8552)	Acc@1 78.052 (82.227)	Acc@5 94.922 (96.211)	Mem 34604MB
[2025-01-19 13:41:12 internimage_b_1k_224] (main.py 575): INFO [Epoch:187] * Acc@1 81.994 Acc@5 96.207
[2025-01-19 13:41:12 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.0%
[2025-01-19 13:41:12 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.00%
[2025-01-19 13:41:14 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][40/312]	eta 0:03:36 lr 0.001250	time 0.7169 (0.7970)	model_time 0.7167 (0.7560)	loss 3.2845 (3.1018)	grad_norm 3.7599 (1.9243/0.8391)	mem 34602MB
[2025-01-19 13:41:21 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][50/312]	eta 0:03:26 lr 0.001250	time 0.7377 (0.7868)	model_time 0.7375 (0.7538)	loss 3.2145 (3.1068)	grad_norm 0.8796 (1.8849/0.8208)	mem 34602MB
[2025-01-19 13:41:22 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.208 (9.208)	Loss 0.6831 (0.6831)	Acc@1 84.985 (84.985)	Acc@5 97.925 (97.925)	Mem 34604MB
[2025-01-19 13:41:26 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.255)	Loss 0.9501 (0.8025)	Acc@1 78.979 (82.702)	Acc@5 94.922 (96.365)	Mem 34604MB
[2025-01-19 13:41:26 internimage_b_1k_224] (main.py 575): INFO [Epoch:187] * Acc@1 82.532 Acc@5 96.423
[2025-01-19 13:41:26 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.5%
[2025-01-19 13:41:26 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:41:29 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][60/312]	eta 0:03:16 lr 0.001249	time 0.7296 (0.7783)	model_time 0.7295 (0.7506)	loss 3.3468 (3.0940)	grad_norm 1.7647 (1.8479/0.8003)	mem 34602MB
[2025-01-19 13:41:30 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:41:30 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.53%
[2025-01-19 13:41:32 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][0/312]	eta 0:12:39 lr 0.001253	time 2.4350 (2.4350)	model_time 0.7530 (0.7530)	loss 1.9190 (1.9190)	grad_norm 1.2429 (1.2429/0.0000)	mem 34604MB
[2025-01-19 13:41:36 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][70/312]	eta 0:03:07 lr 0.001248	time 0.7289 (0.7744)	model_time 0.7284 (0.7506)	loss 3.4543 (3.0804)	grad_norm 1.0636 (1.7562/0.7815)	mem 34602MB
[2025-01-19 13:41:40 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][10/312]	eta 0:04:26 lr 0.001252	time 0.7261 (0.8839)	model_time 0.7257 (0.7307)	loss 3.0796 (3.0038)	grad_norm 2.8578 (1.6729/0.4402)	mem 34604MB
[2025-01-19 13:41:44 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][80/312]	eta 0:02:58 lr 0.001248	time 0.7163 (0.7693)	model_time 0.7161 (0.7483)	loss 2.5690 (3.0503)	grad_norm 2.1170 (1.7406/0.7606)	mem 34602MB
[2025-01-19 13:41:47 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][20/312]	eta 0:03:59 lr 0.001251	time 0.7431 (0.8190)	model_time 0.7429 (0.7385)	loss 3.4438 (2.9373)	grad_norm 1.8174 (1.8833/0.6319)	mem 34604MB
[2025-01-19 13:41:51 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][90/312]	eta 0:02:49 lr 0.001247	time 0.7480 (0.7648)	model_time 0.7478 (0.7461)	loss 3.3113 (3.0468)	grad_norm 1.0444 (1.7208/0.7482)	mem 34602MB
[2025-01-19 13:41:55 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][30/312]	eta 0:03:47 lr 0.001251	time 0.7146 (0.8053)	model_time 0.7145 (0.7506)	loss 3.7047 (3.0588)	grad_norm 0.8581 (1.7626/0.6880)	mem 34604MB
[2025-01-19 13:41:58 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][100/312]	eta 0:02:41 lr 0.001247	time 0.7956 (0.7633)	model_time 0.7951 (0.7464)	loss 3.6291 (3.0605)	grad_norm 1.9948 (1.6768/0.7380)	mem 34602MB
[2025-01-19 13:42:03 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][40/312]	eta 0:03:39 lr 0.001250	time 0.8539 (0.8052)	model_time 0.8535 (0.7638)	loss 3.6073 (3.0604)	grad_norm 2.6467 (1.7762/0.6540)	mem 34604MB
[2025-01-19 13:42:06 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][110/312]	eta 0:02:33 lr 0.001246	time 0.7250 (0.7614)	model_time 0.7245 (0.7461)	loss 2.7764 (3.0556)	grad_norm 2.3237 (1.7412/0.7943)	mem 34602MB
[2025-01-19 13:42:10 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][50/312]	eta 0:03:27 lr 0.001250	time 0.7222 (0.7933)	model_time 0.7221 (0.7599)	loss 2.9507 (3.0954)	grad_norm 2.5248 (1.7229/0.6283)	mem 34604MB
[2025-01-19 13:42:13 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][120/312]	eta 0:02:26 lr 0.001245	time 0.7928 (0.7616)	model_time 0.7924 (0.7474)	loss 3.4371 (3.0579)	grad_norm 1.1834 (1.7503/0.7970)	mem 34602MB
[2025-01-19 13:42:18 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][60/312]	eta 0:03:18 lr 0.001249	time 0.8059 (0.7860)	model_time 0.8057 (0.7580)	loss 2.3969 (3.0921)	grad_norm 0.7148 (1.7038/0.6590)	mem 34604MB
[2025-01-19 13:42:21 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][130/312]	eta 0:02:18 lr 0.001245	time 0.7143 (0.7611)	model_time 0.7141 (0.7480)	loss 2.5947 (3.0654)	grad_norm 1.2031 (1.7275/0.7777)	mem 34602MB
[2025-01-19 13:42:25 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][70/312]	eta 0:03:08 lr 0.001248	time 0.7169 (0.7788)	model_time 0.7164 (0.7547)	loss 3.9178 (3.0655)	grad_norm 0.8791 (1.6478/0.6419)	mem 34604MB
[2025-01-19 13:42:29 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][140/312]	eta 0:02:10 lr 0.001244	time 0.8103 (0.7610)	model_time 0.8101 (0.7489)	loss 2.9776 (3.0728)	grad_norm 1.7961 (1.7466/0.7752)	mem 34602MB
[2025-01-19 13:42:32 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][80/312]	eta 0:02:59 lr 0.001248	time 0.7254 (0.7723)	model_time 0.7252 (0.7512)	loss 2.4640 (3.0451)	grad_norm 2.2316 (1.7275/0.6772)	mem 34604MB
[2025-01-19 13:42:36 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][150/312]	eta 0:02:03 lr 0.001244	time 0.8038 (0.7612)	model_time 0.8036 (0.7498)	loss 3.2304 (3.0740)	grad_norm 3.2861 (1.7865/0.8082)	mem 34602MB
[2025-01-19 13:42:40 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][90/312]	eta 0:02:50 lr 0.001247	time 0.7220 (0.7669)	model_time 0.7219 (0.7480)	loss 2.2942 (3.0544)	grad_norm 2.2257 (1.8370/0.8547)	mem 34604MB
[2025-01-19 13:42:44 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][160/312]	eta 0:01:55 lr 0.001243	time 0.7171 (0.7607)	model_time 0.7169 (0.7500)	loss 3.1998 (3.0578)	grad_norm 1.2037 (1.8067/0.8192)	mem 34602MB
[2025-01-19 13:42:47 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][100/312]	eta 0:02:41 lr 0.001247	time 0.7261 (0.7627)	model_time 0.7260 (0.7457)	loss 2.8428 (3.0466)	grad_norm 1.3385 (1.7890/0.8329)	mem 34604MB
[2025-01-19 13:42:51 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][170/312]	eta 0:01:47 lr 0.001242	time 0.8102 (0.7598)	model_time 0.8097 (0.7497)	loss 3.3868 (3.0565)	grad_norm 1.3677 (1.7710/0.8090)	mem 34602MB
[2025-01-19 13:42:54 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][110/312]	eta 0:02:33 lr 0.001246	time 0.7257 (0.7591)	model_time 0.7253 (0.7436)	loss 2.1527 (3.0591)	grad_norm 1.7346 (1.7818/0.8133)	mem 34604MB
[2025-01-19 13:42:59 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][180/312]	eta 0:01:40 lr 0.001242	time 0.7240 (0.7584)	model_time 0.7236 (0.7488)	loss 2.1902 (3.0443)	grad_norm 1.7336 (1.7485/0.7945)	mem 34602MB
[2025-01-19 13:43:01 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][120/312]	eta 0:02:25 lr 0.001245	time 0.7256 (0.7565)	model_time 0.7254 (0.7422)	loss 2.2601 (3.0498)	grad_norm 1.2538 (1.7490/0.7914)	mem 34604MB
[2025-01-19 13:43:06 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][190/312]	eta 0:01:32 lr 0.001241	time 0.7241 (0.7579)	model_time 0.7239 (0.7488)	loss 2.8321 (3.0400)	grad_norm 1.4611 (1.7577/0.7983)	mem 34602MB
[2025-01-19 13:43:09 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][130/312]	eta 0:02:17 lr 0.001245	time 0.7152 (0.7541)	model_time 0.7148 (0.7409)	loss 1.7107 (3.0361)	grad_norm 1.2142 (1.7487/0.7747)	mem 34604MB
[2025-01-19 13:43:13 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][200/312]	eta 0:01:24 lr 0.001240	time 0.7178 (0.7569)	model_time 0.7176 (0.7482)	loss 2.5891 (3.0341)	grad_norm 1.7771 (1.7702/0.8342)	mem 34602MB
[2025-01-19 13:43:16 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][140/312]	eta 0:02:09 lr 0.001244	time 0.7188 (0.7539)	model_time 0.7183 (0.7416)	loss 1.9895 (3.0300)	grad_norm 1.3442 (1.7243/0.7587)	mem 34604MB
[2025-01-19 13:43:21 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][210/312]	eta 0:01:17 lr 0.001240	time 0.7285 (0.7556)	model_time 0.7283 (0.7473)	loss 3.8307 (3.0439)	grad_norm 1.2426 (1.7491/0.8218)	mem 34602MB
[2025-01-19 13:43:24 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][150/312]	eta 0:02:02 lr 0.001244	time 0.7982 (0.7552)	model_time 0.7978 (0.7437)	loss 3.2446 (3.0435)	grad_norm 1.1291 (1.7195/0.7499)	mem 34604MB
[2025-01-19 13:43:28 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][220/312]	eta 0:01:09 lr 0.001239	time 0.7942 (0.7552)	model_time 0.7938 (0.7473)	loss 2.8967 (3.0485)	grad_norm 2.6101 (1.7311/0.8152)	mem 34602MB
[2025-01-19 13:43:32 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][160/312]	eta 0:01:55 lr 0.001243	time 0.8110 (0.7569)	model_time 0.8106 (0.7461)	loss 3.1542 (3.0601)	grad_norm 1.4733 (1.7406/0.7474)	mem 34604MB
[2025-01-19 13:43:36 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][230/312]	eta 0:01:01 lr 0.001239	time 0.7150 (0.7546)	model_time 0.7149 (0.7470)	loss 3.1142 (3.0510)	grad_norm 1.9326 (1.7213/0.8047)	mem 34602MB
[2025-01-19 13:43:39 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][170/312]	eta 0:01:47 lr 0.001242	time 0.7202 (0.7557)	model_time 0.7200 (0.7455)	loss 2.9996 (3.0368)	grad_norm 1.3210 (1.7483/0.7491)	mem 34604MB
[2025-01-19 13:43:43 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][240/312]	eta 0:00:54 lr 0.001238	time 0.7989 (0.7546)	model_time 0.7985 (0.7473)	loss 2.9152 (3.0447)	grad_norm 4.1048 (1.7266/0.8095)	mem 34602MB
[2025-01-19 13:43:47 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][180/312]	eta 0:01:39 lr 0.001242	time 0.8074 (0.7554)	model_time 0.8070 (0.7458)	loss 3.5902 (3.0289)	grad_norm 2.1902 (1.7756/0.7720)	mem 34604MB
[2025-01-19 13:43:51 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][250/312]	eta 0:00:46 lr 0.001237	time 0.7208 (0.7543)	model_time 0.7206 (0.7473)	loss 2.2382 (3.0380)	grad_norm 1.0081 (1.7434/0.8295)	mem 34602MB
[2025-01-19 13:43:54 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][190/312]	eta 0:01:32 lr 0.001241	time 0.7203 (0.7545)	model_time 0.7198 (0.7453)	loss 3.1726 (3.0201)	grad_norm 1.9130 (1.7672/0.7657)	mem 34604MB
[2025-01-19 13:43:58 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][260/312]	eta 0:00:39 lr 0.001237	time 0.8158 (0.7546)	model_time 0.8154 (0.7478)	loss 2.7669 (3.0295)	grad_norm 1.6509 (1.7368/0.8183)	mem 34602MB
[2025-01-19 13:44:01 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][200/312]	eta 0:01:24 lr 0.001240	time 0.7279 (0.7533)	model_time 0.7274 (0.7446)	loss 2.9481 (3.0289)	grad_norm 1.3435 (1.7516/0.7610)	mem 34604MB
[2025-01-19 13:44:06 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][270/312]	eta 0:00:31 lr 0.001236	time 0.9367 (0.7548)	model_time 0.9365 (0.7483)	loss 3.1692 (3.0366)	grad_norm 2.3211 (1.7255/0.8104)	mem 34602MB
[2025-01-19 13:44:09 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][210/312]	eta 0:01:16 lr 0.001240	time 0.7268 (0.7522)	model_time 0.7263 (0.7438)	loss 3.0918 (3.0325)	grad_norm 1.0943 (1.7354/0.7501)	mem 34604MB
[2025-01-19 13:44:13 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][280/312]	eta 0:00:24 lr 0.001236	time 0.7799 (0.7547)	model_time 0.7795 (0.7484)	loss 3.0548 (3.0351)	grad_norm 1.1458 (1.7434/0.8309)	mem 34602MB
[2025-01-19 13:44:16 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][220/312]	eta 0:01:09 lr 0.001239	time 0.7200 (0.7510)	model_time 0.7199 (0.7431)	loss 3.6173 (3.0308)	grad_norm 2.0917 (1.7522/0.7690)	mem 34604MB
[2025-01-19 13:44:21 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][290/312]	eta 0:00:16 lr 0.001235	time 0.8115 (0.7543)	model_time 0.8114 (0.7482)	loss 2.9898 (3.0290)	grad_norm 1.8921 (1.7685/0.8442)	mem 34602MB
[2025-01-19 13:44:23 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][230/312]	eta 0:01:01 lr 0.001239	time 0.7246 (0.7505)	model_time 0.7245 (0.7429)	loss 3.1949 (3.0250)	grad_norm 1.7650 (1.7571/0.7704)	mem 34604MB
[2025-01-19 13:44:28 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][300/312]	eta 0:00:09 lr 0.001234	time 0.7138 (0.7536)	model_time 0.7137 (0.7477)	loss 3.4069 (3.0397)	grad_norm 1.0377 (1.7839/0.8547)	mem 34602MB
[2025-01-19 13:44:31 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][240/312]	eta 0:00:53 lr 0.001238	time 0.7161 (0.7495)	model_time 0.7159 (0.7421)	loss 2.2431 (3.0186)	grad_norm 1.1456 (1.7439/0.7609)	mem 34604MB
[2025-01-19 13:44:36 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][310/312]	eta 0:00:01 lr 0.001234	time 0.8047 (0.7534)	model_time 0.8046 (0.7477)	loss 3.3157 (3.0466)	grad_norm 2.1809 (1.7809/0.8492)	mem 34602MB
[2025-01-19 13:44:36 internimage_b_1k_224] (main.py 519): INFO EPOCH 188 training takes 0:03:55
[2025-01-19 13:44:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_188.pth saving......
[2025-01-19 13:44:38 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][250/312]	eta 0:00:46 lr 0.001237	time 0.7194 (0.7485)	model_time 0.7193 (0.7414)	loss 3.4564 (3.0247)	grad_norm 1.1968 (1.7482/0.7663)	mem 34604MB
[2025-01-19 13:44:39 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_188.pth saved !!!
[2025-01-19 13:44:45 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][260/312]	eta 0:00:38 lr 0.001237	time 0.7273 (0.7485)	model_time 0.7272 (0.7417)	loss 3.3948 (3.0261)	grad_norm 2.4514 (1.7620/0.7590)	mem 34604MB
[2025-01-19 13:44:47 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.624 (7.624)	Loss 0.7829 (0.7829)	Acc@1 84.497 (84.497)	Acc@5 97.363 (97.363)	Mem 34602MB
[2025-01-19 13:44:50 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.980)	Loss 1.0060 (0.8722)	Acc@1 78.174 (82.278)	Acc@5 94.995 (96.238)	Mem 34602MB
[2025-01-19 13:44:51 internimage_b_1k_224] (main.py 575): INFO [Epoch:188] * Acc@1 82.102 Acc@5 96.259
[2025-01-19 13:44:51 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.1%
[2025-01-19 13:44:51 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 13:44:53 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][270/312]	eta 0:00:31 lr 0.001236	time 0.8102 (0.7493)	model_time 0.8100 (0.7428)	loss 2.1578 (3.0173)	grad_norm 0.8762 (1.7567/0.7571)	mem 34604MB
[2025-01-19 13:44:54 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 13:44:54 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.10%
[2025-01-19 13:45:01 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][280/312]	eta 0:00:24 lr 0.001236	time 0.8258 (0.7504)	model_time 0.8253 (0.7440)	loss 3.5035 (3.0212)	grad_norm 0.8636 (1.7480/0.7549)	mem 34604MB
[2025-01-19 13:45:01 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.490 (7.490)	Loss 0.6861 (0.6861)	Acc@1 85.010 (85.010)	Acc@5 97.876 (97.876)	Mem 34602MB
[2025-01-19 13:45:04 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.971)	Loss 0.9490 (0.8041)	Acc@1 78.589 (82.631)	Acc@5 95.020 (96.398)	Mem 34602MB
[2025-01-19 13:45:05 internimage_b_1k_224] (main.py 575): INFO [Epoch:188] * Acc@1 82.474 Acc@5 96.447
[2025-01-19 13:45:05 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.5%
[2025-01-19 13:45:05 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:45:08 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][290/312]	eta 0:00:16 lr 0.001235	time 0.7155 (0.7501)	model_time 0.7150 (0.7439)	loss 3.2434 (3.0236)	grad_norm 2.3416 (1.7436/0.7490)	mem 34604MB
[2025-01-19 13:45:09 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:45:09 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.47%
[2025-01-19 13:45:11 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][0/312]	eta 0:10:04 lr 0.001234	time 1.9376 (1.9376)	model_time 0.7551 (0.7551)	loss 2.9819 (2.9819)	grad_norm 1.3837 (1.3837/0.0000)	mem 34602MB
[2025-01-19 13:45:16 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][300/312]	eta 0:00:08 lr 0.001234	time 0.7948 (0.7498)	model_time 0.7947 (0.7439)	loss 3.3168 (3.0254)	grad_norm 1.1708 (1.7582/0.7638)	mem 34604MB
[2025-01-19 13:45:18 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][10/312]	eta 0:04:17 lr 0.001233	time 0.7262 (0.8521)	model_time 0.7258 (0.7443)	loss 3.0984 (2.9562)	grad_norm 2.3370 (1.3686/0.4224)	mem 34602MB
[2025-01-19 13:45:23 internimage_b_1k_224] (main.py 510): INFO Train: [188/300][310/312]	eta 0:00:01 lr 0.001234	time 0.7144 (0.7490)	model_time 0.7143 (0.7432)	loss 3.1759 (3.0281)	grad_norm 1.9482 (1.7676/0.7744)	mem 34604MB
[2025-01-19 13:45:24 internimage_b_1k_224] (main.py 519): INFO EPOCH 188 training takes 0:03:53
[2025-01-19 13:45:24 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_188.pth saving......
[2025-01-19 13:45:25 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][20/312]	eta 0:03:51 lr 0.001232	time 0.7269 (0.7933)	model_time 0.7268 (0.7367)	loss 3.3828 (3.0647)	grad_norm 0.7795 (1.2925/0.3764)	mem 34602MB
[2025-01-19 13:45:27 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_188.pth saved !!!
[2025-01-19 13:45:33 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][30/312]	eta 0:03:40 lr 0.001232	time 0.7476 (0.7810)	model_time 0.7475 (0.7426)	loss 2.2298 (2.9869)	grad_norm 1.1492 (1.2493/0.3568)	mem 34602MB
[2025-01-19 13:45:34 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.489 (7.489)	Loss 0.7332 (0.7332)	Acc@1 84.839 (84.839)	Acc@5 97.534 (97.534)	Mem 34604MB
[2025-01-19 13:45:37 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.957)	Loss 0.9832 (0.8451)	Acc@1 78.564 (82.331)	Acc@5 94.995 (96.276)	Mem 34604MB
[2025-01-19 13:45:38 internimage_b_1k_224] (main.py 575): INFO [Epoch:188] * Acc@1 82.232 Acc@5 96.281
[2025-01-19 13:45:38 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.2%
[2025-01-19 13:45:38 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 13:45:40 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][40/312]	eta 0:03:30 lr 0.001231	time 0.7268 (0.7732)	model_time 0.7266 (0.7440)	loss 3.7537 (2.9978)	grad_norm 3.0834 (1.3963/0.5443)	mem 34602MB
[2025-01-19 13:45:41 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 13:45:41 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.23%
[2025-01-19 13:45:48 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][50/312]	eta 0:03:21 lr 0.001231	time 0.7166 (0.7697)	model_time 0.7165 (0.7462)	loss 2.4207 (2.9914)	grad_norm 1.3153 (1.5305/0.6490)	mem 34602MB
[2025-01-19 13:45:48 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.377 (7.377)	Loss 0.6839 (0.6839)	Acc@1 85.132 (85.132)	Acc@5 97.949 (97.949)	Mem 34604MB
[2025-01-19 13:45:51 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.184 (0.947)	Loss 0.9497 (0.8029)	Acc@1 79.053 (82.757)	Acc@5 94.922 (96.382)	Mem 34604MB
[2025-01-19 13:45:52 internimage_b_1k_224] (main.py 575): INFO [Epoch:188] * Acc@1 82.586 Acc@5 96.443
[2025-01-19 13:45:52 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.6%
[2025-01-19 13:45:52 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:45:55 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:45:55 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.59%
[2025-01-19 13:45:55 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][60/312]	eta 0:03:12 lr 0.001230	time 0.7245 (0.7654)	model_time 0.7243 (0.7457)	loss 3.5505 (2.9891)	grad_norm 1.1425 (1.5824/0.6806)	mem 34602MB
[2025-01-19 13:45:57 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][0/312]	eta 0:10:31 lr 0.001234	time 2.0225 (2.0225)	model_time 0.7562 (0.7562)	loss 3.0338 (3.0338)	grad_norm 0.8882 (0.8882/0.0000)	mem 34604MB
[2025-01-19 13:46:03 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][70/312]	eta 0:03:05 lr 0.001229	time 0.8042 (0.7668)	model_time 0.8038 (0.7498)	loss 3.4982 (2.9983)	grad_norm 2.3086 (1.7133/0.8470)	mem 34602MB
[2025-01-19 13:46:04 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][10/312]	eta 0:04:14 lr 0.001233	time 0.7228 (0.8443)	model_time 0.7226 (0.7288)	loss 3.1947 (2.9786)	grad_norm 1.9346 (1.7655/0.6268)	mem 34604MB
[2025-01-19 13:46:11 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][80/312]	eta 0:02:57 lr 0.001229	time 0.7174 (0.7650)	model_time 0.7170 (0.7500)	loss 2.4420 (3.0122)	grad_norm 1.5846 (1.7121/0.8113)	mem 34602MB
[2025-01-19 13:46:12 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][20/312]	eta 0:03:50 lr 0.001232	time 0.7260 (0.7898)	model_time 0.7259 (0.7291)	loss 2.8850 (3.0494)	grad_norm 2.9493 (1.9460/0.8279)	mem 34604MB
[2025-01-19 13:46:18 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][90/312]	eta 0:02:49 lr 0.001228	time 0.7233 (0.7634)	model_time 0.7232 (0.7501)	loss 2.1104 (2.9823)	grad_norm 1.1546 (1.6567/0.7858)	mem 34602MB
[2025-01-19 13:46:19 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][30/312]	eta 0:03:36 lr 0.001232	time 0.7257 (0.7685)	model_time 0.7256 (0.7273)	loss 3.2521 (3.0670)	grad_norm 4.4764 (2.2848/0.9991)	mem 34604MB
[2025-01-19 13:46:26 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][100/312]	eta 0:02:41 lr 0.001228	time 0.7166 (0.7619)	model_time 0.7162 (0.7498)	loss 3.6312 (2.9973)	grad_norm 1.1306 (1.6573/0.7555)	mem 34602MB
[2025-01-19 13:46:26 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][40/312]	eta 0:03:27 lr 0.001231	time 0.7640 (0.7611)	model_time 0.7639 (0.7299)	loss 2.7761 (3.0546)	grad_norm 3.3867 (2.4533/1.0235)	mem 34604MB
[2025-01-19 13:46:33 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][110/312]	eta 0:02:33 lr 0.001227	time 0.7232 (0.7592)	model_time 0.7228 (0.7482)	loss 2.9029 (3.0143)	grad_norm 1.3014 (1.6631/0.7331)	mem 34602MB
[2025-01-19 13:46:34 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][50/312]	eta 0:03:17 lr 0.001231	time 0.7217 (0.7550)	model_time 0.7212 (0.7298)	loss 3.2234 (3.1015)	grad_norm 1.6412 (2.3875/0.9823)	mem 34604MB
[2025-01-19 13:46:40 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][120/312]	eta 0:02:25 lr 0.001226	time 0.7186 (0.7586)	model_time 0.7184 (0.7485)	loss 3.1908 (3.0149)	grad_norm 1.3669 (1.6363/0.7227)	mem 34602MB
[2025-01-19 13:46:41 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][60/312]	eta 0:03:09 lr 0.001230	time 0.7252 (0.7509)	model_time 0.7251 (0.7298)	loss 2.8015 (3.1016)	grad_norm 0.9716 (2.2717/0.9483)	mem 34604MB
[2025-01-19 13:46:48 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][130/312]	eta 0:02:17 lr 0.001226	time 0.7284 (0.7576)	model_time 0.7283 (0.7483)	loss 2.2632 (2.9986)	grad_norm 3.1230 (1.6489/0.7091)	mem 34602MB
[2025-01-19 13:46:49 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][70/312]	eta 0:03:02 lr 0.001229	time 0.7156 (0.7528)	model_time 0.7152 (0.7346)	loss 3.8114 (3.0874)	grad_norm 1.5637 (2.1877/0.9455)	mem 34604MB
[2025-01-19 13:46:55 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][140/312]	eta 0:02:09 lr 0.001225	time 0.7478 (0.7555)	model_time 0.7476 (0.7468)	loss 3.6318 (2.9998)	grad_norm 1.2648 (1.6757/0.7361)	mem 34602MB
[2025-01-19 13:46:56 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][80/312]	eta 0:02:54 lr 0.001229	time 0.8379 (0.7541)	model_time 0.8374 (0.7381)	loss 3.1348 (3.1060)	grad_norm 1.4771 (2.1278/0.9227)	mem 34604MB
[2025-01-19 13:47:03 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][150/312]	eta 0:02:02 lr 0.001225	time 0.7291 (0.7550)	model_time 0.7287 (0.7469)	loss 3.4848 (3.0148)	grad_norm 0.7414 (1.6603/0.7239)	mem 34602MB
[2025-01-19 13:47:04 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][90/312]	eta 0:02:48 lr 0.001228	time 0.8216 (0.7589)	model_time 0.8215 (0.7446)	loss 2.6281 (3.0960)	grad_norm 1.6449 (2.0789/0.8912)	mem 34604MB
[2025-01-19 13:47:10 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][160/312]	eta 0:01:54 lr 0.001224	time 0.7274 (0.7553)	model_time 0.7269 (0.7476)	loss 3.1577 (3.0227)	grad_norm 0.9476 (1.6360/0.7130)	mem 34602MB
[2025-01-19 13:47:12 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][100/312]	eta 0:02:40 lr 0.001228	time 0.8326 (0.7574)	model_time 0.8325 (0.7445)	loss 3.5631 (3.1012)	grad_norm 1.3241 (2.0841/0.8889)	mem 34604MB
[2025-01-19 13:47:18 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][170/312]	eta 0:01:47 lr 0.001223	time 0.7596 (0.7553)	model_time 0.7595 (0.7480)	loss 2.5253 (3.0123)	grad_norm 1.4168 (1.6320/0.6979)	mem 34602MB
[2025-01-19 13:47:19 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][110/312]	eta 0:02:32 lr 0.001227	time 0.7180 (0.7558)	model_time 0.7179 (0.7440)	loss 3.1513 (3.1002)	grad_norm 2.5448 (2.0828/0.8684)	mem 34604MB
[2025-01-19 13:47:25 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][180/312]	eta 0:01:39 lr 0.001223	time 0.8075 (0.7545)	model_time 0.8070 (0.7476)	loss 2.1062 (3.0000)	grad_norm 1.3175 (1.6312/0.6911)	mem 34602MB
[2025-01-19 13:47:26 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][120/312]	eta 0:02:24 lr 0.001226	time 0.7514 (0.7537)	model_time 0.7510 (0.7428)	loss 3.2989 (3.1244)	grad_norm 1.2119 (2.0344/0.8604)	mem 34604MB
[2025-01-19 13:47:33 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][190/312]	eta 0:01:31 lr 0.001222	time 0.7287 (0.7536)	model_time 0.7283 (0.7471)	loss 2.9274 (3.0113)	grad_norm 1.8471 (1.6323/0.6830)	mem 34602MB
[2025-01-19 13:47:34 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][130/312]	eta 0:02:16 lr 0.001226	time 0.7069 (0.7520)	model_time 0.7064 (0.7419)	loss 3.2868 (3.1138)	grad_norm 1.6529 (1.9858/0.8509)	mem 34604MB
[2025-01-19 13:47:40 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][200/312]	eta 0:01:24 lr 0.001221	time 0.8082 (0.7551)	model_time 0.8081 (0.7488)	loss 3.0964 (3.0119)	grad_norm 1.4206 (1.6430/0.6790)	mem 34602MB
[2025-01-19 13:47:41 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][140/312]	eta 0:02:09 lr 0.001225	time 0.7211 (0.7501)	model_time 0.7207 (0.7407)	loss 2.0855 (3.1246)	grad_norm 0.8957 (1.9261/0.8513)	mem 34604MB
[2025-01-19 13:47:48 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][210/312]	eta 0:01:16 lr 0.001221	time 0.7309 (0.7548)	model_time 0.7307 (0.7488)	loss 3.0473 (3.0182)	grad_norm 1.0164 (1.6650/0.7028)	mem 34602MB
[2025-01-19 13:47:48 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][150/312]	eta 0:02:01 lr 0.001225	time 0.7478 (0.7483)	model_time 0.7476 (0.7396)	loss 2.0953 (3.1178)	grad_norm 1.9109 (1.8932/0.8448)	mem 34604MB
[2025-01-19 13:47:55 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][220/312]	eta 0:01:09 lr 0.001220	time 0.7159 (0.7546)	model_time 0.7155 (0.7488)	loss 3.2309 (3.0080)	grad_norm 3.4204 (1.6822/0.7027)	mem 34602MB
[2025-01-19 13:47:55 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][160/312]	eta 0:01:53 lr 0.001224	time 0.7294 (0.7469)	model_time 0.7290 (0.7387)	loss 2.9925 (3.1097)	grad_norm 1.7111 (1.8869/0.8351)	mem 34604MB
[2025-01-19 13:48:03 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][170/312]	eta 0:01:45 lr 0.001223	time 0.7244 (0.7458)	model_time 0.7239 (0.7379)	loss 2.4836 (3.1116)	grad_norm 1.3190 (1.8536/0.8321)	mem 34604MB
[2025-01-19 13:48:03 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][230/312]	eta 0:01:01 lr 0.001220	time 0.7249 (0.7543)	model_time 0.7245 (0.7488)	loss 3.3839 (3.0140)	grad_norm 1.5433 (1.7055/0.7232)	mem 34602MB
[2025-01-19 13:48:10 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][180/312]	eta 0:01:38 lr 0.001223	time 0.7193 (0.7448)	model_time 0.7192 (0.7375)	loss 2.9270 (3.1080)	grad_norm 2.6060 (1.8645/0.8225)	mem 34604MB
[2025-01-19 13:48:10 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][240/312]	eta 0:00:54 lr 0.001219	time 0.7189 (0.7538)	model_time 0.7187 (0.7486)	loss 3.5232 (3.0212)	grad_norm 0.9518 (1.7344/0.7440)	mem 34602MB
[2025-01-19 13:48:18 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][190/312]	eta 0:01:30 lr 0.001222	time 0.7146 (0.7458)	model_time 0.7142 (0.7388)	loss 3.5082 (3.1023)	grad_norm 3.0905 (1.8963/0.8440)	mem 34604MB
[2025-01-19 13:48:18 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][250/312]	eta 0:00:46 lr 0.001218	time 0.7240 (0.7538)	model_time 0.7239 (0.7487)	loss 3.1186 (3.0308)	grad_norm 2.0973 (1.7475/0.7405)	mem 34602MB
[2025-01-19 13:48:25 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][260/312]	eta 0:00:39 lr 0.001218	time 0.7268 (0.7528)	model_time 0.7263 (0.7479)	loss 2.2427 (3.0305)	grad_norm 0.9464 (1.7348/0.7334)	mem 34602MB
[2025-01-19 13:48:25 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][200/312]	eta 0:01:23 lr 0.001221	time 0.8037 (0.7463)	model_time 0.8035 (0.7397)	loss 3.6335 (3.1033)	grad_norm 0.8746 (1.9018/0.8558)	mem 34604MB
[2025-01-19 13:48:32 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][270/312]	eta 0:00:31 lr 0.001217	time 0.7409 (0.7524)	model_time 0.7405 (0.7476)	loss 2.6225 (3.0301)	grad_norm 1.1721 (1.7165/0.7292)	mem 34602MB
[2025-01-19 13:48:33 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][210/312]	eta 0:01:16 lr 0.001221	time 0.8043 (0.7501)	model_time 0.8039 (0.7438)	loss 2.0644 (3.0990)	grad_norm 0.9488 (1.9115/0.8593)	mem 34604MB
[2025-01-19 13:48:40 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][280/312]	eta 0:00:24 lr 0.001217	time 0.8095 (0.7525)	model_time 0.8094 (0.7479)	loss 2.9144 (3.0249)	grad_norm 1.0273 (1.6970/0.7258)	mem 34602MB
[2025-01-19 13:48:41 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][220/312]	eta 0:01:08 lr 0.001220	time 0.7862 (0.7497)	model_time 0.7858 (0.7436)	loss 3.3771 (3.0958)	grad_norm 1.0650 (1.9009/0.8506)	mem 34604MB
[2025-01-19 13:48:47 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][290/312]	eta 0:00:16 lr 0.001216	time 0.7154 (0.7520)	model_time 0.7152 (0.7476)	loss 2.7293 (3.0152)	grad_norm 2.2540 (1.7007/0.7247)	mem 34602MB
[2025-01-19 13:48:48 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][230/312]	eta 0:01:01 lr 0.001220	time 0.7202 (0.7496)	model_time 0.7200 (0.7438)	loss 3.3922 (3.0938)	grad_norm 1.9504 (1.8826/0.8438)	mem 34604MB
[2025-01-19 13:48:55 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][300/312]	eta 0:00:09 lr 0.001215	time 0.7853 (0.7518)	model_time 0.7852 (0.7475)	loss 2.5370 (3.0184)	grad_norm 2.0312 (1.7088/0.7208)	mem 34602MB
[2025-01-19 13:48:56 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][240/312]	eta 0:00:53 lr 0.001219	time 0.7229 (0.7490)	model_time 0.7227 (0.7434)	loss 3.0571 (3.0936)	grad_norm 2.3940 (1.8870/0.8329)	mem 34604MB
[2025-01-19 13:49:02 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][310/312]	eta 0:00:01 lr 0.001215	time 0.7186 (0.7512)	model_time 0.7185 (0.7470)	loss 3.0713 (3.0110)	grad_norm 3.0678 (1.7397/0.7392)	mem 34602MB
[2025-01-19 13:49:03 internimage_b_1k_224] (main.py 519): INFO EPOCH 189 training takes 0:03:54
[2025-01-19 13:49:03 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_189.pth saving......
[2025-01-19 13:49:03 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][250/312]	eta 0:00:46 lr 0.001218	time 0.7621 (0.7481)	model_time 0.7619 (0.7426)	loss 3.1953 (3.0946)	grad_norm 1.3698 (1.9064/0.8402)	mem 34604MB
[2025-01-19 13:49:06 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_189.pth saved !!!
[2025-01-19 13:49:10 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][260/312]	eta 0:00:38 lr 0.001218	time 0.7371 (0.7474)	model_time 0.7369 (0.7422)	loss 3.6409 (3.1027)	grad_norm 1.9956 (1.9128/0.8331)	mem 34604MB
[2025-01-19 13:49:14 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.706 (7.706)	Loss 0.7996 (0.7996)	Acc@1 84.497 (84.497)	Acc@5 97.363 (97.363)	Mem 34602MB
[2025-01-19 13:49:17 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.992)	Loss 0.9987 (0.8812)	Acc@1 78.345 (82.220)	Acc@5 95.142 (96.245)	Mem 34602MB
[2025-01-19 13:49:17 internimage_b_1k_224] (main.py 575): INFO [Epoch:189] * Acc@1 82.082 Acc@5 96.283
[2025-01-19 13:49:17 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.1%
[2025-01-19 13:49:17 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.10%
[2025-01-19 13:49:18 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][270/312]	eta 0:00:31 lr 0.001217	time 0.7219 (0.7469)	model_time 0.7215 (0.7418)	loss 2.8196 (3.1033)	grad_norm 1.5626 (1.9077/0.8226)	mem 34604MB
[2025-01-19 13:49:25 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][280/312]	eta 0:00:23 lr 0.001217	time 0.7200 (0.7462)	model_time 0.7198 (0.7413)	loss 2.0091 (3.0965)	grad_norm 1.5143 (1.9026/0.8155)	mem 34604MB
[2025-01-19 13:49:27 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.335 (9.335)	Loss 0.6873 (0.6873)	Acc@1 85.034 (85.034)	Acc@5 97.876 (97.876)	Mem 34602MB
[2025-01-19 13:49:31 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.183 (1.258)	Loss 0.9488 (0.8046)	Acc@1 78.687 (82.695)	Acc@5 94.971 (96.402)	Mem 34602MB
[2025-01-19 13:49:31 internimage_b_1k_224] (main.py 575): INFO [Epoch:189] * Acc@1 82.536 Acc@5 96.447
[2025-01-19 13:49:31 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.5%
[2025-01-19 13:49:31 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:49:32 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][290/312]	eta 0:00:16 lr 0.001216	time 0.7202 (0.7457)	model_time 0.7198 (0.7410)	loss 3.3845 (3.0879)	grad_norm 2.7017 (1.8983/0.8066)	mem 34604MB
[2025-01-19 13:49:35 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:49:35 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.54%
[2025-01-19 13:49:38 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][0/312]	eta 0:12:23 lr 0.001215	time 2.3843 (2.3843)	model_time 0.7476 (0.7476)	loss 3.4755 (3.4755)	grad_norm 1.5901 (1.5901/0.0000)	mem 34602MB
[2025-01-19 13:49:39 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][300/312]	eta 0:00:08 lr 0.001215	time 0.7148 (0.7450)	model_time 0.7147 (0.7404)	loss 3.5620 (3.0847)	grad_norm 1.6094 (1.9160/0.8053)	mem 34604MB
[2025-01-19 13:49:45 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][10/312]	eta 0:04:36 lr 0.001214	time 0.7563 (0.9149)	model_time 0.7562 (0.7658)	loss 3.4028 (2.9140)	grad_norm 1.1658 (1.4803/0.4723)	mem 34602MB
[2025-01-19 13:49:47 internimage_b_1k_224] (main.py 510): INFO Train: [189/300][310/312]	eta 0:00:01 lr 0.001215	time 0.7127 (0.7449)	model_time 0.7126 (0.7404)	loss 2.2780 (3.0840)	grad_norm 1.1660 (1.8944/0.8095)	mem 34604MB
[2025-01-19 13:49:48 internimage_b_1k_224] (main.py 519): INFO EPOCH 189 training takes 0:03:52
[2025-01-19 13:49:48 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_189.pth saving......
[2025-01-19 13:49:51 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_189.pth saved !!!
[2025-01-19 13:49:53 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][20/312]	eta 0:04:04 lr 0.001213	time 0.8070 (0.8386)	model_time 0.8068 (0.7603)	loss 3.2630 (2.8574)	grad_norm 0.9976 (1.6839/0.6033)	mem 34602MB
[2025-01-19 13:49:59 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.619 (7.619)	Loss 0.6829 (0.6829)	Acc@1 85.474 (85.474)	Acc@5 97.559 (97.559)	Mem 34604MB
[2025-01-19 13:50:00 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][30/312]	eta 0:03:48 lr 0.001213	time 0.7280 (0.8086)	model_time 0.7275 (0.7554)	loss 2.8900 (2.9343)	grad_norm 2.5836 (1.8257/0.7279)	mem 34602MB
[2025-01-19 13:50:02 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.982)	Loss 0.9329 (0.8168)	Acc@1 79.297 (82.402)	Acc@5 95.190 (96.300)	Mem 34604MB
[2025-01-19 13:50:02 internimage_b_1k_224] (main.py 575): INFO [Epoch:189] * Acc@1 82.248 Acc@5 96.295
[2025-01-19 13:50:02 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.2%
[2025-01-19 13:50:02 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 13:50:06 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 13:50:06 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.25%
[2025-01-19 13:50:08 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][40/312]	eta 0:03:34 lr 0.001212	time 0.7169 (0.7898)	model_time 0.7165 (0.7495)	loss 3.2769 (2.9730)	grad_norm 1.6553 (1.8063/0.7104)	mem 34602MB
[2025-01-19 13:50:13 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.380 (7.380)	Loss 0.6848 (0.6848)	Acc@1 85.205 (85.205)	Acc@5 97.998 (97.998)	Mem 34604MB
[2025-01-19 13:50:15 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][50/312]	eta 0:03:24 lr 0.001212	time 0.7173 (0.7817)	model_time 0.7171 (0.7492)	loss 3.4411 (2.9867)	grad_norm 0.9500 (1.8235/0.7432)	mem 34602MB
[2025-01-19 13:50:16 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.923)	Loss 0.9492 (0.8032)	Acc@1 79.077 (82.790)	Acc@5 94.971 (96.393)	Mem 34604MB
[2025-01-19 13:50:16 internimage_b_1k_224] (main.py 575): INFO [Epoch:189] * Acc@1 82.620 Acc@5 96.447
[2025-01-19 13:50:16 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.6%
[2025-01-19 13:50:16 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:50:19 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:50:19 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.62%
[2025-01-19 13:50:22 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][0/312]	eta 0:12:02 lr 0.001215	time 2.3151 (2.3151)	model_time 0.7469 (0.7469)	loss 3.3775 (3.3775)	grad_norm 1.8340 (1.8340/0.0000)	mem 34604MB
[2025-01-19 13:50:22 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][60/312]	eta 0:03:14 lr 0.001211	time 0.7392 (0.7735)	model_time 0.7388 (0.7463)	loss 3.2074 (2.9997)	grad_norm 1.5180 (1.7530/0.7134)	mem 34602MB
[2025-01-19 13:50:29 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][10/312]	eta 0:04:31 lr 0.001214	time 0.8175 (0.8996)	model_time 0.8174 (0.7567)	loss 3.1429 (2.9141)	grad_norm 1.6022 (1.9617/0.5757)	mem 34604MB
[2025-01-19 13:50:30 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][70/312]	eta 0:03:05 lr 0.001210	time 0.7225 (0.7677)	model_time 0.7221 (0.7443)	loss 3.1493 (3.0282)	grad_norm 1.6488 (1.7247/0.6725)	mem 34602MB
[2025-01-19 13:50:37 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][80/312]	eta 0:02:57 lr 0.001210	time 0.7217 (0.7662)	model_time 0.7216 (0.7456)	loss 1.8990 (3.0282)	grad_norm 1.4230 (1.6729/0.6552)	mem 34602MB
[2025-01-19 13:50:38 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][20/312]	eta 0:04:11 lr 0.001213	time 0.7419 (0.8601)	model_time 0.7414 (0.7852)	loss 2.8733 (2.8712)	grad_norm 1.5285 (1.8095/0.5322)	mem 34604MB
[2025-01-19 13:50:45 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][90/312]	eta 0:02:49 lr 0.001209	time 0.8089 (0.7646)	model_time 0.8087 (0.7462)	loss 2.6284 (3.0335)	grad_norm 1.3109 (1.6929/0.7178)	mem 34602MB
[2025-01-19 13:50:45 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][30/312]	eta 0:03:51 lr 0.001213	time 0.7228 (0.8216)	model_time 0.7224 (0.7707)	loss 2.0469 (2.7472)	grad_norm 1.3795 (1.8526/0.5752)	mem 34604MB
[2025-01-19 13:50:52 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][100/312]	eta 0:02:41 lr 0.001209	time 0.8129 (0.7639)	model_time 0.8128 (0.7473)	loss 3.6761 (3.0482)	grad_norm 2.6907 (1.7867/0.7961)	mem 34602MB
[2025-01-19 13:50:53 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][40/312]	eta 0:03:39 lr 0.001212	time 0.7240 (0.8076)	model_time 0.7236 (0.7689)	loss 3.0505 (2.7849)	grad_norm 2.0301 (1.9326/0.6851)	mem 34604MB
[2025-01-19 13:51:00 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][50/312]	eta 0:03:27 lr 0.001212	time 0.7228 (0.7922)	model_time 0.7227 (0.7611)	loss 3.7311 (2.8327)	grad_norm 3.6515 (2.0085/0.8442)	mem 34604MB
[2025-01-19 13:51:00 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][110/312]	eta 0:02:33 lr 0.001208	time 0.7179 (0.7622)	model_time 0.7177 (0.7471)	loss 3.0462 (3.0557)	grad_norm 2.2744 (1.8000/0.7823)	mem 34602MB
[2025-01-19 13:51:07 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][60/312]	eta 0:03:17 lr 0.001211	time 0.7081 (0.7826)	model_time 0.7080 (0.7565)	loss 3.6068 (2.8437)	grad_norm 2.3021 (1.9589/0.8449)	mem 34604MB
[2025-01-19 13:51:07 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][120/312]	eta 0:02:26 lr 0.001207	time 0.7299 (0.7608)	model_time 0.7298 (0.7469)	loss 2.5439 (3.0525)	grad_norm 0.8330 (1.7915/0.7680)	mem 34602MB
[2025-01-19 13:51:15 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][70/312]	eta 0:03:07 lr 0.001210	time 0.7196 (0.7752)	model_time 0.7192 (0.7528)	loss 3.2380 (2.8563)	grad_norm 1.5573 (1.9622/0.8574)	mem 34604MB
[2025-01-19 13:51:15 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][130/312]	eta 0:02:18 lr 0.001207	time 0.7160 (0.7610)	model_time 0.7157 (0.7482)	loss 2.7608 (3.0463)	grad_norm 0.9119 (1.7469/0.7590)	mem 34602MB
[2025-01-19 13:51:22 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][80/312]	eta 0:02:58 lr 0.001210	time 0.7467 (0.7691)	model_time 0.7462 (0.7494)	loss 3.2481 (2.8778)	grad_norm 1.0337 (1.8970/0.8403)	mem 34604MB
[2025-01-19 13:51:23 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][140/312]	eta 0:02:10 lr 0.001206	time 0.8057 (0.7612)	model_time 0.8056 (0.7492)	loss 3.3090 (3.0525)	grad_norm 1.5770 (1.7332/0.7645)	mem 34602MB
[2025-01-19 13:51:29 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][90/312]	eta 0:02:49 lr 0.001209	time 0.7299 (0.7641)	model_time 0.7295 (0.7465)	loss 3.2554 (2.8882)	grad_norm 2.6336 (1.9296/0.8579)	mem 34604MB
[2025-01-19 13:51:30 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][150/312]	eta 0:02:03 lr 0.001206	time 0.7173 (0.7598)	model_time 0.7168 (0.7486)	loss 3.1647 (3.0480)	grad_norm 0.9628 (1.7155/0.7533)	mem 34602MB
[2025-01-19 13:51:36 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][100/312]	eta 0:02:41 lr 0.001209	time 0.7209 (0.7607)	model_time 0.7204 (0.7448)	loss 3.3657 (2.8940)	grad_norm 1.2320 (1.9118/0.8359)	mem 34604MB
[2025-01-19 13:51:37 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][160/312]	eta 0:01:55 lr 0.001205	time 0.7197 (0.7582)	model_time 0.7192 (0.7477)	loss 2.9270 (3.0452)	grad_norm 4.3259 (1.8026/0.8900)	mem 34602MB
[2025-01-19 13:51:44 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][110/312]	eta 0:02:33 lr 0.001208	time 0.7194 (0.7587)	model_time 0.7193 (0.7442)	loss 3.0038 (2.8905)	grad_norm 2.4017 (1.8802/0.8191)	mem 34604MB
[2025-01-19 13:51:45 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][170/312]	eta 0:01:47 lr 0.001204	time 0.7163 (0.7575)	model_time 0.7161 (0.7476)	loss 3.0600 (3.0426)	grad_norm 1.5316 (1.8517/0.9133)	mem 34602MB
[2025-01-19 13:51:51 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][120/312]	eta 0:02:25 lr 0.001207	time 0.8939 (0.7586)	model_time 0.8934 (0.7452)	loss 3.0727 (2.8904)	grad_norm 2.1605 (1.8549/0.7973)	mem 34604MB
[2025-01-19 13:51:52 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][180/312]	eta 0:01:39 lr 0.001204	time 0.7185 (0.7564)	model_time 0.7180 (0.7470)	loss 3.3175 (3.0229)	grad_norm 2.4706 (1.8379/0.8969)	mem 34602MB
[2025-01-19 13:51:59 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][130/312]	eta 0:02:17 lr 0.001207	time 0.8092 (0.7581)	model_time 0.8088 (0.7457)	loss 2.5873 (2.9178)	grad_norm 2.8888 (1.8443/0.7939)	mem 34604MB
[2025-01-19 13:51:59 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][190/312]	eta 0:01:32 lr 0.001203	time 0.7263 (0.7547)	model_time 0.7262 (0.7458)	loss 2.6796 (3.0152)	grad_norm 1.6628 (1.8363/0.8861)	mem 34602MB
[2025-01-19 13:52:07 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][140/312]	eta 0:02:10 lr 0.001206	time 0.7216 (0.7606)	model_time 0.7214 (0.7491)	loss 3.0155 (2.9325)	grad_norm 1.6200 (1.8429/0.7811)	mem 34604MB
[2025-01-19 13:52:07 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][200/312]	eta 0:01:24 lr 0.001203	time 0.7197 (0.7545)	model_time 0.7192 (0.7460)	loss 3.5090 (3.0108)	grad_norm 1.2873 (1.8253/0.8682)	mem 34602MB
[2025-01-19 13:52:14 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][150/312]	eta 0:02:03 lr 0.001206	time 0.7182 (0.7597)	model_time 0.7178 (0.7489)	loss 3.0082 (2.9322)	grad_norm 1.3667 (1.8369/0.7728)	mem 34604MB
[2025-01-19 13:52:14 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][210/312]	eta 0:01:16 lr 0.001202	time 0.8081 (0.7545)	model_time 0.8080 (0.7464)	loss 3.3031 (3.0159)	grad_norm 1.5959 (1.8079/0.8555)	mem 34602MB
[2025-01-19 13:52:22 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][160/312]	eta 0:01:55 lr 0.001205	time 0.7178 (0.7594)	model_time 0.7174 (0.7493)	loss 2.5061 (2.9126)	grad_norm 3.1521 (1.8479/0.7769)	mem 34604MB
[2025-01-19 13:52:22 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][220/312]	eta 0:01:09 lr 0.001201	time 0.8115 (0.7550)	model_time 0.8114 (0.7473)	loss 3.3309 (3.0218)	grad_norm 1.7218 (1.8092/0.8469)	mem 34602MB
[2025-01-19 13:52:29 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][170/312]	eta 0:01:47 lr 0.001204	time 0.7241 (0.7575)	model_time 0.7236 (0.7479)	loss 3.7631 (2.9327)	grad_norm 1.4906 (1.8605/0.8009)	mem 34604MB
[2025-01-19 13:52:29 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][230/312]	eta 0:01:01 lr 0.001201	time 0.7201 (0.7540)	model_time 0.7196 (0.7466)	loss 3.0167 (3.0225)	grad_norm 1.5579 (1.8082/0.8404)	mem 34602MB
[2025-01-19 13:52:36 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][180/312]	eta 0:01:39 lr 0.001204	time 0.7422 (0.7559)	model_time 0.7417 (0.7469)	loss 3.4599 (2.9435)	grad_norm 1.7658 (1.8479/0.7921)	mem 34604MB
[2025-01-19 13:52:37 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][240/312]	eta 0:00:54 lr 0.001200	time 0.7206 (0.7539)	model_time 0.7205 (0.7467)	loss 2.1974 (3.0324)	grad_norm 2.1945 (1.7880/0.8348)	mem 34602MB
[2025-01-19 13:52:44 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][190/312]	eta 0:01:32 lr 0.001203	time 0.7620 (0.7548)	model_time 0.7619 (0.7462)	loss 3.0280 (2.9480)	grad_norm 1.1966 (1.8334/0.7863)	mem 34604MB
[2025-01-19 13:52:45 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][250/312]	eta 0:00:46 lr 0.001200	time 0.7187 (0.7548)	model_time 0.7185 (0.7479)	loss 3.3110 (3.0413)	grad_norm 1.3513 (1.7763/0.8275)	mem 34602MB
[2025-01-19 13:52:51 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][200/312]	eta 0:01:24 lr 0.001203	time 0.7250 (0.7535)	model_time 0.7246 (0.7453)	loss 3.4423 (2.9566)	grad_norm 0.9841 (1.8090/0.7758)	mem 34604MB
[2025-01-19 13:52:52 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][260/312]	eta 0:00:39 lr 0.001199	time 0.8106 (0.7552)	model_time 0.8104 (0.7486)	loss 2.0688 (3.0348)	grad_norm 1.5211 (1.7592/0.8188)	mem 34602MB
[2025-01-19 13:52:58 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][210/312]	eta 0:01:16 lr 0.001202	time 0.7358 (0.7524)	model_time 0.7354 (0.7446)	loss 3.4005 (2.9584)	grad_norm 1.1357 (1.7782/0.7739)	mem 34604MB
[2025-01-19 13:53:00 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][270/312]	eta 0:00:31 lr 0.001198	time 0.7176 (0.7547)	model_time 0.7171 (0.7483)	loss 2.9794 (3.0294)	grad_norm 0.9799 (1.7493/0.8096)	mem 34602MB
[2025-01-19 13:53:05 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][220/312]	eta 0:01:09 lr 0.001201	time 0.7240 (0.7511)	model_time 0.7239 (0.7436)	loss 2.4590 (2.9626)	grad_norm 1.0218 (1.7702/0.7634)	mem 34604MB
[2025-01-19 13:53:07 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][280/312]	eta 0:00:24 lr 0.001198	time 0.7178 (0.7538)	model_time 0.7173 (0.7477)	loss 2.6090 (3.0350)	grad_norm 1.3136 (1.7460/0.8032)	mem 34602MB
[2025-01-19 13:53:13 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][230/312]	eta 0:01:01 lr 0.001201	time 0.7262 (0.7505)	model_time 0.7258 (0.7433)	loss 2.8196 (2.9597)	grad_norm 3.4953 (1.7937/0.7653)	mem 34604MB
[2025-01-19 13:53:15 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][290/312]	eta 0:00:16 lr 0.001197	time 0.7191 (0.7537)	model_time 0.7189 (0.7477)	loss 3.1940 (3.0299)	grad_norm 1.7161 (1.7470/0.7921)	mem 34602MB
[2025-01-19 13:53:20 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][240/312]	eta 0:00:54 lr 0.001200	time 0.8281 (0.7508)	model_time 0.8279 (0.7439)	loss 3.2821 (2.9656)	grad_norm 3.4111 (1.8195/0.7951)	mem 34604MB
[2025-01-19 13:53:22 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][300/312]	eta 0:00:09 lr 0.001196	time 0.7120 (0.7530)	model_time 0.7119 (0.7472)	loss 3.0858 (3.0298)	grad_norm 1.9762 (1.7503/0.7853)	mem 34602MB
[2025-01-19 13:53:28 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][250/312]	eta 0:00:46 lr 0.001200	time 0.7413 (0.7505)	model_time 0.7409 (0.7438)	loss 3.3544 (2.9775)	grad_norm 2.8111 (1.8276/0.7886)	mem 34604MB
[2025-01-19 13:53:29 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][310/312]	eta 0:00:01 lr 0.001196	time 0.7138 (0.7517)	model_time 0.7137 (0.7461)	loss 3.4691 (3.0316)	grad_norm 1.6404 (1.7502/0.7837)	mem 34602MB
[2025-01-19 13:53:30 internimage_b_1k_224] (main.py 519): INFO EPOCH 190 training takes 0:03:54
[2025-01-19 13:53:30 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_190.pth saving......
[2025-01-19 13:53:33 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_190.pth saved !!!
[2025-01-19 13:53:36 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][260/312]	eta 0:00:39 lr 0.001199	time 0.7259 (0.7518)	model_time 0.7257 (0.7455)	loss 3.4105 (2.9771)	grad_norm 1.9547 (1.8173/0.7808)	mem 34604MB
[2025-01-19 13:53:41 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.554 (7.554)	Loss 0.7435 (0.7435)	Acc@1 84.814 (84.814)	Acc@5 97.290 (97.290)	Mem 34602MB
[2025-01-19 13:53:43 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][270/312]	eta 0:00:31 lr 0.001198	time 0.7233 (0.7517)	model_time 0.7229 (0.7455)	loss 3.3905 (2.9692)	grad_norm 1.7570 (1.8225/0.7791)	mem 34604MB
[2025-01-19 13:53:44 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.948)	Loss 1.0100 (0.8522)	Acc@1 77.100 (82.433)	Acc@5 95.093 (96.274)	Mem 34602MB
[2025-01-19 13:53:44 internimage_b_1k_224] (main.py 575): INFO [Epoch:190] * Acc@1 82.260 Acc@5 96.291
[2025-01-19 13:53:44 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.3%
[2025-01-19 13:53:44 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 13:53:47 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 13:53:47 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.26%
[2025-01-19 13:53:51 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][280/312]	eta 0:00:24 lr 0.001198	time 0.7299 (0.7516)	model_time 0.7295 (0.7456)	loss 2.5305 (2.9700)	grad_norm 2.8102 (1.8359/0.7822)	mem 34604MB
[2025-01-19 13:53:55 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.372 (7.372)	Loss 0.6883 (0.6883)	Acc@1 85.059 (85.059)	Acc@5 97.925 (97.925)	Mem 34602MB
[2025-01-19 13:53:57 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.183 (0.937)	Loss 0.9488 (0.8049)	Acc@1 78.760 (82.730)	Acc@5 94.995 (96.429)	Mem 34602MB
[2025-01-19 13:53:58 internimage_b_1k_224] (main.py 575): INFO [Epoch:190] * Acc@1 82.576 Acc@5 96.473
[2025-01-19 13:53:58 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.6%
[2025-01-19 13:53:58 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:53:58 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][290/312]	eta 0:00:16 lr 0.001197	time 0.7205 (0.7509)	model_time 0.7203 (0.7451)	loss 2.8872 (2.9760)	grad_norm 2.2616 (1.8289/0.7768)	mem 34604MB
[2025-01-19 13:54:01 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:54:01 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.58%
[2025-01-19 13:54:04 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][0/312]	eta 0:10:54 lr 0.001196	time 2.0967 (2.0967)	model_time 0.7385 (0.7385)	loss 2.8328 (2.8328)	grad_norm 2.1399 (2.1399/0.0000)	mem 34602MB
[2025-01-19 13:54:05 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][300/312]	eta 0:00:08 lr 0.001196	time 0.7149 (0.7499)	model_time 0.7148 (0.7443)	loss 3.1968 (2.9806)	grad_norm 1.7497 (1.8134/0.7708)	mem 34604MB
[2025-01-19 13:54:11 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][10/312]	eta 0:04:23 lr 0.001195	time 0.7477 (0.8709)	model_time 0.7476 (0.7471)	loss 3.3179 (3.1167)	grad_norm 1.6282 (1.7586/0.4142)	mem 34602MB
[2025-01-19 13:54:12 internimage_b_1k_224] (main.py 510): INFO Train: [190/300][310/312]	eta 0:00:01 lr 0.001196	time 0.7209 (0.7490)	model_time 0.7208 (0.7436)	loss 3.3042 (2.9758)	grad_norm 1.3650 (1.7910/0.7698)	mem 34604MB
[2025-01-19 13:54:13 internimage_b_1k_224] (main.py 519): INFO EPOCH 190 training takes 0:03:53
[2025-01-19 13:54:13 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_190.pth saving......
[2025-01-19 13:54:16 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_190.pth saved !!!
[2025-01-19 13:54:19 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][20/312]	eta 0:04:00 lr 0.001195	time 0.7414 (0.8234)	model_time 0.7412 (0.7583)	loss 3.0682 (2.9261)	grad_norm 1.1359 (1.5245/0.4360)	mem 34602MB
[2025-01-19 13:54:24 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.418 (7.418)	Loss 0.7315 (0.7315)	Acc@1 84.985 (84.985)	Acc@5 97.412 (97.412)	Mem 34604MB
[2025-01-19 13:54:26 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][30/312]	eta 0:03:45 lr 0.001194	time 0.7178 (0.8009)	model_time 0.7177 (0.7566)	loss 3.7906 (3.0069)	grad_norm 3.3503 (1.7016/0.6204)	mem 34602MB
[2025-01-19 13:54:27 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.971)	Loss 1.0110 (0.8529)	Acc@1 77.295 (82.351)	Acc@5 95.044 (96.205)	Mem 34604MB
[2025-01-19 13:54:27 internimage_b_1k_224] (main.py 575): INFO [Epoch:190] * Acc@1 82.164 Acc@5 96.227
[2025-01-19 13:54:27 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.2%
[2025-01-19 13:54:27 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.25%
[2025-01-19 13:54:34 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][40/312]	eta 0:03:34 lr 0.001193	time 0.7216 (0.7888)	model_time 0.7214 (0.7552)	loss 3.8801 (3.0561)	grad_norm 2.7413 (1.8305/0.7982)	mem 34602MB
[2025-01-19 13:54:36 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.064 (9.064)	Loss 0.6856 (0.6856)	Acc@1 85.254 (85.254)	Acc@5 97.974 (97.974)	Mem 34604MB
[2025-01-19 13:54:41 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.242)	Loss 0.9489 (0.8035)	Acc@1 79.028 (82.835)	Acc@5 94.971 (96.409)	Mem 34604MB
[2025-01-19 13:54:41 internimage_b_1k_224] (main.py 575): INFO [Epoch:190] * Acc@1 82.658 Acc@5 96.463
[2025-01-19 13:54:41 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.7%
[2025-01-19 13:54:41 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:54:41 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][50/312]	eta 0:03:24 lr 0.001193	time 0.8337 (0.7812)	model_time 0.8333 (0.7542)	loss 3.3101 (2.9939)	grad_norm 1.9067 (1.8446/0.7616)	mem 34602MB
[2025-01-19 13:54:45 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:54:45 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.66%
[2025-01-19 13:54:47 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][0/312]	eta 0:10:40 lr 0.001196	time 2.0532 (2.0532)	model_time 0.7424 (0.7424)	loss 2.8640 (2.8640)	grad_norm 1.5756 (1.5756/0.0000)	mem 34604MB
[2025-01-19 13:54:49 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][60/312]	eta 0:03:16 lr 0.001192	time 0.8191 (0.7793)	model_time 0.8189 (0.7567)	loss 2.6464 (2.9675)	grad_norm 1.5125 (1.8312/0.7166)	mem 34602MB
[2025-01-19 13:54:54 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][10/312]	eta 0:04:18 lr 0.001195	time 0.7220 (0.8545)	model_time 0.7219 (0.7350)	loss 2.1800 (3.0172)	grad_norm 1.8517 (1.6057/0.5478)	mem 34604MB
[2025-01-19 13:54:56 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][70/312]	eta 0:03:07 lr 0.001192	time 0.7212 (0.7750)	model_time 0.7211 (0.7556)	loss 3.1740 (2.9360)	grad_norm 2.8862 (1.8884/0.7515)	mem 34602MB
[2025-01-19 13:55:02 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][20/312]	eta 0:03:54 lr 0.001195	time 0.8213 (0.8025)	model_time 0.8209 (0.7397)	loss 3.7047 (3.0583)	grad_norm 1.0407 (1.6247/0.5893)	mem 34604MB
[2025-01-19 13:55:04 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][80/312]	eta 0:02:59 lr 0.001191	time 0.8143 (0.7720)	model_time 0.8141 (0.7549)	loss 3.4808 (2.9439)	grad_norm 1.7888 (1.9002/0.7461)	mem 34602MB
[2025-01-19 13:55:09 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][30/312]	eta 0:03:39 lr 0.001194	time 0.7484 (0.7801)	model_time 0.7480 (0.7375)	loss 3.8035 (3.1069)	grad_norm 0.6884 (1.9228/0.9469)	mem 34604MB
[2025-01-19 13:55:11 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][90/312]	eta 0:02:50 lr 0.001190	time 0.7142 (0.7693)	model_time 0.7137 (0.7540)	loss 3.6247 (2.9503)	grad_norm 1.0697 (1.8620/0.7327)	mem 34602MB
[2025-01-19 13:55:16 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][40/312]	eta 0:03:29 lr 0.001193	time 0.7103 (0.7705)	model_time 0.7102 (0.7382)	loss 3.3801 (3.0797)	grad_norm 3.2685 (2.1204/1.0538)	mem 34604MB
[2025-01-19 13:55:19 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][100/312]	eta 0:02:42 lr 0.001190	time 0.8129 (0.7665)	model_time 0.8128 (0.7527)	loss 2.9904 (2.9158)	grad_norm 1.5076 (1.8613/0.7205)	mem 34602MB
[2025-01-19 13:55:24 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][50/312]	eta 0:03:21 lr 0.001193	time 0.7178 (0.7689)	model_time 0.7174 (0.7428)	loss 2.1542 (3.0329)	grad_norm 1.7299 (2.0620/0.9938)	mem 34604MB
[2025-01-19 13:55:26 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][110/312]	eta 0:02:34 lr 0.001189	time 0.7169 (0.7642)	model_time 0.7168 (0.7516)	loss 3.0024 (2.9128)	grad_norm 2.0442 (1.8852/0.7074)	mem 34602MB
[2025-01-19 13:55:32 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][60/312]	eta 0:03:13 lr 0.001192	time 0.7271 (0.7666)	model_time 0.7269 (0.7447)	loss 2.7701 (3.0270)	grad_norm 1.4241 (1.9594/0.9611)	mem 34604MB
[2025-01-19 13:55:33 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][120/312]	eta 0:02:26 lr 0.001189	time 0.7264 (0.7609)	model_time 0.7259 (0.7493)	loss 3.0074 (2.9273)	grad_norm 1.7104 (1.8578/0.6931)	mem 34602MB
[2025-01-19 13:55:40 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][70/312]	eta 0:03:06 lr 0.001192	time 0.7128 (0.7707)	model_time 0.7123 (0.7518)	loss 2.1803 (3.0041)	grad_norm 1.1480 (1.9487/0.9228)	mem 34604MB
[2025-01-19 13:55:41 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][130/312]	eta 0:02:18 lr 0.001188	time 0.7443 (0.7607)	model_time 0.7441 (0.7499)	loss 2.2400 (2.9351)	grad_norm 1.9615 (1.8447/0.6999)	mem 34602MB
[2025-01-19 13:55:47 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][80/312]	eta 0:02:57 lr 0.001191	time 0.7254 (0.7670)	model_time 0.7252 (0.7504)	loss 2.3915 (2.9906)	grad_norm 1.2358 (1.8967/0.8905)	mem 34604MB
[2025-01-19 13:55:49 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][140/312]	eta 0:02:10 lr 0.001187	time 0.7235 (0.7601)	model_time 0.7230 (0.7502)	loss 2.7938 (2.9267)	grad_norm 2.7342 (1.8884/0.7754)	mem 34602MB
[2025-01-19 13:55:54 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][90/312]	eta 0:02:49 lr 0.001190	time 0.8023 (0.7652)	model_time 0.8021 (0.7504)	loss 3.4339 (2.9597)	grad_norm 2.5281 (1.8480/0.8659)	mem 34604MB
[2025-01-19 13:55:56 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][150/312]	eta 0:02:02 lr 0.001187	time 0.7192 (0.7591)	model_time 0.7188 (0.7497)	loss 3.6745 (2.9334)	grad_norm 2.7270 (1.9011/0.7730)	mem 34602MB
[2025-01-19 13:56:02 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][100/312]	eta 0:02:41 lr 0.001190	time 0.7242 (0.7615)	model_time 0.7241 (0.7482)	loss 3.3978 (2.9662)	grad_norm 1.8425 (1.8346/0.8361)	mem 34604MB
[2025-01-19 13:56:04 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][160/312]	eta 0:01:55 lr 0.001186	time 0.7164 (0.7598)	model_time 0.7163 (0.7510)	loss 3.1577 (2.9453)	grad_norm 3.0952 (1.9261/0.8028)	mem 34602MB
[2025-01-19 13:56:09 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][110/312]	eta 0:02:33 lr 0.001189	time 0.7225 (0.7581)	model_time 0.7224 (0.7460)	loss 2.0314 (2.9622)	grad_norm 2.7204 (1.8261/0.8145)	mem 34604MB
[2025-01-19 13:56:11 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][170/312]	eta 0:01:47 lr 0.001186	time 0.8104 (0.7588)	model_time 0.8102 (0.7505)	loss 2.1322 (2.9435)	grad_norm 0.8501 (1.9011/0.7933)	mem 34602MB
[2025-01-19 13:56:16 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][120/312]	eta 0:02:25 lr 0.001189	time 0.7274 (0.7557)	model_time 0.7269 (0.7445)	loss 3.1320 (2.9846)	grad_norm 2.0615 (1.8823/0.8614)	mem 34604MB
[2025-01-19 13:56:19 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][180/312]	eta 0:01:40 lr 0.001185	time 0.8138 (0.7593)	model_time 0.8132 (0.7514)	loss 2.6434 (2.9431)	grad_norm 2.8647 (1.9081/0.8064)	mem 34602MB
[2025-01-19 13:56:24 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][130/312]	eta 0:02:17 lr 0.001188	time 0.7268 (0.7540)	model_time 0.7264 (0.7436)	loss 3.2561 (2.9671)	grad_norm 1.5343 (1.8730/0.8593)	mem 34604MB
[2025-01-19 13:56:26 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][190/312]	eta 0:01:32 lr 0.001184	time 0.7160 (0.7592)	model_time 0.7159 (0.7517)	loss 3.1301 (2.9434)	grad_norm 1.4933 (1.9047/0.8131)	mem 34602MB
[2025-01-19 13:56:31 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][140/312]	eta 0:02:09 lr 0.001187	time 0.7631 (0.7523)	model_time 0.7630 (0.7427)	loss 3.3085 (2.9856)	grad_norm 1.2935 (1.8243/0.8546)	mem 34604MB
[2025-01-19 13:56:34 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][200/312]	eta 0:01:24 lr 0.001184	time 0.7182 (0.7580)	model_time 0.7178 (0.7509)	loss 2.8558 (2.9358)	grad_norm 1.8576 (1.8982/0.7990)	mem 34602MB
[2025-01-19 13:56:38 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][150/312]	eta 0:02:01 lr 0.001187	time 0.7226 (0.7509)	model_time 0.7222 (0.7419)	loss 3.6048 (2.9868)	grad_norm 1.8202 (1.8165/0.8351)	mem 34604MB
[2025-01-19 13:56:41 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][210/312]	eta 0:01:17 lr 0.001183	time 0.8043 (0.7578)	model_time 0.8041 (0.7510)	loss 3.2838 (2.9421)	grad_norm 1.7417 (1.9076/0.7888)	mem 34602MB
[2025-01-19 13:56:46 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][160/312]	eta 0:01:53 lr 0.001186	time 0.7178 (0.7499)	model_time 0.7174 (0.7414)	loss 3.6976 (2.9761)	grad_norm 1.3705 (1.8682/0.8756)	mem 34604MB
[2025-01-19 13:56:49 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][220/312]	eta 0:01:09 lr 0.001182	time 0.8081 (0.7572)	model_time 0.8080 (0.7507)	loss 2.1313 (2.9564)	grad_norm 1.1106 (1.8836/0.7813)	mem 34602MB
[2025-01-19 13:56:53 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][170/312]	eta 0:01:46 lr 0.001186	time 0.7170 (0.7497)	model_time 0.7168 (0.7416)	loss 3.7939 (2.9861)	grad_norm 0.9706 (1.8639/0.8647)	mem 34604MB
[2025-01-19 13:56:56 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][230/312]	eta 0:01:01 lr 0.001182	time 0.7201 (0.7560)	model_time 0.7197 (0.7498)	loss 3.0001 (2.9568)	grad_norm 1.1252 (1.8610/0.7762)	mem 34602MB
[2025-01-19 13:57:01 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][180/312]	eta 0:01:38 lr 0.001185	time 0.7565 (0.7499)	model_time 0.7564 (0.7423)	loss 3.3763 (2.9960)	grad_norm 1.5409 (1.8565/0.8451)	mem 34604MB
[2025-01-19 13:57:03 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][240/312]	eta 0:00:54 lr 0.001181	time 0.7108 (0.7547)	model_time 0.7106 (0.7487)	loss 1.8600 (2.9576)	grad_norm 1.7072 (1.8403/0.7695)	mem 34602MB
[2025-01-19 13:57:08 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][190/312]	eta 0:01:31 lr 0.001184	time 0.7178 (0.7518)	model_time 0.7174 (0.7446)	loss 3.1182 (3.0000)	grad_norm 1.4798 (1.8379/0.8316)	mem 34604MB
[2025-01-19 13:57:11 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][250/312]	eta 0:00:46 lr 0.001181	time 0.7746 (0.7544)	model_time 0.7744 (0.7486)	loss 2.8304 (2.9548)	grad_norm 1.3602 (1.8190/0.7623)	mem 34602MB
[2025-01-19 13:57:16 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][200/312]	eta 0:01:24 lr 0.001184	time 0.7194 (0.7515)	model_time 0.7190 (0.7446)	loss 2.9981 (3.0021)	grad_norm 1.3930 (1.8238/0.8246)	mem 34604MB
[2025-01-19 13:57:18 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][260/312]	eta 0:00:39 lr 0.001180	time 0.7243 (0.7545)	model_time 0.7238 (0.7489)	loss 1.8407 (2.9456)	grad_norm 1.9632 (1.8110/0.7561)	mem 34602MB
[2025-01-19 13:57:23 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][210/312]	eta 0:01:16 lr 0.001183	time 0.8082 (0.7515)	model_time 0.8078 (0.7449)	loss 3.3758 (3.0073)	grad_norm 1.2205 (1.8125/0.8214)	mem 34604MB
[2025-01-19 13:57:26 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][270/312]	eta 0:00:31 lr 0.001179	time 0.7245 (0.7538)	model_time 0.7243 (0.7484)	loss 2.2989 (2.9560)	grad_norm 2.6374 (1.8193/0.7576)	mem 34602MB
[2025-01-19 13:57:31 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][220/312]	eta 0:01:09 lr 0.001182	time 0.7265 (0.7505)	model_time 0.7260 (0.7443)	loss 2.4608 (3.0020)	grad_norm 1.5213 (1.8133/0.8130)	mem 34604MB
[2025-01-19 13:57:33 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][280/312]	eta 0:00:24 lr 0.001179	time 0.7167 (0.7540)	model_time 0.7165 (0.7488)	loss 3.1803 (2.9618)	grad_norm 1.5308 (1.8272/0.7697)	mem 34602MB
[2025-01-19 13:57:38 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][230/312]	eta 0:01:01 lr 0.001182	time 0.7325 (0.7495)	model_time 0.7323 (0.7435)	loss 2.5280 (3.0035)	grad_norm 1.1917 (1.8041/0.8046)	mem 34604MB
[2025-01-19 13:57:41 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][290/312]	eta 0:00:16 lr 0.001178	time 0.8162 (0.7536)	model_time 0.8160 (0.7486)	loss 2.8100 (2.9569)	grad_norm 1.5957 (1.8196/0.7644)	mem 34602MB
[2025-01-19 13:57:45 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][240/312]	eta 0:00:53 lr 0.001181	time 0.7186 (0.7485)	model_time 0.7182 (0.7427)	loss 2.5787 (3.0026)	grad_norm 1.1357 (1.8263/0.8078)	mem 34604MB
[2025-01-19 13:57:48 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][300/312]	eta 0:00:09 lr 0.001178	time 0.7124 (0.7536)	model_time 0.7123 (0.7488)	loss 3.3733 (2.9578)	grad_norm 3.7794 (1.8460/0.7878)	mem 34602MB
[2025-01-19 13:57:53 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][250/312]	eta 0:00:46 lr 0.001181	time 0.7092 (0.7478)	model_time 0.7087 (0.7422)	loss 3.5941 (3.0079)	grad_norm 1.9919 (1.8435/0.8005)	mem 34604MB
[2025-01-19 13:57:56 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][310/312]	eta 0:00:01 lr 0.001177	time 0.8280 (0.7535)	model_time 0.8279 (0.7488)	loss 3.6090 (2.9644)	grad_norm 1.9106 (1.8676/0.7985)	mem 34602MB
[2025-01-19 13:57:57 internimage_b_1k_224] (main.py 519): INFO EPOCH 191 training takes 0:03:55
[2025-01-19 13:57:57 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_191.pth saving......
[2025-01-19 13:58:00 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_191.pth saved !!!
[2025-01-19 13:58:00 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][260/312]	eta 0:00:38 lr 0.001180	time 0.7236 (0.7469)	model_time 0.7235 (0.7415)	loss 3.5073 (3.0090)	grad_norm 2.5556 (1.8367/0.7938)	mem 34604MB
[2025-01-19 13:58:07 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][270/312]	eta 0:00:31 lr 0.001179	time 0.7275 (0.7465)	model_time 0.7271 (0.7412)	loss 3.8099 (3.0124)	grad_norm 1.8014 (1.8405/0.7832)	mem 34604MB
[2025-01-19 13:58:08 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.603 (7.603)	Loss 0.7813 (0.7813)	Acc@1 85.010 (85.010)	Acc@5 97.583 (97.583)	Mem 34602MB
[2025-01-19 13:58:11 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.969)	Loss 1.0261 (0.8791)	Acc@1 78.125 (82.566)	Acc@5 95.044 (96.320)	Mem 34602MB
[2025-01-19 13:58:11 internimage_b_1k_224] (main.py 575): INFO [Epoch:191] * Acc@1 82.466 Acc@5 96.339
[2025-01-19 13:58:11 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.5%
[2025-01-19 13:58:11 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 13:58:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 13:58:14 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.47%
[2025-01-19 13:58:14 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][280/312]	eta 0:00:23 lr 0.001179	time 0.7214 (0.7460)	model_time 0.7209 (0.7410)	loss 2.6750 (3.0093)	grad_norm 1.4729 (1.8345/0.7771)	mem 34604MB
[2025-01-19 13:58:22 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.365 (7.365)	Loss 0.6894 (0.6894)	Acc@1 85.132 (85.132)	Acc@5 97.925 (97.925)	Mem 34602MB
[2025-01-19 13:58:22 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][290/312]	eta 0:00:16 lr 0.001178	time 0.7433 (0.7461)	model_time 0.7431 (0.7412)	loss 2.6754 (3.0110)	grad_norm 2.4017 (1.8460/0.7849)	mem 34604MB
[2025-01-19 13:58:25 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.958)	Loss 0.9487 (0.8052)	Acc@1 78.687 (82.773)	Acc@5 95.044 (96.438)	Mem 34602MB
[2025-01-19 13:58:25 internimage_b_1k_224] (main.py 575): INFO [Epoch:191] * Acc@1 82.626 Acc@5 96.481
[2025-01-19 13:58:25 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.6%
[2025-01-19 13:58:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:58:29 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:58:29 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.63%
[2025-01-19 13:58:29 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][300/312]	eta 0:00:08 lr 0.001178	time 0.7142 (0.7464)	model_time 0.7141 (0.7416)	loss 3.6130 (3.0178)	grad_norm 2.2590 (1.8361/0.7791)	mem 34604MB
[2025-01-19 13:58:31 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][0/312]	eta 0:11:00 lr 0.001177	time 2.1167 (2.1167)	model_time 0.7341 (0.7341)	loss 2.3410 (2.3410)	grad_norm 2.5269 (2.5269/0.0000)	mem 34602MB
[2025-01-19 13:58:37 internimage_b_1k_224] (main.py 510): INFO Train: [191/300][310/312]	eta 0:00:01 lr 0.001177	time 0.7114 (0.7473)	model_time 0.7113 (0.7427)	loss 3.2502 (3.0175)	grad_norm 1.1319 (1.8333/0.7767)	mem 34604MB
[2025-01-19 13:58:38 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][10/312]	eta 0:04:21 lr 0.001176	time 0.7334 (0.8646)	model_time 0.7330 (0.7385)	loss 3.1609 (2.7116)	grad_norm 1.1547 (2.0144/0.7352)	mem 34602MB
[2025-01-19 13:58:38 internimage_b_1k_224] (main.py 519): INFO EPOCH 191 training takes 0:03:53
[2025-01-19 13:58:38 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_191.pth saving......
[2025-01-19 13:58:41 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_191.pth saved !!!
[2025-01-19 13:58:46 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][20/312]	eta 0:03:57 lr 0.001176	time 0.7315 (0.8128)	model_time 0.7311 (0.7466)	loss 2.3863 (2.8526)	grad_norm 0.9560 (1.6490/0.6965)	mem 34602MB
[2025-01-19 13:58:49 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.268 (7.268)	Loss 0.7745 (0.7745)	Acc@1 84.595 (84.595)	Acc@5 97.827 (97.827)	Mem 34604MB
[2025-01-19 13:58:52 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.953)	Loss 1.0099 (0.8720)	Acc@1 78.174 (82.227)	Acc@5 94.995 (96.300)	Mem 34604MB
[2025-01-19 13:58:52 internimage_b_1k_224] (main.py 575): INFO [Epoch:191] * Acc@1 82.110 Acc@5 96.315
[2025-01-19 13:58:52 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.1%
[2025-01-19 13:58:52 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.25%
[2025-01-19 13:58:53 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][30/312]	eta 0:03:43 lr 0.001175	time 0.7167 (0.7920)	model_time 0.7165 (0.7470)	loss 2.2733 (2.8605)	grad_norm 1.0953 (1.4999/0.6435)	mem 34602MB
[2025-01-19 13:59:00 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][40/312]	eta 0:03:31 lr 0.001175	time 0.7227 (0.7793)	model_time 0.7225 (0.7453)	loss 3.0421 (2.9444)	grad_norm 1.3872 (1.4481/0.6322)	mem 34602MB
[2025-01-19 13:59:01 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.294 (9.294)	Loss 0.6866 (0.6866)	Acc@1 85.254 (85.254)	Acc@5 97.949 (97.949)	Mem 34604MB
[2025-01-19 13:59:06 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.267)	Loss 0.9485 (0.8038)	Acc@1 79.053 (82.839)	Acc@5 94.946 (96.402)	Mem 34604MB
[2025-01-19 13:59:06 internimage_b_1k_224] (main.py 575): INFO [Epoch:191] * Acc@1 82.660 Acc@5 96.461
[2025-01-19 13:59:06 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.7%
[2025-01-19 13:59:06 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 13:59:08 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][50/312]	eta 0:03:21 lr 0.001174	time 0.7212 (0.7690)	model_time 0.7211 (0.7415)	loss 3.1036 (2.9288)	grad_norm 1.8717 (1.5099/0.6950)	mem 34602MB
[2025-01-19 13:59:10 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 13:59:10 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.66%
[2025-01-19 13:59:12 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][0/312]	eta 0:10:56 lr 0.001177	time 2.1052 (2.1052)	model_time 0.7501 (0.7501)	loss 3.2913 (3.2913)	grad_norm 1.1193 (1.1193/0.0000)	mem 34604MB
[2025-01-19 13:59:15 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][60/312]	eta 0:03:12 lr 0.001173	time 0.7183 (0.7658)	model_time 0.7179 (0.7426)	loss 3.5768 (2.9562)	grad_norm 2.3379 (1.5646/0.6873)	mem 34602MB
[2025-01-19 13:59:20 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][10/312]	eta 0:04:25 lr 0.001176	time 0.7179 (0.8790)	model_time 0.7178 (0.7555)	loss 2.6688 (3.1262)	grad_norm 2.0329 (2.1954/0.8673)	mem 34604MB
[2025-01-19 13:59:23 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][70/312]	eta 0:03:05 lr 0.001173	time 0.7156 (0.7653)	model_time 0.7155 (0.7453)	loss 3.0238 (2.9894)	grad_norm 0.9899 (1.6536/0.8273)	mem 34602MB
[2025-01-19 13:59:27 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][20/312]	eta 0:03:59 lr 0.001176	time 0.7191 (0.8187)	model_time 0.7187 (0.7538)	loss 2.2371 (2.9503)	grad_norm 1.1441 (1.8601/0.8191)	mem 34604MB
[2025-01-19 13:59:30 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][80/312]	eta 0:02:56 lr 0.001172	time 0.7343 (0.7627)	model_time 0.7339 (0.7451)	loss 3.4089 (2.9771)	grad_norm 1.7375 (1.6691/0.8528)	mem 34602MB
[2025-01-19 13:59:35 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][30/312]	eta 0:03:43 lr 0.001175	time 0.7185 (0.7919)	model_time 0.7183 (0.7478)	loss 2.0369 (2.9899)	grad_norm 1.1094 (1.7760/0.7729)	mem 34604MB
[2025-01-19 13:59:38 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][90/312]	eta 0:02:49 lr 0.001172	time 0.7952 (0.7620)	model_time 0.7948 (0.7463)	loss 3.6128 (2.9930)	grad_norm 1.0641 (1.6808/0.8655)	mem 34602MB
[2025-01-19 13:59:42 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][40/312]	eta 0:03:31 lr 0.001175	time 0.7429 (0.7772)	model_time 0.7425 (0.7438)	loss 3.1361 (2.9388)	grad_norm 2.0353 (1.7069/0.7028)	mem 34604MB
[2025-01-19 13:59:45 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][100/312]	eta 0:02:41 lr 0.001171	time 0.7380 (0.7605)	model_time 0.7378 (0.7463)	loss 2.1015 (3.0048)	grad_norm 1.0876 (1.6383/0.8355)	mem 34602MB
[2025-01-19 13:59:49 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][50/312]	eta 0:03:21 lr 0.001174	time 0.7378 (0.7678)	model_time 0.7374 (0.7409)	loss 2.8950 (2.9299)	grad_norm 3.6781 (1.7853/0.7426)	mem 34604MB
[2025-01-19 13:59:53 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][110/312]	eta 0:02:33 lr 0.001170	time 0.7174 (0.7598)	model_time 0.7170 (0.7469)	loss 3.4015 (2.9944)	grad_norm 1.5214 (1.6434/0.8201)	mem 34602MB
[2025-01-19 13:59:57 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][60/312]	eta 0:03:11 lr 0.001173	time 0.7074 (0.7613)	model_time 0.7069 (0.7387)	loss 2.5058 (2.9234)	grad_norm 2.0590 (1.8107/0.7449)	mem 34604MB
[2025-01-19 14:00:00 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][120/312]	eta 0:02:25 lr 0.001170	time 0.7221 (0.7595)	model_time 0.7219 (0.7477)	loss 3.0008 (2.9908)	grad_norm 2.6115 (1.6645/0.8005)	mem 34602MB
[2025-01-19 14:00:04 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][70/312]	eta 0:03:03 lr 0.001173	time 0.7260 (0.7566)	model_time 0.7255 (0.7371)	loss 3.3248 (2.9725)	grad_norm 1.5732 (1.7924/0.7438)	mem 34604MB
[2025-01-19 14:00:08 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][130/312]	eta 0:02:17 lr 0.001169	time 0.7329 (0.7581)	model_time 0.7327 (0.7471)	loss 3.2578 (2.9924)	grad_norm 2.1430 (1.6768/0.7970)	mem 34602MB
[2025-01-19 14:00:11 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][80/312]	eta 0:02:54 lr 0.001172	time 0.7264 (0.7537)	model_time 0.7260 (0.7366)	loss 3.3759 (2.9773)	grad_norm 0.7717 (1.7403/0.7255)	mem 34604MB
[2025-01-19 14:00:15 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][140/312]	eta 0:02:10 lr 0.001169	time 0.7224 (0.7571)	model_time 0.7222 (0.7469)	loss 2.8332 (2.9980)	grad_norm 1.6071 (1.6640/0.7730)	mem 34602MB
[2025-01-19 14:00:18 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][90/312]	eta 0:02:46 lr 0.001172	time 0.7464 (0.7516)	model_time 0.7460 (0.7363)	loss 2.0680 (2.9969)	grad_norm 1.1058 (1.6671/0.7169)	mem 34604MB
[2025-01-19 14:00:23 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][150/312]	eta 0:02:02 lr 0.001168	time 0.7173 (0.7568)	model_time 0.7169 (0.7473)	loss 3.5621 (3.0189)	grad_norm 2.3611 (1.7021/0.7940)	mem 34602MB
[2025-01-19 14:00:26 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][100/312]	eta 0:02:39 lr 0.001171	time 0.7207 (0.7521)	model_time 0.7203 (0.7383)	loss 2.7125 (2.9977)	grad_norm 1.7563 (1.6719/0.7002)	mem 34604MB
[2025-01-19 14:00:30 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][160/312]	eta 0:01:54 lr 0.001167	time 0.7286 (0.7555)	model_time 0.7282 (0.7465)	loss 2.7166 (3.0215)	grad_norm 1.8259 (1.7005/0.7846)	mem 34602MB
[2025-01-19 14:00:34 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][110/312]	eta 0:02:32 lr 0.001170	time 0.7945 (0.7537)	model_time 0.7943 (0.7411)	loss 3.3553 (2.9742)	grad_norm 1.1253 (1.6520/0.6815)	mem 34604MB
[2025-01-19 14:00:37 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][170/312]	eta 0:01:47 lr 0.001167	time 0.7406 (0.7539)	model_time 0.7404 (0.7454)	loss 3.7286 (3.0110)	grad_norm 2.5282 (1.7173/0.7764)	mem 34602MB
[2025-01-19 14:00:42 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][120/312]	eta 0:02:25 lr 0.001170	time 0.8552 (0.7559)	model_time 0.8548 (0.7443)	loss 3.1544 (2.9702)	grad_norm 1.4576 (1.6745/0.6877)	mem 34604MB
[2025-01-19 14:00:45 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][180/312]	eta 0:01:39 lr 0.001166	time 0.8049 (0.7536)	model_time 0.8045 (0.7456)	loss 3.1117 (3.0205)	grad_norm 2.9446 (1.7859/0.8237)	mem 34602MB
[2025-01-19 14:00:49 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][130/312]	eta 0:02:17 lr 0.001169	time 0.7157 (0.7558)	model_time 0.7155 (0.7451)	loss 3.5902 (2.9842)	grad_norm 2.5096 (1.6844/0.6712)	mem 34604MB
[2025-01-19 14:00:52 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][190/312]	eta 0:01:31 lr 0.001166	time 0.7199 (0.7538)	model_time 0.7195 (0.7461)	loss 3.5986 (3.0254)	grad_norm 1.2424 (1.7925/0.8103)	mem 34602MB
[2025-01-19 14:00:57 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][140/312]	eta 0:02:09 lr 0.001169	time 0.7242 (0.7554)	model_time 0.7238 (0.7454)	loss 3.3547 (2.9664)	grad_norm 2.3971 (1.7445/0.7501)	mem 34604MB
[2025-01-19 14:01:00 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][200/312]	eta 0:01:24 lr 0.001165	time 0.7169 (0.7531)	model_time 0.7168 (0.7458)	loss 3.4981 (3.0234)	grad_norm 1.1479 (1.7709/0.7978)	mem 34602MB
[2025-01-19 14:01:04 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][150/312]	eta 0:02:02 lr 0.001168	time 0.7201 (0.7540)	model_time 0.7199 (0.7447)	loss 2.9562 (2.9708)	grad_norm 0.8934 (1.7545/0.7539)	mem 34604MB
[2025-01-19 14:01:07 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][210/312]	eta 0:01:16 lr 0.001164	time 0.8036 (0.7535)	model_time 0.8031 (0.7465)	loss 1.9530 (3.0232)	grad_norm 1.2865 (1.7595/0.7841)	mem 34602MB
[2025-01-19 14:01:11 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][160/312]	eta 0:01:54 lr 0.001167	time 0.7260 (0.7520)	model_time 0.7259 (0.7432)	loss 3.1183 (2.9783)	grad_norm 3.5089 (1.7688/0.7557)	mem 34604MB
[2025-01-19 14:01:15 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][220/312]	eta 0:01:09 lr 0.001164	time 0.7368 (0.7527)	model_time 0.7366 (0.7461)	loss 3.6246 (3.0274)	grad_norm 2.8968 (1.7780/0.7880)	mem 34602MB
[2025-01-19 14:01:18 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][170/312]	eta 0:01:46 lr 0.001167	time 0.7180 (0.7505)	model_time 0.7178 (0.7422)	loss 2.4821 (2.9734)	grad_norm 1.1832 (1.7762/0.7616)	mem 34604MB
[2025-01-19 14:01:23 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][230/312]	eta 0:01:01 lr 0.001163	time 0.7148 (0.7532)	model_time 0.7144 (0.7469)	loss 3.0425 (3.0276)	grad_norm 2.0533 (1.7868/0.7818)	mem 34602MB
[2025-01-19 14:01:26 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][180/312]	eta 0:01:38 lr 0.001166	time 0.7248 (0.7488)	model_time 0.7246 (0.7410)	loss 2.6474 (2.9657)	grad_norm 1.3444 (1.7673/0.7504)	mem 34604MB
[2025-01-19 14:01:30 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][240/312]	eta 0:00:54 lr 0.001163	time 0.7167 (0.7534)	model_time 0.7162 (0.7472)	loss 3.2398 (3.0274)	grad_norm 1.7032 (1.7789/0.7752)	mem 34602MB
[2025-01-19 14:01:33 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][190/312]	eta 0:01:31 lr 0.001166	time 0.7211 (0.7475)	model_time 0.7206 (0.7400)	loss 2.1602 (2.9574)	grad_norm 2.6979 (1.7610/0.7437)	mem 34604MB
[2025-01-19 14:01:37 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][250/312]	eta 0:00:46 lr 0.001162	time 0.7293 (0.7527)	model_time 0.7292 (0.7468)	loss 3.7303 (3.0330)	grad_norm 0.9889 (1.7775/0.7682)	mem 34602MB
[2025-01-19 14:01:40 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][200/312]	eta 0:01:23 lr 0.001165	time 0.7196 (0.7462)	model_time 0.7194 (0.7391)	loss 3.4540 (2.9694)	grad_norm 1.1347 (1.7523/0.7359)	mem 34604MB
[2025-01-19 14:01:45 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][260/312]	eta 0:00:39 lr 0.001161	time 0.7968 (0.7523)	model_time 0.7966 (0.7466)	loss 3.2144 (3.0322)	grad_norm 1.2663 (1.7678/0.7592)	mem 34602MB
[2025-01-19 14:01:47 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][210/312]	eta 0:01:16 lr 0.001164	time 0.7276 (0.7458)	model_time 0.7272 (0.7390)	loss 3.1846 (2.9818)	grad_norm 2.8224 (1.7478/0.7330)	mem 34604MB
[2025-01-19 14:01:52 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][270/312]	eta 0:00:31 lr 0.001161	time 0.7228 (0.7518)	model_time 0.7226 (0.7463)	loss 3.2592 (3.0262)	grad_norm 1.3360 (1.7757/0.7592)	mem 34602MB
[2025-01-19 14:01:55 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][220/312]	eta 0:01:08 lr 0.001164	time 0.7145 (0.7461)	model_time 0.7144 (0.7396)	loss 2.3177 (2.9776)	grad_norm 1.1077 (1.7615/0.7418)	mem 34604MB
[2025-01-19 14:02:00 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][280/312]	eta 0:00:24 lr 0.001160	time 0.7276 (0.7514)	model_time 0.7272 (0.7461)	loss 3.3142 (3.0232)	grad_norm 2.1853 (1.7722/0.7509)	mem 34602MB
[2025-01-19 14:02:03 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][230/312]	eta 0:01:01 lr 0.001163	time 0.8096 (0.7487)	model_time 0.8095 (0.7425)	loss 3.1138 (2.9819)	grad_norm 1.1972 (1.7531/0.7326)	mem 34604MB
[2025-01-19 14:02:07 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][290/312]	eta 0:00:16 lr 0.001160	time 0.7392 (0.7508)	model_time 0.7391 (0.7457)	loss 2.4453 (3.0190)	grad_norm 1.0778 (1.7843/0.7576)	mem 34602MB
[2025-01-19 14:02:11 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][240/312]	eta 0:00:54 lr 0.001163	time 0.8259 (0.7503)	model_time 0.8255 (0.7443)	loss 2.4718 (2.9895)	grad_norm 2.2546 (1.7550/0.7255)	mem 34604MB
[2025-01-19 14:02:14 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][300/312]	eta 0:00:09 lr 0.001159	time 0.7986 (0.7503)	model_time 0.7985 (0.7454)	loss 3.1934 (3.0195)	grad_norm 0.8941 (1.7708/0.7530)	mem 34602MB
[2025-01-19 14:02:19 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][250/312]	eta 0:00:46 lr 0.001162	time 0.8021 (0.7511)	model_time 0.8016 (0.7453)	loss 2.3695 (2.9893)	grad_norm 1.2559 (1.7583/0.7236)	mem 34604MB
[2025-01-19 14:02:22 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][310/312]	eta 0:00:01 lr 0.001158	time 0.7123 (0.7500)	model_time 0.7122 (0.7452)	loss 3.3069 (3.0290)	grad_norm 1.1886 (1.7485/0.7461)	mem 34602MB
[2025-01-19 14:02:22 internimage_b_1k_224] (main.py 519): INFO EPOCH 192 training takes 0:03:53
[2025-01-19 14:02:23 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_192.pth saving......
[2025-01-19 14:02:26 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_192.pth saved !!!
[2025-01-19 14:02:26 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][260/312]	eta 0:00:39 lr 0.001161	time 0.7211 (0.7507)	model_time 0.7210 (0.7451)	loss 2.9618 (2.9925)	grad_norm 1.8396 (1.7380/0.7199)	mem 34604MB
[2025-01-19 14:02:33 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][270/312]	eta 0:00:31 lr 0.001161	time 0.7261 (0.7499)	model_time 0.7260 (0.7446)	loss 2.2329 (2.9920)	grad_norm 1.0193 (1.7199/0.7157)	mem 34604MB
[2025-01-19 14:02:34 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.764 (7.764)	Loss 0.7637 (0.7637)	Acc@1 85.034 (85.034)	Acc@5 97.510 (97.510)	Mem 34602MB
[2025-01-19 14:02:37 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.993)	Loss 1.0154 (0.8635)	Acc@1 78.174 (82.364)	Acc@5 95.093 (96.329)	Mem 34602MB
[2025-01-19 14:02:37 internimage_b_1k_224] (main.py 575): INFO [Epoch:192] * Acc@1 82.172 Acc@5 96.327
[2025-01-19 14:02:37 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.2%
[2025-01-19 14:02:37 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.47%
[2025-01-19 14:02:41 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][280/312]	eta 0:00:23 lr 0.001160	time 0.7263 (0.7491)	model_time 0.7258 (0.7439)	loss 3.4089 (3.0024)	grad_norm 1.7730 (1.7103/0.7083)	mem 34604MB
[2025-01-19 14:02:46 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.343 (9.343)	Loss 0.6905 (0.6905)	Acc@1 85.181 (85.181)	Acc@5 97.925 (97.925)	Mem 34602MB
[2025-01-19 14:02:48 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][290/312]	eta 0:00:16 lr 0.001160	time 0.7260 (0.7485)	model_time 0.7256 (0.7434)	loss 3.3448 (3.0053)	grad_norm 1.7183 (1.7154/0.7037)	mem 34604MB
[2025-01-19 14:02:51 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.187 (1.267)	Loss 0.9484 (0.8055)	Acc@1 78.833 (82.815)	Acc@5 95.044 (96.460)	Mem 34602MB
[2025-01-19 14:02:51 internimage_b_1k_224] (main.py 575): INFO [Epoch:192] * Acc@1 82.668 Acc@5 96.503
[2025-01-19 14:02:51 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.7%
[2025-01-19 14:02:51 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:02:55 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:02:55 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.67%
[2025-01-19 14:02:55 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][300/312]	eta 0:00:08 lr 0.001159	time 0.7153 (0.7476)	model_time 0.7152 (0.7427)	loss 3.1754 (2.9985)	grad_norm 1.0548 (1.7348/0.7238)	mem 34604MB
[2025-01-19 14:02:57 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][0/312]	eta 0:10:39 lr 0.001158	time 2.0506 (2.0506)	model_time 0.7584 (0.7584)	loss 2.5798 (2.5798)	grad_norm 1.3607 (1.3607/0.0000)	mem 34602MB
[2025-01-19 14:03:02 internimage_b_1k_224] (main.py 510): INFO Train: [192/300][310/312]	eta 0:00:01 lr 0.001158	time 0.7159 (0.7465)	model_time 0.7157 (0.7418)	loss 3.3422 (2.9919)	grad_norm 2.1057 (1.7030/0.7055)	mem 34604MB
[2025-01-19 14:03:03 internimage_b_1k_224] (main.py 519): INFO EPOCH 192 training takes 0:03:52
[2025-01-19 14:03:03 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_192.pth saving......
[2025-01-19 14:03:04 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][10/312]	eta 0:04:20 lr 0.001158	time 0.8311 (0.8631)	model_time 0.8309 (0.7453)	loss 2.3455 (2.8173)	grad_norm 1.5515 (1.5221/0.4446)	mem 34602MB
[2025-01-19 14:03:07 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_192.pth saved !!!
[2025-01-19 14:03:12 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][20/312]	eta 0:03:58 lr 0.001157	time 0.8198 (0.8164)	model_time 0.8194 (0.7545)	loss 2.5593 (2.9676)	grad_norm 1.1731 (1.4231/0.4307)	mem 34602MB
[2025-01-19 14:03:14 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.660 (7.660)	Loss 0.7170 (0.7170)	Acc@1 84.741 (84.741)	Acc@5 97.314 (97.314)	Mem 34604MB
[2025-01-19 14:03:17 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.952)	Loss 0.9513 (0.8247)	Acc@1 78.857 (82.395)	Acc@5 95.166 (96.227)	Mem 34604MB
[2025-01-19 14:03:17 internimage_b_1k_224] (main.py 575): INFO [Epoch:192] * Acc@1 82.230 Acc@5 96.261
[2025-01-19 14:03:17 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.2%
[2025-01-19 14:03:17 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.25%
[2025-01-19 14:03:19 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][30/312]	eta 0:03:43 lr 0.001156	time 0.7201 (0.7922)	model_time 0.7200 (0.7502)	loss 3.2388 (2.9681)	grad_norm 1.9591 (1.4811/0.4495)	mem 34602MB
[2025-01-19 14:03:26 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.090 (9.090)	Loss 0.6874 (0.6874)	Acc@1 85.303 (85.303)	Acc@5 97.949 (97.949)	Mem 34604MB
[2025-01-19 14:03:27 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][40/312]	eta 0:03:33 lr 0.001156	time 0.7172 (0.7852)	model_time 0.7167 (0.7534)	loss 2.3147 (2.9758)	grad_norm 0.8930 (1.5932/0.5531)	mem 34602MB
[2025-01-19 14:03:31 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.249)	Loss 0.9482 (0.8041)	Acc@1 79.199 (82.895)	Acc@5 94.946 (96.407)	Mem 34604MB
[2025-01-19 14:03:31 internimage_b_1k_224] (main.py 575): INFO [Epoch:192] * Acc@1 82.710 Acc@5 96.467
[2025-01-19 14:03:31 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.7%
[2025-01-19 14:03:31 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:03:35 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][50/312]	eta 0:03:24 lr 0.001155	time 0.7407 (0.7787)	model_time 0.7405 (0.7530)	loss 3.5416 (2.9760)	grad_norm 2.7398 (1.6732/0.5850)	mem 34602MB
[2025-01-19 14:03:35 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:03:35 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.71%
[2025-01-19 14:03:37 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][0/312]	eta 0:10:41 lr 0.001158	time 2.0550 (2.0550)	model_time 0.7343 (0.7343)	loss 2.7386 (2.7386)	grad_norm 2.1310 (2.1310/0.0000)	mem 34604MB
[2025-01-19 14:03:42 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][60/312]	eta 0:03:14 lr 0.001155	time 0.7160 (0.7722)	model_time 0.7159 (0.7507)	loss 2.4631 (2.9562)	grad_norm 0.9676 (1.7838/0.7523)	mem 34602MB
[2025-01-19 14:03:45 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][10/312]	eta 0:04:16 lr 0.001158	time 0.7262 (0.8489)	model_time 0.7261 (0.7286)	loss 2.4244 (3.0350)	grad_norm 1.4628 (1.4494/0.3742)	mem 34604MB
[2025-01-19 14:03:49 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][70/312]	eta 0:03:06 lr 0.001154	time 0.7220 (0.7687)	model_time 0.7218 (0.7502)	loss 2.7777 (2.9317)	grad_norm 1.2037 (1.8728/0.7890)	mem 34602MB
[2025-01-19 14:03:52 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][20/312]	eta 0:03:52 lr 0.001157	time 0.7295 (0.7949)	model_time 0.7291 (0.7317)	loss 3.4711 (3.0845)	grad_norm 1.4019 (1.7587/0.6416)	mem 34604MB
[2025-01-19 14:03:57 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][80/312]	eta 0:02:57 lr 0.001153	time 0.7159 (0.7662)	model_time 0.7158 (0.7499)	loss 3.1501 (2.9722)	grad_norm 1.4246 (1.8363/0.7660)	mem 34602MB
[2025-01-19 14:04:00 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][30/312]	eta 0:03:41 lr 0.001156	time 0.8797 (0.7837)	model_time 0.8792 (0.7407)	loss 3.1068 (3.1179)	grad_norm 3.5317 (1.8767/0.6643)	mem 34604MB
[2025-01-19 14:04:04 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][90/312]	eta 0:02:49 lr 0.001153	time 0.7314 (0.7629)	model_time 0.7312 (0.7483)	loss 3.3380 (2.9699)	grad_norm 1.7400 (1.8317/0.7545)	mem 34602MB
[2025-01-19 14:04:07 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][40/312]	eta 0:03:31 lr 0.001156	time 0.8041 (0.7787)	model_time 0.8039 (0.7462)	loss 3.5523 (3.0833)	grad_norm 1.6307 (1.7852/0.6853)	mem 34604MB
[2025-01-19 14:04:12 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][100/312]	eta 0:02:41 lr 0.001152	time 0.7209 (0.7598)	model_time 0.7204 (0.7466)	loss 3.2435 (2.9630)	grad_norm 1.0592 (1.8415/0.7435)	mem 34602MB
[2025-01-19 14:04:15 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][50/312]	eta 0:03:24 lr 0.001155	time 0.8097 (0.7794)	model_time 0.8096 (0.7532)	loss 2.9727 (3.0141)	grad_norm 2.8924 (1.8660/0.6984)	mem 34604MB
[2025-01-19 14:04:19 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][110/312]	eta 0:02:33 lr 0.001152	time 0.8134 (0.7596)	model_time 0.8130 (0.7475)	loss 3.0632 (2.9518)	grad_norm 1.9572 (1.7972/0.7314)	mem 34602MB
[2025-01-19 14:04:22 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][60/312]	eta 0:03:15 lr 0.001155	time 0.7553 (0.7743)	model_time 0.7549 (0.7523)	loss 3.1986 (3.0410)	grad_norm 2.2226 (1.7892/0.6881)	mem 34604MB
[2025-01-19 14:04:27 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][120/312]	eta 0:02:25 lr 0.001151	time 0.8113 (0.7579)	model_time 0.8108 (0.7468)	loss 2.4245 (2.9515)	grad_norm 1.6783 (1.7610/0.7142)	mem 34602MB
[2025-01-19 14:04:30 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][70/312]	eta 0:03:06 lr 0.001154	time 0.7764 (0.7719)	model_time 0.7762 (0.7530)	loss 3.4306 (3.0312)	grad_norm 3.6295 (1.7857/0.7373)	mem 34604MB
[2025-01-19 14:04:34 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][130/312]	eta 0:02:17 lr 0.001150	time 0.8171 (0.7569)	model_time 0.8167 (0.7467)	loss 3.8293 (2.9630)	grad_norm 1.6895 (1.7640/0.7098)	mem 34602MB
[2025-01-19 14:04:37 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][80/312]	eta 0:02:57 lr 0.001153	time 0.7170 (0.7661)	model_time 0.7169 (0.7494)	loss 2.4782 (3.0340)	grad_norm 2.3616 (1.7707/0.7204)	mem 34604MB
[2025-01-19 14:04:42 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][140/312]	eta 0:02:10 lr 0.001150	time 0.8064 (0.7571)	model_time 0.8062 (0.7476)	loss 3.0271 (2.9783)	grad_norm 3.6536 (1.7651/0.7077)	mem 34602MB
[2025-01-19 14:04:45 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][90/312]	eta 0:02:49 lr 0.001153	time 0.7525 (0.7626)	model_time 0.7521 (0.7477)	loss 2.4951 (3.0091)	grad_norm 3.1708 (1.9019/0.8246)	mem 34604MB
[2025-01-19 14:04:49 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][150/312]	eta 0:02:02 lr 0.001149	time 0.7170 (0.7559)	model_time 0.7166 (0.7470)	loss 3.2899 (2.9823)	grad_norm 1.3637 (1.7352/0.6978)	mem 34602MB
[2025-01-19 14:04:52 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][100/312]	eta 0:02:41 lr 0.001152	time 0.7295 (0.7598)	model_time 0.7293 (0.7464)	loss 3.2984 (3.0118)	grad_norm 1.3820 (1.8671/0.8024)	mem 34604MB
[2025-01-19 14:04:57 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][160/312]	eta 0:01:54 lr 0.001149	time 0.7261 (0.7563)	model_time 0.7257 (0.7479)	loss 3.2469 (2.9692)	grad_norm 3.1875 (1.7487/0.6941)	mem 34602MB
[2025-01-19 14:04:59 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][110/312]	eta 0:02:32 lr 0.001152	time 0.7592 (0.7572)	model_time 0.7588 (0.7450)	loss 3.1937 (3.0198)	grad_norm 3.2248 (1.8699/0.7919)	mem 34604MB
[2025-01-19 14:05:04 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][170/312]	eta 0:01:47 lr 0.001148	time 0.7161 (0.7564)	model_time 0.7157 (0.7485)	loss 3.8477 (2.9735)	grad_norm 2.2081 (1.7717/0.6937)	mem 34602MB
[2025-01-19 14:05:07 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][120/312]	eta 0:02:24 lr 0.001151	time 0.7608 (0.7549)	model_time 0.7603 (0.7436)	loss 2.7691 (3.0256)	grad_norm 5.5542 (1.9560/0.8931)	mem 34604MB
[2025-01-19 14:05:12 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][180/312]	eta 0:01:39 lr 0.001147	time 0.7209 (0.7559)	model_time 0.7207 (0.7484)	loss 2.4151 (2.9714)	grad_norm 1.1573 (1.7608/0.6883)	mem 34602MB
[2025-01-19 14:05:14 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][130/312]	eta 0:02:16 lr 0.001150	time 0.7249 (0.7526)	model_time 0.7245 (0.7421)	loss 2.6790 (3.0115)	grad_norm 2.2787 (1.9718/0.8755)	mem 34604MB
[2025-01-19 14:05:19 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][190/312]	eta 0:01:32 lr 0.001147	time 0.7157 (0.7553)	model_time 0.7152 (0.7481)	loss 3.3929 (2.9767)	grad_norm 1.7096 (1.7650/0.6939)	mem 34602MB
[2025-01-19 14:05:21 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][140/312]	eta 0:02:09 lr 0.001150	time 0.7234 (0.7520)	model_time 0.7230 (0.7423)	loss 2.1772 (3.0061)	grad_norm 1.9511 (2.0009/0.8688)	mem 34604MB
[2025-01-19 14:05:26 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][200/312]	eta 0:01:24 lr 0.001146	time 0.7171 (0.7546)	model_time 0.7167 (0.7478)	loss 3.1542 (2.9642)	grad_norm 2.5732 (1.7748/0.6912)	mem 34602MB
[2025-01-19 14:05:29 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][150/312]	eta 0:02:01 lr 0.001149	time 0.8406 (0.7519)	model_time 0.8404 (0.7428)	loss 2.8542 (3.0161)	grad_norm 1.6040 (1.9840/0.8491)	mem 34604MB
[2025-01-19 14:05:34 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][210/312]	eta 0:01:16 lr 0.001146	time 0.7177 (0.7537)	model_time 0.7172 (0.7472)	loss 2.7003 (2.9615)	grad_norm 1.2015 (1.7700/0.6843)	mem 34602MB
[2025-01-19 14:05:36 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][160/312]	eta 0:01:54 lr 0.001149	time 0.8043 (0.7521)	model_time 0.8042 (0.7436)	loss 3.1820 (3.0239)	grad_norm 2.9587 (1.9581/0.8425)	mem 34604MB
[2025-01-19 14:05:41 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][220/312]	eta 0:01:09 lr 0.001145	time 0.7277 (0.7528)	model_time 0.7273 (0.7465)	loss 2.3260 (2.9785)	grad_norm 1.8738 (1.7519/0.6783)	mem 34602MB
[2025-01-19 14:05:44 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][170/312]	eta 0:01:47 lr 0.001148	time 0.8081 (0.7538)	model_time 0.8079 (0.7458)	loss 3.6422 (3.0124)	grad_norm 1.0927 (1.9617/0.8416)	mem 34604MB
[2025-01-19 14:05:49 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][230/312]	eta 0:01:01 lr 0.001145	time 0.8318 (0.7529)	model_time 0.8316 (0.7469)	loss 3.7208 (2.9800)	grad_norm 1.4923 (1.7535/0.6790)	mem 34602MB
[2025-01-19 14:05:52 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][180/312]	eta 0:01:39 lr 0.001147	time 0.7256 (0.7531)	model_time 0.7252 (0.7455)	loss 3.2816 (3.0058)	grad_norm 1.4169 (1.9646/0.8408)	mem 34604MB
[2025-01-19 14:05:56 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][240/312]	eta 0:00:54 lr 0.001144	time 0.8090 (0.7524)	model_time 0.8089 (0.7467)	loss 2.0624 (2.9753)	grad_norm 0.8476 (1.7492/0.6813)	mem 34602MB
[2025-01-19 14:05:59 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][190/312]	eta 0:01:31 lr 0.001147	time 0.7167 (0.7536)	model_time 0.7162 (0.7463)	loss 2.0769 (3.0004)	grad_norm 1.8474 (1.9813/0.8507)	mem 34604MB
[2025-01-19 14:06:04 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][250/312]	eta 0:00:46 lr 0.001143	time 0.8263 (0.7520)	model_time 0.8262 (0.7465)	loss 3.1580 (2.9790)	grad_norm 1.6987 (1.7400/0.6771)	mem 34602MB
[2025-01-19 14:06:06 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][200/312]	eta 0:01:24 lr 0.001146	time 0.7159 (0.7523)	model_time 0.7157 (0.7454)	loss 2.9972 (3.0068)	grad_norm 1.1238 (1.9535/0.8422)	mem 34604MB
[2025-01-19 14:06:11 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][260/312]	eta 0:00:39 lr 0.001143	time 0.8069 (0.7521)	model_time 0.8065 (0.7468)	loss 3.1058 (2.9752)	grad_norm 1.2194 (1.7507/0.6851)	mem 34602MB
[2025-01-19 14:06:14 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][210/312]	eta 0:01:16 lr 0.001146	time 0.7207 (0.7510)	model_time 0.7203 (0.7444)	loss 2.7886 (3.0049)	grad_norm 1.3386 (1.9526/0.8268)	mem 34604MB
[2025-01-19 14:06:19 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][270/312]	eta 0:00:31 lr 0.001142	time 0.7177 (0.7521)	model_time 0.7173 (0.7470)	loss 1.9355 (2.9769)	grad_norm 1.3018 (1.7440/0.6806)	mem 34602MB
[2025-01-19 14:06:21 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][220/312]	eta 0:01:09 lr 0.001145	time 0.7226 (0.7503)	model_time 0.7224 (0.7440)	loss 2.7142 (3.0095)	grad_norm 2.4288 (1.9693/0.8228)	mem 34604MB
[2025-01-19 14:06:26 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][280/312]	eta 0:00:24 lr 0.001142	time 0.7108 (0.7525)	model_time 0.7106 (0.7476)	loss 3.4039 (2.9714)	grad_norm 2.3422 (1.7367/0.6754)	mem 34602MB
[2025-01-19 14:06:28 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][230/312]	eta 0:01:01 lr 0.001145	time 0.7220 (0.7492)	model_time 0.7218 (0.7431)	loss 3.1723 (3.0110)	grad_norm 0.7598 (1.9752/0.8243)	mem 34604MB
[2025-01-19 14:06:34 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][290/312]	eta 0:00:16 lr 0.001141	time 0.7258 (0.7527)	model_time 0.7256 (0.7479)	loss 2.4207 (2.9683)	grad_norm 1.2352 (1.7383/0.6727)	mem 34602MB
[2025-01-19 14:06:36 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][240/312]	eta 0:00:53 lr 0.001144	time 0.7263 (0.7482)	model_time 0.7262 (0.7424)	loss 3.2383 (3.0108)	grad_norm 1.3596 (1.9678/0.8216)	mem 34604MB
[2025-01-19 14:06:41 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][300/312]	eta 0:00:09 lr 0.001140	time 0.7132 (0.7523)	model_time 0.7130 (0.7476)	loss 3.0111 (2.9798)	grad_norm 2.7672 (1.7552/0.6800)	mem 34602MB
[2025-01-19 14:06:43 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][250/312]	eta 0:00:46 lr 0.001143	time 0.7228 (0.7472)	model_time 0.7227 (0.7416)	loss 2.4387 (3.0080)	grad_norm 1.3532 (1.9433/0.8172)	mem 34604MB
[2025-01-19 14:06:49 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][310/312]	eta 0:00:01 lr 0.001140	time 0.7149 (0.7515)	model_time 0.7148 (0.7470)	loss 3.5766 (2.9839)	grad_norm 1.6481 (1.7576/0.6779)	mem 34602MB
[2025-01-19 14:06:49 internimage_b_1k_224] (main.py 519): INFO EPOCH 193 training takes 0:03:54
[2025-01-19 14:06:49 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_193.pth saving......
[2025-01-19 14:06:50 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][260/312]	eta 0:00:38 lr 0.001143	time 0.7245 (0.7467)	model_time 0.7240 (0.7413)	loss 2.8150 (3.0145)	grad_norm 1.8015 (1.9246/0.8129)	mem 34604MB
[2025-01-19 14:06:52 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_193.pth saved !!!
[2025-01-19 14:06:58 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][270/312]	eta 0:00:31 lr 0.001142	time 0.8216 (0.7469)	model_time 0.8211 (0.7417)	loss 3.0001 (3.0192)	grad_norm 2.4668 (1.9343/0.8037)	mem 34604MB
[2025-01-19 14:07:00 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.999 (7.999)	Loss 0.7552 (0.7552)	Acc@1 85.010 (85.010)	Acc@5 97.388 (97.388)	Mem 34602MB
[2025-01-19 14:07:04 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.017)	Loss 0.9827 (0.8644)	Acc@1 78.760 (82.440)	Acc@5 95.386 (96.298)	Mem 34602MB
[2025-01-19 14:07:04 internimage_b_1k_224] (main.py 575): INFO [Epoch:193] * Acc@1 82.352 Acc@5 96.341
[2025-01-19 14:07:04 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.4%
[2025-01-19 14:07:04 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.47%
[2025-01-19 14:07:05 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][280/312]	eta 0:00:23 lr 0.001142	time 0.8063 (0.7474)	model_time 0.8061 (0.7424)	loss 3.4584 (3.0252)	grad_norm 1.5066 (1.9437/0.8029)	mem 34604MB
[2025-01-19 14:07:13 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][290/312]	eta 0:00:16 lr 0.001141	time 0.7998 (0.7481)	model_time 0.7996 (0.7432)	loss 3.5658 (3.0290)	grad_norm 2.0411 (1.9319/0.7982)	mem 34604MB
[2025-01-19 14:07:13 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.468 (9.468)	Loss 0.6916 (0.6916)	Acc@1 85.181 (85.181)	Acc@5 97.949 (97.949)	Mem 34602MB
[2025-01-19 14:07:18 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.288)	Loss 0.9482 (0.8059)	Acc@1 78.857 (82.835)	Acc@5 95.044 (96.484)	Mem 34602MB
[2025-01-19 14:07:18 internimage_b_1k_224] (main.py 575): INFO [Epoch:193] * Acc@1 82.700 Acc@5 96.527
[2025-01-19 14:07:18 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.7%
[2025-01-19 14:07:18 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:07:20 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][300/312]	eta 0:00:08 lr 0.001140	time 0.7165 (0.7479)	model_time 0.7164 (0.7431)	loss 2.6942 (3.0300)	grad_norm 2.1989 (1.9205/0.7928)	mem 34604MB
[2025-01-19 14:07:22 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:07:22 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.70%
[2025-01-19 14:07:24 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][0/312]	eta 0:10:54 lr 0.001140	time 2.0985 (2.0985)	model_time 0.7472 (0.7472)	loss 3.2830 (3.2830)	grad_norm 1.5760 (1.5760/0.0000)	mem 34602MB
[2025-01-19 14:07:28 internimage_b_1k_224] (main.py 510): INFO Train: [193/300][310/312]	eta 0:00:01 lr 0.001140	time 0.8094 (0.7477)	model_time 0.8093 (0.7431)	loss 2.3323 (3.0263)	grad_norm 1.6522 (1.9257/0.7947)	mem 34604MB
[2025-01-19 14:07:29 internimage_b_1k_224] (main.py 519): INFO EPOCH 193 training takes 0:03:53
[2025-01-19 14:07:29 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_193.pth saving......
[2025-01-19 14:07:32 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][10/312]	eta 0:04:21 lr 0.001139	time 0.7177 (0.8643)	model_time 0.7172 (0.7411)	loss 3.0964 (3.1111)	grad_norm 3.4889 (2.5142/0.9894)	mem 34602MB
[2025-01-19 14:07:32 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_193.pth saved !!!
[2025-01-19 14:07:39 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.192 (7.192)	Loss 0.7409 (0.7409)	Acc@1 85.010 (85.010)	Acc@5 97.754 (97.754)	Mem 34604MB
[2025-01-19 14:07:39 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][20/312]	eta 0:03:54 lr 0.001138	time 0.7228 (0.8042)	model_time 0.7226 (0.7396)	loss 2.9355 (3.1662)	grad_norm 1.2492 (2.2231/0.9168)	mem 34602MB
[2025-01-19 14:07:42 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.953)	Loss 0.9716 (0.8528)	Acc@1 78.955 (82.484)	Acc@5 95.312 (96.338)	Mem 34604MB
[2025-01-19 14:07:43 internimage_b_1k_224] (main.py 575): INFO [Epoch:193] * Acc@1 82.340 Acc@5 96.369
[2025-01-19 14:07:43 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.3%
[2025-01-19 14:07:43 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 14:07:46 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 14:07:46 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.34%
[2025-01-19 14:07:47 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][30/312]	eta 0:03:39 lr 0.001138	time 0.7287 (0.7799)	model_time 0.7286 (0.7360)	loss 3.3802 (3.1208)	grad_norm 0.7765 (2.1769/1.0365)	mem 34602MB
[2025-01-19 14:07:54 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.557 (7.557)	Loss 0.6881 (0.6881)	Acc@1 85.352 (85.352)	Acc@5 97.925 (97.925)	Mem 34604MB
[2025-01-19 14:07:54 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][40/312]	eta 0:03:30 lr 0.001137	time 0.7679 (0.7736)	model_time 0.7677 (0.7403)	loss 1.9225 (3.0273)	grad_norm 3.2079 (2.1631/0.9830)	mem 34602MB
[2025-01-19 14:07:57 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.966)	Loss 0.9477 (0.8045)	Acc@1 79.297 (82.948)	Acc@5 94.971 (96.411)	Mem 34604MB
[2025-01-19 14:07:57 internimage_b_1k_224] (main.py 575): INFO [Epoch:193] * Acc@1 82.754 Acc@5 96.471
[2025-01-19 14:07:57 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.8%
[2025-01-19 14:07:57 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:08:01 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:08:01 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.75%
[2025-01-19 14:08:02 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][50/312]	eta 0:03:21 lr 0.001137	time 0.7168 (0.7689)	model_time 0.7164 (0.7421)	loss 3.3242 (3.0089)	grad_norm 1.7950 (2.1456/0.9991)	mem 34602MB
[2025-01-19 14:08:03 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][0/312]	eta 0:11:27 lr 0.001140	time 2.2025 (2.2025)	model_time 0.7246 (0.7246)	loss 3.2259 (3.2259)	grad_norm 1.6841 (1.6841/0.0000)	mem 34604MB
[2025-01-19 14:08:09 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][60/312]	eta 0:03:12 lr 0.001136	time 0.7164 (0.7651)	model_time 0.7160 (0.7426)	loss 3.3377 (3.0618)	grad_norm 1.3544 (2.0563/0.9592)	mem 34602MB
[2025-01-19 14:08:10 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][10/312]	eta 0:04:19 lr 0.001139	time 0.7203 (0.8576)	model_time 0.7202 (0.7229)	loss 3.6314 (2.9238)	grad_norm 1.5037 (2.3847/1.1537)	mem 34604MB
[2025-01-19 14:08:17 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][70/312]	eta 0:03:04 lr 0.001135	time 0.7191 (0.7628)	model_time 0.7190 (0.7435)	loss 2.3026 (3.0590)	grad_norm 1.2477 (1.9955/0.9174)	mem 34602MB
[2025-01-19 14:08:18 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][20/312]	eta 0:03:52 lr 0.001138	time 0.7324 (0.7969)	model_time 0.7320 (0.7262)	loss 2.5697 (2.7593)	grad_norm 2.1277 (2.2219/0.9718)	mem 34604MB
[2025-01-19 14:08:24 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][80/312]	eta 0:02:56 lr 0.001135	time 0.7294 (0.7611)	model_time 0.7290 (0.7441)	loss 3.2956 (3.0449)	grad_norm 1.8962 (1.9218/0.8872)	mem 34602MB
[2025-01-19 14:08:25 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][30/312]	eta 0:03:38 lr 0.001138	time 0.7355 (0.7762)	model_time 0.7354 (0.7282)	loss 3.6969 (2.8261)	grad_norm 1.2039 (2.0699/0.9474)	mem 34604MB
[2025-01-19 14:08:32 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][90/312]	eta 0:02:48 lr 0.001134	time 0.8355 (0.7611)	model_time 0.8354 (0.7459)	loss 3.6073 (3.0587)	grad_norm 1.5547 (1.9217/0.8626)	mem 34602MB
[2025-01-19 14:08:32 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][40/312]	eta 0:03:28 lr 0.001137	time 0.7283 (0.7661)	model_time 0.7279 (0.7297)	loss 2.9455 (2.8291)	grad_norm 1.9928 (2.0722/0.9134)	mem 34604MB
[2025-01-19 14:08:39 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][100/312]	eta 0:02:41 lr 0.001134	time 0.7200 (0.7599)	model_time 0.7199 (0.7462)	loss 2.3206 (3.0378)	grad_norm 0.9102 (1.9318/0.8350)	mem 34602MB
[2025-01-19 14:08:40 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][50/312]	eta 0:03:18 lr 0.001137	time 0.7181 (0.7589)	model_time 0.7177 (0.7296)	loss 3.4747 (2.8616)	grad_norm 1.4746 (1.9914/0.8656)	mem 34604MB
[2025-01-19 14:08:46 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][110/312]	eta 0:02:33 lr 0.001133	time 0.7464 (0.7576)	model_time 0.7463 (0.7451)	loss 2.7923 (3.0465)	grad_norm 0.9314 (1.8915/0.8176)	mem 34602MB
[2025-01-19 14:08:47 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][60/312]	eta 0:03:10 lr 0.001136	time 0.7231 (0.7548)	model_time 0.7226 (0.7302)	loss 3.4711 (2.8791)	grad_norm 0.9296 (1.9377/0.8295)	mem 34604MB
[2025-01-19 14:08:54 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][120/312]	eta 0:02:25 lr 0.001132	time 0.7216 (0.7558)	model_time 0.7214 (0.7443)	loss 3.5487 (3.0566)	grad_norm 3.8959 (1.8900/0.8144)	mem 34602MB
[2025-01-19 14:08:54 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][70/312]	eta 0:03:02 lr 0.001135	time 0.7171 (0.7524)	model_time 0.7166 (0.7313)	loss 2.2598 (2.8773)	grad_norm 2.1516 (1.8982/0.7880)	mem 34604MB
[2025-01-19 14:09:01 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][130/312]	eta 0:02:17 lr 0.001132	time 0.7154 (0.7556)	model_time 0.7150 (0.7449)	loss 3.2196 (3.0591)	grad_norm 1.3395 (1.9035/0.8257)	mem 34602MB
[2025-01-19 14:09:02 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][80/312]	eta 0:02:54 lr 0.001135	time 0.7360 (0.7515)	model_time 0.7359 (0.7329)	loss 3.0827 (2.8663)	grad_norm 1.5550 (1.9022/0.7815)	mem 34604MB
[2025-01-19 14:09:09 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][140/312]	eta 0:02:09 lr 0.001131	time 0.7286 (0.7547)	model_time 0.7284 (0.7448)	loss 3.2367 (3.0561)	grad_norm 1.1312 (1.8855/0.8100)	mem 34602MB
[2025-01-19 14:09:09 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][90/312]	eta 0:02:47 lr 0.001134	time 0.7171 (0.7533)	model_time 0.7169 (0.7367)	loss 3.3424 (2.9037)	grad_norm 1.6789 (1.9098/0.7603)	mem 34604MB
[2025-01-19 14:09:16 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][150/312]	eta 0:02:01 lr 0.001131	time 0.7155 (0.7528)	model_time 0.7151 (0.7435)	loss 2.9174 (3.0546)	grad_norm 1.0083 (1.8526/0.8005)	mem 34602MB
[2025-01-19 14:09:17 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][100/312]	eta 0:02:40 lr 0.001134	time 0.7164 (0.7566)	model_time 0.7163 (0.7416)	loss 2.8473 (2.8968)	grad_norm 1.3258 (1.9089/0.7446)	mem 34604MB
[2025-01-19 14:09:24 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][160/312]	eta 0:01:54 lr 0.001130	time 0.7172 (0.7528)	model_time 0.7171 (0.7441)	loss 3.7238 (3.0590)	grad_norm 1.1729 (1.8873/0.8492)	mem 34602MB
[2025-01-19 14:09:25 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][110/312]	eta 0:02:32 lr 0.001133	time 0.7184 (0.7557)	model_time 0.7183 (0.7421)	loss 2.2456 (2.9071)	grad_norm 1.1496 (1.8815/0.7390)	mem 34604MB
[2025-01-19 14:09:31 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][170/312]	eta 0:01:46 lr 0.001130	time 0.7211 (0.7526)	model_time 0.7205 (0.7443)	loss 2.5427 (3.0560)	grad_norm 1.4259 (1.8791/0.8278)	mem 34602MB
[2025-01-19 14:09:32 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][120/312]	eta 0:02:25 lr 0.001132	time 0.8045 (0.7563)	model_time 0.8043 (0.7437)	loss 3.4147 (2.9086)	grad_norm 1.8342 (1.8665/0.7217)	mem 34604MB
[2025-01-19 14:09:38 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][180/312]	eta 0:01:39 lr 0.001129	time 0.7212 (0.7520)	model_time 0.7210 (0.7442)	loss 3.6289 (3.0421)	grad_norm 1.3034 (1.8536/0.8214)	mem 34602MB
[2025-01-19 14:09:40 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][130/312]	eta 0:02:17 lr 0.001132	time 0.7206 (0.7540)	model_time 0.7201 (0.7424)	loss 2.6393 (2.9130)	grad_norm 1.7395 (1.8255/0.7139)	mem 34604MB
[2025-01-19 14:09:46 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][190/312]	eta 0:01:31 lr 0.001128	time 0.7202 (0.7518)	model_time 0.7198 (0.7444)	loss 2.8907 (3.0418)	grad_norm 0.9528 (1.8217/0.8136)	mem 34602MB
[2025-01-19 14:09:47 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][140/312]	eta 0:02:09 lr 0.001131	time 0.7165 (0.7519)	model_time 0.7160 (0.7410)	loss 2.3703 (2.9093)	grad_norm 2.6576 (1.8308/0.7037)	mem 34604MB
[2025-01-19 14:09:53 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][200/312]	eta 0:01:24 lr 0.001128	time 0.7439 (0.7514)	model_time 0.7434 (0.7443)	loss 2.8531 (3.0358)	grad_norm 1.4234 (1.8160/0.8135)	mem 34602MB
[2025-01-19 14:09:54 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][150/312]	eta 0:02:01 lr 0.001131	time 0.7185 (0.7502)	model_time 0.7184 (0.7401)	loss 3.4457 (2.9062)	grad_norm 1.6025 (1.8241/0.6893)	mem 34604MB
[2025-01-19 14:10:01 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][210/312]	eta 0:01:16 lr 0.001127	time 0.8314 (0.7520)	model_time 0.8313 (0.7452)	loss 3.6441 (3.0451)	grad_norm 1.6354 (1.8084/0.8064)	mem 34602MB
[2025-01-19 14:10:01 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][160/312]	eta 0:01:53 lr 0.001130	time 0.8322 (0.7494)	model_time 0.8317 (0.7399)	loss 3.1574 (2.9137)	grad_norm 2.0490 (1.8289/0.6878)	mem 34604MB
[2025-01-19 14:10:09 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][220/312]	eta 0:01:09 lr 0.001127	time 0.7184 (0.7521)	model_time 0.7179 (0.7457)	loss 3.2668 (3.0500)	grad_norm 1.1660 (1.8130/0.8175)	mem 34602MB
[2025-01-19 14:10:09 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][170/312]	eta 0:01:46 lr 0.001130	time 0.7723 (0.7480)	model_time 0.7718 (0.7390)	loss 3.5645 (2.9290)	grad_norm 2.2974 (1.8445/0.7181)	mem 34604MB
[2025-01-19 14:10:16 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][180/312]	eta 0:01:38 lr 0.001129	time 0.7235 (0.7468)	model_time 0.7230 (0.7383)	loss 2.2655 (2.9250)	grad_norm 2.7399 (1.8334/0.7169)	mem 34604MB
[2025-01-19 14:10:16 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][230/312]	eta 0:01:01 lr 0.001126	time 0.7277 (0.7516)	model_time 0.7275 (0.7455)	loss 3.0373 (3.0588)	grad_norm 2.6043 (1.8169/0.8205)	mem 34602MB
[2025-01-19 14:10:23 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][190/312]	eta 0:01:31 lr 0.001128	time 0.7194 (0.7461)	model_time 0.7192 (0.7380)	loss 2.9161 (2.9197)	grad_norm 2.7720 (1.8548/0.7192)	mem 34604MB
[2025-01-19 14:10:23 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][240/312]	eta 0:00:54 lr 0.001125	time 0.7190 (0.7509)	model_time 0.7186 (0.7449)	loss 2.3364 (3.0500)	grad_norm 2.2853 (1.8067/0.8091)	mem 34602MB
[2025-01-19 14:10:31 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][200/312]	eta 0:01:23 lr 0.001128	time 0.7179 (0.7456)	model_time 0.7177 (0.7379)	loss 2.9050 (2.9220)	grad_norm 1.6130 (1.8774/0.7378)	mem 34604MB
[2025-01-19 14:10:31 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][250/312]	eta 0:00:46 lr 0.001125	time 0.7216 (0.7509)	model_time 0.7215 (0.7452)	loss 3.6476 (3.0444)	grad_norm 1.9333 (1.8039/0.7994)	mem 34602MB
[2025-01-19 14:10:38 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][260/312]	eta 0:00:39 lr 0.001124	time 0.7173 (0.7507)	model_time 0.7171 (0.7452)	loss 3.1756 (3.0395)	grad_norm 1.5265 (1.8217/0.7971)	mem 34602MB
[2025-01-19 14:10:38 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][210/312]	eta 0:01:16 lr 0.001127	time 0.7206 (0.7468)	model_time 0.7204 (0.7394)	loss 1.9490 (2.9230)	grad_norm 1.5832 (1.9056/0.7496)	mem 34604MB
[2025-01-19 14:10:46 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][270/312]	eta 0:00:31 lr 0.001124	time 0.7442 (0.7501)	model_time 0.7437 (0.7447)	loss 3.5603 (3.0387)	grad_norm 1.2946 (1.8184/0.7899)	mem 34602MB
[2025-01-19 14:10:46 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][220/312]	eta 0:01:08 lr 0.001127	time 0.8074 (0.7481)	model_time 0.8070 (0.7410)	loss 2.7910 (2.9256)	grad_norm 1.8848 (1.9081/0.7424)	mem 34604MB
[2025-01-19 14:10:53 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][280/312]	eta 0:00:23 lr 0.001123	time 0.7265 (0.7498)	model_time 0.7261 (0.7447)	loss 3.1452 (3.0443)	grad_norm 1.3380 (1.8417/0.8054)	mem 34602MB
[2025-01-19 14:10:54 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][230/312]	eta 0:01:01 lr 0.001126	time 0.7158 (0.7477)	model_time 0.7156 (0.7410)	loss 2.5304 (2.9368)	grad_norm 1.1185 (1.8904/0.7367)	mem 34604MB
[2025-01-19 14:11:01 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][290/312]	eta 0:00:16 lr 0.001122	time 0.7166 (0.7497)	model_time 0.7164 (0.7447)	loss 2.8231 (3.0414)	grad_norm 2.9862 (1.8546/0.8191)	mem 34602MB
[2025-01-19 14:11:01 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][240/312]	eta 0:00:53 lr 0.001125	time 0.8059 (0.7481)	model_time 0.8054 (0.7416)	loss 2.8525 (2.9529)	grad_norm 1.7683 (1.8726/0.7393)	mem 34604MB
[2025-01-19 14:11:08 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][300/312]	eta 0:00:08 lr 0.001122	time 0.7150 (0.7498)	model_time 0.7149 (0.7449)	loss 3.3374 (3.0440)	grad_norm 1.8923 (1.8423/0.8133)	mem 34602MB
[2025-01-19 14:11:08 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][250/312]	eta 0:00:46 lr 0.001125	time 0.7244 (0.7471)	model_time 0.7240 (0.7408)	loss 2.5015 (2.9584)	grad_norm 3.1906 (1.8801/0.7388)	mem 34604MB
[2025-01-19 14:11:15 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][310/312]	eta 0:00:01 lr 0.001121	time 0.7116 (0.7495)	model_time 0.7115 (0.7448)	loss 3.4501 (3.0515)	grad_norm 1.5880 (1.8077/0.7848)	mem 34602MB
[2025-01-19 14:11:16 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][260/312]	eta 0:00:38 lr 0.001124	time 0.7252 (0.7465)	model_time 0.7248 (0.7405)	loss 3.1624 (2.9583)	grad_norm 1.8667 (1.8910/0.7539)	mem 34604MB
[2025-01-19 14:11:16 internimage_b_1k_224] (main.py 519): INFO EPOCH 194 training takes 0:03:53
[2025-01-19 14:11:16 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_194.pth saving......
[2025-01-19 14:11:19 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_194.pth saved !!!
[2025-01-19 14:11:23 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][270/312]	eta 0:00:31 lr 0.001124	time 0.7146 (0.7458)	model_time 0.7144 (0.7400)	loss 2.8133 (2.9474)	grad_norm 1.5488 (1.8758/0.7473)	mem 34604MB
[2025-01-19 14:11:27 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.716 (7.716)	Loss 0.7580 (0.7580)	Acc@1 84.644 (84.644)	Acc@5 97.241 (97.241)	Mem 34602MB
[2025-01-19 14:11:30 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][280/312]	eta 0:00:23 lr 0.001123	time 0.8496 (0.7455)	model_time 0.8495 (0.7399)	loss 3.0210 (2.9510)	grad_norm 1.0124 (1.8559/0.7439)	mem 34604MB
[2025-01-19 14:11:31 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.994)	Loss 0.9518 (0.8500)	Acc@1 79.541 (82.444)	Acc@5 95.410 (96.322)	Mem 34602MB
[2025-01-19 14:11:31 internimage_b_1k_224] (main.py 575): INFO [Epoch:194] * Acc@1 82.318 Acc@5 96.351
[2025-01-19 14:11:31 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.3%
[2025-01-19 14:11:31 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.47%
[2025-01-19 14:11:38 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][290/312]	eta 0:00:16 lr 0.001122	time 0.7218 (0.7446)	model_time 0.7213 (0.7392)	loss 3.7023 (2.9568)	grad_norm 2.1738 (1.8606/0.7418)	mem 34604MB
[2025-01-19 14:11:40 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.094 (9.094)	Loss 0.6926 (0.6926)	Acc@1 85.205 (85.205)	Acc@5 97.949 (97.949)	Mem 34602MB
[2025-01-19 14:11:45 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.254)	Loss 0.9480 (0.8063)	Acc@1 78.760 (82.841)	Acc@5 95.044 (96.498)	Mem 34602MB
[2025-01-19 14:11:45 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][300/312]	eta 0:00:08 lr 0.001122	time 0.7133 (0.7438)	model_time 0.7132 (0.7385)	loss 2.3752 (2.9602)	grad_norm 1.7854 (1.8620/0.7400)	mem 34604MB
[2025-01-19 14:11:45 internimage_b_1k_224] (main.py 575): INFO [Epoch:194] * Acc@1 82.702 Acc@5 96.541
[2025-01-19 14:11:45 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.7%
[2025-01-19 14:11:45 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:11:49 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:11:49 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.70%
[2025-01-19 14:11:51 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][0/312]	eta 0:11:06 lr 0.001121	time 2.1371 (2.1371)	model_time 0.7393 (0.7393)	loss 2.0614 (2.0614)	grad_norm 2.2390 (2.2390/0.0000)	mem 34602MB
[2025-01-19 14:11:52 internimage_b_1k_224] (main.py 510): INFO Train: [194/300][310/312]	eta 0:00:01 lr 0.001121	time 0.7920 (0.7431)	model_time 0.7919 (0.7380)	loss 3.0625 (2.9593)	grad_norm 2.4440 (1.8553/0.7129)	mem 34604MB
[2025-01-19 14:11:53 internimage_b_1k_224] (main.py 519): INFO EPOCH 194 training takes 0:03:51
[2025-01-19 14:11:53 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_194.pth saving......
[2025-01-19 14:11:56 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_194.pth saved !!!
[2025-01-19 14:11:58 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][10/312]	eta 0:04:25 lr 0.001121	time 0.7192 (0.8783)	model_time 0.7191 (0.7509)	loss 2.2736 (3.0321)	grad_norm 1.1258 (1.3754/0.4530)	mem 34602MB
[2025-01-19 14:12:03 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.133 (7.133)	Loss 0.7307 (0.7307)	Acc@1 85.034 (85.034)	Acc@5 97.656 (97.656)	Mem 34604MB
[2025-01-19 14:12:06 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][20/312]	eta 0:04:01 lr 0.001120	time 0.7194 (0.8267)	model_time 0.7190 (0.7598)	loss 2.9342 (2.8909)	grad_norm 1.3176 (1.4095/0.5206)	mem 34602MB
[2025-01-19 14:12:06 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.946)	Loss 0.9482 (0.8363)	Acc@1 79.199 (82.453)	Acc@5 95.239 (96.276)	Mem 34604MB
[2025-01-19 14:12:06 internimage_b_1k_224] (main.py 575): INFO [Epoch:194] * Acc@1 82.300 Acc@5 96.291
[2025-01-19 14:12:06 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.3%
[2025-01-19 14:12:06 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.34%
[2025-01-19 14:12:14 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][30/312]	eta 0:03:48 lr 0.001119	time 0.7179 (0.8105)	model_time 0.7175 (0.7650)	loss 3.3084 (2.9113)	grad_norm 2.5446 (1.4653/0.4988)	mem 34602MB
[2025-01-19 14:12:15 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.805 (8.805)	Loss 0.6888 (0.6888)	Acc@1 85.352 (85.352)	Acc@5 97.900 (97.900)	Mem 34604MB
[2025-01-19 14:12:20 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.183 (1.236)	Loss 0.9473 (0.8048)	Acc@1 79.224 (82.950)	Acc@5 95.020 (96.427)	Mem 34604MB
[2025-01-19 14:12:20 internimage_b_1k_224] (main.py 575): INFO [Epoch:194] * Acc@1 82.760 Acc@5 96.485
[2025-01-19 14:12:20 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.8%
[2025-01-19 14:12:20 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:12:21 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][40/312]	eta 0:03:35 lr 0.001119	time 0.7218 (0.7921)	model_time 0.7216 (0.7576)	loss 2.9089 (2.8969)	grad_norm 1.4902 (1.5882/0.5882)	mem 34602MB
[2025-01-19 14:12:24 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:12:24 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.76%
[2025-01-19 14:12:26 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][0/312]	eta 0:10:19 lr 0.001121	time 1.9866 (1.9866)	model_time 0.7372 (0.7372)	loss 3.1269 (3.1269)	grad_norm 2.3968 (2.3968/0.0000)	mem 34604MB
[2025-01-19 14:12:29 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][50/312]	eta 0:03:24 lr 0.001118	time 0.7417 (0.7804)	model_time 0.7415 (0.7527)	loss 3.2831 (2.9259)	grad_norm 1.1235 (1.6730/0.6461)	mem 34602MB
[2025-01-19 14:12:34 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][10/312]	eta 0:04:23 lr 0.001121	time 0.8089 (0.8709)	model_time 0.8087 (0.7570)	loss 2.0101 (2.9524)	grad_norm 2.8006 (2.3137/0.8568)	mem 34604MB
[2025-01-19 14:12:36 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][60/312]	eta 0:03:15 lr 0.001118	time 0.7228 (0.7745)	model_time 0.7223 (0.7512)	loss 3.2516 (2.9143)	grad_norm 2.6600 (1.6853/0.6754)	mem 34602MB
[2025-01-19 14:12:41 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][20/312]	eta 0:03:57 lr 0.001120	time 0.7217 (0.8140)	model_time 0.7215 (0.7542)	loss 3.6839 (2.9264)	grad_norm 1.0545 (1.9936/0.8130)	mem 34604MB
[2025-01-19 14:12:43 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][70/312]	eta 0:03:06 lr 0.001117	time 0.7577 (0.7697)	model_time 0.7572 (0.7497)	loss 3.2154 (2.9250)	grad_norm 2.1398 (1.6280/0.6550)	mem 34602MB
[2025-01-19 14:12:49 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][30/312]	eta 0:03:45 lr 0.001119	time 0.8220 (0.8001)	model_time 0.8218 (0.7595)	loss 2.7188 (2.8998)	grad_norm 1.5898 (1.8888/0.7261)	mem 34604MB
[2025-01-19 14:12:51 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][80/312]	eta 0:02:57 lr 0.001116	time 0.7334 (0.7648)	model_time 0.7332 (0.7472)	loss 2.7843 (2.9281)	grad_norm 2.8334 (1.6125/0.6378)	mem 34602MB
[2025-01-19 14:12:56 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][40/312]	eta 0:03:33 lr 0.001119	time 0.7158 (0.7856)	model_time 0.7154 (0.7548)	loss 3.2502 (2.9362)	grad_norm 1.5372 (1.7879/0.6756)	mem 34604MB
[2025-01-19 14:12:58 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][90/312]	eta 0:02:49 lr 0.001116	time 0.8178 (0.7633)	model_time 0.8176 (0.7476)	loss 3.1143 (2.9497)	grad_norm 2.7947 (1.7485/0.8298)	mem 34602MB
[2025-01-19 14:13:04 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][50/312]	eta 0:03:24 lr 0.001118	time 0.7153 (0.7788)	model_time 0.7152 (0.7539)	loss 3.4300 (2.9039)	grad_norm 1.5822 (1.7402/0.6489)	mem 34604MB
[2025-01-19 14:13:06 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][100/312]	eta 0:02:41 lr 0.001115	time 0.7282 (0.7630)	model_time 0.7278 (0.7488)	loss 2.6700 (2.9210)	grad_norm 2.9476 (1.8130/0.8538)	mem 34602MB
[2025-01-19 14:13:11 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][60/312]	eta 0:03:14 lr 0.001118	time 0.7566 (0.7703)	model_time 0.7565 (0.7495)	loss 2.9504 (2.9385)	grad_norm 1.0975 (1.7129/0.6550)	mem 34604MB
[2025-01-19 14:13:13 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][110/312]	eta 0:02:33 lr 0.001115	time 0.8169 (0.7614)	model_time 0.8167 (0.7485)	loss 3.2053 (2.9226)	grad_norm 1.0558 (1.7990/0.8366)	mem 34602MB
[2025-01-19 14:13:18 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][70/312]	eta 0:03:04 lr 0.001117	time 0.7276 (0.7644)	model_time 0.7275 (0.7465)	loss 3.4378 (2.9325)	grad_norm 2.6567 (1.7152/0.6416)	mem 34604MB
[2025-01-19 14:13:21 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][120/312]	eta 0:02:26 lr 0.001114	time 0.8026 (0.7611)	model_time 0.8021 (0.7491)	loss 2.2307 (2.9177)	grad_norm 1.6633 (1.7845/0.8084)	mem 34602MB
[2025-01-19 14:13:26 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][80/312]	eta 0:02:56 lr 0.001116	time 0.7227 (0.7594)	model_time 0.7223 (0.7436)	loss 3.2946 (2.9264)	grad_norm 2.8521 (1.7406/0.6297)	mem 34604MB
[2025-01-19 14:13:28 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][130/312]	eta 0:02:18 lr 0.001113	time 0.7343 (0.7598)	model_time 0.7341 (0.7488)	loss 2.8667 (2.9196)	grad_norm 1.6829 (1.7556/0.7850)	mem 34602MB
[2025-01-19 14:13:33 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][90/312]	eta 0:02:47 lr 0.001116	time 0.7160 (0.7556)	model_time 0.7158 (0.7415)	loss 3.6815 (2.9416)	grad_norm 1.9216 (1.7340/0.6272)	mem 34604MB
[2025-01-19 14:13:36 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][140/312]	eta 0:02:10 lr 0.001113	time 0.7233 (0.7603)	model_time 0.7232 (0.7500)	loss 2.7212 (2.9402)	grad_norm 0.9634 (1.7202/0.7723)	mem 34602MB
[2025-01-19 14:13:40 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][100/312]	eta 0:02:39 lr 0.001115	time 0.7430 (0.7529)	model_time 0.7426 (0.7402)	loss 2.9285 (2.9520)	grad_norm 0.8092 (1.8080/0.7368)	mem 34604MB
[2025-01-19 14:13:44 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][150/312]	eta 0:02:03 lr 0.001112	time 0.7254 (0.7608)	model_time 0.7250 (0.7511)	loss 3.1831 (2.9551)	grad_norm 1.2102 (1.7304/0.7781)	mem 34602MB
[2025-01-19 14:13:48 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][110/312]	eta 0:02:31 lr 0.001115	time 0.7314 (0.7510)	model_time 0.7312 (0.7394)	loss 3.7245 (2.9579)	grad_norm 3.1220 (1.8450/0.7873)	mem 34604MB
[2025-01-19 14:13:51 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][160/312]	eta 0:01:55 lr 0.001112	time 0.7149 (0.7596)	model_time 0.7144 (0.7506)	loss 2.5611 (2.9519)	grad_norm 2.1356 (1.7409/0.7708)	mem 34602MB
[2025-01-19 14:13:55 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][120/312]	eta 0:02:24 lr 0.001114	time 0.7165 (0.7502)	model_time 0.7164 (0.7395)	loss 2.5280 (2.9465)	grad_norm 1.4109 (1.8350/0.7674)	mem 34604MB
[2025-01-19 14:13:58 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][170/312]	eta 0:01:47 lr 0.001111	time 0.7973 (0.7581)	model_time 0.7972 (0.7495)	loss 2.4750 (2.9432)	grad_norm 1.7960 (1.7243/0.7596)	mem 34602MB
[2025-01-19 14:14:03 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][130/312]	eta 0:02:16 lr 0.001113	time 0.8095 (0.7508)	model_time 0.8091 (0.7409)	loss 2.1558 (2.9309)	grad_norm 1.5857 (1.8059/0.7610)	mem 34604MB
[2025-01-19 14:14:06 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][180/312]	eta 0:01:40 lr 0.001110	time 0.7180 (0.7577)	model_time 0.7175 (0.7496)	loss 2.7887 (2.9454)	grad_norm 2.0282 (1.7179/0.7470)	mem 34602MB
[2025-01-19 14:14:10 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][140/312]	eta 0:02:09 lr 0.001113	time 0.8047 (0.7518)	model_time 0.8043 (0.7426)	loss 3.0296 (2.9326)	grad_norm 3.5121 (1.8102/0.7675)	mem 34604MB
[2025-01-19 14:14:13 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][190/312]	eta 0:01:32 lr 0.001110	time 0.7260 (0.7566)	model_time 0.7256 (0.7489)	loss 2.7460 (2.9465)	grad_norm 2.2429 (1.7159/0.7382)	mem 34602MB
[2025-01-19 14:14:18 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][150/312]	eta 0:02:01 lr 0.001112	time 0.8093 (0.7529)	model_time 0.8092 (0.7443)	loss 3.0787 (2.9308)	grad_norm 1.4035 (1.8590/0.7931)	mem 34604MB
[2025-01-19 14:14:21 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][200/312]	eta 0:01:24 lr 0.001109	time 0.7286 (0.7551)	model_time 0.7282 (0.7478)	loss 3.2007 (2.9668)	grad_norm 1.8332 (1.6993/0.7288)	mem 34602MB
[2025-01-19 14:14:25 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][160/312]	eta 0:01:54 lr 0.001112	time 0.8046 (0.7514)	model_time 0.8042 (0.7433)	loss 2.9887 (2.9279)	grad_norm 1.0319 (1.8401/0.7785)	mem 34604MB
[2025-01-19 14:14:28 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][210/312]	eta 0:01:16 lr 0.001109	time 0.8141 (0.7548)	model_time 0.8139 (0.7478)	loss 3.4084 (2.9602)	grad_norm 2.0864 (1.6883/0.7172)	mem 34602MB
[2025-01-19 14:14:33 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][170/312]	eta 0:01:46 lr 0.001111	time 0.7175 (0.7515)	model_time 0.7173 (0.7439)	loss 3.2587 (2.9348)	grad_norm 1.8903 (1.8406/0.7701)	mem 34604MB
[2025-01-19 14:14:36 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][220/312]	eta 0:01:09 lr 0.001108	time 0.8044 (0.7552)	model_time 0.8042 (0.7485)	loss 3.5555 (2.9648)	grad_norm 1.5142 (1.7103/0.7223)	mem 34602MB
[2025-01-19 14:14:40 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][180/312]	eta 0:01:39 lr 0.001110	time 0.7174 (0.7501)	model_time 0.7173 (0.7428)	loss 2.6163 (2.9302)	grad_norm 1.6254 (1.8363/0.7603)	mem 34604MB
[2025-01-19 14:14:43 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][230/312]	eta 0:01:01 lr 0.001108	time 0.8184 (0.7549)	model_time 0.8182 (0.7484)	loss 1.9028 (2.9552)	grad_norm 1.0590 (1.7165/0.7149)	mem 34602MB
[2025-01-19 14:14:47 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][190/312]	eta 0:01:31 lr 0.001110	time 0.7309 (0.7491)	model_time 0.7304 (0.7422)	loss 3.4681 (2.9451)	grad_norm 1.8487 (1.8365/0.7536)	mem 34604MB
[2025-01-19 14:14:51 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][240/312]	eta 0:00:54 lr 0.001107	time 0.7988 (0.7550)	model_time 0.7983 (0.7488)	loss 3.6275 (2.9531)	grad_norm 1.5958 (1.7411/0.7652)	mem 34602MB
[2025-01-19 14:14:55 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][200/312]	eta 0:01:23 lr 0.001109	time 0.7348 (0.7479)	model_time 0.7344 (0.7414)	loss 3.2474 (2.9395)	grad_norm 1.5381 (1.8369/0.7435)	mem 34604MB
[2025-01-19 14:14:58 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][250/312]	eta 0:00:46 lr 0.001106	time 0.7311 (0.7545)	model_time 0.7310 (0.7485)	loss 2.2809 (2.9473)	grad_norm 1.5539 (1.7618/0.7714)	mem 34602MB
[2025-01-19 14:15:02 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][210/312]	eta 0:01:16 lr 0.001109	time 0.7397 (0.7469)	model_time 0.7395 (0.7407)	loss 3.7231 (2.9388)	grad_norm 3.0697 (1.8418/0.7541)	mem 34604MB
[2025-01-19 14:15:06 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][260/312]	eta 0:00:39 lr 0.001106	time 0.7239 (0.7547)	model_time 0.7237 (0.7490)	loss 2.7558 (2.9455)	grad_norm 2.2076 (1.7860/0.7951)	mem 34602MB
[2025-01-19 14:15:09 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][220/312]	eta 0:01:08 lr 0.001108	time 0.7486 (0.7464)	model_time 0.7482 (0.7404)	loss 3.7937 (2.9601)	grad_norm 1.1530 (1.8469/0.7637)	mem 34604MB
[2025-01-19 14:15:13 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][270/312]	eta 0:00:31 lr 0.001105	time 0.7158 (0.7545)	model_time 0.7156 (0.7490)	loss 2.1376 (2.9481)	grad_norm 2.6806 (1.7989/0.7888)	mem 34602MB
[2025-01-19 14:15:16 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][230/312]	eta 0:01:01 lr 0.001108	time 0.7143 (0.7456)	model_time 0.7141 (0.7399)	loss 2.7763 (2.9495)	grad_norm 1.2914 (1.8430/0.7555)	mem 34604MB
[2025-01-19 14:15:21 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][280/312]	eta 0:00:24 lr 0.001105	time 0.7226 (0.7538)	model_time 0.7224 (0.7484)	loss 2.9204 (2.9598)	grad_norm 1.6402 (1.7957/0.7795)	mem 34602MB
[2025-01-19 14:15:24 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][240/312]	eta 0:00:53 lr 0.001107	time 0.7168 (0.7452)	model_time 0.7164 (0.7396)	loss 2.9775 (2.9478)	grad_norm 1.2072 (1.8333/0.7440)	mem 34604MB
[2025-01-19 14:15:28 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][290/312]	eta 0:00:16 lr 0.001104	time 0.7988 (0.7532)	model_time 0.7986 (0.7480)	loss 3.6633 (2.9600)	grad_norm 1.0301 (1.7873/0.7742)	mem 34602MB
[2025-01-19 14:15:32 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][250/312]	eta 0:00:46 lr 0.001106	time 0.8106 (0.7463)	model_time 0.8105 (0.7410)	loss 2.6188 (2.9503)	grad_norm 1.1409 (1.8594/0.7698)	mem 34604MB
[2025-01-19 14:15:35 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][300/312]	eta 0:00:09 lr 0.001103	time 0.7134 (0.7525)	model_time 0.7133 (0.7475)	loss 3.1153 (2.9566)	grad_norm 2.6991 (1.8065/0.7785)	mem 34602MB
[2025-01-19 14:15:39 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][260/312]	eta 0:00:38 lr 0.001106	time 0.8187 (0.7471)	model_time 0.8182 (0.7420)	loss 3.7633 (2.9516)	grad_norm 3.4493 (1.8824/0.8343)	mem 34604MB
[2025-01-19 14:15:43 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][310/312]	eta 0:00:01 lr 0.001103	time 0.7153 (0.7519)	model_time 0.7152 (0.7471)	loss 3.0392 (2.9575)	grad_norm 2.0589 (1.8262/0.7746)	mem 34602MB
[2025-01-19 14:15:43 internimage_b_1k_224] (main.py 519): INFO EPOCH 195 training takes 0:03:54
[2025-01-19 14:15:43 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_195.pth saving......
[2025-01-19 14:15:47 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_195.pth saved !!!
[2025-01-19 14:15:47 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][270/312]	eta 0:00:31 lr 0.001105	time 0.8108 (0.7476)	model_time 0.8107 (0.7426)	loss 3.2494 (2.9509)	grad_norm 1.6145 (1.8879/0.8318)	mem 34604MB
[2025-01-19 14:15:54 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][280/312]	eta 0:00:23 lr 0.001105	time 0.8033 (0.7478)	model_time 0.8031 (0.7430)	loss 3.5012 (2.9630)	grad_norm 1.9309 (1.8837/0.8191)	mem 34604MB
[2025-01-19 14:15:54 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.582 (7.582)	Loss 0.7479 (0.7479)	Acc@1 85.107 (85.107)	Acc@5 97.412 (97.412)	Mem 34602MB
[2025-01-19 14:15:58 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.987)	Loss 0.9967 (0.8513)	Acc@1 78.369 (82.686)	Acc@5 95.093 (96.267)	Mem 34602MB
[2025-01-19 14:15:58 internimage_b_1k_224] (main.py 575): INFO [Epoch:195] * Acc@1 82.592 Acc@5 96.321
[2025-01-19 14:15:58 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.6%
[2025-01-19 14:15:58 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 14:16:01 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 14:16:01 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.59%
[2025-01-19 14:16:02 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][290/312]	eta 0:00:16 lr 0.001104	time 0.7135 (0.7477)	model_time 0.7131 (0.7431)	loss 3.1748 (2.9686)	grad_norm 1.1510 (1.8642/0.8154)	mem 34604MB
[2025-01-19 14:16:09 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.409 (7.409)	Loss 0.6937 (0.6937)	Acc@1 85.205 (85.205)	Acc@5 97.925 (97.925)	Mem 34602MB
[2025-01-19 14:16:09 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][300/312]	eta 0:00:08 lr 0.001103	time 0.7174 (0.7473)	model_time 0.7173 (0.7428)	loss 3.0189 (2.9649)	grad_norm 5.1576 (1.8594/0.8342)	mem 34604MB
[2025-01-19 14:16:12 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.968)	Loss 0.9479 (0.8068)	Acc@1 78.687 (82.884)	Acc@5 95.142 (96.524)	Mem 34602MB
[2025-01-19 14:16:12 internimage_b_1k_224] (main.py 575): INFO [Epoch:195] * Acc@1 82.746 Acc@5 96.567
[2025-01-19 14:16:12 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.7%
[2025-01-19 14:16:12 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:16:16 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:16:16 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.75%
[2025-01-19 14:16:16 internimage_b_1k_224] (main.py 510): INFO Train: [195/300][310/312]	eta 0:00:01 lr 0.001103	time 0.7108 (0.7464)	model_time 0.7107 (0.7420)	loss 2.8359 (2.9606)	grad_norm 1.0388 (1.8511/0.8401)	mem 34604MB
[2025-01-19 14:16:17 internimage_b_1k_224] (main.py 519): INFO EPOCH 195 training takes 0:03:52
[2025-01-19 14:16:17 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_195.pth saving......
[2025-01-19 14:16:18 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][0/312]	eta 0:10:37 lr 0.001103	time 2.0418 (2.0418)	model_time 0.7341 (0.7341)	loss 2.4788 (2.4788)	grad_norm 1.3869 (1.3869/0.0000)	mem 34602MB
[2025-01-19 14:16:20 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_195.pth saved !!!
[2025-01-19 14:16:25 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][10/312]	eta 0:04:16 lr 0.001102	time 0.7191 (0.8478)	model_time 0.7189 (0.7286)	loss 3.1957 (2.9559)	grad_norm 2.5402 (1.8357/0.4644)	mem 34602MB
[2025-01-19 14:16:28 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.609 (7.609)	Loss 0.7420 (0.7420)	Acc@1 85.034 (85.034)	Acc@5 97.388 (97.388)	Mem 34604MB
[2025-01-19 14:16:31 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.981)	Loss 0.9810 (0.8430)	Acc@1 78.418 (82.429)	Acc@5 95.386 (96.393)	Mem 34604MB
[2025-01-19 14:16:31 internimage_b_1k_224] (main.py 575): INFO [Epoch:195] * Acc@1 82.280 Acc@5 96.401
[2025-01-19 14:16:31 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.3%
[2025-01-19 14:16:31 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.34%
[2025-01-19 14:16:33 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][20/312]	eta 0:03:54 lr 0.001101	time 0.7256 (0.8020)	model_time 0.7251 (0.7394)	loss 2.1462 (2.7870)	grad_norm 1.8666 (1.8932/0.5223)	mem 34602MB
[2025-01-19 14:16:40 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][30/312]	eta 0:03:41 lr 0.001101	time 0.8323 (0.7860)	model_time 0.8318 (0.7435)	loss 3.1071 (2.8929)	grad_norm 0.7633 (1.6611/0.5807)	mem 34602MB
[2025-01-19 14:16:41 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.270 (9.270)	Loss 0.6894 (0.6894)	Acc@1 85.327 (85.327)	Acc@5 97.900 (97.900)	Mem 34604MB
[2025-01-19 14:16:45 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.248)	Loss 0.9468 (0.8051)	Acc@1 79.272 (82.966)	Acc@5 95.068 (96.451)	Mem 34604MB
[2025-01-19 14:16:45 internimage_b_1k_224] (main.py 575): INFO [Epoch:195] * Acc@1 82.772 Acc@5 96.511
[2025-01-19 14:16:45 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.8%
[2025-01-19 14:16:45 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:16:47 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][40/312]	eta 0:03:30 lr 0.001100	time 0.7235 (0.7733)	model_time 0.7231 (0.7411)	loss 2.5078 (2.8581)	grad_norm 1.1602 (1.5683/0.5425)	mem 34602MB
[2025-01-19 14:16:49 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:16:49 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.77%
[2025-01-19 14:16:51 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][0/312]	eta 0:10:23 lr 0.001103	time 1.9970 (1.9970)	model_time 0.7401 (0.7401)	loss 3.2296 (3.2296)	grad_norm 4.8502 (4.8502/0.0000)	mem 34604MB
[2025-01-19 14:16:55 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][50/312]	eta 0:03:22 lr 0.001100	time 0.8087 (0.7716)	model_time 0.8082 (0.7456)	loss 2.7972 (2.8712)	grad_norm 1.9770 (1.6288/0.5616)	mem 34602MB
[2025-01-19 14:16:59 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][10/312]	eta 0:04:15 lr 0.001102	time 0.7243 (0.8456)	model_time 0.7242 (0.7310)	loss 2.3409 (2.9126)	grad_norm 2.2741 (2.8843/1.1267)	mem 34604MB
[2025-01-19 14:17:03 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][60/312]	eta 0:03:13 lr 0.001099	time 0.7547 (0.7677)	model_time 0.7542 (0.7459)	loss 2.1462 (2.8930)	grad_norm 2.4374 (1.6519/0.5651)	mem 34602MB
[2025-01-19 14:17:06 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][20/312]	eta 0:03:50 lr 0.001101	time 0.7288 (0.7898)	model_time 0.7286 (0.7296)	loss 2.7336 (2.7837)	grad_norm 1.8090 (2.3812/1.0699)	mem 34604MB
[2025-01-19 14:17:10 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][70/312]	eta 0:03:05 lr 0.001099	time 0.7177 (0.7666)	model_time 0.7175 (0.7478)	loss 3.0616 (2.9291)	grad_norm 0.9520 (1.7263/0.7635)	mem 34602MB
[2025-01-19 14:17:13 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][30/312]	eta 0:03:37 lr 0.001101	time 0.7432 (0.7705)	model_time 0.7430 (0.7296)	loss 3.2586 (2.8449)	grad_norm 1.5952 (2.0368/1.0420)	mem 34604MB
[2025-01-19 14:17:18 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][80/312]	eta 0:02:57 lr 0.001098	time 0.8114 (0.7656)	model_time 0.8110 (0.7491)	loss 2.9600 (2.9595)	grad_norm 1.5077 (1.6864/0.7389)	mem 34602MB
[2025-01-19 14:17:20 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][40/312]	eta 0:03:27 lr 0.001100	time 0.7508 (0.7620)	model_time 0.7504 (0.7310)	loss 3.4115 (2.8745)	grad_norm 1.4299 (1.8893/0.9524)	mem 34604MB
[2025-01-19 14:17:25 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][90/312]	eta 0:02:49 lr 0.001097	time 0.7171 (0.7624)	model_time 0.7167 (0.7476)	loss 3.3871 (2.9722)	grad_norm 1.4406 (1.6547/0.7179)	mem 34602MB
[2025-01-19 14:17:28 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][50/312]	eta 0:03:18 lr 0.001100	time 0.7155 (0.7572)	model_time 0.7154 (0.7322)	loss 3.1607 (2.9346)	grad_norm 2.3935 (1.8250/0.8849)	mem 34604MB
[2025-01-19 14:17:32 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][100/312]	eta 0:02:40 lr 0.001097	time 0.7277 (0.7592)	model_time 0.7273 (0.7459)	loss 2.6980 (2.9807)	grad_norm 1.8098 (1.6026/0.7061)	mem 34602MB
[2025-01-19 14:17:35 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][60/312]	eta 0:03:10 lr 0.001099	time 0.7205 (0.7571)	model_time 0.7203 (0.7361)	loss 2.2811 (2.9148)	grad_norm 2.7571 (1.8701/0.8812)	mem 34604MB
[2025-01-19 14:17:40 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][110/312]	eta 0:02:33 lr 0.001096	time 0.8093 (0.7579)	model_time 0.8088 (0.7457)	loss 3.1390 (2.9985)	grad_norm 2.2570 (1.6144/0.6823)	mem 34602MB
[2025-01-19 14:17:43 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][70/312]	eta 0:03:03 lr 0.001099	time 0.7501 (0.7591)	model_time 0.7497 (0.7410)	loss 3.2224 (2.9181)	grad_norm 2.5695 (1.9562/0.9434)	mem 34604MB
[2025-01-19 14:17:47 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][120/312]	eta 0:02:25 lr 0.001096	time 0.7194 (0.7564)	model_time 0.7189 (0.7453)	loss 3.6864 (3.0062)	grad_norm 1.0233 (1.6130/0.6707)	mem 34602MB
[2025-01-19 14:17:51 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][80/312]	eta 0:02:56 lr 0.001098	time 0.8052 (0.7617)	model_time 0.8051 (0.7459)	loss 3.3368 (2.9225)	grad_norm 1.7491 (1.9256/0.9247)	mem 34604MB
[2025-01-19 14:17:55 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][130/312]	eta 0:02:17 lr 0.001095	time 0.7242 (0.7547)	model_time 0.7237 (0.7443)	loss 3.1686 (2.9925)	grad_norm 0.8070 (1.6359/0.6836)	mem 34602MB
[2025-01-19 14:17:58 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][90/312]	eta 0:02:48 lr 0.001097	time 0.7239 (0.7595)	model_time 0.7237 (0.7454)	loss 3.4010 (2.9287)	grad_norm 3.2640 (2.0078/0.9554)	mem 34604MB
[2025-01-19 14:18:02 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][140/312]	eta 0:02:09 lr 0.001094	time 0.8091 (0.7536)	model_time 0.8090 (0.7439)	loss 3.3640 (2.9773)	grad_norm 0.8794 (1.6344/0.7005)	mem 34602MB
[2025-01-19 14:18:06 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][100/312]	eta 0:02:41 lr 0.001097	time 0.8103 (0.7599)	model_time 0.8098 (0.7471)	loss 2.6106 (2.9361)	grad_norm 3.0947 (2.0122/0.9440)	mem 34604MB
[2025-01-19 14:18:10 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][150/312]	eta 0:02:02 lr 0.001094	time 0.8010 (0.7540)	model_time 0.8006 (0.7449)	loss 3.3570 (2.9769)	grad_norm 1.5400 (1.6591/0.6922)	mem 34602MB
[2025-01-19 14:18:13 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][110/312]	eta 0:02:32 lr 0.001096	time 0.7106 (0.7573)	model_time 0.7105 (0.7456)	loss 3.1163 (2.9513)	grad_norm 1.1989 (1.9680/0.9187)	mem 34604MB
[2025-01-19 14:18:17 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][160/312]	eta 0:01:54 lr 0.001093	time 0.7232 (0.7530)	model_time 0.7228 (0.7445)	loss 3.4808 (2.9887)	grad_norm 1.2065 (1.6868/0.7125)	mem 34602MB
[2025-01-19 14:18:21 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][120/312]	eta 0:02:24 lr 0.001096	time 0.7213 (0.7548)	model_time 0.7211 (0.7441)	loss 3.0524 (2.9466)	grad_norm 3.0336 (1.9707/0.9005)	mem 34604MB
[2025-01-19 14:18:25 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][170/312]	eta 0:01:47 lr 0.001093	time 0.8085 (0.7536)	model_time 0.8084 (0.7455)	loss 3.0184 (2.9875)	grad_norm 1.9377 (1.7234/0.7473)	mem 34602MB
[2025-01-19 14:18:28 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][130/312]	eta 0:02:16 lr 0.001095	time 0.7212 (0.7525)	model_time 0.7208 (0.7426)	loss 3.2230 (2.9455)	grad_norm 1.0021 (1.9417/0.8829)	mem 34604MB
[2025-01-19 14:18:32 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][180/312]	eta 0:01:39 lr 0.001092	time 0.7273 (0.7537)	model_time 0.7272 (0.7461)	loss 2.4773 (2.9807)	grad_norm 1.3085 (1.7190/0.7408)	mem 34602MB
[2025-01-19 14:18:35 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][140/312]	eta 0:02:09 lr 0.001094	time 0.7107 (0.7508)	model_time 0.7105 (0.7415)	loss 3.1616 (2.9454)	grad_norm 1.9237 (1.9194/0.8595)	mem 34604MB
[2025-01-19 14:18:40 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][190/312]	eta 0:01:32 lr 0.001092	time 0.7166 (0.7548)	model_time 0.7161 (0.7475)	loss 3.1484 (2.9801)	grad_norm 2.4956 (1.7374/0.7546)	mem 34602MB
[2025-01-19 14:18:42 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][150/312]	eta 0:02:01 lr 0.001094	time 0.7083 (0.7490)	model_time 0.7082 (0.7403)	loss 3.0726 (2.9513)	grad_norm 4.2100 (1.9663/0.9046)	mem 34604MB
[2025-01-19 14:18:48 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][200/312]	eta 0:01:24 lr 0.001091	time 0.8090 (0.7552)	model_time 0.8088 (0.7484)	loss 2.4017 (2.9800)	grad_norm 3.7525 (1.7563/0.7554)	mem 34602MB
[2025-01-19 14:18:50 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][160/312]	eta 0:01:53 lr 0.001093	time 0.7168 (0.7477)	model_time 0.7163 (0.7396)	loss 3.4667 (2.9690)	grad_norm 2.7645 (1.9998/0.9165)	mem 34604MB
[2025-01-19 14:18:55 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][210/312]	eta 0:01:16 lr 0.001090	time 0.7243 (0.7546)	model_time 0.7242 (0.7480)	loss 2.7622 (2.9784)	grad_norm 1.2646 (1.7559/0.7424)	mem 34602MB
[2025-01-19 14:18:57 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][170/312]	eta 0:01:46 lr 0.001093	time 0.7214 (0.7476)	model_time 0.7212 (0.7399)	loss 3.9264 (2.9898)	grad_norm 1.8383 (1.9956/0.8976)	mem 34604MB
[2025-01-19 14:19:02 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][220/312]	eta 0:01:09 lr 0.001090	time 0.7431 (0.7533)	model_time 0.7429 (0.7471)	loss 2.9713 (2.9791)	grad_norm 0.9927 (1.7299/0.7372)	mem 34602MB
[2025-01-19 14:19:05 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][180/312]	eta 0:01:38 lr 0.001092	time 0.8380 (0.7484)	model_time 0.8378 (0.7411)	loss 3.0705 (2.9874)	grad_norm 2.8809 (1.9915/0.8827)	mem 34604MB
[2025-01-19 14:19:10 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][230/312]	eta 0:01:01 lr 0.001089	time 0.8037 (0.7537)	model_time 0.8033 (0.7477)	loss 2.9801 (2.9834)	grad_norm 1.1055 (1.7238/0.7360)	mem 34602MB
[2025-01-19 14:19:12 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][190/312]	eta 0:01:31 lr 0.001092	time 0.7230 (0.7495)	model_time 0.7229 (0.7426)	loss 2.9660 (2.9701)	grad_norm 2.4926 (1.9874/0.8728)	mem 34604MB
[2025-01-19 14:19:17 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][240/312]	eta 0:00:54 lr 0.001089	time 0.7192 (0.7530)	model_time 0.7187 (0.7472)	loss 3.0713 (2.9755)	grad_norm 1.1237 (1.7156/0.7280)	mem 34602MB
[2025-01-19 14:19:20 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][200/312]	eta 0:01:24 lr 0.001091	time 0.8078 (0.7516)	model_time 0.8073 (0.7450)	loss 3.2453 (2.9673)	grad_norm 1.4716 (1.9770/0.8594)	mem 34604MB
[2025-01-19 14:19:25 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][250/312]	eta 0:00:46 lr 0.001088	time 0.7283 (0.7521)	model_time 0.7278 (0.7465)	loss 3.4343 (2.9679)	grad_norm 1.4313 (1.7274/0.7458)	mem 34602MB
[2025-01-19 14:19:28 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][210/312]	eta 0:01:16 lr 0.001090	time 0.7201 (0.7510)	model_time 0.7197 (0.7447)	loss 3.5549 (2.9768)	grad_norm 1.0310 (1.9706/0.8487)	mem 34604MB
[2025-01-19 14:19:32 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][260/312]	eta 0:00:39 lr 0.001087	time 0.8025 (0.7517)	model_time 0.8023 (0.7464)	loss 2.7263 (2.9656)	grad_norm 1.4622 (1.7574/0.7740)	mem 34602MB
[2025-01-19 14:19:35 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][220/312]	eta 0:01:09 lr 0.001090	time 0.8104 (0.7515)	model_time 0.8103 (0.7454)	loss 3.1219 (2.9839)	grad_norm 1.7074 (1.9766/0.8327)	mem 34604MB
[2025-01-19 14:19:39 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][270/312]	eta 0:00:31 lr 0.001087	time 0.8096 (0.7516)	model_time 0.8092 (0.7464)	loss 3.1778 (2.9635)	grad_norm 2.4124 (1.7709/0.7781)	mem 34602MB
[2025-01-19 14:19:43 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][230/312]	eta 0:01:01 lr 0.001089	time 0.7174 (0.7504)	model_time 0.7169 (0.7446)	loss 2.7345 (2.9909)	grad_norm 2.0681 (1.9630/0.8207)	mem 34604MB
[2025-01-19 14:19:47 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][280/312]	eta 0:00:24 lr 0.001086	time 0.7213 (0.7513)	model_time 0.7209 (0.7462)	loss 2.6633 (2.9641)	grad_norm 1.7511 (1.7664/0.7698)	mem 34602MB
[2025-01-19 14:19:50 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][240/312]	eta 0:00:53 lr 0.001089	time 0.7242 (0.7492)	model_time 0.7241 (0.7436)	loss 3.0399 (2.9991)	grad_norm 0.8880 (1.9389/0.8174)	mem 34604MB
[2025-01-19 14:19:54 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][290/312]	eta 0:00:16 lr 0.001086	time 0.7188 (0.7512)	model_time 0.7187 (0.7464)	loss 2.7917 (2.9660)	grad_norm 1.2919 (1.7565/0.7620)	mem 34602MB
[2025-01-19 14:19:57 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][250/312]	eta 0:00:46 lr 0.001088	time 0.7181 (0.7485)	model_time 0.7177 (0.7431)	loss 2.8992 (2.9875)	grad_norm 1.2975 (1.9132/0.8136)	mem 34604MB
[2025-01-19 14:20:02 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][300/312]	eta 0:00:09 lr 0.001085	time 0.7148 (0.7514)	model_time 0.7147 (0.7467)	loss 3.6779 (2.9672)	grad_norm 1.3395 (1.7608/0.7683)	mem 34602MB
[2025-01-19 14:20:04 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][260/312]	eta 0:00:38 lr 0.001087	time 0.7490 (0.7478)	model_time 0.7489 (0.7426)	loss 2.8810 (2.9770)	grad_norm 1.0234 (1.8945/0.8106)	mem 34604MB
[2025-01-19 14:20:09 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][310/312]	eta 0:00:01 lr 0.001084	time 0.8024 (0.7515)	model_time 0.8024 (0.7469)	loss 1.8772 (2.9639)	grad_norm 1.8992 (1.7583/0.7725)	mem 34602MB
[2025-01-19 14:20:10 internimage_b_1k_224] (main.py 519): INFO EPOCH 196 training takes 0:03:54
[2025-01-19 14:20:10 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_196.pth saving......
[2025-01-19 14:20:12 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][270/312]	eta 0:00:31 lr 0.001087	time 0.7397 (0.7471)	model_time 0.7393 (0.7421)	loss 3.7221 (2.9772)	grad_norm 1.0936 (1.9089/0.8426)	mem 34604MB
[2025-01-19 14:20:13 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_196.pth saved !!!
[2025-01-19 14:20:19 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][280/312]	eta 0:00:23 lr 0.001086	time 0.7270 (0.7464)	model_time 0.7269 (0.7416)	loss 1.8433 (2.9661)	grad_norm 1.0359 (1.8973/0.8330)	mem 34604MB
[2025-01-19 14:20:21 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.568 (7.568)	Loss 0.7474 (0.7474)	Acc@1 84.888 (84.888)	Acc@5 97.607 (97.607)	Mem 34602MB
[2025-01-19 14:20:24 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.995)	Loss 0.9967 (0.8509)	Acc@1 77.930 (82.540)	Acc@5 95.190 (96.307)	Mem 34602MB
[2025-01-19 14:20:25 internimage_b_1k_224] (main.py 575): INFO [Epoch:196] * Acc@1 82.422 Acc@5 96.323
[2025-01-19 14:20:25 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.4%
[2025-01-19 14:20:25 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.59%
[2025-01-19 14:20:26 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][290/312]	eta 0:00:16 lr 0.001086	time 0.7416 (0.7462)	model_time 0.7411 (0.7415)	loss 3.1925 (2.9701)	grad_norm 1.0268 (1.8843/0.8239)	mem 34604MB
[2025-01-19 14:20:34 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][300/312]	eta 0:00:08 lr 0.001085	time 0.7114 (0.7460)	model_time 0.7113 (0.7415)	loss 3.5331 (2.9745)	grad_norm 1.3360 (1.8659/0.8009)	mem 34604MB
[2025-01-19 14:20:34 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.380 (9.380)	Loss 0.6947 (0.6947)	Acc@1 85.254 (85.254)	Acc@5 97.925 (97.925)	Mem 34602MB
[2025-01-19 14:20:39 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.286)	Loss 0.9477 (0.8071)	Acc@1 78.760 (82.919)	Acc@5 95.190 (96.535)	Mem 34602MB
[2025-01-19 14:20:39 internimage_b_1k_224] (main.py 575): INFO [Epoch:196] * Acc@1 82.782 Acc@5 96.579
[2025-01-19 14:20:39 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.8%
[2025-01-19 14:20:39 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:20:41 internimage_b_1k_224] (main.py 510): INFO Train: [196/300][310/312]	eta 0:00:01 lr 0.001084	time 0.7137 (0.7461)	model_time 0.7136 (0.7417)	loss 2.7143 (2.9765)	grad_norm 3.0297 (1.8553/0.7978)	mem 34604MB
[2025-01-19 14:20:42 internimage_b_1k_224] (main.py 519): INFO EPOCH 196 training takes 0:03:52
[2025-01-19 14:20:42 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_196.pth saving......
[2025-01-19 14:20:43 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:20:43 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.78%
[2025-01-19 14:20:45 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][0/312]	eta 0:11:34 lr 0.001084	time 2.2260 (2.2260)	model_time 0.7520 (0.7520)	loss 2.9375 (2.9375)	grad_norm 1.1151 (1.1151/0.0000)	mem 34602MB
[2025-01-19 14:20:45 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_196.pth saved !!!
[2025-01-19 14:20:53 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][10/312]	eta 0:04:33 lr 0.001084	time 0.8103 (0.9062)	model_time 0.8101 (0.7719)	loss 3.3523 (2.8274)	grad_norm 2.3157 (1.8047/0.5519)	mem 34602MB
[2025-01-19 14:20:53 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.754 (7.754)	Loss 0.7252 (0.7252)	Acc@1 84.302 (84.302)	Acc@5 97.681 (97.681)	Mem 34604MB
[2025-01-19 14:20:56 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.013)	Loss 0.9848 (0.8405)	Acc@1 78.516 (82.422)	Acc@5 95.044 (96.318)	Mem 34604MB
[2025-01-19 14:20:57 internimage_b_1k_224] (main.py 575): INFO [Epoch:196] * Acc@1 82.254 Acc@5 96.333
[2025-01-19 14:20:57 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.3%
[2025-01-19 14:20:57 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.34%
[2025-01-19 14:21:00 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][20/312]	eta 0:04:01 lr 0.001083	time 0.8072 (0.8275)	model_time 0.8070 (0.7571)	loss 2.5692 (2.9366)	grad_norm 1.5200 (1.7971/0.5152)	mem 34602MB
[2025-01-19 14:21:06 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.852 (9.852)	Loss 0.6903 (0.6903)	Acc@1 85.352 (85.352)	Acc@5 97.974 (97.974)	Mem 34604MB
[2025-01-19 14:21:08 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][30/312]	eta 0:03:44 lr 0.001083	time 0.7485 (0.7973)	model_time 0.7480 (0.7494)	loss 2.0828 (2.8732)	grad_norm 0.9131 (1.6399/0.5408)	mem 34602MB
[2025-01-19 14:21:11 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.331)	Loss 0.9462 (0.8055)	Acc@1 79.224 (82.961)	Acc@5 95.093 (96.464)	Mem 34604MB
[2025-01-19 14:21:12 internimage_b_1k_224] (main.py 575): INFO [Epoch:196] * Acc@1 82.774 Acc@5 96.519
[2025-01-19 14:21:12 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.8%
[2025-01-19 14:21:12 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:21:15 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][40/312]	eta 0:03:34 lr 0.001082	time 0.8169 (0.7879)	model_time 0.8168 (0.7517)	loss 2.0408 (2.8294)	grad_norm 1.3287 (1.5801/0.5081)	mem 34602MB
[2025-01-19 14:21:16 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:21:16 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.77%
[2025-01-19 14:21:18 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][0/312]	eta 0:11:21 lr 0.001084	time 2.1851 (2.1851)	model_time 0.7437 (0.7437)	loss 3.5930 (3.5930)	grad_norm 3.1023 (3.1023/0.0000)	mem 34604MB
[2025-01-19 14:21:23 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][50/312]	eta 0:03:23 lr 0.001081	time 0.7384 (0.7782)	model_time 0.7382 (0.7489)	loss 3.0220 (2.8510)	grad_norm 1.1497 (1.7114/0.7057)	mem 34602MB
[2025-01-19 14:21:26 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][10/312]	eta 0:04:35 lr 0.001084	time 0.7147 (0.9135)	model_time 0.7146 (0.7822)	loss 2.0040 (2.7914)	grad_norm 1.2294 (1.7986/0.5801)	mem 34604MB
[2025-01-19 14:21:30 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][60/312]	eta 0:03:14 lr 0.001081	time 0.7109 (0.7702)	model_time 0.7105 (0.7457)	loss 2.8986 (2.8685)	grad_norm 1.8761 (1.7139/0.6700)	mem 34602MB
[2025-01-19 14:21:33 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][20/312]	eta 0:04:03 lr 0.001083	time 0.7088 (0.8353)	model_time 0.7086 (0.7664)	loss 2.7748 (2.9854)	grad_norm 2.5728 (1.8160/0.5132)	mem 34604MB
[2025-01-19 14:21:38 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][70/312]	eta 0:03:05 lr 0.001080	time 0.7202 (0.7677)	model_time 0.7201 (0.7466)	loss 2.9949 (2.8886)	grad_norm 1.3488 (1.6895/0.6385)	mem 34602MB
[2025-01-19 14:21:41 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][30/312]	eta 0:03:50 lr 0.001083	time 0.7162 (0.8156)	model_time 0.7161 (0.7689)	loss 3.3619 (2.9683)	grad_norm 3.3507 (2.0114/0.6981)	mem 34604MB
[2025-01-19 14:21:45 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][80/312]	eta 0:02:57 lr 0.001080	time 0.7167 (0.7660)	model_time 0.7165 (0.7475)	loss 2.0668 (2.9079)	grad_norm 2.0665 (1.6781/0.6133)	mem 34602MB
[2025-01-19 14:21:48 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][40/312]	eta 0:03:36 lr 0.001082	time 0.7188 (0.7947)	model_time 0.7187 (0.7593)	loss 2.3367 (2.9623)	grad_norm 1.4835 (2.0844/0.8461)	mem 34604MB
[2025-01-19 14:21:52 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][90/312]	eta 0:02:49 lr 0.001079	time 0.7363 (0.7624)	model_time 0.7361 (0.7459)	loss 3.6654 (2.8977)	grad_norm 1.5979 (1.6456/0.5931)	mem 34602MB
[2025-01-19 14:21:56 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][50/312]	eta 0:03:24 lr 0.001081	time 0.7176 (0.7823)	model_time 0.7172 (0.7537)	loss 3.4974 (2.9481)	grad_norm 1.1878 (1.9891/0.8116)	mem 34604MB
[2025-01-19 14:22:00 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][100/312]	eta 0:02:41 lr 0.001078	time 0.7200 (0.7612)	model_time 0.7195 (0.7463)	loss 2.9303 (2.8999)	grad_norm 5.5757 (1.7375/0.7825)	mem 34602MB
[2025-01-19 14:22:03 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][60/312]	eta 0:03:15 lr 0.001081	time 0.7468 (0.7743)	model_time 0.7463 (0.7503)	loss 2.3147 (2.9113)	grad_norm 1.5064 (1.9551/0.7873)	mem 34604MB
[2025-01-19 14:22:07 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][110/312]	eta 0:02:33 lr 0.001078	time 0.7268 (0.7595)	model_time 0.7266 (0.7459)	loss 3.1398 (2.9017)	grad_norm 1.2918 (1.8289/0.8826)	mem 34602MB
[2025-01-19 14:22:10 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][70/312]	eta 0:03:05 lr 0.001080	time 0.7245 (0.7675)	model_time 0.7243 (0.7469)	loss 3.3440 (2.9445)	grad_norm 2.1597 (2.0574/0.9323)	mem 34604MB
[2025-01-19 14:22:15 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][120/312]	eta 0:02:26 lr 0.001077	time 0.8318 (0.7606)	model_time 0.8313 (0.7481)	loss 2.1262 (2.9044)	grad_norm 2.0660 (1.8124/0.8625)	mem 34602MB
[2025-01-19 14:22:17 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][80/312]	eta 0:02:56 lr 0.001080	time 0.7203 (0.7624)	model_time 0.7201 (0.7443)	loss 2.7804 (2.9402)	grad_norm 1.4250 (1.9831/0.9056)	mem 34604MB
[2025-01-19 14:22:23 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][130/312]	eta 0:02:18 lr 0.001077	time 0.7245 (0.7599)	model_time 0.7239 (0.7483)	loss 2.2007 (2.9092)	grad_norm 1.2818 (1.8038/0.8443)	mem 34602MB
[2025-01-19 14:22:25 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][90/312]	eta 0:02:48 lr 0.001079	time 0.7190 (0.7593)	model_time 0.7185 (0.7431)	loss 3.1896 (2.9160)	grad_norm 2.6198 (1.9596/0.8744)	mem 34604MB
[2025-01-19 14:22:30 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][140/312]	eta 0:02:10 lr 0.001076	time 0.8083 (0.7588)	model_time 0.8081 (0.7480)	loss 3.2255 (2.9071)	grad_norm 1.3132 (1.7602/0.8324)	mem 34602MB
[2025-01-19 14:22:32 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][100/312]	eta 0:02:40 lr 0.001078	time 0.7887 (0.7570)	model_time 0.7882 (0.7424)	loss 3.3169 (2.9368)	grad_norm 2.5718 (1.8994/0.8634)	mem 34604MB
[2025-01-19 14:22:37 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][150/312]	eta 0:02:02 lr 0.001076	time 0.7352 (0.7574)	model_time 0.7348 (0.7472)	loss 3.7343 (2.9119)	grad_norm 1.1974 (1.7288/0.8194)	mem 34602MB
[2025-01-19 14:22:39 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][110/312]	eta 0:02:32 lr 0.001078	time 0.7161 (0.7554)	model_time 0.7159 (0.7421)	loss 2.5442 (2.9416)	grad_norm 3.4451 (1.9548/0.8776)	mem 34604MB
[2025-01-19 14:22:45 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][160/312]	eta 0:01:55 lr 0.001075	time 0.8328 (0.7583)	model_time 0.8326 (0.7488)	loss 2.8427 (2.9180)	grad_norm 1.2205 (1.7364/0.8014)	mem 34602MB
[2025-01-19 14:22:47 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][120/312]	eta 0:02:24 lr 0.001077	time 0.7181 (0.7551)	model_time 0.7180 (0.7428)	loss 3.0224 (2.9292)	grad_norm 1.2524 (2.0078/0.9218)	mem 34604MB
[2025-01-19 14:22:53 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][170/312]	eta 0:01:47 lr 0.001074	time 0.7195 (0.7575)	model_time 0.7191 (0.7485)	loss 3.0471 (2.9190)	grad_norm 2.0477 (1.7301/0.7836)	mem 34602MB
[2025-01-19 14:22:55 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][130/312]	eta 0:02:17 lr 0.001077	time 0.7225 (0.7571)	model_time 0.7223 (0.7458)	loss 1.6007 (2.9383)	grad_norm 2.9927 (2.0393/0.9348)	mem 34604MB
[2025-01-19 14:23:00 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][180/312]	eta 0:01:39 lr 0.001074	time 0.7308 (0.7561)	model_time 0.7306 (0.7476)	loss 1.9438 (2.9152)	grad_norm 1.6390 (1.7128/0.7687)	mem 34602MB
[2025-01-19 14:23:02 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][140/312]	eta 0:02:10 lr 0.001076	time 0.7148 (0.7572)	model_time 0.7144 (0.7465)	loss 2.4259 (2.9317)	grad_norm 0.7480 (2.0047/0.9322)	mem 34604MB
[2025-01-19 14:23:07 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][190/312]	eta 0:01:32 lr 0.001073	time 0.7315 (0.7555)	model_time 0.7313 (0.7474)	loss 3.2557 (2.9235)	grad_norm 2.1476 (1.7075/0.7556)	mem 34602MB
[2025-01-19 14:23:10 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][150/312]	eta 0:02:02 lr 0.001076	time 0.8062 (0.7573)	model_time 0.8061 (0.7474)	loss 3.1687 (2.9382)	grad_norm 1.4089 (1.9600/0.9194)	mem 34604MB
[2025-01-19 14:23:15 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][200/312]	eta 0:01:24 lr 0.001073	time 0.7166 (0.7556)	model_time 0.7164 (0.7479)	loss 3.1914 (2.9346)	grad_norm 1.2402 (1.7113/0.7433)	mem 34602MB
[2025-01-19 14:23:17 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][160/312]	eta 0:01:54 lr 0.001075	time 0.7414 (0.7565)	model_time 0.7410 (0.7472)	loss 3.4483 (2.9368)	grad_norm 1.1267 (1.9349/0.9010)	mem 34604MB
[2025-01-19 14:23:22 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][210/312]	eta 0:01:16 lr 0.001072	time 0.7275 (0.7547)	model_time 0.7271 (0.7473)	loss 3.6297 (2.9279)	grad_norm 0.8770 (1.6974/0.7335)	mem 34602MB
[2025-01-19 14:23:25 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][170/312]	eta 0:01:47 lr 0.001074	time 0.7722 (0.7549)	model_time 0.7721 (0.7461)	loss 2.8391 (2.9327)	grad_norm 1.7174 (1.9160/0.8802)	mem 34604MB
[2025-01-19 14:23:30 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][220/312]	eta 0:01:09 lr 0.001071	time 0.7246 (0.7547)	model_time 0.7243 (0.7477)	loss 3.4925 (2.9411)	grad_norm 2.3251 (1.6954/0.7248)	mem 34602MB
[2025-01-19 14:23:32 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][180/312]	eta 0:01:39 lr 0.001074	time 0.7208 (0.7534)	model_time 0.7204 (0.7451)	loss 2.0379 (2.9248)	grad_norm 1.3781 (1.9021/0.8623)	mem 34604MB
[2025-01-19 14:23:37 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][230/312]	eta 0:01:01 lr 0.001071	time 0.7252 (0.7544)	model_time 0.7247 (0.7477)	loss 3.2254 (2.9466)	grad_norm 2.1902 (1.7021/0.7200)	mem 34602MB
[2025-01-19 14:23:39 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][190/312]	eta 0:01:31 lr 0.001073	time 0.7572 (0.7524)	model_time 0.7568 (0.7445)	loss 3.0341 (2.9160)	grad_norm 1.5729 (1.8823/0.8504)	mem 34604MB
[2025-01-19 14:23:45 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][240/312]	eta 0:00:54 lr 0.001070	time 0.8763 (0.7553)	model_time 0.8758 (0.7489)	loss 2.2062 (2.9498)	grad_norm 1.6809 (1.7132/0.7188)	mem 34602MB
[2025-01-19 14:23:47 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][200/312]	eta 0:01:24 lr 0.001073	time 0.7664 (0.7515)	model_time 0.7660 (0.7440)	loss 2.0102 (2.9221)	grad_norm 1.5653 (1.8726/0.8400)	mem 34604MB
[2025-01-19 14:23:53 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][250/312]	eta 0:00:46 lr 0.001070	time 0.7257 (0.7556)	model_time 0.7256 (0.7493)	loss 2.5469 (2.9531)	grad_norm 1.1060 (1.7140/0.7247)	mem 34602MB
[2025-01-19 14:23:54 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][210/312]	eta 0:01:16 lr 0.001072	time 0.7357 (0.7503)	model_time 0.7352 (0.7431)	loss 2.9243 (2.9186)	grad_norm 0.9086 (1.8655/0.8321)	mem 34604MB
[2025-01-19 14:24:00 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][260/312]	eta 0:00:39 lr 0.001069	time 0.8116 (0.7553)	model_time 0.8114 (0.7493)	loss 3.1742 (2.9511)	grad_norm 1.0917 (1.7248/0.7277)	mem 34602MB
[2025-01-19 14:24:01 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][220/312]	eta 0:01:08 lr 0.001071	time 0.8255 (0.7495)	model_time 0.8253 (0.7426)	loss 2.3134 (2.9172)	grad_norm 1.6526 (1.8604/0.8203)	mem 34604MB
[2025-01-19 14:24:07 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][270/312]	eta 0:00:31 lr 0.001069	time 0.7200 (0.7543)	model_time 0.7196 (0.7485)	loss 2.9781 (2.9594)	grad_norm 0.8941 (1.7184/0.7217)	mem 34602MB
[2025-01-19 14:24:09 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][230/312]	eta 0:01:01 lr 0.001071	time 0.7971 (0.7494)	model_time 0.7966 (0.7427)	loss 2.4611 (2.9215)	grad_norm 1.7783 (1.8749/0.8216)	mem 34604MB
[2025-01-19 14:24:15 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][280/312]	eta 0:00:24 lr 0.001068	time 0.8069 (0.7543)	model_time 0.8067 (0.7487)	loss 3.1132 (2.9638)	grad_norm 3.2981 (1.7227/0.7231)	mem 34602MB
[2025-01-19 14:24:16 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][240/312]	eta 0:00:54 lr 0.001070	time 0.7182 (0.7501)	model_time 0.7181 (0.7437)	loss 2.6322 (2.9347)	grad_norm 1.4852 (1.9105/0.8431)	mem 34604MB
[2025-01-19 14:24:22 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][290/312]	eta 0:00:16 lr 0.001067	time 0.7161 (0.7541)	model_time 0.7159 (0.7487)	loss 2.0558 (2.9661)	grad_norm 2.1557 (1.7372/0.7279)	mem 34602MB
[2025-01-19 14:24:24 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][250/312]	eta 0:00:46 lr 0.001070	time 0.7150 (0.7513)	model_time 0.7145 (0.7451)	loss 3.1153 (2.9375)	grad_norm 1.4497 (1.9271/0.8629)	mem 34604MB
[2025-01-19 14:24:30 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][300/312]	eta 0:00:09 lr 0.001067	time 0.7153 (0.7533)	model_time 0.7152 (0.7481)	loss 1.8798 (2.9611)	grad_norm 4.5944 (1.7722/0.7684)	mem 34602MB
[2025-01-19 14:24:32 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][260/312]	eta 0:00:39 lr 0.001069	time 0.7470 (0.7517)	model_time 0.7468 (0.7458)	loss 3.3913 (2.9446)	grad_norm 2.1574 (1.9038/0.8625)	mem 34604MB
[2025-01-19 14:24:37 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][310/312]	eta 0:00:01 lr 0.001066	time 0.7867 (0.7525)	model_time 0.7866 (0.7474)	loss 2.1273 (2.9509)	grad_norm 2.6023 (1.7745/0.7678)	mem 34602MB
[2025-01-19 14:24:38 internimage_b_1k_224] (main.py 519): INFO EPOCH 197 training takes 0:03:54
[2025-01-19 14:24:38 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_197.pth saving......
[2025-01-19 14:24:39 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][270/312]	eta 0:00:31 lr 0.001069	time 0.8067 (0.7520)	model_time 0.8063 (0.7463)	loss 3.4239 (2.9541)	grad_norm 2.9073 (1.9032/0.8536)	mem 34604MB
[2025-01-19 14:24:41 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_197.pth saved !!!
[2025-01-19 14:24:47 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][280/312]	eta 0:00:24 lr 0.001068	time 0.7218 (0.7515)	model_time 0.7217 (0.7460)	loss 2.1303 (2.9511)	grad_norm 3.7124 (1.9298/0.8899)	mem 34604MB
[2025-01-19 14:24:49 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.495 (7.495)	Loss 0.7186 (0.7186)	Acc@1 84.912 (84.912)	Acc@5 97.534 (97.534)	Mem 34602MB
[2025-01-19 14:24:52 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.978)	Loss 0.9527 (0.8327)	Acc@1 79.175 (82.626)	Acc@5 95.093 (96.302)	Mem 34602MB
[2025-01-19 14:24:52 internimage_b_1k_224] (main.py 575): INFO [Epoch:197] * Acc@1 82.520 Acc@5 96.319
[2025-01-19 14:24:52 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.5%
[2025-01-19 14:24:52 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.59%
[2025-01-19 14:24:54 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][290/312]	eta 0:00:16 lr 0.001067	time 0.7249 (0.7505)	model_time 0.7247 (0.7452)	loss 3.2565 (2.9533)	grad_norm 2.2602 (1.9448/0.8919)	mem 34604MB
[2025-01-19 14:25:01 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][300/312]	eta 0:00:08 lr 0.001067	time 0.7605 (0.7498)	model_time 0.7604 (0.7446)	loss 3.5746 (2.9571)	grad_norm 1.9571 (1.9539/0.8872)	mem 34604MB
[2025-01-19 14:25:01 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.235 (9.235)	Loss 0.6957 (0.6957)	Acc@1 85.303 (85.303)	Acc@5 97.925 (97.925)	Mem 34602MB
[2025-01-19 14:25:06 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.277)	Loss 0.9474 (0.8075)	Acc@1 78.882 (82.961)	Acc@5 95.190 (96.544)	Mem 34602MB
[2025-01-19 14:25:06 internimage_b_1k_224] (main.py 575): INFO [Epoch:197] * Acc@1 82.817 Acc@5 96.593
[2025-01-19 14:25:06 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.8%
[2025-01-19 14:25:06 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:25:08 internimage_b_1k_224] (main.py 510): INFO Train: [197/300][310/312]	eta 0:00:01 lr 0.001066	time 0.7126 (0.7486)	model_time 0.7125 (0.7436)	loss 3.6653 (2.9642)	grad_norm 1.6400 (1.9405/0.8892)	mem 34604MB
[2025-01-19 14:25:09 internimage_b_1k_224] (main.py 519): INFO EPOCH 197 training takes 0:03:53
[2025-01-19 14:25:09 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_197.pth saving......
[2025-01-19 14:25:10 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:25:10 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.82%
[2025-01-19 14:25:12 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_197.pth saved !!!
[2025-01-19 14:25:12 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][0/312]	eta 0:11:40 lr 0.001066	time 2.2456 (2.2456)	model_time 0.7388 (0.7388)	loss 3.3883 (3.3883)	grad_norm 1.2370 (1.2370/0.0000)	mem 34602MB
[2025-01-19 14:25:20 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.451 (7.451)	Loss 0.7384 (0.7384)	Acc@1 84.888 (84.888)	Acc@5 97.559 (97.559)	Mem 34604MB
[2025-01-19 14:25:20 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][10/312]	eta 0:04:29 lr 0.001066	time 0.7175 (0.8915)	model_time 0.7173 (0.7541)	loss 3.5119 (3.1923)	grad_norm 1.4239 (1.7190/0.8592)	mem 34602MB
[2025-01-19 14:25:23 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.989)	Loss 0.9714 (0.8429)	Acc@1 79.028 (82.475)	Acc@5 95.142 (96.269)	Mem 34604MB
[2025-01-19 14:25:23 internimage_b_1k_224] (main.py 575): INFO [Epoch:197] * Acc@1 82.352 Acc@5 96.313
[2025-01-19 14:25:23 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.4%
[2025-01-19 14:25:23 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 14:25:27 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 14:25:27 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.35%
[2025-01-19 14:25:27 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][20/312]	eta 0:03:59 lr 0.001065	time 0.7225 (0.8196)	model_time 0.7224 (0.7475)	loss 3.1285 (2.9637)	grad_norm 1.8501 (1.8858/0.8193)	mem 34602MB
[2025-01-19 14:25:34 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.272 (7.272)	Loss 0.6913 (0.6913)	Acc@1 85.449 (85.449)	Acc@5 97.974 (97.974)	Mem 34604MB
[2025-01-19 14:25:35 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][30/312]	eta 0:03:44 lr 0.001064	time 0.7368 (0.7976)	model_time 0.7367 (0.7486)	loss 2.4624 (3.0034)	grad_norm 1.0480 (1.7905/0.7881)	mem 34602MB
[2025-01-19 14:25:37 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (0.961)	Loss 0.9459 (0.8060)	Acc@1 79.224 (82.983)	Acc@5 95.093 (96.471)	Mem 34604MB
[2025-01-19 14:25:38 internimage_b_1k_224] (main.py 575): INFO [Epoch:197] * Acc@1 82.796 Acc@5 96.527
[2025-01-19 14:25:38 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.8%
[2025-01-19 14:25:38 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:25:42 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:25:42 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.80%
[2025-01-19 14:25:42 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][40/312]	eta 0:03:33 lr 0.001064	time 0.7231 (0.7862)	model_time 0.7229 (0.7491)	loss 2.4707 (2.9761)	grad_norm 1.7623 (1.7918/0.7339)	mem 34602MB
[2025-01-19 14:25:44 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][0/312]	eta 0:11:19 lr 0.001066	time 2.1772 (2.1772)	model_time 0.7297 (0.7297)	loss 3.4173 (3.4173)	grad_norm 2.7059 (2.7059/0.0000)	mem 34604MB
[2025-01-19 14:25:50 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][50/312]	eta 0:03:24 lr 0.001063	time 0.7162 (0.7803)	model_time 0.7161 (0.7504)	loss 1.7440 (2.9744)	grad_norm 1.8793 (1.7783/0.6850)	mem 34602MB
[2025-01-19 14:25:51 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][10/312]	eta 0:04:20 lr 0.001066	time 0.7381 (0.8631)	model_time 0.7377 (0.7312)	loss 2.8978 (2.9252)	grad_norm 1.5636 (1.9252/0.6923)	mem 34604MB
[2025-01-19 14:25:58 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][60/312]	eta 0:03:16 lr 0.001063	time 0.7668 (0.7783)	model_time 0.7667 (0.7533)	loss 3.3159 (2.9411)	grad_norm 1.4467 (1.7158/0.6532)	mem 34602MB
[2025-01-19 14:25:59 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][20/312]	eta 0:03:53 lr 0.001065	time 0.7150 (0.7987)	model_time 0.7149 (0.7295)	loss 1.8084 (2.8760)	grad_norm 1.0418 (1.7561/0.6160)	mem 34604MB
[2025-01-19 14:26:05 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][70/312]	eta 0:03:07 lr 0.001062	time 0.7140 (0.7735)	model_time 0.7137 (0.7519)	loss 2.2850 (2.9215)	grad_norm 1.7762 (1.7144/0.6532)	mem 34602MB
[2025-01-19 14:26:06 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][30/312]	eta 0:03:40 lr 0.001064	time 0.7330 (0.7817)	model_time 0.7325 (0.7347)	loss 3.0237 (2.8018)	grad_norm 3.3482 (2.0879/0.8777)	mem 34604MB
[2025-01-19 14:26:13 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][80/312]	eta 0:02:58 lr 0.001061	time 0.7243 (0.7688)	model_time 0.7238 (0.7499)	loss 2.3520 (2.9234)	grad_norm 3.8740 (1.7332/0.6774)	mem 34602MB
[2025-01-19 14:26:13 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][40/312]	eta 0:03:29 lr 0.001064	time 0.7179 (0.7720)	model_time 0.7175 (0.7363)	loss 3.1627 (2.8700)	grad_norm 1.1513 (2.0663/0.8328)	mem 34604MB
[2025-01-19 14:26:20 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][90/312]	eta 0:02:50 lr 0.001061	time 0.7164 (0.7671)	model_time 0.7162 (0.7502)	loss 3.5009 (2.9377)	grad_norm 0.7487 (1.7323/0.6636)	mem 34602MB
[2025-01-19 14:26:21 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][50/312]	eta 0:03:21 lr 0.001063	time 0.7143 (0.7703)	model_time 0.7138 (0.7416)	loss 2.9257 (2.8950)	grad_norm 1.0202 (2.0496/0.8001)	mem 34604MB
[2025-01-19 14:26:28 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][100/312]	eta 0:02:42 lr 0.001060	time 0.7186 (0.7650)	model_time 0.7182 (0.7497)	loss 2.7252 (2.9450)	grad_norm 2.7461 (1.7877/0.6971)	mem 34602MB
[2025-01-19 14:26:29 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][60/312]	eta 0:03:14 lr 0.001063	time 0.9054 (0.7727)	model_time 0.9052 (0.7487)	loss 3.6160 (2.9035)	grad_norm 3.2902 (2.0610/0.7742)	mem 34604MB
[2025-01-19 14:26:35 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][110/312]	eta 0:02:33 lr 0.001060	time 0.7430 (0.7617)	model_time 0.7428 (0.7478)	loss 3.6306 (2.9582)	grad_norm 1.9671 (1.8019/0.7022)	mem 34602MB
[2025-01-19 14:26:37 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][70/312]	eta 0:03:06 lr 0.001062	time 0.7169 (0.7707)	model_time 0.7167 (0.7500)	loss 2.6289 (2.8780)	grad_norm 1.5673 (2.0426/0.7507)	mem 34604MB
[2025-01-19 14:26:42 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][120/312]	eta 0:02:25 lr 0.001059	time 0.7300 (0.7599)	model_time 0.7299 (0.7471)	loss 3.1981 (2.9726)	grad_norm 2.3692 (1.8491/0.7274)	mem 34602MB
[2025-01-19 14:26:44 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][80/312]	eta 0:02:58 lr 0.001061	time 0.7246 (0.7679)	model_time 0.7242 (0.7497)	loss 2.6808 (2.8875)	grad_norm 1.9106 (1.9983/0.7198)	mem 34604MB
[2025-01-19 14:26:50 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][130/312]	eta 0:02:18 lr 0.001059	time 0.7190 (0.7597)	model_time 0.7189 (0.7478)	loss 3.6110 (2.9696)	grad_norm 1.2458 (1.8082/0.7156)	mem 34602MB
[2025-01-19 14:26:51 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][90/312]	eta 0:02:49 lr 0.001061	time 0.7288 (0.7648)	model_time 0.7287 (0.7486)	loss 2.8486 (2.9111)	grad_norm 1.0318 (1.9952/0.7061)	mem 34604MB
[2025-01-19 14:26:57 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][140/312]	eta 0:02:10 lr 0.001058	time 0.7242 (0.7587)	model_time 0.7240 (0.7477)	loss 3.4205 (2.9810)	grad_norm 1.4410 (1.7794/0.7045)	mem 34602MB
[2025-01-19 14:26:59 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][100/312]	eta 0:02:41 lr 0.001060	time 0.7323 (0.7609)	model_time 0.7321 (0.7463)	loss 3.5760 (2.9294)	grad_norm 2.0461 (1.9992/0.6977)	mem 34604MB
[2025-01-19 14:27:05 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][150/312]	eta 0:02:02 lr 0.001057	time 0.7970 (0.7585)	model_time 0.7968 (0.7482)	loss 2.7709 (2.9922)	grad_norm 2.9678 (1.8566/0.7739)	mem 34602MB
[2025-01-19 14:27:06 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][110/312]	eta 0:02:33 lr 0.001060	time 0.7196 (0.7576)	model_time 0.7194 (0.7443)	loss 1.8916 (2.9237)	grad_norm 2.7990 (1.9839/0.6898)	mem 34604MB
[2025-01-19 14:27:12 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][160/312]	eta 0:01:55 lr 0.001057	time 0.7174 (0.7579)	model_time 0.7172 (0.7482)	loss 3.6199 (3.0016)	grad_norm 2.5839 (1.8836/0.8092)	mem 34602MB
[2025-01-19 14:27:13 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][120/312]	eta 0:02:25 lr 0.001059	time 0.7666 (0.7556)	model_time 0.7665 (0.7433)	loss 2.9781 (2.9191)	grad_norm 1.3409 (1.9359/0.6931)	mem 34604MB
[2025-01-19 14:27:20 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][170/312]	eta 0:01:47 lr 0.001056	time 0.7275 (0.7577)	model_time 0.7271 (0.7485)	loss 2.3227 (3.0077)	grad_norm 1.2208 (1.8753/0.7957)	mem 34602MB
[2025-01-19 14:27:20 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][130/312]	eta 0:02:17 lr 0.001059	time 0.7279 (0.7532)	model_time 0.7274 (0.7418)	loss 3.4090 (2.9398)	grad_norm 1.4620 (1.9169/0.6804)	mem 34604MB
[2025-01-19 14:27:27 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][180/312]	eta 0:01:40 lr 0.001056	time 0.7461 (0.7577)	model_time 0.7459 (0.7491)	loss 3.5753 (3.0077)	grad_norm 3.2258 (1.8901/0.8090)	mem 34602MB
[2025-01-19 14:27:28 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][140/312]	eta 0:02:09 lr 0.001058	time 0.7403 (0.7517)	model_time 0.7401 (0.7411)	loss 3.1073 (2.9426)	grad_norm 1.7664 (1.8957/0.6833)	mem 34604MB
[2025-01-19 14:27:35 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][190/312]	eta 0:01:32 lr 0.001055	time 0.7173 (0.7578)	model_time 0.7169 (0.7495)	loss 3.2242 (3.0095)	grad_norm 2.0150 (1.8770/0.7918)	mem 34602MB
[2025-01-19 14:27:35 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][150/312]	eta 0:02:01 lr 0.001057	time 0.7299 (0.7505)	model_time 0.7295 (0.7406)	loss 3.0456 (2.9501)	grad_norm 1.7632 (1.8621/0.6770)	mem 34604MB
[2025-01-19 14:27:42 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][200/312]	eta 0:01:24 lr 0.001055	time 0.7210 (0.7572)	model_time 0.7208 (0.7494)	loss 2.1380 (3.0009)	grad_norm 1.9133 (1.8711/0.7778)	mem 34602MB
[2025-01-19 14:27:43 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][160/312]	eta 0:01:54 lr 0.001057	time 0.7444 (0.7503)	model_time 0.7443 (0.7410)	loss 3.3109 (2.9533)	grad_norm 1.2145 (1.8369/0.6667)	mem 34604MB
[2025-01-19 14:27:50 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][210/312]	eta 0:01:17 lr 0.001054	time 0.7180 (0.7576)	model_time 0.7175 (0.7501)	loss 2.9275 (2.9883)	grad_norm 1.7828 (1.8713/0.7749)	mem 34602MB
[2025-01-19 14:27:50 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][170/312]	eta 0:01:46 lr 0.001056	time 0.8059 (0.7504)	model_time 0.8054 (0.7416)	loss 3.1099 (2.9645)	grad_norm 1.6240 (1.8299/0.6579)	mem 34604MB
[2025-01-19 14:27:58 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][220/312]	eta 0:01:09 lr 0.001053	time 0.7210 (0.7569)	model_time 0.7209 (0.7497)	loss 2.7563 (2.9869)	grad_norm 1.8177 (1.8625/0.7673)	mem 34602MB
[2025-01-19 14:27:58 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][180/312]	eta 0:01:39 lr 0.001056	time 0.9096 (0.7529)	model_time 0.9091 (0.7446)	loss 2.0893 (2.9537)	grad_norm 1.9611 (1.8351/0.6570)	mem 34604MB
[2025-01-19 14:28:05 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][230/312]	eta 0:01:01 lr 0.001053	time 0.7220 (0.7558)	model_time 0.7215 (0.7489)	loss 1.9689 (2.9889)	grad_norm 1.0103 (1.8427/0.7611)	mem 34602MB
[2025-01-19 14:28:06 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][190/312]	eta 0:01:32 lr 0.001055	time 0.8012 (0.7542)	model_time 0.8010 (0.7463)	loss 3.2857 (2.9520)	grad_norm 1.2690 (1.8509/0.6533)	mem 34604MB
[2025-01-19 14:28:12 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][240/312]	eta 0:00:54 lr 0.001052	time 0.7172 (0.7548)	model_time 0.7167 (0.7482)	loss 3.2796 (2.9916)	grad_norm 2.9579 (1.8484/0.7560)	mem 34602MB
[2025-01-19 14:28:13 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][200/312]	eta 0:01:24 lr 0.001055	time 0.7292 (0.7538)	model_time 0.7291 (0.7463)	loss 3.1236 (2.9486)	grad_norm 0.9617 (1.8382/0.6531)	mem 34604MB
[2025-01-19 14:28:20 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][250/312]	eta 0:00:46 lr 0.001052	time 0.7388 (0.7548)	model_time 0.7383 (0.7485)	loss 3.7086 (2.9902)	grad_norm 1.3262 (1.8438/0.7525)	mem 34602MB
[2025-01-19 14:28:21 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][210/312]	eta 0:01:16 lr 0.001054	time 0.7155 (0.7530)	model_time 0.7153 (0.7458)	loss 3.5333 (2.9506)	grad_norm 2.5090 (1.8214/0.6502)	mem 34604MB
[2025-01-19 14:28:27 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][260/312]	eta 0:00:39 lr 0.001051	time 0.7185 (0.7543)	model_time 0.7184 (0.7482)	loss 2.5481 (2.9936)	grad_norm 2.9022 (1.8446/0.7499)	mem 34602MB
[2025-01-19 14:28:28 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][220/312]	eta 0:01:09 lr 0.001053	time 0.7252 (0.7520)	model_time 0.7250 (0.7451)	loss 1.7747 (2.9370)	grad_norm 3.2948 (1.8357/0.6557)	mem 34604MB
[2025-01-19 14:28:35 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][270/312]	eta 0:00:31 lr 0.001050	time 0.7881 (0.7543)	model_time 0.7876 (0.7484)	loss 3.3189 (2.9918)	grad_norm 1.8861 (1.8336/0.7463)	mem 34602MB
[2025-01-19 14:28:35 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][230/312]	eta 0:01:01 lr 0.001053	time 0.7227 (0.7511)	model_time 0.7226 (0.7445)	loss 3.7114 (2.9392)	grad_norm 1.4959 (1.8287/0.6460)	mem 34604MB
[2025-01-19 14:28:42 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][280/312]	eta 0:00:24 lr 0.001050	time 0.7263 (0.7543)	model_time 0.7262 (0.7486)	loss 2.8145 (2.9950)	grad_norm 2.8616 (1.8383/0.7490)	mem 34602MB
[2025-01-19 14:28:43 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][240/312]	eta 0:00:54 lr 0.001052	time 0.7399 (0.7501)	model_time 0.7394 (0.7438)	loss 3.0632 (2.9450)	grad_norm 1.9049 (1.8299/0.6478)	mem 34604MB
[2025-01-19 14:28:50 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][290/312]	eta 0:00:16 lr 0.001049	time 0.7402 (0.7541)	model_time 0.7401 (0.7486)	loss 2.8578 (2.9894)	grad_norm 3.4117 (1.8608/0.7607)	mem 34602MB
[2025-01-19 14:28:50 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][250/312]	eta 0:00:46 lr 0.001052	time 0.7353 (0.7492)	model_time 0.7349 (0.7431)	loss 3.1107 (2.9501)	grad_norm 1.4937 (1.8248/0.6421)	mem 34604MB
[2025-01-19 14:28:57 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][260/312]	eta 0:00:38 lr 0.001051	time 0.7285 (0.7484)	model_time 0.7284 (0.7425)	loss 3.1569 (2.9571)	grad_norm 2.2232 (1.8302/0.6470)	mem 34604MB
[2025-01-19 14:28:57 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][300/312]	eta 0:00:09 lr 0.001049	time 0.7154 (0.7539)	model_time 0.7153 (0.7486)	loss 2.0993 (2.9902)	grad_norm 1.1887 (1.8706/0.7637)	mem 34602MB
[2025-01-19 14:29:04 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][310/312]	eta 0:00:01 lr 0.001048	time 0.7134 (0.7529)	model_time 0.7133 (0.7477)	loss 3.2378 (2.9884)	grad_norm 2.5685 (1.8807/0.7518)	mem 34602MB
[2025-01-19 14:29:04 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][270/312]	eta 0:00:31 lr 0.001050	time 0.7523 (0.7480)	model_time 0.7521 (0.7423)	loss 3.3368 (2.9565)	grad_norm 1.8993 (1.8357/0.6441)	mem 34604MB
[2025-01-19 14:29:05 internimage_b_1k_224] (main.py 519): INFO EPOCH 198 training takes 0:03:54
[2025-01-19 14:29:05 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_198.pth saving......
[2025-01-19 14:29:08 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_198.pth saved !!!
[2025-01-19 14:29:12 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][280/312]	eta 0:00:23 lr 0.001050	time 0.8101 (0.7481)	model_time 0.8097 (0.7426)	loss 3.0122 (2.9582)	grad_norm 1.4162 (1.8244/0.6440)	mem 34604MB
[2025-01-19 14:29:17 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.207 (8.207)	Loss 0.7574 (0.7574)	Acc@1 84.692 (84.692)	Acc@5 97.534 (97.534)	Mem 34602MB
[2025-01-19 14:29:20 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][290/312]	eta 0:00:16 lr 0.001049	time 0.8227 (0.7489)	model_time 0.8226 (0.7436)	loss 2.4615 (2.9514)	grad_norm 1.7955 (1.8235/0.6414)	mem 34604MB
[2025-01-19 14:29:20 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.041)	Loss 0.9777 (0.8514)	Acc@1 78.467 (82.579)	Acc@5 95.288 (96.302)	Mem 34602MB
[2025-01-19 14:29:20 internimage_b_1k_224] (main.py 575): INFO [Epoch:198] * Acc@1 82.446 Acc@5 96.305
[2025-01-19 14:29:20 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.4%
[2025-01-19 14:29:20 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.59%
[2025-01-19 14:29:27 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][300/312]	eta 0:00:08 lr 0.001049	time 0.8034 (0.7495)	model_time 0.8033 (0.7444)	loss 3.2598 (2.9465)	grad_norm 1.7521 (1.8274/0.6409)	mem 34604MB
[2025-01-19 14:29:30 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.385 (9.385)	Loss 0.6966 (0.6966)	Acc@1 85.376 (85.376)	Acc@5 97.925 (97.925)	Mem 34602MB
[2025-01-19 14:29:34 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.270)	Loss 0.9470 (0.8078)	Acc@1 78.906 (83.006)	Acc@5 95.190 (96.558)	Mem 34602MB
[2025-01-19 14:29:34 internimage_b_1k_224] (main.py 575): INFO [Epoch:198] * Acc@1 82.853 Acc@5 96.605
[2025-01-19 14:29:34 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.9%
[2025-01-19 14:29:34 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:29:35 internimage_b_1k_224] (main.py 510): INFO Train: [198/300][310/312]	eta 0:00:01 lr 0.001048	time 0.7145 (0.7500)	model_time 0.7144 (0.7450)	loss 3.6471 (2.9525)	grad_norm 3.5316 (1.8478/0.6674)	mem 34604MB
[2025-01-19 14:29:36 internimage_b_1k_224] (main.py 519): INFO EPOCH 198 training takes 0:03:53
[2025-01-19 14:29:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_198.pth saving......
[2025-01-19 14:29:38 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:29:38 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.85%
[2025-01-19 14:29:39 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_198.pth saved !!!
[2025-01-19 14:29:41 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][0/312]	eta 0:12:57 lr 0.001048	time 2.4924 (2.4924)	model_time 0.7652 (0.7652)	loss 2.9706 (2.9706)	grad_norm 1.0857 (1.0857/0.0000)	mem 34602MB
[2025-01-19 14:29:47 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.587 (7.587)	Loss 0.7456 (0.7456)	Acc@1 85.474 (85.474)	Acc@5 97.534 (97.534)	Mem 34604MB
[2025-01-19 14:29:48 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][10/312]	eta 0:04:29 lr 0.001047	time 0.7308 (0.8927)	model_time 0.7306 (0.7354)	loss 2.0134 (2.8149)	grad_norm 2.5112 (1.7875/0.6347)	mem 34602MB
[2025-01-19 14:29:50 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.994)	Loss 0.9883 (0.8430)	Acc@1 78.784 (82.657)	Acc@5 95.239 (96.376)	Mem 34604MB
[2025-01-19 14:29:50 internimage_b_1k_224] (main.py 575): INFO [Epoch:198] * Acc@1 82.436 Acc@5 96.357
[2025-01-19 14:29:50 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.4%
[2025-01-19 14:29:50 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 14:29:54 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 14:29:54 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.44%
[2025-01-19 14:29:55 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][20/312]	eta 0:04:00 lr 0.001047	time 0.7370 (0.8235)	model_time 0.7369 (0.7409)	loss 3.1869 (2.7767)	grad_norm 1.2332 (1.6977/0.6275)	mem 34602MB
[2025-01-19 14:30:01 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.488 (7.488)	Loss 0.6921 (0.6921)	Acc@1 85.522 (85.522)	Acc@5 98.022 (98.022)	Mem 34604MB
[2025-01-19 14:30:03 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][30/312]	eta 0:03:45 lr 0.001046	time 0.7504 (0.7988)	model_time 0.7503 (0.7428)	loss 2.8131 (2.7958)	grad_norm 1.7797 (1.6812/0.5884)	mem 34602MB
[2025-01-19 14:30:04 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.968)	Loss 0.9456 (0.8064)	Acc@1 79.224 (83.026)	Acc@5 95.093 (96.478)	Mem 34604MB
[2025-01-19 14:30:04 internimage_b_1k_224] (main.py 575): INFO [Epoch:198] * Acc@1 82.833 Acc@5 96.531
[2025-01-19 14:30:04 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.8%
[2025-01-19 14:30:04 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:30:09 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:30:09 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.83%
[2025-01-19 14:30:10 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][40/312]	eta 0:03:32 lr 0.001046	time 0.7334 (0.7825)	model_time 0.7333 (0.7401)	loss 2.0988 (2.8378)	grad_norm 2.1080 (1.6841/0.5608)	mem 34602MB
[2025-01-19 14:30:11 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][0/312]	eta 0:12:29 lr 0.001048	time 2.4014 (2.4014)	model_time 0.7722 (0.7722)	loss 2.7399 (2.7399)	grad_norm 2.7261 (2.7261/0.0000)	mem 34604MB
[2025-01-19 14:30:18 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][50/312]	eta 0:03:22 lr 0.001045	time 0.7309 (0.7722)	model_time 0.7307 (0.7381)	loss 2.3172 (2.8516)	grad_norm 2.7056 (1.7551/0.6845)	mem 34602MB
[2025-01-19 14:30:19 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][10/312]	eta 0:04:31 lr 0.001047	time 0.7229 (0.8996)	model_time 0.7225 (0.7512)	loss 3.3626 (2.9797)	grad_norm 3.1181 (2.5933/0.8938)	mem 34604MB
[2025-01-19 14:30:25 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][60/312]	eta 0:03:14 lr 0.001045	time 0.8012 (0.7718)	model_time 0.8010 (0.7432)	loss 3.5393 (2.8652)	grad_norm 1.1779 (1.7361/0.6414)	mem 34602MB
[2025-01-19 14:30:26 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][20/312]	eta 0:04:00 lr 0.001047	time 0.7356 (0.8230)	model_time 0.7354 (0.7451)	loss 2.0765 (2.9383)	grad_norm 1.2016 (2.4564/1.0388)	mem 34604MB
[2025-01-19 14:30:33 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][70/312]	eta 0:03:06 lr 0.001044	time 0.8207 (0.7693)	model_time 0.8206 (0.7447)	loss 3.6454 (2.8738)	grad_norm 1.2118 (1.7086/0.6210)	mem 34602MB
[2025-01-19 14:30:33 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][30/312]	eta 0:03:43 lr 0.001046	time 0.7261 (0.7920)	model_time 0.7257 (0.7392)	loss 2.0855 (2.8435)	grad_norm 2.4511 (2.2016/1.0181)	mem 34604MB
[2025-01-19 14:30:40 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][80/312]	eta 0:02:57 lr 0.001043	time 0.7190 (0.7667)	model_time 0.7188 (0.7451)	loss 3.0136 (2.8819)	grad_norm 1.1882 (1.6810/0.5995)	mem 34602MB
[2025-01-19 14:30:40 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][40/312]	eta 0:03:31 lr 0.001046	time 0.7475 (0.7759)	model_time 0.7474 (0.7359)	loss 2.3579 (2.9011)	grad_norm 0.8713 (2.0577/0.9759)	mem 34604MB
[2025-01-19 14:30:48 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][50/312]	eta 0:03:20 lr 0.001045	time 0.7465 (0.7667)	model_time 0.7464 (0.7345)	loss 3.5787 (2.9463)	grad_norm 2.2036 (1.9903/0.9373)	mem 34604MB
[2025-01-19 14:30:48 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][90/312]	eta 0:02:49 lr 0.001043	time 0.7306 (0.7650)	model_time 0.7305 (0.7457)	loss 3.3449 (2.9130)	grad_norm 1.6989 (1.7038/0.5949)	mem 34602MB
[2025-01-19 14:30:55 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][60/312]	eta 0:03:11 lr 0.001045	time 0.7223 (0.7598)	model_time 0.7221 (0.7328)	loss 2.5576 (2.9202)	grad_norm 4.1304 (2.0511/0.9750)	mem 34604MB
[2025-01-19 14:30:55 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][100/312]	eta 0:02:41 lr 0.001042	time 0.7199 (0.7639)	model_time 0.7194 (0.7465)	loss 3.3634 (2.9255)	grad_norm 1.4162 (1.6661/0.5853)	mem 34602MB
[2025-01-19 14:31:02 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][70/312]	eta 0:03:03 lr 0.001044	time 0.7229 (0.7566)	model_time 0.7227 (0.7333)	loss 3.4102 (2.9610)	grad_norm 2.9840 (2.0365/0.9460)	mem 34604MB
[2025-01-19 14:31:03 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][110/312]	eta 0:02:34 lr 0.001042	time 0.7162 (0.7625)	model_time 0.7160 (0.7466)	loss 2.7048 (2.9296)	grad_norm 2.6045 (1.7077/0.6386)	mem 34602MB
[2025-01-19 14:31:10 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][80/312]	eta 0:02:54 lr 0.001043	time 0.7203 (0.7540)	model_time 0.7202 (0.7335)	loss 3.4309 (2.9337)	grad_norm 1.1909 (2.0165/0.9002)	mem 34604MB
[2025-01-19 14:31:10 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][120/312]	eta 0:02:26 lr 0.001041	time 0.7161 (0.7606)	model_time 0.7159 (0.7460)	loss 3.1716 (2.9179)	grad_norm 1.3430 (1.7045/0.6374)	mem 34602MB
[2025-01-19 14:31:17 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][90/312]	eta 0:02:47 lr 0.001043	time 0.7232 (0.7536)	model_time 0.7228 (0.7354)	loss 2.6995 (2.9215)	grad_norm 1.3999 (1.9641/0.8687)	mem 34604MB
[2025-01-19 14:31:18 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][130/312]	eta 0:02:18 lr 0.001040	time 0.7174 (0.7583)	model_time 0.7170 (0.7448)	loss 2.8199 (2.9126)	grad_norm 1.0038 (1.6733/0.6352)	mem 34602MB
[2025-01-19 14:31:25 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][100/312]	eta 0:02:39 lr 0.001042	time 0.7230 (0.7521)	model_time 0.7228 (0.7357)	loss 3.4658 (2.9429)	grad_norm 1.3647 (1.9263/0.8508)	mem 34604MB
[2025-01-19 14:31:25 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][140/312]	eta 0:02:10 lr 0.001040	time 0.7225 (0.7576)	model_time 0.7221 (0.7450)	loss 2.7995 (2.9110)	grad_norm 1.5004 (1.6640/0.6326)	mem 34602MB
[2025-01-19 14:31:32 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][150/312]	eta 0:02:02 lr 0.001039	time 0.7218 (0.7567)	model_time 0.7214 (0.7449)	loss 1.8502 (2.9098)	grad_norm 1.6439 (1.6686/0.6264)	mem 34602MB
[2025-01-19 14:31:33 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][110/312]	eta 0:02:32 lr 0.001042	time 0.8579 (0.7564)	model_time 0.8575 (0.7414)	loss 3.3234 (2.9455)	grad_norm 0.7622 (1.8842/0.8384)	mem 34604MB
[2025-01-19 14:31:40 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][160/312]	eta 0:01:54 lr 0.001039	time 0.7579 (0.7550)	model_time 0.7575 (0.7440)	loss 3.4117 (2.9191)	grad_norm 1.8974 (1.7042/0.6571)	mem 34602MB
[2025-01-19 14:31:40 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][120/312]	eta 0:02:25 lr 0.001041	time 0.7179 (0.7570)	model_time 0.7178 (0.7432)	loss 3.0212 (2.9557)	grad_norm 2.0517 (1.8745/0.8278)	mem 34604MB
[2025-01-19 14:31:47 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][170/312]	eta 0:01:47 lr 0.001038	time 0.7158 (0.7538)	model_time 0.7155 (0.7433)	loss 2.8734 (2.9075)	grad_norm 2.2415 (1.7330/0.6660)	mem 34602MB
[2025-01-19 14:31:48 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][130/312]	eta 0:02:17 lr 0.001040	time 0.7182 (0.7568)	model_time 0.7177 (0.7441)	loss 2.9648 (2.9624)	grad_norm 2.2368 (1.8709/0.8219)	mem 34604MB
[2025-01-19 14:31:55 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][180/312]	eta 0:01:39 lr 0.001038	time 0.8031 (0.7541)	model_time 0.8026 (0.7442)	loss 2.7134 (2.9133)	grad_norm 2.8955 (1.7724/0.6956)	mem 34602MB
[2025-01-19 14:31:55 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][140/312]	eta 0:02:10 lr 0.001040	time 0.7219 (0.7565)	model_time 0.7218 (0.7446)	loss 2.8535 (2.9622)	grad_norm 1.5712 (1.8489/0.8054)	mem 34604MB
[2025-01-19 14:32:02 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][190/312]	eta 0:01:31 lr 0.001037	time 0.7194 (0.7535)	model_time 0.7192 (0.7442)	loss 2.7366 (2.9011)	grad_norm 1.9315 (1.7687/0.6847)	mem 34602MB
[2025-01-19 14:32:03 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][150/312]	eta 0:02:02 lr 0.001039	time 0.7217 (0.7546)	model_time 0.7216 (0.7435)	loss 3.3645 (2.9592)	grad_norm 1.4463 (1.8405/0.7899)	mem 34604MB
[2025-01-19 14:32:10 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][200/312]	eta 0:01:24 lr 0.001036	time 0.7324 (0.7537)	model_time 0.7322 (0.7448)	loss 3.0324 (2.9051)	grad_norm 2.1934 (1.7750/0.6798)	mem 34602MB
[2025-01-19 14:32:10 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][160/312]	eta 0:01:54 lr 0.001039	time 0.7351 (0.7535)	model_time 0.7350 (0.7431)	loss 2.2619 (2.9556)	grad_norm 2.0518 (1.8314/0.7789)	mem 34604MB
[2025-01-19 14:32:17 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][210/312]	eta 0:01:16 lr 0.001036	time 0.7235 (0.7533)	model_time 0.7233 (0.7448)	loss 2.2811 (2.9115)	grad_norm 1.5818 (1.7725/0.6702)	mem 34602MB
[2025-01-19 14:32:17 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][170/312]	eta 0:01:46 lr 0.001038	time 0.7161 (0.7521)	model_time 0.7160 (0.7422)	loss 3.3509 (2.9680)	grad_norm 2.8055 (1.8577/0.7772)	mem 34604MB
[2025-01-19 14:32:25 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][180/312]	eta 0:01:39 lr 0.001038	time 0.7202 (0.7509)	model_time 0.7200 (0.7416)	loss 3.4689 (2.9587)	grad_norm 1.8861 (1.8767/0.8002)	mem 34604MB
[2025-01-19 14:32:25 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][220/312]	eta 0:01:09 lr 0.001035	time 0.7277 (0.7531)	model_time 0.7272 (0.7450)	loss 3.4674 (2.9136)	grad_norm 1.2156 (1.7498/0.6682)	mem 34602MB
[2025-01-19 14:32:32 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][190/312]	eta 0:01:31 lr 0.001037	time 0.7386 (0.7498)	model_time 0.7382 (0.7409)	loss 3.1072 (2.9641)	grad_norm 1.2272 (1.9221/0.8226)	mem 34604MB
[2025-01-19 14:32:32 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][230/312]	eta 0:01:01 lr 0.001035	time 0.7183 (0.7535)	model_time 0.7182 (0.7457)	loss 3.2463 (2.9166)	grad_norm 1.0634 (1.7407/0.6650)	mem 34602MB
[2025-01-19 14:32:39 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][200/312]	eta 0:01:23 lr 0.001036	time 0.7493 (0.7494)	model_time 0.7492 (0.7410)	loss 3.1943 (2.9699)	grad_norm 2.6761 (1.9211/0.8092)	mem 34604MB
[2025-01-19 14:32:40 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][240/312]	eta 0:00:54 lr 0.001034	time 0.7176 (0.7532)	model_time 0.7172 (0.7457)	loss 3.2888 (2.9178)	grad_norm 1.3040 (1.7676/0.6747)	mem 34602MB
[2025-01-19 14:32:47 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][210/312]	eta 0:01:16 lr 0.001036	time 0.7205 (0.7493)	model_time 0.7200 (0.7413)	loss 3.6381 (2.9614)	grad_norm 1.3143 (1.9024/0.8199)	mem 34604MB
[2025-01-19 14:32:47 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][250/312]	eta 0:00:46 lr 0.001034	time 0.7222 (0.7524)	model_time 0.7221 (0.7452)	loss 3.3545 (2.9237)	grad_norm 0.9005 (1.7713/0.6793)	mem 34602MB
[2025-01-19 14:32:54 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][220/312]	eta 0:01:08 lr 0.001035	time 0.7206 (0.7489)	model_time 0.7205 (0.7412)	loss 1.8590 (2.9433)	grad_norm 0.9633 (1.8854/0.8131)	mem 34604MB
[2025-01-19 14:32:54 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][260/312]	eta 0:00:39 lr 0.001033	time 0.7942 (0.7521)	model_time 0.7938 (0.7451)	loss 3.0372 (2.9209)	grad_norm 1.2268 (1.7777/0.6737)	mem 34602MB
[2025-01-19 14:33:02 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][230/312]	eta 0:01:01 lr 0.001035	time 0.8094 (0.7500)	model_time 0.8092 (0.7426)	loss 2.9107 (2.9486)	grad_norm 1.4979 (1.8649/0.8087)	mem 34604MB
[2025-01-19 14:33:02 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][270/312]	eta 0:00:31 lr 0.001032	time 0.7190 (0.7517)	model_time 0.7185 (0.7450)	loss 3.4068 (2.9207)	grad_norm 1.2866 (1.7820/0.6716)	mem 34602MB
[2025-01-19 14:33:09 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][280/312]	eta 0:00:24 lr 0.001032	time 0.7343 (0.7509)	model_time 0.7339 (0.7444)	loss 3.8147 (2.9301)	grad_norm 2.3108 (1.7771/0.6686)	mem 34602MB
[2025-01-19 14:33:10 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][240/312]	eta 0:00:54 lr 0.001034	time 0.7488 (0.7520)	model_time 0.7487 (0.7449)	loss 3.7704 (2.9483)	grad_norm 2.1522 (1.8659/0.7948)	mem 34604MB
[2025-01-19 14:33:16 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][290/312]	eta 0:00:16 lr 0.001031	time 0.7175 (0.7502)	model_time 0.7174 (0.7439)	loss 2.9303 (2.9190)	grad_norm 1.9673 (1.7801/0.6660)	mem 34602MB
[2025-01-19 14:33:17 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][250/312]	eta 0:00:46 lr 0.001034	time 0.7167 (0.7521)	model_time 0.7163 (0.7453)	loss 2.8845 (2.9507)	grad_norm 2.2912 (1.8875/0.8031)	mem 34604MB
[2025-01-19 14:33:24 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][300/312]	eta 0:00:09 lr 0.001031	time 0.7156 (0.7506)	model_time 0.7155 (0.7445)	loss 2.7718 (2.9236)	grad_norm 1.0189 (1.7865/0.6778)	mem 34602MB
[2025-01-19 14:33:25 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][260/312]	eta 0:00:39 lr 0.001033	time 0.7200 (0.7514)	model_time 0.7196 (0.7448)	loss 2.3368 (2.9460)	grad_norm 0.7854 (1.8658/0.8029)	mem 34604MB
[2025-01-19 14:33:31 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][310/312]	eta 0:00:01 lr 0.001030	time 0.7231 (0.7500)	model_time 0.7229 (0.7441)	loss 2.9133 (2.9264)	grad_norm 1.4148 (1.7939/0.6898)	mem 34602MB
[2025-01-19 14:33:32 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][270/312]	eta 0:00:31 lr 0.001032	time 0.7316 (0.7507)	model_time 0.7314 (0.7443)	loss 3.7788 (2.9500)	grad_norm 0.8425 (1.8473/0.7971)	mem 34604MB
[2025-01-19 14:33:32 internimage_b_1k_224] (main.py 519): INFO EPOCH 199 training takes 0:03:53
[2025-01-19 14:33:32 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_199.pth saving......
[2025-01-19 14:33:35 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_199.pth saved !!!
[2025-01-19 14:33:39 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][280/312]	eta 0:00:23 lr 0.001032	time 0.7265 (0.7498)	model_time 0.7261 (0.7436)	loss 3.6635 (2.9534)	grad_norm 3.1214 (1.8493/0.7919)	mem 34604MB
[2025-01-19 14:33:43 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.843 (7.843)	Loss 0.7396 (0.7396)	Acc@1 84.668 (84.668)	Acc@5 97.510 (97.510)	Mem 34602MB
[2025-01-19 14:33:47 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][290/312]	eta 0:00:16 lr 0.001031	time 0.7189 (0.7490)	model_time 0.7185 (0.7431)	loss 2.9847 (2.9563)	grad_norm 2.4117 (1.8584/0.8023)	mem 34604MB
[2025-01-19 14:33:47 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.013)	Loss 0.9641 (0.8400)	Acc@1 78.711 (82.526)	Acc@5 95.239 (96.373)	Mem 34602MB
[2025-01-19 14:33:47 internimage_b_1k_224] (main.py 575): INFO [Epoch:199] * Acc@1 82.394 Acc@5 96.391
[2025-01-19 14:33:47 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.4%
[2025-01-19 14:33:47 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.59%
[2025-01-19 14:33:54 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][300/312]	eta 0:00:08 lr 0.001031	time 0.7139 (0.7481)	model_time 0.7138 (0.7424)	loss 3.4844 (2.9566)	grad_norm 1.3342 (1.8597/0.7995)	mem 34604MB
[2025-01-19 14:33:57 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.613 (9.613)	Loss 0.6978 (0.6978)	Acc@1 85.376 (85.376)	Acc@5 97.949 (97.949)	Mem 34602MB
[2025-01-19 14:34:01 internimage_b_1k_224] (main.py 510): INFO Train: [199/300][310/312]	eta 0:00:01 lr 0.001030	time 0.7159 (0.7471)	model_time 0.7158 (0.7416)	loss 2.7900 (2.9520)	grad_norm 2.1664 (1.8363/0.7761)	mem 34604MB
[2025-01-19 14:34:01 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.288)	Loss 0.9468 (0.8082)	Acc@1 78.979 (83.043)	Acc@5 95.190 (96.564)	Mem 34602MB
[2025-01-19 14:34:01 internimage_b_1k_224] (main.py 575): INFO [Epoch:199] * Acc@1 82.899 Acc@5 96.613
[2025-01-19 14:34:01 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.9%
[2025-01-19 14:34:01 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:34:02 internimage_b_1k_224] (main.py 519): INFO EPOCH 199 training takes 0:03:53
[2025-01-19 14:34:02 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_199.pth saving......
[2025-01-19 14:34:05 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:34:05 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.90%
[2025-01-19 14:34:05 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_199.pth saved !!!
[2025-01-19 14:34:07 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][0/312]	eta 0:12:18 lr 0.001030	time 2.3655 (2.3655)	model_time 0.7565 (0.7565)	loss 3.6322 (3.6322)	grad_norm 2.9828 (2.9828/0.0000)	mem 34602MB
[2025-01-19 14:34:12 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.228 (7.228)	Loss 0.7165 (0.7165)	Acc@1 85.083 (85.083)	Acc@5 97.510 (97.510)	Mem 34604MB
[2025-01-19 14:34:15 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][10/312]	eta 0:04:34 lr 0.001029	time 0.7184 (0.9094)	model_time 0.7182 (0.7628)	loss 1.7686 (2.8375)	grad_norm 1.6976 (2.2471/0.8752)	mem 34602MB
[2025-01-19 14:34:16 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.958)	Loss 0.9607 (0.8326)	Acc@1 78.833 (82.639)	Acc@5 95.459 (96.365)	Mem 34604MB
[2025-01-19 14:34:16 internimage_b_1k_224] (main.py 575): INFO [Epoch:199] * Acc@1 82.492 Acc@5 96.373
[2025-01-19 14:34:16 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.5%
[2025-01-19 14:34:16 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 14:34:19 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 14:34:19 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.49%
[2025-01-19 14:34:23 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][20/312]	eta 0:04:03 lr 0.001029	time 0.7274 (0.8353)	model_time 0.7272 (0.7584)	loss 3.0364 (2.8572)	grad_norm 2.5497 (2.0747/0.8107)	mem 34602MB
[2025-01-19 14:34:27 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.591 (7.591)	Loss 0.6928 (0.6928)	Acc@1 85.474 (85.474)	Acc@5 97.998 (97.998)	Mem 34604MB
[2025-01-19 14:34:30 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.954)	Loss 0.9452 (0.8067)	Acc@1 79.272 (83.066)	Acc@5 95.117 (96.489)	Mem 34604MB
[2025-01-19 14:34:30 internimage_b_1k_224] (main.py 575): INFO [Epoch:199] * Acc@1 82.871 Acc@5 96.539
[2025-01-19 14:34:30 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.9%
[2025-01-19 14:34:30 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:34:30 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][30/312]	eta 0:03:48 lr 0.001028	time 0.8025 (0.8111)	model_time 0.8021 (0.7589)	loss 3.5758 (2.8715)	grad_norm 1.9980 (2.0742/0.7392)	mem 34602MB
[2025-01-19 14:34:34 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:34:34 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.87%
[2025-01-19 14:34:36 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][0/312]	eta 0:12:04 lr 0.001030	time 2.3216 (2.3216)	model_time 0.7504 (0.7504)	loss 2.1156 (2.1156)	grad_norm 1.8775 (1.8775/0.0000)	mem 34604MB
[2025-01-19 14:34:38 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][40/312]	eta 0:03:37 lr 0.001028	time 0.7427 (0.7998)	model_time 0.7426 (0.7602)	loss 3.2925 (2.8998)	grad_norm 1.8071 (2.1547/0.8656)	mem 34602MB
[2025-01-19 14:34:44 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][10/312]	eta 0:04:26 lr 0.001029	time 0.8411 (0.8826)	model_time 0.8409 (0.7395)	loss 2.6525 (2.8434)	grad_norm 1.1652 (2.1755/0.7180)	mem 34604MB
[2025-01-19 14:34:45 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][50/312]	eta 0:03:26 lr 0.001027	time 0.7922 (0.7884)	model_time 0.7921 (0.7565)	loss 3.6140 (2.9345)	grad_norm 1.1971 (2.0166/0.8577)	mem 34602MB
[2025-01-19 14:34:51 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][20/312]	eta 0:04:00 lr 0.001029	time 0.8704 (0.8226)	model_time 0.8703 (0.7475)	loss 2.9412 (2.8684)	grad_norm 2.0191 (2.1029/0.8246)	mem 34604MB
[2025-01-19 14:34:53 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][60/312]	eta 0:03:16 lr 0.001027	time 0.7160 (0.7796)	model_time 0.7155 (0.7529)	loss 2.1762 (2.9440)	grad_norm 1.8467 (1.8967/0.8521)	mem 34602MB
[2025-01-19 14:34:59 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][30/312]	eta 0:03:45 lr 0.001028	time 0.7190 (0.7988)	model_time 0.7186 (0.7478)	loss 2.6351 (2.9111)	grad_norm 1.4159 (2.0547/0.7784)	mem 34604MB
[2025-01-19 14:35:00 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][70/312]	eta 0:03:07 lr 0.001026	time 0.8030 (0.7745)	model_time 0.8025 (0.7515)	loss 2.9006 (2.9490)	grad_norm 1.5867 (1.8407/0.8153)	mem 34602MB
[2025-01-19 14:35:06 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][40/312]	eta 0:03:35 lr 0.001028	time 0.8074 (0.7925)	model_time 0.8070 (0.7539)	loss 2.6485 (2.8528)	grad_norm 1.0773 (2.0289/0.7553)	mem 34604MB
[2025-01-19 14:35:07 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][80/312]	eta 0:02:58 lr 0.001025	time 0.7302 (0.7709)	model_time 0.7298 (0.7507)	loss 3.3305 (2.9447)	grad_norm 1.0151 (1.7700/0.7897)	mem 34602MB
[2025-01-19 14:35:14 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][50/312]	eta 0:03:26 lr 0.001027	time 0.7164 (0.7879)	model_time 0.7163 (0.7568)	loss 3.3552 (2.8525)	grad_norm 2.0185 (1.9902/0.7312)	mem 34604MB
[2025-01-19 14:35:15 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][90/312]	eta 0:02:50 lr 0.001025	time 0.7239 (0.7663)	model_time 0.7234 (0.7483)	loss 2.0933 (2.9294)	grad_norm 1.2575 (1.7503/0.7686)	mem 34602MB
[2025-01-19 14:35:22 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][60/312]	eta 0:03:17 lr 0.001027	time 0.8067 (0.7821)	model_time 0.8065 (0.7560)	loss 2.9121 (2.8729)	grad_norm 1.1883 (1.9236/0.7233)	mem 34604MB
[2025-01-19 14:35:22 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][100/312]	eta 0:02:42 lr 0.001024	time 0.7227 (0.7643)	model_time 0.7225 (0.7480)	loss 2.9770 (2.9332)	grad_norm 3.6059 (1.8402/0.8583)	mem 34602MB
[2025-01-19 14:35:29 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][70/312]	eta 0:03:07 lr 0.001026	time 0.7205 (0.7752)	model_time 0.7203 (0.7527)	loss 2.8336 (2.8593)	grad_norm 1.9616 (1.9430/0.7365)	mem 34604MB
[2025-01-19 14:35:30 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][110/312]	eta 0:02:33 lr 0.001024	time 0.7175 (0.7617)	model_time 0.7173 (0.7469)	loss 2.4005 (2.9431)	grad_norm 0.8644 (1.8094/0.8329)	mem 34602MB
[2025-01-19 14:35:36 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][80/312]	eta 0:02:58 lr 0.001025	time 0.7182 (0.7694)	model_time 0.7181 (0.7496)	loss 2.3865 (2.8713)	grad_norm 1.7925 (1.9134/0.7115)	mem 34604MB
[2025-01-19 14:35:37 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][120/312]	eta 0:02:26 lr 0.001023	time 0.7163 (0.7605)	model_time 0.7159 (0.7469)	loss 3.0250 (2.9049)	grad_norm 1.6748 (1.7829/0.8169)	mem 34602MB
[2025-01-19 14:35:43 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][90/312]	eta 0:02:49 lr 0.001025	time 0.7450 (0.7646)	model_time 0.7445 (0.7470)	loss 3.7930 (2.8940)	grad_norm 1.0340 (1.8881/0.6900)	mem 34604MB
[2025-01-19 14:35:45 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][130/312]	eta 0:02:18 lr 0.001023	time 0.7265 (0.7601)	model_time 0.7263 (0.7474)	loss 3.1057 (2.9190)	grad_norm 1.5758 (1.8052/0.8208)	mem 34602MB
[2025-01-19 14:35:51 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][100/312]	eta 0:02:41 lr 0.001024	time 0.7560 (0.7610)	model_time 0.7558 (0.7451)	loss 3.2968 (2.8794)	grad_norm 1.4833 (1.8810/0.6812)	mem 34604MB
[2025-01-19 14:35:52 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][140/312]	eta 0:02:10 lr 0.001022	time 0.7167 (0.7604)	model_time 0.7166 (0.7486)	loss 3.0739 (2.9398)	grad_norm 0.8163 (1.8113/0.8206)	mem 34602MB
[2025-01-19 14:35:58 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][110/312]	eta 0:02:33 lr 0.001024	time 0.7146 (0.7578)	model_time 0.7145 (0.7433)	loss 2.6326 (2.8964)	grad_norm 2.5527 (1.9188/0.6990)	mem 34604MB
[2025-01-19 14:36:00 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][150/312]	eta 0:02:03 lr 0.001021	time 0.8048 (0.7593)	model_time 0.8047 (0.7483)	loss 2.2764 (2.9438)	grad_norm 1.9107 (1.8034/0.8156)	mem 34602MB
[2025-01-19 14:36:05 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][120/312]	eta 0:02:25 lr 0.001023	time 0.7484 (0.7558)	model_time 0.7479 (0.7425)	loss 3.3429 (2.8999)	grad_norm 1.4377 (1.8910/0.6921)	mem 34604MB
[2025-01-19 14:36:07 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][160/312]	eta 0:01:55 lr 0.001021	time 0.7170 (0.7588)	model_time 0.7166 (0.7484)	loss 2.8181 (2.9342)	grad_norm 1.4920 (1.7950/0.7976)	mem 34602MB
[2025-01-19 14:36:13 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][130/312]	eta 0:02:17 lr 0.001023	time 0.7183 (0.7538)	model_time 0.7179 (0.7414)	loss 3.0698 (2.9180)	grad_norm 1.1567 (1.8762/0.6844)	mem 34604MB
[2025-01-19 14:36:15 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][170/312]	eta 0:01:47 lr 0.001020	time 0.8005 (0.7583)	model_time 0.8000 (0.7485)	loss 2.3014 (2.9367)	grad_norm 1.1244 (1.8044/0.7962)	mem 34602MB
[2025-01-19 14:36:20 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][140/312]	eta 0:02:09 lr 0.001022	time 0.8183 (0.7547)	model_time 0.8181 (0.7432)	loss 3.6232 (2.9280)	grad_norm 1.6292 (1.8620/0.6793)	mem 34604MB
[2025-01-19 14:36:22 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][180/312]	eta 0:01:39 lr 0.001020	time 0.7387 (0.7568)	model_time 0.7386 (0.7476)	loss 1.8265 (2.9391)	grad_norm 2.0796 (1.8207/0.8176)	mem 34602MB
[2025-01-19 14:36:28 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][150/312]	eta 0:02:02 lr 0.001021	time 0.7202 (0.7549)	model_time 0.7201 (0.7442)	loss 2.4599 (2.9157)	grad_norm 3.3799 (1.9237/0.7259)	mem 34604MB
[2025-01-19 14:36:29 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][190/312]	eta 0:01:32 lr 0.001019	time 0.7210 (0.7555)	model_time 0.7206 (0.7467)	loss 2.5299 (2.9332)	grad_norm 1.1402 (1.8296/0.8231)	mem 34602MB
[2025-01-19 14:36:36 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][160/312]	eta 0:01:54 lr 0.001021	time 0.7156 (0.7560)	model_time 0.7154 (0.7459)	loss 3.2453 (2.9265)	grad_norm 1.5587 (1.9204/0.7314)	mem 34604MB
[2025-01-19 14:36:37 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][200/312]	eta 0:01:24 lr 0.001019	time 0.7224 (0.7548)	model_time 0.7222 (0.7465)	loss 3.4983 (2.9308)	grad_norm 1.5165 (1.8246/0.8101)	mem 34602MB
[2025-01-19 14:36:43 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][170/312]	eta 0:01:47 lr 0.001020	time 0.7164 (0.7563)	model_time 0.7162 (0.7468)	loss 3.2014 (2.9144)	grad_norm 1.7800 (1.9063/0.7160)	mem 34604MB
[2025-01-19 14:36:44 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][210/312]	eta 0:01:16 lr 0.001018	time 0.7288 (0.7534)	model_time 0.7287 (0.7454)	loss 2.8943 (2.9407)	grad_norm 4.1760 (1.8561/0.8243)	mem 34602MB
[2025-01-19 14:36:51 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][180/312]	eta 0:01:39 lr 0.001020	time 0.8089 (0.7565)	model_time 0.8085 (0.7475)	loss 2.9368 (2.9157)	grad_norm 2.1308 (1.8985/0.7146)	mem 34604MB
[2025-01-19 14:36:51 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][220/312]	eta 0:01:09 lr 0.001017	time 0.7189 (0.7532)	model_time 0.7185 (0.7456)	loss 1.9957 (2.9374)	grad_norm 1.8783 (1.8474/0.8162)	mem 34602MB
[2025-01-19 14:36:58 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][190/312]	eta 0:01:32 lr 0.001019	time 0.7476 (0.7554)	model_time 0.7474 (0.7469)	loss 3.2158 (2.9245)	grad_norm 1.1742 (1.8962/0.7172)	mem 34604MB
[2025-01-19 14:36:59 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][230/312]	eta 0:01:01 lr 0.001017	time 0.7212 (0.7523)	model_time 0.7210 (0.7450)	loss 3.5330 (2.9342)	grad_norm 1.0703 (1.8246/0.8105)	mem 34602MB
[2025-01-19 14:37:05 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][200/312]	eta 0:01:24 lr 0.001019	time 0.7240 (0.7539)	model_time 0.7239 (0.7457)	loss 3.4874 (2.9092)	grad_norm 1.0196 (1.9250/0.7648)	mem 34604MB
[2025-01-19 14:37:06 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][240/312]	eta 0:00:54 lr 0.001016	time 0.7209 (0.7526)	model_time 0.7205 (0.7456)	loss 3.2648 (2.9364)	grad_norm 1.3741 (1.8457/0.8101)	mem 34602MB
[2025-01-19 14:37:13 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][210/312]	eta 0:01:16 lr 0.001018	time 0.7180 (0.7524)	model_time 0.7178 (0.7446)	loss 2.4773 (2.9027)	grad_norm 1.1386 (1.9019/0.7557)	mem 34604MB
[2025-01-19 14:37:14 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][250/312]	eta 0:00:46 lr 0.001016	time 0.7201 (0.7527)	model_time 0.7195 (0.7459)	loss 2.9550 (2.9308)	grad_norm 3.7298 (1.8543/0.8126)	mem 34602MB
[2025-01-19 14:37:20 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][220/312]	eta 0:01:09 lr 0.001017	time 0.7274 (0.7511)	model_time 0.7270 (0.7436)	loss 3.1631 (2.9113)	grad_norm 1.5257 (1.8832/0.7471)	mem 34604MB
[2025-01-19 14:37:22 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][260/312]	eta 0:00:39 lr 0.001015	time 0.7237 (0.7534)	model_time 0.7233 (0.7469)	loss 3.5297 (2.9381)	grad_norm 3.0051 (1.8729/0.8196)	mem 34602MB
[2025-01-19 14:37:27 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][230/312]	eta 0:01:01 lr 0.001017	time 0.7241 (0.7499)	model_time 0.7239 (0.7428)	loss 3.4338 (2.9140)	grad_norm 2.3596 (1.8786/0.7439)	mem 34604MB
[2025-01-19 14:37:29 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][270/312]	eta 0:00:31 lr 0.001015	time 0.8040 (0.7529)	model_time 0.8039 (0.7466)	loss 3.1842 (2.9456)	grad_norm 2.4797 (1.8734/0.8283)	mem 34602MB
[2025-01-19 14:37:34 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][240/312]	eta 0:00:53 lr 0.001016	time 0.7278 (0.7490)	model_time 0.7276 (0.7421)	loss 2.2266 (2.9191)	grad_norm 1.2433 (1.8676/0.7358)	mem 34604MB
[2025-01-19 14:37:37 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][280/312]	eta 0:00:24 lr 0.001014	time 0.7571 (0.7529)	model_time 0.7569 (0.7468)	loss 2.8513 (2.9415)	grad_norm 1.4423 (1.8915/0.8384)	mem 34602MB
[2025-01-19 14:37:42 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][250/312]	eta 0:00:46 lr 0.001016	time 0.7296 (0.7483)	model_time 0.7290 (0.7417)	loss 3.0237 (2.9161)	grad_norm 1.1452 (1.8734/0.7373)	mem 34604MB
[2025-01-19 14:37:44 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][290/312]	eta 0:00:16 lr 0.001013	time 0.8068 (0.7526)	model_time 0.8064 (0.7467)	loss 3.5220 (2.9493)	grad_norm 0.8447 (1.8853/0.8316)	mem 34602MB
[2025-01-19 14:37:49 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][260/312]	eta 0:00:38 lr 0.001015	time 0.8200 (0.7484)	model_time 0.8198 (0.7421)	loss 3.0946 (2.9188)	grad_norm 1.5257 (1.8772/0.7340)	mem 34604MB
[2025-01-19 14:37:51 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][300/312]	eta 0:00:09 lr 0.001013	time 0.7141 (0.7519)	model_time 0.7140 (0.7462)	loss 3.2700 (2.9528)	grad_norm 1.6764 (1.8653/0.8242)	mem 34602MB
[2025-01-19 14:37:57 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][270/312]	eta 0:00:31 lr 0.001015	time 0.7147 (0.7486)	model_time 0.7146 (0.7425)	loss 1.8466 (2.9114)	grad_norm 1.0613 (1.8642/0.7302)	mem 34604MB
[2025-01-19 14:37:59 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][310/312]	eta 0:00:01 lr 0.001012	time 0.7157 (0.7511)	model_time 0.7156 (0.7456)	loss 3.6935 (2.9541)	grad_norm 1.2735 (1.8389/0.8127)	mem 34602MB
[2025-01-19 14:37:59 internimage_b_1k_224] (main.py 519): INFO EPOCH 200 training takes 0:03:54
[2025-01-19 14:37:59 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_200.pth saving......
[2025-01-19 14:38:03 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_200.pth saved !!!
[2025-01-19 14:38:05 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][280/312]	eta 0:00:23 lr 0.001014	time 0.7108 (0.7497)	model_time 0.7103 (0.7437)	loss 2.0549 (2.9159)	grad_norm 1.4293 (1.8750/0.7464)	mem 34604MB
[2025-01-19 14:38:10 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.601 (7.601)	Loss 0.7195 (0.7195)	Acc@1 85.596 (85.596)	Acc@5 97.729 (97.729)	Mem 34602MB
[2025-01-19 14:38:12 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][290/312]	eta 0:00:16 lr 0.001013	time 0.7173 (0.7499)	model_time 0.7171 (0.7441)	loss 2.4825 (2.9211)	grad_norm 1.5018 (1.8624/0.7399)	mem 34604MB
[2025-01-19 14:38:14 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.976)	Loss 0.9876 (0.8361)	Acc@1 77.954 (82.591)	Acc@5 95.142 (96.449)	Mem 34602MB
[2025-01-19 14:38:14 internimage_b_1k_224] (main.py 575): INFO [Epoch:200] * Acc@1 82.502 Acc@5 96.433
[2025-01-19 14:38:14 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.5%
[2025-01-19 14:38:14 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.59%
[2025-01-19 14:38:20 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][300/312]	eta 0:00:08 lr 0.001013	time 0.7138 (0.7497)	model_time 0.7137 (0.7442)	loss 2.9031 (2.9202)	grad_norm 1.8081 (1.8495/0.7345)	mem 34604MB
[2025-01-19 14:38:23 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.420 (9.420)	Loss 0.6989 (0.6989)	Acc@1 85.376 (85.376)	Acc@5 97.925 (97.925)	Mem 34602MB
[2025-01-19 14:38:27 internimage_b_1k_224] (main.py 510): INFO Train: [200/300][310/312]	eta 0:00:01 lr 0.001012	time 0.7153 (0.7495)	model_time 0.7152 (0.7441)	loss 3.6052 (2.9289)	grad_norm 1.3756 (1.8202/0.7258)	mem 34604MB
[2025-01-19 14:38:28 internimage_b_1k_224] (main.py 519): INFO EPOCH 200 training takes 0:03:53
[2025-01-19 14:38:28 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_200.pth saving......
[2025-01-19 14:38:28 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.273)	Loss 0.9466 (0.8086)	Acc@1 78.979 (83.059)	Acc@5 95.239 (96.551)	Mem 34602MB
[2025-01-19 14:38:28 internimage_b_1k_224] (main.py 575): INFO [Epoch:200] * Acc@1 82.921 Acc@5 96.599
[2025-01-19 14:38:28 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.9%
[2025-01-19 14:38:28 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:38:31 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_200.pth saved !!!
[2025-01-19 14:38:32 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:38:32 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.92%
[2025-01-19 14:38:34 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][0/312]	eta 0:11:14 lr 0.001012	time 2.1610 (2.1610)	model_time 0.7478 (0.7478)	loss 2.8573 (2.8573)	grad_norm 1.5739 (1.5739/0.0000)	mem 34602MB
[2025-01-19 14:38:38 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.447 (7.447)	Loss 0.7303 (0.7303)	Acc@1 85.742 (85.742)	Acc@5 97.510 (97.510)	Mem 34604MB
[2025-01-19 14:38:42 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.969)	Loss 0.9921 (0.8510)	Acc@1 79.175 (82.739)	Acc@5 95.020 (96.351)	Mem 34604MB
[2025-01-19 14:38:42 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][10/312]	eta 0:04:26 lr 0.001012	time 0.7180 (0.8819)	model_time 0.7178 (0.7531)	loss 2.9893 (2.9386)	grad_norm 1.0866 (1.3962/0.3845)	mem 34602MB
[2025-01-19 14:38:42 internimage_b_1k_224] (main.py 575): INFO [Epoch:200] * Acc@1 82.620 Acc@5 96.397
[2025-01-19 14:38:42 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.6%
[2025-01-19 14:38:42 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 14:38:45 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 14:38:45 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.62%
[2025-01-19 14:38:49 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][20/312]	eta 0:03:56 lr 0.001011	time 0.7222 (0.8103)	model_time 0.7218 (0.7426)	loss 3.3526 (3.0028)	grad_norm 1.7563 (1.5154/0.3431)	mem 34602MB
[2025-01-19 14:38:53 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.381 (7.381)	Loss 0.6936 (0.6936)	Acc@1 85.425 (85.425)	Acc@5 98.047 (98.047)	Mem 34604MB
[2025-01-19 14:38:56 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.971)	Loss 0.9449 (0.8070)	Acc@1 79.248 (83.048)	Acc@5 95.117 (96.518)	Mem 34604MB
[2025-01-19 14:38:56 internimage_b_1k_224] (main.py 575): INFO [Epoch:200] * Acc@1 82.857 Acc@5 96.569
[2025-01-19 14:38:56 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.9%
[2025-01-19 14:38:56 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.87%
[2025-01-19 14:38:57 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][30/312]	eta 0:03:42 lr 0.001010	time 0.7239 (0.7907)	model_time 0.7235 (0.7447)	loss 2.4583 (2.9649)	grad_norm 3.9099 (1.6981/0.6694)	mem 34602MB
[2025-01-19 14:39:00 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][0/312]	eta 0:20:51 lr 0.001012	time 4.0123 (4.0123)	model_time 1.4950 (1.4950)	loss 3.0998 (3.0998)	grad_norm 2.0747 (2.0747/0.0000)	mem 34604MB
[2025-01-19 14:39:04 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][40/312]	eta 0:03:31 lr 0.001010	time 0.7276 (0.7780)	model_time 0.7274 (0.7431)	loss 2.8924 (2.9327)	grad_norm 2.1466 (1.7256/0.7186)	mem 34602MB
[2025-01-19 14:39:07 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][10/312]	eta 0:05:11 lr 0.001012	time 0.7129 (1.0300)	model_time 0.7127 (0.8008)	loss 2.4693 (2.9992)	grad_norm 2.0397 (1.7213/0.4644)	mem 34604MB
[2025-01-19 14:39:11 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][50/312]	eta 0:03:22 lr 0.001009	time 0.8119 (0.7724)	model_time 0.8117 (0.7443)	loss 2.6338 (2.9000)	grad_norm 0.9383 (1.6817/0.6818)	mem 34602MB
[2025-01-19 14:39:15 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][20/312]	eta 0:04:18 lr 0.001011	time 0.7318 (0.8855)	model_time 0.7316 (0.7653)	loss 1.8551 (2.9720)	grad_norm 3.6192 (2.0974/0.8456)	mem 34604MB
[2025-01-19 14:39:19 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][60/312]	eta 0:03:13 lr 0.001009	time 0.8012 (0.7693)	model_time 0.8011 (0.7457)	loss 2.8494 (2.9100)	grad_norm 2.0721 (1.7858/0.7505)	mem 34602MB
[2025-01-19 14:39:22 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][30/312]	eta 0:03:55 lr 0.001010	time 0.7225 (0.8337)	model_time 0.7221 (0.7522)	loss 3.3328 (2.9842)	grad_norm 3.5572 (2.3357/0.9560)	mem 34604MB
[2025-01-19 14:39:26 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][70/312]	eta 0:03:05 lr 0.001008	time 0.7225 (0.7660)	model_time 0.7220 (0.7457)	loss 3.0852 (2.9388)	grad_norm 1.4697 (1.7854/0.7197)	mem 34602MB
[2025-01-19 14:39:29 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][40/312]	eta 0:03:39 lr 0.001010	time 0.7288 (0.8085)	model_time 0.7284 (0.7468)	loss 3.1019 (2.9598)	grad_norm 2.4774 (2.3168/0.8768)	mem 34604MB
[2025-01-19 14:39:34 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][80/312]	eta 0:02:57 lr 0.001008	time 0.7258 (0.7629)	model_time 0.7253 (0.7451)	loss 1.8798 (2.9435)	grad_norm 1.2691 (1.7706/0.7096)	mem 34602MB
[2025-01-19 14:39:37 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][50/312]	eta 0:03:27 lr 0.001009	time 0.7179 (0.7916)	model_time 0.7177 (0.7420)	loss 2.7130 (2.9596)	grad_norm 2.6319 (2.1668/0.8713)	mem 34604MB
[2025-01-19 14:39:41 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][90/312]	eta 0:02:49 lr 0.001007	time 0.7179 (0.7624)	model_time 0.7175 (0.7465)	loss 1.9043 (2.9351)	grad_norm 3.4815 (1.7672/0.7073)	mem 34602MB
[2025-01-19 14:39:44 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][60/312]	eta 0:03:16 lr 0.001009	time 0.7451 (0.7810)	model_time 0.7450 (0.7395)	loss 3.1536 (2.9455)	grad_norm 1.5235 (2.1200/0.8223)	mem 34604MB
[2025-01-19 14:39:49 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][100/312]	eta 0:02:40 lr 0.001006	time 0.7177 (0.7594)	model_time 0.7176 (0.7450)	loss 3.2141 (2.9462)	grad_norm 1.3212 (1.7891/0.6990)	mem 34602MB
[2025-01-19 14:39:51 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][70/312]	eta 0:03:08 lr 0.001008	time 0.8105 (0.7770)	model_time 0.8101 (0.7412)	loss 3.2402 (2.9303)	grad_norm 2.1410 (2.1127/0.8421)	mem 34604MB
[2025-01-19 14:39:56 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][110/312]	eta 0:02:33 lr 0.001006	time 0.7298 (0.7575)	model_time 0.7296 (0.7444)	loss 3.6037 (2.9636)	grad_norm 2.0803 (1.7710/0.6936)	mem 34602MB
[2025-01-19 14:39:59 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][80/312]	eta 0:02:59 lr 0.001008	time 0.8074 (0.7746)	model_time 0.8073 (0.7432)	loss 2.5851 (2.9421)	grad_norm 1.8313 (2.1381/0.8712)	mem 34604MB
[2025-01-19 14:40:04 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][120/312]	eta 0:02:25 lr 0.001005	time 0.7224 (0.7575)	model_time 0.7223 (0.7455)	loss 2.7709 (2.9563)	grad_norm 1.2471 (1.7394/0.6790)	mem 34602MB
[2025-01-19 14:40:07 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][90/312]	eta 0:02:51 lr 0.001007	time 0.8038 (0.7733)	model_time 0.8033 (0.7453)	loss 2.9015 (2.9384)	grad_norm 1.6465 (2.0615/0.8551)	mem 34604MB
[2025-01-19 14:40:11 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][130/312]	eta 0:02:17 lr 0.001005	time 0.7335 (0.7572)	model_time 0.7331 (0.7460)	loss 2.4916 (2.9475)	grad_norm 1.5950 (1.7052/0.6711)	mem 34602MB
[2025-01-19 14:40:14 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][100/312]	eta 0:02:43 lr 0.001006	time 0.8020 (0.7733)	model_time 0.8018 (0.7481)	loss 3.1669 (2.9543)	grad_norm 3.4170 (2.0551/0.8514)	mem 34604MB
[2025-01-19 14:40:19 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][140/312]	eta 0:02:09 lr 0.001004	time 0.7207 (0.7553)	model_time 0.7206 (0.7448)	loss 3.5505 (2.9347)	grad_norm 2.7313 (1.7234/0.6725)	mem 34602MB
[2025-01-19 14:40:22 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][110/312]	eta 0:02:35 lr 0.001006	time 0.8193 (0.7706)	model_time 0.8191 (0.7476)	loss 2.8644 (2.9556)	grad_norm 1.9544 (2.0342/0.8448)	mem 34604MB
[2025-01-19 14:40:26 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][150/312]	eta 0:02:02 lr 0.001004	time 0.7168 (0.7549)	model_time 0.7166 (0.7451)	loss 3.6931 (2.9604)	grad_norm 2.2643 (1.7907/0.7512)	mem 34602MB
[2025-01-19 14:40:29 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][120/312]	eta 0:02:27 lr 0.001005	time 0.7285 (0.7680)	model_time 0.7284 (0.7469)	loss 3.8987 (2.9724)	grad_norm 2.1315 (1.9931/0.8270)	mem 34604MB
[2025-01-19 14:40:33 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][160/312]	eta 0:01:54 lr 0.001003	time 0.7225 (0.7537)	model_time 0.7221 (0.7445)	loss 3.7002 (2.9716)	grad_norm 0.9620 (1.7689/0.7392)	mem 34602MB
[2025-01-19 14:40:36 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][130/312]	eta 0:02:19 lr 0.001005	time 0.7208 (0.7647)	model_time 0.7203 (0.7451)	loss 3.1800 (2.9758)	grad_norm 2.6387 (1.9809/0.8065)	mem 34604MB
[2025-01-19 14:40:41 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][170/312]	eta 0:01:47 lr 0.001002	time 0.8194 (0.7538)	model_time 0.8189 (0.7451)	loss 2.9550 (2.9735)	grad_norm 0.9856 (1.7598/0.7330)	mem 34602MB
[2025-01-19 14:40:44 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][140/312]	eta 0:02:11 lr 0.001004	time 0.7337 (0.7623)	model_time 0.7332 (0.7441)	loss 2.7303 (2.9814)	grad_norm 1.0771 (1.9928/0.8147)	mem 34604MB
[2025-01-19 14:40:48 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][180/312]	eta 0:01:39 lr 0.001002	time 0.7934 (0.7535)	model_time 0.7933 (0.7453)	loss 3.7204 (2.9801)	grad_norm 1.4776 (1.7405/0.7245)	mem 34602MB
[2025-01-19 14:40:51 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][150/312]	eta 0:02:03 lr 0.001004	time 0.7107 (0.7597)	model_time 0.7105 (0.7427)	loss 2.6752 (2.9854)	grad_norm 3.2785 (2.0024/0.8343)	mem 34604MB
[2025-01-19 14:40:56 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][190/312]	eta 0:01:31 lr 0.001001	time 0.7290 (0.7533)	model_time 0.7286 (0.7455)	loss 3.4046 (2.9906)	grad_norm 1.5978 (1.7296/0.7223)	mem 34602MB
[2025-01-19 14:40:58 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][160/312]	eta 0:01:55 lr 0.001003	time 0.7255 (0.7578)	model_time 0.7250 (0.7418)	loss 3.6660 (3.0011)	grad_norm 1.5466 (1.9872/0.8302)	mem 34604MB
[2025-01-19 14:41:03 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][200/312]	eta 0:01:24 lr 0.001001	time 0.7192 (0.7525)	model_time 0.7186 (0.7451)	loss 2.6018 (2.9927)	grad_norm 3.1204 (1.7429/0.7363)	mem 34602MB
[2025-01-19 14:41:05 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][170/312]	eta 0:01:47 lr 0.001002	time 0.7203 (0.7558)	model_time 0.7199 (0.7408)	loss 3.2010 (3.0108)	grad_norm 3.0554 (1.9895/0.8172)	mem 34604MB
[2025-01-19 14:41:11 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][210/312]	eta 0:01:16 lr 0.001000	time 0.7279 (0.7528)	model_time 0.7278 (0.7457)	loss 3.0702 (2.9875)	grad_norm 2.0129 (1.7649/0.7451)	mem 34602MB
[2025-01-19 14:41:13 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][180/312]	eta 0:01:39 lr 0.001002	time 0.7290 (0.7541)	model_time 0.7285 (0.7399)	loss 3.4739 (3.0237)	grad_norm 0.8345 (1.9906/0.8222)	mem 34604MB
[2025-01-19 14:41:18 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][220/312]	eta 0:01:09 lr 0.001000	time 0.7546 (0.7520)	model_time 0.7541 (0.7452)	loss 2.5275 (2.9868)	grad_norm 1.5345 (1.7800/0.7418)	mem 34602MB
[2025-01-19 14:41:20 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][190/312]	eta 0:01:31 lr 0.001001	time 0.7207 (0.7537)	model_time 0.7202 (0.7402)	loss 3.3284 (3.0249)	grad_norm 1.3599 (1.9586/0.8152)	mem 34604MB
[2025-01-19 14:41:26 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][230/312]	eta 0:01:01 lr 0.000999	time 0.7469 (0.7515)	model_time 0.7464 (0.7450)	loss 3.1814 (2.9868)	grad_norm 1.5337 (1.7853/0.7349)	mem 34602MB
[2025-01-19 14:41:28 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][200/312]	eta 0:01:24 lr 0.001001	time 0.8157 (0.7548)	model_time 0.8155 (0.7419)	loss 3.2756 (3.0136)	grad_norm 3.8811 (1.9858/0.8718)	mem 34604MB
[2025-01-19 14:41:33 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][240/312]	eta 0:00:54 lr 0.000998	time 0.7436 (0.7511)	model_time 0.7435 (0.7448)	loss 2.9678 (2.9888)	grad_norm 1.1033 (1.7892/0.7402)	mem 34602MB
[2025-01-19 14:41:35 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][210/312]	eta 0:01:17 lr 0.001000	time 0.8068 (0.7551)	model_time 0.8067 (0.7429)	loss 2.3833 (3.0168)	grad_norm 1.0957 (1.9546/0.8663)	mem 34604MB
[2025-01-19 14:41:40 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][250/312]	eta 0:00:46 lr 0.000998	time 0.7238 (0.7507)	model_time 0.7236 (0.7447)	loss 3.4475 (2.9854)	grad_norm 3.7360 (1.8127/0.7497)	mem 34602MB
[2025-01-19 14:41:43 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][220/312]	eta 0:01:09 lr 0.001000	time 0.8095 (0.7557)	model_time 0.8094 (0.7440)	loss 2.9739 (3.0138)	grad_norm 2.6359 (1.9596/0.8745)	mem 34604MB
[2025-01-19 14:41:48 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][260/312]	eta 0:00:38 lr 0.000997	time 0.7252 (0.7498)	model_time 0.7248 (0.7440)	loss 2.3394 (2.9893)	grad_norm 1.7670 (1.8209/0.7449)	mem 34602MB
[2025-01-19 14:41:51 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][230/312]	eta 0:01:01 lr 0.000999	time 0.8109 (0.7550)	model_time 0.8108 (0.7438)	loss 2.0166 (3.0122)	grad_norm 1.3238 (1.9542/0.8632)	mem 34604MB
[2025-01-19 14:41:55 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][270/312]	eta 0:00:31 lr 0.000997	time 0.7161 (0.7497)	model_time 0.7156 (0.7441)	loss 3.4669 (2.9988)	grad_norm 1.7570 (1.8059/0.7384)	mem 34602MB
[2025-01-19 14:41:58 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][240/312]	eta 0:00:54 lr 0.000998	time 0.7206 (0.7550)	model_time 0.7202 (0.7442)	loss 3.6671 (3.0113)	grad_norm 1.3685 (1.9615/0.8593)	mem 34604MB
[2025-01-19 14:42:03 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][280/312]	eta 0:00:23 lr 0.000996	time 0.7304 (0.7493)	model_time 0.7302 (0.7439)	loss 3.0496 (2.9977)	grad_norm 1.8035 (1.8087/0.7345)	mem 34602MB
[2025-01-19 14:42:05 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][250/312]	eta 0:00:46 lr 0.000998	time 0.7216 (0.7538)	model_time 0.7215 (0.7434)	loss 3.0097 (2.9997)	grad_norm 0.8929 (1.9428/0.8496)	mem 34604MB
[2025-01-19 14:42:10 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][290/312]	eta 0:00:16 lr 0.000996	time 0.8124 (0.7494)	model_time 0.8123 (0.7442)	loss 3.2484 (2.9962)	grad_norm 2.8057 (1.8273/0.7485)	mem 34602MB
[2025-01-19 14:42:13 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][260/312]	eta 0:00:39 lr 0.000997	time 0.7341 (0.7529)	model_time 0.7340 (0.7429)	loss 2.4034 (2.9952)	grad_norm 1.3502 (1.9272/0.8426)	mem 34604MB
[2025-01-19 14:42:18 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][300/312]	eta 0:00:08 lr 0.000995	time 0.7139 (0.7491)	model_time 0.7138 (0.7440)	loss 3.1950 (3.0007)	grad_norm 2.7588 (1.8214/0.7471)	mem 34602MB
[2025-01-19 14:42:20 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][270/312]	eta 0:00:31 lr 0.000997	time 0.7197 (0.7517)	model_time 0.7196 (0.7421)	loss 2.6104 (2.9959)	grad_norm 2.1217 (1.9253/0.8380)	mem 34604MB
[2025-01-19 14:42:25 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][310/312]	eta 0:00:01 lr 0.000994	time 0.7136 (0.7490)	model_time 0.7135 (0.7441)	loss 3.1402 (2.9937)	grad_norm 2.9107 (1.8315/0.7480)	mem 34602MB
[2025-01-19 14:42:26 internimage_b_1k_224] (main.py 519): INFO EPOCH 201 training takes 0:03:53
[2025-01-19 14:42:26 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_201.pth saving......
[2025-01-19 14:42:27 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][280/312]	eta 0:00:24 lr 0.000996	time 0.7189 (0.7507)	model_time 0.7184 (0.7414)	loss 3.2955 (2.9990)	grad_norm 5.4312 (1.9656/0.8999)	mem 34604MB
[2025-01-19 14:42:29 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_201.pth saved !!!
[2025-01-19 14:42:34 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][290/312]	eta 0:00:16 lr 0.000996	time 0.7205 (0.7499)	model_time 0.7201 (0.7409)	loss 3.3839 (3.0061)	grad_norm 2.4784 (1.9988/0.9147)	mem 34604MB
[2025-01-19 14:42:37 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.723 (7.723)	Loss 0.7342 (0.7342)	Acc@1 85.083 (85.083)	Acc@5 97.632 (97.632)	Mem 34602MB
[2025-01-19 14:42:40 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.994)	Loss 0.9747 (0.8415)	Acc@1 78.857 (82.748)	Acc@5 95.093 (96.456)	Mem 34602MB
[2025-01-19 14:42:40 internimage_b_1k_224] (main.py 575): INFO [Epoch:201] * Acc@1 82.562 Acc@5 96.469
[2025-01-19 14:42:40 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.6%
[2025-01-19 14:42:40 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.59%
[2025-01-19 14:42:42 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][300/312]	eta 0:00:08 lr 0.000995	time 0.7146 (0.7489)	model_time 0.7144 (0.7402)	loss 2.9598 (3.0040)	grad_norm 1.6634 (1.9952/0.9076)	mem 34604MB
[2025-01-19 14:42:49 internimage_b_1k_224] (main.py 510): INFO Train: [201/300][310/312]	eta 0:00:01 lr 0.000994	time 0.7968 (0.7483)	model_time 0.7967 (0.7399)	loss 2.9240 (3.0024)	grad_norm 2.2273 (1.9978/0.9092)	mem 34604MB
[2025-01-19 14:42:49 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.285 (9.285)	Loss 0.7000 (0.7000)	Acc@1 85.376 (85.376)	Acc@5 97.974 (97.974)	Mem 34602MB
[2025-01-19 14:42:50 internimage_b_1k_224] (main.py 519): INFO EPOCH 201 training takes 0:03:53
[2025-01-19 14:42:50 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_201.pth saving......
[2025-01-19 14:42:53 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_201.pth saved !!!
[2025-01-19 14:42:58 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.616)	Loss 0.9464 (0.8090)	Acc@1 78.955 (83.059)	Acc@5 95.288 (96.566)	Mem 34602MB
[2025-01-19 14:42:58 internimage_b_1k_224] (main.py 575): INFO [Epoch:201] * Acc@1 82.927 Acc@5 96.613
[2025-01-19 14:42:58 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.9%
[2025-01-19 14:42:58 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:43:02 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:43:02 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.93%
[2025-01-19 14:43:03 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 10.352 (10.352)	Loss 0.7420 (0.7420)	Acc@1 84.814 (84.814)	Acc@5 97.461 (97.461)	Mem 34604MB
[2025-01-19 14:43:05 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][0/312]	eta 0:11:59 lr 0.000994	time 2.3074 (2.3074)	model_time 0.7977 (0.7977)	loss 3.5123 (3.5123)	grad_norm 1.8792 (1.8792/0.0000)	mem 34602MB
[2025-01-19 14:43:08 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.329)	Loss 0.9765 (0.8440)	Acc@1 78.491 (82.697)	Acc@5 95.361 (96.418)	Mem 34604MB
[2025-01-19 14:43:08 internimage_b_1k_224] (main.py 575): INFO [Epoch:201] * Acc@1 82.574 Acc@5 96.411
[2025-01-19 14:43:08 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.6%
[2025-01-19 14:43:08 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.62%
[2025-01-19 14:43:12 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][10/312]	eta 0:04:28 lr 0.000994	time 0.7168 (0.8878)	model_time 0.7166 (0.7503)	loss 3.2909 (3.0084)	grad_norm 0.7839 (1.7503/0.9433)	mem 34602MB
[2025-01-19 14:43:17 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.528 (9.528)	Loss 0.6943 (0.6943)	Acc@1 85.498 (85.498)	Acc@5 98.047 (98.047)	Mem 34604MB
[2025-01-19 14:43:20 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][20/312]	eta 0:04:01 lr 0.000993	time 0.7330 (0.8256)	model_time 0.7328 (0.7534)	loss 2.9855 (3.0011)	grad_norm 1.4491 (1.9445/0.8837)	mem 34602MB
[2025-01-19 14:43:22 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.295)	Loss 0.9447 (0.8073)	Acc@1 79.321 (83.081)	Acc@5 95.190 (96.524)	Mem 34604MB
[2025-01-19 14:43:22 internimage_b_1k_224] (main.py 575): INFO [Epoch:201] * Acc@1 82.889 Acc@5 96.575
[2025-01-19 14:43:22 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.9%
[2025-01-19 14:43:22 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:43:26 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:43:26 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.89%
[2025-01-19 14:43:27 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][30/312]	eta 0:03:44 lr 0.000993	time 0.7255 (0.7966)	model_time 0.7253 (0.7475)	loss 2.6735 (2.9579)	grad_norm 2.5882 (2.0986/0.9082)	mem 34602MB
[2025-01-19 14:43:29 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][0/312]	eta 0:11:17 lr 0.000994	time 2.1711 (2.1711)	model_time 0.7269 (0.7269)	loss 2.8238 (2.8238)	grad_norm 1.2020 (1.2020/0.0000)	mem 34604MB
[2025-01-19 14:43:34 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][40/312]	eta 0:03:33 lr 0.000992	time 0.7188 (0.7849)	model_time 0.7187 (0.7477)	loss 1.7692 (2.9373)	grad_norm 1.5961 (2.1997/0.9050)	mem 34602MB
[2025-01-19 14:43:36 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][10/312]	eta 0:04:35 lr 0.000994	time 0.8676 (0.9128)	model_time 0.8675 (0.7812)	loss 2.7545 (3.1157)	grad_norm 1.7254 (1.5266/0.2778)	mem 34604MB
[2025-01-19 14:43:42 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][50/312]	eta 0:03:23 lr 0.000991	time 0.7179 (0.7763)	model_time 0.7174 (0.7464)	loss 3.1899 (2.9472)	grad_norm 0.9447 (2.2138/0.9219)	mem 34602MB
[2025-01-19 14:43:44 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][20/312]	eta 0:04:06 lr 0.000993	time 0.8185 (0.8426)	model_time 0.8181 (0.7735)	loss 2.2698 (3.0143)	grad_norm 1.3755 (1.4844/0.3207)	mem 34604MB
[2025-01-19 14:43:49 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][60/312]	eta 0:03:14 lr 0.000991	time 0.7301 (0.7717)	model_time 0.7299 (0.7466)	loss 3.2528 (2.9657)	grad_norm 1.2396 (2.1471/0.9005)	mem 34602MB
[2025-01-19 14:43:52 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][30/312]	eta 0:03:49 lr 0.000993	time 0.8241 (0.8154)	model_time 0.8239 (0.7684)	loss 2.2769 (2.9985)	grad_norm 2.1691 (1.5565/0.3858)	mem 34604MB
[2025-01-19 14:43:57 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][70/312]	eta 0:03:05 lr 0.000990	time 0.7269 (0.7658)	model_time 0.7264 (0.7442)	loss 3.1651 (3.0091)	grad_norm 1.9072 (2.1270/0.9207)	mem 34602MB
[2025-01-19 14:43:59 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][40/312]	eta 0:03:37 lr 0.000992	time 0.7177 (0.7987)	model_time 0.7172 (0.7631)	loss 2.2774 (2.9655)	grad_norm 2.8855 (1.7404/0.7217)	mem 34604MB
[2025-01-19 14:44:04 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][80/312]	eta 0:02:57 lr 0.000990	time 0.7179 (0.7637)	model_time 0.7177 (0.7447)	loss 3.1343 (3.0120)	grad_norm 2.3613 (2.0660/0.8983)	mem 34602MB
[2025-01-19 14:44:06 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][50/312]	eta 0:03:25 lr 0.000991	time 0.7207 (0.7858)	model_time 0.7205 (0.7572)	loss 3.1659 (2.9248)	grad_norm 4.3842 (1.8511/0.8617)	mem 34604MB
[2025-01-19 14:44:12 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][90/312]	eta 0:02:49 lr 0.000989	time 0.7169 (0.7615)	model_time 0.7167 (0.7446)	loss 2.9164 (2.9932)	grad_norm 1.3213 (2.0340/0.8704)	mem 34602MB
[2025-01-19 14:44:14 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][60/312]	eta 0:03:15 lr 0.000991	time 0.7265 (0.7772)	model_time 0.7260 (0.7532)	loss 3.0257 (2.9002)	grad_norm 2.7086 (1.9164/0.8728)	mem 34604MB
[2025-01-19 14:44:19 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][100/312]	eta 0:02:41 lr 0.000989	time 0.7164 (0.7603)	model_time 0.7163 (0.7450)	loss 3.3075 (3.0143)	grad_norm 1.7470 (1.9949/0.8582)	mem 34602MB
[2025-01-19 14:44:21 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][70/312]	eta 0:03:06 lr 0.000990	time 0.7368 (0.7702)	model_time 0.7367 (0.7495)	loss 2.9523 (2.9570)	grad_norm 2.3735 (1.9083/0.8495)	mem 34604MB
[2025-01-19 14:44:27 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][110/312]	eta 0:02:33 lr 0.000988	time 0.7242 (0.7600)	model_time 0.7238 (0.7460)	loss 3.4706 (3.0052)	grad_norm 1.0779 (1.9502/0.8441)	mem 34602MB
[2025-01-19 14:44:28 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][80/312]	eta 0:02:57 lr 0.000990	time 0.7243 (0.7654)	model_time 0.7239 (0.7473)	loss 2.7020 (2.9498)	grad_norm 2.0002 (1.8894/0.8068)	mem 34604MB
[2025-01-19 14:44:34 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][120/312]	eta 0:02:25 lr 0.000987	time 0.7189 (0.7593)	model_time 0.7187 (0.7465)	loss 2.5879 (2.9860)	grad_norm 1.9347 (1.8946/0.8347)	mem 34602MB
[2025-01-19 14:44:36 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][90/312]	eta 0:02:49 lr 0.000989	time 0.7185 (0.7616)	model_time 0.7183 (0.7454)	loss 3.3754 (2.9636)	grad_norm 1.2088 (1.8403/0.7889)	mem 34604MB
[2025-01-19 14:44:42 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][130/312]	eta 0:02:17 lr 0.000987	time 0.7281 (0.7580)	model_time 0.7279 (0.7461)	loss 3.1675 (2.9650)	grad_norm 1.5290 (1.9173/0.8435)	mem 34602MB
[2025-01-19 14:44:43 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][100/312]	eta 0:02:40 lr 0.000989	time 0.7570 (0.7582)	model_time 0.7566 (0.7436)	loss 2.0564 (2.9660)	grad_norm 1.6004 (1.8212/0.7950)	mem 34604MB
[2025-01-19 14:44:49 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][140/312]	eta 0:02:10 lr 0.000986	time 0.8034 (0.7593)	model_time 0.8032 (0.7482)	loss 2.8381 (2.9477)	grad_norm 1.3454 (1.9263/0.8531)	mem 34602MB
[2025-01-19 14:44:50 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][110/312]	eta 0:02:32 lr 0.000988	time 0.8220 (0.7563)	model_time 0.8219 (0.7430)	loss 3.1088 (2.9719)	grad_norm 1.1719 (1.8220/0.7742)	mem 34604MB
[2025-01-19 14:44:57 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][150/312]	eta 0:02:02 lr 0.000986	time 0.7163 (0.7575)	model_time 0.7159 (0.7471)	loss 2.8170 (2.9533)	grad_norm 3.6674 (1.9294/0.8535)	mem 34602MB
[2025-01-19 14:44:58 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][120/312]	eta 0:02:25 lr 0.000987	time 0.7217 (0.7553)	model_time 0.7212 (0.7431)	loss 3.4529 (2.9728)	grad_norm 3.5294 (1.8445/0.8128)	mem 34604MB
[2025-01-19 14:45:04 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][160/312]	eta 0:01:54 lr 0.000985	time 0.7243 (0.7564)	model_time 0.7242 (0.7467)	loss 3.1555 (2.9569)	grad_norm 1.8396 (1.9702/0.8960)	mem 34602MB
[2025-01-19 14:45:06 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][130/312]	eta 0:02:17 lr 0.000987	time 0.8149 (0.7575)	model_time 0.8148 (0.7461)	loss 3.1606 (2.9544)	grad_norm 1.7353 (1.8847/0.8337)	mem 34604MB
[2025-01-19 14:45:11 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][170/312]	eta 0:01:47 lr 0.000985	time 0.7247 (0.7555)	model_time 0.7242 (0.7463)	loss 3.2771 (2.9506)	grad_norm 1.9648 (1.9735/0.8778)	mem 34602MB
[2025-01-19 14:45:13 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][140/312]	eta 0:02:10 lr 0.000986	time 0.8050 (0.7584)	model_time 0.8048 (0.7478)	loss 2.8818 (2.9345)	grad_norm 2.3597 (1.8903/0.8360)	mem 34604MB
[2025-01-19 14:45:19 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][180/312]	eta 0:01:39 lr 0.000984	time 0.8157 (0.7553)	model_time 0.8156 (0.7466)	loss 3.2463 (2.9479)	grad_norm 3.9629 (1.9926/0.8806)	mem 34602MB
[2025-01-19 14:45:21 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][150/312]	eta 0:02:02 lr 0.000986	time 0.8000 (0.7589)	model_time 0.7995 (0.7490)	loss 3.1987 (2.9479)	grad_norm 3.2962 (1.8926/0.8272)	mem 34604MB
[2025-01-19 14:45:26 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][190/312]	eta 0:01:31 lr 0.000984	time 0.7378 (0.7538)	model_time 0.7374 (0.7456)	loss 3.4115 (2.9558)	grad_norm 1.3902 (1.9983/0.8793)	mem 34602MB
[2025-01-19 14:45:28 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][160/312]	eta 0:01:55 lr 0.000985	time 0.7178 (0.7582)	model_time 0.7173 (0.7489)	loss 2.4283 (2.9325)	grad_norm 1.5421 (1.8964/0.8172)	mem 34604MB
[2025-01-19 14:45:34 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][200/312]	eta 0:01:24 lr 0.000983	time 0.7233 (0.7532)	model_time 0.7228 (0.7453)	loss 3.5232 (2.9654)	grad_norm 2.5984 (2.0081/0.8728)	mem 34602MB
[2025-01-19 14:45:36 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][170/312]	eta 0:01:47 lr 0.000985	time 0.7216 (0.7570)	model_time 0.7213 (0.7482)	loss 2.8293 (2.9401)	grad_norm 1.5654 (1.8874/0.7999)	mem 34604MB
[2025-01-19 14:45:41 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][210/312]	eta 0:01:16 lr 0.000982	time 0.7168 (0.7529)	model_time 0.7167 (0.7454)	loss 3.4659 (2.9630)	grad_norm 2.2421 (2.0025/0.8613)	mem 34602MB
[2025-01-19 14:45:43 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][180/312]	eta 0:01:39 lr 0.000984	time 0.7198 (0.7554)	model_time 0.7196 (0.7470)	loss 2.3529 (2.9380)	grad_norm 1.0401 (1.8689/0.7871)	mem 34604MB
[2025-01-19 14:45:49 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][220/312]	eta 0:01:09 lr 0.000982	time 0.7168 (0.7530)	model_time 0.7164 (0.7458)	loss 3.1467 (2.9630)	grad_norm 0.8274 (1.9843/0.8568)	mem 34602MB
[2025-01-19 14:45:50 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][190/312]	eta 0:01:31 lr 0.000984	time 0.7260 (0.7539)	model_time 0.7258 (0.7460)	loss 2.2827 (2.9363)	grad_norm 1.8614 (1.8460/0.7765)	mem 34604MB
[2025-01-19 14:45:56 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][230/312]	eta 0:01:01 lr 0.000981	time 0.7320 (0.7534)	model_time 0.7315 (0.7465)	loss 3.5141 (2.9604)	grad_norm 3.7276 (1.9694/0.8561)	mem 34602MB
[2025-01-19 14:45:58 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][200/312]	eta 0:01:24 lr 0.000983	time 0.7464 (0.7527)	model_time 0.7460 (0.7451)	loss 3.2150 (2.9430)	grad_norm 1.8685 (1.8596/0.7865)	mem 34604MB
[2025-01-19 14:46:04 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][240/312]	eta 0:00:54 lr 0.000981	time 0.7430 (0.7531)	model_time 0.7428 (0.7464)	loss 2.7692 (2.9658)	grad_norm 0.9052 (1.9568/0.8567)	mem 34602MB
[2025-01-19 14:46:05 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][210/312]	eta 0:01:16 lr 0.000982	time 0.7266 (0.7515)	model_time 0.7265 (0.7443)	loss 2.9864 (2.9396)	grad_norm 1.2309 (1.8603/0.7824)	mem 34604MB
[2025-01-19 14:46:11 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][250/312]	eta 0:00:46 lr 0.000980	time 0.7488 (0.7527)	model_time 0.7487 (0.7464)	loss 3.5427 (2.9692)	grad_norm 2.2905 (1.9781/0.8662)	mem 34602MB
[2025-01-19 14:46:12 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][220/312]	eta 0:01:09 lr 0.000982	time 0.7282 (0.7506)	model_time 0.7277 (0.7437)	loss 3.1788 (2.9259)	grad_norm 5.5898 (1.8971/0.8509)	mem 34604MB
[2025-01-19 14:46:19 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][260/312]	eta 0:00:39 lr 0.000980	time 0.8122 (0.7535)	model_time 0.8121 (0.7473)	loss 3.0096 (2.9703)	grad_norm 1.2666 (1.9708/0.8593)	mem 34602MB
[2025-01-19 14:46:20 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][230/312]	eta 0:01:01 lr 0.000981	time 0.7218 (0.7497)	model_time 0.7213 (0.7430)	loss 3.1741 (2.9258)	grad_norm 2.6594 (1.9651/0.9801)	mem 34604MB
[2025-01-19 14:46:26 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][270/312]	eta 0:00:31 lr 0.000979	time 0.7290 (0.7529)	model_time 0.7286 (0.7470)	loss 3.1410 (2.9652)	grad_norm 1.2515 (1.9488/0.8525)	mem 34602MB
[2025-01-19 14:46:27 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][240/312]	eta 0:00:53 lr 0.000981	time 0.7233 (0.7498)	model_time 0.7231 (0.7434)	loss 3.1640 (2.9306)	grad_norm 1.1726 (1.9587/0.9661)	mem 34604MB
[2025-01-19 14:46:34 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][280/312]	eta 0:00:24 lr 0.000978	time 0.7168 (0.7525)	model_time 0.7164 (0.7467)	loss 3.4841 (2.9651)	grad_norm 2.3282 (1.9494/0.8486)	mem 34602MB
[2025-01-19 14:46:35 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][250/312]	eta 0:00:46 lr 0.000980	time 0.7192 (0.7503)	model_time 0.7191 (0.7442)	loss 3.2847 (2.9323)	grad_norm 1.8818 (1.9399/0.9544)	mem 34604MB
[2025-01-19 14:46:41 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][290/312]	eta 0:00:16 lr 0.000978	time 0.7180 (0.7522)	model_time 0.7178 (0.7466)	loss 3.5059 (2.9642)	grad_norm 1.9623 (1.9416/0.8386)	mem 34602MB
[2025-01-19 14:46:42 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][260/312]	eta 0:00:39 lr 0.000980	time 0.8138 (0.7510)	model_time 0.8137 (0.7450)	loss 2.6596 (2.9365)	grad_norm 0.8120 (1.9185/0.9450)	mem 34604MB
[2025-01-19 14:46:49 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][300/312]	eta 0:00:09 lr 0.000977	time 0.7192 (0.7519)	model_time 0.7191 (0.7465)	loss 3.5576 (2.9703)	grad_norm 1.0420 (1.9329/0.8311)	mem 34602MB
[2025-01-19 14:46:50 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][270/312]	eta 0:00:31 lr 0.000979	time 0.8045 (0.7522)	model_time 0.8040 (0.7465)	loss 3.1632 (2.9291)	grad_norm 0.9705 (1.9254/0.9514)	mem 34604MB
[2025-01-19 14:46:56 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][310/312]	eta 0:00:01 lr 0.000977	time 0.7153 (0.7510)	model_time 0.7152 (0.7458)	loss 2.9741 (2.9761)	grad_norm 1.9556 (1.9228/0.8178)	mem 34602MB
[2025-01-19 14:46:57 internimage_b_1k_224] (main.py 519): INFO EPOCH 202 training takes 0:03:54
[2025-01-19 14:46:57 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_202.pth saving......
[2025-01-19 14:46:58 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][280/312]	eta 0:00:24 lr 0.000978	time 0.7156 (0.7521)	model_time 0.7151 (0.7466)	loss 3.2274 (2.9337)	grad_norm 2.8416 (1.9263/0.9456)	mem 34604MB
[2025-01-19 14:47:00 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_202.pth saved !!!
[2025-01-19 14:47:05 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][290/312]	eta 0:00:16 lr 0.000978	time 0.7204 (0.7517)	model_time 0.7200 (0.7463)	loss 3.0173 (2.9391)	grad_norm 2.1452 (1.9288/0.9434)	mem 34604MB
[2025-01-19 14:47:07 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.324 (7.324)	Loss 0.7489 (0.7489)	Acc@1 84.741 (84.741)	Acc@5 97.510 (97.510)	Mem 34602MB
[2025-01-19 14:47:11 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.967)	Loss 0.9874 (0.8604)	Acc@1 79.272 (82.839)	Acc@5 95.288 (96.442)	Mem 34602MB
[2025-01-19 14:47:11 internimage_b_1k_224] (main.py 575): INFO [Epoch:202] * Acc@1 82.654 Acc@5 96.457
[2025-01-19 14:47:11 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.7%
[2025-01-19 14:47:11 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 14:47:12 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][300/312]	eta 0:00:09 lr 0.000977	time 0.7162 (0.7509)	model_time 0.7161 (0.7457)	loss 2.1626 (2.9327)	grad_norm 1.3208 (1.9192/0.9397)	mem 34604MB
[2025-01-19 14:47:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 14:47:14 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.65%
[2025-01-19 14:47:20 internimage_b_1k_224] (main.py 510): INFO Train: [202/300][310/312]	eta 0:00:01 lr 0.000977	time 0.7144 (0.7501)	model_time 0.7143 (0.7450)	loss 2.8944 (2.9274)	grad_norm 1.2663 (1.9304/0.9502)	mem 34604MB
[2025-01-19 14:47:20 internimage_b_1k_224] (main.py 519): INFO EPOCH 202 training takes 0:03:53
[2025-01-19 14:47:20 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_202.pth saving......
[2025-01-19 14:47:22 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.421 (8.421)	Loss 0.7012 (0.7012)	Acc@1 85.400 (85.400)	Acc@5 97.974 (97.974)	Mem 34602MB
[2025-01-19 14:47:24 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_202.pth saved !!!
[2025-01-19 14:47:28 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.272)	Loss 0.9462 (0.8094)	Acc@1 79.077 (83.110)	Acc@5 95.435 (96.604)	Mem 34602MB
[2025-01-19 14:47:28 internimage_b_1k_224] (main.py 575): INFO [Epoch:202] * Acc@1 82.973 Acc@5 96.649
[2025-01-19 14:47:28 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.0%
[2025-01-19 14:47:28 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:47:32 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:47:32 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.97%
[2025-01-19 14:47:33 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.751 (9.751)	Loss 0.7487 (0.7487)	Acc@1 84.521 (84.521)	Acc@5 97.534 (97.534)	Mem 34604MB
[2025-01-19 14:47:34 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][0/312]	eta 0:11:01 lr 0.000977	time 2.1200 (2.1200)	model_time 0.7481 (0.7481)	loss 3.2297 (3.2297)	grad_norm 1.4077 (1.4077/0.0000)	mem 34602MB
[2025-01-19 14:47:37 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.237)	Loss 0.9949 (0.8452)	Acc@1 78.735 (82.579)	Acc@5 95.068 (96.329)	Mem 34604MB
[2025-01-19 14:47:37 internimage_b_1k_224] (main.py 575): INFO [Epoch:202] * Acc@1 82.416 Acc@5 96.335
[2025-01-19 14:47:37 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.4%
[2025-01-19 14:47:37 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.62%
[2025-01-19 14:47:42 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][10/312]	eta 0:04:25 lr 0.000976	time 0.7194 (0.8796)	model_time 0.7193 (0.7546)	loss 2.3696 (3.0750)	grad_norm 0.8495 (1.2962/0.3453)	mem 34602MB
[2025-01-19 14:47:47 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.647 (9.647)	Loss 0.6951 (0.6951)	Acc@1 85.449 (85.449)	Acc@5 98.047 (98.047)	Mem 34604MB
[2025-01-19 14:47:49 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][20/312]	eta 0:03:57 lr 0.000975	time 0.7235 (0.8130)	model_time 0.7234 (0.7473)	loss 2.0438 (2.9364)	grad_norm 1.4579 (1.5565/0.6472)	mem 34602MB
[2025-01-19 14:47:52 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.285)	Loss 0.9446 (0.8075)	Acc@1 79.297 (83.114)	Acc@5 95.264 (96.542)	Mem 34604MB
[2025-01-19 14:47:52 internimage_b_1k_224] (main.py 575): INFO [Epoch:202] * Acc@1 82.919 Acc@5 96.591
[2025-01-19 14:47:52 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.9%
[2025-01-19 14:47:52 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:47:56 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:47:56 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.92%
[2025-01-19 14:47:57 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][30/312]	eta 0:03:44 lr 0.000975	time 0.7197 (0.7965)	model_time 0.7195 (0.7506)	loss 2.2572 (2.9406)	grad_norm 2.6190 (1.6774/0.6544)	mem 34602MB
[2025-01-19 14:47:58 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][0/312]	eta 0:10:17 lr 0.000977	time 1.9807 (1.9807)	model_time 0.7404 (0.7404)	loss 2.8074 (2.8074)	grad_norm 1.8516 (1.8516/0.0000)	mem 34604MB
[2025-01-19 14:48:04 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][40/312]	eta 0:03:33 lr 0.000974	time 0.7186 (0.7853)	model_time 0.7184 (0.7506)	loss 2.9562 (2.9975)	grad_norm 4.5166 (1.8897/0.8585)	mem 34602MB
[2025-01-19 14:48:05 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][10/312]	eta 0:04:14 lr 0.000976	time 0.7533 (0.8434)	model_time 0.7532 (0.7303)	loss 2.5469 (2.9750)	grad_norm 1.3398 (1.5871/0.4650)	mem 34604MB
[2025-01-19 14:48:12 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][50/312]	eta 0:03:23 lr 0.000974	time 0.7202 (0.7771)	model_time 0.7198 (0.7490)	loss 2.5294 (2.9739)	grad_norm 3.0334 (1.9562/0.8512)	mem 34602MB
[2025-01-19 14:48:12 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][20/312]	eta 0:03:51 lr 0.000975	time 0.7361 (0.7914)	model_time 0.7360 (0.7320)	loss 2.9411 (2.8768)	grad_norm 1.0616 (1.6059/0.4812)	mem 34604MB
[2025-01-19 14:48:19 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][60/312]	eta 0:03:14 lr 0.000973	time 0.7877 (0.7728)	model_time 0.7875 (0.7493)	loss 1.7901 (2.9859)	grad_norm 3.2750 (1.9965/0.8821)	mem 34602MB
[2025-01-19 14:48:20 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][30/312]	eta 0:03:38 lr 0.000975	time 0.7196 (0.7734)	model_time 0.7194 (0.7330)	loss 1.8139 (2.8814)	grad_norm 1.1715 (1.4671/0.4656)	mem 34604MB
[2025-01-19 14:48:27 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][70/312]	eta 0:03:06 lr 0.000973	time 0.7170 (0.7708)	model_time 0.7166 (0.7505)	loss 2.6303 (2.9623)	grad_norm 1.3355 (2.0057/0.8768)	mem 34602MB
[2025-01-19 14:48:27 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][40/312]	eta 0:03:27 lr 0.000974	time 0.7252 (0.7619)	model_time 0.7247 (0.7313)	loss 2.6613 (2.8665)	grad_norm 2.4733 (1.5208/0.4531)	mem 34604MB
[2025-01-19 14:48:34 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][80/312]	eta 0:02:57 lr 0.000972	time 0.7285 (0.7671)	model_time 0.7281 (0.7492)	loss 3.0893 (2.9623)	grad_norm 1.7577 (1.9842/0.8523)	mem 34602MB
[2025-01-19 14:48:35 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][50/312]	eta 0:03:18 lr 0.000974	time 0.7181 (0.7592)	model_time 0.7176 (0.7345)	loss 3.2043 (2.9005)	grad_norm 1.6650 (1.6259/0.5862)	mem 34604MB
[2025-01-19 14:48:42 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][90/312]	eta 0:02:49 lr 0.000972	time 0.8363 (0.7647)	model_time 0.8362 (0.7488)	loss 2.0340 (2.9649)	grad_norm 1.7872 (1.9710/0.8481)	mem 34602MB
[2025-01-19 14:48:42 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][60/312]	eta 0:03:12 lr 0.000973	time 0.7228 (0.7636)	model_time 0.7223 (0.7429)	loss 3.0183 (2.9133)	grad_norm 2.7011 (1.6698/0.5831)	mem 34604MB
[2025-01-19 14:48:49 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][100/312]	eta 0:02:41 lr 0.000971	time 0.8255 (0.7619)	model_time 0.8254 (0.7476)	loss 2.0881 (2.9513)	grad_norm 2.8744 (1.9949/0.8478)	mem 34602MB
[2025-01-19 14:48:50 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][70/312]	eta 0:03:05 lr 0.000973	time 0.7145 (0.7675)	model_time 0.7143 (0.7496)	loss 2.3652 (2.9033)	grad_norm 0.8519 (1.6155/0.5644)	mem 34604MB
[2025-01-19 14:48:56 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][110/312]	eta 0:02:33 lr 0.000970	time 0.7250 (0.7602)	model_time 0.7246 (0.7471)	loss 3.4289 (2.9615)	grad_norm 0.9616 (1.9318/0.8413)	mem 34602MB
[2025-01-19 14:48:58 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][80/312]	eta 0:02:58 lr 0.000972	time 0.7115 (0.7682)	model_time 0.7114 (0.7525)	loss 3.5460 (2.9203)	grad_norm 3.1888 (1.6761/0.5975)	mem 34604MB
[2025-01-19 14:49:04 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][120/312]	eta 0:02:25 lr 0.000970	time 0.7314 (0.7584)	model_time 0.7313 (0.7463)	loss 3.0546 (2.9714)	grad_norm 1.7898 (1.9541/0.8358)	mem 34602MB
[2025-01-19 14:49:06 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][90/312]	eta 0:02:50 lr 0.000972	time 0.7168 (0.7658)	model_time 0.7167 (0.7518)	loss 2.8834 (2.9327)	grad_norm 5.4727 (1.7961/0.7865)	mem 34604MB
[2025-01-19 14:49:11 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][130/312]	eta 0:02:17 lr 0.000969	time 0.7170 (0.7575)	model_time 0.7165 (0.7463)	loss 3.1652 (2.9632)	grad_norm 1.7953 (1.9397/0.8142)	mem 34602MB
[2025-01-19 14:49:13 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][100/312]	eta 0:02:41 lr 0.000971	time 0.7251 (0.7623)	model_time 0.7246 (0.7497)	loss 2.3584 (2.9234)	grad_norm 2.4562 (1.8329/0.7778)	mem 34604MB
[2025-01-19 14:49:19 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][140/312]	eta 0:02:10 lr 0.000969	time 0.7176 (0.7559)	model_time 0.7171 (0.7455)	loss 3.5216 (2.9643)	grad_norm 2.3259 (1.9614/0.8272)	mem 34602MB
[2025-01-19 14:49:20 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][110/312]	eta 0:02:33 lr 0.000970	time 0.7138 (0.7592)	model_time 0.7137 (0.7476)	loss 2.4513 (2.9196)	grad_norm 1.3516 (1.8077/0.7602)	mem 34604MB
[2025-01-19 14:49:26 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][150/312]	eta 0:02:02 lr 0.000968	time 0.7220 (0.7560)	model_time 0.7218 (0.7462)	loss 3.3437 (2.9469)	grad_norm 2.3743 (1.9680/0.8241)	mem 34602MB
[2025-01-19 14:49:27 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][120/312]	eta 0:02:25 lr 0.000970	time 0.7371 (0.7569)	model_time 0.7369 (0.7463)	loss 2.2432 (2.9192)	grad_norm 1.5887 (1.7963/0.7461)	mem 34604MB
[2025-01-19 14:49:34 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][160/312]	eta 0:01:54 lr 0.000968	time 0.7184 (0.7559)	model_time 0.7182 (0.7467)	loss 3.4560 (2.9450)	grad_norm 1.3366 (1.9369/0.8145)	mem 34602MB
[2025-01-19 14:49:35 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][130/312]	eta 0:02:17 lr 0.000969	time 0.7166 (0.7554)	model_time 0.7164 (0.7455)	loss 2.5396 (2.8947)	grad_norm 1.8776 (1.8294/0.7801)	mem 34604MB
[2025-01-19 14:49:41 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][170/312]	eta 0:01:47 lr 0.000967	time 0.7240 (0.7550)	model_time 0.7235 (0.7464)	loss 3.2034 (2.9561)	grad_norm 1.6736 (1.9255/0.7965)	mem 34602MB
[2025-01-19 14:49:42 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][140/312]	eta 0:02:09 lr 0.000969	time 0.7275 (0.7536)	model_time 0.7274 (0.7445)	loss 3.0747 (2.8992)	grad_norm 1.6759 (1.8880/0.8581)	mem 34604MB
[2025-01-19 14:49:49 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][180/312]	eta 0:01:39 lr 0.000966	time 0.8095 (0.7548)	model_time 0.8093 (0.7466)	loss 2.1229 (2.9503)	grad_norm 2.5561 (1.9006/0.7904)	mem 34602MB
[2025-01-19 14:49:49 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][150/312]	eta 0:02:01 lr 0.000968	time 0.7389 (0.7524)	model_time 0.7387 (0.7438)	loss 3.3614 (2.9123)	grad_norm 2.0596 (1.8832/0.8361)	mem 34604MB
[2025-01-19 14:49:56 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][190/312]	eta 0:01:32 lr 0.000966	time 0.7170 (0.7545)	model_time 0.7165 (0.7467)	loss 2.6702 (2.9486)	grad_norm 1.7015 (1.8893/0.7775)	mem 34602MB
[2025-01-19 14:49:57 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][160/312]	eta 0:01:54 lr 0.000968	time 0.7250 (0.7516)	model_time 0.7245 (0.7435)	loss 2.2073 (2.9171)	grad_norm 5.0432 (1.9747/0.9678)	mem 34604MB
[2025-01-19 14:50:04 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][200/312]	eta 0:01:24 lr 0.000965	time 0.7164 (0.7539)	model_time 0.7159 (0.7465)	loss 3.2079 (2.9483)	grad_norm 1.5198 (1.8939/0.7730)	mem 34602MB
[2025-01-19 14:50:04 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][170/312]	eta 0:01:46 lr 0.000967	time 0.7145 (0.7513)	model_time 0.7141 (0.7437)	loss 3.1346 (2.9388)	grad_norm 1.8676 (1.9889/0.9744)	mem 34604MB
[2025-01-19 14:50:11 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][210/312]	eta 0:01:16 lr 0.000965	time 0.7663 (0.7534)	model_time 0.7659 (0.7464)	loss 2.8053 (2.9537)	grad_norm 1.7494 (1.8744/0.7715)	mem 34602MB
[2025-01-19 14:50:12 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][180/312]	eta 0:01:39 lr 0.000966	time 0.7199 (0.7525)	model_time 0.7197 (0.7453)	loss 3.6958 (2.9477)	grad_norm 1.5539 (1.9698/0.9598)	mem 34604MB
[2025-01-19 14:50:18 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][220/312]	eta 0:01:09 lr 0.000964	time 0.8790 (0.7530)	model_time 0.8789 (0.7463)	loss 2.9529 (2.9465)	grad_norm 2.9358 (1.9035/0.7726)	mem 34602MB
[2025-01-19 14:50:20 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][190/312]	eta 0:01:31 lr 0.000966	time 0.7946 (0.7530)	model_time 0.7942 (0.7459)	loss 3.1407 (2.9408)	grad_norm 1.3632 (1.9410/0.9458)	mem 34604MB
[2025-01-19 14:50:26 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][230/312]	eta 0:01:01 lr 0.000964	time 0.7451 (0.7528)	model_time 0.7446 (0.7463)	loss 3.2036 (2.9452)	grad_norm 2.0563 (1.9178/0.7778)	mem 34602MB
[2025-01-19 14:50:27 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][200/312]	eta 0:01:24 lr 0.000965	time 0.7138 (0.7543)	model_time 0.7136 (0.7475)	loss 2.7496 (2.9368)	grad_norm 3.5978 (1.9502/0.9376)	mem 34604MB
[2025-01-19 14:50:33 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][240/312]	eta 0:00:54 lr 0.000963	time 0.7236 (0.7519)	model_time 0.7232 (0.7457)	loss 2.2945 (2.9506)	grad_norm 1.1396 (1.9131/0.7687)	mem 34602MB
[2025-01-19 14:50:35 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][210/312]	eta 0:01:16 lr 0.000965	time 0.8070 (0.7540)	model_time 0.8069 (0.7476)	loss 2.6466 (2.9416)	grad_norm 2.0884 (1.9464/0.9190)	mem 34604MB
[2025-01-19 14:50:41 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][250/312]	eta 0:00:46 lr 0.000963	time 0.7203 (0.7518)	model_time 0.7201 (0.7458)	loss 2.7803 (2.9489)	grad_norm 3.5915 (1.9252/0.7846)	mem 34602MB
[2025-01-19 14:50:42 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][220/312]	eta 0:01:09 lr 0.000964	time 0.7165 (0.7529)	model_time 0.7164 (0.7467)	loss 2.3615 (2.9312)	grad_norm 1.1870 (1.9185/0.9121)	mem 34604MB
[2025-01-19 14:50:48 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][260/312]	eta 0:00:39 lr 0.000962	time 0.7272 (0.7511)	model_time 0.7270 (0.7453)	loss 1.9916 (2.9429)	grad_norm 1.6829 (1.9105/0.7775)	mem 34602MB
[2025-01-19 14:50:50 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][230/312]	eta 0:01:01 lr 0.000964	time 0.7350 (0.7521)	model_time 0.7346 (0.7462)	loss 2.8958 (2.9321)	grad_norm 3.7156 (1.9218/0.9198)	mem 34604MB
[2025-01-19 14:50:56 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][270/312]	eta 0:00:31 lr 0.000961	time 0.7156 (0.7512)	model_time 0.7151 (0.7456)	loss 2.4983 (2.9375)	grad_norm 2.0070 (1.9112/0.7756)	mem 34602MB
[2025-01-19 14:50:57 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][240/312]	eta 0:00:54 lr 0.000963	time 0.7637 (0.7512)	model_time 0.7636 (0.7455)	loss 2.7204 (2.9197)	grad_norm 1.2106 (1.8989/0.9096)	mem 34604MB
[2025-01-19 14:51:03 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][280/312]	eta 0:00:24 lr 0.000961	time 0.7170 (0.7515)	model_time 0.7169 (0.7461)	loss 3.2942 (2.9391)	grad_norm 2.8052 (1.8981/0.7756)	mem 34602MB
[2025-01-19 14:51:04 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][250/312]	eta 0:00:46 lr 0.000963	time 0.7160 (0.7503)	model_time 0.7159 (0.7448)	loss 3.0218 (2.9235)	grad_norm 1.9703 (1.9161/0.9343)	mem 34604MB
[2025-01-19 14:51:11 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][290/312]	eta 0:00:16 lr 0.000960	time 0.7322 (0.7511)	model_time 0.7321 (0.7459)	loss 2.9166 (2.9316)	grad_norm 1.5888 (1.9031/0.7700)	mem 34602MB
[2025-01-19 14:51:11 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][260/312]	eta 0:00:38 lr 0.000962	time 0.7322 (0.7494)	model_time 0.7320 (0.7441)	loss 2.6687 (2.9273)	grad_norm 3.7716 (1.9478/0.9379)	mem 34604MB
[2025-01-19 14:51:18 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][300/312]	eta 0:00:09 lr 0.000960	time 0.8022 (0.7506)	model_time 0.8021 (0.7456)	loss 3.0436 (2.9342)	grad_norm 2.0306 (1.9073/0.7649)	mem 34602MB
[2025-01-19 14:51:19 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][270/312]	eta 0:00:31 lr 0.000961	time 0.7175 (0.7487)	model_time 0.7171 (0.7436)	loss 2.9702 (2.9222)	grad_norm 2.2551 (1.9476/0.9287)	mem 34604MB
[2025-01-19 14:51:25 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][310/312]	eta 0:00:01 lr 0.000959	time 0.7157 (0.7505)	model_time 0.7156 (0.7456)	loss 3.2657 (2.9349)	grad_norm 1.1479 (1.9191/0.7640)	mem 34602MB
[2025-01-19 14:51:26 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][280/312]	eta 0:00:23 lr 0.000961	time 0.7564 (0.7482)	model_time 0.7560 (0.7433)	loss 2.9718 (2.9179)	grad_norm 2.5745 (1.9443/0.9175)	mem 34604MB
[2025-01-19 14:51:26 internimage_b_1k_224] (main.py 519): INFO EPOCH 203 training takes 0:03:54
[2025-01-19 14:51:26 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_203.pth saving......
[2025-01-19 14:51:29 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_203.pth saved !!!
[2025-01-19 14:51:34 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][290/312]	eta 0:00:16 lr 0.000960	time 0.7158 (0.7480)	model_time 0.7156 (0.7432)	loss 3.3113 (2.9217)	grad_norm 1.6930 (1.9375/0.9148)	mem 34604MB
[2025-01-19 14:51:37 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.959 (7.959)	Loss 0.7326 (0.7326)	Acc@1 85.156 (85.156)	Acc@5 97.681 (97.681)	Mem 34602MB
[2025-01-19 14:51:41 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.032)	Loss 0.9766 (0.8437)	Acc@1 78.394 (82.722)	Acc@5 95.288 (96.382)	Mem 34602MB
[2025-01-19 14:51:41 internimage_b_1k_224] (main.py 575): INFO [Epoch:203] * Acc@1 82.562 Acc@5 96.413
[2025-01-19 14:51:41 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.6%
[2025-01-19 14:51:41 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.65%
[2025-01-19 14:51:41 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][300/312]	eta 0:00:08 lr 0.000960	time 0.7179 (0.7489)	model_time 0.7178 (0.7443)	loss 3.1573 (2.9228)	grad_norm 1.0696 (1.9329/0.9129)	mem 34604MB
[2025-01-19 14:51:49 internimage_b_1k_224] (main.py 510): INFO Train: [203/300][310/312]	eta 0:00:01 lr 0.000959	time 0.7129 (0.7492)	model_time 0.7128 (0.7447)	loss 2.7099 (2.9212)	grad_norm 2.9376 (1.9458/0.9166)	mem 34604MB
[2025-01-19 14:51:50 internimage_b_1k_224] (main.py 519): INFO EPOCH 203 training takes 0:03:53
[2025-01-19 14:51:50 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_203.pth saving......
[2025-01-19 14:51:50 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.985 (8.985)	Loss 0.7020 (0.7020)	Acc@1 85.400 (85.400)	Acc@5 97.998 (97.998)	Mem 34602MB
[2025-01-19 14:51:53 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_203.pth saved !!!
[2025-01-19 14:51:59 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.636)	Loss 0.9459 (0.8097)	Acc@1 79.150 (83.139)	Acc@5 95.435 (96.606)	Mem 34602MB
[2025-01-19 14:51:59 internimage_b_1k_224] (main.py 575): INFO [Epoch:203] * Acc@1 83.013 Acc@5 96.653
[2025-01-19 14:51:59 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.0%
[2025-01-19 14:51:59 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:52:03 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:52:03 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.01%
[2025-01-19 14:52:04 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 10.485 (10.485)	Loss 0.7153 (0.7153)	Acc@1 85.107 (85.107)	Acc@5 97.510 (97.510)	Mem 34604MB
[2025-01-19 14:52:05 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][0/312]	eta 0:10:32 lr 0.000959	time 2.0257 (2.0257)	model_time 0.7468 (0.7468)	loss 2.5894 (2.5894)	grad_norm 1.9560 (1.9560/0.0000)	mem 34602MB
[2025-01-19 14:52:07 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.283)	Loss 0.9664 (0.8334)	Acc@1 78.979 (82.890)	Acc@5 95.483 (96.424)	Mem 34604MB
[2025-01-19 14:52:07 internimage_b_1k_224] (main.py 575): INFO [Epoch:203] * Acc@1 82.730 Acc@5 96.449
[2025-01-19 14:52:07 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.7%
[2025-01-19 14:52:08 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 14:52:11 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 14:52:11 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.73%
[2025-01-19 14:52:13 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][10/312]	eta 0:04:20 lr 0.000959	time 0.7357 (0.8627)	model_time 0.7355 (0.7462)	loss 3.5989 (2.9726)	grad_norm 1.9305 (1.9525/0.6741)	mem 34602MB
[2025-01-19 14:52:18 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.397 (7.397)	Loss 0.6958 (0.6958)	Acc@1 85.498 (85.498)	Acc@5 98.096 (98.096)	Mem 34604MB
[2025-01-19 14:52:20 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][20/312]	eta 0:03:55 lr 0.000958	time 0.8046 (0.8076)	model_time 0.8041 (0.7464)	loss 3.3991 (3.1054)	grad_norm 1.5029 (2.3633/0.9435)	mem 34602MB
[2025-01-19 14:52:21 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.955)	Loss 0.9445 (0.8078)	Acc@1 79.297 (83.137)	Acc@5 95.215 (96.560)	Mem 34604MB
[2025-01-19 14:52:21 internimage_b_1k_224] (main.py 575): INFO [Epoch:203] * Acc@1 82.937 Acc@5 96.615
[2025-01-19 14:52:21 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.9%
[2025-01-19 14:52:21 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:52:25 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:52:25 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.94%
[2025-01-19 14:52:27 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][0/312]	eta 0:10:16 lr 0.000959	time 1.9757 (1.9757)	model_time 0.7387 (0.7387)	loss 3.3820 (3.3820)	grad_norm 1.8955 (1.8955/0.0000)	mem 34604MB
[2025-01-19 14:52:27 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][30/312]	eta 0:03:41 lr 0.000957	time 0.7306 (0.7853)	model_time 0.7305 (0.7438)	loss 2.9873 (3.0681)	grad_norm 1.1513 (2.2683/0.8919)	mem 34602MB
[2025-01-19 14:52:35 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][40/312]	eta 0:03:31 lr 0.000957	time 0.7228 (0.7758)	model_time 0.7227 (0.7443)	loss 3.2475 (3.0131)	grad_norm 0.8357 (2.0094/0.9095)	mem 34602MB
[2025-01-19 14:52:35 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][10/312]	eta 0:04:34 lr 0.000959	time 0.7178 (0.9082)	model_time 0.7174 (0.7954)	loss 1.9146 (2.7717)	grad_norm 1.4390 (1.4788/0.2494)	mem 34604MB
[2025-01-19 14:52:42 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][50/312]	eta 0:03:21 lr 0.000956	time 0.7489 (0.7688)	model_time 0.7484 (0.7433)	loss 1.9362 (2.9867)	grad_norm 1.9798 (1.8775/0.8805)	mem 34602MB
[2025-01-19 14:52:43 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][20/312]	eta 0:04:05 lr 0.000958	time 0.8257 (0.8410)	model_time 0.8255 (0.7818)	loss 3.2259 (2.8319)	grad_norm 1.3651 (1.4674/0.3834)	mem 34604MB
[2025-01-19 14:52:50 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][60/312]	eta 0:03:12 lr 0.000956	time 0.8295 (0.7651)	model_time 0.8293 (0.7438)	loss 1.9776 (2.9679)	grad_norm 2.3298 (1.9562/0.9641)	mem 34602MB
[2025-01-19 14:52:50 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][30/312]	eta 0:03:46 lr 0.000957	time 0.7183 (0.8039)	model_time 0.7179 (0.7636)	loss 2.7430 (2.9079)	grad_norm 1.1854 (1.7813/0.7986)	mem 34604MB
[2025-01-19 14:52:57 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][70/312]	eta 0:03:04 lr 0.000955	time 0.7181 (0.7612)	model_time 0.7176 (0.7428)	loss 3.4011 (2.9844)	grad_norm 1.8475 (2.0939/1.0434)	mem 34602MB
[2025-01-19 14:52:57 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][40/312]	eta 0:03:34 lr 0.000957	time 0.7504 (0.7868)	model_time 0.7499 (0.7563)	loss 3.0149 (2.9701)	grad_norm 2.2875 (1.8710/0.8187)	mem 34604MB
[2025-01-19 14:53:05 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][80/312]	eta 0:02:56 lr 0.000955	time 0.7313 (0.7590)	model_time 0.7309 (0.7429)	loss 3.7036 (2.9817)	grad_norm 1.3496 (2.0567/1.0134)	mem 34602MB
[2025-01-19 14:53:05 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][50/312]	eta 0:03:23 lr 0.000956	time 0.7473 (0.7766)	model_time 0.7472 (0.7519)	loss 3.2430 (2.9933)	grad_norm 1.8426 (1.8723/0.8052)	mem 34604MB
[2025-01-19 14:53:12 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][60/312]	eta 0:03:13 lr 0.000956	time 0.7211 (0.7689)	model_time 0.7210 (0.7482)	loss 3.5958 (2.9533)	grad_norm 1.3416 (1.8718/0.8037)	mem 34604MB
[2025-01-19 14:53:12 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][90/312]	eta 0:02:48 lr 0.000954	time 0.7179 (0.7600)	model_time 0.7177 (0.7456)	loss 3.4652 (2.9986)	grad_norm 1.5551 (2.0536/0.9852)	mem 34602MB
[2025-01-19 14:53:19 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][70/312]	eta 0:03:04 lr 0.000955	time 0.7476 (0.7633)	model_time 0.7475 (0.7455)	loss 2.9151 (2.9883)	grad_norm 1.3569 (1.8888/0.8006)	mem 34604MB
[2025-01-19 14:53:20 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][100/312]	eta 0:02:40 lr 0.000953	time 0.8087 (0.7594)	model_time 0.8083 (0.7464)	loss 3.2111 (2.9792)	grad_norm 1.3307 (2.0099/0.9545)	mem 34602MB
[2025-01-19 14:53:27 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][80/312]	eta 0:02:55 lr 0.000955	time 0.7417 (0.7586)	model_time 0.7415 (0.7429)	loss 2.1255 (3.0117)	grad_norm 1.4499 (1.8898/0.8054)	mem 34604MB
[2025-01-19 14:53:27 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][110/312]	eta 0:02:32 lr 0.000953	time 0.7532 (0.7573)	model_time 0.7530 (0.7454)	loss 3.1368 (2.9879)	grad_norm 2.2568 (1.9940/0.9245)	mem 34602MB
[2025-01-19 14:53:34 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][90/312]	eta 0:02:47 lr 0.000954	time 0.7497 (0.7557)	model_time 0.7493 (0.7417)	loss 2.6991 (2.9977)	grad_norm 1.6108 (1.8652/0.7797)	mem 34604MB
[2025-01-19 14:53:35 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][120/312]	eta 0:02:25 lr 0.000952	time 0.7246 (0.7570)	model_time 0.7244 (0.7461)	loss 2.7574 (2.9831)	grad_norm 1.8869 (2.0076/0.9251)	mem 34602MB
[2025-01-19 14:53:42 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][100/312]	eta 0:02:40 lr 0.000953	time 0.7186 (0.7561)	model_time 0.7184 (0.7435)	loss 1.8713 (2.9632)	grad_norm 3.0655 (1.8313/0.7740)	mem 34604MB
[2025-01-19 14:53:42 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][130/312]	eta 0:02:17 lr 0.000952	time 0.7146 (0.7563)	model_time 0.7144 (0.7461)	loss 1.9157 (2.9735)	grad_norm 1.5725 (2.0471/0.9628)	mem 34602MB
[2025-01-19 14:53:50 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][110/312]	eta 0:02:33 lr 0.000953	time 0.8094 (0.7601)	model_time 0.8090 (0.7486)	loss 3.1060 (2.9517)	grad_norm 3.0328 (1.8739/0.8142)	mem 34604MB
[2025-01-19 14:53:50 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][140/312]	eta 0:02:09 lr 0.000951	time 0.7203 (0.7552)	model_time 0.7202 (0.7457)	loss 3.1996 (2.9870)	grad_norm 3.3160 (2.0389/0.9607)	mem 34602MB
[2025-01-19 14:53:57 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][120/312]	eta 0:02:25 lr 0.000952	time 0.8086 (0.7585)	model_time 0.8085 (0.7480)	loss 2.8535 (2.9492)	grad_norm 3.2273 (1.8826/0.8095)	mem 34604MB
[2025-01-19 14:53:57 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][150/312]	eta 0:02:02 lr 0.000951	time 0.7426 (0.7546)	model_time 0.7422 (0.7457)	loss 1.9609 (2.9843)	grad_norm 1.5202 (1.9955/0.9446)	mem 34602MB
[2025-01-19 14:54:05 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][160/312]	eta 0:01:54 lr 0.000950	time 0.7235 (0.7539)	model_time 0.7233 (0.7456)	loss 2.9192 (2.9767)	grad_norm 1.9944 (2.0158/0.9289)	mem 34602MB
[2025-01-19 14:54:05 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][130/312]	eta 0:02:18 lr 0.000952	time 0.7087 (0.7617)	model_time 0.7085 (0.7519)	loss 3.3871 (2.9445)	grad_norm 2.1639 (1.8886/0.7908)	mem 34604MB
[2025-01-19 14:54:12 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][170/312]	eta 0:01:46 lr 0.000950	time 0.7172 (0.7530)	model_time 0.7167 (0.7451)	loss 1.8565 (2.9806)	grad_norm 2.4285 (2.0311/0.9227)	mem 34602MB
[2025-01-19 14:54:13 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][140/312]	eta 0:02:11 lr 0.000951	time 0.9918 (0.7636)	model_time 0.9914 (0.7544)	loss 2.5689 (2.9608)	grad_norm 1.1178 (1.8651/0.7764)	mem 34604MB
[2025-01-19 14:54:20 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][180/312]	eta 0:01:39 lr 0.000949	time 0.9994 (0.7535)	model_time 0.9992 (0.7460)	loss 3.0638 (2.9709)	grad_norm 1.3193 (2.0502/0.9433)	mem 34602MB
[2025-01-19 14:54:20 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][150/312]	eta 0:02:03 lr 0.000951	time 0.7160 (0.7615)	model_time 0.7158 (0.7530)	loss 2.8657 (2.9628)	grad_norm 2.4643 (1.9031/0.7938)	mem 34604MB
[2025-01-19 14:54:27 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][190/312]	eta 0:01:31 lr 0.000948	time 0.7169 (0.7523)	model_time 0.7165 (0.7452)	loss 3.0131 (2.9723)	grad_norm 2.2378 (2.0429/0.9308)	mem 34602MB
[2025-01-19 14:54:27 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][160/312]	eta 0:01:55 lr 0.000950	time 0.7272 (0.7594)	model_time 0.7271 (0.7514)	loss 3.1023 (2.9649)	grad_norm 1.4847 (1.9270/0.8052)	mem 34604MB
[2025-01-19 14:54:34 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][200/312]	eta 0:01:24 lr 0.000948	time 0.7239 (0.7514)	model_time 0.7234 (0.7447)	loss 3.6858 (2.9804)	grad_norm 2.1207 (2.0312/0.9205)	mem 34602MB
[2025-01-19 14:54:35 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][170/312]	eta 0:01:47 lr 0.000950	time 0.7452 (0.7576)	model_time 0.7450 (0.7500)	loss 3.2246 (2.9695)	grad_norm 1.5401 (1.9166/0.7872)	mem 34604MB
[2025-01-19 14:54:42 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][210/312]	eta 0:01:16 lr 0.000947	time 0.7187 (0.7521)	model_time 0.7185 (0.7457)	loss 2.1768 (2.9694)	grad_norm 1.9968 (2.0082/0.9064)	mem 34602MB
[2025-01-19 14:54:42 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][180/312]	eta 0:01:39 lr 0.000949	time 0.7256 (0.7561)	model_time 0.7255 (0.7490)	loss 2.6273 (2.9748)	grad_norm 1.6194 (1.8947/0.7761)	mem 34604MB
[2025-01-19 14:54:49 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][190/312]	eta 0:01:32 lr 0.000948	time 0.7227 (0.7546)	model_time 0.7222 (0.7477)	loss 2.9912 (2.9876)	grad_norm 2.5966 (1.8899/0.7677)	mem 34604MB
[2025-01-19 14:54:49 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][220/312]	eta 0:01:09 lr 0.000947	time 0.8147 (0.7527)	model_time 0.8143 (0.7466)	loss 2.4386 (2.9775)	grad_norm 1.6434 (2.0306/0.9421)	mem 34602MB
[2025-01-19 14:54:57 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][200/312]	eta 0:01:24 lr 0.000948	time 0.7316 (0.7530)	model_time 0.7315 (0.7465)	loss 3.3435 (2.9984)	grad_norm 1.4107 (1.8924/0.7614)	mem 34604MB
[2025-01-19 14:54:57 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][230/312]	eta 0:01:01 lr 0.000946	time 0.7168 (0.7522)	model_time 0.7167 (0.7462)	loss 3.3130 (2.9831)	grad_norm 1.7693 (1.9979/0.9366)	mem 34602MB
[2025-01-19 14:55:04 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][210/312]	eta 0:01:16 lr 0.000947	time 0.7319 (0.7516)	model_time 0.7314 (0.7454)	loss 2.8424 (2.9978)	grad_norm 1.6116 (1.8921/0.7543)	mem 34604MB
[2025-01-19 14:55:04 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][240/312]	eta 0:00:54 lr 0.000946	time 0.7282 (0.7522)	model_time 0.7278 (0.7465)	loss 3.0875 (2.9821)	grad_norm 2.6995 (2.0003/0.9257)	mem 34602MB
[2025-01-19 14:55:11 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][220/312]	eta 0:01:09 lr 0.000947	time 0.7165 (0.7509)	model_time 0.7161 (0.7450)	loss 2.2560 (2.9842)	grad_norm 2.2043 (1.9128/0.7617)	mem 34604MB
[2025-01-19 14:55:12 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][250/312]	eta 0:00:46 lr 0.000945	time 0.7181 (0.7515)	model_time 0.7180 (0.7460)	loss 2.9565 (2.9889)	grad_norm 2.8904 (2.0068/0.9172)	mem 34602MB
[2025-01-19 14:55:19 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][230/312]	eta 0:01:01 lr 0.000946	time 0.8242 (0.7526)	model_time 0.8240 (0.7469)	loss 3.2254 (2.9791)	grad_norm 1.7532 (1.9039/0.7556)	mem 34604MB
[2025-01-19 14:55:19 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][260/312]	eta 0:00:39 lr 0.000945	time 0.7180 (0.7514)	model_time 0.7179 (0.7461)	loss 2.8807 (2.9893)	grad_norm 2.1232 (2.0142/0.9172)	mem 34602MB
[2025-01-19 14:55:26 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][240/312]	eta 0:00:54 lr 0.000946	time 0.8048 (0.7522)	model_time 0.8044 (0.7467)	loss 2.7932 (2.9734)	grad_norm 1.4443 (1.9194/0.7583)	mem 34604MB
[2025-01-19 14:55:27 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][270/312]	eta 0:00:31 lr 0.000944	time 0.7232 (0.7519)	model_time 0.7231 (0.7468)	loss 3.4810 (2.9905)	grad_norm 1.2275 (2.0145/0.9063)	mem 34602MB
[2025-01-19 14:55:34 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][280/312]	eta 0:00:24 lr 0.000943	time 0.7244 (0.7517)	model_time 0.7239 (0.7467)	loss 2.8480 (2.9868)	grad_norm 1.1586 (1.9914/0.9009)	mem 34602MB
[2025-01-19 14:55:34 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][250/312]	eta 0:00:46 lr 0.000945	time 0.7084 (0.7540)	model_time 0.7082 (0.7487)	loss 2.2524 (2.9648)	grad_norm 1.9163 (1.9238/0.7534)	mem 34604MB
[2025-01-19 14:55:42 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][290/312]	eta 0:00:16 lr 0.000943	time 0.7179 (0.7510)	model_time 0.7175 (0.7463)	loss 2.6363 (2.9835)	grad_norm 0.9779 (1.9688/0.8954)	mem 34602MB
[2025-01-19 14:55:42 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][260/312]	eta 0:00:39 lr 0.000945	time 0.8026 (0.7540)	model_time 0.8021 (0.7489)	loss 3.1426 (2.9669)	grad_norm 1.3570 (1.9415/0.7805)	mem 34604MB
[2025-01-19 14:55:49 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][300/312]	eta 0:00:09 lr 0.000942	time 0.7947 (0.7510)	model_time 0.7946 (0.7464)	loss 2.6507 (2.9777)	grad_norm 1.0590 (1.9679/0.8893)	mem 34602MB
[2025-01-19 14:55:49 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][270/312]	eta 0:00:31 lr 0.000944	time 0.7210 (0.7537)	model_time 0.7206 (0.7488)	loss 3.0024 (2.9667)	grad_norm 1.2812 (1.9323/0.7814)	mem 34604MB
[2025-01-19 14:55:56 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][310/312]	eta 0:00:01 lr 0.000942	time 0.7160 (0.7502)	model_time 0.7159 (0.7457)	loss 3.6222 (2.9834)	grad_norm 1.4229 (1.9795/0.9046)	mem 34602MB
[2025-01-19 14:55:57 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][280/312]	eta 0:00:24 lr 0.000943	time 0.7241 (0.7527)	model_time 0.7237 (0.7479)	loss 3.5679 (2.9662)	grad_norm 2.2994 (1.9326/0.7782)	mem 34604MB
[2025-01-19 14:55:57 internimage_b_1k_224] (main.py 519): INFO EPOCH 204 training takes 0:03:54
[2025-01-19 14:55:57 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_204.pth saving......
[2025-01-19 14:56:00 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_204.pth saved !!!
[2025-01-19 14:56:04 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][290/312]	eta 0:00:16 lr 0.000943	time 0.7161 (0.7518)	model_time 0.7159 (0.7472)	loss 3.2276 (2.9626)	grad_norm 3.4164 (1.9482/0.7819)	mem 34604MB
[2025-01-19 14:56:11 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][300/312]	eta 0:00:09 lr 0.000942	time 0.7152 (0.7508)	model_time 0.7151 (0.7464)	loss 2.6486 (2.9536)	grad_norm 1.5955 (1.9551/0.7835)	mem 34604MB
[2025-01-19 14:56:11 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 11.106 (11.106)	Loss 0.7529 (0.7529)	Acc@1 85.278 (85.278)	Acc@5 97.583 (97.583)	Mem 34602MB
[2025-01-19 14:56:15 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.323)	Loss 0.9739 (0.8394)	Acc@1 78.369 (82.848)	Acc@5 95.142 (96.413)	Mem 34602MB
[2025-01-19 14:56:15 internimage_b_1k_224] (main.py 575): INFO [Epoch:204] * Acc@1 82.668 Acc@5 96.443
[2025-01-19 14:56:15 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.7%
[2025-01-19 14:56:15 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 14:56:18 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 14:56:18 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.67%
[2025-01-19 14:56:18 internimage_b_1k_224] (main.py 510): INFO Train: [204/300][310/312]	eta 0:00:01 lr 0.000942	time 0.7189 (0.7499)	model_time 0.7188 (0.7456)	loss 3.4496 (2.9582)	grad_norm 2.0404 (1.9727/0.7863)	mem 34604MB
[2025-01-19 14:56:19 internimage_b_1k_224] (main.py 519): INFO EPOCH 204 training takes 0:03:53
[2025-01-19 14:56:19 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_204.pth saving......
[2025-01-19 14:56:22 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_204.pth saved !!!
[2025-01-19 14:56:32 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 13.677 (13.677)	Loss 0.7031 (0.7031)	Acc@1 85.376 (85.376)	Acc@5 97.998 (97.998)	Mem 34602MB
[2025-01-19 14:56:38 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.254 (15.254)	Loss 0.7389 (0.7389)	Acc@1 84.985 (84.985)	Acc@5 97.607 (97.607)	Mem 34604MB
[2025-01-19 14:56:38 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.769)	Loss 0.9458 (0.8100)	Acc@1 79.321 (83.179)	Acc@5 95.435 (96.622)	Mem 34602MB
[2025-01-19 14:56:38 internimage_b_1k_224] (main.py 575): INFO [Epoch:204] * Acc@1 83.053 Acc@5 96.665
[2025-01-19 14:56:38 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.1%
[2025-01-19 14:56:38 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:56:42 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.733)	Loss 0.9776 (0.8332)	Acc@1 78.687 (82.704)	Acc@5 95.142 (96.371)	Mem 34604MB
[2025-01-19 14:56:42 internimage_b_1k_224] (main.py 575): INFO [Epoch:204] * Acc@1 82.592 Acc@5 96.413
[2025-01-19 14:56:42 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.6%
[2025-01-19 14:56:42 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.73%
[2025-01-19 14:56:42 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:56:42 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.05%
[2025-01-19 14:56:44 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][0/312]	eta 0:10:54 lr 0.000942	time 2.0976 (2.0976)	model_time 0.7492 (0.7492)	loss 3.0932 (3.0932)	grad_norm 4.5129 (4.5129/0.0000)	mem 34602MB
[2025-01-19 14:56:51 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.766 (8.766)	Loss 0.6966 (0.6966)	Acc@1 85.571 (85.571)	Acc@5 98.096 (98.096)	Mem 34604MB
[2025-01-19 14:56:51 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][10/312]	eta 0:04:20 lr 0.000941	time 0.7521 (0.8627)	model_time 0.7519 (0.7398)	loss 1.9885 (2.8853)	grad_norm 1.5116 (2.3494/1.0670)	mem 34602MB
[2025-01-19 14:56:55 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.213)	Loss 0.9441 (0.8080)	Acc@1 79.297 (83.174)	Acc@5 95.264 (96.573)	Mem 34604MB
[2025-01-19 14:56:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:204] * Acc@1 82.985 Acc@5 96.623
[2025-01-19 14:56:55 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.0%
[2025-01-19 14:56:55 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 14:56:59 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 14:56:59 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 82.99%
[2025-01-19 14:56:59 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][20/312]	eta 0:04:01 lr 0.000941	time 0.7450 (0.8260)	model_time 0.7446 (0.7615)	loss 3.0554 (2.9384)	grad_norm 1.3193 (1.7795/0.9889)	mem 34602MB
[2025-01-19 14:57:01 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][0/312]	eta 0:10:14 lr 0.000942	time 1.9696 (1.9696)	model_time 0.7283 (0.7283)	loss 3.2752 (3.2752)	grad_norm 2.0900 (2.0900/0.0000)	mem 34604MB
[2025-01-19 14:57:07 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][30/312]	eta 0:03:47 lr 0.000940	time 0.7307 (0.8067)	model_time 0.7302 (0.7629)	loss 3.0594 (2.9603)	grad_norm 2.4183 (1.7840/0.8902)	mem 34602MB
[2025-01-19 14:57:09 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][10/312]	eta 0:04:14 lr 0.000941	time 0.7349 (0.8435)	model_time 0.7347 (0.7304)	loss 3.0394 (2.9767)	grad_norm 1.0074 (1.9297/1.0879)	mem 34604MB
[2025-01-19 14:57:14 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][40/312]	eta 0:03:35 lr 0.000939	time 0.7215 (0.7907)	model_time 0.7214 (0.7574)	loss 2.4794 (2.9381)	grad_norm 1.9801 (1.9439/0.9664)	mem 34602MB
[2025-01-19 14:57:16 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][20/312]	eta 0:03:50 lr 0.000941	time 0.7411 (0.7890)	model_time 0.7406 (0.7296)	loss 2.9842 (3.0173)	grad_norm 1.8921 (2.2175/1.1173)	mem 34604MB
[2025-01-19 14:57:22 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][50/312]	eta 0:03:24 lr 0.000939	time 0.7171 (0.7817)	model_time 0.7169 (0.7549)	loss 1.9926 (2.9754)	grad_norm 1.4744 (2.0087/0.9611)	mem 34602MB
[2025-01-19 14:57:23 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][30/312]	eta 0:03:38 lr 0.000940	time 0.7167 (0.7759)	model_time 0.7163 (0.7355)	loss 3.1692 (2.9047)	grad_norm 2.1543 (2.2109/1.0321)	mem 34604MB
[2025-01-19 14:57:29 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][60/312]	eta 0:03:15 lr 0.000938	time 0.7230 (0.7747)	model_time 0.7226 (0.7522)	loss 2.8417 (2.9818)	grad_norm 2.5457 (2.0350/0.9608)	mem 34602MB
[2025-01-19 14:57:31 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][40/312]	eta 0:03:30 lr 0.000939	time 0.7206 (0.7756)	model_time 0.7205 (0.7450)	loss 3.3127 (2.8844)	grad_norm 1.7990 (2.0565/0.9711)	mem 34604MB
[2025-01-19 14:57:37 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][70/312]	eta 0:03:06 lr 0.000938	time 0.7472 (0.7694)	model_time 0.7468 (0.7500)	loss 3.1524 (2.9639)	grad_norm 0.8891 (1.9690/0.9266)	mem 34602MB
[2025-01-19 14:57:39 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][50/312]	eta 0:03:21 lr 0.000939	time 0.7216 (0.7693)	model_time 0.7212 (0.7447)	loss 1.9865 (2.8276)	grad_norm 1.3230 (1.9564/0.9240)	mem 34604MB
[2025-01-19 14:57:44 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][80/312]	eta 0:02:58 lr 0.000937	time 0.7201 (0.7682)	model_time 0.7200 (0.7512)	loss 3.5149 (2.9294)	grad_norm 1.7864 (2.0111/0.8990)	mem 34602MB
[2025-01-19 14:57:46 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][60/312]	eta 0:03:14 lr 0.000938	time 0.8308 (0.7738)	model_time 0.8306 (0.7531)	loss 3.0090 (2.8585)	grad_norm 1.3779 (1.9023/0.8752)	mem 34604MB
[2025-01-19 14:57:52 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][90/312]	eta 0:02:50 lr 0.000937	time 0.7181 (0.7671)	model_time 0.7179 (0.7519)	loss 2.4006 (2.9377)	grad_norm 1.6777 (1.9873/0.8663)	mem 34602MB
[2025-01-19 14:57:54 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][70/312]	eta 0:03:06 lr 0.000938	time 0.7303 (0.7695)	model_time 0.7302 (0.7517)	loss 2.6601 (2.8853)	grad_norm 1.7875 (1.9815/0.9120)	mem 34604MB
[2025-01-19 14:57:59 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][100/312]	eta 0:02:41 lr 0.000936	time 0.7298 (0.7636)	model_time 0.7297 (0.7498)	loss 2.5688 (2.9362)	grad_norm 5.3423 (2.0465/0.9367)	mem 34602MB
[2025-01-19 14:58:01 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][80/312]	eta 0:02:57 lr 0.000937	time 0.7209 (0.7667)	model_time 0.7204 (0.7511)	loss 3.8678 (2.9547)	grad_norm 0.7785 (2.0617/0.9783)	mem 34604MB
[2025-01-19 14:58:07 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][110/312]	eta 0:02:33 lr 0.000935	time 0.7167 (0.7624)	model_time 0.7166 (0.7498)	loss 3.1763 (2.9440)	grad_norm 1.1613 (2.0157/0.9183)	mem 34602MB
[2025-01-19 14:58:09 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][90/312]	eta 0:02:49 lr 0.000937	time 0.7306 (0.7628)	model_time 0.7304 (0.7488)	loss 2.8353 (2.9426)	grad_norm 2.1895 (2.0649/0.9630)	mem 34604MB
[2025-01-19 14:58:14 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][120/312]	eta 0:02:25 lr 0.000935	time 0.7209 (0.7601)	model_time 0.7204 (0.7485)	loss 2.4741 (2.9342)	grad_norm 1.5782 (1.9694/0.9015)	mem 34602MB
[2025-01-19 14:58:16 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][100/312]	eta 0:02:41 lr 0.000936	time 0.7075 (0.7595)	model_time 0.7070 (0.7469)	loss 2.1331 (2.9551)	grad_norm 1.6289 (1.9878/0.9511)	mem 34604MB
[2025-01-19 14:58:21 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][130/312]	eta 0:02:17 lr 0.000934	time 0.7244 (0.7581)	model_time 0.7243 (0.7474)	loss 3.1983 (2.9327)	grad_norm 5.3743 (1.9864/0.9266)	mem 34602MB
[2025-01-19 14:58:23 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][110/312]	eta 0:02:32 lr 0.000935	time 0.7190 (0.7564)	model_time 0.7187 (0.7449)	loss 3.4803 (2.9639)	grad_norm 2.5062 (1.9613/0.9295)	mem 34604MB
[2025-01-19 14:58:29 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][140/312]	eta 0:02:10 lr 0.000934	time 0.7195 (0.7587)	model_time 0.7191 (0.7488)	loss 3.2735 (2.9351)	grad_norm 2.9110 (2.0412/0.9413)	mem 34602MB
[2025-01-19 14:58:31 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][120/312]	eta 0:02:24 lr 0.000935	time 0.7176 (0.7544)	model_time 0.7174 (0.7437)	loss 2.1382 (2.9649)	grad_norm 1.4767 (1.9354/0.9165)	mem 34604MB
[2025-01-19 14:58:37 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][150/312]	eta 0:02:02 lr 0.000933	time 0.7200 (0.7592)	model_time 0.7199 (0.7499)	loss 2.0014 (2.9338)	grad_norm 1.9660 (2.0230/0.9276)	mem 34602MB
[2025-01-19 14:58:38 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][130/312]	eta 0:02:16 lr 0.000934	time 0.7169 (0.7521)	model_time 0.7165 (0.7423)	loss 2.9036 (2.9666)	grad_norm 0.8096 (1.9030/0.8976)	mem 34604MB
[2025-01-19 14:58:44 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][160/312]	eta 0:01:55 lr 0.000933	time 0.7271 (0.7585)	model_time 0.7270 (0.7497)	loss 2.6498 (2.9122)	grad_norm 1.2041 (1.9908/0.9157)	mem 34602MB
[2025-01-19 14:58:45 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][140/312]	eta 0:02:09 lr 0.000934	time 0.7224 (0.7502)	model_time 0.7220 (0.7410)	loss 2.8849 (2.9806)	grad_norm 2.2421 (1.8955/0.8743)	mem 34604MB
[2025-01-19 14:58:52 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][170/312]	eta 0:01:47 lr 0.000932	time 0.8040 (0.7583)	model_time 0.8039 (0.7500)	loss 3.2597 (2.9057)	grad_norm 2.6534 (1.9896/0.8939)	mem 34602MB
[2025-01-19 14:58:52 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][150/312]	eta 0:02:01 lr 0.000933	time 0.7147 (0.7497)	model_time 0.7146 (0.7411)	loss 3.1305 (2.9762)	grad_norm 2.4310 (1.8568/0.8659)	mem 34604MB
[2025-01-19 14:58:59 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][180/312]	eta 0:01:39 lr 0.000932	time 0.7233 (0.7573)	model_time 0.7232 (0.7494)	loss 2.9390 (2.9053)	grad_norm 1.0659 (1.9790/0.8833)	mem 34602MB
[2025-01-19 14:59:01 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][160/312]	eta 0:01:54 lr 0.000933	time 0.7176 (0.7545)	model_time 0.7174 (0.7464)	loss 1.9458 (2.9662)	grad_norm 1.6615 (1.8655/0.8511)	mem 34604MB
[2025-01-19 14:59:06 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][190/312]	eta 0:01:32 lr 0.000931	time 0.7176 (0.7565)	model_time 0.7171 (0.7490)	loss 3.0402 (2.9126)	grad_norm 1.4166 (1.9519/0.8787)	mem 34602MB
[2025-01-19 14:59:08 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][170/312]	eta 0:01:46 lr 0.000932	time 0.7207 (0.7531)	model_time 0.7206 (0.7455)	loss 3.4433 (2.9593)	grad_norm 0.9364 (1.8803/0.8417)	mem 34604MB
[2025-01-19 14:59:14 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][200/312]	eta 0:01:24 lr 0.000930	time 0.7458 (0.7564)	model_time 0.7457 (0.7493)	loss 2.7909 (2.9049)	grad_norm 1.0489 (1.9263/0.8694)	mem 34602MB
[2025-01-19 14:59:16 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][180/312]	eta 0:01:39 lr 0.000932	time 0.9849 (0.7568)	model_time 0.9847 (0.7495)	loss 3.1583 (2.9627)	grad_norm 1.2646 (1.8620/0.8318)	mem 34604MB
[2025-01-19 14:59:21 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][210/312]	eta 0:01:17 lr 0.000930	time 0.7199 (0.7557)	model_time 0.7198 (0.7489)	loss 3.3853 (2.9060)	grad_norm 2.0553 (1.9102/0.8547)	mem 34602MB
[2025-01-19 14:59:24 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][190/312]	eta 0:01:32 lr 0.000931	time 0.7252 (0.7563)	model_time 0.7247 (0.7495)	loss 3.4974 (2.9664)	grad_norm 1.9970 (1.8630/0.8287)	mem 34604MB
[2025-01-19 14:59:29 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][220/312]	eta 0:01:09 lr 0.000929	time 0.7158 (0.7549)	model_time 0.7153 (0.7485)	loss 3.4958 (2.9152)	grad_norm 1.2545 (1.9054/0.8456)	mem 34602MB
[2025-01-19 14:59:31 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][200/312]	eta 0:01:24 lr 0.000930	time 0.7212 (0.7556)	model_time 0.7211 (0.7490)	loss 2.7063 (2.9707)	grad_norm 4.8590 (1.9024/0.8694)	mem 34604MB
[2025-01-19 14:59:36 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][230/312]	eta 0:01:01 lr 0.000929	time 0.7179 (0.7543)	model_time 0.7178 (0.7481)	loss 2.3426 (2.9098)	grad_norm 3.0017 (1.9053/0.8396)	mem 34602MB
[2025-01-19 14:59:38 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][210/312]	eta 0:01:16 lr 0.000930	time 0.7143 (0.7542)	model_time 0.7138 (0.7479)	loss 3.2187 (2.9691)	grad_norm 1.9051 (1.9349/0.9127)	mem 34604MB
[2025-01-19 14:59:44 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][240/312]	eta 0:00:54 lr 0.000928	time 0.7265 (0.7534)	model_time 0.7261 (0.7474)	loss 1.9151 (2.9068)	grad_norm 1.6933 (1.9076/0.8443)	mem 34602MB
[2025-01-19 14:59:46 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][220/312]	eta 0:01:09 lr 0.000929	time 0.7323 (0.7531)	model_time 0.7321 (0.7471)	loss 3.5572 (2.9683)	grad_norm 1.0695 (1.9273/0.9098)	mem 34604MB
[2025-01-19 14:59:51 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][250/312]	eta 0:00:46 lr 0.000928	time 0.7343 (0.7528)	model_time 0.7342 (0.7470)	loss 2.3924 (2.9106)	grad_norm 1.6469 (1.9323/0.8509)	mem 34602MB
[2025-01-19 14:59:53 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][230/312]	eta 0:01:01 lr 0.000929	time 0.7221 (0.7518)	model_time 0.7219 (0.7460)	loss 3.1551 (2.9805)	grad_norm 1.7773 (1.9186/0.8959)	mem 34604MB
[2025-01-19 14:59:59 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][260/312]	eta 0:00:39 lr 0.000927	time 0.7199 (0.7532)	model_time 0.7194 (0.7477)	loss 2.6345 (2.9117)	grad_norm 2.8621 (1.9391/0.8515)	mem 34602MB
[2025-01-19 15:00:00 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][240/312]	eta 0:00:54 lr 0.000928	time 0.7985 (0.7514)	model_time 0.7980 (0.7458)	loss 2.2292 (2.9746)	grad_norm 1.5687 (1.9059/0.8834)	mem 34604MB
[2025-01-19 15:00:06 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][270/312]	eta 0:00:31 lr 0.000927	time 0.7191 (0.7534)	model_time 0.7189 (0.7480)	loss 2.9846 (2.9141)	grad_norm 1.4244 (1.9533/0.8495)	mem 34602MB
[2025-01-19 15:00:08 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][250/312]	eta 0:00:46 lr 0.000928	time 0.7252 (0.7506)	model_time 0.7248 (0.7453)	loss 3.1018 (2.9781)	grad_norm 1.8190 (1.9077/0.8762)	mem 34604MB
[2025-01-19 15:00:14 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][280/312]	eta 0:00:24 lr 0.000926	time 0.7162 (0.7533)	model_time 0.7158 (0.7481)	loss 2.8977 (2.9128)	grad_norm 1.4870 (1.9522/0.8514)	mem 34602MB
[2025-01-19 15:00:15 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][260/312]	eta 0:00:38 lr 0.000927	time 0.7421 (0.7499)	model_time 0.7416 (0.7448)	loss 3.1202 (2.9765)	grad_norm 2.1583 (1.9012/0.8639)	mem 34604MB
[2025-01-19 15:00:21 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][290/312]	eta 0:00:16 lr 0.000926	time 0.8028 (0.7534)	model_time 0.8026 (0.7483)	loss 3.2044 (2.9136)	grad_norm 1.2381 (1.9394/0.8427)	mem 34602MB
[2025-01-19 15:00:23 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][270/312]	eta 0:00:31 lr 0.000927	time 0.7171 (0.7501)	model_time 0.7167 (0.7451)	loss 2.9170 (2.9770)	grad_norm 1.9270 (1.9006/0.8560)	mem 34604MB
[2025-01-19 15:00:29 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][300/312]	eta 0:00:09 lr 0.000925	time 0.7134 (0.7529)	model_time 0.7133 (0.7481)	loss 3.2636 (2.9126)	grad_norm 1.2238 (1.9241/0.8266)	mem 34602MB
[2025-01-19 15:00:31 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][280/312]	eta 0:00:24 lr 0.000926	time 0.7328 (0.7523)	model_time 0.7324 (0.7475)	loss 3.5030 (2.9772)	grad_norm 1.4525 (1.8880/0.8473)	mem 34604MB
[2025-01-19 15:00:36 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][310/312]	eta 0:00:01 lr 0.000924	time 0.7205 (0.7519)	model_time 0.7204 (0.7472)	loss 3.2793 (2.9089)	grad_norm 2.4988 (1.9427/0.8533)	mem 34602MB
[2025-01-19 15:00:37 internimage_b_1k_224] (main.py 519): INFO EPOCH 205 training takes 0:03:54
[2025-01-19 15:00:37 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_205.pth saving......
[2025-01-19 15:00:38 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][290/312]	eta 0:00:16 lr 0.000926	time 0.7308 (0.7518)	model_time 0.7305 (0.7472)	loss 3.0900 (2.9755)	grad_norm 1.7156 (1.8812/0.8373)	mem 34604MB
[2025-01-19 15:00:40 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_205.pth saved !!!
[2025-01-19 15:00:46 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][300/312]	eta 0:00:09 lr 0.000925	time 0.8327 (0.7530)	model_time 0.8327 (0.7485)	loss 2.9347 (2.9684)	grad_norm 2.2947 (1.8715/0.8290)	mem 34604MB
[2025-01-19 15:00:48 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.941 (7.941)	Loss 0.7310 (0.7310)	Acc@1 85.083 (85.083)	Acc@5 97.656 (97.656)	Mem 34602MB
[2025-01-19 15:00:51 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.034)	Loss 0.9629 (0.8339)	Acc@1 78.760 (82.926)	Acc@5 95.239 (96.462)	Mem 34602MB
[2025-01-19 15:00:51 internimage_b_1k_224] (main.py 575): INFO [Epoch:205] * Acc@1 82.746 Acc@5 96.461
[2025-01-19 15:00:51 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.7%
[2025-01-19 15:00:51 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 15:00:53 internimage_b_1k_224] (main.py 510): INFO Train: [205/300][310/312]	eta 0:00:01 lr 0.000924	time 0.7148 (0.7525)	model_time 0.7147 (0.7481)	loss 3.7301 (2.9625)	grad_norm 2.9861 (1.8979/0.8285)	mem 34604MB
[2025-01-19 15:00:54 internimage_b_1k_224] (main.py 519): INFO EPOCH 205 training takes 0:03:54
[2025-01-19 15:00:54 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_205.pth saving......
[2025-01-19 15:00:55 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 15:00:55 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.75%
[2025-01-19 15:00:57 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_205.pth saved !!!
[2025-01-19 15:01:10 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.333 (15.333)	Loss 0.7040 (0.7040)	Acc@1 85.352 (85.352)	Acc@5 97.998 (97.998)	Mem 34602MB
[2025-01-19 15:01:13 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.118 (16.118)	Loss 0.7506 (0.7506)	Acc@1 84.644 (84.644)	Acc@5 97.437 (97.437)	Mem 34604MB
[2025-01-19 15:01:17 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.991)	Loss 0.9455 (0.8104)	Acc@1 79.321 (83.199)	Acc@5 95.435 (96.631)	Mem 34602MB
[2025-01-19 15:01:17 internimage_b_1k_224] (main.py 575): INFO [Epoch:205] * Acc@1 83.069 Acc@5 96.675
[2025-01-19 15:01:17 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.1%
[2025-01-19 15:01:17 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:01:19 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.983)	Loss 0.9814 (0.8426)	Acc@1 78.955 (82.684)	Acc@5 95.435 (96.402)	Mem 34604MB
[2025-01-19 15:01:19 internimage_b_1k_224] (main.py 575): INFO [Epoch:205] * Acc@1 82.540 Acc@5 96.411
[2025-01-19 15:01:19 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.5%
[2025-01-19 15:01:19 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.73%
[2025-01-19 15:01:21 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:01:21 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.07%
[2025-01-19 15:01:23 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][0/312]	eta 0:11:03 lr 0.000924	time 2.1269 (2.1269)	model_time 0.7373 (0.7373)	loss 2.9187 (2.9187)	grad_norm 1.3269 (1.3269/0.0000)	mem 34602MB
[2025-01-19 15:01:28 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.172 (9.172)	Loss 0.6975 (0.6975)	Acc@1 85.645 (85.645)	Acc@5 98.096 (98.096)	Mem 34604MB
[2025-01-19 15:01:31 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][10/312]	eta 0:04:28 lr 0.000924	time 0.7228 (0.8899)	model_time 0.7223 (0.7632)	loss 2.1113 (2.8335)	grad_norm 1.4066 (2.3495/0.7449)	mem 34602MB
[2025-01-19 15:01:33 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.245)	Loss 0.9438 (0.8083)	Acc@1 79.321 (83.212)	Acc@5 95.264 (96.586)	Mem 34604MB
[2025-01-19 15:01:33 internimage_b_1k_224] (main.py 575): INFO [Epoch:205] * Acc@1 83.017 Acc@5 96.635
[2025-01-19 15:01:33 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.0%
[2025-01-19 15:01:33 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:01:37 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:01:37 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.02%
[2025-01-19 15:01:38 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][20/312]	eta 0:04:00 lr 0.000923	time 0.7166 (0.8244)	model_time 0.7165 (0.7578)	loss 3.0870 (2.9384)	grad_norm 1.6814 (2.1746/0.8012)	mem 34602MB
[2025-01-19 15:01:39 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][0/312]	eta 0:11:02 lr 0.000924	time 2.1221 (2.1221)	model_time 0.7628 (0.7628)	loss 2.2583 (2.2583)	grad_norm 1.6986 (1.6986/0.0000)	mem 34604MB
[2025-01-19 15:01:46 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][30/312]	eta 0:03:44 lr 0.000923	time 0.7170 (0.7971)	model_time 0.7165 (0.7519)	loss 2.6103 (2.9982)	grad_norm 1.2381 (2.1028/0.8167)	mem 34602MB
[2025-01-19 15:01:47 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][10/312]	eta 0:04:22 lr 0.000924	time 0.7117 (0.8694)	model_time 0.7116 (0.7455)	loss 3.2288 (2.8096)	grad_norm 2.2189 (2.0291/0.4100)	mem 34604MB
[2025-01-19 15:01:53 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][40/312]	eta 0:03:33 lr 0.000922	time 0.7199 (0.7853)	model_time 0.7195 (0.7510)	loss 3.7665 (3.0061)	grad_norm 1.4815 (1.8891/0.8139)	mem 34602MB
[2025-01-19 15:01:54 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][20/312]	eta 0:03:53 lr 0.000923	time 0.7149 (0.8012)	model_time 0.7145 (0.7361)	loss 2.3763 (2.8586)	grad_norm 2.6683 (1.8313/0.5490)	mem 34604MB
[2025-01-19 15:02:00 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][50/312]	eta 0:03:23 lr 0.000922	time 0.7282 (0.7770)	model_time 0.7281 (0.7494)	loss 2.4620 (2.9550)	grad_norm 2.0473 (1.7995/0.7737)	mem 34602MB
[2025-01-19 15:02:01 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][30/312]	eta 0:03:38 lr 0.000923	time 0.7199 (0.7765)	model_time 0.7193 (0.7323)	loss 2.0115 (2.8775)	grad_norm 1.0117 (1.8716/0.6248)	mem 34604MB
[2025-01-19 15:02:08 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][60/312]	eta 0:03:14 lr 0.000921	time 0.7206 (0.7722)	model_time 0.7202 (0.7491)	loss 3.2108 (2.9743)	grad_norm 1.7289 (1.7945/0.7452)	mem 34602MB
[2025-01-19 15:02:08 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][40/312]	eta 0:03:27 lr 0.000922	time 0.7182 (0.7639)	model_time 0.7177 (0.7304)	loss 3.3022 (2.8938)	grad_norm 1.1016 (1.8894/0.6285)	mem 34604MB
[2025-01-19 15:02:16 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][70/312]	eta 0:03:06 lr 0.000920	time 0.7170 (0.7701)	model_time 0.7165 (0.7502)	loss 2.6954 (2.9645)	grad_norm 3.5056 (1.8067/0.7346)	mem 34602MB
[2025-01-19 15:02:16 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][50/312]	eta 0:03:18 lr 0.000922	time 0.7242 (0.7564)	model_time 0.7237 (0.7293)	loss 3.2984 (2.9355)	grad_norm 0.9485 (1.8894/0.6111)	mem 34604MB
[2025-01-19 15:02:23 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][60/312]	eta 0:03:09 lr 0.000921	time 0.7264 (0.7520)	model_time 0.7262 (0.7293)	loss 2.8983 (2.8836)	grad_norm 2.2803 (1.8811/0.5922)	mem 34604MB
[2025-01-19 15:02:23 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][80/312]	eta 0:02:59 lr 0.000920	time 0.7195 (0.7716)	model_time 0.7191 (0.7540)	loss 2.6490 (2.9574)	grad_norm 2.5968 (1.8739/0.7381)	mem 34602MB
[2025-01-19 15:02:30 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][70/312]	eta 0:03:01 lr 0.000920	time 0.7145 (0.7486)	model_time 0.7140 (0.7291)	loss 2.8279 (2.9141)	grad_norm 2.5998 (1.9404/0.6474)	mem 34604MB
[2025-01-19 15:02:31 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][90/312]	eta 0:02:50 lr 0.000919	time 0.7190 (0.7684)	model_time 0.7188 (0.7527)	loss 2.2161 (2.9450)	grad_norm 0.9993 (1.8630/0.7224)	mem 34602MB
[2025-01-19 15:02:38 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][80/312]	eta 0:02:54 lr 0.000920	time 0.7170 (0.7504)	model_time 0.7165 (0.7332)	loss 2.6036 (2.9279)	grad_norm 1.1451 (1.9155/0.6665)	mem 34604MB
[2025-01-19 15:02:38 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][100/312]	eta 0:02:42 lr 0.000919	time 0.8346 (0.7666)	model_time 0.8345 (0.7524)	loss 3.0038 (2.9444)	grad_norm 3.1121 (1.8313/0.7215)	mem 34602MB
[2025-01-19 15:02:46 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][90/312]	eta 0:02:47 lr 0.000919	time 0.7070 (0.7542)	model_time 0.7068 (0.7389)	loss 2.8662 (2.9205)	grad_norm 1.3822 (1.8763/0.6676)	mem 34604MB
[2025-01-19 15:02:46 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][110/312]	eta 0:02:34 lr 0.000918	time 0.7171 (0.7646)	model_time 0.7166 (0.7517)	loss 3.5025 (2.9453)	grad_norm 1.3523 (1.8350/0.7192)	mem 34602MB
[2025-01-19 15:02:53 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][100/312]	eta 0:02:39 lr 0.000919	time 0.7144 (0.7527)	model_time 0.7140 (0.7388)	loss 1.9609 (2.9106)	grad_norm 1.0940 (1.8579/0.6654)	mem 34604MB
[2025-01-19 15:02:53 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][120/312]	eta 0:02:26 lr 0.000918	time 0.7215 (0.7621)	model_time 0.7211 (0.7502)	loss 2.7048 (2.9350)	grad_norm 1.6737 (1.8858/0.7509)	mem 34602MB
[2025-01-19 15:03:00 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][130/312]	eta 0:02:18 lr 0.000917	time 0.8213 (0.7607)	model_time 0.8208 (0.7497)	loss 3.3766 (2.9347)	grad_norm 1.5366 (1.9061/0.7479)	mem 34602MB
[2025-01-19 15:03:01 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][110/312]	eta 0:02:32 lr 0.000918	time 0.7250 (0.7554)	model_time 0.7249 (0.7428)	loss 3.2401 (2.9318)	grad_norm 1.2949 (1.8686/0.6751)	mem 34604MB
[2025-01-19 15:03:08 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][140/312]	eta 0:02:10 lr 0.000917	time 0.7229 (0.7598)	model_time 0.7227 (0.7496)	loss 3.1602 (2.9437)	grad_norm 3.5741 (1.9541/0.7792)	mem 34602MB
[2025-01-19 15:03:08 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][120/312]	eta 0:02:24 lr 0.000918	time 0.7215 (0.7544)	model_time 0.7213 (0.7428)	loss 2.8082 (2.9120)	grad_norm 1.1831 (1.8373/0.6736)	mem 34604MB
[2025-01-19 15:03:15 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][150/312]	eta 0:02:02 lr 0.000916	time 0.7386 (0.7585)	model_time 0.7384 (0.7489)	loss 3.1284 (2.9523)	grad_norm 2.3728 (1.9540/0.7734)	mem 34602MB
[2025-01-19 15:03:16 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][130/312]	eta 0:02:17 lr 0.000917	time 0.7127 (0.7553)	model_time 0.7122 (0.7446)	loss 3.5350 (2.9021)	grad_norm 1.3747 (1.8182/0.6667)	mem 34604MB
[2025-01-19 15:03:23 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][160/312]	eta 0:01:55 lr 0.000915	time 0.7194 (0.7583)	model_time 0.7190 (0.7493)	loss 3.4024 (2.9342)	grad_norm 4.4393 (1.9656/0.7845)	mem 34602MB
[2025-01-19 15:03:23 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][140/312]	eta 0:02:09 lr 0.000917	time 0.7288 (0.7534)	model_time 0.7286 (0.7434)	loss 2.1688 (2.8885)	grad_norm 2.4170 (1.8221/0.6560)	mem 34604MB
[2025-01-19 15:03:30 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][170/312]	eta 0:01:47 lr 0.000915	time 0.7161 (0.7576)	model_time 0.7159 (0.7491)	loss 2.8806 (2.9254)	grad_norm 1.0612 (1.9472/0.7830)	mem 34602MB
[2025-01-19 15:03:31 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][150/312]	eta 0:02:01 lr 0.000916	time 0.7274 (0.7518)	model_time 0.7272 (0.7424)	loss 2.4638 (2.8935)	grad_norm 1.6452 (1.8351/0.6660)	mem 34604MB
[2025-01-19 15:03:38 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][160/312]	eta 0:01:54 lr 0.000915	time 0.7217 (0.7502)	model_time 0.7212 (0.7414)	loss 3.1744 (2.8879)	grad_norm 2.1147 (1.8294/0.6605)	mem 34604MB
[2025-01-19 15:03:38 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][180/312]	eta 0:01:39 lr 0.000914	time 0.7193 (0.7568)	model_time 0.7191 (0.7488)	loss 3.4426 (2.9305)	grad_norm 1.2235 (1.9363/0.7706)	mem 34602MB
[2025-01-19 15:03:45 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][170/312]	eta 0:01:46 lr 0.000915	time 0.7175 (0.7489)	model_time 0.7174 (0.7406)	loss 3.0554 (2.8788)	grad_norm 1.7644 (1.8667/0.7081)	mem 34604MB
[2025-01-19 15:03:46 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][190/312]	eta 0:01:32 lr 0.000914	time 0.7561 (0.7575)	model_time 0.7556 (0.7498)	loss 2.6571 (2.9316)	grad_norm 2.3567 (1.9377/0.7585)	mem 34602MB
[2025-01-19 15:03:52 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][180/312]	eta 0:01:38 lr 0.000914	time 0.7597 (0.7480)	model_time 0.7592 (0.7401)	loss 3.3160 (2.8843)	grad_norm 2.2259 (1.9202/0.7630)	mem 34604MB
[2025-01-19 15:03:53 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][200/312]	eta 0:01:24 lr 0.000913	time 0.7223 (0.7581)	model_time 0.7218 (0.7508)	loss 2.7020 (2.9375)	grad_norm 3.3842 (1.9512/0.7646)	mem 34602MB
[2025-01-19 15:04:00 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][190/312]	eta 0:01:31 lr 0.000914	time 0.7303 (0.7474)	model_time 0.7300 (0.7399)	loss 1.9543 (2.8849)	grad_norm 1.2110 (1.9098/0.7535)	mem 34604MB
[2025-01-19 15:04:01 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][210/312]	eta 0:01:17 lr 0.000913	time 0.7264 (0.7574)	model_time 0.7263 (0.7504)	loss 3.0503 (2.9430)	grad_norm 1.6497 (1.9573/0.7595)	mem 34602MB
[2025-01-19 15:04:07 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][200/312]	eta 0:01:23 lr 0.000913	time 0.7202 (0.7484)	model_time 0.7200 (0.7413)	loss 3.2541 (2.8826)	grad_norm 1.3520 (1.8795/0.7492)	mem 34604MB
[2025-01-19 15:04:08 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][220/312]	eta 0:01:09 lr 0.000912	time 0.7458 (0.7571)	model_time 0.7457 (0.7504)	loss 3.2393 (2.9433)	grad_norm 1.6260 (1.9295/0.7560)	mem 34602MB
[2025-01-19 15:04:15 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][210/312]	eta 0:01:16 lr 0.000913	time 0.7270 (0.7504)	model_time 0.7269 (0.7436)	loss 2.7882 (2.8927)	grad_norm 4.0967 (1.8922/0.7647)	mem 34604MB
[2025-01-19 15:04:16 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][230/312]	eta 0:01:02 lr 0.000912	time 0.7247 (0.7565)	model_time 0.7243 (0.7501)	loss 3.1069 (2.9437)	grad_norm 2.3518 (1.9060/0.7530)	mem 34602MB
[2025-01-19 15:04:23 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][220/312]	eta 0:01:08 lr 0.000912	time 0.7167 (0.7496)	model_time 0.7163 (0.7431)	loss 2.3823 (2.8917)	grad_norm 1.0419 (1.9200/0.7863)	mem 34604MB
[2025-01-19 15:04:23 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][240/312]	eta 0:00:54 lr 0.000911	time 0.7189 (0.7552)	model_time 0.7185 (0.7490)	loss 2.3236 (2.9350)	grad_norm 1.0414 (1.8807/0.7499)	mem 34602MB
[2025-01-19 15:04:30 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][250/312]	eta 0:00:46 lr 0.000910	time 0.8483 (0.7553)	model_time 0.8479 (0.7494)	loss 2.9210 (2.9389)	grad_norm 2.3794 (1.8797/0.7465)	mem 34602MB
[2025-01-19 15:04:30 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][230/312]	eta 0:01:01 lr 0.000912	time 0.7168 (0.7510)	model_time 0.7167 (0.7448)	loss 3.4084 (2.9058)	grad_norm 2.7632 (1.9402/0.7823)	mem 34604MB
[2025-01-19 15:04:38 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][240/312]	eta 0:00:54 lr 0.000911	time 0.7176 (0.7507)	model_time 0.7172 (0.7446)	loss 3.3173 (2.9124)	grad_norm 3.4383 (1.9423/0.7867)	mem 34604MB
[2025-01-19 15:04:38 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][260/312]	eta 0:00:39 lr 0.000910	time 0.7186 (0.7552)	model_time 0.7181 (0.7495)	loss 1.9272 (2.9283)	grad_norm 2.1407 (1.8828/0.7529)	mem 34602MB
[2025-01-19 15:04:45 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][270/312]	eta 0:00:31 lr 0.000909	time 0.7224 (0.7545)	model_time 0.7219 (0.7490)	loss 3.2298 (2.9303)	grad_norm 4.7711 (1.9074/0.7866)	mem 34602MB
[2025-01-19 15:04:45 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][250/312]	eta 0:00:46 lr 0.000910	time 0.7264 (0.7507)	model_time 0.7262 (0.7449)	loss 2.7939 (2.9131)	grad_norm 1.9242 (1.9543/0.7800)	mem 34604MB
[2025-01-19 15:04:53 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][260/312]	eta 0:00:38 lr 0.000910	time 0.7201 (0.7496)	model_time 0.7199 (0.7440)	loss 3.3142 (2.9172)	grad_norm 3.2232 (1.9809/0.8053)	mem 34604MB
[2025-01-19 15:04:53 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][280/312]	eta 0:00:24 lr 0.000909	time 0.7173 (0.7547)	model_time 0.7172 (0.7494)	loss 2.9782 (2.9285)	grad_norm 2.6236 (1.9268/0.8187)	mem 34602MB
[2025-01-19 15:05:00 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][270/312]	eta 0:00:31 lr 0.000909	time 0.7179 (0.7488)	model_time 0.7174 (0.7434)	loss 2.7148 (2.9234)	grad_norm 1.2364 (2.0016/0.8076)	mem 34604MB
[2025-01-19 15:05:00 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][290/312]	eta 0:00:16 lr 0.000908	time 0.7503 (0.7544)	model_time 0.7502 (0.7492)	loss 3.2820 (2.9285)	grad_norm 1.3731 (1.9426/0.8300)	mem 34602MB
[2025-01-19 15:05:07 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][280/312]	eta 0:00:23 lr 0.000909	time 0.7243 (0.7479)	model_time 0.7241 (0.7427)	loss 3.5883 (2.9302)	grad_norm 1.0665 (2.0135/0.8264)	mem 34604MB
[2025-01-19 15:05:08 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][300/312]	eta 0:00:09 lr 0.000908	time 0.7197 (0.7537)	model_time 0.7196 (0.7487)	loss 3.6052 (2.9260)	grad_norm 1.5745 (1.9275/0.8240)	mem 34602MB
[2025-01-19 15:05:14 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][290/312]	eta 0:00:16 lr 0.000908	time 0.7217 (0.7473)	model_time 0.7211 (0.7423)	loss 2.8080 (2.9229)	grad_norm 1.4573 (1.9868/0.8263)	mem 34604MB
[2025-01-19 15:05:15 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][310/312]	eta 0:00:01 lr 0.000907	time 0.7924 (0.7533)	model_time 0.7923 (0.7485)	loss 2.8522 (2.9334)	grad_norm 1.4400 (1.9215/0.8333)	mem 34602MB
[2025-01-19 15:05:16 internimage_b_1k_224] (main.py 519): INFO EPOCH 206 training takes 0:03:55
[2025-01-19 15:05:16 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_206.pth saving......
[2025-01-19 15:05:19 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_206.pth saved !!!
[2025-01-19 15:05:22 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][300/312]	eta 0:00:08 lr 0.000908	time 0.7114 (0.7465)	model_time 0.7113 (0.7416)	loss 3.2282 (2.9286)	grad_norm 0.9802 (1.9699/0.8240)	mem 34604MB
[2025-01-19 15:05:26 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.114 (7.114)	Loss 0.7410 (0.7410)	Acc@1 85.571 (85.571)	Acc@5 97.681 (97.681)	Mem 34602MB
[2025-01-19 15:05:29 internimage_b_1k_224] (main.py 510): INFO Train: [206/300][310/312]	eta 0:00:01 lr 0.000907	time 0.7604 (0.7458)	model_time 0.7602 (0.7411)	loss 3.0809 (2.9299)	grad_norm 1.5680 (1.9547/0.8285)	mem 34604MB
[2025-01-19 15:05:30 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.945)	Loss 0.9721 (0.8425)	Acc@1 79.126 (82.981)	Acc@5 95.508 (96.535)	Mem 34602MB
[2025-01-19 15:05:30 internimage_b_1k_224] (main.py 519): INFO EPOCH 206 training takes 0:03:52
[2025-01-19 15:05:30 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_206.pth saving......
[2025-01-19 15:05:30 internimage_b_1k_224] (main.py 575): INFO [Epoch:206] * Acc@1 82.812 Acc@5 96.553
[2025-01-19 15:05:30 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.8%
[2025-01-19 15:05:30 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 15:05:33 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_206.pth saved !!!
[2025-01-19 15:05:33 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 15:05:33 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.81%
[2025-01-19 15:05:49 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.336 (15.336)	Loss 0.7050 (0.7050)	Acc@1 85.474 (85.474)	Acc@5 98.022 (98.022)	Mem 34602MB
[2025-01-19 15:05:49 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.316 (16.316)	Loss 0.7143 (0.7143)	Acc@1 84.888 (84.888)	Acc@5 97.388 (97.388)	Mem 34604MB
[2025-01-19 15:05:56 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.133)	Loss 0.9316 (0.8118)	Acc@1 79.248 (82.892)	Acc@5 95.654 (96.431)	Mem 34604MB
[2025-01-19 15:05:57 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.124)	Loss 0.9454 (0.8107)	Acc@1 79.297 (83.216)	Acc@5 95.410 (96.642)	Mem 34602MB
[2025-01-19 15:05:57 internimage_b_1k_224] (main.py 575): INFO [Epoch:206] * Acc@1 82.730 Acc@5 96.449
[2025-01-19 15:05:57 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.7%
[2025-01-19 15:05:57 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.73%
[2025-01-19 15:05:57 internimage_b_1k_224] (main.py 575): INFO [Epoch:206] * Acc@1 83.077 Acc@5 96.689
[2025-01-19 15:05:57 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.1%
[2025-01-19 15:05:57 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:06:01 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:06:01 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.08%
[2025-01-19 15:06:03 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][0/312]	eta 0:13:20 lr 0.000907	time 2.5662 (2.5662)	model_time 0.7543 (0.7543)	loss 2.8133 (2.8133)	grad_norm 1.4138 (1.4138/0.0000)	mem 34602MB
[2025-01-19 15:06:06 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.117 (9.117)	Loss 0.6982 (0.6982)	Acc@1 85.620 (85.620)	Acc@5 98.071 (98.071)	Mem 34604MB
[2025-01-19 15:06:10 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (1.237)	Loss 0.9435 (0.8085)	Acc@1 79.346 (83.234)	Acc@5 95.312 (96.595)	Mem 34604MB
[2025-01-19 15:06:10 internimage_b_1k_224] (main.py 575): INFO [Epoch:206] * Acc@1 83.039 Acc@5 96.647
[2025-01-19 15:06:10 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.0%
[2025-01-19 15:06:11 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:06:11 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][10/312]	eta 0:04:42 lr 0.000907	time 0.8065 (0.9348)	model_time 0.8061 (0.7698)	loss 2.9230 (2.7630)	grad_norm 1.8667 (1.6594/0.6514)	mem 34602MB
[2025-01-19 15:06:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:06:14 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.04%
[2025-01-19 15:06:17 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][0/312]	eta 0:12:54 lr 0.000907	time 2.4831 (2.4831)	model_time 0.7415 (0.7415)	loss 2.8612 (2.8612)	grad_norm 1.9358 (1.9358/0.0000)	mem 34604MB
[2025-01-19 15:06:19 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][20/312]	eta 0:04:07 lr 0.000906	time 0.7920 (0.8486)	model_time 0.7919 (0.7620)	loss 2.9804 (2.9562)	grad_norm 1.0657 (1.6160/0.6292)	mem 34602MB
[2025-01-19 15:06:24 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][10/312]	eta 0:04:37 lr 0.000907	time 0.7148 (0.9194)	model_time 0.7147 (0.7608)	loss 3.6433 (2.8637)	grad_norm 2.1362 (1.9315/0.5014)	mem 34604MB
[2025-01-19 15:06:26 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][30/312]	eta 0:03:51 lr 0.000905	time 0.7905 (0.8199)	model_time 0.7901 (0.7611)	loss 3.2978 (3.0207)	grad_norm 2.1399 (1.6000/0.5936)	mem 34602MB
[2025-01-19 15:06:33 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][20/312]	eta 0:04:13 lr 0.000906	time 0.7370 (0.8675)	model_time 0.7365 (0.7842)	loss 3.1444 (2.8151)	grad_norm 3.6451 (1.9052/0.6441)	mem 34604MB
[2025-01-19 15:06:34 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][40/312]	eta 0:03:38 lr 0.000905	time 0.7611 (0.8019)	model_time 0.7609 (0.7573)	loss 3.0244 (2.9678)	grad_norm 1.4227 (1.5354/0.5512)	mem 34602MB
[2025-01-19 15:06:40 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][30/312]	eta 0:03:53 lr 0.000905	time 0.7203 (0.8288)	model_time 0.7201 (0.7722)	loss 2.8591 (2.8042)	grad_norm 1.7487 (1.9651/0.6883)	mem 34604MB
[2025-01-19 15:06:41 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][50/312]	eta 0:03:26 lr 0.000904	time 0.8116 (0.7890)	model_time 0.8114 (0.7531)	loss 3.5641 (2.9398)	grad_norm 0.9093 (1.5322/0.5195)	mem 34602MB
[2025-01-19 15:06:48 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][40/312]	eta 0:03:41 lr 0.000905	time 0.7069 (0.8136)	model_time 0.7065 (0.7707)	loss 2.0402 (2.8296)	grad_norm 1.7845 (2.0142/0.6599)	mem 34604MB
[2025-01-19 15:06:49 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][60/312]	eta 0:03:16 lr 0.000904	time 0.8218 (0.7812)	model_time 0.8216 (0.7511)	loss 2.7475 (2.9364)	grad_norm 1.6024 (1.5772/0.4986)	mem 34602MB
[2025-01-19 15:06:55 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][50/312]	eta 0:03:30 lr 0.000904	time 0.7172 (0.8017)	model_time 0.7167 (0.7672)	loss 3.1183 (2.8727)	grad_norm 2.8731 (2.0419/0.6454)	mem 34604MB
[2025-01-19 15:06:56 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][70/312]	eta 0:03:08 lr 0.000903	time 0.7178 (0.7769)	model_time 0.7176 (0.7510)	loss 2.2602 (2.9284)	grad_norm 1.6158 (1.6152/0.5253)	mem 34602MB
[2025-01-19 15:07:03 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][60/312]	eta 0:03:19 lr 0.000904	time 0.7329 (0.7917)	model_time 0.7327 (0.7628)	loss 3.7346 (2.8743)	grad_norm 1.3461 (1.9849/0.6362)	mem 34604MB
[2025-01-19 15:07:03 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][80/312]	eta 0:02:58 lr 0.000903	time 0.7253 (0.7715)	model_time 0.7252 (0.7488)	loss 2.0498 (2.8811)	grad_norm 3.3393 (1.6456/0.5539)	mem 34602MB
[2025-01-19 15:07:10 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][70/312]	eta 0:03:09 lr 0.000903	time 0.7078 (0.7828)	model_time 0.7076 (0.7579)	loss 3.1223 (2.9139)	grad_norm 2.6221 (2.0225/0.6561)	mem 34604MB
[2025-01-19 15:07:11 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][90/312]	eta 0:02:50 lr 0.000902	time 0.7163 (0.7681)	model_time 0.7158 (0.7478)	loss 3.0789 (2.8929)	grad_norm 1.5660 (1.7426/0.6370)	mem 34602MB
[2025-01-19 15:07:17 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][80/312]	eta 0:03:00 lr 0.000903	time 0.7154 (0.7759)	model_time 0.7152 (0.7540)	loss 3.1194 (2.9338)	grad_norm 3.0292 (2.0662/0.7421)	mem 34604MB
[2025-01-19 15:07:18 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][100/312]	eta 0:02:42 lr 0.000902	time 0.7315 (0.7667)	model_time 0.7314 (0.7484)	loss 3.1407 (2.8953)	grad_norm 1.7276 (1.8193/0.7480)	mem 34602MB
[2025-01-19 15:07:24 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][90/312]	eta 0:02:51 lr 0.000902	time 0.7138 (0.7703)	model_time 0.7133 (0.7508)	loss 3.0942 (2.9312)	grad_norm 1.3645 (2.0707/0.7216)	mem 34604MB
[2025-01-19 15:07:26 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][110/312]	eta 0:02:34 lr 0.000901	time 0.8169 (0.7646)	model_time 0.8165 (0.7479)	loss 2.0460 (2.8901)	grad_norm 1.8998 (1.8137/0.7466)	mem 34602MB
[2025-01-19 15:07:32 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][100/312]	eta 0:02:42 lr 0.000902	time 0.7268 (0.7661)	model_time 0.7262 (0.7485)	loss 3.3227 (2.9418)	grad_norm 1.7857 (2.0652/0.7372)	mem 34604MB
[2025-01-19 15:07:33 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][120/312]	eta 0:02:26 lr 0.000900	time 0.8149 (0.7642)	model_time 0.8143 (0.7488)	loss 2.9850 (2.8952)	grad_norm 0.9603 (1.7838/0.7310)	mem 34602MB
[2025-01-19 15:07:39 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][110/312]	eta 0:02:34 lr 0.000901	time 0.7262 (0.7626)	model_time 0.7258 (0.7465)	loss 2.9586 (2.9593)	grad_norm 1.2016 (2.0421/0.7176)	mem 34604MB
[2025-01-19 15:07:41 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][130/312]	eta 0:02:19 lr 0.000900	time 0.8178 (0.7656)	model_time 0.8176 (0.7514)	loss 3.3106 (2.8998)	grad_norm 4.1737 (1.8171/0.7521)	mem 34602MB
[2025-01-19 15:07:46 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][120/312]	eta 0:02:25 lr 0.000900	time 0.7106 (0.7595)	model_time 0.7104 (0.7448)	loss 1.7632 (2.9457)	grad_norm 1.3399 (1.9769/0.7251)	mem 34604MB
[2025-01-19 15:07:49 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][140/312]	eta 0:02:11 lr 0.000899	time 0.7992 (0.7643)	model_time 0.7991 (0.7511)	loss 3.0988 (2.8930)	grad_norm 2.3981 (1.8412/0.7439)	mem 34602MB
[2025-01-19 15:07:54 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][130/312]	eta 0:02:18 lr 0.000900	time 0.7980 (0.7590)	model_time 0.7978 (0.7453)	loss 3.5076 (2.9685)	grad_norm 2.6291 (1.9742/0.7183)	mem 34604MB
[2025-01-19 15:07:56 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][150/312]	eta 0:02:03 lr 0.000899	time 0.7215 (0.7623)	model_time 0.7211 (0.7500)	loss 2.7037 (2.8912)	grad_norm 1.8344 (1.8312/0.7263)	mem 34602MB
[2025-01-19 15:08:02 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][140/312]	eta 0:02:10 lr 0.000899	time 0.8322 (0.7604)	model_time 0.8320 (0.7477)	loss 2.7914 (2.9613)	grad_norm 1.6923 (1.9954/0.7574)	mem 34604MB
[2025-01-19 15:08:04 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][160/312]	eta 0:01:55 lr 0.000898	time 0.7288 (0.7619)	model_time 0.7286 (0.7503)	loss 3.4443 (2.9120)	grad_norm 3.2127 (1.8700/0.7624)	mem 34602MB
[2025-01-19 15:08:09 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][150/312]	eta 0:02:03 lr 0.000899	time 0.7110 (0.7595)	model_time 0.7107 (0.7476)	loss 1.8599 (2.9446)	grad_norm 1.0534 (1.9755/0.7546)	mem 34604MB
[2025-01-19 15:08:11 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][170/312]	eta 0:01:47 lr 0.000898	time 0.8072 (0.7602)	model_time 0.8070 (0.7493)	loss 2.1843 (2.9100)	grad_norm 2.6944 (1.8771/0.7561)	mem 34602MB
[2025-01-19 15:08:17 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][160/312]	eta 0:01:55 lr 0.000898	time 0.8039 (0.7605)	model_time 0.8036 (0.7494)	loss 1.8984 (2.9349)	grad_norm 1.2861 (1.9943/0.7558)	mem 34604MB
[2025-01-19 15:08:18 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][180/312]	eta 0:01:40 lr 0.000897	time 0.8194 (0.7594)	model_time 0.8190 (0.7490)	loss 2.0484 (2.9049)	grad_norm 2.9696 (1.9070/0.8043)	mem 34602MB
[2025-01-19 15:08:24 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][170/312]	eta 0:01:47 lr 0.000898	time 0.7637 (0.7605)	model_time 0.7631 (0.7499)	loss 3.4891 (2.9376)	grad_norm 1.6894 (2.0070/0.7520)	mem 34604MB
[2025-01-19 15:08:26 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][190/312]	eta 0:01:32 lr 0.000897	time 0.7184 (0.7585)	model_time 0.7180 (0.7486)	loss 2.5877 (2.9016)	grad_norm 2.1785 (1.9258/0.7971)	mem 34602MB
[2025-01-19 15:08:32 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][180/312]	eta 0:01:40 lr 0.000897	time 0.7430 (0.7596)	model_time 0.7428 (0.7496)	loss 3.2261 (2.9337)	grad_norm 1.7089 (2.0348/0.7627)	mem 34604MB
[2025-01-19 15:08:33 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][200/312]	eta 0:01:24 lr 0.000896	time 0.7177 (0.7571)	model_time 0.7175 (0.7477)	loss 3.2565 (2.9033)	grad_norm 1.1343 (1.9140/0.7872)	mem 34602MB
[2025-01-19 15:08:39 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][190/312]	eta 0:01:32 lr 0.000897	time 0.7162 (0.7580)	model_time 0.7160 (0.7485)	loss 2.6086 (2.9346)	grad_norm 3.1905 (2.0410/0.7791)	mem 34604MB
[2025-01-19 15:08:40 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][210/312]	eta 0:01:17 lr 0.000896	time 0.7180 (0.7562)	model_time 0.7179 (0.7472)	loss 3.4440 (2.9041)	grad_norm 2.1314 (1.9286/0.7814)	mem 34602MB
[2025-01-19 15:08:46 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][200/312]	eta 0:01:24 lr 0.000896	time 0.7190 (0.7565)	model_time 0.7188 (0.7474)	loss 2.0493 (2.9246)	grad_norm 1.9122 (2.0753/0.8050)	mem 34604MB
[2025-01-19 15:08:48 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][220/312]	eta 0:01:09 lr 0.000895	time 0.7360 (0.7568)	model_time 0.7356 (0.7482)	loss 2.6889 (2.8917)	grad_norm 1.1621 (1.9189/0.7715)	mem 34602MB
[2025-01-19 15:08:54 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][210/312]	eta 0:01:17 lr 0.000896	time 0.7230 (0.7551)	model_time 0.7228 (0.7465)	loss 1.9033 (2.9204)	grad_norm 2.9600 (2.0880/0.8114)	mem 34604MB
[2025-01-19 15:08:56 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][230/312]	eta 0:01:02 lr 0.000894	time 0.8143 (0.7562)	model_time 0.8139 (0.7480)	loss 2.9368 (2.8877)	grad_norm 0.9748 (1.9084/0.7638)	mem 34602MB
[2025-01-19 15:09:01 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][220/312]	eta 0:01:09 lr 0.000895	time 0.7145 (0.7538)	model_time 0.7144 (0.7456)	loss 2.8983 (2.9113)	grad_norm 3.0567 (2.0899/0.8006)	mem 34604MB
[2025-01-19 15:09:03 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][240/312]	eta 0:00:54 lr 0.000894	time 0.7200 (0.7559)	model_time 0.7198 (0.7480)	loss 3.3927 (2.8855)	grad_norm 2.3950 (1.8892/0.7594)	mem 34602MB
[2025-01-19 15:09:08 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][230/312]	eta 0:01:01 lr 0.000894	time 0.7228 (0.7528)	model_time 0.7226 (0.7449)	loss 2.9290 (2.9120)	grad_norm 3.9074 (2.1001/0.8123)	mem 34604MB
[2025-01-19 15:09:11 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][250/312]	eta 0:00:46 lr 0.000893	time 0.8102 (0.7566)	model_time 0.8100 (0.7489)	loss 3.0114 (2.8826)	grad_norm 2.3119 (1.8954/0.7603)	mem 34602MB
[2025-01-19 15:09:15 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][240/312]	eta 0:00:54 lr 0.000894	time 0.7206 (0.7517)	model_time 0.7203 (0.7441)	loss 3.2718 (2.9065)	grad_norm 1.4990 (2.0839/0.8117)	mem 34604MB
[2025-01-19 15:09:18 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][260/312]	eta 0:00:39 lr 0.000893	time 0.7214 (0.7560)	model_time 0.7212 (0.7486)	loss 3.6281 (2.8859)	grad_norm 2.4128 (1.8772/0.7552)	mem 34602MB
[2025-01-19 15:09:23 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][250/312]	eta 0:00:46 lr 0.000893	time 0.8085 (0.7518)	model_time 0.8081 (0.7445)	loss 3.1459 (2.9077)	grad_norm 1.9219 (2.0629/0.8073)	mem 34604MB
[2025-01-19 15:09:26 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][270/312]	eta 0:00:31 lr 0.000892	time 0.8185 (0.7557)	model_time 0.8183 (0.7486)	loss 2.6173 (2.8854)	grad_norm 1.9120 (1.8572/0.7502)	mem 34602MB
[2025-01-19 15:09:31 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][260/312]	eta 0:00:39 lr 0.000893	time 0.9196 (0.7529)	model_time 0.9193 (0.7459)	loss 3.2579 (2.9095)	grad_norm 1.8458 (2.0463/0.8018)	mem 34604MB
[2025-01-19 15:09:33 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][280/312]	eta 0:00:24 lr 0.000892	time 0.7216 (0.7554)	model_time 0.7211 (0.7486)	loss 3.1873 (2.8945)	grad_norm 3.2079 (1.8702/0.7783)	mem 34602MB
[2025-01-19 15:09:38 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][270/312]	eta 0:00:31 lr 0.000892	time 0.7102 (0.7532)	model_time 0.7100 (0.7464)	loss 3.4155 (2.9087)	grad_norm 1.4440 (2.0297/0.7949)	mem 34604MB
[2025-01-19 15:09:40 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][290/312]	eta 0:00:16 lr 0.000891	time 0.7813 (0.7545)	model_time 0.7812 (0.7479)	loss 3.4863 (2.9017)	grad_norm 1.0602 (1.8979/0.8281)	mem 34602MB
[2025-01-19 15:09:46 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][280/312]	eta 0:00:24 lr 0.000892	time 0.8044 (0.7543)	model_time 0.8042 (0.7478)	loss 2.1310 (2.9167)	grad_norm 2.7474 (2.0288/0.7902)	mem 34604MB
[2025-01-19 15:09:48 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][300/312]	eta 0:00:09 lr 0.000891	time 0.7135 (0.7537)	model_time 0.7134 (0.7473)	loss 3.1919 (2.9015)	grad_norm 1.4286 (1.9121/0.8528)	mem 34602MB
[2025-01-19 15:09:54 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][290/312]	eta 0:00:16 lr 0.000891	time 0.8094 (0.7541)	model_time 0.8092 (0.7477)	loss 3.4525 (2.9089)	grad_norm 1.6783 (2.0362/0.8042)	mem 34604MB
[2025-01-19 15:09:55 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][310/312]	eta 0:00:01 lr 0.000890	time 0.8054 (0.7538)	model_time 0.8053 (0.7476)	loss 3.2953 (2.9081)	grad_norm 2.2210 (1.9184/0.8523)	mem 34602MB
[2025-01-19 15:09:56 internimage_b_1k_224] (main.py 519): INFO EPOCH 207 training takes 0:03:55
[2025-01-19 15:09:56 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_207.pth saving......
[2025-01-19 15:10:00 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_207.pth saved !!!
[2025-01-19 15:10:01 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][300/312]	eta 0:00:09 lr 0.000891	time 0.7169 (0.7540)	model_time 0.7169 (0.7478)	loss 2.6533 (2.9069)	grad_norm 1.3060 (2.0345/0.7993)	mem 34604MB
[2025-01-19 15:10:07 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.717 (7.717)	Loss 0.7176 (0.7176)	Acc@1 85.596 (85.596)	Acc@5 97.681 (97.681)	Mem 34602MB
[2025-01-19 15:10:08 internimage_b_1k_224] (main.py 510): INFO Train: [207/300][310/312]	eta 0:00:01 lr 0.000890	time 0.7091 (0.7528)	model_time 0.7089 (0.7468)	loss 3.0992 (2.9088)	grad_norm 1.5567 (2.0408/0.8094)	mem 34604MB
[2025-01-19 15:10:09 internimage_b_1k_224] (main.py 519): INFO EPOCH 207 training takes 0:03:54
[2025-01-19 15:10:09 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_207.pth saving......
[2025-01-19 15:10:11 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.064)	Loss 0.9518 (0.8102)	Acc@1 78.955 (83.083)	Acc@5 95.410 (96.509)	Mem 34602MB
[2025-01-19 15:10:12 internimage_b_1k_224] (main.py 575): INFO [Epoch:207] * Acc@1 82.943 Acc@5 96.535
[2025-01-19 15:10:12 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.9%
[2025-01-19 15:10:12 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 15:10:12 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_207.pth saved !!!
[2025-01-19 15:10:15 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 15:10:15 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.94%
[2025-01-19 15:10:27 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.690 (14.690)	Loss 0.7248 (0.7248)	Acc@1 85.547 (85.547)	Acc@5 97.632 (97.632)	Mem 34604MB
[2025-01-19 15:10:31 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.460 (16.460)	Loss 0.7056 (0.7056)	Acc@1 85.571 (85.571)	Acc@5 98.022 (98.022)	Mem 34602MB
[2025-01-19 15:10:35 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.094)	Loss 0.9747 (0.8325)	Acc@1 79.199 (83.037)	Acc@5 95.312 (96.482)	Mem 34604MB
[2025-01-19 15:10:36 internimage_b_1k_224] (main.py 575): INFO [Epoch:207] * Acc@1 82.875 Acc@5 96.517
[2025-01-19 15:10:36 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.9%
[2025-01-19 15:10:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 15:10:37 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.069)	Loss 0.9451 (0.8109)	Acc@1 79.443 (83.261)	Acc@5 95.459 (96.651)	Mem 34602MB
[2025-01-19 15:10:38 internimage_b_1k_224] (main.py 575): INFO [Epoch:207] * Acc@1 83.117 Acc@5 96.695
[2025-01-19 15:10:38 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.1%
[2025-01-19 15:10:38 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:10:39 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 15:10:39 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.88%
[2025-01-19 15:10:42 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:10:42 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.12%
[2025-01-19 15:10:44 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][0/312]	eta 0:11:18 lr 0.000890	time 2.1758 (2.1758)	model_time 0.7473 (0.7473)	loss 2.8547 (2.8547)	grad_norm 1.0438 (1.0438/0.0000)	mem 34602MB
[2025-01-19 15:10:46 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.514 (7.514)	Loss 0.6989 (0.6989)	Acc@1 85.645 (85.645)	Acc@5 98.071 (98.071)	Mem 34604MB
[2025-01-19 15:10:50 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.988)	Loss 0.9430 (0.8087)	Acc@1 79.370 (83.261)	Acc@5 95.312 (96.600)	Mem 34604MB
[2025-01-19 15:10:50 internimage_b_1k_224] (main.py 575): INFO [Epoch:207] * Acc@1 83.059 Acc@5 96.655
[2025-01-19 15:10:50 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.1%
[2025-01-19 15:10:50 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:10:51 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][10/312]	eta 0:04:22 lr 0.000889	time 0.7168 (0.8708)	model_time 0.7164 (0.7407)	loss 2.6905 (3.0227)	grad_norm 1.0628 (1.7050/0.6073)	mem 34602MB
[2025-01-19 15:10:54 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:10:54 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.06%
[2025-01-19 15:10:56 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][0/312]	eta 0:10:59 lr 0.000890	time 2.1138 (2.1138)	model_time 0.7247 (0.7247)	loss 3.3349 (3.3349)	grad_norm 2.2955 (2.2955/0.0000)	mem 34604MB
[2025-01-19 15:10:59 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][20/312]	eta 0:03:57 lr 0.000889	time 0.8138 (0.8132)	model_time 0.8136 (0.7449)	loss 3.2989 (2.9890)	grad_norm 2.0139 (2.0572/1.0379)	mem 34602MB
[2025-01-19 15:11:03 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][10/312]	eta 0:04:18 lr 0.000889	time 0.7184 (0.8563)	model_time 0.7182 (0.7297)	loss 2.7069 (3.0559)	grad_norm 2.1337 (1.8275/0.4503)	mem 34604MB
[2025-01-19 15:11:06 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][30/312]	eta 0:03:41 lr 0.000888	time 0.7372 (0.7854)	model_time 0.7367 (0.7390)	loss 2.2771 (2.9554)	grad_norm 1.1538 (2.0076/0.9110)	mem 34602MB
[2025-01-19 15:11:10 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][20/312]	eta 0:03:53 lr 0.000889	time 0.7195 (0.7987)	model_time 0.7193 (0.7322)	loss 2.0466 (3.0147)	grad_norm 2.6959 (1.7076/0.5913)	mem 34604MB
[2025-01-19 15:11:14 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][40/312]	eta 0:03:31 lr 0.000888	time 0.8247 (0.7759)	model_time 0.8246 (0.7407)	loss 2.7281 (2.9664)	grad_norm 1.7756 (2.0903/0.9130)	mem 34602MB
[2025-01-19 15:11:18 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][30/312]	eta 0:03:38 lr 0.000888	time 0.7355 (0.7744)	model_time 0.7354 (0.7292)	loss 3.0570 (2.9527)	grad_norm 0.9065 (1.6568/0.5668)	mem 34604MB
[2025-01-19 15:11:21 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][50/312]	eta 0:03:22 lr 0.000887	time 0.7234 (0.7711)	model_time 0.7233 (0.7427)	loss 3.0982 (2.9170)	grad_norm 1.6398 (2.0522/0.8355)	mem 34602MB
[2025-01-19 15:11:25 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][40/312]	eta 0:03:27 lr 0.000888	time 0.7349 (0.7632)	model_time 0.7343 (0.7290)	loss 3.0061 (2.9319)	grad_norm 1.8640 (1.7141/0.6109)	mem 34604MB
[2025-01-19 15:11:29 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][60/312]	eta 0:03:14 lr 0.000887	time 0.7195 (0.7727)	model_time 0.7194 (0.7489)	loss 2.6314 (2.9473)	grad_norm 2.4861 (2.1208/0.9338)	mem 34602MB
[2025-01-19 15:11:32 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][50/312]	eta 0:03:18 lr 0.000887	time 0.7417 (0.7579)	model_time 0.7413 (0.7303)	loss 3.0930 (2.9377)	grad_norm 1.6796 (1.7165/0.5996)	mem 34604MB
[2025-01-19 15:11:36 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][70/312]	eta 0:03:05 lr 0.000886	time 0.7329 (0.7683)	model_time 0.7324 (0.7479)	loss 3.1090 (2.9307)	grad_norm 1.3301 (2.1167/0.9141)	mem 34602MB
[2025-01-19 15:11:40 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][60/312]	eta 0:03:10 lr 0.000887	time 0.7229 (0.7565)	model_time 0.7227 (0.7334)	loss 3.7062 (2.9801)	grad_norm 2.6833 (1.7359/0.6154)	mem 34604MB
[2025-01-19 15:11:44 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][80/312]	eta 0:02:57 lr 0.000886	time 0.7162 (0.7650)	model_time 0.7160 (0.7470)	loss 3.3595 (2.9461)	grad_norm 2.3011 (2.1420/0.9180)	mem 34602MB
[2025-01-19 15:11:48 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][70/312]	eta 0:03:04 lr 0.000886	time 0.8081 (0.7608)	model_time 0.8077 (0.7409)	loss 2.5904 (2.9294)	grad_norm 3.6426 (1.8606/0.7584)	mem 34604MB
[2025-01-19 15:11:51 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][90/312]	eta 0:02:49 lr 0.000885	time 0.7192 (0.7635)	model_time 0.7190 (0.7474)	loss 3.3024 (2.9491)	grad_norm 2.5115 (2.1450/0.9167)	mem 34602MB
[2025-01-19 15:11:55 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][80/312]	eta 0:02:56 lr 0.000886	time 0.8063 (0.7607)	model_time 0.8059 (0.7431)	loss 2.4048 (2.8934)	grad_norm 2.8509 (1.9223/0.7898)	mem 34604MB
[2025-01-19 15:11:59 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][100/312]	eta 0:02:41 lr 0.000885	time 0.7216 (0.7613)	model_time 0.7215 (0.7468)	loss 3.2788 (2.9527)	grad_norm 2.3777 (2.1619/0.9062)	mem 34602MB
[2025-01-19 15:12:03 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][90/312]	eta 0:02:49 lr 0.000885	time 0.8068 (0.7618)	model_time 0.8066 (0.7461)	loss 3.4132 (2.9167)	grad_norm 1.1094 (1.8931/0.7720)	mem 34604MB
[2025-01-19 15:12:06 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][110/312]	eta 0:02:33 lr 0.000884	time 0.7328 (0.7589)	model_time 0.7323 (0.7457)	loss 3.3001 (2.9385)	grad_norm 2.2042 (2.1014/0.8912)	mem 34602MB
[2025-01-19 15:12:10 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][100/312]	eta 0:02:41 lr 0.000885	time 0.8223 (0.7600)	model_time 0.8218 (0.7459)	loss 2.9542 (2.9208)	grad_norm 1.1511 (1.8541/0.7546)	mem 34604MB
[2025-01-19 15:12:14 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][120/312]	eta 0:02:25 lr 0.000883	time 0.7172 (0.7597)	model_time 0.7170 (0.7475)	loss 2.9188 (2.9141)	grad_norm 1.7677 (2.0852/0.8805)	mem 34602MB
[2025-01-19 15:12:18 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][110/312]	eta 0:02:33 lr 0.000884	time 0.7509 (0.7589)	model_time 0.7506 (0.7460)	loss 3.3247 (2.9256)	grad_norm 2.0303 (1.8142/0.7459)	mem 34604MB
[2025-01-19 15:12:21 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][130/312]	eta 0:02:17 lr 0.000883	time 0.7159 (0.7578)	model_time 0.7154 (0.7466)	loss 3.0491 (2.9289)	grad_norm 1.2092 (2.1098/0.8936)	mem 34602MB
[2025-01-19 15:12:25 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][120/312]	eta 0:02:25 lr 0.000883	time 0.7167 (0.7565)	model_time 0.7164 (0.7447)	loss 2.4309 (2.9212)	grad_norm 1.4837 (1.7944/0.7548)	mem 34604MB
[2025-01-19 15:12:29 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][140/312]	eta 0:02:10 lr 0.000882	time 0.8052 (0.7573)	model_time 0.8048 (0.7468)	loss 1.7816 (2.9139)	grad_norm 1.9638 (2.0954/0.8759)	mem 34602MB
[2025-01-19 15:12:32 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][130/312]	eta 0:02:17 lr 0.000883	time 0.7299 (0.7542)	model_time 0.7297 (0.7432)	loss 3.4560 (2.9062)	grad_norm 2.1173 (1.7966/0.7422)	mem 34604MB
[2025-01-19 15:12:36 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][150/312]	eta 0:02:02 lr 0.000882	time 0.7172 (0.7552)	model_time 0.7170 (0.7454)	loss 3.7175 (2.9171)	grad_norm 1.8420 (2.0713/0.8555)	mem 34602MB
[2025-01-19 15:12:40 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][140/312]	eta 0:02:09 lr 0.000882	time 0.7108 (0.7520)	model_time 0.7106 (0.7417)	loss 3.0219 (2.9145)	grad_norm 2.1403 (1.8198/0.7389)	mem 34604MB
[2025-01-19 15:12:43 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][160/312]	eta 0:01:54 lr 0.000881	time 0.7356 (0.7539)	model_time 0.7354 (0.7446)	loss 2.8843 (2.9183)	grad_norm 1.1503 (2.0363/0.8438)	mem 34602MB
[2025-01-19 15:12:47 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][150/312]	eta 0:02:01 lr 0.000882	time 0.7155 (0.7505)	model_time 0.7153 (0.7409)	loss 2.3505 (2.9287)	grad_norm 3.8110 (1.8741/0.8108)	mem 34604MB
[2025-01-19 15:12:51 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][170/312]	eta 0:01:47 lr 0.000881	time 0.7276 (0.7541)	model_time 0.7274 (0.7454)	loss 3.4994 (2.9278)	grad_norm 1.7575 (2.0113/0.8333)	mem 34602MB
[2025-01-19 15:12:54 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][160/312]	eta 0:01:53 lr 0.000881	time 0.7158 (0.7492)	model_time 0.7156 (0.7402)	loss 2.5761 (2.9219)	grad_norm 2.4839 (1.9679/0.9050)	mem 34604MB
[2025-01-19 15:12:58 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][180/312]	eta 0:01:39 lr 0.000880	time 0.7294 (0.7545)	model_time 0.7290 (0.7462)	loss 2.9572 (2.9151)	grad_norm 1.4607 (2.0207/0.8397)	mem 34602MB
[2025-01-19 15:13:02 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][170/312]	eta 0:01:46 lr 0.000881	time 0.7311 (0.7479)	model_time 0.7309 (0.7394)	loss 3.0640 (2.9195)	grad_norm 1.4076 (2.0000/0.9034)	mem 34604MB
[2025-01-19 15:13:06 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][190/312]	eta 0:01:31 lr 0.000880	time 0.7209 (0.7538)	model_time 0.7208 (0.7460)	loss 3.5323 (2.9222)	grad_norm 2.2068 (2.0047/0.8306)	mem 34602MB
[2025-01-19 15:13:09 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][180/312]	eta 0:01:38 lr 0.000880	time 0.7314 (0.7480)	model_time 0.7312 (0.7400)	loss 3.3996 (2.9249)	grad_norm 1.9710 (1.9849/0.8887)	mem 34604MB
[2025-01-19 15:13:13 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][200/312]	eta 0:01:24 lr 0.000879	time 0.7286 (0.7533)	model_time 0.7281 (0.7459)	loss 2.5592 (2.9228)	grad_norm 1.6397 (1.9734/0.8234)	mem 34602MB
[2025-01-19 15:13:17 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][190/312]	eta 0:01:31 lr 0.000880	time 0.8131 (0.7510)	model_time 0.8128 (0.7433)	loss 3.2252 (2.9256)	grad_norm 0.9061 (1.9538/0.8822)	mem 34604MB
[2025-01-19 15:13:21 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][210/312]	eta 0:01:16 lr 0.000879	time 0.7189 (0.7530)	model_time 0.7187 (0.7459)	loss 3.0816 (2.9306)	grad_norm 1.2436 (1.9599/0.8168)	mem 34602MB
[2025-01-19 15:13:25 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][200/312]	eta 0:01:24 lr 0.000879	time 0.8235 (0.7515)	model_time 0.8234 (0.7442)	loss 3.1482 (2.9296)	grad_norm 1.2968 (1.9486/0.8718)	mem 34604MB
[2025-01-19 15:13:28 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][220/312]	eta 0:01:09 lr 0.000878	time 0.7317 (0.7519)	model_time 0.7313 (0.7451)	loss 3.0661 (2.9362)	grad_norm 2.1734 (1.9570/0.8020)	mem 34602MB
[2025-01-19 15:13:32 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][210/312]	eta 0:01:16 lr 0.000879	time 0.8033 (0.7527)	model_time 0.8031 (0.7458)	loss 3.7073 (2.9328)	grad_norm 3.2652 (1.9479/0.8604)	mem 34604MB
[2025-01-19 15:13:35 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][230/312]	eta 0:01:01 lr 0.000877	time 0.7233 (0.7517)	model_time 0.7232 (0.7451)	loss 2.3226 (2.9287)	grad_norm 3.2529 (1.9812/0.8058)	mem 34602MB
[2025-01-19 15:13:40 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][220/312]	eta 0:01:09 lr 0.000878	time 0.8064 (0.7525)	model_time 0.8062 (0.7459)	loss 2.3107 (2.9240)	grad_norm 1.3358 (1.9383/0.8534)	mem 34604MB
[2025-01-19 15:13:43 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][240/312]	eta 0:00:54 lr 0.000877	time 0.7239 (0.7521)	model_time 0.7238 (0.7458)	loss 2.9654 (2.9209)	grad_norm 1.3138 (1.9651/0.7968)	mem 34602MB
[2025-01-19 15:13:47 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][230/312]	eta 0:01:01 lr 0.000877	time 0.7255 (0.7520)	model_time 0.7253 (0.7456)	loss 2.8969 (2.9305)	grad_norm 2.0465 (1.9271/0.8379)	mem 34604MB
[2025-01-19 15:13:50 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][250/312]	eta 0:00:46 lr 0.000876	time 0.7223 (0.7514)	model_time 0.7221 (0.7454)	loss 3.1834 (2.9162)	grad_norm 2.2890 (1.9670/0.8050)	mem 34602MB
[2025-01-19 15:13:55 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][240/312]	eta 0:00:54 lr 0.000877	time 0.7127 (0.7510)	model_time 0.7125 (0.7448)	loss 3.2518 (2.9300)	grad_norm 2.0328 (1.9305/0.8333)	mem 34604MB
[2025-01-19 15:13:58 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][260/312]	eta 0:00:39 lr 0.000876	time 0.7942 (0.7509)	model_time 0.7938 (0.7451)	loss 3.0615 (2.9195)	grad_norm 2.4176 (1.9705/0.8007)	mem 34602MB
[2025-01-19 15:14:02 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][250/312]	eta 0:00:46 lr 0.000876	time 0.7157 (0.7501)	model_time 0.7155 (0.7442)	loss 2.9814 (2.9269)	grad_norm 1.6081 (1.9307/0.8268)	mem 34604MB
[2025-01-19 15:14:05 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][270/312]	eta 0:00:31 lr 0.000875	time 0.7202 (0.7504)	model_time 0.7198 (0.7448)	loss 3.0192 (2.9203)	grad_norm 1.5824 (1.9518/0.7964)	mem 34602MB
[2025-01-19 15:14:09 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][260/312]	eta 0:00:38 lr 0.000876	time 0.7309 (0.7491)	model_time 0.7307 (0.7434)	loss 3.1627 (2.9382)	grad_norm 1.0596 (1.9374/0.8247)	mem 34604MB
[2025-01-19 15:14:12 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][280/312]	eta 0:00:23 lr 0.000875	time 0.7254 (0.7499)	model_time 0.7253 (0.7445)	loss 3.6304 (2.9256)	grad_norm 1.0182 (1.9413/0.7884)	mem 34602MB
[2025-01-19 15:14:16 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][270/312]	eta 0:00:31 lr 0.000875	time 0.7130 (0.7482)	model_time 0.7129 (0.7427)	loss 3.8043 (2.9396)	grad_norm 3.1679 (1.9512/0.8371)	mem 34604MB
[2025-01-19 15:14:20 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][290/312]	eta 0:00:16 lr 0.000874	time 0.7189 (0.7498)	model_time 0.7185 (0.7446)	loss 3.2850 (2.9343)	grad_norm 1.7603 (1.9386/0.7818)	mem 34602MB
[2025-01-19 15:14:24 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][280/312]	eta 0:00:23 lr 0.000875	time 0.7228 (0.7476)	model_time 0.7226 (0.7423)	loss 3.2746 (2.9364)	grad_norm 1.7627 (1.9560/0.8384)	mem 34604MB
[2025-01-19 15:14:28 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][300/312]	eta 0:00:09 lr 0.000874	time 0.7131 (0.7502)	model_time 0.7131 (0.7451)	loss 3.4545 (2.9393)	grad_norm 2.1524 (1.9453/0.7737)	mem 34602MB
[2025-01-19 15:14:31 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][290/312]	eta 0:00:16 lr 0.000874	time 0.7211 (0.7470)	model_time 0.7208 (0.7418)	loss 3.2838 (2.9435)	grad_norm 1.5360 (1.9425/0.8309)	mem 34604MB
[2025-01-19 15:14:35 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][310/312]	eta 0:00:01 lr 0.000873	time 0.7157 (0.7499)	model_time 0.7156 (0.7449)	loss 3.2476 (2.9497)	grad_norm 1.5645 (1.9523/0.7797)	mem 34602MB
[2025-01-19 15:14:36 internimage_b_1k_224] (main.py 519): INFO EPOCH 208 training takes 0:03:53
[2025-01-19 15:14:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_208.pth saving......
[2025-01-19 15:14:38 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][300/312]	eta 0:00:08 lr 0.000874	time 0.7130 (0.7467)	model_time 0.7129 (0.7417)	loss 3.2840 (2.9431)	grad_norm 1.1107 (1.9257/0.8275)	mem 34604MB
[2025-01-19 15:14:39 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_208.pth saved !!!
[2025-01-19 15:14:46 internimage_b_1k_224] (main.py 510): INFO Train: [208/300][310/312]	eta 0:00:01 lr 0.000873	time 0.7223 (0.7473)	model_time 0.7222 (0.7425)	loss 3.0256 (2.9543)	grad_norm 1.6491 (1.9228/0.8305)	mem 34604MB
[2025-01-19 15:14:46 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.080 (7.080)	Loss 0.7271 (0.7271)	Acc@1 85.083 (85.083)	Acc@5 97.388 (97.388)	Mem 34602MB
[2025-01-19 15:14:47 internimage_b_1k_224] (main.py 519): INFO EPOCH 208 training takes 0:03:53
[2025-01-19 15:14:47 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_208.pth saving......
[2025-01-19 15:14:50 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_208.pth saved !!!
[2025-01-19 15:14:51 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.077)	Loss 0.9463 (0.8189)	Acc@1 79.614 (83.050)	Acc@5 95.288 (96.444)	Mem 34602MB
[2025-01-19 15:14:51 internimage_b_1k_224] (main.py 575): INFO [Epoch:208] * Acc@1 82.883 Acc@5 96.413
[2025-01-19 15:14:51 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.9%
[2025-01-19 15:14:51 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.94%
[2025-01-19 15:15:05 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.508 (14.508)	Loss 0.7512 (0.7512)	Acc@1 85.425 (85.425)	Acc@5 97.510 (97.510)	Mem 34604MB
[2025-01-19 15:15:09 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.483 (17.483)	Loss 0.7062 (0.7062)	Acc@1 85.571 (85.571)	Acc@5 98.047 (98.047)	Mem 34602MB
[2025-01-19 15:15:12 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.996)	Loss 0.9541 (0.8487)	Acc@1 79.883 (82.941)	Acc@5 95.728 (96.382)	Mem 34604MB
[2025-01-19 15:15:12 internimage_b_1k_224] (main.py 575): INFO [Epoch:208] * Acc@1 82.776 Acc@5 96.389
[2025-01-19 15:15:12 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.8%
[2025-01-19 15:15:12 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.88%
[2025-01-19 15:15:16 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.271)	Loss 0.9449 (0.8110)	Acc@1 79.468 (83.276)	Acc@5 95.483 (96.660)	Mem 34602MB
[2025-01-19 15:15:16 internimage_b_1k_224] (main.py 575): INFO [Epoch:208] * Acc@1 83.135 Acc@5 96.703
[2025-01-19 15:15:16 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.1%
[2025-01-19 15:15:16 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:15:20 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:15:20 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.14%
[2025-01-19 15:15:22 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][0/312]	eta 0:11:29 lr 0.000873	time 2.2105 (2.2105)	model_time 0.7729 (0.7729)	loss 3.7205 (3.7205)	grad_norm 3.4168 (3.4168/0.0000)	mem 34602MB
[2025-01-19 15:15:23 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 10.408 (10.408)	Loss 0.6996 (0.6996)	Acc@1 85.718 (85.718)	Acc@5 98.096 (98.096)	Mem 34604MB
[2025-01-19 15:15:27 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.369)	Loss 0.9428 (0.8089)	Acc@1 79.468 (83.299)	Acc@5 95.312 (96.611)	Mem 34604MB
[2025-01-19 15:15:28 internimage_b_1k_224] (main.py 575): INFO [Epoch:208] * Acc@1 83.095 Acc@5 96.661
[2025-01-19 15:15:28 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.1%
[2025-01-19 15:15:28 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:15:30 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][10/312]	eta 0:04:24 lr 0.000872	time 0.7216 (0.8766)	model_time 0.7214 (0.7456)	loss 3.0205 (2.8092)	grad_norm 1.1207 (1.9873/0.7240)	mem 34602MB
[2025-01-19 15:15:31 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:15:31 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.10%
[2025-01-19 15:15:33 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][0/312]	eta 0:10:59 lr 0.000873	time 2.1140 (2.1140)	model_time 0.7293 (0.7293)	loss 3.3540 (3.3540)	grad_norm 1.2519 (1.2519/0.0000)	mem 34604MB
[2025-01-19 15:15:37 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][20/312]	eta 0:04:00 lr 0.000872	time 0.7193 (0.8234)	model_time 0.7189 (0.7546)	loss 1.7462 (2.9576)	grad_norm 2.0508 (1.9302/0.6187)	mem 34602MB
[2025-01-19 15:15:41 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][10/312]	eta 0:04:24 lr 0.000872	time 0.7797 (0.8747)	model_time 0.7794 (0.7484)	loss 3.5249 (3.0203)	grad_norm 1.9851 (1.9624/0.4387)	mem 34604MB
[2025-01-19 15:15:45 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][30/312]	eta 0:03:43 lr 0.000871	time 0.7182 (0.7922)	model_time 0.7180 (0.7455)	loss 3.1380 (2.9073)	grad_norm 1.5654 (2.0660/0.8318)	mem 34602MB
[2025-01-19 15:15:49 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][20/312]	eta 0:04:02 lr 0.000872	time 0.8187 (0.8297)	model_time 0.8185 (0.7634)	loss 3.3533 (3.0302)	grad_norm 1.0753 (2.1598/0.9122)	mem 34604MB
[2025-01-19 15:15:52 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][40/312]	eta 0:03:32 lr 0.000871	time 0.7428 (0.7817)	model_time 0.7424 (0.7463)	loss 1.9826 (2.8903)	grad_norm 4.0086 (2.2324/0.9001)	mem 34602MB
[2025-01-19 15:15:56 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][30/312]	eta 0:03:47 lr 0.000871	time 0.7235 (0.8056)	model_time 0.7234 (0.7606)	loss 3.1285 (2.9908)	grad_norm 1.8155 (2.0472/0.8388)	mem 34604MB
[2025-01-19 15:16:00 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][50/312]	eta 0:03:23 lr 0.000870	time 0.7160 (0.7784)	model_time 0.7158 (0.7499)	loss 2.1728 (2.9128)	grad_norm 0.9636 (2.2830/0.9118)	mem 34602MB
[2025-01-19 15:16:04 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][40/312]	eta 0:03:35 lr 0.000871	time 0.7755 (0.7918)	model_time 0.7753 (0.7576)	loss 2.8634 (2.9535)	grad_norm 1.4588 (1.9319/0.7713)	mem 34604MB
[2025-01-19 15:16:07 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][60/312]	eta 0:03:14 lr 0.000870	time 0.7363 (0.7723)	model_time 0.7362 (0.7484)	loss 3.4508 (2.9358)	grad_norm 2.1078 (2.2060/0.8901)	mem 34602MB
[2025-01-19 15:16:11 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][50/312]	eta 0:03:24 lr 0.000870	time 0.7168 (0.7810)	model_time 0.7166 (0.7535)	loss 3.5790 (2.9393)	grad_norm 1.3223 (1.9068/0.7702)	mem 34604MB
[2025-01-19 15:16:15 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][70/312]	eta 0:03:05 lr 0.000869	time 0.7198 (0.7682)	model_time 0.7196 (0.7476)	loss 2.7085 (2.9334)	grad_norm 2.0072 (2.1268/0.8581)	mem 34602MB
[2025-01-19 15:16:18 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][60/312]	eta 0:03:14 lr 0.000870	time 0.7224 (0.7720)	model_time 0.7222 (0.7489)	loss 3.2226 (2.9582)	grad_norm 2.3781 (1.9018/0.7613)	mem 34604MB
[2025-01-19 15:16:22 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][80/312]	eta 0:02:58 lr 0.000869	time 0.7246 (0.7677)	model_time 0.7242 (0.7496)	loss 1.7643 (2.9206)	grad_norm 3.1248 (2.0709/0.8475)	mem 34602MB
[2025-01-19 15:16:26 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][70/312]	eta 0:03:05 lr 0.000869	time 0.7145 (0.7661)	model_time 0.7142 (0.7462)	loss 3.0713 (2.9605)	grad_norm 1.9007 (1.8680/0.7483)	mem 34604MB
[2025-01-19 15:16:30 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][90/312]	eta 0:02:49 lr 0.000868	time 0.7305 (0.7652)	model_time 0.7303 (0.7491)	loss 2.3564 (2.9208)	grad_norm 1.3465 (2.1724/0.9372)	mem 34602MB
[2025-01-19 15:16:33 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][80/312]	eta 0:02:56 lr 0.000869	time 0.7342 (0.7616)	model_time 0.7340 (0.7442)	loss 2.1327 (2.9327)	grad_norm 2.5297 (1.8382/0.7313)	mem 34604MB
[2025-01-19 15:16:37 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][100/312]	eta 0:02:42 lr 0.000868	time 0.7199 (0.7648)	model_time 0.7195 (0.7502)	loss 3.2238 (2.9026)	grad_norm 2.8563 (2.2283/0.9876)	mem 34602MB
[2025-01-19 15:16:40 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][90/312]	eta 0:02:48 lr 0.000868	time 0.7321 (0.7580)	model_time 0.7317 (0.7424)	loss 2.5157 (2.9440)	grad_norm 2.6900 (1.8393/0.7096)	mem 34604MB
[2025-01-19 15:16:45 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][110/312]	eta 0:02:34 lr 0.000867	time 0.7191 (0.7639)	model_time 0.7189 (0.7506)	loss 2.8548 (2.9079)	grad_norm 0.8944 (2.1532/0.9829)	mem 34602MB
[2025-01-19 15:16:48 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][100/312]	eta 0:02:40 lr 0.000868	time 0.8385 (0.7561)	model_time 0.8383 (0.7420)	loss 3.1174 (2.9394)	grad_norm 2.4588 (1.8637/0.7288)	mem 34604MB
[2025-01-19 15:16:52 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][120/312]	eta 0:02:26 lr 0.000867	time 0.7211 (0.7618)	model_time 0.7206 (0.7495)	loss 2.0283 (2.8967)	grad_norm 2.0629 (2.0737/0.9828)	mem 34602MB
[2025-01-19 15:16:55 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][110/312]	eta 0:02:32 lr 0.000867	time 0.8087 (0.7548)	model_time 0.8084 (0.7420)	loss 3.3390 (2.9494)	grad_norm 1.2624 (1.9120/0.7546)	mem 34604MB
[2025-01-19 15:17:00 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][130/312]	eta 0:02:18 lr 0.000866	time 0.7246 (0.7600)	model_time 0.7244 (0.7487)	loss 1.7588 (2.8765)	grad_norm 1.9684 (2.0269/0.9648)	mem 34602MB
[2025-01-19 15:17:03 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][120/312]	eta 0:02:25 lr 0.000867	time 0.8095 (0.7557)	model_time 0.8093 (0.7439)	loss 2.5836 (2.9416)	grad_norm 2.9672 (1.9461/0.7574)	mem 34604MB
[2025-01-19 15:17:07 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][140/312]	eta 0:02:10 lr 0.000865	time 0.7201 (0.7591)	model_time 0.7200 (0.7486)	loss 3.1443 (2.8807)	grad_norm 2.1869 (1.9783/0.9549)	mem 34602MB
[2025-01-19 15:17:10 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][130/312]	eta 0:02:17 lr 0.000866	time 0.7222 (0.7548)	model_time 0.7219 (0.7439)	loss 2.9436 (2.9336)	grad_norm 2.2771 (1.9836/0.7741)	mem 34604MB
[2025-01-19 15:17:14 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][150/312]	eta 0:02:02 lr 0.000865	time 0.7359 (0.7573)	model_time 0.7354 (0.7475)	loss 2.7727 (2.8832)	grad_norm 1.3879 (1.9786/0.9408)	mem 34602MB
[2025-01-19 15:17:18 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][140/312]	eta 0:02:10 lr 0.000865	time 0.7151 (0.7568)	model_time 0.7150 (0.7466)	loss 3.2268 (2.9359)	grad_norm 1.7706 (2.0136/0.7920)	mem 34604MB
[2025-01-19 15:17:22 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][160/312]	eta 0:01:55 lr 0.000864	time 0.7335 (0.7592)	model_time 0.7333 (0.7499)	loss 3.6220 (2.8672)	grad_norm 1.4069 (1.9877/0.9219)	mem 34602MB
[2025-01-19 15:17:25 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][150/312]	eta 0:02:02 lr 0.000865	time 0.7214 (0.7569)	model_time 0.7212 (0.7474)	loss 3.5728 (2.9307)	grad_norm 2.6190 (1.9890/0.7891)	mem 34604MB
[2025-01-19 15:17:30 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][170/312]	eta 0:01:47 lr 0.000864	time 0.7225 (0.7582)	model_time 0.7223 (0.7495)	loss 3.1461 (2.8780)	grad_norm 1.8737 (1.9692/0.9089)	mem 34602MB
[2025-01-19 15:17:33 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][160/312]	eta 0:01:54 lr 0.000864	time 0.7271 (0.7559)	model_time 0.7266 (0.7469)	loss 2.7465 (2.9371)	grad_norm 2.4864 (1.9948/0.7979)	mem 34604MB
[2025-01-19 15:17:37 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][180/312]	eta 0:01:39 lr 0.000863	time 0.7163 (0.7569)	model_time 0.7161 (0.7486)	loss 2.4330 (2.8766)	grad_norm 1.8147 (1.9521/0.8977)	mem 34602MB
[2025-01-19 15:17:40 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][170/312]	eta 0:01:47 lr 0.000864	time 0.7254 (0.7546)	model_time 0.7253 (0.7462)	loss 3.3396 (2.9339)	grad_norm 1.4920 (1.9851/0.7884)	mem 34604MB
[2025-01-19 15:17:45 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][190/312]	eta 0:01:32 lr 0.000863	time 0.7336 (0.7561)	model_time 0.7331 (0.7482)	loss 2.8264 (2.8828)	grad_norm 1.2679 (1.9453/0.8867)	mem 34602MB
[2025-01-19 15:17:48 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][180/312]	eta 0:01:39 lr 0.000863	time 0.7160 (0.7531)	model_time 0.7158 (0.7451)	loss 3.0459 (2.9387)	grad_norm 1.2302 (1.9528/0.7798)	mem 34604MB
[2025-01-19 15:17:52 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][200/312]	eta 0:01:24 lr 0.000862	time 0.7167 (0.7552)	model_time 0.7165 (0.7477)	loss 2.3467 (2.8886)	grad_norm 2.4596 (1.9492/0.8802)	mem 34602MB
[2025-01-19 15:17:55 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][190/312]	eta 0:01:31 lr 0.000863	time 0.7191 (0.7515)	model_time 0.7189 (0.7439)	loss 3.0567 (2.9403)	grad_norm 1.4112 (1.9255/0.7718)	mem 34604MB
[2025-01-19 15:17:59 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][210/312]	eta 0:01:16 lr 0.000862	time 0.7172 (0.7546)	model_time 0.7171 (0.7475)	loss 3.0196 (2.9034)	grad_norm 1.0317 (1.9426/0.8786)	mem 34602MB
[2025-01-19 15:18:02 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][200/312]	eta 0:01:24 lr 0.000862	time 0.7274 (0.7501)	model_time 0.7269 (0.7429)	loss 3.5825 (2.9408)	grad_norm 3.5024 (1.9143/0.7709)	mem 34604MB
[2025-01-19 15:18:07 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][220/312]	eta 0:01:09 lr 0.000861	time 0.7329 (0.7547)	model_time 0.7328 (0.7479)	loss 3.2032 (2.9087)	grad_norm 1.0312 (1.9387/0.8662)	mem 34602MB
[2025-01-19 15:18:09 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][210/312]	eta 0:01:16 lr 0.000862	time 0.7244 (0.7489)	model_time 0.7243 (0.7420)	loss 1.9172 (2.9236)	grad_norm 1.8312 (1.8918/0.7636)	mem 34604MB
[2025-01-19 15:18:15 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][230/312]	eta 0:01:01 lr 0.000861	time 0.8032 (0.7556)	model_time 0.8030 (0.7490)	loss 3.7352 (2.9191)	grad_norm 1.4555 (1.9301/0.8546)	mem 34602MB
[2025-01-19 15:18:17 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][220/312]	eta 0:01:08 lr 0.000861	time 0.7988 (0.7483)	model_time 0.7983 (0.7417)	loss 3.0279 (2.9307)	grad_norm 1.1177 (1.8694/0.7589)	mem 34604MB
[2025-01-19 15:18:22 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][240/312]	eta 0:00:54 lr 0.000860	time 0.7218 (0.7547)	model_time 0.7216 (0.7484)	loss 2.6672 (2.9193)	grad_norm 2.3268 (1.9143/0.8443)	mem 34602MB
[2025-01-19 15:18:24 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][230/312]	eta 0:01:01 lr 0.000861	time 0.8080 (0.7482)	model_time 0.8078 (0.7419)	loss 3.0254 (2.9384)	grad_norm 3.6512 (1.9209/0.8282)	mem 34604MB
[2025-01-19 15:18:29 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][250/312]	eta 0:00:46 lr 0.000860	time 0.7268 (0.7542)	model_time 0.7264 (0.7481)	loss 3.3885 (2.9238)	grad_norm 1.2056 (1.9290/0.8527)	mem 34602MB
[2025-01-19 15:18:32 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][240/312]	eta 0:00:53 lr 0.000860	time 0.8346 (0.7487)	model_time 0.8344 (0.7426)	loss 3.0679 (2.9371)	grad_norm 4.4683 (1.9360/0.8498)	mem 34604MB
[2025-01-19 15:18:37 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][260/312]	eta 0:00:39 lr 0.000859	time 0.7249 (0.7541)	model_time 0.7247 (0.7483)	loss 3.2732 (2.9294)	grad_norm 2.4701 (1.9461/0.8624)	mem 34602MB
[2025-01-19 15:18:39 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][250/312]	eta 0:00:46 lr 0.000860	time 0.7602 (0.7486)	model_time 0.7600 (0.7427)	loss 2.8651 (2.9450)	grad_norm 3.5138 (1.9544/0.8582)	mem 34604MB
[2025-01-19 15:18:44 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][270/312]	eta 0:00:31 lr 0.000858	time 0.7156 (0.7533)	model_time 0.7154 (0.7477)	loss 3.3473 (2.9258)	grad_norm 1.4667 (1.9433/0.8540)	mem 34602MB
[2025-01-19 15:18:47 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][260/312]	eta 0:00:38 lr 0.000859	time 0.7168 (0.7498)	model_time 0.7166 (0.7442)	loss 2.7331 (2.9383)	grad_norm 3.0736 (1.9641/0.8551)	mem 34604MB
[2025-01-19 15:18:52 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][280/312]	eta 0:00:24 lr 0.000858	time 0.7160 (0.7530)	model_time 0.7155 (0.7475)	loss 2.6748 (2.9293)	grad_norm 1.5404 (1.9568/0.8619)	mem 34602MB
[2025-01-19 15:18:54 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][270/312]	eta 0:00:31 lr 0.000858	time 0.7168 (0.7495)	model_time 0.7166 (0.7441)	loss 2.9170 (2.9324)	grad_norm 1.7593 (1.9687/0.8506)	mem 34604MB
[2025-01-19 15:18:59 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][290/312]	eta 0:00:16 lr 0.000857	time 0.8118 (0.7527)	model_time 0.8116 (0.7475)	loss 1.9578 (2.9320)	grad_norm 2.1442 (1.9456/0.8566)	mem 34602MB
[2025-01-19 15:19:02 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][280/312]	eta 0:00:23 lr 0.000858	time 0.7161 (0.7494)	model_time 0.7159 (0.7441)	loss 2.0308 (2.9295)	grad_norm 1.2442 (1.9501/0.8444)	mem 34604MB
[2025-01-19 15:19:06 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][300/312]	eta 0:00:09 lr 0.000857	time 0.7125 (0.7521)	model_time 0.7124 (0.7470)	loss 3.0494 (2.9376)	grad_norm 2.4672 (1.9461/0.8486)	mem 34602MB
[2025-01-19 15:19:09 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][290/312]	eta 0:00:16 lr 0.000857	time 0.7292 (0.7488)	model_time 0.7287 (0.7437)	loss 2.1863 (2.9281)	grad_norm 1.6252 (1.9557/0.8407)	mem 34604MB
[2025-01-19 15:19:14 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][310/312]	eta 0:00:01 lr 0.000856	time 0.7136 (0.7516)	model_time 0.7135 (0.7466)	loss 3.1700 (2.9413)	grad_norm 2.0977 (1.9474/0.8468)	mem 34602MB
[2025-01-19 15:19:15 internimage_b_1k_224] (main.py 519): INFO EPOCH 209 training takes 0:03:54
[2025-01-19 15:19:15 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_209.pth saving......
[2025-01-19 15:19:16 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][300/312]	eta 0:00:08 lr 0.000857	time 0.7142 (0.7479)	model_time 0.7140 (0.7429)	loss 3.4727 (2.9301)	grad_norm 3.0521 (1.9665/0.8370)	mem 34604MB
[2025-01-19 15:19:18 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_209.pth saved !!!
[2025-01-19 15:19:24 internimage_b_1k_224] (main.py 510): INFO Train: [209/300][310/312]	eta 0:00:01 lr 0.000856	time 0.7063 (0.7471)	model_time 0.7061 (0.7423)	loss 3.7268 (2.9300)	grad_norm 0.9525 (1.9398/0.8456)	mem 34604MB
[2025-01-19 15:19:24 internimage_b_1k_224] (main.py 519): INFO EPOCH 209 training takes 0:03:53
[2025-01-19 15:19:24 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_209.pth saving......
[2025-01-19 15:19:26 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.269 (8.269)	Loss 0.7136 (0.7136)	Acc@1 84.985 (84.985)	Acc@5 97.583 (97.583)	Mem 34602MB
[2025-01-19 15:19:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_209.pth saved !!!
[2025-01-19 15:19:32 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.321)	Loss 0.9491 (0.8053)	Acc@1 79.761 (83.114)	Acc@5 95.020 (96.518)	Mem 34602MB
[2025-01-19 15:19:33 internimage_b_1k_224] (main.py 575): INFO [Epoch:209] * Acc@1 82.893 Acc@5 96.531
[2025-01-19 15:19:33 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.9%
[2025-01-19 15:19:33 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.94%
[2025-01-19 15:19:42 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.755 (14.755)	Loss 0.7055 (0.7055)	Acc@1 85.571 (85.571)	Acc@5 97.729 (97.729)	Mem 34604MB
[2025-01-19 15:19:50 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.207 (17.207)	Loss 0.7072 (0.7072)	Acc@1 85.571 (85.571)	Acc@5 98.047 (98.047)	Mem 34602MB
[2025-01-19 15:19:51 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (2.096)	Loss 0.9533 (0.8132)	Acc@1 79.541 (83.010)	Acc@5 95.435 (96.491)	Mem 34604MB
[2025-01-19 15:19:51 internimage_b_1k_224] (main.py 575): INFO [Epoch:209] * Acc@1 82.841 Acc@5 96.501
[2025-01-19 15:19:51 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.8%
[2025-01-19 15:19:51 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.88%
[2025-01-19 15:19:58 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.289)	Loss 0.9447 (0.8113)	Acc@1 79.443 (83.339)	Acc@5 95.483 (96.660)	Mem 34602MB
[2025-01-19 15:19:58 internimage_b_1k_224] (main.py 575): INFO [Epoch:209] * Acc@1 83.191 Acc@5 96.705
[2025-01-19 15:19:58 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.2%
[2025-01-19 15:19:58 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:20:02 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:20:02 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.19%
[2025-01-19 15:20:03 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 12.254 (12.254)	Loss 0.7002 (0.7002)	Acc@1 85.718 (85.718)	Acc@5 98.096 (98.096)	Mem 34604MB
[2025-01-19 15:20:04 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][0/312]	eta 0:11:13 lr 0.000856	time 2.1578 (2.1578)	model_time 0.7437 (0.7437)	loss 3.7323 (3.7323)	grad_norm 1.4533 (1.4533/0.0000)	mem 34602MB
[2025-01-19 15:20:08 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.531)	Loss 0.9426 (0.8091)	Acc@1 79.443 (83.347)	Acc@5 95.337 (96.604)	Mem 34604MB
[2025-01-19 15:20:08 internimage_b_1k_224] (main.py 575): INFO [Epoch:209] * Acc@1 83.147 Acc@5 96.657
[2025-01-19 15:20:08 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.1%
[2025-01-19 15:20:08 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:20:11 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:20:11 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.15%
[2025-01-19 15:20:12 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][10/312]	eta 0:04:23 lr 0.000856	time 0.7175 (0.8737)	model_time 0.7173 (0.7449)	loss 2.8132 (2.9917)	grad_norm 1.8503 (2.3332/0.8665)	mem 34602MB
[2025-01-19 15:20:14 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][0/312]	eta 0:11:34 lr 0.000856	time 2.2247 (2.2247)	model_time 0.7534 (0.7534)	loss 2.7669 (2.7669)	grad_norm 1.6663 (1.6663/0.0000)	mem 34604MB
[2025-01-19 15:20:19 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][20/312]	eta 0:03:56 lr 0.000855	time 0.7169 (0.8088)	model_time 0.7168 (0.7411)	loss 3.0967 (3.0848)	grad_norm 1.2627 (2.0756/0.9774)	mem 34602MB
[2025-01-19 15:20:21 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][10/312]	eta 0:04:23 lr 0.000856	time 0.7391 (0.8712)	model_time 0.7389 (0.7371)	loss 2.9388 (2.7985)	grad_norm 1.7701 (1.6253/0.6153)	mem 34604MB
[2025-01-19 15:20:27 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][30/312]	eta 0:03:43 lr 0.000855	time 0.8055 (0.7934)	model_time 0.8051 (0.7474)	loss 3.2236 (3.0007)	grad_norm 2.3688 (2.0921/1.0316)	mem 34602MB
[2025-01-19 15:20:28 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][20/312]	eta 0:03:54 lr 0.000855	time 0.7282 (0.8033)	model_time 0.7280 (0.7329)	loss 2.9279 (2.8806)	grad_norm 1.7364 (1.5834/0.5033)	mem 34604MB
[2025-01-19 15:20:34 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][40/312]	eta 0:03:35 lr 0.000854	time 0.8079 (0.7908)	model_time 0.8077 (0.7560)	loss 3.0172 (3.0101)	grad_norm 2.7958 (2.0925/0.9521)	mem 34602MB
[2025-01-19 15:20:36 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][30/312]	eta 0:03:40 lr 0.000855	time 0.7163 (0.7827)	model_time 0.7161 (0.7348)	loss 2.9842 (2.8183)	grad_norm 2.3160 (1.6872/0.5463)	mem 34604MB
[2025-01-19 15:20:42 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][50/312]	eta 0:03:24 lr 0.000853	time 0.7252 (0.7820)	model_time 0.7251 (0.7539)	loss 2.9745 (3.0006)	grad_norm 1.1754 (2.0935/0.9483)	mem 34602MB
[2025-01-19 15:20:43 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][40/312]	eta 0:03:30 lr 0.000854	time 0.7186 (0.7732)	model_time 0.7181 (0.7369)	loss 2.5455 (2.7896)	grad_norm 2.1884 (1.7115/0.5456)	mem 34604MB
[2025-01-19 15:20:49 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][60/312]	eta 0:03:15 lr 0.000853	time 0.8119 (0.7762)	model_time 0.8115 (0.7527)	loss 3.3950 (2.9834)	grad_norm 2.5127 (2.0497/0.9374)	mem 34602MB
[2025-01-19 15:20:51 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][50/312]	eta 0:03:22 lr 0.000853	time 0.8246 (0.7748)	model_time 0.8244 (0.7456)	loss 3.6178 (2.8467)	grad_norm 1.3359 (1.7101/0.5384)	mem 34604MB
[2025-01-19 15:20:57 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][70/312]	eta 0:03:06 lr 0.000852	time 0.7166 (0.7720)	model_time 0.7162 (0.7517)	loss 2.0393 (2.9510)	grad_norm 2.1231 (2.0110/0.8910)	mem 34602MB
[2025-01-19 15:20:58 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][60/312]	eta 0:03:13 lr 0.000853	time 0.7160 (0.7667)	model_time 0.7157 (0.7422)	loss 1.8947 (2.8435)	grad_norm 3.1074 (1.7816/0.6340)	mem 34604MB
[2025-01-19 15:21:04 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][80/312]	eta 0:02:58 lr 0.000852	time 0.7445 (0.7674)	model_time 0.7441 (0.7496)	loss 3.2365 (2.9235)	grad_norm 1.9497 (1.9892/0.8589)	mem 34602MB
[2025-01-19 15:21:06 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][70/312]	eta 0:03:05 lr 0.000852	time 0.7335 (0.7663)	model_time 0.7333 (0.7452)	loss 3.1698 (2.8388)	grad_norm 1.9610 (1.8175/0.6831)	mem 34604MB
[2025-01-19 15:21:12 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][90/312]	eta 0:02:50 lr 0.000851	time 0.7155 (0.7671)	model_time 0.7153 (0.7512)	loss 3.1198 (2.9413)	grad_norm 1.4426 (1.9965/0.8613)	mem 34602MB
[2025-01-19 15:21:13 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][80/312]	eta 0:02:57 lr 0.000852	time 0.7228 (0.7652)	model_time 0.7226 (0.7467)	loss 3.6115 (2.8360)	grad_norm 0.9888 (1.8060/0.6596)	mem 34604MB
[2025-01-19 15:21:19 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][100/312]	eta 0:02:42 lr 0.000851	time 0.7189 (0.7648)	model_time 0.7185 (0.7504)	loss 3.3588 (2.9323)	grad_norm 1.3166 (1.9676/0.8317)	mem 34602MB
[2025-01-19 15:21:21 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][90/312]	eta 0:02:49 lr 0.000851	time 0.7220 (0.7631)	model_time 0.7215 (0.7465)	loss 3.1894 (2.8455)	grad_norm 1.9317 (1.8323/0.6567)	mem 34604MB
[2025-01-19 15:21:27 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][110/312]	eta 0:02:33 lr 0.000850	time 0.7274 (0.7618)	model_time 0.7273 (0.7487)	loss 3.4247 (2.9183)	grad_norm 1.7579 (1.9572/0.8300)	mem 34602MB
[2025-01-19 15:21:28 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][100/312]	eta 0:02:41 lr 0.000851	time 0.7264 (0.7596)	model_time 0.7263 (0.7447)	loss 3.2241 (2.8657)	grad_norm 1.0305 (1.8052/0.6580)	mem 34604MB
[2025-01-19 15:21:34 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][120/312]	eta 0:02:25 lr 0.000850	time 0.7262 (0.7602)	model_time 0.7258 (0.7482)	loss 3.5945 (2.9117)	grad_norm 1.2351 (1.9411/0.8183)	mem 34602MB
[2025-01-19 15:21:35 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][110/312]	eta 0:02:32 lr 0.000850	time 0.7231 (0.7565)	model_time 0.7229 (0.7428)	loss 2.5060 (2.8592)	grad_norm 1.4468 (1.8051/0.6560)	mem 34604MB
[2025-01-19 15:21:41 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][130/312]	eta 0:02:18 lr 0.000849	time 0.7156 (0.7584)	model_time 0.7154 (0.7473)	loss 2.4512 (2.8959)	grad_norm 2.0087 (1.9242/0.8082)	mem 34602MB
[2025-01-19 15:21:43 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][120/312]	eta 0:02:24 lr 0.000850	time 0.7256 (0.7545)	model_time 0.7252 (0.7420)	loss 3.3915 (2.8474)	grad_norm 3.1907 (1.8175/0.6650)	mem 34604MB
[2025-01-19 15:21:49 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][140/312]	eta 0:02:10 lr 0.000849	time 0.8068 (0.7568)	model_time 0.8066 (0.7464)	loss 3.3738 (2.8833)	grad_norm 1.2544 (1.8952/0.7941)	mem 34602MB
[2025-01-19 15:21:50 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][130/312]	eta 0:02:17 lr 0.000849	time 0.7739 (0.7535)	model_time 0.7735 (0.7419)	loss 2.3983 (2.8460)	grad_norm 1.3687 (1.8357/0.7002)	mem 34604MB
[2025-01-19 15:21:56 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][150/312]	eta 0:02:02 lr 0.000848	time 0.8055 (0.7567)	model_time 0.8053 (0.7470)	loss 3.6158 (2.8981)	grad_norm 1.7417 (1.9101/0.7940)	mem 34602MB
[2025-01-19 15:21:57 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][140/312]	eta 0:02:09 lr 0.000849	time 0.7165 (0.7516)	model_time 0.7163 (0.7408)	loss 2.7892 (2.8519)	grad_norm 1.8966 (1.8482/0.6933)	mem 34604MB
[2025-01-19 15:22:04 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][160/312]	eta 0:01:55 lr 0.000848	time 0.7943 (0.7566)	model_time 0.7942 (0.7475)	loss 2.7415 (2.8960)	grad_norm 2.1278 (1.9458/0.7991)	mem 34602MB
[2025-01-19 15:22:05 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][150/312]	eta 0:02:01 lr 0.000848	time 0.7280 (0.7501)	model_time 0.7275 (0.7399)	loss 3.5267 (2.8509)	grad_norm 1.2686 (1.8837/0.7724)	mem 34604MB
[2025-01-19 15:22:11 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][170/312]	eta 0:01:47 lr 0.000847	time 0.7193 (0.7554)	model_time 0.7189 (0.7468)	loss 3.6916 (2.8940)	grad_norm 1.3567 (1.9133/0.7896)	mem 34602MB
[2025-01-19 15:22:12 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][160/312]	eta 0:01:54 lr 0.000848	time 0.7348 (0.7503)	model_time 0.7346 (0.7408)	loss 3.3964 (2.8580)	grad_norm 1.9704 (1.8876/0.7725)	mem 34604MB
[2025-01-19 15:22:19 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][180/312]	eta 0:01:39 lr 0.000847	time 0.7969 (0.7546)	model_time 0.7968 (0.7465)	loss 3.1761 (2.8870)	grad_norm 1.6918 (1.8922/0.7758)	mem 34602MB
[2025-01-19 15:22:20 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][170/312]	eta 0:01:46 lr 0.000847	time 0.8058 (0.7516)	model_time 0.8053 (0.7426)	loss 2.8571 (2.8529)	grad_norm 2.3501 (1.8991/0.7659)	mem 34604MB
[2025-01-19 15:22:26 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][190/312]	eta 0:01:32 lr 0.000846	time 0.7172 (0.7542)	model_time 0.7170 (0.7464)	loss 2.7739 (2.8877)	grad_norm 1.9452 (1.9067/0.7995)	mem 34602MB
[2025-01-19 15:22:27 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][180/312]	eta 0:01:39 lr 0.000847	time 0.7141 (0.7504)	model_time 0.7139 (0.7419)	loss 2.7608 (2.8497)	grad_norm 2.2784 (1.9216/0.7631)	mem 34604MB
[2025-01-19 15:22:33 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][200/312]	eta 0:01:24 lr 0.000845	time 0.7197 (0.7531)	model_time 0.7192 (0.7457)	loss 3.2179 (2.8918)	grad_norm 1.2338 (1.9472/0.8347)	mem 34602MB
[2025-01-19 15:22:35 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][190/312]	eta 0:01:31 lr 0.000846	time 0.7172 (0.7513)	model_time 0.7167 (0.7432)	loss 3.0962 (2.8574)	grad_norm 3.4481 (1.9142/0.7636)	mem 34604MB
[2025-01-19 15:22:41 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][210/312]	eta 0:01:16 lr 0.000845	time 0.7257 (0.7523)	model_time 0.7256 (0.7453)	loss 2.7263 (2.8899)	grad_norm 0.9852 (1.9587/0.8537)	mem 34602MB
[2025-01-19 15:22:42 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][200/312]	eta 0:01:24 lr 0.000845	time 0.7180 (0.7517)	model_time 0.7176 (0.7440)	loss 3.0196 (2.8590)	grad_norm 1.7024 (1.9532/0.7844)	mem 34604MB
[2025-01-19 15:22:48 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][220/312]	eta 0:01:09 lr 0.000844	time 0.7246 (0.7516)	model_time 0.7245 (0.7449)	loss 2.4559 (2.8792)	grad_norm 1.7778 (1.9633/0.8543)	mem 34602MB
[2025-01-19 15:22:50 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][210/312]	eta 0:01:16 lr 0.000845	time 0.7414 (0.7516)	model_time 0.7412 (0.7442)	loss 3.5556 (2.8534)	grad_norm 4.5280 (1.9866/0.8175)	mem 34604MB
[2025-01-19 15:22:55 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][230/312]	eta 0:01:01 lr 0.000844	time 0.7379 (0.7512)	model_time 0.7374 (0.7448)	loss 2.8206 (2.8800)	grad_norm 1.8705 (1.9611/0.8438)	mem 34602MB
[2025-01-19 15:22:57 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][220/312]	eta 0:01:09 lr 0.000844	time 0.7248 (0.7506)	model_time 0.7243 (0.7435)	loss 3.1682 (2.8425)	grad_norm 1.0076 (1.9730/0.8081)	mem 34604MB
[2025-01-19 15:23:03 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][240/312]	eta 0:00:54 lr 0.000843	time 0.7193 (0.7509)	model_time 0.7191 (0.7447)	loss 2.3831 (2.8861)	grad_norm 1.9210 (1.9431/0.8331)	mem 34602MB
[2025-01-19 15:23:05 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][230/312]	eta 0:01:01 lr 0.000844	time 0.7274 (0.7495)	model_time 0.7272 (0.7427)	loss 3.5612 (2.8407)	grad_norm 1.9713 (1.9501/0.8013)	mem 34604MB
[2025-01-19 15:23:10 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][250/312]	eta 0:00:46 lr 0.000843	time 0.7240 (0.7505)	model_time 0.7236 (0.7445)	loss 3.1706 (2.8944)	grad_norm 1.6323 (1.9469/0.8299)	mem 34602MB
[2025-01-19 15:23:12 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][240/312]	eta 0:00:53 lr 0.000843	time 0.7191 (0.7484)	model_time 0.7187 (0.7419)	loss 3.1371 (2.8439)	grad_norm 1.2126 (1.9612/0.8095)	mem 34604MB
[2025-01-19 15:23:18 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][260/312]	eta 0:00:38 lr 0.000842	time 0.8019 (0.7498)	model_time 0.8015 (0.7440)	loss 3.1001 (2.8779)	grad_norm 5.1907 (1.9659/0.8643)	mem 34602MB
[2025-01-19 15:23:19 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][250/312]	eta 0:00:46 lr 0.000843	time 0.7403 (0.7479)	model_time 0.7398 (0.7417)	loss 2.0719 (2.8525)	grad_norm 1.4899 (1.9557/0.8039)	mem 34604MB
[2025-01-19 15:23:25 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][270/312]	eta 0:00:31 lr 0.000842	time 0.7988 (0.7502)	model_time 0.7986 (0.7446)	loss 3.1024 (2.8906)	grad_norm 1.4014 (1.9978/0.9096)	mem 34602MB
[2025-01-19 15:23:26 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][260/312]	eta 0:00:38 lr 0.000842	time 0.7219 (0.7472)	model_time 0.7215 (0.7412)	loss 2.5566 (2.8540)	grad_norm 1.0495 (1.9579/0.8098)	mem 34604MB
[2025-01-19 15:23:33 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][280/312]	eta 0:00:24 lr 0.000841	time 0.7907 (0.7504)	model_time 0.7905 (0.7450)	loss 3.0016 (2.8979)	grad_norm 1.1627 (1.9788/0.9028)	mem 34602MB
[2025-01-19 15:23:34 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][270/312]	eta 0:00:31 lr 0.000842	time 0.7223 (0.7467)	model_time 0.7222 (0.7408)	loss 2.3130 (2.8539)	grad_norm 3.5744 (1.9856/0.8378)	mem 34604MB
[2025-01-19 15:23:40 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][290/312]	eta 0:00:16 lr 0.000841	time 0.7297 (0.7504)	model_time 0.7292 (0.7451)	loss 2.0359 (2.8985)	grad_norm 1.6188 (1.9534/0.8982)	mem 34602MB
[2025-01-19 15:23:41 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][280/312]	eta 0:00:23 lr 0.000841	time 0.7422 (0.7468)	model_time 0.7418 (0.7411)	loss 3.4535 (2.8547)	grad_norm 1.2161 (1.9970/0.8381)	mem 34604MB
[2025-01-19 15:23:48 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][300/312]	eta 0:00:09 lr 0.000840	time 0.8128 (0.7502)	model_time 0.8127 (0.7452)	loss 2.9797 (2.8910)	grad_norm 1.2913 (1.9287/0.8960)	mem 34602MB
[2025-01-19 15:23:49 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][290/312]	eta 0:00:16 lr 0.000841	time 0.8120 (0.7477)	model_time 0.8119 (0.7423)	loss 3.3378 (2.8670)	grad_norm 1.7637 (1.9889/0.8279)	mem 34604MB
[2025-01-19 15:23:55 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][310/312]	eta 0:00:01 lr 0.000840	time 0.7243 (0.7496)	model_time 0.7242 (0.7447)	loss 1.7485 (2.8834)	grad_norm 2.1279 (1.9243/0.8959)	mem 34602MB
[2025-01-19 15:23:56 internimage_b_1k_224] (main.py 519): INFO EPOCH 210 training takes 0:03:54
[2025-01-19 15:23:56 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_210.pth saving......
[2025-01-19 15:23:56 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][300/312]	eta 0:00:08 lr 0.000840	time 0.7169 (0.7473)	model_time 0.7168 (0.7420)	loss 2.9193 (2.8700)	grad_norm 3.2206 (1.9793/0.8252)	mem 34604MB
[2025-01-19 15:23:59 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_210.pth saved !!!
[2025-01-19 15:24:04 internimage_b_1k_224] (main.py 510): INFO Train: [210/300][310/312]	eta 0:00:01 lr 0.000840	time 0.7941 (0.7484)	model_time 0.7939 (0.7433)	loss 2.1802 (2.8745)	grad_norm 1.2451 (1.9824/0.8223)	mem 34604MB
[2025-01-19 15:24:05 internimage_b_1k_224] (main.py 519): INFO EPOCH 210 training takes 0:03:53
[2025-01-19 15:24:05 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_210.pth saving......
[2025-01-19 15:24:08 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_210.pth saved !!!
[2025-01-19 15:24:08 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.058 (9.058)	Loss 0.7313 (0.7313)	Acc@1 85.034 (85.034)	Acc@5 97.681 (97.681)	Mem 34602MB
[2025-01-19 15:24:15 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.387)	Loss 0.9669 (0.8279)	Acc@1 78.662 (82.868)	Acc@5 95.435 (96.564)	Mem 34602MB
[2025-01-19 15:24:15 internimage_b_1k_224] (main.py 575): INFO [Epoch:210] * Acc@1 82.708 Acc@5 96.585
[2025-01-19 15:24:15 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.7%
[2025-01-19 15:24:15 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.94%
[2025-01-19 15:24:23 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.789 (14.789)	Loss 0.7182 (0.7182)	Acc@1 85.547 (85.547)	Acc@5 97.583 (97.583)	Mem 34604MB
[2025-01-19 15:24:31 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.044)	Loss 0.9730 (0.8363)	Acc@1 78.223 (83.099)	Acc@5 95.679 (96.553)	Mem 34604MB
[2025-01-19 15:24:31 internimage_b_1k_224] (main.py 575): INFO [Epoch:210] * Acc@1 82.947 Acc@5 96.581
[2025-01-19 15:24:31 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.9%
[2025-01-19 15:24:31 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 15:24:32 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.044 (17.044)	Loss 0.7081 (0.7081)	Acc@1 85.596 (85.596)	Acc@5 98.071 (98.071)	Mem 34602MB
[2025-01-19 15:24:34 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 15:24:34 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.95%
[2025-01-19 15:24:41 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.384)	Loss 0.9444 (0.8116)	Acc@1 79.492 (83.354)	Acc@5 95.483 (96.669)	Mem 34602MB
[2025-01-19 15:24:41 internimage_b_1k_224] (main.py 575): INFO [Epoch:210] * Acc@1 83.201 Acc@5 96.713
[2025-01-19 15:24:41 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.2%
[2025-01-19 15:24:41 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:24:45 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 10.771 (10.771)	Loss 0.7007 (0.7007)	Acc@1 85.767 (85.767)	Acc@5 98.096 (98.096)	Mem 34604MB
[2025-01-19 15:24:45 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:24:45 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.20%
[2025-01-19 15:24:47 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][0/312]	eta 0:11:32 lr 0.000839	time 2.2184 (2.2184)	model_time 0.7434 (0.7434)	loss 2.5491 (2.5491)	grad_norm 1.5063 (1.5063/0.0000)	mem 34602MB
[2025-01-19 15:24:49 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.319)	Loss 0.9424 (0.8092)	Acc@1 79.492 (83.367)	Acc@5 95.337 (96.624)	Mem 34604MB
[2025-01-19 15:24:49 internimage_b_1k_224] (main.py 575): INFO [Epoch:210] * Acc@1 83.171 Acc@5 96.677
[2025-01-19 15:24:49 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.2%
[2025-01-19 15:24:49 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:24:53 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:24:53 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.17%
[2025-01-19 15:24:55 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][10/312]	eta 0:04:23 lr 0.000839	time 0.7276 (0.8719)	model_time 0.7274 (0.7375)	loss 3.6447 (2.7771)	grad_norm 1.7252 (2.0386/0.8412)	mem 34602MB
[2025-01-19 15:24:55 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][0/312]	eta 0:11:30 lr 0.000839	time 2.2136 (2.2136)	model_time 0.7346 (0.7346)	loss 3.2005 (3.2005)	grad_norm 1.0032 (1.0032/0.0000)	mem 34604MB
[2025-01-19 15:25:02 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][20/312]	eta 0:03:55 lr 0.000838	time 0.7207 (0.8072)	model_time 0.7205 (0.7366)	loss 3.7104 (2.9098)	grad_norm 1.3987 (1.7834/0.7046)	mem 34602MB
[2025-01-19 15:25:03 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][10/312]	eta 0:04:28 lr 0.000839	time 0.7291 (0.8905)	model_time 0.7289 (0.7557)	loss 3.1017 (2.9275)	grad_norm 1.3325 (2.3746/0.9276)	mem 34604MB
[2025-01-19 15:25:09 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][30/312]	eta 0:03:42 lr 0.000838	time 0.7212 (0.7896)	model_time 0.7210 (0.7417)	loss 2.2099 (2.8917)	grad_norm 2.3980 (1.7967/0.6423)	mem 34602MB
[2025-01-19 15:25:10 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][20/312]	eta 0:03:59 lr 0.000838	time 0.7166 (0.8218)	model_time 0.7164 (0.7511)	loss 2.9266 (2.9230)	grad_norm 1.2011 (2.0392/0.7943)	mem 34604MB
[2025-01-19 15:25:17 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][40/312]	eta 0:03:31 lr 0.000837	time 0.7432 (0.7771)	model_time 0.7430 (0.7408)	loss 3.0666 (2.9031)	grad_norm 2.1388 (1.8483/0.6408)	mem 34602MB
[2025-01-19 15:25:17 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][30/312]	eta 0:03:43 lr 0.000838	time 0.7290 (0.7921)	model_time 0.7288 (0.7441)	loss 3.0351 (2.9419)	grad_norm 1.0264 (1.9161/0.7197)	mem 34604MB
[2025-01-19 15:25:24 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][50/312]	eta 0:03:22 lr 0.000837	time 0.7232 (0.7710)	model_time 0.7227 (0.7418)	loss 3.1446 (2.9262)	grad_norm 4.6649 (1.9279/0.7373)	mem 34602MB
[2025-01-19 15:25:25 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][40/312]	eta 0:03:31 lr 0.000837	time 0.7498 (0.7761)	model_time 0.7494 (0.7397)	loss 3.2312 (2.9257)	grad_norm 1.6976 (1.8461/0.6713)	mem 34604MB
[2025-01-19 15:25:32 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][60/312]	eta 0:03:12 lr 0.000836	time 0.7199 (0.7646)	model_time 0.7198 (0.7401)	loss 2.6072 (2.8967)	grad_norm 1.6216 (1.9845/0.7722)	mem 34602MB
[2025-01-19 15:25:32 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][50/312]	eta 0:03:20 lr 0.000837	time 0.7160 (0.7670)	model_time 0.7158 (0.7376)	loss 2.9815 (2.9154)	grad_norm 1.4199 (1.7557/0.6394)	mem 34604MB
[2025-01-19 15:25:39 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][70/312]	eta 0:03:03 lr 0.000836	time 0.7199 (0.7599)	model_time 0.7194 (0.7388)	loss 3.6480 (2.9007)	grad_norm 2.2435 (2.0372/0.7703)	mem 34602MB
[2025-01-19 15:25:39 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][60/312]	eta 0:03:11 lr 0.000836	time 0.7298 (0.7604)	model_time 0.7297 (0.7358)	loss 2.5031 (2.9115)	grad_norm 2.3545 (1.8011/0.6831)	mem 34604MB
[2025-01-19 15:25:46 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][80/312]	eta 0:02:55 lr 0.000835	time 0.7363 (0.7576)	model_time 0.7361 (0.7390)	loss 3.6625 (2.9236)	grad_norm 2.6165 (1.9861/0.7563)	mem 34602MB
[2025-01-19 15:25:46 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][70/312]	eta 0:03:03 lr 0.000836	time 0.7196 (0.7570)	model_time 0.7194 (0.7358)	loss 3.2451 (2.9421)	grad_norm 5.3686 (1.9249/0.8241)	mem 34604MB
[2025-01-19 15:25:54 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][80/312]	eta 0:02:54 lr 0.000835	time 0.7302 (0.7534)	model_time 0.7300 (0.7347)	loss 2.8667 (2.9134)	grad_norm 3.2943 (2.0465/0.9096)	mem 34604MB
[2025-01-19 15:25:54 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][90/312]	eta 0:02:48 lr 0.000835	time 0.7170 (0.7577)	model_time 0.7169 (0.7412)	loss 3.2815 (2.9389)	grad_norm 1.4969 (2.0428/0.7858)	mem 34602MB
[2025-01-19 15:26:01 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][90/312]	eta 0:02:47 lr 0.000835	time 0.7185 (0.7523)	model_time 0.7180 (0.7357)	loss 1.9966 (2.8901)	grad_norm 1.2033 (2.0321/0.8938)	mem 34604MB
[2025-01-19 15:26:01 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][100/312]	eta 0:02:40 lr 0.000834	time 0.7745 (0.7568)	model_time 0.7744 (0.7418)	loss 1.8987 (2.9302)	grad_norm 1.4571 (2.0015/0.7734)	mem 34602MB
[2025-01-19 15:26:09 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][110/312]	eta 0:02:32 lr 0.000834	time 0.7230 (0.7554)	model_time 0.7228 (0.7418)	loss 3.5707 (2.9504)	grad_norm 3.6626 (2.0244/0.7986)	mem 34602MB
[2025-01-19 15:26:09 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][100/312]	eta 0:02:40 lr 0.000834	time 0.8070 (0.7561)	model_time 0.8069 (0.7411)	loss 2.5800 (2.8420)	grad_norm 1.2429 (1.9866/0.8749)	mem 34604MB
[2025-01-19 15:26:17 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][110/312]	eta 0:02:32 lr 0.000834	time 0.8288 (0.7547)	model_time 0.8283 (0.7410)	loss 3.0864 (2.8606)	grad_norm 1.7506 (1.9356/0.8607)	mem 34604MB
[2025-01-19 15:26:17 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][120/312]	eta 0:02:25 lr 0.000833	time 0.8044 (0.7563)	model_time 0.8042 (0.7438)	loss 3.1755 (2.9423)	grad_norm 1.6109 (1.9955/0.7990)	mem 34602MB
[2025-01-19 15:26:24 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][130/312]	eta 0:02:17 lr 0.000833	time 0.7195 (0.7545)	model_time 0.7193 (0.7429)	loss 2.7592 (2.9367)	grad_norm 1.6963 (1.9772/0.7859)	mem 34602MB
[2025-01-19 15:26:25 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][120/312]	eta 0:02:25 lr 0.000833	time 0.7181 (0.7585)	model_time 0.7176 (0.7459)	loss 3.0263 (2.8651)	grad_norm 1.9660 (1.9419/0.8687)	mem 34604MB
[2025-01-19 15:26:31 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][140/312]	eta 0:02:09 lr 0.000832	time 0.7188 (0.7535)	model_time 0.7186 (0.7428)	loss 3.4062 (2.9241)	grad_norm 1.8644 (1.9653/0.7733)	mem 34602MB
[2025-01-19 15:26:32 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][130/312]	eta 0:02:18 lr 0.000833	time 0.7226 (0.7594)	model_time 0.7221 (0.7477)	loss 2.7495 (2.8744)	grad_norm 2.0355 (1.9474/0.8805)	mem 34604MB
[2025-01-19 15:26:39 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][150/312]	eta 0:02:02 lr 0.000831	time 0.7158 (0.7535)	model_time 0.7154 (0.7434)	loss 2.8017 (2.9062)	grad_norm 4.1068 (1.9660/0.7785)	mem 34602MB
[2025-01-19 15:26:40 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][140/312]	eta 0:02:10 lr 0.000832	time 0.7416 (0.7585)	model_time 0.7414 (0.7476)	loss 2.5705 (2.8878)	grad_norm 0.7897 (1.9311/0.8626)	mem 34604MB
[2025-01-19 15:26:46 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][160/312]	eta 0:01:54 lr 0.000831	time 0.7213 (0.7524)	model_time 0.7211 (0.7429)	loss 3.1860 (2.9206)	grad_norm 1.1373 (1.9228/0.7759)	mem 34602MB
[2025-01-19 15:26:47 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][150/312]	eta 0:02:02 lr 0.000831	time 0.7210 (0.7565)	model_time 0.7208 (0.7463)	loss 2.2876 (2.8961)	grad_norm 1.4899 (1.9579/0.8662)	mem 34604MB
[2025-01-19 15:26:54 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][170/312]	eta 0:01:46 lr 0.000830	time 0.7205 (0.7523)	model_time 0.7201 (0.7433)	loss 2.9081 (2.9126)	grad_norm 1.9006 (1.9200/0.7609)	mem 34602MB
[2025-01-19 15:26:54 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][160/312]	eta 0:01:54 lr 0.000831	time 0.7385 (0.7546)	model_time 0.7383 (0.7450)	loss 3.1581 (2.9006)	grad_norm 2.4940 (1.9763/0.8723)	mem 34604MB
[2025-01-19 15:27:01 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][180/312]	eta 0:01:39 lr 0.000830	time 0.7175 (0.7514)	model_time 0.7174 (0.7429)	loss 2.7695 (2.9132)	grad_norm 2.0241 (1.9381/0.7573)	mem 34602MB
[2025-01-19 15:27:01 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][170/312]	eta 0:01:46 lr 0.000830	time 0.7226 (0.7528)	model_time 0.7220 (0.7438)	loss 3.5685 (2.8893)	grad_norm 1.1637 (1.9494/0.8658)	mem 34604MB
[2025-01-19 15:27:08 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][190/312]	eta 0:01:31 lr 0.000829	time 0.7112 (0.7505)	model_time 0.7108 (0.7425)	loss 3.1938 (2.9077)	grad_norm 2.2789 (1.9493/0.7580)	mem 34602MB
[2025-01-19 15:27:09 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][180/312]	eta 0:01:39 lr 0.000830	time 0.7491 (0.7516)	model_time 0.7490 (0.7430)	loss 2.6779 (2.8920)	grad_norm 1.4424 (1.9198/0.8556)	mem 34604MB
[2025-01-19 15:27:16 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][200/312]	eta 0:01:24 lr 0.000829	time 0.7196 (0.7504)	model_time 0.7194 (0.7427)	loss 2.2496 (2.9088)	grad_norm 3.8827 (1.9922/0.7986)	mem 34602MB
[2025-01-19 15:27:16 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][190/312]	eta 0:01:31 lr 0.000829	time 0.7186 (0.7506)	model_time 0.7184 (0.7425)	loss 2.7791 (2.8904)	grad_norm 2.8336 (1.9670/0.8750)	mem 34604MB
[2025-01-19 15:27:23 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][210/312]	eta 0:01:16 lr 0.000828	time 0.7173 (0.7505)	model_time 0.7169 (0.7431)	loss 3.3663 (2.9087)	grad_norm 0.8384 (1.9675/0.7922)	mem 34602MB
[2025-01-19 15:27:23 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][200/312]	eta 0:01:23 lr 0.000829	time 0.7271 (0.7497)	model_time 0.7269 (0.7419)	loss 1.9223 (2.8864)	grad_norm 2.2176 (2.0071/0.9211)	mem 34604MB
[2025-01-19 15:27:31 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][210/312]	eta 0:01:16 lr 0.000828	time 0.7222 (0.7495)	model_time 0.7218 (0.7421)	loss 3.3588 (2.8848)	grad_norm 1.8782 (2.0137/0.9202)	mem 34604MB
[2025-01-19 15:27:31 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][220/312]	eta 0:01:09 lr 0.000828	time 0.8125 (0.7507)	model_time 0.8121 (0.7437)	loss 3.1966 (2.9136)	grad_norm 2.0649 (1.9442/0.7860)	mem 34602MB
[2025-01-19 15:27:38 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][230/312]	eta 0:01:01 lr 0.000827	time 0.7301 (0.7500)	model_time 0.7299 (0.7432)	loss 3.3472 (2.9095)	grad_norm 2.7843 (1.9405/0.7768)	mem 34602MB
[2025-01-19 15:27:39 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][220/312]	eta 0:01:09 lr 0.000828	time 0.8103 (0.7521)	model_time 0.8101 (0.7451)	loss 2.6770 (2.8825)	grad_norm 1.6673 (2.0037/0.9027)	mem 34604MB
[2025-01-19 15:27:46 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][240/312]	eta 0:00:54 lr 0.000827	time 0.8072 (0.7506)	model_time 0.8071 (0.7441)	loss 3.3152 (2.9097)	grad_norm 2.4715 (1.9471/0.7688)	mem 34602MB
[2025-01-19 15:27:46 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][230/312]	eta 0:01:01 lr 0.000827	time 0.8161 (0.7520)	model_time 0.8159 (0.7452)	loss 2.9594 (2.8820)	grad_norm 2.0315 (2.0109/0.8988)	mem 34604MB
[2025-01-19 15:27:53 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][250/312]	eta 0:00:46 lr 0.000826	time 0.7348 (0.7496)	model_time 0.7346 (0.7434)	loss 3.4107 (2.9209)	grad_norm 1.0785 (1.9311/0.7648)	mem 34602MB
[2025-01-19 15:27:54 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][240/312]	eta 0:00:54 lr 0.000827	time 0.7134 (0.7524)	model_time 0.7132 (0.7459)	loss 3.0999 (2.8842)	grad_norm 2.2323 (2.0322/0.9017)	mem 34604MB
[2025-01-19 15:28:01 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][260/312]	eta 0:00:38 lr 0.000826	time 0.7164 (0.7495)	model_time 0.7162 (0.7434)	loss 2.5602 (2.9170)	grad_norm 1.7243 (1.9040/0.7641)	mem 34602MB
[2025-01-19 15:28:02 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][250/312]	eta 0:00:46 lr 0.000826	time 0.8076 (0.7537)	model_time 0.8074 (0.7474)	loss 3.4030 (2.8761)	grad_norm 1.7334 (2.0290/0.8902)	mem 34604MB
[2025-01-19 15:28:08 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][270/312]	eta 0:00:31 lr 0.000825	time 0.7150 (0.7496)	model_time 0.7145 (0.7438)	loss 2.1960 (2.9203)	grad_norm 2.1731 (1.8916/0.7575)	mem 34602MB
[2025-01-19 15:28:09 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][260/312]	eta 0:00:39 lr 0.000826	time 0.7270 (0.7529)	model_time 0.7269 (0.7469)	loss 3.1136 (2.8802)	grad_norm 3.0846 (2.0190/0.8856)	mem 34604MB
[2025-01-19 15:28:16 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][280/312]	eta 0:00:23 lr 0.000825	time 0.7325 (0.7491)	model_time 0.7324 (0.7435)	loss 2.4556 (2.9258)	grad_norm 3.0256 (1.8943/0.7545)	mem 34602MB
[2025-01-19 15:28:17 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][270/312]	eta 0:00:31 lr 0.000825	time 0.7218 (0.7522)	model_time 0.7213 (0.7463)	loss 3.2045 (2.8823)	grad_norm 1.1206 (2.0091/0.8757)	mem 34604MB
[2025-01-19 15:28:23 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][290/312]	eta 0:00:16 lr 0.000824	time 0.7238 (0.7489)	model_time 0.7236 (0.7435)	loss 2.3598 (2.9206)	grad_norm 3.4346 (1.9110/0.7575)	mem 34602MB
[2025-01-19 15:28:24 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][280/312]	eta 0:00:24 lr 0.000825	time 0.7187 (0.7514)	model_time 0.7186 (0.7458)	loss 2.0214 (2.8739)	grad_norm 1.6262 (1.9918/0.8715)	mem 34604MB
[2025-01-19 15:28:30 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][300/312]	eta 0:00:08 lr 0.000824	time 0.7136 (0.7486)	model_time 0.7135 (0.7433)	loss 2.4303 (2.9250)	grad_norm 1.8035 (1.9051/0.7550)	mem 34602MB
[2025-01-19 15:28:31 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][290/312]	eta 0:00:16 lr 0.000824	time 0.7187 (0.7506)	model_time 0.7185 (0.7451)	loss 2.3266 (2.8715)	grad_norm 1.2323 (1.9836/0.8636)	mem 34604MB
[2025-01-19 15:28:38 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][310/312]	eta 0:00:01 lr 0.000823	time 0.7175 (0.7480)	model_time 0.7174 (0.7429)	loss 2.9145 (2.9265)	grad_norm 1.5013 (1.9084/0.7550)	mem 34602MB
[2025-01-19 15:28:38 internimage_b_1k_224] (main.py 519): INFO EPOCH 211 training takes 0:03:53
[2025-01-19 15:28:38 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_211.pth saving......
[2025-01-19 15:28:38 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][300/312]	eta 0:00:08 lr 0.000824	time 0.7108 (0.7496)	model_time 0.7107 (0.7443)	loss 1.8616 (2.8692)	grad_norm 2.9690 (2.0078/0.8731)	mem 34604MB
[2025-01-19 15:28:41 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_211.pth saved !!!
[2025-01-19 15:28:46 internimage_b_1k_224] (main.py 510): INFO Train: [211/300][310/312]	eta 0:00:01 lr 0.000823	time 0.7181 (0.7490)	model_time 0.7180 (0.7438)	loss 2.9651 (2.8748)	grad_norm 1.6228 (1.9839/0.8578)	mem 34604MB
[2025-01-19 15:28:46 internimage_b_1k_224] (main.py 519): INFO EPOCH 211 training takes 0:03:53
[2025-01-19 15:28:46 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_211.pth saving......
[2025-01-19 15:28:50 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_211.pth saved !!!
[2025-01-19 15:28:52 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 10.232 (10.232)	Loss 0.7157 (0.7157)	Acc@1 84.961 (84.961)	Acc@5 97.827 (97.827)	Mem 34602MB
[2025-01-19 15:28:58 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.186 (1.469)	Loss 0.9357 (0.8100)	Acc@1 79.248 (83.132)	Acc@5 95.337 (96.535)	Mem 34602MB
[2025-01-19 15:28:58 internimage_b_1k_224] (main.py 575): INFO [Epoch:211] * Acc@1 83.003 Acc@5 96.553
[2025-01-19 15:28:58 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.0%
[2025-01-19 15:28:58 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 15:29:01 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 15:29:01 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.00%
[2025-01-19 15:29:04 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.612 (14.612)	Loss 0.7236 (0.7236)	Acc@1 85.254 (85.254)	Acc@5 97.729 (97.729)	Mem 34604MB
[2025-01-19 15:29:12 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.046)	Loss 0.9478 (0.8264)	Acc@1 79.395 (83.145)	Acc@5 95.410 (96.471)	Mem 34604MB
[2025-01-19 15:29:12 internimage_b_1k_224] (main.py 575): INFO [Epoch:211] * Acc@1 82.943 Acc@5 96.487
[2025-01-19 15:29:12 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.9%
[2025-01-19 15:29:12 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 82.95%
[2025-01-19 15:29:17 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.768 (15.768)	Loss 0.7089 (0.7089)	Acc@1 85.596 (85.596)	Acc@5 98.096 (98.096)	Mem 34602MB
[2025-01-19 15:29:24 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.109)	Loss 0.9442 (0.8118)	Acc@1 79.541 (83.383)	Acc@5 95.483 (96.664)	Mem 34602MB
[2025-01-19 15:29:25 internimage_b_1k_224] (main.py 575): INFO [Epoch:211] * Acc@1 83.223 Acc@5 96.711
[2025-01-19 15:29:25 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.2%
[2025-01-19 15:29:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:29:27 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.454 (14.454)	Loss 0.7012 (0.7012)	Acc@1 85.767 (85.767)	Acc@5 98.120 (98.120)	Mem 34604MB
[2025-01-19 15:29:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:29:28 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.22%
[2025-01-19 15:29:30 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][0/312]	eta 0:11:12 lr 0.000823	time 2.1570 (2.1570)	model_time 0.7626 (0.7626)	loss 3.3609 (3.3609)	grad_norm 1.6131 (1.6131/0.0000)	mem 34602MB
[2025-01-19 15:29:31 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (1.733)	Loss 0.9421 (0.8094)	Acc@1 79.395 (83.385)	Acc@5 95.337 (96.631)	Mem 34604MB
[2025-01-19 15:29:32 internimage_b_1k_224] (main.py 575): INFO [Epoch:211] * Acc@1 83.185 Acc@5 96.679
[2025-01-19 15:29:32 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.2%
[2025-01-19 15:29:32 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:29:35 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:29:35 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.19%
[2025-01-19 15:29:37 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][0/312]	eta 0:11:19 lr 0.000823	time 2.1771 (2.1771)	model_time 0.7536 (0.7536)	loss 2.2228 (2.2228)	grad_norm 1.2643 (1.2643/0.0000)	mem 34604MB
[2025-01-19 15:29:38 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][10/312]	eta 0:04:28 lr 0.000822	time 0.7191 (0.8880)	model_time 0.7189 (0.7609)	loss 3.1297 (2.9330)	grad_norm 1.1757 (1.6178/0.3527)	mem 34602MB
[2025-01-19 15:29:45 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][10/312]	eta 0:04:22 lr 0.000822	time 0.8509 (0.8698)	model_time 0.8504 (0.7401)	loss 2.1959 (2.5853)	grad_norm 1.5724 (1.8750/0.6027)	mem 34604MB
[2025-01-19 15:29:46 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][20/312]	eta 0:04:00 lr 0.000822	time 0.7172 (0.8246)	model_time 0.7170 (0.7579)	loss 3.2988 (2.9994)	grad_norm 1.4347 (1.6049/0.3285)	mem 34602MB
[2025-01-19 15:29:52 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][20/312]	eta 0:03:56 lr 0.000822	time 0.7326 (0.8106)	model_time 0.7324 (0.7425)	loss 2.9393 (2.7010)	grad_norm 2.9372 (1.8734/0.6222)	mem 34604MB
[2025-01-19 15:29:53 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][30/312]	eta 0:03:45 lr 0.000821	time 0.7187 (0.8006)	model_time 0.7182 (0.7553)	loss 2.7969 (2.9832)	grad_norm 2.5840 (1.6602/0.4081)	mem 34602MB
[2025-01-19 15:30:00 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][30/312]	eta 0:03:46 lr 0.000821	time 0.8337 (0.8037)	model_time 0.8335 (0.7575)	loss 2.4757 (2.6856)	grad_norm 1.5593 (2.2020/1.0529)	mem 34604MB
[2025-01-19 15:30:01 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][40/312]	eta 0:03:34 lr 0.000821	time 0.7191 (0.7885)	model_time 0.7189 (0.7542)	loss 2.1587 (2.9407)	grad_norm 1.4817 (1.7854/0.6637)	mem 34602MB
[2025-01-19 15:30:07 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][40/312]	eta 0:03:34 lr 0.000821	time 0.7396 (0.7893)	model_time 0.7393 (0.7542)	loss 3.2344 (2.7722)	grad_norm 1.6270 (2.4225/1.3042)	mem 34604MB
[2025-01-19 15:30:08 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][50/312]	eta 0:03:24 lr 0.000820	time 0.7174 (0.7822)	model_time 0.7173 (0.7545)	loss 3.1349 (2.9575)	grad_norm 0.9155 (1.8521/0.7385)	mem 34602MB
[2025-01-19 15:30:15 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][50/312]	eta 0:03:24 lr 0.000820	time 0.7195 (0.7814)	model_time 0.7192 (0.7531)	loss 3.0442 (2.8143)	grad_norm 0.8425 (2.3269/1.2576)	mem 34604MB
[2025-01-19 15:30:16 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][60/312]	eta 0:03:15 lr 0.000820	time 0.7187 (0.7744)	model_time 0.7186 (0.7512)	loss 2.3020 (2.9735)	grad_norm 3.7160 (1.8811/0.7409)	mem 34602MB
[2025-01-19 15:30:23 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][60/312]	eta 0:03:16 lr 0.000820	time 0.7215 (0.7800)	model_time 0.7209 (0.7563)	loss 3.0650 (2.8412)	grad_norm 2.0756 (2.2672/1.1914)	mem 34604MB
[2025-01-19 15:30:23 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][70/312]	eta 0:03:06 lr 0.000819	time 0.7173 (0.7705)	model_time 0.7171 (0.7505)	loss 2.0542 (2.9547)	grad_norm 2.4972 (1.9435/0.7586)	mem 34602MB
[2025-01-19 15:30:30 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][70/312]	eta 0:03:07 lr 0.000819	time 0.7164 (0.7746)	model_time 0.7162 (0.7541)	loss 2.9565 (2.7916)	grad_norm 1.5251 (2.1675/1.1389)	mem 34604MB
[2025-01-19 15:30:31 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][80/312]	eta 0:02:58 lr 0.000819	time 0.7170 (0.7683)	model_time 0.7168 (0.7508)	loss 3.1054 (2.9221)	grad_norm 2.4116 (1.9906/0.7486)	mem 34602MB
[2025-01-19 15:30:37 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][80/312]	eta 0:02:58 lr 0.000819	time 0.7195 (0.7687)	model_time 0.7193 (0.7507)	loss 1.7709 (2.7730)	grad_norm 1.6767 (2.1511/1.0902)	mem 34604MB
[2025-01-19 15:30:38 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][90/312]	eta 0:02:49 lr 0.000818	time 0.7234 (0.7645)	model_time 0.7232 (0.7488)	loss 2.6907 (2.9387)	grad_norm 1.0291 (1.9716/0.7438)	mem 34602MB
[2025-01-19 15:30:45 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][90/312]	eta 0:02:49 lr 0.000818	time 0.7231 (0.7640)	model_time 0.7229 (0.7480)	loss 3.4732 (2.7523)	grad_norm 1.3928 (2.1121/1.0474)	mem 34604MB
[2025-01-19 15:30:46 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][100/312]	eta 0:02:42 lr 0.000818	time 1.0065 (0.7651)	model_time 1.0063 (0.7510)	loss 2.8867 (2.9497)	grad_norm 1.1693 (1.9380/0.7179)	mem 34602MB
[2025-01-19 15:30:52 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][100/312]	eta 0:02:41 lr 0.000818	time 0.7413 (0.7603)	model_time 0.7411 (0.7458)	loss 3.1085 (2.7754)	grad_norm 3.0333 (2.0395/1.0363)	mem 34604MB
[2025-01-19 15:30:53 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][110/312]	eta 0:02:33 lr 0.000817	time 0.7534 (0.7622)	model_time 0.7532 (0.7493)	loss 3.0497 (2.9379)	grad_norm 2.4386 (1.9243/0.7114)	mem 34602MB
[2025-01-19 15:30:59 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][110/312]	eta 0:02:33 lr 0.000817	time 0.7222 (0.7574)	model_time 0.7220 (0.7442)	loss 2.9600 (2.7992)	grad_norm 2.1988 (2.0330/1.0019)	mem 34604MB
[2025-01-19 15:31:00 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][120/312]	eta 0:02:25 lr 0.000817	time 0.7182 (0.7601)	model_time 0.7180 (0.7482)	loss 2.1316 (2.9258)	grad_norm 2.5601 (1.9300/0.7005)	mem 34602MB
[2025-01-19 15:31:06 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][120/312]	eta 0:02:24 lr 0.000817	time 0.7300 (0.7547)	model_time 0.7299 (0.7425)	loss 3.1451 (2.8131)	grad_norm 1.5092 (2.0115/0.9735)	mem 34604MB
[2025-01-19 15:31:08 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][130/312]	eta 0:02:18 lr 0.000816	time 0.7160 (0.7592)	model_time 0.7159 (0.7482)	loss 3.4030 (2.9204)	grad_norm 1.6788 (1.9012/0.6980)	mem 34602MB
[2025-01-19 15:31:14 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][130/312]	eta 0:02:17 lr 0.000816	time 0.7925 (0.7534)	model_time 0.7919 (0.7421)	loss 2.5588 (2.8141)	grad_norm 3.1109 (2.0111/0.9617)	mem 34604MB
[2025-01-19 15:31:15 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][140/312]	eta 0:02:10 lr 0.000815	time 0.7206 (0.7596)	model_time 0.7201 (0.7493)	loss 2.4660 (2.9164)	grad_norm 0.9229 (1.8477/0.7047)	mem 34602MB
[2025-01-19 15:31:21 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][140/312]	eta 0:02:09 lr 0.000815	time 0.9399 (0.7530)	model_time 0.9397 (0.7425)	loss 2.8546 (2.8174)	grad_norm 0.9390 (2.0457/0.9837)	mem 34604MB
[2025-01-19 15:31:23 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][150/312]	eta 0:02:02 lr 0.000815	time 0.7148 (0.7588)	model_time 0.7146 (0.7492)	loss 2.8647 (2.9066)	grad_norm 2.0381 (1.8728/0.7009)	mem 34602MB
[2025-01-19 15:31:29 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][150/312]	eta 0:02:02 lr 0.000815	time 0.8349 (0.7552)	model_time 0.8344 (0.7454)	loss 3.1429 (2.8270)	grad_norm 2.6814 (2.0435/0.9708)	mem 34604MB
[2025-01-19 15:31:30 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][160/312]	eta 0:01:55 lr 0.000814	time 0.7200 (0.7580)	model_time 0.7198 (0.7489)	loss 2.7621 (2.9168)	grad_norm 1.3704 (1.9112/0.7411)	mem 34602MB
[2025-01-19 15:31:37 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][160/312]	eta 0:01:54 lr 0.000814	time 0.7178 (0.7549)	model_time 0.7173 (0.7456)	loss 2.5192 (2.8330)	grad_norm 2.5220 (2.0811/0.9704)	mem 34604MB
[2025-01-19 15:31:38 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][170/312]	eta 0:01:47 lr 0.000814	time 0.7566 (0.7582)	model_time 0.7561 (0.7497)	loss 1.8460 (2.8954)	grad_norm 2.9757 (1.9351/0.7555)	mem 34602MB
[2025-01-19 15:31:44 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][170/312]	eta 0:01:47 lr 0.000814	time 0.7213 (0.7548)	model_time 0.7207 (0.7461)	loss 2.9065 (2.8409)	grad_norm 4.5511 (2.1239/0.9980)	mem 34604MB
[2025-01-19 15:31:45 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][180/312]	eta 0:01:39 lr 0.000813	time 0.7249 (0.7564)	model_time 0.7243 (0.7484)	loss 2.8839 (2.8907)	grad_norm 1.1942 (1.9298/0.7551)	mem 34602MB
[2025-01-19 15:31:52 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][180/312]	eta 0:01:39 lr 0.000813	time 0.7168 (0.7558)	model_time 0.7166 (0.7475)	loss 2.9730 (2.8451)	grad_norm 2.4822 (2.1576/1.0165)	mem 34604MB
[2025-01-19 15:31:53 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][190/312]	eta 0:01:32 lr 0.000813	time 0.7302 (0.7560)	model_time 0.7301 (0.7484)	loss 2.5779 (2.8920)	grad_norm 1.6947 (1.9753/0.8148)	mem 34602MB
[2025-01-19 15:31:59 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][190/312]	eta 0:01:32 lr 0.000813	time 0.7196 (0.7551)	model_time 0.7191 (0.7472)	loss 3.2689 (2.8616)	grad_norm 1.1120 (2.1015/1.0183)	mem 34604MB
[2025-01-19 15:32:00 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][200/312]	eta 0:01:24 lr 0.000812	time 0.7169 (0.7559)	model_time 0.7165 (0.7486)	loss 3.4837 (2.8949)	grad_norm 1.5273 (1.9712/0.8119)	mem 34602MB
[2025-01-19 15:32:06 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][200/312]	eta 0:01:24 lr 0.000812	time 0.7157 (0.7536)	model_time 0.7155 (0.7461)	loss 2.3333 (2.8649)	grad_norm 0.9127 (2.0638/1.0089)	mem 34604MB
[2025-01-19 15:32:08 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][210/312]	eta 0:01:17 lr 0.000812	time 0.7296 (0.7549)	model_time 0.7295 (0.7480)	loss 2.8530 (2.8990)	grad_norm 1.8060 (1.9507/0.8006)	mem 34602MB
[2025-01-19 15:32:14 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][210/312]	eta 0:01:16 lr 0.000812	time 0.7383 (0.7523)	model_time 0.7381 (0.7452)	loss 2.9815 (2.8655)	grad_norm 1.6668 (2.0541/1.0021)	mem 34604MB
[2025-01-19 15:32:15 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][220/312]	eta 0:01:09 lr 0.000811	time 0.8082 (0.7547)	model_time 0.8081 (0.7481)	loss 3.2735 (2.9099)	grad_norm 4.1482 (1.9728/0.8275)	mem 34602MB
[2025-01-19 15:32:21 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][220/312]	eta 0:01:09 lr 0.000811	time 0.7254 (0.7510)	model_time 0.7249 (0.7442)	loss 2.1352 (2.8638)	grad_norm 2.1550 (2.0312/0.9884)	mem 34604MB
[2025-01-19 15:32:22 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][230/312]	eta 0:01:01 lr 0.000811	time 0.7193 (0.7537)	model_time 0.7191 (0.7473)	loss 2.1294 (2.9173)	grad_norm 1.5027 (1.9690/0.8236)	mem 34602MB
[2025-01-19 15:32:28 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][230/312]	eta 0:01:01 lr 0.000811	time 0.7393 (0.7501)	model_time 0.7391 (0.7436)	loss 3.2527 (2.8709)	grad_norm 1.9033 (2.0294/0.9817)	mem 34604MB
[2025-01-19 15:32:30 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][240/312]	eta 0:00:54 lr 0.000810	time 0.7319 (0.7529)	model_time 0.7314 (0.7468)	loss 1.9474 (2.9111)	grad_norm 2.5948 (1.9656/0.8146)	mem 34602MB
[2025-01-19 15:32:36 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][240/312]	eta 0:00:53 lr 0.000810	time 0.7166 (0.7491)	model_time 0.7161 (0.7428)	loss 2.2865 (2.8772)	grad_norm 0.8227 (2.0228/0.9663)	mem 34604MB
[2025-01-19 15:32:37 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][250/312]	eta 0:00:46 lr 0.000810	time 0.7205 (0.7529)	model_time 0.7203 (0.7470)	loss 3.3685 (2.9182)	grad_norm 2.0349 (1.9626/0.8013)	mem 34602MB
[2025-01-19 15:32:43 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][250/312]	eta 0:00:46 lr 0.000810	time 0.8525 (0.7485)	model_time 0.8523 (0.7424)	loss 3.2719 (2.8754)	grad_norm 2.5038 (2.0139/0.9542)	mem 34604MB
[2025-01-19 15:32:45 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][260/312]	eta 0:00:39 lr 0.000809	time 0.7161 (0.7532)	model_time 0.7159 (0.7475)	loss 2.1907 (2.9179)	grad_norm 2.9333 (1.9923/0.8128)	mem 34602MB
[2025-01-19 15:32:50 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][260/312]	eta 0:00:38 lr 0.000809	time 0.8071 (0.7482)	model_time 0.8069 (0.7424)	loss 2.3385 (2.8808)	grad_norm 2.1758 (2.0266/0.9500)	mem 34604MB
[2025-01-19 15:32:52 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][270/312]	eta 0:00:31 lr 0.000809	time 0.7248 (0.7531)	model_time 0.7246 (0.7476)	loss 3.1788 (2.9192)	grad_norm 1.3260 (1.9753/0.8105)	mem 34602MB
[2025-01-19 15:32:58 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][270/312]	eta 0:00:31 lr 0.000809	time 0.8367 (0.7494)	model_time 0.8363 (0.7437)	loss 3.1736 (2.8748)	grad_norm 4.1215 (2.0426/0.9446)	mem 34604MB
[2025-01-19 15:33:00 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][280/312]	eta 0:00:24 lr 0.000808	time 0.7222 (0.7526)	model_time 0.7220 (0.7473)	loss 2.4019 (2.9120)	grad_norm 4.3260 (1.9763/0.8145)	mem 34602MB
[2025-01-19 15:33:06 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][280/312]	eta 0:00:23 lr 0.000808	time 0.7200 (0.7492)	model_time 0.7196 (0.7437)	loss 2.9899 (2.8783)	grad_norm 1.8007 (2.0441/0.9394)	mem 34604MB
[2025-01-19 15:33:08 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][290/312]	eta 0:00:16 lr 0.000808	time 0.7229 (0.7532)	model_time 0.7228 (0.7481)	loss 2.8154 (2.9216)	grad_norm 2.0812 (1.9672/0.8152)	mem 34602MB
[2025-01-19 15:33:13 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][290/312]	eta 0:00:16 lr 0.000808	time 0.8140 (0.7495)	model_time 0.8138 (0.7443)	loss 3.4063 (2.8881)	grad_norm 2.5013 (2.0345/0.9317)	mem 34604MB
[2025-01-19 15:33:15 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][300/312]	eta 0:00:09 lr 0.000807	time 0.7143 (0.7522)	model_time 0.7142 (0.7472)	loss 2.9150 (2.9176)	grad_norm 1.5963 (1.9549/0.8075)	mem 34602MB
[2025-01-19 15:33:21 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][300/312]	eta 0:00:08 lr 0.000807	time 0.7155 (0.7499)	model_time 0.7154 (0.7448)	loss 3.5680 (2.8922)	grad_norm 0.8028 (2.0280/0.9230)	mem 34604MB
[2025-01-19 15:33:22 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][310/312]	eta 0:00:01 lr 0.000807	time 0.7142 (0.7520)	model_time 0.7141 (0.7472)	loss 3.3760 (2.9092)	grad_norm 1.5624 (1.9570/0.8138)	mem 34602MB
[2025-01-19 15:33:23 internimage_b_1k_224] (main.py 519): INFO EPOCH 212 training takes 0:03:54
[2025-01-19 15:33:23 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_212.pth saving......
[2025-01-19 15:33:26 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_212.pth saved !!!
[2025-01-19 15:33:28 internimage_b_1k_224] (main.py 510): INFO Train: [212/300][310/312]	eta 0:00:01 lr 0.000807	time 0.7140 (0.7498)	model_time 0.7139 (0.7448)	loss 3.3340 (2.8876)	grad_norm 2.5564 (2.0393/0.9215)	mem 34604MB
[2025-01-19 15:33:29 internimage_b_1k_224] (main.py 519): INFO EPOCH 212 training takes 0:03:53
[2025-01-19 15:33:29 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_212.pth saving......
[2025-01-19 15:33:32 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_212.pth saved !!!
[2025-01-19 15:33:39 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 12.545 (12.545)	Loss 0.7125 (0.7125)	Acc@1 85.352 (85.352)	Acc@5 97.534 (97.534)	Mem 34602MB
[2025-01-19 15:33:45 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.698)	Loss 0.9309 (0.8064)	Acc@1 79.224 (83.239)	Acc@5 95.386 (96.562)	Mem 34602MB
[2025-01-19 15:33:45 internimage_b_1k_224] (main.py 575): INFO [Epoch:212] * Acc@1 83.053 Acc@5 96.579
[2025-01-19 15:33:45 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.1%
[2025-01-19 15:33:45 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 15:33:47 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.328 (15.328)	Loss 0.7101 (0.7101)	Acc@1 85.400 (85.400)	Acc@5 97.705 (97.705)	Mem 34604MB
[2025-01-19 15:33:48 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 15:33:48 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.05%
[2025-01-19 15:33:55 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.192 (2.101)	Loss 0.9504 (0.8188)	Acc@1 79.468 (83.192)	Acc@5 95.679 (96.582)	Mem 34604MB
[2025-01-19 15:33:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:212] * Acc@1 83.027 Acc@5 96.581
[2025-01-19 15:33:55 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.0%
[2025-01-19 15:33:55 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 15:33:59 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 15:33:59 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.03%
[2025-01-19 15:34:03 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.771 (14.771)	Loss 0.7097 (0.7097)	Acc@1 85.571 (85.571)	Acc@5 98.096 (98.096)	Mem 34602MB
[2025-01-19 15:34:12 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.130)	Loss 0.9439 (0.8120)	Acc@1 79.565 (83.418)	Acc@5 95.483 (96.673)	Mem 34602MB
[2025-01-19 15:34:12 internimage_b_1k_224] (main.py 575): INFO [Epoch:212] * Acc@1 83.257 Acc@5 96.721
[2025-01-19 15:34:12 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.3%
[2025-01-19 15:34:12 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:34:13 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 13.816 (13.816)	Loss 0.7018 (0.7018)	Acc@1 85.742 (85.742)	Acc@5 98.120 (98.120)	Mem 34604MB
[2025-01-19 15:34:16 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:34:16 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.26%
[2025-01-19 15:34:17 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.644)	Loss 0.9418 (0.8096)	Acc@1 79.419 (83.423)	Acc@5 95.386 (96.642)	Mem 34604MB
[2025-01-19 15:34:17 internimage_b_1k_224] (main.py 575): INFO [Epoch:212] * Acc@1 83.231 Acc@5 96.689
[2025-01-19 15:34:17 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.2%
[2025-01-19 15:34:17 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:34:18 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][0/312]	eta 0:11:29 lr 0.000806	time 2.2113 (2.2113)	model_time 0.7411 (0.7411)	loss 3.5916 (3.5916)	grad_norm 1.7567 (1.7567/0.0000)	mem 34602MB
[2025-01-19 15:34:21 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:34:21 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.23%
[2025-01-19 15:34:23 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][0/312]	eta 0:11:15 lr 0.000806	time 2.1662 (2.1662)	model_time 0.7344 (0.7344)	loss 3.3436 (3.3436)	grad_norm 3.1173 (3.1173/0.0000)	mem 34604MB
[2025-01-19 15:34:25 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][10/312]	eta 0:04:27 lr 0.000806	time 0.7183 (0.8850)	model_time 0.7181 (0.7510)	loss 3.1135 (3.0338)	grad_norm 1.4763 (2.2392/1.1571)	mem 34602MB
[2025-01-19 15:34:30 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][10/312]	eta 0:04:19 lr 0.000806	time 0.7176 (0.8584)	model_time 0.7171 (0.7279)	loss 3.2646 (2.8514)	grad_norm 1.5587 (2.5234/1.0752)	mem 34604MB
[2025-01-19 15:34:33 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][20/312]	eta 0:03:58 lr 0.000805	time 0.7284 (0.8155)	model_time 0.7282 (0.7452)	loss 2.6661 (2.8270)	grad_norm 1.3388 (1.9146/0.9553)	mem 34602MB
[2025-01-19 15:34:37 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][20/312]	eta 0:03:53 lr 0.000805	time 0.7462 (0.7990)	model_time 0.7461 (0.7305)	loss 2.6619 (2.7821)	grad_norm 1.5283 (2.6140/1.0718)	mem 34604MB
[2025-01-19 15:34:40 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][30/312]	eta 0:03:44 lr 0.000805	time 0.7229 (0.7943)	model_time 0.7227 (0.7466)	loss 2.3035 (2.8729)	grad_norm 2.7674 (1.8800/0.8471)	mem 34602MB
[2025-01-19 15:34:45 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][30/312]	eta 0:03:38 lr 0.000805	time 0.7091 (0.7750)	model_time 0.7089 (0.7284)	loss 3.5069 (2.8758)	grad_norm 1.7523 (2.3548/0.9902)	mem 34604MB
[2025-01-19 15:34:48 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][40/312]	eta 0:03:32 lr 0.000804	time 0.7176 (0.7798)	model_time 0.7171 (0.7436)	loss 2.0988 (2.8006)	grad_norm 2.6067 (1.9721/0.8610)	mem 34602MB
[2025-01-19 15:34:52 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][40/312]	eta 0:03:27 lr 0.000804	time 0.7253 (0.7646)	model_time 0.7247 (0.7293)	loss 2.3752 (2.8842)	grad_norm 2.6696 (2.2234/0.9440)	mem 34604MB
[2025-01-19 15:34:55 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][50/312]	eta 0:03:22 lr 0.000804	time 0.7185 (0.7717)	model_time 0.7183 (0.7425)	loss 3.3324 (2.8297)	grad_norm 1.0608 (1.8980/0.8132)	mem 34602MB
[2025-01-19 15:34:59 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][50/312]	eta 0:03:18 lr 0.000804	time 0.7221 (0.7575)	model_time 0.7216 (0.7290)	loss 3.3301 (2.8759)	grad_norm 1.7074 (2.1463/0.8973)	mem 34604MB
[2025-01-19 15:35:03 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][60/312]	eta 0:03:14 lr 0.000803	time 0.7229 (0.7711)	model_time 0.7225 (0.7466)	loss 3.4695 (2.8561)	grad_norm 3.5079 (1.9631/0.8514)	mem 34602MB
[2025-01-19 15:35:06 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][60/312]	eta 0:03:09 lr 0.000803	time 0.7272 (0.7525)	model_time 0.7270 (0.7286)	loss 3.2024 (2.9191)	grad_norm 1.5218 (2.1028/0.8721)	mem 34604MB
[2025-01-19 15:35:10 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][70/312]	eta 0:03:06 lr 0.000803	time 0.7430 (0.7696)	model_time 0.7425 (0.7486)	loss 2.9727 (2.8805)	grad_norm 0.8680 (2.0251/0.8959)	mem 34602MB
[2025-01-19 15:35:14 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][70/312]	eta 0:03:02 lr 0.000803	time 0.7179 (0.7524)	model_time 0.7178 (0.7319)	loss 2.5309 (2.8763)	grad_norm 1.9483 (2.0572/0.8389)	mem 34604MB
[2025-01-19 15:35:18 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][80/312]	eta 0:02:58 lr 0.000802	time 0.8005 (0.7682)	model_time 0.8000 (0.7497)	loss 2.5736 (2.8796)	grad_norm 1.1518 (2.0828/0.9457)	mem 34602MB
[2025-01-19 15:35:22 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][80/312]	eta 0:02:54 lr 0.000802	time 0.7272 (0.7540)	model_time 0.7271 (0.7360)	loss 2.4084 (2.8991)	grad_norm 1.5758 (2.0947/0.8703)	mem 34604MB
[2025-01-19 15:35:25 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][90/312]	eta 0:02:49 lr 0.000802	time 0.7190 (0.7633)	model_time 0.7188 (0.7468)	loss 2.9431 (2.8818)	grad_norm 2.6812 (2.0674/0.9276)	mem 34602MB
[2025-01-19 15:35:29 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][90/312]	eta 0:02:47 lr 0.000802	time 0.8049 (0.7552)	model_time 0.8047 (0.7391)	loss 2.5282 (2.9124)	grad_norm 2.3728 (2.0669/0.8380)	mem 34604MB
[2025-01-19 15:35:33 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][100/312]	eta 0:02:41 lr 0.000801	time 0.7158 (0.7629)	model_time 0.7154 (0.7480)	loss 3.3247 (2.8927)	grad_norm 2.3260 (2.0749/0.9225)	mem 34602MB
[2025-01-19 15:35:37 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][100/312]	eta 0:02:40 lr 0.000801	time 0.8143 (0.7578)	model_time 0.8141 (0.7432)	loss 3.0919 (2.9073)	grad_norm 1.1077 (2.0199/0.8207)	mem 34604MB
[2025-01-19 15:35:40 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][110/312]	eta 0:02:33 lr 0.000801	time 0.8013 (0.7601)	model_time 0.8011 (0.7465)	loss 3.0684 (2.9047)	grad_norm 1.5549 (2.0279/0.8966)	mem 34602MB
[2025-01-19 15:35:45 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][110/312]	eta 0:02:33 lr 0.000801	time 0.7195 (0.7576)	model_time 0.7191 (0.7443)	loss 3.2207 (2.9017)	grad_norm 1.6817 (1.9720/0.8107)	mem 34604MB
[2025-01-19 15:35:48 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][120/312]	eta 0:02:25 lr 0.000800	time 0.7124 (0.7595)	model_time 0.7122 (0.7469)	loss 3.3588 (2.9064)	grad_norm 1.8758 (1.9945/0.8820)	mem 34602MB
[2025-01-19 15:35:52 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][120/312]	eta 0:02:25 lr 0.000800	time 0.8005 (0.7561)	model_time 0.8000 (0.7438)	loss 3.1321 (2.8972)	grad_norm 0.9492 (1.9836/0.8403)	mem 34604MB
[2025-01-19 15:35:55 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][130/312]	eta 0:02:18 lr 0.000800	time 0.7239 (0.7587)	model_time 0.7237 (0.7471)	loss 3.2849 (2.9103)	grad_norm 1.7980 (1.9682/0.8576)	mem 34602MB
[2025-01-19 15:35:59 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][130/312]	eta 0:02:17 lr 0.000800	time 0.7169 (0.7543)	model_time 0.7167 (0.7430)	loss 2.5236 (2.8887)	grad_norm 0.9718 (1.9255/0.8358)	mem 34604MB
[2025-01-19 15:36:03 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][140/312]	eta 0:02:10 lr 0.000799	time 0.7413 (0.7573)	model_time 0.7412 (0.7464)	loss 3.0352 (2.8919)	grad_norm 2.2199 (1.9869/0.8474)	mem 34602MB
[2025-01-19 15:36:07 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][140/312]	eta 0:02:09 lr 0.000799	time 0.7247 (0.7524)	model_time 0.7244 (0.7419)	loss 1.9259 (2.9041)	grad_norm 1.7119 (1.9261/0.8558)	mem 34604MB
[2025-01-19 15:36:10 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][150/312]	eta 0:02:02 lr 0.000799	time 0.7178 (0.7567)	model_time 0.7176 (0.7466)	loss 2.8734 (2.8827)	grad_norm 2.0614 (2.0191/0.8704)	mem 34602MB
[2025-01-19 15:36:14 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][150/312]	eta 0:02:01 lr 0.000799	time 0.7561 (0.7510)	model_time 0.7556 (0.7411)	loss 2.2586 (2.9123)	grad_norm 0.9905 (1.9157/0.8382)	mem 34604MB
[2025-01-19 15:36:17 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][160/312]	eta 0:01:54 lr 0.000798	time 0.7190 (0.7555)	model_time 0.7188 (0.7460)	loss 2.7441 (2.8865)	grad_norm 2.6027 (2.0054/0.8562)	mem 34602MB
[2025-01-19 15:36:21 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][160/312]	eta 0:01:53 lr 0.000798	time 0.7254 (0.7496)	model_time 0.7251 (0.7403)	loss 2.6305 (2.9069)	grad_norm 2.1486 (1.9298/0.8440)	mem 34604MB
[2025-01-19 15:36:25 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][170/312]	eta 0:01:47 lr 0.000798	time 0.7227 (0.7545)	model_time 0.7225 (0.7455)	loss 3.2671 (2.8712)	grad_norm 4.0370 (2.0149/0.8564)	mem 34602MB
[2025-01-19 15:36:29 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][170/312]	eta 0:01:46 lr 0.000798	time 0.7137 (0.7482)	model_time 0.7132 (0.7395)	loss 2.5278 (2.9192)	grad_norm 2.1733 (1.9168/0.8278)	mem 34604MB
[2025-01-19 15:36:32 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][180/312]	eta 0:01:39 lr 0.000797	time 0.7255 (0.7545)	model_time 0.7253 (0.7460)	loss 3.0693 (2.8694)	grad_norm 2.4083 (2.0156/0.8600)	mem 34602MB
[2025-01-19 15:36:36 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][180/312]	eta 0:01:38 lr 0.000797	time 0.7163 (0.7473)	model_time 0.7161 (0.7390)	loss 2.9224 (2.9178)	grad_norm 1.6575 (1.9292/0.8183)	mem 34604MB
[2025-01-19 15:36:40 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][190/312]	eta 0:01:32 lr 0.000796	time 0.7181 (0.7543)	model_time 0.7176 (0.7463)	loss 3.0592 (2.8708)	grad_norm 2.2542 (2.0235/0.8663)	mem 34602MB
[2025-01-19 15:36:43 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][190/312]	eta 0:01:31 lr 0.000796	time 0.7203 (0.7469)	model_time 0.7201 (0.7390)	loss 1.9712 (2.9078)	grad_norm 0.9994 (1.9184/0.8152)	mem 34604MB
[2025-01-19 15:36:48 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][200/312]	eta 0:01:24 lr 0.000796	time 0.8110 (0.7551)	model_time 0.8108 (0.7475)	loss 3.4051 (2.8762)	grad_norm 2.2049 (2.0363/0.8712)	mem 34602MB
[2025-01-19 15:36:51 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][200/312]	eta 0:01:23 lr 0.000796	time 0.7304 (0.7476)	model_time 0.7302 (0.7401)	loss 3.2955 (2.8995)	grad_norm 2.0085 (1.9060/0.8066)	mem 34604MB
[2025-01-19 15:36:55 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][210/312]	eta 0:01:16 lr 0.000795	time 0.7225 (0.7539)	model_time 0.7220 (0.7466)	loss 3.2254 (2.8746)	grad_norm 0.9607 (2.0152/0.8652)	mem 34602MB
[2025-01-19 15:36:58 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][210/312]	eta 0:01:16 lr 0.000795	time 0.8120 (0.7482)	model_time 0.8115 (0.7410)	loss 2.6107 (2.9028)	grad_norm 1.1266 (1.9109/0.8061)	mem 34604MB
[2025-01-19 15:37:02 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][220/312]	eta 0:01:09 lr 0.000795	time 0.7196 (0.7539)	model_time 0.7193 (0.7469)	loss 3.3977 (2.8843)	grad_norm 1.0309 (2.0190/0.8638)	mem 34602MB
[2025-01-19 15:37:06 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][220/312]	eta 0:01:08 lr 0.000795	time 0.8064 (0.7498)	model_time 0.8059 (0.7430)	loss 2.3847 (2.9039)	grad_norm 1.6702 (1.9197/0.8039)	mem 34604MB
[2025-01-19 15:37:10 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][230/312]	eta 0:01:01 lr 0.000794	time 0.8238 (0.7532)	model_time 0.8237 (0.7465)	loss 3.6197 (2.8856)	grad_norm 1.3804 (1.9959/0.8548)	mem 34602MB
[2025-01-19 15:37:14 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][230/312]	eta 0:01:01 lr 0.000794	time 0.7162 (0.7511)	model_time 0.7161 (0.7445)	loss 2.9286 (2.9111)	grad_norm 3.8881 (1.9134/0.8072)	mem 34604MB
[2025-01-19 15:37:17 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][240/312]	eta 0:00:54 lr 0.000794	time 0.7588 (0.7530)	model_time 0.7583 (0.7466)	loss 2.9866 (2.8767)	grad_norm 1.3269 (1.9768/0.8440)	mem 34602MB
[2025-01-19 15:37:21 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][240/312]	eta 0:00:54 lr 0.000794	time 0.8056 (0.7507)	model_time 0.8055 (0.7444)	loss 3.1257 (2.9046)	grad_norm 1.9893 (1.9113/0.8110)	mem 34604MB
[2025-01-19 15:37:25 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][250/312]	eta 0:00:46 lr 0.000793	time 0.7442 (0.7530)	model_time 0.7441 (0.7468)	loss 2.9766 (2.8849)	grad_norm 2.2582 (1.9839/0.8507)	mem 34602MB
[2025-01-19 15:37:29 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][250/312]	eta 0:00:46 lr 0.000793	time 0.7231 (0.7498)	model_time 0.7227 (0.7437)	loss 3.3640 (2.9029)	grad_norm 1.3641 (1.9295/0.8242)	mem 34604MB
[2025-01-19 15:37:32 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][260/312]	eta 0:00:39 lr 0.000793	time 0.7195 (0.7524)	model_time 0.7191 (0.7464)	loss 3.4495 (2.8894)	grad_norm 1.0930 (1.9997/0.8565)	mem 34602MB
[2025-01-19 15:37:36 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][260/312]	eta 0:00:38 lr 0.000793	time 0.7121 (0.7490)	model_time 0.7118 (0.7431)	loss 3.2131 (2.9042)	grad_norm 2.1686 (1.9332/0.8215)	mem 34604MB
[2025-01-19 15:37:40 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][270/312]	eta 0:00:31 lr 0.000792	time 0.7090 (0.7522)	model_time 0.7086 (0.7464)	loss 3.3265 (2.8899)	grad_norm 1.9747 (2.0194/0.8684)	mem 34602MB
[2025-01-19 15:37:43 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][270/312]	eta 0:00:31 lr 0.000792	time 0.7270 (0.7484)	model_time 0.7264 (0.7427)	loss 2.8567 (2.9060)	grad_norm 2.6643 (1.9563/0.8324)	mem 34604MB
[2025-01-19 15:37:47 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][280/312]	eta 0:00:24 lr 0.000792	time 0.7191 (0.7518)	model_time 0.7189 (0.7462)	loss 3.1150 (2.8909)	grad_norm 2.3172 (2.0252/0.8573)	mem 34602MB
[2025-01-19 15:37:51 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][280/312]	eta 0:00:23 lr 0.000792	time 0.7700 (0.7478)	model_time 0.7698 (0.7424)	loss 2.4732 (2.8978)	grad_norm 2.2336 (1.9503/0.8291)	mem 34604MB
[2025-01-19 15:37:54 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][290/312]	eta 0:00:16 lr 0.000791	time 0.7269 (0.7514)	model_time 0.7268 (0.7460)	loss 3.0726 (2.8903)	grad_norm 2.0386 (2.0206/0.8541)	mem 34602MB
[2025-01-19 15:37:58 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][290/312]	eta 0:00:16 lr 0.000791	time 0.7108 (0.7472)	model_time 0.7106 (0.7419)	loss 2.5214 (2.8955)	grad_norm 2.7168 (1.9605/0.8309)	mem 34604MB
[2025-01-19 15:38:02 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][300/312]	eta 0:00:09 lr 0.000791	time 0.8086 (0.7515)	model_time 0.8085 (0.7463)	loss 2.6669 (2.8877)	grad_norm 2.7029 (2.0131/0.8498)	mem 34602MB
[2025-01-19 15:38:05 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][300/312]	eta 0:00:08 lr 0.000791	time 0.7157 (0.7464)	model_time 0.7156 (0.7413)	loss 2.7243 (2.8904)	grad_norm 4.1994 (1.9615/0.8297)	mem 34604MB
[2025-01-19 15:38:09 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][310/312]	eta 0:00:01 lr 0.000790	time 0.7952 (0.7512)	model_time 0.7950 (0.7462)	loss 3.3184 (2.8909)	grad_norm 2.3567 (2.0167/0.8399)	mem 34602MB
[2025-01-19 15:38:10 internimage_b_1k_224] (main.py 519): INFO EPOCH 213 training takes 0:03:54
[2025-01-19 15:38:10 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_213.pth saving......
[2025-01-19 15:38:13 internimage_b_1k_224] (main.py 510): INFO Train: [213/300][310/312]	eta 0:00:01 lr 0.000790	time 0.7143 (0.7458)	model_time 0.7143 (0.7408)	loss 3.4117 (2.8904)	grad_norm 1.6151 (1.9684/0.8205)	mem 34604MB
[2025-01-19 15:38:13 internimage_b_1k_224] (main.py 519): INFO EPOCH 213 training takes 0:03:52
[2025-01-19 15:38:13 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_213.pth saving......
[2025-01-19 15:38:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_213.pth saved !!!
[2025-01-19 15:38:17 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_213.pth saved !!!
[2025-01-19 15:38:30 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.164 (16.164)	Loss 0.7496 (0.7496)	Acc@1 85.327 (85.327)	Acc@5 97.607 (97.607)	Mem 34602MB
[2025-01-19 15:38:34 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.644 (16.644)	Loss 0.7197 (0.7197)	Acc@1 85.059 (85.059)	Acc@5 97.876 (97.876)	Mem 34604MB
[2025-01-19 15:38:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.996)	Loss 0.9615 (0.8376)	Acc@1 79.248 (83.159)	Acc@5 95.190 (96.591)	Mem 34602MB
[2025-01-19 15:38:36 internimage_b_1k_224] (main.py 575): INFO [Epoch:213] * Acc@1 82.987 Acc@5 96.625
[2025-01-19 15:38:36 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.0%
[2025-01-19 15:38:36 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.05%
[2025-01-19 15:38:41 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (2.148)	Loss 0.9331 (0.8168)	Acc@1 79.688 (83.274)	Acc@5 95.605 (96.560)	Mem 34604MB
[2025-01-19 15:38:41 internimage_b_1k_224] (main.py 575): INFO [Epoch:213] * Acc@1 83.119 Acc@5 96.585
[2025-01-19 15:38:41 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.1%
[2025-01-19 15:38:41 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 15:38:44 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 15:38:44 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.12%
[2025-01-19 15:38:53 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.570 (17.570)	Loss 0.7105 (0.7105)	Acc@1 85.596 (85.596)	Acc@5 98.096 (98.096)	Mem 34602MB
[2025-01-19 15:39:01 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.407 (16.407)	Loss 0.7024 (0.7024)	Acc@1 85.791 (85.791)	Acc@5 98.145 (98.145)	Mem 34604MB
[2025-01-19 15:39:03 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.449)	Loss 0.9437 (0.8122)	Acc@1 79.590 (83.452)	Acc@5 95.581 (96.684)	Mem 34602MB
[2025-01-19 15:39:03 internimage_b_1k_224] (main.py 575): INFO [Epoch:213] * Acc@1 83.291 Acc@5 96.731
[2025-01-19 15:39:03 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.3%
[2025-01-19 15:39:03 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:39:05 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (1.925)	Loss 0.9418 (0.8098)	Acc@1 79.370 (83.465)	Acc@5 95.410 (96.649)	Mem 34604MB
[2025-01-19 15:39:06 internimage_b_1k_224] (main.py 575): INFO [Epoch:213] * Acc@1 83.267 Acc@5 96.695
[2025-01-19 15:39:06 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.3%
[2025-01-19 15:39:06 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:39:07 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:39:07 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.29%
[2025-01-19 15:39:09 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:39:09 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.27%
[2025-01-19 15:39:10 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][0/312]	eta 0:12:57 lr 0.000790	time 2.4930 (2.4930)	model_time 0.7331 (0.7331)	loss 3.2608 (3.2608)	grad_norm 2.3658 (2.3658/0.0000)	mem 34602MB
[2025-01-19 15:39:12 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][0/312]	eta 0:13:19 lr 0.000790	time 2.5630 (2.5630)	model_time 0.7718 (0.7718)	loss 2.4680 (2.4680)	grad_norm 3.7405 (3.7405/0.0000)	mem 34604MB
[2025-01-19 15:39:17 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][10/312]	eta 0:04:38 lr 0.000790	time 0.8007 (0.9235)	model_time 0.8006 (0.7632)	loss 3.1243 (2.9140)	grad_norm 2.1816 (2.2921/0.7685)	mem 34602MB
[2025-01-19 15:39:20 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][10/312]	eta 0:04:45 lr 0.000790	time 0.8325 (0.9453)	model_time 0.8321 (0.7821)	loss 3.2503 (2.7256)	grad_norm 2.4335 (2.4699/0.9331)	mem 34604MB
[2025-01-19 15:39:25 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][20/312]	eta 0:04:02 lr 0.000789	time 0.7231 (0.8316)	model_time 0.7229 (0.7475)	loss 2.4537 (2.9271)	grad_norm 2.8676 (2.1016/0.7572)	mem 34602MB
[2025-01-19 15:39:27 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][20/312]	eta 0:04:08 lr 0.000789	time 0.8104 (0.8517)	model_time 0.8102 (0.7660)	loss 3.1146 (2.8395)	grad_norm 1.3545 (1.9963/0.8687)	mem 34604MB
[2025-01-19 15:39:32 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][30/312]	eta 0:03:47 lr 0.000789	time 0.7234 (0.8082)	model_time 0.7233 (0.7512)	loss 2.7257 (2.9038)	grad_norm 2.1622 (2.0493/0.7201)	mem 34602MB
[2025-01-19 15:39:35 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][30/312]	eta 0:03:53 lr 0.000789	time 0.7755 (0.8294)	model_time 0.7751 (0.7713)	loss 3.4970 (2.9234)	grad_norm 1.0223 (1.8787/0.8095)	mem 34604MB
[2025-01-19 15:39:39 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][40/312]	eta 0:03:35 lr 0.000788	time 0.7441 (0.7908)	model_time 0.7439 (0.7476)	loss 3.4854 (2.9184)	grad_norm 2.2841 (2.1197/0.8371)	mem 34602MB
[2025-01-19 15:39:43 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][40/312]	eta 0:03:41 lr 0.000788	time 0.7242 (0.8152)	model_time 0.7237 (0.7711)	loss 2.5171 (2.8858)	grad_norm 2.3039 (1.9483/0.7945)	mem 34604MB
[2025-01-19 15:39:47 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][50/312]	eta 0:03:24 lr 0.000788	time 0.7205 (0.7815)	model_time 0.7200 (0.7467)	loss 3.4671 (2.9219)	grad_norm 1.7321 (2.0708/0.8019)	mem 34602MB
[2025-01-19 15:39:50 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][50/312]	eta 0:03:30 lr 0.000788	time 0.7509 (0.8027)	model_time 0.7507 (0.7672)	loss 3.2127 (2.8790)	grad_norm 1.4103 (1.8830/0.7369)	mem 34604MB
[2025-01-19 15:39:54 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][60/312]	eta 0:03:15 lr 0.000787	time 0.7354 (0.7776)	model_time 0.7351 (0.7485)	loss 2.3886 (2.9573)	grad_norm 1.0490 (2.0097/0.7856)	mem 34602MB
[2025-01-19 15:39:58 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][60/312]	eta 0:03:19 lr 0.000787	time 0.7174 (0.7908)	model_time 0.7172 (0.7610)	loss 3.2741 (2.8773)	grad_norm 2.6252 (1.9380/0.7124)	mem 34604MB
[2025-01-19 15:40:02 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][70/312]	eta 0:03:06 lr 0.000786	time 0.7163 (0.7717)	model_time 0.7162 (0.7466)	loss 2.8017 (2.9835)	grad_norm 1.3791 (2.0085/0.7522)	mem 34602MB
[2025-01-19 15:40:05 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][70/312]	eta 0:03:09 lr 0.000786	time 0.7382 (0.7821)	model_time 0.7378 (0.7565)	loss 3.1871 (2.8927)	grad_norm 1.4233 (1.8823/0.7053)	mem 34604MB
[2025-01-19 15:40:09 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][80/312]	eta 0:02:58 lr 0.000786	time 0.8050 (0.7704)	model_time 0.8048 (0.7484)	loss 3.3574 (2.9944)	grad_norm 0.9564 (1.9526/0.7524)	mem 34602MB
[2025-01-19 15:40:12 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][80/312]	eta 0:02:59 lr 0.000786	time 0.7169 (0.7748)	model_time 0.7168 (0.7523)	loss 3.3537 (2.8883)	grad_norm 1.1656 (1.9612/0.9225)	mem 34604MB
[2025-01-19 15:40:17 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][90/312]	eta 0:02:50 lr 0.000785	time 0.7272 (0.7659)	model_time 0.7270 (0.7463)	loss 2.9308 (3.0136)	grad_norm 3.3806 (1.9050/0.7644)	mem 34602MB
[2025-01-19 15:40:19 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][90/312]	eta 0:02:50 lr 0.000785	time 0.7134 (0.7696)	model_time 0.7132 (0.7495)	loss 2.8745 (2.8806)	grad_norm 1.2373 (1.9438/0.8868)	mem 34604MB
[2025-01-19 15:40:24 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][100/312]	eta 0:02:41 lr 0.000785	time 0.7210 (0.7629)	model_time 0.7208 (0.7452)	loss 3.0452 (2.9955)	grad_norm 1.5458 (1.9133/0.7554)	mem 34602MB
[2025-01-19 15:40:27 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][100/312]	eta 0:02:42 lr 0.000785	time 0.7243 (0.7652)	model_time 0.7241 (0.7471)	loss 3.0984 (2.8959)	grad_norm 1.4671 (1.9104/0.8639)	mem 34604MB
[2025-01-19 15:40:32 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][110/312]	eta 0:02:33 lr 0.000784	time 0.7274 (0.7620)	model_time 0.7272 (0.7458)	loss 3.0080 (2.9803)	grad_norm 2.0075 (1.9289/0.7447)	mem 34602MB
[2025-01-19 15:40:34 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][110/312]	eta 0:02:33 lr 0.000784	time 0.7230 (0.7618)	model_time 0.7225 (0.7453)	loss 3.1071 (2.9167)	grad_norm 1.9210 (1.8874/0.8364)	mem 34604MB
[2025-01-19 15:40:39 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][120/312]	eta 0:02:26 lr 0.000784	time 0.7287 (0.7615)	model_time 0.7283 (0.7466)	loss 3.6596 (2.9696)	grad_norm 3.1949 (1.9140/0.7517)	mem 34602MB
[2025-01-19 15:40:41 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][120/312]	eta 0:02:26 lr 0.000784	time 0.8942 (0.7620)	model_time 0.8941 (0.7468)	loss 3.5046 (2.9361)	grad_norm 1.7076 (1.8565/0.8135)	mem 34604MB
[2025-01-19 15:40:47 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][130/312]	eta 0:02:18 lr 0.000783	time 0.7518 (0.7619)	model_time 0.7516 (0.7481)	loss 3.1592 (2.9486)	grad_norm 1.3089 (1.9548/0.7885)	mem 34602MB
[2025-01-19 15:40:49 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][130/312]	eta 0:02:18 lr 0.000783	time 0.8117 (0.7618)	model_time 0.8113 (0.7477)	loss 3.1459 (2.9542)	grad_norm 4.5269 (1.8687/0.8314)	mem 34604MB
[2025-01-19 15:40:54 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][140/312]	eta 0:02:10 lr 0.000783	time 0.7402 (0.7601)	model_time 0.7400 (0.7473)	loss 3.4646 (2.9280)	grad_norm 1.6595 (2.0007/0.7988)	mem 34602MB
[2025-01-19 15:40:57 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][140/312]	eta 0:02:10 lr 0.000783	time 0.7298 (0.7613)	model_time 0.7296 (0.7482)	loss 3.1845 (2.9350)	grad_norm 1.4137 (1.9614/0.9872)	mem 34604MB
[2025-01-19 15:41:02 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][150/312]	eta 0:02:03 lr 0.000782	time 0.7087 (0.7603)	model_time 0.7085 (0.7483)	loss 2.5366 (2.9312)	grad_norm 1.4772 (1.9906/0.8044)	mem 34602MB
[2025-01-19 15:41:05 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][150/312]	eta 0:02:03 lr 0.000782	time 0.8061 (0.7647)	model_time 0.8057 (0.7525)	loss 3.4751 (2.9187)	grad_norm 2.8629 (1.9977/0.9952)	mem 34604MB
[2025-01-19 15:41:09 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][160/312]	eta 0:01:55 lr 0.000782	time 0.7309 (0.7587)	model_time 0.7304 (0.7474)	loss 3.0178 (2.9411)	grad_norm 1.7783 (1.9638/0.7903)	mem 34602MB
[2025-01-19 15:41:12 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][160/312]	eta 0:01:56 lr 0.000782	time 0.7168 (0.7645)	model_time 0.7164 (0.7530)	loss 2.8223 (2.9176)	grad_norm 1.5704 (1.9999/0.9999)	mem 34604MB
[2025-01-19 15:41:17 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][170/312]	eta 0:01:47 lr 0.000781	time 0.7308 (0.7579)	model_time 0.7303 (0.7473)	loss 3.2824 (2.9387)	grad_norm 3.7517 (1.9563/0.7875)	mem 34602MB
[2025-01-19 15:41:20 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][170/312]	eta 0:01:48 lr 0.000781	time 0.7284 (0.7633)	model_time 0.7283 (0.7525)	loss 3.5174 (2.9195)	grad_norm 2.6236 (2.0430/1.0038)	mem 34604MB
[2025-01-19 15:41:24 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][180/312]	eta 0:01:40 lr 0.000781	time 0.7177 (0.7579)	model_time 0.7175 (0.7479)	loss 3.0294 (2.9423)	grad_norm 3.4501 (1.9479/0.7832)	mem 34602MB
[2025-01-19 15:41:27 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][180/312]	eta 0:01:40 lr 0.000781	time 0.7177 (0.7615)	model_time 0.7176 (0.7512)	loss 3.3862 (2.9345)	grad_norm 2.0958 (2.0559/0.9861)	mem 34604MB
[2025-01-19 15:41:32 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][190/312]	eta 0:01:32 lr 0.000780	time 0.7281 (0.7568)	model_time 0.7276 (0.7472)	loss 3.2199 (2.9342)	grad_norm 1.2785 (1.9485/0.7814)	mem 34602MB
[2025-01-19 15:41:34 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][190/312]	eta 0:01:32 lr 0.000780	time 0.7298 (0.7597)	model_time 0.7293 (0.7500)	loss 2.7322 (2.9377)	grad_norm 2.0232 (2.0892/0.9898)	mem 34604MB
[2025-01-19 15:41:39 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][200/312]	eta 0:01:24 lr 0.000780	time 0.8062 (0.7567)	model_time 0.8061 (0.7476)	loss 1.9665 (2.9296)	grad_norm 0.9699 (1.9247/0.7784)	mem 34602MB
[2025-01-19 15:41:42 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][200/312]	eta 0:01:24 lr 0.000780	time 0.7415 (0.7584)	model_time 0.7414 (0.7491)	loss 2.5061 (2.9354)	grad_norm 2.7122 (2.0962/0.9845)	mem 34604MB
[2025-01-19 15:41:46 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][210/312]	eta 0:01:17 lr 0.000779	time 0.7239 (0.7555)	model_time 0.7237 (0.7469)	loss 2.8559 (2.9264)	grad_norm 1.4555 (1.9110/0.7661)	mem 34602MB
[2025-01-19 15:41:49 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][210/312]	eta 0:01:17 lr 0.000779	time 0.7184 (0.7572)	model_time 0.7183 (0.7483)	loss 3.2214 (2.9386)	grad_norm 1.8906 (2.1123/0.9857)	mem 34604MB
[2025-01-19 15:41:54 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][220/312]	eta 0:01:09 lr 0.000779	time 0.7239 (0.7550)	model_time 0.7237 (0.7467)	loss 2.8905 (2.9264)	grad_norm 3.0963 (1.9023/0.7590)	mem 34602MB
[2025-01-19 15:41:56 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][220/312]	eta 0:01:09 lr 0.000779	time 0.7156 (0.7558)	model_time 0.7150 (0.7473)	loss 3.4728 (2.9293)	grad_norm 1.7673 (2.0982/0.9690)	mem 34604MB
[2025-01-19 15:42:01 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][230/312]	eta 0:01:01 lr 0.000778	time 0.7177 (0.7547)	model_time 0.7175 (0.7467)	loss 2.3832 (2.9199)	grad_norm 1.5011 (1.8927/0.7583)	mem 34602MB
[2025-01-19 15:42:04 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][230/312]	eta 0:01:01 lr 0.000778	time 0.7230 (0.7546)	model_time 0.7228 (0.7464)	loss 3.3000 (2.9329)	grad_norm 1.8466 (2.0772/0.9564)	mem 34604MB
[2025-01-19 15:42:09 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][240/312]	eta 0:00:54 lr 0.000778	time 0.7946 (0.7548)	model_time 0.7941 (0.7472)	loss 2.1779 (2.9135)	grad_norm 1.1197 (1.8832/0.7545)	mem 34602MB
[2025-01-19 15:42:11 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][240/312]	eta 0:00:54 lr 0.000778	time 0.8963 (0.7546)	model_time 0.8961 (0.7468)	loss 2.7283 (2.9344)	grad_norm 1.5864 (2.0763/0.9478)	mem 34604MB
[2025-01-19 15:42:17 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][250/312]	eta 0:00:46 lr 0.000777	time 0.8049 (0.7556)	model_time 0.8045 (0.7483)	loss 1.9860 (2.9174)	grad_norm 1.8620 (1.8874/0.7500)	mem 34602MB
[2025-01-19 15:42:19 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][250/312]	eta 0:00:46 lr 0.000777	time 0.8146 (0.7553)	model_time 0.8141 (0.7478)	loss 3.2256 (2.9364)	grad_norm 1.7224 (2.0769/0.9524)	mem 34604MB
[2025-01-19 15:42:24 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][260/312]	eta 0:00:39 lr 0.000777	time 0.7298 (0.7549)	model_time 0.7296 (0.7478)	loss 3.1323 (2.9090)	grad_norm 3.3388 (1.8905/0.7462)	mem 34602MB
[2025-01-19 15:42:26 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][260/312]	eta 0:00:39 lr 0.000777	time 0.7248 (0.7548)	model_time 0.7244 (0.7475)	loss 2.3881 (2.9314)	grad_norm 2.3620 (2.0935/0.9714)	mem 34604MB
[2025-01-19 15:42:32 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][270/312]	eta 0:00:31 lr 0.000776	time 0.8058 (0.7558)	model_time 0.8053 (0.7490)	loss 3.0879 (2.9062)	grad_norm 2.2576 (1.8984/0.7508)	mem 34602MB
[2025-01-19 15:42:34 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][270/312]	eta 0:00:31 lr 0.000776	time 0.8094 (0.7561)	model_time 0.8092 (0.7491)	loss 2.7204 (2.9340)	grad_norm 1.8194 (2.0792/0.9595)	mem 34604MB
[2025-01-19 15:42:39 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][280/312]	eta 0:00:24 lr 0.000776	time 0.7168 (0.7548)	model_time 0.7166 (0.7481)	loss 2.3178 (2.9051)	grad_norm 1.3454 (1.8969/0.7551)	mem 34602MB
[2025-01-19 15:42:42 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][280/312]	eta 0:00:24 lr 0.000776	time 0.7320 (0.7562)	model_time 0.7315 (0.7495)	loss 3.1196 (2.9345)	grad_norm 1.1313 (2.0585/0.9543)	mem 34604MB
[2025-01-19 15:42:47 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][290/312]	eta 0:00:16 lr 0.000775	time 0.7496 (0.7554)	model_time 0.7491 (0.7490)	loss 2.6749 (2.9028)	grad_norm 1.5433 (1.8824/0.7485)	mem 34602MB
[2025-01-19 15:42:49 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][290/312]	eta 0:00:16 lr 0.000775	time 0.7198 (0.7557)	model_time 0.7193 (0.7492)	loss 2.1860 (2.9384)	grad_norm 1.8651 (2.0594/0.9526)	mem 34604MB
[2025-01-19 15:42:54 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][300/312]	eta 0:00:09 lr 0.000775	time 0.7141 (0.7550)	model_time 0.7139 (0.7488)	loss 2.8573 (2.9079)	grad_norm 3.5691 (1.8954/0.7560)	mem 34602MB
[2025-01-19 15:42:56 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][300/312]	eta 0:00:09 lr 0.000775	time 0.7118 (0.7546)	model_time 0.7117 (0.7482)	loss 2.7511 (2.9406)	grad_norm 1.4213 (2.0459/0.9422)	mem 34604MB
[2025-01-19 15:43:02 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][310/312]	eta 0:00:01 lr 0.000774	time 0.7125 (0.7541)	model_time 0.7125 (0.7481)	loss 2.7109 (2.9061)	grad_norm 3.3121 (1.9079/0.7742)	mem 34602MB
[2025-01-19 15:43:02 internimage_b_1k_224] (main.py 519): INFO EPOCH 214 training takes 0:03:55
[2025-01-19 15:43:02 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_214.pth saving......
[2025-01-19 15:43:04 internimage_b_1k_224] (main.py 510): INFO Train: [214/300][310/312]	eta 0:00:01 lr 0.000774	time 0.7542 (0.7534)	model_time 0.7541 (0.7473)	loss 3.0551 (2.9429)	grad_norm 2.3012 (2.0398/0.9405)	mem 34604MB
[2025-01-19 15:43:04 internimage_b_1k_224] (main.py 519): INFO EPOCH 214 training takes 0:03:55
[2025-01-19 15:43:04 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_214.pth saving......
[2025-01-19 15:43:05 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_214.pth saved !!!
[2025-01-19 15:43:08 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_214.pth saved !!!
[2025-01-19 15:43:21 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.346 (15.346)	Loss 0.7178 (0.7178)	Acc@1 85.425 (85.425)	Acc@5 97.534 (97.534)	Mem 34602MB
[2025-01-19 15:43:24 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.130 (16.130)	Loss 0.7043 (0.7043)	Acc@1 85.791 (85.791)	Acc@5 97.510 (97.510)	Mem 34604MB
[2025-01-19 15:43:28 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.988)	Loss 0.9273 (0.8199)	Acc@1 79.590 (83.125)	Acc@5 95.532 (96.493)	Mem 34602MB
[2025-01-19 15:43:28 internimage_b_1k_224] (main.py 575): INFO [Epoch:214] * Acc@1 82.961 Acc@5 96.505
[2025-01-19 15:43:28 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.0%
[2025-01-19 15:43:28 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.05%
[2025-01-19 15:43:30 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.028)	Loss 0.9179 (0.8113)	Acc@1 80.542 (83.236)	Acc@5 95.508 (96.549)	Mem 34604MB
[2025-01-19 15:43:30 internimage_b_1k_224] (main.py 575): INFO [Epoch:214] * Acc@1 83.075 Acc@5 96.571
[2025-01-19 15:43:30 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.1%
[2025-01-19 15:43:30 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.12%
[2025-01-19 15:43:46 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.770 (17.770)	Loss 0.7114 (0.7114)	Acc@1 85.620 (85.620)	Acc@5 98.145 (98.145)	Mem 34602MB
[2025-01-19 15:43:48 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.778 (17.778)	Loss 0.7031 (0.7031)	Acc@1 85.840 (85.840)	Acc@5 98.145 (98.145)	Mem 34604MB
[2025-01-19 15:43:54 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.421)	Loss 0.9434 (0.8123)	Acc@1 79.565 (83.465)	Acc@5 95.630 (96.702)	Mem 34602MB
[2025-01-19 15:43:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:214] * Acc@1 83.313 Acc@5 96.749
[2025-01-19 15:43:55 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.3%
[2025-01-19 15:43:55 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:43:55 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.287)	Loss 0.9414 (0.8100)	Acc@1 79.517 (83.512)	Acc@5 95.459 (96.669)	Mem 34604MB
[2025-01-19 15:43:56 internimage_b_1k_224] (main.py 575): INFO [Epoch:214] * Acc@1 83.307 Acc@5 96.715
[2025-01-19 15:43:56 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.3%
[2025-01-19 15:43:56 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:43:58 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:43:58 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.31%
[2025-01-19 15:44:00 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:44:00 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.31%
[2025-01-19 15:44:00 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][0/312]	eta 0:10:29 lr 0.000774	time 2.0175 (2.0175)	model_time 0.7409 (0.7409)	loss 2.4327 (2.4327)	grad_norm 3.3588 (3.3588/0.0000)	mem 34602MB
[2025-01-19 15:44:02 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][0/312]	eta 0:10:06 lr 0.000774	time 1.9452 (1.9452)	model_time 0.7466 (0.7466)	loss 2.4311 (2.4311)	grad_norm 1.1051 (1.1051/0.0000)	mem 34604MB
[2025-01-19 15:44:08 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][10/312]	eta 0:04:21 lr 0.000773	time 0.7218 (0.8660)	model_time 0.7216 (0.7495)	loss 2.8936 (2.6424)	grad_norm 2.0341 (2.6592/0.9650)	mem 34602MB
[2025-01-19 15:44:09 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][10/312]	eta 0:04:12 lr 0.000773	time 0.7361 (0.8366)	model_time 0.7359 (0.7274)	loss 3.2104 (2.8176)	grad_norm 0.7501 (1.6757/0.8131)	mem 34604MB
[2025-01-19 15:44:15 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][20/312]	eta 0:03:54 lr 0.000773	time 0.7282 (0.8048)	model_time 0.7278 (0.7437)	loss 3.6091 (2.8393)	grad_norm 1.2896 (2.2956/0.9086)	mem 34602MB
[2025-01-19 15:44:16 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][20/312]	eta 0:03:49 lr 0.000773	time 0.7249 (0.7856)	model_time 0.7245 (0.7282)	loss 3.6518 (2.9213)	grad_norm 1.2108 (1.6826/0.6695)	mem 34604MB
[2025-01-19 15:44:23 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][30/312]	eta 0:03:40 lr 0.000772	time 0.7208 (0.7819)	model_time 0.7206 (0.7404)	loss 2.3084 (2.7333)	grad_norm 1.5071 (2.1675/0.8439)	mem 34602MB
[2025-01-19 15:44:24 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][30/312]	eta 0:03:36 lr 0.000772	time 0.7149 (0.7672)	model_time 0.7145 (0.7282)	loss 2.5220 (2.8661)	grad_norm 1.8607 (1.7740/0.6868)	mem 34604MB
[2025-01-19 15:44:30 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][40/312]	eta 0:03:31 lr 0.000772	time 0.7174 (0.7765)	model_time 0.7169 (0.7451)	loss 1.9965 (2.7380)	grad_norm 1.6120 (2.1988/0.8342)	mem 34602MB
[2025-01-19 15:44:31 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][40/312]	eta 0:03:25 lr 0.000772	time 0.7180 (0.7571)	model_time 0.7175 (0.7275)	loss 2.8447 (2.8741)	grad_norm 1.6915 (1.7455/0.6469)	mem 34604MB
[2025-01-19 15:44:38 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][50/312]	eta 0:03:22 lr 0.000771	time 0.7166 (0.7727)	model_time 0.7165 (0.7473)	loss 2.2536 (2.7851)	grad_norm 2.2715 (2.2733/0.8719)	mem 34602MB
[2025-01-19 15:44:38 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][50/312]	eta 0:03:18 lr 0.000771	time 0.8084 (0.7575)	model_time 0.8079 (0.7337)	loss 3.1976 (2.9440)	grad_norm 5.6551 (1.8599/0.8402)	mem 34604MB
[2025-01-19 15:44:45 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][60/312]	eta 0:03:14 lr 0.000771	time 0.7413 (0.7711)	model_time 0.7409 (0.7498)	loss 2.2576 (2.7814)	grad_norm 1.9927 (2.2934/0.8861)	mem 34602MB
[2025-01-19 15:44:46 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][60/312]	eta 0:03:12 lr 0.000771	time 0.8151 (0.7631)	model_time 0.8150 (0.7431)	loss 3.4040 (2.9467)	grad_norm 3.1061 (1.9681/0.8356)	mem 34604MB
[2025-01-19 15:44:53 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][70/312]	eta 0:03:05 lr 0.000770	time 0.7197 (0.7672)	model_time 0.7195 (0.7489)	loss 2.4136 (2.8011)	grad_norm 1.6808 (2.2493/0.8712)	mem 34602MB
[2025-01-19 15:44:54 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][70/312]	eta 0:03:03 lr 0.000770	time 0.7216 (0.7585)	model_time 0.7214 (0.7412)	loss 1.9103 (2.9323)	grad_norm 2.0839 (1.9997/0.8211)	mem 34604MB
[2025-01-19 15:45:00 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][80/312]	eta 0:02:57 lr 0.000770	time 0.7798 (0.7651)	model_time 0.7794 (0.7490)	loss 3.4470 (2.7955)	grad_norm 1.0563 (2.1410/0.8805)	mem 34602MB
[2025-01-19 15:45:01 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][80/312]	eta 0:02:56 lr 0.000770	time 0.7339 (0.7607)	model_time 0.7334 (0.7455)	loss 1.7680 (2.8971)	grad_norm 1.4784 (2.1208/0.9340)	mem 34604MB
[2025-01-19 15:45:08 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][90/312]	eta 0:02:49 lr 0.000769	time 0.7181 (0.7616)	model_time 0.7177 (0.7472)	loss 2.6090 (2.8071)	grad_norm 0.9199 (2.0857/0.8719)	mem 34602MB
[2025-01-19 15:45:09 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][90/312]	eta 0:02:48 lr 0.000769	time 0.7176 (0.7611)	model_time 0.7172 (0.7476)	loss 3.6490 (2.8951)	grad_norm 3.7695 (2.1579/0.9432)	mem 34604MB
[2025-01-19 15:45:15 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][100/312]	eta 0:02:41 lr 0.000769	time 0.8100 (0.7595)	model_time 0.8098 (0.7465)	loss 3.4818 (2.8203)	grad_norm 1.0904 (2.0797/0.8465)	mem 34602MB
[2025-01-19 15:45:17 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][100/312]	eta 0:02:41 lr 0.000769	time 0.7454 (0.7601)	model_time 0.7449 (0.7478)	loss 2.9765 (2.8733)	grad_norm 3.3194 (2.1671/0.9383)	mem 34604MB
[2025-01-19 15:45:23 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][110/312]	eta 0:02:33 lr 0.000768	time 0.7407 (0.7581)	model_time 0.7403 (0.7463)	loss 3.2057 (2.8490)	grad_norm 2.3840 (2.0573/0.8264)	mem 34602MB
[2025-01-19 15:45:24 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][110/312]	eta 0:02:33 lr 0.000768	time 0.8240 (0.7578)	model_time 0.8236 (0.7466)	loss 3.5536 (2.8806)	grad_norm 2.4691 (2.1443/0.9088)	mem 34604MB
[2025-01-19 15:45:30 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][120/312]	eta 0:02:25 lr 0.000768	time 0.7092 (0.7563)	model_time 0.7087 (0.7454)	loss 2.5237 (2.8255)	grad_norm 1.6221 (2.0117/0.8136)	mem 34602MB
[2025-01-19 15:45:31 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][120/312]	eta 0:02:24 lr 0.000768	time 0.7133 (0.7550)	model_time 0.7128 (0.7447)	loss 3.2370 (2.8817)	grad_norm 1.8770 (2.1491/0.9628)	mem 34604MB
[2025-01-19 15:45:37 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][130/312]	eta 0:02:17 lr 0.000767	time 0.7378 (0.7563)	model_time 0.7377 (0.7462)	loss 3.0414 (2.8311)	grad_norm 2.9355 (1.9867/0.8002)	mem 34602MB
[2025-01-19 15:45:38 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][130/312]	eta 0:02:17 lr 0.000767	time 0.7164 (0.7529)	model_time 0.7162 (0.7434)	loss 3.1884 (2.8538)	grad_norm 1.9037 (2.1109/0.9447)	mem 34604MB
[2025-01-19 15:45:45 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][140/312]	eta 0:02:09 lr 0.000767	time 0.7337 (0.7547)	model_time 0.7335 (0.7453)	loss 2.6251 (2.8403)	grad_norm 2.0257 (1.9915/0.7822)	mem 34602MB
[2025-01-19 15:45:46 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][140/312]	eta 0:02:09 lr 0.000767	time 0.7213 (0.7511)	model_time 0.7212 (0.7422)	loss 2.9076 (2.8654)	grad_norm 1.9222 (2.0769/0.9266)	mem 34604MB
[2025-01-19 15:45:52 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][150/312]	eta 0:02:02 lr 0.000766	time 0.7382 (0.7533)	model_time 0.7377 (0.7445)	loss 3.2431 (2.8427)	grad_norm 1.7513 (1.9844/0.7779)	mem 34602MB
[2025-01-19 15:45:53 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][150/312]	eta 0:02:01 lr 0.000766	time 0.7223 (0.7491)	model_time 0.7218 (0.7408)	loss 3.1661 (2.8730)	grad_norm 2.9896 (2.0807/0.9014)	mem 34604MB
[2025-01-19 15:46:00 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][160/312]	eta 0:01:54 lr 0.000766	time 0.7170 (0.7532)	model_time 0.7168 (0.7449)	loss 3.2655 (2.8448)	grad_norm 1.4489 (1.9457/0.7745)	mem 34602MB
[2025-01-19 15:46:00 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][160/312]	eta 0:01:53 lr 0.000766	time 0.7349 (0.7480)	model_time 0.7345 (0.7401)	loss 2.7470 (2.8734)	grad_norm 3.2744 (2.0914/0.8920)	mem 34604MB
[2025-01-19 15:46:07 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][170/312]	eta 0:01:46 lr 0.000765	time 0.7192 (0.7534)	model_time 0.7190 (0.7456)	loss 3.3212 (2.8351)	grad_norm 1.9781 (1.9276/0.7650)	mem 34602MB
[2025-01-19 15:46:08 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][170/312]	eta 0:01:46 lr 0.000765	time 0.8172 (0.7495)	model_time 0.8168 (0.7421)	loss 3.0989 (2.8834)	grad_norm 1.5142 (2.1048/0.9020)	mem 34604MB
[2025-01-19 15:46:15 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][180/312]	eta 0:01:39 lr 0.000765	time 0.7208 (0.7539)	model_time 0.7204 (0.7465)	loss 2.5650 (2.8300)	grad_norm 0.9023 (1.9201/0.7535)	mem 34602MB
[2025-01-19 15:46:16 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][180/312]	eta 0:01:39 lr 0.000765	time 0.8148 (0.7510)	model_time 0.8147 (0.7440)	loss 2.7746 (2.8868)	grad_norm 1.1189 (2.0911/0.8922)	mem 34604MB
[2025-01-19 15:46:22 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][190/312]	eta 0:01:31 lr 0.000764	time 0.7165 (0.7532)	model_time 0.7163 (0.7462)	loss 2.8844 (2.8326)	grad_norm 1.2163 (1.8946/0.7461)	mem 34602MB
[2025-01-19 15:46:23 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][190/312]	eta 0:01:31 lr 0.000764	time 0.7169 (0.7499)	model_time 0.7167 (0.7432)	loss 3.0823 (2.8975)	grad_norm 1.4441 (2.0687/0.8788)	mem 34604MB
[2025-01-19 15:46:30 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][200/312]	eta 0:01:24 lr 0.000764	time 0.7256 (0.7537)	model_time 0.7251 (0.7470)	loss 3.4615 (2.8396)	grad_norm 4.9886 (1.9179/0.7776)	mem 34602MB
[2025-01-19 15:46:31 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][200/312]	eta 0:01:24 lr 0.000764	time 0.8047 (0.7518)	model_time 0.8043 (0.7454)	loss 2.4100 (2.8970)	grad_norm 1.2124 (2.0508/0.8683)	mem 34604MB
[2025-01-19 15:46:37 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][210/312]	eta 0:01:16 lr 0.000763	time 0.7183 (0.7533)	model_time 0.7181 (0.7469)	loss 3.1380 (2.8495)	grad_norm 1.3777 (1.9805/0.8634)	mem 34602MB
[2025-01-19 15:46:39 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][210/312]	eta 0:01:16 lr 0.000763	time 0.7137 (0.7523)	model_time 0.7135 (0.7463)	loss 2.5274 (2.8845)	grad_norm 1.3274 (2.0208/0.8603)	mem 34604MB
[2025-01-19 15:46:45 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][220/312]	eta 0:01:09 lr 0.000763	time 0.8136 (0.7527)	model_time 0.8134 (0.7466)	loss 2.9141 (2.8467)	grad_norm 2.2568 (1.9923/0.8808)	mem 34602MB
[2025-01-19 15:46:46 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][220/312]	eta 0:01:09 lr 0.000763	time 0.7168 (0.7528)	model_time 0.7164 (0.7470)	loss 2.5853 (2.8764)	grad_norm 1.4983 (2.0020/0.8522)	mem 34604MB
[2025-01-19 15:46:52 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][230/312]	eta 0:01:01 lr 0.000762	time 0.7239 (0.7525)	model_time 0.7235 (0.7466)	loss 3.0264 (2.8451)	grad_norm 2.5973 (1.9868/0.8727)	mem 34602MB
[2025-01-19 15:46:53 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][230/312]	eta 0:01:01 lr 0.000762	time 0.7234 (0.7518)	model_time 0.7232 (0.7462)	loss 2.6979 (2.8627)	grad_norm 1.7373 (1.9928/0.8458)	mem 34604MB
[2025-01-19 15:47:00 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][240/312]	eta 0:00:54 lr 0.000762	time 0.7300 (0.7517)	model_time 0.7299 (0.7461)	loss 2.0594 (2.8372)	grad_norm 2.3330 (1.9962/0.8654)	mem 34602MB
[2025-01-19 15:47:01 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][240/312]	eta 0:00:54 lr 0.000762	time 0.7234 (0.7511)	model_time 0.7230 (0.7457)	loss 2.1300 (2.8616)	grad_norm 1.5719 (1.9815/0.8335)	mem 34604MB
[2025-01-19 15:47:07 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][250/312]	eta 0:00:46 lr 0.000761	time 0.8141 (0.7517)	model_time 0.8139 (0.7462)	loss 3.4337 (2.8394)	grad_norm 1.7453 (1.9972/0.8553)	mem 34602MB
[2025-01-19 15:47:08 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][250/312]	eta 0:00:46 lr 0.000761	time 0.7168 (0.7504)	model_time 0.7167 (0.7452)	loss 2.1410 (2.8614)	grad_norm 1.5172 (1.9843/0.8360)	mem 34604MB
[2025-01-19 15:47:14 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][260/312]	eta 0:00:39 lr 0.000761	time 0.7199 (0.7509)	model_time 0.7194 (0.7457)	loss 2.8022 (2.8416)	grad_norm 2.5517 (2.0030/0.8700)	mem 34602MB
[2025-01-19 15:47:15 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][260/312]	eta 0:00:38 lr 0.000761	time 0.7157 (0.7496)	model_time 0.7156 (0.7446)	loss 3.6070 (2.8638)	grad_norm 2.5147 (1.9715/0.8290)	mem 34604MB
[2025-01-19 15:47:22 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][270/312]	eta 0:00:31 lr 0.000760	time 0.7241 (0.7506)	model_time 0.7239 (0.7455)	loss 1.9679 (2.8489)	grad_norm 2.1586 (2.0025/0.8635)	mem 34602MB
[2025-01-19 15:47:23 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][270/312]	eta 0:00:31 lr 0.000760	time 0.7217 (0.7487)	model_time 0.7212 (0.7438)	loss 1.9636 (2.8649)	grad_norm 2.0658 (1.9545/0.8254)	mem 34604MB
[2025-01-19 15:47:29 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][280/312]	eta 0:00:24 lr 0.000760	time 0.7174 (0.7507)	model_time 0.7173 (0.7458)	loss 3.0334 (2.8547)	grad_norm 1.3035 (2.0132/0.8605)	mem 34602MB
[2025-01-19 15:47:30 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][280/312]	eta 0:00:23 lr 0.000760	time 0.7257 (0.7479)	model_time 0.7254 (0.7432)	loss 2.9986 (2.8690)	grad_norm 1.1697 (1.9409/0.8189)	mem 34604MB
[2025-01-19 15:47:37 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][290/312]	eta 0:00:16 lr 0.000759	time 0.7280 (0.7510)	model_time 0.7278 (0.7462)	loss 3.0078 (2.8563)	grad_norm 0.9528 (2.0014/0.8551)	mem 34602MB
[2025-01-19 15:47:37 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][290/312]	eta 0:00:16 lr 0.000759	time 0.8080 (0.7477)	model_time 0.8075 (0.7432)	loss 3.1762 (2.8756)	grad_norm 1.2773 (1.9249/0.8121)	mem 34604MB
[2025-01-19 15:47:45 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][300/312]	eta 0:00:09 lr 0.000759	time 0.7138 (0.7516)	model_time 0.7136 (0.7470)	loss 2.0539 (2.8488)	grad_norm 1.7112 (1.9860/0.8470)	mem 34602MB
[2025-01-19 15:47:45 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][300/312]	eta 0:00:08 lr 0.000759	time 0.8010 (0.7489)	model_time 0.8009 (0.7445)	loss 2.4224 (2.8765)	grad_norm 3.5179 (1.9339/0.8089)	mem 34604MB
[2025-01-19 15:47:52 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][310/312]	eta 0:00:01 lr 0.000758	time 0.7052 (0.7506)	model_time 0.7051 (0.7462)	loss 3.1928 (2.8542)	grad_norm 0.8355 (1.9560/0.8259)	mem 34602MB
[2025-01-19 15:47:52 internimage_b_1k_224] (main.py 510): INFO Train: [215/300][310/312]	eta 0:00:01 lr 0.000758	time 0.7145 (0.7478)	model_time 0.7144 (0.7436)	loss 2.7627 (2.8659)	grad_norm 2.5306 (1.9377/0.8008)	mem 34604MB
[2025-01-19 15:47:53 internimage_b_1k_224] (main.py 519): INFO EPOCH 215 training takes 0:03:54
[2025-01-19 15:47:53 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_215.pth saving......
[2025-01-19 15:47:53 internimage_b_1k_224] (main.py 519): INFO EPOCH 215 training takes 0:03:53
[2025-01-19 15:47:53 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_215.pth saving......
[2025-01-19 15:47:56 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_215.pth saved !!!
[2025-01-19 15:47:56 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_215.pth saved !!!
[2025-01-19 15:48:12 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.996 (15.996)	Loss 0.7102 (0.7102)	Acc@1 85.767 (85.767)	Acc@5 97.632 (97.632)	Mem 34602MB
[2025-01-19 15:48:13 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.390 (16.390)	Loss 0.7228 (0.7228)	Acc@1 85.425 (85.425)	Acc@5 97.778 (97.778)	Mem 34604MB
[2025-01-19 15:48:19 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (2.138)	Loss 0.9209 (0.8104)	Acc@1 79.785 (83.243)	Acc@5 95.532 (96.589)	Mem 34602MB
[2025-01-19 15:48:20 internimage_b_1k_224] (main.py 575): INFO [Epoch:215] * Acc@1 83.097 Acc@5 96.603
[2025-01-19 15:48:20 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.1%
[2025-01-19 15:48:20 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 15:48:20 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.134)	Loss 0.9312 (0.8218)	Acc@1 79.883 (83.330)	Acc@5 95.801 (96.695)	Mem 34604MB
[2025-01-19 15:48:20 internimage_b_1k_224] (main.py 575): INFO [Epoch:215] * Acc@1 83.167 Acc@5 96.701
[2025-01-19 15:48:20 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.2%
[2025-01-19 15:48:20 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 15:48:23 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 15:48:23 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.10%
[2025-01-19 15:48:23 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 15:48:23 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.17%
[2025-01-19 15:48:40 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.478 (16.478)	Loss 0.7036 (0.7036)	Acc@1 85.840 (85.840)	Acc@5 98.193 (98.193)	Mem 34604MB
[2025-01-19 15:48:40 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.740 (16.740)	Loss 0.7120 (0.7120)	Acc@1 85.620 (85.620)	Acc@5 98.096 (98.096)	Mem 34602MB
[2025-01-19 15:48:47 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.147)	Loss 0.9429 (0.8124)	Acc@1 79.590 (83.489)	Acc@5 95.605 (96.709)	Mem 34602MB
[2025-01-19 15:48:47 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (2.130)	Loss 0.9411 (0.8100)	Acc@1 79.541 (83.538)	Acc@5 95.459 (96.684)	Mem 34604MB
[2025-01-19 15:48:47 internimage_b_1k_224] (main.py 575): INFO [Epoch:215] * Acc@1 83.343 Acc@5 96.755
[2025-01-19 15:48:47 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.3%
[2025-01-19 15:48:47 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:48:47 internimage_b_1k_224] (main.py 575): INFO [Epoch:215] * Acc@1 83.345 Acc@5 96.729
[2025-01-19 15:48:47 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.3%
[2025-01-19 15:48:47 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:48:50 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:48:50 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.35%
[2025-01-19 15:48:51 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:48:51 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.34%
[2025-01-19 15:48:52 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][0/312]	eta 0:10:33 lr 0.000758	time 2.0307 (2.0307)	model_time 0.7394 (0.7394)	loss 3.4764 (3.4764)	grad_norm 2.0353 (2.0353/0.0000)	mem 34604MB
[2025-01-19 15:48:53 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][0/312]	eta 0:11:16 lr 0.000758	time 2.1680 (2.1680)	model_time 0.7341 (0.7341)	loss 3.3993 (3.3993)	grad_norm 1.3857 (1.3857/0.0000)	mem 34602MB
[2025-01-19 15:49:00 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][10/312]	eta 0:04:23 lr 0.000757	time 0.7469 (0.8729)	model_time 0.7467 (0.7423)	loss 3.0536 (2.7746)	grad_norm 1.5833 (1.6634/0.5358)	mem 34602MB
[2025-01-19 15:49:00 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][10/312]	eta 0:04:32 lr 0.000757	time 0.8427 (0.9038)	model_time 0.8423 (0.7860)	loss 3.6904 (3.2107)	grad_norm 2.0673 (2.1047/1.0124)	mem 34604MB
[2025-01-19 15:49:08 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][20/312]	eta 0:03:58 lr 0.000757	time 0.7369 (0.8157)	model_time 0.7368 (0.7471)	loss 2.3488 (2.8986)	grad_norm 3.3381 (2.1578/0.9769)	mem 34602MB
[2025-01-19 15:49:08 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][20/312]	eta 0:04:05 lr 0.000757	time 0.7375 (0.8409)	model_time 0.7371 (0.7790)	loss 2.7577 (3.0116)	grad_norm 1.2858 (2.0557/0.9104)	mem 34604MB
[2025-01-19 15:49:15 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][30/312]	eta 0:03:42 lr 0.000756	time 0.7188 (0.7896)	model_time 0.7187 (0.7431)	loss 2.4817 (2.8475)	grad_norm 2.0156 (1.9813/0.9205)	mem 34602MB
[2025-01-19 15:49:16 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][30/312]	eta 0:03:49 lr 0.000756	time 0.8011 (0.8129)	model_time 0.8010 (0.7709)	loss 3.1829 (3.0570)	grad_norm 3.0176 (2.0283/0.8877)	mem 34604MB
[2025-01-19 15:49:23 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][40/312]	eta 0:03:32 lr 0.000756	time 0.7240 (0.7813)	model_time 0.7238 (0.7460)	loss 2.9503 (2.8463)	grad_norm 1.6288 (1.8036/0.8687)	mem 34602MB
[2025-01-19 15:49:23 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][40/312]	eta 0:03:35 lr 0.000756	time 0.7410 (0.7939)	model_time 0.7408 (0.7621)	loss 3.5333 (3.0309)	grad_norm 1.1430 (2.0493/0.8898)	mem 34604MB
[2025-01-19 15:49:30 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][50/312]	eta 0:03:22 lr 0.000755	time 0.7183 (0.7727)	model_time 0.7181 (0.7443)	loss 3.2837 (2.8688)	grad_norm 1.6028 (1.8149/0.8161)	mem 34602MB
[2025-01-19 15:49:30 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][50/312]	eta 0:03:24 lr 0.000755	time 0.7222 (0.7810)	model_time 0.7216 (0.7553)	loss 3.0211 (2.9635)	grad_norm 2.4620 (2.0667/0.8473)	mem 34604MB
[2025-01-19 15:49:37 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][60/312]	eta 0:03:13 lr 0.000755	time 0.7180 (0.7681)	model_time 0.7175 (0.7443)	loss 2.3937 (2.8424)	grad_norm 2.2830 (1.8066/0.7818)	mem 34602MB
[2025-01-19 15:49:38 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][60/312]	eta 0:03:14 lr 0.000755	time 0.7295 (0.7730)	model_time 0.7291 (0.7514)	loss 2.7959 (2.9530)	grad_norm 1.4777 (1.9872/0.8276)	mem 34604MB
[2025-01-19 15:49:45 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][70/312]	eta 0:03:04 lr 0.000754	time 0.7186 (0.7639)	model_time 0.7185 (0.7434)	loss 1.9539 (2.8434)	grad_norm 2.3517 (1.8434/0.7985)	mem 34602MB
[2025-01-19 15:49:52 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][80/312]	eta 0:02:56 lr 0.000754	time 0.7406 (0.7614)	model_time 0.7402 (0.7451)	loss 3.3072 (2.9408)	grad_norm 1.1924 (1.9375/0.8297)	mem 34604MB
[2025-01-19 15:49:52 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][80/312]	eta 0:02:56 lr 0.000754	time 0.7212 (0.7598)	model_time 0.7206 (0.7418)	loss 3.2474 (2.8556)	grad_norm 1.4269 (1.8442/0.7939)	mem 34602MB
[2025-01-19 15:49:59 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][90/312]	eta 0:02:48 lr 0.000753	time 0.7221 (0.7580)	model_time 0.7220 (0.7434)	loss 3.1783 (2.9065)	grad_norm 1.5808 (1.9745/0.8384)	mem 34604MB
[2025-01-19 15:50:00 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][90/312]	eta 0:02:48 lr 0.000753	time 0.8084 (0.7598)	model_time 0.8083 (0.7437)	loss 3.3963 (2.8355)	grad_norm 2.2897 (1.8533/0.7730)	mem 34602MB
[2025-01-19 15:50:07 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][100/312]	eta 0:02:40 lr 0.000753	time 0.7252 (0.7564)	model_time 0.7251 (0.7433)	loss 2.6601 (2.8780)	grad_norm 2.1619 (1.9706/0.8121)	mem 34604MB
[2025-01-19 15:50:07 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][100/312]	eta 0:02:41 lr 0.000753	time 0.8126 (0.7609)	model_time 0.8121 (0.7464)	loss 2.8506 (2.8235)	grad_norm 2.4572 (1.8637/0.7727)	mem 34602MB
[2025-01-19 15:50:15 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][110/312]	eta 0:02:33 lr 0.000752	time 0.7578 (0.7587)	model_time 0.7573 (0.7467)	loss 2.9879 (2.8716)	grad_norm 1.5719 (1.9848/0.8014)	mem 34604MB
[2025-01-19 15:50:15 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][110/312]	eta 0:02:33 lr 0.000752	time 0.7242 (0.7603)	model_time 0.7237 (0.7470)	loss 3.4573 (2.8426)	grad_norm 1.9301 (1.8965/0.7890)	mem 34602MB
[2025-01-19 15:50:22 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][120/312]	eta 0:02:25 lr 0.000752	time 0.7074 (0.7567)	model_time 0.7070 (0.7457)	loss 1.6920 (2.8722)	grad_norm 2.2513 (1.9854/0.7834)	mem 34604MB
[2025-01-19 15:50:22 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][120/312]	eta 0:02:25 lr 0.000752	time 0.8386 (0.7589)	model_time 0.8381 (0.7467)	loss 3.1752 (2.8314)	grad_norm 1.2862 (1.8790/0.7734)	mem 34602MB
[2025-01-19 15:50:30 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][130/312]	eta 0:02:17 lr 0.000751	time 0.7152 (0.7574)	model_time 0.7151 (0.7461)	loss 2.8551 (2.8398)	grad_norm 3.3839 (1.8758/0.7702)	mem 34602MB
[2025-01-19 15:50:30 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][130/312]	eta 0:02:18 lr 0.000751	time 0.8063 (0.7594)	model_time 0.8058 (0.7491)	loss 3.0482 (2.8680)	grad_norm 1.3691 (1.9456/0.7726)	mem 34604MB
[2025-01-19 15:50:37 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][140/312]	eta 0:02:10 lr 0.000751	time 0.7172 (0.7565)	model_time 0.7168 (0.7460)	loss 2.3102 (2.8234)	grad_norm 2.0676 (1.9182/0.7884)	mem 34602MB
[2025-01-19 15:50:37 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][140/312]	eta 0:02:10 lr 0.000751	time 0.7391 (0.7596)	model_time 0.7387 (0.7501)	loss 2.9970 (2.8862)	grad_norm 1.5746 (1.9125/0.7714)	mem 34604MB
[2025-01-19 15:50:45 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][150/312]	eta 0:02:02 lr 0.000750	time 0.7203 (0.7548)	model_time 0.7201 (0.7450)	loss 2.8832 (2.8322)	grad_norm 2.5592 (1.9116/0.8001)	mem 34602MB
[2025-01-19 15:50:45 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][150/312]	eta 0:02:03 lr 0.000750	time 0.8027 (0.7593)	model_time 0.8026 (0.7504)	loss 2.9738 (2.8835)	grad_norm 2.4386 (1.9088/0.7595)	mem 34604MB
[2025-01-19 15:50:52 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][160/312]	eta 0:01:54 lr 0.000750	time 0.7975 (0.7546)	model_time 0.7970 (0.7453)	loss 2.0799 (2.8186)	grad_norm 1.2752 (1.9098/0.7883)	mem 34602MB
[2025-01-19 15:50:52 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][160/312]	eta 0:01:55 lr 0.000750	time 0.7172 (0.7570)	model_time 0.7167 (0.7486)	loss 3.1801 (2.8848)	grad_norm 1.6965 (1.9057/0.7390)	mem 34604MB
[2025-01-19 15:50:59 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][170/312]	eta 0:01:46 lr 0.000749	time 0.8068 (0.7535)	model_time 0.8067 (0.7447)	loss 2.9377 (2.8258)	grad_norm 3.1096 (1.9031/0.7805)	mem 34602MB
[2025-01-19 15:51:00 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][170/312]	eta 0:01:47 lr 0.000749	time 0.7263 (0.7559)	model_time 0.7258 (0.7480)	loss 3.1671 (2.8882)	grad_norm 0.7660 (1.8953/0.7440)	mem 34604MB
[2025-01-19 15:51:07 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][180/312]	eta 0:01:39 lr 0.000749	time 0.7151 (0.7541)	model_time 0.7150 (0.7466)	loss 2.6923 (2.8882)	grad_norm 1.9700 (1.9078/0.7358)	mem 34604MB
[2025-01-19 15:51:07 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][180/312]	eta 0:01:39 lr 0.000749	time 0.7192 (0.7535)	model_time 0.7190 (0.7453)	loss 2.7447 (2.8393)	grad_norm 2.0807 (1.8897/0.7680)	mem 34602MB
[2025-01-19 15:51:14 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][190/312]	eta 0:01:31 lr 0.000748	time 0.7235 (0.7526)	model_time 0.7234 (0.7455)	loss 2.2177 (2.8909)	grad_norm 4.2952 (1.9681/0.8278)	mem 34604MB
[2025-01-19 15:51:14 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][190/312]	eta 0:01:31 lr 0.000748	time 0.7237 (0.7528)	model_time 0.7232 (0.7449)	loss 2.9251 (2.8433)	grad_norm 3.1395 (1.9127/0.8034)	mem 34602MB
[2025-01-19 15:51:21 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][200/312]	eta 0:01:24 lr 0.000748	time 0.7608 (0.7516)	model_time 0.7607 (0.7448)	loss 3.2896 (2.8891)	grad_norm 2.3912 (1.9985/0.8489)	mem 34604MB
[2025-01-19 15:51:22 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][200/312]	eta 0:01:24 lr 0.000748	time 0.8040 (0.7517)	model_time 0.8038 (0.7442)	loss 2.4655 (2.8503)	grad_norm 2.1529 (1.8981/0.7928)	mem 34602MB
[2025-01-19 15:51:29 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][210/312]	eta 0:01:16 lr 0.000747	time 0.7290 (0.7504)	model_time 0.7286 (0.7439)	loss 3.1764 (2.8870)	grad_norm 2.4375 (1.9882/0.8477)	mem 34604MB
[2025-01-19 15:51:29 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][210/312]	eta 0:01:16 lr 0.000747	time 0.8374 (0.7521)	model_time 0.8373 (0.7450)	loss 3.4828 (2.8436)	grad_norm 3.3646 (1.9305/0.8163)	mem 34602MB
[2025-01-19 15:51:36 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][220/312]	eta 0:01:09 lr 0.000747	time 0.7141 (0.7503)	model_time 0.7140 (0.7441)	loss 3.2207 (2.8893)	grad_norm 1.8695 (1.9999/0.8498)	mem 34604MB
[2025-01-19 15:51:37 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][220/312]	eta 0:01:09 lr 0.000747	time 0.8986 (0.7529)	model_time 0.8985 (0.7461)	loss 2.2626 (2.8478)	grad_norm 3.4757 (1.9514/0.8355)	mem 34602MB
[2025-01-19 15:51:44 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][230/312]	eta 0:01:01 lr 0.000746	time 0.8103 (0.7524)	model_time 0.8097 (0.7464)	loss 2.6729 (2.8908)	grad_norm 3.0870 (2.0162/0.8524)	mem 34604MB
[2025-01-19 15:51:44 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][230/312]	eta 0:01:01 lr 0.000746	time 0.8111 (0.7529)	model_time 0.8109 (0.7464)	loss 2.8396 (2.8522)	grad_norm 1.5075 (1.9527/0.8391)	mem 34602MB
[2025-01-19 15:51:51 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][240/312]	eta 0:00:54 lr 0.000746	time 0.7167 (0.7512)	model_time 0.7165 (0.7455)	loss 3.5955 (2.8956)	grad_norm 1.3679 (2.0015/0.8496)	mem 34604MB
[2025-01-19 15:51:52 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][240/312]	eta 0:00:54 lr 0.000746	time 0.8224 (0.7522)	model_time 0.8219 (0.7459)	loss 3.2183 (2.8550)	grad_norm 1.7337 (1.9606/0.8427)	mem 34602MB
[2025-01-19 15:51:59 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][250/312]	eta 0:00:46 lr 0.000745	time 0.7178 (0.7521)	model_time 0.7177 (0.7461)	loss 3.2521 (2.8613)	grad_norm 1.8768 (1.9649/0.8449)	mem 34602MB
[2025-01-19 15:52:00 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][250/312]	eta 0:00:46 lr 0.000745	time 0.8074 (0.7536)	model_time 0.8070 (0.7480)	loss 3.1158 (2.8886)	grad_norm 1.0312 (1.9963/0.8447)	mem 34604MB
[2025-01-19 15:52:07 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][260/312]	eta 0:00:39 lr 0.000745	time 0.8324 (0.7520)	model_time 0.8322 (0.7462)	loss 3.3019 (2.8568)	grad_norm 1.4887 (1.9697/0.8418)	mem 34602MB
[2025-01-19 15:52:07 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][260/312]	eta 0:00:39 lr 0.000745	time 0.7271 (0.7544)	model_time 0.7269 (0.7491)	loss 3.3856 (2.8819)	grad_norm 1.3548 (1.9803/0.8389)	mem 34604MB
[2025-01-19 15:52:14 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][270/312]	eta 0:00:31 lr 0.000744	time 0.7275 (0.7515)	model_time 0.7270 (0.7458)	loss 2.1886 (2.8609)	grad_norm 1.9813 (1.9730/0.8417)	mem 34602MB
[2025-01-19 15:52:15 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][270/312]	eta 0:00:31 lr 0.000744	time 0.8111 (0.7542)	model_time 0.8110 (0.7490)	loss 2.2393 (2.8799)	grad_norm 1.4046 (1.9852/0.8455)	mem 34604MB
[2025-01-19 15:52:22 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][280/312]	eta 0:00:24 lr 0.000744	time 0.7786 (0.7515)	model_time 0.7784 (0.7460)	loss 3.4387 (2.8708)	grad_norm 3.0046 (1.9834/0.8437)	mem 34602MB
[2025-01-19 15:52:22 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][280/312]	eta 0:00:24 lr 0.000744	time 0.7211 (0.7532)	model_time 0.7210 (0.7482)	loss 1.6902 (2.8682)	grad_norm 2.9582 (1.9924/0.8459)	mem 34604MB
[2025-01-19 15:52:29 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][290/312]	eta 0:00:16 lr 0.000743	time 0.8157 (0.7509)	model_time 0.8153 (0.7457)	loss 2.9725 (2.8735)	grad_norm 2.8827 (1.9796/0.8345)	mem 34602MB
[2025-01-19 15:52:29 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][290/312]	eta 0:00:16 lr 0.000743	time 0.7174 (0.7525)	model_time 0.7170 (0.7477)	loss 2.9947 (2.8644)	grad_norm 0.9329 (1.9757/0.8404)	mem 34604MB
[2025-01-19 15:52:36 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][300/312]	eta 0:00:09 lr 0.000743	time 0.7139 (0.7501)	model_time 0.7138 (0.7450)	loss 2.8935 (2.8691)	grad_norm 1.5295 (1.9795/0.8283)	mem 34602MB
[2025-01-19 15:52:37 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][300/312]	eta 0:00:09 lr 0.000743	time 0.7144 (0.7516)	model_time 0.7143 (0.7469)	loss 1.6890 (2.8638)	grad_norm 3.5319 (1.9879/0.8541)	mem 34604MB
[2025-01-19 15:52:44 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][310/312]	eta 0:00:01 lr 0.000742	time 0.7112 (0.7497)	model_time 0.7111 (0.7448)	loss 3.2226 (2.8747)	grad_norm 2.1283 (2.0039/0.8394)	mem 34602MB
[2025-01-19 15:52:44 internimage_b_1k_224] (main.py 510): INFO Train: [216/300][310/312]	eta 0:00:01 lr 0.000742	time 0.7154 (0.7504)	model_time 0.7153 (0.7459)	loss 3.3304 (2.8727)	grad_norm 1.2161 (2.0039/0.8820)	mem 34604MB
[2025-01-19 15:52:44 internimage_b_1k_224] (main.py 519): INFO EPOCH 216 training takes 0:03:53
[2025-01-19 15:52:44 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_216.pth saving......
[2025-01-19 15:52:44 internimage_b_1k_224] (main.py 519): INFO EPOCH 216 training takes 0:03:54
[2025-01-19 15:52:44 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_216.pth saving......
[2025-01-19 15:52:47 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_216.pth saved !!!
[2025-01-19 15:52:47 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_216.pth saved !!!
[2025-01-19 15:53:04 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.766 (16.766)	Loss 0.7334 (0.7334)	Acc@1 85.742 (85.742)	Acc@5 97.705 (97.705)	Mem 34604MB
[2025-01-19 15:53:05 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.434 (17.434)	Loss 0.7312 (0.7312)	Acc@1 85.156 (85.156)	Acc@5 97.461 (97.461)	Mem 34602MB
[2025-01-19 15:53:12 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.192)	Loss 0.9788 (0.8430)	Acc@1 79.443 (83.401)	Acc@5 95.142 (96.502)	Mem 34604MB
[2025-01-19 15:53:12 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.196)	Loss 0.9555 (0.8198)	Acc@1 79.297 (83.365)	Acc@5 95.581 (96.584)	Mem 34602MB
[2025-01-19 15:53:12 internimage_b_1k_224] (main.py 575): INFO [Epoch:216] * Acc@1 83.235 Acc@5 96.529
[2025-01-19 15:53:12 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.2%
[2025-01-19 15:53:12 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 15:53:12 internimage_b_1k_224] (main.py 575): INFO [Epoch:216] * Acc@1 83.147 Acc@5 96.565
[2025-01-19 15:53:12 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.1%
[2025-01-19 15:53:12 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 15:53:15 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 15:53:15 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.24%
[2025-01-19 15:53:15 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 15:53:15 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.15%
[2025-01-19 15:53:32 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.507 (16.507)	Loss 0.7041 (0.7041)	Acc@1 85.864 (85.864)	Acc@5 98.193 (98.193)	Mem 34604MB
[2025-01-19 15:53:32 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.941 (16.941)	Loss 0.7126 (0.7126)	Acc@1 85.669 (85.669)	Acc@5 98.096 (98.096)	Mem 34602MB
[2025-01-19 15:53:39 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (2.152)	Loss 0.9408 (0.8101)	Acc@1 79.541 (83.574)	Acc@5 95.483 (96.713)	Mem 34604MB
[2025-01-19 15:53:39 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.168)	Loss 0.9424 (0.8124)	Acc@1 79.614 (83.529)	Acc@5 95.581 (96.726)	Mem 34602MB
[2025-01-19 15:53:39 internimage_b_1k_224] (main.py 575): INFO [Epoch:216] * Acc@1 83.381 Acc@5 96.761
[2025-01-19 15:53:39 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.4%
[2025-01-19 15:53:39 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:53:39 internimage_b_1k_224] (main.py 575): INFO [Epoch:216] * Acc@1 83.375 Acc@5 96.769
[2025-01-19 15:53:39 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.4%
[2025-01-19 15:53:39 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:53:43 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:53:43 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.38%
[2025-01-19 15:53:43 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:53:43 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.38%
[2025-01-19 15:53:45 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][0/312]	eta 0:10:29 lr 0.000742	time 2.0181 (2.0181)	model_time 0.7337 (0.7337)	loss 2.8231 (2.8231)	grad_norm 2.3293 (2.3293/0.0000)	mem 34604MB
[2025-01-19 15:53:45 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][0/312]	eta 0:10:55 lr 0.000742	time 2.1014 (2.1014)	model_time 0.7482 (0.7482)	loss 3.3576 (3.3576)	grad_norm 1.6629 (1.6629/0.0000)	mem 34602MB
[2025-01-19 15:53:52 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][10/312]	eta 0:04:15 lr 0.000741	time 0.7337 (0.8460)	model_time 0.7336 (0.7289)	loss 3.3767 (2.8771)	grad_norm 2.7974 (2.0088/0.5179)	mem 34604MB
[2025-01-19 15:53:53 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][10/312]	eta 0:04:21 lr 0.000741	time 0.7174 (0.8665)	model_time 0.7173 (0.7432)	loss 3.6106 (2.9784)	grad_norm 3.4845 (2.0593/0.8850)	mem 34602MB
[2025-01-19 15:53:59 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][20/312]	eta 0:03:50 lr 0.000741	time 0.7350 (0.7901)	model_time 0.7346 (0.7286)	loss 3.0626 (2.9494)	grad_norm 1.7583 (1.9338/0.6016)	mem 34604MB
[2025-01-19 15:54:00 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][20/312]	eta 0:03:57 lr 0.000741	time 0.7247 (0.8127)	model_time 0.7243 (0.7479)	loss 2.2445 (2.8121)	grad_norm 3.5399 (2.2320/1.0046)	mem 34602MB
[2025-01-19 15:54:07 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][30/312]	eta 0:03:39 lr 0.000740	time 0.7206 (0.7767)	model_time 0.7201 (0.7349)	loss 3.3993 (2.8213)	grad_norm 1.7390 (1.9328/0.6838)	mem 34604MB
[2025-01-19 15:54:08 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][30/312]	eta 0:03:45 lr 0.000740	time 0.8012 (0.7981)	model_time 0.8010 (0.7542)	loss 3.3072 (2.8591)	grad_norm 0.9190 (2.0849/0.9482)	mem 34602MB
[2025-01-19 15:54:15 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][40/312]	eta 0:03:33 lr 0.000740	time 0.8042 (0.7834)	model_time 0.8041 (0.7517)	loss 2.8236 (2.8548)	grad_norm 0.8382 (1.8813/0.6430)	mem 34604MB
[2025-01-19 15:54:15 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][40/312]	eta 0:03:34 lr 0.000740	time 0.7194 (0.7893)	model_time 0.7190 (0.7559)	loss 3.4232 (2.8278)	grad_norm 1.3887 (2.0273/0.9583)	mem 34602MB
[2025-01-19 15:54:22 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][50/312]	eta 0:03:22 lr 0.000739	time 0.7149 (0.7737)	model_time 0.7144 (0.7481)	loss 3.3828 (2.8323)	grad_norm 3.2920 (2.0824/0.8567)	mem 34604MB
[2025-01-19 15:54:23 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][50/312]	eta 0:03:24 lr 0.000739	time 0.7182 (0.7793)	model_time 0.7180 (0.7524)	loss 3.0083 (2.8573)	grad_norm 1.0583 (1.9859/0.9325)	mem 34602MB
[2025-01-19 15:54:30 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][60/312]	eta 0:03:15 lr 0.000739	time 0.8096 (0.7741)	model_time 0.8095 (0.7527)	loss 2.9681 (2.8436)	grad_norm 2.8290 (2.1397/0.8638)	mem 34604MB
[2025-01-19 15:54:30 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][60/312]	eta 0:03:15 lr 0.000739	time 0.7293 (0.7771)	model_time 0.7288 (0.7546)	loss 2.8811 (2.8514)	grad_norm 2.4461 (1.9956/0.8840)	mem 34602MB
[2025-01-19 15:54:38 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][70/312]	eta 0:03:06 lr 0.000738	time 0.7157 (0.7715)	model_time 0.7155 (0.7530)	loss 2.9638 (2.8553)	grad_norm 3.4192 (2.2560/0.9400)	mem 34604MB
[2025-01-19 15:54:38 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][70/312]	eta 0:03:06 lr 0.000738	time 0.8225 (0.7726)	model_time 0.8220 (0.7532)	loss 3.3414 (2.8372)	grad_norm 1.3559 (2.0760/0.9495)	mem 34602MB
[2025-01-19 15:54:45 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][80/312]	eta 0:02:58 lr 0.000738	time 0.8342 (0.7692)	model_time 0.8338 (0.7530)	loss 1.9818 (2.8395)	grad_norm 1.4196 (2.1937/0.9169)	mem 34604MB
[2025-01-19 15:54:45 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][80/312]	eta 0:02:58 lr 0.000738	time 0.7254 (0.7692)	model_time 0.7252 (0.7521)	loss 2.2420 (2.8227)	grad_norm 1.4858 (2.1359/0.9888)	mem 34602MB
[2025-01-19 15:54:52 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][90/312]	eta 0:02:49 lr 0.000737	time 0.7635 (0.7651)	model_time 0.7630 (0.7506)	loss 3.3911 (2.8358)	grad_norm 1.1604 (2.1569/0.9010)	mem 34604MB
[2025-01-19 15:54:53 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][90/312]	eta 0:02:49 lr 0.000737	time 0.7228 (0.7655)	model_time 0.7223 (0.7503)	loss 2.2954 (2.8255)	grad_norm 1.3031 (2.1410/0.9750)	mem 34602MB
[2025-01-19 15:55:00 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][100/312]	eta 0:02:41 lr 0.000737	time 0.7279 (0.7613)	model_time 0.7278 (0.7483)	loss 2.7650 (2.8157)	grad_norm 4.2510 (2.2203/0.9884)	mem 34604MB
[2025-01-19 15:55:00 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][100/312]	eta 0:02:41 lr 0.000737	time 0.7365 (0.7615)	model_time 0.7364 (0.7477)	loss 3.2974 (2.8648)	grad_norm 1.8770 (2.1522/0.9421)	mem 34602MB
[2025-01-19 15:55:07 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][110/312]	eta 0:02:33 lr 0.000736	time 0.7224 (0.7596)	model_time 0.7219 (0.7476)	loss 3.7434 (2.8362)	grad_norm 3.0643 (2.3116/1.0043)	mem 34604MB
[2025-01-19 15:55:07 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][110/312]	eta 0:02:33 lr 0.000736	time 0.7214 (0.7604)	model_time 0.7209 (0.7479)	loss 3.6181 (2.8761)	grad_norm 3.4440 (2.1386/0.9315)	mem 34602MB
[2025-01-19 15:55:14 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][120/312]	eta 0:02:25 lr 0.000736	time 0.7158 (0.7574)	model_time 0.7154 (0.7464)	loss 3.3514 (2.8328)	grad_norm 0.9426 (2.2603/0.9922)	mem 34604MB
[2025-01-19 15:55:15 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][120/312]	eta 0:02:25 lr 0.000736	time 0.7218 (0.7587)	model_time 0.7216 (0.7471)	loss 2.7943 (2.8733)	grad_norm 3.0271 (2.1210/0.9123)	mem 34602MB
[2025-01-19 15:55:22 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][130/312]	eta 0:02:17 lr 0.000735	time 0.7453 (0.7551)	model_time 0.7451 (0.7449)	loss 3.1438 (2.8378)	grad_norm 2.5889 (2.2705/0.9608)	mem 34604MB
[2025-01-19 15:55:22 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][130/312]	eta 0:02:17 lr 0.000735	time 0.7171 (0.7577)	model_time 0.7169 (0.7470)	loss 3.5236 (2.8683)	grad_norm 1.1721 (2.0721/0.9005)	mem 34602MB
[2025-01-19 15:55:29 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][140/312]	eta 0:02:09 lr 0.000735	time 0.7225 (0.7534)	model_time 0.7223 (0.7439)	loss 3.0971 (2.8521)	grad_norm 1.4964 (2.2588/0.9430)	mem 34604MB
[2025-01-19 15:55:30 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][140/312]	eta 0:02:10 lr 0.000735	time 0.8119 (0.7589)	model_time 0.8117 (0.7490)	loss 2.3830 (2.8638)	grad_norm 0.9545 (2.0490/0.8811)	mem 34602MB
[2025-01-19 15:55:36 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][150/312]	eta 0:02:01 lr 0.000734	time 0.7161 (0.7526)	model_time 0.7159 (0.7437)	loss 3.0184 (2.8582)	grad_norm 1.3519 (2.2639/0.9415)	mem 34604MB
[2025-01-19 15:55:38 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][150/312]	eta 0:02:02 lr 0.000734	time 0.8043 (0.7584)	model_time 0.8041 (0.7491)	loss 2.4101 (2.8398)	grad_norm 2.6019 (2.0172/0.8683)	mem 34602MB
[2025-01-19 15:55:44 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][160/312]	eta 0:01:54 lr 0.000734	time 0.7219 (0.7557)	model_time 0.7218 (0.7474)	loss 2.7510 (2.8553)	grad_norm 1.5952 (2.2801/0.9363)	mem 34604MB
[2025-01-19 15:55:45 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][160/312]	eta 0:01:55 lr 0.000734	time 0.8072 (0.7581)	model_time 0.8071 (0.7493)	loss 2.0318 (2.8333)	grad_norm 2.0190 (1.9907/0.8531)	mem 34602MB
[2025-01-19 15:55:52 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][170/312]	eta 0:01:47 lr 0.000733	time 0.7148 (0.7551)	model_time 0.7147 (0.7472)	loss 3.1477 (2.8622)	grad_norm 1.4695 (2.2626/0.9204)	mem 34604MB
[2025-01-19 15:55:53 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][170/312]	eta 0:01:47 lr 0.000733	time 0.7171 (0.7578)	model_time 0.7167 (0.7495)	loss 2.9203 (2.8340)	grad_norm 2.4563 (1.9933/0.8415)	mem 34602MB
[2025-01-19 15:56:00 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][180/312]	eta 0:01:39 lr 0.000733	time 0.8148 (0.7561)	model_time 0.8143 (0.7486)	loss 2.5247 (2.8736)	grad_norm 2.3173 (2.2681/0.9133)	mem 34604MB
[2025-01-19 15:56:00 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][180/312]	eta 0:01:39 lr 0.000733	time 0.7235 (0.7574)	model_time 0.7234 (0.7496)	loss 2.6296 (2.8405)	grad_norm 1.0536 (1.9779/0.8372)	mem 34602MB
[2025-01-19 15:56:07 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][190/312]	eta 0:01:32 lr 0.000732	time 0.7117 (0.7566)	model_time 0.7115 (0.7496)	loss 3.6654 (2.8785)	grad_norm 3.0513 (2.2609/0.9088)	mem 34604MB
[2025-01-19 15:56:07 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][190/312]	eta 0:01:32 lr 0.000732	time 0.7200 (0.7563)	model_time 0.7195 (0.7488)	loss 1.6927 (2.8508)	grad_norm 2.3653 (1.9566/0.8274)	mem 34602MB
[2025-01-19 15:56:15 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][200/312]	eta 0:01:24 lr 0.000732	time 0.7308 (0.7559)	model_time 0.7304 (0.7491)	loss 1.8513 (2.8616)	grad_norm 2.2146 (2.2683/0.9015)	mem 34604MB
[2025-01-19 15:56:15 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][200/312]	eta 0:01:24 lr 0.000732	time 0.7179 (0.7565)	model_time 0.7177 (0.7494)	loss 2.9776 (2.8554)	grad_norm 0.7395 (1.9581/0.8380)	mem 34602MB
[2025-01-19 15:56:22 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][210/312]	eta 0:01:17 lr 0.000731	time 0.7114 (0.7556)	model_time 0.7110 (0.7491)	loss 2.0004 (2.8623)	grad_norm 1.1759 (2.2286/0.9029)	mem 34604MB
[2025-01-19 15:56:22 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][210/312]	eta 0:01:17 lr 0.000731	time 0.7167 (0.7556)	model_time 0.7163 (0.7489)	loss 3.0735 (2.8566)	grad_norm 3.5421 (1.9598/0.8306)	mem 34602MB
[2025-01-19 15:56:30 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][220/312]	eta 0:01:09 lr 0.000731	time 0.7365 (0.7547)	model_time 0.7364 (0.7486)	loss 3.1508 (2.8668)	grad_norm 2.3936 (2.2107/0.8941)	mem 34604MB
[2025-01-19 15:56:30 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][220/312]	eta 0:01:09 lr 0.000731	time 0.7289 (0.7544)	model_time 0.7287 (0.7479)	loss 3.5415 (2.8573)	grad_norm 1.7157 (1.9643/0.8258)	mem 34602MB
[2025-01-19 15:56:37 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][230/312]	eta 0:01:01 lr 0.000730	time 0.7146 (0.7537)	model_time 0.7145 (0.7478)	loss 2.7725 (2.8775)	grad_norm 5.0935 (2.2592/0.9239)	mem 34604MB
[2025-01-19 15:56:37 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][230/312]	eta 0:01:01 lr 0.000730	time 0.7189 (0.7541)	model_time 0.7187 (0.7479)	loss 3.3243 (2.8474)	grad_norm 1.6609 (1.9817/0.8401)	mem 34602MB
[2025-01-19 15:56:44 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][240/312]	eta 0:00:54 lr 0.000730	time 0.7234 (0.7527)	model_time 0.7233 (0.7470)	loss 3.0295 (2.8782)	grad_norm 1.9173 (2.2759/0.9274)	mem 34604MB
[2025-01-19 15:56:45 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][240/312]	eta 0:00:54 lr 0.000730	time 0.7276 (0.7538)	model_time 0.7274 (0.7478)	loss 3.0843 (2.8478)	grad_norm 3.4155 (1.9825/0.8331)	mem 34602MB
[2025-01-19 15:56:51 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][250/312]	eta 0:00:46 lr 0.000729	time 0.7166 (0.7517)	model_time 0.7164 (0.7462)	loss 2.8002 (2.8751)	grad_norm 1.5305 (2.2406/0.9264)	mem 34604MB
[2025-01-19 15:56:52 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][250/312]	eta 0:00:46 lr 0.000729	time 0.7343 (0.7529)	model_time 0.7342 (0.7471)	loss 3.1900 (2.8503)	grad_norm 1.2304 (2.0007/0.8277)	mem 34602MB
[2025-01-19 15:56:59 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][260/312]	eta 0:00:39 lr 0.000729	time 0.7553 (0.7508)	model_time 0.7549 (0.7456)	loss 2.9221 (2.8827)	grad_norm 2.1486 (2.2147/0.9207)	mem 34604MB
[2025-01-19 15:57:00 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][260/312]	eta 0:00:39 lr 0.000729	time 0.8143 (0.7529)	model_time 0.8141 (0.7474)	loss 2.6392 (2.8525)	grad_norm 1.3668 (1.9970/0.8198)	mem 34602MB
[2025-01-19 15:57:06 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][270/312]	eta 0:00:31 lr 0.000728	time 0.7544 (0.7507)	model_time 0.7543 (0.7456)	loss 2.7435 (2.8805)	grad_norm 1.3758 (2.1894/0.9137)	mem 34604MB
[2025-01-19 15:57:07 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][270/312]	eta 0:00:31 lr 0.000728	time 0.7956 (0.7532)	model_time 0.7952 (0.7478)	loss 1.7931 (2.8512)	grad_norm 1.1745 (1.9889/0.8189)	mem 34602MB
[2025-01-19 15:57:14 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][280/312]	eta 0:00:24 lr 0.000728	time 0.7623 (0.7527)	model_time 0.7622 (0.7478)	loss 3.2344 (2.8824)	grad_norm 2.7065 (2.1812/0.9022)	mem 34604MB
[2025-01-19 15:57:15 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][280/312]	eta 0:00:24 lr 0.000728	time 0.8020 (0.7535)	model_time 0.8019 (0.7483)	loss 3.2947 (2.8573)	grad_norm 2.2059 (2.0039/0.8290)	mem 34602MB
[2025-01-19 15:57:22 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][290/312]	eta 0:00:16 lr 0.000727	time 0.7155 (0.7524)	model_time 0.7153 (0.7476)	loss 3.0748 (2.8770)	grad_norm 1.3025 (2.1609/0.8993)	mem 34604MB
[2025-01-19 15:57:22 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][290/312]	eta 0:00:16 lr 0.000727	time 0.7586 (0.7532)	model_time 0.7584 (0.7482)	loss 2.9491 (2.8489)	grad_norm 1.3219 (2.0035/0.8205)	mem 34602MB
[2025-01-19 15:57:29 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][300/312]	eta 0:00:09 lr 0.000727	time 0.7989 (0.7529)	model_time 0.7988 (0.7482)	loss 2.2867 (2.8745)	grad_norm 2.0041 (2.1512/0.8951)	mem 34604MB
[2025-01-19 15:57:30 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][300/312]	eta 0:00:09 lr 0.000727	time 0.7151 (0.7529)	model_time 0.7150 (0.7480)	loss 3.0034 (2.8516)	grad_norm 6.1801 (2.0334/0.8671)	mem 34602MB
[2025-01-19 15:57:37 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][310/312]	eta 0:00:01 lr 0.000726	time 0.7139 (0.7519)	model_time 0.7138 (0.7472)	loss 3.3750 (2.8525)	grad_norm 2.3211 (2.0494/0.8672)	mem 34602MB
[2025-01-19 15:57:37 internimage_b_1k_224] (main.py 510): INFO Train: [217/300][310/312]	eta 0:00:01 lr 0.000726	time 0.8014 (0.7529)	model_time 0.8013 (0.7484)	loss 3.1752 (2.8718)	grad_norm 4.0635 (2.1632/0.9213)	mem 34604MB
[2025-01-19 15:57:38 internimage_b_1k_224] (main.py 519): INFO EPOCH 217 training takes 0:03:54
[2025-01-19 15:57:38 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_217.pth saving......
[2025-01-19 15:57:38 internimage_b_1k_224] (main.py 519): INFO EPOCH 217 training takes 0:03:54
[2025-01-19 15:57:38 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_217.pth saving......
[2025-01-19 15:57:41 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_217.pth saved !!!
[2025-01-19 15:57:41 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_217.pth saved !!!
[2025-01-19 15:57:57 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.163 (16.163)	Loss 0.7448 (0.7448)	Acc@1 85.400 (85.400)	Acc@5 97.900 (97.900)	Mem 34604MB
[2025-01-19 15:57:58 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.294 (17.294)	Loss 0.7352 (0.7352)	Acc@1 85.400 (85.400)	Acc@5 97.705 (97.705)	Mem 34602MB
[2025-01-19 15:58:05 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.191)	Loss 0.9318 (0.8229)	Acc@1 79.199 (83.179)	Acc@5 95.898 (96.598)	Mem 34604MB
[2025-01-19 15:58:05 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.198)	Loss 0.9397 (0.8274)	Acc@1 79.297 (83.252)	Acc@5 95.801 (96.644)	Mem 34602MB
[2025-01-19 15:58:05 internimage_b_1k_224] (main.py 575): INFO [Epoch:217] * Acc@1 83.111 Acc@5 96.653
[2025-01-19 15:58:05 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.1%
[2025-01-19 15:58:05 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.15%
[2025-01-19 15:58:05 internimage_b_1k_224] (main.py 575): INFO [Epoch:217] * Acc@1 83.003 Acc@5 96.597
[2025-01-19 15:58:05 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.0%
[2025-01-19 15:58:05 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.24%
[2025-01-19 15:58:24 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 18.408 (18.408)	Loss 0.7047 (0.7047)	Acc@1 85.840 (85.840)	Acc@5 98.193 (98.193)	Mem 34604MB
[2025-01-19 15:58:24 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 18.653 (18.653)	Loss 0.7132 (0.7132)	Acc@1 85.620 (85.620)	Acc@5 98.096 (98.096)	Mem 34602MB
[2025-01-19 15:58:32 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (2.468)	Loss 0.9404 (0.8102)	Acc@1 79.614 (83.596)	Acc@5 95.508 (96.715)	Mem 34604MB
[2025-01-19 15:58:32 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.480)	Loss 0.9419 (0.8123)	Acc@1 79.688 (83.540)	Acc@5 95.483 (96.729)	Mem 34602MB
[2025-01-19 15:58:33 internimage_b_1k_224] (main.py 575): INFO [Epoch:217] * Acc@1 83.405 Acc@5 96.759
[2025-01-19 15:58:33 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.4%
[2025-01-19 15:58:33 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:58:33 internimage_b_1k_224] (main.py 575): INFO [Epoch:217] * Acc@1 83.385 Acc@5 96.773
[2025-01-19 15:58:33 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.4%
[2025-01-19 15:58:33 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 15:58:37 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:58:37 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.41%
[2025-01-19 15:58:37 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 15:58:37 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.39%
[2025-01-19 15:58:38 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][0/312]	eta 0:10:02 lr 0.000726	time 1.9310 (1.9310)	model_time 0.7414 (0.7414)	loss 3.1426 (3.1426)	grad_norm 1.0450 (1.0450/0.0000)	mem 34604MB
[2025-01-19 15:58:39 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][0/312]	eta 0:10:55 lr 0.000726	time 2.1006 (2.1006)	model_time 0.7416 (0.7416)	loss 2.2261 (2.2261)	grad_norm 3.4426 (3.4426/0.0000)	mem 34602MB
[2025-01-19 15:58:46 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][10/312]	eta 0:04:14 lr 0.000726	time 0.7275 (0.8424)	model_time 0.7274 (0.7340)	loss 2.7347 (2.7079)	grad_norm 4.5878 (2.3573/1.2158)	mem 34604MB
[2025-01-19 15:58:47 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][10/312]	eta 0:04:31 lr 0.000726	time 0.8111 (0.9001)	model_time 0.8109 (0.7762)	loss 2.9463 (2.7898)	grad_norm 2.8352 (2.0463/0.7614)	mem 34602MB
[2025-01-19 15:58:53 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][20/312]	eta 0:03:51 lr 0.000725	time 0.7345 (0.7933)	model_time 0.7343 (0.7364)	loss 3.0963 (2.6724)	grad_norm 1.2598 (2.2487/1.0850)	mem 34604MB
[2025-01-19 15:58:54 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][20/312]	eta 0:04:00 lr 0.000725	time 0.7375 (0.8225)	model_time 0.7373 (0.7575)	loss 2.6352 (2.9279)	grad_norm 1.4572 (1.8085/0.7132)	mem 34602MB
[2025-01-19 15:59:01 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][30/312]	eta 0:03:38 lr 0.000725	time 0.7324 (0.7747)	model_time 0.7323 (0.7360)	loss 3.1403 (2.6953)	grad_norm 2.7164 (2.2656/0.9911)	mem 34604MB
[2025-01-19 15:59:01 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][30/312]	eta 0:03:44 lr 0.000725	time 0.7176 (0.7956)	model_time 0.7174 (0.7514)	loss 2.0725 (2.8406)	grad_norm 2.2376 (1.7944/0.6314)	mem 34602MB
[2025-01-19 15:59:08 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][40/312]	eta 0:03:27 lr 0.000724	time 0.7184 (0.7626)	model_time 0.7183 (0.7333)	loss 2.2612 (2.7211)	grad_norm 1.4778 (2.0568/0.9438)	mem 34604MB
[2025-01-19 15:59:09 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][40/312]	eta 0:03:32 lr 0.000724	time 0.7177 (0.7830)	model_time 0.7175 (0.7496)	loss 2.4970 (2.8189)	grad_norm 1.0905 (1.8554/0.6670)	mem 34602MB
[2025-01-19 15:59:15 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][50/312]	eta 0:03:18 lr 0.000724	time 0.7260 (0.7567)	model_time 0.7259 (0.7330)	loss 2.6903 (2.7634)	grad_norm 1.7315 (1.9324/0.9070)	mem 34604MB
[2025-01-19 15:59:16 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][50/312]	eta 0:03:22 lr 0.000724	time 0.7268 (0.7743)	model_time 0.7266 (0.7473)	loss 2.1998 (2.8213)	grad_norm 1.4987 (1.7535/0.6505)	mem 34602MB
[2025-01-19 15:59:22 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][60/312]	eta 0:03:09 lr 0.000723	time 0.7498 (0.7518)	model_time 0.7497 (0.7319)	loss 3.2968 (2.8173)	grad_norm 1.2341 (1.9007/0.8687)	mem 34604MB
[2025-01-19 15:59:24 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][60/312]	eta 0:03:13 lr 0.000723	time 0.8096 (0.7698)	model_time 0.8095 (0.7472)	loss 2.2672 (2.8278)	grad_norm 1.5636 (1.7054/0.6232)	mem 34602MB
[2025-01-19 15:59:30 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][70/312]	eta 0:03:00 lr 0.000723	time 0.7176 (0.7474)	model_time 0.7172 (0.7303)	loss 2.6705 (2.8279)	grad_norm 1.8235 (1.8966/0.8289)	mem 34604MB
[2025-01-19 15:59:31 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][70/312]	eta 0:03:05 lr 0.000723	time 0.8394 (0.7671)	model_time 0.8389 (0.7477)	loss 3.3846 (2.8264)	grad_norm 2.1176 (1.7529/0.6149)	mem 34602MB
[2025-01-19 15:59:37 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][80/312]	eta 0:02:53 lr 0.000722	time 0.7181 (0.7478)	model_time 0.7180 (0.7328)	loss 2.4140 (2.8473)	grad_norm 1.4451 (1.9092/0.8155)	mem 34604MB
[2025-01-19 15:59:39 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][80/312]	eta 0:02:57 lr 0.000722	time 0.8134 (0.7644)	model_time 0.8130 (0.7473)	loss 2.8677 (2.8343)	grad_norm 1.8094 (1.7390/0.5927)	mem 34602MB
[2025-01-19 15:59:45 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][90/312]	eta 0:02:46 lr 0.000722	time 0.8393 (0.7511)	model_time 0.8389 (0.7377)	loss 2.6676 (2.8439)	grad_norm 2.2870 (1.9412/0.7970)	mem 34604MB
[2025-01-19 15:59:46 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][90/312]	eta 0:02:49 lr 0.000722	time 0.7204 (0.7631)	model_time 0.7202 (0.7479)	loss 2.3462 (2.8561)	grad_norm 1.3342 (1.7378/0.5668)	mem 34602MB
[2025-01-19 15:59:52 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][100/312]	eta 0:02:39 lr 0.000721	time 0.8104 (0.7506)	model_time 0.8102 (0.7385)	loss 2.1823 (2.8235)	grad_norm 3.6050 (2.0138/0.8436)	mem 34604MB
[2025-01-19 15:59:53 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][100/312]	eta 0:02:41 lr 0.000721	time 0.7179 (0.7606)	model_time 0.7176 (0.7468)	loss 2.2446 (2.8714)	grad_norm 1.4602 (1.7499/0.5510)	mem 34602MB
[2025-01-19 16:00:00 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][110/312]	eta 0:02:32 lr 0.000721	time 0.7228 (0.7528)	model_time 0.7226 (0.7418)	loss 2.2817 (2.8273)	grad_norm 1.0830 (2.0006/0.8431)	mem 34604MB
[2025-01-19 16:00:01 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][110/312]	eta 0:02:33 lr 0.000721	time 0.7182 (0.7591)	model_time 0.7181 (0.7465)	loss 3.2180 (2.8531)	grad_norm 0.9565 (1.7044/0.5492)	mem 34602MB
[2025-01-19 16:00:08 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][120/312]	eta 0:02:24 lr 0.000720	time 0.8019 (0.7543)	model_time 0.8015 (0.7441)	loss 2.4972 (2.8328)	grad_norm 3.3486 (2.0054/0.8314)	mem 34604MB
[2025-01-19 16:00:08 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][120/312]	eta 0:02:25 lr 0.000720	time 0.7226 (0.7573)	model_time 0.7221 (0.7457)	loss 2.7167 (2.8792)	grad_norm 1.1874 (1.6955/0.5520)	mem 34602MB
[2025-01-19 16:00:15 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][130/312]	eta 0:02:17 lr 0.000720	time 0.7223 (0.7531)	model_time 0.7222 (0.7437)	loss 3.1537 (2.8410)	grad_norm 1.9017 (1.9852/0.8134)	mem 34604MB
[2025-01-19 16:00:16 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][130/312]	eta 0:02:17 lr 0.000720	time 0.8023 (0.7582)	model_time 0.8021 (0.7475)	loss 2.8158 (2.8667)	grad_norm 1.6390 (1.7180/0.5914)	mem 34602MB
[2025-01-19 16:00:23 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][140/312]	eta 0:02:09 lr 0.000719	time 0.7286 (0.7523)	model_time 0.7284 (0.7435)	loss 3.2076 (2.8354)	grad_norm 1.5898 (1.9586/0.8072)	mem 34604MB
[2025-01-19 16:00:24 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][140/312]	eta 0:02:10 lr 0.000719	time 0.7225 (0.7592)	model_time 0.7221 (0.7492)	loss 2.0671 (2.8608)	grad_norm 3.8419 (1.7754/0.6705)	mem 34602MB
[2025-01-19 16:00:30 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][150/312]	eta 0:02:01 lr 0.000719	time 0.7239 (0.7508)	model_time 0.7238 (0.7426)	loss 3.3431 (2.8398)	grad_norm 2.3364 (1.9319/0.7962)	mem 34604MB
[2025-01-19 16:00:31 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][150/312]	eta 0:02:02 lr 0.000719	time 0.7161 (0.7579)	model_time 0.7160 (0.7485)	loss 3.1288 (2.8568)	grad_norm 2.7101 (1.7955/0.6676)	mem 34602MB
[2025-01-19 16:00:37 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][160/312]	eta 0:01:53 lr 0.000718	time 0.7217 (0.7493)	model_time 0.7212 (0.7416)	loss 3.2880 (2.8518)	grad_norm 2.7611 (1.9296/0.7991)	mem 34604MB
[2025-01-19 16:00:39 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][160/312]	eta 0:01:55 lr 0.000718	time 0.7685 (0.7572)	model_time 0.7683 (0.7485)	loss 3.5927 (2.8805)	grad_norm 2.8354 (1.8866/0.7899)	mem 34602MB
[2025-01-19 16:00:44 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][170/312]	eta 0:01:46 lr 0.000718	time 0.7257 (0.7480)	model_time 0.7255 (0.7407)	loss 3.2288 (2.8586)	grad_norm 1.7424 (1.9019/0.7875)	mem 34604MB
[2025-01-19 16:00:46 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][170/312]	eta 0:01:47 lr 0.000718	time 0.7340 (0.7566)	model_time 0.7339 (0.7483)	loss 2.6311 (2.8889)	grad_norm 1.4076 (1.9106/0.8121)	mem 34602MB
[2025-01-19 16:00:52 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][180/312]	eta 0:01:38 lr 0.000717	time 0.7204 (0.7471)	model_time 0.7202 (0.7401)	loss 3.4037 (2.8690)	grad_norm 1.0448 (1.9041/0.7785)	mem 34604MB
[2025-01-19 16:00:53 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][180/312]	eta 0:01:39 lr 0.000717	time 0.8141 (0.7562)	model_time 0.8136 (0.7483)	loss 3.2917 (2.8958)	grad_norm 4.1260 (1.9248/0.8183)	mem 34602MB
[2025-01-19 16:00:59 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][190/312]	eta 0:01:31 lr 0.000717	time 0.7244 (0.7461)	model_time 0.7240 (0.7395)	loss 3.3520 (2.8685)	grad_norm 3.5173 (1.9822/0.8675)	mem 34604MB
[2025-01-19 16:01:01 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][190/312]	eta 0:01:32 lr 0.000717	time 0.8120 (0.7561)	model_time 0.8118 (0.7487)	loss 3.1771 (2.8925)	grad_norm 2.0727 (1.9517/0.8314)	mem 34602MB
[2025-01-19 16:01:07 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][200/312]	eta 0:01:23 lr 0.000716	time 0.7204 (0.7465)	model_time 0.7200 (0.7402)	loss 2.8986 (2.8728)	grad_norm 2.6869 (2.0062/0.8719)	mem 34604MB
[2025-01-19 16:01:09 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][200/312]	eta 0:01:24 lr 0.000716	time 0.8307 (0.7561)	model_time 0.8305 (0.7490)	loss 2.8030 (2.8942)	grad_norm 1.9812 (1.9530/0.8224)	mem 34602MB
[2025-01-19 16:01:14 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][210/312]	eta 0:01:16 lr 0.000716	time 0.8340 (0.7477)	model_time 0.8335 (0.7417)	loss 3.1956 (2.8795)	grad_norm 2.0182 (1.9939/0.8654)	mem 34604MB
[2025-01-19 16:01:16 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][210/312]	eta 0:01:17 lr 0.000716	time 0.7228 (0.7565)	model_time 0.7226 (0.7498)	loss 3.0661 (2.8941)	grad_norm 1.0223 (1.9380/0.8111)	mem 34602MB
[2025-01-19 16:01:22 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][220/312]	eta 0:01:08 lr 0.000715	time 0.8329 (0.7481)	model_time 0.8324 (0.7423)	loss 2.8617 (2.8847)	grad_norm 0.9766 (1.9740/0.8547)	mem 34604MB
[2025-01-19 16:01:24 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][220/312]	eta 0:01:09 lr 0.000715	time 0.7186 (0.7555)	model_time 0.7185 (0.7490)	loss 2.2976 (2.8990)	grad_norm 1.0686 (1.9208/0.8011)	mem 34602MB
[2025-01-19 16:01:30 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][230/312]	eta 0:01:01 lr 0.000715	time 0.7989 (0.7496)	model_time 0.7985 (0.7441)	loss 3.1131 (2.8820)	grad_norm 2.7382 (1.9639/0.8479)	mem 34604MB
[2025-01-19 16:01:31 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][230/312]	eta 0:01:01 lr 0.000715	time 0.7663 (0.7559)	model_time 0.7662 (0.7497)	loss 2.4082 (2.8978)	grad_norm 3.7587 (1.9397/0.8128)	mem 34602MB
[2025-01-19 16:01:37 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][240/312]	eta 0:00:54 lr 0.000714	time 0.8113 (0.7501)	model_time 0.8112 (0.7448)	loss 2.2691 (2.8844)	grad_norm 1.2758 (1.9881/0.8648)	mem 34604MB
[2025-01-19 16:01:39 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][240/312]	eta 0:00:54 lr 0.000714	time 0.7308 (0.7551)	model_time 0.7307 (0.7491)	loss 2.8604 (2.9012)	grad_norm 2.5967 (1.9603/0.8320)	mem 34602MB
[2025-01-19 16:01:45 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][250/312]	eta 0:00:46 lr 0.000714	time 0.7177 (0.7503)	model_time 0.7175 (0.7452)	loss 2.4472 (2.8771)	grad_norm 1.5204 (2.0022/0.8711)	mem 34604MB
[2025-01-19 16:01:46 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][250/312]	eta 0:00:46 lr 0.000714	time 0.8077 (0.7555)	model_time 0.8076 (0.7497)	loss 2.7492 (2.9061)	grad_norm 2.1487 (1.9997/0.8558)	mem 34602MB
[2025-01-19 16:01:52 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][260/312]	eta 0:00:38 lr 0.000713	time 0.7235 (0.7499)	model_time 0.7231 (0.7450)	loss 2.0055 (2.8727)	grad_norm 2.4761 (1.9990/0.8662)	mem 34604MB
[2025-01-19 16:01:54 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][260/312]	eta 0:00:39 lr 0.000713	time 0.7172 (0.7554)	model_time 0.7171 (0.7499)	loss 3.0555 (2.9077)	grad_norm 2.3147 (2.0020/0.8454)	mem 34602MB
[2025-01-19 16:02:00 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][270/312]	eta 0:00:31 lr 0.000713	time 0.7609 (0.7494)	model_time 0.7607 (0.7447)	loss 2.4128 (2.8758)	grad_norm 1.3179 (1.9856/0.8587)	mem 34604MB
[2025-01-19 16:02:01 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][270/312]	eta 0:00:31 lr 0.000713	time 0.7188 (0.7549)	model_time 0.7186 (0.7495)	loss 3.1548 (2.9030)	grad_norm 1.9390 (2.0203/0.8569)	mem 34602MB
[2025-01-19 16:02:07 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][280/312]	eta 0:00:23 lr 0.000712	time 0.7516 (0.7485)	model_time 0.7515 (0.7439)	loss 2.5841 (2.8811)	grad_norm 1.3869 (1.9652/0.8569)	mem 34604MB
[2025-01-19 16:02:09 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][280/312]	eta 0:00:24 lr 0.000712	time 0.7180 (0.7545)	model_time 0.7175 (0.7493)	loss 3.0897 (2.8964)	grad_norm 1.8069 (2.0451/0.8747)	mem 34602MB
[2025-01-19 16:02:14 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][290/312]	eta 0:00:16 lr 0.000712	time 0.7233 (0.7480)	model_time 0.7232 (0.7436)	loss 3.3529 (2.8795)	grad_norm 2.9633 (1.9615/0.8499)	mem 34604MB
[2025-01-19 16:02:16 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][290/312]	eta 0:00:16 lr 0.000712	time 0.7549 (0.7543)	model_time 0.7547 (0.7493)	loss 2.5924 (2.8983)	grad_norm 1.4023 (2.0363/0.8686)	mem 34602MB
[2025-01-19 16:02:21 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][300/312]	eta 0:00:08 lr 0.000711	time 0.7577 (0.7471)	model_time 0.7576 (0.7428)	loss 3.0777 (2.8816)	grad_norm 3.1282 (1.9663/0.8428)	mem 34604MB
[2025-01-19 16:02:24 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][300/312]	eta 0:00:09 lr 0.000711	time 0.7977 (0.7539)	model_time 0.7975 (0.7490)	loss 3.0497 (2.9046)	grad_norm 1.2892 (2.0057/0.8664)	mem 34602MB
[2025-01-19 16:02:29 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][310/312]	eta 0:00:01 lr 0.000711	time 0.7146 (0.7462)	model_time 0.7145 (0.7421)	loss 2.3615 (2.8795)	grad_norm 2.6377 (1.9766/0.8367)	mem 34604MB
[2025-01-19 16:02:29 internimage_b_1k_224] (main.py 519): INFO EPOCH 218 training takes 0:03:52
[2025-01-19 16:02:29 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_218.pth saving......
[2025-01-19 16:02:31 internimage_b_1k_224] (main.py 510): INFO Train: [218/300][310/312]	eta 0:00:01 lr 0.000711	time 0.7137 (0.7528)	model_time 0.7136 (0.7481)	loss 3.5036 (2.9086)	grad_norm 1.6260 (2.0056/0.8696)	mem 34602MB
[2025-01-19 16:02:32 internimage_b_1k_224] (main.py 519): INFO EPOCH 218 training takes 0:03:54
[2025-01-19 16:02:32 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_218.pth saving......
[2025-01-19 16:02:32 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_218.pth saved !!!
[2025-01-19 16:02:35 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_218.pth saved !!!
[2025-01-19 16:02:48 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.371 (15.371)	Loss 0.7034 (0.7034)	Acc@1 85.913 (85.913)	Acc@5 97.900 (97.900)	Mem 34604MB
[2025-01-19 16:02:50 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.732 (15.732)	Loss 0.7157 (0.7157)	Acc@1 85.181 (85.181)	Acc@5 97.705 (97.705)	Mem 34602MB
[2025-01-19 16:02:55 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.017)	Loss 0.9290 (0.8070)	Acc@1 79.907 (83.496)	Acc@5 95.557 (96.562)	Mem 34604MB
[2025-01-19 16:02:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:218] * Acc@1 83.267 Acc@5 96.575
[2025-01-19 16:02:55 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.3%
[2025-01-19 16:02:55 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 16:02:58 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.109)	Loss 0.9508 (0.8115)	Acc@1 78.784 (83.456)	Acc@5 95.483 (96.611)	Mem 34602MB
[2025-01-19 16:02:58 internimage_b_1k_224] (main.py 575): INFO [Epoch:218] * Acc@1 83.277 Acc@5 96.625
[2025-01-19 16:02:58 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.3%
[2025-01-19 16:02:58 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 16:02:59 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 16:02:59 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.27%
[2025-01-19 16:03:01 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 16:03:01 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.28%
[2025-01-19 16:03:14 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.534 (15.534)	Loss 0.7050 (0.7050)	Acc@1 85.889 (85.889)	Acc@5 98.193 (98.193)	Mem 34604MB
[2025-01-19 16:03:18 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.331 (16.331)	Loss 0.7139 (0.7139)	Acc@1 85.669 (85.669)	Acc@5 98.096 (98.096)	Mem 34602MB
[2025-01-19 16:03:21 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.177 (2.060)	Loss 0.9398 (0.8101)	Acc@1 79.736 (83.631)	Acc@5 95.532 (96.731)	Mem 34604MB
[2025-01-19 16:03:22 internimage_b_1k_224] (main.py 575): INFO [Epoch:218] * Acc@1 83.441 Acc@5 96.775
[2025-01-19 16:03:22 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.4%
[2025-01-19 16:03:22 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:03:23 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.990)	Loss 0.9417 (0.8125)	Acc@1 79.712 (83.578)	Acc@5 95.508 (96.733)	Mem 34602MB
[2025-01-19 16:03:23 internimage_b_1k_224] (main.py 575): INFO [Epoch:218] * Acc@1 83.419 Acc@5 96.777
[2025-01-19 16:03:23 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.4%
[2025-01-19 16:03:23 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:03:25 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:03:25 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.44%
[2025-01-19 16:03:27 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:03:27 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.42%
[2025-01-19 16:03:28 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][0/312]	eta 0:11:18 lr 0.000711	time 2.1754 (2.1754)	model_time 0.7386 (0.7386)	loss 3.2864 (3.2864)	grad_norm 2.3045 (2.3045/0.0000)	mem 34604MB
[2025-01-19 16:03:30 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][0/312]	eta 0:12:17 lr 0.000711	time 2.3641 (2.3641)	model_time 0.7357 (0.7357)	loss 3.0038 (3.0038)	grad_norm 1.7435 (1.7435/0.0000)	mem 34602MB
[2025-01-19 16:03:35 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][10/312]	eta 0:04:25 lr 0.000710	time 0.7332 (0.8804)	model_time 0.7330 (0.7495)	loss 2.8131 (2.9224)	grad_norm 0.8852 (1.8703/0.8102)	mem 34604MB
[2025-01-19 16:03:37 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][10/312]	eta 0:04:31 lr 0.000710	time 0.8163 (0.8999)	model_time 0.8161 (0.7516)	loss 2.8226 (2.9486)	grad_norm 1.0647 (1.6126/0.2960)	mem 34602MB
[2025-01-19 16:03:43 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][20/312]	eta 0:04:02 lr 0.000710	time 0.7197 (0.8313)	model_time 0.7195 (0.7627)	loss 2.9086 (2.8152)	grad_norm 3.1405 (2.0539/0.9529)	mem 34604MB
[2025-01-19 16:03:45 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][20/312]	eta 0:04:04 lr 0.000710	time 0.7287 (0.8360)	model_time 0.7282 (0.7582)	loss 2.7832 (2.9604)	grad_norm 1.4750 (1.5577/0.4241)	mem 34602MB
[2025-01-19 16:03:50 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][30/312]	eta 0:03:45 lr 0.000709	time 0.7121 (0.8006)	model_time 0.7119 (0.7539)	loss 2.6819 (2.8336)	grad_norm 1.5800 (2.2032/0.9437)	mem 34604MB
[2025-01-19 16:03:52 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][30/312]	eta 0:03:46 lr 0.000709	time 0.7187 (0.8041)	model_time 0.7185 (0.7513)	loss 2.7164 (2.9293)	grad_norm 1.8388 (1.5515/0.4623)	mem 34602MB
[2025-01-19 16:03:58 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][40/312]	eta 0:03:36 lr 0.000709	time 0.7154 (0.7950)	model_time 0.7149 (0.7597)	loss 3.5149 (2.8292)	grad_norm 2.5834 (2.1221/0.8715)	mem 34604MB
[2025-01-19 16:04:00 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][40/312]	eta 0:03:34 lr 0.000709	time 0.7206 (0.7892)	model_time 0.7204 (0.7492)	loss 2.8673 (2.9378)	grad_norm 2.7688 (1.8149/0.8827)	mem 34602MB
[2025-01-19 16:04:06 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][50/312]	eta 0:03:26 lr 0.000708	time 0.7643 (0.7886)	model_time 0.7639 (0.7601)	loss 2.9876 (2.8099)	grad_norm 1.1873 (1.9904/0.8704)	mem 34604MB
[2025-01-19 16:04:07 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][50/312]	eta 0:03:24 lr 0.000708	time 0.7219 (0.7788)	model_time 0.7217 (0.7466)	loss 2.4454 (2.9429)	grad_norm 1.7527 (1.8346/0.8349)	mem 34602MB
[2025-01-19 16:04:13 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][60/312]	eta 0:03:17 lr 0.000708	time 0.8122 (0.7825)	model_time 0.8120 (0.7587)	loss 2.8635 (2.8228)	grad_norm 1.9654 (1.9784/0.8278)	mem 34604MB
[2025-01-19 16:04:15 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][60/312]	eta 0:03:15 lr 0.000708	time 0.8127 (0.7768)	model_time 0.8126 (0.7498)	loss 2.0810 (2.9259)	grad_norm 2.2572 (1.8970/0.8499)	mem 34602MB
[2025-01-19 16:04:21 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][70/312]	eta 0:03:07 lr 0.000707	time 0.7396 (0.7766)	model_time 0.7392 (0.7561)	loss 1.9799 (2.8039)	grad_norm 2.4055 (2.0660/0.8959)	mem 34604MB
[2025-01-19 16:04:22 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][70/312]	eta 0:03:06 lr 0.000707	time 0.7165 (0.7725)	model_time 0.7163 (0.7493)	loss 2.8293 (2.9133)	grad_norm 1.8885 (1.8911/0.8032)	mem 34602MB
[2025-01-19 16:04:28 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][80/312]	eta 0:02:58 lr 0.000707	time 0.7193 (0.7700)	model_time 0.7188 (0.7519)	loss 2.6344 (2.7922)	grad_norm 2.0748 (2.0577/0.8798)	mem 34604MB
[2025-01-19 16:04:30 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][80/312]	eta 0:02:58 lr 0.000707	time 0.8146 (0.7678)	model_time 0.8144 (0.7474)	loss 2.8405 (2.9252)	grad_norm 1.9990 (1.9724/0.8761)	mem 34602MB
[2025-01-19 16:04:35 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][90/312]	eta 0:02:50 lr 0.000706	time 0.7205 (0.7661)	model_time 0.7201 (0.7500)	loss 2.9928 (2.7836)	grad_norm 1.8144 (2.0554/0.8545)	mem 34604MB
[2025-01-19 16:04:37 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][90/312]	eta 0:02:49 lr 0.000706	time 0.8092 (0.7651)	model_time 0.8087 (0.7469)	loss 2.7550 (2.9207)	grad_norm 1.6906 (2.0170/0.9112)	mem 34602MB
[2025-01-19 16:04:42 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][100/312]	eta 0:02:41 lr 0.000706	time 0.7191 (0.7620)	model_time 0.7189 (0.7474)	loss 2.9244 (2.7874)	grad_norm 3.3348 (2.0756/0.8422)	mem 34604MB
[2025-01-19 16:04:45 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][100/312]	eta 0:02:41 lr 0.000706	time 0.7233 (0.7626)	model_time 0.7231 (0.7462)	loss 3.0038 (2.9202)	grad_norm 1.0408 (1.9859/0.9168)	mem 34602MB
[2025-01-19 16:04:50 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][110/312]	eta 0:02:33 lr 0.000705	time 0.7363 (0.7589)	model_time 0.7359 (0.7456)	loss 3.3038 (2.7810)	grad_norm 1.6497 (2.0946/0.8758)	mem 34604MB
[2025-01-19 16:04:52 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][110/312]	eta 0:02:33 lr 0.000705	time 0.7296 (0.7612)	model_time 0.7294 (0.7462)	loss 3.0162 (2.9387)	grad_norm 2.3923 (1.9763/0.8936)	mem 34602MB
[2025-01-19 16:04:57 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][120/312]	eta 0:02:25 lr 0.000705	time 0.7661 (0.7569)	model_time 0.7659 (0.7447)	loss 2.9895 (2.7937)	grad_norm 1.5575 (2.1004/0.8786)	mem 34604MB
[2025-01-19 16:05:00 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][120/312]	eta 0:02:26 lr 0.000705	time 0.8217 (0.7604)	model_time 0.8213 (0.7467)	loss 2.9203 (2.9357)	grad_norm 1.1590 (1.9973/0.8851)	mem 34602MB
[2025-01-19 16:05:04 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][130/312]	eta 0:02:17 lr 0.000704	time 0.7181 (0.7561)	model_time 0.7179 (0.7448)	loss 2.0124 (2.7887)	grad_norm 1.7090 (2.0937/0.8594)	mem 34604MB
[2025-01-19 16:05:07 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][130/312]	eta 0:02:18 lr 0.000704	time 0.7201 (0.7590)	model_time 0.7197 (0.7463)	loss 3.2323 (2.9128)	grad_norm 1.5919 (2.0130/0.8780)	mem 34602MB
[2025-01-19 16:05:12 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][140/312]	eta 0:02:10 lr 0.000704	time 0.7125 (0.7583)	model_time 0.7119 (0.7477)	loss 2.4229 (2.7759)	grad_norm 1.1406 (2.0470/0.8494)	mem 34604MB
[2025-01-19 16:05:15 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][140/312]	eta 0:02:10 lr 0.000704	time 0.7179 (0.7602)	model_time 0.7178 (0.7483)	loss 3.1201 (2.9219)	grad_norm 2.3712 (2.0200/0.8654)	mem 34602MB
[2025-01-19 16:05:20 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][150/312]	eta 0:02:02 lr 0.000703	time 0.7212 (0.7572)	model_time 0.7211 (0.7473)	loss 2.8469 (2.7966)	grad_norm 2.0451 (2.0150/0.8401)	mem 34604MB
[2025-01-19 16:05:22 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][150/312]	eta 0:02:02 lr 0.000703	time 0.7275 (0.7579)	model_time 0.7274 (0.7468)	loss 2.0638 (2.9213)	grad_norm 2.7892 (1.9915/0.8529)	mem 34602MB
[2025-01-19 16:05:28 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][160/312]	eta 0:01:55 lr 0.000703	time 0.7180 (0.7587)	model_time 0.7176 (0.7494)	loss 1.8091 (2.8157)	grad_norm 1.6909 (2.0379/0.8756)	mem 34604MB
[2025-01-19 16:05:29 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][160/312]	eta 0:01:55 lr 0.000703	time 0.7625 (0.7575)	model_time 0.7624 (0.7471)	loss 3.0531 (2.9178)	grad_norm 1.6804 (1.9678/0.8405)	mem 34602MB
[2025-01-19 16:05:35 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][170/312]	eta 0:01:47 lr 0.000702	time 0.7150 (0.7588)	model_time 0.7146 (0.7500)	loss 3.5530 (2.8160)	grad_norm 3.2741 (2.0766/0.8908)	mem 34604MB
[2025-01-19 16:05:37 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][170/312]	eta 0:01:47 lr 0.000702	time 0.7229 (0.7561)	model_time 0.7227 (0.7463)	loss 3.4564 (2.9050)	grad_norm 1.6764 (1.9518/0.8274)	mem 34602MB
[2025-01-19 16:05:43 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][180/312]	eta 0:01:40 lr 0.000702	time 0.7225 (0.7580)	model_time 0.7223 (0.7497)	loss 1.7955 (2.8207)	grad_norm 1.0847 (2.0892/0.9103)	mem 34604MB
[2025-01-19 16:05:44 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][180/312]	eta 0:01:39 lr 0.000702	time 0.7437 (0.7563)	model_time 0.7433 (0.7469)	loss 3.0695 (2.9021)	grad_norm 1.5350 (1.9306/0.8113)	mem 34602MB
[2025-01-19 16:05:50 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][190/312]	eta 0:01:32 lr 0.000701	time 0.7232 (0.7572)	model_time 0.7227 (0.7493)	loss 3.0347 (2.8202)	grad_norm 1.4876 (2.0932/0.9116)	mem 34604MB
[2025-01-19 16:05:52 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][190/312]	eta 0:01:32 lr 0.000701	time 0.7634 (0.7561)	model_time 0.7632 (0.7473)	loss 2.4861 (2.8883)	grad_norm 1.8058 (1.9249/0.8050)	mem 34602MB
[2025-01-19 16:05:57 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][200/312]	eta 0:01:24 lr 0.000701	time 0.7417 (0.7557)	model_time 0.7413 (0.7482)	loss 3.1431 (2.8172)	grad_norm 2.0474 (2.0925/0.9007)	mem 34604MB
[2025-01-19 16:05:59 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][200/312]	eta 0:01:24 lr 0.000701	time 0.8120 (0.7550)	model_time 0.8116 (0.7465)	loss 3.5530 (2.8999)	grad_norm 2.9737 (1.9354/0.8050)	mem 34602MB
[2025-01-19 16:06:05 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][210/312]	eta 0:01:16 lr 0.000700	time 0.7420 (0.7544)	model_time 0.7418 (0.7473)	loss 2.5286 (2.8253)	grad_norm 1.1596 (2.0749/0.8889)	mem 34604MB
[2025-01-19 16:06:07 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][210/312]	eta 0:01:16 lr 0.000700	time 0.7308 (0.7536)	model_time 0.7306 (0.7456)	loss 2.7755 (2.9011)	grad_norm 2.6230 (1.9584/0.8153)	mem 34602MB
[2025-01-19 16:06:12 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][220/312]	eta 0:01:09 lr 0.000700	time 0.7262 (0.7531)	model_time 0.7258 (0.7463)	loss 3.0689 (2.8325)	grad_norm 1.1478 (2.0389/0.8857)	mem 34604MB
[2025-01-19 16:06:14 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][220/312]	eta 0:01:09 lr 0.000700	time 0.7163 (0.7534)	model_time 0.7162 (0.7457)	loss 2.9072 (2.9076)	grad_norm 1.2697 (1.9467/0.8044)	mem 34602MB
[2025-01-19 16:06:19 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][230/312]	eta 0:01:01 lr 0.000699	time 0.7405 (0.7522)	model_time 0.7404 (0.7456)	loss 2.2824 (2.8330)	grad_norm 1.7357 (2.0251/0.8731)	mem 34604MB
[2025-01-19 16:06:21 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][230/312]	eta 0:01:01 lr 0.000699	time 0.8095 (0.7528)	model_time 0.8094 (0.7454)	loss 3.5882 (2.9101)	grad_norm 1.8504 (1.9466/0.8035)	mem 34602MB
[2025-01-19 16:06:26 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][240/312]	eta 0:00:54 lr 0.000699	time 0.7156 (0.7511)	model_time 0.7152 (0.7448)	loss 2.9944 (2.8352)	grad_norm 4.0450 (2.0224/0.8731)	mem 34604MB
[2025-01-19 16:06:29 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][240/312]	eta 0:00:54 lr 0.000699	time 0.8070 (0.7529)	model_time 0.8068 (0.7458)	loss 3.4353 (2.9157)	grad_norm 1.1955 (1.9257/0.7955)	mem 34602MB
[2025-01-19 16:06:34 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][250/312]	eta 0:00:46 lr 0.000698	time 0.8086 (0.7514)	model_time 0.8084 (0.7453)	loss 3.6652 (2.8480)	grad_norm 7.3826 (2.0715/0.9509)	mem 34604MB
[2025-01-19 16:06:36 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][250/312]	eta 0:00:46 lr 0.000698	time 0.7267 (0.7529)	model_time 0.7262 (0.7460)	loss 2.9253 (2.9037)	grad_norm 1.4062 (1.9060/0.7891)	mem 34602MB
[2025-01-19 16:06:42 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][260/312]	eta 0:00:39 lr 0.000698	time 0.7215 (0.7518)	model_time 0.7213 (0.7459)	loss 2.1722 (2.8494)	grad_norm 2.2412 (2.0902/0.9849)	mem 34604MB
[2025-01-19 16:06:44 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][260/312]	eta 0:00:39 lr 0.000698	time 0.7172 (0.7536)	model_time 0.7170 (0.7470)	loss 3.1048 (2.9040)	grad_norm 2.4889 (1.9140/0.7938)	mem 34602MB
[2025-01-19 16:06:49 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][270/312]	eta 0:00:31 lr 0.000697	time 0.7222 (0.7519)	model_time 0.7217 (0.7462)	loss 2.8991 (2.8532)	grad_norm 1.5229 (2.0899/0.9742)	mem 34604MB
[2025-01-19 16:06:51 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][270/312]	eta 0:00:31 lr 0.000697	time 0.7206 (0.7526)	model_time 0.7201 (0.7462)	loss 2.4120 (2.9038)	grad_norm 3.0278 (1.9363/0.8221)	mem 34602MB
[2025-01-19 16:06:57 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][280/312]	eta 0:00:24 lr 0.000697	time 0.8069 (0.7530)	model_time 0.8067 (0.7476)	loss 3.6663 (2.8520)	grad_norm 2.0436 (2.0707/0.9662)	mem 34604MB
[2025-01-19 16:06:59 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][280/312]	eta 0:00:24 lr 0.000697	time 0.7189 (0.7524)	model_time 0.7187 (0.7462)	loss 2.9055 (2.8995)	grad_norm 1.3093 (1.9236/0.8133)	mem 34602MB
[2025-01-19 16:07:04 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][290/312]	eta 0:00:16 lr 0.000696	time 0.8115 (0.7528)	model_time 0.8114 (0.7475)	loss 3.4888 (2.8562)	grad_norm 2.2751 (2.0666/0.9587)	mem 34604MB
[2025-01-19 16:07:06 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][290/312]	eta 0:00:16 lr 0.000696	time 0.7184 (0.7519)	model_time 0.7182 (0.7460)	loss 3.4676 (2.9012)	grad_norm 3.2051 (1.9149/0.8085)	mem 34602MB
[2025-01-19 16:07:12 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][300/312]	eta 0:00:09 lr 0.000696	time 0.7143 (0.7526)	model_time 0.7142 (0.7474)	loss 2.7621 (2.8607)	grad_norm 2.1162 (2.0543/0.9474)	mem 34604MB
[2025-01-19 16:07:14 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][300/312]	eta 0:00:09 lr 0.000696	time 0.7163 (0.7519)	model_time 0.7162 (0.7461)	loss 2.1118 (2.9047)	grad_norm 1.1495 (1.9078/0.8036)	mem 34602MB
[2025-01-19 16:07:19 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][310/312]	eta 0:00:01 lr 0.000695	time 0.7138 (0.7522)	model_time 0.7137 (0.7472)	loss 2.9854 (2.8563)	grad_norm 2.6976 (2.0471/0.9417)	mem 34604MB
[2025-01-19 16:07:20 internimage_b_1k_224] (main.py 519): INFO EPOCH 219 training takes 0:03:54
[2025-01-19 16:07:20 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_219.pth saving......
[2025-01-19 16:07:21 internimage_b_1k_224] (main.py 510): INFO Train: [219/300][310/312]	eta 0:00:01 lr 0.000695	time 0.8017 (0.7516)	model_time 0.8016 (0.7461)	loss 3.2661 (2.8991)	grad_norm 1.8740 (1.9353/0.8156)	mem 34602MB
[2025-01-19 16:07:22 internimage_b_1k_224] (main.py 519): INFO EPOCH 219 training takes 0:03:54
[2025-01-19 16:07:22 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_219.pth saving......
[2025-01-19 16:07:23 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_219.pth saved !!!
[2025-01-19 16:07:25 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_219.pth saved !!!
[2025-01-19 16:07:39 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.404 (15.404)	Loss 0.7185 (0.7185)	Acc@1 85.791 (85.791)	Acc@5 97.656 (97.656)	Mem 34604MB
[2025-01-19 16:07:42 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.488 (16.488)	Loss 0.7341 (0.7341)	Acc@1 85.229 (85.229)	Acc@5 97.510 (97.510)	Mem 34602MB
[2025-01-19 16:07:45 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.003)	Loss 0.9323 (0.8132)	Acc@1 79.321 (83.441)	Acc@5 95.605 (96.591)	Mem 34604MB
[2025-01-19 16:07:46 internimage_b_1k_224] (main.py 575): INFO [Epoch:219] * Acc@1 83.223 Acc@5 96.581
[2025-01-19 16:07:46 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.2%
[2025-01-19 16:07:46 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.27%
[2025-01-19 16:07:48 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.183 (2.120)	Loss 0.9316 (0.8137)	Acc@1 79.297 (83.358)	Acc@5 95.532 (96.604)	Mem 34602MB
[2025-01-19 16:07:49 internimage_b_1k_224] (main.py 575): INFO [Epoch:219] * Acc@1 83.183 Acc@5 96.611
[2025-01-19 16:07:49 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.2%
[2025-01-19 16:07:49 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.28%
[2025-01-19 16:08:02 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.783 (16.783)	Loss 0.7054 (0.7054)	Acc@1 85.938 (85.938)	Acc@5 98.218 (98.218)	Mem 34604MB
[2025-01-19 16:08:08 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 18.842 (18.842)	Loss 0.7146 (0.7146)	Acc@1 85.693 (85.693)	Acc@5 98.120 (98.120)	Mem 34602MB
[2025-01-19 16:08:12 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (2.386)	Loss 0.9394 (0.8101)	Acc@1 79.810 (83.656)	Acc@5 95.557 (96.760)	Mem 34604MB
[2025-01-19 16:08:12 internimage_b_1k_224] (main.py 575): INFO [Epoch:219] * Acc@1 83.465 Acc@5 96.803
[2025-01-19 16:08:12 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.5%
[2025-01-19 16:08:12 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:08:14 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.300)	Loss 0.9415 (0.8126)	Acc@1 79.688 (83.598)	Acc@5 95.508 (96.740)	Mem 34602MB
[2025-01-19 16:08:14 internimage_b_1k_224] (main.py 575): INFO [Epoch:219] * Acc@1 83.439 Acc@5 96.785
[2025-01-19 16:08:14 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.4%
[2025-01-19 16:08:14 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:08:16 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:08:16 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.47%
[2025-01-19 16:08:18 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:08:18 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.44%
[2025-01-19 16:08:18 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][0/312]	eta 0:11:17 lr 0.000695	time 2.1714 (2.1714)	model_time 0.7438 (0.7438)	loss 3.3790 (3.3790)	grad_norm 1.8667 (1.8667/0.0000)	mem 34604MB
[2025-01-19 16:08:20 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][0/312]	eta 0:11:52 lr 0.000695	time 2.2834 (2.2834)	model_time 0.7624 (0.7624)	loss 3.1833 (3.1833)	grad_norm 1.5859 (1.5859/0.0000)	mem 34602MB
[2025-01-19 16:08:26 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][10/312]	eta 0:04:20 lr 0.000695	time 0.7254 (0.8623)	model_time 0.7250 (0.7321)	loss 2.6424 (2.6160)	grad_norm 2.0082 (1.9351/0.5495)	mem 34604MB
[2025-01-19 16:08:28 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][10/312]	eta 0:04:24 lr 0.000695	time 0.8236 (0.8756)	model_time 0.8232 (0.7370)	loss 3.2923 (3.0840)	grad_norm 1.4303 (2.1517/1.1025)	mem 34602MB
[2025-01-19 16:08:33 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][20/312]	eta 0:03:55 lr 0.000694	time 0.7586 (0.8054)	model_time 0.7585 (0.7370)	loss 3.3211 (2.7694)	grad_norm 1.1197 (1.9924/0.5554)	mem 34604MB
[2025-01-19 16:08:35 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][20/312]	eta 0:03:56 lr 0.000694	time 0.7209 (0.8100)	model_time 0.7208 (0.7373)	loss 3.2636 (3.0824)	grad_norm 1.3903 (2.2996/1.1108)	mem 34602MB
[2025-01-19 16:08:40 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][30/312]	eta 0:03:39 lr 0.000694	time 0.7219 (0.7793)	model_time 0.7217 (0.7329)	loss 3.2541 (2.8442)	grad_norm 3.0223 (2.1936/0.8674)	mem 34604MB
[2025-01-19 16:08:43 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][30/312]	eta 0:03:43 lr 0.000694	time 0.7336 (0.7910)	model_time 0.7335 (0.7416)	loss 3.4030 (3.0164)	grad_norm 1.1668 (2.2473/1.0166)	mem 34602MB
[2025-01-19 16:08:48 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][40/312]	eta 0:03:28 lr 0.000693	time 0.7266 (0.7670)	model_time 0.7264 (0.7318)	loss 2.5669 (2.8130)	grad_norm 1.6582 (2.0790/0.8279)	mem 34604MB
[2025-01-19 16:08:50 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][40/312]	eta 0:03:32 lr 0.000693	time 0.7291 (0.7797)	model_time 0.7287 (0.7423)	loss 2.0735 (2.8853)	grad_norm 3.2287 (2.3353/1.0299)	mem 34602MB
[2025-01-19 16:08:55 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][50/312]	eta 0:03:18 lr 0.000693	time 0.7184 (0.7586)	model_time 0.7183 (0.7302)	loss 3.6496 (2.8262)	grad_norm 2.1158 (2.0861/0.8771)	mem 34604MB
[2025-01-19 16:08:58 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][50/312]	eta 0:03:22 lr 0.000693	time 0.7358 (0.7725)	model_time 0.7354 (0.7424)	loss 3.0222 (2.8891)	grad_norm 3.0715 (2.3227/0.9860)	mem 34602MB
[2025-01-19 16:09:02 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][60/312]	eta 0:03:10 lr 0.000692	time 0.7150 (0.7579)	model_time 0.7145 (0.7341)	loss 2.4519 (2.8265)	grad_norm 1.5924 (1.9887/0.8508)	mem 34604MB
[2025-01-19 16:09:05 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][60/312]	eta 0:03:14 lr 0.000692	time 0.7973 (0.7700)	model_time 0.7969 (0.7448)	loss 3.3333 (2.8535)	grad_norm 1.9031 (2.2403/0.9291)	mem 34602MB
[2025-01-19 16:09:10 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][70/312]	eta 0:03:04 lr 0.000692	time 0.8157 (0.7610)	model_time 0.8156 (0.7405)	loss 3.3835 (2.8663)	grad_norm 3.0344 (1.9787/0.8295)	mem 34604MB
[2025-01-19 16:09:13 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][70/312]	eta 0:03:06 lr 0.000692	time 0.8030 (0.7698)	model_time 0.8029 (0.7480)	loss 1.9362 (2.8396)	grad_norm 1.2123 (2.1817/0.8994)	mem 34602MB
[2025-01-19 16:09:18 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][80/312]	eta 0:02:55 lr 0.000691	time 0.7182 (0.7584)	model_time 0.7178 (0.7404)	loss 2.3887 (2.8707)	grad_norm 3.2065 (2.0292/0.8396)	mem 34604MB
[2025-01-19 16:09:20 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][80/312]	eta 0:02:57 lr 0.000691	time 0.7343 (0.7652)	model_time 0.7339 (0.7461)	loss 3.1630 (2.8857)	grad_norm 2.7136 (2.1781/0.8693)	mem 34602MB
[2025-01-19 16:09:25 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][90/312]	eta 0:02:49 lr 0.000691	time 0.8104 (0.7617)	model_time 0.8100 (0.7456)	loss 3.4113 (2.8729)	grad_norm 4.2459 (2.1057/0.8955)	mem 34604MB
[2025-01-19 16:09:28 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][90/312]	eta 0:02:49 lr 0.000691	time 0.7242 (0.7647)	model_time 0.7237 (0.7476)	loss 3.4694 (2.9042)	grad_norm 2.7731 (2.2232/0.8903)	mem 34602MB
[2025-01-19 16:09:33 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][100/312]	eta 0:02:41 lr 0.000690	time 0.7260 (0.7604)	model_time 0.7258 (0.7459)	loss 2.8348 (2.8555)	grad_norm 1.4587 (2.1682/0.8891)	mem 34604MB
[2025-01-19 16:09:35 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][100/312]	eta 0:02:41 lr 0.000690	time 0.7338 (0.7611)	model_time 0.7334 (0.7457)	loss 3.1375 (2.8939)	grad_norm 0.8590 (2.2660/0.9508)	mem 34602MB
[2025-01-19 16:09:40 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][110/312]	eta 0:02:33 lr 0.000690	time 0.7218 (0.7588)	model_time 0.7216 (0.7456)	loss 3.3998 (2.8554)	grad_norm 2.2020 (2.1809/0.8633)	mem 34604MB
[2025-01-19 16:09:43 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][110/312]	eta 0:02:33 lr 0.000690	time 0.7333 (0.7603)	model_time 0.7328 (0.7462)	loss 3.1450 (2.8893)	grad_norm 1.7076 (2.2734/1.0112)	mem 34602MB
[2025-01-19 16:09:48 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][120/312]	eta 0:02:25 lr 0.000689	time 0.7212 (0.7576)	model_time 0.7211 (0.7454)	loss 2.0271 (2.8652)	grad_norm 1.7954 (2.1257/0.8631)	mem 34604MB
[2025-01-19 16:09:50 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][120/312]	eta 0:02:25 lr 0.000689	time 0.7304 (0.7596)	model_time 0.7300 (0.7466)	loss 2.2532 (2.8724)	grad_norm 1.3496 (2.2167/0.9885)	mem 34602MB
[2025-01-19 16:09:55 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][130/312]	eta 0:02:17 lr 0.000689	time 0.7180 (0.7555)	model_time 0.7179 (0.7442)	loss 2.1390 (2.8629)	grad_norm 0.8157 (2.0721/0.8605)	mem 34604MB
[2025-01-19 16:09:57 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][130/312]	eta 0:02:17 lr 0.000689	time 0.7158 (0.7578)	model_time 0.7156 (0.7458)	loss 2.5196 (2.8658)	grad_norm 1.5001 (2.1491/0.9831)	mem 34602MB
[2025-01-19 16:10:02 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][140/312]	eta 0:02:09 lr 0.000688	time 0.7202 (0.7540)	model_time 0.7200 (0.7435)	loss 3.1656 (2.8753)	grad_norm 1.5013 (2.0669/0.8669)	mem 34604MB
[2025-01-19 16:10:05 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][140/312]	eta 0:02:10 lr 0.000688	time 0.7235 (0.7568)	model_time 0.7233 (0.7456)	loss 2.9565 (2.8504)	grad_norm 1.2623 (2.1301/0.9708)	mem 34602MB
[2025-01-19 16:10:10 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][150/312]	eta 0:02:01 lr 0.000688	time 0.7268 (0.7520)	model_time 0.7267 (0.7422)	loss 2.4343 (2.8616)	grad_norm 0.9656 (2.0571/0.8537)	mem 34604MB
[2025-01-19 16:10:12 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][150/312]	eta 0:02:02 lr 0.000688	time 0.7174 (0.7557)	model_time 0.7169 (0.7452)	loss 1.6401 (2.8454)	grad_norm 2.0331 (2.0944/0.9581)	mem 34602MB
[2025-01-19 16:10:17 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][160/312]	eta 0:01:54 lr 0.000687	time 0.7233 (0.7505)	model_time 0.7231 (0.7413)	loss 3.3638 (2.8750)	grad_norm 1.1121 (2.0717/0.8907)	mem 34604MB
[2025-01-19 16:10:20 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][160/312]	eta 0:01:54 lr 0.000687	time 0.7207 (0.7550)	model_time 0.7203 (0.7452)	loss 3.1897 (2.8413)	grad_norm 1.4516 (2.0947/0.9621)	mem 34602MB
[2025-01-19 16:10:24 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][170/312]	eta 0:01:46 lr 0.000687	time 0.7343 (0.7490)	model_time 0.7339 (0.7403)	loss 3.0887 (2.8773)	grad_norm 2.5835 (2.0868/0.8850)	mem 34604MB
[2025-01-19 16:10:27 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][170/312]	eta 0:01:47 lr 0.000687	time 0.7968 (0.7547)	model_time 0.7963 (0.7454)	loss 2.3367 (2.8412)	grad_norm 1.6540 (2.0762/0.9476)	mem 34602MB
[2025-01-19 16:10:32 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][180/312]	eta 0:01:38 lr 0.000686	time 0.7985 (0.7492)	model_time 0.7980 (0.7409)	loss 3.2908 (2.8805)	grad_norm 1.0529 (2.0629/0.8726)	mem 34604MB
[2025-01-19 16:10:35 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][180/312]	eta 0:01:39 lr 0.000686	time 0.7796 (0.7546)	model_time 0.7795 (0.7458)	loss 2.5835 (2.8448)	grad_norm 1.8009 (2.1108/0.9694)	mem 34602MB
[2025-01-19 16:10:40 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][190/312]	eta 0:01:31 lr 0.000686	time 0.8114 (0.7510)	model_time 0.8112 (0.7432)	loss 2.4602 (2.8816)	grad_norm 3.1155 (2.0521/0.8596)	mem 34604MB
[2025-01-19 16:10:43 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][190/312]	eta 0:01:32 lr 0.000686	time 0.8023 (0.7564)	model_time 0.8019 (0.7480)	loss 3.2317 (2.8555)	grad_norm 1.3184 (2.1050/0.9710)	mem 34602MB
[2025-01-19 16:10:47 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][200/312]	eta 0:01:24 lr 0.000685	time 0.7579 (0.7502)	model_time 0.7578 (0.7427)	loss 3.1288 (2.8806)	grad_norm 2.0939 (2.0503/0.8497)	mem 34604MB
[2025-01-19 16:10:50 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][200/312]	eta 0:01:24 lr 0.000685	time 0.7231 (0.7547)	model_time 0.7229 (0.7467)	loss 2.9149 (2.8524)	grad_norm 0.9015 (2.1127/0.9656)	mem 34602MB
[2025-01-19 16:10:55 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][210/312]	eta 0:01:16 lr 0.000685	time 0.8106 (0.7518)	model_time 0.8102 (0.7446)	loss 2.8748 (2.8675)	grad_norm 1.2504 (2.0357/0.8393)	mem 34604MB
[2025-01-19 16:10:57 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][210/312]	eta 0:01:16 lr 0.000685	time 0.7190 (0.7546)	model_time 0.7188 (0.7470)	loss 2.1175 (2.8442)	grad_norm 1.8511 (2.1223/0.9693)	mem 34602MB
[2025-01-19 16:11:02 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][220/312]	eta 0:01:09 lr 0.000684	time 0.7190 (0.7518)	model_time 0.7188 (0.7450)	loss 2.9840 (2.8647)	grad_norm 0.9631 (2.0111/0.8339)	mem 34604MB
[2025-01-19 16:11:05 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][220/312]	eta 0:01:09 lr 0.000684	time 0.7292 (0.7537)	model_time 0.7287 (0.7465)	loss 2.9650 (2.8409)	grad_norm 2.1469 (2.1178/0.9530)	mem 34602MB
[2025-01-19 16:11:10 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][230/312]	eta 0:01:01 lr 0.000684	time 0.7143 (0.7518)	model_time 0.7142 (0.7452)	loss 3.0819 (2.8659)	grad_norm 1.6430 (2.0020/0.8277)	mem 34604MB
[2025-01-19 16:11:12 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][230/312]	eta 0:01:01 lr 0.000684	time 0.7154 (0.7541)	model_time 0.7152 (0.7471)	loss 2.8071 (2.8432)	grad_norm 4.1227 (2.1359/0.9539)	mem 34602MB
[2025-01-19 16:11:17 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][240/312]	eta 0:00:54 lr 0.000683	time 0.7285 (0.7515)	model_time 0.7281 (0.7452)	loss 2.9353 (2.8719)	grad_norm 2.7275 (1.9985/0.8209)	mem 34604MB
[2025-01-19 16:11:20 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][240/312]	eta 0:00:54 lr 0.000683	time 0.7183 (0.7535)	model_time 0.7181 (0.7468)	loss 2.8685 (2.8307)	grad_norm 1.9650 (2.1221/0.9415)	mem 34602MB
[2025-01-19 16:11:25 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][250/312]	eta 0:00:46 lr 0.000683	time 0.7483 (0.7505)	model_time 0.7478 (0.7445)	loss 3.2327 (2.8768)	grad_norm 1.0806 (1.9960/0.8194)	mem 34604MB
[2025-01-19 16:11:27 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][250/312]	eta 0:00:46 lr 0.000683	time 0.7199 (0.7531)	model_time 0.7195 (0.7467)	loss 3.0120 (2.8379)	grad_norm 2.4148 (2.1357/0.9396)	mem 34602MB
[2025-01-19 16:11:32 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][260/312]	eta 0:00:38 lr 0.000682	time 0.7230 (0.7499)	model_time 0.7228 (0.7441)	loss 2.6685 (2.8734)	grad_norm 2.0688 (1.9866/0.8111)	mem 34604MB
[2025-01-19 16:11:35 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][260/312]	eta 0:00:39 lr 0.000682	time 0.7309 (0.7527)	model_time 0.7308 (0.7465)	loss 2.4819 (2.8388)	grad_norm 1.4544 (2.1349/0.9369)	mem 34602MB
[2025-01-19 16:11:39 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][270/312]	eta 0:00:31 lr 0.000682	time 0.7172 (0.7489)	model_time 0.7170 (0.7433)	loss 2.8267 (2.8684)	grad_norm 1.5247 (1.9994/0.8298)	mem 34604MB
[2025-01-19 16:11:42 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][270/312]	eta 0:00:31 lr 0.000682	time 0.7218 (0.7526)	model_time 0.7216 (0.7466)	loss 2.8527 (2.8310)	grad_norm 3.0459 (2.1643/0.9551)	mem 34602MB
[2025-01-19 16:11:46 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][280/312]	eta 0:00:23 lr 0.000681	time 0.7229 (0.7482)	model_time 0.7228 (0.7428)	loss 3.1569 (2.8748)	grad_norm 2.9041 (2.0214/0.8489)	mem 34604MB
[2025-01-19 16:11:50 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][280/312]	eta 0:00:24 lr 0.000681	time 0.7179 (0.7522)	model_time 0.7178 (0.7464)	loss 2.7701 (2.8353)	grad_norm 1.2533 (2.1558/0.9468)	mem 34602MB
[2025-01-19 16:11:54 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][290/312]	eta 0:00:16 lr 0.000681	time 0.7264 (0.7474)	model_time 0.7262 (0.7421)	loss 2.9176 (2.8792)	grad_norm 3.2491 (2.0315/0.8482)	mem 34604MB
[2025-01-19 16:11:57 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][290/312]	eta 0:00:16 lr 0.000681	time 0.8126 (0.7517)	model_time 0.8122 (0.7461)	loss 3.1946 (2.8399)	grad_norm 2.4831 (2.1445/0.9413)	mem 34602MB
[2025-01-19 16:12:01 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][300/312]	eta 0:00:08 lr 0.000680	time 0.7898 (0.7470)	model_time 0.7897 (0.7419)	loss 2.8096 (2.8831)	grad_norm 1.2362 (2.0517/0.8689)	mem 34604MB
[2025-01-19 16:12:04 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][300/312]	eta 0:00:09 lr 0.000680	time 0.7130 (0.7516)	model_time 0.7129 (0.7462)	loss 2.9232 (2.8467)	grad_norm 1.7084 (2.1325/0.9309)	mem 34602MB
[2025-01-19 16:12:09 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][310/312]	eta 0:00:01 lr 0.000680	time 0.7978 (0.7477)	model_time 0.7977 (0.7427)	loss 2.3541 (2.8798)	grad_norm 2.0829 (2.0692/0.8758)	mem 34604MB
[2025-01-19 16:12:09 internimage_b_1k_224] (main.py 519): INFO EPOCH 220 training takes 0:03:53
[2025-01-19 16:12:09 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_220.pth saving......
[2025-01-19 16:12:12 internimage_b_1k_224] (main.py 510): INFO Train: [220/300][310/312]	eta 0:00:01 lr 0.000680	time 0.7144 (0.7516)	model_time 0.7143 (0.7463)	loss 2.3807 (2.8448)	grad_norm 1.4982 (2.1155/0.9198)	mem 34602MB
[2025-01-19 16:12:13 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_220.pth saved !!!
[2025-01-19 16:12:13 internimage_b_1k_224] (main.py 519): INFO EPOCH 220 training takes 0:03:54
[2025-01-19 16:12:13 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_220.pth saving......
[2025-01-19 16:12:16 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_220.pth saved !!!
[2025-01-19 16:12:28 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.583 (15.583)	Loss 0.7390 (0.7390)	Acc@1 85.449 (85.449)	Acc@5 97.803 (97.803)	Mem 34604MB
[2025-01-19 16:12:33 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.613 (16.613)	Loss 0.7351 (0.7351)	Acc@1 85.645 (85.645)	Acc@5 97.803 (97.803)	Mem 34602MB
[2025-01-19 16:12:34 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.923)	Loss 0.9676 (0.8322)	Acc@1 79.590 (83.279)	Acc@5 95.410 (96.533)	Mem 34604MB
[2025-01-19 16:12:34 internimage_b_1k_224] (main.py 575): INFO [Epoch:220] * Acc@1 83.167 Acc@5 96.539
[2025-01-19 16:12:34 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.2%
[2025-01-19 16:12:34 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.27%
[2025-01-19 16:12:39 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.059)	Loss 0.9608 (0.8319)	Acc@1 79.883 (83.356)	Acc@5 95.435 (96.640)	Mem 34602MB
[2025-01-19 16:12:39 internimage_b_1k_224] (main.py 575): INFO [Epoch:220] * Acc@1 83.173 Acc@5 96.647
[2025-01-19 16:12:39 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.2%
[2025-01-19 16:12:39 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.28%
[2025-01-19 16:12:52 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.542 (17.542)	Loss 0.7059 (0.7059)	Acc@1 85.938 (85.938)	Acc@5 98.218 (98.218)	Mem 34604MB
[2025-01-19 16:12:58 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 19.122 (19.122)	Loss 0.7153 (0.7153)	Acc@1 85.645 (85.645)	Acc@5 98.120 (98.120)	Mem 34602MB
[2025-01-19 16:13:02 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (2.544)	Loss 0.9391 (0.8102)	Acc@1 79.883 (83.676)	Acc@5 95.581 (96.755)	Mem 34604MB
[2025-01-19 16:13:02 internimage_b_1k_224] (main.py 575): INFO [Epoch:220] * Acc@1 83.487 Acc@5 96.799
[2025-01-19 16:13:02 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.5%
[2025-01-19 16:13:02 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:13:04 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.331)	Loss 0.9412 (0.8127)	Acc@1 79.663 (83.618)	Acc@5 95.508 (96.744)	Mem 34602MB
[2025-01-19 16:13:05 internimage_b_1k_224] (main.py 575): INFO [Epoch:220] * Acc@1 83.459 Acc@5 96.793
[2025-01-19 16:13:05 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.5%
[2025-01-19 16:13:05 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:13:06 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:13:06 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.49%
[2025-01-19 16:13:09 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:13:09 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.46%
[2025-01-19 16:13:09 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][0/312]	eta 0:10:53 lr 0.000680	time 2.0950 (2.0950)	model_time 0.7465 (0.7465)	loss 1.8715 (1.8715)	grad_norm 2.6122 (2.6122/0.0000)	mem 34604MB
[2025-01-19 16:13:11 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][0/312]	eta 0:11:11 lr 0.000680	time 2.1538 (2.1538)	model_time 0.7585 (0.7585)	loss 2.2174 (2.2174)	grad_norm 1.0885 (1.0885/0.0000)	mem 34602MB
[2025-01-19 16:13:16 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][10/312]	eta 0:04:20 lr 0.000679	time 0.7204 (0.8638)	model_time 0.7203 (0.7409)	loss 2.8822 (2.8810)	grad_norm 1.4910 (2.4729/1.1507)	mem 34604MB
[2025-01-19 16:13:18 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][10/312]	eta 0:04:17 lr 0.000679	time 0.7311 (0.8543)	model_time 0.7310 (0.7271)	loss 2.7875 (2.8708)	grad_norm 1.7042 (1.4593/0.3673)	mem 34602MB
[2025-01-19 16:13:24 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][20/312]	eta 0:04:01 lr 0.000679	time 0.8072 (0.8274)	model_time 0.8067 (0.7629)	loss 2.7081 (2.7830)	grad_norm 1.5334 (2.0230/1.0028)	mem 34604MB
[2025-01-19 16:13:25 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][20/312]	eta 0:03:56 lr 0.000679	time 0.7192 (0.8085)	model_time 0.7186 (0.7417)	loss 3.0106 (2.9228)	grad_norm 1.9014 (1.9076/0.9486)	mem 34602MB
[2025-01-19 16:13:31 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][30/312]	eta 0:03:47 lr 0.000678	time 0.7242 (0.8050)	model_time 0.7241 (0.7611)	loss 2.4086 (2.8139)	grad_norm 0.9333 (1.9259/0.8679)	mem 34604MB
[2025-01-19 16:13:33 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][30/312]	eta 0:03:40 lr 0.000678	time 0.7207 (0.7820)	model_time 0.7203 (0.7367)	loss 2.7014 (2.8986)	grad_norm 3.4899 (2.1227/0.9566)	mem 34602MB
[2025-01-19 16:13:39 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][40/312]	eta 0:03:35 lr 0.000678	time 0.7511 (0.7906)	model_time 0.7509 (0.7574)	loss 3.1617 (2.8297)	grad_norm 1.9320 (1.8950/0.8516)	mem 34604MB
[2025-01-19 16:13:40 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][40/312]	eta 0:03:30 lr 0.000678	time 0.7184 (0.7747)	model_time 0.7183 (0.7404)	loss 3.6122 (2.9102)	grad_norm 2.5258 (2.2031/0.9631)	mem 34602MB
[2025-01-19 16:13:46 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][50/312]	eta 0:03:24 lr 0.000677	time 0.7268 (0.7808)	model_time 0.7266 (0.7540)	loss 2.2442 (2.7560)	grad_norm 2.2560 (1.9066/0.8031)	mem 34604MB
[2025-01-19 16:13:48 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][50/312]	eta 0:03:21 lr 0.000677	time 0.7200 (0.7682)	model_time 0.7199 (0.7405)	loss 2.8063 (2.9096)	grad_norm 3.3873 (2.1087/0.9745)	mem 34602MB
[2025-01-19 16:13:54 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][60/312]	eta 0:03:14 lr 0.000677	time 0.7397 (0.7725)	model_time 0.7392 (0.7500)	loss 3.2623 (2.7987)	grad_norm 1.0344 (1.8491/0.7676)	mem 34604MB
[2025-01-19 16:13:55 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][60/312]	eta 0:03:12 lr 0.000677	time 0.7629 (0.7644)	model_time 0.7628 (0.7411)	loss 3.0514 (2.9040)	grad_norm 2.5275 (2.0968/0.9182)	mem 34602MB
[2025-01-19 16:14:01 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][70/312]	eta 0:03:05 lr 0.000676	time 0.7248 (0.7656)	model_time 0.7244 (0.7462)	loss 3.0261 (2.8078)	grad_norm 1.6013 (1.8600/0.8054)	mem 34604MB
[2025-01-19 16:14:03 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][70/312]	eta 0:03:04 lr 0.000676	time 0.8086 (0.7609)	model_time 0.8082 (0.7409)	loss 2.7478 (2.8890)	grad_norm 2.0478 (2.1036/0.8891)	mem 34602MB
[2025-01-19 16:14:08 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][80/312]	eta 0:02:56 lr 0.000676	time 0.7245 (0.7615)	model_time 0.7244 (0.7444)	loss 2.0653 (2.8207)	grad_norm 1.9980 (1.9383/0.8549)	mem 34604MB
[2025-01-19 16:14:10 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][80/312]	eta 0:02:55 lr 0.000676	time 0.7280 (0.7582)	model_time 0.7276 (0.7407)	loss 3.1339 (2.8923)	grad_norm 1.7378 (2.0509/0.8664)	mem 34602MB
[2025-01-19 16:14:15 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][90/312]	eta 0:02:48 lr 0.000675	time 0.7277 (0.7582)	model_time 0.7276 (0.7431)	loss 3.0101 (2.8061)	grad_norm 1.8933 (1.9489/0.8600)	mem 34604MB
[2025-01-19 16:14:17 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][90/312]	eta 0:02:47 lr 0.000675	time 0.8069 (0.7565)	model_time 0.8068 (0.7408)	loss 3.2502 (2.8557)	grad_norm 1.7764 (2.0345/0.8354)	mem 34602MB
[2025-01-19 16:14:23 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][100/312]	eta 0:02:40 lr 0.000675	time 0.7232 (0.7554)	model_time 0.7230 (0.7417)	loss 2.1049 (2.7966)	grad_norm 0.9279 (1.8931/0.8430)	mem 34604MB
[2025-01-19 16:14:25 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][100/312]	eta 0:02:40 lr 0.000675	time 0.7241 (0.7552)	model_time 0.7239 (0.7410)	loss 2.8763 (2.8772)	grad_norm 3.6784 (2.0390/0.8313)	mem 34602MB
[2025-01-19 16:14:30 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][110/312]	eta 0:02:32 lr 0.000674	time 0.8372 (0.7545)	model_time 0.8367 (0.7420)	loss 2.8924 (2.7855)	grad_norm 3.0048 (1.8835/0.8275)	mem 34604MB
[2025-01-19 16:14:32 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][110/312]	eta 0:02:32 lr 0.000674	time 0.8160 (0.7554)	model_time 0.8156 (0.7425)	loss 3.3835 (2.9034)	grad_norm 2.2193 (1.9892/0.8153)	mem 34602MB
[2025-01-19 16:14:38 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][120/312]	eta 0:02:25 lr 0.000674	time 0.8134 (0.7563)	model_time 0.8132 (0.7448)	loss 3.4816 (2.7741)	grad_norm 2.9216 (1.8908/0.8291)	mem 34604MB
[2025-01-19 16:14:40 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][120/312]	eta 0:02:25 lr 0.000674	time 0.7197 (0.7562)	model_time 0.7193 (0.7443)	loss 3.0837 (2.8860)	grad_norm 1.9965 (1.9980/0.7968)	mem 34602MB
[2025-01-19 16:14:45 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][130/312]	eta 0:02:17 lr 0.000673	time 0.7240 (0.7554)	model_time 0.7238 (0.7447)	loss 3.1396 (2.7818)	grad_norm 0.9898 (1.8771/0.8120)	mem 34604MB
[2025-01-19 16:14:47 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][130/312]	eta 0:02:17 lr 0.000673	time 0.7199 (0.7547)	model_time 0.7194 (0.7437)	loss 1.5716 (2.8646)	grad_norm 1.1799 (1.9906/0.7837)	mem 34602MB
[2025-01-19 16:14:53 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][140/312]	eta 0:02:10 lr 0.000673	time 0.8785 (0.7579)	model_time 0.8781 (0.7479)	loss 3.5389 (2.8040)	grad_norm 2.0497 (1.8615/0.7945)	mem 34604MB
[2025-01-19 16:14:55 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][140/312]	eta 0:02:09 lr 0.000673	time 0.8137 (0.7556)	model_time 0.8136 (0.7453)	loss 3.2631 (2.8530)	grad_norm 3.1211 (2.0682/0.8917)	mem 34602MB
[2025-01-19 16:15:01 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][150/312]	eta 0:02:02 lr 0.000672	time 0.8372 (0.7577)	model_time 0.8367 (0.7484)	loss 2.4966 (2.8060)	grad_norm 1.1986 (1.8544/0.7865)	mem 34604MB
[2025-01-19 16:15:02 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][150/312]	eta 0:02:02 lr 0.000672	time 0.7252 (0.7535)	model_time 0.7250 (0.7439)	loss 3.4465 (2.8546)	grad_norm 1.4892 (2.0424/0.8736)	mem 34602MB
[2025-01-19 16:15:08 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][160/312]	eta 0:01:55 lr 0.000672	time 0.7288 (0.7570)	model_time 0.7283 (0.7483)	loss 1.9396 (2.8134)	grad_norm 2.1287 (1.8801/0.7949)	mem 34604MB
[2025-01-19 16:15:10 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][160/312]	eta 0:01:54 lr 0.000672	time 0.7180 (0.7536)	model_time 0.7174 (0.7446)	loss 3.2667 (2.8506)	grad_norm 2.1710 (2.0811/0.8821)	mem 34602MB
[2025-01-19 16:15:16 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][170/312]	eta 0:01:47 lr 0.000671	time 0.7183 (0.7561)	model_time 0.7181 (0.7479)	loss 3.0648 (2.8198)	grad_norm 2.0379 (1.8903/0.8052)	mem 34604MB
[2025-01-19 16:15:17 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][170/312]	eta 0:01:46 lr 0.000671	time 0.7319 (0.7532)	model_time 0.7315 (0.7447)	loss 3.1464 (2.8453)	grad_norm 2.0368 (2.0742/0.8620)	mem 34602MB
[2025-01-19 16:15:23 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][180/312]	eta 0:01:39 lr 0.000671	time 0.7198 (0.7543)	model_time 0.7197 (0.7465)	loss 2.9714 (2.8221)	grad_norm 3.1739 (1.9422/0.8528)	mem 34604MB
[2025-01-19 16:15:25 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][180/312]	eta 0:01:39 lr 0.000671	time 0.7171 (0.7524)	model_time 0.7167 (0.7443)	loss 2.0446 (2.8460)	grad_norm 2.9365 (2.0686/0.8629)	mem 34602MB
[2025-01-19 16:15:30 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][190/312]	eta 0:01:31 lr 0.000671	time 0.7102 (0.7526)	model_time 0.7100 (0.7452)	loss 2.8912 (2.8242)	grad_norm 2.1104 (2.0105/0.9042)	mem 34604MB
[2025-01-19 16:15:32 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][190/312]	eta 0:01:31 lr 0.000671	time 0.8009 (0.7523)	model_time 0.8007 (0.7446)	loss 2.5902 (2.8376)	grad_norm 1.7247 (2.0808/0.8514)	mem 34602MB
[2025-01-19 16:15:37 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][200/312]	eta 0:01:24 lr 0.000670	time 0.7254 (0.7513)	model_time 0.7250 (0.7442)	loss 3.3001 (2.8342)	grad_norm 2.8111 (2.0010/0.8867)	mem 34604MB
[2025-01-19 16:15:40 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][200/312]	eta 0:01:24 lr 0.000670	time 0.7311 (0.7519)	model_time 0.7309 (0.7446)	loss 2.8596 (2.8377)	grad_norm 3.1389 (2.0871/0.8488)	mem 34602MB
[2025-01-19 16:15:45 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][210/312]	eta 0:01:16 lr 0.000670	time 0.7502 (0.7504)	model_time 0.7498 (0.7437)	loss 3.1191 (2.8436)	grad_norm 1.2942 (1.9796/0.8735)	mem 34604MB
[2025-01-19 16:15:47 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][210/312]	eta 0:01:16 lr 0.000670	time 0.8072 (0.7519)	model_time 0.8067 (0.7449)	loss 2.9843 (2.8407)	grad_norm 1.3866 (2.0695/0.8586)	mem 34602MB
[2025-01-19 16:15:52 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][220/312]	eta 0:01:08 lr 0.000669	time 0.7179 (0.7492)	model_time 0.7176 (0.7427)	loss 3.1977 (2.8455)	grad_norm 1.5909 (1.9630/0.8630)	mem 34604MB
[2025-01-19 16:15:54 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][220/312]	eta 0:01:09 lr 0.000669	time 0.7133 (0.7508)	model_time 0.7132 (0.7441)	loss 2.9565 (2.8422)	grad_norm inf (2.0690/0.8553)	mem 34602MB
[2025-01-19 16:15:59 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][230/312]	eta 0:01:01 lr 0.000669	time 0.8374 (0.7488)	model_time 0.8372 (0.7426)	loss 3.0218 (2.8402)	grad_norm 1.9543 (1.9329/0.8587)	mem 34604MB
[2025-01-19 16:16:02 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][230/312]	eta 0:01:01 lr 0.000669	time 0.8166 (0.7511)	model_time 0.8165 (0.7446)	loss 2.3703 (2.8452)	grad_norm 1.5173 (2.0761/0.8627)	mem 34602MB
[2025-01-19 16:16:07 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][240/312]	eta 0:00:53 lr 0.000668	time 0.8165 (0.7500)	model_time 0.8161 (0.7440)	loss 3.0652 (2.8484)	grad_norm 2.3982 (1.9135/0.8515)	mem 34604MB
[2025-01-19 16:16:10 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][240/312]	eta 0:00:54 lr 0.000668	time 0.7201 (0.7523)	model_time 0.7200 (0.7461)	loss 3.1255 (2.8434)	grad_norm 3.1735 (2.0749/0.8528)	mem 34602MB
[2025-01-19 16:16:15 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][250/312]	eta 0:00:46 lr 0.000668	time 0.7085 (0.7497)	model_time 0.7084 (0.7439)	loss 2.1268 (2.8434)	grad_norm 1.8853 (1.8948/0.8420)	mem 34604MB
[2025-01-19 16:16:17 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][250/312]	eta 0:00:46 lr 0.000668	time 0.7245 (0.7516)	model_time 0.7243 (0.7457)	loss 2.7002 (2.8417)	grad_norm 2.2546 (2.0601/0.8483)	mem 34602MB
[2025-01-19 16:16:22 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][260/312]	eta 0:00:39 lr 0.000667	time 0.7984 (0.7509)	model_time 0.7980 (0.7454)	loss 2.7601 (2.8476)	grad_norm 2.8059 (1.9324/0.8633)	mem 34604MB
[2025-01-19 16:16:25 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][260/312]	eta 0:00:39 lr 0.000667	time 0.7999 (0.7517)	model_time 0.7998 (0.7460)	loss 2.8357 (2.8408)	grad_norm 1.7747 (2.0519/0.8418)	mem 34602MB
[2025-01-19 16:16:30 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][270/312]	eta 0:00:31 lr 0.000667	time 0.8611 (0.7511)	model_time 0.8610 (0.7458)	loss 2.4722 (2.8434)	grad_norm 2.8845 (1.9693/0.8912)	mem 34604MB
[2025-01-19 16:16:32 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][270/312]	eta 0:00:31 lr 0.000667	time 0.7237 (0.7510)	model_time 0.7232 (0.7455)	loss 3.3994 (2.8490)	grad_norm 1.2631 (2.0363/0.8365)	mem 34602MB
[2025-01-19 16:16:37 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][280/312]	eta 0:00:24 lr 0.000666	time 0.7355 (0.7510)	model_time 0.7350 (0.7459)	loss 2.9846 (2.8390)	grad_norm 2.4998 (1.9831/0.8931)	mem 34604MB
[2025-01-19 16:16:40 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][280/312]	eta 0:00:24 lr 0.000666	time 0.7178 (0.7511)	model_time 0.7173 (0.7457)	loss 3.0996 (2.8463)	grad_norm 2.7843 (2.0522/0.8345)	mem 34602MB
[2025-01-19 16:16:45 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][290/312]	eta 0:00:16 lr 0.000666	time 0.7164 (0.7507)	model_time 0.7159 (0.7457)	loss 3.0223 (2.8479)	grad_norm 2.6359 (1.9882/0.8854)	mem 34604MB
[2025-01-19 16:16:47 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][290/312]	eta 0:00:16 lr 0.000666	time 0.7276 (0.7509)	model_time 0.7274 (0.7457)	loss 2.7364 (2.8371)	grad_norm 3.7545 (2.0682/0.8357)	mem 34602MB
[2025-01-19 16:16:52 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][300/312]	eta 0:00:08 lr 0.000665	time 0.7125 (0.7499)	model_time 0.7124 (0.7451)	loss 2.9942 (2.8537)	grad_norm 2.4501 (1.9920/0.8786)	mem 34604MB
[2025-01-19 16:16:54 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][300/312]	eta 0:00:09 lr 0.000665	time 0.7170 (0.7503)	model_time 0.7169 (0.7453)	loss 3.5126 (2.8382)	grad_norm 2.6843 (2.0950/0.8604)	mem 34602MB
[2025-01-19 16:16:59 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][310/312]	eta 0:00:01 lr 0.000665	time 0.7125 (0.7488)	model_time 0.7124 (0.7441)	loss 2.9121 (2.8530)	grad_norm 2.1321 (1.9880/0.8675)	mem 34604MB
[2025-01-19 16:17:00 internimage_b_1k_224] (main.py 519): INFO EPOCH 221 training takes 0:03:53
[2025-01-19 16:17:00 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_221.pth saving......
[2025-01-19 16:17:02 internimage_b_1k_224] (main.py 510): INFO Train: [221/300][310/312]	eta 0:00:01 lr 0.000665	time 0.7186 (0.7495)	model_time 0.7185 (0.7446)	loss 2.5251 (2.8347)	grad_norm 1.2621 (2.1255/0.8628)	mem 34602MB
[2025-01-19 16:17:02 internimage_b_1k_224] (main.py 519): INFO EPOCH 221 training takes 0:03:53
[2025-01-19 16:17:02 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_221.pth saving......
[2025-01-19 16:17:03 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_221.pth saved !!!
[2025-01-19 16:17:06 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_221.pth saved !!!
[2025-01-19 16:17:19 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.714 (15.714)	Loss 0.7244 (0.7244)	Acc@1 85.596 (85.596)	Acc@5 97.778 (97.778)	Mem 34604MB
[2025-01-19 16:17:22 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.293 (16.293)	Loss 0.7123 (0.7123)	Acc@1 85.303 (85.303)	Acc@5 97.729 (97.729)	Mem 34602MB
[2025-01-19 16:17:25 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (1.991)	Loss 0.9345 (0.8252)	Acc@1 80.054 (83.552)	Acc@5 95.874 (96.591)	Mem 34604MB
[2025-01-19 16:17:25 internimage_b_1k_224] (main.py 575): INFO [Epoch:221] * Acc@1 83.389 Acc@5 96.591
[2025-01-19 16:17:25 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.4%
[2025-01-19 16:17:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 16:17:28 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.070)	Loss 0.9255 (0.8081)	Acc@1 79.541 (83.432)	Acc@5 96.021 (96.684)	Mem 34602MB
[2025-01-19 16:17:29 internimage_b_1k_224] (main.py 575): INFO [Epoch:221] * Acc@1 83.281 Acc@5 96.691
[2025-01-19 16:17:29 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.3%
[2025-01-19 16:17:29 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 16:17:29 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 16:17:29 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.39%
[2025-01-19 16:17:32 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 16:17:32 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.28%
[2025-01-19 16:17:45 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.567 (15.567)	Loss 0.7066 (0.7066)	Acc@1 85.962 (85.962)	Acc@5 98.218 (98.218)	Mem 34604MB
[2025-01-19 16:17:48 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.263 (16.263)	Loss 0.7160 (0.7160)	Acc@1 85.693 (85.693)	Acc@5 98.120 (98.120)	Mem 34602MB
[2025-01-19 16:17:51 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (2.037)	Loss 0.9386 (0.8103)	Acc@1 79.932 (83.705)	Acc@5 95.581 (96.760)	Mem 34604MB
[2025-01-19 16:17:52 internimage_b_1k_224] (main.py 575): INFO [Epoch:221] * Acc@1 83.519 Acc@5 96.803
[2025-01-19 16:17:52 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.5%
[2025-01-19 16:17:52 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:17:53 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.956)	Loss 0.9408 (0.8127)	Acc@1 79.663 (83.647)	Acc@5 95.483 (96.751)	Mem 34602MB
[2025-01-19 16:17:54 internimage_b_1k_224] (main.py 575): INFO [Epoch:221] * Acc@1 83.481 Acc@5 96.801
[2025-01-19 16:17:54 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.5%
[2025-01-19 16:17:54 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:17:56 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:17:56 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.52%
[2025-01-19 16:17:58 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][0/312]	eta 0:10:14 lr 0.000665	time 1.9696 (1.9696)	model_time 0.7299 (0.7299)	loss 2.5406 (2.5406)	grad_norm 2.1653 (2.1653/0.0000)	mem 34604MB
[2025-01-19 16:17:58 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:17:58 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.48%
[2025-01-19 16:18:00 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][0/312]	eta 0:10:38 lr 0.000665	time 2.0477 (2.0477)	model_time 0.7507 (0.7507)	loss 2.9394 (2.9394)	grad_norm 2.3609 (2.3609/0.0000)	mem 34602MB
[2025-01-19 16:18:05 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][10/312]	eta 0:04:14 lr 0.000664	time 0.7306 (0.8435)	model_time 0.7302 (0.7304)	loss 3.7365 (3.0155)	grad_norm 1.3175 (2.0475/0.5851)	mem 34604MB
[2025-01-19 16:18:07 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][10/312]	eta 0:04:20 lr 0.000664	time 0.7382 (0.8637)	model_time 0.7380 (0.7455)	loss 2.1110 (2.8793)	grad_norm 1.4939 (1.9783/0.6563)	mem 34602MB
[2025-01-19 16:18:12 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][20/312]	eta 0:03:50 lr 0.000664	time 0.7272 (0.7880)	model_time 0.7270 (0.7286)	loss 2.3447 (2.9346)	grad_norm 0.9260 (1.8045/0.6738)	mem 34604MB
[2025-01-19 16:18:15 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][20/312]	eta 0:03:54 lr 0.000664	time 0.7177 (0.8039)	model_time 0.7172 (0.7418)	loss 2.4922 (2.8152)	grad_norm 2.7119 (1.9896/0.5445)	mem 34602MB
[2025-01-19 16:18:20 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][30/312]	eta 0:03:37 lr 0.000663	time 0.7419 (0.7697)	model_time 0.7418 (0.7293)	loss 3.1939 (2.9123)	grad_norm 2.6262 (1.8851/0.6900)	mem 34604MB
[2025-01-19 16:18:22 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][30/312]	eta 0:03:41 lr 0.000663	time 0.8065 (0.7845)	model_time 0.8064 (0.7423)	loss 3.4953 (2.8948)	grad_norm 1.4011 (1.9651/0.5956)	mem 34602MB
[2025-01-19 16:18:27 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][40/312]	eta 0:03:28 lr 0.000663	time 0.8106 (0.7650)	model_time 0.8101 (0.7344)	loss 2.9122 (2.9003)	grad_norm 1.4059 (1.8905/0.6726)	mem 34604MB
[2025-01-19 16:18:30 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][40/312]	eta 0:03:31 lr 0.000663	time 0.8091 (0.7759)	model_time 0.8087 (0.7439)	loss 2.5509 (2.8719)	grad_norm 1.9217 (1.8518/0.6040)	mem 34602MB
[2025-01-19 16:18:35 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][50/312]	eta 0:03:20 lr 0.000662	time 0.7154 (0.7654)	model_time 0.7149 (0.7407)	loss 3.5133 (2.9121)	grad_norm 1.5209 (1.8559/0.6636)	mem 34604MB
[2025-01-19 16:18:37 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][50/312]	eta 0:03:23 lr 0.000662	time 0.7177 (0.7772)	model_time 0.7175 (0.7515)	loss 3.0548 (2.8443)	grad_norm 2.5646 (1.8768/0.6040)	mem 34602MB
[2025-01-19 16:18:42 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][60/312]	eta 0:03:12 lr 0.000662	time 0.8057 (0.7639)	model_time 0.8056 (0.7432)	loss 2.0674 (2.8971)	grad_norm 1.7343 (1.7784/0.6466)	mem 34604MB
[2025-01-19 16:18:45 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][60/312]	eta 0:03:14 lr 0.000662	time 0.7231 (0.7706)	model_time 0.7229 (0.7490)	loss 2.8634 (2.8638)	grad_norm 4.4638 (1.9147/0.6512)	mem 34602MB
[2025-01-19 16:18:50 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][70/312]	eta 0:03:05 lr 0.000661	time 0.8044 (0.7670)	model_time 0.8039 (0.7492)	loss 3.2287 (2.9000)	grad_norm 1.8459 (1.7740/0.6426)	mem 34604MB
[2025-01-19 16:18:52 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][70/312]	eta 0:03:05 lr 0.000661	time 0.8026 (0.7675)	model_time 0.8021 (0.7490)	loss 3.1281 (2.8680)	grad_norm 1.5239 (2.0101/0.7515)	mem 34602MB
[2025-01-19 16:18:58 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][80/312]	eta 0:02:57 lr 0.000661	time 0.8139 (0.7668)	model_time 0.8137 (0.7511)	loss 3.1000 (2.9030)	grad_norm 1.6116 (1.8152/0.7146)	mem 34604MB
[2025-01-19 16:19:00 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][80/312]	eta 0:02:57 lr 0.000661	time 0.7230 (0.7637)	model_time 0.7226 (0.7474)	loss 2.9160 (2.8782)	grad_norm 1.3054 (2.0637/0.8370)	mem 34602MB
[2025-01-19 16:19:05 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][90/312]	eta 0:02:49 lr 0.000660	time 0.7175 (0.7642)	model_time 0.7171 (0.7502)	loss 3.0425 (2.9298)	grad_norm 2.1902 (1.9001/0.7694)	mem 34604MB
[2025-01-19 16:19:07 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][90/312]	eta 0:02:49 lr 0.000660	time 0.7195 (0.7624)	model_time 0.7193 (0.7478)	loss 3.3274 (2.8765)	grad_norm 1.2194 (2.0436/0.8582)	mem 34602MB
[2025-01-19 16:19:13 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][100/312]	eta 0:02:41 lr 0.000660	time 0.7156 (0.7619)	model_time 0.7154 (0.7492)	loss 3.1541 (2.9472)	grad_norm 1.0526 (1.8812/0.7522)	mem 34604MB
[2025-01-19 16:19:15 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][100/312]	eta 0:02:41 lr 0.000660	time 0.7262 (0.7599)	model_time 0.7257 (0.7467)	loss 2.9129 (2.8820)	grad_norm 2.3804 (2.1267/0.9570)	mem 34602MB
[2025-01-19 16:19:20 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][110/312]	eta 0:02:33 lr 0.000659	time 0.7219 (0.7588)	model_time 0.7215 (0.7473)	loss 3.2055 (2.9439)	grad_norm 1.1312 (1.8721/0.7361)	mem 34604MB
[2025-01-19 16:19:22 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][110/312]	eta 0:02:33 lr 0.000659	time 0.8291 (0.7589)	model_time 0.8290 (0.7469)	loss 3.1220 (2.8735)	grad_norm 1.9951 (2.1259/0.9515)	mem 34602MB
[2025-01-19 16:19:27 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][120/312]	eta 0:02:25 lr 0.000659	time 0.7213 (0.7564)	model_time 0.7212 (0.7458)	loss 2.7609 (2.9411)	grad_norm 1.3858 (1.8813/0.7393)	mem 34604MB
[2025-01-19 16:19:29 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][120/312]	eta 0:02:25 lr 0.000659	time 0.7189 (0.7566)	model_time 0.7187 (0.7455)	loss 3.0382 (2.8805)	grad_norm 1.3869 (2.1269/0.9348)	mem 34602MB
[2025-01-19 16:19:35 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][130/312]	eta 0:02:17 lr 0.000658	time 0.7253 (0.7543)	model_time 0.7249 (0.7445)	loss 3.2491 (2.9484)	grad_norm 1.5578 (1.8769/0.7346)	mem 34604MB
[2025-01-19 16:19:37 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][130/312]	eta 0:02:17 lr 0.000658	time 0.7262 (0.7561)	model_time 0.7257 (0.7458)	loss 3.4135 (2.8804)	grad_norm 0.8644 (2.0885/0.9148)	mem 34602MB
[2025-01-19 16:19:42 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][140/312]	eta 0:02:09 lr 0.000658	time 0.7178 (0.7523)	model_time 0.7176 (0.7431)	loss 2.5989 (2.9053)	grad_norm 1.1963 (1.8837/0.7266)	mem 34604MB
[2025-01-19 16:19:44 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][140/312]	eta 0:02:09 lr 0.000658	time 0.7178 (0.7552)	model_time 0.7176 (0.7457)	loss 2.9756 (2.8672)	grad_norm 1.8774 (2.0761/0.9017)	mem 34602MB
[2025-01-19 16:19:49 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][150/312]	eta 0:02:01 lr 0.000657	time 0.7270 (0.7509)	model_time 0.7268 (0.7423)	loss 1.9482 (2.9061)	grad_norm 2.3472 (1.8774/0.7144)	mem 34604MB
[2025-01-19 16:19:52 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][150/312]	eta 0:02:02 lr 0.000657	time 0.7187 (0.7535)	model_time 0.7185 (0.7446)	loss 2.6117 (2.8643)	grad_norm 1.2414 (2.0517/0.8861)	mem 34602MB
[2025-01-19 16:19:57 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][160/312]	eta 0:01:54 lr 0.000657	time 0.8334 (0.7509)	model_time 0.8329 (0.7428)	loss 1.9116 (2.8923)	grad_norm 2.7774 (1.9288/0.7596)	mem 34604MB
[2025-01-19 16:19:59 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][160/312]	eta 0:01:54 lr 0.000657	time 0.8110 (0.7540)	model_time 0.8106 (0.7456)	loss 2.8481 (2.8769)	grad_norm 1.9729 (2.0521/0.8829)	mem 34602MB
[2025-01-19 16:20:04 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][170/312]	eta 0:01:46 lr 0.000656	time 0.7595 (0.7520)	model_time 0.7590 (0.7444)	loss 2.9188 (2.8918)	grad_norm 1.8800 (1.9295/0.7560)	mem 34604MB
[2025-01-19 16:20:07 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][170/312]	eta 0:01:47 lr 0.000656	time 0.7175 (0.7548)	model_time 0.7171 (0.7469)	loss 3.1263 (2.8876)	grad_norm 2.2715 (2.0526/0.8675)	mem 34602MB
[2025-01-19 16:20:12 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][180/312]	eta 0:01:39 lr 0.000656	time 0.8066 (0.7517)	model_time 0.8061 (0.7444)	loss 2.4098 (2.8811)	grad_norm 1.6383 (1.9110/0.7455)	mem 34604MB
[2025-01-19 16:20:15 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][180/312]	eta 0:01:39 lr 0.000656	time 0.7654 (0.7553)	model_time 0.7650 (0.7478)	loss 3.0228 (2.8899)	grad_norm 1.8423 (2.0396/0.8513)	mem 34602MB
[2025-01-19 16:20:20 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][190/312]	eta 0:01:31 lr 0.000655	time 0.8042 (0.7532)	model_time 0.8041 (0.7464)	loss 3.1480 (2.8762)	grad_norm 1.4316 (1.9019/0.7320)	mem 34604MB
[2025-01-19 16:20:22 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][190/312]	eta 0:01:32 lr 0.000655	time 0.7996 (0.7550)	model_time 0.7994 (0.7478)	loss 2.0696 (2.8869)	grad_norm 2.0675 (2.0559/0.8496)	mem 34602MB
[2025-01-19 16:20:27 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][200/312]	eta 0:01:24 lr 0.000655	time 0.8239 (0.7532)	model_time 0.8235 (0.7467)	loss 3.0080 (2.8741)	grad_norm 2.6957 (1.8976/0.7244)	mem 34604MB
[2025-01-19 16:20:29 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][200/312]	eta 0:01:24 lr 0.000655	time 0.7199 (0.7543)	model_time 0.7194 (0.7475)	loss 2.6275 (2.8887)	grad_norm 1.3838 (2.0717/0.8504)	mem 34602MB
[2025-01-19 16:20:35 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][210/312]	eta 0:01:16 lr 0.000654	time 0.7587 (0.7530)	model_time 0.7585 (0.7468)	loss 2.9059 (2.8775)	grad_norm 1.6229 (1.9122/0.7551)	mem 34604MB
[2025-01-19 16:20:37 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][210/312]	eta 0:01:16 lr 0.000654	time 0.7199 (0.7542)	model_time 0.7194 (0.7477)	loss 1.8289 (2.8779)	grad_norm 1.6380 (2.0528/0.8438)	mem 34602MB
[2025-01-19 16:20:42 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][220/312]	eta 0:01:09 lr 0.000654	time 0.7468 (0.7523)	model_time 0.7467 (0.7463)	loss 3.4714 (2.8848)	grad_norm 1.8858 (1.8985/0.7489)	mem 34604MB
[2025-01-19 16:20:44 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][220/312]	eta 0:01:09 lr 0.000654	time 0.7213 (0.7536)	model_time 0.7208 (0.7473)	loss 2.9288 (2.8799)	grad_norm 1.2822 (2.0520/0.8340)	mem 34602MB
[2025-01-19 16:20:49 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][230/312]	eta 0:01:01 lr 0.000653	time 0.7578 (0.7515)	model_time 0.7572 (0.7458)	loss 2.6503 (2.8807)	grad_norm 3.2816 (1.9085/0.7529)	mem 34604MB
[2025-01-19 16:20:52 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][230/312]	eta 0:01:01 lr 0.000653	time 0.8136 (0.7532)	model_time 0.8132 (0.7472)	loss 2.7278 (2.8745)	grad_norm 2.3557 (2.0582/0.8309)	mem 34602MB
[2025-01-19 16:20:57 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][240/312]	eta 0:00:54 lr 0.000653	time 0.7158 (0.7504)	model_time 0.7154 (0.7449)	loss 3.0921 (2.8865)	grad_norm 1.4059 (1.9123/0.7769)	mem 34604MB
[2025-01-19 16:20:59 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][240/312]	eta 0:00:54 lr 0.000653	time 0.7716 (0.7523)	model_time 0.7715 (0.7466)	loss 3.1055 (2.8681)	grad_norm 2.4136 (2.0658/0.8201)	mem 34602MB
[2025-01-19 16:21:04 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][250/312]	eta 0:00:46 lr 0.000653	time 0.7219 (0.7494)	model_time 0.7214 (0.7441)	loss 3.0367 (2.8733)	grad_norm 1.1917 (1.8992/0.7716)	mem 34604MB
[2025-01-19 16:21:07 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][250/312]	eta 0:00:46 lr 0.000653	time 0.7186 (0.7520)	model_time 0.7184 (0.7464)	loss 3.0859 (2.8634)	grad_norm 1.3132 (2.0531/0.8171)	mem 34602MB
[2025-01-19 16:21:11 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][260/312]	eta 0:00:38 lr 0.000652	time 0.7274 (0.7486)	model_time 0.7273 (0.7434)	loss 2.6996 (2.8686)	grad_norm 2.3240 (1.9012/0.7602)	mem 34604MB
[2025-01-19 16:21:14 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][260/312]	eta 0:00:39 lr 0.000652	time 0.7268 (0.7513)	model_time 0.7266 (0.7459)	loss 3.5093 (2.8635)	grad_norm 2.0934 (2.0679/0.8205)	mem 34602MB
[2025-01-19 16:21:19 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][270/312]	eta 0:00:31 lr 0.000652	time 0.7709 (0.7479)	model_time 0.7705 (0.7429)	loss 2.7194 (2.8629)	grad_norm 2.3854 (1.9421/0.8134)	mem 34604MB
[2025-01-19 16:21:21 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][270/312]	eta 0:00:31 lr 0.000652	time 0.7325 (0.7510)	model_time 0.7324 (0.7459)	loss 2.6837 (2.8624)	grad_norm 4.0794 (2.0780/0.8232)	mem 34602MB
[2025-01-19 16:21:26 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][280/312]	eta 0:00:23 lr 0.000651	time 0.8169 (0.7475)	model_time 0.8168 (0.7427)	loss 3.1965 (2.8661)	grad_norm 2.2262 (1.9446/0.8081)	mem 34604MB
[2025-01-19 16:21:29 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][280/312]	eta 0:00:24 lr 0.000651	time 0.8038 (0.7514)	model_time 0.8036 (0.7464)	loss 2.1557 (2.8641)	grad_norm 2.6446 (2.0749/0.8247)	mem 34602MB
[2025-01-19 16:21:34 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][290/312]	eta 0:00:16 lr 0.000651	time 0.7132 (0.7485)	model_time 0.7130 (0.7438)	loss 1.8208 (2.8619)	grad_norm 1.8685 (1.9323/0.8010)	mem 34604MB
[2025-01-19 16:21:37 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][290/312]	eta 0:00:16 lr 0.000651	time 0.7179 (0.7519)	model_time 0.7175 (0.7471)	loss 1.9876 (2.8651)	grad_norm 1.1961 (2.0821/0.8393)	mem 34602MB
[2025-01-19 16:21:41 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][300/312]	eta 0:00:08 lr 0.000650	time 0.8136 (0.7481)	model_time 0.8135 (0.7436)	loss 2.7410 (2.8663)	grad_norm 2.8690 (1.9636/0.8287)	mem 34604MB
[2025-01-19 16:21:44 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][300/312]	eta 0:00:09 lr 0.000650	time 0.7158 (0.7516)	model_time 0.7157 (0.7470)	loss 2.4023 (2.8569)	grad_norm 1.1543 (2.0773/0.8339)	mem 34602MB
[2025-01-19 16:21:49 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][310/312]	eta 0:00:01 lr 0.000650	time 0.8084 (0.7483)	model_time 0.8083 (0.7439)	loss 3.1277 (2.8764)	grad_norm 2.2290 (1.9832/0.8427)	mem 34604MB
[2025-01-19 16:21:49 internimage_b_1k_224] (main.py 519): INFO EPOCH 222 training takes 0:03:53
[2025-01-19 16:21:49 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_222.pth saving......
[2025-01-19 16:21:51 internimage_b_1k_224] (main.py 510): INFO Train: [222/300][310/312]	eta 0:00:01 lr 0.000650	time 0.7117 (0.7513)	model_time 0.7116 (0.7467)	loss 3.0378 (2.8524)	grad_norm 1.1967 (2.0539/0.8390)	mem 34602MB
[2025-01-19 16:21:52 internimage_b_1k_224] (main.py 519): INFO EPOCH 222 training takes 0:03:54
[2025-01-19 16:21:52 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_222.pth saving......
[2025-01-19 16:21:53 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_222.pth saved !!!
[2025-01-19 16:21:55 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_222.pth saved !!!
[2025-01-19 16:22:08 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.260 (15.260)	Loss 0.7227 (0.7227)	Acc@1 85.376 (85.376)	Acc@5 97.705 (97.705)	Mem 34604MB
[2025-01-19 16:22:12 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.678 (16.678)	Loss 0.7275 (0.7275)	Acc@1 85.522 (85.522)	Acc@5 97.803 (97.803)	Mem 34602MB
[2025-01-19 16:22:14 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.935)	Loss 0.9411 (0.8156)	Acc@1 79.688 (83.467)	Acc@5 95.605 (96.604)	Mem 34604MB
[2025-01-19 16:22:14 internimage_b_1k_224] (main.py 575): INFO [Epoch:222] * Acc@1 83.303 Acc@5 96.621
[2025-01-19 16:22:14 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.3%
[2025-01-19 16:22:14 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.39%
[2025-01-19 16:22:18 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.093)	Loss 0.9403 (0.8162)	Acc@1 79.443 (83.474)	Acc@5 95.654 (96.702)	Mem 34602MB
[2025-01-19 16:22:19 internimage_b_1k_224] (main.py 575): INFO [Epoch:222] * Acc@1 83.371 Acc@5 96.723
[2025-01-19 16:22:19 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.4%
[2025-01-19 16:22:19 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 16:22:22 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 16:22:22 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.37%
[2025-01-19 16:22:31 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.529 (16.529)	Loss 0.7071 (0.7071)	Acc@1 86.035 (86.035)	Acc@5 98.193 (98.193)	Mem 34604MB
[2025-01-19 16:22:39 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.004 (17.004)	Loss 0.7165 (0.7165)	Acc@1 85.718 (85.718)	Acc@5 98.145 (98.145)	Mem 34602MB
[2025-01-19 16:22:40 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.368)	Loss 0.9381 (0.8104)	Acc@1 79.883 (83.734)	Acc@5 95.605 (96.764)	Mem 34604MB
[2025-01-19 16:22:41 internimage_b_1k_224] (main.py 575): INFO [Epoch:222] * Acc@1 83.549 Acc@5 96.809
[2025-01-19 16:22:41 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.5%
[2025-01-19 16:22:41 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:22:43 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.930)	Loss 0.9405 (0.8127)	Acc@1 79.663 (83.665)	Acc@5 95.557 (96.760)	Mem 34602MB
[2025-01-19 16:22:43 internimage_b_1k_224] (main.py 575): INFO [Epoch:222] * Acc@1 83.497 Acc@5 96.809
[2025-01-19 16:22:43 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.5%
[2025-01-19 16:22:43 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:22:45 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:22:45 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.55%
[2025-01-19 16:22:47 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][0/312]	eta 0:11:00 lr 0.000650	time 2.1176 (2.1176)	model_time 0.7346 (0.7346)	loss 3.1057 (3.1057)	grad_norm 3.3780 (3.3780/0.0000)	mem 34604MB
[2025-01-19 16:22:48 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:22:48 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.50%
[2025-01-19 16:22:50 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][0/312]	eta 0:10:46 lr 0.000650	time 2.0705 (2.0705)	model_time 0.7362 (0.7362)	loss 2.6620 (2.6620)	grad_norm 1.0771 (1.0771/0.0000)	mem 34602MB
[2025-01-19 16:22:54 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][10/312]	eta 0:04:26 lr 0.000649	time 0.8161 (0.8821)	model_time 0.8159 (0.7561)	loss 3.4916 (2.8514)	grad_norm 1.0012 (2.0302/0.8191)	mem 34604MB
[2025-01-19 16:22:57 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][10/312]	eta 0:04:20 lr 0.000649	time 0.7320 (0.8619)	model_time 0.7315 (0.7402)	loss 2.4191 (2.6747)	grad_norm 1.4083 (1.4707/0.3050)	mem 34602MB
[2025-01-19 16:23:02 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][20/312]	eta 0:03:58 lr 0.000649	time 0.7268 (0.8166)	model_time 0.7266 (0.7504)	loss 3.0170 (3.0154)	grad_norm 2.3633 (2.1714/0.8947)	mem 34604MB
[2025-01-19 16:23:05 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][20/312]	eta 0:03:59 lr 0.000649	time 0.8435 (0.8189)	model_time 0.8431 (0.7550)	loss 3.0483 (2.7873)	grad_norm 2.7059 (1.8340/0.7786)	mem 34602MB
[2025-01-19 16:23:09 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][30/312]	eta 0:03:42 lr 0.000648	time 0.7254 (0.7896)	model_time 0.7252 (0.7446)	loss 2.7175 (2.8962)	grad_norm 1.8317 (2.1739/0.8885)	mem 34604MB
[2025-01-19 16:23:12 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][30/312]	eta 0:03:43 lr 0.000648	time 0.7593 (0.7911)	model_time 0.7591 (0.7477)	loss 2.6683 (2.7591)	grad_norm 2.7202 (2.3952/1.3428)	mem 34602MB
[2025-01-19 16:23:17 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][40/312]	eta 0:03:30 lr 0.000648	time 0.7139 (0.7754)	model_time 0.7134 (0.7414)	loss 3.1815 (2.9074)	grad_norm 1.7433 (2.1095/0.8486)	mem 34604MB
[2025-01-19 16:23:20 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][40/312]	eta 0:03:32 lr 0.000648	time 0.7206 (0.7801)	model_time 0.7202 (0.7473)	loss 3.0805 (2.8059)	grad_norm 2.2217 (2.3628/1.2172)	mem 34602MB
[2025-01-19 16:23:24 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][50/312]	eta 0:03:20 lr 0.000647	time 0.7170 (0.7665)	model_time 0.7169 (0.7391)	loss 3.2306 (2.8987)	grad_norm 1.9590 (2.0497/0.8066)	mem 34604MB
[2025-01-19 16:23:27 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][50/312]	eta 0:03:22 lr 0.000647	time 0.8065 (0.7727)	model_time 0.8063 (0.7462)	loss 2.7360 (2.7740)	grad_norm 1.4610 (2.3205/1.1786)	mem 34602MB
[2025-01-19 16:23:31 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][60/312]	eta 0:03:11 lr 0.000647	time 0.7193 (0.7602)	model_time 0.7188 (0.7372)	loss 2.7527 (2.8823)	grad_norm 3.0484 (2.1977/0.9230)	mem 34604MB
[2025-01-19 16:23:34 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][60/312]	eta 0:03:13 lr 0.000647	time 0.7232 (0.7661)	model_time 0.7230 (0.7439)	loss 2.9600 (2.7758)	grad_norm 1.4783 (2.2245/1.1285)	mem 34602MB
[2025-01-19 16:23:38 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][70/312]	eta 0:03:02 lr 0.000646	time 0.7358 (0.7558)	model_time 0.7354 (0.7360)	loss 2.1330 (2.8884)	grad_norm 1.1934 (2.1200/0.9017)	mem 34604MB
[2025-01-19 16:23:42 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][70/312]	eta 0:03:04 lr 0.000646	time 0.7234 (0.7634)	model_time 0.7232 (0.7443)	loss 2.2907 (2.7737)	grad_norm 3.1610 (2.2452/1.1315)	mem 34602MB
[2025-01-19 16:23:46 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][80/312]	eta 0:02:54 lr 0.000646	time 0.7254 (0.7522)	model_time 0.7249 (0.7348)	loss 2.1722 (2.8908)	grad_norm 1.3088 (2.0401/0.8835)	mem 34604MB
[2025-01-19 16:23:49 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][80/312]	eta 0:02:56 lr 0.000646	time 0.7461 (0.7604)	model_time 0.7460 (0.7436)	loss 2.5633 (2.7658)	grad_norm 1.4835 (2.2996/1.1648)	mem 34602MB
[2025-01-19 16:23:53 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][90/312]	eta 0:02:46 lr 0.000645	time 0.7135 (0.7517)	model_time 0.7134 (0.7361)	loss 3.2694 (2.8770)	grad_norm 2.1410 (2.0525/0.8564)	mem 34604MB
[2025-01-19 16:23:57 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][90/312]	eta 0:02:48 lr 0.000645	time 0.7196 (0.7608)	model_time 0.7194 (0.7458)	loss 3.4901 (2.7859)	grad_norm 2.5046 (2.2616/1.1198)	mem 34602MB
[2025-01-19 16:24:01 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][100/312]	eta 0:02:40 lr 0.000645	time 0.7187 (0.7550)	model_time 0.7183 (0.7410)	loss 2.4284 (2.8529)	grad_norm 1.6626 (2.0337/0.8285)	mem 34604MB
[2025-01-19 16:24:04 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][100/312]	eta 0:02:41 lr 0.000645	time 0.8021 (0.7611)	model_time 0.8016 (0.7475)	loss 3.0790 (2.7804)	grad_norm 1.8261 (2.2350/1.0758)	mem 34602MB
[2025-01-19 16:24:08 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][110/312]	eta 0:02:32 lr 0.000644	time 0.7208 (0.7539)	model_time 0.7206 (0.7411)	loss 1.9133 (2.8438)	grad_norm 0.9957 (2.0198/0.8311)	mem 34604MB
[2025-01-19 16:24:12 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][110/312]	eta 0:02:33 lr 0.000644	time 0.7226 (0.7584)	model_time 0.7225 (0.7460)	loss 2.3842 (2.8024)	grad_norm 1.9493 (2.2496/1.0735)	mem 34602MB
[2025-01-19 16:24:16 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][120/312]	eta 0:02:24 lr 0.000644	time 0.8067 (0.7545)	model_time 0.8063 (0.7428)	loss 2.7514 (2.8426)	grad_norm 3.1762 (1.9968/0.8173)	mem 34604MB
[2025-01-19 16:24:19 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][120/312]	eta 0:02:25 lr 0.000644	time 0.7187 (0.7572)	model_time 0.7185 (0.7458)	loss 2.7213 (2.8056)	grad_norm 1.9982 (2.2430/1.0522)	mem 34602MB
[2025-01-19 16:24:24 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][130/312]	eta 0:02:17 lr 0.000643	time 0.7237 (0.7543)	model_time 0.7236 (0.7434)	loss 2.9547 (2.8524)	grad_norm 2.1206 (2.0082/0.8118)	mem 34604MB
[2025-01-19 16:24:27 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][130/312]	eta 0:02:17 lr 0.000643	time 0.7244 (0.7559)	model_time 0.7242 (0.7453)	loss 3.6454 (2.8192)	grad_norm 2.9913 (2.2208/1.0326)	mem 34602MB
[2025-01-19 16:24:31 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][140/312]	eta 0:02:09 lr 0.000643	time 0.7149 (0.7538)	model_time 0.7147 (0.7436)	loss 3.2567 (2.8554)	grad_norm 1.4715 (2.0310/0.8047)	mem 34604MB
[2025-01-19 16:24:34 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][140/312]	eta 0:02:09 lr 0.000643	time 0.8142 (0.7558)	model_time 0.8138 (0.7460)	loss 3.1320 (2.8290)	grad_norm 1.2595 (2.1729/1.0140)	mem 34602MB
[2025-01-19 16:24:38 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][150/312]	eta 0:02:01 lr 0.000642	time 0.7241 (0.7522)	model_time 0.7237 (0.7427)	loss 2.3872 (2.8435)	grad_norm 1.4771 (2.0200/0.7952)	mem 34604MB
[2025-01-19 16:24:42 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][150/312]	eta 0:02:02 lr 0.000642	time 0.7263 (0.7545)	model_time 0.7258 (0.7453)	loss 2.7407 (2.8232)	grad_norm 2.1745 (2.1258/1.0004)	mem 34602MB
[2025-01-19 16:24:46 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][160/312]	eta 0:01:54 lr 0.000642	time 0.7262 (0.7515)	model_time 0.7261 (0.7426)	loss 2.9542 (2.8228)	grad_norm 1.3016 (1.9840/0.7877)	mem 34604MB
[2025-01-19 16:24:49 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][160/312]	eta 0:01:54 lr 0.000642	time 0.7212 (0.7552)	model_time 0.7210 (0.7465)	loss 3.3922 (2.8402)	grad_norm 2.3276 (2.1491/0.9905)	mem 34602MB
[2025-01-19 16:24:53 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][170/312]	eta 0:01:46 lr 0.000641	time 0.7391 (0.7502)	model_time 0.7390 (0.7417)	loss 3.3076 (2.8245)	grad_norm 0.9447 (1.9583/0.7762)	mem 34604MB
[2025-01-19 16:24:57 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][170/312]	eta 0:01:47 lr 0.000641	time 0.8059 (0.7547)	model_time 0.8055 (0.7465)	loss 2.6242 (2.8499)	grad_norm 1.7893 (2.1343/0.9742)	mem 34602MB
[2025-01-19 16:25:00 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][180/312]	eta 0:01:38 lr 0.000641	time 0.7203 (0.7487)	model_time 0.7202 (0.7407)	loss 2.9057 (2.8235)	grad_norm 3.7516 (1.9813/0.7809)	mem 34604MB
[2025-01-19 16:25:04 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][180/312]	eta 0:01:39 lr 0.000641	time 0.7220 (0.7538)	model_time 0.7218 (0.7461)	loss 1.9150 (2.8518)	grad_norm 1.1154 (2.1219/0.9613)	mem 34602MB
[2025-01-19 16:25:08 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][190/312]	eta 0:01:31 lr 0.000640	time 0.7228 (0.7475)	model_time 0.7224 (0.7399)	loss 2.1704 (2.8177)	grad_norm 2.4395 (1.9913/0.7920)	mem 34604MB
[2025-01-19 16:25:12 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][190/312]	eta 0:01:31 lr 0.000640	time 0.7187 (0.7538)	model_time 0.7183 (0.7464)	loss 3.0180 (2.8683)	grad_norm 1.4632 (2.1379/0.9643)	mem 34602MB
[2025-01-19 16:25:15 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][200/312]	eta 0:01:23 lr 0.000640	time 0.7224 (0.7464)	model_time 0.7219 (0.7391)	loss 2.7453 (2.8145)	grad_norm 2.7844 (2.0071/0.7830)	mem 34604MB
[2025-01-19 16:25:19 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][200/312]	eta 0:01:24 lr 0.000640	time 0.7292 (0.7531)	model_time 0.7288 (0.7461)	loss 3.1868 (2.8619)	grad_norm 3.9823 (2.1279/0.9627)	mem 34602MB
[2025-01-19 16:25:22 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][210/312]	eta 0:01:16 lr 0.000640	time 0.7138 (0.7462)	model_time 0.7136 (0.7392)	loss 2.8069 (2.8204)	grad_norm 2.2768 (2.0124/0.7799)	mem 34604MB
[2025-01-19 16:25:27 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][210/312]	eta 0:01:16 lr 0.000640	time 0.7168 (0.7534)	model_time 0.7166 (0.7467)	loss 3.0696 (2.8484)	grad_norm 1.8289 (2.1470/0.9793)	mem 34602MB
[2025-01-19 16:25:30 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][220/312]	eta 0:01:08 lr 0.000639	time 0.7182 (0.7471)	model_time 0.7181 (0.7405)	loss 3.1572 (2.8236)	grad_norm 5.5665 (2.0604/0.8217)	mem 34604MB
[2025-01-19 16:25:34 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][220/312]	eta 0:01:09 lr 0.000639	time 0.8072 (0.7544)	model_time 0.8068 (0.7480)	loss 2.2068 (2.8493)	grad_norm 1.5625 (2.1395/0.9773)	mem 34602MB
[2025-01-19 16:25:37 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][230/312]	eta 0:01:01 lr 0.000639	time 0.7175 (0.7469)	model_time 0.7170 (0.7405)	loss 2.5294 (2.8150)	grad_norm 1.7598 (2.0521/0.8137)	mem 34604MB
[2025-01-19 16:25:42 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][230/312]	eta 0:01:01 lr 0.000639	time 0.7361 (0.7537)	model_time 0.7359 (0.7475)	loss 2.9229 (2.8565)	grad_norm 2.0969 (2.1224/0.9640)	mem 34602MB
[2025-01-19 16:25:45 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][240/312]	eta 0:00:53 lr 0.000638	time 0.8084 (0.7475)	model_time 0.8079 (0.7414)	loss 3.2402 (2.8264)	grad_norm 2.1070 (2.1036/0.8931)	mem 34604MB
[2025-01-19 16:25:49 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][240/312]	eta 0:00:54 lr 0.000638	time 0.7235 (0.7533)	model_time 0.7234 (0.7474)	loss 3.0975 (2.8504)	grad_norm 3.4077 (2.1492/0.9720)	mem 34602MB
[2025-01-19 16:25:53 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][250/312]	eta 0:00:46 lr 0.000638	time 0.7205 (0.7482)	model_time 0.7200 (0.7423)	loss 2.6031 (2.8368)	grad_norm 4.0455 (2.1290/0.9090)	mem 34604MB
[2025-01-19 16:25:57 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][250/312]	eta 0:00:46 lr 0.000638	time 0.7204 (0.7530)	model_time 0.7203 (0.7473)	loss 1.6743 (2.8469)	grad_norm 2.3102 (2.1576/0.9629)	mem 34602MB
[2025-01-19 16:26:00 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][260/312]	eta 0:00:38 lr 0.000637	time 0.7197 (0.7485)	model_time 0.7196 (0.7428)	loss 2.6708 (2.8439)	grad_norm 1.7344 (2.1136/0.9006)	mem 34604MB
[2025-01-19 16:26:04 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][260/312]	eta 0:00:39 lr 0.000637	time 0.8649 (0.7531)	model_time 0.8648 (0.7476)	loss 2.3176 (2.8489)	grad_norm 1.3441 (2.1435/0.9653)	mem 34602MB
[2025-01-19 16:26:08 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][270/312]	eta 0:00:31 lr 0.000637	time 0.7341 (0.7481)	model_time 0.7339 (0.7426)	loss 2.5232 (2.8486)	grad_norm 1.8226 (2.0942/0.8969)	mem 34604MB
[2025-01-19 16:26:12 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][270/312]	eta 0:00:31 lr 0.000637	time 0.7270 (0.7525)	model_time 0.7268 (0.7473)	loss 3.1072 (2.8575)	grad_norm 2.0059 (2.1320/0.9558)	mem 34602MB
[2025-01-19 16:26:15 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][280/312]	eta 0:00:23 lr 0.000636	time 0.7306 (0.7480)	model_time 0.7300 (0.7427)	loss 2.2423 (2.8508)	grad_norm 3.8997 (2.1162/0.9084)	mem 34604MB
[2025-01-19 16:26:19 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][280/312]	eta 0:00:24 lr 0.000636	time 0.7171 (0.7525)	model_time 0.7166 (0.7474)	loss 3.1886 (2.8511)	grad_norm 2.0310 (2.1301/0.9477)	mem 34602MB
[2025-01-19 16:26:22 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][290/312]	eta 0:00:16 lr 0.000636	time 0.7225 (0.7472)	model_time 0.7224 (0.7421)	loss 2.8503 (2.8527)	grad_norm 2.0919 (2.1282/0.9091)	mem 34604MB
[2025-01-19 16:26:26 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][290/312]	eta 0:00:16 lr 0.000636	time 0.7934 (0.7522)	model_time 0.7930 (0.7472)	loss 3.1627 (2.8525)	grad_norm 1.0765 (2.1171/0.9431)	mem 34602MB
[2025-01-19 16:26:29 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][300/312]	eta 0:00:08 lr 0.000635	time 0.7212 (0.7463)	model_time 0.7211 (0.7413)	loss 2.0935 (2.8512)	grad_norm 2.5500 (2.1296/0.9006)	mem 34604MB
[2025-01-19 16:26:34 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][300/312]	eta 0:00:09 lr 0.000635	time 0.7142 (0.7514)	model_time 0.7141 (0.7466)	loss 2.2506 (2.8345)	grad_norm 1.4931 (2.1052/0.9344)	mem 34602MB
[2025-01-19 16:26:37 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][310/312]	eta 0:00:01 lr 0.000635	time 0.7183 (0.7452)	model_time 0.7182 (0.7404)	loss 3.1480 (2.8500)	grad_norm 1.3386 (2.1441/0.9170)	mem 34604MB
[2025-01-19 16:26:37 internimage_b_1k_224] (main.py 519): INFO EPOCH 223 training takes 0:03:52
[2025-01-19 16:26:37 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_223.pth saving......
[2025-01-19 16:26:41 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_223.pth saved !!!
[2025-01-19 16:26:41 internimage_b_1k_224] (main.py 510): INFO Train: [223/300][310/312]	eta 0:00:01 lr 0.000635	time 0.7152 (0.7503)	model_time 0.7151 (0.7456)	loss 3.1508 (2.8357)	grad_norm 1.5103 (2.1255/0.9356)	mem 34602MB
[2025-01-19 16:26:42 internimage_b_1k_224] (main.py 519): INFO EPOCH 223 training takes 0:03:54
[2025-01-19 16:26:42 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_223.pth saving......
[2025-01-19 16:26:45 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_223.pth saved !!!
[2025-01-19 16:26:54 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 13.205 (13.205)	Loss 0.7108 (0.7108)	Acc@1 85.669 (85.669)	Acc@5 97.656 (97.656)	Mem 34604MB
[2025-01-19 16:27:00 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.783)	Loss 0.9542 (0.8132)	Acc@1 79.102 (83.501)	Acc@5 95.703 (96.660)	Mem 34604MB
[2025-01-19 16:27:00 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.426 (15.426)	Loss 0.7269 (0.7269)	Acc@1 85.693 (85.693)	Acc@5 97.632 (97.632)	Mem 34602MB
[2025-01-19 16:27:01 internimage_b_1k_224] (main.py 575): INFO [Epoch:223] * Acc@1 83.349 Acc@5 96.653
[2025-01-19 16:27:01 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.3%
[2025-01-19 16:27:01 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.39%
[2025-01-19 16:27:07 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.040)	Loss 0.9238 (0.8111)	Acc@1 79.785 (83.563)	Acc@5 95.752 (96.724)	Mem 34602MB
[2025-01-19 16:27:08 internimage_b_1k_224] (main.py 575): INFO [Epoch:223] * Acc@1 83.407 Acc@5 96.739
[2025-01-19 16:27:08 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.4%
[2025-01-19 16:27:08 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 16:27:11 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 16:27:11 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.41%
[2025-01-19 16:27:17 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.751 (16.751)	Loss 0.7076 (0.7076)	Acc@1 86.035 (86.035)	Acc@5 98.193 (98.193)	Mem 34604MB
[2025-01-19 16:27:26 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.571 (15.571)	Loss 0.7171 (0.7171)	Acc@1 85.718 (85.718)	Acc@5 98.145 (98.145)	Mem 34602MB
[2025-01-19 16:27:26 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.344)	Loss 0.9378 (0.8105)	Acc@1 79.980 (83.740)	Acc@5 95.605 (96.768)	Mem 34604MB
[2025-01-19 16:27:27 internimage_b_1k_224] (main.py 575): INFO [Epoch:223] * Acc@1 83.555 Acc@5 96.813
[2025-01-19 16:27:27 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.6%
[2025-01-19 16:27:27 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:27:31 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.790)	Loss 0.9402 (0.8126)	Acc@1 79.688 (83.696)	Acc@5 95.557 (96.766)	Mem 34602MB
[2025-01-19 16:27:31 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:27:31 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.56%
[2025-01-19 16:27:31 internimage_b_1k_224] (main.py 575): INFO [Epoch:223] * Acc@1 83.525 Acc@5 96.817
[2025-01-19 16:27:31 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.5%
[2025-01-19 16:27:31 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:27:33 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][0/312]	eta 0:11:34 lr 0.000635	time 2.2251 (2.2251)	model_time 0.7451 (0.7451)	loss 3.4811 (3.4811)	grad_norm 1.8951 (1.8951/0.0000)	mem 34604MB
[2025-01-19 16:27:35 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:27:35 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.53%
[2025-01-19 16:27:37 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][0/312]	eta 0:11:53 lr 0.000635	time 2.2873 (2.2873)	model_time 0.7523 (0.7523)	loss 3.0921 (3.0921)	grad_norm 1.3993 (1.3993/0.0000)	mem 34602MB
[2025-01-19 16:27:40 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][10/312]	eta 0:04:21 lr 0.000634	time 0.7253 (0.8651)	model_time 0.7251 (0.7303)	loss 3.0761 (2.9918)	grad_norm 1.1475 (1.7207/0.5276)	mem 34604MB
[2025-01-19 16:27:44 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][10/312]	eta 0:04:24 lr 0.000634	time 0.7257 (0.8754)	model_time 0.7253 (0.7355)	loss 3.3874 (2.9080)	grad_norm 3.4720 (1.7209/0.6683)	mem 34602MB
[2025-01-19 16:27:48 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][20/312]	eta 0:03:56 lr 0.000634	time 0.7373 (0.8104)	model_time 0.7369 (0.7397)	loss 3.0497 (2.8970)	grad_norm 4.4781 (1.9376/0.8544)	mem 34604MB
[2025-01-19 16:27:52 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][20/312]	eta 0:04:01 lr 0.000634	time 0.7202 (0.8263)	model_time 0.7201 (0.7530)	loss 3.0884 (2.9178)	grad_norm 1.9472 (2.1076/0.9106)	mem 34602MB
[2025-01-19 16:27:56 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][30/312]	eta 0:03:45 lr 0.000633	time 0.7972 (0.8006)	model_time 0.7970 (0.7525)	loss 3.0141 (2.9041)	grad_norm 2.2293 (2.0723/0.8594)	mem 34604MB
[2025-01-19 16:28:00 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][30/312]	eta 0:03:47 lr 0.000633	time 0.8011 (0.8053)	model_time 0.8006 (0.7554)	loss 2.2916 (2.8816)	grad_norm 1.4614 (2.3126/1.0803)	mem 34602MB
[2025-01-19 16:28:03 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][40/312]	eta 0:03:34 lr 0.000633	time 0.7458 (0.7879)	model_time 0.7456 (0.7515)	loss 3.5473 (2.8797)	grad_norm 1.3025 (2.1309/0.9481)	mem 34604MB
[2025-01-19 16:28:07 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][40/312]	eta 0:03:34 lr 0.000633	time 0.7171 (0.7903)	model_time 0.7167 (0.7525)	loss 3.2334 (2.9084)	grad_norm 3.7323 (2.3659/1.1375)	mem 34602MB
[2025-01-19 16:28:11 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][50/312]	eta 0:03:25 lr 0.000632	time 0.8088 (0.7844)	model_time 0.8083 (0.7550)	loss 2.7045 (2.8488)	grad_norm 0.9051 (2.0879/0.8952)	mem 34604MB
[2025-01-19 16:28:15 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][50/312]	eta 0:03:24 lr 0.000632	time 0.7434 (0.7817)	model_time 0.7430 (0.7512)	loss 3.2838 (2.9390)	grad_norm 2.0775 (2.2480/1.1230)	mem 34602MB
[2025-01-19 16:28:18 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][60/312]	eta 0:03:16 lr 0.000632	time 0.7197 (0.7811)	model_time 0.7195 (0.7565)	loss 3.4791 (2.8508)	grad_norm 2.1502 (2.0638/0.8426)	mem 34604MB
[2025-01-19 16:28:22 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][60/312]	eta 0:03:15 lr 0.000632	time 0.7280 (0.7755)	model_time 0.7279 (0.7500)	loss 2.8472 (2.9034)	grad_norm 1.4241 (2.1226/1.0821)	mem 34602MB
[2025-01-19 16:28:26 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][70/312]	eta 0:03:07 lr 0.000631	time 0.7170 (0.7763)	model_time 0.7168 (0.7551)	loss 1.7991 (2.8429)	grad_norm 1.6541 (1.9989/0.8070)	mem 34604MB
[2025-01-19 16:28:29 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][70/312]	eta 0:03:06 lr 0.000631	time 0.7162 (0.7713)	model_time 0.7157 (0.7493)	loss 1.9456 (2.8958)	grad_norm 2.1729 (2.0551/1.0379)	mem 34602MB
[2025-01-19 16:28:33 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][80/312]	eta 0:02:59 lr 0.000631	time 0.7161 (0.7717)	model_time 0.7157 (0.7531)	loss 3.1223 (2.8586)	grad_norm 2.1210 (2.0701/0.8205)	mem 34604MB
[2025-01-19 16:28:37 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][80/312]	eta 0:02:57 lr 0.000631	time 0.7323 (0.7670)	model_time 0.7322 (0.7477)	loss 2.6791 (2.8710)	grad_norm 3.1817 (2.1392/1.0689)	mem 34602MB
[2025-01-19 16:28:41 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][90/312]	eta 0:02:50 lr 0.000630	time 0.7269 (0.7685)	model_time 0.7266 (0.7519)	loss 3.0764 (2.8708)	grad_norm 1.1608 (2.0178/0.8055)	mem 34604MB
[2025-01-19 16:28:44 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][90/312]	eta 0:02:49 lr 0.000630	time 0.7190 (0.7644)	model_time 0.7189 (0.7471)	loss 2.2188 (2.8578)	grad_norm 3.1863 (2.1783/1.0763)	mem 34602MB
[2025-01-19 16:28:48 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][100/312]	eta 0:02:42 lr 0.000630	time 0.7426 (0.7652)	model_time 0.7421 (0.7503)	loss 3.1529 (2.8572)	grad_norm 1.1688 (1.9976/0.7809)	mem 34604MB
[2025-01-19 16:28:52 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][100/312]	eta 0:02:41 lr 0.000630	time 0.7405 (0.7620)	model_time 0.7401 (0.7465)	loss 1.8933 (2.8342)	grad_norm 3.0906 (2.1679/1.0456)	mem 34602MB
[2025-01-19 16:28:55 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][110/312]	eta 0:02:33 lr 0.000629	time 0.7385 (0.7618)	model_time 0.7380 (0.7481)	loss 2.1574 (2.8461)	grad_norm 2.6425 (1.9834/0.7703)	mem 34604MB
[2025-01-19 16:28:59 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][110/312]	eta 0:02:33 lr 0.000629	time 0.7206 (0.7605)	model_time 0.7201 (0.7463)	loss 3.0726 (2.8331)	grad_norm 1.7834 (2.1719/1.0268)	mem 34602MB
[2025-01-19 16:29:03 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][120/312]	eta 0:02:25 lr 0.000629	time 0.7170 (0.7600)	model_time 0.7166 (0.7474)	loss 2.3067 (2.8373)	grad_norm 4.4627 (2.0754/0.8853)	mem 34604MB
[2025-01-19 16:29:06 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][120/312]	eta 0:02:25 lr 0.000629	time 0.7198 (0.7587)	model_time 0.7197 (0.7456)	loss 2.9012 (2.8048)	grad_norm 2.1298 (2.1882/1.0469)	mem 34602MB
[2025-01-19 16:29:10 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][130/312]	eta 0:02:17 lr 0.000629	time 0.7449 (0.7574)	model_time 0.7448 (0.7457)	loss 2.8152 (2.8443)	grad_norm 2.4293 (2.1034/0.9165)	mem 34604MB
[2025-01-19 16:29:14 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][130/312]	eta 0:02:17 lr 0.000629	time 0.7260 (0.7569)	model_time 0.7258 (0.7449)	loss 3.1112 (2.8145)	grad_norm 3.8835 (2.2261/1.0807)	mem 34602MB
[2025-01-19 16:29:17 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][140/312]	eta 0:02:10 lr 0.000628	time 0.7206 (0.7565)	model_time 0.7200 (0.7457)	loss 3.3478 (2.8359)	grad_norm 1.2821 (2.0846/0.8999)	mem 34604MB
[2025-01-19 16:29:22 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][140/312]	eta 0:02:10 lr 0.000628	time 0.7632 (0.7579)	model_time 0.7630 (0.7466)	loss 3.1953 (2.8049)	grad_norm 1.4168 (2.1952/1.0538)	mem 34602MB
[2025-01-19 16:29:25 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][150/312]	eta 0:02:02 lr 0.000628	time 0.7214 (0.7572)	model_time 0.7212 (0.7471)	loss 2.0864 (2.8268)	grad_norm 1.4961 (2.1045/0.9006)	mem 34604MB
[2025-01-19 16:29:29 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][150/312]	eta 0:02:02 lr 0.000628	time 0.8040 (0.7579)	model_time 0.8039 (0.7473)	loss 2.1682 (2.7904)	grad_norm 1.9475 (2.1875/1.0249)	mem 34602MB
[2025-01-19 16:29:33 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][160/312]	eta 0:01:54 lr 0.000627	time 0.7205 (0.7566)	model_time 0.7204 (0.7470)	loss 3.3475 (2.8365)	grad_norm 1.6555 (2.0781/0.8819)	mem 34604MB
[2025-01-19 16:29:36 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][160/312]	eta 0:01:54 lr 0.000627	time 0.7418 (0.7565)	model_time 0.7414 (0.7466)	loss 2.8387 (2.8020)	grad_norm 1.6517 (2.1558/1.0033)	mem 34602MB
[2025-01-19 16:29:40 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][170/312]	eta 0:01:47 lr 0.000627	time 0.8076 (0.7573)	model_time 0.8074 (0.7483)	loss 2.8746 (2.8528)	grad_norm 0.8896 (2.0436/0.8741)	mem 34604MB
[2025-01-19 16:29:44 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][170/312]	eta 0:01:47 lr 0.000627	time 0.7202 (0.7560)	model_time 0.7198 (0.7466)	loss 2.1161 (2.7953)	grad_norm 1.8547 (2.1506/0.9813)	mem 34602MB
[2025-01-19 16:29:48 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][180/312]	eta 0:01:40 lr 0.000626	time 0.7152 (0.7578)	model_time 0.7151 (0.7492)	loss 1.9645 (2.8570)	grad_norm 2.4006 (2.0744/0.8960)	mem 34604MB
[2025-01-19 16:29:51 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][180/312]	eta 0:01:39 lr 0.000626	time 0.7335 (0.7553)	model_time 0.7331 (0.7464)	loss 3.2019 (2.7980)	grad_norm 2.2303 (2.1799/0.9816)	mem 34602MB
[2025-01-19 16:29:55 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][190/312]	eta 0:01:32 lr 0.000626	time 0.7363 (0.7576)	model_time 0.7359 (0.7495)	loss 3.2104 (2.8447)	grad_norm 1.5218 (2.0736/0.8916)	mem 34604MB
[2025-01-19 16:29:59 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][190/312]	eta 0:01:32 lr 0.000626	time 0.7191 (0.7545)	model_time 0.7190 (0.7461)	loss 3.1843 (2.8139)	grad_norm 1.3921 (2.1699/0.9705)	mem 34602MB
[2025-01-19 16:30:03 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][200/312]	eta 0:01:24 lr 0.000625	time 0.7281 (0.7568)	model_time 0.7279 (0.7490)	loss 3.4232 (2.8292)	grad_norm 2.3178 (2.0786/0.8853)	mem 34604MB
[2025-01-19 16:30:06 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][200/312]	eta 0:01:24 lr 0.000625	time 0.7602 (0.7543)	model_time 0.7601 (0.7464)	loss 2.8790 (2.8143)	grad_norm 1.9412 (2.1601/0.9587)	mem 34602MB
[2025-01-19 16:30:10 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][210/312]	eta 0:01:17 lr 0.000625	time 0.7261 (0.7557)	model_time 0.7256 (0.7484)	loss 3.0647 (2.8358)	grad_norm 2.2654 (2.0831/0.8816)	mem 34604MB
[2025-01-19 16:30:14 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][210/312]	eta 0:01:16 lr 0.000625	time 0.7178 (0.7537)	model_time 0.7177 (0.7460)	loss 2.5536 (2.8005)	grad_norm 2.3460 (2.1546/0.9494)	mem 34602MB
[2025-01-19 16:30:17 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][220/312]	eta 0:01:09 lr 0.000624	time 0.7200 (0.7543)	model_time 0.7199 (0.7472)	loss 3.0331 (2.8335)	grad_norm 1.0345 (2.0544/0.8729)	mem 34604MB
[2025-01-19 16:30:21 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][220/312]	eta 0:01:09 lr 0.000624	time 0.8313 (0.7528)	model_time 0.8312 (0.7455)	loss 1.7925 (2.7950)	grad_norm 2.8487 (2.1650/0.9345)	mem 34602MB
[2025-01-19 16:30:25 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][230/312]	eta 0:01:01 lr 0.000624	time 0.7267 (0.7533)	model_time 0.7265 (0.7466)	loss 2.8365 (2.8198)	grad_norm 1.6475 (2.0424/0.8674)	mem 34604MB
[2025-01-19 16:30:29 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][230/312]	eta 0:01:01 lr 0.000624	time 0.7309 (0.7526)	model_time 0.7307 (0.7456)	loss 2.3481 (2.7991)	grad_norm 3.3551 (2.1833/0.9631)	mem 34602MB
[2025-01-19 16:30:32 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][240/312]	eta 0:00:54 lr 0.000623	time 0.7190 (0.7527)	model_time 0.7188 (0.7462)	loss 2.9770 (2.8147)	grad_norm 3.1615 (2.0848/0.8879)	mem 34604MB
[2025-01-19 16:30:36 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][240/312]	eta 0:00:54 lr 0.000623	time 0.7185 (0.7520)	model_time 0.7181 (0.7453)	loss 2.1468 (2.7998)	grad_norm 1.6969 (2.1543/0.9582)	mem 34602MB
[2025-01-19 16:30:39 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][250/312]	eta 0:00:46 lr 0.000623	time 0.7125 (0.7516)	model_time 0.7119 (0.7454)	loss 2.9497 (2.8079)	grad_norm 2.1292 (2.1218/0.9209)	mem 34604MB
[2025-01-19 16:30:43 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][250/312]	eta 0:00:46 lr 0.000623	time 0.7168 (0.7517)	model_time 0.7164 (0.7453)	loss 2.1457 (2.7940)	grad_norm 2.0341 (2.1513/0.9468)	mem 34602MB
[2025-01-19 16:30:47 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][260/312]	eta 0:00:39 lr 0.000622	time 0.8205 (0.7513)	model_time 0.8203 (0.7453)	loss 2.6826 (2.7934)	grad_norm 1.4256 (2.1286/0.9221)	mem 34604MB
[2025-01-19 16:30:51 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][260/312]	eta 0:00:39 lr 0.000622	time 0.7958 (0.7522)	model_time 0.7957 (0.7460)	loss 3.6095 (2.7999)	grad_norm 1.8987 (2.1436/0.9345)	mem 34602MB
[2025-01-19 16:30:54 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][270/312]	eta 0:00:31 lr 0.000622	time 0.8086 (0.7519)	model_time 0.8082 (0.7461)	loss 2.3570 (2.7895)	grad_norm 4.6852 (2.1405/0.9316)	mem 34604MB
[2025-01-19 16:30:58 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][270/312]	eta 0:00:31 lr 0.000622	time 0.7205 (0.7521)	model_time 0.7200 (0.7460)	loss 3.0969 (2.8088)	grad_norm 1.3175 (2.1326/0.9250)	mem 34602MB
[2025-01-19 16:31:02 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][280/312]	eta 0:00:24 lr 0.000621	time 0.7168 (0.7519)	model_time 0.7163 (0.7463)	loss 2.2652 (2.7934)	grad_norm 1.8872 (2.1318/0.9189)	mem 34604MB
[2025-01-19 16:31:06 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][280/312]	eta 0:00:24 lr 0.000621	time 0.7204 (0.7522)	model_time 0.7202 (0.7464)	loss 2.8067 (2.8078)	grad_norm 0.9272 (2.1198/0.9147)	mem 34602MB
[2025-01-19 16:31:10 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][290/312]	eta 0:00:16 lr 0.000621	time 0.8053 (0.7523)	model_time 0.8052 (0.7469)	loss 3.1468 (2.7928)	grad_norm 1.5372 (2.1183/0.9136)	mem 34604MB
[2025-01-19 16:31:14 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][290/312]	eta 0:00:16 lr 0.000621	time 0.7209 (0.7524)	model_time 0.7205 (0.7468)	loss 3.0415 (2.8039)	grad_norm 1.2387 (2.1417/0.9561)	mem 34602MB
[2025-01-19 16:31:17 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][300/312]	eta 0:00:09 lr 0.000620	time 0.7124 (0.7526)	model_time 0.7123 (0.7474)	loss 2.2178 (2.7941)	grad_norm 3.3802 (2.1263/0.9121)	mem 34604MB
[2025-01-19 16:31:21 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][300/312]	eta 0:00:09 lr 0.000620	time 0.7139 (0.7518)	model_time 0.7138 (0.7464)	loss 3.0332 (2.8091)	grad_norm 1.2773 (2.1343/0.9478)	mem 34602MB
[2025-01-19 16:31:25 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][310/312]	eta 0:00:01 lr 0.000620	time 0.7976 (0.7528)	model_time 0.7975 (0.7477)	loss 2.8185 (2.7957)	grad_norm 2.1595 (2.1262/0.9176)	mem 34604MB
[2025-01-19 16:31:26 internimage_b_1k_224] (main.py 519): INFO EPOCH 224 training takes 0:03:54
[2025-01-19 16:31:26 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_224.pth saving......
[2025-01-19 16:31:28 internimage_b_1k_224] (main.py 510): INFO Train: [224/300][310/312]	eta 0:00:01 lr 0.000620	time 0.7121 (0.7509)	model_time 0.7120 (0.7456)	loss 2.6066 (2.8130)	grad_norm 1.2389 (2.1235/0.9487)	mem 34602MB
[2025-01-19 16:31:29 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_224.pth saved !!!
[2025-01-19 16:31:29 internimage_b_1k_224] (main.py 519): INFO EPOCH 224 training takes 0:03:54
[2025-01-19 16:31:29 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_224.pth saving......
[2025-01-19 16:31:32 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_224.pth saved !!!
[2025-01-19 16:31:44 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.820 (14.820)	Loss 0.7116 (0.7116)	Acc@1 85.132 (85.132)	Acc@5 97.632 (97.632)	Mem 34604MB
[2025-01-19 16:31:49 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.589 (16.589)	Loss 0.7104 (0.7104)	Acc@1 85.229 (85.229)	Acc@5 97.900 (97.900)	Mem 34602MB
[2025-01-19 16:31:50 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.916)	Loss 0.9179 (0.8058)	Acc@1 79.590 (83.365)	Acc@5 95.703 (96.675)	Mem 34604MB
[2025-01-19 16:31:50 internimage_b_1k_224] (main.py 575): INFO [Epoch:224] * Acc@1 83.261 Acc@5 96.691
[2025-01-19 16:31:50 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.3%
[2025-01-19 16:31:50 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.39%
[2025-01-19 16:31:55 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.072)	Loss 0.9355 (0.8006)	Acc@1 79.272 (83.583)	Acc@5 95.776 (96.780)	Mem 34602MB
[2025-01-19 16:31:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:224] * Acc@1 83.445 Acc@5 96.803
[2025-01-19 16:31:55 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.4%
[2025-01-19 16:31:55 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 16:31:58 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 16:31:58 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.45%
[2025-01-19 16:32:07 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.150 (17.150)	Loss 0.7082 (0.7082)	Acc@1 86.011 (86.011)	Acc@5 98.193 (98.193)	Mem 34604MB
[2025-01-19 16:32:14 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.110 (16.110)	Loss 0.7175 (0.7175)	Acc@1 85.742 (85.742)	Acc@5 98.120 (98.120)	Mem 34602MB
[2025-01-19 16:32:16 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.377)	Loss 0.9375 (0.8107)	Acc@1 80.054 (83.778)	Acc@5 95.605 (96.775)	Mem 34604MB
[2025-01-19 16:32:17 internimage_b_1k_224] (main.py 575): INFO [Epoch:224] * Acc@1 83.593 Acc@5 96.815
[2025-01-19 16:32:17 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.6%
[2025-01-19 16:32:17 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:32:19 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.859)	Loss 0.9400 (0.8125)	Acc@1 79.639 (83.727)	Acc@5 95.605 (96.771)	Mem 34602MB
[2025-01-19 16:32:19 internimage_b_1k_224] (main.py 575): INFO [Epoch:224] * Acc@1 83.549 Acc@5 96.817
[2025-01-19 16:32:19 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.5%
[2025-01-19 16:32:19 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:32:21 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:32:21 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.59%
[2025-01-19 16:32:23 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][0/312]	eta 0:11:20 lr 0.000620	time 2.1824 (2.1824)	model_time 0.7311 (0.7311)	loss 2.2774 (2.2774)	grad_norm 1.6284 (1.6284/0.0000)	mem 34604MB
[2025-01-19 16:32:23 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:32:23 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.55%
[2025-01-19 16:32:25 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][0/312]	eta 0:11:36 lr 0.000620	time 2.2320 (2.2320)	model_time 0.7381 (0.7381)	loss 2.7681 (2.7681)	grad_norm 1.2148 (1.2148/0.0000)	mem 34602MB
[2025-01-19 16:32:30 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][10/312]	eta 0:04:23 lr 0.000619	time 0.7240 (0.8721)	model_time 0.7239 (0.7399)	loss 3.1917 (2.9255)	grad_norm 2.7944 (1.8696/0.5718)	mem 34604MB
[2025-01-19 16:32:33 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][10/312]	eta 0:04:32 lr 0.000619	time 0.7278 (0.9026)	model_time 0.7277 (0.7665)	loss 3.0102 (2.8200)	grad_norm 3.6696 (2.4631/0.9223)	mem 34602MB
[2025-01-19 16:32:38 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][20/312]	eta 0:03:55 lr 0.000619	time 0.7243 (0.8052)	model_time 0.7238 (0.7358)	loss 3.3884 (2.8313)	grad_norm 1.6590 (1.8598/0.5198)	mem 34604MB
[2025-01-19 16:32:40 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][20/312]	eta 0:04:01 lr 0.000619	time 0.7556 (0.8262)	model_time 0.7554 (0.7547)	loss 3.4293 (2.8013)	grad_norm 2.9179 (2.3309/0.8331)	mem 34602MB
[2025-01-19 16:32:45 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][30/312]	eta 0:03:40 lr 0.000619	time 0.7180 (0.7807)	model_time 0.7175 (0.7335)	loss 3.0488 (2.9210)	grad_norm 2.8144 (1.8527/0.5454)	mem 34604MB
[2025-01-19 16:32:48 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][30/312]	eta 0:03:47 lr 0.000619	time 0.7641 (0.8071)	model_time 0.7640 (0.7586)	loss 3.2984 (2.7558)	grad_norm 0.7925 (2.1080/0.8267)	mem 34602MB
[2025-01-19 16:32:52 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][40/312]	eta 0:03:28 lr 0.000618	time 0.7502 (0.7684)	model_time 0.7500 (0.7326)	loss 2.0919 (2.8969)	grad_norm 1.3198 (1.8714/0.5252)	mem 34604MB
[2025-01-19 16:32:56 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][40/312]	eta 0:03:35 lr 0.000618	time 0.7560 (0.7915)	model_time 0.7555 (0.7546)	loss 3.0172 (2.8244)	grad_norm 1.8521 (2.0539/0.8651)	mem 34602MB
[2025-01-19 16:33:00 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][50/312]	eta 0:03:19 lr 0.000618	time 0.7658 (0.7613)	model_time 0.7656 (0.7325)	loss 1.9357 (2.8704)	grad_norm 1.9117 (1.8101/0.5275)	mem 34604MB
[2025-01-19 16:33:03 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][50/312]	eta 0:03:25 lr 0.000618	time 0.7514 (0.7825)	model_time 0.7512 (0.7528)	loss 1.9767 (2.7920)	grad_norm 1.9185 (1.9959/0.8111)	mem 34602MB
[2025-01-19 16:33:07 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][60/312]	eta 0:03:10 lr 0.000617	time 0.7143 (0.7566)	model_time 0.7142 (0.7324)	loss 2.9312 (2.8414)	grad_norm 1.6320 (1.8277/0.6491)	mem 34604MB
[2025-01-19 16:33:10 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][60/312]	eta 0:03:15 lr 0.000617	time 0.7268 (0.7767)	model_time 0.7266 (0.7518)	loss 2.7728 (2.7705)	grad_norm 1.9232 (2.1313/0.9478)	mem 34602MB
[2025-01-19 16:33:14 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][70/312]	eta 0:03:02 lr 0.000617	time 0.8061 (0.7542)	model_time 0.8059 (0.7334)	loss 2.7171 (2.8395)	grad_norm 2.5696 (1.7972/0.6377)	mem 34604MB
[2025-01-19 16:33:18 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][70/312]	eta 0:03:08 lr 0.000617	time 0.8199 (0.7770)	model_time 0.8197 (0.7556)	loss 3.0601 (2.7983)	grad_norm 3.0638 (2.2750/1.1039)	mem 34602MB
[2025-01-19 16:33:22 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][80/312]	eta 0:02:55 lr 0.000616	time 0.8079 (0.7567)	model_time 0.8077 (0.7384)	loss 3.3087 (2.8339)	grad_norm 2.2032 (1.7968/0.6128)	mem 34604MB
[2025-01-19 16:33:26 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][80/312]	eta 0:02:59 lr 0.000616	time 0.7159 (0.7751)	model_time 0.7157 (0.7563)	loss 2.0397 (2.7797)	grad_norm 1.4390 (2.3005/1.0912)	mem 34602MB
[2025-01-19 16:33:30 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][90/312]	eta 0:02:47 lr 0.000616	time 0.8138 (0.7567)	model_time 0.8137 (0.7404)	loss 2.8587 (2.8163)	grad_norm 3.3752 (1.8369/0.6516)	mem 34604MB
[2025-01-19 16:33:33 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][90/312]	eta 0:02:51 lr 0.000616	time 0.7197 (0.7724)	model_time 0.7196 (0.7556)	loss 3.3939 (2.7983)	grad_norm 1.5439 (2.2188/1.0624)	mem 34602MB
[2025-01-19 16:33:37 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][100/312]	eta 0:02:40 lr 0.000615	time 0.8508 (0.7577)	model_time 0.8504 (0.7429)	loss 2.4948 (2.7910)	grad_norm 3.3196 (1.8442/0.6523)	mem 34604MB
[2025-01-19 16:33:41 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][100/312]	eta 0:02:43 lr 0.000615	time 0.7173 (0.7698)	model_time 0.7169 (0.7546)	loss 2.5134 (2.8170)	grad_norm 1.5911 (2.1996/1.0524)	mem 34602MB
[2025-01-19 16:33:45 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][110/312]	eta 0:02:33 lr 0.000615	time 0.7269 (0.7593)	model_time 0.7267 (0.7459)	loss 2.9776 (2.7849)	grad_norm 3.5266 (1.8667/0.6775)	mem 34604MB
[2025-01-19 16:33:48 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][110/312]	eta 0:02:34 lr 0.000615	time 0.7187 (0.7672)	model_time 0.7185 (0.7533)	loss 2.2627 (2.8062)	grad_norm 0.9731 (2.1882/1.0443)	mem 34602MB
[2025-01-19 16:33:53 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][120/312]	eta 0:02:25 lr 0.000614	time 0.7237 (0.7603)	model_time 0.7232 (0.7480)	loss 3.6191 (2.7966)	grad_norm 1.5242 (1.8489/0.6611)	mem 34604MB
[2025-01-19 16:33:56 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][120/312]	eta 0:02:26 lr 0.000614	time 0.7136 (0.7652)	model_time 0.7132 (0.7524)	loss 2.6063 (2.7991)	grad_norm 2.4821 (2.2020/1.0275)	mem 34602MB
[2025-01-19 16:34:00 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][130/312]	eta 0:02:18 lr 0.000614	time 0.7164 (0.7585)	model_time 0.7162 (0.7471)	loss 2.6768 (2.8056)	grad_norm 2.0332 (1.8398/0.6529)	mem 34604MB
[2025-01-19 16:34:03 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][130/312]	eta 0:02:19 lr 0.000614	time 0.7175 (0.7646)	model_time 0.7173 (0.7528)	loss 3.3188 (2.8106)	grad_norm 1.9831 (2.1476/1.0120)	mem 34602MB
[2025-01-19 16:34:08 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][140/312]	eta 0:02:10 lr 0.000613	time 0.7670 (0.7574)	model_time 0.7668 (0.7467)	loss 2.4952 (2.8183)	grad_norm 3.3275 (1.8654/0.6857)	mem 34604MB
[2025-01-19 16:34:11 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][140/312]	eta 0:02:11 lr 0.000613	time 0.7175 (0.7635)	model_time 0.7170 (0.7525)	loss 2.7450 (2.8242)	grad_norm 1.5485 (2.1396/0.9964)	mem 34602MB
[2025-01-19 16:34:15 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][150/312]	eta 0:02:02 lr 0.000613	time 0.7133 (0.7553)	model_time 0.7131 (0.7453)	loss 3.3344 (2.8290)	grad_norm 1.7710 (1.8793/0.6826)	mem 34604MB
[2025-01-19 16:34:18 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][150/312]	eta 0:02:03 lr 0.000613	time 0.7168 (0.7621)	model_time 0.7164 (0.7519)	loss 2.1556 (2.8358)	grad_norm 0.9081 (2.0704/0.9987)	mem 34602MB
[2025-01-19 16:34:22 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][160/312]	eta 0:01:54 lr 0.000612	time 0.7397 (0.7538)	model_time 0.7395 (0.7445)	loss 2.4307 (2.8316)	grad_norm 1.0294 (1.9604/0.7774)	mem 34604MB
[2025-01-19 16:34:26 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][160/312]	eta 0:01:55 lr 0.000612	time 0.7281 (0.7608)	model_time 0.7277 (0.7512)	loss 1.9058 (2.8341)	grad_norm 1.3875 (2.0740/1.0106)	mem 34602MB
[2025-01-19 16:34:29 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][170/312]	eta 0:01:46 lr 0.000612	time 0.7180 (0.7520)	model_time 0.7175 (0.7431)	loss 2.9907 (2.8249)	grad_norm 2.0037 (1.9708/0.7843)	mem 34604MB
[2025-01-19 16:34:33 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][170/312]	eta 0:01:47 lr 0.000612	time 0.7210 (0.7595)	model_time 0.7205 (0.7504)	loss 3.4908 (2.8303)	grad_norm 2.7393 (2.1025/1.0364)	mem 34602MB
[2025-01-19 16:34:37 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][180/312]	eta 0:01:39 lr 0.000611	time 0.7147 (0.7510)	model_time 0.7146 (0.7427)	loss 1.6185 (2.8187)	grad_norm 3.5803 (1.9861/0.7812)	mem 34604MB
[2025-01-19 16:34:40 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][180/312]	eta 0:01:40 lr 0.000611	time 0.7194 (0.7585)	model_time 0.7190 (0.7499)	loss 2.9647 (2.8431)	grad_norm 2.2738 (2.0991/1.0157)	mem 34602MB
[2025-01-19 16:34:44 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][190/312]	eta 0:01:31 lr 0.000611	time 0.8096 (0.7503)	model_time 0.8094 (0.7423)	loss 3.2674 (2.8129)	grad_norm 1.0502 (1.9841/0.7696)	mem 34604MB
[2025-01-19 16:34:48 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][190/312]	eta 0:01:32 lr 0.000611	time 0.8040 (0.7592)	model_time 0.8036 (0.7510)	loss 2.9799 (2.8541)	grad_norm 1.2117 (2.0943/1.0134)	mem 34602MB
[2025-01-19 16:34:52 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][200/312]	eta 0:01:24 lr 0.000611	time 0.7162 (0.7516)	model_time 0.7158 (0.7441)	loss 2.8780 (2.8143)	grad_norm 3.3412 (1.9986/0.7921)	mem 34604MB
[2025-01-19 16:34:56 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][200/312]	eta 0:01:25 lr 0.000611	time 0.7327 (0.7592)	model_time 0.7325 (0.7514)	loss 2.8811 (2.8482)	grad_norm 0.9472 (2.0970/1.0021)	mem 34602MB
[2025-01-19 16:35:00 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][210/312]	eta 0:01:16 lr 0.000610	time 0.8092 (0.7522)	model_time 0.8087 (0.7449)	loss 2.1961 (2.8088)	grad_norm 1.6067 (1.9902/0.7795)	mem 34604MB
[2025-01-19 16:35:03 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][210/312]	eta 0:01:17 lr 0.000610	time 0.7303 (0.7587)	model_time 0.7301 (0.7513)	loss 2.6761 (2.8521)	grad_norm 1.9846 (2.1119/0.9997)	mem 34602MB
[2025-01-19 16:35:07 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][220/312]	eta 0:01:09 lr 0.000610	time 0.8061 (0.7523)	model_time 0.8059 (0.7453)	loss 2.8108 (2.8144)	grad_norm 1.3818 (1.9721/0.7759)	mem 34604MB
[2025-01-19 16:35:11 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][220/312]	eta 0:01:09 lr 0.000610	time 0.7364 (0.7580)	model_time 0.7363 (0.7509)	loss 2.9486 (2.8534)	grad_norm 3.8991 (2.1301/1.0000)	mem 34602MB
[2025-01-19 16:35:15 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][230/312]	eta 0:01:01 lr 0.000609	time 0.8071 (0.7527)	model_time 0.8070 (0.7461)	loss 2.9385 (2.8093)	grad_norm 1.3068 (1.9515/0.7691)	mem 34604MB
[2025-01-19 16:35:18 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][230/312]	eta 0:01:02 lr 0.000609	time 0.7200 (0.7573)	model_time 0.7198 (0.7504)	loss 2.9558 (2.8466)	grad_norm 2.1473 (2.1148/0.9894)	mem 34602MB
[2025-01-19 16:35:22 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][240/312]	eta 0:00:54 lr 0.000609	time 0.7334 (0.7532)	model_time 0.7333 (0.7468)	loss 3.0557 (2.8126)	grad_norm 1.3998 (1.9665/0.7762)	mem 34604MB
[2025-01-19 16:35:26 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][240/312]	eta 0:00:54 lr 0.000609	time 0.7249 (0.7571)	model_time 0.7248 (0.7506)	loss 2.6017 (2.8444)	grad_norm 2.3858 (2.1276/0.9910)	mem 34602MB
[2025-01-19 16:35:30 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][250/312]	eta 0:00:46 lr 0.000608	time 0.7315 (0.7526)	model_time 0.7313 (0.7465)	loss 1.9777 (2.8151)	grad_norm 1.6474 (1.9655/0.7808)	mem 34604MB
[2025-01-19 16:35:33 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][250/312]	eta 0:00:46 lr 0.000608	time 0.7373 (0.7569)	model_time 0.7369 (0.7506)	loss 3.0328 (2.8486)	grad_norm 1.4765 (2.1160/0.9801)	mem 34602MB
[2025-01-19 16:35:37 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][260/312]	eta 0:00:39 lr 0.000608	time 0.7167 (0.7520)	model_time 0.7166 (0.7461)	loss 3.0610 (2.8196)	grad_norm 1.5155 (1.9994/0.8378)	mem 34604MB
[2025-01-19 16:35:41 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][260/312]	eta 0:00:39 lr 0.000608	time 0.7188 (0.7564)	model_time 0.7186 (0.7503)	loss 2.9755 (2.8523)	grad_norm 1.3971 (2.0975/0.9704)	mem 34602MB
[2025-01-19 16:35:44 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][270/312]	eta 0:00:31 lr 0.000607	time 0.7153 (0.7512)	model_time 0.7149 (0.7455)	loss 3.1487 (2.8274)	grad_norm 1.3855 (1.9993/0.8333)	mem 34604MB
[2025-01-19 16:35:48 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][270/312]	eta 0:00:31 lr 0.000607	time 0.7176 (0.7561)	model_time 0.7171 (0.7502)	loss 2.9279 (2.8491)	grad_norm 2.1866 (2.0847/0.9654)	mem 34602MB
[2025-01-19 16:35:52 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][280/312]	eta 0:00:24 lr 0.000607	time 0.7225 (0.7503)	model_time 0.7224 (0.7448)	loss 2.7692 (2.8297)	grad_norm 1.0250 (1.9838/0.8271)	mem 34604MB
[2025-01-19 16:35:55 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][280/312]	eta 0:00:24 lr 0.000607	time 0.7205 (0.7553)	model_time 0.7201 (0.7496)	loss 2.8929 (2.8504)	grad_norm 1.2379 (2.0791/0.9576)	mem 34602MB
[2025-01-19 16:35:59 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][290/312]	eta 0:00:16 lr 0.000606	time 0.7251 (0.7497)	model_time 0.7249 (0.7444)	loss 3.4528 (2.8338)	grad_norm 1.8299 (1.9615/0.8226)	mem 34604MB
[2025-01-19 16:36:03 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][290/312]	eta 0:00:16 lr 0.000606	time 0.7235 (0.7550)	model_time 0.7230 (0.7495)	loss 3.2319 (2.8495)	grad_norm 1.5360 (2.0719/0.9496)	mem 34602MB
[2025-01-19 16:36:06 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][300/312]	eta 0:00:08 lr 0.000606	time 0.7151 (0.7488)	model_time 0.7150 (0.7436)	loss 2.6674 (2.8187)	grad_norm 1.2847 (1.9627/0.8153)	mem 34604MB
[2025-01-19 16:36:10 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][300/312]	eta 0:00:09 lr 0.000606	time 0.7131 (0.7544)	model_time 0.7130 (0.7491)	loss 2.8055 (2.8466)	grad_norm 1.0023 (2.0708/0.9409)	mem 34602MB
[2025-01-19 16:36:13 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][310/312]	eta 0:00:01 lr 0.000605	time 0.7153 (0.7479)	model_time 0.7152 (0.7428)	loss 3.1548 (2.8161)	grad_norm 3.6760 (1.9829/0.8208)	mem 34604MB
[2025-01-19 16:36:14 internimage_b_1k_224] (main.py 519): INFO EPOCH 225 training takes 0:03:53
[2025-01-19 16:36:14 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_225.pth saving......
[2025-01-19 16:36:17 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_225.pth saved !!!
[2025-01-19 16:36:18 internimage_b_1k_224] (main.py 510): INFO Train: [225/300][310/312]	eta 0:00:01 lr 0.000605	time 0.8264 (0.7544)	model_time 0.8263 (0.7493)	loss 2.0353 (2.8475)	grad_norm 2.4782 (2.0483/0.9313)	mem 34602MB
[2025-01-19 16:36:18 internimage_b_1k_224] (main.py 519): INFO EPOCH 225 training takes 0:03:55
[2025-01-19 16:36:18 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_225.pth saving......
[2025-01-19 16:36:22 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_225.pth saved !!!
[2025-01-19 16:36:32 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.207 (14.207)	Loss 0.7082 (0.7082)	Acc@1 85.913 (85.913)	Acc@5 97.778 (97.778)	Mem 34604MB
[2025-01-19 16:36:37 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.002 (15.002)	Loss 0.7168 (0.7168)	Acc@1 85.693 (85.693)	Acc@5 97.803 (97.803)	Mem 34602MB
[2025-01-19 16:36:37 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.795)	Loss 0.9112 (0.8047)	Acc@1 79.956 (83.629)	Acc@5 95.850 (96.686)	Mem 34604MB
[2025-01-19 16:36:37 internimage_b_1k_224] (main.py 575): INFO [Epoch:225] * Acc@1 83.453 Acc@5 96.685
[2025-01-19 16:36:37 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.5%
[2025-01-19 16:36:38 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 16:36:41 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 16:36:41 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.45%
[2025-01-19 16:36:44 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.039)	Loss 0.9289 (0.8067)	Acc@1 79.712 (83.569)	Acc@5 95.654 (96.680)	Mem 34602MB
[2025-01-19 16:36:44 internimage_b_1k_224] (main.py 575): INFO [Epoch:225] * Acc@1 83.403 Acc@5 96.703
[2025-01-19 16:36:44 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.4%
[2025-01-19 16:36:44 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.45%
[2025-01-19 16:36:56 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.637 (14.637)	Loss 0.7087 (0.7087)	Acc@1 86.035 (86.035)	Acc@5 98.193 (98.193)	Mem 34604MB
[2025-01-19 16:37:02 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.422 (17.422)	Loss 0.7179 (0.7179)	Acc@1 85.767 (85.767)	Acc@5 98.120 (98.120)	Mem 34602MB
[2025-01-19 16:37:03 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.045)	Loss 0.9372 (0.8107)	Acc@1 80.176 (83.782)	Acc@5 95.654 (96.780)	Mem 34604MB
[2025-01-19 16:37:04 internimage_b_1k_224] (main.py 575): INFO [Epoch:225] * Acc@1 83.601 Acc@5 96.817
[2025-01-19 16:37:04 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.6%
[2025-01-19 16:37:04 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:37:07 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.073)	Loss 0.9396 (0.8124)	Acc@1 79.663 (83.754)	Acc@5 95.630 (96.793)	Mem 34602MB
[2025-01-19 16:37:07 internimage_b_1k_224] (main.py 575): INFO [Epoch:225] * Acc@1 83.579 Acc@5 96.841
[2025-01-19 16:37:07 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.6%
[2025-01-19 16:37:07 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:37:08 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:37:08 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.60%
[2025-01-19 16:37:10 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][0/312]	eta 0:10:42 lr 0.000605	time 2.0580 (2.0580)	model_time 0.7585 (0.7585)	loss 3.0101 (3.0101)	grad_norm 2.1643 (2.1643/0.0000)	mem 34604MB
[2025-01-19 16:37:11 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:37:11 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.58%
[2025-01-19 16:37:13 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][0/312]	eta 0:10:15 lr 0.000605	time 1.9725 (1.9725)	model_time 0.7477 (0.7477)	loss 3.0020 (3.0020)	grad_norm 1.2863 (1.2863/0.0000)	mem 34602MB
[2025-01-19 16:37:18 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][10/312]	eta 0:04:26 lr 0.000605	time 0.7161 (0.8832)	model_time 0.7157 (0.7646)	loss 2.8852 (2.5771)	grad_norm 2.8769 (2.7459/1.6569)	mem 34604MB
[2025-01-19 16:37:21 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][10/312]	eta 0:04:24 lr 0.000605	time 0.7180 (0.8742)	model_time 0.7175 (0.7625)	loss 2.8854 (2.9536)	grad_norm 2.3713 (2.1965/0.6934)	mem 34602MB
[2025-01-19 16:37:25 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][20/312]	eta 0:04:01 lr 0.000604	time 0.7261 (0.8276)	model_time 0.7260 (0.7653)	loss 2.7411 (2.7430)	grad_norm 4.2995 (2.6984/1.4073)	mem 34604MB
[2025-01-19 16:37:28 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][20/312]	eta 0:03:59 lr 0.000604	time 0.7267 (0.8189)	model_time 0.7266 (0.7603)	loss 3.0236 (2.9926)	grad_norm 3.2701 (2.5082/0.9361)	mem 34602MB
[2025-01-19 16:37:33 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][30/312]	eta 0:03:48 lr 0.000604	time 0.7991 (0.8088)	model_time 0.7986 (0.7665)	loss 2.8896 (2.7698)	grad_norm 1.5453 (2.4309/1.2550)	mem 34604MB
[2025-01-19 16:37:36 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][30/312]	eta 0:03:44 lr 0.000604	time 0.7174 (0.7960)	model_time 0.7170 (0.7561)	loss 1.7281 (2.9923)	grad_norm 1.8957 (2.2794/0.9157)	mem 34602MB
[2025-01-19 16:37:41 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][40/312]	eta 0:03:36 lr 0.000603	time 0.7168 (0.7948)	model_time 0.7167 (0.7627)	loss 1.9216 (2.7597)	grad_norm 1.8641 (2.2950/1.1824)	mem 34604MB
[2025-01-19 16:37:43 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][40/312]	eta 0:03:32 lr 0.000603	time 0.7188 (0.7818)	model_time 0.7186 (0.7516)	loss 2.1569 (2.9230)	grad_norm 1.3203 (2.1596/0.8849)	mem 34602MB
[2025-01-19 16:37:48 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][50/312]	eta 0:03:25 lr 0.000603	time 0.7194 (0.7840)	model_time 0.7190 (0.7581)	loss 2.8422 (2.7691)	grad_norm 2.0169 (2.2251/1.1153)	mem 34604MB
[2025-01-19 16:37:51 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][50/312]	eta 0:03:23 lr 0.000603	time 0.7175 (0.7783)	model_time 0.7171 (0.7539)	loss 2.0088 (2.9110)	grad_norm 1.4074 (2.0864/0.8502)	mem 34602MB
[2025-01-19 16:37:55 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][60/312]	eta 0:03:15 lr 0.000603	time 0.7293 (0.7757)	model_time 0.7291 (0.7540)	loss 2.5135 (2.7389)	grad_norm 1.3164 (2.0903/1.0719)	mem 34604MB
[2025-01-19 16:37:58 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][60/312]	eta 0:03:14 lr 0.000603	time 0.7206 (0.7721)	model_time 0.7205 (0.7517)	loss 2.7132 (2.9142)	grad_norm 2.1180 (2.0205/0.8198)	mem 34602MB
[2025-01-19 16:38:03 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][70/312]	eta 0:03:06 lr 0.000602	time 0.7289 (0.7699)	model_time 0.7284 (0.7512)	loss 3.3660 (2.7629)	grad_norm 1.5958 (1.9927/1.0316)	mem 34604MB
[2025-01-19 16:38:06 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][70/312]	eta 0:03:05 lr 0.000602	time 0.7255 (0.7685)	model_time 0.7254 (0.7509)	loss 1.9881 (2.8879)	grad_norm 1.2812 (2.0057/0.8192)	mem 34602MB
[2025-01-19 16:38:10 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][80/312]	eta 0:02:57 lr 0.000602	time 0.7363 (0.7649)	model_time 0.7362 (0.7485)	loss 2.7251 (2.7582)	grad_norm 1.2455 (1.9062/0.9959)	mem 34604MB
[2025-01-19 16:38:13 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][80/312]	eta 0:02:57 lr 0.000602	time 0.7541 (0.7654)	model_time 0.7536 (0.7497)	loss 3.0005 (2.8892)	grad_norm 2.3989 (2.1656/0.9637)	mem 34602MB
[2025-01-19 16:38:17 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][90/312]	eta 0:02:48 lr 0.000601	time 0.7170 (0.7604)	model_time 0.7168 (0.7458)	loss 2.5495 (2.7403)	grad_norm 0.7951 (1.8772/0.9735)	mem 34604MB
[2025-01-19 16:38:21 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][90/312]	eta 0:02:49 lr 0.000601	time 0.7214 (0.7626)	model_time 0.7210 (0.7486)	loss 2.1622 (2.9035)	grad_norm 1.7114 (2.1811/0.9404)	mem 34602MB
[2025-01-19 16:38:25 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][100/312]	eta 0:02:40 lr 0.000601	time 0.7440 (0.7580)	model_time 0.7435 (0.7448)	loss 2.8754 (2.7324)	grad_norm 2.7346 (1.9257/0.9843)	mem 34604MB
[2025-01-19 16:38:28 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][100/312]	eta 0:02:41 lr 0.000601	time 0.7205 (0.7602)	model_time 0.7203 (0.7475)	loss 3.0594 (2.9045)	grad_norm 1.8017 (2.1218/0.9276)	mem 34602MB
[2025-01-19 16:38:32 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][110/312]	eta 0:02:32 lr 0.000600	time 0.7113 (0.7552)	model_time 0.7111 (0.7431)	loss 2.8574 (2.7343)	grad_norm 4.2043 (1.9833/1.0093)	mem 34604MB
[2025-01-19 16:38:35 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][110/312]	eta 0:02:33 lr 0.000600	time 0.7185 (0.7587)	model_time 0.7183 (0.7472)	loss 2.9368 (2.8918)	grad_norm 0.9291 (2.0947/0.9058)	mem 34602MB
[2025-01-19 16:38:39 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][120/312]	eta 0:02:24 lr 0.000600	time 0.7226 (0.7530)	model_time 0.7224 (0.7419)	loss 2.1730 (2.7280)	grad_norm 2.0615 (2.0426/1.0389)	mem 34604MB
[2025-01-19 16:38:43 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][120/312]	eta 0:02:25 lr 0.000600	time 0.8260 (0.7596)	model_time 0.8256 (0.7489)	loss 2.6563 (2.8855)	grad_norm 1.0717 (2.0634/0.8967)	mem 34602MB
[2025-01-19 16:38:47 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][130/312]	eta 0:02:17 lr 0.000599	time 0.7890 (0.7555)	model_time 0.7889 (0.7452)	loss 3.3188 (2.7414)	grad_norm 4.4895 (2.0794/1.0561)	mem 34604MB
[2025-01-19 16:38:51 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][130/312]	eta 0:02:18 lr 0.000599	time 0.7170 (0.7597)	model_time 0.7166 (0.7498)	loss 2.0257 (2.8756)	grad_norm 2.6280 (2.0705/0.8850)	mem 34602MB
[2025-01-19 16:38:55 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][140/312]	eta 0:02:10 lr 0.000599	time 0.7470 (0.7567)	model_time 0.7466 (0.7472)	loss 3.1015 (2.7477)	grad_norm 2.8381 (2.0832/1.0306)	mem 34604MB
[2025-01-19 16:38:58 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][140/312]	eta 0:02:10 lr 0.000599	time 0.7418 (0.7597)	model_time 0.7416 (0.7505)	loss 3.1062 (2.8706)	grad_norm 3.5197 (2.0646/0.8719)	mem 34602MB
[2025-01-19 16:39:02 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][150/312]	eta 0:02:02 lr 0.000598	time 0.8000 (0.7574)	model_time 0.7998 (0.7485)	loss 2.1756 (2.7334)	grad_norm 2.1290 (2.0761/1.0050)	mem 34604MB
[2025-01-19 16:39:06 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][150/312]	eta 0:02:02 lr 0.000598	time 0.8051 (0.7584)	model_time 0.8049 (0.7498)	loss 3.1200 (2.8739)	grad_norm 4.5430 (2.0965/0.8737)	mem 34602MB
[2025-01-19 16:39:10 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][160/312]	eta 0:01:55 lr 0.000598	time 0.7142 (0.7579)	model_time 0.7141 (0.7495)	loss 2.3065 (2.7303)	grad_norm 3.2045 (2.0454/0.9939)	mem 34604MB
[2025-01-19 16:39:13 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][160/312]	eta 0:01:55 lr 0.000598	time 0.7440 (0.7575)	model_time 0.7438 (0.7494)	loss 3.1361 (2.8827)	grad_norm 2.9586 (2.1152/0.8917)	mem 34602MB
[2025-01-19 16:39:18 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][170/312]	eta 0:01:47 lr 0.000597	time 0.7247 (0.7581)	model_time 0.7245 (0.7501)	loss 3.0113 (2.7273)	grad_norm 1.9029 (2.0312/0.9740)	mem 34604MB
[2025-01-19 16:39:21 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][170/312]	eta 0:01:47 lr 0.000597	time 0.7239 (0.7577)	model_time 0.7238 (0.7501)	loss 1.9205 (2.8858)	grad_norm 1.4621 (2.1054/0.8806)	mem 34602MB
[2025-01-19 16:39:25 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][180/312]	eta 0:01:39 lr 0.000597	time 0.7221 (0.7568)	model_time 0.7216 (0.7492)	loss 2.9662 (2.7362)	grad_norm 3.0969 (2.0231/0.9712)	mem 34604MB
[2025-01-19 16:39:28 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][180/312]	eta 0:01:39 lr 0.000597	time 0.7198 (0.7570)	model_time 0.7194 (0.7498)	loss 2.9812 (2.8887)	grad_norm 1.3768 (2.1118/0.8776)	mem 34602MB
[2025-01-19 16:39:32 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][190/312]	eta 0:01:32 lr 0.000597	time 0.7157 (0.7555)	model_time 0.7152 (0.7483)	loss 3.1583 (2.7469)	grad_norm 1.4348 (2.0496/0.9875)	mem 34604MB
[2025-01-19 16:39:36 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][190/312]	eta 0:01:32 lr 0.000597	time 0.7355 (0.7567)	model_time 0.7351 (0.7498)	loss 3.0825 (2.8923)	grad_norm 2.1945 (2.0958/0.8615)	mem 34602MB
[2025-01-19 16:39:40 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][200/312]	eta 0:01:24 lr 0.000596	time 0.7275 (0.7547)	model_time 0.7274 (0.7479)	loss 3.4460 (2.7489)	grad_norm 1.9339 (2.0570/0.9770)	mem 34604MB
[2025-01-19 16:39:43 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][200/312]	eta 0:01:24 lr 0.000596	time 0.7230 (0.7563)	model_time 0.7226 (0.7497)	loss 2.0250 (2.8952)	grad_norm 3.1701 (2.1059/0.8609)	mem 34602MB
[2025-01-19 16:39:47 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][210/312]	eta 0:01:16 lr 0.000596	time 0.7215 (0.7535)	model_time 0.7213 (0.7470)	loss 3.3967 (2.7497)	grad_norm 5.4947 (2.0581/0.9894)	mem 34604MB
[2025-01-19 16:39:51 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][210/312]	eta 0:01:17 lr 0.000596	time 0.7190 (0.7556)	model_time 0.7188 (0.7493)	loss 2.9814 (2.8951)	grad_norm 1.4954 (2.1148/0.8565)	mem 34602MB
[2025-01-19 16:39:54 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][220/312]	eta 0:01:09 lr 0.000595	time 0.7204 (0.7521)	model_time 0.7199 (0.7458)	loss 2.5698 (2.7478)	grad_norm 1.6865 (2.0531/0.9740)	mem 34604MB
[2025-01-19 16:39:58 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][220/312]	eta 0:01:09 lr 0.000595	time 0.7687 (0.7548)	model_time 0.7685 (0.7489)	loss 3.0584 (2.9000)	grad_norm 1.7760 (2.1195/0.8453)	mem 34602MB
[2025-01-19 16:40:01 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][230/312]	eta 0:01:01 lr 0.000595	time 0.7157 (0.7510)	model_time 0.7155 (0.7450)	loss 2.0815 (2.7491)	grad_norm 1.8052 (2.0333/0.9599)	mem 34604MB
[2025-01-19 16:40:06 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][230/312]	eta 0:01:01 lr 0.000595	time 0.7160 (0.7543)	model_time 0.7156 (0.7486)	loss 2.3248 (2.8951)	grad_norm 1.7344 (2.1133/0.8405)	mem 34602MB
[2025-01-19 16:40:09 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][240/312]	eta 0:00:53 lr 0.000594	time 0.7305 (0.7499)	model_time 0.7304 (0.7442)	loss 2.6801 (2.7463)	grad_norm 1.6310 (2.0201/0.9453)	mem 34604MB
[2025-01-19 16:40:13 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][240/312]	eta 0:00:54 lr 0.000594	time 0.7253 (0.7547)	model_time 0.7248 (0.7492)	loss 2.2263 (2.8821)	grad_norm 1.4541 (2.1129/0.8342)	mem 34602MB
[2025-01-19 16:40:17 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][250/312]	eta 0:00:46 lr 0.000594	time 0.8065 (0.7512)	model_time 0.8060 (0.7457)	loss 2.4166 (2.7449)	grad_norm 1.9155 (2.0045/0.9337)	mem 34604MB
[2025-01-19 16:40:21 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][250/312]	eta 0:00:46 lr 0.000594	time 0.7954 (0.7550)	model_time 0.7949 (0.7497)	loss 3.1825 (2.8829)	grad_norm 1.5298 (2.0835/0.8327)	mem 34602MB
[2025-01-19 16:40:24 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][260/312]	eta 0:00:39 lr 0.000593	time 0.7238 (0.7513)	model_time 0.7234 (0.7460)	loss 2.2745 (2.7471)	grad_norm 1.5087 (1.9956/0.9232)	mem 34604MB
[2025-01-19 16:40:28 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][260/312]	eta 0:00:39 lr 0.000593	time 0.7445 (0.7549)	model_time 0.7443 (0.7498)	loss 3.1299 (2.8769)	grad_norm 2.6100 (2.0786/0.8283)	mem 34602MB
[2025-01-19 16:40:32 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][270/312]	eta 0:00:31 lr 0.000593	time 0.8139 (0.7516)	model_time 0.8137 (0.7465)	loss 1.9711 (2.7490)	grad_norm 2.1869 (1.9971/0.9161)	mem 34604MB
[2025-01-19 16:40:36 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][270/312]	eta 0:00:31 lr 0.000593	time 0.8109 (0.7545)	model_time 0.8105 (0.7496)	loss 3.3390 (2.8718)	grad_norm 1.3802 (2.0799/0.8252)	mem 34602MB
[2025-01-19 16:40:39 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][280/312]	eta 0:00:24 lr 0.000592	time 0.7165 (0.7522)	model_time 0.7160 (0.7472)	loss 2.9954 (2.7586)	grad_norm 1.3472 (1.9927/0.9058)	mem 34604MB
[2025-01-19 16:40:43 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][280/312]	eta 0:00:24 lr 0.000592	time 0.7206 (0.7540)	model_time 0.7205 (0.7492)	loss 2.0154 (2.8580)	grad_norm 1.1863 (2.0807/0.8227)	mem 34602MB
[2025-01-19 16:40:47 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][290/312]	eta 0:00:16 lr 0.000592	time 0.7332 (0.7527)	model_time 0.7330 (0.7479)	loss 2.9038 (2.7600)	grad_norm 2.8383 (2.0095/0.9105)	mem 34604MB
[2025-01-19 16:40:51 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][290/312]	eta 0:00:16 lr 0.000592	time 0.7193 (0.7548)	model_time 0.7192 (0.7501)	loss 2.1211 (2.8497)	grad_norm 3.9973 (2.0882/0.8290)	mem 34602MB
[2025-01-19 16:40:54 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][300/312]	eta 0:00:09 lr 0.000591	time 0.7135 (0.7519)	model_time 0.7134 (0.7473)	loss 2.8442 (2.7602)	grad_norm 4.6588 (2.0617/0.9717)	mem 34604MB
[2025-01-19 16:40:58 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][300/312]	eta 0:00:09 lr 0.000591	time 0.7144 (0.7543)	model_time 0.7143 (0.7498)	loss 2.2876 (2.8503)	grad_norm 2.1989 (2.0935/0.8286)	mem 34602MB
[2025-01-19 16:41:02 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][310/312]	eta 0:00:01 lr 0.000591	time 0.7934 (0.7510)	model_time 0.7933 (0.7465)	loss 2.6667 (2.7572)	grad_norm 3.1450 (2.0615/0.9387)	mem 34604MB
[2025-01-19 16:41:02 internimage_b_1k_224] (main.py 519): INFO EPOCH 226 training takes 0:03:54
[2025-01-19 16:41:02 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_226.pth saving......
[2025-01-19 16:41:05 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_226.pth saved !!!
[2025-01-19 16:41:06 internimage_b_1k_224] (main.py 510): INFO Train: [226/300][310/312]	eta 0:00:01 lr 0.000591	time 0.7137 (0.7535)	model_time 0.7136 (0.7492)	loss 3.2149 (2.8460)	grad_norm 2.5420 (2.0971/0.8309)	mem 34602MB
[2025-01-19 16:41:06 internimage_b_1k_224] (main.py 519): INFO EPOCH 226 training takes 0:03:55
[2025-01-19 16:41:06 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_226.pth saving......
[2025-01-19 16:41:10 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_226.pth saved !!!
[2025-01-19 16:41:20 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.497 (14.497)	Loss 0.7049 (0.7049)	Acc@1 85.986 (85.986)	Acc@5 97.778 (97.778)	Mem 34604MB
[2025-01-19 16:41:26 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.256 (16.256)	Loss 0.7073 (0.7073)	Acc@1 85.938 (85.938)	Acc@5 97.583 (97.583)	Mem 34602MB
[2025-01-19 16:41:26 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.848)	Loss 0.9144 (0.8000)	Acc@1 80.688 (83.811)	Acc@5 95.508 (96.635)	Mem 34604MB
[2025-01-19 16:41:26 internimage_b_1k_224] (main.py 575): INFO [Epoch:226] * Acc@1 83.655 Acc@5 96.631
[2025-01-19 16:41:26 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.7%
[2025-01-19 16:41:26 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 16:41:29 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 16:41:29 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.66%
[2025-01-19 16:41:33 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.083)	Loss 0.9383 (0.8048)	Acc@1 79.346 (83.567)	Acc@5 95.654 (96.713)	Mem 34602MB
[2025-01-19 16:41:33 internimage_b_1k_224] (main.py 575): INFO [Epoch:226] * Acc@1 83.447 Acc@5 96.727
[2025-01-19 16:41:33 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.4%
[2025-01-19 16:41:33 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 16:41:36 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 16:41:36 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.45%
[2025-01-19 16:41:45 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.270 (15.270)	Loss 0.7091 (0.7091)	Acc@1 86.035 (86.035)	Acc@5 98.242 (98.242)	Mem 34604MB
[2025-01-19 16:41:52 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.883 (15.883)	Loss 0.7184 (0.7184)	Acc@1 85.864 (85.864)	Acc@5 98.120 (98.120)	Mem 34602MB
[2025-01-19 16:41:52 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.054)	Loss 0.9368 (0.8106)	Acc@1 80.054 (83.771)	Acc@5 95.630 (96.793)	Mem 34604MB
[2025-01-19 16:41:52 internimage_b_1k_224] (main.py 575): INFO [Epoch:226] * Acc@1 83.595 Acc@5 96.829
[2025-01-19 16:41:52 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.6%
[2025-01-19 16:41:52 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.60%
[2025-01-19 16:41:55 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][0/312]	eta 0:16:22 lr 0.000591	time 3.1480 (3.1480)	model_time 1.1070 (1.1070)	loss 2.7947 (2.7947)	grad_norm 1.5146 (1.5146/0.0000)	mem 34604MB
[2025-01-19 16:41:56 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.800)	Loss 0.9391 (0.8123)	Acc@1 79.688 (83.789)	Acc@5 95.630 (96.800)	Mem 34602MB
[2025-01-19 16:41:56 internimage_b_1k_224] (main.py 575): INFO [Epoch:226] * Acc@1 83.613 Acc@5 96.853
[2025-01-19 16:41:56 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.6%
[2025-01-19 16:41:56 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:42:00 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:42:00 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.61%
[2025-01-19 16:42:02 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][0/312]	eta 0:10:42 lr 0.000591	time 2.0585 (2.0585)	model_time 0.7550 (0.7550)	loss 3.0205 (3.0205)	grad_norm 2.7722 (2.7722/0.0000)	mem 34602MB
[2025-01-19 16:42:03 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][10/312]	eta 0:04:48 lr 0.000590	time 0.7209 (0.9547)	model_time 0.7205 (0.7671)	loss 1.7205 (2.7966)	grad_norm 1.0099 (1.5843/0.4094)	mem 34604MB
[2025-01-19 16:42:10 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][10/312]	eta 0:04:21 lr 0.000590	time 0.8409 (0.8658)	model_time 0.8405 (0.7469)	loss 2.5448 (2.8391)	grad_norm 2.2066 (2.4741/0.9882)	mem 34602MB
[2025-01-19 16:42:10 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][20/312]	eta 0:04:08 lr 0.000590	time 0.7246 (0.8501)	model_time 0.7241 (0.7517)	loss 1.7044 (2.7696)	grad_norm 2.9624 (1.7490/0.4879)	mem 34604MB
[2025-01-19 16:42:17 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][20/312]	eta 0:03:56 lr 0.000590	time 0.7401 (0.8084)	model_time 0.7400 (0.7460)	loss 2.6302 (2.7390)	grad_norm 0.9040 (2.2736/1.0395)	mem 34602MB
[2025-01-19 16:42:18 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][30/312]	eta 0:03:49 lr 0.000590	time 0.7512 (0.8151)	model_time 0.7510 (0.7483)	loss 2.8772 (2.7499)	grad_norm 3.4290 (1.8279/0.6340)	mem 34604MB
[2025-01-19 16:42:24 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][30/312]	eta 0:03:41 lr 0.000590	time 0.7902 (0.7861)	model_time 0.7897 (0.7437)	loss 2.9502 (2.8277)	grad_norm 0.9946 (2.0337/0.9972)	mem 34602MB
[2025-01-19 16:42:25 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][40/312]	eta 0:03:36 lr 0.000589	time 0.7425 (0.7952)	model_time 0.7423 (0.7447)	loss 3.1473 (2.7949)	grad_norm 5.1149 (1.9415/0.8128)	mem 34604MB
[2025-01-19 16:42:32 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][40/312]	eta 0:03:30 lr 0.000589	time 0.7364 (0.7750)	model_time 0.7363 (0.7429)	loss 3.0551 (2.8531)	grad_norm 2.5577 (2.0983/0.9872)	mem 34602MB
[2025-01-19 16:42:32 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][50/312]	eta 0:03:24 lr 0.000589	time 0.7312 (0.7818)	model_time 0.7310 (0.7411)	loss 3.3528 (2.8541)	grad_norm 4.0457 (2.0950/0.9163)	mem 34604MB
[2025-01-19 16:42:40 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][50/312]	eta 0:03:22 lr 0.000589	time 0.7174 (0.7736)	model_time 0.7170 (0.7477)	loss 1.9922 (2.8404)	grad_norm 3.4580 (2.1066/0.9724)	mem 34602MB
[2025-01-19 16:42:40 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][60/312]	eta 0:03:16 lr 0.000588	time 0.7170 (0.7813)	model_time 0.7168 (0.7473)	loss 2.6053 (2.8509)	grad_norm 1.2247 (2.0591/0.9070)	mem 34604MB
[2025-01-19 16:42:47 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][60/312]	eta 0:03:14 lr 0.000588	time 0.7182 (0.7720)	model_time 0.7180 (0.7503)	loss 2.7956 (2.7957)	grad_norm 4.0017 (2.1470/1.0266)	mem 34602MB
[2025-01-19 16:42:48 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][70/312]	eta 0:03:08 lr 0.000588	time 0.7281 (0.7796)	model_time 0.7279 (0.7503)	loss 2.3166 (2.8698)	grad_norm 3.6903 (2.0951/0.8856)	mem 34604MB
[2025-01-19 16:42:55 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][70/312]	eta 0:03:05 lr 0.000588	time 0.7340 (0.7684)	model_time 0.7338 (0.7497)	loss 2.5233 (2.8058)	grad_norm 2.5276 (2.2568/1.0292)	mem 34602MB
[2025-01-19 16:42:55 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][80/312]	eta 0:03:00 lr 0.000587	time 0.8079 (0.7794)	model_time 0.8077 (0.7537)	loss 3.1218 (2.8946)	grad_norm 1.9943 (2.0989/0.9022)	mem 34604MB
[2025-01-19 16:43:02 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][80/312]	eta 0:02:57 lr 0.000587	time 0.7167 (0.7646)	model_time 0.7165 (0.7482)	loss 1.8690 (2.8088)	grad_norm 1.0059 (2.1835/1.0024)	mem 34602MB
[2025-01-19 16:43:03 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][90/312]	eta 0:02:53 lr 0.000587	time 0.7225 (0.7798)	model_time 0.7220 (0.7569)	loss 3.1981 (2.8706)	grad_norm 3.3158 (2.1539/0.8943)	mem 34604MB
[2025-01-19 16:43:10 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][90/312]	eta 0:02:49 lr 0.000587	time 0.7186 (0.7625)	model_time 0.7181 (0.7478)	loss 2.9283 (2.8328)	grad_norm 2.6952 (2.2222/1.0312)	mem 34602MB
[2025-01-19 16:43:11 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][100/312]	eta 0:02:45 lr 0.000586	time 0.8081 (0.7787)	model_time 0.8079 (0.7580)	loss 3.1295 (2.8739)	grad_norm 1.2838 (2.1433/0.9154)	mem 34604MB
[2025-01-19 16:43:17 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][100/312]	eta 0:02:41 lr 0.000586	time 0.8685 (0.7613)	model_time 0.8684 (0.7481)	loss 2.6501 (2.8204)	grad_norm 2.0227 (2.2569/1.0233)	mem 34602MB
[2025-01-19 16:43:18 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][110/312]	eta 0:02:36 lr 0.000586	time 0.7393 (0.7749)	model_time 0.7391 (0.7560)	loss 3.1624 (2.8553)	grad_norm 2.4989 (2.1236/0.8961)	mem 34604MB
[2025-01-19 16:43:24 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][110/312]	eta 0:02:33 lr 0.000586	time 0.7237 (0.7601)	model_time 0.7233 (0.7480)	loss 2.5914 (2.8074)	grad_norm 1.3766 (2.2527/0.9915)	mem 34602MB
[2025-01-19 16:43:26 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][120/312]	eta 0:02:28 lr 0.000585	time 0.7264 (0.7725)	model_time 0.7260 (0.7552)	loss 3.3113 (2.8633)	grad_norm 2.2566 (2.1226/0.8615)	mem 34604MB
[2025-01-19 16:43:32 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][120/312]	eta 0:02:25 lr 0.000585	time 0.7199 (0.7594)	model_time 0.7195 (0.7483)	loss 3.4514 (2.8237)	grad_norm 2.2309 (2.2602/0.9720)	mem 34602MB
[2025-01-19 16:43:33 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][130/312]	eta 0:02:19 lr 0.000585	time 0.7272 (0.7691)	model_time 0.7268 (0.7531)	loss 3.3620 (2.8594)	grad_norm 1.3447 (2.0947/0.8451)	mem 34604MB
[2025-01-19 16:43:39 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][130/312]	eta 0:02:18 lr 0.000585	time 0.8069 (0.7583)	model_time 0.8067 (0.7480)	loss 3.1784 (2.8465)	grad_norm 3.2658 (2.2666/0.9640)	mem 34602MB
[2025-01-19 16:43:40 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][140/312]	eta 0:02:11 lr 0.000584	time 0.7541 (0.7662)	model_time 0.7539 (0.7513)	loss 2.5624 (2.8711)	grad_norm 1.9145 (2.0536/0.8338)	mem 34604MB
[2025-01-19 16:43:47 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][140/312]	eta 0:02:10 lr 0.000584	time 0.7215 (0.7568)	model_time 0.7214 (0.7472)	loss 2.5380 (2.8639)	grad_norm 2.4891 (2.2400/0.9449)	mem 34602MB
[2025-01-19 16:43:48 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][150/312]	eta 0:02:03 lr 0.000584	time 0.7213 (0.7633)	model_time 0.7208 (0.7494)	loss 3.2425 (2.8619)	grad_norm 1.3206 (2.0367/0.8246)	mem 34604MB
[2025-01-19 16:43:54 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][150/312]	eta 0:02:02 lr 0.000584	time 0.7349 (0.7557)	model_time 0.7347 (0.7468)	loss 3.1904 (2.8687)	grad_norm 1.4951 (2.2328/0.9346)	mem 34602MB
[2025-01-19 16:43:55 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][160/312]	eta 0:01:55 lr 0.000584	time 0.7271 (0.7612)	model_time 0.7269 (0.7481)	loss 3.1386 (2.8662)	grad_norm 1.2043 (2.0108/0.8141)	mem 34604MB
[2025-01-19 16:44:02 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][160/312]	eta 0:01:54 lr 0.000584	time 0.7481 (0.7552)	model_time 0.7477 (0.7467)	loss 2.8304 (2.8647)	grad_norm 3.8239 (2.2400/0.9502)	mem 34602MB
[2025-01-19 16:44:02 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][170/312]	eta 0:01:47 lr 0.000583	time 0.7170 (0.7591)	model_time 0.7165 (0.7467)	loss 2.5892 (2.8668)	grad_norm 1.2558 (2.0053/0.8165)	mem 34604MB
[2025-01-19 16:44:09 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][170/312]	eta 0:01:47 lr 0.000583	time 0.7289 (0.7551)	model_time 0.7288 (0.7471)	loss 2.8664 (2.8564)	grad_norm 3.6678 (2.2725/0.9518)	mem 34602MB
[2025-01-19 16:44:10 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][180/312]	eta 0:01:40 lr 0.000583	time 0.7190 (0.7597)	model_time 0.7188 (0.7480)	loss 2.7231 (2.8670)	grad_norm 1.3274 (1.9853/0.8077)	mem 34604MB
[2025-01-19 16:44:17 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][180/312]	eta 0:01:39 lr 0.000583	time 0.7179 (0.7546)	model_time 0.7178 (0.7470)	loss 1.9674 (2.8503)	grad_norm 2.3428 (2.2674/0.9464)	mem 34602MB
[2025-01-19 16:44:18 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][190/312]	eta 0:01:32 lr 0.000582	time 0.7139 (0.7602)	model_time 0.7137 (0.7491)	loss 2.8836 (2.8644)	grad_norm 1.0083 (1.9758/0.8036)	mem 34604MB
[2025-01-19 16:44:24 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][190/312]	eta 0:01:32 lr 0.000582	time 0.7657 (0.7548)	model_time 0.7652 (0.7476)	loss 3.0900 (2.8580)	grad_norm 2.3353 (2.2219/0.9480)	mem 34602MB
[2025-01-19 16:44:25 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][200/312]	eta 0:01:25 lr 0.000582	time 0.8080 (0.7603)	model_time 0.8076 (0.7497)	loss 3.1028 (2.8549)	grad_norm 3.7572 (2.0029/0.8140)	mem 34604MB
[2025-01-19 16:44:32 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][200/312]	eta 0:01:24 lr 0.000582	time 0.7351 (0.7539)	model_time 0.7349 (0.7471)	loss 2.6788 (2.8623)	grad_norm 2.4206 (2.1990/0.9362)	mem 34602MB
[2025-01-19 16:44:33 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][210/312]	eta 0:01:17 lr 0.000581	time 0.7166 (0.7609)	model_time 0.7161 (0.7508)	loss 3.2658 (2.8589)	grad_norm 1.4590 (2.0593/0.8827)	mem 34604MB
[2025-01-19 16:44:39 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][210/312]	eta 0:01:16 lr 0.000581	time 0.7230 (0.7537)	model_time 0.7228 (0.7471)	loss 3.3584 (2.8634)	grad_norm 4.5033 (2.2175/0.9580)	mem 34602MB
[2025-01-19 16:44:40 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][220/312]	eta 0:01:09 lr 0.000581	time 0.8073 (0.7602)	model_time 0.8071 (0.7506)	loss 2.9568 (2.8570)	grad_norm 2.4495 (2.0860/0.8968)	mem 34604MB
[2025-01-19 16:44:47 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][220/312]	eta 0:01:09 lr 0.000581	time 0.9461 (0.7539)	model_time 0.9460 (0.7477)	loss 3.1395 (2.8751)	grad_norm 1.7217 (2.2085/0.9494)	mem 34602MB
[2025-01-19 16:44:48 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][230/312]	eta 0:01:02 lr 0.000580	time 0.7097 (0.7591)	model_time 0.7095 (0.7499)	loss 2.9130 (2.8614)	grad_norm 0.8062 (2.0773/0.8846)	mem 34604MB
[2025-01-19 16:44:54 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][230/312]	eta 0:01:01 lr 0.000580	time 0.7310 (0.7540)	model_time 0.7309 (0.7480)	loss 3.1162 (2.8798)	grad_norm 1.8055 (2.1851/0.9416)	mem 34602MB
[2025-01-19 16:44:55 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][240/312]	eta 0:00:54 lr 0.000580	time 0.7248 (0.7580)	model_time 0.7246 (0.7492)	loss 3.2530 (2.8564)	grad_norm 1.6106 (2.0629/0.8750)	mem 34604MB
[2025-01-19 16:45:02 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][240/312]	eta 0:00:54 lr 0.000580	time 0.7164 (0.7541)	model_time 0.7159 (0.7483)	loss 2.9998 (2.8705)	grad_norm 1.7381 (2.1791/0.9245)	mem 34602MB
[2025-01-19 16:45:02 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][250/312]	eta 0:00:46 lr 0.000579	time 0.7197 (0.7569)	model_time 0.7196 (0.7484)	loss 2.9032 (2.8547)	grad_norm 2.6382 (2.0524/0.8693)	mem 34604MB
[2025-01-19 16:45:09 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][250/312]	eta 0:00:46 lr 0.000579	time 0.7990 (0.7537)	model_time 0.7986 (0.7481)	loss 2.4920 (2.8609)	grad_norm 2.4116 (2.1681/0.9129)	mem 34602MB
[2025-01-19 16:45:10 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][260/312]	eta 0:00:39 lr 0.000579	time 0.7202 (0.7558)	model_time 0.7201 (0.7476)	loss 3.3205 (2.8569)	grad_norm 1.8118 (2.0530/0.8588)	mem 34604MB
[2025-01-19 16:45:17 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][260/312]	eta 0:00:39 lr 0.000579	time 0.7166 (0.7529)	model_time 0.7164 (0.7475)	loss 3.1174 (2.8572)	grad_norm 3.4871 (2.1769/0.9220)	mem 34602MB
[2025-01-19 16:45:17 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][270/312]	eta 0:00:31 lr 0.000579	time 0.7267 (0.7546)	model_time 0.7265 (0.7467)	loss 2.8456 (2.8443)	grad_norm 2.4495 (2.0641/0.8574)	mem 34604MB
[2025-01-19 16:45:24 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][270/312]	eta 0:00:31 lr 0.000579	time 0.7160 (0.7522)	model_time 0.7159 (0.7470)	loss 2.3057 (2.8475)	grad_norm 1.6751 (2.1701/0.9099)	mem 34602MB
[2025-01-19 16:45:24 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][280/312]	eta 0:00:24 lr 0.000578	time 0.7327 (0.7535)	model_time 0.7322 (0.7458)	loss 2.1599 (2.8434)	grad_norm 1.1723 (2.0438/0.8586)	mem 34604MB
[2025-01-19 16:45:31 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][290/312]	eta 0:00:16 lr 0.000578	time 0.7268 (0.7526)	model_time 0.7267 (0.7452)	loss 3.4043 (2.8459)	grad_norm 3.2659 (2.0386/0.8542)	mem 34604MB
[2025-01-19 16:45:31 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][280/312]	eta 0:00:24 lr 0.000578	time 0.7219 (0.7519)	model_time 0.7215 (0.7469)	loss 2.8119 (2.8445)	grad_norm 5.1587 (2.1930/0.9255)	mem 34602MB
[2025-01-19 16:45:39 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][300/312]	eta 0:00:09 lr 0.000577	time 0.7958 (0.7529)	model_time 0.7957 (0.7458)	loss 3.2648 (2.8482)	grad_norm 3.3208 (2.0474/0.8504)	mem 34604MB
[2025-01-19 16:45:39 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][290/312]	eta 0:00:16 lr 0.000578	time 0.7167 (0.7521)	model_time 0.7165 (0.7473)	loss 3.1314 (2.8426)	grad_norm 1.8063 (2.1864/0.9125)	mem 34602MB
[2025-01-19 16:45:46 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][300/312]	eta 0:00:09 lr 0.000577	time 0.7179 (0.7519)	model_time 0.7178 (0.7472)	loss 3.0245 (2.8453)	grad_norm 1.9723 (2.1794/0.9055)	mem 34602MB
[2025-01-19 16:45:46 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][310/312]	eta 0:00:01 lr 0.000577	time 0.7165 (0.7529)	model_time 0.7164 (0.7459)	loss 2.8955 (2.8443)	grad_norm 2.2014 (2.0693/0.8599)	mem 34604MB
[2025-01-19 16:45:47 internimage_b_1k_224] (main.py 519): INFO EPOCH 227 training takes 0:03:54
[2025-01-19 16:45:47 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_227.pth saving......
[2025-01-19 16:45:50 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_227.pth saved !!!
[2025-01-19 16:45:54 internimage_b_1k_224] (main.py 510): INFO Train: [227/300][310/312]	eta 0:00:01 lr 0.000577	time 0.7137 (0.7518)	model_time 0.7136 (0.7472)	loss 2.1411 (2.8423)	grad_norm 1.1363 (2.1431/0.8984)	mem 34602MB
[2025-01-19 16:45:55 internimage_b_1k_224] (main.py 519): INFO EPOCH 227 training takes 0:03:54
[2025-01-19 16:45:55 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_227.pth saving......
[2025-01-19 16:45:58 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_227.pth saved !!!
[2025-01-19 16:46:01 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 10.843 (10.843)	Loss 0.7253 (0.7253)	Acc@1 85.620 (85.620)	Acc@5 97.949 (97.949)	Mem 34604MB
[2025-01-19 16:46:08 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.553)	Loss 0.9211 (0.8076)	Acc@1 79.443 (83.594)	Acc@5 95.532 (96.686)	Mem 34604MB
[2025-01-19 16:46:08 internimage_b_1k_224] (main.py 575): INFO [Epoch:227] * Acc@1 83.413 Acc@5 96.683
[2025-01-19 16:46:08 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.4%
[2025-01-19 16:46:08 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.66%
[2025-01-19 16:46:13 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.616 (15.616)	Loss 0.7159 (0.7159)	Acc@1 85.352 (85.352)	Acc@5 97.607 (97.607)	Mem 34602MB
[2025-01-19 16:46:21 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.106)	Loss 0.9190 (0.7996)	Acc@1 79.883 (83.654)	Acc@5 96.069 (96.784)	Mem 34602MB
[2025-01-19 16:46:21 internimage_b_1k_224] (main.py 575): INFO [Epoch:227] * Acc@1 83.515 Acc@5 96.799
[2025-01-19 16:46:21 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.5%
[2025-01-19 16:46:21 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 16:46:24 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 16:46:24 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.52%
[2025-01-19 16:46:24 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.603 (16.603)	Loss 0.7096 (0.7096)	Acc@1 86.060 (86.060)	Acc@5 98.267 (98.267)	Mem 34604MB
[2025-01-19 16:46:34 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (2.347)	Loss 0.9362 (0.8106)	Acc@1 80.029 (83.798)	Acc@5 95.654 (96.811)	Mem 34604MB
[2025-01-19 16:46:34 internimage_b_1k_224] (main.py 575): INFO [Epoch:227] * Acc@1 83.635 Acc@5 96.847
[2025-01-19 16:46:34 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.6%
[2025-01-19 16:46:34 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:46:37 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 12.295 (12.295)	Loss 0.7188 (0.7188)	Acc@1 85.864 (85.864)	Acc@5 98.145 (98.145)	Mem 34602MB
[2025-01-19 16:46:38 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:46:38 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.64%
[2025-01-19 16:46:40 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][0/312]	eta 0:11:19 lr 0.000577	time 2.1768 (2.1768)	model_time 0.7435 (0.7435)	loss 2.5209 (2.5209)	grad_norm 0.9109 (0.9109/0.0000)	mem 34604MB
[2025-01-19 16:46:41 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.481)	Loss 0.9384 (0.8121)	Acc@1 79.688 (83.796)	Acc@5 95.703 (96.820)	Mem 34602MB
[2025-01-19 16:46:41 internimage_b_1k_224] (main.py 575): INFO [Epoch:227] * Acc@1 83.619 Acc@5 96.869
[2025-01-19 16:46:41 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.6%
[2025-01-19 16:46:41 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:46:45 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:46:45 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.62%
[2025-01-19 16:46:47 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][0/312]	eta 0:11:02 lr 0.000577	time 2.1247 (2.1247)	model_time 0.7506 (0.7506)	loss 2.9071 (2.9071)	grad_norm 1.7501 (1.7501/0.0000)	mem 34602MB
[2025-01-19 16:46:48 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][10/312]	eta 0:04:30 lr 0.000576	time 0.7167 (0.8967)	model_time 0.7163 (0.7661)	loss 2.6239 (2.8438)	grad_norm 2.1526 (2.0253/1.0841)	mem 34604MB
[2025-01-19 16:46:54 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][10/312]	eta 0:04:24 lr 0.000576	time 0.7284 (0.8743)	model_time 0.7283 (0.7492)	loss 2.2998 (2.6394)	grad_norm 1.7906 (2.1682/0.9731)	mem 34602MB
[2025-01-19 16:46:56 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][20/312]	eta 0:04:04 lr 0.000576	time 0.7521 (0.8367)	model_time 0.7519 (0.7681)	loss 3.3115 (2.9320)	grad_norm 2.3431 (2.0007/0.8976)	mem 34604MB
[2025-01-19 16:47:02 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][20/312]	eta 0:03:58 lr 0.000576	time 0.7243 (0.8154)	model_time 0.7239 (0.7497)	loss 2.2753 (2.7432)	grad_norm 1.8190 (2.6662/1.2245)	mem 34602MB
[2025-01-19 16:47:03 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][30/312]	eta 0:03:49 lr 0.000575	time 0.7264 (0.8130)	model_time 0.7262 (0.7664)	loss 2.6350 (2.9193)	grad_norm 1.8638 (1.9014/0.7936)	mem 34604MB
[2025-01-19 16:47:10 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][30/312]	eta 0:03:44 lr 0.000575	time 0.8369 (0.7967)	model_time 0.8368 (0.7521)	loss 2.5690 (2.7678)	grad_norm 2.3485 (2.5455/1.1141)	mem 34602MB
[2025-01-19 16:47:11 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][40/312]	eta 0:03:36 lr 0.000575	time 0.7241 (0.7944)	model_time 0.7239 (0.7592)	loss 3.3374 (2.9168)	grad_norm 3.6557 (1.8619/0.7888)	mem 34604MB
[2025-01-19 16:47:17 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][40/312]	eta 0:03:34 lr 0.000575	time 0.7333 (0.7868)	model_time 0.7328 (0.7530)	loss 2.3331 (2.7904)	grad_norm 1.9775 (2.4316/1.0510)	mem 34602MB
[2025-01-19 16:47:18 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][50/312]	eta 0:03:25 lr 0.000574	time 0.7151 (0.7839)	model_time 0.7149 (0.7554)	loss 3.0158 (2.9385)	grad_norm 2.7491 (1.9151/0.7967)	mem 34604MB
[2025-01-19 16:47:25 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][50/312]	eta 0:03:23 lr 0.000574	time 0.7282 (0.7782)	model_time 0.7280 (0.7509)	loss 3.0493 (2.8180)	grad_norm 2.4116 (2.3436/1.0222)	mem 34602MB
[2025-01-19 16:47:25 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][60/312]	eta 0:03:15 lr 0.000574	time 0.7241 (0.7746)	model_time 0.7240 (0.7507)	loss 2.6443 (2.9108)	grad_norm 1.6701 (1.9308/0.7925)	mem 34604MB
[2025-01-19 16:47:32 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][60/312]	eta 0:03:15 lr 0.000574	time 0.7458 (0.7743)	model_time 0.7457 (0.7514)	loss 1.9696 (2.7714)	grad_norm 2.0774 (2.3535/1.0345)	mem 34602MB
[2025-01-19 16:47:33 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][70/312]	eta 0:03:05 lr 0.000573	time 0.7251 (0.7685)	model_time 0.7249 (0.7480)	loss 3.1977 (2.9025)	grad_norm 1.0464 (1.8925/0.7837)	mem 34604MB
[2025-01-19 16:47:39 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][70/312]	eta 0:03:06 lr 0.000573	time 0.7179 (0.7692)	model_time 0.7178 (0.7495)	loss 3.0598 (2.7784)	grad_norm 1.3559 (2.3771/1.0960)	mem 34602MB
[2025-01-19 16:47:40 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][80/312]	eta 0:02:57 lr 0.000573	time 0.7241 (0.7634)	model_time 0.7240 (0.7454)	loss 2.8795 (2.8867)	grad_norm 3.0987 (1.8801/0.7646)	mem 34604MB
[2025-01-19 16:47:47 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][80/312]	eta 0:02:57 lr 0.000573	time 0.7503 (0.7661)	model_time 0.7502 (0.7488)	loss 3.1478 (2.7883)	grad_norm 2.2929 (2.3034/1.0542)	mem 34602MB
[2025-01-19 16:47:47 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][90/312]	eta 0:02:48 lr 0.000573	time 0.7318 (0.7599)	model_time 0.7316 (0.7438)	loss 2.0272 (2.8724)	grad_norm 6.0365 (1.9586/0.8893)	mem 34604MB
[2025-01-19 16:47:54 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][90/312]	eta 0:02:49 lr 0.000573	time 0.7234 (0.7646)	model_time 0.7230 (0.7491)	loss 2.9370 (2.7876)	grad_norm 0.8683 (2.2578/1.0390)	mem 34602MB
[2025-01-19 16:47:54 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][100/312]	eta 0:02:40 lr 0.000572	time 0.7131 (0.7577)	model_time 0.7129 (0.7431)	loss 2.7166 (2.8637)	grad_norm 4.7574 (2.1085/1.0573)	mem 34604MB
[2025-01-19 16:48:02 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][100/312]	eta 0:02:41 lr 0.000572	time 0.7268 (0.7629)	model_time 0.7266 (0.7489)	loss 3.0137 (2.8073)	grad_norm 2.9872 (2.2836/1.0113)	mem 34602MB
[2025-01-19 16:48:02 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][110/312]	eta 0:02:33 lr 0.000572	time 0.8105 (0.7600)	model_time 0.8103 (0.7467)	loss 3.0481 (2.8491)	grad_norm 3.2818 (2.1641/1.0673)	mem 34604MB
[2025-01-19 16:48:09 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][110/312]	eta 0:02:33 lr 0.000572	time 0.7419 (0.7624)	model_time 0.7418 (0.7497)	loss 2.8263 (2.8280)	grad_norm 2.4594 (2.2979/1.0088)	mem 34602MB
[2025-01-19 16:48:10 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][120/312]	eta 0:02:26 lr 0.000571	time 0.8037 (0.7605)	model_time 0.8036 (0.7483)	loss 2.0749 (2.8228)	grad_norm 1.8667 (2.2084/1.0537)	mem 34604MB
[2025-01-19 16:48:17 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][120/312]	eta 0:02:26 lr 0.000571	time 0.7256 (0.7606)	model_time 0.7254 (0.7489)	loss 2.0992 (2.8160)	grad_norm 1.2940 (2.3386/1.0759)	mem 34602MB
[2025-01-19 16:48:18 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][130/312]	eta 0:02:18 lr 0.000571	time 0.7178 (0.7608)	model_time 0.7176 (0.7495)	loss 2.9928 (2.8268)	grad_norm 1.8869 (2.1870/1.0276)	mem 34604MB
[2025-01-19 16:48:24 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][130/312]	eta 0:02:18 lr 0.000571	time 0.7180 (0.7592)	model_time 0.7178 (0.7484)	loss 3.0267 (2.8193)	grad_norm 3.4189 (2.3704/1.0991)	mem 34602MB
[2025-01-19 16:48:26 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][140/312]	eta 0:02:11 lr 0.000570	time 1.0012 (0.7627)	model_time 1.0008 (0.7522)	loss 2.7438 (2.8430)	grad_norm 0.9580 (2.1407/1.0085)	mem 34604MB
[2025-01-19 16:48:32 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][140/312]	eta 0:02:10 lr 0.000570	time 0.8235 (0.7591)	model_time 0.8234 (0.7491)	loss 3.1543 (2.8314)	grad_norm 3.9877 (2.4010/1.0913)	mem 34602MB
[2025-01-19 16:48:33 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][150/312]	eta 0:02:03 lr 0.000570	time 0.7341 (0.7619)	model_time 0.7339 (0.7521)	loss 1.9895 (2.8546)	grad_norm 1.0199 (2.0864/1.0009)	mem 34604MB
[2025-01-19 16:48:39 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][150/312]	eta 0:02:02 lr 0.000570	time 0.7198 (0.7575)	model_time 0.7197 (0.7481)	loss 2.7763 (2.8143)	grad_norm 1.2886 (2.3769/1.0744)	mem 34602MB
[2025-01-19 16:48:40 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][160/312]	eta 0:01:55 lr 0.000569	time 0.7159 (0.7602)	model_time 0.7158 (0.7510)	loss 3.2366 (2.8576)	grad_norm 1.3037 (2.0448/0.9901)	mem 34604MB
[2025-01-19 16:48:47 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][160/312]	eta 0:01:55 lr 0.000569	time 0.7178 (0.7576)	model_time 0.7173 (0.7488)	loss 2.7427 (2.8065)	grad_norm 1.3681 (2.3199/1.0683)	mem 34602MB
[2025-01-19 16:48:48 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][170/312]	eta 0:01:47 lr 0.000569	time 0.7196 (0.7594)	model_time 0.7195 (0.7507)	loss 2.3782 (2.8546)	grad_norm 2.4600 (2.0174/0.9734)	mem 34604MB
[2025-01-19 16:48:54 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][170/312]	eta 0:01:47 lr 0.000569	time 0.7251 (0.7567)	model_time 0.7250 (0.7484)	loss 2.9944 (2.8061)	grad_norm 2.3299 (2.2941/1.0533)	mem 34602MB
[2025-01-19 16:48:55 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][180/312]	eta 0:01:39 lr 0.000568	time 0.7110 (0.7575)	model_time 0.7106 (0.7492)	loss 3.2982 (2.8526)	grad_norm 1.6392 (2.0181/0.9535)	mem 34604MB
[2025-01-19 16:49:02 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][180/312]	eta 0:01:39 lr 0.000568	time 0.7161 (0.7560)	model_time 0.7160 (0.7481)	loss 3.2908 (2.8162)	grad_norm 1.7691 (2.2804/1.0420)	mem 34602MB
[2025-01-19 16:49:02 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][190/312]	eta 0:01:32 lr 0.000568	time 0.7214 (0.7557)	model_time 0.7213 (0.7478)	loss 2.9181 (2.8604)	grad_norm 2.5676 (2.0163/0.9352)	mem 34604MB
[2025-01-19 16:49:09 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][190/312]	eta 0:01:32 lr 0.000568	time 0.7287 (0.7552)	model_time 0.7283 (0.7477)	loss 3.1087 (2.7956)	grad_norm 1.7515 (2.2404/1.0345)	mem 34602MB
[2025-01-19 16:49:10 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][200/312]	eta 0:01:24 lr 0.000568	time 0.7231 (0.7544)	model_time 0.7230 (0.7469)	loss 3.1404 (2.8590)	grad_norm 3.7463 (2.0249/0.9277)	mem 34604MB
[2025-01-19 16:49:16 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][200/312]	eta 0:01:24 lr 0.000568	time 0.7176 (0.7543)	model_time 0.7174 (0.7471)	loss 2.5836 (2.7868)	grad_norm 1.9157 (2.2263/1.0149)	mem 34602MB
[2025-01-19 16:49:17 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][210/312]	eta 0:01:16 lr 0.000567	time 0.7279 (0.7529)	model_time 0.7277 (0.7458)	loss 3.1765 (2.8631)	grad_norm 2.8496 (2.0570/0.9414)	mem 34604MB
[2025-01-19 16:49:24 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][210/312]	eta 0:01:16 lr 0.000567	time 0.7246 (0.7538)	model_time 0.7245 (0.7470)	loss 3.4439 (2.7816)	grad_norm 3.1757 (2.2151/1.0112)	mem 34602MB
[2025-01-19 16:49:24 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][220/312]	eta 0:01:09 lr 0.000567	time 0.7148 (0.7524)	model_time 0.7143 (0.7455)	loss 2.7931 (2.8605)	grad_norm 1.6927 (2.0527/0.9320)	mem 34604MB
[2025-01-19 16:49:31 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][220/312]	eta 0:01:09 lr 0.000567	time 0.7829 (0.7536)	model_time 0.7828 (0.7470)	loss 3.4150 (2.7744)	grad_norm 1.5597 (2.2121/0.9999)	mem 34602MB
[2025-01-19 16:49:32 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][230/312]	eta 0:01:01 lr 0.000566	time 0.8024 (0.7531)	model_time 0.8022 (0.7465)	loss 3.4100 (2.8609)	grad_norm 1.1379 (2.0372/0.9261)	mem 34604MB
[2025-01-19 16:49:39 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][230/312]	eta 0:01:01 lr 0.000566	time 0.7281 (0.7535)	model_time 0.7279 (0.7473)	loss 2.5727 (2.7785)	grad_norm 3.3426 (2.2006/0.9911)	mem 34602MB
[2025-01-19 16:49:40 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][240/312]	eta 0:00:54 lr 0.000566	time 0.8050 (0.7533)	model_time 0.8046 (0.7470)	loss 2.7938 (2.8505)	grad_norm 3.3874 (2.0346/0.9183)	mem 34604MB
[2025-01-19 16:49:46 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][240/312]	eta 0:00:54 lr 0.000566	time 0.7178 (0.7530)	model_time 0.7176 (0.7470)	loss 2.9532 (2.7737)	grad_norm 2.3323 (2.1884/0.9833)	mem 34602MB
[2025-01-19 16:49:47 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][250/312]	eta 0:00:46 lr 0.000565	time 0.7979 (0.7536)	model_time 0.7974 (0.7475)	loss 3.3415 (2.8518)	grad_norm 2.2360 (2.0330/0.9035)	mem 34604MB
[2025-01-19 16:49:54 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][250/312]	eta 0:00:46 lr 0.000565	time 0.7245 (0.7527)	model_time 0.7241 (0.7469)	loss 2.1530 (2.7777)	grad_norm 1.0106 (2.1703/0.9697)	mem 34602MB
[2025-01-19 16:49:55 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][260/312]	eta 0:00:39 lr 0.000565	time 0.8006 (0.7544)	model_time 0.8005 (0.7486)	loss 3.3731 (2.8509)	grad_norm 1.9798 (2.0418/0.8989)	mem 34604MB
[2025-01-19 16:50:01 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][260/312]	eta 0:00:39 lr 0.000565	time 0.8107 (0.7527)	model_time 0.8105 (0.7471)	loss 2.3670 (2.7821)	grad_norm 2.7653 (2.1684/0.9617)	mem 34602MB
[2025-01-19 16:50:02 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][270/312]	eta 0:00:31 lr 0.000564	time 0.7161 (0.7540)	model_time 0.7159 (0.7484)	loss 3.0624 (2.8558)	grad_norm 1.6485 (2.0440/0.8893)	mem 34604MB
[2025-01-19 16:50:09 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][270/312]	eta 0:00:31 lr 0.000564	time 0.7165 (0.7522)	model_time 0.7161 (0.7468)	loss 3.1561 (2.7845)	grad_norm 2.1120 (2.1665/0.9524)	mem 34602MB
[2025-01-19 16:50:10 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][280/312]	eta 0:00:24 lr 0.000564	time 0.7159 (0.7535)	model_time 0.7154 (0.7481)	loss 3.0350 (2.8506)	grad_norm 2.1788 (2.0426/0.8825)	mem 34604MB
[2025-01-19 16:50:16 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][280/312]	eta 0:00:24 lr 0.000564	time 0.7302 (0.7521)	model_time 0.7297 (0.7469)	loss 3.2865 (2.7908)	grad_norm 3.3672 (2.1817/0.9589)	mem 34602MB
[2025-01-19 16:50:17 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][290/312]	eta 0:00:16 lr 0.000564	time 0.7262 (0.7529)	model_time 0.7261 (0.7477)	loss 2.7556 (2.8519)	grad_norm 1.0903 (2.0409/0.8835)	mem 34604MB
[2025-01-19 16:50:24 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][290/312]	eta 0:00:16 lr 0.000564	time 0.8384 (0.7519)	model_time 0.8380 (0.7469)	loss 2.8748 (2.7791)	grad_norm 1.0593 (2.1727/0.9502)	mem 34602MB
[2025-01-19 16:50:24 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][300/312]	eta 0:00:09 lr 0.000563	time 0.7145 (0.7520)	model_time 0.7144 (0.7469)	loss 2.6754 (2.8507)	grad_norm 1.6759 (2.0484/0.8778)	mem 34604MB
[2025-01-19 16:50:31 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][300/312]	eta 0:00:09 lr 0.000563	time 0.7142 (0.7514)	model_time 0.7141 (0.7465)	loss 2.8960 (2.7837)	grad_norm 2.4767 (2.1546/0.9448)	mem 34602MB
[2025-01-19 16:50:31 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][310/312]	eta 0:00:01 lr 0.000563	time 0.7136 (0.7508)	model_time 0.7135 (0.7459)	loss 2.7996 (2.8542)	grad_norm 3.0815 (2.0624/0.8811)	mem 34604MB
[2025-01-19 16:50:32 internimage_b_1k_224] (main.py 519): INFO EPOCH 228 training takes 0:03:54
[2025-01-19 16:50:32 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_228.pth saving......
[2025-01-19 16:50:35 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_228.pth saved !!!
[2025-01-19 16:50:38 internimage_b_1k_224] (main.py 510): INFO Train: [228/300][310/312]	eta 0:00:01 lr 0.000563	time 0.7821 (0.7514)	model_time 0.7820 (0.7466)	loss 2.8345 (2.7974)	grad_norm 2.2206 (2.1677/0.9461)	mem 34602MB
[2025-01-19 16:50:39 internimage_b_1k_224] (main.py 519): INFO EPOCH 228 training takes 0:03:54
[2025-01-19 16:50:39 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_228.pth saving......
[2025-01-19 16:50:42 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_228.pth saved !!!
[2025-01-19 16:50:46 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 10.731 (10.731)	Loss 0.7144 (0.7144)	Acc@1 85.840 (85.840)	Acc@5 97.656 (97.656)	Mem 34604MB
[2025-01-19 16:50:52 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.537)	Loss 0.9203 (0.8099)	Acc@1 80.127 (83.716)	Acc@5 95.947 (96.682)	Mem 34604MB
[2025-01-19 16:50:53 internimage_b_1k_224] (main.py 575): INFO [Epoch:228] * Acc@1 83.511 Acc@5 96.691
[2025-01-19 16:50:53 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.5%
[2025-01-19 16:50:53 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.66%
[2025-01-19 16:50:57 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.776 (14.776)	Loss 0.7081 (0.7081)	Acc@1 85.742 (85.742)	Acc@5 97.827 (97.827)	Mem 34602MB
[2025-01-19 16:51:05 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (2.087)	Loss 0.9413 (0.8044)	Acc@1 79.736 (83.669)	Acc@5 95.850 (96.768)	Mem 34602MB
[2025-01-19 16:51:06 internimage_b_1k_224] (main.py 575): INFO [Epoch:228] * Acc@1 83.503 Acc@5 96.789
[2025-01-19 16:51:06 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.5%
[2025-01-19 16:51:06 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.52%
[2025-01-19 16:51:09 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.872 (15.872)	Loss 0.7100 (0.7100)	Acc@1 86.084 (86.084)	Acc@5 98.267 (98.267)	Mem 34604MB
[2025-01-19 16:51:18 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.320)	Loss 0.9359 (0.8105)	Acc@1 80.078 (83.860)	Acc@5 95.654 (96.822)	Mem 34604MB
[2025-01-19 16:51:18 internimage_b_1k_224] (main.py 575): INFO [Epoch:228] * Acc@1 83.705 Acc@5 96.855
[2025-01-19 16:51:18 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.7%
[2025-01-19 16:51:18 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:51:21 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.186 (15.186)	Loss 0.7191 (0.7191)	Acc@1 85.962 (85.962)	Acc@5 98.145 (98.145)	Mem 34602MB
[2025-01-19 16:51:22 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:51:22 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.71%
[2025-01-19 16:51:25 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][0/312]	eta 0:11:48 lr 0.000563	time 2.2715 (2.2715)	model_time 0.7448 (0.7448)	loss 1.8703 (1.8703)	grad_norm 1.9204 (1.9204/0.0000)	mem 34604MB
[2025-01-19 16:51:25 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.805)	Loss 0.9377 (0.8118)	Acc@1 79.761 (83.831)	Acc@5 95.703 (96.835)	Mem 34602MB
[2025-01-19 16:51:26 internimage_b_1k_224] (main.py 575): INFO [Epoch:228] * Acc@1 83.651 Acc@5 96.883
[2025-01-19 16:51:26 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.7%
[2025-01-19 16:51:26 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:51:29 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:51:29 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.65%
[2025-01-19 16:51:32 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][0/312]	eta 0:12:07 lr 0.000563	time 2.3304 (2.3304)	model_time 0.7531 (0.7531)	loss 2.5101 (2.5101)	grad_norm 1.8144 (1.8144/0.0000)	mem 34602MB
[2025-01-19 16:51:32 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][10/312]	eta 0:04:22 lr 0.000562	time 0.7234 (0.8684)	model_time 0.7233 (0.7293)	loss 2.7106 (2.6656)	grad_norm 2.9090 (2.1680/0.7722)	mem 34604MB
[2025-01-19 16:51:39 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][10/312]	eta 0:04:25 lr 0.000562	time 0.7313 (0.8794)	model_time 0.7309 (0.7357)	loss 2.9084 (2.9138)	grad_norm 2.8435 (1.9074/0.7548)	mem 34602MB
[2025-01-19 16:51:39 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][20/312]	eta 0:03:53 lr 0.000562	time 0.7175 (0.8011)	model_time 0.7173 (0.7281)	loss 3.0875 (2.7816)	grad_norm 1.2316 (2.2495/0.8056)	mem 34604MB
[2025-01-19 16:51:47 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][30/312]	eta 0:03:39 lr 0.000561	time 0.7278 (0.7778)	model_time 0.7273 (0.7282)	loss 3.0370 (2.8553)	grad_norm 3.6337 (2.1435/0.8184)	mem 34604MB
[2025-01-19 16:51:47 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][20/312]	eta 0:03:59 lr 0.000562	time 0.7315 (0.8186)	model_time 0.7313 (0.7432)	loss 2.9175 (2.8693)	grad_norm 2.4313 (1.8362/0.6775)	mem 34602MB
[2025-01-19 16:51:54 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][30/312]	eta 0:03:44 lr 0.000561	time 0.7171 (0.7966)	model_time 0.7169 (0.7454)	loss 3.1705 (2.8643)	grad_norm 1.0972 (1.8661/0.7279)	mem 34602MB
[2025-01-19 16:51:54 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][40/312]	eta 0:03:32 lr 0.000561	time 0.7152 (0.7795)	model_time 0.7150 (0.7419)	loss 3.4427 (2.8602)	grad_norm 3.4040 (2.2449/0.8495)	mem 34604MB
[2025-01-19 16:52:02 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][40/312]	eta 0:03:35 lr 0.000561	time 0.7204 (0.7927)	model_time 0.7203 (0.7540)	loss 3.1317 (2.8700)	grad_norm 1.7758 (1.9478/0.7569)	mem 34602MB
[2025-01-19 16:52:02 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][50/312]	eta 0:03:23 lr 0.000560	time 0.7109 (0.7753)	model_time 0.7105 (0.7450)	loss 3.3013 (2.8766)	grad_norm 1.7934 (2.2092/0.7787)	mem 34604MB
[2025-01-19 16:52:09 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][50/312]	eta 0:03:25 lr 0.000560	time 0.7160 (0.7854)	model_time 0.7159 (0.7542)	loss 2.8244 (2.8620)	grad_norm 1.2588 (1.8694/0.7631)	mem 34602MB
[2025-01-19 16:52:10 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][60/312]	eta 0:03:14 lr 0.000560	time 0.8266 (0.7728)	model_time 0.8264 (0.7474)	loss 1.8460 (2.8261)	grad_norm 2.0547 (2.1642/0.7613)	mem 34604MB
[2025-01-19 16:52:17 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][60/312]	eta 0:03:16 lr 0.000560	time 0.8027 (0.7782)	model_time 0.8026 (0.7521)	loss 2.7548 (2.8403)	grad_norm 1.1304 (1.8211/0.7296)	mem 34602MB
[2025-01-19 16:52:17 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][70/312]	eta 0:03:06 lr 0.000559	time 0.7186 (0.7711)	model_time 0.7182 (0.7493)	loss 2.7915 (2.8432)	grad_norm 1.1005 (2.1385/0.7782)	mem 34604MB
[2025-01-19 16:52:24 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][70/312]	eta 0:03:07 lr 0.000559	time 0.7362 (0.7749)	model_time 0.7360 (0.7524)	loss 2.5520 (2.8011)	grad_norm 3.4208 (1.7984/0.7204)	mem 34602MB
[2025-01-19 16:52:25 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][80/312]	eta 0:02:58 lr 0.000559	time 0.7172 (0.7695)	model_time 0.7171 (0.7503)	loss 2.6778 (2.8340)	grad_norm 1.6796 (2.1259/0.7897)	mem 34604MB
[2025-01-19 16:52:32 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][80/312]	eta 0:02:59 lr 0.000559	time 0.7171 (0.7725)	model_time 0.7167 (0.7528)	loss 3.0966 (2.7912)	grad_norm 2.0413 (1.8226/0.6971)	mem 34602MB
[2025-01-19 16:52:32 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][90/312]	eta 0:02:50 lr 0.000558	time 0.7258 (0.7663)	model_time 0.7253 (0.7492)	loss 2.7133 (2.8332)	grad_norm 3.0224 (2.0877/0.7830)	mem 34604MB
[2025-01-19 16:52:39 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][90/312]	eta 0:02:50 lr 0.000558	time 0.7256 (0.7693)	model_time 0.7251 (0.7517)	loss 1.9937 (2.7814)	grad_norm 2.2816 (1.8898/0.7647)	mem 34602MB
[2025-01-19 16:52:40 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][100/312]	eta 0:02:41 lr 0.000558	time 0.8018 (0.7631)	model_time 0.8016 (0.7476)	loss 2.7967 (2.8200)	grad_norm 2.1349 (2.0733/0.7650)	mem 34604MB
[2025-01-19 16:52:47 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][100/312]	eta 0:02:42 lr 0.000558	time 0.7303 (0.7660)	model_time 0.7301 (0.7501)	loss 2.7251 (2.7852)	grad_norm 0.8881 (1.9031/0.7565)	mem 34602MB
[2025-01-19 16:52:47 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][110/312]	eta 0:02:33 lr 0.000558	time 0.7276 (0.7599)	model_time 0.7274 (0.7458)	loss 2.6416 (2.8198)	grad_norm 1.5422 (2.0442/0.7506)	mem 34604MB
[2025-01-19 16:52:54 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][120/312]	eta 0:02:25 lr 0.000557	time 0.7383 (0.7574)	model_time 0.7378 (0.7444)	loss 2.9333 (2.8254)	grad_norm 2.2815 (2.0951/0.7858)	mem 34604MB
[2025-01-19 16:52:54 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][110/312]	eta 0:02:34 lr 0.000558	time 0.7214 (0.7648)	model_time 0.7210 (0.7503)	loss 2.3284 (2.7828)	grad_norm 2.7698 (1.8808/0.7514)	mem 34602MB
[2025-01-19 16:53:01 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][130/312]	eta 0:02:17 lr 0.000557	time 0.7205 (0.7549)	model_time 0.7201 (0.7429)	loss 2.4178 (2.8343)	grad_norm 0.8723 (2.0419/0.7882)	mem 34604MB
[2025-01-19 16:53:02 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][120/312]	eta 0:02:26 lr 0.000557	time 0.8022 (0.7629)	model_time 0.8020 (0.7495)	loss 2.6368 (2.7858)	grad_norm 3.4761 (1.9138/0.7722)	mem 34602MB
[2025-01-19 16:53:09 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][140/312]	eta 0:02:09 lr 0.000556	time 0.7347 (0.7527)	model_time 0.7345 (0.7415)	loss 2.3822 (2.8300)	grad_norm 3.0357 (2.0373/0.7691)	mem 34604MB
[2025-01-19 16:53:09 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][130/312]	eta 0:02:18 lr 0.000557	time 0.7234 (0.7611)	model_time 0.7232 (0.7488)	loss 1.9475 (2.7868)	grad_norm 3.3905 (1.9457/0.7732)	mem 34602MB
[2025-01-19 16:53:16 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][150/312]	eta 0:02:01 lr 0.000556	time 0.7101 (0.7507)	model_time 0.7097 (0.7402)	loss 2.4312 (2.8207)	grad_norm 2.3049 (2.0706/0.7914)	mem 34604MB
[2025-01-19 16:53:17 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][140/312]	eta 0:02:10 lr 0.000556	time 0.8090 (0.7613)	model_time 0.8089 (0.7498)	loss 1.8212 (2.7829)	grad_norm 1.2742 (1.9253/0.7647)	mem 34602MB
[2025-01-19 16:53:23 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][160/312]	eta 0:01:54 lr 0.000555	time 0.7158 (0.7512)	model_time 0.7157 (0.7413)	loss 3.1381 (2.8245)	grad_norm 0.9990 (2.0502/0.7798)	mem 34604MB
[2025-01-19 16:53:24 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][150/312]	eta 0:02:03 lr 0.000556	time 0.7985 (0.7603)	model_time 0.7983 (0.7496)	loss 1.9578 (2.7806)	grad_norm 1.3186 (1.9003/0.7571)	mem 34602MB
[2025-01-19 16:53:31 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][170/312]	eta 0:01:46 lr 0.000555	time 0.7200 (0.7519)	model_time 0.7198 (0.7426)	loss 3.6428 (2.8274)	grad_norm 1.5874 (2.0173/0.7734)	mem 34604MB
[2025-01-19 16:53:32 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][160/312]	eta 0:01:55 lr 0.000555	time 0.7277 (0.7600)	model_time 0.7276 (0.7499)	loss 3.0049 (2.7885)	grad_norm 1.3726 (1.8748/0.7456)	mem 34602MB
[2025-01-19 16:53:39 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][180/312]	eta 0:01:39 lr 0.000554	time 0.9071 (0.7528)	model_time 0.9069 (0.7440)	loss 3.1225 (2.8208)	grad_norm 2.0597 (2.0550/0.8001)	mem 34604MB
[2025-01-19 16:53:39 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][170/312]	eta 0:01:47 lr 0.000555	time 0.7181 (0.7598)	model_time 0.7180 (0.7502)	loss 3.4919 (2.7952)	grad_norm 2.6687 (1.8907/0.7473)	mem 34602MB
[2025-01-19 16:53:46 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][190/312]	eta 0:01:31 lr 0.000554	time 0.7171 (0.7536)	model_time 0.7169 (0.7453)	loss 2.3384 (2.8135)	grad_norm 1.8068 (2.0767/0.8232)	mem 34604MB
[2025-01-19 16:53:47 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][180/312]	eta 0:01:40 lr 0.000554	time 0.7995 (0.7587)	model_time 0.7993 (0.7496)	loss 3.1541 (2.8029)	grad_norm 3.0174 (1.8892/0.7402)	mem 34602MB
[2025-01-19 16:53:54 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][200/312]	eta 0:01:24 lr 0.000554	time 0.7159 (0.7543)	model_time 0.7157 (0.7464)	loss 2.9190 (2.8171)	grad_norm 1.3865 (2.0751/0.8231)	mem 34604MB
[2025-01-19 16:53:54 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][190/312]	eta 0:01:32 lr 0.000554	time 0.7244 (0.7585)	model_time 0.7240 (0.7499)	loss 2.7691 (2.8014)	grad_norm 3.0852 (1.9067/0.7526)	mem 34602MB
[2025-01-19 16:54:01 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][210/312]	eta 0:01:16 lr 0.000553	time 0.7174 (0.7536)	model_time 0.7172 (0.7460)	loss 2.8915 (2.8147)	grad_norm 2.0994 (2.1090/0.8393)	mem 34604MB
[2025-01-19 16:54:02 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][200/312]	eta 0:01:24 lr 0.000554	time 0.8091 (0.7584)	model_time 0.8090 (0.7502)	loss 2.8923 (2.7876)	grad_norm 1.4908 (1.9209/0.7492)	mem 34602MB
[2025-01-19 16:54:09 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][220/312]	eta 0:01:09 lr 0.000553	time 0.7484 (0.7525)	model_time 0.7480 (0.7452)	loss 2.7990 (2.8218)	grad_norm 2.3161 (2.1309/0.8605)	mem 34604MB
[2025-01-19 16:54:09 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][210/312]	eta 0:01:17 lr 0.000553	time 0.7334 (0.7577)	model_time 0.7330 (0.7499)	loss 2.8359 (2.7901)	grad_norm 1.1882 (1.9111/0.7443)	mem 34602MB
[2025-01-19 16:54:16 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][230/312]	eta 0:01:01 lr 0.000552	time 0.7119 (0.7517)	model_time 0.7117 (0.7447)	loss 3.2274 (2.8174)	grad_norm 3.0504 (2.1317/0.8568)	mem 34604MB
[2025-01-19 16:54:17 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][220/312]	eta 0:01:09 lr 0.000553	time 0.7586 (0.7568)	model_time 0.7585 (0.7493)	loss 2.8861 (2.7927)	grad_norm 1.3439 (1.9013/0.7301)	mem 34602MB
[2025-01-19 16:54:23 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][240/312]	eta 0:00:54 lr 0.000552	time 0.7566 (0.7508)	model_time 0.7564 (0.7441)	loss 2.4514 (2.8093)	grad_norm 2.1001 (2.1376/0.8501)	mem 34604MB
[2025-01-19 16:54:24 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][230/312]	eta 0:01:02 lr 0.000552	time 0.7180 (0.7566)	model_time 0.7178 (0.7494)	loss 3.1718 (2.8024)	grad_norm 2.4541 (1.9217/0.7404)	mem 34602MB
[2025-01-19 16:54:31 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][250/312]	eta 0:00:46 lr 0.000551	time 0.7180 (0.7500)	model_time 0.7179 (0.7435)	loss 3.6320 (2.8140)	grad_norm 0.9385 (2.1097/0.8523)	mem 34604MB
[2025-01-19 16:54:32 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][240/312]	eta 0:00:54 lr 0.000552	time 0.8166 (0.7561)	model_time 0.8165 (0.7492)	loss 2.8480 (2.8052)	grad_norm 2.2133 (1.9147/0.7326)	mem 34602MB
[2025-01-19 16:54:38 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][260/312]	eta 0:00:38 lr 0.000551	time 0.7100 (0.7494)	model_time 0.7098 (0.7432)	loss 3.4134 (2.8250)	grad_norm 3.0717 (2.0998/0.8463)	mem 34604MB
[2025-01-19 16:54:39 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][250/312]	eta 0:00:46 lr 0.000551	time 0.7581 (0.7556)	model_time 0.7579 (0.7489)	loss 3.4170 (2.8153)	grad_norm 1.9466 (1.9109/0.7232)	mem 34602MB
[2025-01-19 16:54:45 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][270/312]	eta 0:00:31 lr 0.000550	time 0.7203 (0.7487)	model_time 0.7198 (0.7428)	loss 2.8498 (2.8242)	grad_norm 1.9722 (2.1083/0.8508)	mem 34604MB
[2025-01-19 16:54:47 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][260/312]	eta 0:00:39 lr 0.000551	time 0.8306 (0.7556)	model_time 0.8304 (0.7492)	loss 2.5919 (2.8169)	grad_norm 2.6208 (1.9151/0.7213)	mem 34602MB
[2025-01-19 16:54:53 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][280/312]	eta 0:00:23 lr 0.000550	time 0.7157 (0.7490)	model_time 0.7156 (0.7432)	loss 3.3336 (2.8292)	grad_norm 1.3266 (2.1050/0.8526)	mem 34604MB
[2025-01-19 16:54:54 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][270/312]	eta 0:00:31 lr 0.000550	time 0.7943 (0.7552)	model_time 0.7939 (0.7490)	loss 2.8745 (2.8121)	grad_norm 1.3190 (1.9315/0.7463)	mem 34602MB
[2025-01-19 16:55:00 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][290/312]	eta 0:00:16 lr 0.000550	time 0.7233 (0.7490)	model_time 0.7231 (0.7434)	loss 3.2706 (2.8357)	grad_norm 1.7340 (2.1166/0.8459)	mem 34604MB
[2025-01-19 16:55:02 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][280/312]	eta 0:00:24 lr 0.000550	time 0.7221 (0.7550)	model_time 0.7220 (0.7491)	loss 3.5780 (2.8115)	grad_norm 1.8349 (1.9535/0.7536)	mem 34602MB
[2025-01-19 16:55:08 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][300/312]	eta 0:00:08 lr 0.000549	time 0.7128 (0.7490)	model_time 0.7127 (0.7435)	loss 2.9205 (2.8347)	grad_norm 1.8868 (2.1029/0.8416)	mem 34604MB
[2025-01-19 16:55:09 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][290/312]	eta 0:00:16 lr 0.000550	time 0.7181 (0.7549)	model_time 0.7179 (0.7492)	loss 2.9102 (2.8109)	grad_norm 4.1105 (1.9815/0.7679)	mem 34602MB
[2025-01-19 16:55:16 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][310/312]	eta 0:00:01 lr 0.000549	time 0.8016 (0.7495)	model_time 0.8015 (0.7442)	loss 3.0177 (2.8369)	grad_norm 3.5359 (2.0963/0.8395)	mem 34604MB
[2025-01-19 16:55:16 internimage_b_1k_224] (main.py 519): INFO EPOCH 229 training takes 0:03:53
[2025-01-19 16:55:16 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_229.pth saving......
[2025-01-19 16:55:17 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][300/312]	eta 0:00:09 lr 0.000549	time 0.7897 (0.7545)	model_time 0.7896 (0.7489)	loss 3.1596 (2.8125)	grad_norm 2.5054 (1.9798/0.7652)	mem 34602MB
[2025-01-19 16:55:19 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_229.pth saved !!!
[2025-01-19 16:55:24 internimage_b_1k_224] (main.py 510): INFO Train: [229/300][310/312]	eta 0:00:01 lr 0.000549	time 0.7945 (0.7537)	model_time 0.7943 (0.7484)	loss 3.1649 (2.8223)	grad_norm 1.1734 (1.9708/0.7628)	mem 34602MB
[2025-01-19 16:55:25 internimage_b_1k_224] (main.py 519): INFO EPOCH 229 training takes 0:03:55
[2025-01-19 16:55:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_229.pth saving......
[2025-01-19 16:55:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_229.pth saved !!!
[2025-01-19 16:55:30 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 10.323 (10.323)	Loss 0.7287 (0.7287)	Acc@1 86.084 (86.084)	Acc@5 97.876 (97.876)	Mem 34604MB
[2025-01-19 16:55:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.517)	Loss 0.9395 (0.8153)	Acc@1 79.468 (83.671)	Acc@5 95.728 (96.766)	Mem 34604MB
[2025-01-19 16:55:37 internimage_b_1k_224] (main.py 575): INFO [Epoch:229] * Acc@1 83.503 Acc@5 96.779
[2025-01-19 16:55:37 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.5%
[2025-01-19 16:55:37 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.66%
[2025-01-19 16:55:43 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.180 (15.180)	Loss 0.7215 (0.7215)	Acc@1 85.791 (85.791)	Acc@5 97.656 (97.656)	Mem 34602MB
[2025-01-19 16:55:50 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.051)	Loss 0.9218 (0.7977)	Acc@1 79.395 (83.640)	Acc@5 95.752 (96.764)	Mem 34602MB
[2025-01-19 16:55:50 internimage_b_1k_224] (main.py 575): INFO [Epoch:229] * Acc@1 83.499 Acc@5 96.783
[2025-01-19 16:55:50 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.5%
[2025-01-19 16:55:50 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.52%
[2025-01-19 16:55:53 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.504 (16.504)	Loss 0.7105 (0.7105)	Acc@1 86.157 (86.157)	Acc@5 98.267 (98.267)	Mem 34604MB
[2025-01-19 16:56:02 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (2.348)	Loss 0.9354 (0.8105)	Acc@1 80.029 (83.871)	Acc@5 95.630 (96.828)	Mem 34604MB
[2025-01-19 16:56:03 internimage_b_1k_224] (main.py 575): INFO [Epoch:229] * Acc@1 83.727 Acc@5 96.859
[2025-01-19 16:56:03 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.7%
[2025-01-19 16:56:03 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:56:05 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.075 (15.075)	Loss 0.7197 (0.7197)	Acc@1 85.962 (85.962)	Acc@5 98.145 (98.145)	Mem 34602MB
[2025-01-19 16:56:07 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:56:07 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.73%
[2025-01-19 16:56:09 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][0/312]	eta 0:11:28 lr 0.000549	time 2.2075 (2.2075)	model_time 0.7295 (0.7295)	loss 2.8982 (2.8982)	grad_norm 3.4149 (3.4149/0.0000)	mem 34604MB
[2025-01-19 16:56:10 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.777)	Loss 0.9369 (0.8115)	Acc@1 79.761 (83.842)	Acc@5 95.728 (96.864)	Mem 34602MB
[2025-01-19 16:56:10 internimage_b_1k_224] (main.py 575): INFO [Epoch:229] * Acc@1 83.661 Acc@5 96.911
[2025-01-19 16:56:10 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.7%
[2025-01-19 16:56:10 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 16:56:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 16:56:14 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.66%
[2025-01-19 16:56:16 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][0/312]	eta 0:11:47 lr 0.000549	time 2.2678 (2.2678)	model_time 0.7561 (0.7561)	loss 2.1467 (2.1467)	grad_norm 2.1183 (2.1183/0.0000)	mem 34602MB
[2025-01-19 16:56:16 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][10/312]	eta 0:04:31 lr 0.000548	time 0.7250 (0.8976)	model_time 0.7249 (0.7629)	loss 2.7922 (3.0164)	grad_norm 4.3603 (2.4181/1.0880)	mem 34604MB
[2025-01-19 16:56:24 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][10/312]	eta 0:04:26 lr 0.000548	time 0.8120 (0.8836)	model_time 0.8116 (0.7458)	loss 3.1533 (2.7885)	grad_norm 1.2381 (1.7458/0.4837)	mem 34602MB
[2025-01-19 16:56:24 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][20/312]	eta 0:04:00 lr 0.000548	time 0.7181 (0.8223)	model_time 0.7177 (0.7516)	loss 3.1622 (2.9415)	grad_norm 2.0961 (2.8465/1.3894)	mem 34604MB
[2025-01-19 16:56:31 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][30/312]	eta 0:03:43 lr 0.000547	time 0.7084 (0.7939)	model_time 0.7079 (0.7459)	loss 2.5968 (2.8715)	grad_norm 1.5151 (2.4814/1.3030)	mem 34604MB
[2025-01-19 16:56:31 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][20/312]	eta 0:04:00 lr 0.000548	time 0.7193 (0.8234)	model_time 0.7191 (0.7511)	loss 2.1058 (2.7988)	grad_norm 2.1299 (1.7738/0.3929)	mem 34602MB
[2025-01-19 16:56:39 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][40/312]	eta 0:03:32 lr 0.000547	time 0.7202 (0.7805)	model_time 0.7200 (0.7442)	loss 2.3177 (2.8417)	grad_norm 1.0404 (2.2479/1.2266)	mem 34604MB
[2025-01-19 16:56:39 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][30/312]	eta 0:03:43 lr 0.000547	time 0.7252 (0.7934)	model_time 0.7247 (0.7444)	loss 2.3753 (2.7159)	grad_norm 3.2446 (2.1172/0.8644)	mem 34602MB
[2025-01-19 16:56:46 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][50/312]	eta 0:03:21 lr 0.000546	time 0.7281 (0.7706)	model_time 0.7279 (0.7413)	loss 3.0138 (2.8606)	grad_norm 1.4877 (2.0667/1.1612)	mem 34604MB
[2025-01-19 16:56:46 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][40/312]	eta 0:03:32 lr 0.000547	time 0.7172 (0.7827)	model_time 0.7167 (0.7455)	loss 1.8837 (2.7154)	grad_norm 1.3811 (1.9373/0.8517)	mem 34602MB
[2025-01-19 16:56:53 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][60/312]	eta 0:03:12 lr 0.000546	time 0.7151 (0.7634)	model_time 0.7146 (0.7388)	loss 2.6521 (2.8558)	grad_norm 2.0903 (2.0152/1.0823)	mem 34604MB
[2025-01-19 16:56:54 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][50/312]	eta 0:03:23 lr 0.000546	time 0.7176 (0.7761)	model_time 0.7172 (0.7461)	loss 3.5287 (2.7475)	grad_norm 2.4281 (1.9319/0.8247)	mem 34602MB
[2025-01-19 16:57:00 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][70/312]	eta 0:03:03 lr 0.000545	time 0.7338 (0.7583)	model_time 0.7336 (0.7372)	loss 3.0696 (2.8179)	grad_norm 1.3498 (1.9417/1.0423)	mem 34604MB
[2025-01-19 16:57:01 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][60/312]	eta 0:03:14 lr 0.000546	time 0.7107 (0.7714)	model_time 0.7103 (0.7462)	loss 2.3716 (2.7366)	grad_norm 2.3024 (2.0054/0.8257)	mem 34602MB
[2025-01-19 16:57:08 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][80/312]	eta 0:02:55 lr 0.000545	time 0.7157 (0.7544)	model_time 0.7152 (0.7358)	loss 2.8061 (2.7977)	grad_norm 1.3959 (2.0597/1.1906)	mem 34604MB
[2025-01-19 16:57:09 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][70/312]	eta 0:03:06 lr 0.000545	time 0.7254 (0.7710)	model_time 0.7253 (0.7494)	loss 2.9715 (2.7460)	grad_norm 4.2775 (2.1416/0.9104)	mem 34602MB
[2025-01-19 16:57:15 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][90/312]	eta 0:02:47 lr 0.000545	time 0.7154 (0.7552)	model_time 0.7152 (0.7386)	loss 3.5233 (2.7743)	grad_norm 2.3395 (2.1655/1.1921)	mem 34604MB
[2025-01-19 16:57:16 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][80/312]	eta 0:02:58 lr 0.000545	time 0.7204 (0.7691)	model_time 0.7202 (0.7500)	loss 2.5726 (2.7500)	grad_norm 1.3420 (2.1641/0.9580)	mem 34602MB
[2025-01-19 16:57:23 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][100/312]	eta 0:02:40 lr 0.000544	time 0.7169 (0.7548)	model_time 0.7167 (0.7398)	loss 1.7108 (2.7521)	grad_norm 1.5404 (2.1643/1.1521)	mem 34604MB
[2025-01-19 16:57:24 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][90/312]	eta 0:02:50 lr 0.000545	time 0.8066 (0.7681)	model_time 0.8065 (0.7511)	loss 2.9204 (2.7591)	grad_norm 1.1491 (2.1713/0.9338)	mem 34602MB
[2025-01-19 16:57:30 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][110/312]	eta 0:02:32 lr 0.000544	time 0.8090 (0.7560)	model_time 0.8088 (0.7423)	loss 2.9821 (2.7753)	grad_norm 1.8117 (2.1629/1.1161)	mem 34604MB
[2025-01-19 16:57:31 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][100/312]	eta 0:02:42 lr 0.000544	time 0.7213 (0.7650)	model_time 0.7211 (0.7497)	loss 1.9943 (2.7524)	grad_norm 2.1276 (2.1705/0.9082)	mem 34602MB
[2025-01-19 16:57:38 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][120/312]	eta 0:02:25 lr 0.000543	time 0.8113 (0.7575)	model_time 0.8108 (0.7450)	loss 3.2723 (2.7972)	grad_norm 2.8177 (2.1665/1.0781)	mem 34604MB
[2025-01-19 16:57:39 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][110/312]	eta 0:02:34 lr 0.000544	time 0.7291 (0.7630)	model_time 0.7287 (0.7491)	loss 2.9367 (2.7516)	grad_norm 1.0242 (2.1144/0.9014)	mem 34602MB
[2025-01-19 16:57:46 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][130/312]	eta 0:02:17 lr 0.000543	time 0.8097 (0.7579)	model_time 0.8096 (0.7462)	loss 1.9910 (2.7967)	grad_norm 2.0230 (2.1486/1.0517)	mem 34604MB
[2025-01-19 16:57:46 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][120/312]	eta 0:02:26 lr 0.000543	time 0.7301 (0.7632)	model_time 0.7296 (0.7504)	loss 3.6899 (2.7501)	grad_norm 1.3231 (2.1170/0.8891)	mem 34602MB
[2025-01-19 16:57:53 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][140/312]	eta 0:02:10 lr 0.000542	time 0.7206 (0.7562)	model_time 0.7201 (0.7454)	loss 2.7747 (2.7863)	grad_norm 1.2525 (2.1377/1.0232)	mem 34604MB
[2025-01-19 16:57:54 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][130/312]	eta 0:02:18 lr 0.000543	time 0.8083 (0.7617)	model_time 0.8079 (0.7498)	loss 2.5195 (2.7290)	grad_norm 2.4319 (2.1124/0.8645)	mem 34602MB
[2025-01-19 16:58:00 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][150/312]	eta 0:02:02 lr 0.000542	time 0.7192 (0.7541)	model_time 0.7191 (0.7439)	loss 1.7318 (2.7823)	grad_norm 2.9435 (2.1493/1.0102)	mem 34604MB
[2025-01-19 16:58:01 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][140/312]	eta 0:02:10 lr 0.000542	time 0.7283 (0.7615)	model_time 0.7281 (0.7504)	loss 2.4599 (2.7259)	grad_norm 5.1371 (2.1272/0.8841)	mem 34602MB
[2025-01-19 16:58:08 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][160/312]	eta 0:01:54 lr 0.000541	time 0.7089 (0.7530)	model_time 0.7085 (0.7435)	loss 2.9636 (2.7817)	grad_norm 3.1954 (2.2016/1.0569)	mem 34604MB
[2025-01-19 16:58:09 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][150/312]	eta 0:02:02 lr 0.000542	time 0.7177 (0.7590)	model_time 0.7173 (0.7486)	loss 2.9576 (2.7221)	grad_norm 2.0963 (2.1280/0.9101)	mem 34602MB
[2025-01-19 16:58:15 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][170/312]	eta 0:01:46 lr 0.000541	time 0.7246 (0.7516)	model_time 0.7244 (0.7425)	loss 2.1256 (2.7803)	grad_norm 3.2418 (2.2688/1.0769)	mem 34604MB
[2025-01-19 16:58:16 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][160/312]	eta 0:01:55 lr 0.000541	time 0.7228 (0.7572)	model_time 0.7223 (0.7475)	loss 3.1808 (2.7241)	grad_norm 2.3492 (2.1316/0.9131)	mem 34602MB
[2025-01-19 16:58:22 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][180/312]	eta 0:01:39 lr 0.000541	time 0.7220 (0.7501)	model_time 0.7215 (0.7416)	loss 3.3243 (2.7915)	grad_norm 1.3415 (2.2399/1.0661)	mem 34604MB
[2025-01-19 16:58:24 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][170/312]	eta 0:01:47 lr 0.000541	time 0.7289 (0.7578)	model_time 0.7287 (0.7486)	loss 2.9623 (2.7235)	grad_norm 1.3034 (2.1518/0.9249)	mem 34602MB
[2025-01-19 16:58:30 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][190/312]	eta 0:01:31 lr 0.000540	time 0.7298 (0.7489)	model_time 0.7296 (0.7408)	loss 2.1440 (2.7885)	grad_norm 2.5028 (2.2310/1.0573)	mem 34604MB
[2025-01-19 16:58:31 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][180/312]	eta 0:01:39 lr 0.000541	time 0.7187 (0.7565)	model_time 0.7182 (0.7477)	loss 2.6946 (2.7258)	grad_norm 1.5506 (2.1544/0.9260)	mem 34602MB
[2025-01-19 16:58:37 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][200/312]	eta 0:01:23 lr 0.000540	time 0.7281 (0.7476)	model_time 0.7277 (0.7399)	loss 3.1296 (2.7798)	grad_norm 2.4509 (2.2526/1.0482)	mem 34604MB
[2025-01-19 16:58:38 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][190/312]	eta 0:01:32 lr 0.000540	time 0.7196 (0.7559)	model_time 0.7191 (0.7476)	loss 2.8522 (2.7349)	grad_norm 1.5028 (2.1361/0.9159)	mem 34602MB
[2025-01-19 16:58:45 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][210/312]	eta 0:01:16 lr 0.000539	time 0.8433 (0.7489)	model_time 0.8432 (0.7415)	loss 2.1148 (2.7710)	grad_norm 1.6729 (2.2542/1.0494)	mem 34604MB
[2025-01-19 16:58:46 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][200/312]	eta 0:01:24 lr 0.000540	time 0.7174 (0.7566)	model_time 0.7170 (0.7487)	loss 2.9729 (2.7386)	grad_norm 1.3897 (2.1360/0.9208)	mem 34602MB
[2025-01-19 16:58:52 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][220/312]	eta 0:01:08 lr 0.000539	time 0.7160 (0.7494)	model_time 0.7158 (0.7423)	loss 2.5729 (2.7756)	grad_norm 1.6686 (2.2532/1.0425)	mem 34604MB
[2025-01-19 16:58:54 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][210/312]	eta 0:01:17 lr 0.000539	time 0.7209 (0.7567)	model_time 0.7207 (0.7492)	loss 3.0244 (2.7486)	grad_norm 3.0831 (2.1530/0.9101)	mem 34602MB
[2025-01-19 16:59:00 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][230/312]	eta 0:01:01 lr 0.000538	time 0.8065 (0.7496)	model_time 0.8063 (0.7429)	loss 2.5469 (2.7798)	grad_norm 2.5101 (2.2751/1.0391)	mem 34604MB
[2025-01-19 16:59:01 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][220/312]	eta 0:01:09 lr 0.000539	time 0.7398 (0.7567)	model_time 0.7396 (0.7495)	loss 2.1193 (2.7547)	grad_norm 2.1834 (2.1554/0.8982)	mem 34602MB
[2025-01-19 16:59:07 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][240/312]	eta 0:00:54 lr 0.000538	time 0.7599 (0.7502)	model_time 0.7597 (0.7437)	loss 3.0424 (2.7851)	grad_norm 2.9380 (2.2609/1.0276)	mem 34604MB
[2025-01-19 16:59:09 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][230/312]	eta 0:01:02 lr 0.000538	time 0.7206 (0.7562)	model_time 0.7202 (0.7493)	loss 3.0100 (2.7651)	grad_norm 0.9514 (2.1245/0.8950)	mem 34602MB
[2025-01-19 16:59:15 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][250/312]	eta 0:00:46 lr 0.000538	time 0.7152 (0.7504)	model_time 0.7147 (0.7442)	loss 2.5097 (2.7932)	grad_norm 1.4982 (2.2376/1.0158)	mem 34604MB
[2025-01-19 16:59:16 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][240/312]	eta 0:00:54 lr 0.000538	time 0.7192 (0.7561)	model_time 0.7190 (0.7494)	loss 3.5037 (2.7685)	grad_norm 2.1174 (2.1281/0.8872)	mem 34602MB
[2025-01-19 16:59:22 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][260/312]	eta 0:00:38 lr 0.000537	time 0.7237 (0.7500)	model_time 0.7235 (0.7439)	loss 3.1098 (2.7951)	grad_norm 2.6677 (2.2142/1.0072)	mem 34604MB
[2025-01-19 16:59:24 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][250/312]	eta 0:00:46 lr 0.000538	time 0.7352 (0.7552)	model_time 0.7351 (0.7488)	loss 3.1556 (2.7756)	grad_norm 1.4997 (2.1084/0.8827)	mem 34602MB
[2025-01-19 16:59:30 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][270/312]	eta 0:00:31 lr 0.000537	time 0.7307 (0.7492)	model_time 0.7305 (0.7434)	loss 2.9078 (2.7918)	grad_norm 0.7781 (2.2049/0.9984)	mem 34604MB
[2025-01-19 16:59:31 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][260/312]	eta 0:00:39 lr 0.000537	time 0.7161 (0.7551)	model_time 0.7157 (0.7490)	loss 2.7757 (2.7799)	grad_norm 1.2982 (2.0860/0.8758)	mem 34602MB
[2025-01-19 16:59:37 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][280/312]	eta 0:00:23 lr 0.000536	time 0.7165 (0.7488)	model_time 0.7164 (0.7432)	loss 3.3149 (2.7936)	grad_norm 3.2135 (2.1929/0.9878)	mem 34604MB
[2025-01-19 16:59:38 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][270/312]	eta 0:00:31 lr 0.000537	time 0.7356 (0.7542)	model_time 0.7354 (0.7482)	loss 3.2646 (2.7832)	grad_norm 1.4631 (2.0912/0.8690)	mem 34602MB
[2025-01-19 16:59:44 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][290/312]	eta 0:00:16 lr 0.000536	time 0.7258 (0.7483)	model_time 0.7256 (0.7428)	loss 2.6849 (2.7918)	grad_norm 1.0521 (2.1861/0.9798)	mem 34604MB
[2025-01-19 16:59:46 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][280/312]	eta 0:00:24 lr 0.000536	time 0.7235 (0.7534)	model_time 0.7234 (0.7477)	loss 3.1654 (2.7822)	grad_norm 1.5516 (2.0981/0.8723)	mem 34602MB
[2025-01-19 16:59:52 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][300/312]	eta 0:00:08 lr 0.000535	time 0.7163 (0.7473)	model_time 0.7162 (0.7421)	loss 3.3034 (2.7894)	grad_norm 1.1907 (2.1659/0.9686)	mem 34604MB
[2025-01-19 16:59:53 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][290/312]	eta 0:00:16 lr 0.000536	time 0.7175 (0.7532)	model_time 0.7173 (0.7476)	loss 3.1507 (2.7837)	grad_norm 2.4981 (2.0821/0.8666)	mem 34602MB
[2025-01-19 16:59:59 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][310/312]	eta 0:00:01 lr 0.000535	time 0.7149 (0.7465)	model_time 0.7148 (0.7413)	loss 2.4255 (2.7933)	grad_norm 4.4730 (2.1789/0.9735)	mem 34604MB
[2025-01-19 16:59:59 internimage_b_1k_224] (main.py 519): INFO EPOCH 230 training takes 0:03:52
[2025-01-19 16:59:59 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_230.pth saving......
[2025-01-19 17:00:00 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][300/312]	eta 0:00:09 lr 0.000535	time 0.7144 (0.7525)	model_time 0.7143 (0.7471)	loss 3.3250 (2.7777)	grad_norm 2.2169 (2.0819/0.8682)	mem 34602MB
[2025-01-19 17:00:03 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_230.pth saved !!!
[2025-01-19 17:00:08 internimage_b_1k_224] (main.py 510): INFO Train: [230/300][310/312]	eta 0:00:01 lr 0.000535	time 0.7123 (0.7522)	model_time 0.7122 (0.7470)	loss 2.6880 (2.7796)	grad_norm 3.4631 (2.0894/0.8693)	mem 34602MB
[2025-01-19 17:00:09 internimage_b_1k_224] (main.py 519): INFO EPOCH 230 training takes 0:03:54
[2025-01-19 17:00:09 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_230.pth saving......
[2025-01-19 17:00:12 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.872 (8.872)	Loss 0.7183 (0.7183)	Acc@1 85.547 (85.547)	Acc@5 97.900 (97.900)	Mem 34604MB
[2025-01-19 17:00:12 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_230.pth saved !!!
[2025-01-19 17:00:18 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.360)	Loss 0.9316 (0.8082)	Acc@1 80.078 (83.794)	Acc@5 95.825 (96.711)	Mem 34604MB
[2025-01-19 17:00:18 internimage_b_1k_224] (main.py 575): INFO [Epoch:230] * Acc@1 83.623 Acc@5 96.709
[2025-01-19 17:00:18 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.6%
[2025-01-19 17:00:18 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.66%
[2025-01-19 17:00:27 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.225 (15.225)	Loss 0.7184 (0.7184)	Acc@1 85.840 (85.840)	Acc@5 97.803 (97.803)	Mem 34602MB
[2025-01-19 17:00:35 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.105)	Loss 0.9250 (0.8052)	Acc@1 79.883 (83.649)	Acc@5 95.728 (96.780)	Mem 34602MB
[2025-01-19 17:00:35 internimage_b_1k_224] (main.py 575): INFO [Epoch:230] * Acc@1 83.509 Acc@5 96.813
[2025-01-19 17:00:35 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.5%
[2025-01-19 17:00:35 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.52%
[2025-01-19 17:00:35 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.360 (17.360)	Loss 0.7109 (0.7109)	Acc@1 86.133 (86.133)	Acc@5 98.242 (98.242)	Mem 34604MB
[2025-01-19 17:00:44 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.180 (2.378)	Loss 0.9351 (0.8105)	Acc@1 80.103 (83.887)	Acc@5 95.654 (96.828)	Mem 34604MB
[2025-01-19 17:00:44 internimage_b_1k_224] (main.py 575): INFO [Epoch:230] * Acc@1 83.743 Acc@5 96.859
[2025-01-19 17:00:44 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.7%
[2025-01-19 17:00:44 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:00:49 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:00:49 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.74%
[2025-01-19 17:00:49 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 13.383 (13.383)	Loss 0.7198 (0.7198)	Acc@1 85.962 (85.962)	Acc@5 98.145 (98.145)	Mem 34602MB
[2025-01-19 17:00:51 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][0/312]	eta 0:11:04 lr 0.000535	time 2.1299 (2.1299)	model_time 0.7308 (0.7308)	loss 2.0098 (2.0098)	grad_norm 1.2407 (1.2407/0.0000)	mem 34604MB
[2025-01-19 17:00:53 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.185 (1.626)	Loss 0.9363 (0.8112)	Acc@1 79.810 (83.860)	Acc@5 95.825 (96.875)	Mem 34602MB
[2025-01-19 17:00:53 internimage_b_1k_224] (main.py 575): INFO [Epoch:230] * Acc@1 83.681 Acc@5 96.921
[2025-01-19 17:00:53 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.7%
[2025-01-19 17:00:54 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:00:57 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:00:57 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.68%
[2025-01-19 17:00:58 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][10/312]	eta 0:04:19 lr 0.000534	time 0.7150 (0.8592)	model_time 0.7149 (0.7316)	loss 2.7024 (2.5445)	grad_norm 3.5453 (2.3577/0.7462)	mem 34604MB
[2025-01-19 17:00:59 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][0/312]	eta 0:11:36 lr 0.000535	time 2.2322 (2.2322)	model_time 0.7487 (0.7487)	loss 2.9559 (2.9559)	grad_norm 1.2319 (1.2319/0.0000)	mem 34602MB
[2025-01-19 17:01:06 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][20/312]	eta 0:03:57 lr 0.000534	time 0.7189 (0.8134)	model_time 0.7184 (0.7465)	loss 2.1794 (2.6518)	grad_norm 1.6946 (2.3650/1.0857)	mem 34604MB
[2025-01-19 17:01:07 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][10/312]	eta 0:04:26 lr 0.000534	time 0.7175 (0.8826)	model_time 0.7171 (0.7472)	loss 3.3366 (2.8677)	grad_norm 2.5794 (1.5325/0.4749)	mem 34602MB
[2025-01-19 17:01:13 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][30/312]	eta 0:03:44 lr 0.000533	time 0.8015 (0.7967)	model_time 0.8013 (0.7513)	loss 2.7911 (2.7470)	grad_norm 2.7314 (2.4898/1.0396)	mem 34604MB
[2025-01-19 17:01:15 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][20/312]	eta 0:04:00 lr 0.000534	time 0.7250 (0.8246)	model_time 0.7244 (0.7535)	loss 2.6974 (2.8675)	grad_norm 1.4343 (1.7355/0.7743)	mem 34602MB
[2025-01-19 17:01:21 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][40/312]	eta 0:03:34 lr 0.000533	time 0.7216 (0.7878)	model_time 0.7214 (0.7533)	loss 3.4147 (2.7857)	grad_norm 3.6655 (2.5163/1.0618)	mem 34604MB
[2025-01-19 17:01:22 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][30/312]	eta 0:03:46 lr 0.000533	time 0.7269 (0.8015)	model_time 0.7267 (0.7532)	loss 2.9954 (2.8662)	grad_norm 1.7824 (1.9254/0.8670)	mem 34602MB
[2025-01-19 17:01:29 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][50/312]	eta 0:03:25 lr 0.000533	time 0.7209 (0.7855)	model_time 0.7207 (0.7578)	loss 2.9692 (2.7796)	grad_norm 1.2423 (2.3609/1.0224)	mem 34604MB
[2025-01-19 17:01:30 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][40/312]	eta 0:03:34 lr 0.000533	time 0.7153 (0.7873)	model_time 0.7148 (0.7507)	loss 3.1129 (2.9192)	grad_norm 1.2178 (1.9555/0.8374)	mem 34602MB
[2025-01-19 17:01:36 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][60/312]	eta 0:03:16 lr 0.000532	time 0.7218 (0.7813)	model_time 0.7214 (0.7580)	loss 2.2704 (2.7624)	grad_norm 1.8017 (2.3348/0.9656)	mem 34604MB
[2025-01-19 17:01:37 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][50/312]	eta 0:03:24 lr 0.000533	time 0.7177 (0.7806)	model_time 0.7173 (0.7511)	loss 2.7035 (2.9038)	grad_norm 1.7506 (2.1627/1.0917)	mem 34602MB
[2025-01-19 17:01:44 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][70/312]	eta 0:03:07 lr 0.000532	time 0.7321 (0.7762)	model_time 0.7316 (0.7562)	loss 2.5563 (2.7765)	grad_norm 1.0312 (2.2753/0.9519)	mem 34604MB
[2025-01-19 17:01:44 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][60/312]	eta 0:03:14 lr 0.000532	time 0.8276 (0.7737)	model_time 0.8274 (0.7489)	loss 2.9410 (2.8780)	grad_norm 1.1896 (2.1518/1.0873)	mem 34602MB
[2025-01-19 17:01:51 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][80/312]	eta 0:02:58 lr 0.000531	time 0.7456 (0.7703)	model_time 0.7454 (0.7527)	loss 1.9594 (2.7882)	grad_norm 1.1696 (2.1726/0.9399)	mem 34604MB
[2025-01-19 17:01:52 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][70/312]	eta 0:03:06 lr 0.000532	time 0.7311 (0.7712)	model_time 0.7310 (0.7500)	loss 2.7770 (2.8461)	grad_norm 1.1707 (2.1366/1.0470)	mem 34602MB
[2025-01-19 17:01:58 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][90/312]	eta 0:02:50 lr 0.000531	time 0.7195 (0.7669)	model_time 0.7190 (0.7512)	loss 3.3555 (2.7984)	grad_norm 1.2183 (2.1161/0.9076)	mem 34604MB
[2025-01-19 17:01:59 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][80/312]	eta 0:02:58 lr 0.000531	time 0.7190 (0.7685)	model_time 0.7186 (0.7497)	loss 1.8579 (2.8289)	grad_norm 1.8486 (2.1333/1.0112)	mem 34602MB
[2025-01-19 17:02:06 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][100/312]	eta 0:02:41 lr 0.000530	time 0.7304 (0.7635)	model_time 0.7303 (0.7493)	loss 3.2336 (2.8089)	grad_norm 1.1741 (2.1297/0.8863)	mem 34604MB
[2025-01-19 17:02:07 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][90/312]	eta 0:02:49 lr 0.000531	time 0.7182 (0.7641)	model_time 0.7180 (0.7474)	loss 3.1970 (2.8227)	grad_norm 2.8260 (2.1694/1.0002)	mem 34602MB
[2025-01-19 17:02:13 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][110/312]	eta 0:02:33 lr 0.000530	time 0.7221 (0.7604)	model_time 0.7216 (0.7475)	loss 1.9146 (2.7892)	grad_norm 2.7247 (2.2037/0.9361)	mem 34604MB
[2025-01-19 17:02:15 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][100/312]	eta 0:02:42 lr 0.000530	time 0.7182 (0.7655)	model_time 0.7181 (0.7504)	loss 2.7790 (2.8012)	grad_norm 1.4029 (2.2689/1.1016)	mem 34602MB
[2025-01-19 17:02:20 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][120/312]	eta 0:02:25 lr 0.000530	time 0.7174 (0.7578)	model_time 0.7172 (0.7458)	loss 2.9214 (2.7806)	grad_norm 1.2624 (2.1985/0.9330)	mem 34604MB
[2025-01-19 17:02:22 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][110/312]	eta 0:02:34 lr 0.000530	time 0.7220 (0.7627)	model_time 0.7218 (0.7489)	loss 3.1589 (2.7979)	grad_norm 1.2805 (2.2623/1.0784)	mem 34602MB
[2025-01-19 17:02:28 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][130/312]	eta 0:02:17 lr 0.000529	time 0.8209 (0.7560)	model_time 0.8207 (0.7449)	loss 3.0992 (2.7804)	grad_norm 1.7102 (2.1648/0.9126)	mem 34604MB
[2025-01-19 17:02:29 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][120/312]	eta 0:02:26 lr 0.000530	time 0.8117 (0.7613)	model_time 0.8115 (0.7487)	loss 2.8823 (2.7768)	grad_norm 5.4016 (2.2831/1.1134)	mem 34602MB
[2025-01-19 17:02:35 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][140/312]	eta 0:02:09 lr 0.000529	time 0.8167 (0.7556)	model_time 0.8165 (0.7453)	loss 2.9163 (2.7734)	grad_norm 3.5068 (2.2194/0.9464)	mem 34604MB
[2025-01-19 17:02:37 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][130/312]	eta 0:02:18 lr 0.000529	time 0.7207 (0.7605)	model_time 0.7206 (0.7488)	loss 2.7131 (2.7780)	grad_norm 3.0445 (2.2880/1.0989)	mem 34602MB
[2025-01-19 17:02:43 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][150/312]	eta 0:02:02 lr 0.000528	time 0.8008 (0.7559)	model_time 0.8006 (0.7463)	loss 3.3844 (2.7841)	grad_norm 1.6306 (2.2456/0.9444)	mem 34604MB
[2025-01-19 17:02:45 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][140/312]	eta 0:02:10 lr 0.000529	time 0.7423 (0.7610)	model_time 0.7418 (0.7501)	loss 3.0946 (2.7858)	grad_norm 2.0134 (2.2437/1.0822)	mem 34602MB
[2025-01-19 17:02:50 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][160/312]	eta 0:01:54 lr 0.000528	time 0.8036 (0.7561)	model_time 0.8034 (0.7471)	loss 3.1666 (2.7850)	grad_norm 2.2472 (2.2163/0.9246)	mem 34604MB
[2025-01-19 17:02:52 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][150/312]	eta 0:02:03 lr 0.000528	time 0.7349 (0.7606)	model_time 0.7347 (0.7504)	loss 2.8588 (2.7918)	grad_norm 1.0120 (2.2268/1.0625)	mem 34602MB
[2025-01-19 17:02:58 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][170/312]	eta 0:01:47 lr 0.000527	time 0.7176 (0.7576)	model_time 0.7175 (0.7491)	loss 2.9593 (2.7788)	grad_norm 1.7726 (2.1952/0.9076)	mem 34604MB
[2025-01-19 17:02:59 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][160/312]	eta 0:01:55 lr 0.000528	time 0.7188 (0.7591)	model_time 0.7185 (0.7495)	loss 3.0876 (2.8049)	grad_norm 2.3896 (2.2276/1.0340)	mem 34602MB
[2025-01-19 17:03:06 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][180/312]	eta 0:01:39 lr 0.000527	time 0.8065 (0.7571)	model_time 0.8061 (0.7491)	loss 2.6994 (2.7889)	grad_norm 1.7206 (2.1912/0.8877)	mem 34604MB
[2025-01-19 17:03:07 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][170/312]	eta 0:01:47 lr 0.000527	time 0.9707 (0.7602)	model_time 0.9705 (0.7511)	loss 2.0482 (2.7988)	grad_norm 2.6435 (2.2133/1.0134)	mem 34602MB
[2025-01-19 17:03:13 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][190/312]	eta 0:01:32 lr 0.000526	time 0.7188 (0.7563)	model_time 0.7184 (0.7486)	loss 2.5881 (2.7793)	grad_norm 2.9407 (2.1715/0.8798)	mem 34604MB
[2025-01-19 17:03:15 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][180/312]	eta 0:01:40 lr 0.000527	time 0.7948 (0.7587)	model_time 0.7943 (0.7501)	loss 3.1917 (2.7889)	grad_norm 1.9443 (2.2077/0.9980)	mem 34602MB
[2025-01-19 17:03:20 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][200/312]	eta 0:01:24 lr 0.000526	time 0.7205 (0.7551)	model_time 0.7203 (0.7478)	loss 3.0374 (2.7883)	grad_norm 2.3187 (2.1673/0.8641)	mem 34604MB
[2025-01-19 17:03:22 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][190/312]	eta 0:01:32 lr 0.000526	time 0.7980 (0.7586)	model_time 0.7978 (0.7504)	loss 3.5155 (2.7980)	grad_norm 1.3947 (2.1761/0.9939)	mem 34602MB
[2025-01-19 17:03:28 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][210/312]	eta 0:01:16 lr 0.000526	time 0.7291 (0.7542)	model_time 0.7289 (0.7472)	loss 3.3178 (2.7939)	grad_norm 2.1202 (2.1464/0.8580)	mem 34604MB
[2025-01-19 17:03:29 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][200/312]	eta 0:01:24 lr 0.000526	time 0.7184 (0.7574)	model_time 0.7180 (0.7496)	loss 2.5271 (2.8047)	grad_norm 3.3400 (2.1592/0.9844)	mem 34602MB
[2025-01-19 17:03:35 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][220/312]	eta 0:01:09 lr 0.000525	time 0.7220 (0.7528)	model_time 0.7218 (0.7461)	loss 2.1209 (2.7790)	grad_norm 3.1981 (2.1630/0.8484)	mem 34604MB
[2025-01-19 17:03:37 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][210/312]	eta 0:01:17 lr 0.000526	time 0.7248 (0.7558)	model_time 0.7244 (0.7484)	loss 3.1344 (2.8131)	grad_norm 4.1684 (2.1756/0.9758)	mem 34602MB
[2025-01-19 17:03:42 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][230/312]	eta 0:01:01 lr 0.000525	time 0.7205 (0.7518)	model_time 0.7200 (0.7454)	loss 2.7881 (2.7784)	grad_norm 1.7445 (2.1588/0.8593)	mem 34604MB
[2025-01-19 17:03:44 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][220/312]	eta 0:01:09 lr 0.000525	time 0.7107 (0.7558)	model_time 0.7102 (0.7487)	loss 3.4124 (2.8176)	grad_norm 2.9695 (2.1975/0.9742)	mem 34602MB
[2025-01-19 17:03:50 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][240/312]	eta 0:00:54 lr 0.000524	time 0.7162 (0.7507)	model_time 0.7160 (0.7446)	loss 3.0203 (2.7828)	grad_norm 1.6129 (2.1526/0.8511)	mem 34604MB
[2025-01-19 17:03:52 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][230/312]	eta 0:01:01 lr 0.000525	time 0.8045 (0.7549)	model_time 0.8043 (0.7482)	loss 3.2331 (2.8172)	grad_norm 2.6052 (2.1947/0.9659)	mem 34602MB
[2025-01-19 17:03:57 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][250/312]	eta 0:00:46 lr 0.000524	time 0.8115 (0.7500)	model_time 0.8112 (0.7441)	loss 2.3267 (2.7859)	grad_norm 2.7162 (2.1790/0.8674)	mem 34604MB
[2025-01-19 17:03:59 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][240/312]	eta 0:00:54 lr 0.000524	time 0.7987 (0.7544)	model_time 0.7985 (0.7479)	loss 3.0146 (2.8196)	grad_norm 1.9140 (2.1827/0.9514)	mem 34602MB
[2025-01-19 17:04:05 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][260/312]	eta 0:00:39 lr 0.000523	time 0.8165 (0.7507)	model_time 0.8161 (0.7450)	loss 3.0613 (2.7800)	grad_norm 4.7877 (2.1758/0.8787)	mem 34604MB
[2025-01-19 17:04:07 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][250/312]	eta 0:00:46 lr 0.000524	time 0.7239 (0.7542)	model_time 0.7234 (0.7479)	loss 3.2915 (2.8157)	grad_norm 3.0754 (2.1728/0.9471)	mem 34602MB
[2025-01-19 17:04:12 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][270/312]	eta 0:00:31 lr 0.000523	time 0.8086 (0.7511)	model_time 0.8084 (0.7455)	loss 3.1033 (2.7850)	grad_norm 1.6004 (2.1601/0.8747)	mem 34604MB
[2025-01-19 17:04:14 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][260/312]	eta 0:00:39 lr 0.000523	time 0.7974 (0.7549)	model_time 0.7969 (0.7489)	loss 3.2873 (2.8093)	grad_norm 1.3500 (2.1564/0.9377)	mem 34602MB
[2025-01-19 17:04:20 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][280/312]	eta 0:00:24 lr 0.000523	time 0.8129 (0.7510)	model_time 0.8125 (0.7456)	loss 2.3453 (2.7842)	grad_norm 2.2935 (2.1568/0.8659)	mem 34604MB
[2025-01-19 17:04:22 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][270/312]	eta 0:00:31 lr 0.000523	time 0.7237 (0.7550)	model_time 0.7235 (0.7491)	loss 2.2919 (2.8075)	grad_norm 1.2340 (2.1342/0.9337)	mem 34602MB
[2025-01-19 17:04:27 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][290/312]	eta 0:00:16 lr 0.000522	time 0.7229 (0.7513)	model_time 0.7224 (0.7461)	loss 2.4653 (2.7811)	grad_norm 1.2856 (2.1677/0.8749)	mem 34604MB
[2025-01-19 17:04:29 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][280/312]	eta 0:00:24 lr 0.000523	time 0.7270 (0.7542)	model_time 0.7265 (0.7486)	loss 2.6074 (2.8065)	grad_norm 1.6346 (2.1119/0.9276)	mem 34602MB
[2025-01-19 17:04:35 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][300/312]	eta 0:00:09 lr 0.000522	time 0.7212 (0.7511)	model_time 0.7211 (0.7461)	loss 2.5808 (2.7767)	grad_norm 1.1501 (2.1705/0.8733)	mem 34604MB
[2025-01-19 17:04:37 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][290/312]	eta 0:00:16 lr 0.000522	time 0.8618 (0.7550)	model_time 0.8615 (0.7495)	loss 2.3668 (2.8036)	grad_norm 3.5116 (2.1197/0.9328)	mem 34602MB
[2025-01-19 17:04:42 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][310/312]	eta 0:00:01 lr 0.000521	time 0.7146 (0.7511)	model_time 0.7145 (0.7462)	loss 2.3489 (2.7748)	grad_norm 1.9021 (2.1719/0.8899)	mem 34604MB
[2025-01-19 17:04:43 internimage_b_1k_224] (main.py 519): INFO EPOCH 231 training takes 0:03:54
[2025-01-19 17:04:43 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_231.pth saving......
[2025-01-19 17:04:44 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][300/312]	eta 0:00:09 lr 0.000522	time 0.7151 (0.7539)	model_time 0.7150 (0.7486)	loss 3.3732 (2.8009)	grad_norm 3.4957 (2.1359/0.9347)	mem 34602MB
[2025-01-19 17:04:46 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_231.pth saved !!!
[2025-01-19 17:04:52 internimage_b_1k_224] (main.py 510): INFO Train: [231/300][310/312]	eta 0:00:01 lr 0.000521	time 0.7944 (0.7538)	model_time 0.7943 (0.7486)	loss 2.9873 (2.7964)	grad_norm 1.3984 (2.1554/0.9405)	mem 34602MB
[2025-01-19 17:04:52 internimage_b_1k_224] (main.py 519): INFO EPOCH 231 training takes 0:03:55
[2025-01-19 17:04:52 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_231.pth saving......
[2025-01-19 17:04:54 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.146 (8.146)	Loss 0.6978 (0.6978)	Acc@1 86.133 (86.133)	Acc@5 97.900 (97.900)	Mem 34604MB
[2025-01-19 17:04:56 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_231.pth saved !!!
[2025-01-19 17:05:01 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.342)	Loss 0.9194 (0.7982)	Acc@1 80.225 (83.796)	Acc@5 95.801 (96.773)	Mem 34604MB
[2025-01-19 17:05:01 internimage_b_1k_224] (main.py 575): INFO [Epoch:231] * Acc@1 83.607 Acc@5 96.767
[2025-01-19 17:05:01 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.6%
[2025-01-19 17:05:01 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.66%
[2025-01-19 17:05:11 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.075 (15.075)	Loss 0.7082 (0.7082)	Acc@1 86.084 (86.084)	Acc@5 97.876 (97.876)	Mem 34602MB
[2025-01-19 17:05:18 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.121 (17.121)	Loss 0.7112 (0.7112)	Acc@1 86.230 (86.230)	Acc@5 98.218 (98.218)	Mem 34604MB
[2025-01-19 17:05:19 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.120)	Loss 0.9070 (0.7980)	Acc@1 79.932 (83.722)	Acc@5 95.654 (96.784)	Mem 34602MB
[2025-01-19 17:05:19 internimage_b_1k_224] (main.py 575): INFO [Epoch:231] * Acc@1 83.561 Acc@5 96.805
[2025-01-19 17:05:19 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.6%
[2025-01-19 17:05:19 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 17:05:22 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 17:05:22 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.56%
[2025-01-19 17:05:26 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (2.273)	Loss 0.9348 (0.8104)	Acc@1 80.103 (83.916)	Acc@5 95.630 (96.835)	Mem 34604MB
[2025-01-19 17:05:26 internimage_b_1k_224] (main.py 575): INFO [Epoch:231] * Acc@1 83.761 Acc@5 96.869
[2025-01-19 17:05:26 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.8%
[2025-01-19 17:05:26 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:05:31 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:05:31 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.76%
[2025-01-19 17:05:32 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.951 (9.951)	Loss 0.7201 (0.7201)	Acc@1 85.913 (85.913)	Acc@5 98.169 (98.169)	Mem 34602MB
[2025-01-19 17:05:33 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][0/312]	eta 0:11:10 lr 0.000521	time 2.1496 (2.1496)	model_time 0.7338 (0.7338)	loss 3.3008 (3.3008)	grad_norm 3.1184 (3.1184/0.0000)	mem 34604MB
[2025-01-19 17:05:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.231)	Loss 0.9356 (0.8110)	Acc@1 79.907 (83.889)	Acc@5 95.825 (96.888)	Mem 34602MB
[2025-01-19 17:05:36 internimage_b_1k_224] (main.py 575): INFO [Epoch:231] * Acc@1 83.711 Acc@5 96.939
[2025-01-19 17:05:36 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.7%
[2025-01-19 17:05:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:05:40 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:05:40 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.71%
[2025-01-19 17:05:40 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][10/312]	eta 0:04:18 lr 0.000521	time 0.7150 (0.8560)	model_time 0.7147 (0.7271)	loss 2.6905 (2.8718)	grad_norm 1.9164 (2.2903/0.7408)	mem 34604MB
[2025-01-19 17:05:42 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][0/312]	eta 0:11:17 lr 0.000521	time 2.1711 (2.1711)	model_time 0.7569 (0.7569)	loss 2.8967 (2.8967)	grad_norm 1.2397 (1.2397/0.0000)	mem 34602MB
[2025-01-19 17:05:47 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][20/312]	eta 0:03:53 lr 0.000520	time 0.7161 (0.7990)	model_time 0.7157 (0.7313)	loss 2.8692 (2.8228)	grad_norm 1.6271 (2.1213/0.7534)	mem 34604MB
[2025-01-19 17:05:49 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][10/312]	eta 0:04:26 lr 0.000521	time 0.7164 (0.8810)	model_time 0.7162 (0.7521)	loss 2.2222 (2.9736)	grad_norm 2.5237 (1.9129/0.5220)	mem 34602MB
[2025-01-19 17:05:55 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][30/312]	eta 0:03:39 lr 0.000520	time 0.7176 (0.7767)	model_time 0.7175 (0.7307)	loss 3.2603 (2.8136)	grad_norm 1.2457 (1.9772/0.6969)	mem 34604MB
[2025-01-19 17:05:57 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][20/312]	eta 0:03:57 lr 0.000520	time 0.7165 (0.8130)	model_time 0.7160 (0.7453)	loss 2.8355 (2.7588)	grad_norm 2.4046 (2.1234/0.9876)	mem 34602MB
[2025-01-19 17:06:02 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][40/312]	eta 0:03:27 lr 0.000519	time 0.7207 (0.7643)	model_time 0.7205 (0.7294)	loss 3.1955 (2.8371)	grad_norm 4.5829 (2.1376/0.7795)	mem 34604MB
[2025-01-19 17:06:04 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][30/312]	eta 0:03:43 lr 0.000520	time 0.7252 (0.7924)	model_time 0.7250 (0.7464)	loss 2.5153 (2.7988)	grad_norm 2.0185 (2.2486/1.0667)	mem 34602MB
[2025-01-19 17:06:09 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][50/312]	eta 0:03:18 lr 0.000519	time 0.7296 (0.7577)	model_time 0.7294 (0.7296)	loss 3.2044 (2.8195)	grad_norm 2.2245 (2.1221/0.7568)	mem 34604MB
[2025-01-19 17:06:12 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][40/312]	eta 0:03:31 lr 0.000519	time 0.7272 (0.7767)	model_time 0.7270 (0.7419)	loss 2.3368 (2.7411)	grad_norm 2.0943 (2.1896/1.0072)	mem 34602MB
[2025-01-19 17:06:16 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][60/312]	eta 0:03:09 lr 0.000519	time 0.7094 (0.7525)	model_time 0.7092 (0.7289)	loss 3.1792 (2.8264)	grad_norm 1.8633 (2.2073/0.8760)	mem 34604MB
[2025-01-19 17:06:19 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][50/312]	eta 0:03:22 lr 0.000519	time 0.7248 (0.7726)	model_time 0.7246 (0.7445)	loss 2.8903 (2.7304)	grad_norm 1.2160 (2.1086/0.9705)	mem 34602MB
[2025-01-19 17:06:24 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][70/312]	eta 0:03:02 lr 0.000518	time 0.7221 (0.7555)	model_time 0.7217 (0.7352)	loss 3.2333 (2.8196)	grad_norm 1.7472 (2.1973/0.8358)	mem 34604MB
[2025-01-19 17:06:27 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][60/312]	eta 0:03:14 lr 0.000519	time 0.8177 (0.7705)	model_time 0.8175 (0.7470)	loss 3.0953 (2.7137)	grad_norm 2.9675 (2.0689/0.9228)	mem 34602MB
[2025-01-19 17:06:32 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][80/312]	eta 0:02:55 lr 0.000518	time 0.7255 (0.7565)	model_time 0.7253 (0.7386)	loss 3.0475 (2.8325)	grad_norm 2.2889 (2.1031/0.8354)	mem 34604MB
[2025-01-19 17:06:34 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][70/312]	eta 0:03:06 lr 0.000518	time 0.8001 (0.7713)	model_time 0.7996 (0.7510)	loss 2.9814 (2.7430)	grad_norm 1.2620 (2.0033/0.8841)	mem 34602MB
[2025-01-19 17:06:40 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][90/312]	eta 0:02:48 lr 0.000517	time 0.8159 (0.7582)	model_time 0.8157 (0.7422)	loss 3.3388 (2.8500)	grad_norm 4.4954 (2.1401/0.8640)	mem 34604MB
[2025-01-19 17:06:42 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][80/312]	eta 0:02:58 lr 0.000518	time 0.7403 (0.7687)	model_time 0.7401 (0.7509)	loss 2.5092 (2.7536)	grad_norm 1.7217 (2.0297/0.8900)	mem 34602MB
[2025-01-19 17:06:47 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][100/312]	eta 0:02:40 lr 0.000517	time 0.8077 (0.7589)	model_time 0.8075 (0.7445)	loss 2.4503 (2.8562)	grad_norm 4.9452 (2.2382/0.9469)	mem 34604MB
[2025-01-19 17:06:49 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][90/312]	eta 0:02:49 lr 0.000517	time 0.7157 (0.7651)	model_time 0.7156 (0.7492)	loss 2.0126 (2.7639)	grad_norm 5.6458 (2.1377/1.0126)	mem 34602MB
[2025-01-19 17:06:55 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][110/312]	eta 0:02:32 lr 0.000516	time 0.7163 (0.7571)	model_time 0.7158 (0.7440)	loss 3.0897 (2.8589)	grad_norm 1.5792 (2.2524/0.9796)	mem 34604MB
[2025-01-19 17:06:57 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][100/312]	eta 0:02:41 lr 0.000517	time 0.8067 (0.7637)	model_time 0.8063 (0.7494)	loss 2.7473 (2.7523)	grad_norm 2.0285 (2.2136/1.1135)	mem 34602MB
[2025-01-19 17:07:02 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][120/312]	eta 0:02:25 lr 0.000516	time 0.8166 (0.7576)	model_time 0.8165 (0.7455)	loss 3.0824 (2.8472)	grad_norm 4.3226 (2.2642/0.9759)	mem 34604MB
[2025-01-19 17:07:04 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][110/312]	eta 0:02:33 lr 0.000516	time 0.7292 (0.7603)	model_time 0.7288 (0.7472)	loss 2.2917 (2.7440)	grad_norm 1.8081 (2.1862/1.0884)	mem 34602MB
[2025-01-19 17:07:10 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][130/312]	eta 0:02:17 lr 0.000516	time 0.7237 (0.7558)	model_time 0.7235 (0.7447)	loss 2.0715 (2.8288)	grad_norm 2.7948 (2.3498/1.0499)	mem 34604MB
[2025-01-19 17:07:12 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][120/312]	eta 0:02:25 lr 0.000516	time 0.7160 (0.7599)	model_time 0.7158 (0.7478)	loss 3.1716 (2.7568)	grad_norm 1.2477 (2.1567/1.0562)	mem 34602MB
[2025-01-19 17:07:17 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][140/312]	eta 0:02:09 lr 0.000515	time 0.7437 (0.7542)	model_time 0.7436 (0.7438)	loss 2.7720 (2.8178)	grad_norm 2.7616 (2.3721/1.0434)	mem 34604MB
[2025-01-19 17:07:19 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][130/312]	eta 0:02:18 lr 0.000516	time 0.7061 (0.7601)	model_time 0.7057 (0.7489)	loss 2.2944 (2.7295)	grad_norm 1.2617 (2.1106/1.0353)	mem 34602MB
[2025-01-19 17:07:24 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][150/312]	eta 0:02:01 lr 0.000515	time 0.7309 (0.7527)	model_time 0.7307 (0.7430)	loss 3.1437 (2.8158)	grad_norm 2.0507 (2.3745/1.0305)	mem 34604MB
[2025-01-19 17:07:27 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][140/312]	eta 0:02:10 lr 0.000515	time 0.7161 (0.7586)	model_time 0.7160 (0.7482)	loss 2.9358 (2.7343)	grad_norm 2.9195 (2.1155/1.0137)	mem 34602MB
[2025-01-19 17:07:32 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][160/312]	eta 0:01:54 lr 0.000514	time 0.7200 (0.7512)	model_time 0.7198 (0.7421)	loss 2.5104 (2.8203)	grad_norm 1.9734 (2.3263/1.0182)	mem 34604MB
[2025-01-19 17:07:34 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][150/312]	eta 0:02:02 lr 0.000515	time 0.7334 (0.7579)	model_time 0.7332 (0.7482)	loss 2.8936 (2.7183)	grad_norm 1.4461 (2.1282/1.0460)	mem 34602MB
[2025-01-19 17:07:39 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][170/312]	eta 0:01:46 lr 0.000514	time 0.7263 (0.7498)	model_time 0.7258 (0.7412)	loss 2.0702 (2.8104)	grad_norm 1.3831 (2.2837/1.0098)	mem 34604MB
[2025-01-19 17:07:41 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][160/312]	eta 0:01:54 lr 0.000514	time 0.7199 (0.7560)	model_time 0.7197 (0.7468)	loss 2.2495 (2.7288)	grad_norm 1.1436 (2.1115/1.0259)	mem 34602MB
[2025-01-19 17:07:46 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][180/312]	eta 0:01:38 lr 0.000513	time 0.7243 (0.7488)	model_time 0.7242 (0.7406)	loss 3.6720 (2.8125)	grad_norm 1.1218 (2.2480/1.0023)	mem 34604MB
[2025-01-19 17:07:49 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][170/312]	eta 0:01:47 lr 0.000514	time 0.7320 (0.7559)	model_time 0.7316 (0.7473)	loss 2.0575 (2.7336)	grad_norm 1.9735 (2.1062/1.0080)	mem 34602MB
[2025-01-19 17:07:54 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][190/312]	eta 0:01:31 lr 0.000513	time 0.7143 (0.7494)	model_time 0.7138 (0.7416)	loss 2.4855 (2.8027)	grad_norm 1.6004 (2.2079/0.9931)	mem 34604MB
[2025-01-19 17:07:56 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][180/312]	eta 0:01:39 lr 0.000513	time 0.8139 (0.7557)	model_time 0.8137 (0.7476)	loss 2.2655 (2.7227)	grad_norm 1.2400 (2.0922/0.9956)	mem 34602MB
[2025-01-19 17:08:01 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][200/312]	eta 0:01:23 lr 0.000512	time 0.7284 (0.7493)	model_time 0.7283 (0.7419)	loss 3.1103 (2.8097)	grad_norm 1.2367 (2.1988/0.9794)	mem 34604MB
[2025-01-19 17:08:04 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][190/312]	eta 0:01:32 lr 0.000513	time 0.7180 (0.7565)	model_time 0.7175 (0.7487)	loss 3.2228 (2.7237)	grad_norm 2.2950 (2.0891/0.9761)	mem 34602MB
[2025-01-19 17:08:09 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][210/312]	eta 0:01:16 lr 0.000512	time 0.8193 (0.7504)	model_time 0.8188 (0.7433)	loss 2.7617 (2.8127)	grad_norm 1.9846 (2.1774/0.9649)	mem 34604MB
[2025-01-19 17:08:12 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][200/312]	eta 0:01:24 lr 0.000512	time 0.8202 (0.7567)	model_time 0.8198 (0.7493)	loss 2.8861 (2.7240)	grad_norm 2.6860 (2.0941/0.9762)	mem 34602MB
[2025-01-19 17:08:17 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][220/312]	eta 0:01:09 lr 0.000512	time 0.8229 (0.7514)	model_time 0.8225 (0.7447)	loss 2.4707 (2.8067)	grad_norm 1.5649 (2.1588/0.9515)	mem 34604MB
[2025-01-19 17:08:19 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][210/312]	eta 0:01:17 lr 0.000512	time 0.7158 (0.7560)	model_time 0.7155 (0.7490)	loss 3.0812 (2.7273)	grad_norm 1.7302 (2.0986/0.9684)	mem 34602MB
[2025-01-19 17:08:24 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][230/312]	eta 0:01:01 lr 0.000511	time 0.7448 (0.7512)	model_time 0.7446 (0.7448)	loss 3.4012 (2.8096)	grad_norm 2.6623 (2.1808/0.9612)	mem 34604MB
[2025-01-19 17:08:27 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][220/312]	eta 0:01:09 lr 0.000512	time 0.8188 (0.7561)	model_time 0.8184 (0.7493)	loss 2.6630 (2.7185)	grad_norm 1.5142 (2.0696/0.9578)	mem 34602MB
[2025-01-19 17:08:32 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][240/312]	eta 0:00:54 lr 0.000511	time 0.8091 (0.7519)	model_time 0.8090 (0.7457)	loss 3.1345 (2.8125)	grad_norm 0.8361 (2.1702/0.9713)	mem 34604MB
[2025-01-19 17:08:34 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][230/312]	eta 0:01:01 lr 0.000511	time 0.7274 (0.7553)	model_time 0.7272 (0.7488)	loss 1.8107 (2.7171)	grad_norm 1.5844 (2.0763/0.9459)	mem 34602MB
[2025-01-19 17:08:39 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][250/312]	eta 0:00:46 lr 0.000510	time 0.7159 (0.7510)	model_time 0.7158 (0.7450)	loss 2.0382 (2.8060)	grad_norm 2.0195 (2.1813/0.9622)	mem 34604MB
[2025-01-19 17:08:42 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][240/312]	eta 0:00:54 lr 0.000511	time 0.7217 (0.7552)	model_time 0.7213 (0.7490)	loss 3.1269 (2.7171)	grad_norm 2.6439 (2.0851/0.9418)	mem 34602MB
[2025-01-19 17:08:47 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][260/312]	eta 0:00:39 lr 0.000510	time 0.7255 (0.7508)	model_time 0.7250 (0.7450)	loss 2.3222 (2.7986)	grad_norm 2.1102 (2.1683/0.9488)	mem 34604MB
[2025-01-19 17:08:49 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][250/312]	eta 0:00:46 lr 0.000510	time 0.7066 (0.7553)	model_time 0.7064 (0.7492)	loss 3.0642 (2.7251)	grad_norm 1.9400 (2.1009/0.9560)	mem 34602MB
[2025-01-19 17:08:54 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][270/312]	eta 0:00:31 lr 0.000509	time 0.7240 (0.7500)	model_time 0.7235 (0.7444)	loss 2.3070 (2.8021)	grad_norm 0.9940 (2.1546/0.9446)	mem 34604MB
[2025-01-19 17:08:57 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][260/312]	eta 0:00:39 lr 0.000510	time 0.7150 (0.7545)	model_time 0.7145 (0.7487)	loss 2.9285 (2.7350)	grad_norm 1.1829 (2.1159/0.9597)	mem 34602MB
[2025-01-19 17:09:01 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][280/312]	eta 0:00:23 lr 0.000509	time 0.7330 (0.7495)	model_time 0.7326 (0.7441)	loss 2.9505 (2.8050)	grad_norm 1.6364 (2.1553/0.9360)	mem 34604MB
[2025-01-19 17:09:04 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][270/312]	eta 0:00:31 lr 0.000509	time 0.7343 (0.7541)	model_time 0.7342 (0.7485)	loss 3.1943 (2.7386)	grad_norm 1.5654 (2.1524/0.9873)	mem 34602MB
[2025-01-19 17:09:08 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][290/312]	eta 0:00:16 lr 0.000509	time 0.7666 (0.7488)	model_time 0.7662 (0.7436)	loss 3.5621 (2.8073)	grad_norm 2.8408 (2.1551/0.9243)	mem 34604MB
[2025-01-19 17:09:11 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][280/312]	eta 0:00:24 lr 0.000509	time 0.7277 (0.7531)	model_time 0.7275 (0.7477)	loss 3.0678 (2.7443)	grad_norm 1.2061 (2.1822/1.0142)	mem 34602MB
[2025-01-19 17:09:16 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][300/312]	eta 0:00:08 lr 0.000508	time 0.7160 (0.7481)	model_time 0.7159 (0.7430)	loss 3.1566 (2.8021)	grad_norm 2.3919 (2.1381/0.9168)	mem 34604MB
[2025-01-19 17:09:19 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][290/312]	eta 0:00:16 lr 0.000509	time 0.8145 (0.7529)	model_time 0.8140 (0.7476)	loss 3.1582 (2.7373)	grad_norm 2.7886 (2.1901/1.0081)	mem 34602MB
[2025-01-19 17:09:23 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][310/312]	eta 0:00:01 lr 0.000508	time 0.8067 (0.7479)	model_time 0.8066 (0.7430)	loss 3.3952 (2.8045)	grad_norm 1.5409 (2.1265/0.9206)	mem 34604MB
[2025-01-19 17:09:24 internimage_b_1k_224] (main.py 519): INFO EPOCH 232 training takes 0:03:53
[2025-01-19 17:09:24 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_232.pth saving......
[2025-01-19 17:09:26 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][300/312]	eta 0:00:09 lr 0.000508	time 0.7144 (0.7527)	model_time 0.7143 (0.7477)	loss 2.3306 (2.7413)	grad_norm 2.7800 (2.1787/0.9992)	mem 34602MB
[2025-01-19 17:09:27 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_232.pth saved !!!
[2025-01-19 17:09:34 internimage_b_1k_224] (main.py 510): INFO Train: [232/300][310/312]	eta 0:00:01 lr 0.000508	time 0.8227 (0.7531)	model_time 0.8226 (0.7481)	loss 2.9940 (2.7364)	grad_norm 1.5330 (2.1892/1.0009)	mem 34602MB
[2025-01-19 17:09:35 internimage_b_1k_224] (main.py 519): INFO EPOCH 232 training takes 0:03:54
[2025-01-19 17:09:35 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_232.pth saving......
[2025-01-19 17:09:35 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.701 (7.701)	Loss 0.7055 (0.7055)	Acc@1 86.011 (86.011)	Acc@5 97.681 (97.681)	Mem 34604MB
[2025-01-19 17:09:38 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_232.pth saved !!!
[2025-01-19 17:09:41 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.292)	Loss 0.9017 (0.7995)	Acc@1 80.518 (83.893)	Acc@5 95.825 (96.820)	Mem 34604MB
[2025-01-19 17:09:42 internimage_b_1k_224] (main.py 575): INFO [Epoch:232] * Acc@1 83.693 Acc@5 96.831
[2025-01-19 17:09:42 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.7%
[2025-01-19 17:09:42 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 17:09:45 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 17:09:45 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.69%
[2025-01-19 17:09:53 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.477 (15.477)	Loss 0.7204 (0.7204)	Acc@1 85.938 (85.938)	Acc@5 97.729 (97.729)	Mem 34602MB
[2025-01-19 17:10:01 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.623 (15.623)	Loss 0.7112 (0.7112)	Acc@1 86.206 (86.206)	Acc@5 98.218 (98.218)	Mem 34604MB
[2025-01-19 17:10:01 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.104)	Loss 0.9210 (0.8035)	Acc@1 80.640 (83.975)	Acc@5 95.557 (96.742)	Mem 34602MB
[2025-01-19 17:10:01 internimage_b_1k_224] (main.py 575): INFO [Epoch:232] * Acc@1 83.791 Acc@5 96.739
[2025-01-19 17:10:01 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.8%
[2025-01-19 17:10:01 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 17:10:04 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 17:10:04 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.79%
[2025-01-19 17:10:08 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.066)	Loss 0.9343 (0.8100)	Acc@1 80.151 (83.940)	Acc@5 95.630 (96.839)	Mem 34604MB
[2025-01-19 17:10:08 internimage_b_1k_224] (main.py 575): INFO [Epoch:232] * Acc@1 83.781 Acc@5 96.871
[2025-01-19 17:10:08 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.8%
[2025-01-19 17:10:08 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:10:12 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:10:12 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.78%
[2025-01-19 17:10:14 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.795 (9.795)	Loss 0.7202 (0.7202)	Acc@1 85.986 (85.986)	Acc@5 98.193 (98.193)	Mem 34602MB
[2025-01-19 17:10:14 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][0/312]	eta 0:12:11 lr 0.000508	time 2.3438 (2.3438)	model_time 0.7414 (0.7414)	loss 2.1724 (2.1724)	grad_norm 1.6339 (1.6339/0.0000)	mem 34604MB
[2025-01-19 17:10:18 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.246)	Loss 0.9351 (0.8107)	Acc@1 79.932 (83.911)	Acc@5 95.874 (96.899)	Mem 34602MB
[2025-01-19 17:10:18 internimage_b_1k_224] (main.py 575): INFO [Epoch:232] * Acc@1 83.733 Acc@5 96.945
[2025-01-19 17:10:18 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.7%
[2025-01-19 17:10:18 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:10:22 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][10/312]	eta 0:04:30 lr 0.000507	time 0.7616 (0.8956)	model_time 0.7615 (0.7496)	loss 3.4193 (2.9912)	grad_norm 1.1191 (1.8553/0.6267)	mem 34604MB
[2025-01-19 17:10:22 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:10:22 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.73%
[2025-01-19 17:10:24 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][0/312]	eta 0:12:17 lr 0.000508	time 2.3637 (2.3637)	model_time 0.7452 (0.7452)	loss 3.2323 (3.2323)	grad_norm 1.7091 (1.7091/0.0000)	mem 34602MB
[2025-01-19 17:10:30 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][20/312]	eta 0:04:05 lr 0.000507	time 0.8345 (0.8410)	model_time 0.8341 (0.7643)	loss 2.7102 (2.7710)	grad_norm 1.6716 (1.8046/0.6387)	mem 34604MB
[2025-01-19 17:10:32 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][10/312]	eta 0:04:30 lr 0.000507	time 0.7313 (0.8941)	model_time 0.7308 (0.7467)	loss 3.0965 (3.0920)	grad_norm 2.3045 (2.5624/1.1213)	mem 34602MB
[2025-01-19 17:10:37 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][30/312]	eta 0:03:50 lr 0.000506	time 0.7199 (0.8163)	model_time 0.7197 (0.7643)	loss 2.8624 (2.7861)	grad_norm 2.4283 (1.9948/0.7659)	mem 34604MB
[2025-01-19 17:10:39 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][20/312]	eta 0:04:00 lr 0.000507	time 0.7315 (0.8234)	model_time 0.7313 (0.7461)	loss 3.4977 (2.9993)	grad_norm 4.1778 (2.4851/0.9589)	mem 34602MB
[2025-01-19 17:10:45 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][40/312]	eta 0:03:37 lr 0.000506	time 0.7355 (0.7993)	model_time 0.7351 (0.7599)	loss 2.6004 (2.7603)	grad_norm 1.8876 (2.0413/0.8023)	mem 34604MB
[2025-01-19 17:10:47 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][30/312]	eta 0:03:47 lr 0.000506	time 0.7137 (0.8069)	model_time 0.7136 (0.7544)	loss 2.2703 (2.9321)	grad_norm 1.3316 (2.3251/0.9435)	mem 34602MB
[2025-01-19 17:10:52 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][50/312]	eta 0:03:27 lr 0.000506	time 0.7446 (0.7927)	model_time 0.7442 (0.7609)	loss 3.0596 (2.7715)	grad_norm 1.1644 (2.0184/0.7925)	mem 34604MB
[2025-01-19 17:10:54 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][40/312]	eta 0:03:34 lr 0.000506	time 0.7276 (0.7884)	model_time 0.7274 (0.7486)	loss 1.9789 (2.9105)	grad_norm 2.4534 (2.3382/0.9705)	mem 34602MB
[2025-01-19 17:11:00 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][60/312]	eta 0:03:17 lr 0.000505	time 0.7225 (0.7832)	model_time 0.7221 (0.7566)	loss 3.2975 (2.7429)	grad_norm 3.1779 (2.0240/0.8212)	mem 34604MB
[2025-01-19 17:11:02 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][50/312]	eta 0:03:25 lr 0.000506	time 0.8009 (0.7826)	model_time 0.8007 (0.7506)	loss 2.1232 (2.8918)	grad_norm 0.9622 (2.5063/1.1390)	mem 34602MB
[2025-01-19 17:11:07 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][70/312]	eta 0:03:07 lr 0.000505	time 0.7244 (0.7762)	model_time 0.7239 (0.7533)	loss 3.0273 (2.7729)	grad_norm 3.1962 (2.0773/0.8734)	mem 34604MB
[2025-01-19 17:11:09 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][60/312]	eta 0:03:15 lr 0.000505	time 0.7153 (0.7758)	model_time 0.7150 (0.7489)	loss 3.3390 (2.8897)	grad_norm 2.3507 (2.4930/1.0866)	mem 34602MB
[2025-01-19 17:11:14 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][80/312]	eta 0:02:58 lr 0.000504	time 0.7212 (0.7698)	model_time 0.7208 (0.7496)	loss 3.1303 (2.7645)	grad_norm 1.3906 (2.0599/0.8680)	mem 34604MB
[2025-01-19 17:11:17 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][70/312]	eta 0:03:06 lr 0.000505	time 0.8133 (0.7711)	model_time 0.8130 (0.7480)	loss 3.4100 (2.8691)	grad_norm 1.6866 (2.4015/1.0634)	mem 34602MB
[2025-01-19 17:11:22 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][90/312]	eta 0:02:49 lr 0.000504	time 0.7191 (0.7654)	model_time 0.7187 (0.7474)	loss 3.1996 (2.7618)	grad_norm 1.3919 (2.0598/0.8418)	mem 34604MB
[2025-01-19 17:11:24 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][80/312]	eta 0:02:58 lr 0.000504	time 0.7451 (0.7680)	model_time 0.7447 (0.7476)	loss 3.0543 (2.8373)	grad_norm 2.2127 (2.3933/1.0399)	mem 34602MB
[2025-01-19 17:11:29 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][100/312]	eta 0:02:41 lr 0.000503	time 0.7209 (0.7618)	model_time 0.7207 (0.7456)	loss 2.6450 (2.7691)	grad_norm 1.2968 (2.1494/0.9327)	mem 34604MB
[2025-01-19 17:11:31 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][90/312]	eta 0:02:49 lr 0.000504	time 0.7186 (0.7632)	model_time 0.7184 (0.7450)	loss 1.8562 (2.8150)	grad_norm 1.5441 (2.3696/1.0188)	mem 34602MB
[2025-01-19 17:11:36 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][110/312]	eta 0:02:33 lr 0.000503	time 0.7196 (0.7582)	model_time 0.7194 (0.7434)	loss 2.6318 (2.7608)	grad_norm 1.9814 (2.1583/0.9220)	mem 34604MB
[2025-01-19 17:11:39 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][100/312]	eta 0:02:41 lr 0.000503	time 0.7146 (0.7616)	model_time 0.7142 (0.7451)	loss 2.9412 (2.8191)	grad_norm 1.6637 (2.3330/1.0044)	mem 34602MB
[2025-01-19 17:11:44 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][120/312]	eta 0:02:25 lr 0.000503	time 0.7226 (0.7585)	model_time 0.7225 (0.7449)	loss 2.8424 (2.7503)	grad_norm 0.9242 (2.1123/0.9072)	mem 34604MB
[2025-01-19 17:11:46 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][110/312]	eta 0:02:33 lr 0.000503	time 0.7274 (0.7598)	model_time 0.7272 (0.7449)	loss 2.1030 (2.8045)	grad_norm 3.1583 (2.3147/0.9876)	mem 34602MB
[2025-01-19 17:11:51 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][130/312]	eta 0:02:17 lr 0.000502	time 0.7395 (0.7581)	model_time 0.7393 (0.7455)	loss 2.6034 (2.7565)	grad_norm 2.4054 (2.1244/0.9243)	mem 34604MB
[2025-01-19 17:11:54 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][120/312]	eta 0:02:25 lr 0.000503	time 0.7171 (0.7601)	model_time 0.7169 (0.7464)	loss 2.4852 (2.8028)	grad_norm 2.1208 (2.3238/0.9697)	mem 34602MB
[2025-01-19 17:11:59 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][140/312]	eta 0:02:10 lr 0.000502	time 0.8340 (0.7604)	model_time 0.8336 (0.7487)	loss 2.7984 (2.7518)	grad_norm 2.7350 (2.1930/0.9429)	mem 34604MB
[2025-01-19 17:12:01 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][130/312]	eta 0:02:18 lr 0.000502	time 0.7314 (0.7587)	model_time 0.7309 (0.7459)	loss 3.1641 (2.8014)	grad_norm 1.8637 (2.3443/1.0034)	mem 34602MB
[2025-01-19 17:12:07 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][150/312]	eta 0:02:03 lr 0.000501	time 0.8021 (0.7607)	model_time 0.8018 (0.7498)	loss 3.0589 (2.7641)	grad_norm 1.8180 (2.1868/0.9322)	mem 34604MB
[2025-01-19 17:12:09 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][140/312]	eta 0:02:10 lr 0.000502	time 0.7200 (0.7576)	model_time 0.7195 (0.7457)	loss 2.7587 (2.8020)	grad_norm 1.9813 (2.2885/0.9972)	mem 34602MB
[2025-01-19 17:12:14 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][160/312]	eta 0:01:55 lr 0.000501	time 0.7168 (0.7606)	model_time 0.7164 (0.7503)	loss 1.8550 (2.7572)	grad_norm 1.4516 (2.1621/0.9221)	mem 34604MB
[2025-01-19 17:12:16 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][150/312]	eta 0:02:02 lr 0.000501	time 0.7327 (0.7569)	model_time 0.7325 (0.7457)	loss 3.1959 (2.8122)	grad_norm 0.9226 (2.2682/0.9855)	mem 34602MB
[2025-01-19 17:12:22 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][170/312]	eta 0:01:47 lr 0.000500	time 0.7212 (0.7600)	model_time 0.7207 (0.7503)	loss 3.0293 (2.7542)	grad_norm 1.9789 (2.1591/0.9100)	mem 34604MB
[2025-01-19 17:12:24 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][160/312]	eta 0:01:54 lr 0.000501	time 0.7182 (0.7553)	model_time 0.7178 (0.7449)	loss 2.5172 (2.8046)	grad_norm 0.9388 (2.2373/0.9780)	mem 34602MB
[2025-01-19 17:12:29 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][180/312]	eta 0:01:40 lr 0.000500	time 0.7312 (0.7589)	model_time 0.7311 (0.7497)	loss 3.5518 (2.7671)	grad_norm 1.2113 (2.1370/0.8959)	mem 34604MB
[2025-01-19 17:12:31 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][170/312]	eta 0:01:47 lr 0.000500	time 0.8075 (0.7556)	model_time 0.8070 (0.7457)	loss 2.9769 (2.8064)	grad_norm 1.4443 (2.2487/0.9744)	mem 34602MB
[2025-01-19 17:12:37 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][190/312]	eta 0:01:32 lr 0.000500	time 0.7188 (0.7577)	model_time 0.7183 (0.7489)	loss 2.8837 (2.7719)	grad_norm 1.3932 (2.1426/0.9017)	mem 34604MB
[2025-01-19 17:12:39 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][180/312]	eta 0:01:39 lr 0.000500	time 0.7252 (0.7547)	model_time 0.7251 (0.7454)	loss 3.3926 (2.8099)	grad_norm 1.4510 (2.2347/0.9549)	mem 34602MB
[2025-01-19 17:12:44 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][200/312]	eta 0:01:24 lr 0.000499	time 0.7194 (0.7561)	model_time 0.7193 (0.7478)	loss 3.0631 (2.7760)	grad_norm 1.4668 (2.1293/0.8916)	mem 34604MB
[2025-01-19 17:12:46 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][190/312]	eta 0:01:31 lr 0.000500	time 0.7167 (0.7538)	model_time 0.7162 (0.7449)	loss 2.4111 (2.8178)	grad_norm 4.5199 (2.2397/0.9535)	mem 34602MB
[2025-01-19 17:12:51 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][210/312]	eta 0:01:17 lr 0.000499	time 0.7660 (0.7549)	model_time 0.7656 (0.7470)	loss 3.1571 (2.7644)	grad_norm 1.8577 (2.1222/0.8872)	mem 34604MB
[2025-01-19 17:12:53 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][200/312]	eta 0:01:24 lr 0.000499	time 0.7233 (0.7537)	model_time 0.7228 (0.7452)	loss 3.0812 (2.8325)	grad_norm 1.5398 (2.2344/0.9403)	mem 34602MB
[2025-01-19 17:12:59 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][220/312]	eta 0:01:09 lr 0.000498	time 0.7202 (0.7536)	model_time 0.7197 (0.7460)	loss 3.0913 (2.7609)	grad_norm 1.5264 (2.1213/0.8788)	mem 34604MB
[2025-01-19 17:13:01 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][210/312]	eta 0:01:16 lr 0.000499	time 0.7238 (0.7523)	model_time 0.7237 (0.7442)	loss 1.9252 (2.8184)	grad_norm 4.3836 (2.2456/0.9507)	mem 34602MB
[2025-01-19 17:13:06 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][230/312]	eta 0:01:01 lr 0.000498	time 0.7172 (0.7525)	model_time 0.7170 (0.7452)	loss 3.2325 (2.7668)	grad_norm 2.3211 (2.1503/0.8836)	mem 34604MB
[2025-01-19 17:13:08 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][220/312]	eta 0:01:09 lr 0.000498	time 0.7137 (0.7520)	model_time 0.7136 (0.7443)	loss 3.4482 (2.8292)	grad_norm 1.2478 (2.2633/0.9613)	mem 34602MB
[2025-01-19 17:13:13 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][240/312]	eta 0:00:54 lr 0.000497	time 0.7234 (0.7523)	model_time 0.7232 (0.7453)	loss 2.9659 (2.7650)	grad_norm 1.1101 (2.1430/0.8855)	mem 34604MB
[2025-01-19 17:13:16 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][230/312]	eta 0:01:01 lr 0.000498	time 0.7233 (0.7518)	model_time 0.7228 (0.7444)	loss 3.0330 (2.8224)	grad_norm 2.5552 (2.2776/0.9515)	mem 34602MB
[2025-01-19 17:13:21 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][250/312]	eta 0:00:46 lr 0.000497	time 0.7212 (0.7524)	model_time 0.7207 (0.7456)	loss 2.1770 (2.7676)	grad_norm 2.7688 (2.1315/0.8799)	mem 34604MB
[2025-01-19 17:13:23 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][240/312]	eta 0:00:54 lr 0.000497	time 0.7193 (0.7525)	model_time 0.7188 (0.7454)	loss 2.7019 (2.8203)	grad_norm 2.5575 (2.2653/0.9401)	mem 34602MB
[2025-01-19 17:13:28 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][260/312]	eta 0:00:39 lr 0.000497	time 0.7336 (0.7526)	model_time 0.7331 (0.7461)	loss 2.7349 (2.7659)	grad_norm 1.7921 (2.1249/0.8714)	mem 34604MB
[2025-01-19 17:13:31 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][250/312]	eta 0:00:46 lr 0.000497	time 0.7168 (0.7525)	model_time 0.7166 (0.7456)	loss 2.0447 (2.8226)	grad_norm 2.3363 (2.2716/0.9377)	mem 34602MB
[2025-01-19 17:13:36 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][270/312]	eta 0:00:31 lr 0.000496	time 0.7886 (0.7539)	model_time 0.7884 (0.7476)	loss 2.8342 (2.7553)	grad_norm 1.3899 (2.1193/0.8706)	mem 34604MB
[2025-01-19 17:13:38 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][260/312]	eta 0:00:39 lr 0.000497	time 0.7542 (0.7521)	model_time 0.7541 (0.7455)	loss 3.3797 (2.8251)	grad_norm 2.4355 (2.2450/0.9340)	mem 34602MB
[2025-01-19 17:13:44 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][280/312]	eta 0:00:24 lr 0.000496	time 0.7138 (0.7542)	model_time 0.7134 (0.7481)	loss 2.0997 (2.7630)	grad_norm 1.7992 (2.1268/0.8722)	mem 34604MB
[2025-01-19 17:13:46 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][270/312]	eta 0:00:31 lr 0.000496	time 0.7259 (0.7520)	model_time 0.7257 (0.7456)	loss 3.1142 (2.8228)	grad_norm 1.1178 (2.2176/0.9293)	mem 34602MB
[2025-01-19 17:13:51 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][290/312]	eta 0:00:16 lr 0.000495	time 0.7242 (0.7539)	model_time 0.7238 (0.7481)	loss 3.0959 (2.7653)	grad_norm 1.4771 (2.1202/0.8669)	mem 34604MB
[2025-01-19 17:13:53 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][280/312]	eta 0:00:24 lr 0.000496	time 0.7276 (0.7514)	model_time 0.7275 (0.7452)	loss 3.5049 (2.8284)	grad_norm 1.2239 (2.2097/0.9287)	mem 34602MB
[2025-01-19 17:13:59 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][300/312]	eta 0:00:09 lr 0.000495	time 0.7160 (0.7536)	model_time 0.7158 (0.7479)	loss 2.3814 (2.7636)	grad_norm 0.9661 (2.1006/0.8643)	mem 34604MB
[2025-01-19 17:14:01 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][290/312]	eta 0:00:16 lr 0.000495	time 0.8006 (0.7515)	model_time 0.8004 (0.7456)	loss 2.7506 (2.8355)	grad_norm 1.0625 (2.2052/0.9253)	mem 34602MB
[2025-01-19 17:14:06 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][310/312]	eta 0:00:01 lr 0.000494	time 0.7137 (0.7528)	model_time 0.7135 (0.7473)	loss 1.9818 (2.7606)	grad_norm 2.1681 (2.0941/0.8651)	mem 34604MB
[2025-01-19 17:14:07 internimage_b_1k_224] (main.py 519): INFO EPOCH 233 training takes 0:03:54
[2025-01-19 17:14:07 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_233.pth saving......
[2025-01-19 17:14:08 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][300/312]	eta 0:00:09 lr 0.000495	time 0.7123 (0.7511)	model_time 0.7122 (0.7453)	loss 3.2349 (2.8397)	grad_norm 2.2201 (2.2201/0.9247)	mem 34602MB
[2025-01-19 17:14:10 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_233.pth saved !!!
[2025-01-19 17:14:15 internimage_b_1k_224] (main.py 510): INFO Train: [233/300][310/312]	eta 0:00:01 lr 0.000494	time 0.7173 (0.7505)	model_time 0.7172 (0.7449)	loss 3.0895 (2.8411)	grad_norm 1.4896 (2.1840/0.9095)	mem 34602MB
[2025-01-19 17:14:16 internimage_b_1k_224] (main.py 519): INFO EPOCH 233 training takes 0:03:54
[2025-01-19 17:14:16 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_233.pth saving......
[2025-01-19 17:14:18 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.274 (8.274)	Loss 0.6967 (0.6967)	Acc@1 85.742 (85.742)	Acc@5 97.998 (97.998)	Mem 34604MB
[2025-01-19 17:14:19 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_233.pth saved !!!
[2025-01-19 17:14:25 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.341)	Loss 0.9302 (0.7987)	Acc@1 79.858 (83.856)	Acc@5 95.605 (96.757)	Mem 34604MB
[2025-01-19 17:14:25 internimage_b_1k_224] (main.py 575): INFO [Epoch:233] * Acc@1 83.681 Acc@5 96.785
[2025-01-19 17:14:25 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.7%
[2025-01-19 17:14:25 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.69%
[2025-01-19 17:14:35 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.420 (15.420)	Loss 0.7179 (0.7179)	Acc@1 85.938 (85.938)	Acc@5 97.729 (97.729)	Mem 34602MB
[2025-01-19 17:14:42 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.183 (2.083)	Loss 0.9356 (0.8049)	Acc@1 79.980 (83.813)	Acc@5 95.508 (96.744)	Mem 34602MB
[2025-01-19 17:14:42 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.111 (17.111)	Loss 0.7113 (0.7113)	Acc@1 86.230 (86.230)	Acc@5 98.169 (98.169)	Mem 34604MB
[2025-01-19 17:14:42 internimage_b_1k_224] (main.py 575): INFO [Epoch:233] * Acc@1 83.677 Acc@5 96.739
[2025-01-19 17:14:42 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.7%
[2025-01-19 17:14:42 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.79%
[2025-01-19 17:14:51 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (2.331)	Loss 0.9340 (0.8099)	Acc@1 80.176 (83.933)	Acc@5 95.581 (96.844)	Mem 34604MB
[2025-01-19 17:14:51 internimage_b_1k_224] (main.py 575): INFO [Epoch:233] * Acc@1 83.773 Acc@5 96.877
[2025-01-19 17:14:51 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.8%
[2025-01-19 17:14:51 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.78%
[2025-01-19 17:14:54 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][0/312]	eta 0:16:35 lr 0.000494	time 3.1904 (3.1904)	model_time 1.1818 (1.1818)	loss 2.6881 (2.6881)	grad_norm 1.2981 (1.2981/0.0000)	mem 34604MB
[2025-01-19 17:14:55 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 12.970 (12.970)	Loss 0.7205 (0.7205)	Acc@1 86.060 (86.060)	Acc@5 98.193 (98.193)	Mem 34602MB
[2025-01-19 17:15:00 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.593)	Loss 0.9347 (0.8106)	Acc@1 80.005 (83.958)	Acc@5 95.923 (96.908)	Mem 34602MB
[2025-01-19 17:15:00 internimage_b_1k_224] (main.py 575): INFO [Epoch:233] * Acc@1 83.781 Acc@5 96.955
[2025-01-19 17:15:00 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.8%
[2025-01-19 17:15:00 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:15:01 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][10/312]	eta 0:04:48 lr 0.000494	time 0.7289 (0.9569)	model_time 0.7288 (0.7740)	loss 3.1143 (2.7602)	grad_norm 3.8383 (2.4229/1.1981)	mem 34604MB
[2025-01-19 17:15:04 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:15:04 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.78%
[2025-01-19 17:15:06 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][0/312]	eta 0:10:52 lr 0.000494	time 2.0914 (2.0914)	model_time 0.7458 (0.7458)	loss 2.2214 (2.2214)	grad_norm 2.5302 (2.5302/0.0000)	mem 34602MB
[2025-01-19 17:15:09 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][20/312]	eta 0:04:08 lr 0.000494	time 0.7307 (0.8498)	model_time 0.7302 (0.7538)	loss 3.0881 (2.7349)	grad_norm 1.8405 (2.2205/1.0047)	mem 34604MB
[2025-01-19 17:15:13 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][10/312]	eta 0:04:21 lr 0.000494	time 0.8110 (0.8664)	model_time 0.8108 (0.7438)	loss 3.3598 (2.6281)	grad_norm 1.8909 (2.4794/0.7865)	mem 34602MB
[2025-01-19 17:15:16 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][30/312]	eta 0:03:48 lr 0.000493	time 0.7216 (0.8099)	model_time 0.7215 (0.7448)	loss 2.7148 (2.7416)	grad_norm 2.1174 (2.1836/0.9097)	mem 34604MB
[2025-01-19 17:15:21 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][20/312]	eta 0:03:55 lr 0.000494	time 0.7088 (0.8071)	model_time 0.7084 (0.7427)	loss 2.8312 (2.6949)	grad_norm 1.0257 (2.4233/0.9088)	mem 34602MB
[2025-01-19 17:15:23 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][40/312]	eta 0:03:35 lr 0.000493	time 0.7510 (0.7919)	model_time 0.7508 (0.7426)	loss 2.2968 (2.7456)	grad_norm 1.5669 (2.0302/0.8638)	mem 34604MB
[2025-01-19 17:15:28 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][30/312]	eta 0:03:42 lr 0.000493	time 0.7305 (0.7906)	model_time 0.7304 (0.7468)	loss 3.3672 (2.8029)	grad_norm 1.1170 (2.0589/0.9299)	mem 34602MB
[2025-01-19 17:15:31 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][50/312]	eta 0:03:25 lr 0.000492	time 0.7185 (0.7855)	model_time 0.7181 (0.7458)	loss 3.0828 (2.7285)	grad_norm 2.3066 (2.1152/0.8352)	mem 34604MB
[2025-01-19 17:15:36 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][40/312]	eta 0:03:32 lr 0.000493	time 0.7239 (0.7819)	model_time 0.7234 (0.7488)	loss 2.6960 (2.7700)	grad_norm 2.2418 (2.0385/0.8388)	mem 34602MB
[2025-01-19 17:15:39 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][60/312]	eta 0:03:17 lr 0.000492	time 0.8387 (0.7830)	model_time 0.8385 (0.7497)	loss 2.5457 (2.7501)	grad_norm 2.5990 (2.2225/0.8462)	mem 34604MB
[2025-01-19 17:15:43 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][50/312]	eta 0:03:24 lr 0.000492	time 0.8041 (0.7789)	model_time 0.8038 (0.7522)	loss 1.9418 (2.7223)	grad_norm 2.3463 (2.0470/0.7805)	mem 34602MB
[2025-01-19 17:15:46 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][70/312]	eta 0:03:08 lr 0.000491	time 0.8132 (0.7788)	model_time 0.8127 (0.7502)	loss 2.8015 (2.7727)	grad_norm 3.9401 (2.2178/0.8786)	mem 34604MB
[2025-01-19 17:15:51 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][60/312]	eta 0:03:15 lr 0.000492	time 0.7158 (0.7758)	model_time 0.7153 (0.7533)	loss 3.1949 (2.7808)	grad_norm 2.0160 (2.0115/0.7668)	mem 34602MB
[2025-01-19 17:15:54 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][80/312]	eta 0:03:00 lr 0.000491	time 0.7181 (0.7766)	model_time 0.7176 (0.7515)	loss 3.0815 (2.7738)	grad_norm 0.9415 (2.1950/0.8641)	mem 34604MB
[2025-01-19 17:15:58 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][70/312]	eta 0:03:06 lr 0.000491	time 0.7235 (0.7711)	model_time 0.7233 (0.7518)	loss 3.2349 (2.7964)	grad_norm 1.1150 (1.9462/0.7480)	mem 34602MB
[2025-01-19 17:16:01 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][90/312]	eta 0:02:51 lr 0.000491	time 0.7190 (0.7740)	model_time 0.7185 (0.7516)	loss 3.0013 (2.7600)	grad_norm 1.5729 (2.1540/0.8313)	mem 34604MB
[2025-01-19 17:16:06 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][80/312]	eta 0:02:58 lr 0.000491	time 0.7139 (0.7697)	model_time 0.7137 (0.7528)	loss 2.2325 (2.7992)	grad_norm 2.6979 (1.9453/0.7597)	mem 34602MB
[2025-01-19 17:16:09 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][100/312]	eta 0:02:43 lr 0.000490	time 0.7234 (0.7703)	model_time 0.7232 (0.7501)	loss 2.4654 (2.7635)	grad_norm 1.3655 (2.1454/0.8253)	mem 34604MB
[2025-01-19 17:16:13 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][90/312]	eta 0:02:50 lr 0.000491	time 0.7209 (0.7659)	model_time 0.7207 (0.7507)	loss 3.1716 (2.8226)	grad_norm 3.6808 (2.0015/0.8063)	mem 34602MB
[2025-01-19 17:16:16 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][110/312]	eta 0:02:34 lr 0.000490	time 0.7353 (0.7672)	model_time 0.7348 (0.7488)	loss 2.9300 (2.7600)	grad_norm 1.3956 (2.1473/0.8771)	mem 34604MB
[2025-01-19 17:16:21 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][100/312]	eta 0:02:42 lr 0.000490	time 0.7156 (0.7650)	model_time 0.7154 (0.7513)	loss 2.7822 (2.8012)	grad_norm 1.9021 (2.0758/0.8385)	mem 34602MB
[2025-01-19 17:16:23 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][120/312]	eta 0:02:26 lr 0.000489	time 0.7170 (0.7644)	model_time 0.7169 (0.7475)	loss 3.1096 (2.7765)	grad_norm 1.8046 (2.1204/0.8744)	mem 34604MB
[2025-01-19 17:16:28 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][110/312]	eta 0:02:34 lr 0.000490	time 0.7253 (0.7637)	model_time 0.7248 (0.7512)	loss 2.9640 (2.7901)	grad_norm 2.5793 (2.0858/0.8270)	mem 34602MB
[2025-01-19 17:16:31 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][130/312]	eta 0:02:18 lr 0.000489	time 0.7332 (0.7619)	model_time 0.7328 (0.7462)	loss 2.7245 (2.7752)	grad_norm 3.4937 (2.1163/0.8718)	mem 34604MB
[2025-01-19 17:16:36 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][120/312]	eta 0:02:26 lr 0.000489	time 0.7218 (0.7612)	model_time 0.7214 (0.7497)	loss 3.1087 (2.8002)	grad_norm 1.0326 (2.0442/0.8113)	mem 34602MB
[2025-01-19 17:16:38 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][140/312]	eta 0:02:10 lr 0.000488	time 0.7262 (0.7593)	model_time 0.7260 (0.7447)	loss 3.1879 (2.7797)	grad_norm 2.2608 (2.1251/0.8645)	mem 34604MB
[2025-01-19 17:16:43 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][130/312]	eta 0:02:18 lr 0.000489	time 0.8318 (0.7600)	model_time 0.8315 (0.7494)	loss 2.9692 (2.8193)	grad_norm 1.2946 (2.0057/0.8032)	mem 34602MB
[2025-01-19 17:16:45 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][150/312]	eta 0:02:02 lr 0.000488	time 0.7157 (0.7573)	model_time 0.7153 (0.7437)	loss 3.1933 (2.7819)	grad_norm 1.1945 (2.1393/0.8734)	mem 34604MB
[2025-01-19 17:16:51 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][140/312]	eta 0:02:10 lr 0.000488	time 0.7181 (0.7583)	model_time 0.7176 (0.7484)	loss 2.5827 (2.8075)	grad_norm 1.7135 (2.0250/0.8144)	mem 34602MB
[2025-01-19 17:16:53 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][160/312]	eta 0:01:54 lr 0.000488	time 0.7236 (0.7553)	model_time 0.7232 (0.7425)	loss 3.1974 (2.7804)	grad_norm 1.4273 (2.1243/0.8596)	mem 34604MB
[2025-01-19 17:16:58 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][150/312]	eta 0:02:02 lr 0.000488	time 0.7209 (0.7573)	model_time 0.7207 (0.7480)	loss 2.7812 (2.8078)	grad_norm 2.5405 (2.0639/0.8368)	mem 34602MB
[2025-01-19 17:17:00 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][170/312]	eta 0:01:47 lr 0.000487	time 0.7167 (0.7557)	model_time 0.7165 (0.7436)	loss 3.0517 (2.7903)	grad_norm 3.4441 (2.1531/0.8893)	mem 34604MB
[2025-01-19 17:17:06 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][160/312]	eta 0:01:55 lr 0.000488	time 0.7192 (0.7572)	model_time 0.7188 (0.7485)	loss 3.1951 (2.8081)	grad_norm 1.3871 (2.0906/0.8528)	mem 34602MB
[2025-01-19 17:17:08 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][180/312]	eta 0:01:39 lr 0.000487	time 0.7088 (0.7558)	model_time 0.7083 (0.7444)	loss 3.0558 (2.7798)	grad_norm 3.4597 (2.1511/0.8904)	mem 34604MB
[2025-01-19 17:17:13 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][170/312]	eta 0:01:47 lr 0.000487	time 0.8055 (0.7571)	model_time 0.8053 (0.7488)	loss 3.0849 (2.8051)	grad_norm 3.2456 (2.1145/0.8599)	mem 34602MB
[2025-01-19 17:17:15 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][190/312]	eta 0:01:32 lr 0.000486	time 0.8151 (0.7561)	model_time 0.8150 (0.7452)	loss 3.2360 (2.7874)	grad_norm 1.0983 (2.1314/0.8842)	mem 34604MB
[2025-01-19 17:17:21 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][180/312]	eta 0:01:39 lr 0.000487	time 0.7141 (0.7572)	model_time 0.7140 (0.7493)	loss 3.0568 (2.7951)	grad_norm 1.6690 (2.0858/0.8503)	mem 34602MB
[2025-01-19 17:17:23 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][200/312]	eta 0:01:24 lr 0.000486	time 0.7168 (0.7564)	model_time 0.7166 (0.7461)	loss 2.9143 (2.7878)	grad_norm 1.7973 (2.1520/0.9063)	mem 34604MB
[2025-01-19 17:17:28 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][190/312]	eta 0:01:32 lr 0.000486	time 0.7217 (0.7564)	model_time 0.7212 (0.7489)	loss 2.8346 (2.8075)	grad_norm 2.9732 (2.0627/0.8484)	mem 34602MB
[2025-01-19 17:17:31 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][210/312]	eta 0:01:17 lr 0.000486	time 0.7297 (0.7570)	model_time 0.7295 (0.7471)	loss 3.3918 (2.7910)	grad_norm 3.4783 (2.1484/0.8982)	mem 34604MB
[2025-01-19 17:17:36 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][200/312]	eta 0:01:24 lr 0.000486	time 0.7153 (0.7559)	model_time 0.7151 (0.7488)	loss 2.0269 (2.8135)	grad_norm 1.9661 (2.0475/0.8391)	mem 34602MB
[2025-01-19 17:17:38 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][220/312]	eta 0:01:09 lr 0.000485	time 0.7632 (0.7568)	model_time 0.7628 (0.7473)	loss 3.2333 (2.7963)	grad_norm 1.2881 (2.1615/0.9145)	mem 34604MB
[2025-01-19 17:17:43 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][210/312]	eta 0:01:17 lr 0.000486	time 0.7453 (0.7550)	model_time 0.7448 (0.7483)	loss 2.8179 (2.8183)	grad_norm 2.4781 (2.0463/0.8316)	mem 34602MB
[2025-01-19 17:17:46 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][230/312]	eta 0:01:01 lr 0.000485	time 0.7158 (0.7561)	model_time 0.7157 (0.7470)	loss 3.3190 (2.8102)	grad_norm 3.0611 (2.1686/0.9025)	mem 34604MB
[2025-01-19 17:17:51 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][220/312]	eta 0:01:09 lr 0.000485	time 0.8116 (0.7552)	model_time 0.8114 (0.7488)	loss 2.9123 (2.8212)	grad_norm 2.4989 (2.0586/0.8259)	mem 34602MB
[2025-01-19 17:17:53 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][240/312]	eta 0:00:54 lr 0.000484	time 0.7170 (0.7555)	model_time 0.7168 (0.7468)	loss 2.9674 (2.8053)	grad_norm 0.9651 (2.1633/0.9026)	mem 34604MB
[2025-01-19 17:17:58 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][230/312]	eta 0:01:01 lr 0.000485	time 0.7147 (0.7546)	model_time 0.7145 (0.7483)	loss 3.1065 (2.8161)	grad_norm 4.8421 (2.0892/0.8822)	mem 34602MB
[2025-01-19 17:18:00 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][250/312]	eta 0:00:46 lr 0.000484	time 0.7158 (0.7545)	model_time 0.7154 (0.7461)	loss 1.6838 (2.8020)	grad_norm 2.1147 (2.1748/0.9031)	mem 34604MB
[2025-01-19 17:18:05 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][240/312]	eta 0:00:54 lr 0.000484	time 0.7225 (0.7533)	model_time 0.7223 (0.7473)	loss 2.3028 (2.8099)	grad_norm 1.7613 (2.1370/0.9440)	mem 34602MB
[2025-01-19 17:18:08 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][260/312]	eta 0:00:39 lr 0.000483	time 0.7194 (0.7535)	model_time 0.7192 (0.7455)	loss 2.1350 (2.8017)	grad_norm 1.4471 (2.2049/0.9541)	mem 34604MB
[2025-01-19 17:18:13 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][250/312]	eta 0:00:46 lr 0.000484	time 0.8295 (0.7530)	model_time 0.8293 (0.7473)	loss 2.8907 (2.8131)	grad_norm 1.7147 (2.1380/0.9477)	mem 34602MB
[2025-01-19 17:18:15 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][270/312]	eta 0:00:31 lr 0.000483	time 0.7161 (0.7526)	model_time 0.7156 (0.7448)	loss 2.8753 (2.8073)	grad_norm 1.2972 (2.1822/0.9454)	mem 34604MB
[2025-01-19 17:18:20 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][260/312]	eta 0:00:39 lr 0.000483	time 0.7160 (0.7523)	model_time 0.7155 (0.7467)	loss 3.2018 (2.8139)	grad_norm 2.1607 (2.1188/0.9377)	mem 34602MB
[2025-01-19 17:18:22 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][280/312]	eta 0:00:24 lr 0.000483	time 0.7291 (0.7518)	model_time 0.7289 (0.7443)	loss 2.6150 (2.8012)	grad_norm 1.4400 (2.1586/0.9414)	mem 34604MB
[2025-01-19 17:18:27 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][270/312]	eta 0:00:31 lr 0.000483	time 0.7162 (0.7519)	model_time 0.7160 (0.7465)	loss 1.7318 (2.8162)	grad_norm 1.7520 (2.1261/0.9398)	mem 34602MB
[2025-01-19 17:18:30 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][290/312]	eta 0:00:16 lr 0.000482	time 0.7198 (0.7521)	model_time 0.7196 (0.7448)	loss 2.8262 (2.8025)	grad_norm 2.0580 (2.1646/0.9437)	mem 34604MB
[2025-01-19 17:18:35 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][280/312]	eta 0:00:24 lr 0.000483	time 0.7230 (0.7521)	model_time 0.7226 (0.7470)	loss 3.2096 (2.8173)	grad_norm 2.4151 (2.1482/0.9448)	mem 34602MB
[2025-01-19 17:18:37 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][300/312]	eta 0:00:09 lr 0.000482	time 0.7086 (0.7523)	model_time 0.7085 (0.7453)	loss 3.2794 (2.8026)	grad_norm 2.1939 (2.1488/0.9393)	mem 34604MB
[2025-01-19 17:18:43 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][290/312]	eta 0:00:16 lr 0.000482	time 0.8170 (0.7527)	model_time 0.8168 (0.7477)	loss 2.4422 (2.8110)	grad_norm 2.4762 (2.1416/0.9368)	mem 34602MB
[2025-01-19 17:18:45 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][310/312]	eta 0:00:01 lr 0.000481	time 0.7166 (0.7518)	model_time 0.7165 (0.7450)	loss 3.3217 (2.8058)	grad_norm 1.8693 (2.1234/0.9219)	mem 34604MB
[2025-01-19 17:18:46 internimage_b_1k_224] (main.py 519): INFO EPOCH 234 training takes 0:03:54
[2025-01-19 17:18:46 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_234.pth saving......
[2025-01-19 17:18:49 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_234.pth saved !!!
[2025-01-19 17:18:50 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][300/312]	eta 0:00:09 lr 0.000482	time 0.7115 (0.7533)	model_time 0.7114 (0.7484)	loss 3.0047 (2.8114)	grad_norm 3.5384 (2.1526/0.9392)	mem 34602MB
[2025-01-19 17:18:56 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.370 (7.370)	Loss 0.7019 (0.7019)	Acc@1 85.864 (85.864)	Acc@5 97.900 (97.900)	Mem 34604MB
[2025-01-19 17:18:58 internimage_b_1k_224] (main.py 510): INFO Train: [234/300][310/312]	eta 0:00:01 lr 0.000481	time 0.7118 (0.7524)	model_time 0.7117 (0.7476)	loss 3.0727 (2.8068)	grad_norm 2.6539 (2.1663/0.9750)	mem 34602MB
[2025-01-19 17:18:58 internimage_b_1k_224] (main.py 519): INFO EPOCH 234 training takes 0:03:54
[2025-01-19 17:18:58 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_234.pth saving......
[2025-01-19 17:18:59 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.934)	Loss 0.8977 (0.7935)	Acc@1 81.128 (83.971)	Acc@5 95.898 (96.826)	Mem 34604MB
[2025-01-19 17:18:59 internimage_b_1k_224] (main.py 575): INFO [Epoch:234] * Acc@1 83.755 Acc@5 96.835
[2025-01-19 17:18:59 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.8%
[2025-01-19 17:18:59 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 17:19:02 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_234.pth saved !!!
[2025-01-19 17:19:03 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 17:19:03 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.76%
[2025-01-19 17:19:18 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.995 (15.995)	Loss 0.7213 (0.7213)	Acc@1 85.864 (85.864)	Acc@5 97.754 (97.754)	Mem 34602MB
[2025-01-19 17:19:18 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.457 (15.457)	Loss 0.7115 (0.7115)	Acc@1 86.304 (86.304)	Acc@5 98.169 (98.169)	Mem 34604MB
[2025-01-19 17:19:25 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.083)	Loss 0.9274 (0.8074)	Acc@1 80.859 (83.944)	Acc@5 95.850 (96.802)	Mem 34602MB
[2025-01-19 17:19:25 internimage_b_1k_224] (main.py 575): INFO [Epoch:234] * Acc@1 83.747 Acc@5 96.795
[2025-01-19 17:19:25 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.7%
[2025-01-19 17:19:25 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.79%
[2025-01-19 17:19:25 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.036)	Loss 0.9335 (0.8096)	Acc@1 80.273 (83.969)	Acc@5 95.581 (96.866)	Mem 34604MB
[2025-01-19 17:19:25 internimage_b_1k_224] (main.py 575): INFO [Epoch:234] * Acc@1 83.815 Acc@5 96.895
[2025-01-19 17:19:25 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.8%
[2025-01-19 17:19:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:19:29 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:19:29 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.82%
[2025-01-19 17:19:31 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][0/312]	eta 0:10:10 lr 0.000481	time 1.9577 (1.9577)	model_time 0.7272 (0.7272)	loss 3.2296 (3.2296)	grad_norm 2.1649 (2.1649/0.0000)	mem 34604MB
[2025-01-19 17:19:34 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.389 (9.389)	Loss 0.7207 (0.7207)	Acc@1 86.084 (86.084)	Acc@5 98.193 (98.193)	Mem 34602MB
[2025-01-19 17:19:39 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.259)	Loss 0.9343 (0.8104)	Acc@1 79.956 (83.971)	Acc@5 95.947 (96.922)	Mem 34602MB
[2025-01-19 17:19:39 internimage_b_1k_224] (main.py 575): INFO [Epoch:234] * Acc@1 83.799 Acc@5 96.967
[2025-01-19 17:19:39 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.8%
[2025-01-19 17:19:39 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:19:39 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][10/312]	eta 0:04:23 lr 0.000481	time 0.7166 (0.8718)	model_time 0.7162 (0.7596)	loss 2.6517 (2.6567)	grad_norm 2.0391 (2.3330/0.8117)	mem 34604MB
[2025-01-19 17:19:42 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:19:42 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.80%
[2025-01-19 17:19:44 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][0/312]	eta 0:10:19 lr 0.000481	time 1.9849 (1.9849)	model_time 0.7350 (0.7350)	loss 3.1501 (3.1501)	grad_norm 2.1964 (2.1964/0.0000)	mem 34602MB
[2025-01-19 17:19:47 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][20/312]	eta 0:04:00 lr 0.000480	time 0.7202 (0.8241)	model_time 0.7201 (0.7652)	loss 2.3231 (2.7846)	grad_norm 2.4701 (2.1762/0.7763)	mem 34604MB
[2025-01-19 17:19:52 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][10/312]	eta 0:04:22 lr 0.000481	time 0.7194 (0.8697)	model_time 0.7192 (0.7558)	loss 2.6608 (2.6608)	grad_norm 2.3896 (1.9310/0.3489)	mem 34602MB
[2025-01-19 17:19:54 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][30/312]	eta 0:03:44 lr 0.000480	time 0.7246 (0.7965)	model_time 0.7241 (0.7564)	loss 3.2153 (2.8527)	grad_norm 1.6673 (2.4213/1.0374)	mem 34604MB
[2025-01-19 17:19:59 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][20/312]	eta 0:03:55 lr 0.000480	time 0.7254 (0.8076)	model_time 0.7252 (0.7477)	loss 3.1539 (2.6837)	grad_norm 0.8490 (1.8476/0.4618)	mem 34602MB
[2025-01-19 17:20:01 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][40/312]	eta 0:03:32 lr 0.000480	time 0.7238 (0.7817)	model_time 0.7237 (0.7513)	loss 3.3383 (2.7958)	grad_norm 3.7839 (2.4436/1.0663)	mem 34604MB
[2025-01-19 17:20:07 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][30/312]	eta 0:03:43 lr 0.000480	time 0.7210 (0.7935)	model_time 0.7208 (0.7528)	loss 3.2211 (2.7159)	grad_norm 0.7776 (1.7821/0.6364)	mem 34602MB
[2025-01-19 17:20:09 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][50/312]	eta 0:03:22 lr 0.000479	time 0.7452 (0.7733)	model_time 0.7450 (0.7488)	loss 2.1426 (2.8044)	grad_norm 1.5635 (2.3173/1.0288)	mem 34604MB
[2025-01-19 17:20:14 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][40/312]	eta 0:03:32 lr 0.000480	time 0.8027 (0.7816)	model_time 0.8026 (0.7507)	loss 3.1918 (2.7504)	grad_norm 1.6170 (1.7791/0.5987)	mem 34602MB
[2025-01-19 17:20:16 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][60/312]	eta 0:03:12 lr 0.000479	time 0.7195 (0.7659)	model_time 0.7191 (0.7453)	loss 2.2763 (2.7667)	grad_norm 2.0070 (2.2245/0.9725)	mem 34604MB
[2025-01-19 17:20:22 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][50/312]	eta 0:03:21 lr 0.000479	time 0.7238 (0.7708)	model_time 0.7237 (0.7460)	loss 3.1034 (2.7600)	grad_norm 1.6949 (1.8242/0.6702)	mem 34602MB
[2025-01-19 17:20:23 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][70/312]	eta 0:03:04 lr 0.000478	time 0.7374 (0.7605)	model_time 0.7372 (0.7428)	loss 2.2997 (2.7300)	grad_norm 1.8584 (2.2628/0.9576)	mem 34604MB
[2025-01-19 17:20:29 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][60/312]	eta 0:03:13 lr 0.000479	time 0.7372 (0.7676)	model_time 0.7368 (0.7468)	loss 2.8803 (2.7631)	grad_norm 3.7159 (1.9395/0.7708)	mem 34602MB
[2025-01-19 17:20:31 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][80/312]	eta 0:02:55 lr 0.000478	time 0.7220 (0.7565)	model_time 0.7219 (0.7410)	loss 2.5003 (2.7204)	grad_norm 1.7438 (2.3116/0.9752)	mem 34604MB
[2025-01-19 17:20:37 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][70/312]	eta 0:03:05 lr 0.000478	time 0.8089 (0.7653)	model_time 0.8085 (0.7473)	loss 2.7955 (2.7636)	grad_norm 2.6004 (1.9610/0.7601)	mem 34602MB
[2025-01-19 17:20:38 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][90/312]	eta 0:02:47 lr 0.000477	time 0.7256 (0.7533)	model_time 0.7252 (0.7395)	loss 2.0445 (2.7292)	grad_norm 2.8199 (2.3954/1.0187)	mem 34604MB
[2025-01-19 17:20:44 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][80/312]	eta 0:02:56 lr 0.000478	time 0.7155 (0.7628)	model_time 0.7153 (0.7470)	loss 2.4622 (2.7719)	grad_norm 1.8453 (2.0170/0.7833)	mem 34602MB
[2025-01-19 17:20:46 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][100/312]	eta 0:02:40 lr 0.000477	time 0.6705 (0.7551)	model_time 0.6701 (0.7426)	loss 3.0570 (2.7383)	grad_norm inf (2.3752/1.0277)	mem 34604MB
[2025-01-19 17:20:52 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][90/312]	eta 0:02:49 lr 0.000477	time 0.8109 (0.7621)	model_time 0.8108 (0.7480)	loss 2.8058 (2.7580)	grad_norm 1.5895 (2.0068/0.7674)	mem 34602MB
[2025-01-19 17:20:53 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][110/312]	eta 0:02:32 lr 0.000477	time 0.7200 (0.7545)	model_time 0.7199 (0.7430)	loss 3.2722 (2.7383)	grad_norm 2.6988 (2.3525/1.0003)	mem 34604MB
[2025-01-19 17:20:59 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][100/312]	eta 0:02:41 lr 0.000477	time 0.8931 (0.7631)	model_time 0.8927 (0.7504)	loss 3.2055 (2.7795)	grad_norm 0.9167 (1.9793/0.7529)	mem 34602MB
[2025-01-19 17:21:01 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][120/312]	eta 0:02:24 lr 0.000476	time 0.8160 (0.7545)	model_time 0.8156 (0.7440)	loss 2.5096 (2.7403)	grad_norm 1.5622 (2.3184/0.9795)	mem 34604MB
[2025-01-19 17:21:07 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][110/312]	eta 0:02:33 lr 0.000477	time 0.7231 (0.7609)	model_time 0.7229 (0.7493)	loss 3.4116 (2.7797)	grad_norm 1.9996 (1.9941/0.7492)	mem 34602MB
[2025-01-19 17:21:08 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][130/312]	eta 0:02:17 lr 0.000476	time 0.7220 (0.7549)	model_time 0.7218 (0.7451)	loss 3.0885 (2.7465)	grad_norm 2.7131 (2.2737/0.9713)	mem 34604MB
[2025-01-19 17:21:14 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][120/312]	eta 0:02:25 lr 0.000476	time 0.8015 (0.7594)	model_time 0.8011 (0.7487)	loss 2.5682 (2.7932)	grad_norm 1.6878 (2.0055/0.7569)	mem 34602MB
[2025-01-19 17:21:16 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][140/312]	eta 0:02:10 lr 0.000475	time 0.7161 (0.7560)	model_time 0.7160 (0.7469)	loss 2.6058 (2.7359)	grad_norm 4.1218 (2.2947/0.9931)	mem 34604MB
[2025-01-19 17:21:22 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][130/312]	eta 0:02:18 lr 0.000476	time 0.7158 (0.7593)	model_time 0.7157 (0.7494)	loss 2.8325 (2.7850)	grad_norm 1.9815 (2.0204/0.7739)	mem 34602MB
[2025-01-19 17:21:23 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][150/312]	eta 0:02:02 lr 0.000475	time 0.7246 (0.7549)	model_time 0.7241 (0.7464)	loss 2.9657 (2.7475)	grad_norm 4.4742 (2.2934/0.9973)	mem 34604MB
[2025-01-19 17:21:29 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][140/312]	eta 0:02:10 lr 0.000475	time 0.7300 (0.7592)	model_time 0.7295 (0.7500)	loss 3.2745 (2.7949)	grad_norm 2.7546 (2.0177/0.7711)	mem 34602MB
[2025-01-19 17:21:31 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][160/312]	eta 0:01:54 lr 0.000475	time 0.7385 (0.7534)	model_time 0.7383 (0.7454)	loss 2.8139 (2.7606)	grad_norm 4.5293 (2.3320/1.0209)	mem 34604MB
[2025-01-19 17:21:37 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][150/312]	eta 0:02:02 lr 0.000475	time 0.7147 (0.7587)	model_time 0.7143 (0.7500)	loss 2.9363 (2.7808)	grad_norm 2.7441 (2.0099/0.7640)	mem 34602MB
[2025-01-19 17:21:38 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][170/312]	eta 0:01:46 lr 0.000474	time 0.8067 (0.7524)	model_time 0.8066 (0.7448)	loss 2.6997 (2.7727)	grad_norm 2.5287 (2.3334/1.0119)	mem 34604MB
[2025-01-19 17:21:44 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][160/312]	eta 0:01:55 lr 0.000475	time 0.8642 (0.7579)	model_time 0.8640 (0.7497)	loss 2.9344 (2.7863)	grad_norm 1.0650 (2.0190/0.7749)	mem 34602MB
[2025-01-19 17:21:45 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][180/312]	eta 0:01:39 lr 0.000474	time 0.7234 (0.7511)	model_time 0.7229 (0.7439)	loss 2.1482 (2.7744)	grad_norm 1.6946 (2.3397/0.9942)	mem 34604MB
[2025-01-19 17:21:52 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][170/312]	eta 0:01:47 lr 0.000474	time 0.7169 (0.7565)	model_time 0.7167 (0.7488)	loss 3.0474 (2.7957)	grad_norm 1.2598 (1.9840/0.7715)	mem 34602MB
[2025-01-19 17:21:53 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][190/312]	eta 0:01:31 lr 0.000473	time 0.7172 (0.7500)	model_time 0.7171 (0.7432)	loss 2.1428 (2.7641)	grad_norm 3.0299 (2.3469/0.9861)	mem 34604MB
[2025-01-19 17:21:59 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][180/312]	eta 0:01:39 lr 0.000474	time 0.8130 (0.7561)	model_time 0.8128 (0.7488)	loss 2.5580 (2.7900)	grad_norm 2.4104 (1.9982/0.7809)	mem 34602MB
[2025-01-19 17:22:00 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][200/312]	eta 0:01:23 lr 0.000473	time 0.7237 (0.7495)	model_time 0.7233 (0.7430)	loss 2.8084 (2.7606)	grad_norm 1.0526 (2.3552/0.9720)	mem 34604MB
[2025-01-19 17:22:07 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][190/312]	eta 0:01:32 lr 0.000473	time 0.8173 (0.7564)	model_time 0.8171 (0.7495)	loss 2.6412 (2.7911)	grad_norm 3.9855 (2.0130/0.7955)	mem 34602MB
[2025-01-19 17:22:07 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][210/312]	eta 0:01:16 lr 0.000473	time 0.7928 (0.7487)	model_time 0.7926 (0.7426)	loss 3.1585 (2.7590)	grad_norm 1.7015 (2.3419/0.9610)	mem 34604MB
[2025-01-19 17:22:14 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][200/312]	eta 0:01:24 lr 0.000473	time 0.8484 (0.7556)	model_time 0.8480 (0.7490)	loss 3.0774 (2.7832)	grad_norm 3.3810 (2.0331/0.8093)	mem 34602MB
[2025-01-19 17:22:15 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][220/312]	eta 0:01:08 lr 0.000472	time 0.7295 (0.7495)	model_time 0.7291 (0.7436)	loss 2.0783 (2.7472)	grad_norm 1.1775 (2.3637/0.9835)	mem 34604MB
[2025-01-19 17:22:22 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][210/312]	eta 0:01:17 lr 0.000473	time 0.8279 (0.7556)	model_time 0.8274 (0.7493)	loss 3.1366 (2.7880)	grad_norm 1.2822 (2.0611/0.8270)	mem 34602MB
[2025-01-19 17:22:23 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][230/312]	eta 0:01:01 lr 0.000472	time 0.7245 (0.7503)	model_time 0.7244 (0.7446)	loss 3.2442 (2.7495)	grad_norm 1.2184 (2.3301/0.9801)	mem 34604MB
[2025-01-19 17:22:29 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][220/312]	eta 0:01:09 lr 0.000472	time 0.8041 (0.7548)	model_time 0.8039 (0.7488)	loss 2.5908 (2.7896)	grad_norm 2.6963 (2.0543/0.8200)	mem 34602MB
[2025-01-19 17:22:30 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][240/312]	eta 0:00:54 lr 0.000471	time 0.8126 (0.7503)	model_time 0.8125 (0.7448)	loss 2.5291 (2.7444)	grad_norm 1.5932 (2.3373/0.9856)	mem 34604MB
[2025-01-19 17:22:37 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][230/312]	eta 0:01:01 lr 0.000472	time 0.8082 (0.7553)	model_time 0.8077 (0.7495)	loss 3.1816 (2.7860)	grad_norm 2.5626 (2.0512/0.8126)	mem 34602MB
[2025-01-19 17:22:38 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][250/312]	eta 0:00:46 lr 0.000471	time 0.7170 (0.7506)	model_time 0.7165 (0.7454)	loss 3.1284 (2.7378)	grad_norm 3.3107 (2.3536/0.9968)	mem 34604MB
[2025-01-19 17:22:44 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][240/312]	eta 0:00:54 lr 0.000471	time 0.8295 (0.7548)	model_time 0.8291 (0.7492)	loss 2.7653 (2.7778)	grad_norm 1.8780 (2.0466/0.8092)	mem 34602MB
[2025-01-19 17:22:45 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][260/312]	eta 0:00:39 lr 0.000470	time 0.7187 (0.7513)	model_time 0.7183 (0.7462)	loss 3.2275 (2.7470)	grad_norm 2.0117 (2.3477/0.9814)	mem 34604MB
[2025-01-19 17:22:52 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][250/312]	eta 0:00:46 lr 0.000471	time 0.8069 (0.7548)	model_time 0.8065 (0.7495)	loss 3.0929 (2.7827)	grad_norm 1.8262 (2.0471/0.8047)	mem 34602MB
[2025-01-19 17:22:53 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][270/312]	eta 0:00:31 lr 0.000470	time 0.7181 (0.7508)	model_time 0.7176 (0.7459)	loss 2.0245 (2.7461)	grad_norm 1.9823 (2.3679/0.9913)	mem 34604MB
[2025-01-19 17:22:59 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][260/312]	eta 0:00:39 lr 0.000470	time 0.7169 (0.7539)	model_time 0.7167 (0.7487)	loss 1.7655 (2.7791)	grad_norm 4.0438 (2.0520/0.8086)	mem 34602MB
[2025-01-19 17:23:00 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][280/312]	eta 0:00:24 lr 0.000470	time 0.7500 (0.7506)	model_time 0.7498 (0.7459)	loss 3.3612 (2.7520)	grad_norm 2.5812 (2.3848/0.9943)	mem 34604MB
[2025-01-19 17:23:06 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][270/312]	eta 0:00:31 lr 0.000470	time 0.7166 (0.7534)	model_time 0.7161 (0.7484)	loss 2.9506 (2.7811)	grad_norm 2.0729 (2.0889/0.8488)	mem 34602MB
[2025-01-19 17:23:08 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][290/312]	eta 0:00:16 lr 0.000469	time 0.8152 (0.7502)	model_time 0.8151 (0.7456)	loss 3.2563 (2.7518)	grad_norm 3.5028 (2.3855/0.9913)	mem 34604MB
[2025-01-19 17:23:14 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][280/312]	eta 0:00:24 lr 0.000470	time 0.8244 (0.7535)	model_time 0.8242 (0.7487)	loss 2.3273 (2.7721)	grad_norm 2.9795 (2.1226/0.8589)	mem 34602MB
[2025-01-19 17:23:15 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][300/312]	eta 0:00:08 lr 0.000469	time 0.7221 (0.7493)	model_time 0.7220 (0.7449)	loss 3.2473 (2.7517)	grad_norm 1.8159 (2.3984/0.9981)	mem 34604MB
[2025-01-19 17:23:21 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][290/312]	eta 0:00:16 lr 0.000469	time 0.7230 (0.7527)	model_time 0.7228 (0.7480)	loss 2.7712 (2.7811)	grad_norm 3.1150 (2.1370/0.8589)	mem 34602MB
[2025-01-19 17:23:22 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][310/312]	eta 0:00:01 lr 0.000468	time 0.7154 (0.7482)	model_time 0.7153 (0.7439)	loss 2.9489 (2.7490)	grad_norm 2.6351 (2.4116/0.9957)	mem 34604MB
[2025-01-19 17:23:23 internimage_b_1k_224] (main.py 519): INFO EPOCH 235 training takes 0:03:53
[2025-01-19 17:23:23 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_235.pth saving......
[2025-01-19 17:23:26 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_235.pth saved !!!
[2025-01-19 17:23:29 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][300/312]	eta 0:00:09 lr 0.000469	time 0.7987 (0.7520)	model_time 0.7986 (0.7474)	loss 3.0158 (2.7776)	grad_norm 3.7090 (2.1480/0.8632)	mem 34602MB
[2025-01-19 17:23:34 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.856 (7.856)	Loss 0.6932 (0.6932)	Acc@1 85.962 (85.962)	Acc@5 97.998 (97.998)	Mem 34604MB
[2025-01-19 17:23:36 internimage_b_1k_224] (main.py 510): INFO Train: [235/300][310/312]	eta 0:00:01 lr 0.000468	time 0.7160 (0.7512)	model_time 0.7159 (0.7468)	loss 2.8804 (2.7786)	grad_norm 1.1932 (2.1526/0.8682)	mem 34602MB
[2025-01-19 17:23:37 internimage_b_1k_224] (main.py 519): INFO EPOCH 235 training takes 0:03:54
[2025-01-19 17:23:37 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_235.pth saving......
[2025-01-19 17:23:37 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.994)	Loss 0.9111 (0.7856)	Acc@1 80.103 (83.980)	Acc@5 95.630 (96.766)	Mem 34604MB
[2025-01-19 17:23:38 internimage_b_1k_224] (main.py 575): INFO [Epoch:235] * Acc@1 83.797 Acc@5 96.801
[2025-01-19 17:23:38 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.8%
[2025-01-19 17:23:38 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 17:23:40 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_235.pth saved !!!
[2025-01-19 17:23:41 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 17:23:41 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.80%
[2025-01-19 17:23:55 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.336 (15.336)	Loss 0.7037 (0.7037)	Acc@1 85.693 (85.693)	Acc@5 97.876 (97.876)	Mem 34602MB
[2025-01-19 17:23:57 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.952 (15.952)	Loss 0.7117 (0.7117)	Acc@1 86.353 (86.353)	Acc@5 98.169 (98.169)	Mem 34604MB
[2025-01-19 17:24:03 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.186 (2.084)	Loss 0.9113 (0.7875)	Acc@1 80.518 (84.033)	Acc@5 96.021 (96.853)	Mem 34602MB
[2025-01-19 17:24:03 internimage_b_1k_224] (main.py 575): INFO [Epoch:235] * Acc@1 83.811 Acc@5 96.849
[2025-01-19 17:24:03 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.8%
[2025-01-19 17:24:03 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 17:24:03 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.014)	Loss 0.9330 (0.8094)	Acc@1 80.249 (83.969)	Acc@5 95.679 (96.882)	Mem 34604MB
[2025-01-19 17:24:04 internimage_b_1k_224] (main.py 575): INFO [Epoch:235] * Acc@1 83.817 Acc@5 96.909
[2025-01-19 17:24:04 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.8%
[2025-01-19 17:24:04 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:24:07 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 17:24:07 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.81%
[2025-01-19 17:24:08 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:24:08 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.82%
[2025-01-19 17:24:10 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][0/312]	eta 0:11:37 lr 0.000468	time 2.2346 (2.2346)	model_time 0.7426 (0.7426)	loss 3.2030 (3.2030)	grad_norm 5.2620 (5.2620/0.0000)	mem 34604MB
[2025-01-19 17:24:14 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.544 (7.544)	Loss 0.7209 (0.7209)	Acc@1 86.060 (86.060)	Acc@5 98.218 (98.218)	Mem 34602MB
[2025-01-19 17:24:17 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.957)	Loss 0.9338 (0.8103)	Acc@1 79.980 (83.982)	Acc@5 95.923 (96.924)	Mem 34602MB
[2025-01-19 17:24:17 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][10/312]	eta 0:04:23 lr 0.000468	time 0.7198 (0.8709)	model_time 0.7194 (0.7350)	loss 3.0962 (2.8097)	grad_norm 1.5701 (2.6676/1.4628)	mem 34604MB
[2025-01-19 17:24:17 internimage_b_1k_224] (main.py 575): INFO [Epoch:235] * Acc@1 83.809 Acc@5 96.967
[2025-01-19 17:24:17 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.8%
[2025-01-19 17:24:17 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:24:21 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:24:21 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.81%
[2025-01-19 17:24:23 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][0/312]	eta 0:12:06 lr 0.000468	time 2.3271 (2.3271)	model_time 0.7359 (0.7359)	loss 2.8287 (2.8287)	grad_norm 2.5221 (2.5221/0.0000)	mem 34602MB
[2025-01-19 17:24:25 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][20/312]	eta 0:03:56 lr 0.000467	time 0.7230 (0.8096)	model_time 0.7229 (0.7383)	loss 2.5261 (2.7919)	grad_norm 1.7657 (2.3815/1.1617)	mem 34604MB
[2025-01-19 17:24:31 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][10/312]	eta 0:04:26 lr 0.000468	time 0.7169 (0.8815)	model_time 0.7167 (0.7366)	loss 2.3074 (2.7154)	grad_norm 6.0289 (2.9183/1.5893)	mem 34602MB
[2025-01-19 17:24:32 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][30/312]	eta 0:03:45 lr 0.000467	time 0.9446 (0.7986)	model_time 0.9441 (0.7501)	loss 2.7017 (2.8003)	grad_norm 2.1286 (2.1230/1.0485)	mem 34604MB
[2025-01-19 17:24:38 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][20/312]	eta 0:03:59 lr 0.000467	time 0.7175 (0.8199)	model_time 0.7172 (0.7438)	loss 2.6513 (2.7503)	grad_norm 1.4899 (2.5638/1.3154)	mem 34602MB
[2025-01-19 17:24:40 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][40/312]	eta 0:03:33 lr 0.000467	time 0.7158 (0.7863)	model_time 0.7157 (0.7495)	loss 2.5737 (2.7851)	grad_norm 2.2201 (2.2251/0.9870)	mem 34604MB
[2025-01-19 17:24:46 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][30/312]	eta 0:03:45 lr 0.000467	time 0.7337 (0.8006)	model_time 0.7336 (0.7490)	loss 3.2221 (2.6972)	grad_norm 1.7111 (2.4213/1.1466)	mem 34602MB
[2025-01-19 17:24:47 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][50/312]	eta 0:03:24 lr 0.000466	time 0.8259 (0.7798)	model_time 0.8253 (0.7502)	loss 2.1897 (2.8189)	grad_norm 2.3400 (2.1805/1.0033)	mem 34604MB
[2025-01-19 17:24:53 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][40/312]	eta 0:03:34 lr 0.000467	time 0.7163 (0.7900)	model_time 0.7161 (0.7509)	loss 2.5754 (2.7152)	grad_norm 1.3199 (2.3015/1.0531)	mem 34602MB
[2025-01-19 17:24:55 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][60/312]	eta 0:03:16 lr 0.000466	time 0.8128 (0.7791)	model_time 0.8127 (0.7543)	loss 2.7300 (2.7934)	grad_norm 1.7832 (2.2134/0.9687)	mem 34604MB
[2025-01-19 17:25:01 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][50/312]	eta 0:03:24 lr 0.000466	time 0.7235 (0.7807)	model_time 0.7233 (0.7492)	loss 2.8132 (2.7128)	grad_norm 1.8351 (2.4043/1.0322)	mem 34602MB
[2025-01-19 17:25:03 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][70/312]	eta 0:03:07 lr 0.000465	time 0.7229 (0.7752)	model_time 0.7227 (0.7538)	loss 3.2799 (2.8095)	grad_norm 1.0312 (2.2127/0.9861)	mem 34604MB
[2025-01-19 17:25:08 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][60/312]	eta 0:03:15 lr 0.000466	time 0.7228 (0.7751)	model_time 0.7222 (0.7487)	loss 3.1453 (2.7282)	grad_norm 1.9778 (2.5100/1.1030)	mem 34602MB
[2025-01-19 17:25:10 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][80/312]	eta 0:02:58 lr 0.000465	time 0.7238 (0.7701)	model_time 0.7236 (0.7514)	loss 2.4988 (2.7997)	grad_norm 1.1066 (2.1278/0.9599)	mem 34604MB
[2025-01-19 17:25:16 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][70/312]	eta 0:03:06 lr 0.000465	time 0.7166 (0.7696)	model_time 0.7165 (0.7469)	loss 2.2013 (2.6942)	grad_norm 1.4259 (2.4593/1.0633)	mem 34602MB
[2025-01-19 17:25:17 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][90/312]	eta 0:02:50 lr 0.000465	time 0.7234 (0.7668)	model_time 0.7230 (0.7501)	loss 1.8564 (2.7838)	grad_norm 1.7995 (2.0847/0.9334)	mem 34604MB
[2025-01-19 17:25:23 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][80/312]	eta 0:02:58 lr 0.000465	time 0.7171 (0.7673)	model_time 0.7170 (0.7474)	loss 2.2078 (2.6866)	grad_norm 0.9393 (2.3309/1.0597)	mem 34602MB
[2025-01-19 17:25:25 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][100/312]	eta 0:02:41 lr 0.000464	time 0.8079 (0.7638)	model_time 0.8078 (0.7487)	loss 2.2146 (2.7834)	grad_norm 1.2246 (2.0603/0.9092)	mem 34604MB
[2025-01-19 17:25:31 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][90/312]	eta 0:02:49 lr 0.000465	time 0.7166 (0.7647)	model_time 0.7164 (0.7469)	loss 3.0979 (2.6869)	grad_norm 1.7643 (2.2542/1.0330)	mem 34602MB
[2025-01-19 17:25:32 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][110/312]	eta 0:02:33 lr 0.000464	time 0.7164 (0.7607)	model_time 0.7159 (0.7469)	loss 2.7409 (2.7683)	grad_norm 1.0636 (2.0619/0.8877)	mem 34604MB
[2025-01-19 17:25:38 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][100/312]	eta 0:02:41 lr 0.000464	time 0.7381 (0.7624)	model_time 0.7379 (0.7464)	loss 3.0380 (2.7025)	grad_norm 1.6703 (2.2120/1.0011)	mem 34602MB
[2025-01-19 17:25:39 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][120/312]	eta 0:02:25 lr 0.000463	time 0.7185 (0.7580)	model_time 0.7180 (0.7452)	loss 2.7531 (2.7604)	grad_norm 1.2237 (2.0798/0.8756)	mem 34604MB
[2025-01-19 17:25:45 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][110/312]	eta 0:02:33 lr 0.000464	time 0.7116 (0.7603)	model_time 0.7114 (0.7456)	loss 3.2201 (2.7082)	grad_norm 2.0231 (2.2493/1.0396)	mem 34602MB
[2025-01-19 17:25:47 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][130/312]	eta 0:02:17 lr 0.000463	time 0.7129 (0.7557)	model_time 0.7127 (0.7439)	loss 3.3242 (2.7730)	grad_norm 1.5711 (2.0648/0.8550)	mem 34604MB
[2025-01-19 17:25:53 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][120/312]	eta 0:02:25 lr 0.000463	time 0.7207 (0.7579)	model_time 0.7205 (0.7445)	loss 2.1066 (2.7027)	grad_norm 1.7972 (2.2387/1.0204)	mem 34602MB
[2025-01-19 17:25:54 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][140/312]	eta 0:02:09 lr 0.000463	time 0.7147 (0.7543)	model_time 0.7146 (0.7434)	loss 3.2563 (2.7741)	grad_norm 2.4691 (2.1139/0.8819)	mem 34604MB
[2025-01-19 17:26:01 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][130/312]	eta 0:02:18 lr 0.000463	time 0.7179 (0.7589)	model_time 0.7178 (0.7465)	loss 3.3478 (2.7197)	grad_norm 3.3332 (2.2284/1.0153)	mem 34602MB
[2025-01-19 17:26:02 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][150/312]	eta 0:02:02 lr 0.000462	time 0.8309 (0.7553)	model_time 0.8305 (0.7450)	loss 2.8632 (2.7746)	grad_norm 1.2103 (2.1075/0.8768)	mem 34604MB
[2025-01-19 17:26:08 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][140/312]	eta 0:02:10 lr 0.000463	time 0.7198 (0.7581)	model_time 0.7196 (0.7465)	loss 2.2849 (2.7142)	grad_norm 2.7670 (2.2088/1.0053)	mem 34602MB
[2025-01-19 17:26:09 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][160/312]	eta 0:01:54 lr 0.000462	time 0.7184 (0.7556)	model_time 0.7182 (0.7460)	loss 2.7007 (2.7661)	grad_norm 1.8668 (2.0620/0.8700)	mem 34604MB
[2025-01-19 17:26:16 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][150/312]	eta 0:02:03 lr 0.000462	time 0.8093 (0.7597)	model_time 0.8091 (0.7489)	loss 2.9037 (2.7202)	grad_norm 3.1750 (2.2449/1.0191)	mem 34602MB
[2025-01-19 17:26:17 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][170/312]	eta 0:01:47 lr 0.000461	time 0.8270 (0.7552)	model_time 0.8265 (0.7461)	loss 3.1451 (2.7671)	grad_norm 3.0220 (2.0388/0.8578)	mem 34604MB
[2025-01-19 17:26:23 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][160/312]	eta 0:01:55 lr 0.000462	time 0.7165 (0.7595)	model_time 0.7163 (0.7494)	loss 1.8587 (2.7214)	grad_norm 2.6429 (2.2589/1.0050)	mem 34602MB
[2025-01-19 17:26:25 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][180/312]	eta 0:01:39 lr 0.000461	time 0.8162 (0.7562)	model_time 0.8160 (0.7476)	loss 2.6612 (2.7595)	grad_norm 1.2923 (2.0111/0.8470)	mem 34604MB
[2025-01-19 17:26:31 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][170/312]	eta 0:01:47 lr 0.000461	time 0.7158 (0.7586)	model_time 0.7156 (0.7490)	loss 2.4172 (2.7328)	grad_norm 1.8049 (2.2387/0.9868)	mem 34602MB
[2025-01-19 17:26:32 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][190/312]	eta 0:01:32 lr 0.000460	time 0.7147 (0.7574)	model_time 0.7142 (0.7493)	loss 3.0171 (2.7644)	grad_norm 3.2056 (2.0321/0.8537)	mem 34604MB
[2025-01-19 17:26:38 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][180/312]	eta 0:01:40 lr 0.000461	time 0.7142 (0.7581)	model_time 0.7137 (0.7490)	loss 1.9881 (2.7297)	grad_norm 1.6097 (2.2590/0.9853)	mem 34602MB
[2025-01-19 17:26:40 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][200/312]	eta 0:01:24 lr 0.000460	time 0.7347 (0.7565)	model_time 0.7343 (0.7487)	loss 3.0368 (2.7594)	grad_norm 3.4158 (2.1165/0.9541)	mem 34604MB
[2025-01-19 17:26:46 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][190/312]	eta 0:01:32 lr 0.000460	time 0.7422 (0.7569)	model_time 0.7420 (0.7482)	loss 2.5761 (2.7371)	grad_norm 2.2669 (2.2697/0.9773)	mem 34602MB
[2025-01-19 17:26:47 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][210/312]	eta 0:01:17 lr 0.000460	time 0.7209 (0.7556)	model_time 0.7204 (0.7481)	loss 2.8899 (2.7575)	grad_norm 1.4307 (2.1267/0.9560)	mem 34604MB
[2025-01-19 17:26:53 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][200/312]	eta 0:01:24 lr 0.000460	time 0.7189 (0.7578)	model_time 0.7188 (0.7495)	loss 2.8458 (2.7304)	grad_norm 2.6160 (2.2618/0.9627)	mem 34602MB
[2025-01-19 17:26:54 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][220/312]	eta 0:01:09 lr 0.000459	time 0.7213 (0.7542)	model_time 0.7209 (0.7471)	loss 2.9885 (2.7635)	grad_norm 1.3130 (2.1330/0.9417)	mem 34604MB
[2025-01-19 17:27:01 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][210/312]	eta 0:01:17 lr 0.000460	time 0.7183 (0.7578)	model_time 0.7181 (0.7499)	loss 2.7676 (2.7445)	grad_norm 3.0546 (2.2834/0.9569)	mem 34602MB
[2025-01-19 17:27:02 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][230/312]	eta 0:01:01 lr 0.000459	time 0.7216 (0.7536)	model_time 0.7212 (0.7468)	loss 3.0871 (2.7545)	grad_norm 2.1245 (2.1338/0.9297)	mem 34604MB
[2025-01-19 17:27:08 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][220/312]	eta 0:01:09 lr 0.000459	time 0.7294 (0.7569)	model_time 0.7292 (0.7494)	loss 2.1286 (2.7411)	grad_norm 2.6076 (2.2956/0.9542)	mem 34602MB
[2025-01-19 17:27:09 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][240/312]	eta 0:00:54 lr 0.000458	time 0.7213 (0.7527)	model_time 0.7209 (0.7461)	loss 2.7341 (2.7623)	grad_norm 1.9086 (2.1467/0.9286)	mem 34604MB
[2025-01-19 17:27:16 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][230/312]	eta 0:01:02 lr 0.000459	time 0.7172 (0.7564)	model_time 0.7170 (0.7493)	loss 3.1326 (2.7483)	grad_norm 1.6774 (2.2764/0.9435)	mem 34602MB
[2025-01-19 17:27:16 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][250/312]	eta 0:00:46 lr 0.000458	time 0.7321 (0.7518)	model_time 0.7316 (0.7455)	loss 2.7206 (2.7552)	grad_norm 4.3795 (2.1618/0.9344)	mem 34604MB
[2025-01-19 17:27:23 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][240/312]	eta 0:00:54 lr 0.000458	time 0.7127 (0.7551)	model_time 0.7125 (0.7482)	loss 2.2239 (2.7387)	grad_norm 3.4611 (2.2809/0.9375)	mem 34602MB
[2025-01-19 17:27:24 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][260/312]	eta 0:00:39 lr 0.000458	time 0.7211 (0.7513)	model_time 0.7207 (0.7452)	loss 3.1551 (2.7664)	grad_norm 3.1709 (2.1852/0.9426)	mem 34604MB
[2025-01-19 17:27:30 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][250/312]	eta 0:00:46 lr 0.000458	time 0.7334 (0.7547)	model_time 0.7332 (0.7480)	loss 2.3048 (2.7381)	grad_norm 2.3377 (2.2655/0.9279)	mem 34602MB
[2025-01-19 17:27:31 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][270/312]	eta 0:00:31 lr 0.000457	time 0.8397 (0.7517)	model_time 0.8392 (0.7458)	loss 3.1445 (2.7747)	grad_norm 1.3411 (2.2140/0.9559)	mem 34604MB
[2025-01-19 17:27:38 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][260/312]	eta 0:00:39 lr 0.000458	time 0.7256 (0.7548)	model_time 0.7254 (0.7484)	loss 3.1211 (2.7387)	grad_norm 1.0983 (2.2506/0.9311)	mem 34602MB
[2025-01-19 17:27:39 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][280/312]	eta 0:00:24 lr 0.000457	time 0.7181 (0.7523)	model_time 0.7177 (0.7466)	loss 3.4265 (2.7801)	grad_norm 2.0264 (2.2158/0.9452)	mem 34604MB
[2025-01-19 17:27:46 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][270/312]	eta 0:00:31 lr 0.000457	time 0.8072 (0.7551)	model_time 0.8070 (0.7489)	loss 3.3508 (2.7399)	grad_norm 1.0914 (2.2321/0.9241)	mem 34602MB
[2025-01-19 17:27:47 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][290/312]	eta 0:00:16 lr 0.000456	time 0.8295 (0.7524)	model_time 0.8291 (0.7469)	loss 2.7470 (2.7782)	grad_norm 1.1434 (2.2285/0.9477)	mem 34604MB
[2025-01-19 17:27:53 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][280/312]	eta 0:00:24 lr 0.000457	time 0.7172 (0.7546)	model_time 0.7170 (0.7486)	loss 3.2270 (2.7469)	grad_norm 1.4801 (2.2192/0.9315)	mem 34602MB
[2025-01-19 17:27:54 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][300/312]	eta 0:00:09 lr 0.000456	time 0.7103 (0.7526)	model_time 0.7102 (0.7473)	loss 2.6472 (2.7803)	grad_norm 5.0536 (2.2518/0.9591)	mem 34604MB
[2025-01-19 17:28:01 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][290/312]	eta 0:00:16 lr 0.000456	time 0.7288 (0.7549)	model_time 0.7287 (0.7491)	loss 2.2037 (2.7464)	grad_norm 1.9657 (2.2255/0.9365)	mem 34602MB
[2025-01-19 17:28:02 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][310/312]	eta 0:00:01 lr 0.000456	time 0.8261 (0.7523)	model_time 0.8260 (0.7472)	loss 3.3121 (2.7824)	grad_norm 1.7688 (2.2461/0.9490)	mem 34604MB
[2025-01-19 17:28:02 internimage_b_1k_224] (main.py 519): INFO EPOCH 236 training takes 0:03:54
[2025-01-19 17:28:02 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_236.pth saving......
[2025-01-19 17:28:06 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_236.pth saved !!!
[2025-01-19 17:28:08 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][300/312]	eta 0:00:09 lr 0.000456	time 0.7142 (0.7552)	model_time 0.7141 (0.7496)	loss 2.3778 (2.7455)	grad_norm 3.6593 (2.2352/0.9386)	mem 34602MB
[2025-01-19 17:28:13 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.373 (7.373)	Loss 0.7076 (0.7076)	Acc@1 85.913 (85.913)	Acc@5 97.852 (97.852)	Mem 34604MB
[2025-01-19 17:28:16 internimage_b_1k_224] (main.py 510): INFO Train: [236/300][310/312]	eta 0:00:01 lr 0.000456	time 0.7929 (0.7544)	model_time 0.7928 (0.7490)	loss 3.2541 (2.7464)	grad_norm 5.6944 (2.2348/0.9390)	mem 34602MB
[2025-01-19 17:28:16 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.183 (0.957)	Loss 0.9183 (0.7997)	Acc@1 80.273 (83.827)	Acc@5 95.654 (96.755)	Mem 34604MB
[2025-01-19 17:28:17 internimage_b_1k_224] (main.py 575): INFO [Epoch:236] * Acc@1 83.663 Acc@5 96.761
[2025-01-19 17:28:17 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.7%
[2025-01-19 17:28:17 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.80%
[2025-01-19 17:28:17 internimage_b_1k_224] (main.py 519): INFO EPOCH 236 training takes 0:03:55
[2025-01-19 17:28:17 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_236.pth saving......
[2025-01-19 17:28:20 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_236.pth saved !!!
[2025-01-19 17:28:34 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.803 (17.803)	Loss 0.7120 (0.7120)	Acc@1 86.426 (86.426)	Acc@5 98.169 (98.169)	Mem 34604MB
[2025-01-19 17:28:36 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.688 (16.688)	Loss 0.7064 (0.7064)	Acc@1 85.938 (85.938)	Acc@5 97.925 (97.925)	Mem 34602MB
[2025-01-19 17:28:43 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.442)	Loss 0.9324 (0.8092)	Acc@1 80.273 (84.004)	Acc@5 95.654 (96.871)	Mem 34604MB
[2025-01-19 17:28:44 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.169)	Loss 0.9084 (0.7970)	Acc@1 80.884 (83.922)	Acc@5 95.703 (96.788)	Mem 34602MB
[2025-01-19 17:28:44 internimage_b_1k_224] (main.py 575): INFO [Epoch:236] * Acc@1 83.853 Acc@5 96.901
[2025-01-19 17:28:44 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.9%
[2025-01-19 17:28:44 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:28:44 internimage_b_1k_224] (main.py 575): INFO [Epoch:236] * Acc@1 83.733 Acc@5 96.789
[2025-01-19 17:28:44 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.7%
[2025-01-19 17:28:44 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.81%
[2025-01-19 17:28:48 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:28:48 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.85%
[2025-01-19 17:28:50 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][0/312]	eta 0:11:16 lr 0.000455	time 2.1678 (2.1678)	model_time 0.7345 (0.7345)	loss 3.0883 (3.0883)	grad_norm 2.5759 (2.5759/0.0000)	mem 34604MB
[2025-01-19 17:28:53 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.370 (9.370)	Loss 0.7211 (0.7211)	Acc@1 86.060 (86.060)	Acc@5 98.218 (98.218)	Mem 34602MB
[2025-01-19 17:28:57 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][10/312]	eta 0:04:22 lr 0.000455	time 0.7369 (0.8690)	model_time 0.7365 (0.7384)	loss 3.4293 (2.9502)	grad_norm 1.2923 (1.8181/0.5909)	mem 34604MB
[2025-01-19 17:28:58 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.252)	Loss 0.9334 (0.8101)	Acc@1 79.980 (84.007)	Acc@5 95.898 (96.917)	Mem 34602MB
[2025-01-19 17:28:58 internimage_b_1k_224] (main.py 575): INFO [Epoch:236] * Acc@1 83.831 Acc@5 96.959
[2025-01-19 17:28:58 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.8%
[2025-01-19 17:28:58 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:29:02 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:29:02 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.83%
[2025-01-19 17:29:04 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][0/312]	eta 0:11:21 lr 0.000455	time 2.1852 (2.1852)	model_time 0.7357 (0.7357)	loss 2.3047 (2.3047)	grad_norm 1.4866 (1.4866/0.0000)	mem 34602MB
[2025-01-19 17:29:05 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][20/312]	eta 0:03:55 lr 0.000455	time 0.7295 (0.8079)	model_time 0.7293 (0.7392)	loss 2.3116 (2.9521)	grad_norm 2.0626 (1.9625/0.5476)	mem 34604MB
[2025-01-19 17:29:11 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][10/312]	eta 0:04:27 lr 0.000455	time 0.7282 (0.8851)	model_time 0.7281 (0.7531)	loss 2.4741 (2.4819)	grad_norm 1.2062 (2.3962/1.0124)	mem 34602MB
[2025-01-19 17:29:12 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][30/312]	eta 0:03:40 lr 0.000454	time 0.7238 (0.7821)	model_time 0.7236 (0.7355)	loss 2.8426 (2.8600)	grad_norm 2.3839 (1.9590/0.5931)	mem 34604MB
[2025-01-19 17:29:19 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][20/312]	eta 0:04:00 lr 0.000455	time 0.7458 (0.8240)	model_time 0.7456 (0.7548)	loss 2.8327 (2.6816)	grad_norm 1.8903 (2.7047/1.2628)	mem 34602MB
[2025-01-19 17:29:20 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][40/312]	eta 0:03:30 lr 0.000454	time 0.7286 (0.7730)	model_time 0.7281 (0.7377)	loss 2.8284 (2.8279)	grad_norm 1.8769 (1.8943/0.5815)	mem 34604MB
[2025-01-19 17:29:26 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][30/312]	eta 0:03:43 lr 0.000454	time 0.7241 (0.7932)	model_time 0.7239 (0.7462)	loss 3.1133 (2.7056)	grad_norm 2.5962 (2.5784/1.1123)	mem 34602MB
[2025-01-19 17:29:27 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][50/312]	eta 0:03:20 lr 0.000453	time 0.7256 (0.7649)	model_time 0.7251 (0.7364)	loss 2.3038 (2.8301)	grad_norm 2.1824 (1.8821/0.5605)	mem 34604MB
[2025-01-19 17:29:34 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][40/312]	eta 0:03:32 lr 0.000454	time 0.7180 (0.7805)	model_time 0.7178 (0.7449)	loss 2.5511 (2.7085)	grad_norm 2.1286 (2.5647/1.0333)	mem 34602MB
[2025-01-19 17:29:34 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][60/312]	eta 0:03:11 lr 0.000453	time 0.7229 (0.7597)	model_time 0.7227 (0.7358)	loss 3.3567 (2.7770)	grad_norm 1.0991 (1.8486/0.5453)	mem 34604MB
[2025-01-19 17:29:41 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][50/312]	eta 0:03:21 lr 0.000453	time 0.7193 (0.7701)	model_time 0.7191 (0.7414)	loss 2.5946 (2.7603)	grad_norm 2.1552 (2.5176/1.0345)	mem 34602MB
[2025-01-19 17:29:42 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][70/312]	eta 0:03:02 lr 0.000453	time 0.8027 (0.7560)	model_time 0.8022 (0.7354)	loss 2.4188 (2.7948)	grad_norm 2.4897 (1.8964/0.6286)	mem 34604MB
[2025-01-19 17:29:48 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][60/312]	eta 0:03:13 lr 0.000453	time 0.8110 (0.7671)	model_time 0.8109 (0.7431)	loss 2.1848 (2.7447)	grad_norm 2.7326 (2.4002/0.9991)	mem 34602MB
[2025-01-19 17:29:49 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][80/312]	eta 0:02:55 lr 0.000452	time 0.8137 (0.7549)	model_time 0.8133 (0.7368)	loss 2.9659 (2.7805)	grad_norm 2.4269 (1.9092/0.6193)	mem 34604MB
[2025-01-19 17:29:56 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][70/312]	eta 0:03:04 lr 0.000453	time 0.7163 (0.7639)	model_time 0.7161 (0.7432)	loss 3.1054 (2.7478)	grad_norm 3.2314 (2.3200/0.9837)	mem 34602MB
[2025-01-19 17:29:57 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][90/312]	eta 0:02:47 lr 0.000452	time 0.8101 (0.7566)	model_time 0.8099 (0.7404)	loss 2.3483 (2.7782)	grad_norm 4.2812 (1.9383/0.6972)	mem 34604MB
[2025-01-19 17:30:03 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][80/312]	eta 0:02:57 lr 0.000452	time 0.7178 (0.7642)	model_time 0.7176 (0.7460)	loss 2.9543 (2.7734)	grad_norm 1.4108 (2.3835/1.0532)	mem 34602MB
[2025-01-19 17:30:05 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][100/312]	eta 0:02:40 lr 0.000451	time 0.7617 (0.7585)	model_time 0.7611 (0.7439)	loss 2.9609 (2.7692)	grad_norm 1.6552 (1.9907/0.7583)	mem 34604MB
[2025-01-19 17:30:11 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][90/312]	eta 0:02:49 lr 0.000452	time 0.7170 (0.7631)	model_time 0.7168 (0.7469)	loss 3.1813 (2.7745)	grad_norm 1.8885 (2.3712/1.0158)	mem 34602MB
[2025-01-19 17:30:12 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][110/312]	eta 0:02:33 lr 0.000451	time 0.7264 (0.7585)	model_time 0.7262 (0.7452)	loss 3.2529 (2.7723)	grad_norm 3.0169 (2.0011/0.7540)	mem 34604MB
[2025-01-19 17:30:18 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][100/312]	eta 0:02:41 lr 0.000451	time 0.7182 (0.7616)	model_time 0.7180 (0.7469)	loss 2.5575 (2.7605)	grad_norm 2.6968 (2.3658/1.0239)	mem 34602MB
[2025-01-19 17:30:20 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][120/312]	eta 0:02:26 lr 0.000451	time 0.8893 (0.7609)	model_time 0.8888 (0.7486)	loss 2.6277 (2.7510)	grad_norm 3.7702 (2.0290/0.8231)	mem 34604MB
[2025-01-19 17:30:26 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][110/312]	eta 0:02:33 lr 0.000451	time 0.7196 (0.7611)	model_time 0.7191 (0.7477)	loss 2.9950 (2.7603)	grad_norm 1.2218 (2.3033/1.0058)	mem 34602MB
[2025-01-19 17:30:28 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][130/312]	eta 0:02:18 lr 0.000450	time 0.8326 (0.7602)	model_time 0.8321 (0.7488)	loss 2.9436 (2.7536)	grad_norm 3.5419 (2.0447/0.8168)	mem 34604MB
[2025-01-19 17:30:33 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][120/312]	eta 0:02:25 lr 0.000451	time 0.7293 (0.7594)	model_time 0.7291 (0.7471)	loss 2.6722 (2.7678)	grad_norm 1.7919 (2.3684/1.0366)	mem 34602MB
[2025-01-19 17:30:35 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][140/312]	eta 0:02:10 lr 0.000450	time 0.7265 (0.7582)	model_time 0.7263 (0.7476)	loss 2.8743 (2.7569)	grad_norm 0.9487 (2.0503/0.8327)	mem 34604MB
[2025-01-19 17:30:41 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][130/312]	eta 0:02:18 lr 0.000450	time 0.7205 (0.7594)	model_time 0.7203 (0.7481)	loss 2.5843 (2.7655)	grad_norm 4.0094 (2.4530/1.1204)	mem 34602MB
[2025-01-19 17:30:42 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][150/312]	eta 0:02:02 lr 0.000449	time 0.7573 (0.7568)	model_time 0.7572 (0.7469)	loss 3.2682 (2.7639)	grad_norm 1.5549 (2.0222/0.8158)	mem 34604MB
[2025-01-19 17:30:49 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][140/312]	eta 0:02:10 lr 0.000450	time 0.7236 (0.7600)	model_time 0.7235 (0.7494)	loss 2.6416 (2.7707)	grad_norm 1.1837 (2.4477/1.1114)	mem 34602MB
[2025-01-19 17:30:50 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][160/312]	eta 0:01:54 lr 0.000449	time 0.7506 (0.7556)	model_time 0.7502 (0.7463)	loss 2.5391 (2.7621)	grad_norm 2.3469 (2.0229/0.8003)	mem 34604MB
[2025-01-19 17:30:56 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][150/312]	eta 0:02:02 lr 0.000449	time 0.7289 (0.7580)	model_time 0.7287 (0.7481)	loss 2.9180 (2.7737)	grad_norm 2.1436 (2.3806/1.1090)	mem 34602MB
[2025-01-19 17:30:57 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][170/312]	eta 0:01:47 lr 0.000449	time 0.7213 (0.7542)	model_time 0.7211 (0.7454)	loss 2.6914 (2.7751)	grad_norm 1.3878 (2.0127/0.8069)	mem 34604MB
[2025-01-19 17:31:03 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][160/312]	eta 0:01:55 lr 0.000449	time 0.7238 (0.7570)	model_time 0.7234 (0.7477)	loss 2.6096 (2.7702)	grad_norm 4.0692 (2.3868/1.0989)	mem 34602MB
[2025-01-19 17:31:04 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][180/312]	eta 0:01:39 lr 0.000448	time 0.7221 (0.7527)	model_time 0.7219 (0.7444)	loss 3.3380 (2.7826)	grad_norm 2.4292 (1.9963/0.7948)	mem 34604MB
[2025-01-19 17:31:11 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][170/312]	eta 0:01:47 lr 0.000449	time 0.7163 (0.7557)	model_time 0.7162 (0.7469)	loss 2.9999 (2.7791)	grad_norm 1.7113 (2.3377/1.0866)	mem 34602MB
[2025-01-19 17:31:12 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][190/312]	eta 0:01:31 lr 0.000448	time 0.8075 (0.7522)	model_time 0.8071 (0.7443)	loss 2.6278 (2.7801)	grad_norm 1.9235 (1.9981/0.7827)	mem 34604MB
[2025-01-19 17:31:18 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][180/312]	eta 0:01:39 lr 0.000448	time 0.8096 (0.7549)	model_time 0.8094 (0.7466)	loss 3.0341 (2.7922)	grad_norm 2.9210 (2.3210/1.0663)	mem 34602MB
[2025-01-19 17:31:19 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][200/312]	eta 0:01:24 lr 0.000447	time 0.8120 (0.7522)	model_time 0.8116 (0.7447)	loss 3.0767 (2.7732)	grad_norm 2.0883 (1.9832/0.7747)	mem 34604MB
[2025-01-19 17:31:26 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][190/312]	eta 0:01:32 lr 0.000448	time 0.7215 (0.7555)	model_time 0.7214 (0.7476)	loss 2.9412 (2.7962)	grad_norm 1.5252 (2.3198/1.0664)	mem 34602MB
[2025-01-19 17:31:27 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][210/312]	eta 0:01:16 lr 0.000447	time 0.8161 (0.7528)	model_time 0.8160 (0.7456)	loss 2.8118 (2.7690)	grad_norm 2.2423 (1.9991/0.7745)	mem 34604MB
[2025-01-19 17:31:33 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][200/312]	eta 0:01:24 lr 0.000447	time 0.7249 (0.7559)	model_time 0.7245 (0.7484)	loss 2.7180 (2.7936)	grad_norm 3.1519 (2.3248/1.0614)	mem 34602MB
[2025-01-19 17:31:34 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][220/312]	eta 0:01:09 lr 0.000447	time 0.7170 (0.7520)	model_time 0.7165 (0.7451)	loss 2.4555 (2.7631)	grad_norm 3.9617 (2.0369/0.8026)	mem 34604MB
[2025-01-19 17:31:41 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][210/312]	eta 0:01:17 lr 0.000447	time 0.7202 (0.7559)	model_time 0.7200 (0.7487)	loss 2.9056 (2.7937)	grad_norm 1.8211 (2.2972/1.0617)	mem 34602MB
[2025-01-19 17:31:42 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][230/312]	eta 0:01:01 lr 0.000446	time 0.8162 (0.7530)	model_time 0.8160 (0.7464)	loss 2.7027 (2.7652)	grad_norm 5.4835 (2.0638/0.8441)	mem 34604MB
[2025-01-19 17:31:48 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][220/312]	eta 0:01:09 lr 0.000447	time 0.7232 (0.7549)	model_time 0.7228 (0.7481)	loss 3.0652 (2.7970)	grad_norm 1.7401 (2.2711/1.0482)	mem 34602MB
[2025-01-19 17:31:50 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][240/312]	eta 0:00:54 lr 0.000446	time 0.8741 (0.7536)	model_time 0.8740 (0.7473)	loss 2.4259 (2.7648)	grad_norm 2.8475 (2.0828/0.8537)	mem 34604MB
[2025-01-19 17:31:56 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][230/312]	eta 0:01:01 lr 0.000446	time 0.7202 (0.7548)	model_time 0.7200 (0.7482)	loss 1.7598 (2.7824)	grad_norm 1.3358 (2.2596/1.0388)	mem 34602MB
[2025-01-19 17:31:57 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][250/312]	eta 0:00:46 lr 0.000445	time 0.8183 (0.7533)	model_time 0.8178 (0.7472)	loss 3.0362 (2.7745)	grad_norm 2.1418 (2.0936/0.8592)	mem 34604MB
[2025-01-19 17:32:03 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][240/312]	eta 0:00:54 lr 0.000446	time 0.7240 (0.7539)	model_time 0.7236 (0.7475)	loss 2.6315 (2.7896)	grad_norm 3.4373 (2.2671/1.0319)	mem 34602MB
[2025-01-19 17:32:04 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][260/312]	eta 0:00:39 lr 0.000445	time 0.7331 (0.7526)	model_time 0.7330 (0.7467)	loss 3.2705 (2.7713)	grad_norm 2.4369 (2.0925/0.8508)	mem 34604MB
[2025-01-19 17:32:11 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][250/312]	eta 0:00:46 lr 0.000445	time 0.7172 (0.7533)	model_time 0.7170 (0.7472)	loss 3.3582 (2.7886)	grad_norm 2.9667 (2.2710/1.0264)	mem 34602MB
[2025-01-19 17:32:12 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][270/312]	eta 0:00:31 lr 0.000445	time 0.7251 (0.7516)	model_time 0.7246 (0.7460)	loss 2.9462 (2.7674)	grad_norm 2.1092 (2.0879/0.8409)	mem 34604MB
[2025-01-19 17:32:18 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][260/312]	eta 0:00:39 lr 0.000445	time 0.7182 (0.7535)	model_time 0.7178 (0.7476)	loss 2.6387 (2.7884)	grad_norm 1.9880 (2.2649/1.0167)	mem 34602MB
[2025-01-19 17:32:19 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][280/312]	eta 0:00:24 lr 0.000444	time 0.7335 (0.7511)	model_time 0.7333 (0.7456)	loss 2.5415 (2.7645)	grad_norm 1.6223 (2.0808/0.8352)	mem 34604MB
[2025-01-19 17:32:25 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][270/312]	eta 0:00:31 lr 0.000445	time 0.7277 (0.7524)	model_time 0.7276 (0.7467)	loss 2.8670 (2.7774)	grad_norm 1.2185 (2.2560/1.0026)	mem 34602MB
[2025-01-19 17:32:26 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][290/312]	eta 0:00:16 lr 0.000444	time 0.7236 (0.7501)	model_time 0.7231 (0.7448)	loss 2.4041 (2.7560)	grad_norm 2.6013 (2.0680/0.8290)	mem 34604MB
[2025-01-19 17:32:33 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][280/312]	eta 0:00:24 lr 0.000444	time 0.7258 (0.7519)	model_time 0.7256 (0.7464)	loss 3.1097 (2.7684)	grad_norm 1.2535 (2.2438/0.9919)	mem 34602MB
[2025-01-19 17:32:33 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][300/312]	eta 0:00:08 lr 0.000443	time 0.7144 (0.7494)	model_time 0.7143 (0.7442)	loss 3.0888 (2.7491)	grad_norm 1.7062 (2.0815/0.8345)	mem 34604MB
[2025-01-19 17:32:40 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][290/312]	eta 0:00:16 lr 0.000444	time 0.7171 (0.7513)	model_time 0.7170 (0.7460)	loss 2.8073 (2.7634)	grad_norm 2.1609 (2.2313/0.9804)	mem 34602MB
[2025-01-19 17:32:41 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][310/312]	eta 0:00:01 lr 0.000443	time 0.7142 (0.7482)	model_time 0.7141 (0.7432)	loss 2.8784 (2.7579)	grad_norm 5.1075 (2.1201/0.8567)	mem 34604MB
[2025-01-19 17:32:41 internimage_b_1k_224] (main.py 519): INFO EPOCH 237 training takes 0:03:53
[2025-01-19 17:32:41 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_237.pth saving......
[2025-01-19 17:32:44 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_237.pth saved !!!
[2025-01-19 17:32:48 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][300/312]	eta 0:00:09 lr 0.000443	time 0.7067 (0.7508)	model_time 0.7066 (0.7456)	loss 2.2066 (2.7586)	grad_norm 0.9344 (2.2191/0.9757)	mem 34602MB
[2025-01-19 17:32:52 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.330 (7.330)	Loss 0.6915 (0.6915)	Acc@1 85.938 (85.938)	Acc@5 97.803 (97.803)	Mem 34604MB
[2025-01-19 17:32:55 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.944)	Loss 0.9360 (0.7895)	Acc@1 79.810 (84.015)	Acc@5 95.508 (96.737)	Mem 34604MB
[2025-01-19 17:32:55 internimage_b_1k_224] (main.py 510): INFO Train: [237/300][310/312]	eta 0:00:01 lr 0.000443	time 0.7137 (0.7507)	model_time 0.7136 (0.7457)	loss 2.4864 (2.7599)	grad_norm 1.8115 (2.1949/0.9679)	mem 34602MB
[2025-01-19 17:32:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:237] * Acc@1 83.907 Acc@5 96.763
[2025-01-19 17:32:55 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.9%
[2025-01-19 17:32:55 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 17:32:56 internimage_b_1k_224] (main.py 519): INFO EPOCH 237 training takes 0:03:54
[2025-01-19 17:32:56 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_237.pth saving......
[2025-01-19 17:32:59 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_237.pth saved !!!
[2025-01-19 17:32:59 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 17:32:59 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.91%
[2025-01-19 17:33:14 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.516 (15.516)	Loss 0.7120 (0.7120)	Acc@1 86.401 (86.401)	Acc@5 98.145 (98.145)	Mem 34604MB
[2025-01-19 17:33:15 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.734 (15.734)	Loss 0.7038 (0.7038)	Acc@1 85.425 (85.425)	Acc@5 97.778 (97.778)	Mem 34602MB
[2025-01-19 17:33:22 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (2.095)	Loss 0.9318 (0.8090)	Acc@1 80.371 (84.038)	Acc@5 95.679 (96.866)	Mem 34604MB
[2025-01-19 17:33:22 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.107)	Loss 0.8978 (0.7810)	Acc@1 80.566 (83.816)	Acc@5 95.874 (96.822)	Mem 34602MB
[2025-01-19 17:33:22 internimage_b_1k_224] (main.py 575): INFO [Epoch:237] * Acc@1 83.881 Acc@5 96.897
[2025-01-19 17:33:22 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.9%
[2025-01-19 17:33:22 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:33:22 internimage_b_1k_224] (main.py 575): INFO [Epoch:237] * Acc@1 83.649 Acc@5 96.813
[2025-01-19 17:33:22 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.6%
[2025-01-19 17:33:22 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.81%
[2025-01-19 17:33:26 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:33:26 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.88%
[2025-01-19 17:33:28 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][0/312]	eta 0:10:18 lr 0.000443	time 1.9815 (1.9815)	model_time 0.7493 (0.7493)	loss 2.5159 (2.5159)	grad_norm 1.4321 (1.4321/0.0000)	mem 34604MB
[2025-01-19 17:33:32 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.262 (9.262)	Loss 0.7212 (0.7212)	Acc@1 86.011 (86.011)	Acc@5 98.242 (98.242)	Mem 34602MB
[2025-01-19 17:33:36 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][10/312]	eta 0:04:24 lr 0.000442	time 0.7218 (0.8753)	model_time 0.7214 (0.7629)	loss 3.3914 (2.7575)	grad_norm 1.6494 (2.1520/0.7318)	mem 34604MB
[2025-01-19 17:33:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.254)	Loss 0.9326 (0.8098)	Acc@1 79.907 (84.024)	Acc@5 95.947 (96.942)	Mem 34602MB
[2025-01-19 17:33:36 internimage_b_1k_224] (main.py 575): INFO [Epoch:237] * Acc@1 83.845 Acc@5 96.985
[2025-01-19 17:33:36 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.8%
[2025-01-19 17:33:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:33:40 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:33:40 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.85%
[2025-01-19 17:33:42 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][0/312]	eta 0:10:20 lr 0.000443	time 1.9878 (1.9878)	model_time 0.7389 (0.7389)	loss 2.7561 (2.7561)	grad_norm 1.0336 (1.0336/0.0000)	mem 34602MB
[2025-01-19 17:33:44 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][20/312]	eta 0:03:59 lr 0.000442	time 0.7273 (0.8205)	model_time 0.7271 (0.7615)	loss 2.0563 (2.7420)	grad_norm 1.8043 (2.1081/0.7437)	mem 34604MB
[2025-01-19 17:33:50 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][10/312]	eta 0:04:21 lr 0.000442	time 0.7211 (0.8671)	model_time 0.7207 (0.7532)	loss 2.7256 (2.7745)	grad_norm 1.7194 (1.9602/0.7277)	mem 34602MB
[2025-01-19 17:33:51 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][30/312]	eta 0:03:45 lr 0.000442	time 0.8110 (0.7998)	model_time 0.8108 (0.7597)	loss 3.0322 (2.7985)	grad_norm 1.8938 (2.0837/0.6663)	mem 34604MB
[2025-01-19 17:33:57 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][20/312]	eta 0:03:55 lr 0.000442	time 0.7172 (0.8076)	model_time 0.7171 (0.7478)	loss 3.1572 (2.8023)	grad_norm 1.6266 (2.0366/0.8668)	mem 34602MB
[2025-01-19 17:33:59 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][40/312]	eta 0:03:35 lr 0.000441	time 0.7174 (0.7908)	model_time 0.7169 (0.7603)	loss 3.1106 (2.8164)	grad_norm 2.6851 (2.1364/0.6729)	mem 34604MB
[2025-01-19 17:34:05 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][30/312]	eta 0:03:41 lr 0.000442	time 0.8002 (0.7837)	model_time 0.8001 (0.7431)	loss 2.7632 (2.7681)	grad_norm 2.0894 (1.9947/0.7657)	mem 34602MB
[2025-01-19 17:34:06 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][50/312]	eta 0:03:25 lr 0.000441	time 0.7160 (0.7834)	model_time 0.7158 (0.7588)	loss 2.8492 (2.8162)	grad_norm 1.7046 (2.1328/0.6398)	mem 34604MB
[2025-01-19 17:34:12 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][40/312]	eta 0:03:31 lr 0.000441	time 0.7325 (0.7760)	model_time 0.7321 (0.7451)	loss 2.1661 (2.7992)	grad_norm 1.7572 (1.8852/0.7033)	mem 34602MB
[2025-01-19 17:34:14 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][60/312]	eta 0:03:15 lr 0.000440	time 0.7249 (0.7760)	model_time 0.7244 (0.7554)	loss 3.3113 (2.8238)	grad_norm 3.2445 (2.1844/0.6762)	mem 34604MB
[2025-01-19 17:34:20 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][50/312]	eta 0:03:21 lr 0.000441	time 0.7175 (0.7704)	model_time 0.7170 (0.7455)	loss 2.7848 (2.7838)	grad_norm 2.3010 (1.9060/0.7137)	mem 34602MB
[2025-01-19 17:34:21 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][70/312]	eta 0:03:06 lr 0.000440	time 0.7267 (0.7701)	model_time 0.7263 (0.7524)	loss 2.7535 (2.8103)	grad_norm 2.2850 (2.1663/0.6512)	mem 34604MB
[2025-01-19 17:34:27 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][60/312]	eta 0:03:12 lr 0.000440	time 0.7187 (0.7657)	model_time 0.7185 (0.7449)	loss 2.0961 (2.7916)	grad_norm 1.8366 (2.0785/0.9424)	mem 34602MB
[2025-01-19 17:34:28 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][80/312]	eta 0:02:57 lr 0.000440	time 0.7288 (0.7647)	model_time 0.7286 (0.7492)	loss 3.2452 (2.8061)	grad_norm 2.2826 (2.1199/0.6589)	mem 34604MB
[2025-01-19 17:34:35 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][70/312]	eta 0:03:05 lr 0.000440	time 0.8038 (0.7655)	model_time 0.8036 (0.7476)	loss 3.2642 (2.8211)	grad_norm 3.5904 (2.1460/1.0013)	mem 34602MB
[2025-01-19 17:34:36 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][90/312]	eta 0:02:49 lr 0.000439	time 0.7235 (0.7620)	model_time 0.7231 (0.7480)	loss 1.9239 (2.7950)	grad_norm 1.8994 (2.1347/0.6766)	mem 34604MB
[2025-01-19 17:34:42 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][80/312]	eta 0:02:56 lr 0.000440	time 0.7292 (0.7614)	model_time 0.7290 (0.7456)	loss 3.1898 (2.8345)	grad_norm 1.7077 (2.1367/0.9837)	mem 34602MB
[2025-01-19 17:34:43 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][100/312]	eta 0:02:40 lr 0.000439	time 0.7324 (0.7588)	model_time 0.7322 (0.7462)	loss 2.7592 (2.7928)	grad_norm 2.2182 (2.1513/0.6942)	mem 34604MB
[2025-01-19 17:34:49 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][90/312]	eta 0:02:48 lr 0.000439	time 0.7179 (0.7597)	model_time 0.7174 (0.7456)	loss 3.0277 (2.8191)	grad_norm 2.1899 (2.1134/0.9569)	mem 34602MB
[2025-01-19 17:34:50 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][110/312]	eta 0:02:32 lr 0.000438	time 0.7360 (0.7563)	model_time 0.7358 (0.7448)	loss 2.9807 (2.7884)	grad_norm 3.4794 (2.1863/0.7126)	mem 34604MB
[2025-01-19 17:34:57 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][100/312]	eta 0:02:40 lr 0.000439	time 0.7160 (0.7576)	model_time 0.7155 (0.7448)	loss 3.4108 (2.8496)	grad_norm 1.1091 (2.1740/1.0141)	mem 34602MB
[2025-01-19 17:34:58 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][120/312]	eta 0:02:24 lr 0.000438	time 0.7247 (0.7538)	model_time 0.7246 (0.7432)	loss 2.2712 (2.7873)	grad_norm 1.7139 (2.2577/0.8328)	mem 34604MB
[2025-01-19 17:35:04 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][110/312]	eta 0:02:32 lr 0.000438	time 0.7196 (0.7563)	model_time 0.7194 (0.7447)	loss 2.5867 (2.8435)	grad_norm 2.3201 (2.1772/1.0396)	mem 34602MB
[2025-01-19 17:35:05 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][130/312]	eta 0:02:17 lr 0.000438	time 0.7166 (0.7546)	model_time 0.7164 (0.7449)	loss 2.5632 (2.7888)	grad_norm 1.6482 (2.2638/0.8371)	mem 34604MB
[2025-01-19 17:35:12 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][120/312]	eta 0:02:25 lr 0.000438	time 0.7229 (0.7564)	model_time 0.7225 (0.7457)	loss 2.4924 (2.8352)	grad_norm 1.4525 (2.1402/1.0192)	mem 34602MB
[2025-01-19 17:35:13 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][140/312]	eta 0:02:09 lr 0.000437	time 0.7229 (0.7554)	model_time 0.7225 (0.7463)	loss 1.9993 (2.7659)	grad_norm 2.0153 (2.2498/0.8270)	mem 34604MB
[2025-01-19 17:35:19 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][130/312]	eta 0:02:17 lr 0.000438	time 0.7265 (0.7567)	model_time 0.7263 (0.7468)	loss 2.2524 (2.8397)	grad_norm 2.0135 (2.1096/0.9927)	mem 34602MB
[2025-01-19 17:35:20 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][150/312]	eta 0:02:02 lr 0.000437	time 0.8010 (0.7554)	model_time 0.8008 (0.7468)	loss 3.3021 (2.7746)	grad_norm 2.1578 (2.2638/0.8301)	mem 34604MB
[2025-01-19 17:35:27 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][140/312]	eta 0:02:10 lr 0.000437	time 0.8076 (0.7565)	model_time 0.8071 (0.7472)	loss 2.6014 (2.8489)	grad_norm 1.1255 (2.0971/0.9786)	mem 34602MB
[2025-01-19 17:35:28 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][160/312]	eta 0:01:55 lr 0.000436	time 0.7463 (0.7569)	model_time 0.7461 (0.7489)	loss 2.9997 (2.7803)	grad_norm 2.0442 (2.2670/0.8497)	mem 34604MB
[2025-01-19 17:35:34 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][150/312]	eta 0:02:02 lr 0.000437	time 0.8048 (0.7549)	model_time 0.8047 (0.7462)	loss 2.2838 (2.8342)	grad_norm 2.2276 (2.1371/0.9848)	mem 34602MB
[2025-01-19 17:35:36 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][170/312]	eta 0:01:47 lr 0.000436	time 0.7180 (0.7568)	model_time 0.7176 (0.7492)	loss 2.3208 (2.7877)	grad_norm 3.1054 (2.2868/0.8872)	mem 34604MB
[2025-01-19 17:35:42 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][160/312]	eta 0:01:54 lr 0.000436	time 0.7302 (0.7546)	model_time 0.7298 (0.7465)	loss 2.6829 (2.8189)	grad_norm 1.6582 (2.1280/0.9696)	mem 34602MB
[2025-01-19 17:35:43 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][180/312]	eta 0:01:39 lr 0.000436	time 0.7523 (0.7559)	model_time 0.7522 (0.7488)	loss 3.0055 (2.7811)	grad_norm 1.0820 (2.2635/0.8837)	mem 34604MB
[2025-01-19 17:35:49 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][170/312]	eta 0:01:47 lr 0.000436	time 0.7164 (0.7538)	model_time 0.7162 (0.7461)	loss 2.8067 (2.8191)	grad_norm 1.9192 (2.1065/0.9526)	mem 34602MB
[2025-01-19 17:35:51 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][190/312]	eta 0:01:32 lr 0.000435	time 0.7264 (0.7549)	model_time 0.7259 (0.7480)	loss 2.9888 (2.7838)	grad_norm 1.2745 (2.2536/0.8731)	mem 34604MB
[2025-01-19 17:35:57 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][180/312]	eta 0:01:39 lr 0.000436	time 0.7176 (0.7540)	model_time 0.7172 (0.7467)	loss 3.2057 (2.8127)	grad_norm 1.7502 (2.1162/0.9736)	mem 34602MB
[2025-01-19 17:35:58 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][200/312]	eta 0:01:24 lr 0.000435	time 0.7284 (0.7535)	model_time 0.7279 (0.7470)	loss 2.7238 (2.7845)	grad_norm 1.2994 (2.2470/0.8841)	mem 34604MB
[2025-01-19 17:36:04 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][190/312]	eta 0:01:32 lr 0.000435	time 0.8028 (0.7543)	model_time 0.8026 (0.7474)	loss 3.2913 (2.8037)	grad_norm 3.4270 (2.1476/0.9769)	mem 34602MB
[2025-01-19 17:36:05 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][210/312]	eta 0:01:16 lr 0.000434	time 0.7224 (0.7524)	model_time 0.7223 (0.7462)	loss 3.1068 (2.7897)	grad_norm 1.2084 (2.2391/0.8785)	mem 34604MB
[2025-01-19 17:36:12 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][200/312]	eta 0:01:24 lr 0.000435	time 0.7181 (0.7529)	model_time 0.7180 (0.7463)	loss 2.7217 (2.8035)	grad_norm 2.4045 (2.1710/0.9779)	mem 34602MB
[2025-01-19 17:36:12 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][220/312]	eta 0:01:09 lr 0.000434	time 0.7307 (0.7515)	model_time 0.7305 (0.7456)	loss 2.6482 (2.7846)	grad_norm 2.1305 (2.2311/0.8649)	mem 34604MB
[2025-01-19 17:36:19 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][210/312]	eta 0:01:16 lr 0.000434	time 0.7185 (0.7520)	model_time 0.7181 (0.7457)	loss 3.2836 (2.8081)	grad_norm 1.7920 (2.1981/0.9978)	mem 34602MB
[2025-01-19 17:36:20 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][230/312]	eta 0:01:01 lr 0.000434	time 0.7232 (0.7505)	model_time 0.7230 (0.7448)	loss 1.6952 (2.7799)	grad_norm 1.4452 (2.2254/0.8655)	mem 34604MB
[2025-01-19 17:36:26 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][220/312]	eta 0:01:09 lr 0.000434	time 0.7162 (0.7520)	model_time 0.7160 (0.7460)	loss 2.8056 (2.8124)	grad_norm 1.8445 (2.1942/0.9880)	mem 34602MB
[2025-01-19 17:36:27 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][240/312]	eta 0:00:53 lr 0.000433	time 0.7277 (0.7497)	model_time 0.7276 (0.7442)	loss 2.5651 (2.7823)	grad_norm 1.6657 (2.2314/0.8601)	mem 34604MB
[2025-01-19 17:36:34 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][230/312]	eta 0:01:01 lr 0.000434	time 0.7196 (0.7515)	model_time 0.7192 (0.7457)	loss 2.7277 (2.8125)	grad_norm 1.7898 (2.1850/0.9709)	mem 34602MB
[2025-01-19 17:36:35 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][250/312]	eta 0:00:46 lr 0.000433	time 0.7211 (0.7498)	model_time 0.7210 (0.7446)	loss 3.1773 (2.7766)	grad_norm 1.3327 (2.2131/0.8522)	mem 34604MB
[2025-01-19 17:36:41 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][240/312]	eta 0:00:54 lr 0.000433	time 0.7172 (0.7517)	model_time 0.7167 (0.7461)	loss 3.0998 (2.8098)	grad_norm 1.1555 (2.1650/0.9603)	mem 34602MB
[2025-01-19 17:36:42 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][260/312]	eta 0:00:38 lr 0.000432	time 0.7296 (0.7499)	model_time 0.7294 (0.7448)	loss 2.7896 (2.7731)	grad_norm 1.2976 (2.2131/0.8424)	mem 34604MB
[2025-01-19 17:36:49 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][250/312]	eta 0:00:46 lr 0.000433	time 0.7161 (0.7516)	model_time 0.7159 (0.7462)	loss 3.0142 (2.8028)	grad_norm 1.2357 (2.1369/0.9557)	mem 34602MB
[2025-01-19 17:36:50 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][270/312]	eta 0:00:31 lr 0.000432	time 0.8110 (0.7498)	model_time 0.8108 (0.7449)	loss 2.3433 (2.7721)	grad_norm 1.1413 (2.1918/0.8414)	mem 34604MB
[2025-01-19 17:36:56 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][260/312]	eta 0:00:39 lr 0.000432	time 0.8206 (0.7518)	model_time 0.8204 (0.7466)	loss 2.9664 (2.8007)	grad_norm 1.5164 (2.1362/0.9437)	mem 34602MB
[2025-01-19 17:36:57 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][280/312]	eta 0:00:23 lr 0.000432	time 0.7100 (0.7500)	model_time 0.7095 (0.7452)	loss 2.9757 (2.7638)	grad_norm 1.5589 (2.1789/0.8369)	mem 34604MB
[2025-01-19 17:37:04 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][270/312]	eta 0:00:31 lr 0.000432	time 0.8055 (0.7513)	model_time 0.8051 (0.7463)	loss 3.1282 (2.8019)	grad_norm 3.7220 (2.1356/0.9366)	mem 34602MB
[2025-01-19 17:37:05 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][290/312]	eta 0:00:16 lr 0.000431	time 0.7143 (0.7508)	model_time 0.7139 (0.7462)	loss 2.4577 (2.7628)	grad_norm 4.2493 (2.1987/0.8584)	mem 34604MB
[2025-01-19 17:37:11 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][280/312]	eta 0:00:24 lr 0.000432	time 0.7176 (0.7510)	model_time 0.7174 (0.7462)	loss 2.5999 (2.8022)	grad_norm 2.7625 (2.1710/0.9864)	mem 34602MB
[2025-01-19 17:37:12 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][300/312]	eta 0:00:09 lr 0.000431	time 0.7153 (0.7504)	model_time 0.7152 (0.7459)	loss 2.9827 (2.7653)	grad_norm 1.2381 (2.1830/0.8563)	mem 34604MB
[2025-01-19 17:37:19 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][290/312]	eta 0:00:16 lr 0.000431	time 0.7327 (0.7507)	model_time 0.7323 (0.7461)	loss 2.0043 (2.7918)	grad_norm 2.1630 (2.1811/0.9858)	mem 34602MB
[2025-01-19 17:37:20 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][310/312]	eta 0:00:01 lr 0.000431	time 0.7162 (0.7495)	model_time 0.7161 (0.7452)	loss 2.9144 (2.7668)	grad_norm 2.1267 (2.1703/0.8552)	mem 34604MB
[2025-01-19 17:37:20 internimage_b_1k_224] (main.py 519): INFO EPOCH 238 training takes 0:03:53
[2025-01-19 17:37:20 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_238.pth saving......
[2025-01-19 17:37:23 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_238.pth saved !!!
[2025-01-19 17:37:26 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][300/312]	eta 0:00:09 lr 0.000431	time 0.7139 (0.7505)	model_time 0.7138 (0.7460)	loss 2.5330 (2.7896)	grad_norm 1.7960 (2.1951/0.9810)	mem 34602MB
[2025-01-19 17:37:31 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.274 (7.274)	Loss 0.7129 (0.7129)	Acc@1 86.035 (86.035)	Acc@5 97.656 (97.656)	Mem 34604MB
[2025-01-19 17:37:34 internimage_b_1k_224] (main.py 510): INFO Train: [238/300][310/312]	eta 0:00:01 lr 0.000431	time 0.7129 (0.7507)	model_time 0.7128 (0.7463)	loss 2.0372 (2.7924)	grad_norm 1.9628 (2.1998/0.9793)	mem 34602MB
[2025-01-19 17:37:34 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.952)	Loss 0.9132 (0.7966)	Acc@1 80.859 (84.053)	Acc@5 95.850 (96.793)	Mem 34604MB
[2025-01-19 17:37:34 internimage_b_1k_224] (main.py 575): INFO [Epoch:238] * Acc@1 83.875 Acc@5 96.793
[2025-01-19 17:37:34 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.9%
[2025-01-19 17:37:34 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.91%
[2025-01-19 17:37:34 internimage_b_1k_224] (main.py 519): INFO EPOCH 238 training takes 0:03:54
[2025-01-19 17:37:34 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_238.pth saving......
[2025-01-19 17:37:38 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_238.pth saved !!!
[2025-01-19 17:37:52 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.675 (17.675)	Loss 0.7121 (0.7121)	Acc@1 86.450 (86.450)	Acc@5 98.145 (98.145)	Mem 34604MB
[2025-01-19 17:37:54 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.356 (16.356)	Loss 0.7461 (0.7461)	Acc@1 85.400 (85.400)	Acc@5 97.705 (97.705)	Mem 34602MB
[2025-01-19 17:38:01 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.413)	Loss 0.9313 (0.8087)	Acc@1 80.493 (84.064)	Acc@5 95.703 (96.877)	Mem 34604MB
[2025-01-19 17:38:01 internimage_b_1k_224] (main.py 575): INFO [Epoch:238] * Acc@1 83.911 Acc@5 96.911
[2025-01-19 17:38:01 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.9%
[2025-01-19 17:38:01 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:38:01 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (2.112)	Loss 0.9409 (0.8198)	Acc@1 80.078 (83.964)	Acc@5 95.459 (96.697)	Mem 34602MB
[2025-01-19 17:38:01 internimage_b_1k_224] (main.py 575): INFO [Epoch:238] * Acc@1 83.807 Acc@5 96.713
[2025-01-19 17:38:01 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.8%
[2025-01-19 17:38:01 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.81%
[2025-01-19 17:38:05 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:38:05 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.91%
[2025-01-19 17:38:07 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][0/312]	eta 0:11:33 lr 0.000430	time 2.2229 (2.2229)	model_time 0.7444 (0.7444)	loss 3.2726 (3.2726)	grad_norm 1.6548 (1.6548/0.0000)	mem 34604MB
[2025-01-19 17:38:11 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.499 (9.499)	Loss 0.7214 (0.7214)	Acc@1 86.035 (86.035)	Acc@5 98.242 (98.242)	Mem 34602MB
[2025-01-19 17:38:15 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][10/312]	eta 0:04:23 lr 0.000430	time 0.7339 (0.8725)	model_time 0.7337 (0.7378)	loss 2.8957 (2.8688)	grad_norm 1.9925 (1.6247/0.2326)	mem 34604MB
[2025-01-19 17:38:15 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.282)	Loss 0.9319 (0.8095)	Acc@1 80.005 (84.053)	Acc@5 95.996 (96.955)	Mem 34602MB
[2025-01-19 17:38:16 internimage_b_1k_224] (main.py 575): INFO [Epoch:238] * Acc@1 83.867 Acc@5 96.997
[2025-01-19 17:38:16 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.9%
[2025-01-19 17:38:16 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:38:19 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:38:19 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.87%
[2025-01-19 17:38:22 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][0/312]	eta 0:11:19 lr 0.000430	time 2.1773 (2.1773)	model_time 0.7591 (0.7591)	loss 2.9864 (2.9864)	grad_norm 2.2598 (2.2598/0.0000)	mem 34602MB
[2025-01-19 17:38:22 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][20/312]	eta 0:03:56 lr 0.000430	time 0.7355 (0.8098)	model_time 0.7353 (0.7390)	loss 3.2548 (2.9425)	grad_norm 1.5317 (1.6667/0.4954)	mem 34604MB
[2025-01-19 17:38:29 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][10/312]	eta 0:04:19 lr 0.000430	time 0.7188 (0.8596)	model_time 0.7186 (0.7304)	loss 2.6456 (2.7120)	grad_norm 2.8546 (2.2037/0.5109)	mem 34602MB
[2025-01-19 17:38:29 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][30/312]	eta 0:03:41 lr 0.000429	time 0.7225 (0.7838)	model_time 0.7224 (0.7358)	loss 2.0070 (2.8309)	grad_norm 1.5524 (1.7128/0.4971)	mem 34604MB
[2025-01-19 17:38:36 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][20/312]	eta 0:03:56 lr 0.000430	time 0.8074 (0.8093)	model_time 0.8070 (0.7414)	loss 3.0512 (2.7509)	grad_norm 2.0496 (2.1239/0.5353)	mem 34602MB
[2025-01-19 17:38:37 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][40/312]	eta 0:03:29 lr 0.000429	time 0.7431 (0.7718)	model_time 0.7427 (0.7354)	loss 3.2438 (2.8392)	grad_norm 2.6772 (1.8619/0.6071)	mem 34604MB
[2025-01-19 17:38:44 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][30/312]	eta 0:03:41 lr 0.000429	time 0.7218 (0.7838)	model_time 0.7216 (0.7378)	loss 3.2280 (2.7622)	grad_norm 1.6740 (2.0298/0.5076)	mem 34602MB
[2025-01-19 17:38:44 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][50/312]	eta 0:03:20 lr 0.000428	time 0.7244 (0.7641)	model_time 0.7242 (0.7348)	loss 2.2462 (2.8375)	grad_norm 2.8170 (2.0108/0.7799)	mem 34604MB
[2025-01-19 17:38:51 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][40/312]	eta 0:03:30 lr 0.000429	time 0.7182 (0.7750)	model_time 0.7178 (0.7401)	loss 2.8710 (2.8397)	grad_norm 2.0764 (1.9708/0.5269)	mem 34602MB
[2025-01-19 17:38:52 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][60/312]	eta 0:03:12 lr 0.000428	time 0.8012 (0.7630)	model_time 0.8011 (0.7384)	loss 2.6338 (2.8177)	grad_norm 1.6238 (2.0700/0.7863)	mem 34604MB
[2025-01-19 17:38:59 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][50/312]	eta 0:03:21 lr 0.000428	time 0.8067 (0.7699)	model_time 0.8062 (0.7418)	loss 2.9855 (2.7855)	grad_norm 1.2845 (2.0097/0.6033)	mem 34602MB
[2025-01-19 17:38:59 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][70/312]	eta 0:03:04 lr 0.000428	time 0.7262 (0.7623)	model_time 0.7258 (0.7412)	loss 2.6375 (2.8073)	grad_norm 1.2999 (2.0819/0.7707)	mem 34604MB
[2025-01-19 17:39:06 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][60/312]	eta 0:03:13 lr 0.000428	time 0.8148 (0.7668)	model_time 0.8146 (0.7432)	loss 2.6389 (2.7362)	grad_norm 2.8794 (2.0225/0.6366)	mem 34602MB
[2025-01-19 17:39:07 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][80/312]	eta 0:02:56 lr 0.000427	time 0.8159 (0.7598)	model_time 0.8154 (0.7412)	loss 2.9347 (2.7920)	grad_norm 1.5714 (2.0340/0.7473)	mem 34604MB
[2025-01-19 17:39:14 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][70/312]	eta 0:03:05 lr 0.000428	time 0.7516 (0.7648)	model_time 0.7511 (0.7445)	loss 3.1620 (2.7800)	grad_norm 1.3926 (2.0610/0.6866)	mem 34602MB
[2025-01-19 17:39:14 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][90/312]	eta 0:02:49 lr 0.000427	time 0.7167 (0.7626)	model_time 0.7166 (0.7460)	loss 2.3654 (2.7728)	grad_norm 4.9157 (2.1164/0.8259)	mem 34604MB
[2025-01-19 17:39:21 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][80/312]	eta 0:02:56 lr 0.000427	time 0.7180 (0.7623)	model_time 0.7176 (0.7444)	loss 1.8503 (2.7801)	grad_norm 1.7658 (2.1330/0.7451)	mem 34602MB
[2025-01-19 17:39:22 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][100/312]	eta 0:02:41 lr 0.000426	time 0.8101 (0.7625)	model_time 0.8100 (0.7476)	loss 2.9004 (2.7755)	grad_norm 2.4561 (2.2225/0.9347)	mem 34604MB
[2025-01-19 17:39:29 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][90/312]	eta 0:02:48 lr 0.000427	time 0.7180 (0.7604)	model_time 0.7178 (0.7445)	loss 2.9985 (2.7984)	grad_norm 2.8971 (2.1666/0.8188)	mem 34602MB
[2025-01-19 17:39:29 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][110/312]	eta 0:02:33 lr 0.000426	time 0.7251 (0.7598)	model_time 0.7249 (0.7461)	loss 3.0584 (2.7899)	grad_norm 3.7619 (2.2860/0.9631)	mem 34604MB
[2025-01-19 17:39:36 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][100/312]	eta 0:02:40 lr 0.000426	time 0.7225 (0.7591)	model_time 0.7220 (0.7447)	loss 2.8291 (2.7946)	grad_norm 1.5069 (2.1296/0.7985)	mem 34602MB
[2025-01-19 17:39:37 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][120/312]	eta 0:02:25 lr 0.000426	time 0.7097 (0.7582)	model_time 0.7092 (0.7456)	loss 2.3649 (2.7777)	grad_norm 3.1240 (2.2906/0.9509)	mem 34604MB
[2025-01-19 17:39:43 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][110/312]	eta 0:02:33 lr 0.000426	time 0.7242 (0.7575)	model_time 0.7236 (0.7444)	loss 2.7242 (2.7976)	grad_norm 1.8712 (2.0833/0.7851)	mem 34602MB
[2025-01-19 17:39:44 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][130/312]	eta 0:02:17 lr 0.000425	time 0.7159 (0.7566)	model_time 0.7158 (0.7450)	loss 2.2378 (2.7623)	grad_norm 1.6606 (2.3403/1.0083)	mem 34604MB
[2025-01-19 17:39:51 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][120/312]	eta 0:02:25 lr 0.000426	time 0.8004 (0.7578)	model_time 0.8002 (0.7458)	loss 3.2188 (2.8026)	grad_norm 1.8191 (2.0506/0.7716)	mem 34602MB
[2025-01-19 17:39:52 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][140/312]	eta 0:02:09 lr 0.000425	time 0.7420 (0.7551)	model_time 0.7419 (0.7442)	loss 1.7727 (2.7628)	grad_norm 3.6437 (2.3629/1.0035)	mem 34604MB
[2025-01-19 17:39:58 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][130/312]	eta 0:02:17 lr 0.000425	time 0.7185 (0.7552)	model_time 0.7182 (0.7440)	loss 2.4077 (2.8054)	grad_norm 3.3433 (2.0588/0.7581)	mem 34602MB
[2025-01-19 17:39:59 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][150/312]	eta 0:02:02 lr 0.000424	time 0.7200 (0.7532)	model_time 0.7196 (0.7430)	loss 3.1870 (2.7786)	grad_norm 1.8101 (2.3512/0.9867)	mem 34604MB
[2025-01-19 17:40:06 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][140/312]	eta 0:02:09 lr 0.000425	time 0.8112 (0.7550)	model_time 0.8108 (0.7446)	loss 3.1043 (2.7967)	grad_norm 3.3498 (2.0459/0.7588)	mem 34602MB
[2025-01-19 17:40:06 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][160/312]	eta 0:01:54 lr 0.000424	time 0.7140 (0.7517)	model_time 0.7136 (0.7421)	loss 2.8942 (2.7814)	grad_norm 2.3372 (2.3350/0.9707)	mem 34604MB
[2025-01-19 17:40:13 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][150/312]	eta 0:02:02 lr 0.000424	time 0.7193 (0.7534)	model_time 0.7192 (0.7436)	loss 3.3882 (2.7996)	grad_norm 1.5650 (2.0601/0.7512)	mem 34602MB
[2025-01-19 17:40:13 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][170/312]	eta 0:01:46 lr 0.000424	time 0.7317 (0.7504)	model_time 0.7315 (0.7414)	loss 3.0840 (2.7848)	grad_norm 1.6273 (2.3210/0.9518)	mem 34604MB
[2025-01-19 17:40:21 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][160/312]	eta 0:01:54 lr 0.000424	time 0.7161 (0.7530)	model_time 0.7156 (0.7439)	loss 2.9676 (2.8055)	grad_norm 1.5195 (2.0372/0.7494)	mem 34602MB
[2025-01-19 17:40:21 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][180/312]	eta 0:01:39 lr 0.000423	time 0.7986 (0.7512)	model_time 0.7982 (0.7427)	loss 2.9672 (2.7931)	grad_norm 4.8703 (2.3306/0.9479)	mem 34604MB
[2025-01-19 17:40:28 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][170/312]	eta 0:01:46 lr 0.000424	time 0.8013 (0.7529)	model_time 0.8012 (0.7443)	loss 3.0104 (2.8174)	grad_norm 2.2174 (2.0257/0.7387)	mem 34602MB
[2025-01-19 17:40:29 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][190/312]	eta 0:01:31 lr 0.000423	time 0.7177 (0.7525)	model_time 0.7176 (0.7444)	loss 2.2376 (2.7943)	grad_norm 3.2905 (2.3730/1.0017)	mem 34604MB
[2025-01-19 17:40:36 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][180/312]	eta 0:01:39 lr 0.000423	time 0.8595 (0.7530)	model_time 0.8591 (0.7448)	loss 3.0279 (2.8172)	grad_norm 4.2120 (2.0276/0.7480)	mem 34602MB
[2025-01-19 17:40:36 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][200/312]	eta 0:01:24 lr 0.000423	time 0.7323 (0.7521)	model_time 0.7322 (0.7444)	loss 3.1251 (2.7965)	grad_norm 2.6240 (2.3583/0.9951)	mem 34604MB
[2025-01-19 17:40:43 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][190/312]	eta 0:01:31 lr 0.000423	time 0.7405 (0.7532)	model_time 0.7403 (0.7454)	loss 3.0020 (2.8140)	grad_norm 1.3377 (2.0365/0.7668)	mem 34602MB
[2025-01-19 17:40:44 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][210/312]	eta 0:01:16 lr 0.000422	time 0.8049 (0.7537)	model_time 0.8047 (0.7464)	loss 2.9823 (2.7934)	grad_norm 1.2565 (2.3467/0.9887)	mem 34604MB
[2025-01-19 17:40:51 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][200/312]	eta 0:01:24 lr 0.000423	time 0.7418 (0.7535)	model_time 0.7413 (0.7461)	loss 2.6477 (2.8063)	grad_norm 1.1307 (2.0502/0.7694)	mem 34602MB
[2025-01-19 17:40:52 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][220/312]	eta 0:01:09 lr 0.000422	time 0.8094 (0.7545)	model_time 0.8091 (0.7475)	loss 3.2948 (2.7957)	grad_norm 3.1097 (2.3511/0.9793)	mem 34604MB
[2025-01-19 17:40:58 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][210/312]	eta 0:01:16 lr 0.000422	time 0.7347 (0.7531)	model_time 0.7343 (0.7460)	loss 3.2999 (2.8008)	grad_norm 2.1954 (2.0538/0.7620)	mem 34602MB
[2025-01-19 17:40:59 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][230/312]	eta 0:01:01 lr 0.000421	time 0.7223 (0.7539)	model_time 0.7219 (0.7472)	loss 2.3207 (2.7902)	grad_norm 2.9538 (2.3558/0.9727)	mem 34604MB
[2025-01-19 17:41:06 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][220/312]	eta 0:01:09 lr 0.000422	time 0.7209 (0.7530)	model_time 0.7207 (0.7462)	loss 3.0737 (2.8007)	grad_norm 1.4146 (2.0406/0.7610)	mem 34602MB
[2025-01-19 17:41:07 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][240/312]	eta 0:00:54 lr 0.000421	time 0.7259 (0.7531)	model_time 0.7254 (0.7466)	loss 2.5561 (2.7941)	grad_norm 2.7736 (2.3603/1.0012)	mem 34604MB
[2025-01-19 17:41:13 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][230/312]	eta 0:01:01 lr 0.000421	time 0.7195 (0.7527)	model_time 0.7190 (0.7462)	loss 2.9294 (2.8040)	grad_norm 1.2653 (2.0237/0.7542)	mem 34602MB
[2025-01-19 17:41:14 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][250/312]	eta 0:00:46 lr 0.000421	time 0.7242 (0.7525)	model_time 0.7240 (0.7463)	loss 2.4536 (2.7904)	grad_norm 3.5131 (2.3716/0.9942)	mem 34604MB
[2025-01-19 17:41:21 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][240/312]	eta 0:00:54 lr 0.000421	time 0.7168 (0.7524)	model_time 0.7166 (0.7462)	loss 3.0272 (2.8086)	grad_norm 2.8724 (2.0419/0.7576)	mem 34602MB
[2025-01-19 17:41:21 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][260/312]	eta 0:00:39 lr 0.000420	time 0.7221 (0.7519)	model_time 0.7217 (0.7459)	loss 2.1254 (2.7963)	grad_norm 0.8950 (2.3641/1.0004)	mem 34604MB
[2025-01-19 17:41:28 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][250/312]	eta 0:00:46 lr 0.000421	time 0.7227 (0.7516)	model_time 0.7225 (0.7456)	loss 3.0569 (2.8038)	grad_norm 3.8056 (2.0500/0.7715)	mem 34602MB
[2025-01-19 17:41:29 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][270/312]	eta 0:00:31 lr 0.000420	time 0.7242 (0.7509)	model_time 0.7241 (0.7451)	loss 2.1857 (2.7867)	grad_norm 2.7680 (2.3782/1.0244)	mem 34604MB
[2025-01-19 17:41:35 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][260/312]	eta 0:00:39 lr 0.000420	time 0.7224 (0.7510)	model_time 0.7223 (0.7452)	loss 2.6489 (2.7950)	grad_norm 2.7900 (2.0667/0.7876)	mem 34602MB
[2025-01-19 17:41:36 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][280/312]	eta 0:00:24 lr 0.000419	time 0.7245 (0.7501)	model_time 0.7244 (0.7444)	loss 3.2333 (2.7809)	grad_norm 3.7816 (2.3803/1.0232)	mem 34604MB
[2025-01-19 17:41:43 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][270/312]	eta 0:00:31 lr 0.000420	time 0.7295 (0.7506)	model_time 0.7293 (0.7451)	loss 3.6263 (2.7943)	grad_norm 1.0922 (2.0605/0.7974)	mem 34602MB
[2025-01-19 17:41:43 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][290/312]	eta 0:00:16 lr 0.000419	time 0.7203 (0.7492)	model_time 0.7201 (0.7437)	loss 2.6704 (2.7794)	grad_norm 1.9631 (2.3744/1.0114)	mem 34604MB
[2025-01-19 17:41:50 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][280/312]	eta 0:00:24 lr 0.000419	time 0.7170 (0.7506)	model_time 0.7165 (0.7452)	loss 3.2239 (2.7955)	grad_norm 0.9090 (2.0555/0.8053)	mem 34602MB
[2025-01-19 17:41:51 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][300/312]	eta 0:00:08 lr 0.000419	time 0.7850 (0.7496)	model_time 0.7849 (0.7444)	loss 3.2899 (2.7881)	grad_norm 3.7039 (2.3901/1.0092)	mem 34604MB
[2025-01-19 17:41:58 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][290/312]	eta 0:00:16 lr 0.000419	time 0.8459 (0.7508)	model_time 0.8457 (0.7456)	loss 3.2827 (2.8013)	grad_norm 1.4746 (2.0533/0.8092)	mem 34602MB
[2025-01-19 17:41:58 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][310/312]	eta 0:00:01 lr 0.000418	time 0.7186 (0.7492)	model_time 0.7185 (0.7441)	loss 2.8859 (2.7897)	grad_norm 2.9054 (2.4332/1.0382)	mem 34604MB
[2025-01-19 17:41:59 internimage_b_1k_224] (main.py 519): INFO EPOCH 239 training takes 0:03:53
[2025-01-19 17:41:59 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_239.pth saving......
[2025-01-19 17:42:02 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_239.pth saved !!!
[2025-01-19 17:42:05 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][300/312]	eta 0:00:09 lr 0.000419	time 0.7189 (0.7504)	model_time 0.7188 (0.7454)	loss 3.3546 (2.8022)	grad_norm 1.2399 (2.0640/0.8161)	mem 34602MB
[2025-01-19 17:42:10 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.423 (7.423)	Loss 0.6794 (0.6794)	Acc@1 86.230 (86.230)	Acc@5 97.852 (97.852)	Mem 34604MB
[2025-01-19 17:42:13 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.947)	Loss 0.9167 (0.7787)	Acc@1 80.103 (84.118)	Acc@5 95.850 (96.751)	Mem 34604MB
[2025-01-19 17:42:13 internimage_b_1k_224] (main.py 510): INFO Train: [239/300][310/312]	eta 0:00:01 lr 0.000418	time 0.7216 (0.7503)	model_time 0.7215 (0.7454)	loss 2.0979 (2.7944)	grad_norm 1.2582 (2.0613/0.8256)	mem 34602MB
[2025-01-19 17:42:13 internimage_b_1k_224] (main.py 575): INFO [Epoch:239] * Acc@1 83.931 Acc@5 96.773
[2025-01-19 17:42:13 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.9%
[2025-01-19 17:42:13 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 17:42:13 internimage_b_1k_224] (main.py 519): INFO EPOCH 239 training takes 0:03:54
[2025-01-19 17:42:13 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_239.pth saving......
[2025-01-19 17:42:16 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 17:42:16 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.93%
[2025-01-19 17:42:17 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_239.pth saved !!!
[2025-01-19 17:42:32 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.555 (15.555)	Loss 0.7122 (0.7122)	Acc@1 86.450 (86.450)	Acc@5 98.145 (98.145)	Mem 34604MB
[2025-01-19 17:42:33 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.093 (16.093)	Loss 0.6948 (0.6948)	Acc@1 85.962 (85.962)	Acc@5 97.778 (97.778)	Mem 34602MB
[2025-01-19 17:42:39 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.076)	Loss 0.9307 (0.8085)	Acc@1 80.444 (84.091)	Acc@5 95.776 (96.877)	Mem 34604MB
[2025-01-19 17:42:39 internimage_b_1k_224] (main.py 575): INFO [Epoch:239] * Acc@1 83.931 Acc@5 96.921
[2025-01-19 17:42:39 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.9%
[2025-01-19 17:42:39 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:42:39 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.183 (2.079)	Loss 0.9086 (0.7840)	Acc@1 80.542 (84.191)	Acc@5 95.898 (96.822)	Mem 34602MB
[2025-01-19 17:42:40 internimage_b_1k_224] (main.py 575): INFO [Epoch:239] * Acc@1 84.023 Acc@5 96.847
[2025-01-19 17:42:40 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.0%
[2025-01-19 17:42:40 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 17:42:43 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 17:42:43 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.02%
[2025-01-19 17:42:43 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:42:43 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.93%
[2025-01-19 17:42:45 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][0/312]	eta 0:10:46 lr 0.000418	time 2.0728 (2.0728)	model_time 0.7437 (0.7437)	loss 2.9810 (2.9810)	grad_norm 3.6903 (3.6903/0.0000)	mem 34604MB
[2025-01-19 17:42:50 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.219 (7.219)	Loss 0.7216 (0.7216)	Acc@1 86.011 (86.011)	Acc@5 98.242 (98.242)	Mem 34602MB
[2025-01-19 17:42:53 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][10/312]	eta 0:04:20 lr 0.000418	time 0.7177 (0.8634)	model_time 0.7175 (0.7423)	loss 2.2626 (2.7079)	grad_norm 1.0208 (2.0806/0.8047)	mem 34604MB
[2025-01-19 17:42:53 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.919)	Loss 0.9313 (0.8093)	Acc@1 80.005 (84.066)	Acc@5 95.947 (96.955)	Mem 34602MB
[2025-01-19 17:42:53 internimage_b_1k_224] (main.py 575): INFO [Epoch:239] * Acc@1 83.885 Acc@5 96.997
[2025-01-19 17:42:53 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.9%
[2025-01-19 17:42:53 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:42:57 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:42:57 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.89%
[2025-01-19 17:43:00 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][0/312]	eta 0:11:35 lr 0.000418	time 2.2300 (2.2300)	model_time 0.7522 (0.7522)	loss 2.5594 (2.5594)	grad_norm 4.0949 (4.0949/0.0000)	mem 34602MB
[2025-01-19 17:43:01 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][20/312]	eta 0:04:00 lr 0.000417	time 0.7169 (0.8235)	model_time 0.7167 (0.7599)	loss 2.1205 (2.6442)	grad_norm 1.1875 (1.7413/0.7361)	mem 34604MB
[2025-01-19 17:43:07 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][10/312]	eta 0:04:27 lr 0.000418	time 0.7175 (0.8847)	model_time 0.7174 (0.7500)	loss 2.4641 (2.9052)	grad_norm 3.3208 (2.8672/1.3477)	mem 34602MB
[2025-01-19 17:43:08 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][30/312]	eta 0:03:46 lr 0.000417	time 0.7155 (0.8033)	model_time 0.7154 (0.7601)	loss 2.7135 (2.6530)	grad_norm 5.0664 (1.8562/0.9415)	mem 34604MB
[2025-01-19 17:43:15 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][20/312]	eta 0:04:00 lr 0.000417	time 0.8044 (0.8252)	model_time 0.8038 (0.7545)	loss 3.3605 (2.8542)	grad_norm 2.4096 (2.9826/1.3438)	mem 34602MB
[2025-01-19 17:43:16 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][40/312]	eta 0:03:33 lr 0.000417	time 0.7267 (0.7863)	model_time 0.7263 (0.7535)	loss 2.3176 (2.7209)	grad_norm 4.9584 (2.2352/1.2315)	mem 34604MB
[2025-01-19 17:43:22 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][30/312]	eta 0:03:47 lr 0.000417	time 0.7186 (0.8066)	model_time 0.7181 (0.7586)	loss 1.7508 (2.8334)	grad_norm 4.1761 (2.9456/1.2665)	mem 34602MB
[2025-01-19 17:43:23 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][50/312]	eta 0:03:23 lr 0.000416	time 0.7506 (0.7783)	model_time 0.7504 (0.7519)	loss 2.7296 (2.7286)	grad_norm 2.9841 (2.4404/1.2786)	mem 34604MB
[2025-01-19 17:43:30 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][40/312]	eta 0:03:34 lr 0.000417	time 0.7227 (0.7878)	model_time 0.7226 (0.7514)	loss 2.7195 (2.8126)	grad_norm 2.1568 (2.8663/1.1795)	mem 34602MB
[2025-01-19 17:43:30 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][60/312]	eta 0:03:14 lr 0.000416	time 0.7238 (0.7701)	model_time 0.7234 (0.7480)	loss 2.8173 (2.7437)	grad_norm 1.3540 (2.3311/1.2115)	mem 34604MB
[2025-01-19 17:43:37 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][50/312]	eta 0:03:24 lr 0.000416	time 0.7177 (0.7818)	model_time 0.7175 (0.7525)	loss 2.3211 (2.8075)	grad_norm 2.0940 (2.8456/1.1460)	mem 34602MB
[2025-01-19 17:43:38 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][70/312]	eta 0:03:05 lr 0.000415	time 0.7224 (0.7653)	model_time 0.7220 (0.7462)	loss 2.4311 (2.7519)	grad_norm 2.4968 (2.3698/1.1804)	mem 34604MB
[2025-01-19 17:43:45 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][60/312]	eta 0:03:14 lr 0.000416	time 0.7223 (0.7736)	model_time 0.7218 (0.7490)	loss 2.7950 (2.8282)	grad_norm 2.1288 (2.7553/1.1174)	mem 34602MB
[2025-01-19 17:43:45 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][80/312]	eta 0:02:56 lr 0.000415	time 0.7201 (0.7613)	model_time 0.7196 (0.7446)	loss 2.8642 (2.7601)	grad_norm 2.6000 (2.3969/1.1366)	mem 34604MB
[2025-01-19 17:43:52 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][70/312]	eta 0:03:06 lr 0.000415	time 0.8018 (0.7692)	model_time 0.8016 (0.7480)	loss 2.7476 (2.8022)	grad_norm 3.5745 (2.8492/1.1532)	mem 34602MB
[2025-01-19 17:43:52 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][90/312]	eta 0:02:48 lr 0.000415	time 0.7177 (0.7585)	model_time 0.7175 (0.7436)	loss 2.3193 (2.7448)	grad_norm 3.8578 (2.4008/1.1294)	mem 34604MB
[2025-01-19 17:43:59 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][80/312]	eta 0:02:57 lr 0.000415	time 0.7224 (0.7656)	model_time 0.7222 (0.7470)	loss 2.2718 (2.7921)	grad_norm 1.1078 (2.7545/1.1562)	mem 34602MB
[2025-01-19 17:44:00 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][100/312]	eta 0:02:40 lr 0.000414	time 0.7153 (0.7559)	model_time 0.7149 (0.7424)	loss 2.1759 (2.7646)	grad_norm 2.5595 (2.4230/1.0988)	mem 34604MB
[2025-01-19 17:44:07 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][90/312]	eta 0:02:49 lr 0.000415	time 0.7188 (0.7631)	model_time 0.7187 (0.7465)	loss 2.8145 (2.7779)	grad_norm 1.9244 (2.6556/1.1360)	mem 34602MB
[2025-01-19 17:44:07 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][110/312]	eta 0:02:32 lr 0.000414	time 0.7080 (0.7567)	model_time 0.7076 (0.7444)	loss 2.1197 (2.7508)	grad_norm 1.3218 (2.3620/1.0705)	mem 34604MB
[2025-01-19 17:44:14 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][100/312]	eta 0:02:41 lr 0.000414	time 0.7992 (0.7616)	model_time 0.7991 (0.7467)	loss 1.6566 (2.7682)	grad_norm 2.3739 (2.5927/1.1008)	mem 34602MB
[2025-01-19 17:44:15 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][120/312]	eta 0:02:25 lr 0.000413	time 0.8162 (0.7583)	model_time 0.8158 (0.7469)	loss 2.5118 (2.7504)	grad_norm 3.0276 (2.3292/1.0557)	mem 34604MB
[2025-01-19 17:44:22 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][110/312]	eta 0:02:33 lr 0.000414	time 0.7180 (0.7605)	model_time 0.7175 (0.7469)	loss 1.6432 (2.7655)	grad_norm 1.0003 (2.5724/1.0993)	mem 34602MB
[2025-01-19 17:44:23 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][130/312]	eta 0:02:17 lr 0.000413	time 0.7131 (0.7575)	model_time 0.7129 (0.7470)	loss 2.8234 (2.7508)	grad_norm 2.2915 (2.3121/1.0393)	mem 34604MB
[2025-01-19 17:44:29 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][120/312]	eta 0:02:26 lr 0.000413	time 0.7189 (0.7608)	model_time 0.7184 (0.7482)	loss 2.6203 (2.7606)	grad_norm 2.8979 (2.5312/1.0894)	mem 34602MB
[2025-01-19 17:44:30 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][140/312]	eta 0:02:10 lr 0.000413	time 0.7196 (0.7583)	model_time 0.7194 (0.7485)	loss 2.9067 (2.7417)	grad_norm 2.0650 (2.3418/1.0448)	mem 34604MB
[2025-01-19 17:44:37 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][130/312]	eta 0:02:18 lr 0.000413	time 0.7566 (0.7596)	model_time 0.7564 (0.7479)	loss 2.9479 (2.7550)	grad_norm 2.3235 (2.5541/1.0965)	mem 34602MB
[2025-01-19 17:44:38 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][150/312]	eta 0:02:02 lr 0.000412	time 0.7329 (0.7576)	model_time 0.7324 (0.7485)	loss 2.5752 (2.7304)	grad_norm 1.2934 (2.2959/1.0307)	mem 34604MB
[2025-01-19 17:44:45 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][140/312]	eta 0:02:10 lr 0.000413	time 0.8104 (0.7615)	model_time 0.8100 (0.7506)	loss 2.7513 (2.7542)	grad_norm 2.5709 (2.5360/1.1002)	mem 34602MB
[2025-01-19 17:44:45 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][160/312]	eta 0:01:54 lr 0.000412	time 0.7296 (0.7565)	model_time 0.7292 (0.7479)	loss 2.7022 (2.7384)	grad_norm 5.1568 (2.3411/1.0373)	mem 34604MB
[2025-01-19 17:44:52 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][150/312]	eta 0:02:03 lr 0.000412	time 0.7157 (0.7609)	model_time 0.7155 (0.7508)	loss 2.9062 (2.7571)	grad_norm 1.4200 (2.4947/1.0822)	mem 34602MB
[2025-01-19 17:44:53 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][170/312]	eta 0:01:47 lr 0.000412	time 0.7617 (0.7565)	model_time 0.7615 (0.7483)	loss 2.7779 (2.7429)	grad_norm 3.6574 (2.3460/1.0302)	mem 34604MB
[2025-01-19 17:45:00 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][160/312]	eta 0:01:55 lr 0.000412	time 0.7709 (0.7597)	model_time 0.7704 (0.7502)	loss 3.2358 (2.7577)	grad_norm 2.8049 (2.4446/1.0750)	mem 34602MB
[2025-01-19 17:45:00 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][180/312]	eta 0:01:39 lr 0.000411	time 0.7270 (0.7550)	model_time 0.7266 (0.7473)	loss 2.4797 (2.7488)	grad_norm 1.2171 (2.3567/1.0401)	mem 34604MB
[2025-01-19 17:45:07 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][170/312]	eta 0:01:47 lr 0.000412	time 0.7177 (0.7592)	model_time 0.7173 (0.7502)	loss 2.8526 (2.7649)	grad_norm 1.7286 (2.4248/1.0522)	mem 34602MB
[2025-01-19 17:45:07 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][190/312]	eta 0:01:32 lr 0.000411	time 0.7512 (0.7542)	model_time 0.7510 (0.7468)	loss 2.6394 (2.7382)	grad_norm 3.4113 (2.3554/1.0291)	mem 34604MB
[2025-01-19 17:45:15 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][180/312]	eta 0:01:40 lr 0.000411	time 0.7584 (0.7580)	model_time 0.7580 (0.7495)	loss 2.6913 (2.7619)	grad_norm 1.4673 (2.3963/1.0403)	mem 34602MB
[2025-01-19 17:45:15 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][200/312]	eta 0:01:24 lr 0.000410	time 0.7086 (0.7533)	model_time 0.7081 (0.7464)	loss 3.0213 (2.7431)	grad_norm 1.7211 (2.3392/1.0145)	mem 34604MB
[2025-01-19 17:45:22 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][190/312]	eta 0:01:32 lr 0.000411	time 0.8024 (0.7573)	model_time 0.8023 (0.7493)	loss 3.0281 (2.7611)	grad_norm 1.5075 (2.3721/1.0239)	mem 34602MB
[2025-01-19 17:45:22 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][210/312]	eta 0:01:16 lr 0.000410	time 0.7224 (0.7523)	model_time 0.7223 (0.7456)	loss 2.9394 (2.7454)	grad_norm 2.1692 (2.3286/0.9984)	mem 34604MB
[2025-01-19 17:45:29 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][200/312]	eta 0:01:24 lr 0.000410	time 0.7174 (0.7562)	model_time 0.7170 (0.7485)	loss 2.4849 (2.7515)	grad_norm 2.2047 (2.3405/1.0132)	mem 34602MB
[2025-01-19 17:45:29 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][220/312]	eta 0:01:09 lr 0.000410	time 0.7156 (0.7516)	model_time 0.7151 (0.7452)	loss 3.2561 (2.7550)	grad_norm 1.1872 (2.2836/0.9981)	mem 34604MB
[2025-01-19 17:45:37 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][210/312]	eta 0:01:17 lr 0.000410	time 0.7252 (0.7554)	model_time 0.7247 (0.7481)	loss 3.0356 (2.7587)	grad_norm 1.1623 (2.2937/1.0119)	mem 34602MB
[2025-01-19 17:45:37 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][230/312]	eta 0:01:01 lr 0.000409	time 0.7300 (0.7519)	model_time 0.7298 (0.7458)	loss 2.0496 (2.7554)	grad_norm 1.2466 (2.2601/0.9911)	mem 34604MB
[2025-01-19 17:45:44 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][220/312]	eta 0:01:09 lr 0.000410	time 0.7252 (0.7552)	model_time 0.7250 (0.7481)	loss 2.6061 (2.7563)	grad_norm 2.4499 (2.2910/0.9938)	mem 34602MB
[2025-01-19 17:45:45 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][240/312]	eta 0:00:54 lr 0.000409	time 0.8090 (0.7522)	model_time 0.8089 (0.7463)	loss 3.1000 (2.7556)	grad_norm 1.5906 (2.2300/0.9876)	mem 34604MB
[2025-01-19 17:45:52 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][230/312]	eta 0:01:01 lr 0.000409	time 0.7173 (0.7555)	model_time 0.7171 (0.7487)	loss 3.0808 (2.7660)	grad_norm 1.8437 (2.2755/0.9831)	mem 34602MB
[2025-01-19 17:45:52 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][250/312]	eta 0:00:46 lr 0.000408	time 0.7229 (0.7519)	model_time 0.7225 (0.7463)	loss 2.9947 (2.7471)	grad_norm 2.4313 (2.2132/0.9754)	mem 34604MB
[2025-01-19 17:45:59 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][240/312]	eta 0:00:54 lr 0.000409	time 0.7223 (0.7557)	model_time 0.7221 (0.7492)	loss 2.7715 (2.7653)	grad_norm 2.2060 (2.3045/0.9899)	mem 34602MB
[2025-01-19 17:46:00 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][260/312]	eta 0:00:39 lr 0.000408	time 0.7225 (0.7529)	model_time 0.7220 (0.7474)	loss 2.1882 (2.7391)	grad_norm 1.4559 (2.1908/0.9647)	mem 34604MB
[2025-01-19 17:46:07 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][250/312]	eta 0:00:46 lr 0.000408	time 0.7181 (0.7551)	model_time 0.7180 (0.7488)	loss 3.5010 (2.7666)	grad_norm 1.4825 (2.3576/1.0723)	mem 34602MB
[2025-01-19 17:46:07 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][270/312]	eta 0:00:31 lr 0.000408	time 0.7184 (0.7527)	model_time 0.7183 (0.7474)	loss 3.0231 (2.7312)	grad_norm 1.4468 (2.1775/0.9600)	mem 34604MB
[2025-01-19 17:46:15 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][260/312]	eta 0:00:39 lr 0.000408	time 0.8169 (0.7555)	model_time 0.8164 (0.7495)	loss 3.0952 (2.7667)	grad_norm 2.2196 (2.3561/1.0686)	mem 34602MB
[2025-01-19 17:46:15 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][280/312]	eta 0:00:24 lr 0.000407	time 0.7197 (0.7525)	model_time 0.7193 (0.7474)	loss 2.9234 (2.7332)	grad_norm 2.5066 (2.1720/0.9479)	mem 34604MB
[2025-01-19 17:46:22 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][270/312]	eta 0:00:31 lr 0.000408	time 0.7253 (0.7550)	model_time 0.7248 (0.7491)	loss 3.1125 (2.7640)	grad_norm 2.6424 (2.3681/1.0694)	mem 34602MB
[2025-01-19 17:46:22 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][290/312]	eta 0:00:16 lr 0.000407	time 0.7309 (0.7521)	model_time 0.7304 (0.7472)	loss 2.9997 (2.7363)	grad_norm 2.1568 (2.1552/0.9391)	mem 34604MB
[2025-01-19 17:46:29 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][300/312]	eta 0:00:09 lr 0.000407	time 0.7180 (0.7512)	model_time 0.7179 (0.7464)	loss 2.5501 (2.7308)	grad_norm 1.2912 (2.1463/0.9231)	mem 34604MB
[2025-01-19 17:46:29 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][280/312]	eta 0:00:24 lr 0.000407	time 0.7268 (0.7546)	model_time 0.7267 (0.7489)	loss 3.4367 (2.7586)	grad_norm 1.6469 (2.3609/1.0630)	mem 34602MB
[2025-01-19 17:46:37 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][310/312]	eta 0:00:01 lr 0.000406	time 0.7137 (0.7500)	model_time 0.7136 (0.7454)	loss 3.0334 (2.7254)	grad_norm 3.0225 (2.1414/0.9234)	mem 34604MB
[2025-01-19 17:46:37 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][290/312]	eta 0:00:16 lr 0.000407	time 0.7386 (0.7542)	model_time 0.7385 (0.7487)	loss 3.0472 (2.7606)	grad_norm 2.4108 (2.3446/1.0728)	mem 34602MB
[2025-01-19 17:46:37 internimage_b_1k_224] (main.py 519): INFO EPOCH 240 training takes 0:03:53
[2025-01-19 17:46:37 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_240.pth saving......
[2025-01-19 17:46:40 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_240.pth saved !!!
[2025-01-19 17:46:44 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][300/312]	eta 0:00:09 lr 0.000407	time 0.7132 (0.7538)	model_time 0.7131 (0.7485)	loss 2.8236 (2.7604)	grad_norm 2.6018 (2.3555/1.0828)	mem 34602MB
[2025-01-19 17:46:48 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.437 (7.437)	Loss 0.7045 (0.7045)	Acc@1 86.279 (86.279)	Acc@5 97.852 (97.852)	Mem 34604MB
[2025-01-19 17:46:51 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.963)	Loss 0.9035 (0.7884)	Acc@1 80.396 (84.111)	Acc@5 95.850 (96.757)	Mem 34604MB
[2025-01-19 17:46:51 internimage_b_1k_224] (main.py 575): INFO [Epoch:240] * Acc@1 83.949 Acc@5 96.755
[2025-01-19 17:46:51 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.9%
[2025-01-19 17:46:51 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 17:46:52 internimage_b_1k_224] (main.py 510): INFO Train: [240/300][310/312]	eta 0:00:01 lr 0.000406	time 0.7111 (0.7529)	model_time 0.7110 (0.7478)	loss 2.8342 (2.7609)	grad_norm 1.7431 (2.3238/1.0615)	mem 34602MB
[2025-01-19 17:46:52 internimage_b_1k_224] (main.py 519): INFO EPOCH 240 training takes 0:03:54
[2025-01-19 17:46:52 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_240.pth saving......
[2025-01-19 17:46:55 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 17:46:55 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.95%
[2025-01-19 17:46:55 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_240.pth saved !!!
[2025-01-19 17:47:10 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.508 (15.508)	Loss 0.7123 (0.7123)	Acc@1 86.328 (86.328)	Acc@5 98.169 (98.169)	Mem 34604MB
[2025-01-19 17:47:12 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.395 (16.395)	Loss 0.7211 (0.7211)	Acc@1 85.669 (85.669)	Acc@5 97.705 (97.705)	Mem 34602MB
[2025-01-19 17:47:18 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.090)	Loss 0.9301 (0.8081)	Acc@1 80.469 (84.109)	Acc@5 95.703 (96.886)	Mem 34604MB
[2025-01-19 17:47:18 internimage_b_1k_224] (main.py 575): INFO [Epoch:240] * Acc@1 83.947 Acc@5 96.929
[2025-01-19 17:47:18 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.9%
[2025-01-19 17:47:18 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:47:18 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.087)	Loss 0.9057 (0.7913)	Acc@1 80.859 (84.066)	Acc@5 95.581 (96.788)	Mem 34602MB
[2025-01-19 17:47:19 internimage_b_1k_224] (main.py 575): INFO [Epoch:240] * Acc@1 83.887 Acc@5 96.801
[2025-01-19 17:47:19 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.9%
[2025-01-19 17:47:19 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.02%
[2025-01-19 17:47:22 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:47:22 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.95%
[2025-01-19 17:47:24 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][0/312]	eta 0:10:17 lr 0.000406	time 1.9799 (1.9799)	model_time 0.7448 (0.7448)	loss 3.0549 (3.0549)	grad_norm 3.0924 (3.0924/0.0000)	mem 34604MB
[2025-01-19 17:47:28 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.387 (9.387)	Loss 0.7217 (0.7217)	Acc@1 86.035 (86.035)	Acc@5 98.218 (98.218)	Mem 34602MB
[2025-01-19 17:47:31 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][10/312]	eta 0:04:17 lr 0.000406	time 0.7386 (0.8523)	model_time 0.7382 (0.7397)	loss 2.7371 (2.7164)	grad_norm 4.6521 (2.9887/1.3799)	mem 34604MB
[2025-01-19 17:47:32 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.270)	Loss 0.9306 (0.8090)	Acc@1 80.005 (84.086)	Acc@5 95.972 (96.955)	Mem 34602MB
[2025-01-19 17:47:33 internimage_b_1k_224] (main.py 575): INFO [Epoch:240] * Acc@1 83.905 Acc@5 96.995
[2025-01-19 17:47:33 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.9%
[2025-01-19 17:47:33 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:47:37 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:47:37 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.91%
[2025-01-19 17:47:39 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][20/312]	eta 0:03:52 lr 0.000405	time 0.7604 (0.7977)	model_time 0.7600 (0.7385)	loss 2.5275 (2.7607)	grad_norm 3.0660 (3.0104/1.3282)	mem 34604MB
[2025-01-19 17:47:39 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][0/312]	eta 0:11:00 lr 0.000406	time 2.1169 (2.1169)	model_time 0.7753 (0.7753)	loss 1.8191 (1.8191)	grad_norm 1.7925 (1.7925/0.0000)	mem 34602MB
[2025-01-19 17:47:46 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][30/312]	eta 0:03:39 lr 0.000405	time 0.8018 (0.7784)	model_time 0.8014 (0.7382)	loss 2.6704 (2.7414)	grad_norm 3.1712 (2.7678/1.2896)	mem 34604MB
[2025-01-19 17:47:46 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][10/312]	eta 0:04:21 lr 0.000406	time 0.7227 (0.8665)	model_time 0.7226 (0.7442)	loss 2.7211 (2.8503)	grad_norm 2.0153 (2.3277/0.9625)	mem 34602MB
[2025-01-19 17:47:54 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][20/312]	eta 0:03:55 lr 0.000405	time 0.7229 (0.8080)	model_time 0.7227 (0.7438)	loss 2.6627 (2.7250)	grad_norm 3.1379 (2.2975/0.9004)	mem 34602MB
[2025-01-19 17:47:54 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][40/312]	eta 0:03:30 lr 0.000405	time 0.7148 (0.7743)	model_time 0.7147 (0.7438)	loss 2.8147 (2.7480)	grad_norm 3.5105 (2.9275/1.2781)	mem 34604MB
[2025-01-19 17:48:01 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][30/312]	eta 0:03:42 lr 0.000405	time 0.7241 (0.7884)	model_time 0.7240 (0.7447)	loss 3.1743 (2.7520)	grad_norm 4.2973 (2.4640/0.9507)	mem 34602MB
[2025-01-19 17:48:01 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][50/312]	eta 0:03:22 lr 0.000404	time 0.7959 (0.7730)	model_time 0.7956 (0.7484)	loss 2.8083 (2.7657)	grad_norm 3.2000 (2.7103/1.2652)	mem 34604MB
[2025-01-19 17:48:09 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][40/312]	eta 0:03:34 lr 0.000405	time 0.7256 (0.7869)	model_time 0.7254 (0.7538)	loss 2.9747 (2.8075)	grad_norm 1.6237 (2.4051/0.9600)	mem 34602MB
[2025-01-19 17:48:09 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][60/312]	eta 0:03:14 lr 0.000404	time 0.7191 (0.7701)	model_time 0.7189 (0.7495)	loss 2.1813 (2.7368)	grad_norm 1.7623 (2.5373/1.2329)	mem 34604MB
[2025-01-19 17:48:16 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][50/312]	eta 0:03:23 lr 0.000404	time 0.7305 (0.7772)	model_time 0.7300 (0.7505)	loss 3.4574 (2.7680)	grad_norm 1.8122 (2.3246/0.9068)	mem 34602MB
[2025-01-19 17:48:17 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][70/312]	eta 0:03:06 lr 0.000403	time 0.8135 (0.7715)	model_time 0.8133 (0.7537)	loss 1.8389 (2.7377)	grad_norm 1.6536 (2.4690/1.1828)	mem 34604MB
[2025-01-19 17:48:24 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][60/312]	eta 0:03:14 lr 0.000404	time 0.8079 (0.7731)	model_time 0.8077 (0.7507)	loss 2.6266 (2.7702)	grad_norm 1.4753 (2.2096/0.9070)	mem 34602MB
[2025-01-19 17:48:24 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][80/312]	eta 0:02:58 lr 0.000403	time 0.7096 (0.7702)	model_time 0.7094 (0.7546)	loss 3.3997 (2.7760)	grad_norm 5.1953 (2.5793/1.2103)	mem 34604MB
[2025-01-19 17:48:31 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][70/312]	eta 0:03:06 lr 0.000403	time 0.7848 (0.7689)	model_time 0.7847 (0.7496)	loss 2.6115 (2.7517)	grad_norm 2.5814 (2.2350/0.9282)	mem 34602MB
[2025-01-19 17:48:32 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][90/312]	eta 0:02:50 lr 0.000403	time 0.7217 (0.7682)	model_time 0.7213 (0.7543)	loss 1.9383 (2.7866)	grad_norm 2.7523 (2.6520/1.2229)	mem 34604MB
[2025-01-19 17:48:39 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][80/312]	eta 0:02:57 lr 0.000403	time 0.7365 (0.7672)	model_time 0.7361 (0.7503)	loss 3.0238 (2.7610)	grad_norm 1.9082 (2.1748/0.9034)	mem 34602MB
[2025-01-19 17:48:39 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][100/312]	eta 0:02:41 lr 0.000402	time 0.7203 (0.7640)	model_time 0.7201 (0.7514)	loss 2.6288 (2.7684)	grad_norm 2.4077 (2.6191/1.1957)	mem 34604MB
[2025-01-19 17:48:46 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][90/312]	eta 0:02:49 lr 0.000403	time 0.7468 (0.7656)	model_time 0.7467 (0.7505)	loss 2.0346 (2.7589)	grad_norm 1.5626 (2.1979/0.9131)	mem 34602MB
[2025-01-19 17:48:46 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][110/312]	eta 0:02:33 lr 0.000402	time 0.7211 (0.7610)	model_time 0.7209 (0.7495)	loss 1.8332 (2.7342)	grad_norm 1.2601 (2.5770/1.1916)	mem 34604MB
[2025-01-19 17:48:54 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][120/312]	eta 0:02:25 lr 0.000401	time 0.7226 (0.7581)	model_time 0.7225 (0.7475)	loss 3.0996 (2.7414)	grad_norm 2.3657 (2.5275/1.1658)	mem 34604MB
[2025-01-19 17:48:54 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][100/312]	eta 0:02:41 lr 0.000402	time 0.8105 (0.7641)	model_time 0.8101 (0.7505)	loss 2.3876 (2.7641)	grad_norm 3.5189 (2.2246/0.9288)	mem 34602MB
[2025-01-19 17:49:01 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][130/312]	eta 0:02:17 lr 0.000401	time 0.7200 (0.7561)	model_time 0.7199 (0.7463)	loss 2.1560 (2.7370)	grad_norm 3.3790 (2.5018/1.1497)	mem 34604MB
[2025-01-19 17:49:01 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][110/312]	eta 0:02:33 lr 0.000402	time 0.7409 (0.7618)	model_time 0.7407 (0.7493)	loss 2.8817 (2.7791)	grad_norm 2.0071 (2.2813/0.9899)	mem 34602MB
[2025-01-19 17:49:08 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][140/312]	eta 0:02:09 lr 0.000401	time 0.7639 (0.7542)	model_time 0.7634 (0.7451)	loss 2.6276 (2.7434)	grad_norm 1.7410 (2.4635/1.1259)	mem 34604MB
[2025-01-19 17:49:09 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][120/312]	eta 0:02:25 lr 0.000401	time 0.7181 (0.7601)	model_time 0.7177 (0.7487)	loss 2.8565 (2.7802)	grad_norm 3.5361 (2.3141/1.0022)	mem 34602MB
[2025-01-19 17:49:16 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][150/312]	eta 0:02:02 lr 0.000400	time 0.8060 (0.7535)	model_time 0.8055 (0.7450)	loss 3.1116 (2.7514)	grad_norm 1.4748 (2.4695/1.1253)	mem 34604MB
[2025-01-19 17:49:16 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][130/312]	eta 0:02:18 lr 0.000401	time 0.7191 (0.7586)	model_time 0.7186 (0.7480)	loss 2.9505 (2.7793)	grad_norm 1.7733 (2.3004/0.9791)	mem 34602MB
[2025-01-19 17:49:23 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][160/312]	eta 0:01:54 lr 0.000400	time 0.7198 (0.7542)	model_time 0.7197 (0.7461)	loss 2.5272 (2.7463)	grad_norm 1.7199 (2.4459/1.1104)	mem 34604MB
[2025-01-19 17:49:24 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][140/312]	eta 0:02:10 lr 0.000401	time 0.7271 (0.7578)	model_time 0.7269 (0.7480)	loss 2.8060 (2.7790)	grad_norm 1.7547 (2.2844/0.9652)	mem 34602MB
[2025-01-19 17:49:31 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][150/312]	eta 0:02:02 lr 0.000400	time 0.7395 (0.7573)	model_time 0.7391 (0.7481)	loss 1.9775 (2.7810)	grad_norm 3.1524 (2.3037/0.9578)	mem 34602MB
[2025-01-19 17:49:31 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][170/312]	eta 0:01:47 lr 0.000400	time 0.8009 (0.7557)	model_time 0.8003 (0.7482)	loss 3.1847 (2.7484)	grad_norm 1.2172 (2.3924/1.1052)	mem 34604MB
[2025-01-19 17:49:39 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][180/312]	eta 0:01:39 lr 0.000399	time 0.8013 (0.7556)	model_time 0.8008 (0.7484)	loss 3.0681 (2.7565)	grad_norm 1.6111 (2.3860/1.0926)	mem 34604MB
[2025-01-19 17:49:39 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][160/312]	eta 0:01:55 lr 0.000400	time 0.7225 (0.7583)	model_time 0.7220 (0.7497)	loss 1.9436 (2.7684)	grad_norm 1.2635 (2.2640/0.9447)	mem 34602MB
[2025-01-19 17:49:46 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][170/312]	eta 0:01:47 lr 0.000400	time 1.0169 (0.7588)	model_time 1.0168 (0.7506)	loss 2.8282 (2.7602)	grad_norm 2.0862 (2.2412/0.9292)	mem 34602MB
[2025-01-19 17:49:47 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][190/312]	eta 0:01:32 lr 0.000399	time 0.8148 (0.7566)	model_time 0.8146 (0.7498)	loss 3.0641 (2.7650)	grad_norm 3.9493 (2.3673/1.0910)	mem 34604MB
[2025-01-19 17:49:54 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][180/312]	eta 0:01:40 lr 0.000399	time 0.8103 (0.7583)	model_time 0.8099 (0.7505)	loss 3.1196 (2.7648)	grad_norm 1.8350 (2.2076/0.9211)	mem 34602MB
[2025-01-19 17:49:54 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][200/312]	eta 0:01:24 lr 0.000398	time 0.7091 (0.7567)	model_time 0.7087 (0.7502)	loss 2.2589 (2.7690)	grad_norm 4.0434 (2.3890/1.0949)	mem 34604MB
[2025-01-19 17:50:01 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][190/312]	eta 0:01:32 lr 0.000399	time 0.8036 (0.7576)	model_time 0.8031 (0.7502)	loss 2.2684 (2.7546)	grad_norm 2.5388 (2.2615/0.9528)	mem 34602MB
[2025-01-19 17:50:02 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][210/312]	eta 0:01:17 lr 0.000398	time 0.7256 (0.7565)	model_time 0.7252 (0.7503)	loss 2.9077 (2.7694)	grad_norm 2.0580 (2.3761/1.0776)	mem 34604MB
[2025-01-19 17:50:09 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][220/312]	eta 0:01:09 lr 0.000398	time 0.7347 (0.7553)	model_time 0.7343 (0.7494)	loss 2.9255 (2.7760)	grad_norm 2.2611 (2.3350/1.0740)	mem 34604MB
[2025-01-19 17:50:09 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][200/312]	eta 0:01:24 lr 0.000398	time 0.7165 (0.7575)	model_time 0.7164 (0.7505)	loss 2.9662 (2.7520)	grad_norm 1.4565 (2.2749/0.9696)	mem 34602MB
[2025-01-19 17:50:16 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][230/312]	eta 0:01:01 lr 0.000397	time 0.7221 (0.7544)	model_time 0.7216 (0.7487)	loss 2.8946 (2.7833)	grad_norm 2.4861 (2.3280/1.0624)	mem 34604MB
[2025-01-19 17:50:16 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][210/312]	eta 0:01:17 lr 0.000398	time 0.7238 (0.7571)	model_time 0.7234 (0.7504)	loss 3.0438 (2.7564)	grad_norm 1.6354 (2.2471/0.9578)	mem 34602MB
[2025-01-19 17:50:24 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][240/312]	eta 0:00:54 lr 0.000397	time 0.7240 (0.7533)	model_time 0.7236 (0.7478)	loss 2.9490 (2.7951)	grad_norm 1.6600 (2.3130/1.0471)	mem 34604MB
[2025-01-19 17:50:24 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][220/312]	eta 0:01:09 lr 0.000398	time 0.7164 (0.7562)	model_time 0.7160 (0.7497)	loss 3.1412 (2.7583)	grad_norm 2.2717 (2.2289/0.9441)	mem 34602MB
[2025-01-19 17:50:31 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][250/312]	eta 0:00:46 lr 0.000396	time 0.7243 (0.7526)	model_time 0.7239 (0.7473)	loss 2.9849 (2.8024)	grad_norm 2.6480 (2.3046/1.0345)	mem 34604MB
[2025-01-19 17:50:31 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][230/312]	eta 0:01:01 lr 0.000397	time 0.7210 (0.7555)	model_time 0.7206 (0.7493)	loss 3.2856 (2.7690)	grad_norm 5.2103 (2.2355/0.9554)	mem 34602MB
[2025-01-19 17:50:38 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][260/312]	eta 0:00:39 lr 0.000396	time 0.7198 (0.7516)	model_time 0.7194 (0.7464)	loss 3.0827 (2.7981)	grad_norm 1.6022 (2.3001/1.0317)	mem 34604MB
[2025-01-19 17:50:39 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][240/312]	eta 0:00:54 lr 0.000397	time 0.7528 (0.7550)	model_time 0.7524 (0.7491)	loss 3.2406 (2.7688)	grad_norm 3.5894 (2.2819/1.0070)	mem 34602MB
[2025-01-19 17:50:46 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][270/312]	eta 0:00:31 lr 0.000396	time 0.8072 (0.7512)	model_time 0.8067 (0.7463)	loss 2.6595 (2.7967)	grad_norm 2.5546 (2.3072/1.0236)	mem 34604MB
[2025-01-19 17:50:46 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][250/312]	eta 0:00:46 lr 0.000396	time 0.7205 (0.7542)	model_time 0.7204 (0.7485)	loss 3.1986 (2.7691)	grad_norm 2.8590 (2.3009/1.0083)	mem 34602MB
[2025-01-19 17:50:53 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][280/312]	eta 0:00:24 lr 0.000395	time 0.7152 (0.7511)	model_time 0.7147 (0.7463)	loss 2.6349 (2.7958)	grad_norm 3.2942 (2.3285/1.0386)	mem 34604MB
[2025-01-19 17:50:53 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][260/312]	eta 0:00:39 lr 0.000396	time 0.7188 (0.7538)	model_time 0.7184 (0.7483)	loss 3.4373 (2.7721)	grad_norm 1.6993 (2.3069/1.0087)	mem 34602MB
[2025-01-19 17:51:01 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][290/312]	eta 0:00:16 lr 0.000395	time 0.7148 (0.7514)	model_time 0.7143 (0.7468)	loss 3.1732 (2.8043)	grad_norm 2.2104 (2.3529/1.0583)	mem 34604MB
[2025-01-19 17:51:01 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][270/312]	eta 0:00:31 lr 0.000396	time 0.7503 (0.7538)	model_time 0.7501 (0.7485)	loss 3.0725 (2.7744)	grad_norm 1.5228 (2.3230/1.0077)	mem 34602MB
[2025-01-19 17:51:08 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][300/312]	eta 0:00:09 lr 0.000395	time 0.7919 (0.7514)	model_time 0.7918 (0.7469)	loss 2.9098 (2.8063)	grad_norm 1.8692 (2.3822/1.0765)	mem 34604MB
[2025-01-19 17:51:09 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][280/312]	eta 0:00:24 lr 0.000395	time 0.7350 (0.7544)	model_time 0.7348 (0.7492)	loss 2.9624 (2.7784)	grad_norm 2.0211 (2.3205/1.0074)	mem 34602MB
[2025-01-19 17:51:16 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][310/312]	eta 0:00:01 lr 0.000394	time 0.7977 (0.7516)	model_time 0.7976 (0.7473)	loss 2.1396 (2.8044)	grad_norm 2.5355 (2.3982/1.0849)	mem 34604MB
[2025-01-19 17:51:16 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][290/312]	eta 0:00:16 lr 0.000395	time 0.8000 (0.7539)	model_time 0.7999 (0.7489)	loss 2.3615 (2.7714)	grad_norm 1.0186 (2.3027/0.9986)	mem 34602MB
[2025-01-19 17:51:16 internimage_b_1k_224] (main.py 519): INFO EPOCH 241 training takes 0:03:54
[2025-01-19 17:51:17 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_241.pth saving......
[2025-01-19 17:51:20 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_241.pth saved !!!
[2025-01-19 17:51:24 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][300/312]	eta 0:00:09 lr 0.000395	time 0.8656 (0.7535)	model_time 0.8655 (0.7487)	loss 2.3604 (2.7717)	grad_norm 1.6718 (2.2898/0.9870)	mem 34602MB
[2025-01-19 17:51:27 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.542 (7.542)	Loss 0.6906 (0.6906)	Acc@1 86.255 (86.255)	Acc@5 97.900 (97.900)	Mem 34604MB
[2025-01-19 17:51:30 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.973)	Loss 0.9058 (0.7820)	Acc@1 80.322 (84.111)	Acc@5 95.654 (96.811)	Mem 34604MB
[2025-01-19 17:51:31 internimage_b_1k_224] (main.py 575): INFO [Epoch:241] * Acc@1 83.959 Acc@5 96.841
[2025-01-19 17:51:31 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.0%
[2025-01-19 17:51:31 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 17:51:31 internimage_b_1k_224] (main.py 510): INFO Train: [241/300][310/312]	eta 0:00:01 lr 0.000394	time 0.7200 (0.7529)	model_time 0.7199 (0.7483)	loss 2.7367 (2.7745)	grad_norm 1.2596 (2.2726/0.9788)	mem 34602MB
[2025-01-19 17:51:32 internimage_b_1k_224] (main.py 519): INFO EPOCH 241 training takes 0:03:54
[2025-01-19 17:51:32 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_241.pth saving......
[2025-01-19 17:51:34 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 17:51:34 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 83.96%
[2025-01-19 17:51:35 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_241.pth saved !!!
[2025-01-19 17:51:50 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.599 (15.599)	Loss 0.7123 (0.7123)	Acc@1 86.353 (86.353)	Acc@5 98.193 (98.193)	Mem 34604MB
[2025-01-19 17:51:52 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.697 (16.697)	Loss 0.6940 (0.6940)	Acc@1 86.035 (86.035)	Acc@5 97.754 (97.754)	Mem 34602MB
[2025-01-19 17:51:57 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (2.090)	Loss 0.9296 (0.8078)	Acc@1 80.420 (84.149)	Acc@5 95.703 (96.893)	Mem 34604MB
[2025-01-19 17:51:57 internimage_b_1k_224] (main.py 575): INFO [Epoch:241] * Acc@1 83.991 Acc@5 96.933
[2025-01-19 17:51:57 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.0%
[2025-01-19 17:51:57 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:51:58 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (2.095)	Loss 0.8936 (0.7787)	Acc@1 80.054 (84.044)	Acc@5 95.728 (96.833)	Mem 34602MB
[2025-01-19 17:51:58 internimage_b_1k_224] (main.py 575): INFO [Epoch:241] * Acc@1 83.895 Acc@5 96.857
[2025-01-19 17:51:58 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.9%
[2025-01-19 17:51:58 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.02%
[2025-01-19 17:52:01 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:52:01 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.99%
[2025-01-19 17:52:03 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][0/312]	eta 0:11:27 lr 0.000394	time 2.2039 (2.2039)	model_time 0.7339 (0.7339)	loss 2.8396 (2.8396)	grad_norm 1.2837 (1.2837/0.0000)	mem 34604MB
[2025-01-19 17:52:08 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.316 (9.316)	Loss 0.7218 (0.7218)	Acc@1 86.084 (86.084)	Acc@5 98.218 (98.218)	Mem 34602MB
[2025-01-19 17:52:11 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][10/312]	eta 0:04:32 lr 0.000394	time 0.7183 (0.9027)	model_time 0.7181 (0.7686)	loss 2.8114 (2.6236)	grad_norm 1.7971 (2.0593/0.7313)	mem 34604MB
[2025-01-19 17:52:12 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.272)	Loss 0.9299 (0.8086)	Acc@1 79.980 (84.122)	Acc@5 95.947 (96.964)	Mem 34602MB
[2025-01-19 17:52:12 internimage_b_1k_224] (main.py 575): INFO [Epoch:241] * Acc@1 83.935 Acc@5 97.003
[2025-01-19 17:52:12 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.9%
[2025-01-19 17:52:12 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:52:16 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:52:16 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.94%
[2025-01-19 17:52:19 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][20/312]	eta 0:04:02 lr 0.000393	time 0.7169 (0.8321)	model_time 0.7167 (0.7618)	loss 2.7627 (2.6872)	grad_norm 1.8384 (2.1394/0.9078)	mem 34604MB
[2025-01-19 17:52:19 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][0/312]	eta 0:12:08 lr 0.000394	time 2.3349 (2.3349)	model_time 0.7479 (0.7479)	loss 2.2192 (2.2192)	grad_norm 3.6209 (3.6209/0.0000)	mem 34602MB
[2025-01-19 17:52:26 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][30/312]	eta 0:03:45 lr 0.000393	time 0.7267 (0.8004)	model_time 0.7265 (0.7526)	loss 1.9142 (2.7272)	grad_norm 1.9023 (2.1949/0.8829)	mem 34604MB
[2025-01-19 17:52:26 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][10/312]	eta 0:04:30 lr 0.000394	time 0.7246 (0.8964)	model_time 0.7245 (0.7519)	loss 3.0030 (2.8457)	grad_norm 2.6535 (2.8403/1.1755)	mem 34602MB
[2025-01-19 17:52:33 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][40/312]	eta 0:03:33 lr 0.000393	time 0.7197 (0.7838)	model_time 0.7195 (0.7476)	loss 3.3161 (2.7367)	grad_norm 2.0362 (2.1566/0.8288)	mem 34604MB
[2025-01-19 17:52:34 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][20/312]	eta 0:04:02 lr 0.000393	time 0.7172 (0.8294)	model_time 0.7170 (0.7536)	loss 2.2976 (2.7894)	grad_norm 1.9906 (2.4974/1.0581)	mem 34602MB
[2025-01-19 17:52:41 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][50/312]	eta 0:03:22 lr 0.000392	time 0.7234 (0.7745)	model_time 0.7230 (0.7453)	loss 1.8363 (2.7349)	grad_norm 1.1707 (2.0010/0.8205)	mem 34604MB
[2025-01-19 17:52:41 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][30/312]	eta 0:03:45 lr 0.000393	time 0.7355 (0.7999)	model_time 0.7353 (0.7484)	loss 3.0302 (2.7692)	grad_norm 1.9098 (2.3180/0.9861)	mem 34602MB
[2025-01-19 17:52:48 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][60/312]	eta 0:03:13 lr 0.000392	time 0.7119 (0.7675)	model_time 0.7118 (0.7431)	loss 3.1000 (2.7168)	grad_norm 1.3574 (1.9666/0.7890)	mem 34604MB
[2025-01-19 17:52:49 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][40/312]	eta 0:03:33 lr 0.000393	time 0.7375 (0.7852)	model_time 0.7373 (0.7462)	loss 2.1571 (2.7595)	grad_norm 1.3972 (2.2739/0.9425)	mem 34602MB
[2025-01-19 17:52:55 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][70/312]	eta 0:03:04 lr 0.000391	time 0.7209 (0.7628)	model_time 0.7204 (0.7418)	loss 2.9303 (2.6884)	grad_norm 2.0040 (1.9750/0.7494)	mem 34604MB
[2025-01-19 17:52:56 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][50/312]	eta 0:03:23 lr 0.000392	time 0.7171 (0.7764)	model_time 0.7170 (0.7450)	loss 2.8531 (2.7415)	grad_norm 3.4326 (2.3115/0.9404)	mem 34602MB
[2025-01-19 17:53:03 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][80/312]	eta 0:02:56 lr 0.000391	time 0.7435 (0.7600)	model_time 0.7430 (0.7415)	loss 1.9580 (2.6762)	grad_norm 1.4333 (1.9023/0.7300)	mem 34604MB
[2025-01-19 17:53:03 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][60/312]	eta 0:03:13 lr 0.000392	time 0.7232 (0.7696)	model_time 0.7227 (0.7432)	loss 2.9106 (2.7431)	grad_norm 1.9217 (2.3017/0.9061)	mem 34602MB
[2025-01-19 17:53:10 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][90/312]	eta 0:02:48 lr 0.000391	time 0.7240 (0.7591)	model_time 0.7238 (0.7426)	loss 2.6422 (2.6906)	grad_norm 1.5617 (1.9388/0.7415)	mem 34604MB
[2025-01-19 17:53:11 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][70/312]	eta 0:03:05 lr 0.000391	time 0.7286 (0.7659)	model_time 0.7281 (0.7432)	loss 2.5531 (2.7483)	grad_norm 1.6503 (2.2706/0.8826)	mem 34602MB
[2025-01-19 17:53:18 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][100/312]	eta 0:02:40 lr 0.000390	time 0.7178 (0.7591)	model_time 0.7173 (0.7442)	loss 2.6567 (2.6883)	grad_norm 2.9713 (1.9939/0.7910)	mem 34604MB
[2025-01-19 17:53:18 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][80/312]	eta 0:02:57 lr 0.000391	time 0.7294 (0.7648)	model_time 0.7292 (0.7448)	loss 3.1055 (2.7549)	grad_norm 1.7123 (2.2798/0.8415)	mem 34602MB
[2025-01-19 17:53:25 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][110/312]	eta 0:02:33 lr 0.000390	time 0.8124 (0.7588)	model_time 0.8122 (0.7452)	loss 2.7593 (2.6839)	grad_norm 2.3268 (1.9990/0.7704)	mem 34604MB
[2025-01-19 17:53:26 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][90/312]	eta 0:02:50 lr 0.000391	time 0.8176 (0.7671)	model_time 0.8172 (0.7493)	loss 3.2811 (2.7692)	grad_norm 1.4028 (2.2280/0.8286)	mem 34602MB
[2025-01-19 17:53:33 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][120/312]	eta 0:02:25 lr 0.000390	time 0.8241 (0.7599)	model_time 0.8240 (0.7474)	loss 2.1618 (2.6806)	grad_norm 1.6689 (1.9936/0.7494)	mem 34604MB
[2025-01-19 17:53:34 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][100/312]	eta 0:02:42 lr 0.000390	time 0.7176 (0.7646)	model_time 0.7174 (0.7485)	loss 3.1257 (2.7712)	grad_norm 2.4084 (2.2252/0.8193)	mem 34602MB
[2025-01-19 17:53:41 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][130/312]	eta 0:02:18 lr 0.000389	time 0.7259 (0.7601)	model_time 0.7255 (0.7485)	loss 2.9664 (2.6896)	grad_norm 2.3724 (1.9908/0.7413)	mem 34604MB
[2025-01-19 17:53:41 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][110/312]	eta 0:02:34 lr 0.000390	time 0.8025 (0.7644)	model_time 0.8021 (0.7498)	loss 3.1509 (2.7816)	grad_norm 3.0443 (2.2341/0.7990)	mem 34602MB
[2025-01-19 17:53:48 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][140/312]	eta 0:02:10 lr 0.000389	time 0.7957 (0.7600)	model_time 0.7955 (0.7492)	loss 2.9952 (2.6916)	grad_norm 1.5473 (2.0572/0.8186)	mem 34604MB
[2025-01-19 17:53:49 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][120/312]	eta 0:02:26 lr 0.000390	time 0.7225 (0.7624)	model_time 0.7223 (0.7489)	loss 3.0044 (2.7807)	grad_norm 1.4642 (2.2413/0.7917)	mem 34602MB
[2025-01-19 17:53:56 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][150/312]	eta 0:02:02 lr 0.000388	time 0.7254 (0.7579)	model_time 0.7253 (0.7478)	loss 3.0188 (2.7009)	grad_norm 3.5486 (2.1210/0.8609)	mem 34604MB
[2025-01-19 17:53:56 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][130/312]	eta 0:02:18 lr 0.000389	time 0.7176 (0.7615)	model_time 0.7174 (0.7491)	loss 3.1777 (2.7894)	grad_norm 1.8907 (2.2457/0.7737)	mem 34602MB
[2025-01-19 17:54:03 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][160/312]	eta 0:01:54 lr 0.000388	time 0.7415 (0.7561)	model_time 0.7411 (0.7466)	loss 3.0458 (2.7240)	grad_norm 1.5556 (2.1568/0.9287)	mem 34604MB
[2025-01-19 17:54:04 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][140/312]	eta 0:02:10 lr 0.000389	time 0.8001 (0.7612)	model_time 0.8000 (0.7496)	loss 3.0777 (2.7956)	grad_norm 1.0342 (2.2533/0.8092)	mem 34602MB
[2025-01-19 17:54:10 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][170/312]	eta 0:01:47 lr 0.000388	time 0.7157 (0.7549)	model_time 0.7156 (0.7459)	loss 3.0724 (2.7310)	grad_norm 1.0735 (2.1543/0.9389)	mem 34604MB
[2025-01-19 17:54:11 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][150/312]	eta 0:02:02 lr 0.000388	time 0.7106 (0.7592)	model_time 0.7104 (0.7483)	loss 2.8082 (2.7890)	grad_norm 2.2135 (2.2372/0.7911)	mem 34602MB
[2025-01-19 17:54:18 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][180/312]	eta 0:01:39 lr 0.000387	time 0.7264 (0.7538)	model_time 0.7260 (0.7453)	loss 3.1702 (2.7381)	grad_norm 2.7386 (2.1357/0.9258)	mem 34604MB
[2025-01-19 17:54:18 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][160/312]	eta 0:01:55 lr 0.000388	time 0.7223 (0.7580)	model_time 0.7221 (0.7478)	loss 3.3224 (2.7946)	grad_norm 3.8804 (2.2430/0.7969)	mem 34602MB
[2025-01-19 17:54:25 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][190/312]	eta 0:01:31 lr 0.000387	time 0.7298 (0.7526)	model_time 0.7294 (0.7445)	loss 2.6727 (2.7379)	grad_norm 2.1949 (2.1490/0.9304)	mem 34604MB
[2025-01-19 17:54:26 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][170/312]	eta 0:01:47 lr 0.000388	time 0.7258 (0.7572)	model_time 0.7256 (0.7476)	loss 3.2325 (2.8015)	grad_norm 2.0412 (2.2522/0.7834)	mem 34602MB
[2025-01-19 17:54:32 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][200/312]	eta 0:01:24 lr 0.000387	time 0.7282 (0.7517)	model_time 0.7280 (0.7440)	loss 3.2676 (2.7451)	grad_norm 1.3544 (2.1648/0.9339)	mem 34604MB
[2025-01-19 17:54:33 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][180/312]	eta 0:01:39 lr 0.000387	time 0.7324 (0.7562)	model_time 0.7320 (0.7470)	loss 3.0803 (2.8003)	grad_norm 2.0667 (2.2366/0.7766)	mem 34602MB
[2025-01-19 17:54:40 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][210/312]	eta 0:01:16 lr 0.000386	time 0.8327 (0.7518)	model_time 0.8323 (0.7444)	loss 2.9164 (2.7577)	grad_norm 2.4176 (2.1728/0.9358)	mem 34604MB
[2025-01-19 17:54:41 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][190/312]	eta 0:01:32 lr 0.000387	time 0.7193 (0.7556)	model_time 0.7191 (0.7469)	loss 3.2416 (2.7923)	grad_norm 3.6790 (2.2530/0.8015)	mem 34602MB
[2025-01-19 17:54:47 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][220/312]	eta 0:01:09 lr 0.000386	time 0.7425 (0.7528)	model_time 0.7421 (0.7457)	loss 2.6091 (2.7657)	grad_norm 3.6647 (2.1911/0.9427)	mem 34604MB
[2025-01-19 17:54:48 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][200/312]	eta 0:01:24 lr 0.000387	time 0.7217 (0.7552)	model_time 0.7213 (0.7469)	loss 3.1546 (2.7953)	grad_norm 2.0350 (2.2543/0.7996)	mem 34602MB
[2025-01-19 17:54:55 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][230/312]	eta 0:01:01 lr 0.000385	time 0.8154 (0.7527)	model_time 0.8149 (0.7460)	loss 2.7515 (2.7661)	grad_norm 3.8496 (2.2034/0.9442)	mem 34604MB
[2025-01-19 17:54:56 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][210/312]	eta 0:01:17 lr 0.000386	time 0.8089 (0.7554)	model_time 0.8088 (0.7475)	loss 2.6040 (2.7950)	grad_norm 1.5936 (2.2505/0.7922)	mem 34602MB
[2025-01-19 17:55:03 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][240/312]	eta 0:00:54 lr 0.000385	time 0.8184 (0.7535)	model_time 0.8183 (0.7470)	loss 3.2157 (2.7714)	grad_norm 1.3512 (2.2186/0.9586)	mem 34604MB
[2025-01-19 17:55:03 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][220/312]	eta 0:01:09 lr 0.000386	time 0.7275 (0.7548)	model_time 0.7273 (0.7472)	loss 2.8475 (2.7983)	grad_norm 2.5323 (2.2479/0.7987)	mem 34602MB
[2025-01-19 17:55:10 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][250/312]	eta 0:00:46 lr 0.000385	time 0.9320 (0.7542)	model_time 0.9315 (0.7480)	loss 2.7198 (2.7764)	grad_norm 1.8193 (2.2230/0.9512)	mem 34604MB
[2025-01-19 17:55:11 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][230/312]	eta 0:01:01 lr 0.000385	time 0.8036 (0.7545)	model_time 0.8032 (0.7473)	loss 3.0268 (2.7975)	grad_norm 2.1098 (2.2448/0.8008)	mem 34602MB
[2025-01-19 17:55:18 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][260/312]	eta 0:00:39 lr 0.000384	time 0.8111 (0.7538)	model_time 0.8109 (0.7478)	loss 3.0302 (2.7765)	grad_norm 3.0285 (2.2117/0.9590)	mem 34604MB
[2025-01-19 17:55:18 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][240/312]	eta 0:00:54 lr 0.000385	time 0.7204 (0.7543)	model_time 0.7199 (0.7473)	loss 2.3538 (2.8000)	grad_norm 1.7976 (2.2311/0.7906)	mem 34602MB
[2025-01-19 17:55:25 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][270/312]	eta 0:00:31 lr 0.000384	time 0.7559 (0.7529)	model_time 0.7555 (0.7472)	loss 2.1817 (2.7768)	grad_norm 4.0660 (2.2292/0.9622)	mem 34604MB
[2025-01-19 17:55:26 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][250/312]	eta 0:00:46 lr 0.000385	time 0.7228 (0.7542)	model_time 0.7222 (0.7476)	loss 2.6711 (2.7973)	grad_norm 3.1253 (2.2151/0.7867)	mem 34602MB
[2025-01-19 17:55:33 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][280/312]	eta 0:00:24 lr 0.000384	time 0.7225 (0.7523)	model_time 0.7224 (0.7467)	loss 2.8476 (2.7700)	grad_norm 6.5101 (2.2896/1.0239)	mem 34604MB
[2025-01-19 17:55:33 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][260/312]	eta 0:00:39 lr 0.000384	time 0.8067 (0.7541)	model_time 0.8066 (0.7476)	loss 3.2295 (2.7987)	grad_norm 1.7413 (2.2201/0.7910)	mem 34602MB
[2025-01-19 17:55:40 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][290/312]	eta 0:00:16 lr 0.000383	time 0.7269 (0.7516)	model_time 0.7265 (0.7462)	loss 2.1712 (2.7663)	grad_norm 2.1996 (2.3248/1.0343)	mem 34604MB
[2025-01-19 17:55:40 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][270/312]	eta 0:00:31 lr 0.000384	time 0.7213 (0.7534)	model_time 0.7212 (0.7472)	loss 2.7726 (2.7953)	grad_norm 1.0760 (2.2419/0.8020)	mem 34602MB
[2025-01-19 17:55:47 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][300/312]	eta 0:00:09 lr 0.000383	time 0.7134 (0.7506)	model_time 0.7133 (0.7454)	loss 2.3709 (2.7659)	grad_norm 1.7367 (2.3373/1.0369)	mem 34604MB
[2025-01-19 17:55:48 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][280/312]	eta 0:00:24 lr 0.000384	time 0.7171 (0.7530)	model_time 0.7167 (0.7470)	loss 2.8007 (2.7928)	grad_norm 2.3878 (2.2352/0.7953)	mem 34602MB
[2025-01-19 17:55:54 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][310/312]	eta 0:00:01 lr 0.000382	time 0.7161 (0.7498)	model_time 0.7160 (0.7447)	loss 3.0977 (2.7638)	grad_norm 3.6615 (2.3264/1.0404)	mem 34604MB
[2025-01-19 17:55:55 internimage_b_1k_224] (main.py 519): INFO EPOCH 242 training takes 0:03:53
[2025-01-19 17:55:55 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_242.pth saving......
[2025-01-19 17:55:55 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][290/312]	eta 0:00:16 lr 0.000383	time 0.7188 (0.7525)	model_time 0.7186 (0.7467)	loss 2.8193 (2.7914)	grad_norm 3.3742 (2.2418/0.7911)	mem 34602MB
[2025-01-19 17:55:58 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_242.pth saved !!!
[2025-01-19 17:56:03 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][300/312]	eta 0:00:09 lr 0.000383	time 0.7147 (0.7521)	model_time 0.7146 (0.7464)	loss 1.9080 (2.7938)	grad_norm 5.1217 (2.2660/0.8197)	mem 34602MB
[2025-01-19 17:56:06 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.580 (7.580)	Loss 0.6920 (0.6920)	Acc@1 86.621 (86.621)	Acc@5 97.827 (97.827)	Mem 34604MB
[2025-01-19 17:56:09 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.966)	Loss 0.9072 (0.7818)	Acc@1 80.420 (84.217)	Acc@5 96.069 (96.888)	Mem 34604MB
[2025-01-19 17:56:09 internimage_b_1k_224] (main.py 575): INFO [Epoch:242] * Acc@1 84.025 Acc@5 96.899
[2025-01-19 17:56:09 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.0%
[2025-01-19 17:56:09 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 17:56:10 internimage_b_1k_224] (main.py 510): INFO Train: [242/300][310/312]	eta 0:00:01 lr 0.000382	time 0.7154 (0.7515)	model_time 0.7153 (0.7461)	loss 3.0279 (2.7869)	grad_norm 2.1562 (2.2717/0.8207)	mem 34602MB
[2025-01-19 17:56:11 internimage_b_1k_224] (main.py 519): INFO EPOCH 242 training takes 0:03:54
[2025-01-19 17:56:11 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_242.pth saving......
[2025-01-19 17:56:12 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 17:56:12 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.03%
[2025-01-19 17:56:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_242.pth saved !!!
[2025-01-19 17:56:28 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.580 (15.580)	Loss 0.7122 (0.7122)	Acc@1 86.353 (86.353)	Acc@5 98.193 (98.193)	Mem 34604MB
[2025-01-19 17:56:31 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.769 (16.769)	Loss 0.6990 (0.6990)	Acc@1 85.718 (85.718)	Acc@5 97.852 (97.852)	Mem 34602MB
[2025-01-19 17:56:34 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.998)	Loss 0.9291 (0.8074)	Acc@1 80.493 (84.180)	Acc@5 95.728 (96.891)	Mem 34604MB
[2025-01-19 17:56:35 internimage_b_1k_224] (main.py 575): INFO [Epoch:242] * Acc@1 84.025 Acc@5 96.931
[2025-01-19 17:56:35 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.0%
[2025-01-19 17:56:35 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:56:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.999)	Loss 0.8948 (0.7797)	Acc@1 80.078 (84.084)	Acc@5 96.167 (96.933)	Mem 34602MB
[2025-01-19 17:56:36 internimage_b_1k_224] (main.py 575): INFO [Epoch:242] * Acc@1 83.935 Acc@5 96.939
[2025-01-19 17:56:36 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.9%
[2025-01-19 17:56:36 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.02%
[2025-01-19 17:56:38 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:56:38 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.03%
[2025-01-19 17:56:41 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][0/312]	eta 0:11:34 lr 0.000382	time 2.2259 (2.2259)	model_time 0.7308 (0.7308)	loss 2.0042 (2.0042)	grad_norm 4.0463 (4.0463/0.0000)	mem 34604MB
[2025-01-19 17:56:45 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.206 (9.206)	Loss 0.7218 (0.7218)	Acc@1 86.060 (86.060)	Acc@5 98.218 (98.218)	Mem 34602MB
[2025-01-19 17:56:48 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][10/312]	eta 0:04:23 lr 0.000382	time 0.7256 (0.8730)	model_time 0.7254 (0.7368)	loss 1.9942 (2.5597)	grad_norm 2.9328 (2.3379/0.7109)	mem 34604MB
[2025-01-19 17:56:50 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.246)	Loss 0.9290 (0.8082)	Acc@1 79.956 (84.129)	Acc@5 95.972 (96.977)	Mem 34602MB
[2025-01-19 17:56:50 internimage_b_1k_224] (main.py 575): INFO [Epoch:242] * Acc@1 83.949 Acc@5 97.013
[2025-01-19 17:56:50 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.9%
[2025-01-19 17:56:50 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 17:56:54 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 17:56:54 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.95%
[2025-01-19 17:56:56 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][20/312]	eta 0:03:58 lr 0.000382	time 0.8036 (0.8168)	model_time 0.8034 (0.7454)	loss 2.2909 (2.6446)	grad_norm 1.1903 (2.1997/0.7344)	mem 34604MB
[2025-01-19 17:56:56 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][0/312]	eta 0:11:10 lr 0.000382	time 2.1480 (2.1480)	model_time 0.7541 (0.7541)	loss 1.6708 (1.6708)	grad_norm 2.3195 (2.3195/0.0000)	mem 34602MB
[2025-01-19 17:57:03 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][30/312]	eta 0:03:46 lr 0.000381	time 0.7182 (0.8023)	model_time 0.7177 (0.7538)	loss 3.2289 (2.7035)	grad_norm 3.0701 (2.3609/0.9808)	mem 34604MB
[2025-01-19 17:57:04 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][10/312]	eta 0:04:24 lr 0.000382	time 0.7321 (0.8760)	model_time 0.7320 (0.7489)	loss 3.1631 (2.6701)	grad_norm 1.7020 (2.1358/0.5918)	mem 34602MB
[2025-01-19 17:57:11 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][40/312]	eta 0:03:34 lr 0.000381	time 0.7451 (0.7899)	model_time 0.7449 (0.7531)	loss 2.7062 (2.7469)	grad_norm 1.4478 (2.3063/0.9206)	mem 34604MB
[2025-01-19 17:57:11 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][20/312]	eta 0:03:59 lr 0.000382	time 0.7201 (0.8218)	model_time 0.7200 (0.7551)	loss 3.1679 (2.7245)	grad_norm 1.8487 (1.9206/0.6062)	mem 34602MB
[2025-01-19 17:57:18 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][50/312]	eta 0:03:25 lr 0.000381	time 0.7312 (0.7846)	model_time 0.7308 (0.7549)	loss 2.8705 (2.7590)	grad_norm 1.5064 (2.1666/0.8810)	mem 34604MB
[2025-01-19 17:57:19 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][30/312]	eta 0:03:45 lr 0.000381	time 0.7178 (0.7981)	model_time 0.7177 (0.7529)	loss 2.4206 (2.6713)	grad_norm 4.4890 (2.0706/0.8613)	mem 34602MB
[2025-01-19 17:57:26 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][60/312]	eta 0:03:17 lr 0.000380	time 0.8169 (0.7826)	model_time 0.8167 (0.7578)	loss 1.5370 (2.7429)	grad_norm 1.1140 (2.1019/0.8936)	mem 34604MB
[2025-01-19 17:57:26 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][40/312]	eta 0:03:34 lr 0.000381	time 0.8028 (0.7883)	model_time 0.8026 (0.7540)	loss 2.8007 (2.7425)	grad_norm 2.8731 (2.3606/1.1450)	mem 34602MB
[2025-01-19 17:57:33 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][70/312]	eta 0:03:07 lr 0.000380	time 0.7272 (0.7753)	model_time 0.7268 (0.7539)	loss 2.9551 (2.7387)	grad_norm 1.7029 (2.0819/0.8737)	mem 34604MB
[2025-01-19 17:57:34 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][50/312]	eta 0:03:24 lr 0.000381	time 0.7337 (0.7790)	model_time 0.7331 (0.7514)	loss 2.9368 (2.7397)	grad_norm 1.5826 (2.4228/1.1459)	mem 34602MB
[2025-01-19 17:57:41 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][80/312]	eta 0:02:58 lr 0.000379	time 0.7237 (0.7712)	model_time 0.7235 (0.7524)	loss 3.0072 (2.7497)	grad_norm 1.5414 (2.0716/0.8318)	mem 34604MB
[2025-01-19 17:57:41 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][60/312]	eta 0:03:15 lr 0.000380	time 0.7266 (0.7742)	model_time 0.7262 (0.7511)	loss 2.7025 (2.7397)	grad_norm 2.0612 (2.3551/1.0768)	mem 34602MB
[2025-01-19 17:57:48 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][90/312]	eta 0:02:50 lr 0.000379	time 0.7240 (0.7671)	model_time 0.7235 (0.7504)	loss 2.5320 (2.7549)	grad_norm 2.4390 (2.0668/0.7977)	mem 34604MB
[2025-01-19 17:57:49 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][70/312]	eta 0:03:06 lr 0.000380	time 0.7166 (0.7710)	model_time 0.7165 (0.7511)	loss 1.8841 (2.7218)	grad_norm 2.9180 (2.3587/1.0324)	mem 34602MB
[2025-01-19 17:57:56 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][100/312]	eta 0:02:42 lr 0.000379	time 0.8070 (0.7643)	model_time 0.8065 (0.7491)	loss 2.9953 (2.7249)	grad_norm 1.7520 (2.0571/0.8002)	mem 34604MB
[2025-01-19 17:57:56 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][80/312]	eta 0:02:58 lr 0.000379	time 0.7376 (0.7683)	model_time 0.7370 (0.7508)	loss 2.5701 (2.7231)	grad_norm 2.9689 (2.3463/0.9967)	mem 34602MB
[2025-01-19 17:58:03 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][110/312]	eta 0:02:33 lr 0.000378	time 0.7585 (0.7613)	model_time 0.7580 (0.7475)	loss 2.9414 (2.7272)	grad_norm 2.7548 (2.0568/0.8050)	mem 34604MB
[2025-01-19 17:58:04 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][90/312]	eta 0:02:49 lr 0.000379	time 0.7262 (0.7653)	model_time 0.7258 (0.7496)	loss 2.7866 (2.7300)	grad_norm 2.4647 (2.4080/1.0529)	mem 34602MB
[2025-01-19 17:58:10 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][120/312]	eta 0:02:25 lr 0.000378	time 0.7140 (0.7584)	model_time 0.7138 (0.7457)	loss 2.4400 (2.7083)	grad_norm 2.0215 (2.0096/0.7929)	mem 34604MB
[2025-01-19 17:58:11 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][100/312]	eta 0:02:41 lr 0.000379	time 0.7910 (0.7634)	model_time 0.7909 (0.7493)	loss 2.7794 (2.7303)	grad_norm 2.2486 (2.3963/1.0412)	mem 34602MB
[2025-01-19 17:58:18 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][130/312]	eta 0:02:17 lr 0.000378	time 0.7205 (0.7570)	model_time 0.7201 (0.7452)	loss 3.1254 (2.7203)	grad_norm 1.3169 (2.0377/0.7984)	mem 34604MB
[2025-01-19 17:58:18 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][110/312]	eta 0:02:33 lr 0.000378	time 0.7227 (0.7610)	model_time 0.7222 (0.7481)	loss 2.1201 (2.7206)	grad_norm 1.6618 (2.3711/1.0312)	mem 34602MB
[2025-01-19 17:58:25 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][140/312]	eta 0:02:10 lr 0.000377	time 0.7985 (0.7573)	model_time 0.7984 (0.7463)	loss 3.1354 (2.7434)	grad_norm 1.7949 (2.0405/0.7794)	mem 34604MB
[2025-01-19 17:58:26 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][120/312]	eta 0:02:25 lr 0.000378	time 0.7213 (0.7596)	model_time 0.7211 (0.7477)	loss 2.8217 (2.7206)	grad_norm 2.1619 (2.3264/1.0053)	mem 34602MB
[2025-01-19 17:58:33 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][150/312]	eta 0:02:02 lr 0.000377	time 0.8092 (0.7576)	model_time 0.8091 (0.7473)	loss 2.7808 (2.7348)	grad_norm 2.4888 (2.0197/0.7717)	mem 34604MB
[2025-01-19 17:58:33 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][130/312]	eta 0:02:18 lr 0.000378	time 0.7244 (0.7585)	model_time 0.7243 (0.7475)	loss 2.5960 (2.7232)	grad_norm 1.7003 (2.2665/0.9953)	mem 34602MB
[2025-01-19 17:58:40 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][160/312]	eta 0:01:55 lr 0.000376	time 0.7502 (0.7569)	model_time 0.7500 (0.7472)	loss 3.1743 (2.7389)	grad_norm 3.4543 (2.0342/0.7677)	mem 34604MB
[2025-01-19 17:58:41 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][140/312]	eta 0:02:10 lr 0.000377	time 0.7213 (0.7592)	model_time 0.7208 (0.7490)	loss 2.3917 (2.7249)	grad_norm 2.8069 (2.2537/0.9691)	mem 34602MB
[2025-01-19 17:58:48 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][170/312]	eta 0:01:47 lr 0.000376	time 0.7166 (0.7577)	model_time 0.7162 (0.7486)	loss 3.0053 (2.7372)	grad_norm 3.5520 (2.0825/0.8090)	mem 34604MB
[2025-01-19 17:58:49 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][150/312]	eta 0:02:03 lr 0.000377	time 0.7107 (0.7595)	model_time 0.7105 (0.7499)	loss 2.2984 (2.7135)	grad_norm 3.5798 (2.2780/0.9988)	mem 34602MB
[2025-01-19 17:58:56 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][180/312]	eta 0:01:40 lr 0.000376	time 0.8132 (0.7583)	model_time 0.8131 (0.7497)	loss 2.5264 (2.7325)	grad_norm 1.2351 (2.0828/0.8135)	mem 34604MB
[2025-01-19 17:58:56 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][160/312]	eta 0:01:55 lr 0.000376	time 0.7110 (0.7584)	model_time 0.7105 (0.7495)	loss 2.8101 (2.7211)	grad_norm 2.1799 (2.2841/0.9980)	mem 34602MB
[2025-01-19 17:59:03 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][190/312]	eta 0:01:32 lr 0.000375	time 0.7211 (0.7568)	model_time 0.7207 (0.7487)	loss 3.0637 (2.7444)	grad_norm 1.7984 (2.1119/0.8307)	mem 34604MB
[2025-01-19 17:59:03 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][170/312]	eta 0:01:47 lr 0.000376	time 0.7173 (0.7577)	model_time 0.7172 (0.7492)	loss 2.8980 (2.7189)	grad_norm 1.9981 (2.2646/0.9805)	mem 34602MB
[2025-01-19 17:59:10 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][200/312]	eta 0:01:24 lr 0.000375	time 0.7112 (0.7562)	model_time 0.7111 (0.7484)	loss 2.3184 (2.7386)	grad_norm 1.3534 (2.0891/0.8256)	mem 34604MB
[2025-01-19 17:59:11 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][180/312]	eta 0:01:39 lr 0.000376	time 0.7180 (0.7569)	model_time 0.7176 (0.7488)	loss 2.4646 (2.7128)	grad_norm 1.2433 (2.2453/0.9663)	mem 34602MB
[2025-01-19 17:59:18 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][210/312]	eta 0:01:16 lr 0.000375	time 0.7282 (0.7547)	model_time 0.7281 (0.7472)	loss 2.2528 (2.7377)	grad_norm 1.8092 (2.0718/0.8186)	mem 34604MB
[2025-01-19 17:59:18 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][190/312]	eta 0:01:32 lr 0.000375	time 0.7185 (0.7569)	model_time 0.7184 (0.7492)	loss 1.6796 (2.7045)	grad_norm 1.7267 (2.2459/0.9617)	mem 34602MB
[2025-01-19 17:59:25 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][220/312]	eta 0:01:09 lr 0.000374	time 0.8072 (0.7536)	model_time 0.8068 (0.7465)	loss 3.1173 (2.7419)	grad_norm 1.5686 (2.0516/0.8129)	mem 34604MB
[2025-01-19 17:59:26 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][200/312]	eta 0:01:24 lr 0.000375	time 0.7208 (0.7567)	model_time 0.7204 (0.7494)	loss 1.9674 (2.6999)	grad_norm 2.0018 (2.2705/0.9833)	mem 34602MB
[2025-01-19 17:59:32 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][230/312]	eta 0:01:01 lr 0.000374	time 0.7225 (0.7523)	model_time 0.7220 (0.7455)	loss 1.6608 (2.7461)	grad_norm 1.2202 (2.0468/0.8027)	mem 34604MB
[2025-01-19 17:59:33 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][210/312]	eta 0:01:17 lr 0.000375	time 0.7182 (0.7555)	model_time 0.7178 (0.7486)	loss 2.9898 (2.7019)	grad_norm 3.0553 (2.3023/0.9925)	mem 34602MB
[2025-01-19 17:59:39 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][240/312]	eta 0:00:54 lr 0.000373	time 0.7381 (0.7513)	model_time 0.7380 (0.7447)	loss 3.1321 (2.7524)	grad_norm 1.4551 (2.0550/0.8058)	mem 34604MB
[2025-01-19 17:59:41 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][220/312]	eta 0:01:09 lr 0.000374	time 0.7999 (0.7555)	model_time 0.7997 (0.7489)	loss 3.1394 (2.7076)	grad_norm 1.4190 (2.3456/1.0123)	mem 34602MB
[2025-01-19 17:59:47 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][250/312]	eta 0:00:46 lr 0.000373	time 0.7258 (0.7507)	model_time 0.7256 (0.7444)	loss 2.9454 (2.7525)	grad_norm 1.5817 (2.0523/0.8034)	mem 34604MB
[2025-01-19 17:59:48 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][230/312]	eta 0:01:01 lr 0.000374	time 0.7199 (0.7547)	model_time 0.7197 (0.7484)	loss 2.5515 (2.7057)	grad_norm 3.2299 (2.3619/1.0105)	mem 34602MB
[2025-01-19 17:59:55 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][260/312]	eta 0:00:39 lr 0.000373	time 0.7167 (0.7515)	model_time 0.7163 (0.7454)	loss 3.3948 (2.7529)	grad_norm 2.6449 (2.0482/0.8010)	mem 34604MB
[2025-01-19 17:59:56 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][240/312]	eta 0:00:54 lr 0.000373	time 0.7192 (0.7540)	model_time 0.7187 (0.7479)	loss 2.6622 (2.7040)	grad_norm 3.0349 (2.3727/1.0139)	mem 34602MB
[2025-01-19 18:00:02 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][270/312]	eta 0:00:31 lr 0.000372	time 0.7156 (0.7519)	model_time 0.7152 (0.7460)	loss 2.6750 (2.7541)	grad_norm 3.5822 (2.0666/0.8167)	mem 34604MB
[2025-01-19 18:00:03 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][250/312]	eta 0:00:46 lr 0.000373	time 0.7263 (0.7538)	model_time 0.7261 (0.7479)	loss 2.5950 (2.7019)	grad_norm 1.7771 (2.3588/1.0048)	mem 34602MB
[2025-01-19 18:00:10 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][280/312]	eta 0:00:24 lr 0.000372	time 0.7481 (0.7522)	model_time 0.7477 (0.7465)	loss 2.9871 (2.7612)	grad_norm 3.3651 (2.1043/0.8526)	mem 34604MB
[2025-01-19 18:00:11 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][260/312]	eta 0:00:39 lr 0.000373	time 0.7350 (0.7540)	model_time 0.7345 (0.7483)	loss 2.8891 (2.7087)	grad_norm 5.1203 (2.3566/1.0114)	mem 34602MB
[2025-01-19 18:00:17 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][290/312]	eta 0:00:16 lr 0.000372	time 0.7186 (0.7526)	model_time 0.7184 (0.7471)	loss 3.0127 (2.7608)	grad_norm 2.0163 (2.1226/0.8686)	mem 34604MB
[2025-01-19 18:00:18 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][270/312]	eta 0:00:31 lr 0.000372	time 0.7294 (0.7541)	model_time 0.7290 (0.7486)	loss 2.9094 (2.7151)	grad_norm 1.6248 (2.3625/1.0136)	mem 34602MB
[2025-01-19 18:00:25 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][300/312]	eta 0:00:09 lr 0.000371	time 0.7119 (0.7529)	model_time 0.7118 (0.7476)	loss 3.0719 (2.7603)	grad_norm 2.0948 (2.1337/0.8730)	mem 34604MB
[2025-01-19 18:00:26 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][280/312]	eta 0:00:24 lr 0.000372	time 0.7265 (0.7538)	model_time 0.7264 (0.7484)	loss 2.9620 (2.7179)	grad_norm 2.7419 (2.3670/1.0036)	mem 34602MB
[2025-01-19 18:00:32 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][310/312]	eta 0:00:01 lr 0.000371	time 0.7070 (0.7520)	model_time 0.7069 (0.7468)	loss 3.2397 (2.7565)	grad_norm 1.7238 (2.1353/0.8792)	mem 34604MB
[2025-01-19 18:00:33 internimage_b_1k_224] (main.py 519): INFO EPOCH 243 training takes 0:03:54
[2025-01-19 18:00:33 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_243.pth saving......
[2025-01-19 18:00:33 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][290/312]	eta 0:00:16 lr 0.000372	time 0.7171 (0.7541)	model_time 0.7169 (0.7490)	loss 2.7757 (2.7235)	grad_norm 2.8247 (2.3755/1.0028)	mem 34602MB
[2025-01-19 18:00:36 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_243.pth saved !!!
[2025-01-19 18:00:41 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][300/312]	eta 0:00:09 lr 0.000371	time 0.7635 (0.7539)	model_time 0.7634 (0.7489)	loss 3.5068 (2.7262)	grad_norm 1.6554 (2.3689/1.0002)	mem 34602MB
[2025-01-19 18:00:44 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.306 (7.306)	Loss 0.6902 (0.6902)	Acc@1 85.889 (85.889)	Acc@5 97.949 (97.949)	Mem 34604MB
[2025-01-19 18:00:47 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.936)	Loss 0.8984 (0.7750)	Acc@1 80.908 (84.200)	Acc@5 95.972 (96.842)	Mem 34604MB
[2025-01-19 18:00:47 internimage_b_1k_224] (main.py 575): INFO [Epoch:243] * Acc@1 84.047 Acc@5 96.859
[2025-01-19 18:00:47 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.0%
[2025-01-19 18:00:47 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 18:00:48 internimage_b_1k_224] (main.py 510): INFO Train: [243/300][310/312]	eta 0:00:01 lr 0.000371	time 0.7210 (0.7536)	model_time 0.7209 (0.7488)	loss 3.1023 (2.7342)	grad_norm 2.0854 (2.3777/0.9999)	mem 34602MB
[2025-01-19 18:00:49 internimage_b_1k_224] (main.py 519): INFO EPOCH 243 training takes 0:03:55
[2025-01-19 18:00:49 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_243.pth saving......
[2025-01-19 18:00:50 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 18:00:50 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.05%
[2025-01-19 18:00:52 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_243.pth saved !!!
[2025-01-19 18:01:06 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.469 (15.469)	Loss 0.7122 (0.7122)	Acc@1 86.353 (86.353)	Acc@5 98.193 (98.193)	Mem 34604MB
[2025-01-19 18:01:09 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.437 (16.437)	Loss 0.7041 (0.7041)	Acc@1 86.230 (86.230)	Acc@5 97.827 (97.827)	Mem 34602MB
[2025-01-19 18:01:13 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.081)	Loss 0.9285 (0.8070)	Acc@1 80.518 (84.191)	Acc@5 95.752 (96.919)	Mem 34604MB
[2025-01-19 18:01:14 internimage_b_1k_224] (main.py 575): INFO [Epoch:243] * Acc@1 84.039 Acc@5 96.957
[2025-01-19 18:01:14 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.0%
[2025-01-19 18:01:14 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:01:15 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.017)	Loss 0.9172 (0.7941)	Acc@1 80.664 (84.264)	Acc@5 96.021 (96.884)	Mem 34602MB
[2025-01-19 18:01:15 internimage_b_1k_224] (main.py 575): INFO [Epoch:243] * Acc@1 84.101 Acc@5 96.893
[2025-01-19 18:01:15 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 18:01:15 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 18:01:18 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:01:18 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.04%
[2025-01-19 18:01:18 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 18:01:18 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.10%
[2025-01-19 18:01:20 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][0/312]	eta 0:11:01 lr 0.000371	time 2.1192 (2.1192)	model_time 0.7317 (0.7317)	loss 2.7058 (2.7058)	grad_norm 1.4514 (1.4514/0.0000)	mem 34604MB
[2025-01-19 18:01:26 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.719 (7.719)	Loss 0.7219 (0.7219)	Acc@1 86.157 (86.157)	Acc@5 98.267 (98.267)	Mem 34602MB
[2025-01-19 18:01:27 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][10/312]	eta 0:04:22 lr 0.000370	time 0.7269 (0.8708)	model_time 0.7268 (0.7429)	loss 2.8239 (2.9195)	grad_norm 1.4720 (1.9007/0.7532)	mem 34604MB
[2025-01-19 18:01:29 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.971)	Loss 0.9282 (0.8078)	Acc@1 80.029 (84.157)	Acc@5 95.996 (96.986)	Mem 34602MB
[2025-01-19 18:01:29 internimage_b_1k_224] (main.py 575): INFO [Epoch:243] * Acc@1 83.979 Acc@5 97.023
[2025-01-19 18:01:29 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.0%
[2025-01-19 18:01:29 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:01:33 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:01:33 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.98%
[2025-01-19 18:01:34 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][20/312]	eta 0:03:55 lr 0.000370	time 0.7392 (0.8073)	model_time 0.7390 (0.7401)	loss 2.7925 (2.8316)	grad_norm 1.1937 (1.9020/0.6026)	mem 34604MB
[2025-01-19 18:01:35 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][0/312]	eta 0:11:11 lr 0.000371	time 2.1508 (2.1508)	model_time 0.7497 (0.7497)	loss 3.4592 (3.4592)	grad_norm 2.1667 (2.1667/0.0000)	mem 34602MB
[2025-01-19 18:01:42 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][30/312]	eta 0:03:41 lr 0.000370	time 0.7359 (0.7860)	model_time 0.7358 (0.7403)	loss 2.1976 (2.7756)	grad_norm 2.9532 (2.1309/0.7587)	mem 34604MB
[2025-01-19 18:01:42 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][10/312]	eta 0:04:25 lr 0.000370	time 0.8015 (0.8784)	model_time 0.8014 (0.7507)	loss 2.6865 (2.9616)	grad_norm 1.5011 (1.7624/0.4511)	mem 34602MB
[2025-01-19 18:01:49 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][40/312]	eta 0:03:29 lr 0.000369	time 0.7189 (0.7717)	model_time 0.7187 (0.7371)	loss 2.3591 (2.7123)	grad_norm 2.1636 (2.1628/0.7256)	mem 34604MB
[2025-01-19 18:01:50 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][20/312]	eta 0:03:55 lr 0.000370	time 0.7308 (0.8071)	model_time 0.7302 (0.7401)	loss 2.5966 (2.8324)	grad_norm 3.2932 (2.2994/0.9730)	mem 34602MB
[2025-01-19 18:01:57 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][50/312]	eta 0:03:20 lr 0.000369	time 0.7166 (0.7644)	model_time 0.7162 (0.7365)	loss 2.8794 (2.6994)	grad_norm 1.7830 (2.1687/0.7058)	mem 34604MB
[2025-01-19 18:01:57 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][30/312]	eta 0:03:42 lr 0.000370	time 0.7287 (0.7884)	model_time 0.7285 (0.7428)	loss 2.1135 (2.7295)	grad_norm 2.1064 (2.3771/1.0672)	mem 34602MB
[2025-01-19 18:02:04 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][60/312]	eta 0:03:11 lr 0.000369	time 0.8042 (0.7598)	model_time 0.8041 (0.7364)	loss 2.6958 (2.7288)	grad_norm 1.7136 (2.0627/0.7039)	mem 34604MB
[2025-01-19 18:02:04 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][40/312]	eta 0:03:31 lr 0.000369	time 0.7311 (0.7760)	model_time 0.7306 (0.7415)	loss 2.9640 (2.7249)	grad_norm 1.1395 (2.1999/1.0082)	mem 34602MB
[2025-01-19 18:02:11 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][70/312]	eta 0:03:03 lr 0.000368	time 0.8226 (0.7596)	model_time 0.8224 (0.7395)	loss 2.7790 (2.7630)	grad_norm 2.2388 (2.0389/0.6766)	mem 34604MB
[2025-01-19 18:02:12 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][50/312]	eta 0:03:21 lr 0.000369	time 0.7210 (0.7689)	model_time 0.7208 (0.7411)	loss 3.4031 (2.7400)	grad_norm 1.4885 (2.1525/0.9726)	mem 34602MB
[2025-01-19 18:02:19 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][80/312]	eta 0:02:56 lr 0.000368	time 0.8010 (0.7607)	model_time 0.8009 (0.7430)	loss 3.4554 (2.7828)	grad_norm 3.5365 (2.1142/0.7134)	mem 34604MB
[2025-01-19 18:02:19 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][60/312]	eta 0:03:13 lr 0.000369	time 0.7253 (0.7663)	model_time 0.7251 (0.7430)	loss 2.9586 (2.7391)	grad_norm 1.3474 (2.1682/0.9813)	mem 34602MB
[2025-01-19 18:02:27 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][90/312]	eta 0:02:48 lr 0.000368	time 0.7982 (0.7605)	model_time 0.7980 (0.7447)	loss 2.1824 (2.7662)	grad_norm 1.8584 (2.1053/0.7067)	mem 34604MB
[2025-01-19 18:02:27 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][70/312]	eta 0:03:05 lr 0.000368	time 0.7126 (0.7678)	model_time 0.7124 (0.7476)	loss 2.9363 (2.7406)	grad_norm 2.6383 (2.2461/0.9883)	mem 34602MB
[2025-01-19 18:02:34 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][100/312]	eta 0:02:41 lr 0.000367	time 0.7207 (0.7610)	model_time 0.7203 (0.7467)	loss 2.1758 (2.7484)	grad_norm 1.8376 (2.0936/0.7448)	mem 34604MB
[2025-01-19 18:02:35 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][80/312]	eta 0:02:57 lr 0.000368	time 0.7370 (0.7671)	model_time 0.7365 (0.7495)	loss 2.3079 (2.7146)	grad_norm 3.4111 (2.2675/0.9622)	mem 34602MB
[2025-01-19 18:02:42 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][110/312]	eta 0:02:33 lr 0.000367	time 0.8098 (0.7615)	model_time 0.8094 (0.7485)	loss 2.4632 (2.7483)	grad_norm 1.5325 (2.1347/0.7915)	mem 34604MB
[2025-01-19 18:02:42 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][90/312]	eta 0:02:49 lr 0.000368	time 0.8058 (0.7650)	model_time 0.8056 (0.7492)	loss 2.9549 (2.7098)	grad_norm 1.6390 (2.2745/0.9556)	mem 34602MB
[2025-01-19 18:02:49 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][120/312]	eta 0:02:25 lr 0.000366	time 0.7127 (0.7593)	model_time 0.7125 (0.7474)	loss 2.2286 (2.7393)	grad_norm 0.9287 (2.1219/0.8069)	mem 34604MB
[2025-01-19 18:02:50 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][100/312]	eta 0:02:41 lr 0.000367	time 0.8085 (0.7630)	model_time 0.8084 (0.7488)	loss 3.2425 (2.7199)	grad_norm 2.8115 (2.2914/0.9598)	mem 34602MB
[2025-01-19 18:02:57 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][130/312]	eta 0:02:17 lr 0.000366	time 0.7193 (0.7578)	model_time 0.7192 (0.7468)	loss 2.0904 (2.7474)	grad_norm 4.0058 (2.1234/0.8040)	mem 34604MB
[2025-01-19 18:02:57 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][110/312]	eta 0:02:33 lr 0.000367	time 0.7273 (0.7619)	model_time 0.7272 (0.7489)	loss 2.7953 (2.7259)	grad_norm 2.8185 (2.2357/0.9524)	mem 34602MB
[2025-01-19 18:03:04 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][140/312]	eta 0:02:10 lr 0.000366	time 0.7124 (0.7560)	model_time 0.7122 (0.7457)	loss 3.4406 (2.7570)	grad_norm 3.0510 (2.1320/0.7941)	mem 34604MB
[2025-01-19 18:03:05 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][120/312]	eta 0:02:26 lr 0.000366	time 0.7217 (0.7612)	model_time 0.7215 (0.7493)	loss 3.5214 (2.7181)	grad_norm 1.6412 (2.2529/0.9613)	mem 34602MB
[2025-01-19 18:03:11 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][150/312]	eta 0:02:02 lr 0.000365	time 0.7254 (0.7547)	model_time 0.7252 (0.7451)	loss 2.8340 (2.7495)	grad_norm 3.6358 (2.1998/0.8565)	mem 34604MB
[2025-01-19 18:03:12 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][130/312]	eta 0:02:18 lr 0.000366	time 0.7998 (0.7606)	model_time 0.7997 (0.7495)	loss 2.3353 (2.7248)	grad_norm 1.6331 (2.2327/0.9406)	mem 34602MB
[2025-01-19 18:03:19 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][160/312]	eta 0:01:54 lr 0.000365	time 0.7222 (0.7527)	model_time 0.7220 (0.7437)	loss 3.3160 (2.7562)	grad_norm 1.6882 (2.2369/0.8740)	mem 34604MB
[2025-01-19 18:03:20 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][140/312]	eta 0:02:10 lr 0.000366	time 0.7169 (0.7583)	model_time 0.7164 (0.7480)	loss 2.8712 (2.7266)	grad_norm 2.6257 (2.2265/0.9190)	mem 34602MB
[2025-01-19 18:03:26 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][170/312]	eta 0:01:46 lr 0.000365	time 0.7379 (0.7517)	model_time 0.7375 (0.7431)	loss 3.0446 (2.7652)	grad_norm 1.3122 (2.2328/0.8645)	mem 34604MB
[2025-01-19 18:03:27 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][150/312]	eta 0:02:02 lr 0.000365	time 0.7166 (0.7579)	model_time 0.7164 (0.7482)	loss 3.4212 (2.7293)	grad_norm 3.1059 (2.2040/0.9228)	mem 34602MB
[2025-01-19 18:03:33 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][180/312]	eta 0:01:39 lr 0.000364	time 0.8059 (0.7511)	model_time 0.8057 (0.7430)	loss 3.1526 (2.7577)	grad_norm 1.2135 (2.2244/0.8635)	mem 34604MB
[2025-01-19 18:03:34 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][160/312]	eta 0:01:54 lr 0.000365	time 0.7234 (0.7563)	model_time 0.7229 (0.7473)	loss 3.1474 (2.7250)	grad_norm 1.7506 (2.1844/0.9038)	mem 34602MB
[2025-01-19 18:03:41 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][190/312]	eta 0:01:31 lr 0.000364	time 0.8417 (0.7511)	model_time 0.8416 (0.7434)	loss 2.6318 (2.7662)	grad_norm 2.2495 (2.2760/0.9027)	mem 34604MB
[2025-01-19 18:03:42 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][170/312]	eta 0:01:47 lr 0.000365	time 0.7320 (0.7555)	model_time 0.7319 (0.7469)	loss 2.4654 (2.7203)	grad_norm 1.1131 (2.1582/0.8987)	mem 34602MB
[2025-01-19 18:03:49 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][200/312]	eta 0:01:24 lr 0.000363	time 0.8407 (0.7514)	model_time 0.8406 (0.7440)	loss 3.0170 (2.7685)	grad_norm 3.9693 (2.3184/0.9231)	mem 34604MB
[2025-01-19 18:03:49 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][180/312]	eta 0:01:39 lr 0.000364	time 0.7199 (0.7554)	model_time 0.7198 (0.7473)	loss 3.2248 (2.7230)	grad_norm 2.5789 (2.1423/0.8856)	mem 34602MB
[2025-01-19 18:03:56 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][210/312]	eta 0:01:16 lr 0.000363	time 0.8010 (0.7519)	model_time 0.8009 (0.7449)	loss 2.5877 (2.7656)	grad_norm 2.2472 (2.3239/0.9107)	mem 34604MB
[2025-01-19 18:03:57 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][190/312]	eta 0:01:32 lr 0.000364	time 0.7158 (0.7568)	model_time 0.7153 (0.7491)	loss 1.9336 (2.7231)	grad_norm 1.9032 (2.1265/0.8718)	mem 34602MB
[2025-01-19 18:04:04 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][220/312]	eta 0:01:09 lr 0.000363	time 0.8114 (0.7530)	model_time 0.8113 (0.7463)	loss 2.4294 (2.7612)	grad_norm 1.2285 (2.3163/0.9048)	mem 34604MB
[2025-01-19 18:04:05 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][200/312]	eta 0:01:24 lr 0.000363	time 0.7240 (0.7564)	model_time 0.7239 (0.7491)	loss 3.1942 (2.7236)	grad_norm 1.8215 (2.1135/0.8597)	mem 34602MB
[2025-01-19 18:04:12 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][230/312]	eta 0:01:01 lr 0.000362	time 0.8045 (0.7534)	model_time 0.8043 (0.7469)	loss 2.9359 (2.7524)	grad_norm 2.7525 (2.2964/0.8994)	mem 34604MB
[2025-01-19 18:04:12 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][210/312]	eta 0:01:17 lr 0.000363	time 0.8226 (0.7558)	model_time 0.8221 (0.7488)	loss 2.9580 (2.7220)	grad_norm 2.5814 (2.1348/0.8652)	mem 34602MB
[2025-01-19 18:04:19 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][240/312]	eta 0:00:54 lr 0.000362	time 0.7200 (0.7525)	model_time 0.7199 (0.7463)	loss 3.1695 (2.7596)	grad_norm 1.4854 (2.2694/0.8925)	mem 34604MB
[2025-01-19 18:04:20 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][220/312]	eta 0:01:09 lr 0.000363	time 0.8157 (0.7555)	model_time 0.8155 (0.7488)	loss 2.9382 (2.7276)	grad_norm 2.0697 (2.1323/0.8661)	mem 34602MB
[2025-01-19 18:04:26 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][250/312]	eta 0:00:46 lr 0.000362	time 0.7154 (0.7525)	model_time 0.7150 (0.7465)	loss 2.9351 (2.7651)	grad_norm 2.1199 (2.2759/0.8902)	mem 34604MB
[2025-01-19 18:04:27 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][230/312]	eta 0:01:01 lr 0.000362	time 0.7123 (0.7555)	model_time 0.7118 (0.7491)	loss 1.9285 (2.7246)	grad_norm 1.4295 (2.1110/0.8576)	mem 34602MB
[2025-01-19 18:04:34 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][260/312]	eta 0:00:39 lr 0.000361	time 0.7311 (0.7518)	model_time 0.7310 (0.7461)	loss 3.0828 (2.7717)	grad_norm 2.4965 (2.2853/0.8875)	mem 34604MB
[2025-01-19 18:04:35 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][240/312]	eta 0:00:54 lr 0.000362	time 0.7212 (0.7553)	model_time 0.7210 (0.7491)	loss 3.1860 (2.7210)	grad_norm 2.8462 (2.1060/0.8566)	mem 34602MB
[2025-01-19 18:04:41 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][270/312]	eta 0:00:31 lr 0.000361	time 0.7204 (0.7511)	model_time 0.7202 (0.7455)	loss 3.1638 (2.7703)	grad_norm 3.0772 (2.3153/0.8986)	mem 34604MB
[2025-01-19 18:04:42 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][250/312]	eta 0:00:46 lr 0.000362	time 0.8237 (0.7551)	model_time 0.8235 (0.7491)	loss 2.5249 (2.7244)	grad_norm 1.0952 (2.1032/0.8526)	mem 34602MB
[2025-01-19 18:04:48 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][280/312]	eta 0:00:24 lr 0.000361	time 0.7454 (0.7505)	model_time 0.7450 (0.7452)	loss 3.3779 (2.7762)	grad_norm 4.1895 (2.3386/0.9081)	mem 34604MB
[2025-01-19 18:04:49 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][260/312]	eta 0:00:39 lr 0.000361	time 0.7228 (0.7541)	model_time 0.7224 (0.7484)	loss 3.1551 (2.7202)	grad_norm 4.2938 (2.1207/0.8582)	mem 34602MB
[2025-01-19 18:04:56 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][290/312]	eta 0:00:16 lr 0.000360	time 0.7289 (0.7497)	model_time 0.7285 (0.7445)	loss 2.5732 (2.7766)	grad_norm 1.8943 (2.3414/0.9011)	mem 34604MB
[2025-01-19 18:04:57 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][270/312]	eta 0:00:31 lr 0.000361	time 0.7182 (0.7541)	model_time 0.7180 (0.7486)	loss 3.1795 (2.7259)	grad_norm 2.2396 (2.1199/0.8513)	mem 34602MB
[2025-01-19 18:05:03 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][300/312]	eta 0:00:08 lr 0.000360	time 0.7946 (0.7492)	model_time 0.7945 (0.7441)	loss 3.2315 (2.7743)	grad_norm 4.0291 (2.3723/0.9266)	mem 34604MB
[2025-01-19 18:05:04 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][280/312]	eta 0:00:24 lr 0.000361	time 0.7176 (0.7534)	model_time 0.7170 (0.7481)	loss 2.9275 (2.7347)	grad_norm 2.9895 (2.1302/0.8417)	mem 34602MB
[2025-01-19 18:05:10 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][310/312]	eta 0:00:01 lr 0.000360	time 0.7118 (0.7486)	model_time 0.7117 (0.7437)	loss 3.1859 (2.7742)	grad_norm 4.4471 (2.4134/0.9544)	mem 34604MB
[2025-01-19 18:05:11 internimage_b_1k_224] (main.py 519): INFO EPOCH 244 training takes 0:03:53
[2025-01-19 18:05:11 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_244.pth saving......
[2025-01-19 18:05:12 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][290/312]	eta 0:00:16 lr 0.000360	time 0.7225 (0.7526)	model_time 0.7223 (0.7474)	loss 2.3711 (2.7298)	grad_norm 1.7529 (2.1281/0.8346)	mem 34602MB
[2025-01-19 18:05:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_244.pth saved !!!
[2025-01-19 18:05:19 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][300/312]	eta 0:00:09 lr 0.000360	time 0.7147 (0.7526)	model_time 0.7146 (0.7476)	loss 2.6183 (2.7282)	grad_norm 2.8342 (2.1284/0.8341)	mem 34602MB
[2025-01-19 18:05:22 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.642 (7.642)	Loss 0.6834 (0.6834)	Acc@1 86.353 (86.353)	Acc@5 97.803 (97.803)	Mem 34604MB
[2025-01-19 18:05:25 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.977)	Loss 0.8892 (0.7715)	Acc@1 80.713 (84.275)	Acc@5 96.021 (96.855)	Mem 34604MB
[2025-01-19 18:05:25 internimage_b_1k_224] (main.py 575): INFO [Epoch:244] * Acc@1 84.067 Acc@5 96.861
[2025-01-19 18:05:25 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 18:05:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 18:05:27 internimage_b_1k_224] (main.py 510): INFO Train: [244/300][310/312]	eta 0:00:01 lr 0.000360	time 0.7053 (0.7523)	model_time 0.7052 (0.7475)	loss 2.8856 (2.7280)	grad_norm 2.2864 (2.1402/0.8337)	mem 34602MB
[2025-01-19 18:05:27 internimage_b_1k_224] (main.py 519): INFO EPOCH 244 training takes 0:03:54
[2025-01-19 18:05:27 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_244.pth saving......
[2025-01-19 18:05:29 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 18:05:29 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.07%
[2025-01-19 18:05:31 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_244.pth saved !!!
[2025-01-19 18:05:45 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.664 (16.664)	Loss 0.7122 (0.7122)	Acc@1 86.328 (86.328)	Acc@5 98.169 (98.169)	Mem 34604MB
[2025-01-19 18:05:48 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.461 (17.461)	Loss 0.7108 (0.7108)	Acc@1 85.449 (85.449)	Acc@5 97.803 (97.803)	Mem 34602MB
[2025-01-19 18:05:52 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (2.100)	Loss 0.9279 (0.8066)	Acc@1 80.640 (84.220)	Acc@5 95.752 (96.906)	Mem 34604MB
[2025-01-19 18:05:52 internimage_b_1k_224] (main.py 575): INFO [Epoch:244] * Acc@1 84.073 Acc@5 96.945
[2025-01-19 18:05:52 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.1%
[2025-01-19 18:05:52 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:05:53 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.086)	Loss 0.9021 (0.7885)	Acc@1 80.786 (84.131)	Acc@5 96.045 (96.899)	Mem 34602MB
[2025-01-19 18:05:54 internimage_b_1k_224] (main.py 575): INFO [Epoch:244] * Acc@1 83.935 Acc@5 96.901
[2025-01-19 18:05:54 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.9%
[2025-01-19 18:05:54 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.10%
[2025-01-19 18:05:56 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:05:56 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.07%
[2025-01-19 18:05:58 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][0/312]	eta 0:10:16 lr 0.000359	time 1.9758 (1.9758)	model_time 0.7318 (0.7318)	loss 3.1531 (3.1531)	grad_norm 1.9088 (1.9088/0.0000)	mem 34604MB
[2025-01-19 18:06:03 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.670 (9.670)	Loss 0.7220 (0.7220)	Acc@1 86.157 (86.157)	Acc@5 98.267 (98.267)	Mem 34602MB
[2025-01-19 18:06:06 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][10/312]	eta 0:04:23 lr 0.000359	time 0.7630 (0.8735)	model_time 0.7629 (0.7601)	loss 2.9517 (2.8438)	grad_norm 4.1236 (3.0314/1.0292)	mem 34604MB
[2025-01-19 18:06:08 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.337)	Loss 0.9276 (0.8075)	Acc@1 80.029 (84.155)	Acc@5 95.996 (96.997)	Mem 34602MB
[2025-01-19 18:06:09 internimage_b_1k_224] (main.py 575): INFO [Epoch:244] * Acc@1 83.975 Acc@5 97.029
[2025-01-19 18:06:09 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.0%
[2025-01-19 18:06:09 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 83.98%
[2025-01-19 18:06:12 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][0/312]	eta 0:19:03 lr 0.000359	time 3.6665 (3.6665)	model_time 2.1483 (2.1483)	loss 2.5718 (2.5718)	grad_norm 2.4263 (2.4263/0.0000)	mem 34602MB
[2025-01-19 18:06:14 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][20/312]	eta 0:03:59 lr 0.000359	time 0.7366 (0.8194)	model_time 0.7364 (0.7598)	loss 2.9953 (2.7317)	grad_norm 2.4882 (2.6151/0.9569)	mem 34604MB
[2025-01-19 18:06:20 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][10/312]	eta 0:05:13 lr 0.000359	time 0.7233 (1.0365)	model_time 0.7232 (0.8982)	loss 2.8225 (2.8020)	grad_norm 1.8811 (2.2420/0.5522)	mem 34602MB
[2025-01-19 18:06:22 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][30/312]	eta 0:03:49 lr 0.000358	time 0.9539 (0.8137)	model_time 0.9535 (0.7732)	loss 1.7696 (2.6679)	grad_norm 1.3796 (2.3220/0.9289)	mem 34604MB
[2025-01-19 18:06:28 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][20/312]	eta 0:04:24 lr 0.000359	time 0.9824 (0.9071)	model_time 0.9823 (0.8345)	loss 2.2605 (2.7081)	grad_norm 2.5800 (2.6034/0.9473)	mem 34602MB
[2025-01-19 18:06:29 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][40/312]	eta 0:03:38 lr 0.000358	time 0.7179 (0.8048)	model_time 0.7178 (0.7741)	loss 3.0693 (2.6876)	grad_norm 1.2322 (2.1475/0.9187)	mem 34604MB
[2025-01-19 18:06:35 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][30/312]	eta 0:04:01 lr 0.000358	time 0.7621 (0.8574)	model_time 0.7619 (0.8081)	loss 3.2355 (2.6473)	grad_norm 1.8831 (2.6480/0.9852)	mem 34602MB
[2025-01-19 18:06:37 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][50/312]	eta 0:03:27 lr 0.000358	time 0.7105 (0.7928)	model_time 0.7104 (0.7681)	loss 2.9111 (2.7112)	grad_norm 1.7409 (2.0861/0.8558)	mem 34604MB
[2025-01-19 18:06:43 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][40/312]	eta 0:03:46 lr 0.000358	time 0.7218 (0.8312)	model_time 0.7217 (0.7939)	loss 1.9623 (2.6625)	grad_norm 1.1222 (2.5459/1.0236)	mem 34602MB
[2025-01-19 18:06:44 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][60/312]	eta 0:03:17 lr 0.000357	time 0.7741 (0.7836)	model_time 0.7739 (0.7629)	loss 2.8638 (2.6912)	grad_norm 3.2101 (2.0877/0.8561)	mem 34604MB
[2025-01-19 18:06:50 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][50/312]	eta 0:03:33 lr 0.000358	time 0.7307 (0.8160)	model_time 0.7305 (0.7859)	loss 1.9053 (2.6743)	grad_norm 2.6742 (2.4228/1.0056)	mem 34602MB
[2025-01-19 18:06:52 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][70/312]	eta 0:03:07 lr 0.000357	time 0.7216 (0.7754)	model_time 0.7215 (0.7575)	loss 2.0685 (2.6776)	grad_norm 1.0627 (2.0171/0.8334)	mem 34604MB
[2025-01-19 18:06:58 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][60/312]	eta 0:03:22 lr 0.000357	time 0.7189 (0.8038)	model_time 0.7184 (0.7786)	loss 3.3407 (2.6891)	grad_norm 3.5472 (2.5158/1.0227)	mem 34602MB
[2025-01-19 18:06:59 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][80/312]	eta 0:02:59 lr 0.000357	time 0.7171 (0.7716)	model_time 0.7167 (0.7559)	loss 2.1275 (2.6705)	grad_norm 2.0547 (2.0564/0.8938)	mem 34604MB
[2025-01-19 18:07:05 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][70/312]	eta 0:03:12 lr 0.000357	time 0.7183 (0.7951)	model_time 0.7181 (0.7734)	loss 2.6919 (2.7018)	grad_norm 2.6261 (2.5068/1.0217)	mem 34602MB
[2025-01-19 18:07:06 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][90/312]	eta 0:02:50 lr 0.000356	time 0.7236 (0.7666)	model_time 0.7235 (0.7526)	loss 2.9454 (2.6826)	grad_norm 2.7471 (2.0806/0.9052)	mem 34604MB
[2025-01-19 18:07:13 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][80/312]	eta 0:03:03 lr 0.000357	time 0.8328 (0.7902)	model_time 0.8326 (0.7712)	loss 2.5206 (2.6935)	grad_norm 1.8756 (2.5217/0.9934)	mem 34602MB
[2025-01-19 18:07:14 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][100/312]	eta 0:02:41 lr 0.000356	time 0.7367 (0.7630)	model_time 0.7366 (0.7503)	loss 3.3743 (2.7117)	grad_norm 4.0141 (2.0946/0.9230)	mem 34604MB
[2025-01-19 18:07:20 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][90/312]	eta 0:02:54 lr 0.000356	time 0.7687 (0.7846)	model_time 0.7685 (0.7676)	loss 1.9074 (2.6873)	grad_norm 2.8298 (2.5163/1.0154)	mem 34602MB
[2025-01-19 18:07:21 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][110/312]	eta 0:02:33 lr 0.000355	time 0.7203 (0.7602)	model_time 0.7201 (0.7486)	loss 2.4338 (2.7264)	grad_norm 2.7139 (2.1679/1.0526)	mem 34604MB
[2025-01-19 18:07:27 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][100/312]	eta 0:02:45 lr 0.000356	time 0.7708 (0.7801)	model_time 0.7706 (0.7648)	loss 3.4668 (2.7295)	grad_norm 2.6995 (2.6051/1.0901)	mem 34602MB
[2025-01-19 18:07:28 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][120/312]	eta 0:02:25 lr 0.000355	time 0.8011 (0.7597)	model_time 0.8009 (0.7490)	loss 3.0697 (2.7314)	grad_norm 2.1762 (2.2277/1.0978)	mem 34604MB
[2025-01-19 18:07:35 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][110/312]	eta 0:02:37 lr 0.000355	time 0.7966 (0.7783)	model_time 0.7964 (0.7643)	loss 2.9692 (2.7365)	grad_norm 2.0375 (2.5410/1.0776)	mem 34602MB
[2025-01-19 18:07:36 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][130/312]	eta 0:02:18 lr 0.000355	time 0.7231 (0.7605)	model_time 0.7229 (0.7506)	loss 2.9908 (2.7357)	grad_norm 1.1901 (2.1902/1.0764)	mem 34604MB
[2025-01-19 18:07:43 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][120/312]	eta 0:02:28 lr 0.000355	time 0.7231 (0.7755)	model_time 0.7229 (0.7626)	loss 2.9267 (2.7350)	grad_norm 1.5178 (2.4913/1.0558)	mem 34602MB
[2025-01-19 18:07:44 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][140/312]	eta 0:02:10 lr 0.000354	time 0.8169 (0.7608)	model_time 0.8165 (0.7516)	loss 3.0856 (2.7236)	grad_norm 4.4855 (2.1688/1.0699)	mem 34604MB
[2025-01-19 18:07:50 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][130/312]	eta 0:02:20 lr 0.000355	time 0.7205 (0.7743)	model_time 0.7204 (0.7624)	loss 2.7747 (2.7254)	grad_norm 2.7455 (2.4759/1.0552)	mem 34602MB
[2025-01-19 18:07:52 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][150/312]	eta 0:02:03 lr 0.000354	time 0.8086 (0.7620)	model_time 0.8084 (0.7535)	loss 2.4769 (2.7131)	grad_norm 1.2017 (2.1387/1.0630)	mem 34604MB
[2025-01-19 18:07:57 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][140/312]	eta 0:02:12 lr 0.000354	time 0.7989 (0.7717)	model_time 0.7985 (0.7606)	loss 2.9693 (2.7306)	grad_norm 2.6894 (2.4716/1.0476)	mem 34602MB
[2025-01-19 18:07:59 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][160/312]	eta 0:01:55 lr 0.000354	time 0.7711 (0.7621)	model_time 0.7706 (0.7541)	loss 1.9759 (2.6967)	grad_norm 2.2853 (2.1173/1.0390)	mem 34604MB
[2025-01-19 18:08:05 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][150/312]	eta 0:02:04 lr 0.000354	time 0.7245 (0.7703)	model_time 0.7243 (0.7599)	loss 3.5002 (2.7429)	grad_norm 1.5003 (2.4413/1.0400)	mem 34602MB
[2025-01-19 18:08:07 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][170/312]	eta 0:01:48 lr 0.000353	time 0.7084 (0.7621)	model_time 0.7080 (0.7545)	loss 2.2632 (2.7019)	grad_norm 1.8753 (2.1156/1.0270)	mem 34604MB
[2025-01-19 18:08:12 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][160/312]	eta 0:01:56 lr 0.000354	time 0.7204 (0.7691)	model_time 0.7203 (0.7594)	loss 2.2705 (2.7410)	grad_norm 1.1837 (2.3882/1.0326)	mem 34602MB
[2025-01-19 18:08:14 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][180/312]	eta 0:01:40 lr 0.000353	time 0.7328 (0.7605)	model_time 0.7327 (0.7533)	loss 2.9649 (2.7029)	grad_norm 1.7994 (2.1464/1.0203)	mem 34604MB
[2025-01-19 18:08:20 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][170/312]	eta 0:01:49 lr 0.000353	time 0.7169 (0.7681)	model_time 0.7168 (0.7589)	loss 1.9880 (2.7361)	grad_norm 2.8254 (2.3713/1.0215)	mem 34602MB
[2025-01-19 18:08:21 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][190/312]	eta 0:01:32 lr 0.000353	time 0.7108 (0.7592)	model_time 0.7103 (0.7523)	loss 2.0851 (2.6927)	grad_norm 4.2518 (2.2037/1.0528)	mem 34604MB
[2025-01-19 18:08:27 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][180/312]	eta 0:01:41 lr 0.000353	time 0.7187 (0.7660)	model_time 0.7182 (0.7573)	loss 3.2795 (2.7382)	grad_norm 1.4258 (2.3568/1.0204)	mem 34602MB
[2025-01-19 18:08:29 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][200/312]	eta 0:01:24 lr 0.000352	time 0.7231 (0.7581)	model_time 0.7230 (0.7516)	loss 3.3089 (2.6978)	grad_norm 2.2205 (2.2051/1.0399)	mem 34604MB
[2025-01-19 18:08:35 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][190/312]	eta 0:01:33 lr 0.000353	time 0.7164 (0.7643)	model_time 0.7159 (0.7561)	loss 3.3599 (2.7415)	grad_norm 1.5245 (2.3387/1.0209)	mem 34602MB
[2025-01-19 18:08:36 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][210/312]	eta 0:01:17 lr 0.000352	time 0.7375 (0.7567)	model_time 0.7370 (0.7504)	loss 2.0028 (2.6971)	grad_norm 1.4480 (2.2180/1.0273)	mem 34604MB
[2025-01-19 18:08:42 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][200/312]	eta 0:01:25 lr 0.000352	time 0.8196 (0.7641)	model_time 0.8194 (0.7562)	loss 2.0948 (2.7405)	grad_norm 3.2340 (2.3103/1.0100)	mem 34602MB
[2025-01-19 18:08:43 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][220/312]	eta 0:01:09 lr 0.000352	time 0.7252 (0.7552)	model_time 0.7251 (0.7493)	loss 2.3531 (2.6918)	grad_norm 2.2222 (2.2131/1.0117)	mem 34604MB
[2025-01-19 18:08:50 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][210/312]	eta 0:01:17 lr 0.000352	time 0.7294 (0.7626)	model_time 0.7292 (0.7551)	loss 1.7838 (2.7273)	grad_norm 2.8938 (2.3033/0.9944)	mem 34602MB
[2025-01-19 18:08:51 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][230/312]	eta 0:01:01 lr 0.000351	time 0.7260 (0.7544)	model_time 0.7258 (0.7487)	loss 2.5739 (2.6971)	grad_norm 1.7372 (2.2126/1.0139)	mem 34604MB
[2025-01-19 18:08:57 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][220/312]	eta 0:01:10 lr 0.000352	time 0.7986 (0.7614)	model_time 0.7984 (0.7542)	loss 3.0910 (2.7283)	grad_norm 2.7770 (2.3224/1.0375)	mem 34602MB
[2025-01-19 18:08:58 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][240/312]	eta 0:00:54 lr 0.000351	time 0.8066 (0.7538)	model_time 0.8060 (0.7483)	loss 2.8659 (2.7036)	grad_norm 3.5149 (2.2550/1.0530)	mem 34604MB
[2025-01-19 18:09:05 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][230/312]	eta 0:01:02 lr 0.000351	time 0.8929 (0.7616)	model_time 0.8924 (0.7547)	loss 3.0294 (2.7306)	grad_norm 1.6512 (2.3175/1.0234)	mem 34602MB
[2025-01-19 18:09:06 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][250/312]	eta 0:00:46 lr 0.000350	time 0.7441 (0.7547)	model_time 0.7437 (0.7494)	loss 2.8710 (2.7085)	grad_norm 1.8401 (2.2554/1.0379)	mem 34604MB
[2025-01-19 18:09:12 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][240/312]	eta 0:00:54 lr 0.000351	time 0.8008 (0.7608)	model_time 0.8006 (0.7542)	loss 3.1451 (2.7391)	grad_norm 1.2512 (2.2921/1.0146)	mem 34602MB
[2025-01-19 18:09:14 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][260/312]	eta 0:00:39 lr 0.000350	time 0.8351 (0.7550)	model_time 0.8349 (0.7499)	loss 2.0291 (2.7121)	grad_norm 1.7484 (2.2503/1.0305)	mem 34604MB
[2025-01-19 18:09:20 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][250/312]	eta 0:00:47 lr 0.000350	time 0.7163 (0.7613)	model_time 0.7158 (0.7550)	loss 2.7994 (2.7416)	grad_norm 1.5422 (2.2688/1.0055)	mem 34602MB
[2025-01-19 18:09:21 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][270/312]	eta 0:00:31 lr 0.000350	time 0.8262 (0.7558)	model_time 0.8258 (0.7508)	loss 2.6415 (2.7140)	grad_norm 0.9608 (2.2365/1.0224)	mem 34604MB
[2025-01-19 18:09:27 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][260/312]	eta 0:00:39 lr 0.000350	time 0.7168 (0.7603)	model_time 0.7167 (0.7541)	loss 2.9559 (2.7372)	grad_norm 2.8367 (2.2678/1.0026)	mem 34602MB
[2025-01-19 18:09:29 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][280/312]	eta 0:00:24 lr 0.000349	time 0.8106 (0.7558)	model_time 0.8105 (0.7510)	loss 2.5517 (2.7210)	grad_norm 2.8148 (2.2193/1.0129)	mem 34604MB
[2025-01-19 18:09:35 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][270/312]	eta 0:00:31 lr 0.000350	time 0.7427 (0.7601)	model_time 0.7422 (0.7542)	loss 2.0528 (2.7335)	grad_norm 1.2934 (2.2503/0.9934)	mem 34602MB
[2025-01-19 18:09:37 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][290/312]	eta 0:00:16 lr 0.000349	time 0.7104 (0.7561)	model_time 0.7099 (0.7515)	loss 2.9125 (2.7233)	grad_norm 1.1540 (2.2074/1.0093)	mem 34604MB
[2025-01-19 18:09:42 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][280/312]	eta 0:00:24 lr 0.000349	time 0.7120 (0.7597)	model_time 0.7118 (0.7540)	loss 2.6299 (2.7337)	grad_norm 2.6916 (2.2662/0.9933)	mem 34602MB
[2025-01-19 18:09:44 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][300/312]	eta 0:00:09 lr 0.000349	time 0.7159 (0.7553)	model_time 0.7158 (0.7509)	loss 2.9505 (2.7323)	grad_norm 1.4524 (2.1975/0.9998)	mem 34604MB
[2025-01-19 18:09:50 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][290/312]	eta 0:00:16 lr 0.000349	time 0.7488 (0.7592)	model_time 0.7486 (0.7537)	loss 2.9006 (2.7339)	grad_norm 2.3780 (2.2935/0.9971)	mem 34602MB
[2025-01-19 18:09:51 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][310/312]	eta 0:00:01 lr 0.000348	time 0.7154 (0.7541)	model_time 0.7153 (0.7497)	loss 2.7549 (2.7310)	grad_norm 1.6390 (2.1720/0.9778)	mem 34604MB
[2025-01-19 18:09:52 internimage_b_1k_224] (main.py 519): INFO EPOCH 245 training takes 0:03:55
[2025-01-19 18:09:52 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_245.pth saving......
[2025-01-19 18:09:55 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_245.pth saved !!!
[2025-01-19 18:09:57 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][300/312]	eta 0:00:09 lr 0.000349	time 0.7079 (0.7588)	model_time 0.7078 (0.7534)	loss 2.8663 (2.7270)	grad_norm 3.0478 (2.2901/0.9928)	mem 34602MB
[2025-01-19 18:10:02 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.398 (7.398)	Loss 0.6970 (0.6970)	Acc@1 85.742 (85.742)	Acc@5 97.876 (97.876)	Mem 34604MB
[2025-01-19 18:10:04 internimage_b_1k_224] (main.py 510): INFO Train: [245/300][310/312]	eta 0:00:01 lr 0.000348	time 0.7137 (0.7578)	model_time 0.7136 (0.7526)	loss 3.0456 (2.7272)	grad_norm 1.0523 (2.3032/1.0027)	mem 34602MB
[2025-01-19 18:10:05 internimage_b_1k_224] (main.py 519): INFO EPOCH 245 training takes 0:03:56
[2025-01-19 18:10:05 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_245.pth saving......
[2025-01-19 18:10:06 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.974)	Loss 0.9068 (0.7863)	Acc@1 80.884 (84.098)	Acc@5 95.972 (96.851)	Mem 34604MB
[2025-01-19 18:10:06 internimage_b_1k_224] (main.py 575): INFO [Epoch:245] * Acc@1 83.947 Acc@5 96.853
[2025-01-19 18:10:06 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.9%
[2025-01-19 18:10:06 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.07%
[2025-01-19 18:10:08 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_245.pth saved !!!
[2025-01-19 18:10:24 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 18.574 (18.574)	Loss 0.7123 (0.7123)	Acc@1 86.377 (86.377)	Acc@5 98.169 (98.169)	Mem 34604MB
[2025-01-19 18:10:25 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.460 (16.460)	Loss 0.7092 (0.7092)	Acc@1 86.133 (86.133)	Acc@5 97.949 (97.949)	Mem 34602MB
[2025-01-19 18:10:32 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.187 (2.143)	Loss 0.9045 (0.7899)	Acc@1 80.249 (84.129)	Acc@5 96.069 (96.944)	Mem 34602MB
[2025-01-19 18:10:32 internimage_b_1k_224] (main.py 575): INFO [Epoch:245] * Acc@1 83.961 Acc@5 96.961
[2025-01-19 18:10:32 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.0%
[2025-01-19 18:10:32 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.10%
[2025-01-19 18:10:32 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.386)	Loss 0.9273 (0.8063)	Acc@1 80.640 (84.237)	Acc@5 95.801 (96.919)	Mem 34604MB
[2025-01-19 18:10:32 internimage_b_1k_224] (main.py 575): INFO [Epoch:245] * Acc@1 84.089 Acc@5 96.959
[2025-01-19 18:10:32 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.1%
[2025-01-19 18:10:32 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:10:36 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:10:36 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.09%
[2025-01-19 18:10:39 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][0/312]	eta 0:11:34 lr 0.000348	time 2.2256 (2.2256)	model_time 0.7344 (0.7344)	loss 3.2047 (3.2047)	grad_norm 4.1227 (4.1227/0.0000)	mem 34604MB
[2025-01-19 18:10:41 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.471 (9.471)	Loss 0.7219 (0.7219)	Acc@1 86.182 (86.182)	Acc@5 98.242 (98.242)	Mem 34602MB
[2025-01-19 18:10:46 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][10/312]	eta 0:04:24 lr 0.000348	time 0.8121 (0.8759)	model_time 0.8119 (0.7402)	loss 3.3666 (2.8660)	grad_norm 3.0817 (2.9952/1.0409)	mem 34604MB
[2025-01-19 18:10:46 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.270)	Loss 0.9269 (0.8071)	Acc@1 80.127 (84.200)	Acc@5 96.069 (97.015)	Mem 34602MB
[2025-01-19 18:10:46 internimage_b_1k_224] (main.py 575): INFO [Epoch:245] * Acc@1 84.013 Acc@5 97.045
[2025-01-19 18:10:46 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.0%
[2025-01-19 18:10:46 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:10:50 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:10:50 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.01%
[2025-01-19 18:10:52 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][0/312]	eta 0:11:46 lr 0.000348	time 2.2644 (2.2644)	model_time 0.7349 (0.7349)	loss 2.8031 (2.8031)	grad_norm 1.4470 (1.4470/0.0000)	mem 34602MB
[2025-01-19 18:10:53 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][20/312]	eta 0:03:55 lr 0.000348	time 0.7202 (0.8060)	model_time 0.7198 (0.7347)	loss 2.4165 (2.8528)	grad_norm 2.4059 (2.5706/1.0215)	mem 34604MB
[2025-01-19 18:11:00 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][10/312]	eta 0:04:28 lr 0.000348	time 0.7227 (0.8897)	model_time 0.7226 (0.7504)	loss 2.1406 (2.6307)	grad_norm 1.9006 (1.9232/0.5508)	mem 34602MB
[2025-01-19 18:11:01 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][30/312]	eta 0:03:40 lr 0.000347	time 0.7314 (0.7815)	model_time 0.7309 (0.7330)	loss 2.9280 (2.8521)	grad_norm 3.0390 (2.2923/0.9851)	mem 34604MB
[2025-01-19 18:11:07 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][20/312]	eta 0:04:00 lr 0.000348	time 0.7285 (0.8232)	model_time 0.7283 (0.7501)	loss 3.3173 (2.7484)	grad_norm 2.3804 (2.3105/0.8460)	mem 34602MB
[2025-01-19 18:11:08 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][40/312]	eta 0:03:29 lr 0.000347	time 0.7087 (0.7712)	model_time 0.7086 (0.7346)	loss 2.8875 (2.8208)	grad_norm 1.9423 (2.2048/0.9376)	mem 34604MB
[2025-01-19 18:11:15 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][30/312]	eta 0:03:44 lr 0.000347	time 0.7199 (0.7947)	model_time 0.7194 (0.7450)	loss 2.5321 (2.7375)	grad_norm 1.6628 (2.2419/0.9220)	mem 34602MB
[2025-01-19 18:11:15 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][50/312]	eta 0:03:20 lr 0.000346	time 0.8080 (0.7667)	model_time 0.8078 (0.7371)	loss 2.9690 (2.8260)	grad_norm 1.4191 (2.2782/0.9813)	mem 34604MB
[2025-01-19 18:11:22 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][40/312]	eta 0:03:34 lr 0.000347	time 0.7295 (0.7872)	model_time 0.7294 (0.7496)	loss 3.1231 (2.7416)	grad_norm 2.0559 (2.2437/0.8693)	mem 34602MB
[2025-01-19 18:11:23 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][60/312]	eta 0:03:12 lr 0.000346	time 0.7138 (0.7655)	model_time 0.7137 (0.7407)	loss 2.9758 (2.8181)	grad_norm 0.8949 (2.2391/0.9597)	mem 34604MB
[2025-01-19 18:11:30 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][50/312]	eta 0:03:24 lr 0.000346	time 0.8274 (0.7796)	model_time 0.8272 (0.7493)	loss 3.0881 (2.7495)	grad_norm 3.0030 (2.2722/0.8296)	mem 34602MB
[2025-01-19 18:11:31 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][70/312]	eta 0:03:05 lr 0.000346	time 0.7143 (0.7647)	model_time 0.7141 (0.7433)	loss 2.5988 (2.8060)	grad_norm 2.1149 (2.1790/0.9291)	mem 34604MB
[2025-01-19 18:11:38 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][60/312]	eta 0:03:15 lr 0.000346	time 0.8005 (0.7761)	model_time 0.8004 (0.7507)	loss 3.1420 (2.7534)	grad_norm 1.3684 (2.2793/0.8875)	mem 34602MB
[2025-01-19 18:11:38 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][80/312]	eta 0:02:57 lr 0.000345	time 0.7221 (0.7670)	model_time 0.7217 (0.7482)	loss 2.3257 (2.8136)	grad_norm 2.2582 (2.2018/0.9371)	mem 34604MB
[2025-01-19 18:11:45 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][70/312]	eta 0:03:06 lr 0.000346	time 0.7457 (0.7692)	model_time 0.7455 (0.7473)	loss 3.0633 (2.7586)	grad_norm 2.7959 (2.2498/0.8922)	mem 34602MB
[2025-01-19 18:11:46 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][90/312]	eta 0:02:50 lr 0.000345	time 0.7099 (0.7670)	model_time 0.7096 (0.7503)	loss 3.2981 (2.8162)	grad_norm 2.9562 (2.2541/0.9464)	mem 34604MB
[2025-01-19 18:11:52 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][80/312]	eta 0:02:57 lr 0.000345	time 0.7166 (0.7672)	model_time 0.7164 (0.7480)	loss 1.8940 (2.7613)	grad_norm 1.2685 (2.2172/0.8579)	mem 34602MB
[2025-01-19 18:11:54 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][100/312]	eta 0:02:42 lr 0.000345	time 0.8314 (0.7662)	model_time 0.8312 (0.7511)	loss 2.2908 (2.7805)	grad_norm 2.1853 (2.2827/0.9290)	mem 34604MB
[2025-01-19 18:12:00 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][90/312]	eta 0:02:49 lr 0.000345	time 0.7815 (0.7646)	model_time 0.7814 (0.7475)	loss 3.0090 (2.7770)	grad_norm 2.8653 (2.1947/0.8306)	mem 34602MB
[2025-01-19 18:12:01 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][110/312]	eta 0:02:34 lr 0.000344	time 0.7200 (0.7629)	model_time 0.7196 (0.7491)	loss 1.7603 (2.7842)	grad_norm 1.7737 (2.2611/0.9139)	mem 34604MB
[2025-01-19 18:12:07 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][100/312]	eta 0:02:41 lr 0.000345	time 0.7978 (0.7635)	model_time 0.7976 (0.7480)	loss 2.5063 (2.7581)	grad_norm 1.4332 (2.1908/0.8398)	mem 34602MB
[2025-01-19 18:12:08 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][120/312]	eta 0:02:25 lr 0.000344	time 0.7304 (0.7602)	model_time 0.7299 (0.7475)	loss 1.9291 (2.7687)	grad_norm 1.4708 (2.1973/0.9060)	mem 34604MB
[2025-01-19 18:12:15 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][110/312]	eta 0:02:34 lr 0.000344	time 0.8530 (0.7625)	model_time 0.8528 (0.7484)	loss 3.0275 (2.7742)	grad_norm 4.3958 (2.2669/0.8665)	mem 34602MB
[2025-01-19 18:12:16 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][130/312]	eta 0:02:18 lr 0.000344	time 0.8069 (0.7593)	model_time 0.8068 (0.7476)	loss 2.1482 (2.7617)	grad_norm 2.4331 (2.1634/0.8839)	mem 34604MB
[2025-01-19 18:12:22 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][120/312]	eta 0:02:25 lr 0.000344	time 0.7159 (0.7603)	model_time 0.7157 (0.7473)	loss 2.5714 (2.7745)	grad_norm 1.5135 (2.2940/0.9197)	mem 34602MB
[2025-01-19 18:12:23 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][140/312]	eta 0:02:10 lr 0.000343	time 0.7431 (0.7573)	model_time 0.7427 (0.7464)	loss 3.3378 (2.7651)	grad_norm 1.3743 (2.1707/0.8800)	mem 34604MB
[2025-01-19 18:12:30 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][130/312]	eta 0:02:18 lr 0.000344	time 0.7205 (0.7594)	model_time 0.7201 (0.7474)	loss 2.6716 (2.7686)	grad_norm 1.7215 (2.3333/0.9604)	mem 34602MB
[2025-01-19 18:12:30 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][150/312]	eta 0:02:02 lr 0.000343	time 0.7236 (0.7554)	model_time 0.7234 (0.7452)	loss 2.4556 (2.7585)	grad_norm 1.0767 (2.1446/0.8687)	mem 34604MB
[2025-01-19 18:12:37 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][140/312]	eta 0:02:10 lr 0.000343	time 0.7640 (0.7582)	model_time 0.7638 (0.7470)	loss 2.6759 (2.7783)	grad_norm 2.9144 (2.3448/0.9521)	mem 34602MB
[2025-01-19 18:12:38 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][160/312]	eta 0:01:54 lr 0.000343	time 0.7236 (0.7541)	model_time 0.7232 (0.7445)	loss 3.1471 (2.7556)	grad_norm 2.4473 (2.1443/0.8936)	mem 34604MB
[2025-01-19 18:12:44 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][150/312]	eta 0:02:02 lr 0.000343	time 0.7152 (0.7567)	model_time 0.7148 (0.7462)	loss 2.2318 (2.7745)	grad_norm 2.3820 (2.3903/0.9852)	mem 34602MB
[2025-01-19 18:12:45 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][170/312]	eta 0:01:46 lr 0.000342	time 0.8083 (0.7534)	model_time 0.8082 (0.7444)	loss 3.2426 (2.7642)	grad_norm 2.4821 (2.1599/0.8779)	mem 34604MB
[2025-01-19 18:12:52 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][160/312]	eta 0:01:54 lr 0.000343	time 0.7270 (0.7561)	model_time 0.7265 (0.7463)	loss 2.0217 (2.7703)	grad_norm 5.2064 (2.4370/1.0476)	mem 34602MB
[2025-01-19 18:12:53 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][180/312]	eta 0:01:39 lr 0.000342	time 0.7178 (0.7539)	model_time 0.7174 (0.7453)	loss 2.9441 (2.7684)	grad_norm 2.6871 (2.1481/0.8626)	mem 34604MB
[2025-01-19 18:12:59 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][170/312]	eta 0:01:47 lr 0.000342	time 0.8169 (0.7554)	model_time 0.8167 (0.7461)	loss 2.7965 (2.7703)	grad_norm 1.8712 (2.4824/1.0678)	mem 34602MB
[2025-01-19 18:13:00 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][190/312]	eta 0:01:32 lr 0.000341	time 0.7139 (0.7542)	model_time 0.7137 (0.7461)	loss 2.9923 (2.7668)	grad_norm 2.3597 (2.1314/0.8507)	mem 34604MB
[2025-01-19 18:13:07 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][180/312]	eta 0:01:39 lr 0.000342	time 0.7994 (0.7557)	model_time 0.7989 (0.7469)	loss 3.2097 (2.7682)	grad_norm 2.5894 (2.4886/1.0538)	mem 34602MB
[2025-01-19 18:13:08 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][200/312]	eta 0:01:24 lr 0.000341	time 0.8100 (0.7557)	model_time 0.8096 (0.7479)	loss 2.4022 (2.7709)	grad_norm 1.3941 (2.1092/0.8409)	mem 34604MB
[2025-01-19 18:13:14 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][190/312]	eta 0:01:31 lr 0.000341	time 0.7153 (0.7540)	model_time 0.7151 (0.7456)	loss 2.9657 (2.7666)	grad_norm 1.9289 (2.4529/1.0430)	mem 34602MB
[2025-01-19 18:13:16 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][210/312]	eta 0:01:17 lr 0.000341	time 0.8086 (0.7555)	model_time 0.8081 (0.7481)	loss 3.1740 (2.7807)	grad_norm 3.5868 (2.1104/0.8388)	mem 34604MB
[2025-01-19 18:13:22 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][200/312]	eta 0:01:24 lr 0.000341	time 0.7185 (0.7540)	model_time 0.7183 (0.7460)	loss 3.4523 (2.7620)	grad_norm 1.0442 (2.4225/1.0383)	mem 34602MB
[2025-01-19 18:13:23 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][220/312]	eta 0:01:09 lr 0.000340	time 0.8478 (0.7554)	model_time 0.8474 (0.7483)	loss 2.2886 (2.7710)	grad_norm 1.5492 (2.1468/0.8745)	mem 34604MB
[2025-01-19 18:13:29 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][210/312]	eta 0:01:16 lr 0.000341	time 0.7910 (0.7537)	model_time 0.7908 (0.7461)	loss 2.6505 (2.7583)	grad_norm 5.7157 (2.4444/1.0498)	mem 34602MB
[2025-01-19 18:13:31 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][230/312]	eta 0:01:01 lr 0.000340	time 0.7146 (0.7543)	model_time 0.7145 (0.7475)	loss 2.2280 (2.7632)	grad_norm 1.1359 (2.1585/0.8903)	mem 34604MB
[2025-01-19 18:13:37 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][220/312]	eta 0:01:09 lr 0.000340	time 0.7206 (0.7533)	model_time 0.7201 (0.7460)	loss 3.2604 (2.7555)	grad_norm 1.9371 (2.4465/1.0469)	mem 34602MB
[2025-01-19 18:13:38 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][240/312]	eta 0:00:54 lr 0.000340	time 0.7157 (0.7532)	model_time 0.7156 (0.7467)	loss 2.4799 (2.7603)	grad_norm 1.5410 (2.1622/0.8864)	mem 34604MB
[2025-01-19 18:13:44 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][230/312]	eta 0:01:01 lr 0.000340	time 0.8436 (0.7536)	model_time 0.8434 (0.7466)	loss 3.1044 (2.7436)	grad_norm 2.4702 (2.4558/1.0512)	mem 34602MB
[2025-01-19 18:13:45 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][250/312]	eta 0:00:46 lr 0.000339	time 0.8321 (0.7529)	model_time 0.8317 (0.7467)	loss 2.8423 (2.7644)	grad_norm 5.1190 (2.2080/0.9371)	mem 34604MB
[2025-01-19 18:13:52 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][240/312]	eta 0:00:54 lr 0.000340	time 0.7225 (0.7527)	model_time 0.7223 (0.7460)	loss 2.4823 (2.7442)	grad_norm 1.2101 (2.4254/1.0495)	mem 34602MB
[2025-01-19 18:13:53 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][260/312]	eta 0:00:39 lr 0.000339	time 0.7258 (0.7520)	model_time 0.7254 (0.7460)	loss 2.8592 (2.7655)	grad_norm 2.0993 (2.2396/0.9524)	mem 34604MB
[2025-01-19 18:13:59 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][250/312]	eta 0:00:46 lr 0.000339	time 0.7176 (0.7524)	model_time 0.7174 (0.7459)	loss 2.7648 (2.7412)	grad_norm 3.3393 (2.4238/1.0380)	mem 34602MB
[2025-01-19 18:14:00 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][270/312]	eta 0:00:31 lr 0.000339	time 0.7230 (0.7513)	model_time 0.7228 (0.7454)	loss 3.0079 (2.7671)	grad_norm 2.3184 (2.2358/0.9441)	mem 34604MB
[2025-01-19 18:14:06 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][260/312]	eta 0:00:39 lr 0.000339	time 0.7243 (0.7520)	model_time 0.7241 (0.7458)	loss 3.1835 (2.7443)	grad_norm 2.9608 (2.4131/1.0263)	mem 34602MB
[2025-01-19 18:14:07 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][280/312]	eta 0:00:24 lr 0.000338	time 0.7248 (0.7508)	model_time 0.7243 (0.7451)	loss 2.8473 (2.7607)	grad_norm 2.2544 (2.2574/0.9710)	mem 34604MB
[2025-01-19 18:14:14 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][270/312]	eta 0:00:31 lr 0.000339	time 0.7235 (0.7510)	model_time 0.7233 (0.7450)	loss 3.1356 (2.7445)	grad_norm 3.0166 (2.4513/1.0349)	mem 34602MB
[2025-01-19 18:14:15 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][290/312]	eta 0:00:16 lr 0.000338	time 0.8080 (0.7507)	model_time 0.8078 (0.7452)	loss 2.7765 (2.7611)	grad_norm 1.6985 (2.2688/0.9686)	mem 34604MB
[2025-01-19 18:14:21 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][280/312]	eta 0:00:24 lr 0.000338	time 0.7224 (0.7505)	model_time 0.7219 (0.7447)	loss 3.0408 (2.7462)	grad_norm 4.6587 (2.4556/1.0514)	mem 34602MB
[2025-01-19 18:14:22 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][300/312]	eta 0:00:09 lr 0.000338	time 0.7134 (0.7507)	model_time 0.7133 (0.7454)	loss 2.6873 (2.7551)	grad_norm 2.7318 (2.2598/0.9590)	mem 34604MB
[2025-01-19 18:14:29 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][290/312]	eta 0:00:16 lr 0.000338	time 0.8157 (0.7505)	model_time 0.8156 (0.7449)	loss 2.4421 (2.7458)	grad_norm 1.9832 (2.4528/1.0482)	mem 34602MB
[2025-01-19 18:14:30 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][310/312]	eta 0:00:01 lr 0.000337	time 0.8048 (0.7501)	model_time 0.8046 (0.7450)	loss 2.2625 (2.7607)	grad_norm 1.3408 (2.2238/0.9561)	mem 34604MB
[2025-01-19 18:14:30 internimage_b_1k_224] (main.py 519): INFO EPOCH 246 training takes 0:03:54
[2025-01-19 18:14:30 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_246.pth saving......
[2025-01-19 18:14:34 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_246.pth saved !!!
[2025-01-19 18:14:36 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][300/312]	eta 0:00:09 lr 0.000338	time 0.7940 (0.7511)	model_time 0.7939 (0.7456)	loss 2.4922 (2.7462)	grad_norm 1.0950 (2.4372/1.0449)	mem 34602MB
[2025-01-19 18:14:43 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.981 (8.981)	Loss 0.7049 (0.7049)	Acc@1 86.377 (86.377)	Acc@5 98.071 (98.071)	Mem 34604MB
[2025-01-19 18:14:43 internimage_b_1k_224] (main.py 510): INFO Train: [246/300][310/312]	eta 0:00:01 lr 0.000337	time 0.7270 (0.7500)	model_time 0.7269 (0.7448)	loss 3.5718 (2.7459)	grad_norm 1.9414 (2.4277/1.0488)	mem 34602MB
[2025-01-19 18:14:44 internimage_b_1k_224] (main.py 519): INFO EPOCH 246 training takes 0:03:53
[2025-01-19 18:14:44 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_246.pth saving......
[2025-01-19 18:14:47 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.180)	Loss 0.8946 (0.7862)	Acc@1 80.835 (84.353)	Acc@5 96.118 (96.948)	Mem 34604MB
[2025-01-19 18:14:47 internimage_b_1k_224] (main.py 575): INFO [Epoch:246] * Acc@1 84.137 Acc@5 96.943
[2025-01-19 18:14:47 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 18:14:47 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 18:14:47 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_246.pth saved !!!
[2025-01-19 18:14:50 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 18:14:50 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.14%
[2025-01-19 18:15:04 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.491 (16.491)	Loss 0.7028 (0.7028)	Acc@1 86.499 (86.499)	Acc@5 97.876 (97.876)	Mem 34602MB
[2025-01-19 18:15:06 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.616 (15.616)	Loss 0.7122 (0.7122)	Acc@1 86.426 (86.426)	Acc@5 98.169 (98.169)	Mem 34604MB
[2025-01-19 18:15:11 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.137)	Loss 0.9003 (0.7875)	Acc@1 80.811 (84.275)	Acc@5 96.143 (96.877)	Mem 34602MB
[2025-01-19 18:15:11 internimage_b_1k_224] (main.py 575): INFO [Epoch:246] * Acc@1 84.095 Acc@5 96.889
[2025-01-19 18:15:11 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 18:15:11 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.10%
[2025-01-19 18:15:13 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.028)	Loss 0.9266 (0.8059)	Acc@1 80.737 (84.262)	Acc@5 95.825 (96.917)	Mem 34604MB
[2025-01-19 18:15:13 internimage_b_1k_224] (main.py 575): INFO [Epoch:246] * Acc@1 84.115 Acc@5 96.961
[2025-01-19 18:15:13 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.1%
[2025-01-19 18:15:13 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:15:17 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:15:17 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.12%
[2025-01-19 18:15:19 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][0/312]	eta 0:11:26 lr 0.000337	time 2.2014 (2.2014)	model_time 0.7360 (0.7360)	loss 2.2320 (2.2320)	grad_norm 1.7043 (1.7043/0.0000)	mem 34604MB
[2025-01-19 18:15:21 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.648 (9.648)	Loss 0.7219 (0.7219)	Acc@1 86.230 (86.230)	Acc@5 98.242 (98.242)	Mem 34602MB
[2025-01-19 18:15:26 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.299)	Loss 0.9260 (0.8067)	Acc@1 80.151 (84.193)	Acc@5 96.094 (97.015)	Mem 34602MB
[2025-01-19 18:15:26 internimage_b_1k_224] (main.py 575): INFO [Epoch:246] * Acc@1 84.011 Acc@5 97.047
[2025-01-19 18:15:26 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.0%
[2025-01-19 18:15:26 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.01%
[2025-01-19 18:15:27 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][10/312]	eta 0:04:33 lr 0.000337	time 0.7211 (0.9071)	model_time 0.7210 (0.7736)	loss 3.1704 (2.6321)	grad_norm 2.7176 (1.8241/0.6194)	mem 34604MB
[2025-01-19 18:15:29 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][0/312]	eta 0:17:27 lr 0.000337	time 3.3582 (3.3582)	model_time 1.7809 (1.7809)	loss 3.0458 (3.0458)	grad_norm 2.0845 (2.0845/0.0000)	mem 34602MB
[2025-01-19 18:15:34 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][20/312]	eta 0:04:04 lr 0.000337	time 0.7469 (0.8373)	model_time 0.7465 (0.7672)	loss 2.5030 (2.6889)	grad_norm 1.6332 (2.0622/0.7792)	mem 34604MB
[2025-01-19 18:15:37 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][10/312]	eta 0:05:01 lr 0.000337	time 0.7292 (0.9984)	model_time 0.7288 (0.8546)	loss 3.3428 (2.8340)	grad_norm 3.1334 (2.9579/1.1300)	mem 34602MB
[2025-01-19 18:15:42 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][30/312]	eta 0:03:48 lr 0.000336	time 0.7221 (0.8103)	model_time 0.7216 (0.7627)	loss 3.2191 (2.7256)	grad_norm 1.8962 (2.0115/0.8132)	mem 34604MB
[2025-01-19 18:15:44 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][20/312]	eta 0:04:18 lr 0.000337	time 0.8365 (0.8838)	model_time 0.8364 (0.8084)	loss 2.6844 (2.8192)	grad_norm 2.0951 (3.2624/1.2658)	mem 34602MB
[2025-01-19 18:15:49 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][40/312]	eta 0:03:35 lr 0.000336	time 0.7276 (0.7916)	model_time 0.7275 (0.7555)	loss 2.0909 (2.6852)	grad_norm 2.4463 (2.1504/0.8599)	mem 34604MB
[2025-01-19 18:15:52 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][30/312]	eta 0:03:56 lr 0.000336	time 0.7283 (0.8385)	model_time 0.7282 (0.7872)	loss 2.6686 (2.8175)	grad_norm 2.9336 (3.1549/1.1390)	mem 34602MB
[2025-01-19 18:15:56 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][50/312]	eta 0:03:24 lr 0.000335	time 0.7173 (0.7806)	model_time 0.7171 (0.7516)	loss 2.3828 (2.6846)	grad_norm 2.8816 (2.2194/0.8225)	mem 34604MB
[2025-01-19 18:15:59 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][40/312]	eta 0:03:42 lr 0.000336	time 0.7173 (0.8188)	model_time 0.7171 (0.7800)	loss 2.5461 (2.8072)	grad_norm 1.6785 (2.8529/1.1767)	mem 34602MB
[2025-01-19 18:16:04 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][60/312]	eta 0:03:14 lr 0.000335	time 0.7220 (0.7732)	model_time 0.7216 (0.7489)	loss 2.4579 (2.7108)	grad_norm 1.9543 (2.2274/0.7919)	mem 34604MB
[2025-01-19 18:16:07 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][50/312]	eta 0:03:30 lr 0.000335	time 0.7327 (0.8028)	model_time 0.7325 (0.7715)	loss 2.9240 (2.8115)	grad_norm 1.0538 (2.6948/1.1565)	mem 34602MB
[2025-01-19 18:16:11 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][70/312]	eta 0:03:05 lr 0.000335	time 0.7194 (0.7666)	model_time 0.7189 (0.7456)	loss 2.6546 (2.6954)	grad_norm 2.1626 (2.2094/0.7837)	mem 34604MB
[2025-01-19 18:16:14 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][60/312]	eta 0:03:20 lr 0.000335	time 0.7162 (0.7957)	model_time 0.7157 (0.7694)	loss 2.5345 (2.7912)	grad_norm 2.1569 (2.6516/1.1052)	mem 34602MB
[2025-01-19 18:16:18 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][80/312]	eta 0:02:56 lr 0.000334	time 0.7207 (0.7614)	model_time 0.7206 (0.7430)	loss 2.4791 (2.6874)	grad_norm 1.3831 (2.1511/0.7656)	mem 34604MB
[2025-01-19 18:16:22 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][70/312]	eta 0:03:10 lr 0.000335	time 0.7218 (0.7870)	model_time 0.7216 (0.7644)	loss 2.7889 (2.7378)	grad_norm 1.9077 (2.5179/1.0889)	mem 34602MB
[2025-01-19 18:16:26 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][90/312]	eta 0:02:48 lr 0.000334	time 0.7192 (0.7591)	model_time 0.7191 (0.7426)	loss 2.8103 (2.6853)	grad_norm 2.2876 (2.1253/0.7393)	mem 34604MB
[2025-01-19 18:16:29 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][80/312]	eta 0:03:01 lr 0.000334	time 0.7172 (0.7812)	model_time 0.7168 (0.7613)	loss 3.5443 (2.7501)	grad_norm 1.2604 (2.4662/1.0622)	mem 34602MB
[2025-01-19 18:16:33 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][100/312]	eta 0:02:40 lr 0.000334	time 0.8152 (0.7578)	model_time 0.8151 (0.7430)	loss 2.6711 (2.6770)	grad_norm 2.0727 (2.0912/0.7248)	mem 34604MB
[2025-01-19 18:16:37 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][90/312]	eta 0:02:52 lr 0.000334	time 0.7446 (0.7778)	model_time 0.7445 (0.7601)	loss 2.8186 (2.7638)	grad_norm 1.4928 (2.4022/1.0358)	mem 34602MB
[2025-01-19 18:16:41 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][110/312]	eta 0:02:33 lr 0.000333	time 0.7248 (0.7582)	model_time 0.7243 (0.7446)	loss 1.7361 (2.6595)	grad_norm 1.2568 (2.1136/0.7595)	mem 34604MB
[2025-01-19 18:16:44 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][100/312]	eta 0:02:44 lr 0.000334	time 0.7286 (0.7739)	model_time 0.7282 (0.7579)	loss 2.7957 (2.7701)	grad_norm 3.0470 (2.3748/1.0096)	mem 34602MB
[2025-01-19 18:16:48 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][120/312]	eta 0:02:25 lr 0.000333	time 0.7263 (0.7579)	model_time 0.7261 (0.7455)	loss 2.7009 (2.6759)	grad_norm 2.9839 (2.1659/0.7800)	mem 34604MB
[2025-01-19 18:16:52 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][110/312]	eta 0:02:36 lr 0.000333	time 0.8139 (0.7731)	model_time 0.8138 (0.7586)	loss 3.0051 (2.7823)	grad_norm 1.7696 (2.3982/0.9794)	mem 34602MB
[2025-01-19 18:16:56 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][130/312]	eta 0:02:18 lr 0.000333	time 0.7150 (0.7587)	model_time 0.7148 (0.7472)	loss 3.1970 (2.6908)	grad_norm 2.5338 (2.1546/0.7639)	mem 34604MB
[2025-01-19 18:16:59 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][120/312]	eta 0:02:27 lr 0.000333	time 0.7181 (0.7700)	model_time 0.7180 (0.7566)	loss 2.5943 (2.7829)	grad_norm 1.5254 (2.3626/0.9597)	mem 34602MB
[2025-01-19 18:17:04 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][140/312]	eta 0:02:10 lr 0.000332	time 0.8205 (0.7600)	model_time 0.8204 (0.7492)	loss 2.8934 (2.6941)	grad_norm 1.7187 (2.1506/0.7548)	mem 34604MB
[2025-01-19 18:17:07 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][130/312]	eta 0:02:19 lr 0.000333	time 0.7145 (0.7692)	model_time 0.7143 (0.7568)	loss 2.3763 (2.7813)	grad_norm 3.8581 (2.3822/0.9503)	mem 34602MB
[2025-01-19 18:17:11 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][150/312]	eta 0:02:02 lr 0.000332	time 0.7384 (0.7588)	model_time 0.7379 (0.7488)	loss 2.4560 (2.6875)	grad_norm 3.1000 (2.1497/0.7436)	mem 34604MB
[2025-01-19 18:17:14 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][140/312]	eta 0:02:12 lr 0.000332	time 0.8129 (0.7682)	model_time 0.8127 (0.7566)	loss 2.8020 (2.7802)	grad_norm 2.6320 (2.4225/0.9731)	mem 34602MB
[2025-01-19 18:17:19 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][160/312]	eta 0:01:55 lr 0.000332	time 0.7245 (0.7573)	model_time 0.7243 (0.7478)	loss 2.7031 (2.6870)	grad_norm 1.7542 (2.1321/0.7296)	mem 34604MB
[2025-01-19 18:17:22 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][150/312]	eta 0:02:04 lr 0.000332	time 0.7300 (0.7668)	model_time 0.7295 (0.7560)	loss 2.9793 (2.7900)	grad_norm 4.1988 (2.4091/0.9938)	mem 34602MB
[2025-01-19 18:17:26 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][170/312]	eta 0:01:47 lr 0.000331	time 0.7219 (0.7559)	model_time 0.7214 (0.7470)	loss 1.8415 (2.6833)	grad_norm 2.6845 (2.1383/0.7357)	mem 34604MB
[2025-01-19 18:17:29 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][160/312]	eta 0:01:56 lr 0.000332	time 0.7139 (0.7653)	model_time 0.7137 (0.7552)	loss 2.8298 (2.7787)	grad_norm 1.7118 (2.3827/0.9805)	mem 34602MB
[2025-01-19 18:17:33 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][180/312]	eta 0:01:39 lr 0.000331	time 0.7428 (0.7546)	model_time 0.7424 (0.7462)	loss 2.0139 (2.6850)	grad_norm 1.9862 (2.1268/0.7274)	mem 34604MB
[2025-01-19 18:17:36 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][170/312]	eta 0:01:48 lr 0.000331	time 0.7192 (0.7641)	model_time 0.7190 (0.7545)	loss 2.8652 (2.7878)	grad_norm 3.6791 (2.3693/0.9665)	mem 34602MB
[2025-01-19 18:17:41 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][190/312]	eta 0:01:31 lr 0.000331	time 0.7286 (0.7534)	model_time 0.7284 (0.7454)	loss 3.3151 (2.6992)	grad_norm 2.8604 (2.1243/0.7149)	mem 34604MB
[2025-01-19 18:17:44 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][180/312]	eta 0:01:40 lr 0.000331	time 0.7194 (0.7634)	model_time 0.7193 (0.7544)	loss 3.0184 (2.7905)	grad_norm 1.2389 (2.3644/0.9722)	mem 34602MB
[2025-01-19 18:17:48 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][200/312]	eta 0:01:24 lr 0.000330	time 0.7256 (0.7522)	model_time 0.7251 (0.7445)	loss 2.6651 (2.7023)	grad_norm 2.2954 (2.1425/0.7254)	mem 34604MB
[2025-01-19 18:17:51 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][190/312]	eta 0:01:33 lr 0.000331	time 0.7607 (0.7628)	model_time 0.7605 (0.7542)	loss 3.2237 (2.7834)	grad_norm 1.6058 (2.3350/0.9641)	mem 34602MB
[2025-01-19 18:17:55 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][210/312]	eta 0:01:16 lr 0.000330	time 0.7203 (0.7511)	model_time 0.7202 (0.7438)	loss 2.9074 (2.6966)	grad_norm 1.9585 (2.1443/0.7249)	mem 34604MB
[2025-01-19 18:17:59 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][200/312]	eta 0:01:25 lr 0.000330	time 0.7203 (0.7613)	model_time 0.7201 (0.7531)	loss 2.9554 (2.7817)	grad_norm 1.8284 (2.3061/0.9559)	mem 34602MB
[2025-01-19 18:18:03 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][220/312]	eta 0:01:09 lr 0.000330	time 0.7192 (0.7506)	model_time 0.7190 (0.7436)	loss 2.8130 (2.6986)	grad_norm 2.9430 (2.1571/0.7343)	mem 34604MB
[2025-01-19 18:18:06 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][210/312]	eta 0:01:17 lr 0.000330	time 0.7171 (0.7609)	model_time 0.7169 (0.7530)	loss 2.8554 (2.7758)	grad_norm 1.9266 (2.2919/0.9441)	mem 34602MB
[2025-01-19 18:18:10 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][230/312]	eta 0:01:01 lr 0.000329	time 0.8338 (0.7517)	model_time 0.8334 (0.7450)	loss 2.8162 (2.6960)	grad_norm 1.0602 (2.1833/0.7847)	mem 34604MB
[2025-01-19 18:18:14 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][220/312]	eta 0:01:09 lr 0.000330	time 0.7266 (0.7602)	model_time 0.7264 (0.7527)	loss 3.0319 (2.7782)	grad_norm 1.5301 (2.2680/0.9382)	mem 34602MB
[2025-01-19 18:18:18 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][240/312]	eta 0:00:54 lr 0.000329	time 0.7137 (0.7518)	model_time 0.7136 (0.7454)	loss 1.6896 (2.6935)	grad_norm 2.0771 (2.1877/0.7792)	mem 34604MB
[2025-01-19 18:18:21 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][230/312]	eta 0:01:02 lr 0.000329	time 0.8117 (0.7607)	model_time 0.8115 (0.7535)	loss 2.4313 (2.7690)	grad_norm 3.8965 (2.2628/0.9312)	mem 34602MB
[2025-01-19 18:18:25 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][250/312]	eta 0:00:46 lr 0.000329	time 0.7253 (0.7520)	model_time 0.7249 (0.7458)	loss 1.9122 (2.6927)	grad_norm 1.2711 (2.1890/0.7975)	mem 34604MB
[2025-01-19 18:18:29 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][240/312]	eta 0:00:54 lr 0.000329	time 0.7299 (0.7592)	model_time 0.7294 (0.7523)	loss 3.0143 (2.7695)	grad_norm 4.0520 (2.2925/0.9545)	mem 34602MB
[2025-01-19 18:18:33 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][260/312]	eta 0:00:39 lr 0.000328	time 0.8270 (0.7527)	model_time 0.8265 (0.7467)	loss 2.9204 (2.6924)	grad_norm 1.6210 (2.2149/0.8194)	mem 34604MB
[2025-01-19 18:18:36 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][250/312]	eta 0:00:47 lr 0.000329	time 0.8030 (0.7595)	model_time 0.8028 (0.7529)	loss 2.6415 (2.7672)	grad_norm 1.7695 (2.2928/0.9620)	mem 34602MB
[2025-01-19 18:18:41 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][270/312]	eta 0:00:31 lr 0.000328	time 0.7519 (0.7528)	model_time 0.7515 (0.7471)	loss 2.8635 (2.7000)	grad_norm 2.1224 (2.2216/0.8159)	mem 34604MB
[2025-01-19 18:18:44 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][260/312]	eta 0:00:39 lr 0.000328	time 0.7561 (0.7587)	model_time 0.7557 (0.7523)	loss 3.1037 (2.7708)	grad_norm 1.5530 (2.2797/0.9540)	mem 34602MB
[2025-01-19 18:18:48 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][280/312]	eta 0:00:24 lr 0.000327	time 0.7240 (0.7521)	model_time 0.7239 (0.7465)	loss 2.8994 (2.7086)	grad_norm 2.1051 (2.2107/0.8093)	mem 34604MB
[2025-01-19 18:18:51 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][270/312]	eta 0:00:31 lr 0.000328	time 0.7269 (0.7583)	model_time 0.7267 (0.7521)	loss 2.9812 (2.7690)	grad_norm 2.2884 (2.2623/0.9448)	mem 34602MB
[2025-01-19 18:18:55 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][290/312]	eta 0:00:16 lr 0.000327	time 0.7236 (0.7515)	model_time 0.7232 (0.7461)	loss 1.6350 (2.7121)	grad_norm 3.7700 (2.2300/0.8108)	mem 34604MB
[2025-01-19 18:18:59 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][280/312]	eta 0:00:24 lr 0.000327	time 0.7187 (0.7576)	model_time 0.7183 (0.7516)	loss 2.8955 (2.7737)	grad_norm 1.7344 (2.2538/0.9359)	mem 34602MB
[2025-01-19 18:19:03 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][300/312]	eta 0:00:09 lr 0.000327	time 0.7149 (0.7508)	model_time 0.7148 (0.7456)	loss 2.3952 (2.7115)	grad_norm 2.4977 (2.2462/0.8141)	mem 34604MB
[2025-01-19 18:19:06 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][290/312]	eta 0:00:16 lr 0.000327	time 0.7248 (0.7569)	model_time 0.7247 (0.7511)	loss 2.9909 (2.7795)	grad_norm 1.4124 (2.2491/0.9318)	mem 34602MB
[2025-01-19 18:19:10 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][310/312]	eta 0:00:01 lr 0.000326	time 0.7137 (0.7498)	model_time 0.7136 (0.7448)	loss 2.9746 (2.7104)	grad_norm 2.2007 (2.2639/0.8131)	mem 34604MB
[2025-01-19 18:19:11 internimage_b_1k_224] (main.py 519): INFO EPOCH 247 training takes 0:03:53
[2025-01-19 18:19:11 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_247.pth saving......
[2025-01-19 18:19:13 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][300/312]	eta 0:00:09 lr 0.000327	time 0.7174 (0.7564)	model_time 0.7173 (0.7508)	loss 1.5752 (2.7736)	grad_norm 2.2077 (2.2529/0.9413)	mem 34602MB
[2025-01-19 18:19:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_247.pth saved !!!
[2025-01-19 18:19:21 internimage_b_1k_224] (main.py 510): INFO Train: [247/300][310/312]	eta 0:00:01 lr 0.000326	time 0.7146 (0.7558)	model_time 0.7145 (0.7504)	loss 2.6107 (2.7708)	grad_norm 2.2136 (2.2150/0.9127)	mem 34602MB
[2025-01-19 18:19:21 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.439 (7.439)	Loss 0.7051 (0.7051)	Acc@1 86.108 (86.108)	Acc@5 98.022 (98.022)	Mem 34604MB
[2025-01-19 18:19:22 internimage_b_1k_224] (main.py 519): INFO EPOCH 247 training takes 0:03:55
[2025-01-19 18:19:22 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_247.pth saving......
[2025-01-19 18:19:25 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_247.pth saved !!!
[2025-01-19 18:19:27 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.202)	Loss 0.9201 (0.7960)	Acc@1 81.006 (84.268)	Acc@5 96.118 (96.922)	Mem 34604MB
[2025-01-19 18:19:27 internimage_b_1k_224] (main.py 575): INFO [Epoch:247] * Acc@1 84.073 Acc@5 96.927
[2025-01-19 18:19:27 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 18:19:27 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.14%
[2025-01-19 18:19:41 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.962 (15.962)	Loss 0.7086 (0.7086)	Acc@1 85.938 (85.938)	Acc@5 97.778 (97.778)	Mem 34602MB
[2025-01-19 18:19:45 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.613 (17.613)	Loss 0.7124 (0.7124)	Acc@1 86.523 (86.523)	Acc@5 98.145 (98.145)	Mem 34604MB
[2025-01-19 18:19:49 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.175)	Loss 0.8984 (0.7899)	Acc@1 80.688 (84.211)	Acc@5 96.216 (96.886)	Mem 34602MB
[2025-01-19 18:19:49 internimage_b_1k_224] (main.py 575): INFO [Epoch:247] * Acc@1 84.043 Acc@5 96.879
[2025-01-19 18:19:49 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.0%
[2025-01-19 18:19:49 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.10%
[2025-01-19 18:19:53 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.361)	Loss 0.9258 (0.8055)	Acc@1 80.859 (84.295)	Acc@5 95.874 (96.919)	Mem 34604MB
[2025-01-19 18:19:54 internimage_b_1k_224] (main.py 575): INFO [Epoch:247] * Acc@1 84.151 Acc@5 96.961
[2025-01-19 18:19:54 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.2%
[2025-01-19 18:19:54 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:19:58 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:19:58 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.15%
[2025-01-19 18:20:00 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][0/312]	eta 0:11:26 lr 0.000326	time 2.1993 (2.1993)	model_time 0.7413 (0.7413)	loss 1.7423 (1.7423)	grad_norm 0.9158 (0.9158/0.0000)	mem 34604MB
[2025-01-19 18:20:00 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 11.433 (11.433)	Loss 0.7219 (0.7219)	Acc@1 86.230 (86.230)	Acc@5 98.242 (98.242)	Mem 34602MB
[2025-01-19 18:20:05 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.478)	Loss 0.9250 (0.8063)	Acc@1 80.176 (84.211)	Acc@5 96.118 (97.013)	Mem 34602MB
[2025-01-19 18:20:05 internimage_b_1k_224] (main.py 575): INFO [Epoch:247] * Acc@1 84.035 Acc@5 97.049
[2025-01-19 18:20:05 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.0%
[2025-01-19 18:20:05 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:20:07 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][10/312]	eta 0:04:22 lr 0.000326	time 0.7169 (0.8684)	model_time 0.7165 (0.7355)	loss 3.0497 (2.7052)	grad_norm 1.4775 (1.4208/0.3021)	mem 34604MB
[2025-01-19 18:20:09 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:20:09 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.04%
[2025-01-19 18:20:11 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][0/312]	eta 0:11:53 lr 0.000326	time 2.2856 (2.2856)	model_time 0.7498 (0.7498)	loss 2.4270 (2.4270)	grad_norm 1.4194 (1.4194/0.0000)	mem 34602MB
[2025-01-19 18:20:15 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][20/312]	eta 0:03:55 lr 0.000326	time 0.8047 (0.8055)	model_time 0.8046 (0.7358)	loss 2.8033 (2.7400)	grad_norm 2.1192 (1.6848/0.4584)	mem 34604MB
[2025-01-19 18:20:19 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][10/312]	eta 0:04:24 lr 0.000326	time 0.7244 (0.8755)	model_time 0.7242 (0.7356)	loss 2.8039 (2.7922)	grad_norm 2.3513 (2.2437/0.6508)	mem 34602MB
[2025-01-19 18:20:22 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][30/312]	eta 0:03:42 lr 0.000325	time 0.8089 (0.7880)	model_time 0.8085 (0.7406)	loss 2.8489 (2.7346)	grad_norm 2.9204 (1.9194/0.8105)	mem 34604MB
[2025-01-19 18:20:27 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][20/312]	eta 0:04:01 lr 0.000326	time 0.7319 (0.8282)	model_time 0.7317 (0.7547)	loss 2.9104 (2.7991)	grad_norm 3.9844 (2.3778/0.8459)	mem 34602MB
[2025-01-19 18:20:30 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][40/312]	eta 0:03:33 lr 0.000325	time 0.7260 (0.7845)	model_time 0.7258 (0.7486)	loss 2.9182 (2.7588)	grad_norm 2.4553 (1.9599/0.7789)	mem 34604MB
[2025-01-19 18:20:34 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][30/312]	eta 0:03:46 lr 0.000325	time 0.8081 (0.8018)	model_time 0.8080 (0.7519)	loss 2.1208 (2.8354)	grad_norm 1.9104 (2.4553/0.9674)	mem 34602MB
[2025-01-19 18:20:37 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][50/312]	eta 0:03:24 lr 0.000325	time 0.7187 (0.7788)	model_time 0.7182 (0.7499)	loss 2.8221 (2.7437)	grad_norm 1.1307 (1.9848/0.7705)	mem 34604MB
[2025-01-19 18:20:42 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][40/312]	eta 0:03:35 lr 0.000325	time 0.7288 (0.7918)	model_time 0.7284 (0.7540)	loss 2.0289 (2.8543)	grad_norm 3.6471 (2.6417/1.0322)	mem 34602MB
[2025-01-19 18:20:45 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][60/312]	eta 0:03:15 lr 0.000324	time 0.7955 (0.7778)	model_time 0.7950 (0.7535)	loss 2.7317 (2.7641)	grad_norm 1.8801 (1.9792/0.7479)	mem 34604MB
[2025-01-19 18:20:49 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][50/312]	eta 0:03:24 lr 0.000325	time 0.7511 (0.7795)	model_time 0.7510 (0.7490)	loss 3.1740 (2.8562)	grad_norm 1.7274 (2.5988/1.0422)	mem 34602MB
[2025-01-19 18:20:53 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][70/312]	eta 0:03:07 lr 0.000324	time 0.7219 (0.7751)	model_time 0.7214 (0.7542)	loss 2.9631 (2.7950)	grad_norm 3.0796 (2.0069/0.7537)	mem 34604MB
[2025-01-19 18:20:57 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][60/312]	eta 0:03:15 lr 0.000324	time 0.7328 (0.7762)	model_time 0.7324 (0.7506)	loss 2.0784 (2.7884)	grad_norm 1.2874 (2.5777/1.0143)	mem 34602MB
[2025-01-19 18:21:00 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][80/312]	eta 0:02:59 lr 0.000324	time 0.7424 (0.7724)	model_time 0.7423 (0.7540)	loss 2.1786 (2.7732)	grad_norm 2.2578 (2.0154/0.7479)	mem 34604MB
[2025-01-19 18:21:04 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][70/312]	eta 0:03:06 lr 0.000324	time 0.7083 (0.7708)	model_time 0.7082 (0.7488)	loss 2.9401 (2.7506)	grad_norm 2.0581 (2.5500/0.9596)	mem 34602MB
[2025-01-19 18:21:08 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][90/312]	eta 0:02:50 lr 0.000323	time 0.7194 (0.7683)	model_time 0.7193 (0.7519)	loss 3.3490 (2.7946)	grad_norm 1.2564 (2.0197/0.7764)	mem 34604MB
[2025-01-19 18:21:11 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][80/312]	eta 0:02:58 lr 0.000324	time 0.7254 (0.7687)	model_time 0.7250 (0.7494)	loss 2.6631 (2.7461)	grad_norm 3.7569 (2.6513/0.9734)	mem 34602MB
[2025-01-19 18:21:15 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][100/312]	eta 0:02:41 lr 0.000323	time 0.6831 (0.7636)	model_time 0.6829 (0.7488)	loss 3.1071 (2.7929)	grad_norm inf (2.0417/0.8012)	mem 34604MB
[2025-01-19 18:21:19 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][90/312]	eta 0:02:49 lr 0.000323	time 0.7167 (0.7650)	model_time 0.7166 (0.7478)	loss 1.9802 (2.7363)	grad_norm 2.1757 (2.6140/0.9530)	mem 34602MB
[2025-01-19 18:21:22 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][110/312]	eta 0:02:33 lr 0.000323	time 0.7243 (0.7608)	model_time 0.7238 (0.7473)	loss 2.7128 (2.7814)	grad_norm 2.6206 (2.0669/0.8441)	mem 34604MB
[2025-01-19 18:21:26 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][100/312]	eta 0:02:41 lr 0.000323	time 0.7634 (0.7635)	model_time 0.7629 (0.7480)	loss 2.4021 (2.7452)	grad_norm 1.2561 (2.5364/0.9599)	mem 34602MB
[2025-01-19 18:21:29 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][120/312]	eta 0:02:25 lr 0.000322	time 0.7162 (0.7578)	model_time 0.7158 (0.7454)	loss 1.7250 (2.7675)	grad_norm 1.7453 (2.0605/0.8340)	mem 34604MB
[2025-01-19 18:21:34 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][110/312]	eta 0:02:34 lr 0.000323	time 0.8097 (0.7637)	model_time 0.8092 (0.7495)	loss 2.5623 (2.7340)	grad_norm 1.3226 (2.4761/0.9458)	mem 34602MB
[2025-01-19 18:21:37 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][130/312]	eta 0:02:17 lr 0.000322	time 0.7268 (0.7563)	model_time 0.7267 (0.7448)	loss 3.4767 (2.7593)	grad_norm 1.4595 (2.1295/0.9341)	mem 34604MB
[2025-01-19 18:21:41 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][120/312]	eta 0:02:26 lr 0.000322	time 0.7197 (0.7613)	model_time 0.7192 (0.7482)	loss 1.6714 (2.7289)	grad_norm 2.1389 (2.4908/0.9713)	mem 34602MB
[2025-01-19 18:21:44 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][140/312]	eta 0:02:09 lr 0.000322	time 0.8045 (0.7551)	model_time 0.8043 (0.7444)	loss 1.9873 (2.7530)	grad_norm 1.9899 (2.1719/0.9714)	mem 34604MB
[2025-01-19 18:21:49 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][130/312]	eta 0:02:18 lr 0.000322	time 0.7181 (0.7594)	model_time 0.7179 (0.7473)	loss 3.1629 (2.7349)	grad_norm 4.1838 (2.5511/1.0326)	mem 34602MB
[2025-01-19 18:21:52 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][150/312]	eta 0:02:02 lr 0.000321	time 0.8216 (0.7546)	model_time 0.8215 (0.7446)	loss 3.0329 (2.7513)	grad_norm 3.9383 (2.2595/1.0267)	mem 34604MB
[2025-01-19 18:21:56 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][140/312]	eta 0:02:10 lr 0.000322	time 0.7183 (0.7581)	model_time 0.7182 (0.7468)	loss 2.3643 (2.7338)	grad_norm 1.6754 (2.5750/1.0591)	mem 34602MB
[2025-01-19 18:21:59 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][160/312]	eta 0:01:54 lr 0.000321	time 0.7193 (0.7551)	model_time 0.7189 (0.7457)	loss 2.8457 (2.7484)	grad_norm 1.0916 (2.2642/1.0260)	mem 34604MB
[2025-01-19 18:22:04 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][150/312]	eta 0:02:02 lr 0.000321	time 0.7850 (0.7588)	model_time 0.7848 (0.7483)	loss 2.7690 (2.7276)	grad_norm 1.7938 (2.5155/1.0535)	mem 34602MB
[2025-01-19 18:22:07 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][170/312]	eta 0:01:47 lr 0.000321	time 0.8150 (0.7555)	model_time 0.8148 (0.7466)	loss 3.3180 (2.7399)	grad_norm 3.1244 (2.2570/1.0092)	mem 34604MB
[2025-01-19 18:22:11 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][160/312]	eta 0:01:55 lr 0.000321	time 0.7330 (0.7585)	model_time 0.7326 (0.7486)	loss 2.2043 (2.7049)	grad_norm 2.5376 (2.4822/1.0491)	mem 34602MB
[2025-01-19 18:22:15 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][180/312]	eta 0:01:39 lr 0.000320	time 0.7191 (0.7566)	model_time 0.7186 (0.7481)	loss 2.7838 (2.7519)	grad_norm 1.7634 (2.2722/1.0087)	mem 34604MB
[2025-01-19 18:22:19 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][170/312]	eta 0:01:47 lr 0.000321	time 0.7195 (0.7567)	model_time 0.7193 (0.7474)	loss 2.2881 (2.7100)	grad_norm 1.4124 (2.4271/1.0515)	mem 34602MB
[2025-01-19 18:22:22 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][190/312]	eta 0:01:32 lr 0.000320	time 0.7440 (0.7572)	model_time 0.7434 (0.7491)	loss 2.4049 (2.7494)	grad_norm 2.4888 (2.2454/0.9946)	mem 34604MB
[2025-01-19 18:22:26 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][180/312]	eta 0:01:39 lr 0.000320	time 0.7167 (0.7566)	model_time 0.7166 (0.7478)	loss 3.0290 (2.7065)	grad_norm 2.3044 (2.3752/1.0486)	mem 34602MB
[2025-01-19 18:22:30 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][200/312]	eta 0:01:24 lr 0.000320	time 0.7339 (0.7571)	model_time 0.7337 (0.7495)	loss 2.8821 (2.7452)	grad_norm 2.2754 (2.2389/0.9769)	mem 34604MB
[2025-01-19 18:22:34 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][190/312]	eta 0:01:32 lr 0.000320	time 0.7174 (0.7558)	model_time 0.7170 (0.7474)	loss 2.9204 (2.7059)	grad_norm 1.6342 (2.3683/1.0349)	mem 34602MB
[2025-01-19 18:22:37 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][210/312]	eta 0:01:17 lr 0.000319	time 0.7223 (0.7560)	model_time 0.7221 (0.7487)	loss 2.8217 (2.7406)	grad_norm 4.0145 (2.2706/0.9890)	mem 34604MB
[2025-01-19 18:22:41 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][200/312]	eta 0:01:24 lr 0.000320	time 0.7238 (0.7551)	model_time 0.7234 (0.7471)	loss 2.8838 (2.7057)	grad_norm 2.9824 (2.3915/1.0445)	mem 34602MB
[2025-01-19 18:22:44 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][220/312]	eta 0:01:09 lr 0.000319	time 0.7645 (0.7549)	model_time 0.7641 (0.7479)	loss 2.8682 (2.7340)	grad_norm 1.1141 (2.2643/1.0002)	mem 34604MB
[2025-01-19 18:22:48 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][210/312]	eta 0:01:16 lr 0.000319	time 0.7202 (0.7541)	model_time 0.7200 (0.7465)	loss 2.7450 (2.7091)	grad_norm 1.6225 (2.4103/1.0521)	mem 34602MB
[2025-01-19 18:22:52 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][230/312]	eta 0:01:01 lr 0.000319	time 0.7260 (0.7541)	model_time 0.7258 (0.7474)	loss 2.6656 (2.7299)	grad_norm 2.3291 (2.2945/0.9958)	mem 34604MB
[2025-01-19 18:22:56 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][220/312]	eta 0:01:09 lr 0.000319	time 0.7237 (0.7541)	model_time 0.7235 (0.7468)	loss 2.7936 (2.7110)	grad_norm 1.4588 (2.4164/1.0590)	mem 34602MB
[2025-01-19 18:22:59 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][240/312]	eta 0:00:54 lr 0.000318	time 0.7287 (0.7531)	model_time 0.7282 (0.7467)	loss 2.8643 (2.7238)	grad_norm 1.6217 (2.3358/1.0249)	mem 34604MB
[2025-01-19 18:23:03 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][230/312]	eta 0:01:01 lr 0.000319	time 0.8091 (0.7542)	model_time 0.8087 (0.7472)	loss 3.1672 (2.7113)	grad_norm 2.2843 (2.4249/1.0521)	mem 34602MB
[2025-01-19 18:23:06 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][250/312]	eta 0:00:46 lr 0.000318	time 0.7270 (0.7523)	model_time 0.7265 (0.7461)	loss 2.4392 (2.7310)	grad_norm 1.0525 (2.3352/1.0143)	mem 34604MB
[2025-01-19 18:23:11 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][240/312]	eta 0:00:54 lr 0.000318	time 0.7198 (0.7535)	model_time 0.7197 (0.7467)	loss 2.3316 (2.7162)	grad_norm 1.1802 (2.4055/1.0438)	mem 34602MB
[2025-01-19 18:23:14 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][260/312]	eta 0:00:39 lr 0.000317	time 0.7246 (0.7516)	model_time 0.7242 (0.7456)	loss 3.1812 (2.7283)	grad_norm 1.4332 (2.3270/1.0036)	mem 34604MB
[2025-01-19 18:23:18 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][250/312]	eta 0:00:46 lr 0.000318	time 0.7902 (0.7525)	model_time 0.7898 (0.7461)	loss 1.9773 (2.7106)	grad_norm 2.8478 (2.3916/1.0286)	mem 34602MB
[2025-01-19 18:23:21 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][270/312]	eta 0:00:31 lr 0.000317	time 0.8081 (0.7512)	model_time 0.8076 (0.7454)	loss 2.7493 (2.7352)	grad_norm 2.0487 (2.3200/0.9974)	mem 34604MB
[2025-01-19 18:23:26 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][260/312]	eta 0:00:39 lr 0.000317	time 0.7233 (0.7531)	model_time 0.7229 (0.7469)	loss 2.1897 (2.7111)	grad_norm 2.8254 (2.3809/1.0185)	mem 34602MB
[2025-01-19 18:23:29 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][280/312]	eta 0:00:24 lr 0.000317	time 0.7400 (0.7525)	model_time 0.7396 (0.7469)	loss 2.9706 (2.7350)	grad_norm 3.3396 (2.3334/1.0077)	mem 34604MB
[2025-01-19 18:23:33 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][270/312]	eta 0:00:31 lr 0.000317	time 0.8601 (0.7531)	model_time 0.8597 (0.7471)	loss 3.1068 (2.7073)	grad_norm 1.0764 (2.3705/1.0125)	mem 34602MB
[2025-01-19 18:23:37 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][290/312]	eta 0:00:16 lr 0.000316	time 0.8390 (0.7531)	model_time 0.8389 (0.7477)	loss 3.0733 (2.7428)	grad_norm 5.0123 (2.3839/1.0557)	mem 34604MB
[2025-01-19 18:23:41 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][280/312]	eta 0:00:24 lr 0.000317	time 0.7594 (0.7534)	model_time 0.7590 (0.7476)	loss 2.9691 (2.6993)	grad_norm 2.6160 (2.3894/1.0405)	mem 34602MB
[2025-01-19 18:23:44 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][300/312]	eta 0:00:09 lr 0.000316	time 0.7211 (0.7527)	model_time 0.7210 (0.7475)	loss 3.3735 (2.7487)	grad_norm 1.3461 (2.3827/1.0494)	mem 34604MB
[2025-01-19 18:23:48 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][290/312]	eta 0:00:16 lr 0.000316	time 0.7323 (0.7528)	model_time 0.7318 (0.7472)	loss 2.9491 (2.7000)	grad_norm 3.0124 (2.3961/1.0390)	mem 34602MB
[2025-01-19 18:23:52 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][310/312]	eta 0:00:01 lr 0.000316	time 0.7987 (0.7529)	model_time 0.7986 (0.7479)	loss 2.2344 (2.7368)	grad_norm 2.9291 (2.4023/1.0435)	mem 34604MB
[2025-01-19 18:23:53 internimage_b_1k_224] (main.py 519): INFO EPOCH 248 training takes 0:03:54
[2025-01-19 18:23:53 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_248.pth saving......
[2025-01-19 18:23:56 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][300/312]	eta 0:00:09 lr 0.000316	time 0.7157 (0.7523)	model_time 0.7156 (0.7469)	loss 3.1205 (2.7025)	grad_norm 1.2650 (2.3888/1.0304)	mem 34602MB
[2025-01-19 18:23:56 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_248.pth saved !!!
[2025-01-19 18:24:03 internimage_b_1k_224] (main.py 510): INFO Train: [248/300][310/312]	eta 0:00:01 lr 0.000316	time 0.7133 (0.7514)	model_time 0.7132 (0.7461)	loss 2.2049 (2.6985)	grad_norm 2.2686 (2.3844/1.0307)	mem 34602MB
[2025-01-19 18:24:03 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.608 (7.608)	Loss 0.6930 (0.6930)	Acc@1 86.304 (86.304)	Acc@5 97.852 (97.852)	Mem 34604MB
[2025-01-19 18:24:04 internimage_b_1k_224] (main.py 519): INFO EPOCH 248 training takes 0:03:54
[2025-01-19 18:24:04 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_248.pth saving......
[2025-01-19 18:24:07 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_248.pth saved !!!
[2025-01-19 18:24:09 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.188)	Loss 0.9064 (0.7828)	Acc@1 80.762 (84.262)	Acc@5 96.143 (96.893)	Mem 34604MB
[2025-01-19 18:24:09 internimage_b_1k_224] (main.py 575): INFO [Epoch:248] * Acc@1 84.095 Acc@5 96.895
[2025-01-19 18:24:09 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 18:24:09 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.14%
[2025-01-19 18:24:22 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.228 (15.228)	Loss 0.7095 (0.7095)	Acc@1 86.060 (86.060)	Acc@5 97.974 (97.974)	Mem 34602MB
[2025-01-19 18:24:27 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.891 (17.891)	Loss 0.7125 (0.7125)	Acc@1 86.499 (86.499)	Acc@5 98.120 (98.120)	Mem 34604MB
[2025-01-19 18:24:30 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.089)	Loss 0.8917 (0.7836)	Acc@1 80.713 (84.129)	Acc@5 95.972 (96.968)	Mem 34602MB
[2025-01-19 18:24:30 internimage_b_1k_224] (main.py 575): INFO [Epoch:248] * Acc@1 83.961 Acc@5 96.959
[2025-01-19 18:24:30 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.0%
[2025-01-19 18:24:30 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.10%
[2025-01-19 18:24:35 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (2.319)	Loss 0.9251 (0.8051)	Acc@1 80.859 (84.306)	Acc@5 95.898 (96.915)	Mem 34604MB
[2025-01-19 18:24:35 internimage_b_1k_224] (main.py 575): INFO [Epoch:248] * Acc@1 84.163 Acc@5 96.955
[2025-01-19 18:24:35 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.2%
[2025-01-19 18:24:35 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:24:39 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:24:39 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.16%
[2025-01-19 18:24:41 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 10.953 (10.953)	Loss 0.7218 (0.7218)	Acc@1 86.206 (86.206)	Acc@5 98.242 (98.242)	Mem 34602MB
[2025-01-19 18:24:41 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][0/312]	eta 0:11:01 lr 0.000316	time 2.1213 (2.1213)	model_time 0.7500 (0.7500)	loss 2.5750 (2.5750)	grad_norm 1.2914 (1.2914/0.0000)	mem 34604MB
[2025-01-19 18:24:46 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.415)	Loss 0.9240 (0.8058)	Acc@1 80.249 (84.233)	Acc@5 96.191 (97.021)	Mem 34602MB
[2025-01-19 18:24:46 internimage_b_1k_224] (main.py 575): INFO [Epoch:248] * Acc@1 84.049 Acc@5 97.055
[2025-01-19 18:24:46 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.0%
[2025-01-19 18:24:46 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:24:49 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][10/312]	eta 0:04:29 lr 0.000315	time 0.8109 (0.8937)	model_time 0.8105 (0.7687)	loss 2.5182 (2.8266)	grad_norm 1.7598 (2.1934/0.9959)	mem 34604MB
[2025-01-19 18:24:50 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:24:50 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.05%
[2025-01-19 18:24:52 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][0/312]	eta 0:11:48 lr 0.000316	time 2.2693 (2.2693)	model_time 0.7356 (0.7356)	loss 1.6696 (1.6696)	grad_norm 3.0738 (3.0738/0.0000)	mem 34602MB
[2025-01-19 18:24:56 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][20/312]	eta 0:03:58 lr 0.000315	time 0.7267 (0.8160)	model_time 0.7265 (0.7504)	loss 2.6153 (2.8126)	grad_norm 2.9660 (2.4351/0.9776)	mem 34604MB
[2025-01-19 18:24:59 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][10/312]	eta 0:04:27 lr 0.000315	time 0.7412 (0.8848)	model_time 0.7410 (0.7451)	loss 2.1140 (2.3563)	grad_norm 1.9710 (2.0657/0.5711)	mem 34602MB
[2025-01-19 18:25:03 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][30/312]	eta 0:03:41 lr 0.000315	time 0.7229 (0.7870)	model_time 0.7225 (0.7424)	loss 2.6478 (2.7561)	grad_norm 1.8188 (2.4395/0.8764)	mem 34604MB
[2025-01-19 18:25:07 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][20/312]	eta 0:03:58 lr 0.000315	time 0.7553 (0.8160)	model_time 0.7551 (0.7427)	loss 2.0013 (2.4685)	grad_norm 1.3403 (1.9418/0.5603)	mem 34602MB
[2025-01-19 18:25:11 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][40/312]	eta 0:03:30 lr 0.000314	time 0.7216 (0.7742)	model_time 0.7214 (0.7404)	loss 3.0928 (2.7859)	grad_norm 2.0894 (2.3763/0.9331)	mem 34604MB
[2025-01-19 18:25:14 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][30/312]	eta 0:03:44 lr 0.000315	time 0.7204 (0.7954)	model_time 0.7202 (0.7456)	loss 3.2999 (2.4892)	grad_norm 1.7404 (2.0320/0.6604)	mem 34602MB
[2025-01-19 18:25:18 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][50/312]	eta 0:03:20 lr 0.000314	time 0.7279 (0.7657)	model_time 0.7277 (0.7385)	loss 3.0614 (2.7831)	grad_norm 1.9010 (2.2992/0.8821)	mem 34604MB
[2025-01-19 18:25:22 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][40/312]	eta 0:03:33 lr 0.000314	time 0.8057 (0.7857)	model_time 0.8053 (0.7480)	loss 2.6125 (2.4944)	grad_norm 1.4803 (2.0462/0.6648)	mem 34602MB
[2025-01-19 18:25:25 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][60/312]	eta 0:03:11 lr 0.000314	time 0.7360 (0.7589)	model_time 0.7355 (0.7361)	loss 2.5626 (2.7541)	grad_norm 1.9543 (2.3241/0.8579)	mem 34604MB
[2025-01-19 18:25:29 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][50/312]	eta 0:03:23 lr 0.000314	time 0.7227 (0.7768)	model_time 0.7226 (0.7464)	loss 3.2788 (2.5020)	grad_norm 3.0068 (2.1120/0.7632)	mem 34602MB
[2025-01-19 18:25:33 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][70/312]	eta 0:03:02 lr 0.000313	time 0.7082 (0.7549)	model_time 0.7080 (0.7353)	loss 2.0278 (2.6983)	grad_norm 3.0880 (2.3829/0.9311)	mem 34604MB
[2025-01-19 18:25:37 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][60/312]	eta 0:03:14 lr 0.000314	time 0.7381 (0.7708)	model_time 0.7380 (0.7454)	loss 2.2733 (2.5405)	grad_norm 2.3039 (2.1370/0.7382)	mem 34602MB
[2025-01-19 18:25:40 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][80/312]	eta 0:02:55 lr 0.000313	time 0.8075 (0.7543)	model_time 0.8070 (0.7371)	loss 3.0803 (2.6746)	grad_norm 1.7025 (2.4296/0.9601)	mem 34604MB
[2025-01-19 18:25:44 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][70/312]	eta 0:03:05 lr 0.000313	time 0.7277 (0.7684)	model_time 0.7272 (0.7465)	loss 2.9086 (2.5628)	grad_norm 2.1927 (2.1638/0.7758)	mem 34602MB
[2025-01-19 18:25:48 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][90/312]	eta 0:02:47 lr 0.000313	time 0.7334 (0.7561)	model_time 0.7332 (0.7407)	loss 2.7115 (2.6921)	grad_norm 2.4789 (2.4183/0.9210)	mem 34604MB
[2025-01-19 18:25:52 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][80/312]	eta 0:02:57 lr 0.000313	time 0.7171 (0.7662)	model_time 0.7170 (0.7470)	loss 1.9751 (2.6042)	grad_norm 5.2810 (2.2227/0.8691)	mem 34602MB
[2025-01-19 18:25:55 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][100/312]	eta 0:02:40 lr 0.000312	time 0.8121 (0.7566)	model_time 0.8117 (0.7427)	loss 1.9140 (2.6939)	grad_norm 3.9175 (2.4699/0.9642)	mem 34604MB
[2025-01-19 18:25:59 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][90/312]	eta 0:02:49 lr 0.000313	time 0.7205 (0.7654)	model_time 0.7204 (0.7482)	loss 1.9105 (2.6308)	grad_norm 1.8924 (2.2382/0.8620)	mem 34602MB
[2025-01-19 18:26:03 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][110/312]	eta 0:02:33 lr 0.000312	time 0.9308 (0.7575)	model_time 0.9304 (0.7448)	loss 3.1834 (2.6954)	grad_norm 2.7589 (2.5651/1.0681)	mem 34604MB
[2025-01-19 18:26:07 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][100/312]	eta 0:02:41 lr 0.000312	time 0.7271 (0.7622)	model_time 0.7266 (0.7466)	loss 3.4731 (2.6213)	grad_norm 2.4642 (2.2049/0.8436)	mem 34602MB
[2025-01-19 18:26:11 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][120/312]	eta 0:02:25 lr 0.000312	time 0.8124 (0.7583)	model_time 0.8122 (0.7466)	loss 3.0614 (2.6990)	grad_norm 3.7718 (2.6016/1.1404)	mem 34604MB
[2025-01-19 18:26:14 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][110/312]	eta 0:02:33 lr 0.000312	time 0.7149 (0.7614)	model_time 0.7147 (0.7473)	loss 3.0591 (2.6479)	grad_norm 2.6718 (2.2022/0.8392)	mem 34602MB
[2025-01-19 18:26:18 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][130/312]	eta 0:02:18 lr 0.000311	time 0.8057 (0.7590)	model_time 0.8055 (0.7482)	loss 2.7478 (2.7020)	grad_norm 0.8737 (2.6069/1.1529)	mem 34604MB
[2025-01-19 18:26:22 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][120/312]	eta 0:02:25 lr 0.000312	time 0.7175 (0.7596)	model_time 0.7170 (0.7466)	loss 2.3712 (2.6515)	grad_norm 1.6271 (2.1909/0.8224)	mem 34602MB
[2025-01-19 18:26:26 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][140/312]	eta 0:02:10 lr 0.000311	time 0.7404 (0.7574)	model_time 0.7399 (0.7473)	loss 2.4606 (2.6962)	grad_norm 2.2096 (2.5478/1.1380)	mem 34604MB
[2025-01-19 18:26:29 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][130/312]	eta 0:02:18 lr 0.000311	time 0.7134 (0.7596)	model_time 0.7130 (0.7475)	loss 2.3379 (2.6485)	grad_norm 1.3083 (2.1943/0.8050)	mem 34602MB
[2025-01-19 18:26:33 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][150/312]	eta 0:02:02 lr 0.000311	time 0.7727 (0.7560)	model_time 0.7725 (0.7466)	loss 2.6195 (2.6923)	grad_norm 1.1538 (2.4928/1.1247)	mem 34604MB
[2025-01-19 18:26:37 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][140/312]	eta 0:02:10 lr 0.000311	time 0.7213 (0.7579)	model_time 0.7211 (0.7466)	loss 3.0320 (2.6379)	grad_norm 0.9234 (2.1856/0.8016)	mem 34602MB
[2025-01-19 18:26:41 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][160/312]	eta 0:01:54 lr 0.000310	time 0.7174 (0.7546)	model_time 0.7172 (0.7457)	loss 2.6193 (2.6980)	grad_norm 3.6079 (2.4521/1.1159)	mem 34604MB
[2025-01-19 18:26:44 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][150/312]	eta 0:02:02 lr 0.000311	time 0.7503 (0.7572)	model_time 0.7501 (0.7466)	loss 1.9783 (2.6436)	grad_norm 3.2634 (2.2712/0.9047)	mem 34602MB
[2025-01-19 18:26:48 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][170/312]	eta 0:01:46 lr 0.000310	time 0.7208 (0.7529)	model_time 0.7207 (0.7446)	loss 3.3066 (2.7069)	grad_norm 1.2901 (2.4202/1.1106)	mem 34604MB
[2025-01-19 18:26:52 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][160/312]	eta 0:01:55 lr 0.000310	time 0.8001 (0.7569)	model_time 0.7999 (0.7470)	loss 3.6390 (2.6450)	grad_norm 3.7834 (2.3532/0.9730)	mem 34602MB
[2025-01-19 18:26:55 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][180/312]	eta 0:01:39 lr 0.000310	time 0.7197 (0.7515)	model_time 0.7195 (0.7436)	loss 2.9401 (2.7055)	grad_norm 3.0231 (2.4198/1.1047)	mem 34604MB
[2025-01-19 18:26:59 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][170/312]	eta 0:01:47 lr 0.000310	time 0.7536 (0.7567)	model_time 0.7534 (0.7473)	loss 2.8786 (2.6572)	grad_norm 1.2665 (2.3861/0.9946)	mem 34602MB
[2025-01-19 18:27:02 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][190/312]	eta 0:01:31 lr 0.000309	time 0.7268 (0.7503)	model_time 0.7266 (0.7428)	loss 2.9969 (2.7098)	grad_norm 3.2068 (2.4319/1.0992)	mem 34604MB
[2025-01-19 18:27:07 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][180/312]	eta 0:01:39 lr 0.000310	time 0.7323 (0.7556)	model_time 0.7320 (0.7467)	loss 3.3574 (2.6742)	grad_norm 1.9092 (2.3835/0.9787)	mem 34602MB
[2025-01-19 18:27:10 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][200/312]	eta 0:01:24 lr 0.000309	time 0.7157 (0.7502)	model_time 0.7155 (0.7430)	loss 2.6038 (2.7131)	grad_norm 1.9033 (2.4406/1.0840)	mem 34604MB
[2025-01-19 18:27:14 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][190/312]	eta 0:01:32 lr 0.000309	time 0.7185 (0.7555)	model_time 0.7183 (0.7471)	loss 2.1832 (2.6730)	grad_norm 1.9039 (2.3785/0.9930)	mem 34602MB
[2025-01-19 18:27:17 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][210/312]	eta 0:01:16 lr 0.000309	time 0.7160 (0.7510)	model_time 0.7158 (0.7442)	loss 3.3589 (2.7141)	grad_norm 1.7830 (2.4147/1.0699)	mem 34604MB
[2025-01-19 18:27:22 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][200/312]	eta 0:01:24 lr 0.000309	time 0.7177 (0.7560)	model_time 0.7172 (0.7479)	loss 2.5777 (2.6755)	grad_norm 4.9475 (2.4178/1.0126)	mem 34602MB
[2025-01-19 18:27:25 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][220/312]	eta 0:01:09 lr 0.000308	time 0.7093 (0.7508)	model_time 0.7088 (0.7442)	loss 2.5440 (2.7171)	grad_norm 1.8293 (2.4129/1.0614)	mem 34604MB
[2025-01-19 18:27:29 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][210/312]	eta 0:01:17 lr 0.000309	time 0.7175 (0.7555)	model_time 0.7173 (0.7479)	loss 1.9710 (2.6687)	grad_norm 1.0748 (2.3933/1.0089)	mem 34602MB
[2025-01-19 18:27:33 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][230/312]	eta 0:01:01 lr 0.000308	time 0.8077 (0.7518)	model_time 0.8075 (0.7456)	loss 2.8119 (2.7208)	grad_norm 3.0167 (2.4644/1.1070)	mem 34604MB
[2025-01-19 18:27:37 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][220/312]	eta 0:01:09 lr 0.000308	time 0.7278 (0.7548)	model_time 0.7273 (0.7475)	loss 1.6425 (2.6715)	grad_norm 1.6589 (2.3692/0.9954)	mem 34602MB
[2025-01-19 18:27:40 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][240/312]	eta 0:00:54 lr 0.000308	time 0.8021 (0.7526)	model_time 0.8019 (0.7466)	loss 2.8157 (2.7208)	grad_norm 1.8874 (2.4641/1.0989)	mem 34604MB
[2025-01-19 18:27:44 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][230/312]	eta 0:01:01 lr 0.000308	time 0.7415 (0.7550)	model_time 0.7413 (0.7479)	loss 3.2397 (2.6824)	grad_norm 1.7318 (2.3479/0.9841)	mem 34602MB
[2025-01-19 18:27:48 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][250/312]	eta 0:00:46 lr 0.000307	time 0.8082 (0.7537)	model_time 0.8080 (0.7479)	loss 3.1723 (2.7273)	grad_norm 5.4901 (2.5264/1.1454)	mem 34604MB
[2025-01-19 18:27:51 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][240/312]	eta 0:00:54 lr 0.000308	time 0.7495 (0.7541)	model_time 0.7491 (0.7473)	loss 2.9034 (2.6926)	grad_norm 2.0396 (2.3564/0.9815)	mem 34602MB
[2025-01-19 18:27:55 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][260/312]	eta 0:00:39 lr 0.000307	time 0.7236 (0.7528)	model_time 0.7234 (0.7472)	loss 2.3170 (2.7353)	grad_norm 2.4741 (2.5102/1.1391)	mem 34604MB
[2025-01-19 18:27:59 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][250/312]	eta 0:00:46 lr 0.000307	time 0.7194 (0.7534)	model_time 0.7192 (0.7469)	loss 3.3744 (2.6897)	grad_norm 2.2199 (2.3350/0.9703)	mem 34602MB
[2025-01-19 18:28:03 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][270/312]	eta 0:00:31 lr 0.000307	time 0.7238 (0.7519)	model_time 0.7233 (0.7465)	loss 2.5286 (2.7333)	grad_norm 2.4854 (2.4870/1.1295)	mem 34604MB
[2025-01-19 18:28:06 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][260/312]	eta 0:00:39 lr 0.000307	time 0.7557 (0.7528)	model_time 0.7553 (0.7465)	loss 1.8522 (2.6955)	grad_norm 2.2186 (2.3251/0.9590)	mem 34602MB
[2025-01-19 18:28:10 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][280/312]	eta 0:00:24 lr 0.000306	time 0.7283 (0.7513)	model_time 0.7282 (0.7461)	loss 2.9468 (2.7397)	grad_norm 3.4676 (2.4752/1.1257)	mem 34604MB
[2025-01-19 18:28:14 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][270/312]	eta 0:00:31 lr 0.000307	time 0.7252 (0.7524)	model_time 0.7250 (0.7464)	loss 2.9905 (2.6956)	grad_norm 1.6119 (2.3208/0.9578)	mem 34602MB
[2025-01-19 18:28:17 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][290/312]	eta 0:00:16 lr 0.000306	time 0.7115 (0.7503)	model_time 0.7114 (0.7453)	loss 3.3870 (2.7350)	grad_norm 1.2529 (2.4598/1.1176)	mem 34604MB
[2025-01-19 18:28:21 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][280/312]	eta 0:00:24 lr 0.000306	time 0.8006 (0.7525)	model_time 0.8001 (0.7467)	loss 2.8602 (2.6940)	grad_norm 1.8740 (2.3041/0.9506)	mem 34602MB
[2025-01-19 18:28:25 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][300/312]	eta 0:00:08 lr 0.000306	time 0.7128 (0.7495)	model_time 0.7127 (0.7446)	loss 2.3942 (2.7249)	grad_norm 1.8517 (2.4538/1.1073)	mem 34604MB
[2025-01-19 18:28:29 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][290/312]	eta 0:00:16 lr 0.000306	time 0.7093 (0.7522)	model_time 0.7091 (0.7466)	loss 2.9602 (2.6981)	grad_norm 1.5139 (2.3280/0.9873)	mem 34602MB
[2025-01-19 18:28:32 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][310/312]	eta 0:00:01 lr 0.000305	time 0.7131 (0.7484)	model_time 0.7130 (0.7437)	loss 2.5928 (2.7281)	grad_norm 2.0396 (2.4373/1.1025)	mem 34604MB
[2025-01-19 18:28:32 internimage_b_1k_224] (main.py 519): INFO EPOCH 249 training takes 0:03:53
[2025-01-19 18:28:33 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_249.pth saving......
[2025-01-19 18:28:36 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_249.pth saved !!!
[2025-01-19 18:28:36 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][300/312]	eta 0:00:09 lr 0.000306	time 0.7130 (0.7511)	model_time 0.7129 (0.7457)	loss 2.5185 (2.6958)	grad_norm 2.3600 (2.3420/0.9873)	mem 34602MB
[2025-01-19 18:28:43 internimage_b_1k_224] (main.py 510): INFO Train: [249/300][310/312]	eta 0:00:01 lr 0.000305	time 0.7074 (0.7508)	model_time 0.7073 (0.7455)	loss 3.1053 (2.6917)	grad_norm 1.8030 (2.3448/0.9890)	mem 34602MB
[2025-01-19 18:28:43 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.538 (7.538)	Loss 0.6800 (0.6800)	Acc@1 86.401 (86.401)	Acc@5 97.900 (97.900)	Mem 34604MB
[2025-01-19 18:28:44 internimage_b_1k_224] (main.py 519): INFO EPOCH 249 training takes 0:03:54
[2025-01-19 18:28:44 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_249.pth saving......
[2025-01-19 18:28:47 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_249.pth saved !!!
[2025-01-19 18:28:48 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.147)	Loss 0.8840 (0.7693)	Acc@1 80.957 (84.393)	Acc@5 95.898 (96.846)	Mem 34604MB
[2025-01-19 18:28:49 internimage_b_1k_224] (main.py 575): INFO [Epoch:249] * Acc@1 84.219 Acc@5 96.865
[2025-01-19 18:28:49 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.2%
[2025-01-19 18:28:49 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 18:28:52 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 18:28:52 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.22%
[2025-01-19 18:29:02 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.175 (15.175)	Loss 0.6966 (0.6966)	Acc@1 86.108 (86.108)	Acc@5 98.096 (98.096)	Mem 34602MB
[2025-01-19 18:29:08 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.317 (16.317)	Loss 0.7126 (0.7126)	Acc@1 86.499 (86.499)	Acc@5 98.120 (98.120)	Mem 34604MB
[2025-01-19 18:29:10 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (2.102)	Loss 0.8974 (0.7782)	Acc@1 80.591 (84.220)	Acc@5 96.167 (96.953)	Mem 34602MB
[2025-01-19 18:29:11 internimage_b_1k_224] (main.py 575): INFO [Epoch:249] * Acc@1 84.029 Acc@5 96.969
[2025-01-19 18:29:11 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.0%
[2025-01-19 18:29:11 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.10%
[2025-01-19 18:29:14 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.047)	Loss 0.9244 (0.8047)	Acc@1 80.859 (84.324)	Acc@5 95.898 (96.922)	Mem 34604MB
[2025-01-19 18:29:15 internimage_b_1k_224] (main.py 575): INFO [Epoch:249] * Acc@1 84.183 Acc@5 96.959
[2025-01-19 18:29:15 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.2%
[2025-01-19 18:29:15 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:29:19 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:29:19 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.18%
[2025-01-19 18:29:21 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][0/312]	eta 0:10:27 lr 0.000305	time 2.0122 (2.0122)	model_time 0.7512 (0.7512)	loss 3.1335 (3.1335)	grad_norm 2.2031 (2.2031/0.0000)	mem 34604MB
[2025-01-19 18:29:21 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 10.765 (10.765)	Loss 0.7219 (0.7219)	Acc@1 86.230 (86.230)	Acc@5 98.218 (98.218)	Mem 34602MB
[2025-01-19 18:29:26 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.390)	Loss 0.9232 (0.8054)	Acc@1 80.249 (84.244)	Acc@5 96.191 (97.015)	Mem 34602MB
[2025-01-19 18:29:26 internimage_b_1k_224] (main.py 575): INFO [Epoch:249] * Acc@1 84.065 Acc@5 97.047
[2025-01-19 18:29:26 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.1%
[2025-01-19 18:29:26 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:29:28 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][10/312]	eta 0:04:21 lr 0.000305	time 0.8111 (0.8659)	model_time 0.8110 (0.7509)	loss 2.3199 (2.6962)	grad_norm 2.2515 (2.5322/1.2130)	mem 34604MB
[2025-01-19 18:29:30 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:29:30 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.07%
[2025-01-19 18:29:32 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][0/312]	eta 0:10:48 lr 0.000305	time 2.0791 (2.0791)	model_time 0.7549 (0.7549)	loss 2.3249 (2.3249)	grad_norm 1.0193 (1.0193/0.0000)	mem 34602MB
[2025-01-19 18:29:36 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][20/312]	eta 0:03:59 lr 0.000305	time 0.7294 (0.8194)	model_time 0.7289 (0.7590)	loss 2.3915 (2.6873)	grad_norm 3.0796 (2.6558/1.0891)	mem 34604MB
[2025-01-19 18:29:40 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][10/312]	eta 0:04:27 lr 0.000305	time 0.7921 (0.8871)	model_time 0.7919 (0.7664)	loss 2.6996 (2.5334)	grad_norm 1.3000 (2.3576/0.9060)	mem 34602MB
[2025-01-19 18:29:44 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][30/312]	eta 0:03:46 lr 0.000304	time 0.8105 (0.8035)	model_time 0.8103 (0.7624)	loss 1.6886 (2.5959)	grad_norm 3.5135 (2.6574/1.0551)	mem 34604MB
[2025-01-19 18:29:47 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][20/312]	eta 0:04:00 lr 0.000305	time 0.8046 (0.8244)	model_time 0.8044 (0.7610)	loss 1.6630 (2.6021)	grad_norm 1.4936 (2.1018/0.7936)	mem 34602MB
[2025-01-19 18:29:51 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][40/312]	eta 0:03:36 lr 0.000304	time 0.7400 (0.7943)	model_time 0.7398 (0.7632)	loss 2.2198 (2.6116)	grad_norm 1.6277 (2.4985/1.0369)	mem 34604MB
[2025-01-19 18:29:55 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][30/312]	eta 0:03:44 lr 0.000304	time 0.7353 (0.7966)	model_time 0.7348 (0.7535)	loss 3.1119 (2.6249)	grad_norm 1.3548 (1.9466/0.7336)	mem 34602MB
[2025-01-19 18:29:59 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][50/312]	eta 0:03:27 lr 0.000304	time 0.8557 (0.7916)	model_time 0.8555 (0.7665)	loss 2.5652 (2.6193)	grad_norm 1.7034 (2.3509/1.0063)	mem 34604MB
[2025-01-19 18:30:02 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][40/312]	eta 0:03:34 lr 0.000304	time 0.7493 (0.7897)	model_time 0.7491 (0.7570)	loss 1.8500 (2.6811)	grad_norm 4.4221 (2.0293/0.8210)	mem 34602MB
[2025-01-19 18:30:07 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][60/312]	eta 0:03:17 lr 0.000303	time 0.7485 (0.7851)	model_time 0.7483 (0.7641)	loss 2.5907 (2.6336)	grad_norm 1.1740 (2.3722/1.0501)	mem 34604MB
[2025-01-19 18:30:10 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][50/312]	eta 0:03:24 lr 0.000304	time 0.7207 (0.7811)	model_time 0.7206 (0.7547)	loss 2.0578 (2.6848)	grad_norm 3.5984 (2.1752/0.8667)	mem 34602MB
[2025-01-19 18:30:14 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][70/312]	eta 0:03:08 lr 0.000303	time 0.7204 (0.7792)	model_time 0.7199 (0.7611)	loss 3.1980 (2.6337)	grad_norm 2.7843 (2.3955/1.0432)	mem 34604MB
[2025-01-19 18:30:17 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][60/312]	eta 0:03:15 lr 0.000303	time 0.7305 (0.7751)	model_time 0.7303 (0.7530)	loss 2.7567 (2.7268)	grad_norm 4.9458 (2.4142/1.1183)	mem 34602MB
[2025-01-19 18:30:21 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][80/312]	eta 0:02:59 lr 0.000303	time 0.7268 (0.7732)	model_time 0.7267 (0.7573)	loss 2.8837 (2.6379)	grad_norm 1.5551 (2.4360/1.0761)	mem 34604MB
[2025-01-19 18:30:25 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][70/312]	eta 0:03:06 lr 0.000303	time 0.7155 (0.7698)	model_time 0.7153 (0.7508)	loss 1.7606 (2.7120)	grad_norm 1.3573 (2.3916/1.0632)	mem 34602MB
[2025-01-19 18:30:29 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][90/312]	eta 0:02:50 lr 0.000302	time 0.7294 (0.7688)	model_time 0.7290 (0.7546)	loss 3.1865 (2.6707)	grad_norm 2.4853 (2.4359/1.0556)	mem 34604MB
[2025-01-19 18:30:32 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][80/312]	eta 0:02:57 lr 0.000303	time 0.7430 (0.7671)	model_time 0.7426 (0.7504)	loss 1.6837 (2.6940)	grad_norm 2.9144 (2.4403/1.0456)	mem 34602MB
[2025-01-19 18:30:36 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][100/312]	eta 0:02:42 lr 0.000302	time 0.7194 (0.7649)	model_time 0.7189 (0.7520)	loss 2.7506 (2.6968)	grad_norm 2.0124 (2.4341/1.0222)	mem 34604MB
[2025-01-19 18:30:40 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][90/312]	eta 0:02:50 lr 0.000302	time 0.7179 (0.7660)	model_time 0.7175 (0.7511)	loss 2.6926 (2.6913)	grad_norm 2.2501 (2.3748/1.0330)	mem 34602MB
[2025-01-19 18:30:43 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][110/312]	eta 0:02:33 lr 0.000302	time 0.7216 (0.7617)	model_time 0.7214 (0.7499)	loss 2.9057 (2.6835)	grad_norm 2.9651 (2.4293/0.9961)	mem 34604MB
[2025-01-19 18:30:47 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][100/312]	eta 0:02:41 lr 0.000302	time 0.7164 (0.7624)	model_time 0.7163 (0.7489)	loss 2.6236 (2.7086)	grad_norm 1.9095 (2.3248/1.0041)	mem 34602MB
[2025-01-19 18:30:51 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][120/312]	eta 0:02:25 lr 0.000301	time 0.7329 (0.7594)	model_time 0.7325 (0.7486)	loss 2.9413 (2.7028)	grad_norm 2.5518 (2.3924/0.9721)	mem 34604MB
[2025-01-19 18:30:54 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][110/312]	eta 0:02:33 lr 0.000302	time 0.7356 (0.7589)	model_time 0.7354 (0.7467)	loss 2.2622 (2.7135)	grad_norm 3.5110 (2.3439/0.9999)	mem 34602MB
[2025-01-19 18:30:58 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][130/312]	eta 0:02:18 lr 0.000301	time 0.8097 (0.7587)	model_time 0.8093 (0.7487)	loss 2.9463 (2.7126)	grad_norm 1.9359 (2.3624/0.9484)	mem 34604MB
[2025-01-19 18:31:02 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][120/312]	eta 0:02:25 lr 0.000301	time 0.8178 (0.7590)	model_time 0.8174 (0.7477)	loss 2.7725 (2.7042)	grad_norm 2.3980 (2.3800/1.0129)	mem 34602MB
[2025-01-19 18:31:06 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][140/312]	eta 0:02:10 lr 0.000301	time 0.7133 (0.7602)	model_time 0.7131 (0.7509)	loss 2.7449 (2.7180)	grad_norm 2.8773 (2.3760/0.9469)	mem 34604MB
[2025-01-19 18:31:09 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][130/312]	eta 0:02:18 lr 0.000301	time 0.8013 (0.7593)	model_time 0.8012 (0.7489)	loss 2.9418 (2.7108)	grad_norm 1.7233 (2.3208/1.0001)	mem 34602MB
[2025-01-19 18:31:13 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][150/312]	eta 0:02:03 lr 0.000300	time 0.8144 (0.7594)	model_time 0.8142 (0.7507)	loss 3.1042 (2.7283)	grad_norm 3.4747 (2.3877/0.9497)	mem 34604MB
[2025-01-19 18:31:17 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][140/312]	eta 0:02:10 lr 0.000301	time 0.8439 (0.7589)	model_time 0.8436 (0.7492)	loss 2.8885 (2.7140)	grad_norm 1.6210 (2.2940/0.9826)	mem 34602MB
[2025-01-19 18:31:21 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][160/312]	eta 0:01:55 lr 0.000300	time 0.7186 (0.7600)	model_time 0.7182 (0.7518)	loss 3.1394 (2.7299)	grad_norm 2.5979 (2.4477/1.0135)	mem 34604MB
[2025-01-19 18:31:24 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][150/312]	eta 0:02:02 lr 0.000300	time 0.7193 (0.7573)	model_time 0.7191 (0.7482)	loss 2.9145 (2.7085)	grad_norm 4.2168 (2.3094/0.9921)	mem 34602MB
[2025-01-19 18:31:29 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][170/312]	eta 0:01:48 lr 0.000300	time 0.8890 (0.7616)	model_time 0.8889 (0.7538)	loss 2.8464 (2.7247)	grad_norm 1.9865 (2.4168/0.9942)	mem 34604MB
[2025-01-19 18:31:32 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][160/312]	eta 0:01:55 lr 0.000300	time 0.7221 (0.7577)	model_time 0.7217 (0.7491)	loss 2.6221 (2.7208)	grad_norm 2.4957 (2.3047/0.9855)	mem 34602MB
[2025-01-19 18:31:36 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][180/312]	eta 0:01:40 lr 0.000299	time 0.7446 (0.7610)	model_time 0.7441 (0.7537)	loss 2.7154 (2.7318)	grad_norm 2.0356 (2.3884/0.9797)	mem 34604MB
[2025-01-19 18:31:39 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][170/312]	eta 0:01:47 lr 0.000300	time 0.7226 (0.7576)	model_time 0.7224 (0.7496)	loss 2.9823 (2.7250)	grad_norm 1.6561 (2.2636/0.9741)	mem 34602MB
[2025-01-19 18:31:44 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][190/312]	eta 0:01:32 lr 0.000299	time 0.7108 (0.7601)	model_time 0.7104 (0.7531)	loss 3.0314 (2.7359)	grad_norm 1.1619 (2.3460/0.9775)	mem 34604MB
[2025-01-19 18:31:47 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][180/312]	eta 0:01:40 lr 0.000299	time 0.7252 (0.7578)	model_time 0.7250 (0.7502)	loss 2.7072 (2.7272)	grad_norm 1.8852 (2.2506/0.9628)	mem 34602MB
[2025-01-19 18:31:51 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][200/312]	eta 0:01:24 lr 0.000299	time 0.7441 (0.7585)	model_time 0.7440 (0.7518)	loss 2.8185 (2.7328)	grad_norm 1.9767 (2.3212/0.9649)	mem 34604MB
[2025-01-19 18:31:54 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][190/312]	eta 0:01:32 lr 0.000299	time 0.7252 (0.7567)	model_time 0.7248 (0.7494)	loss 2.9110 (2.7282)	grad_norm 1.5679 (2.2494/0.9825)	mem 34602MB
[2025-01-19 18:31:58 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][210/312]	eta 0:01:17 lr 0.000298	time 0.7231 (0.7574)	model_time 0.7227 (0.7511)	loss 2.5474 (2.7362)	grad_norm 2.1514 (2.3070/0.9518)	mem 34604MB
[2025-01-19 18:32:02 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][200/312]	eta 0:01:24 lr 0.000299	time 0.7242 (0.7561)	model_time 0.7238 (0.7492)	loss 2.1852 (2.7237)	grad_norm 4.2112 (2.2775/1.0204)	mem 34602MB
[2025-01-19 18:32:06 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][220/312]	eta 0:01:09 lr 0.000298	time 0.7198 (0.7561)	model_time 0.7194 (0.7500)	loss 2.0333 (2.7335)	grad_norm 1.8852 (2.2784/0.9472)	mem 34604MB
[2025-01-19 18:32:09 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][210/312]	eta 0:01:17 lr 0.000298	time 0.7162 (0.7556)	model_time 0.7160 (0.7489)	loss 2.6177 (2.7105)	grad_norm 1.2250 (2.3269/1.0497)	mem 34602MB
[2025-01-19 18:32:13 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][230/312]	eta 0:01:01 lr 0.000298	time 0.7183 (0.7552)	model_time 0.7178 (0.7493)	loss 2.9400 (2.7458)	grad_norm 3.0217 (2.2699/0.9378)	mem 34604MB
[2025-01-19 18:32:17 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][220/312]	eta 0:01:09 lr 0.000298	time 0.7159 (0.7550)	model_time 0.7157 (0.7486)	loss 2.8373 (2.7196)	grad_norm 2.3329 (2.3255/1.0413)	mem 34602MB
[2025-01-19 18:32:20 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][240/312]	eta 0:00:54 lr 0.000297	time 0.7215 (0.7540)	model_time 0.7210 (0.7484)	loss 3.1737 (2.7481)	grad_norm 2.5169 (2.2694/0.9253)	mem 34604MB
[2025-01-19 18:32:24 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][230/312]	eta 0:01:01 lr 0.000298	time 0.7188 (0.7538)	model_time 0.7187 (0.7477)	loss 2.4356 (2.7231)	grad_norm 1.9878 (2.3529/1.0411)	mem 34602MB
[2025-01-19 18:32:28 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][250/312]	eta 0:00:46 lr 0.000297	time 0.7301 (0.7537)	model_time 0.7300 (0.7483)	loss 2.4695 (2.7519)	grad_norm 1.1628 (2.2789/0.9232)	mem 34604MB
[2025-01-19 18:32:32 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][240/312]	eta 0:00:54 lr 0.000297	time 0.8087 (0.7539)	model_time 0.8082 (0.7481)	loss 3.1337 (2.7202)	grad_norm 1.4481 (2.3414/1.0307)	mem 34602MB
[2025-01-19 18:32:35 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][260/312]	eta 0:00:39 lr 0.000297	time 0.7183 (0.7540)	model_time 0.7181 (0.7488)	loss 1.9281 (2.7361)	grad_norm 1.0861 (2.2713/0.9249)	mem 34604MB
[2025-01-19 18:32:39 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][250/312]	eta 0:00:46 lr 0.000297	time 0.7875 (0.7543)	model_time 0.7871 (0.7487)	loss 2.6165 (2.7073)	grad_norm 2.9036 (2.3253/1.0238)	mem 34602MB
[2025-01-19 18:32:43 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][270/312]	eta 0:00:31 lr 0.000296	time 0.8153 (0.7540)	model_time 0.8152 (0.7490)	loss 2.4201 (2.7304)	grad_norm 2.9031 (2.2581/0.9180)	mem 34604MB
[2025-01-19 18:32:47 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][260/312]	eta 0:00:39 lr 0.000297	time 1.0091 (0.7550)	model_time 1.0090 (0.7496)	loss 2.4607 (2.7084)	grad_norm 1.4888 (2.3100/1.0172)	mem 34602MB
[2025-01-19 18:32:51 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][280/312]	eta 0:00:24 lr 0.000296	time 0.7215 (0.7548)	model_time 0.7211 (0.7499)	loss 2.6359 (2.7308)	grad_norm 1.4125 (2.2683/0.9425)	mem 34604MB
[2025-01-19 18:32:54 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][270/312]	eta 0:00:31 lr 0.000296	time 0.7353 (0.7543)	model_time 0.7351 (0.7491)	loss 3.1138 (2.7057)	grad_norm 2.0634 (2.3297/1.0525)	mem 34602MB
[2025-01-19 18:32:58 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][290/312]	eta 0:00:16 lr 0.000296	time 0.8063 (0.7550)	model_time 0.8059 (0.7503)	loss 2.7180 (2.7294)	grad_norm 2.0480 (2.2562/0.9327)	mem 34604MB
[2025-01-19 18:33:02 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][280/312]	eta 0:00:24 lr 0.000296	time 0.7977 (0.7544)	model_time 0.7975 (0.7493)	loss 2.6125 (2.6979)	grad_norm 3.0405 (2.3309/1.0409)	mem 34602MB
[2025-01-19 18:33:06 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][300/312]	eta 0:00:09 lr 0.000295	time 0.7191 (0.7547)	model_time 0.7190 (0.7502)	loss 1.6912 (2.7227)	grad_norm 1.1608 (2.2672/0.9483)	mem 34604MB
[2025-01-19 18:33:10 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][290/312]	eta 0:00:16 lr 0.000296	time 0.7261 (0.7547)	model_time 0.7259 (0.7498)	loss 2.2288 (2.6977)	grad_norm 1.1768 (2.3147/1.0321)	mem 34602MB
[2025-01-19 18:33:13 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][310/312]	eta 0:00:01 lr 0.000295	time 0.7166 (0.7539)	model_time 0.7165 (0.7494)	loss 2.9124 (2.7217)	grad_norm 3.2986 (2.2850/0.9686)	mem 34604MB
[2025-01-19 18:33:14 internimage_b_1k_224] (main.py 519): INFO EPOCH 250 training takes 0:03:55
[2025-01-19 18:33:14 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_250.pth saving......
[2025-01-19 18:33:17 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_250.pth saved !!!
[2025-01-19 18:33:17 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][300/312]	eta 0:00:09 lr 0.000295	time 0.7174 (0.7546)	model_time 0.7173 (0.7499)	loss 2.6895 (2.7020)	grad_norm 2.1369 (2.3008/1.0242)	mem 34602MB
[2025-01-19 18:33:24 internimage_b_1k_224] (main.py 510): INFO Train: [250/300][310/312]	eta 0:00:01 lr 0.000295	time 0.7225 (0.7538)	model_time 0.7224 (0.7492)	loss 2.7565 (2.7016)	grad_norm 4.6379 (2.3047/1.0301)	mem 34602MB
[2025-01-19 18:33:25 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.400 (7.400)	Loss 0.6873 (0.6873)	Acc@1 86.035 (86.035)	Acc@5 97.900 (97.900)	Mem 34604MB
[2025-01-19 18:33:25 internimage_b_1k_224] (main.py 519): INFO EPOCH 250 training takes 0:03:55
[2025-01-19 18:33:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_250.pth saving......
[2025-01-19 18:33:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_250.pth saved !!!
[2025-01-19 18:33:30 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.127)	Loss 0.8962 (0.7753)	Acc@1 81.006 (84.450)	Acc@5 96.045 (96.953)	Mem 34604MB
[2025-01-19 18:33:30 internimage_b_1k_224] (main.py 575): INFO [Epoch:250] * Acc@1 84.287 Acc@5 96.971
[2025-01-19 18:33:30 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.3%
[2025-01-19 18:33:30 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 18:33:33 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 18:33:33 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.29%
[2025-01-19 18:33:43 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.679 (14.679)	Loss 0.7211 (0.7211)	Acc@1 86.182 (86.182)	Acc@5 97.949 (97.949)	Mem 34602MB
[2025-01-19 18:33:49 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.904 (15.904)	Loss 0.7126 (0.7126)	Acc@1 86.499 (86.499)	Acc@5 98.071 (98.071)	Mem 34604MB
[2025-01-19 18:33:50 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.004)	Loss 0.9039 (0.7941)	Acc@1 80.225 (84.257)	Acc@5 96.143 (96.908)	Mem 34602MB
[2025-01-19 18:33:51 internimage_b_1k_224] (main.py 575): INFO [Epoch:250] * Acc@1 84.097 Acc@5 96.923
[2025-01-19 18:33:51 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 18:33:51 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.10%
[2025-01-19 18:33:56 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.084)	Loss 0.9236 (0.8043)	Acc@1 80.811 (84.337)	Acc@5 95.923 (96.935)	Mem 34604MB
[2025-01-19 18:33:56 internimage_b_1k_224] (main.py 575): INFO [Epoch:250] * Acc@1 84.191 Acc@5 96.975
[2025-01-19 18:33:56 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.2%
[2025-01-19 18:33:56 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:34:00 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:34:00 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.19%
[2025-01-19 18:34:02 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 11.084 (11.084)	Loss 0.7218 (0.7218)	Acc@1 86.255 (86.255)	Acc@5 98.218 (98.218)	Mem 34602MB
[2025-01-19 18:34:02 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][0/312]	eta 0:11:30 lr 0.000295	time 2.2128 (2.2128)	model_time 0.7440 (0.7440)	loss 2.9864 (2.9864)	grad_norm 2.9246 (2.9246/0.0000)	mem 34604MB
[2025-01-19 18:34:06 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.425)	Loss 0.9224 (0.8050)	Acc@1 80.298 (84.266)	Acc@5 96.240 (97.030)	Mem 34602MB
[2025-01-19 18:34:07 internimage_b_1k_224] (main.py 575): INFO [Epoch:250] * Acc@1 84.087 Acc@5 97.061
[2025-01-19 18:34:07 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.1%
[2025-01-19 18:34:07 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:34:10 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][10/312]	eta 0:04:20 lr 0.000295	time 0.7178 (0.8623)	model_time 0.7174 (0.7284)	loss 2.9220 (2.6778)	grad_norm 2.3050 (2.7007/0.7078)	mem 34604MB
[2025-01-19 18:34:10 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:34:10 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.09%
[2025-01-19 18:34:13 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][0/312]	eta 0:11:28 lr 0.000295	time 2.2076 (2.2076)	model_time 0.7368 (0.7368)	loss 3.0586 (3.0586)	grad_norm 1.3428 (1.3428/0.0000)	mem 34602MB
[2025-01-19 18:34:17 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][20/312]	eta 0:03:54 lr 0.000294	time 0.7239 (0.8021)	model_time 0.7237 (0.7317)	loss 2.8209 (2.6836)	grad_norm 2.1396 (2.4391/0.8372)	mem 34604MB
[2025-01-19 18:34:20 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][10/312]	eta 0:04:27 lr 0.000295	time 0.7256 (0.8865)	model_time 0.7254 (0.7526)	loss 3.0771 (2.9361)	grad_norm 2.1933 (2.1659/0.8249)	mem 34602MB
[2025-01-19 18:34:24 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][30/312]	eta 0:03:39 lr 0.000294	time 0.7256 (0.7786)	model_time 0.7252 (0.7308)	loss 2.7642 (2.5661)	grad_norm 2.6213 (2.2648/0.7772)	mem 34604MB
[2025-01-19 18:34:28 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][20/312]	eta 0:04:00 lr 0.000294	time 0.7958 (0.8240)	model_time 0.7953 (0.7536)	loss 2.8720 (2.8427)	grad_norm 2.5935 (2.3039/0.7720)	mem 34602MB
[2025-01-19 18:34:31 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][40/312]	eta 0:03:28 lr 0.000294	time 0.7264 (0.7653)	model_time 0.7263 (0.7291)	loss 2.5230 (2.5894)	grad_norm 0.9344 (2.1979/0.7669)	mem 34604MB
[2025-01-19 18:34:35 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][30/312]	eta 0:03:44 lr 0.000294	time 0.7168 (0.7953)	model_time 0.7164 (0.7475)	loss 2.9933 (2.7323)	grad_norm 3.9862 (2.6812/1.0677)	mem 34602MB
[2025-01-19 18:34:39 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][50/312]	eta 0:03:18 lr 0.000293	time 0.7253 (0.7571)	model_time 0.7252 (0.7279)	loss 2.8262 (2.6560)	grad_norm 3.3372 (2.2165/0.7716)	mem 34604MB
[2025-01-19 18:34:42 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][40/312]	eta 0:03:32 lr 0.000294	time 0.7316 (0.7805)	model_time 0.7314 (0.7443)	loss 2.3282 (2.6941)	grad_norm 2.7173 (2.6332/1.0852)	mem 34602MB
[2025-01-19 18:34:46 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][60/312]	eta 0:03:10 lr 0.000293	time 0.8129 (0.7557)	model_time 0.8127 (0.7312)	loss 2.4406 (2.6363)	grad_norm 1.4572 (2.3667/0.8494)	mem 34604MB
[2025-01-19 18:34:50 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][50/312]	eta 0:03:23 lr 0.000293	time 0.8121 (0.7758)	model_time 0.8119 (0.7466)	loss 2.0712 (2.6845)	grad_norm 2.8745 (2.9044/1.4084)	mem 34602MB
[2025-01-19 18:34:54 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][70/312]	eta 0:03:03 lr 0.000293	time 0.8455 (0.7572)	model_time 0.8451 (0.7361)	loss 1.9709 (2.6273)	grad_norm 1.0637 (2.3117/0.8681)	mem 34604MB
[2025-01-19 18:34:57 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][60/312]	eta 0:03:14 lr 0.000293	time 0.8168 (0.7715)	model_time 0.8167 (0.7471)	loss 3.0365 (2.7035)	grad_norm 1.9802 (2.7638/1.3420)	mem 34602MB
[2025-01-19 18:35:01 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][80/312]	eta 0:02:55 lr 0.000292	time 0.7108 (0.7568)	model_time 0.7106 (0.7383)	loss 2.6617 (2.6319)	grad_norm 1.4966 (2.2870/0.8860)	mem 34604MB
[2025-01-19 18:35:05 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][70/312]	eta 0:03:06 lr 0.000293	time 0.7166 (0.7700)	model_time 0.7164 (0.7489)	loss 2.9956 (2.7190)	grad_norm 3.1800 (2.6396/1.3224)	mem 34602MB
[2025-01-19 18:35:09 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][90/312]	eta 0:02:48 lr 0.000292	time 0.7168 (0.7583)	model_time 0.7164 (0.7418)	loss 3.1266 (2.6207)	grad_norm 1.0739 (2.2583/0.8667)	mem 34604MB
[2025-01-19 18:35:13 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][80/312]	eta 0:02:57 lr 0.000292	time 0.8254 (0.7672)	model_time 0.8253 (0.7487)	loss 1.9675 (2.7042)	grad_norm 3.0802 (2.5849/1.2729)	mem 34602MB
[2025-01-19 18:35:17 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][100/312]	eta 0:02:40 lr 0.000292	time 0.7171 (0.7581)	model_time 0.7169 (0.7431)	loss 3.1285 (2.6170)	grad_norm 2.7961 (2.2701/0.8583)	mem 34604MB
[2025-01-19 18:35:20 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][90/312]	eta 0:02:49 lr 0.000292	time 0.7169 (0.7650)	model_time 0.7164 (0.7485)	loss 2.7274 (2.6923)	grad_norm 5.6256 (2.6319/1.2801)	mem 34602MB
[2025-01-19 18:35:24 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][110/312]	eta 0:02:33 lr 0.000291	time 0.7602 (0.7578)	model_time 0.7600 (0.7442)	loss 2.9274 (2.6463)	grad_norm 1.6896 (2.2392/0.8388)	mem 34604MB
[2025-01-19 18:35:28 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][100/312]	eta 0:02:41 lr 0.000292	time 0.7238 (0.7635)	model_time 0.7237 (0.7486)	loss 3.0269 (2.6957)	grad_norm 2.7308 (2.6643/1.2698)	mem 34602MB
[2025-01-19 18:35:32 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][120/312]	eta 0:02:25 lr 0.000291	time 0.7252 (0.7559)	model_time 0.7251 (0.7434)	loss 2.5707 (2.6536)	grad_norm 2.3278 (2.2612/0.8560)	mem 34604MB
[2025-01-19 18:35:35 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][110/312]	eta 0:02:33 lr 0.000291	time 0.7329 (0.7620)	model_time 0.7327 (0.7484)	loss 3.0300 (2.6939)	grad_norm 3.1262 (2.6326/1.2482)	mem 34602MB
[2025-01-19 18:35:39 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][130/312]	eta 0:02:17 lr 0.000291	time 0.7225 (0.7539)	model_time 0.7221 (0.7423)	loss 2.9737 (2.6598)	grad_norm 2.7257 (2.2847/0.8880)	mem 34604MB
[2025-01-19 18:35:42 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][120/312]	eta 0:02:25 lr 0.000291	time 0.7290 (0.7597)	model_time 0.7289 (0.7472)	loss 2.1287 (2.6568)	grad_norm 2.2541 (2.6002/1.2232)	mem 34602MB
[2025-01-19 18:35:46 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][140/312]	eta 0:02:09 lr 0.000290	time 0.7240 (0.7527)	model_time 0.7238 (0.7418)	loss 3.1036 (2.6626)	grad_norm 1.5221 (2.2943/0.8886)	mem 34604MB
[2025-01-19 18:35:50 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][130/312]	eta 0:02:18 lr 0.000291	time 0.8467 (0.7603)	model_time 0.8462 (0.7487)	loss 2.9230 (2.6591)	grad_norm 4.4495 (2.5979/1.2025)	mem 34602MB
[2025-01-19 18:35:54 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][150/312]	eta 0:02:01 lr 0.000290	time 0.7419 (0.7511)	model_time 0.7414 (0.7410)	loss 2.8641 (2.6685)	grad_norm 1.1123 (2.2823/0.8922)	mem 34604MB
[2025-01-19 18:35:58 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][140/312]	eta 0:02:10 lr 0.000290	time 0.8109 (0.7602)	model_time 0.8108 (0.7494)	loss 3.3009 (2.6662)	grad_norm 1.5209 (2.5542/1.1796)	mem 34602MB
[2025-01-19 18:36:01 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][160/312]	eta 0:01:53 lr 0.000290	time 0.7236 (0.7496)	model_time 0.7231 (0.7401)	loss 3.0962 (2.6771)	grad_norm 1.6618 (2.2639/0.8732)	mem 34604MB
[2025-01-19 18:36:05 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][150/312]	eta 0:02:02 lr 0.000290	time 0.8094 (0.7590)	model_time 0.8089 (0.7489)	loss 2.4472 (2.6589)	grad_norm 1.2776 (2.5060/1.1592)	mem 34602MB
[2025-01-19 18:36:08 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][170/312]	eta 0:01:46 lr 0.000289	time 0.7221 (0.7484)	model_time 0.7217 (0.7395)	loss 2.7588 (2.6938)	grad_norm 1.5929 (2.2541/0.8579)	mem 34604MB
[2025-01-19 18:36:12 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][160/312]	eta 0:01:55 lr 0.000290	time 0.7123 (0.7570)	model_time 0.7122 (0.7475)	loss 2.9480 (2.6656)	grad_norm 1.1892 (2.4659/1.1518)	mem 34602MB
[2025-01-19 18:36:15 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][180/312]	eta 0:01:38 lr 0.000289	time 0.7183 (0.7478)	model_time 0.7182 (0.7393)	loss 3.0187 (2.7025)	grad_norm 1.1051 (2.2941/0.9110)	mem 34604MB
[2025-01-19 18:36:20 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][170/312]	eta 0:01:47 lr 0.000289	time 0.8012 (0.7572)	model_time 0.8011 (0.7483)	loss 3.0015 (2.6692)	grad_norm 3.1652 (2.4635/1.1458)	mem 34602MB
[2025-01-19 18:36:23 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][190/312]	eta 0:01:31 lr 0.000289	time 0.7296 (0.7482)	model_time 0.7292 (0.7401)	loss 3.1326 (2.6977)	grad_norm 2.2479 (2.3054/0.9054)	mem 34604MB
[2025-01-19 18:36:28 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][180/312]	eta 0:01:39 lr 0.000289	time 0.8099 (0.7575)	model_time 0.8098 (0.7490)	loss 2.4670 (2.6671)	grad_norm 1.7668 (2.4166/1.1336)	mem 34602MB
[2025-01-19 18:36:31 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][200/312]	eta 0:01:23 lr 0.000289	time 0.7087 (0.7488)	model_time 0.7085 (0.7411)	loss 2.8576 (2.7060)	grad_norm 1.8733 (2.2941/0.9122)	mem 34604MB
[2025-01-19 18:36:35 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][190/312]	eta 0:01:32 lr 0.000289	time 0.7175 (0.7573)	model_time 0.7173 (0.7493)	loss 2.7707 (2.6628)	grad_norm 2.2670 (2.4128/1.1108)	mem 34602MB
[2025-01-19 18:36:38 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][210/312]	eta 0:01:16 lr 0.000288	time 0.8188 (0.7504)	model_time 0.8184 (0.7430)	loss 1.7437 (2.6985)	grad_norm 2.9027 (2.2838/0.9015)	mem 34604MB
[2025-01-19 18:36:43 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][200/312]	eta 0:01:24 lr 0.000289	time 0.9960 (0.7577)	model_time 0.9955 (0.7501)	loss 3.0942 (2.6744)	grad_norm 4.4639 (2.4201/1.1127)	mem 34602MB
[2025-01-19 18:36:46 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][220/312]	eta 0:01:09 lr 0.000288	time 0.7155 (0.7510)	model_time 0.7154 (0.7440)	loss 2.5743 (2.6892)	grad_norm 2.1404 (2.2774/0.8910)	mem 34604MB
[2025-01-19 18:36:50 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][210/312]	eta 0:01:17 lr 0.000288	time 0.7203 (0.7568)	model_time 0.7202 (0.7495)	loss 2.2231 (2.6710)	grad_norm 1.3022 (2.4166/1.1049)	mem 34602MB
[2025-01-19 18:36:54 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][230/312]	eta 0:01:01 lr 0.000288	time 0.7191 (0.7512)	model_time 0.7186 (0.7445)	loss 2.9811 (2.6887)	grad_norm 2.3184 (2.2558/0.8818)	mem 34604MB
[2025-01-19 18:36:58 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][220/312]	eta 0:01:09 lr 0.000288	time 0.8148 (0.7565)	model_time 0.8146 (0.7495)	loss 2.9739 (2.6822)	grad_norm 1.4077 (2.3985/1.0954)	mem 34602MB
[2025-01-19 18:37:01 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][240/312]	eta 0:00:54 lr 0.000287	time 0.7278 (0.7505)	model_time 0.7274 (0.7441)	loss 2.1251 (2.6932)	grad_norm 2.4243 (2.2449/0.8751)	mem 34604MB
[2025-01-19 18:37:05 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][230/312]	eta 0:01:02 lr 0.000288	time 0.7166 (0.7566)	model_time 0.7164 (0.7498)	loss 2.5139 (2.6813)	grad_norm 3.0978 (2.4460/1.1185)	mem 34602MB
[2025-01-19 18:37:08 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][250/312]	eta 0:00:46 lr 0.000287	time 0.7393 (0.7498)	model_time 0.7391 (0.7436)	loss 2.8343 (2.6847)	grad_norm 3.0379 (2.2602/0.8784)	mem 34604MB
[2025-01-19 18:37:12 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][240/312]	eta 0:00:54 lr 0.000287	time 0.8295 (0.7556)	model_time 0.8294 (0.7491)	loss 2.9763 (2.6838)	grad_norm 2.2473 (2.4497/1.1109)	mem 34602MB
[2025-01-19 18:37:16 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][260/312]	eta 0:00:38 lr 0.000287	time 0.7207 (0.7494)	model_time 0.7202 (0.7434)	loss 1.8246 (2.6699)	grad_norm 1.9714 (2.2744/0.8823)	mem 34604MB
[2025-01-19 18:37:20 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][250/312]	eta 0:00:46 lr 0.000287	time 0.7281 (0.7555)	model_time 0.7276 (0.7493)	loss 2.6454 (2.6813)	grad_norm 2.0532 (2.4381/1.1027)	mem 34602MB
[2025-01-19 18:37:23 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][270/312]	eta 0:00:31 lr 0.000286	time 0.7203 (0.7487)	model_time 0.7202 (0.7429)	loss 2.5494 (2.6771)	grad_norm 4.0207 (2.2654/0.8816)	mem 34604MB
[2025-01-19 18:37:28 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][260/312]	eta 0:00:39 lr 0.000287	time 0.8036 (0.7563)	model_time 0.8033 (0.7503)	loss 3.3801 (2.6843)	grad_norm 2.4754 (2.4247/1.0921)	mem 34602MB
[2025-01-19 18:37:30 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][280/312]	eta 0:00:23 lr 0.000286	time 0.7217 (0.7481)	model_time 0.7216 (0.7425)	loss 3.1146 (2.6796)	grad_norm 1.6209 (2.2641/0.8835)	mem 34604MB
[2025-01-19 18:37:35 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][270/312]	eta 0:00:31 lr 0.000286	time 0.8327 (0.7556)	model_time 0.8321 (0.7498)	loss 2.7725 (2.6942)	grad_norm 2.0566 (2.4486/1.0927)	mem 34602MB
[2025-01-19 18:37:38 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][290/312]	eta 0:00:16 lr 0.000286	time 0.7357 (0.7473)	model_time 0.7353 (0.7419)	loss 2.3857 (2.6756)	grad_norm 2.5969 (2.2683/0.8874)	mem 34604MB
[2025-01-19 18:37:42 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][280/312]	eta 0:00:24 lr 0.000286	time 0.7253 (0.7547)	model_time 0.7251 (0.7491)	loss 3.1897 (2.7023)	grad_norm 3.7336 (2.4570/1.0808)	mem 34602MB
[2025-01-19 18:37:45 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][300/312]	eta 0:00:08 lr 0.000285	time 0.7174 (0.7467)	model_time 0.7173 (0.7414)	loss 1.6577 (2.6710)	grad_norm 1.5176 (2.2498/0.8818)	mem 34604MB
[2025-01-19 18:37:50 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][290/312]	eta 0:00:16 lr 0.000286	time 0.8129 (0.7545)	model_time 0.8124 (0.7491)	loss 3.0444 (2.6987)	grad_norm 1.5252 (2.4505/1.0690)	mem 34602MB
[2025-01-19 18:37:52 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][310/312]	eta 0:00:01 lr 0.000285	time 0.7131 (0.7468)	model_time 0.7130 (0.7417)	loss 2.6051 (2.6754)	grad_norm 2.6542 (2.2381/0.8802)	mem 34604MB
[2025-01-19 18:37:53 internimage_b_1k_224] (main.py 519): INFO EPOCH 251 training takes 0:03:52
[2025-01-19 18:37:53 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_251.pth saving......
[2025-01-19 18:37:56 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_251.pth saved !!!
[2025-01-19 18:37:58 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][300/312]	eta 0:00:09 lr 0.000285	time 0.7999 (0.7547)	model_time 0.7998 (0.7495)	loss 2.7794 (2.6927)	grad_norm 2.1541 (2.4515/1.0666)	mem 34602MB
[2025-01-19 18:38:04 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.229 (7.229)	Loss 0.7111 (0.7111)	Acc@1 86.279 (86.279)	Acc@5 98.022 (98.022)	Mem 34604MB
[2025-01-19 18:38:05 internimage_b_1k_224] (main.py 510): INFO Train: [251/300][310/312]	eta 0:00:01 lr 0.000285	time 0.7972 (0.7542)	model_time 0.7971 (0.7491)	loss 1.9223 (2.6934)	grad_norm 2.2224 (2.4697/1.0748)	mem 34602MB
[2025-01-19 18:38:06 internimage_b_1k_224] (main.py 519): INFO EPOCH 251 training takes 0:03:55
[2025-01-19 18:38:06 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_251.pth saving......
[2025-01-19 18:38:07 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.928)	Loss 0.9067 (0.7942)	Acc@1 81.323 (84.488)	Acc@5 95.923 (96.933)	Mem 34604MB
[2025-01-19 18:38:07 internimage_b_1k_224] (main.py 575): INFO [Epoch:251] * Acc@1 84.303 Acc@5 96.949
[2025-01-19 18:38:07 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.3%
[2025-01-19 18:38:07 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 18:38:09 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_251.pth saved !!!
[2025-01-19 18:38:10 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 18:38:10 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.30%
[2025-01-19 18:38:25 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.596 (15.596)	Loss 0.6911 (0.6911)	Acc@1 86.255 (86.255)	Acc@5 97.827 (97.827)	Mem 34602MB
[2025-01-19 18:38:26 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.953 (15.953)	Loss 0.7125 (0.7125)	Acc@1 86.548 (86.548)	Acc@5 98.120 (98.120)	Mem 34604MB
[2025-01-19 18:38:32 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (2.073)	Loss 0.8868 (0.7716)	Acc@1 80.908 (84.242)	Acc@5 96.094 (96.953)	Mem 34602MB
[2025-01-19 18:38:32 internimage_b_1k_224] (main.py 575): INFO [Epoch:251] * Acc@1 84.057 Acc@5 96.941
[2025-01-19 18:38:32 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 18:38:32 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.10%
[2025-01-19 18:38:32 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.027)	Loss 0.9228 (0.8038)	Acc@1 80.884 (84.371)	Acc@5 95.923 (96.948)	Mem 34604MB
[2025-01-19 18:38:33 internimage_b_1k_224] (main.py 575): INFO [Epoch:251] * Acc@1 84.213 Acc@5 96.991
[2025-01-19 18:38:33 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.2%
[2025-01-19 18:38:33 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:38:36 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:38:36 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.21%
[2025-01-19 18:38:39 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][0/312]	eta 0:10:44 lr 0.000285	time 2.0668 (2.0668)	model_time 0.7280 (0.7280)	loss 2.1032 (2.1032)	grad_norm 4.1237 (4.1237/0.0000)	mem 34604MB
[2025-01-19 18:38:41 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.220 (9.220)	Loss 0.7217 (0.7217)	Acc@1 86.255 (86.255)	Acc@5 98.193 (98.193)	Mem 34602MB
[2025-01-19 18:38:46 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.252)	Loss 0.9215 (0.8045)	Acc@1 80.298 (84.302)	Acc@5 96.265 (97.028)	Mem 34602MB
[2025-01-19 18:38:46 internimage_b_1k_224] (main.py 575): INFO [Epoch:251] * Acc@1 84.117 Acc@5 97.059
[2025-01-19 18:38:46 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.1%
[2025-01-19 18:38:46 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:38:46 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][10/312]	eta 0:04:26 lr 0.000285	time 0.7210 (0.8817)	model_time 0.7206 (0.7596)	loss 2.5458 (2.5623)	grad_norm 2.2543 (2.5370/0.8402)	mem 34604MB
[2025-01-19 18:38:50 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:38:50 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.12%
[2025-01-19 18:38:52 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][0/312]	eta 0:10:43 lr 0.000285	time 2.0609 (2.0609)	model_time 0.7569 (0.7569)	loss 2.1516 (2.1516)	grad_norm 1.9348 (1.9348/0.0000)	mem 34602MB
[2025-01-19 18:38:54 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][20/312]	eta 0:04:02 lr 0.000284	time 0.8080 (0.8300)	model_time 0.8079 (0.7659)	loss 2.2405 (2.5802)	grad_norm 1.8681 (2.2302/0.7703)	mem 34604MB
[2025-01-19 18:38:59 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][10/312]	eta 0:04:16 lr 0.000285	time 0.7112 (0.8509)	model_time 0.7110 (0.7320)	loss 3.0634 (2.7317)	grad_norm 4.1060 (1.9078/0.8512)	mem 34602MB
[2025-01-19 18:39:02 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][30/312]	eta 0:03:49 lr 0.000284	time 0.8062 (0.8135)	model_time 0.8057 (0.7700)	loss 2.0651 (2.6364)	grad_norm 1.5186 (2.2164/0.7269)	mem 34604MB
[2025-01-19 18:39:07 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][20/312]	eta 0:03:54 lr 0.000284	time 0.7256 (0.8046)	model_time 0.7254 (0.7422)	loss 1.9052 (2.6707)	grad_norm 3.1788 (2.1612/1.0473)	mem 34602MB
[2025-01-19 18:39:09 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][40/312]	eta 0:03:37 lr 0.000284	time 0.7291 (0.7986)	model_time 0.7290 (0.7656)	loss 2.9747 (2.6576)	grad_norm 0.9738 (2.3378/0.8185)	mem 34604MB
[2025-01-19 18:39:14 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][30/312]	eta 0:03:41 lr 0.000284	time 0.7273 (0.7837)	model_time 0.7268 (0.7413)	loss 2.5709 (2.7444)	grad_norm 4.4254 (2.4938/1.3418)	mem 34602MB
[2025-01-19 18:39:17 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][50/312]	eta 0:03:26 lr 0.000283	time 0.7314 (0.7863)	model_time 0.7310 (0.7597)	loss 3.5830 (2.6587)	grad_norm 3.6962 (2.5031/0.8681)	mem 34604MB
[2025-01-19 18:39:22 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][40/312]	eta 0:03:31 lr 0.000284	time 0.7167 (0.7786)	model_time 0.7165 (0.7465)	loss 3.2330 (2.7801)	grad_norm 1.3236 (2.3548/1.3334)	mem 34602MB
[2025-01-19 18:39:24 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][60/312]	eta 0:03:15 lr 0.000283	time 0.7370 (0.7764)	model_time 0.7366 (0.7541)	loss 2.2866 (2.6845)	grad_norm 1.7826 (2.4631/0.9297)	mem 34604MB
[2025-01-19 18:39:29 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][50/312]	eta 0:03:21 lr 0.000283	time 0.8140 (0.7702)	model_time 0.8138 (0.7443)	loss 2.6107 (2.7486)	grad_norm 1.4544 (2.2828/1.2743)	mem 34602MB
[2025-01-19 18:39:31 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][70/312]	eta 0:03:06 lr 0.000283	time 0.7162 (0.7707)	model_time 0.7160 (0.7515)	loss 2.4889 (2.6915)	grad_norm 2.9207 (2.5571/0.9961)	mem 34604MB
[2025-01-19 18:39:37 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][60/312]	eta 0:03:13 lr 0.000283	time 0.7179 (0.7662)	model_time 0.7173 (0.7445)	loss 2.5594 (2.7705)	grad_norm 2.3743 (2.2132/1.1917)	mem 34602MB
[2025-01-19 18:39:38 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][80/312]	eta 0:02:57 lr 0.000282	time 0.7481 (0.7654)	model_time 0.7480 (0.7486)	loss 2.9335 (2.6731)	grad_norm 1.0008 (2.5301/1.0085)	mem 34604MB
[2025-01-19 18:39:44 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][70/312]	eta 0:03:05 lr 0.000283	time 0.7228 (0.7646)	model_time 0.7227 (0.7459)	loss 3.1139 (2.7476)	grad_norm 1.5715 (2.1465/1.1486)	mem 34602MB
[2025-01-19 18:39:46 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][90/312]	eta 0:02:48 lr 0.000282	time 0.7418 (0.7611)	model_time 0.7413 (0.7460)	loss 3.1709 (2.6876)	grad_norm 1.9681 (2.4908/0.9701)	mem 34604MB
[2025-01-19 18:39:52 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][80/312]	eta 0:02:56 lr 0.000282	time 0.7243 (0.7618)	model_time 0.7239 (0.7453)	loss 2.7532 (2.7650)	grad_norm 1.4104 (2.1057/1.0955)	mem 34602MB
[2025-01-19 18:39:53 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][100/312]	eta 0:02:40 lr 0.000282	time 0.7454 (0.7582)	model_time 0.7449 (0.7446)	loss 2.8224 (2.6638)	grad_norm 3.4016 (2.4927/0.9641)	mem 34604MB
[2025-01-19 18:39:59 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][90/312]	eta 0:02:48 lr 0.000282	time 0.7295 (0.7578)	model_time 0.7294 (0.7431)	loss 2.2690 (2.7460)	grad_norm 1.8104 (2.1203/1.0692)	mem 34602MB
[2025-01-19 18:40:00 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][110/312]	eta 0:02:32 lr 0.000281	time 0.7187 (0.7564)	model_time 0.7182 (0.7439)	loss 2.6202 (2.6653)	grad_norm 2.1774 (2.5208/0.9622)	mem 34604MB
[2025-01-19 18:40:06 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][100/312]	eta 0:02:40 lr 0.000282	time 0.7568 (0.7580)	model_time 0.7563 (0.7447)	loss 3.5360 (2.7510)	grad_norm 1.7190 (2.1318/1.0405)	mem 34602MB
[2025-01-19 18:40:08 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][120/312]	eta 0:02:25 lr 0.000281	time 0.7339 (0.7575)	model_time 0.7334 (0.7460)	loss 2.4187 (2.6628)	grad_norm 1.7231 (2.5302/0.9726)	mem 34604MB
[2025-01-19 18:40:14 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][110/312]	eta 0:02:33 lr 0.000281	time 0.7597 (0.7580)	model_time 0.7595 (0.7459)	loss 3.1640 (2.7495)	grad_norm 2.4930 (2.1027/1.0045)	mem 34602MB
[2025-01-19 18:40:16 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][130/312]	eta 0:02:17 lr 0.000281	time 0.7182 (0.7580)	model_time 0.7181 (0.7474)	loss 2.9200 (2.6850)	grad_norm 2.8220 (2.5373/0.9856)	mem 34604MB
[2025-01-19 18:40:22 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][120/312]	eta 0:02:25 lr 0.000281	time 0.7220 (0.7575)	model_time 0.7215 (0.7463)	loss 2.6574 (2.7428)	grad_norm 3.1913 (2.1481/0.9912)	mem 34602MB
[2025-01-19 18:40:24 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][140/312]	eta 0:02:10 lr 0.000280	time 0.8124 (0.7593)	model_time 0.8120 (0.7494)	loss 2.8289 (2.6728)	grad_norm 2.8805 (2.4978/0.9731)	mem 34604MB
[2025-01-19 18:40:29 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][130/312]	eta 0:02:17 lr 0.000281	time 0.7267 (0.7567)	model_time 0.7265 (0.7464)	loss 2.0921 (2.7427)	grad_norm 1.5866 (2.1732/0.9712)	mem 34602MB
[2025-01-19 18:40:31 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][150/312]	eta 0:02:03 lr 0.000280	time 0.8119 (0.7600)	model_time 0.8115 (0.7508)	loss 2.8600 (2.6779)	grad_norm 1.3923 (2.5177/0.9773)	mem 34604MB
[2025-01-19 18:40:37 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][140/312]	eta 0:02:10 lr 0.000280	time 0.7178 (0.7563)	model_time 0.7174 (0.7467)	loss 3.1081 (2.7397)	grad_norm 1.5885 (2.1753/0.9526)	mem 34602MB
[2025-01-19 18:40:39 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][160/312]	eta 0:01:55 lr 0.000280	time 0.7182 (0.7598)	model_time 0.7180 (0.7511)	loss 1.7424 (2.6778)	grad_norm 2.0484 (2.4917/0.9587)	mem 34604MB
[2025-01-19 18:40:44 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][150/312]	eta 0:02:02 lr 0.000280	time 0.7150 (0.7552)	model_time 0.7148 (0.7462)	loss 1.7286 (2.7238)	grad_norm 2.2881 (2.1615/0.9408)	mem 34602MB
[2025-01-19 18:40:46 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][170/312]	eta 0:01:47 lr 0.000279	time 0.7184 (0.7584)	model_time 0.7183 (0.7502)	loss 3.2581 (2.6677)	grad_norm 1.9744 (2.5156/0.9628)	mem 34604MB
[2025-01-19 18:40:52 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][160/312]	eta 0:01:54 lr 0.000280	time 0.7269 (0.7558)	model_time 0.7264 (0.7473)	loss 2.1321 (2.7127)	grad_norm 2.9097 (2.2003/0.9559)	mem 34602MB
[2025-01-19 18:40:53 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][180/312]	eta 0:01:39 lr 0.000279	time 0.7277 (0.7570)	model_time 0.7275 (0.7492)	loss 2.6811 (2.6786)	grad_norm 1.6350 (2.4662/0.9652)	mem 34604MB
[2025-01-19 18:40:59 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][170/312]	eta 0:01:47 lr 0.000279	time 0.8122 (0.7545)	model_time 0.8120 (0.7465)	loss 2.9201 (2.7016)	grad_norm 2.7463 (2.2137/0.9441)	mem 34602MB
[2025-01-19 18:41:01 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][190/312]	eta 0:01:32 lr 0.000279	time 0.7221 (0.7558)	model_time 0.7217 (0.7484)	loss 1.8009 (2.6584)	grad_norm 1.4957 (2.4517/0.9550)	mem 34604MB
[2025-01-19 18:41:06 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][180/312]	eta 0:01:39 lr 0.000279	time 0.7270 (0.7534)	model_time 0.7264 (0.7459)	loss 2.6151 (2.6863)	grad_norm 2.2450 (2.2082/0.9331)	mem 34602MB
[2025-01-19 18:41:08 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][200/312]	eta 0:01:24 lr 0.000279	time 0.7591 (0.7551)	model_time 0.7589 (0.7481)	loss 2.9792 (2.6579)	grad_norm 1.9184 (2.4452/0.9576)	mem 34604MB
[2025-01-19 18:41:14 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][190/312]	eta 0:01:31 lr 0.000279	time 0.7968 (0.7535)	model_time 0.7964 (0.7464)	loss 1.6591 (2.6882)	grad_norm 1.1322 (2.1816/0.9227)	mem 34602MB
[2025-01-19 18:41:16 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][210/312]	eta 0:01:16 lr 0.000278	time 0.7175 (0.7538)	model_time 0.7171 (0.7471)	loss 2.7236 (2.6598)	grad_norm 2.0026 (2.4666/0.9803)	mem 34604MB
[2025-01-19 18:41:21 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][200/312]	eta 0:01:24 lr 0.000279	time 0.7449 (0.7525)	model_time 0.7447 (0.7457)	loss 2.9459 (2.6839)	grad_norm 1.4725 (2.1714/0.9102)	mem 34602MB
[2025-01-19 18:41:23 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][220/312]	eta 0:01:09 lr 0.000278	time 0.7280 (0.7528)	model_time 0.7279 (0.7464)	loss 2.9648 (2.6464)	grad_norm 1.3256 (2.4390/0.9831)	mem 34604MB
[2025-01-19 18:41:28 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][210/312]	eta 0:01:16 lr 0.000278	time 0.7178 (0.7515)	model_time 0.7177 (0.7449)	loss 2.6972 (2.6848)	grad_norm 1.3052 (2.1648/0.9113)	mem 34602MB
[2025-01-19 18:41:30 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][230/312]	eta 0:01:01 lr 0.000278	time 0.7245 (0.7518)	model_time 0.7240 (0.7457)	loss 3.0948 (2.6565)	grad_norm 3.0596 (2.4490/0.9882)	mem 34604MB
[2025-01-19 18:41:36 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][220/312]	eta 0:01:09 lr 0.000278	time 0.7188 (0.7514)	model_time 0.7184 (0.7451)	loss 3.1311 (2.6897)	grad_norm 2.5305 (2.1520/0.8955)	mem 34602MB
[2025-01-19 18:41:38 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][240/312]	eta 0:00:54 lr 0.000277	time 0.7916 (0.7524)	model_time 0.7912 (0.7464)	loss 2.7894 (2.6551)	grad_norm 4.7234 (2.4647/0.9928)	mem 34604MB
[2025-01-19 18:41:44 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][230/312]	eta 0:01:01 lr 0.000278	time 0.7161 (0.7524)	model_time 0.7157 (0.7464)	loss 2.0030 (2.6880)	grad_norm 1.3513 (2.1319/0.8832)	mem 34602MB
[2025-01-19 18:41:45 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][250/312]	eta 0:00:46 lr 0.000277	time 0.8339 (0.7527)	model_time 0.8337 (0.7470)	loss 2.3709 (2.6530)	grad_norm 2.6551 (2.4635/0.9888)	mem 34604MB
[2025-01-19 18:41:51 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][240/312]	eta 0:00:54 lr 0.000277	time 0.7207 (0.7524)	model_time 0.7206 (0.7466)	loss 2.8598 (2.6905)	grad_norm 1.2324 (2.1280/0.8787)	mem 34602MB
[2025-01-19 18:41:53 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][260/312]	eta 0:00:39 lr 0.000277	time 0.8244 (0.7534)	model_time 0.8243 (0.7478)	loss 3.0298 (2.6517)	grad_norm 1.8071 (2.4738/1.0076)	mem 34604MB
[2025-01-19 18:41:59 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][250/312]	eta 0:00:46 lr 0.000277	time 0.7281 (0.7524)	model_time 0.7279 (0.7469)	loss 1.9786 (2.6901)	grad_norm 1.7316 (2.1140/0.8703)	mem 34602MB
[2025-01-19 18:42:01 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][270/312]	eta 0:00:31 lr 0.000276	time 0.8079 (0.7543)	model_time 0.8077 (0.7490)	loss 2.9376 (2.6571)	grad_norm 1.6762 (2.4556/0.9963)	mem 34604MB
[2025-01-19 18:42:06 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][260/312]	eta 0:00:39 lr 0.000277	time 0.7234 (0.7523)	model_time 0.7230 (0.7469)	loss 2.7065 (2.6913)	grad_norm 3.7637 (2.1387/0.8982)	mem 34602MB
[2025-01-19 18:42:08 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][280/312]	eta 0:00:24 lr 0.000276	time 0.7301 (0.7546)	model_time 0.7296 (0.7494)	loss 2.8189 (2.6638)	grad_norm 1.1079 (2.4421/0.9951)	mem 34604MB
[2025-01-19 18:42:14 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][270/312]	eta 0:00:31 lr 0.000276	time 0.7198 (0.7520)	model_time 0.7196 (0.7468)	loss 2.8170 (2.6829)	grad_norm 3.3457 (2.1650/0.9123)	mem 34602MB
[2025-01-19 18:42:16 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][290/312]	eta 0:00:16 lr 0.000276	time 0.7280 (0.7540)	model_time 0.7278 (0.7490)	loss 2.8546 (2.6663)	grad_norm 2.0334 (2.4369/0.9965)	mem 34604MB
[2025-01-19 18:42:21 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][280/312]	eta 0:00:24 lr 0.000276	time 0.8020 (0.7521)	model_time 0.8019 (0.7471)	loss 2.6470 (2.6888)	grad_norm 2.4896 (2.2160/0.9723)	mem 34602MB
[2025-01-19 18:42:23 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][300/312]	eta 0:00:09 lr 0.000275	time 0.7166 (0.7529)	model_time 0.7165 (0.7480)	loss 2.2193 (2.6722)	grad_norm 2.2080 (2.4167/0.9830)	mem 34604MB
[2025-01-19 18:42:29 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][290/312]	eta 0:00:16 lr 0.000276	time 0.7264 (0.7517)	model_time 0.7263 (0.7469)	loss 2.2377 (2.6908)	grad_norm 3.1083 (2.2252/0.9759)	mem 34602MB
[2025-01-19 18:42:30 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][310/312]	eta 0:00:01 lr 0.000275	time 0.7138 (0.7519)	model_time 0.7136 (0.7473)	loss 2.8865 (2.6738)	grad_norm 1.8455 (2.4211/0.9854)	mem 34604MB
[2025-01-19 18:42:31 internimage_b_1k_224] (main.py 519): INFO EPOCH 252 training takes 0:03:54
[2025-01-19 18:42:31 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_252.pth saving......
[2025-01-19 18:42:34 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_252.pth saved !!!
[2025-01-19 18:42:36 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][300/312]	eta 0:00:09 lr 0.000275	time 0.7187 (0.7509)	model_time 0.7186 (0.7462)	loss 2.9512 (2.6995)	grad_norm 2.7942 (2.2257/0.9715)	mem 34602MB
[2025-01-19 18:42:42 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.229 (7.229)	Loss 0.7018 (0.7018)	Acc@1 86.108 (86.108)	Acc@5 97.974 (97.974)	Mem 34604MB
[2025-01-19 18:42:43 internimage_b_1k_224] (main.py 510): INFO Train: [252/300][310/312]	eta 0:00:01 lr 0.000275	time 0.7272 (0.7508)	model_time 0.7270 (0.7463)	loss 2.7665 (2.6935)	grad_norm 1.3237 (2.2540/0.9850)	mem 34602MB
[2025-01-19 18:42:44 internimage_b_1k_224] (main.py 519): INFO EPOCH 252 training takes 0:03:54
[2025-01-19 18:42:44 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_252.pth saving......
[2025-01-19 18:42:45 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.964)	Loss 0.9084 (0.7913)	Acc@1 81.201 (84.393)	Acc@5 95.850 (96.908)	Mem 34604MB
[2025-01-19 18:42:45 internimage_b_1k_224] (main.py 575): INFO [Epoch:252] * Acc@1 84.225 Acc@5 96.907
[2025-01-19 18:42:45 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.2%
[2025-01-19 18:42:45 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.30%
[2025-01-19 18:42:47 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_252.pth saved !!!
[2025-01-19 18:43:05 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 19.699 (19.699)	Loss 0.7125 (0.7125)	Acc@1 86.572 (86.572)	Acc@5 98.120 (98.120)	Mem 34604MB
[2025-01-19 18:43:05 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.696 (17.696)	Loss 0.7224 (0.7224)	Acc@1 85.547 (85.547)	Acc@5 97.900 (97.900)	Mem 34602MB
[2025-01-19 18:43:12 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.183 (2.250)	Loss 0.9152 (0.7918)	Acc@1 80.591 (84.233)	Acc@5 95.996 (96.950)	Mem 34602MB
[2025-01-19 18:43:12 internimage_b_1k_224] (main.py 575): INFO [Epoch:252] * Acc@1 84.067 Acc@5 96.967
[2025-01-19 18:43:12 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 18:43:12 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.10%
[2025-01-19 18:43:13 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (2.515)	Loss 0.9220 (0.8034)	Acc@1 80.957 (84.397)	Acc@5 95.947 (96.953)	Mem 34604MB
[2025-01-19 18:43:13 internimage_b_1k_224] (main.py 575): INFO [Epoch:252] * Acc@1 84.233 Acc@5 96.991
[2025-01-19 18:43:13 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.2%
[2025-01-19 18:43:13 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:43:17 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:43:17 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.23%
[2025-01-19 18:43:19 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][0/312]	eta 0:11:10 lr 0.000275	time 2.1495 (2.1495)	model_time 0.7359 (0.7359)	loss 2.9251 (2.9251)	grad_norm 1.7619 (1.7619/0.0000)	mem 34604MB
[2025-01-19 18:43:22 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.308 (9.308)	Loss 0.7217 (0.7217)	Acc@1 86.255 (86.255)	Acc@5 98.193 (98.193)	Mem 34602MB
[2025-01-19 18:43:26 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.247)	Loss 0.9208 (0.8040)	Acc@1 80.347 (84.348)	Acc@5 96.289 (97.035)	Mem 34602MB
[2025-01-19 18:43:26 internimage_b_1k_224] (main.py 575): INFO [Epoch:252] * Acc@1 84.159 Acc@5 97.065
[2025-01-19 18:43:26 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.2%
[2025-01-19 18:43:26 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][10/312]	eta 0:04:18 lr 0.000275	time 0.7128 (0.8559)	model_time 0.7127 (0.7271)	loss 2.2592 (2.7902)	grad_norm 2.3454 (2.5346/0.8422)	mem 34604MB
[2025-01-19 18:43:27 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:43:30 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:43:30 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.16%
[2025-01-19 18:43:33 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][0/312]	eta 0:11:01 lr 0.000275	time 2.1190 (2.1190)	model_time 0.7415 (0.7415)	loss 2.9480 (2.9480)	grad_norm 2.1511 (2.1511/0.0000)	mem 34602MB
[2025-01-19 18:43:34 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][20/312]	eta 0:03:52 lr 0.000274	time 0.7392 (0.7960)	model_time 0.7388 (0.7284)	loss 2.0493 (2.6149)	grad_norm 3.9363 (2.3823/0.7889)	mem 34604MB
[2025-01-19 18:43:40 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][10/312]	eta 0:04:21 lr 0.000275	time 0.7197 (0.8660)	model_time 0.7196 (0.7404)	loss 2.4270 (2.6806)	grad_norm 2.3234 (2.1125/0.9283)	mem 34602MB
[2025-01-19 18:43:41 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][30/312]	eta 0:03:38 lr 0.000274	time 0.7203 (0.7735)	model_time 0.7202 (0.7276)	loss 2.9238 (2.6033)	grad_norm 4.7432 (2.8498/1.2279)	mem 34604MB
[2025-01-19 18:43:47 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][20/312]	eta 0:03:53 lr 0.000274	time 0.7352 (0.8011)	model_time 0.7350 (0.7351)	loss 2.3737 (2.7410)	grad_norm 2.6021 (2.1546/0.9567)	mem 34602MB
[2025-01-19 18:43:48 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][40/312]	eta 0:03:27 lr 0.000274	time 0.7210 (0.7630)	model_time 0.7209 (0.7282)	loss 2.8510 (2.6675)	grad_norm 1.7859 (2.8873/1.1882)	mem 34604MB
[2025-01-19 18:43:55 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][30/312]	eta 0:03:44 lr 0.000274	time 0.9709 (0.7949)	model_time 0.9703 (0.7501)	loss 2.3929 (2.6762)	grad_norm 2.7216 (2.3078/0.8467)	mem 34602MB
[2025-01-19 18:43:56 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][50/312]	eta 0:03:20 lr 0.000273	time 0.8423 (0.7671)	model_time 0.8421 (0.7390)	loss 2.9013 (2.6948)	grad_norm 1.0751 (2.8101/1.2585)	mem 34604MB
[2025-01-19 18:44:03 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][40/312]	eta 0:03:33 lr 0.000274	time 0.7263 (0.7855)	model_time 0.7259 (0.7516)	loss 2.3708 (2.5800)	grad_norm 1.1649 (2.4037/1.1489)	mem 34602MB
[2025-01-19 18:44:04 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][60/312]	eta 0:03:12 lr 0.000273	time 0.7749 (0.7627)	model_time 0.7747 (0.7392)	loss 2.8177 (2.7163)	grad_norm 3.9026 (2.8458/1.2072)	mem 34604MB
[2025-01-19 18:44:10 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][50/312]	eta 0:03:24 lr 0.000273	time 0.8068 (0.7798)	model_time 0.8066 (0.7524)	loss 3.0217 (2.6384)	grad_norm 3.3707 (2.4738/1.1655)	mem 34602MB
[2025-01-19 18:44:11 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][70/312]	eta 0:03:04 lr 0.000273	time 0.8390 (0.7631)	model_time 0.8389 (0.7428)	loss 2.3374 (2.7195)	grad_norm 2.5296 (2.8325/1.2504)	mem 34604MB
[2025-01-19 18:44:18 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][60/312]	eta 0:03:15 lr 0.000273	time 0.7205 (0.7752)	model_time 0.7203 (0.7522)	loss 2.6906 (2.6432)	grad_norm 2.4054 (2.3921/1.0947)	mem 34602MB
[2025-01-19 18:44:19 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][80/312]	eta 0:02:57 lr 0.000273	time 0.7289 (0.7650)	model_time 0.7285 (0.7472)	loss 2.9973 (2.7247)	grad_norm 2.4462 (2.7831/1.2129)	mem 34604MB
[2025-01-19 18:44:25 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][70/312]	eta 0:03:06 lr 0.000273	time 0.8113 (0.7712)	model_time 0.8108 (0.7515)	loss 2.8525 (2.6565)	grad_norm 1.6489 (2.4162/1.1018)	mem 34602MB
[2025-01-19 18:44:27 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][90/312]	eta 0:02:49 lr 0.000272	time 0.7240 (0.7643)	model_time 0.7238 (0.7485)	loss 2.8468 (2.7397)	grad_norm 3.8368 (2.8179/1.2224)	mem 34604MB
[2025-01-19 18:44:33 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][80/312]	eta 0:02:58 lr 0.000273	time 0.7211 (0.7675)	model_time 0.7209 (0.7501)	loss 2.8960 (2.6630)	grad_norm 1.6967 (2.3753/1.0739)	mem 34602MB
[2025-01-19 18:44:34 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][100/312]	eta 0:02:41 lr 0.000272	time 0.7158 (0.7621)	model_time 0.7157 (0.7478)	loss 3.0939 (2.7111)	grad_norm 2.3914 (2.8249/1.2013)	mem 34604MB
[2025-01-19 18:44:40 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][90/312]	eta 0:02:50 lr 0.000272	time 0.7171 (0.7670)	model_time 0.7169 (0.7516)	loss 3.1507 (2.6777)	grad_norm 2.7711 (2.3426/1.0359)	mem 34602MB
[2025-01-19 18:44:41 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][110/312]	eta 0:02:33 lr 0.000272	time 0.7220 (0.7591)	model_time 0.7215 (0.7460)	loss 2.8397 (2.7006)	grad_norm 1.7923 (2.7916/1.1784)	mem 34604MB
[2025-01-19 18:44:48 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][100/312]	eta 0:02:41 lr 0.000272	time 0.7158 (0.7636)	model_time 0.7157 (0.7496)	loss 2.7367 (2.6681)	grad_norm 1.9035 (2.3580/1.0046)	mem 34602MB
[2025-01-19 18:44:49 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][120/312]	eta 0:02:25 lr 0.000271	time 0.7315 (0.7575)	model_time 0.7313 (0.7455)	loss 2.7153 (2.6994)	grad_norm 1.5367 (2.7480/1.1515)	mem 34604MB
[2025-01-19 18:44:55 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][110/312]	eta 0:02:33 lr 0.000272	time 0.8093 (0.7614)	model_time 0.8092 (0.7486)	loss 2.5665 (2.6764)	grad_norm 1.4084 (2.3452/0.9839)	mem 34602MB
[2025-01-19 18:44:56 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][130/312]	eta 0:02:17 lr 0.000271	time 0.7157 (0.7550)	model_time 0.7153 (0.7439)	loss 3.1093 (2.7091)	grad_norm 3.9965 (2.7475/1.1175)	mem 34604MB
[2025-01-19 18:45:02 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][120/312]	eta 0:02:25 lr 0.000271	time 0.7416 (0.7602)	model_time 0.7412 (0.7484)	loss 2.6289 (2.6637)	grad_norm 1.4025 (2.3032/0.9627)	mem 34602MB
[2025-01-19 18:45:03 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][140/312]	eta 0:02:09 lr 0.000271	time 0.7191 (0.7529)	model_time 0.7190 (0.7425)	loss 2.0709 (2.7027)	grad_norm 3.0399 (2.7470/1.1137)	mem 34604MB
[2025-01-19 18:45:10 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][130/312]	eta 0:02:18 lr 0.000271	time 0.7266 (0.7596)	model_time 0.7264 (0.7488)	loss 2.7511 (2.6812)	grad_norm 2.4641 (2.2792/0.9419)	mem 34602MB
[2025-01-19 18:45:10 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][150/312]	eta 0:02:01 lr 0.000270	time 0.7213 (0.7511)	model_time 0.7212 (0.7414)	loss 2.7235 (2.6955)	grad_norm 1.4630 (2.7182/1.1126)	mem 34604MB
[2025-01-19 18:45:17 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][140/312]	eta 0:02:10 lr 0.000271	time 0.7174 (0.7571)	model_time 0.7169 (0.7470)	loss 2.7714 (2.6790)	grad_norm 2.0560 (2.2656/0.9166)	mem 34602MB
[2025-01-19 18:45:18 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][160/312]	eta 0:01:54 lr 0.000270	time 0.7090 (0.7504)	model_time 0.7085 (0.7413)	loss 2.9722 (2.7075)	grad_norm 1.4545 (2.6814/1.0996)	mem 34604MB
[2025-01-19 18:45:25 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][150/312]	eta 0:02:02 lr 0.000270	time 0.8177 (0.7572)	model_time 0.8172 (0.7478)	loss 2.0278 (2.6686)	grad_norm 1.1780 (2.2477/0.8985)	mem 34602MB
[2025-01-19 18:45:26 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][170/312]	eta 0:01:46 lr 0.000270	time 0.8448 (0.7519)	model_time 0.8443 (0.7433)	loss 3.2217 (2.7165)	grad_norm 3.9844 (2.6549/1.0883)	mem 34604MB
[2025-01-19 18:45:32 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][160/312]	eta 0:01:55 lr 0.000270	time 0.7168 (0.7574)	model_time 0.7166 (0.7485)	loss 2.8555 (2.6668)	grad_norm 2.2512 (2.2525/0.9083)	mem 34602MB
[2025-01-19 18:45:33 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][180/312]	eta 0:01:39 lr 0.000269	time 0.7845 (0.7512)	model_time 0.7840 (0.7431)	loss 2.3697 (2.7165)	grad_norm 2.8839 (2.6548/1.1196)	mem 34604MB
[2025-01-19 18:45:40 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][170/312]	eta 0:01:47 lr 0.000270	time 0.8039 (0.7570)	model_time 0.8034 (0.7486)	loss 3.2456 (2.6597)	grad_norm 4.5756 (2.2692/0.9196)	mem 34602MB
[2025-01-19 18:45:41 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][190/312]	eta 0:01:31 lr 0.000269	time 0.7157 (0.7514)	model_time 0.7153 (0.7437)	loss 2.4341 (2.7032)	grad_norm 1.6823 (2.6137/1.1116)	mem 34604MB
[2025-01-19 18:45:47 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][180/312]	eta 0:01:39 lr 0.000269	time 0.7200 (0.7565)	model_time 0.7198 (0.7486)	loss 3.0817 (2.6508)	grad_norm 2.7351 (2.2557/0.9090)	mem 34602MB
[2025-01-19 18:45:48 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][200/312]	eta 0:01:24 lr 0.000269	time 0.8116 (0.7528)	model_time 0.8115 (0.7454)	loss 2.1957 (2.7054)	grad_norm 2.5189 (2.6035/1.0939)	mem 34604MB
[2025-01-19 18:45:55 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][190/312]	eta 0:01:32 lr 0.000269	time 0.8172 (0.7559)	model_time 0.8167 (0.7484)	loss 2.6365 (2.6562)	grad_norm 2.0909 (2.2538/0.8930)	mem 34602MB
[2025-01-19 18:45:56 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][210/312]	eta 0:01:16 lr 0.000268	time 0.7233 (0.7528)	model_time 0.7228 (0.7457)	loss 3.0264 (2.7000)	grad_norm 2.1569 (2.5692/1.0831)	mem 34604MB
[2025-01-19 18:46:02 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][200/312]	eta 0:01:24 lr 0.000269	time 0.7212 (0.7558)	model_time 0.7211 (0.7486)	loss 3.0255 (2.6645)	grad_norm 1.2052 (2.2616/0.8877)	mem 34602MB
[2025-01-19 18:46:03 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][220/312]	eta 0:01:09 lr 0.000268	time 0.7294 (0.7522)	model_time 0.7289 (0.7454)	loss 2.2385 (2.7016)	grad_norm 2.2510 (2.5468/1.0678)	mem 34604MB
[2025-01-19 18:46:10 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][210/312]	eta 0:01:17 lr 0.000268	time 0.7189 (0.7559)	model_time 0.7187 (0.7490)	loss 2.5330 (2.6562)	grad_norm 3.4194 (2.2891/0.9112)	mem 34602MB
[2025-01-19 18:46:11 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][230/312]	eta 0:01:01 lr 0.000268	time 0.7285 (0.7511)	model_time 0.7283 (0.7446)	loss 3.2132 (2.7022)	grad_norm 2.7804 (2.5441/1.0547)	mem 34604MB
[2025-01-19 18:46:17 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][220/312]	eta 0:01:09 lr 0.000268	time 0.7267 (0.7551)	model_time 0.7265 (0.7485)	loss 2.7404 (2.6593)	grad_norm 1.7596 (2.3238/0.9721)	mem 34602MB
[2025-01-19 18:46:18 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][240/312]	eta 0:00:54 lr 0.000268	time 0.7169 (0.7511)	model_time 0.7167 (0.7448)	loss 2.8072 (2.6989)	grad_norm 2.7420 (2.5346/1.0412)	mem 34604MB
[2025-01-19 18:46:25 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][230/312]	eta 0:01:01 lr 0.000268	time 0.8119 (0.7544)	model_time 0.8115 (0.7481)	loss 3.2992 (2.6669)	grad_norm 2.1643 (2.3410/0.9757)	mem 34602MB
[2025-01-19 18:46:25 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][250/312]	eta 0:00:46 lr 0.000267	time 0.7257 (0.7503)	model_time 0.7255 (0.7443)	loss 2.8919 (2.6970)	grad_norm 1.8210 (2.5066/1.0313)	mem 34604MB
[2025-01-19 18:46:32 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][240/312]	eta 0:00:54 lr 0.000268	time 0.7117 (0.7544)	model_time 0.7115 (0.7483)	loss 1.8618 (2.6683)	grad_norm 1.8778 (2.3262/0.9673)	mem 34602MB
[2025-01-19 18:46:33 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][260/312]	eta 0:00:38 lr 0.000267	time 0.7253 (0.7494)	model_time 0.7249 (0.7436)	loss 2.9918 (2.6982)	grad_norm 1.0791 (2.4911/1.0237)	mem 34604MB
[2025-01-19 18:46:40 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][250/312]	eta 0:00:46 lr 0.000267	time 0.7314 (0.7541)	model_time 0.7308 (0.7483)	loss 3.0198 (2.6697)	grad_norm 2.6459 (2.3547/0.9788)	mem 34602MB
[2025-01-19 18:46:40 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][270/312]	eta 0:00:31 lr 0.000267	time 0.7248 (0.7485)	model_time 0.7246 (0.7430)	loss 3.0456 (2.7031)	grad_norm 1.9683 (2.4745/1.0260)	mem 34604MB
[2025-01-19 18:46:47 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][260/312]	eta 0:00:39 lr 0.000267	time 0.7236 (0.7532)	model_time 0.7234 (0.7476)	loss 3.2306 (2.6732)	grad_norm 1.3845 (2.3443/0.9744)	mem 34602MB
[2025-01-19 18:46:47 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][280/312]	eta 0:00:23 lr 0.000266	time 0.7223 (0.7480)	model_time 0.7218 (0.7426)	loss 1.9690 (2.6962)	grad_norm 2.1318 (2.5232/1.0875)	mem 34604MB
[2025-01-19 18:46:55 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][270/312]	eta 0:00:31 lr 0.000267	time 0.8302 (0.7532)	model_time 0.8298 (0.7477)	loss 2.9713 (2.6754)	grad_norm 2.2901 (2.3172/0.9691)	mem 34602MB
[2025-01-19 18:46:55 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][290/312]	eta 0:00:16 lr 0.000266	time 0.8410 (0.7490)	model_time 0.8406 (0.7438)	loss 2.7376 (2.6980)	grad_norm 3.7775 (2.5341/1.0800)	mem 34604MB
[2025-01-19 18:47:02 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][280/312]	eta 0:00:24 lr 0.000266	time 0.7182 (0.7534)	model_time 0.7178 (0.7482)	loss 2.7445 (2.6775)	grad_norm 2.5207 (2.3093/0.9653)	mem 34602MB
[2025-01-19 18:47:02 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][300/312]	eta 0:00:08 lr 0.000266	time 0.7779 (0.7486)	model_time 0.7778 (0.7436)	loss 2.8169 (2.6889)	grad_norm 1.7415 (2.5284/1.0762)	mem 34604MB
[2025-01-19 18:47:10 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][290/312]	eta 0:00:16 lr 0.000266	time 0.8125 (0.7532)	model_time 0.8123 (0.7481)	loss 2.9423 (2.6877)	grad_norm 1.2280 (2.2849/0.9595)	mem 34602MB
[2025-01-19 18:47:10 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][310/312]	eta 0:00:01 lr 0.000265	time 0.7157 (0.7483)	model_time 0.7156 (0.7434)	loss 2.7818 (2.6840)	grad_norm 1.6174 (2.5342/1.1016)	mem 34604MB
[2025-01-19 18:47:10 internimage_b_1k_224] (main.py 519): INFO EPOCH 253 training takes 0:03:53
[2025-01-19 18:47:10 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_253.pth saving......
[2025-01-19 18:47:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_253.pth saved !!!
[2025-01-19 18:47:17 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][300/312]	eta 0:00:09 lr 0.000266	time 0.7049 (0.7529)	model_time 0.7048 (0.7480)	loss 1.9573 (2.6932)	grad_norm 1.7608 (2.2809/0.9527)	mem 34602MB
[2025-01-19 18:47:21 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.248 (7.248)	Loss 0.7088 (0.7088)	Acc@1 86.328 (86.328)	Acc@5 97.900 (97.900)	Mem 34604MB
[2025-01-19 18:47:24 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.939)	Loss 0.9090 (0.7912)	Acc@1 80.566 (84.482)	Acc@5 95.996 (96.953)	Mem 34604MB
[2025-01-19 18:47:24 internimage_b_1k_224] (main.py 575): INFO [Epoch:253] * Acc@1 84.265 Acc@5 96.943
[2025-01-19 18:47:24 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.3%
[2025-01-19 18:47:24 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.30%
[2025-01-19 18:47:24 internimage_b_1k_224] (main.py 510): INFO Train: [253/300][310/312]	eta 0:00:01 lr 0.000265	time 0.7098 (0.7520)	model_time 0.7097 (0.7472)	loss 2.8710 (2.7003)	grad_norm 1.8282 (2.2746/0.9443)	mem 34602MB
[2025-01-19 18:47:25 internimage_b_1k_224] (main.py 519): INFO EPOCH 253 training takes 0:03:54
[2025-01-19 18:47:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_253.pth saving......
[2025-01-19 18:47:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_253.pth saved !!!
[2025-01-19 18:47:42 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.684 (17.684)	Loss 0.7126 (0.7126)	Acc@1 86.572 (86.572)	Acc@5 98.120 (98.120)	Mem 34604MB
[2025-01-19 18:47:45 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.599 (16.599)	Loss 0.7041 (0.7041)	Acc@1 86.035 (86.035)	Acc@5 97.900 (97.900)	Mem 34602MB
[2025-01-19 18:47:51 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (2.433)	Loss 0.9211 (0.8030)	Acc@1 80.981 (84.424)	Acc@5 95.947 (96.962)	Mem 34604MB
[2025-01-19 18:47:51 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (2.081)	Loss 0.8897 (0.7778)	Acc@1 80.664 (84.226)	Acc@5 96.167 (96.939)	Mem 34602MB
[2025-01-19 18:47:51 internimage_b_1k_224] (main.py 575): INFO [Epoch:253] * Acc@1 84.255 Acc@5 96.999
[2025-01-19 18:47:51 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.3%
[2025-01-19 18:47:51 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:47:51 internimage_b_1k_224] (main.py 575): INFO [Epoch:253] * Acc@1 84.031 Acc@5 96.947
[2025-01-19 18:47:51 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.0%
[2025-01-19 18:47:51 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.10%
[2025-01-19 18:47:55 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:47:55 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.26%
[2025-01-19 18:47:58 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][0/312]	eta 0:11:06 lr 0.000265	time 2.1364 (2.1364)	model_time 0.7400 (0.7400)	loss 2.9452 (2.9452)	grad_norm 4.1184 (4.1184/0.0000)	mem 34604MB
[2025-01-19 18:48:01 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.341 (9.341)	Loss 0.7217 (0.7217)	Acc@1 86.255 (86.255)	Acc@5 98.193 (98.193)	Mem 34602MB
[2025-01-19 18:48:05 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.254)	Loss 0.9199 (0.8035)	Acc@1 80.371 (84.379)	Acc@5 96.240 (97.037)	Mem 34602MB
[2025-01-19 18:48:05 internimage_b_1k_224] (main.py 575): INFO [Epoch:253] * Acc@1 84.187 Acc@5 97.065
[2025-01-19 18:48:05 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.2%
[2025-01-19 18:48:05 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][10/312]	eta 0:04:34 lr 0.000265	time 0.7139 (0.9092)	model_time 0.7138 (0.7820)	loss 3.1552 (2.4612)	grad_norm 1.9362 (2.9241/0.9150)	mem 34604MB
[2025-01-19 18:48:05 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:48:09 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:48:09 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.19%
[2025-01-19 18:48:11 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][0/312]	eta 0:11:00 lr 0.000265	time 2.1182 (2.1182)	model_time 0.7474 (0.7474)	loss 3.2314 (3.2314)	grad_norm 1.8533 (1.8533/0.0000)	mem 34602MB
[2025-01-19 18:48:13 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][20/312]	eta 0:04:07 lr 0.000265	time 0.7266 (0.8464)	model_time 0.7264 (0.7796)	loss 2.9844 (2.5390)	grad_norm 2.6545 (2.7651/0.8980)	mem 34604MB
[2025-01-19 18:48:19 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][10/312]	eta 0:04:31 lr 0.000265	time 0.7968 (0.8994)	model_time 0.7963 (0.7744)	loss 2.1254 (2.8029)	grad_norm 2.6406 (3.6434/1.6652)	mem 34602MB
[2025-01-19 18:48:20 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][30/312]	eta 0:03:47 lr 0.000264	time 0.7260 (0.8085)	model_time 0.7258 (0.7631)	loss 2.9829 (2.5850)	grad_norm 3.2248 (2.5637/0.8827)	mem 34604MB
[2025-01-19 18:48:26 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][20/312]	eta 0:04:01 lr 0.000265	time 0.7233 (0.8267)	model_time 0.7231 (0.7611)	loss 2.9098 (2.7178)	grad_norm 3.2005 (3.1475/1.4992)	mem 34602MB
[2025-01-19 18:48:28 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][40/312]	eta 0:03:35 lr 0.000264	time 0.7498 (0.7911)	model_time 0.7497 (0.7567)	loss 2.9262 (2.6578)	grad_norm 3.2758 (2.5907/0.9087)	mem 34604MB
[2025-01-19 18:48:34 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][30/312]	eta 0:03:45 lr 0.000264	time 0.7214 (0.7984)	model_time 0.7209 (0.7538)	loss 2.9484 (2.7268)	grad_norm 1.1735 (2.7073/1.4545)	mem 34602MB
[2025-01-19 18:48:35 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][50/312]	eta 0:03:24 lr 0.000264	time 0.7152 (0.7796)	model_time 0.7150 (0.7519)	loss 2.7854 (2.6060)	grad_norm 1.1045 (2.4683/0.9001)	mem 34604MB
[2025-01-19 18:48:41 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][40/312]	eta 0:03:32 lr 0.000264	time 0.8127 (0.7826)	model_time 0.8125 (0.7488)	loss 2.8503 (2.7254)	grad_norm 2.8810 (2.5823/1.3657)	mem 34602MB
[2025-01-19 18:48:43 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][60/312]	eta 0:03:14 lr 0.000263	time 0.7536 (0.7730)	model_time 0.7532 (0.7498)	loss 3.0418 (2.6734)	grad_norm 2.1178 (2.3512/0.8766)	mem 34604MB
[2025-01-19 18:48:49 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][50/312]	eta 0:03:24 lr 0.000264	time 0.8032 (0.7824)	model_time 0.8031 (0.7551)	loss 3.0606 (2.6856)	grad_norm 1.2506 (2.5136/1.2882)	mem 34602MB
[2025-01-19 18:48:50 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][70/312]	eta 0:03:05 lr 0.000263	time 0.7260 (0.7670)	model_time 0.7258 (0.7470)	loss 3.3534 (2.7002)	grad_norm 1.3711 (2.2983/0.8734)	mem 34604MB
[2025-01-19 18:48:56 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][60/312]	eta 0:03:15 lr 0.000263	time 0.8093 (0.7742)	model_time 0.8087 (0.7514)	loss 3.1169 (2.7052)	grad_norm 1.4787 (2.6313/1.3058)	mem 34602MB
[2025-01-19 18:48:57 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][80/312]	eta 0:02:56 lr 0.000263	time 0.7204 (0.7615)	model_time 0.7202 (0.7440)	loss 2.7420 (2.7268)	grad_norm 1.5226 (2.2435/0.8535)	mem 34604MB
[2025-01-19 18:49:04 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][70/312]	eta 0:03:05 lr 0.000263	time 0.7203 (0.7675)	model_time 0.7199 (0.7478)	loss 3.2528 (2.7047)	grad_norm 5.0241 (2.7338/1.3178)	mem 34602MB
[2025-01-19 18:49:04 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][90/312]	eta 0:02:48 lr 0.000263	time 0.7196 (0.7591)	model_time 0.7195 (0.7434)	loss 2.7939 (2.7264)	grad_norm 3.9669 (2.2852/0.9028)	mem 34604MB
[2025-01-19 18:49:11 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][80/312]	eta 0:02:58 lr 0.000263	time 0.8152 (0.7673)	model_time 0.8150 (0.7501)	loss 2.6329 (2.7123)	grad_norm 2.5674 (2.7060/1.2677)	mem 34602MB
[2025-01-19 18:49:12 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][100/312]	eta 0:02:41 lr 0.000262	time 0.8526 (0.7601)	model_time 0.8521 (0.7459)	loss 2.8694 (2.7294)	grad_norm 2.0743 (2.3581/0.9549)	mem 34604MB
[2025-01-19 18:49:19 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][90/312]	eta 0:02:50 lr 0.000263	time 0.8110 (0.7666)	model_time 0.8109 (0.7512)	loss 3.1204 (2.7048)	grad_norm 2.5732 (2.7405/1.3156)	mem 34602MB
[2025-01-19 18:49:20 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][110/312]	eta 0:02:33 lr 0.000262	time 0.8800 (0.7598)	model_time 0.8795 (0.7469)	loss 2.8527 (2.7080)	grad_norm 2.4613 (2.4722/1.1365)	mem 34604MB
[2025-01-19 18:49:26 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][100/312]	eta 0:02:41 lr 0.000262	time 0.7227 (0.7641)	model_time 0.7225 (0.7502)	loss 2.9402 (2.7108)	grad_norm 3.9409 (2.7783/1.3212)	mem 34602MB
[2025-01-19 18:49:27 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][120/312]	eta 0:02:25 lr 0.000262	time 0.8146 (0.7590)	model_time 0.8144 (0.7471)	loss 2.8813 (2.7097)	grad_norm 2.8421 (2.4994/1.1162)	mem 34604MB
[2025-01-19 18:49:34 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][110/312]	eta 0:02:34 lr 0.000262	time 0.7376 (0.7635)	model_time 0.7375 (0.7508)	loss 3.0973 (2.7199)	grad_norm 2.6151 (2.7463/1.2743)	mem 34602MB
[2025-01-19 18:49:35 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][130/312]	eta 0:02:18 lr 0.000261	time 0.7233 (0.7607)	model_time 0.7229 (0.7497)	loss 2.6376 (2.7196)	grad_norm 3.3759 (2.4952/1.1017)	mem 34604MB
[2025-01-19 18:49:41 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][120/312]	eta 0:02:26 lr 0.000262	time 0.7180 (0.7610)	model_time 0.7178 (0.7493)	loss 2.2376 (2.7327)	grad_norm 1.9214 (2.6679/1.2558)	mem 34602MB
[2025-01-19 18:49:43 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][140/312]	eta 0:02:10 lr 0.000261	time 0.7152 (0.7611)	model_time 0.7150 (0.7508)	loss 3.0479 (2.7273)	grad_norm 1.5112 (2.4738/1.0818)	mem 34604MB
[2025-01-19 18:49:49 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][130/312]	eta 0:02:18 lr 0.000261	time 0.8132 (0.7616)	model_time 0.8129 (0.7508)	loss 2.5875 (2.7398)	grad_norm 1.1719 (2.5798/1.2481)	mem 34602MB
[2025-01-19 18:49:50 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][150/312]	eta 0:02:02 lr 0.000261	time 0.7221 (0.7590)	model_time 0.7216 (0.7494)	loss 2.5401 (2.7303)	grad_norm 2.4162 (2.4511/1.0621)	mem 34604MB
[2025-01-19 18:49:56 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][140/312]	eta 0:02:10 lr 0.000261	time 0.7169 (0.7600)	model_time 0.7165 (0.7500)	loss 2.0380 (2.7271)	grad_norm 1.0983 (2.5792/1.2292)	mem 34602MB
[2025-01-19 18:49:57 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][160/312]	eta 0:01:55 lr 0.000260	time 0.7260 (0.7573)	model_time 0.7259 (0.7483)	loss 3.0099 (2.7185)	grad_norm 1.0217 (2.4586/1.0751)	mem 34604MB
[2025-01-19 18:50:04 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][150/312]	eta 0:02:02 lr 0.000261	time 0.7246 (0.7581)	model_time 0.7245 (0.7486)	loss 2.4622 (2.7217)	grad_norm 1.5459 (2.5807/1.2095)	mem 34602MB
[2025-01-19 18:50:05 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][170/312]	eta 0:01:47 lr 0.000260	time 0.8074 (0.7564)	model_time 0.8072 (0.7479)	loss 2.7632 (2.7082)	grad_norm 6.2848 (2.5168/1.1308)	mem 34604MB
[2025-01-19 18:50:11 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][160/312]	eta 0:01:54 lr 0.000260	time 0.7946 (0.7565)	model_time 0.7944 (0.7476)	loss 1.8485 (2.7035)	grad_norm 3.1553 (2.5564/1.1998)	mem 34602MB
[2025-01-19 18:50:12 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][180/312]	eta 0:01:39 lr 0.000260	time 0.7273 (0.7550)	model_time 0.7271 (0.7469)	loss 3.0005 (2.7089)	grad_norm 4.5140 (2.5480/1.1177)	mem 34604MB
[2025-01-19 18:50:19 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][170/312]	eta 0:01:47 lr 0.000260	time 0.8062 (0.7570)	model_time 0.8061 (0.7486)	loss 3.0633 (2.7118)	grad_norm 1.2058 (2.5621/1.1783)	mem 34602MB
[2025-01-19 18:50:19 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][190/312]	eta 0:01:31 lr 0.000260	time 0.7220 (0.7535)	model_time 0.7218 (0.7459)	loss 2.2085 (2.7015)	grad_norm 2.0092 (2.5441/1.1220)	mem 34604MB
[2025-01-19 18:50:26 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][180/312]	eta 0:01:39 lr 0.000260	time 0.8062 (0.7562)	model_time 0.8059 (0.7482)	loss 3.0606 (2.7210)	grad_norm 5.5369 (2.6157/1.2062)	mem 34602MB
[2025-01-19 18:50:27 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][200/312]	eta 0:01:24 lr 0.000259	time 0.7219 (0.7523)	model_time 0.7218 (0.7450)	loss 2.8928 (2.7039)	grad_norm 3.6698 (2.5939/1.1646)	mem 34604MB
[2025-01-19 18:50:33 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][190/312]	eta 0:01:32 lr 0.000260	time 0.7547 (0.7550)	model_time 0.7546 (0.7474)	loss 2.4635 (2.7189)	grad_norm 1.4225 (2.6393/1.2155)	mem 34602MB
[2025-01-19 18:50:34 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][210/312]	eta 0:01:16 lr 0.000259	time 0.7698 (0.7519)	model_time 0.7694 (0.7450)	loss 3.0797 (2.7057)	grad_norm 3.1505 (2.6269/1.1689)	mem 34604MB
[2025-01-19 18:50:41 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][200/312]	eta 0:01:24 lr 0.000259	time 0.8195 (0.7566)	model_time 0.8193 (0.7494)	loss 2.2583 (2.7210)	grad_norm 2.2783 (2.6318/1.2007)	mem 34602MB
[2025-01-19 18:50:42 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][220/312]	eta 0:01:09 lr 0.000259	time 0.8106 (0.7529)	model_time 0.8102 (0.7462)	loss 3.2875 (2.7024)	grad_norm 2.9147 (2.6172/1.1528)	mem 34604MB
[2025-01-19 18:50:49 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][210/312]	eta 0:01:17 lr 0.000259	time 0.8185 (0.7566)	model_time 0.8183 (0.7497)	loss 2.9308 (2.7280)	grad_norm 2.1563 (2.6098/1.1811)	mem 34602MB
[2025-01-19 18:50:49 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][230/312]	eta 0:01:01 lr 0.000258	time 0.8387 (0.7532)	model_time 0.8383 (0.7468)	loss 2.8500 (2.7094)	grad_norm 2.4692 (2.6336/1.1677)	mem 34604MB
[2025-01-19 18:50:56 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][220/312]	eta 0:01:09 lr 0.000259	time 0.7394 (0.7558)	model_time 0.7393 (0.7492)	loss 2.9367 (2.7246)	grad_norm 1.3789 (2.5720/1.1719)	mem 34602MB
[2025-01-19 18:50:57 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][240/312]	eta 0:00:54 lr 0.000258	time 0.8095 (0.7533)	model_time 0.8093 (0.7471)	loss 3.0227 (2.7113)	grad_norm 3.4378 (2.6378/1.1566)	mem 34604MB
[2025-01-19 18:51:04 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][230/312]	eta 0:01:01 lr 0.000258	time 0.8093 (0.7558)	model_time 0.8091 (0.7495)	loss 2.8123 (2.7251)	grad_norm 3.3082 (2.5650/1.1566)	mem 34602MB
[2025-01-19 18:51:05 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][250/312]	eta 0:00:46 lr 0.000258	time 0.7166 (0.7540)	model_time 0.7161 (0.7481)	loss 2.7083 (2.7064)	grad_norm 1.0729 (2.6190/1.1518)	mem 34604MB
[2025-01-19 18:51:11 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][240/312]	eta 0:00:54 lr 0.000258	time 0.7115 (0.7549)	model_time 0.7110 (0.7488)	loss 2.6871 (2.7241)	grad_norm 2.8675 (2.5409/1.1459)	mem 34602MB
[2025-01-19 18:51:12 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][260/312]	eta 0:00:39 lr 0.000257	time 0.7188 (0.7545)	model_time 0.7184 (0.7488)	loss 2.9101 (2.6979)	grad_norm 2.1617 (2.6372/1.1600)	mem 34604MB
[2025-01-19 18:51:19 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][250/312]	eta 0:00:46 lr 0.000258	time 0.8081 (0.7551)	model_time 0.8079 (0.7493)	loss 1.9711 (2.7183)	grad_norm 1.8240 (2.5375/1.1389)	mem 34602MB
[2025-01-19 18:51:20 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][270/312]	eta 0:00:31 lr 0.000257	time 0.7276 (0.7542)	model_time 0.7274 (0.7487)	loss 3.0842 (2.7030)	grad_norm 1.2541 (2.6078/1.1584)	mem 34604MB
[2025-01-19 18:51:26 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][260/312]	eta 0:00:39 lr 0.000257	time 0.7137 (0.7548)	model_time 0.7136 (0.7492)	loss 2.8747 (2.7127)	grad_norm 3.9456 (2.5232/1.1291)	mem 34602MB
[2025-01-19 18:51:27 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][280/312]	eta 0:00:24 lr 0.000257	time 0.7204 (0.7533)	model_time 0.7200 (0.7480)	loss 3.1480 (2.6999)	grad_norm 2.6728 (2.5965/1.1541)	mem 34604MB
[2025-01-19 18:51:33 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][270/312]	eta 0:00:31 lr 0.000257	time 0.7301 (0.7541)	model_time 0.7297 (0.7487)	loss 2.8674 (2.7186)	grad_norm 0.9926 (2.5032/1.1211)	mem 34602MB
[2025-01-19 18:51:34 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][290/312]	eta 0:00:16 lr 0.000256	time 0.8116 (0.7527)	model_time 0.8111 (0.7476)	loss 2.6214 (2.7029)	grad_norm 7.1077 (2.6058/1.1738)	mem 34604MB
[2025-01-19 18:51:41 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][280/312]	eta 0:00:24 lr 0.000257	time 0.7494 (0.7532)	model_time 0.7493 (0.7480)	loss 3.1397 (2.7133)	grad_norm 2.2334 (2.5117/1.1164)	mem 34602MB
[2025-01-19 18:51:42 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][300/312]	eta 0:00:09 lr 0.000256	time 0.7154 (0.7519)	model_time 0.7153 (0.7469)	loss 2.3037 (2.7085)	grad_norm 5.2254 (2.6229/1.1959)	mem 34604MB
[2025-01-19 18:51:48 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][290/312]	eta 0:00:16 lr 0.000256	time 0.8049 (0.7539)	model_time 0.8047 (0.7488)	loss 1.7689 (2.7047)	grad_norm 1.6754 (2.4863/1.1086)	mem 34602MB
[2025-01-19 18:51:49 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][310/312]	eta 0:00:01 lr 0.000256	time 0.7143 (0.7508)	model_time 0.7142 (0.7460)	loss 2.9770 (2.7034)	grad_norm 0.9300 (2.5889/1.1973)	mem 34604MB
[2025-01-19 18:51:50 internimage_b_1k_224] (main.py 519): INFO EPOCH 254 training takes 0:03:54
[2025-01-19 18:51:50 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_254.pth saving......
[2025-01-19 18:51:53 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_254.pth saved !!!
[2025-01-19 18:51:56 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][300/312]	eta 0:00:09 lr 0.000256	time 0.7529 (0.7532)	model_time 0.7528 (0.7483)	loss 2.5704 (2.7012)	grad_norm 1.5186 (2.4644/1.1013)	mem 34602MB
[2025-01-19 18:52:01 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.384 (7.384)	Loss 0.6836 (0.6836)	Acc@1 86.182 (86.182)	Acc@5 97.998 (97.998)	Mem 34604MB
[2025-01-19 18:52:03 internimage_b_1k_224] (main.py 510): INFO Train: [254/300][310/312]	eta 0:00:01 lr 0.000256	time 0.7168 (0.7523)	model_time 0.7167 (0.7475)	loss 2.1678 (2.6945)	grad_norm 3.8316 (2.4028/1.0459)	mem 34602MB
[2025-01-19 18:52:04 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.941)	Loss 0.8838 (0.7714)	Acc@1 81.396 (84.426)	Acc@5 95.850 (96.902)	Mem 34604MB
[2025-01-19 18:52:04 internimage_b_1k_224] (main.py 519): INFO EPOCH 254 training takes 0:03:54
[2025-01-19 18:52:04 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_254.pth saving......
[2025-01-19 18:52:04 internimage_b_1k_224] (main.py 575): INFO [Epoch:254] * Acc@1 84.253 Acc@5 96.899
[2025-01-19 18:52:04 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.3%
[2025-01-19 18:52:04 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.30%
[2025-01-19 18:52:07 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_254.pth saved !!!
[2025-01-19 18:52:22 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.815 (17.815)	Loss 0.7127 (0.7127)	Acc@1 86.572 (86.572)	Acc@5 98.120 (98.120)	Mem 34604MB
[2025-01-19 18:52:24 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.701 (16.701)	Loss 0.6942 (0.6942)	Acc@1 86.426 (86.426)	Acc@5 97.974 (97.974)	Mem 34602MB
[2025-01-19 18:52:30 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.141)	Loss 0.8864 (0.7720)	Acc@1 81.396 (84.399)	Acc@5 96.069 (96.959)	Mem 34602MB
[2025-01-19 18:52:30 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (2.419)	Loss 0.9203 (0.8026)	Acc@1 80.957 (84.439)	Acc@5 95.947 (96.966)	Mem 34604MB
[2025-01-19 18:52:31 internimage_b_1k_224] (main.py 575): INFO [Epoch:254] * Acc@1 84.221 Acc@5 96.951
[2025-01-19 18:52:31 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.2%
[2025-01-19 18:52:31 internimage_b_1k_224] (main.py 575): INFO [Epoch:254] * Acc@1 84.267 Acc@5 97.003
[2025-01-19 18:52:31 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.3%
[2025-01-19 18:52:31 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 18:52:31 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:52:34 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 18:52:34 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.22%
[2025-01-19 18:52:35 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:52:35 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.27%
[2025-01-19 18:52:37 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][0/312]	eta 0:11:39 lr 0.000256	time 2.2430 (2.2430)	model_time 0.7361 (0.7361)	loss 2.8573 (2.8573)	grad_norm 2.4523 (2.4523/0.0000)	mem 34604MB
[2025-01-19 18:52:42 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.621 (7.621)	Loss 0.7217 (0.7217)	Acc@1 86.230 (86.230)	Acc@5 98.169 (98.169)	Mem 34602MB
[2025-01-19 18:52:44 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][10/312]	eta 0:04:22 lr 0.000256	time 0.7177 (0.8702)	model_time 0.7175 (0.7330)	loss 3.2250 (2.8355)	grad_norm 1.6357 (1.8895/0.5650)	mem 34604MB
[2025-01-19 18:52:45 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.966)	Loss 0.9192 (0.8030)	Acc@1 80.518 (84.406)	Acc@5 96.240 (97.046)	Mem 34602MB
[2025-01-19 18:52:45 internimage_b_1k_224] (main.py 575): INFO [Epoch:254] * Acc@1 84.209 Acc@5 97.073
[2025-01-19 18:52:45 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.2%
[2025-01-19 18:52:45 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:52:49 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:52:49 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.21%
[2025-01-19 18:52:51 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][0/312]	eta 0:11:34 lr 0.000256	time 2.2244 (2.2244)	model_time 0.7557 (0.7557)	loss 3.0460 (3.0460)	grad_norm 2.4603 (2.4603/0.0000)	mem 34602MB
[2025-01-19 18:52:52 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][20/312]	eta 0:03:55 lr 0.000255	time 0.7217 (0.8073)	model_time 0.7212 (0.7352)	loss 2.7574 (2.8045)	grad_norm 3.0682 (1.9145/0.6021)	mem 34604MB
[2025-01-19 18:52:59 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][10/312]	eta 0:04:30 lr 0.000256	time 0.8206 (0.8952)	model_time 0.8202 (0.7612)	loss 3.1826 (2.8216)	grad_norm 3.3293 (2.7432/1.0480)	mem 34602MB
[2025-01-19 18:52:59 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][30/312]	eta 0:03:44 lr 0.000255	time 0.8060 (0.7946)	model_time 0.8058 (0.7457)	loss 2.9254 (2.7885)	grad_norm 3.0485 (1.9355/0.6103)	mem 34604MB
[2025-01-19 18:53:06 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][20/312]	eta 0:04:03 lr 0.000255	time 0.8198 (0.8336)	model_time 0.8196 (0.7632)	loss 3.0057 (2.7295)	grad_norm 3.2225 (2.7197/1.0464)	mem 34602MB
[2025-01-19 18:53:07 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][40/312]	eta 0:03:34 lr 0.000255	time 0.7105 (0.7881)	model_time 0.7101 (0.7511)	loss 2.7832 (2.6897)	grad_norm 3.6070 (2.0902/0.7092)	mem 34604MB
[2025-01-19 18:53:14 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][30/312]	eta 0:03:46 lr 0.000255	time 0.7177 (0.8046)	model_time 0.7175 (0.7569)	loss 2.3282 (2.6965)	grad_norm 1.2976 (2.4290/1.0148)	mem 34602MB
[2025-01-19 18:53:15 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][50/312]	eta 0:03:26 lr 0.000254	time 0.7160 (0.7876)	model_time 0.7158 (0.7577)	loss 3.0273 (2.6833)	grad_norm 4.0704 (2.2245/0.7698)	mem 34604MB
[2025-01-19 18:53:21 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][40/312]	eta 0:03:35 lr 0.000255	time 0.7428 (0.7913)	model_time 0.7426 (0.7551)	loss 2.9770 (2.6897)	grad_norm 3.0258 (2.3675/0.9869)	mem 34602MB
[2025-01-19 18:53:23 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][60/312]	eta 0:03:18 lr 0.000254	time 0.7088 (0.7859)	model_time 0.7084 (0.7608)	loss 2.6708 (2.6913)	grad_norm 2.6818 (2.2007/0.7509)	mem 34604MB
[2025-01-19 18:53:29 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][50/312]	eta 0:03:25 lr 0.000254	time 0.7257 (0.7833)	model_time 0.7253 (0.7541)	loss 2.9589 (2.6690)	grad_norm 1.6190 (2.4658/1.0754)	mem 34602MB
[2025-01-19 18:53:30 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][70/312]	eta 0:03:09 lr 0.000254	time 0.8076 (0.7840)	model_time 0.8071 (0.7624)	loss 2.9397 (2.6662)	grad_norm 1.0883 (2.2390/0.7783)	mem 34604MB
[2025-01-19 18:53:36 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][60/312]	eta 0:03:16 lr 0.000254	time 0.7428 (0.7797)	model_time 0.7426 (0.7553)	loss 3.0133 (2.6784)	grad_norm 1.8684 (2.5759/1.1075)	mem 34602MB
[2025-01-19 18:53:38 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][80/312]	eta 0:03:00 lr 0.000253	time 0.7512 (0.7771)	model_time 0.7508 (0.7581)	loss 2.8190 (2.6677)	grad_norm 3.5578 (2.3144/0.8597)	mem 34604MB
[2025-01-19 18:53:44 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][70/312]	eta 0:03:07 lr 0.000254	time 0.7189 (0.7745)	model_time 0.7187 (0.7535)	loss 2.6847 (2.6971)	grad_norm 2.8934 (2.5171/1.0644)	mem 34602MB
[2025-01-19 18:53:45 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][90/312]	eta 0:02:51 lr 0.000253	time 0.7219 (0.7725)	model_time 0.7217 (0.7556)	loss 3.1497 (2.6611)	grad_norm 2.9935 (2.4003/0.9506)	mem 34604MB
[2025-01-19 18:53:51 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][80/312]	eta 0:02:58 lr 0.000253	time 0.7236 (0.7696)	model_time 0.7231 (0.7511)	loss 2.0700 (2.6656)	grad_norm 1.9122 (2.4727/1.0508)	mem 34602MB
[2025-01-19 18:53:52 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][100/312]	eta 0:02:42 lr 0.000253	time 0.7184 (0.7682)	model_time 0.7183 (0.7530)	loss 1.6863 (2.6566)	grad_norm 2.9360 (2.4779/1.0615)	mem 34604MB
[2025-01-19 18:53:59 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][90/312]	eta 0:02:49 lr 0.000253	time 0.7608 (0.7651)	model_time 0.7606 (0.7486)	loss 3.0308 (2.6765)	grad_norm 1.5882 (2.4109/1.0319)	mem 34602MB
[2025-01-19 18:54:00 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][110/312]	eta 0:02:34 lr 0.000253	time 0.7324 (0.7647)	model_time 0.7320 (0.7508)	loss 2.8435 (2.6618)	grad_norm 1.6854 (2.5409/1.1678)	mem 34604MB
[2025-01-19 18:54:06 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][100/312]	eta 0:02:42 lr 0.000253	time 0.8135 (0.7652)	model_time 0.8130 (0.7503)	loss 2.6045 (2.6586)	grad_norm 1.7680 (2.3996/1.0067)	mem 34602MB
[2025-01-19 18:54:07 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][120/312]	eta 0:02:26 lr 0.000252	time 0.7323 (0.7618)	model_time 0.7319 (0.7490)	loss 1.8289 (2.6535)	grad_norm 2.4977 (2.5383/1.1364)	mem 34604MB
[2025-01-19 18:54:14 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][110/312]	eta 0:02:33 lr 0.000253	time 0.7457 (0.7622)	model_time 0.7456 (0.7486)	loss 2.3404 (2.6486)	grad_norm 5.1576 (2.4550/1.0580)	mem 34602MB
[2025-01-19 18:54:14 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][130/312]	eta 0:02:18 lr 0.000252	time 0.7375 (0.7596)	model_time 0.7373 (0.7478)	loss 2.1399 (2.6638)	grad_norm 1.3457 (2.4734/1.1195)	mem 34604MB
[2025-01-19 18:54:21 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][120/312]	eta 0:02:25 lr 0.000252	time 0.7550 (0.7599)	model_time 0.7548 (0.7475)	loss 2.9236 (2.6398)	grad_norm 3.9877 (2.4880/1.0765)	mem 34602MB
[2025-01-19 18:54:22 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][140/312]	eta 0:02:10 lr 0.000252	time 0.7209 (0.7579)	model_time 0.7205 (0.7469)	loss 2.2935 (2.6480)	grad_norm 3.7720 (2.4603/1.1015)	mem 34604MB
[2025-01-19 18:54:29 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][130/312]	eta 0:02:18 lr 0.000252	time 0.8229 (0.7607)	model_time 0.8227 (0.7491)	loss 3.3340 (2.6585)	grad_norm 1.3379 (2.4805/1.0661)	mem 34602MB
[2025-01-19 18:54:29 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][150/312]	eta 0:02:02 lr 0.000251	time 0.7956 (0.7584)	model_time 0.7951 (0.7481)	loss 2.9769 (2.6622)	grad_norm 5.1340 (2.5068/1.1244)	mem 34604MB
[2025-01-19 18:54:36 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][140/312]	eta 0:02:10 lr 0.000252	time 0.7191 (0.7594)	model_time 0.7189 (0.7486)	loss 2.7202 (2.6500)	grad_norm 1.8583 (2.4953/1.0778)	mem 34602MB
[2025-01-19 18:54:37 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][160/312]	eta 0:01:55 lr 0.000251	time 0.7151 (0.7589)	model_time 0.7149 (0.7492)	loss 2.2501 (2.6484)	grad_norm 2.1572 (2.4982/1.1029)	mem 34604MB
[2025-01-19 18:54:44 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][150/312]	eta 0:02:02 lr 0.000251	time 0.7168 (0.7589)	model_time 0.7163 (0.7488)	loss 2.9536 (2.6525)	grad_norm 2.2925 (2.5131/1.0651)	mem 34602MB
[2025-01-19 18:54:45 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][170/312]	eta 0:01:47 lr 0.000251	time 0.7090 (0.7596)	model_time 0.7086 (0.7504)	loss 2.9087 (2.6567)	grad_norm 1.3728 (2.5141/1.1120)	mem 34604MB
[2025-01-19 18:54:51 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][160/312]	eta 0:01:55 lr 0.000251	time 0.7217 (0.7580)	model_time 0.7215 (0.7486)	loss 1.9911 (2.6459)	grad_norm 1.8882 (2.5099/1.0524)	mem 34602MB
[2025-01-19 18:54:52 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][180/312]	eta 0:01:40 lr 0.000250	time 0.7223 (0.7603)	model_time 0.7219 (0.7517)	loss 2.8656 (2.6672)	grad_norm 1.7434 (2.4837/1.0910)	mem 34604MB
[2025-01-19 18:54:58 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][170/312]	eta 0:01:47 lr 0.000251	time 0.7171 (0.7569)	model_time 0.7169 (0.7480)	loss 2.3695 (2.6400)	grad_norm 3.1352 (2.5197/1.0573)	mem 34602MB
[2025-01-19 18:55:00 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][190/312]	eta 0:01:32 lr 0.000250	time 0.8093 (0.7614)	model_time 0.8092 (0.7532)	loss 2.6479 (2.6790)	grad_norm 2.4120 (2.4626/1.0708)	mem 34604MB
[2025-01-19 18:55:06 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][180/312]	eta 0:01:39 lr 0.000250	time 0.7190 (0.7575)	model_time 0.7185 (0.7490)	loss 2.6755 (2.6479)	grad_norm 1.9665 (2.5124/1.0492)	mem 34602MB
[2025-01-19 18:55:07 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][200/312]	eta 0:01:25 lr 0.000250	time 0.7187 (0.7600)	model_time 0.7186 (0.7522)	loss 2.8890 (2.6811)	grad_norm 1.4358 (2.4261/1.0600)	mem 34604MB
[2025-01-19 18:55:14 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][190/312]	eta 0:01:32 lr 0.000250	time 0.7257 (0.7569)	model_time 0.7256 (0.7489)	loss 2.7530 (2.6489)	grad_norm 1.7056 (2.5149/1.0321)	mem 34602MB
[2025-01-19 18:55:15 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][210/312]	eta 0:01:17 lr 0.000250	time 0.7718 (0.7595)	model_time 0.7714 (0.7520)	loss 2.9434 (2.6885)	grad_norm 2.4685 (2.4343/1.0535)	mem 34604MB
[2025-01-19 18:55:21 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][200/312]	eta 0:01:24 lr 0.000250	time 0.7190 (0.7557)	model_time 0.7186 (0.7480)	loss 2.7007 (2.6489)	grad_norm 2.6976 (2.5174/1.0331)	mem 34602MB
[2025-01-19 18:55:22 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][220/312]	eta 0:01:09 lr 0.000249	time 0.7432 (0.7584)	model_time 0.7430 (0.7512)	loss 2.7983 (2.6918)	grad_norm 2.8193 (2.4678/1.0741)	mem 34604MB
[2025-01-19 18:55:28 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][210/312]	eta 0:01:16 lr 0.000250	time 0.7272 (0.7543)	model_time 0.7270 (0.7470)	loss 1.8792 (2.6362)	grad_norm 1.9954 (2.5211/1.0373)	mem 34602MB
[2025-01-19 18:55:30 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][230/312]	eta 0:01:02 lr 0.000249	time 0.7194 (0.7574)	model_time 0.7192 (0.7506)	loss 3.3411 (2.6965)	grad_norm 2.1889 (2.4458/1.0620)	mem 34604MB
[2025-01-19 18:55:36 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][220/312]	eta 0:01:09 lr 0.000249	time 0.7948 (0.7561)	model_time 0.7944 (0.7491)	loss 2.6111 (2.6357)	grad_norm 1.6267 (2.4769/1.0357)	mem 34602MB
[2025-01-19 18:55:37 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][240/312]	eta 0:00:54 lr 0.000249	time 0.7233 (0.7564)	model_time 0.7232 (0.7498)	loss 2.9551 (2.7043)	grad_norm 2.5268 (2.4248/1.0540)	mem 34604MB
[2025-01-19 18:55:43 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][230/312]	eta 0:01:01 lr 0.000249	time 0.7234 (0.7551)	model_time 0.7233 (0.7484)	loss 3.0217 (2.6352)	grad_norm 1.9757 (2.4457/1.0254)	mem 34602MB
[2025-01-19 18:55:44 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][250/312]	eta 0:00:46 lr 0.000248	time 0.7166 (0.7555)	model_time 0.7165 (0.7491)	loss 2.5257 (2.7117)	grad_norm 2.3332 (2.4073/1.0382)	mem 34604MB
[2025-01-19 18:55:51 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][240/312]	eta 0:00:54 lr 0.000249	time 0.7212 (0.7543)	model_time 0.7207 (0.7478)	loss 2.4067 (2.6388)	grad_norm 2.2748 (2.4424/1.0086)	mem 34602MB
[2025-01-19 18:55:52 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][260/312]	eta 0:00:39 lr 0.000248	time 0.7151 (0.7548)	model_time 0.7147 (0.7486)	loss 3.3429 (2.7181)	grad_norm 2.8179 (2.4018/1.0268)	mem 34604MB
[2025-01-19 18:55:58 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][250/312]	eta 0:00:46 lr 0.000248	time 0.8004 (0.7545)	model_time 0.7999 (0.7483)	loss 2.5877 (2.6575)	grad_norm 5.0624 (2.4574/1.0148)	mem 34602MB
[2025-01-19 18:55:59 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][270/312]	eta 0:00:31 lr 0.000248	time 0.7981 (0.7551)	model_time 0.7976 (0.7492)	loss 2.8740 (2.7177)	grad_norm 1.2414 (2.3846/1.0193)	mem 34604MB
[2025-01-19 18:56:06 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][260/312]	eta 0:00:39 lr 0.000248	time 0.7229 (0.7547)	model_time 0.7228 (0.7487)	loss 2.8824 (2.6553)	grad_norm 2.4830 (2.4467/1.0039)	mem 34602MB
[2025-01-19 18:56:07 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][280/312]	eta 0:00:24 lr 0.000247	time 0.7157 (0.7547)	model_time 0.7155 (0.7490)	loss 2.8449 (2.7166)	grad_norm 1.7631 (2.4010/1.0186)	mem 34604MB
[2025-01-19 18:56:13 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][270/312]	eta 0:00:31 lr 0.000248	time 0.7233 (0.7547)	model_time 0.7228 (0.7490)	loss 3.0554 (2.6529)	grad_norm 3.2279 (2.4397/1.0006)	mem 34602MB
[2025-01-19 18:56:15 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][290/312]	eta 0:00:16 lr 0.000247	time 0.7079 (0.7562)	model_time 0.7078 (0.7506)	loss 2.9479 (2.7144)	grad_norm 1.4410 (2.3836/1.0102)	mem 34604MB
[2025-01-19 18:56:21 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][280/312]	eta 0:00:24 lr 0.000247	time 0.7233 (0.7545)	model_time 0.7231 (0.7489)	loss 2.3481 (2.6500)	grad_norm 1.7219 (2.4438/1.0069)	mem 34602MB
[2025-01-19 18:56:23 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][300/312]	eta 0:00:09 lr 0.000247	time 0.7980 (0.7570)	model_time 0.7979 (0.7517)	loss 3.0173 (2.7176)	grad_norm 2.7403 (2.3760/1.0003)	mem 34604MB
[2025-01-19 18:56:28 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][290/312]	eta 0:00:16 lr 0.000247	time 0.7178 (0.7539)	model_time 0.7177 (0.7485)	loss 2.8852 (2.6541)	grad_norm 2.0984 (2.4611/1.0099)	mem 34602MB
[2025-01-19 18:56:30 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][310/312]	eta 0:00:01 lr 0.000247	time 0.7998 (0.7568)	model_time 0.7997 (0.7516)	loss 3.1284 (2.7256)	grad_norm 3.8773 (2.4005/0.9987)	mem 34604MB
[2025-01-19 18:56:31 internimage_b_1k_224] (main.py 519): INFO EPOCH 255 training takes 0:03:56
[2025-01-19 18:56:31 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_255.pth saving......
[2025-01-19 18:56:34 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_255.pth saved !!!
[2025-01-19 18:56:36 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][300/312]	eta 0:00:09 lr 0.000247	time 0.7230 (0.7540)	model_time 0.7229 (0.7487)	loss 2.0047 (2.6555)	grad_norm 4.4632 (2.4783/1.0285)	mem 34602MB
[2025-01-19 18:56:41 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.338 (7.338)	Loss 0.6963 (0.6963)	Acc@1 86.597 (86.597)	Acc@5 98.096 (98.096)	Mem 34604MB
[2025-01-19 18:56:43 internimage_b_1k_224] (main.py 510): INFO Train: [255/300][310/312]	eta 0:00:01 lr 0.000247	time 0.7153 (0.7536)	model_time 0.7152 (0.7485)	loss 2.9484 (2.6532)	grad_norm 4.2621 (2.4727/1.0229)	mem 34602MB
[2025-01-19 18:56:44 internimage_b_1k_224] (main.py 519): INFO EPOCH 255 training takes 0:03:55
[2025-01-19 18:56:44 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_255.pth saving......
[2025-01-19 18:56:44 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.949)	Loss 0.9197 (0.7884)	Acc@1 80.737 (84.442)	Acc@5 96.045 (96.917)	Mem 34604MB
[2025-01-19 18:56:45 internimage_b_1k_224] (main.py 575): INFO [Epoch:255] * Acc@1 84.259 Acc@5 96.915
[2025-01-19 18:56:45 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.3%
[2025-01-19 18:56:45 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.30%
[2025-01-19 18:56:47 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_255.pth saved !!!
[2025-01-19 18:57:03 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 18.284 (18.284)	Loss 0.7127 (0.7127)	Acc@1 86.597 (86.597)	Acc@5 98.145 (98.145)	Mem 34604MB
[2025-01-19 18:57:04 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.800 (16.800)	Loss 0.6979 (0.6979)	Acc@1 86.328 (86.328)	Acc@5 97.925 (97.925)	Mem 34602MB
[2025-01-19 18:57:11 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.147)	Loss 0.9056 (0.7842)	Acc@1 80.884 (84.457)	Acc@5 96.094 (96.930)	Mem 34602MB
[2025-01-19 18:57:11 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.403)	Loss 0.9192 (0.8022)	Acc@1 80.933 (84.466)	Acc@5 95.947 (96.979)	Mem 34604MB
[2025-01-19 18:57:11 internimage_b_1k_224] (main.py 575): INFO [Epoch:255] * Acc@1 84.263 Acc@5 96.923
[2025-01-19 18:57:11 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.3%
[2025-01-19 18:57:11 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 18:57:11 internimage_b_1k_224] (main.py 575): INFO [Epoch:255] * Acc@1 84.289 Acc@5 97.013
[2025-01-19 18:57:11 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.3%
[2025-01-19 18:57:11 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:57:14 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 18:57:14 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.26%
[2025-01-19 18:57:15 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:57:15 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.29%
[2025-01-19 18:57:17 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][0/312]	eta 0:10:42 lr 0.000246	time 2.0582 (2.0582)	model_time 0.7420 (0.7420)	loss 3.2528 (3.2528)	grad_norm 3.3116 (3.3116/0.0000)	mem 34604MB
[2025-01-19 18:57:22 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.419 (7.419)	Loss 0.7215 (0.7215)	Acc@1 86.230 (86.230)	Acc@5 98.145 (98.145)	Mem 34602MB
[2025-01-19 18:57:25 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][10/312]	eta 0:04:17 lr 0.000246	time 0.7480 (0.8529)	model_time 0.7478 (0.7329)	loss 2.7932 (2.6146)	grad_norm 2.0517 (2.6232/0.6668)	mem 34604MB
[2025-01-19 18:57:25 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.967)	Loss 0.9186 (0.8025)	Acc@1 80.591 (84.424)	Acc@5 96.240 (97.055)	Mem 34602MB
[2025-01-19 18:57:25 internimage_b_1k_224] (main.py 575): INFO [Epoch:255] * Acc@1 84.229 Acc@5 97.081
[2025-01-19 18:57:25 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.2%
[2025-01-19 18:57:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 18:57:29 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 18:57:29 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.23%
[2025-01-19 18:57:31 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][0/312]	eta 0:10:49 lr 0.000246	time 2.0806 (2.0806)	model_time 0.7494 (0.7494)	loss 2.8271 (2.8271)	grad_norm 2.2319 (2.2319/0.0000)	mem 34602MB
[2025-01-19 18:57:32 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][20/312]	eta 0:03:53 lr 0.000246	time 0.7247 (0.7990)	model_time 0.7246 (0.7360)	loss 1.9615 (2.5784)	grad_norm 1.6834 (2.0018/0.8294)	mem 34604MB
[2025-01-19 18:57:39 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][10/312]	eta 0:04:19 lr 0.000246	time 0.7408 (0.8608)	model_time 0.7406 (0.7394)	loss 2.9710 (2.5922)	grad_norm 2.7443 (2.5939/1.0296)	mem 34602MB
[2025-01-19 18:57:39 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][30/312]	eta 0:03:40 lr 0.000246	time 0.7167 (0.7816)	model_time 0.7165 (0.7388)	loss 1.9619 (2.5760)	grad_norm 1.4027 (1.9771/0.7381)	mem 34604MB
[2025-01-19 18:57:46 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][20/312]	eta 0:03:55 lr 0.000246	time 0.7182 (0.8063)	model_time 0.7180 (0.7425)	loss 2.4027 (2.5807)	grad_norm 4.0238 (2.5576/1.1240)	mem 34602MB
[2025-01-19 18:57:47 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][40/312]	eta 0:03:29 lr 0.000245	time 0.7270 (0.7692)	model_time 0.7266 (0.7368)	loss 2.8530 (2.5732)	grad_norm 2.1034 (2.2230/0.9616)	mem 34604MB
[2025-01-19 18:57:54 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][30/312]	eta 0:03:41 lr 0.000246	time 0.7298 (0.7858)	model_time 0.7294 (0.7425)	loss 2.6071 (2.6377)	grad_norm 2.5520 (2.5790/1.0451)	mem 34602MB
[2025-01-19 18:57:54 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][50/312]	eta 0:03:19 lr 0.000245	time 0.7209 (0.7616)	model_time 0.7207 (0.7355)	loss 1.7101 (2.5908)	grad_norm 2.4047 (2.1762/0.8888)	mem 34604MB
[2025-01-19 18:58:01 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][60/312]	eta 0:03:10 lr 0.000245	time 0.7265 (0.7570)	model_time 0.7261 (0.7350)	loss 2.7802 (2.6300)	grad_norm 1.4255 (2.1900/0.8663)	mem 34604MB
[2025-01-19 18:58:09 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][70/312]	eta 0:03:02 lr 0.000244	time 0.7312 (0.7541)	model_time 0.7306 (0.7352)	loss 2.5622 (2.6273)	grad_norm 3.0459 (2.3101/0.9726)	mem 34604MB
[2025-01-19 18:58:17 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][80/312]	eta 0:02:55 lr 0.000244	time 0.7168 (0.7566)	model_time 0.7166 (0.7400)	loss 2.1868 (2.6323)	grad_norm 1.6903 (2.3095/0.9554)	mem 34604MB
[2025-01-19 18:58:24 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][90/312]	eta 0:02:47 lr 0.000244	time 0.8095 (0.7564)	model_time 0.8090 (0.7416)	loss 2.7893 (2.6273)	grad_norm 3.5716 (2.2635/0.9370)	mem 34604MB
[2025-01-19 18:58:32 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][100/312]	eta 0:02:40 lr 0.000244	time 0.8195 (0.7577)	model_time 0.8191 (0.7443)	loss 2.0580 (2.6130)	grad_norm 2.5898 (2.2759/0.9051)	mem 34604MB
[2025-01-19 18:58:39 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][110/312]	eta 0:02:33 lr 0.000243	time 0.7499 (0.7585)	model_time 0.7497 (0.7463)	loss 3.0086 (2.6058)	grad_norm 1.6509 (2.2646/0.8838)	mem 34604MB
[2025-01-19 18:58:47 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][120/312]	eta 0:02:25 lr 0.000243	time 0.8131 (0.7590)	model_time 0.8126 (0.7478)	loss 2.7379 (2.6096)	grad_norm 2.5870 (2.3319/0.9352)	mem 34604MB
[2025-01-19 18:58:55 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][130/312]	eta 0:02:17 lr 0.000243	time 0.7252 (0.7579)	model_time 0.7248 (0.7475)	loss 3.2761 (2.6150)	grad_norm 2.4333 (2.3047/0.9282)	mem 34604MB
[2025-01-19 18:59:02 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][140/312]	eta 0:02:10 lr 0.000242	time 0.7239 (0.7570)	model_time 0.7237 (0.7473)	loss 1.6500 (2.5892)	grad_norm 2.3533 (2.3204/0.9084)	mem 34604MB
[2025-01-19 18:59:09 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][150/312]	eta 0:02:02 lr 0.000242	time 0.7168 (0.7558)	model_time 0.7163 (0.7467)	loss 1.7565 (2.5898)	grad_norm 1.9700 (2.3071/0.8923)	mem 34604MB
[2025-01-19 18:59:17 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][160/312]	eta 0:01:54 lr 0.000242	time 0.7216 (0.7537)	model_time 0.7212 (0.7452)	loss 2.8801 (2.6003)	grad_norm 1.5407 (2.2728/0.8865)	mem 34604MB
[2025-01-19 18:59:24 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][170/312]	eta 0:01:46 lr 0.000241	time 0.7330 (0.7525)	model_time 0.7328 (0.7444)	loss 2.1814 (2.6074)	grad_norm 2.3234 (2.2540/0.8695)	mem 34604MB
[2025-01-19 18:59:31 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][180/312]	eta 0:01:39 lr 0.000241	time 0.7548 (0.7513)	model_time 0.7543 (0.7436)	loss 2.6548 (2.6191)	grad_norm 3.2499 (2.2349/0.8640)	mem 34604MB
[2025-01-19 18:59:39 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][190/312]	eta 0:01:31 lr 0.000241	time 0.8044 (0.7502)	model_time 0.8040 (0.7430)	loss 3.0300 (2.6202)	grad_norm 4.0910 (2.2846/0.9462)	mem 34604MB
[2025-01-19 18:59:46 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][200/312]	eta 0:01:24 lr 0.000241	time 0.7154 (0.7510)	model_time 0.7150 (0.7441)	loss 1.7395 (2.6145)	grad_norm 2.0226 (2.3342/1.0482)	mem 34604MB
[2025-01-19 18:59:54 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][210/312]	eta 0:01:16 lr 0.000240	time 0.7242 (0.7511)	model_time 0.7240 (0.7445)	loss 3.0438 (2.6223)	grad_norm 4.0953 (2.3671/1.0595)	mem 34604MB
[2025-01-19 19:00:01 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][220/312]	eta 0:01:09 lr 0.000240	time 0.8145 (0.7519)	model_time 0.8144 (0.7456)	loss 2.9748 (2.6298)	grad_norm 1.4605 (2.3530/1.0458)	mem 34604MB
[2025-01-19 19:00:09 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][230/312]	eta 0:01:01 lr 0.000240	time 0.7188 (0.7521)	model_time 0.7184 (0.7461)	loss 3.0540 (2.6335)	grad_norm 1.3715 (2.3220/1.0363)	mem 34604MB
[2025-01-19 19:00:17 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][240/312]	eta 0:00:54 lr 0.000239	time 0.8105 (0.7521)	model_time 0.8104 (0.7463)	loss 3.1643 (2.6364)	grad_norm 1.2647 (2.3077/1.0257)	mem 34604MB
[2025-01-19 19:00:24 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][250/312]	eta 0:00:46 lr 0.000239	time 0.7369 (0.7516)	model_time 0.7364 (0.7460)	loss 2.0625 (2.6334)	grad_norm 2.6315 (2.2956/1.0169)	mem 34604MB
[2025-01-19 19:00:31 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][260/312]	eta 0:00:39 lr 0.000239	time 0.7241 (0.7510)	model_time 0.7237 (0.7456)	loss 2.7010 (2.6392)	grad_norm 1.5159 (2.3009/1.0127)	mem 34604MB
[2025-01-19 19:00:39 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][270/312]	eta 0:00:31 lr 0.000239	time 0.7186 (0.7507)	model_time 0.7184 (0.7454)	loss 3.0074 (2.6442)	grad_norm 1.9933 (2.2912/1.0005)	mem 34604MB
[2025-01-19 19:00:46 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][280/312]	eta 0:00:23 lr 0.000238	time 0.7204 (0.7500)	model_time 0.7200 (0.7449)	loss 2.0375 (2.6345)	grad_norm 3.0929 (2.2889/0.9876)	mem 34604MB
[2025-01-19 19:00:53 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][290/312]	eta 0:00:16 lr 0.000238	time 0.7176 (0.7492)	model_time 0.7172 (0.7443)	loss 2.9563 (2.6397)	grad_norm 0.8146 (2.2901/0.9969)	mem 34604MB
[2025-01-19 19:01:00 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][300/312]	eta 0:00:08 lr 0.000238	time 0.7127 (0.7482)	model_time 0.7126 (0.7435)	loss 2.8369 (2.6367)	grad_norm 1.7793 (2.2696/0.9881)	mem 34604MB
[2025-01-19 19:01:08 internimage_b_1k_224] (main.py 510): INFO Train: [256/300][310/312]	eta 0:00:01 lr 0.000237	time 0.7154 (0.7472)	model_time 0.7153 (0.7426)	loss 2.9631 (2.6406)	grad_norm 1.5928 (2.2626/0.9894)	mem 34604MB
[2025-01-19 19:01:08 internimage_b_1k_224] (main.py 519): INFO EPOCH 256 training takes 0:03:53
[2025-01-19 19:01:08 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_256.pth saving......
[2025-01-19 19:01:11 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_256.pth saved !!!
[2025-01-19 19:01:19 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.430 (7.430)	Loss 0.6875 (0.6875)	Acc@1 86.206 (86.206)	Acc@5 98.071 (98.071)	Mem 34604MB
[2025-01-19 19:01:22 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.952)	Loss 0.8870 (0.7766)	Acc@1 81.152 (84.413)	Acc@5 96.118 (96.959)	Mem 34604MB
[2025-01-19 19:01:22 internimage_b_1k_224] (main.py 575): INFO [Epoch:256] * Acc@1 84.241 Acc@5 96.963
[2025-01-19 19:01:22 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.2%
[2025-01-19 19:01:22 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.30%
[2025-01-19 19:01:31 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.149 (9.149)	Loss 0.7127 (0.7127)	Acc@1 86.548 (86.548)	Acc@5 98.120 (98.120)	Mem 34604MB
[2025-01-19 19:01:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.243)	Loss 0.9183 (0.8017)	Acc@1 80.933 (84.484)	Acc@5 95.972 (96.993)	Mem 34604MB
[2025-01-19 19:01:36 internimage_b_1k_224] (main.py 575): INFO [Epoch:256] * Acc@1 84.303 Acc@5 97.021
[2025-01-19 19:01:36 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.3%
[2025-01-19 19:01:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 19:01:40 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 19:01:40 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.30%
[2025-01-19 19:01:43 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][0/312]	eta 0:11:23 lr 0.000237	time 2.1898 (2.1898)	model_time 0.7540 (0.7540)	loss 2.2436 (2.2436)	grad_norm 2.1608 (2.1608/0.0000)	mem 34604MB
[2025-01-19 19:01:50 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][10/312]	eta 0:04:35 lr 0.000237	time 0.7608 (0.9120)	model_time 0.7606 (0.7812)	loss 2.7511 (2.7902)	grad_norm 2.3180 (1.8787/0.5665)	mem 34604MB
[2025-01-19 19:01:58 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][20/312]	eta 0:04:03 lr 0.000237	time 0.7370 (0.8355)	model_time 0.7369 (0.7669)	loss 2.6920 (2.7539)	grad_norm 1.3316 (1.7014/0.5166)	mem 34604MB
[2025-01-19 19:02:05 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][30/312]	eta 0:03:48 lr 0.000237	time 0.7159 (0.8109)	model_time 0.7155 (0.7643)	loss 2.9192 (2.7551)	grad_norm 2.4307 (1.6375/0.5132)	mem 34604MB
[2025-01-19 19:02:13 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][40/312]	eta 0:03:38 lr 0.000236	time 0.7370 (0.8045)	model_time 0.7365 (0.7691)	loss 2.6805 (2.8105)	grad_norm 1.1677 (1.7944/0.7317)	mem 34604MB
[2025-01-19 19:02:21 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][50/312]	eta 0:03:28 lr 0.000236	time 0.7281 (0.7944)	model_time 0.7277 (0.7659)	loss 2.5292 (2.7574)	grad_norm 2.0549 (1.9164/0.7766)	mem 34604MB
[2025-01-19 19:02:28 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][60/312]	eta 0:03:17 lr 0.000236	time 0.7203 (0.7852)	model_time 0.7198 (0.7613)	loss 3.1016 (2.7845)	grad_norm 1.2280 (2.0187/0.8547)	mem 34604MB
[2025-01-19 19:02:36 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][70/312]	eta 0:03:08 lr 0.000235	time 0.7181 (0.7781)	model_time 0.7179 (0.7575)	loss 3.0984 (2.7636)	grad_norm 4.3033 (2.0514/0.8873)	mem 34604MB
[2025-01-19 19:02:43 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][80/312]	eta 0:02:59 lr 0.000235	time 0.7230 (0.7734)	model_time 0.7229 (0.7553)	loss 2.8893 (2.7097)	grad_norm 2.5730 (2.1140/0.9016)	mem 34604MB
[2025-01-19 19:02:50 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][90/312]	eta 0:02:50 lr 0.000235	time 0.7266 (0.7683)	model_time 0.7262 (0.7522)	loss 2.8852 (2.7133)	grad_norm 1.3145 (2.1233/0.8818)	mem 34604MB
[2025-01-19 19:02:58 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][100/312]	eta 0:02:42 lr 0.000234	time 0.7118 (0.7649)	model_time 0.7114 (0.7503)	loss 1.9472 (2.6840)	grad_norm 3.0502 (2.1389/0.8780)	mem 34604MB
[2025-01-19 19:03:05 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][110/312]	eta 0:02:33 lr 0.000234	time 0.7220 (0.7620)	model_time 0.7219 (0.7487)	loss 2.2654 (2.6741)	grad_norm 2.5433 (2.1629/0.8706)	mem 34604MB
[2025-01-19 19:03:12 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][120/312]	eta 0:02:25 lr 0.000234	time 0.8041 (0.7598)	model_time 0.8039 (0.7476)	loss 1.8151 (2.6633)	grad_norm 2.2644 (2.1829/0.8624)	mem 34604MB
[2025-01-19 19:03:20 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][130/312]	eta 0:02:18 lr 0.000234	time 0.8568 (0.7610)	model_time 0.8564 (0.7497)	loss 2.6175 (2.6746)	grad_norm 3.3181 (2.1628/0.8566)	mem 34604MB
[2025-01-19 19:03:28 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][140/312]	eta 0:02:10 lr 0.000233	time 0.7290 (0.7604)	model_time 0.7285 (0.7499)	loss 3.0148 (2.6711)	grad_norm 2.1341 (2.1930/0.8665)	mem 34604MB
[2025-01-19 19:03:35 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][150/312]	eta 0:02:03 lr 0.000233	time 0.7209 (0.7602)	model_time 0.7205 (0.7503)	loss 1.7774 (2.6493)	grad_norm 2.4812 (2.1754/0.8498)	mem 34604MB
[2025-01-19 19:03:43 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][160/312]	eta 0:01:55 lr 0.000233	time 0.7152 (0.7617)	model_time 0.7151 (0.7524)	loss 2.8704 (2.6573)	grad_norm 2.3128 (2.1795/0.8490)	mem 34604MB
[2025-01-19 19:03:51 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][170/312]	eta 0:01:48 lr 0.000232	time 0.7242 (0.7616)	model_time 0.7237 (0.7528)	loss 2.6269 (2.6489)	grad_norm 2.4351 (2.1838/0.8411)	mem 34604MB
[2025-01-19 19:03:58 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][180/312]	eta 0:01:40 lr 0.000232	time 0.7214 (0.7601)	model_time 0.7213 (0.7518)	loss 2.9996 (2.6593)	grad_norm 1.5249 (2.2096/0.8718)	mem 34604MB
[2025-01-19 19:04:05 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][190/312]	eta 0:01:32 lr 0.000232	time 0.7313 (0.7588)	model_time 0.7311 (0.7509)	loss 2.2566 (2.6674)	grad_norm 2.9758 (2.2057/0.8603)	mem 34604MB
[2025-01-19 19:04:13 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][200/312]	eta 0:01:24 lr 0.000232	time 0.7209 (0.7576)	model_time 0.7207 (0.7502)	loss 2.2295 (2.6482)	grad_norm 3.6083 (2.2079/0.8592)	mem 34604MB
[2025-01-19 19:04:20 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][210/312]	eta 0:01:17 lr 0.000231	time 0.7174 (0.7567)	model_time 0.7172 (0.7496)	loss 2.5303 (2.6484)	grad_norm 3.7558 (2.2330/0.8807)	mem 34604MB
[2025-01-19 19:04:27 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][220/312]	eta 0:01:09 lr 0.000231	time 0.7190 (0.7560)	model_time 0.7188 (0.7492)	loss 2.7094 (2.6562)	grad_norm 1.9028 (2.2366/0.8844)	mem 34604MB
[2025-01-19 19:04:35 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][230/312]	eta 0:01:01 lr 0.000231	time 0.7229 (0.7548)	model_time 0.7228 (0.7483)	loss 2.8534 (2.6637)	grad_norm 5.0969 (2.2542/0.8905)	mem 34604MB
[2025-01-19 19:04:42 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][240/312]	eta 0:00:54 lr 0.000230	time 0.7211 (0.7538)	model_time 0.7209 (0.7475)	loss 2.8309 (2.6620)	grad_norm 2.8312 (2.2750/0.8930)	mem 34604MB
[2025-01-19 19:04:50 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][250/312]	eta 0:00:46 lr 0.000230	time 1.0071 (0.7549)	model_time 1.0067 (0.7488)	loss 2.4350 (2.6604)	grad_norm 2.1357 (2.2698/0.8806)	mem 34604MB
[2025-01-19 19:04:57 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][260/312]	eta 0:00:39 lr 0.000230	time 0.7146 (0.7552)	model_time 0.7145 (0.7493)	loss 2.7602 (2.6644)	grad_norm 2.0599 (2.2593/0.8782)	mem 34604MB
[2025-01-19 19:05:05 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][270/312]	eta 0:00:31 lr 0.000230	time 0.7156 (0.7551)	model_time 0.7151 (0.7495)	loss 2.7096 (2.6672)	grad_norm 2.2281 (2.2429/0.8683)	mem 34604MB
[2025-01-19 19:05:13 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][280/312]	eta 0:00:24 lr 0.000229	time 0.7240 (0.7564)	model_time 0.7239 (0.7509)	loss 2.3770 (2.6711)	grad_norm 2.4313 (2.2438/0.8665)	mem 34604MB
[2025-01-19 19:05:21 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][290/312]	eta 0:00:16 lr 0.000229	time 0.7146 (0.7568)	model_time 0.7145 (0.7516)	loss 2.7468 (2.6658)	grad_norm 1.4029 (2.2525/0.8638)	mem 34604MB
[2025-01-19 19:05:28 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][300/312]	eta 0:00:09 lr 0.000229	time 0.7170 (0.7561)	model_time 0.7169 (0.7510)	loss 2.0507 (2.6607)	grad_norm 1.9241 (2.2529/0.8645)	mem 34604MB
[2025-01-19 19:05:35 internimage_b_1k_224] (main.py 510): INFO Train: [257/300][310/312]	eta 0:00:01 lr 0.000228	time 0.7155 (0.7549)	model_time 0.7154 (0.7500)	loss 2.0855 (2.6645)	grad_norm 3.0417 (2.2650/0.8627)	mem 34604MB
[2025-01-19 19:05:36 internimage_b_1k_224] (main.py 519): INFO EPOCH 257 training takes 0:03:55
[2025-01-19 19:05:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_257.pth saving......
[2025-01-19 19:05:39 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_257.pth saved !!!
[2025-01-19 19:05:53 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 13.730 (13.730)	Loss 0.6892 (0.6892)	Acc@1 86.426 (86.426)	Acc@5 97.852 (97.852)	Mem 34604MB
[2025-01-19 19:05:59 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.840)	Loss 0.8891 (0.7757)	Acc@1 81.152 (84.391)	Acc@5 95.776 (96.917)	Mem 34604MB
[2025-01-19 19:06:00 internimage_b_1k_224] (main.py 575): INFO [Epoch:257] * Acc@1 84.221 Acc@5 96.927
[2025-01-19 19:06:00 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.2%
[2025-01-19 19:06:00 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.30%
[2025-01-19 19:06:15 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.055 (15.055)	Loss 0.7126 (0.7126)	Acc@1 86.523 (86.523)	Acc@5 98.120 (98.120)	Mem 34604MB
[2025-01-19 19:06:23 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (2.107)	Loss 0.9174 (0.8012)	Acc@1 80.957 (84.468)	Acc@5 95.972 (96.993)	Mem 34604MB
[2025-01-19 19:06:23 internimage_b_1k_224] (main.py 575): INFO [Epoch:257] * Acc@1 84.291 Acc@5 97.019
[2025-01-19 19:06:23 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.3%
[2025-01-19 19:06:23 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.30%
[2025-01-19 19:06:27 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][0/312]	eta 0:18:38 lr 0.000228	time 3.5861 (3.5861)	model_time 0.7556 (0.7556)	loss 2.0328 (2.0328)	grad_norm 1.7697 (1.7697/0.0000)	mem 34604MB
[2025-01-19 19:06:34 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][10/312]	eta 0:05:04 lr 0.000228	time 0.7402 (1.0075)	model_time 0.7398 (0.7499)	loss 1.8570 (2.3315)	grad_norm 1.5874 (2.6062/1.0670)	mem 34604MB
[2025-01-19 19:06:41 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][20/312]	eta 0:04:16 lr 0.000228	time 0.7403 (0.8772)	model_time 0.7401 (0.7421)	loss 2.7255 (2.4692)	grad_norm 1.7794 (2.4808/1.0531)	mem 34604MB
[2025-01-19 19:06:49 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][30/312]	eta 0:03:53 lr 0.000228	time 0.7382 (0.8290)	model_time 0.7380 (0.7374)	loss 2.6821 (2.5446)	grad_norm 4.3323 (2.7678/1.2448)	mem 34604MB
[2025-01-19 19:06:56 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][40/312]	eta 0:03:39 lr 0.000227	time 0.7363 (0.8059)	model_time 0.7361 (0.7365)	loss 3.1797 (2.5847)	grad_norm 3.4805 (2.8412/1.2009)	mem 34604MB
[2025-01-19 19:07:03 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][50/312]	eta 0:03:27 lr 0.000227	time 0.7180 (0.7907)	model_time 0.7179 (0.7349)	loss 2.1321 (2.5629)	grad_norm 3.0715 (2.8557/1.2016)	mem 34604MB
[2025-01-19 19:07:11 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][60/312]	eta 0:03:18 lr 0.000227	time 0.8083 (0.7882)	model_time 0.8081 (0.7415)	loss 3.0261 (2.6104)	grad_norm 3.4691 (2.7708/1.1425)	mem 34604MB
[2025-01-19 19:07:19 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][70/312]	eta 0:03:09 lr 0.000226	time 0.7236 (0.7837)	model_time 0.7232 (0.7435)	loss 1.9119 (2.6165)	grad_norm 1.3658 (2.7131/1.1344)	mem 34604MB
[2025-01-19 19:07:26 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][80/312]	eta 0:03:01 lr 0.000226	time 0.7519 (0.7813)	model_time 0.7517 (0.7460)	loss 2.8502 (2.6534)	grad_norm 3.1410 (2.6272/1.1060)	mem 34604MB
[2025-01-19 19:07:34 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][90/312]	eta 0:02:53 lr 0.000226	time 0.7155 (0.7818)	model_time 0.7153 (0.7504)	loss 1.5185 (2.6208)	grad_norm 1.9886 (2.6904/1.1550)	mem 34604MB
[2025-01-19 19:07:42 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][100/312]	eta 0:02:45 lr 0.000226	time 0.7236 (0.7820)	model_time 0.7231 (0.7537)	loss 2.1096 (2.5948)	grad_norm 2.4420 (2.6299/1.1440)	mem 34604MB
[2025-01-19 19:07:49 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][110/312]	eta 0:02:37 lr 0.000225	time 0.7195 (0.7784)	model_time 0.7190 (0.7525)	loss 3.0454 (2.6006)	grad_norm 2.3284 (2.6087/1.1157)	mem 34604MB
[2025-01-19 19:07:57 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][120/312]	eta 0:02:28 lr 0.000225	time 0.7243 (0.7748)	model_time 0.7241 (0.7510)	loss 2.0268 (2.5878)	grad_norm 2.6859 (2.5692/1.0922)	mem 34604MB
[2025-01-19 19:08:04 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][130/312]	eta 0:02:20 lr 0.000225	time 0.7251 (0.7717)	model_time 0.7249 (0.7498)	loss 2.7557 (2.5862)	grad_norm 1.9019 (2.5247/1.0853)	mem 34604MB
[2025-01-19 19:08:11 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][140/312]	eta 0:02:12 lr 0.000225	time 0.7150 (0.7688)	model_time 0.7149 (0.7484)	loss 1.5602 (2.5797)	grad_norm 1.3498 (2.4662/1.0754)	mem 34604MB
[2025-01-19 19:08:19 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][150/312]	eta 0:02:04 lr 0.000224	time 0.7168 (0.7665)	model_time 0.7163 (0.7474)	loss 2.8290 (2.6007)	grad_norm 3.7646 (2.5354/1.1524)	mem 34604MB
[2025-01-19 19:08:26 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][160/312]	eta 0:01:56 lr 0.000224	time 0.7218 (0.7641)	model_time 0.7214 (0.7462)	loss 3.2661 (2.6097)	grad_norm 2.9632 (2.5384/1.1543)	mem 34604MB
[2025-01-19 19:08:33 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][170/312]	eta 0:01:48 lr 0.000224	time 0.7184 (0.7618)	model_time 0.7180 (0.7449)	loss 2.2186 (2.6209)	grad_norm 1.4321 (2.5130/1.1337)	mem 34604MB
[2025-01-19 19:08:41 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][180/312]	eta 0:01:40 lr 0.000223	time 0.8383 (0.7623)	model_time 0.8379 (0.7463)	loss 3.1784 (2.6255)	grad_norm 3.1468 (2.4923/1.1177)	mem 34604MB
[2025-01-19 19:08:49 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][190/312]	eta 0:01:33 lr 0.000223	time 0.7234 (0.7626)	model_time 0.7230 (0.7474)	loss 2.4787 (2.6255)	grad_norm 4.8355 (2.5144/1.1296)	mem 34604MB
[2025-01-19 19:08:56 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][200/312]	eta 0:01:25 lr 0.000223	time 0.7258 (0.7626)	model_time 0.7256 (0.7481)	loss 1.6779 (2.6154)	grad_norm 3.3923 (2.5828/1.2045)	mem 34604MB
[2025-01-19 19:09:04 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][210/312]	eta 0:01:17 lr 0.000223	time 0.7625 (0.7636)	model_time 0.7623 (0.7498)	loss 2.8642 (2.6220)	grad_norm 2.3394 (2.5861/1.1947)	mem 34604MB
[2025-01-19 19:09:12 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][220/312]	eta 0:01:10 lr 0.000222	time 0.7164 (0.7641)	model_time 0.7163 (0.7509)	loss 2.5739 (2.6219)	grad_norm 3.3839 (2.5564/1.1846)	mem 34604MB
[2025-01-19 19:09:19 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][230/312]	eta 0:01:02 lr 0.000222	time 0.7287 (0.7629)	model_time 0.7285 (0.7503)	loss 2.8670 (2.6189)	grad_norm 2.8331 (2.5722/1.1831)	mem 34604MB
[2025-01-19 19:09:27 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][240/312]	eta 0:00:54 lr 0.000222	time 0.7339 (0.7617)	model_time 0.7335 (0.7497)	loss 2.9262 (2.6171)	grad_norm 2.4498 (2.5658/1.1742)	mem 34604MB
[2025-01-19 19:09:34 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][250/312]	eta 0:00:47 lr 0.000221	time 0.7235 (0.7609)	model_time 0.7234 (0.7493)	loss 1.8744 (2.6142)	grad_norm 2.5345 (2.5597/1.1650)	mem 34604MB
[2025-01-19 19:09:41 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][260/312]	eta 0:00:39 lr 0.000221	time 0.7233 (0.7597)	model_time 0.7232 (0.7485)	loss 2.1054 (2.6192)	grad_norm 3.2010 (2.5640/1.1532)	mem 34604MB
[2025-01-19 19:09:49 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][270/312]	eta 0:00:31 lr 0.000221	time 0.7371 (0.7584)	model_time 0.7367 (0.7476)	loss 2.7424 (2.6186)	grad_norm 1.4349 (2.5687/1.1399)	mem 34604MB
[2025-01-19 19:09:56 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][280/312]	eta 0:00:24 lr 0.000221	time 0.7692 (0.7577)	model_time 0.7690 (0.7473)	loss 3.3648 (2.6276)	grad_norm 1.4293 (2.5512/1.1308)	mem 34604MB
[2025-01-19 19:10:03 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][290/312]	eta 0:00:16 lr 0.000220	time 0.7396 (0.7566)	model_time 0.7395 (0.7466)	loss 3.1298 (2.6303)	grad_norm 3.3247 (2.5415/1.1222)	mem 34604MB
[2025-01-19 19:10:11 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][300/312]	eta 0:00:09 lr 0.000220	time 0.8055 (0.7563)	model_time 0.8054 (0.7466)	loss 1.6128 (2.6258)	grad_norm 2.2875 (2.5485/1.1208)	mem 34604MB
[2025-01-19 19:10:18 internimage_b_1k_224] (main.py 510): INFO Train: [258/300][310/312]	eta 0:00:01 lr 0.000220	time 0.7147 (0.7564)	model_time 0.7146 (0.7469)	loss 2.8195 (2.6298)	grad_norm 1.6267 (2.5152/1.1166)	mem 34604MB
[2025-01-19 19:10:19 internimage_b_1k_224] (main.py 519): INFO EPOCH 258 training takes 0:03:56
[2025-01-19 19:10:19 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_258.pth saving......
[2025-01-19 19:10:22 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_258.pth saved !!!
[2025-01-19 19:10:37 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.394 (14.394)	Loss 0.7092 (0.7092)	Acc@1 86.255 (86.255)	Acc@5 98.047 (98.047)	Mem 34604MB
[2025-01-19 19:10:44 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.929)	Loss 0.8988 (0.7882)	Acc@1 81.372 (84.530)	Acc@5 96.045 (96.968)	Mem 34604MB
[2025-01-19 19:10:44 internimage_b_1k_224] (main.py 575): INFO [Epoch:258] * Acc@1 84.347 Acc@5 96.987
[2025-01-19 19:10:44 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.3%
[2025-01-19 19:10:44 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 19:10:47 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 19:10:47 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.35%
[2025-01-19 19:11:00 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 13.409 (13.409)	Loss 0.7124 (0.7124)	Acc@1 86.548 (86.548)	Acc@5 98.145 (98.145)	Mem 34604MB
[2025-01-19 19:11:06 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.758)	Loss 0.9164 (0.8006)	Acc@1 81.006 (84.479)	Acc@5 95.947 (96.999)	Mem 34604MB
[2025-01-19 19:11:07 internimage_b_1k_224] (main.py 575): INFO [Epoch:258] * Acc@1 84.295 Acc@5 97.023
[2025-01-19 19:11:07 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.3%
[2025-01-19 19:11:07 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.30%
[2025-01-19 19:11:10 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][0/312]	eta 0:19:02 lr 0.000220	time 3.6605 (3.6605)	model_time 1.2412 (1.2412)	loss 2.7597 (2.7597)	grad_norm 1.2954 (1.2954/0.0000)	mem 34604MB
[2025-01-19 19:11:18 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][10/312]	eta 0:05:10 lr 0.000219	time 0.7206 (1.0266)	model_time 0.7204 (0.8063)	loss 2.5990 (2.4853)	grad_norm 1.6272 (1.6228/0.4713)	mem 34604MB
[2025-01-19 19:11:26 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][20/312]	eta 0:04:26 lr 0.000219	time 0.7161 (0.9116)	model_time 0.7157 (0.7960)	loss 3.3108 (2.5900)	grad_norm 1.2495 (2.1391/0.9233)	mem 34604MB
[2025-01-19 19:11:33 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][30/312]	eta 0:04:04 lr 0.000219	time 0.7404 (0.8661)	model_time 0.7402 (0.7878)	loss 2.6285 (2.6159)	grad_norm 3.1056 (2.2601/0.8427)	mem 34604MB
[2025-01-19 19:11:41 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][40/312]	eta 0:03:47 lr 0.000219	time 0.7173 (0.8354)	model_time 0.7169 (0.7761)	loss 2.8718 (2.5947)	grad_norm 1.8980 (2.3334/0.8546)	mem 34604MB
[2025-01-19 19:11:48 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][50/312]	eta 0:03:33 lr 0.000218	time 0.7248 (0.8148)	model_time 0.7247 (0.7670)	loss 2.0548 (2.6269)	grad_norm 1.9071 (2.3213/0.8362)	mem 34604MB
[2025-01-19 19:11:56 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][60/312]	eta 0:03:22 lr 0.000218	time 0.7285 (0.8024)	model_time 0.7283 (0.7624)	loss 2.1948 (2.6418)	grad_norm 3.2503 (2.2471/0.8311)	mem 34604MB
[2025-01-19 19:12:03 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][70/312]	eta 0:03:11 lr 0.000218	time 0.7672 (0.7927)	model_time 0.7668 (0.7583)	loss 2.5680 (2.6571)	grad_norm 1.7318 (2.2727/0.8096)	mem 34604MB
[2025-01-19 19:12:10 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][80/312]	eta 0:03:02 lr 0.000218	time 0.7266 (0.7853)	model_time 0.7265 (0.7551)	loss 2.9153 (2.6792)	grad_norm 2.9804 (2.3350/0.9094)	mem 34604MB
[2025-01-19 19:12:18 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][90/312]	eta 0:02:53 lr 0.000217	time 0.7081 (0.7807)	model_time 0.7079 (0.7538)	loss 2.5529 (2.6912)	grad_norm 3.6738 (2.4189/0.9465)	mem 34604MB
[2025-01-19 19:12:25 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][100/312]	eta 0:02:44 lr 0.000217	time 0.7162 (0.7767)	model_time 0.7161 (0.7524)	loss 1.8195 (2.6913)	grad_norm 2.6071 (2.4563/0.9991)	mem 34604MB
[2025-01-19 19:12:33 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][110/312]	eta 0:02:36 lr 0.000217	time 0.7371 (0.7742)	model_time 0.7369 (0.7521)	loss 2.9650 (2.6972)	grad_norm 2.8392 (2.4808/1.0321)	mem 34604MB
[2025-01-19 19:12:40 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][120/312]	eta 0:02:28 lr 0.000216	time 0.7228 (0.7740)	model_time 0.7224 (0.7537)	loss 2.4397 (2.6786)	grad_norm 2.1307 (2.4815/1.0280)	mem 34604MB
[2025-01-19 19:12:48 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][130/312]	eta 0:02:20 lr 0.000216	time 0.7166 (0.7739)	model_time 0.7164 (0.7551)	loss 2.9520 (2.6597)	grad_norm 2.2766 (2.4716/1.0202)	mem 34604MB
[2025-01-19 19:12:56 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][140/312]	eta 0:02:13 lr 0.000216	time 0.7152 (0.7757)	model_time 0.7150 (0.7582)	loss 2.2510 (2.6575)	grad_norm 3.1737 (2.4744/1.0030)	mem 34604MB
[2025-01-19 19:13:04 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][150/312]	eta 0:02:05 lr 0.000216	time 0.7157 (0.7776)	model_time 0.7155 (0.7612)	loss 2.5262 (2.6418)	grad_norm 2.0558 (2.4742/0.9993)	mem 34604MB
[2025-01-19 19:13:11 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][160/312]	eta 0:01:57 lr 0.000215	time 0.7240 (0.7750)	model_time 0.7236 (0.7596)	loss 3.0385 (2.6440)	grad_norm 1.1890 (2.4977/1.0043)	mem 34604MB
[2025-01-19 19:13:19 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][170/312]	eta 0:01:49 lr 0.000215	time 0.7171 (0.7724)	model_time 0.7167 (0.7579)	loss 2.6090 (2.6432)	grad_norm 3.8877 (2.5345/1.0124)	mem 34604MB
[2025-01-19 19:13:26 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][180/312]	eta 0:01:41 lr 0.000215	time 0.7802 (0.7710)	model_time 0.7801 (0.7573)	loss 2.7970 (2.6509)	grad_norm 2.0224 (2.5032/0.9980)	mem 34604MB
[2025-01-19 19:13:34 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][190/312]	eta 0:01:33 lr 0.000214	time 0.7417 (0.7691)	model_time 0.7416 (0.7561)	loss 3.0649 (2.6555)	grad_norm 3.1417 (2.4764/0.9948)	mem 34604MB
[2025-01-19 19:13:41 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][200/312]	eta 0:01:25 lr 0.000214	time 0.7256 (0.7671)	model_time 0.7251 (0.7547)	loss 2.8795 (2.6486)	grad_norm 2.3569 (2.4441/0.9836)	mem 34604MB
[2025-01-19 19:13:48 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][210/312]	eta 0:01:18 lr 0.000214	time 0.7089 (0.7657)	model_time 0.7088 (0.7539)	loss 1.7548 (2.6509)	grad_norm 1.1843 (2.4361/0.9958)	mem 34604MB
[2025-01-19 19:13:56 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][220/312]	eta 0:01:10 lr 0.000214	time 0.7133 (0.7644)	model_time 0.7131 (0.7531)	loss 1.9975 (2.6510)	grad_norm 2.9952 (2.4124/0.9874)	mem 34604MB
[2025-01-19 19:14:03 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][230/312]	eta 0:01:02 lr 0.000213	time 0.7263 (0.7634)	model_time 0.7261 (0.7526)	loss 1.9360 (2.6534)	grad_norm 2.1375 (2.4289/0.9877)	mem 34604MB
[2025-01-19 19:14:11 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][240/312]	eta 0:00:55 lr 0.000213	time 0.7188 (0.7640)	model_time 0.7187 (0.7536)	loss 2.8218 (2.6564)	grad_norm 3.4377 (2.4559/0.9953)	mem 34604MB
[2025-01-19 19:14:18 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][250/312]	eta 0:00:47 lr 0.000213	time 0.7164 (0.7635)	model_time 0.7162 (0.7535)	loss 2.8855 (2.6643)	grad_norm 4.8715 (2.4717/1.0095)	mem 34604MB
[2025-01-19 19:14:26 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][260/312]	eta 0:00:39 lr 0.000213	time 0.7248 (0.7642)	model_time 0.7247 (0.7546)	loss 2.7269 (2.6655)	grad_norm 2.8821 (2.4818/1.0046)	mem 34604MB
[2025-01-19 19:14:34 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][270/312]	eta 0:00:32 lr 0.000212	time 0.8112 (0.7647)	model_time 0.8110 (0.7555)	loss 3.1974 (2.6674)	grad_norm 2.0352 (2.4675/0.9996)	mem 34604MB
[2025-01-19 19:14:41 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][280/312]	eta 0:00:24 lr 0.000212	time 0.7702 (0.7642)	model_time 0.7698 (0.7552)	loss 3.2884 (2.6587)	grad_norm 1.7353 (2.4425/0.9965)	mem 34604MB
[2025-01-19 19:14:49 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][290/312]	eta 0:00:16 lr 0.000212	time 0.7170 (0.7631)	model_time 0.7168 (0.7544)	loss 2.6223 (2.6510)	grad_norm 3.4093 (2.4309/0.9945)	mem 34604MB
[2025-01-19 19:14:56 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][300/312]	eta 0:00:09 lr 0.000212	time 0.7093 (0.7619)	model_time 0.7092 (0.7535)	loss 2.2247 (2.6533)	grad_norm 2.1280 (2.4073/0.9938)	mem 34604MB
[2025-01-19 19:15:03 internimage_b_1k_224] (main.py 510): INFO Train: [259/300][310/312]	eta 0:00:01 lr 0.000211	time 0.7130 (0.7607)	model_time 0.7128 (0.7526)	loss 2.9390 (2.6579)	grad_norm 4.2382 (2.4238/0.9971)	mem 34604MB
[2025-01-19 19:15:04 internimage_b_1k_224] (main.py 519): INFO EPOCH 259 training takes 0:03:57
[2025-01-19 19:15:04 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_259.pth saving......
[2025-01-19 19:15:07 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_259.pth saved !!!
[2025-01-19 19:15:15 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.455 (7.455)	Loss 0.6856 (0.6856)	Acc@1 86.572 (86.572)	Acc@5 97.949 (97.949)	Mem 34604MB
[2025-01-19 19:15:18 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.957)	Loss 0.8910 (0.7809)	Acc@1 81.299 (84.513)	Acc@5 95.923 (96.939)	Mem 34604MB
[2025-01-19 19:15:18 internimage_b_1k_224] (main.py 575): INFO [Epoch:259] * Acc@1 84.333 Acc@5 96.941
[2025-01-19 19:15:18 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.3%
[2025-01-19 19:15:18 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.35%
[2025-01-19 19:15:27 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.346 (9.346)	Loss 0.7122 (0.7122)	Acc@1 86.499 (86.499)	Acc@5 98.145 (98.145)	Mem 34604MB
[2025-01-19 19:15:33 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.320)	Loss 0.9155 (0.8002)	Acc@1 80.981 (84.490)	Acc@5 95.947 (97.017)	Mem 34604MB
[2025-01-19 19:15:33 internimage_b_1k_224] (main.py 575): INFO [Epoch:259] * Acc@1 84.309 Acc@5 97.037
[2025-01-19 19:15:33 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.3%
[2025-01-19 19:15:33 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 19:15:37 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 19:15:37 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.31%
[2025-01-19 19:15:39 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][0/312]	eta 0:10:33 lr 0.000211	time 2.0318 (2.0318)	model_time 0.7342 (0.7342)	loss 3.1109 (3.1109)	grad_norm 1.6073 (1.6073/0.0000)	mem 34604MB
[2025-01-19 19:15:46 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][10/312]	eta 0:04:16 lr 0.000211	time 0.7197 (0.8499)	model_time 0.7192 (0.7317)	loss 1.8550 (2.6884)	grad_norm 2.7528 (3.0745/0.9352)	mem 34604MB
[2025-01-19 19:15:54 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][20/312]	eta 0:03:52 lr 0.000211	time 0.7425 (0.7951)	model_time 0.7421 (0.7330)	loss 2.3438 (2.7789)	grad_norm 4.3744 (3.1282/1.4021)	mem 34604MB
[2025-01-19 19:16:01 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][30/312]	eta 0:03:39 lr 0.000210	time 0.7168 (0.7768)	model_time 0.7166 (0.7346)	loss 1.8670 (2.6800)	grad_norm 3.1142 (3.0579/1.3767)	mem 34604MB
[2025-01-19 19:16:08 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][40/312]	eta 0:03:29 lr 0.000210	time 0.7195 (0.7704)	model_time 0.7190 (0.7384)	loss 3.0940 (2.6932)	grad_norm 2.3433 (2.8890/1.3106)	mem 34604MB
[2025-01-19 19:16:16 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][50/312]	eta 0:03:21 lr 0.000210	time 0.7424 (0.7688)	model_time 0.7422 (0.7431)	loss 2.6343 (2.6625)	grad_norm 2.1088 (2.7838/1.2714)	mem 34604MB
[2025-01-19 19:16:24 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][60/312]	eta 0:03:13 lr 0.000210	time 0.8057 (0.7693)	model_time 0.8055 (0.7477)	loss 3.1755 (2.6319)	grad_norm 2.1552 (2.7414/1.2255)	mem 34604MB
[2025-01-19 19:16:31 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][70/312]	eta 0:03:05 lr 0.000209	time 0.8002 (0.7683)	model_time 0.7998 (0.7497)	loss 2.8335 (2.6622)	grad_norm 3.6768 (2.6432/1.2100)	mem 34604MB
[2025-01-19 19:16:39 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][80/312]	eta 0:02:58 lr 0.000209	time 0.8249 (0.7694)	model_time 0.8247 (0.7531)	loss 2.9410 (2.6515)	grad_norm 2.3439 (2.5527/1.1702)	mem 34604MB
[2025-01-19 19:16:47 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][90/312]	eta 0:02:50 lr 0.000209	time 0.7160 (0.7658)	model_time 0.7159 (0.7513)	loss 2.7793 (2.6665)	grad_norm 1.6490 (2.4705/1.1456)	mem 34604MB
[2025-01-19 19:16:54 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][100/312]	eta 0:02:41 lr 0.000208	time 0.7813 (0.7624)	model_time 0.7811 (0.7492)	loss 2.9005 (2.6881)	grad_norm 1.1966 (2.3926/1.1227)	mem 34604MB
[2025-01-19 19:17:01 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][110/312]	eta 0:02:33 lr 0.000208	time 0.7206 (0.7602)	model_time 0.7204 (0.7482)	loss 2.7946 (2.6888)	grad_norm 1.5342 (2.3902/1.0999)	mem 34604MB
[2025-01-19 19:17:09 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][120/312]	eta 0:02:25 lr 0.000208	time 0.7238 (0.7573)	model_time 0.7237 (0.7463)	loss 2.5044 (2.6800)	grad_norm 1.6196 (2.3613/1.0719)	mem 34604MB
[2025-01-19 19:17:16 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][130/312]	eta 0:02:17 lr 0.000208	time 0.7266 (0.7549)	model_time 0.7264 (0.7447)	loss 2.6485 (2.6697)	grad_norm 1.0704 (2.3425/1.0875)	mem 34604MB
[2025-01-19 19:17:23 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][140/312]	eta 0:02:09 lr 0.000207	time 0.7304 (0.7531)	model_time 0.7302 (0.7436)	loss 2.0833 (2.6615)	grad_norm 2.0273 (2.3255/1.0627)	mem 34604MB
[2025-01-19 19:17:30 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][150/312]	eta 0:02:01 lr 0.000207	time 0.7190 (0.7521)	model_time 0.7185 (0.7432)	loss 3.0077 (2.6668)	grad_norm 1.3302 (2.3086/1.0428)	mem 34604MB
[2025-01-19 19:17:38 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][160/312]	eta 0:01:54 lr 0.000207	time 0.7154 (0.7513)	model_time 0.7153 (0.7429)	loss 2.4574 (2.6754)	grad_norm 1.0976 (2.2660/1.0297)	mem 34604MB
[2025-01-19 19:17:46 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][170/312]	eta 0:01:46 lr 0.000207	time 0.7208 (0.7524)	model_time 0.7204 (0.7445)	loss 3.2081 (2.6777)	grad_norm 4.4001 (2.2992/1.0480)	mem 34604MB
[2025-01-19 19:17:53 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][180/312]	eta 0:01:39 lr 0.000206	time 0.8027 (0.7532)	model_time 0.8023 (0.7457)	loss 2.9337 (2.6613)	grad_norm 2.4137 (2.3210/1.0393)	mem 34604MB
[2025-01-19 19:18:01 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][190/312]	eta 0:01:32 lr 0.000206	time 0.8107 (0.7548)	model_time 0.8105 (0.7477)	loss 2.2662 (2.6613)	grad_norm 2.2673 (2.3179/1.0357)	mem 34604MB
[2025-01-19 19:18:09 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][200/312]	eta 0:01:24 lr 0.000206	time 0.8043 (0.7545)	model_time 0.8039 (0.7477)	loss 2.6422 (2.6558)	grad_norm 2.0514 (2.2939/1.0211)	mem 34604MB
[2025-01-19 19:18:16 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][210/312]	eta 0:01:16 lr 0.000206	time 0.7275 (0.7541)	model_time 0.7273 (0.7477)	loss 2.0187 (2.6501)	grad_norm 2.0588 (2.2958/1.0147)	mem 34604MB
[2025-01-19 19:18:23 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][220/312]	eta 0:01:09 lr 0.000205	time 0.7160 (0.7529)	model_time 0.7155 (0.7467)	loss 3.0671 (2.6608)	grad_norm 3.6324 (2.2989/1.0062)	mem 34604MB
[2025-01-19 19:18:31 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][230/312]	eta 0:01:01 lr 0.000205	time 0.7090 (0.7520)	model_time 0.7085 (0.7461)	loss 2.1257 (2.6507)	grad_norm 1.4605 (2.2768/0.9962)	mem 34604MB
[2025-01-19 19:18:38 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][240/312]	eta 0:00:54 lr 0.000205	time 0.7310 (0.7512)	model_time 0.7308 (0.7455)	loss 2.7672 (2.6497)	grad_norm 1.6489 (2.2674/0.9820)	mem 34604MB
[2025-01-19 19:18:45 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][250/312]	eta 0:00:46 lr 0.000204	time 0.7206 (0.7503)	model_time 0.7202 (0.7448)	loss 3.0919 (2.6600)	grad_norm 1.2773 (2.2427/0.9774)	mem 34604MB
[2025-01-19 19:18:52 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][260/312]	eta 0:00:38 lr 0.000204	time 0.7386 (0.7494)	model_time 0.7381 (0.7441)	loss 2.4618 (2.6706)	grad_norm 2.7484 (2.2469/0.9659)	mem 34604MB
[2025-01-19 19:19:00 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][270/312]	eta 0:00:31 lr 0.000204	time 0.7209 (0.7489)	model_time 0.7204 (0.7438)	loss 2.3514 (2.6711)	grad_norm 2.8701 (2.2351/0.9613)	mem 34604MB
[2025-01-19 19:19:07 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][280/312]	eta 0:00:23 lr 0.000204	time 0.7262 (0.7487)	model_time 0.7258 (0.7438)	loss 2.8656 (2.6650)	grad_norm 3.0433 (2.2747/1.0041)	mem 34604MB
[2025-01-19 19:19:15 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][290/312]	eta 0:00:16 lr 0.000203	time 0.7175 (0.7494)	model_time 0.7173 (0.7446)	loss 2.5286 (2.6658)	grad_norm 2.1072 (2.3019/1.0233)	mem 34604MB
[2025-01-19 19:19:22 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][300/312]	eta 0:00:08 lr 0.000203	time 0.7127 (0.7494)	model_time 0.7126 (0.7448)	loss 2.2578 (2.6623)	grad_norm 4.7209 (2.3292/1.0448)	mem 34604MB
[2025-01-19 19:19:30 internimage_b_1k_224] (main.py 510): INFO Train: [260/300][310/312]	eta 0:00:01 lr 0.000203	time 0.8126 (0.7498)	model_time 0.8125 (0.7453)	loss 2.9395 (2.6548)	grad_norm 2.9709 (2.3114/1.0257)	mem 34604MB
[2025-01-19 19:19:31 internimage_b_1k_224] (main.py 519): INFO EPOCH 260 training takes 0:03:53
[2025-01-19 19:19:31 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_260.pth saving......
[2025-01-19 19:19:34 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_260.pth saved !!!
[2025-01-19 19:19:42 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.295 (7.295)	Loss 0.6925 (0.6925)	Acc@1 86.523 (86.523)	Acc@5 98.096 (98.096)	Mem 34604MB
[2025-01-19 19:19:45 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.947)	Loss 0.8926 (0.7789)	Acc@1 80.933 (84.595)	Acc@5 96.118 (96.953)	Mem 34604MB
[2025-01-19 19:19:45 internimage_b_1k_224] (main.py 575): INFO [Epoch:260] * Acc@1 84.429 Acc@5 96.959
[2025-01-19 19:19:45 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.4%
[2025-01-19 19:19:45 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 19:19:48 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 19:19:48 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.43%
[2025-01-19 19:19:56 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.492 (7.492)	Loss 0.7119 (0.7119)	Acc@1 86.450 (86.450)	Acc@5 98.120 (98.120)	Mem 34604MB
[2025-01-19 19:19:59 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.969)	Loss 0.9147 (0.7997)	Acc@1 80.981 (84.495)	Acc@5 95.972 (97.010)	Mem 34604MB
[2025-01-19 19:19:59 internimage_b_1k_224] (main.py 575): INFO [Epoch:260] * Acc@1 84.315 Acc@5 97.035
[2025-01-19 19:19:59 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.3%
[2025-01-19 19:19:59 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 19:20:03 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 19:20:03 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.32%
[2025-01-19 19:20:05 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][0/312]	eta 0:10:28 lr 0.000203	time 2.0137 (2.0137)	model_time 0.7528 (0.7528)	loss 3.1273 (3.1273)	grad_norm 1.5172 (1.5172/0.0000)	mem 34604MB
[2025-01-19 19:20:13 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][10/312]	eta 0:04:22 lr 0.000203	time 0.7224 (0.8696)	model_time 0.7220 (0.7548)	loss 2.7221 (2.7339)	grad_norm 2.6983 (2.6615/1.0929)	mem 34604MB
[2025-01-19 19:20:20 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][20/312]	eta 0:03:56 lr 0.000202	time 0.7226 (0.8104)	model_time 0.7222 (0.7501)	loss 3.0864 (2.6228)	grad_norm 2.8577 (2.7492/0.9675)	mem 34604MB
[2025-01-19 19:20:27 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][30/312]	eta 0:03:41 lr 0.000202	time 0.7173 (0.7851)	model_time 0.7169 (0.7441)	loss 1.9554 (2.6833)	grad_norm 2.4018 (2.6596/0.9206)	mem 34604MB
[2025-01-19 19:20:35 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][40/312]	eta 0:03:30 lr 0.000202	time 0.7283 (0.7736)	model_time 0.7281 (0.7425)	loss 3.0846 (2.6660)	grad_norm 2.3476 (2.5387/0.8965)	mem 34604MB
[2025-01-19 19:20:42 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][50/312]	eta 0:03:20 lr 0.000202	time 0.7175 (0.7651)	model_time 0.7173 (0.7400)	loss 2.4145 (2.6991)	grad_norm 1.9264 (2.5317/0.8669)	mem 34604MB
[2025-01-19 19:20:49 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][60/312]	eta 0:03:11 lr 0.000201	time 0.7183 (0.7593)	model_time 0.7181 (0.7383)	loss 2.5892 (2.6874)	grad_norm 1.0689 (2.4470/0.8423)	mem 34604MB
[2025-01-19 19:20:57 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][70/312]	eta 0:03:02 lr 0.000201	time 0.7294 (0.7551)	model_time 0.7290 (0.7370)	loss 2.6392 (2.6874)	grad_norm 2.4968 (2.4387/0.8274)	mem 34604MB
[2025-01-19 19:21:04 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][80/312]	eta 0:02:54 lr 0.000201	time 0.7343 (0.7525)	model_time 0.7341 (0.7366)	loss 2.7292 (2.6894)	grad_norm 2.6186 (2.3844/0.8150)	mem 34604MB
[2025-01-19 19:21:11 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][90/312]	eta 0:02:46 lr 0.000200	time 0.7358 (0.7514)	model_time 0.7357 (0.7372)	loss 1.6932 (2.6748)	grad_norm 2.5003 (2.4005/0.8304)	mem 34604MB
[2025-01-19 19:21:19 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][100/312]	eta 0:02:39 lr 0.000200	time 0.7156 (0.7514)	model_time 0.7152 (0.7386)	loss 2.8929 (2.6830)	grad_norm 2.0387 (2.3406/0.8230)	mem 34604MB
[2025-01-19 19:21:26 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][110/312]	eta 0:02:31 lr 0.000200	time 0.8065 (0.7513)	model_time 0.8063 (0.7396)	loss 2.2777 (2.6601)	grad_norm 2.7049 (2.3406/0.8411)	mem 34604MB
[2025-01-19 19:21:34 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][120/312]	eta 0:02:24 lr 0.000200	time 0.7274 (0.7528)	model_time 0.7272 (0.7421)	loss 3.2962 (2.6922)	grad_norm 3.1355 (2.3641/0.8538)	mem 34604MB
[2025-01-19 19:21:42 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][130/312]	eta 0:02:17 lr 0.000199	time 0.7162 (0.7537)	model_time 0.7157 (0.7437)	loss 2.7594 (2.6783)	grad_norm 1.3699 (2.3376/0.8405)	mem 34604MB
[2025-01-19 19:21:49 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][140/312]	eta 0:02:09 lr 0.000199	time 0.7207 (0.7534)	model_time 0.7206 (0.7441)	loss 2.4742 (2.6730)	grad_norm 2.3200 (2.3381/0.8467)	mem 34604MB
[2025-01-19 19:21:57 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][150/312]	eta 0:02:01 lr 0.000199	time 0.7241 (0.7515)	model_time 0.7240 (0.7429)	loss 3.2196 (2.6847)	grad_norm 1.6602 (2.3274/0.8405)	mem 34604MB
[2025-01-19 19:22:04 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][160/312]	eta 0:01:54 lr 0.000199	time 0.7558 (0.7505)	model_time 0.7556 (0.7423)	loss 2.7991 (2.6810)	grad_norm 4.0841 (2.3106/0.8518)	mem 34604MB
[2025-01-19 19:22:11 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][170/312]	eta 0:01:46 lr 0.000198	time 0.7188 (0.7491)	model_time 0.7183 (0.7414)	loss 2.5034 (2.6854)	grad_norm 1.5422 (2.3299/0.8619)	mem 34604MB
[2025-01-19 19:22:18 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][180/312]	eta 0:01:38 lr 0.000198	time 0.7302 (0.7477)	model_time 0.7298 (0.7404)	loss 2.8298 (2.6919)	grad_norm 2.7226 (2.3449/0.8566)	mem 34604MB
[2025-01-19 19:22:26 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][190/312]	eta 0:01:31 lr 0.000198	time 0.7223 (0.7468)	model_time 0.7221 (0.7399)	loss 1.7435 (2.6925)	grad_norm 1.2821 (2.3695/0.9037)	mem 34604MB
[2025-01-19 19:22:33 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][200/312]	eta 0:01:23 lr 0.000198	time 0.7435 (0.7463)	model_time 0.7434 (0.7397)	loss 2.7642 (2.6892)	grad_norm 2.6876 (2.3503/0.8928)	mem 34604MB
[2025-01-19 19:22:40 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][210/312]	eta 0:01:16 lr 0.000197	time 0.7265 (0.7461)	model_time 0.7261 (0.7398)	loss 2.0590 (2.6770)	grad_norm 2.3287 (2.3695/0.8876)	mem 34604MB
[2025-01-19 19:22:48 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][220/312]	eta 0:01:08 lr 0.000197	time 0.7387 (0.7476)	model_time 0.7386 (0.7416)	loss 2.9070 (2.6803)	grad_norm 3.8705 (2.3604/0.8872)	mem 34604MB
[2025-01-19 19:22:56 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][230/312]	eta 0:01:01 lr 0.000197	time 0.8000 (0.7480)	model_time 0.7998 (0.7422)	loss 2.0462 (2.6696)	grad_norm 4.5139 (2.4284/0.9616)	mem 34604MB
[2025-01-19 19:23:04 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][240/312]	eta 0:00:53 lr 0.000197	time 0.7460 (0.7491)	model_time 0.7459 (0.7436)	loss 2.6531 (2.6701)	grad_norm 1.1225 (2.4626/0.9987)	mem 34604MB
[2025-01-19 19:23:11 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][250/312]	eta 0:00:46 lr 0.000196	time 0.7170 (0.7492)	model_time 0.7166 (0.7439)	loss 3.0675 (2.6660)	grad_norm 1.6011 (2.4710/0.9993)	mem 34604MB
[2025-01-19 19:23:19 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][260/312]	eta 0:00:38 lr 0.000196	time 0.7124 (0.7489)	model_time 0.7122 (0.7438)	loss 2.9937 (2.6666)	grad_norm 1.3846 (2.4797/1.0283)	mem 34604MB
[2025-01-19 19:23:26 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][270/312]	eta 0:00:31 lr 0.000196	time 0.7496 (0.7482)	model_time 0.7494 (0.7433)	loss 2.3228 (2.6646)	grad_norm 2.9703 (2.4994/1.0310)	mem 34604MB
[2025-01-19 19:23:33 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][280/312]	eta 0:00:23 lr 0.000196	time 0.7319 (0.7479)	model_time 0.7318 (0.7431)	loss 2.7738 (2.6600)	grad_norm 2.3737 (2.4982/1.0184)	mem 34604MB
[2025-01-19 19:23:40 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][290/312]	eta 0:00:16 lr 0.000195	time 0.7240 (0.7471)	model_time 0.7236 (0.7424)	loss 2.2412 (2.6548)	grad_norm 2.6266 (2.4956/1.0122)	mem 34604MB
[2025-01-19 19:23:48 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][300/312]	eta 0:00:08 lr 0.000195	time 0.7205 (0.7464)	model_time 0.7204 (0.7419)	loss 2.6269 (2.6594)	grad_norm 3.1066 (2.5164/1.0178)	mem 34604MB
[2025-01-19 19:23:55 internimage_b_1k_224] (main.py 510): INFO Train: [261/300][310/312]	eta 0:00:01 lr 0.000195	time 0.7180 (0.7455)	model_time 0.7179 (0.7411)	loss 1.7948 (2.6519)	grad_norm 1.4420 (2.5088/1.0105)	mem 34604MB
[2025-01-19 19:23:56 internimage_b_1k_224] (main.py 519): INFO EPOCH 261 training takes 0:03:52
[2025-01-19 19:23:56 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_261.pth saving......
[2025-01-19 19:23:59 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_261.pth saved !!!
[2025-01-19 19:24:06 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.388 (7.388)	Loss 0.6981 (0.6981)	Acc@1 86.255 (86.255)	Acc@5 98.120 (98.120)	Mem 34604MB
[2025-01-19 19:24:09 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.934)	Loss 0.9004 (0.7842)	Acc@1 80.835 (84.557)	Acc@5 96.118 (96.959)	Mem 34604MB
[2025-01-19 19:24:10 internimage_b_1k_224] (main.py 575): INFO [Epoch:261] * Acc@1 84.385 Acc@5 96.977
[2025-01-19 19:24:10 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.4%
[2025-01-19 19:24:10 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.43%
[2025-01-19 19:24:19 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.097 (9.097)	Loss 0.7116 (0.7116)	Acc@1 86.450 (86.450)	Acc@5 98.120 (98.120)	Mem 34604MB
[2025-01-19 19:24:23 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.234)	Loss 0.9138 (0.7992)	Acc@1 81.104 (84.508)	Acc@5 95.972 (97.013)	Mem 34604MB
[2025-01-19 19:24:23 internimage_b_1k_224] (main.py 575): INFO [Epoch:261] * Acc@1 84.331 Acc@5 97.035
[2025-01-19 19:24:23 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.3%
[2025-01-19 19:24:23 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 19:24:27 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 19:24:27 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.33%
[2025-01-19 19:24:30 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][0/312]	eta 0:11:54 lr 0.000195	time 2.2898 (2.2898)	model_time 0.7363 (0.7363)	loss 2.9111 (2.9111)	grad_norm 2.6842 (2.6842/0.0000)	mem 34604MB
[2025-01-19 19:24:37 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][10/312]	eta 0:04:25 lr 0.000194	time 0.7236 (0.8790)	model_time 0.7234 (0.7376)	loss 3.4158 (2.8685)	grad_norm 1.9712 (1.8620/0.5069)	mem 34604MB
[2025-01-19 19:24:45 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][20/312]	eta 0:03:59 lr 0.000194	time 0.7950 (0.8194)	model_time 0.7945 (0.7451)	loss 2.3922 (2.7175)	grad_norm 1.7215 (1.9275/0.5834)	mem 34604MB
[2025-01-19 19:24:52 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][30/312]	eta 0:03:45 lr 0.000194	time 0.7244 (0.7983)	model_time 0.7239 (0.7479)	loss 2.7193 (2.7291)	grad_norm 3.7269 (2.3438/1.0016)	mem 34604MB
[2025-01-19 19:25:00 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][40/312]	eta 0:03:35 lr 0.000194	time 0.7201 (0.7906)	model_time 0.7199 (0.7524)	loss 1.7894 (2.6717)	grad_norm 2.1998 (2.6712/1.3759)	mem 34604MB
[2025-01-19 19:25:08 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][50/312]	eta 0:03:26 lr 0.000193	time 0.7265 (0.7891)	model_time 0.7263 (0.7583)	loss 2.5554 (2.7007)	grad_norm 1.7655 (2.6975/1.4206)	mem 34604MB
[2025-01-19 19:25:15 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][60/312]	eta 0:03:17 lr 0.000193	time 0.8131 (0.7857)	model_time 0.8130 (0.7599)	loss 2.2328 (2.6894)	grad_norm 3.1728 (2.6372/1.3495)	mem 34604MB
[2025-01-19 19:25:23 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][70/312]	eta 0:03:08 lr 0.000193	time 0.7243 (0.7793)	model_time 0.7241 (0.7571)	loss 3.0421 (2.6530)	grad_norm 1.8180 (2.5890/1.3103)	mem 34604MB
[2025-01-19 19:25:30 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][80/312]	eta 0:02:59 lr 0.000193	time 0.7104 (0.7734)	model_time 0.7099 (0.7539)	loss 2.6592 (2.6276)	grad_norm 3.4299 (2.5549/1.2652)	mem 34604MB
[2025-01-19 19:25:37 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][90/312]	eta 0:02:50 lr 0.000192	time 0.7401 (0.7687)	model_time 0.7400 (0.7513)	loss 2.8870 (2.6500)	grad_norm 1.6615 (2.5101/1.2268)	mem 34604MB
[2025-01-19 19:25:44 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][100/312]	eta 0:02:41 lr 0.000192	time 0.7238 (0.7640)	model_time 0.7234 (0.7483)	loss 2.4993 (2.6478)	grad_norm 3.6977 (2.4755/1.1923)	mem 34604MB
[2025-01-19 19:25:52 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][110/312]	eta 0:02:33 lr 0.000192	time 0.7592 (0.7609)	model_time 0.7587 (0.7465)	loss 2.7482 (2.6523)	grad_norm 2.3253 (2.4631/1.1595)	mem 34604MB
[2025-01-19 19:25:59 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][120/312]	eta 0:02:25 lr 0.000192	time 0.7241 (0.7579)	model_time 0.7239 (0.7447)	loss 2.8045 (2.6427)	grad_norm 3.3939 (2.5034/1.1298)	mem 34604MB
[2025-01-19 19:26:06 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][130/312]	eta 0:02:17 lr 0.000191	time 0.7614 (0.7565)	model_time 0.7609 (0.7443)	loss 2.8213 (2.6491)	grad_norm 1.8400 (2.4543/1.1019)	mem 34604MB
[2025-01-19 19:26:14 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][140/312]	eta 0:02:10 lr 0.000191	time 0.8002 (0.7562)	model_time 0.7998 (0.7448)	loss 2.1791 (2.6550)	grad_norm 1.6924 (2.4764/1.1029)	mem 34604MB
[2025-01-19 19:26:21 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][150/312]	eta 0:02:02 lr 0.000191	time 0.7354 (0.7562)	model_time 0.7353 (0.7456)	loss 2.8405 (2.6652)	grad_norm 2.2498 (2.4874/1.1021)	mem 34604MB
[2025-01-19 19:26:29 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][160/312]	eta 0:01:54 lr 0.000191	time 0.7263 (0.7561)	model_time 0.7258 (0.7461)	loss 2.2120 (2.6766)	grad_norm 5.0332 (2.5259/1.1276)	mem 34604MB
[2025-01-19 19:26:37 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][170/312]	eta 0:01:47 lr 0.000190	time 0.7144 (0.7568)	model_time 0.7142 (0.7473)	loss 3.2019 (2.6737)	grad_norm 4.8511 (2.5666/1.1487)	mem 34604MB
[2025-01-19 19:26:44 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][180/312]	eta 0:01:39 lr 0.000190	time 0.8160 (0.7575)	model_time 0.8158 (0.7485)	loss 2.9459 (2.6782)	grad_norm 2.2403 (2.5737/1.1506)	mem 34604MB
[2025-01-19 19:26:52 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][190/312]	eta 0:01:32 lr 0.000190	time 0.7113 (0.7569)	model_time 0.7112 (0.7484)	loss 2.8299 (2.6849)	grad_norm 5.5540 (2.5832/1.1563)	mem 34604MB
[2025-01-19 19:26:59 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][200/312]	eta 0:01:24 lr 0.000190	time 0.7113 (0.7563)	model_time 0.7111 (0.7483)	loss 2.8406 (2.6859)	grad_norm 2.2071 (2.5864/1.1627)	mem 34604MB
[2025-01-19 19:27:07 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][210/312]	eta 0:01:17 lr 0.000189	time 0.7283 (0.7550)	model_time 0.7281 (0.7473)	loss 2.0079 (2.6765)	grad_norm 2.8239 (2.5609/1.1493)	mem 34604MB
[2025-01-19 19:27:14 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][220/312]	eta 0:01:09 lr 0.000189	time 0.7444 (0.7540)	model_time 0.7440 (0.7466)	loss 2.4554 (2.6832)	grad_norm 2.3822 (2.5613/1.1448)	mem 34604MB
[2025-01-19 19:27:21 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][230/312]	eta 0:01:01 lr 0.000189	time 0.7406 (0.7530)	model_time 0.7405 (0.7459)	loss 2.7091 (2.6862)	grad_norm 1.6940 (2.5495/1.1451)	mem 34604MB
[2025-01-19 19:27:29 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][240/312]	eta 0:00:54 lr 0.000189	time 0.7167 (0.7521)	model_time 0.7166 (0.7453)	loss 2.4978 (2.6820)	grad_norm 2.3304 (2.5363/1.1315)	mem 34604MB
[2025-01-19 19:27:36 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][250/312]	eta 0:00:46 lr 0.000188	time 0.7280 (0.7514)	model_time 0.7276 (0.7448)	loss 2.7037 (2.6727)	grad_norm 1.5974 (2.5154/1.1187)	mem 34604MB
[2025-01-19 19:27:43 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][260/312]	eta 0:00:39 lr 0.000188	time 0.7963 (0.7510)	model_time 0.7962 (0.7447)	loss 3.0652 (2.6759)	grad_norm 2.5398 (2.5126/1.1022)	mem 34604MB
[2025-01-19 19:27:51 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][270/312]	eta 0:00:31 lr 0.000188	time 0.7194 (0.7518)	model_time 0.7189 (0.7457)	loss 2.9180 (2.6783)	grad_norm 1.7958 (2.5051/1.0906)	mem 34604MB
[2025-01-19 19:27:59 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][280/312]	eta 0:00:24 lr 0.000188	time 0.7178 (0.7518)	model_time 0.7176 (0.7460)	loss 3.1427 (2.6722)	grad_norm 1.6708 (2.5015/1.0971)	mem 34604MB
[2025-01-19 19:28:07 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][290/312]	eta 0:00:16 lr 0.000187	time 0.7190 (0.7536)	model_time 0.7185 (0.7479)	loss 2.8442 (2.6740)	grad_norm 3.3464 (2.5311/1.1151)	mem 34604MB
[2025-01-19 19:28:14 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][300/312]	eta 0:00:09 lr 0.000187	time 0.7145 (0.7537)	model_time 0.7144 (0.7482)	loss 2.1846 (2.6737)	grad_norm 1.8400 (2.5255/1.1123)	mem 34604MB
[2025-01-19 19:28:22 internimage_b_1k_224] (main.py 510): INFO Train: [262/300][310/312]	eta 0:00:01 lr 0.000187	time 0.7223 (0.7531)	model_time 0.7222 (0.7478)	loss 2.5667 (2.6697)	grad_norm 2.8755 (2.5880/1.1463)	mem 34604MB
[2025-01-19 19:28:22 internimage_b_1k_224] (main.py 519): INFO EPOCH 262 training takes 0:03:55
[2025-01-19 19:28:22 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_262.pth saving......
[2025-01-19 19:28:25 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_262.pth saved !!!
[2025-01-19 19:28:33 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.311 (7.311)	Loss 0.6764 (0.6764)	Acc@1 86.621 (86.621)	Acc@5 98.267 (98.267)	Mem 34604MB
[2025-01-19 19:28:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.183 (0.942)	Loss 0.8753 (0.7713)	Acc@1 81.519 (84.621)	Acc@5 96.094 (96.973)	Mem 34604MB
[2025-01-19 19:28:36 internimage_b_1k_224] (main.py 575): INFO [Epoch:262] * Acc@1 84.437 Acc@5 96.977
[2025-01-19 19:28:36 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.4%
[2025-01-19 19:28:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 19:28:39 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 19:28:39 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.44%
[2025-01-19 19:28:47 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.497 (7.497)	Loss 0.7115 (0.7115)	Acc@1 86.450 (86.450)	Acc@5 98.120 (98.120)	Mem 34604MB
[2025-01-19 19:28:50 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.946)	Loss 0.9130 (0.7987)	Acc@1 81.128 (84.541)	Acc@5 95.923 (97.026)	Mem 34604MB
[2025-01-19 19:28:50 internimage_b_1k_224] (main.py 575): INFO [Epoch:262] * Acc@1 84.361 Acc@5 97.043
[2025-01-19 19:28:50 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.4%
[2025-01-19 19:28:50 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 19:28:54 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 19:28:54 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.36%
[2025-01-19 19:28:56 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][0/312]	eta 0:11:16 lr 0.000187	time 2.1675 (2.1675)	model_time 0.7302 (0.7302)	loss 3.0833 (3.0833)	grad_norm 3.1183 (3.1183/0.0000)	mem 34604MB
[2025-01-19 19:29:04 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][10/312]	eta 0:04:25 lr 0.000187	time 0.7222 (0.8787)	model_time 0.7217 (0.7477)	loss 3.2850 (2.6729)	grad_norm 1.5275 (2.3604/0.7436)	mem 34604MB
[2025-01-19 19:29:11 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][20/312]	eta 0:03:56 lr 0.000186	time 0.7565 (0.8104)	model_time 0.7563 (0.7416)	loss 2.9729 (2.6470)	grad_norm 3.0508 (2.2471/0.6833)	mem 34604MB
[2025-01-19 19:29:19 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][30/312]	eta 0:03:40 lr 0.000186	time 0.7142 (0.7829)	model_time 0.7140 (0.7362)	loss 1.8177 (2.6189)	grad_norm 2.7869 (2.1279/0.6407)	mem 34604MB
[2025-01-19 19:29:26 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][40/312]	eta 0:03:29 lr 0.000186	time 0.7207 (0.7694)	model_time 0.7203 (0.7340)	loss 2.5204 (2.6157)	grad_norm 1.6561 (2.1296/0.6600)	mem 34604MB
[2025-01-19 19:29:33 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][50/312]	eta 0:03:19 lr 0.000186	time 0.7214 (0.7612)	model_time 0.7212 (0.7327)	loss 2.5729 (2.6205)	grad_norm 1.3026 (2.1487/0.6656)	mem 34604MB
[2025-01-19 19:29:40 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][60/312]	eta 0:03:10 lr 0.000185	time 0.7128 (0.7561)	model_time 0.7127 (0.7322)	loss 3.0088 (2.5936)	grad_norm 1.6717 (2.1996/0.7093)	mem 34604MB
[2025-01-19 19:29:48 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][70/312]	eta 0:03:02 lr 0.000185	time 0.7972 (0.7550)	model_time 0.7967 (0.7344)	loss 3.3820 (2.6092)	grad_norm 1.2527 (2.1019/0.7131)	mem 34604MB
[2025-01-19 19:29:56 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][80/312]	eta 0:02:55 lr 0.000185	time 0.7968 (0.7579)	model_time 0.7966 (0.7398)	loss 2.8792 (2.5989)	grad_norm 2.8871 (2.0687/0.6945)	mem 34604MB
[2025-01-19 19:30:03 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][90/312]	eta 0:02:48 lr 0.000185	time 0.9918 (0.7599)	model_time 0.9913 (0.7437)	loss 3.1903 (2.6030)	grad_norm 2.7070 (2.1053/0.6896)	mem 34604MB
[2025-01-19 19:30:11 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][100/312]	eta 0:02:41 lr 0.000184	time 0.7337 (0.7614)	model_time 0.7332 (0.7468)	loss 2.8367 (2.6097)	grad_norm 1.3627 (2.1291/0.7038)	mem 34604MB
[2025-01-19 19:30:19 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][110/312]	eta 0:02:33 lr 0.000184	time 0.8128 (0.7613)	model_time 0.8123 (0.7480)	loss 3.0793 (2.6118)	grad_norm 2.4312 (2.1943/0.7331)	mem 34604MB
[2025-01-19 19:30:26 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][120/312]	eta 0:02:26 lr 0.000184	time 0.7232 (0.7616)	model_time 0.7228 (0.7494)	loss 2.8111 (2.6175)	grad_norm 1.8922 (2.2173/0.7256)	mem 34604MB
[2025-01-19 19:30:34 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][130/312]	eta 0:02:18 lr 0.000184	time 0.8026 (0.7608)	model_time 0.8022 (0.7495)	loss 1.8910 (2.6189)	grad_norm 3.6777 (2.2540/0.7419)	mem 34604MB
[2025-01-19 19:30:41 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][140/312]	eta 0:02:10 lr 0.000183	time 0.7240 (0.7589)	model_time 0.7236 (0.7483)	loss 2.9582 (2.6296)	grad_norm 1.8038 (2.2354/0.7374)	mem 34604MB
[2025-01-19 19:30:49 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][150/312]	eta 0:02:02 lr 0.000183	time 0.7245 (0.7569)	model_time 0.7243 (0.7470)	loss 3.1303 (2.6352)	grad_norm 1.7623 (2.2327/0.7344)	mem 34604MB
[2025-01-19 19:30:56 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][160/312]	eta 0:01:54 lr 0.000183	time 0.7184 (0.7547)	model_time 0.7183 (0.7455)	loss 2.5190 (2.6206)	grad_norm 1.7964 (2.2554/0.7664)	mem 34604MB
[2025-01-19 19:31:03 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][170/312]	eta 0:01:46 lr 0.000183	time 0.7116 (0.7532)	model_time 0.7112 (0.7444)	loss 2.7048 (2.6232)	grad_norm 2.7577 (2.2605/0.8333)	mem 34604MB
[2025-01-19 19:31:10 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][180/312]	eta 0:01:39 lr 0.000182	time 0.7174 (0.7523)	model_time 0.7173 (0.7440)	loss 2.6973 (2.6222)	grad_norm 2.1289 (2.2484/0.8264)	mem 34604MB
[2025-01-19 19:31:18 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][190/312]	eta 0:01:31 lr 0.000182	time 0.8100 (0.7516)	model_time 0.8096 (0.7437)	loss 2.0343 (2.6230)	grad_norm 3.4861 (2.3109/0.8707)	mem 34604MB
[2025-01-19 19:31:26 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][200/312]	eta 0:01:24 lr 0.000182	time 0.8004 (0.7528)	model_time 0.7999 (0.7453)	loss 2.9162 (2.6362)	grad_norm 4.4515 (2.3193/0.8996)	mem 34604MB
[2025-01-19 19:31:33 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][210/312]	eta 0:01:16 lr 0.000182	time 0.8044 (0.7528)	model_time 0.8040 (0.7456)	loss 1.7178 (2.6411)	grad_norm 1.5306 (2.2985/0.8927)	mem 34604MB
[2025-01-19 19:31:41 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][220/312]	eta 0:01:09 lr 0.000181	time 0.7221 (0.7534)	model_time 0.7220 (0.7465)	loss 2.6546 (2.6407)	grad_norm 2.2949 (2.2772/0.8827)	mem 34604MB
[2025-01-19 19:31:49 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][230/312]	eta 0:01:01 lr 0.000181	time 0.8117 (0.7547)	model_time 0.8112 (0.7481)	loss 2.5125 (2.6365)	grad_norm 2.3399 (2.2563/0.8730)	mem 34604MB
[2025-01-19 19:31:56 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][240/312]	eta 0:00:54 lr 0.000181	time 0.7210 (0.7544)	model_time 0.7206 (0.7481)	loss 2.3078 (2.6285)	grad_norm 1.6275 (2.2414/0.8660)	mem 34604MB
[2025-01-19 19:32:04 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][250/312]	eta 0:00:46 lr 0.000181	time 0.8102 (0.7542)	model_time 0.8097 (0.7481)	loss 2.5968 (2.6386)	grad_norm 1.7308 (2.2517/0.8871)	mem 34604MB
[2025-01-19 19:32:11 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][260/312]	eta 0:00:39 lr 0.000180	time 0.7251 (0.7530)	model_time 0.7247 (0.7472)	loss 2.8979 (2.6408)	grad_norm 2.5183 (2.2623/0.8883)	mem 34604MB
[2025-01-19 19:32:18 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][270/312]	eta 0:00:31 lr 0.000180	time 0.7161 (0.7521)	model_time 0.7157 (0.7465)	loss 2.1202 (2.6397)	grad_norm 3.4591 (2.2626/0.8924)	mem 34604MB
[2025-01-19 19:32:25 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][280/312]	eta 0:00:24 lr 0.000180	time 0.7307 (0.7515)	model_time 0.7306 (0.7460)	loss 2.6670 (2.6464)	grad_norm 5.0845 (2.2780/0.9048)	mem 34604MB
[2025-01-19 19:32:33 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][290/312]	eta 0:00:16 lr 0.000180	time 0.7391 (0.7507)	model_time 0.7387 (0.7454)	loss 3.0932 (2.6484)	grad_norm 1.1592 (2.2978/0.9491)	mem 34604MB
[2025-01-19 19:32:40 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][300/312]	eta 0:00:09 lr 0.000179	time 0.7976 (0.7502)	model_time 0.7975 (0.7450)	loss 1.9228 (2.6450)	grad_norm 1.7806 (2.3052/0.9520)	mem 34604MB
[2025-01-19 19:32:47 internimage_b_1k_224] (main.py 510): INFO Train: [263/300][310/312]	eta 0:00:01 lr 0.000179	time 0.7147 (0.7493)	model_time 0.7146 (0.7444)	loss 1.9058 (2.6305)	grad_norm 4.3562 (2.3454/0.9977)	mem 34604MB
[2025-01-19 19:32:48 internimage_b_1k_224] (main.py 519): INFO EPOCH 263 training takes 0:03:53
[2025-01-19 19:32:48 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_263.pth saving......
[2025-01-19 19:32:51 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_263.pth saved !!!
[2025-01-19 19:32:59 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.176 (7.176)	Loss 0.6903 (0.6903)	Acc@1 86.816 (86.816)	Acc@5 98.096 (98.096)	Mem 34604MB
[2025-01-19 19:33:02 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.944)	Loss 0.8871 (0.7792)	Acc@1 81.445 (84.650)	Acc@5 95.996 (96.953)	Mem 34604MB
[2025-01-19 19:33:02 internimage_b_1k_224] (main.py 575): INFO [Epoch:263] * Acc@1 84.425 Acc@5 96.947
[2025-01-19 19:33:02 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.4%
[2025-01-19 19:33:02 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.44%
[2025-01-19 19:33:11 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.361 (9.361)	Loss 0.7113 (0.7113)	Acc@1 86.499 (86.499)	Acc@5 98.120 (98.120)	Mem 34604MB
[2025-01-19 19:33:16 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.250)	Loss 0.9123 (0.7983)	Acc@1 81.128 (84.555)	Acc@5 95.923 (97.035)	Mem 34604MB
[2025-01-19 19:33:16 internimage_b_1k_224] (main.py 575): INFO [Epoch:263] * Acc@1 84.375 Acc@5 97.051
[2025-01-19 19:33:16 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.4%
[2025-01-19 19:33:16 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 19:33:20 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 19:33:20 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.37%
[2025-01-19 19:33:22 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][0/312]	eta 0:11:39 lr 0.000179	time 2.2435 (2.2435)	model_time 0.7444 (0.7444)	loss 2.5010 (2.5010)	grad_norm 1.3169 (1.3169/0.0000)	mem 34604MB
[2025-01-19 19:33:30 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][10/312]	eta 0:04:36 lr 0.000179	time 0.8379 (0.9164)	model_time 0.8374 (0.7797)	loss 2.8581 (2.7271)	grad_norm 1.3911 (2.0180/0.4837)	mem 34604MB
[2025-01-19 19:33:38 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][20/312]	eta 0:04:03 lr 0.000179	time 0.7314 (0.8355)	model_time 0.7313 (0.7637)	loss 2.8123 (2.6984)	grad_norm 1.7158 (2.2467/0.7019)	mem 34604MB
[2025-01-19 19:33:45 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][30/312]	eta 0:03:50 lr 0.000178	time 0.7456 (0.8171)	model_time 0.7454 (0.7684)	loss 2.9673 (2.6768)	grad_norm 1.5188 (2.1573/0.6955)	mem 34604MB
[2025-01-19 19:33:53 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][40/312]	eta 0:03:38 lr 0.000178	time 0.7201 (0.8048)	model_time 0.7197 (0.7679)	loss 2.8614 (2.6695)	grad_norm 3.2353 (2.2544/0.7638)	mem 34604MB
[2025-01-19 19:34:01 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][50/312]	eta 0:03:27 lr 0.000178	time 0.7167 (0.7930)	model_time 0.7162 (0.7633)	loss 2.3909 (2.6882)	grad_norm 1.2569 (2.1869/0.7231)	mem 34604MB
[2025-01-19 19:34:08 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][60/312]	eta 0:03:17 lr 0.000178	time 0.7206 (0.7838)	model_time 0.7204 (0.7589)	loss 1.5351 (2.6469)	grad_norm 1.7163 (2.3989/0.9634)	mem 34604MB
[2025-01-19 19:34:15 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][70/312]	eta 0:03:07 lr 0.000177	time 0.7430 (0.7757)	model_time 0.7425 (0.7543)	loss 2.6952 (2.6487)	grad_norm 1.6940 (2.4350/0.9937)	mem 34604MB
[2025-01-19 19:34:23 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][80/312]	eta 0:02:58 lr 0.000177	time 0.7190 (0.7710)	model_time 0.7188 (0.7521)	loss 2.9477 (2.6362)	grad_norm 3.2700 (2.4618/1.0091)	mem 34604MB
[2025-01-19 19:34:30 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][90/312]	eta 0:02:50 lr 0.000177	time 0.7316 (0.7668)	model_time 0.7315 (0.7500)	loss 2.0843 (2.6303)	grad_norm 3.4104 (2.5253/1.0245)	mem 34604MB
[2025-01-19 19:34:37 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][100/312]	eta 0:02:41 lr 0.000177	time 0.7450 (0.7633)	model_time 0.7449 (0.7481)	loss 2.8774 (2.6478)	grad_norm 1.1858 (2.5820/1.0732)	mem 34604MB
[2025-01-19 19:34:45 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][110/312]	eta 0:02:33 lr 0.000176	time 0.7098 (0.7613)	model_time 0.7094 (0.7474)	loss 2.2768 (2.6406)	grad_norm 1.9097 (2.6388/1.2019)	mem 34604MB
[2025-01-19 19:34:52 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][120/312]	eta 0:02:25 lr 0.000176	time 0.7306 (0.7590)	model_time 0.7304 (0.7463)	loss 3.0617 (2.6408)	grad_norm 2.8345 (2.5995/1.1745)	mem 34604MB
[2025-01-19 19:35:00 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][130/312]	eta 0:02:18 lr 0.000176	time 0.7318 (0.7604)	model_time 0.7316 (0.7486)	loss 3.0569 (2.6621)	grad_norm 2.5478 (2.5836/1.1717)	mem 34604MB
[2025-01-19 19:35:07 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][140/312]	eta 0:02:10 lr 0.000176	time 0.7568 (0.7608)	model_time 0.7563 (0.7498)	loss 3.3220 (2.6585)	grad_norm 3.9814 (2.6055/1.1665)	mem 34604MB
[2025-01-19 19:35:15 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][150/312]	eta 0:02:03 lr 0.000175	time 0.7328 (0.7622)	model_time 0.7327 (0.7519)	loss 3.1506 (2.6518)	grad_norm 3.1670 (2.6134/1.1589)	mem 34604MB
[2025-01-19 19:35:23 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][160/312]	eta 0:01:55 lr 0.000175	time 0.7113 (0.7629)	model_time 0.7108 (0.7532)	loss 1.8645 (2.6538)	grad_norm 1.7087 (2.6065/1.1523)	mem 34604MB
[2025-01-19 19:35:30 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][170/312]	eta 0:01:48 lr 0.000175	time 0.7220 (0.7617)	model_time 0.7216 (0.7526)	loss 3.0318 (2.6641)	grad_norm 2.1255 (2.5880/1.1302)	mem 34604MB
[2025-01-19 19:35:38 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][180/312]	eta 0:01:40 lr 0.000175	time 0.7217 (0.7601)	model_time 0.7215 (0.7514)	loss 2.5561 (2.6654)	grad_norm 1.8356 (2.5861/1.1262)	mem 34604MB
[2025-01-19 19:35:45 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][190/312]	eta 0:01:32 lr 0.000174	time 0.7268 (0.7584)	model_time 0.7263 (0.7502)	loss 3.0005 (2.6606)	grad_norm 4.9577 (2.5999/1.1354)	mem 34604MB
[2025-01-19 19:35:52 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][200/312]	eta 0:01:24 lr 0.000174	time 0.7399 (0.7573)	model_time 0.7397 (0.7495)	loss 2.7135 (2.6465)	grad_norm 2.1426 (2.5910/1.1257)	mem 34604MB
[2025-01-19 19:36:00 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][210/312]	eta 0:01:17 lr 0.000174	time 0.7472 (0.7562)	model_time 0.7471 (0.7487)	loss 2.6875 (2.6529)	grad_norm 2.3777 (2.5636/1.1104)	mem 34604MB
[2025-01-19 19:36:07 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][220/312]	eta 0:01:09 lr 0.000174	time 0.7166 (0.7551)	model_time 0.7165 (0.7479)	loss 1.9734 (2.6469)	grad_norm 4.1116 (2.5598/1.0970)	mem 34604MB
[2025-01-19 19:36:14 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][230/312]	eta 0:01:01 lr 0.000173	time 0.7462 (0.7544)	model_time 0.7461 (0.7476)	loss 2.7435 (2.6437)	grad_norm 1.2059 (2.5331/1.0868)	mem 34604MB
[2025-01-19 19:36:22 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][240/312]	eta 0:00:54 lr 0.000173	time 0.7277 (0.7537)	model_time 0.7273 (0.7472)	loss 2.7462 (2.6448)	grad_norm 1.9141 (2.5277/1.0825)	mem 34604MB
[2025-01-19 19:36:29 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][250/312]	eta 0:00:46 lr 0.000173	time 0.7348 (0.7545)	model_time 0.7347 (0.7482)	loss 2.9028 (2.6490)	grad_norm 5.8831 (2.5940/1.1387)	mem 34604MB
[2025-01-19 19:36:37 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][260/312]	eta 0:00:39 lr 0.000173	time 0.7276 (0.7551)	model_time 0.7275 (0.7490)	loss 2.5703 (2.6386)	grad_norm 2.9064 (2.6262/1.1444)	mem 34604MB
[2025-01-19 19:36:45 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][270/312]	eta 0:00:31 lr 0.000173	time 0.7186 (0.7560)	model_time 0.7185 (0.7501)	loss 2.8466 (2.6410)	grad_norm 2.6210 (2.6086/1.1344)	mem 34604MB
[2025-01-19 19:36:53 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][280/312]	eta 0:00:24 lr 0.000172	time 0.7180 (0.7562)	model_time 0.7175 (0.7505)	loss 2.0052 (2.6375)	grad_norm 2.8388 (2.6075/1.1212)	mem 34604MB
[2025-01-19 19:37:00 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][290/312]	eta 0:00:16 lr 0.000172	time 0.7204 (0.7559)	model_time 0.7199 (0.7504)	loss 3.2424 (2.6388)	grad_norm 4.7566 (2.6056/1.1140)	mem 34604MB
[2025-01-19 19:37:07 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][300/312]	eta 0:00:09 lr 0.000172	time 0.7141 (0.7549)	model_time 0.7140 (0.7495)	loss 2.6284 (2.6345)	grad_norm 1.8148 (2.6136/1.1200)	mem 34604MB
[2025-01-19 19:37:15 internimage_b_1k_224] (main.py 510): INFO Train: [264/300][310/312]	eta 0:00:01 lr 0.000172	time 0.7259 (0.7540)	model_time 0.7258 (0.7488)	loss 2.1140 (2.6344)	grad_norm 0.8176 (2.6182/1.1257)	mem 34604MB
[2025-01-19 19:37:15 internimage_b_1k_224] (main.py 519): INFO EPOCH 264 training takes 0:03:55
[2025-01-19 19:37:15 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_264.pth saving......
[2025-01-19 19:37:18 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_264.pth saved !!!
[2025-01-19 19:37:26 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.225 (7.225)	Loss 0.6906 (0.6906)	Acc@1 86.816 (86.816)	Acc@5 97.925 (97.925)	Mem 34604MB
[2025-01-19 19:37:29 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.942)	Loss 0.8919 (0.7780)	Acc@1 81.128 (84.699)	Acc@5 96.191 (96.999)	Mem 34604MB
[2025-01-19 19:37:29 internimage_b_1k_224] (main.py 575): INFO [Epoch:264] * Acc@1 84.529 Acc@5 97.007
[2025-01-19 19:37:29 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.5%
[2025-01-19 19:37:29 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 19:37:32 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 19:37:32 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.53%
[2025-01-19 19:37:40 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.368 (7.368)	Loss 0.7111 (0.7111)	Acc@1 86.572 (86.572)	Acc@5 98.145 (98.145)	Mem 34604MB
[2025-01-19 19:37:43 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.954)	Loss 0.9116 (0.7978)	Acc@1 81.152 (84.570)	Acc@5 95.996 (97.046)	Mem 34604MB
[2025-01-19 19:37:43 internimage_b_1k_224] (main.py 575): INFO [Epoch:264] * Acc@1 84.381 Acc@5 97.067
[2025-01-19 19:37:43 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.4%
[2025-01-19 19:37:43 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 19:37:47 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 19:37:47 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.38%
[2025-01-19 19:37:49 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][0/312]	eta 0:10:12 lr 0.000172	time 1.9626 (1.9626)	model_time 0.7424 (0.7424)	loss 2.7790 (2.7790)	grad_norm 2.1217 (2.1217/0.0000)	mem 34604MB
[2025-01-19 19:37:57 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][10/312]	eta 0:04:16 lr 0.000171	time 0.7341 (0.8500)	model_time 0.7340 (0.7388)	loss 2.7533 (2.5610)	grad_norm 1.5000 (1.7370/0.4388)	mem 34604MB
[2025-01-19 19:38:04 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][20/312]	eta 0:03:51 lr 0.000171	time 0.7280 (0.7932)	model_time 0.7276 (0.7348)	loss 2.6474 (2.5239)	grad_norm 3.1206 (1.7510/0.5765)	mem 34604MB
[2025-01-19 19:38:11 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][30/312]	eta 0:03:38 lr 0.000171	time 0.7199 (0.7737)	model_time 0.7194 (0.7340)	loss 2.8974 (2.5671)	grad_norm 0.9474 (1.9660/0.7533)	mem 34604MB
[2025-01-19 19:38:19 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][40/312]	eta 0:03:28 lr 0.000171	time 0.7201 (0.7654)	model_time 0.7199 (0.7353)	loss 2.6797 (2.6475)	grad_norm 4.4539 (2.0922/0.8241)	mem 34604MB
[2025-01-19 19:38:26 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][50/312]	eta 0:03:19 lr 0.000170	time 0.7321 (0.7615)	model_time 0.7317 (0.7373)	loss 3.2096 (2.6561)	grad_norm 4.0960 (2.2179/0.9157)	mem 34604MB
[2025-01-19 19:38:34 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][60/312]	eta 0:03:12 lr 0.000170	time 0.8077 (0.7634)	model_time 0.8073 (0.7431)	loss 3.0796 (2.6711)	grad_norm 4.9914 (2.3947/1.1171)	mem 34604MB
[2025-01-19 19:38:41 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][70/312]	eta 0:03:04 lr 0.000170	time 0.7161 (0.7619)	model_time 0.7160 (0.7443)	loss 1.9335 (2.6718)	grad_norm 1.7166 (2.3902/1.1294)	mem 34604MB
[2025-01-19 19:38:49 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][80/312]	eta 0:02:57 lr 0.000170	time 0.8263 (0.7663)	model_time 0.8261 (0.7509)	loss 2.9168 (2.6780)	grad_norm 1.2536 (2.3452/1.0861)	mem 34604MB
[2025-01-19 19:38:57 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][90/312]	eta 0:02:49 lr 0.000169	time 0.8277 (0.7646)	model_time 0.8275 (0.7509)	loss 2.9998 (2.6972)	grad_norm 2.7275 (2.3138/1.0414)	mem 34604MB
[2025-01-19 19:39:04 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][100/312]	eta 0:02:41 lr 0.000169	time 0.7666 (0.7628)	model_time 0.7664 (0.7504)	loss 2.8871 (2.6943)	grad_norm 2.7906 (2.2861/1.0217)	mem 34604MB
[2025-01-19 19:39:12 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][110/312]	eta 0:02:33 lr 0.000169	time 0.7358 (0.7599)	model_time 0.7353 (0.7486)	loss 2.9803 (2.6999)	grad_norm 1.4626 (2.2237/1.0013)	mem 34604MB
[2025-01-19 19:39:19 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][120/312]	eta 0:02:25 lr 0.000169	time 0.7570 (0.7581)	model_time 0.7569 (0.7477)	loss 2.8342 (2.6837)	grad_norm 3.0589 (2.2207/0.9762)	mem 34604MB
[2025-01-19 19:39:26 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][130/312]	eta 0:02:17 lr 0.000168	time 0.7238 (0.7570)	model_time 0.7234 (0.7474)	loss 2.0028 (2.6839)	grad_norm 3.2270 (2.2281/0.9589)	mem 34604MB
[2025-01-19 19:39:34 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][140/312]	eta 0:02:09 lr 0.000168	time 0.7351 (0.7547)	model_time 0.7346 (0.7457)	loss 3.1497 (2.6846)	grad_norm 2.3730 (2.2949/0.9730)	mem 34604MB
[2025-01-19 19:39:41 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][150/312]	eta 0:02:01 lr 0.000168	time 0.7223 (0.7528)	model_time 0.7219 (0.7443)	loss 2.9687 (2.6931)	grad_norm 3.1434 (2.2950/0.9543)	mem 34604MB
[2025-01-19 19:39:48 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][160/312]	eta 0:01:54 lr 0.000168	time 0.7199 (0.7517)	model_time 0.7198 (0.7437)	loss 1.9622 (2.6799)	grad_norm 1.4587 (2.2827/0.9456)	mem 34604MB
[2025-01-19 19:39:56 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][170/312]	eta 0:01:46 lr 0.000167	time 0.7458 (0.7509)	model_time 0.7457 (0.7434)	loss 3.3005 (2.6873)	grad_norm 2.0445 (2.2901/0.9253)	mem 34604MB
[2025-01-19 19:40:03 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][180/312]	eta 0:01:39 lr 0.000167	time 0.7408 (0.7522)	model_time 0.7404 (0.7451)	loss 2.9358 (2.6868)	grad_norm 1.4629 (2.2794/0.9221)	mem 34604MB
[2025-01-19 19:40:11 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][190/312]	eta 0:01:31 lr 0.000167	time 0.7119 (0.7525)	model_time 0.7117 (0.7457)	loss 2.9211 (2.6868)	grad_norm 2.9701 (2.2613/0.9091)	mem 34604MB
[2025-01-19 19:40:19 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][200/312]	eta 0:01:24 lr 0.000167	time 0.8232 (0.7528)	model_time 0.8228 (0.7464)	loss 2.5309 (2.6905)	grad_norm 4.0025 (2.2933/0.9556)	mem 34604MB
[2025-01-19 19:40:26 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][210/312]	eta 0:01:16 lr 0.000167	time 0.8106 (0.7527)	model_time 0.8105 (0.7466)	loss 2.7412 (2.6938)	grad_norm 2.5589 (2.3019/0.9540)	mem 34604MB
[2025-01-19 19:40:33 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][220/312]	eta 0:01:09 lr 0.000166	time 0.7256 (0.7524)	model_time 0.7254 (0.7465)	loss 3.3215 (2.6935)	grad_norm 3.6240 (2.3174/0.9501)	mem 34604MB
[2025-01-19 19:40:41 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][230/312]	eta 0:01:01 lr 0.000166	time 0.7122 (0.7516)	model_time 0.7120 (0.7460)	loss 2.8969 (2.6829)	grad_norm 2.7580 (2.3259/0.9371)	mem 34604MB
[2025-01-19 19:40:48 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][240/312]	eta 0:00:54 lr 0.000166	time 0.7395 (0.7511)	model_time 0.7394 (0.7457)	loss 1.9572 (2.6768)	grad_norm 2.6944 (2.3556/0.9554)	mem 34604MB
[2025-01-19 19:40:56 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][250/312]	eta 0:00:46 lr 0.000166	time 0.7198 (0.7505)	model_time 0.7193 (0.7453)	loss 3.0896 (2.6724)	grad_norm 2.6180 (2.3562/0.9516)	mem 34604MB
[2025-01-19 19:41:03 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][260/312]	eta 0:00:38 lr 0.000165	time 0.7536 (0.7499)	model_time 0.7532 (0.7449)	loss 2.5086 (2.6631)	grad_norm 3.0601 (2.3869/0.9575)	mem 34604MB
[2025-01-19 19:41:10 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][270/312]	eta 0:00:31 lr 0.000165	time 0.7210 (0.7490)	model_time 0.7205 (0.7441)	loss 1.7942 (2.6571)	grad_norm 3.4518 (2.3788/0.9496)	mem 34604MB
[2025-01-19 19:41:18 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][280/312]	eta 0:00:23 lr 0.000165	time 0.7247 (0.7487)	model_time 0.7245 (0.7440)	loss 1.9299 (2.6540)	grad_norm 1.4730 (2.3630/0.9481)	mem 34604MB
[2025-01-19 19:41:25 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][290/312]	eta 0:00:16 lr 0.000165	time 0.7300 (0.7483)	model_time 0.7295 (0.7438)	loss 2.9727 (2.6562)	grad_norm 1.8455 (2.3532/0.9394)	mem 34604MB
[2025-01-19 19:41:33 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][300/312]	eta 0:00:08 lr 0.000164	time 0.7194 (0.7493)	model_time 0.7193 (0.7449)	loss 2.7241 (2.6566)	grad_norm 3.1578 (2.3543/0.9377)	mem 34604MB
[2025-01-19 19:41:40 internimage_b_1k_224] (main.py 510): INFO Train: [265/300][310/312]	eta 0:00:01 lr 0.000164	time 0.7166 (0.7490)	model_time 0.7165 (0.7447)	loss 2.8427 (2.6550)	grad_norm 4.7491 (2.3910/0.9583)	mem 34604MB
[2025-01-19 19:41:41 internimage_b_1k_224] (main.py 519): INFO EPOCH 265 training takes 0:03:53
[2025-01-19 19:41:41 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_265.pth saving......
[2025-01-19 19:41:44 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_265.pth saved !!!
[2025-01-19 19:41:52 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.438 (7.438)	Loss 0.6824 (0.6824)	Acc@1 86.353 (86.353)	Acc@5 98.145 (98.145)	Mem 34604MB
[2025-01-19 19:41:55 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.964)	Loss 0.8945 (0.7700)	Acc@1 81.421 (84.688)	Acc@5 96.045 (96.993)	Mem 34604MB
[2025-01-19 19:41:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:265] * Acc@1 84.505 Acc@5 96.995
[2025-01-19 19:41:55 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.5%
[2025-01-19 19:41:55 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.53%
[2025-01-19 19:42:04 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.252 (9.252)	Loss 0.7108 (0.7108)	Acc@1 86.597 (86.597)	Acc@5 98.145 (98.145)	Mem 34604MB
[2025-01-19 19:42:09 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.254)	Loss 0.9108 (0.7972)	Acc@1 81.152 (84.595)	Acc@5 95.996 (97.050)	Mem 34604MB
[2025-01-19 19:42:09 internimage_b_1k_224] (main.py 575): INFO [Epoch:265] * Acc@1 84.409 Acc@5 97.069
[2025-01-19 19:42:09 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.4%
[2025-01-19 19:42:09 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 19:42:13 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 19:42:13 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.41%
[2025-01-19 19:42:15 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][0/312]	eta 0:11:17 lr 0.000164	time 2.1712 (2.1712)	model_time 0.7407 (0.7407)	loss 2.6146 (2.6146)	grad_norm 1.6126 (1.6126/0.0000)	mem 34604MB
[2025-01-19 19:42:23 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][10/312]	eta 0:04:30 lr 0.000164	time 0.7254 (0.8944)	model_time 0.7252 (0.7640)	loss 2.9780 (2.5629)	grad_norm 2.4147 (2.0018/0.5268)	mem 34604MB
[2025-01-19 19:42:31 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][20/312]	eta 0:04:02 lr 0.000164	time 0.7121 (0.8312)	model_time 0.7117 (0.7628)	loss 2.5625 (2.6568)	grad_norm 2.5363 (2.4108/0.7153)	mem 34604MB
[2025-01-19 19:42:38 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][30/312]	eta 0:03:46 lr 0.000163	time 0.7316 (0.8038)	model_time 0.7315 (0.7574)	loss 2.2217 (2.5672)	grad_norm 1.5880 (2.2676/0.6868)	mem 34604MB
[2025-01-19 19:42:45 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][40/312]	eta 0:03:33 lr 0.000163	time 0.7235 (0.7860)	model_time 0.7234 (0.7508)	loss 2.6261 (2.5563)	grad_norm 1.2464 (2.3565/0.7824)	mem 34604MB
[2025-01-19 19:42:53 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][50/312]	eta 0:03:23 lr 0.000163	time 0.7147 (0.7760)	model_time 0.7145 (0.7477)	loss 2.9746 (2.5942)	grad_norm 1.6750 (2.5469/1.1128)	mem 34604MB
[2025-01-19 19:43:00 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][60/312]	eta 0:03:13 lr 0.000163	time 0.7360 (0.7692)	model_time 0.7355 (0.7454)	loss 2.9212 (2.6156)	grad_norm 3.3707 (2.5644/1.0756)	mem 34604MB
[2025-01-19 19:43:07 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][70/312]	eta 0:03:04 lr 0.000163	time 0.7228 (0.7632)	model_time 0.7224 (0.7428)	loss 1.9708 (2.5989)	grad_norm 1.8518 (2.5490/1.0548)	mem 34604MB
[2025-01-19 19:43:15 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][80/312]	eta 0:02:56 lr 0.000162	time 0.7249 (0.7589)	model_time 0.7244 (0.7409)	loss 2.9798 (2.6044)	grad_norm 2.4749 (2.5609/1.0560)	mem 34604MB
[2025-01-19 19:43:22 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][90/312]	eta 0:02:47 lr 0.000162	time 0.8219 (0.7562)	model_time 0.8217 (0.7402)	loss 2.2512 (2.6073)	grad_norm 1.6682 (2.4836/1.0561)	mem 34604MB
[2025-01-19 19:43:30 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][100/312]	eta 0:02:40 lr 0.000162	time 0.7252 (0.7556)	model_time 0.7247 (0.7411)	loss 2.2342 (2.6151)	grad_norm 2.7056 (2.4617/1.0133)	mem 34604MB
[2025-01-19 19:43:37 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][110/312]	eta 0:02:32 lr 0.000162	time 0.7240 (0.7563)	model_time 0.7238 (0.7431)	loss 3.1590 (2.6079)	grad_norm 1.7938 (2.4172/0.9867)	mem 34604MB
[2025-01-19 19:43:45 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][120/312]	eta 0:02:25 lr 0.000161	time 0.7183 (0.7564)	model_time 0.7182 (0.7442)	loss 2.4597 (2.6033)	grad_norm 2.8981 (2.4252/0.9551)	mem 34604MB
[2025-01-19 19:43:52 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][130/312]	eta 0:02:17 lr 0.000161	time 0.7306 (0.7570)	model_time 0.7304 (0.7458)	loss 3.0969 (2.6163)	grad_norm 2.1113 (2.4230/0.9303)	mem 34604MB
[2025-01-19 19:44:00 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][140/312]	eta 0:02:10 lr 0.000161	time 0.8104 (0.7579)	model_time 0.8102 (0.7474)	loss 3.0120 (2.6292)	grad_norm 2.2367 (2.4390/0.9473)	mem 34604MB
[2025-01-19 19:44:08 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][150/312]	eta 0:02:02 lr 0.000161	time 0.7207 (0.7574)	model_time 0.7202 (0.7476)	loss 2.8352 (2.6268)	grad_norm 2.0738 (2.4741/0.9950)	mem 34604MB
[2025-01-19 19:44:15 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][160/312]	eta 0:01:54 lr 0.000161	time 0.7467 (0.7562)	model_time 0.7462 (0.7469)	loss 1.5886 (2.6222)	grad_norm 2.9515 (2.5124/1.0161)	mem 34604MB
[2025-01-19 19:44:22 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][170/312]	eta 0:01:47 lr 0.000160	time 0.7219 (0.7551)	model_time 0.7218 (0.7463)	loss 2.2206 (2.6130)	grad_norm 1.1272 (2.5309/1.0346)	mem 34604MB
[2025-01-19 19:44:30 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][180/312]	eta 0:01:39 lr 0.000160	time 0.7436 (0.7538)	model_time 0.7432 (0.7456)	loss 2.6026 (2.6128)	grad_norm 3.0223 (2.5473/1.0180)	mem 34604MB
[2025-01-19 19:44:37 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][190/312]	eta 0:01:31 lr 0.000160	time 0.7514 (0.7530)	model_time 0.7510 (0.7451)	loss 2.4184 (2.6130)	grad_norm 2.9456 (2.5985/1.0628)	mem 34604MB
[2025-01-19 19:44:44 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][200/312]	eta 0:01:24 lr 0.000160	time 0.7284 (0.7517)	model_time 0.7279 (0.7442)	loss 3.1081 (2.6199)	grad_norm 3.7669 (2.6338/1.0834)	mem 34604MB
[2025-01-19 19:44:52 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][210/312]	eta 0:01:16 lr 0.000159	time 0.7945 (0.7508)	model_time 0.7941 (0.7437)	loss 2.0725 (2.6158)	grad_norm 3.3482 (2.6571/1.0979)	mem 34604MB
[2025-01-19 19:44:59 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][220/312]	eta 0:01:09 lr 0.000159	time 0.7103 (0.7504)	model_time 0.7099 (0.7436)	loss 2.4984 (2.6129)	grad_norm 1.9225 (2.6594/1.1072)	mem 34604MB
[2025-01-19 19:45:07 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][230/312]	eta 0:01:01 lr 0.000159	time 0.7201 (0.7521)	model_time 0.7200 (0.7456)	loss 2.5149 (2.6168)	grad_norm 2.2756 (2.6478/1.0950)	mem 34604MB
[2025-01-19 19:45:15 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][240/312]	eta 0:00:54 lr 0.000159	time 0.7190 (0.7530)	model_time 0.7188 (0.7467)	loss 2.9919 (2.6176)	grad_norm 2.3372 (2.6363/1.0886)	mem 34604MB
[2025-01-19 19:45:22 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][250/312]	eta 0:00:46 lr 0.000158	time 0.8146 (0.7532)	model_time 0.8144 (0.7471)	loss 1.7159 (2.6176)	grad_norm 2.0997 (2.6145/1.0766)	mem 34604MB
[2025-01-19 19:45:30 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][260/312]	eta 0:00:39 lr 0.000158	time 0.8114 (0.7535)	model_time 0.8112 (0.7477)	loss 3.1060 (2.6197)	grad_norm 2.0227 (2.5883/1.0716)	mem 34604MB
[2025-01-19 19:45:37 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][270/312]	eta 0:00:31 lr 0.000158	time 0.7138 (0.7534)	model_time 0.7137 (0.7477)	loss 3.1834 (2.6140)	grad_norm 1.7860 (2.5578/1.0667)	mem 34604MB
[2025-01-19 19:45:45 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][280/312]	eta 0:00:24 lr 0.000158	time 0.7560 (0.7526)	model_time 0.7559 (0.7472)	loss 3.2555 (2.6143)	grad_norm 2.4043 (2.5240/1.0653)	mem 34604MB
[2025-01-19 19:45:52 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][290/312]	eta 0:00:16 lr 0.000158	time 0.7167 (0.7519)	model_time 0.7166 (0.7466)	loss 2.5006 (2.6100)	grad_norm 3.7404 (2.5091/1.0594)	mem 34604MB
[2025-01-19 19:45:59 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][300/312]	eta 0:00:09 lr 0.000157	time 0.7186 (0.7510)	model_time 0.7185 (0.7459)	loss 2.1099 (2.6091)	grad_norm 3.5002 (2.5269/1.0620)	mem 34604MB
[2025-01-19 19:46:06 internimage_b_1k_224] (main.py 510): INFO Train: [266/300][310/312]	eta 0:00:01 lr 0.000157	time 0.7164 (0.7498)	model_time 0.7163 (0.7449)	loss 2.8586 (2.6101)	grad_norm 2.3184 (2.5360/1.0659)	mem 34604MB
[2025-01-19 19:46:07 internimage_b_1k_224] (main.py 519): INFO EPOCH 266 training takes 0:03:53
[2025-01-19 19:46:07 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_266.pth saving......
[2025-01-19 19:46:10 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_266.pth saved !!!
[2025-01-19 19:46:18 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.265 (7.265)	Loss 0.6828 (0.6828)	Acc@1 86.621 (86.621)	Acc@5 98.145 (98.145)	Mem 34604MB
[2025-01-19 19:46:21 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.926)	Loss 0.9039 (0.7781)	Acc@1 80.981 (84.612)	Acc@5 95.923 (96.977)	Mem 34604MB
[2025-01-19 19:46:21 internimage_b_1k_224] (main.py 575): INFO [Epoch:266] * Acc@1 84.445 Acc@5 96.999
[2025-01-19 19:46:21 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.4%
[2025-01-19 19:46:21 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.53%
[2025-01-19 19:46:30 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.243 (9.243)	Loss 0.7106 (0.7106)	Acc@1 86.523 (86.523)	Acc@5 98.193 (98.193)	Mem 34604MB
[2025-01-19 19:46:35 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.238)	Loss 0.9102 (0.7967)	Acc@1 81.177 (84.615)	Acc@5 96.021 (97.061)	Mem 34604MB
[2025-01-19 19:46:35 internimage_b_1k_224] (main.py 575): INFO [Epoch:266] * Acc@1 84.425 Acc@5 97.079
[2025-01-19 19:46:35 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.4%
[2025-01-19 19:46:35 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 19:46:39 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 19:46:39 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.42%
[2025-01-19 19:46:41 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][0/312]	eta 0:11:57 lr 0.000157	time 2.2995 (2.2995)	model_time 0.7468 (0.7468)	loss 1.9655 (1.9655)	grad_norm 2.7258 (2.7258/0.0000)	mem 34604MB
[2025-01-19 19:46:49 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][10/312]	eta 0:04:24 lr 0.000157	time 0.7227 (0.8750)	model_time 0.7226 (0.7335)	loss 3.1473 (2.6131)	grad_norm 1.0381 (1.9407/0.7335)	mem 34604MB
[2025-01-19 19:46:56 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][20/312]	eta 0:03:57 lr 0.000157	time 0.8110 (0.8122)	model_time 0.8109 (0.7379)	loss 2.5977 (2.6583)	grad_norm 1.4199 (1.9811/0.7506)	mem 34604MB
[2025-01-19 19:47:03 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][30/312]	eta 0:03:42 lr 0.000156	time 0.7205 (0.7876)	model_time 0.7200 (0.7372)	loss 3.0649 (2.6500)	grad_norm 2.9913 (1.9393/0.6952)	mem 34604MB
[2025-01-19 19:47:11 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][40/312]	eta 0:03:33 lr 0.000156	time 0.8129 (0.7866)	model_time 0.8128 (0.7484)	loss 2.1132 (2.6094)	grad_norm 1.5427 (2.0211/0.6903)	mem 34604MB
[2025-01-19 19:47:19 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][50/312]	eta 0:03:24 lr 0.000156	time 0.7223 (0.7801)	model_time 0.7221 (0.7494)	loss 2.4457 (2.6590)	grad_norm 1.5866 (2.0924/0.7323)	mem 34604MB
[2025-01-19 19:47:27 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][60/312]	eta 0:03:16 lr 0.000156	time 0.7854 (0.7807)	model_time 0.7852 (0.7549)	loss 2.8646 (2.6410)	grad_norm 2.1809 (2.2210/0.9046)	mem 34604MB
[2025-01-19 19:47:34 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][70/312]	eta 0:03:07 lr 0.000155	time 0.7275 (0.7763)	model_time 0.7271 (0.7541)	loss 2.5823 (2.6399)	grad_norm 1.5573 (2.2057/0.9275)	mem 34604MB
[2025-01-19 19:47:42 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][80/312]	eta 0:02:59 lr 0.000155	time 0.7325 (0.7723)	model_time 0.7324 (0.7528)	loss 1.7188 (2.6067)	grad_norm 2.0611 (2.2612/0.9683)	mem 34604MB
[2025-01-19 19:47:49 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][90/312]	eta 0:02:50 lr 0.000155	time 0.7244 (0.7676)	model_time 0.7242 (0.7503)	loss 2.8722 (2.6112)	grad_norm 2.5831 (2.2326/0.9270)	mem 34604MB
[2025-01-19 19:47:56 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][100/312]	eta 0:02:42 lr 0.000155	time 0.7201 (0.7650)	model_time 0.7199 (0.7493)	loss 2.9772 (2.6078)	grad_norm 1.3925 (2.1788/0.9102)	mem 34604MB
[2025-01-19 19:48:04 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][110/312]	eta 0:02:33 lr 0.000155	time 0.7252 (0.7624)	model_time 0.7247 (0.7480)	loss 3.1861 (2.6184)	grad_norm 1.6059 (2.1297/0.8889)	mem 34604MB
[2025-01-19 19:48:11 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][120/312]	eta 0:02:25 lr 0.000154	time 0.7164 (0.7599)	model_time 0.7160 (0.7467)	loss 2.9401 (2.6165)	grad_norm 2.8021 (2.1179/0.8682)	mem 34604MB
[2025-01-19 19:48:18 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][130/312]	eta 0:02:17 lr 0.000154	time 0.7224 (0.7575)	model_time 0.7222 (0.7453)	loss 2.3630 (2.5955)	grad_norm 3.6043 (2.1543/0.8856)	mem 34604MB
[2025-01-19 19:48:26 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][140/312]	eta 0:02:09 lr 0.000154	time 0.7246 (0.7556)	model_time 0.7241 (0.7442)	loss 2.3613 (2.5784)	grad_norm 1.9423 (2.2085/0.9242)	mem 34604MB
[2025-01-19 19:48:33 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][150/312]	eta 0:02:02 lr 0.000154	time 0.7527 (0.7550)	model_time 0.7526 (0.7444)	loss 2.7840 (2.5759)	grad_norm 1.6909 (2.2050/0.9151)	mem 34604MB
[2025-01-19 19:48:41 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][160/312]	eta 0:01:55 lr 0.000153	time 0.8015 (0.7566)	model_time 0.8013 (0.7466)	loss 3.0552 (2.5718)	grad_norm 2.1244 (2.1997/0.9017)	mem 34604MB
[2025-01-19 19:48:48 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][170/312]	eta 0:01:47 lr 0.000153	time 0.8016 (0.7564)	model_time 0.8011 (0.7470)	loss 2.5729 (2.5666)	grad_norm 2.5548 (2.2438/0.9337)	mem 34604MB
[2025-01-19 19:48:56 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][180/312]	eta 0:01:39 lr 0.000153	time 0.7156 (0.7573)	model_time 0.7155 (0.7484)	loss 2.9831 (2.5808)	grad_norm 2.4004 (2.2443/0.9197)	mem 34604MB
[2025-01-19 19:49:04 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][190/312]	eta 0:01:32 lr 0.000153	time 0.7163 (0.7573)	model_time 0.7158 (0.7488)	loss 3.1607 (2.5930)	grad_norm 2.0791 (2.2563/0.9122)	mem 34604MB
[2025-01-19 19:49:11 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][200/312]	eta 0:01:24 lr 0.000153	time 0.7242 (0.7569)	model_time 0.7240 (0.7488)	loss 3.0340 (2.6029)	grad_norm 1.8885 (2.2716/0.9237)	mem 34604MB
[2025-01-19 19:49:18 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][210/312]	eta 0:01:17 lr 0.000152	time 0.7231 (0.7557)	model_time 0.7227 (0.7480)	loss 2.6859 (2.6129)	grad_norm 1.4166 (2.2934/0.9326)	mem 34604MB
[2025-01-19 19:49:26 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][220/312]	eta 0:01:09 lr 0.000152	time 0.7246 (0.7546)	model_time 0.7244 (0.7472)	loss 3.2118 (2.6228)	grad_norm 6.0743 (2.3289/0.9681)	mem 34604MB
[2025-01-19 19:49:33 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][230/312]	eta 0:01:01 lr 0.000152	time 0.7697 (0.7538)	model_time 0.7695 (0.7467)	loss 2.5900 (2.6212)	grad_norm 3.0751 (2.3568/0.9841)	mem 34604MB
[2025-01-19 19:49:40 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][240/312]	eta 0:00:54 lr 0.000152	time 0.7214 (0.7527)	model_time 0.7209 (0.7459)	loss 3.0892 (2.6165)	grad_norm 3.8827 (2.3790/1.0149)	mem 34604MB
[2025-01-19 19:49:48 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][250/312]	eta 0:00:46 lr 0.000151	time 0.7206 (0.7521)	model_time 0.7205 (0.7456)	loss 2.2568 (2.6123)	grad_norm 1.5307 (2.3795/1.0075)	mem 34604MB
[2025-01-19 19:49:55 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][260/312]	eta 0:00:39 lr 0.000151	time 0.7330 (0.7512)	model_time 0.7326 (0.7449)	loss 2.4769 (2.6104)	grad_norm 3.6444 (2.3921/1.0064)	mem 34604MB
[2025-01-19 19:50:03 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][270/312]	eta 0:00:31 lr 0.000151	time 0.7663 (0.7511)	model_time 0.7662 (0.7450)	loss 2.9569 (2.6239)	grad_norm 2.7341 (2.3709/0.9981)	mem 34604MB
[2025-01-19 19:50:10 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][280/312]	eta 0:00:24 lr 0.000151	time 0.8029 (0.7520)	model_time 0.8025 (0.7462)	loss 2.3800 (2.6185)	grad_norm 2.8588 (2.3702/0.9902)	mem 34604MB
[2025-01-19 19:50:18 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][290/312]	eta 0:00:16 lr 0.000151	time 0.7257 (0.7520)	model_time 0.7253 (0.7463)	loss 3.0073 (2.6186)	grad_norm 2.3732 (2.3700/0.9796)	mem 34604MB
[2025-01-19 19:50:26 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][300/312]	eta 0:00:09 lr 0.000150	time 0.7132 (0.7527)	model_time 0.7131 (0.7472)	loss 2.8397 (2.6247)	grad_norm 2.4631 (2.3630/0.9715)	mem 34604MB
[2025-01-19 19:50:33 internimage_b_1k_224] (main.py 510): INFO Train: [267/300][310/312]	eta 0:00:01 lr 0.000150	time 0.7146 (0.7527)	model_time 0.7145 (0.7474)	loss 2.5380 (2.6241)	grad_norm 2.0056 (2.3723/0.9615)	mem 34604MB
[2025-01-19 19:50:34 internimage_b_1k_224] (main.py 519): INFO EPOCH 267 training takes 0:03:54
[2025-01-19 19:50:34 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_267.pth saving......
[2025-01-19 19:50:37 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_267.pth saved !!!
[2025-01-19 19:50:45 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.349 (7.349)	Loss 0.6896 (0.6896)	Acc@1 86.328 (86.328)	Acc@5 97.998 (97.998)	Mem 34604MB
[2025-01-19 19:50:48 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.947)	Loss 0.8930 (0.7774)	Acc@1 81.445 (84.621)	Acc@5 95.972 (96.975)	Mem 34604MB
[2025-01-19 19:50:48 internimage_b_1k_224] (main.py 575): INFO [Epoch:267] * Acc@1 84.433 Acc@5 96.991
[2025-01-19 19:50:48 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.4%
[2025-01-19 19:50:48 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.53%
[2025-01-19 19:50:57 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.325 (9.325)	Loss 0.7104 (0.7104)	Acc@1 86.475 (86.475)	Acc@5 98.218 (98.218)	Mem 34604MB
[2025-01-19 19:51:02 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.251)	Loss 0.9094 (0.7963)	Acc@1 81.226 (84.632)	Acc@5 96.021 (97.068)	Mem 34604MB
[2025-01-19 19:51:02 internimage_b_1k_224] (main.py 575): INFO [Epoch:267] * Acc@1 84.439 Acc@5 97.089
[2025-01-19 19:51:02 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.4%
[2025-01-19 19:51:02 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 19:51:06 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 19:51:06 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.44%
[2025-01-19 19:51:08 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][0/312]	eta 0:11:17 lr 0.000150	time 2.1713 (2.1713)	model_time 0.7391 (0.7391)	loss 2.8077 (2.8077)	grad_norm 1.2099 (1.2099/0.0000)	mem 34604MB
[2025-01-19 19:51:16 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][10/312]	eta 0:04:24 lr 0.000150	time 0.7396 (0.8765)	model_time 0.7395 (0.7460)	loss 2.6892 (2.5221)	grad_norm 3.4042 (3.1708/1.1809)	mem 34604MB
[2025-01-19 19:51:23 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][20/312]	eta 0:03:56 lr 0.000150	time 0.7212 (0.8093)	model_time 0.7210 (0.7408)	loss 2.4455 (2.4661)	grad_norm 6.4402 (3.3131/1.4899)	mem 34604MB
[2025-01-19 19:51:30 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][30/312]	eta 0:03:42 lr 0.000149	time 0.7270 (0.7885)	model_time 0.7268 (0.7420)	loss 2.8615 (2.5302)	grad_norm 4.0693 (3.3262/1.2986)	mem 34604MB
[2025-01-19 19:51:38 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][40/312]	eta 0:03:30 lr 0.000149	time 0.7243 (0.7745)	model_time 0.7239 (0.7392)	loss 1.7745 (2.5555)	grad_norm 2.4996 (3.2477/1.4582)	mem 34604MB
[2025-01-19 19:51:45 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][50/312]	eta 0:03:20 lr 0.000149	time 0.7544 (0.7654)	model_time 0.7540 (0.7369)	loss 2.1134 (2.6173)	grad_norm 2.6258 (3.2367/1.3465)	mem 34604MB
[2025-01-19 19:51:52 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][60/312]	eta 0:03:11 lr 0.000149	time 0.7173 (0.7604)	model_time 0.7171 (0.7366)	loss 2.8869 (2.5979)	grad_norm 2.3489 (3.2000/1.4245)	mem 34604MB
[2025-01-19 19:52:00 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][70/312]	eta 0:03:03 lr 0.000149	time 0.8099 (0.7572)	model_time 0.8098 (0.7367)	loss 2.0063 (2.6160)	grad_norm 1.2095 (3.0562/1.4049)	mem 34604MB
[2025-01-19 19:52:07 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][80/312]	eta 0:02:55 lr 0.000148	time 0.7570 (0.7551)	model_time 0.7566 (0.7370)	loss 2.3622 (2.6415)	grad_norm 2.3772 (2.9858/1.3609)	mem 34604MB
[2025-01-19 19:52:15 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][90/312]	eta 0:02:48 lr 0.000148	time 0.7139 (0.7578)	model_time 0.7137 (0.7417)	loss 3.0603 (2.6470)	grad_norm 2.7190 (2.9265/1.3180)	mem 34604MB
[2025-01-19 19:52:23 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][100/312]	eta 0:02:40 lr 0.000148	time 0.7261 (0.7580)	model_time 0.7260 (0.7434)	loss 2.3829 (2.6319)	grad_norm 2.2698 (2.8769/1.2842)	mem 34604MB
[2025-01-19 19:52:31 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][110/312]	eta 0:02:34 lr 0.000148	time 0.9231 (0.7626)	model_time 0.9227 (0.7494)	loss 3.0207 (2.6480)	grad_norm 1.7440 (2.7739/1.2783)	mem 34604MB
[2025-01-19 19:52:38 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][120/312]	eta 0:02:26 lr 0.000148	time 0.8292 (0.7623)	model_time 0.8291 (0.7501)	loss 1.9160 (2.6512)	grad_norm 3.9608 (2.7902/1.2637)	mem 34604MB
[2025-01-19 19:52:46 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][130/312]	eta 0:02:18 lr 0.000147	time 0.7227 (0.7613)	model_time 0.7222 (0.7501)	loss 2.1951 (2.6425)	grad_norm 2.6315 (2.7583/1.2531)	mem 34604MB
[2025-01-19 19:52:53 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][140/312]	eta 0:02:10 lr 0.000147	time 0.7316 (0.7593)	model_time 0.7314 (0.7488)	loss 2.8885 (2.6309)	grad_norm 2.8497 (2.7568/1.2300)	mem 34604MB
[2025-01-19 19:53:00 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][150/312]	eta 0:02:02 lr 0.000147	time 0.7080 (0.7583)	model_time 0.7075 (0.7484)	loss 2.8269 (2.6210)	grad_norm 1.0903 (2.7457/1.2270)	mem 34604MB
[2025-01-19 19:53:08 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][160/312]	eta 0:01:54 lr 0.000147	time 0.7199 (0.7563)	model_time 0.7197 (0.7471)	loss 2.8773 (2.6207)	grad_norm 1.5687 (2.7156/1.2179)	mem 34604MB
[2025-01-19 19:53:15 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][170/312]	eta 0:01:47 lr 0.000146	time 0.7419 (0.7547)	model_time 0.7417 (0.7460)	loss 2.4948 (2.6172)	grad_norm 1.7632 (2.6958/1.2065)	mem 34604MB
[2025-01-19 19:53:22 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][180/312]	eta 0:01:39 lr 0.000146	time 0.7349 (0.7532)	model_time 0.7345 (0.7450)	loss 3.0469 (2.6277)	grad_norm 1.9300 (2.6758/1.1896)	mem 34604MB
[2025-01-19 19:53:30 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][190/312]	eta 0:01:31 lr 0.000146	time 0.8146 (0.7524)	model_time 0.8144 (0.7445)	loss 2.1174 (2.6288)	grad_norm 2.0076 (2.6472/1.1715)	mem 34604MB
[2025-01-19 19:53:37 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][200/312]	eta 0:01:24 lr 0.000146	time 0.7174 (0.7515)	model_time 0.7172 (0.7440)	loss 2.0612 (2.6356)	grad_norm 2.2186 (2.6290/1.1561)	mem 34604MB
[2025-01-19 19:53:45 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][210/312]	eta 0:01:16 lr 0.000146	time 0.7954 (0.7525)	model_time 0.7952 (0.7454)	loss 2.5348 (2.6357)	grad_norm 1.7615 (2.5960/1.1450)	mem 34604MB
[2025-01-19 19:53:52 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][220/312]	eta 0:01:09 lr 0.000145	time 0.7174 (0.7527)	model_time 0.7169 (0.7459)	loss 2.8797 (2.6382)	grad_norm 3.5400 (2.6012/1.1242)	mem 34604MB
[2025-01-19 19:54:00 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][230/312]	eta 0:01:01 lr 0.000145	time 0.8201 (0.7542)	model_time 0.8199 (0.7477)	loss 2.8981 (2.6352)	grad_norm 2.0060 (2.5915/1.1150)	mem 34604MB
[2025-01-19 19:54:08 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][240/312]	eta 0:00:54 lr 0.000145	time 0.8156 (0.7540)	model_time 0.8155 (0.7477)	loss 2.4910 (2.6306)	grad_norm 1.2636 (2.5669/1.1081)	mem 34604MB
[2025-01-19 19:54:15 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][250/312]	eta 0:00:46 lr 0.000145	time 0.7097 (0.7537)	model_time 0.7092 (0.7476)	loss 2.6236 (2.6278)	grad_norm 1.1634 (2.5626/1.1029)	mem 34604MB
[2025-01-19 19:54:22 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][260/312]	eta 0:00:39 lr 0.000145	time 0.7218 (0.7529)	model_time 0.7213 (0.7470)	loss 2.8032 (2.6359)	grad_norm 1.6606 (2.5815/1.1087)	mem 34604MB
[2025-01-19 19:54:30 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][270/312]	eta 0:00:31 lr 0.000144	time 0.7077 (0.7526)	model_time 0.7076 (0.7470)	loss 2.4748 (2.6320)	grad_norm 2.4887 (2.5973/1.1173)	mem 34604MB
[2025-01-19 19:54:37 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][280/312]	eta 0:00:24 lr 0.000144	time 0.7209 (0.7519)	model_time 0.7207 (0.7464)	loss 2.6003 (2.6309)	grad_norm 2.4456 (2.5968/1.1163)	mem 34604MB
[2025-01-19 19:54:45 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][290/312]	eta 0:00:16 lr 0.000144	time 0.7415 (0.7511)	model_time 0.7410 (0.7458)	loss 1.7588 (2.6240)	grad_norm 1.6437 (2.5912/1.1057)	mem 34604MB
[2025-01-19 19:54:52 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][300/312]	eta 0:00:09 lr 0.000144	time 0.7157 (0.7502)	model_time 0.7157 (0.7451)	loss 2.6072 (2.6202)	grad_norm 2.3938 (2.5652/1.1042)	mem 34604MB
[2025-01-19 19:54:59 internimage_b_1k_224] (main.py 510): INFO Train: [268/300][310/312]	eta 0:00:01 lr 0.000143	time 0.7162 (0.7493)	model_time 0.7161 (0.7443)	loss 2.6458 (2.6259)	grad_norm 1.6796 (2.5229/1.0920)	mem 34604MB
[2025-01-19 19:55:00 internimage_b_1k_224] (main.py 519): INFO EPOCH 268 training takes 0:03:53
[2025-01-19 19:55:00 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_268.pth saving......
[2025-01-19 19:55:03 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_268.pth saved !!!
[2025-01-19 19:55:11 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.456 (7.456)	Loss 0.6881 (0.6881)	Acc@1 86.499 (86.499)	Acc@5 98.096 (98.096)	Mem 34604MB
[2025-01-19 19:55:14 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.953)	Loss 0.8838 (0.7726)	Acc@1 81.445 (84.739)	Acc@5 96.143 (96.990)	Mem 34604MB
[2025-01-19 19:55:14 internimage_b_1k_224] (main.py 575): INFO [Epoch:268] * Acc@1 84.549 Acc@5 97.015
[2025-01-19 19:55:14 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.5%
[2025-01-19 19:55:14 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 19:55:17 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 19:55:17 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.55%
[2025-01-19 19:55:24 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.229 (7.229)	Loss 0.7101 (0.7101)	Acc@1 86.475 (86.475)	Acc@5 98.218 (98.218)	Mem 34604MB
[2025-01-19 19:55:27 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.930)	Loss 0.9088 (0.7958)	Acc@1 81.274 (84.635)	Acc@5 96.045 (97.073)	Mem 34604MB
[2025-01-19 19:55:28 internimage_b_1k_224] (main.py 575): INFO [Epoch:268] * Acc@1 84.457 Acc@5 97.095
[2025-01-19 19:55:28 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.5%
[2025-01-19 19:55:28 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 19:55:32 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 19:55:32 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.46%
[2025-01-19 19:55:34 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][0/312]	eta 0:11:25 lr 0.000143	time 2.1967 (2.1967)	model_time 0.7466 (0.7466)	loss 2.5845 (2.5845)	grad_norm 1.6871 (1.6871/0.0000)	mem 34604MB
[2025-01-19 19:55:41 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][10/312]	eta 0:04:21 lr 0.000143	time 0.7237 (0.8666)	model_time 0.7236 (0.7345)	loss 3.1321 (2.7069)	grad_norm 2.1233 (2.2864/0.7876)	mem 34604MB
[2025-01-19 19:55:49 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][20/312]	eta 0:04:01 lr 0.000143	time 0.7180 (0.8264)	model_time 0.7179 (0.7571)	loss 3.1893 (2.5143)	grad_norm 2.1611 (2.4731/0.9531)	mem 34604MB
[2025-01-19 19:55:56 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][30/312]	eta 0:03:46 lr 0.000143	time 0.7291 (0.8041)	model_time 0.7289 (0.7570)	loss 2.4057 (2.5001)	grad_norm 2.4605 (2.5361/0.9844)	mem 34604MB
[2025-01-19 19:56:04 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][40/312]	eta 0:03:37 lr 0.000143	time 0.7448 (0.8011)	model_time 0.7446 (0.7654)	loss 3.3905 (2.5814)	grad_norm 1.5406 (2.4165/0.9433)	mem 34604MB
[2025-01-19 19:56:12 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][50/312]	eta 0:03:27 lr 0.000142	time 0.7220 (0.7932)	model_time 0.7215 (0.7644)	loss 2.9357 (2.6088)	grad_norm 1.3501 (2.3727/0.8962)	mem 34604MB
[2025-01-19 19:56:20 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][60/312]	eta 0:03:18 lr 0.000142	time 0.8178 (0.7888)	model_time 0.8177 (0.7647)	loss 2.2844 (2.6107)	grad_norm 4.7159 (2.5257/1.0324)	mem 34604MB
[2025-01-19 19:56:27 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][70/312]	eta 0:03:08 lr 0.000142	time 0.7172 (0.7797)	model_time 0.7168 (0.7589)	loss 3.0835 (2.6223)	grad_norm 1.4325 (2.5802/1.0105)	mem 34604MB
[2025-01-19 19:56:34 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][80/312]	eta 0:02:59 lr 0.000142	time 0.7191 (0.7745)	model_time 0.7189 (0.7563)	loss 2.8380 (2.6184)	grad_norm 2.3645 (2.5390/0.9784)	mem 34604MB
[2025-01-19 19:56:42 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][90/312]	eta 0:02:50 lr 0.000142	time 0.7423 (0.7701)	model_time 0.7422 (0.7538)	loss 2.5746 (2.6557)	grad_norm 2.6841 (2.4636/0.9812)	mem 34604MB
[2025-01-19 19:56:49 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][100/312]	eta 0:02:42 lr 0.000141	time 0.7247 (0.7664)	model_time 0.7246 (0.7517)	loss 1.6705 (2.6448)	grad_norm 2.5599 (2.4420/0.9399)	mem 34604MB
[2025-01-19 19:56:56 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][110/312]	eta 0:02:34 lr 0.000141	time 0.7213 (0.7635)	model_time 0.7209 (0.7501)	loss 2.7578 (2.6512)	grad_norm 2.4228 (2.4725/0.9974)	mem 34604MB
[2025-01-19 19:57:04 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][120/312]	eta 0:02:26 lr 0.000141	time 0.8083 (0.7617)	model_time 0.8081 (0.7494)	loss 2.9549 (2.6518)	grad_norm 2.2475 (2.4570/0.9800)	mem 34604MB
[2025-01-19 19:57:11 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][130/312]	eta 0:02:18 lr 0.000141	time 0.7272 (0.7606)	model_time 0.7267 (0.7492)	loss 2.7750 (2.6414)	grad_norm 3.3919 (2.5442/1.0947)	mem 34604MB
[2025-01-19 19:57:19 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][140/312]	eta 0:02:11 lr 0.000140	time 0.7315 (0.7627)	model_time 0.7311 (0.7521)	loss 2.9946 (2.6492)	grad_norm 2.9179 (2.5876/1.1226)	mem 34604MB
[2025-01-19 19:57:27 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][150/312]	eta 0:02:03 lr 0.000140	time 0.7150 (0.7624)	model_time 0.7146 (0.7525)	loss 2.6819 (2.6435)	grad_norm 1.4616 (2.5709/1.1211)	mem 34604MB
[2025-01-19 19:57:34 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][160/312]	eta 0:01:56 lr 0.000140	time 0.7253 (0.7637)	model_time 0.7251 (0.7544)	loss 2.6409 (2.6417)	grad_norm 1.8795 (2.5680/1.1164)	mem 34604MB
[2025-01-19 19:57:42 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][170/312]	eta 0:01:48 lr 0.000140	time 0.7540 (0.7631)	model_time 0.7536 (0.7543)	loss 2.8220 (2.6537)	grad_norm 1.5080 (2.5480/1.1036)	mem 34604MB
[2025-01-19 19:57:50 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][180/312]	eta 0:01:40 lr 0.000140	time 0.8289 (0.7630)	model_time 0.8288 (0.7546)	loss 2.9776 (2.6478)	grad_norm 2.5831 (2.5383/1.0875)	mem 34604MB
[2025-01-19 19:57:57 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][190/312]	eta 0:01:32 lr 0.000139	time 0.7236 (0.7609)	model_time 0.7231 (0.7529)	loss 2.5820 (2.6510)	grad_norm 3.3564 (2.5433/1.0862)	mem 34604MB
[2025-01-19 19:58:04 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][200/312]	eta 0:01:25 lr 0.000139	time 0.7365 (0.7598)	model_time 0.7364 (0.7522)	loss 2.7327 (2.6508)	grad_norm 3.1765 (2.5615/1.0921)	mem 34604MB
[2025-01-19 19:58:12 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][210/312]	eta 0:01:17 lr 0.000139	time 0.7250 (0.7584)	model_time 0.7248 (0.7512)	loss 2.8217 (2.6593)	grad_norm 2.3418 (2.5501/1.0809)	mem 34604MB
[2025-01-19 19:58:19 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][220/312]	eta 0:01:09 lr 0.000139	time 0.7240 (0.7571)	model_time 0.7238 (0.7501)	loss 1.5344 (2.6540)	grad_norm 2.3654 (2.5425/1.0811)	mem 34604MB
[2025-01-19 19:58:26 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][230/312]	eta 0:01:01 lr 0.000139	time 0.7281 (0.7561)	model_time 0.7279 (0.7494)	loss 2.3970 (2.6465)	grad_norm 1.6184 (2.5827/1.1432)	mem 34604MB
[2025-01-19 19:58:34 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][240/312]	eta 0:00:54 lr 0.000138	time 0.8075 (0.7554)	model_time 0.8070 (0.7490)	loss 2.6205 (2.6382)	grad_norm 3.5892 (2.5888/1.1409)	mem 34604MB
[2025-01-19 19:58:41 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][250/312]	eta 0:00:46 lr 0.000138	time 0.7240 (0.7549)	model_time 0.7235 (0.7487)	loss 2.9520 (2.6325)	grad_norm 1.5764 (2.5681/1.1286)	mem 34604MB
[2025-01-19 19:58:49 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][260/312]	eta 0:00:39 lr 0.000138	time 0.8238 (0.7555)	model_time 0.8236 (0.7496)	loss 2.7709 (2.6346)	grad_norm 1.6734 (2.5417/1.1189)	mem 34604MB
[2025-01-19 19:58:56 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][270/312]	eta 0:00:31 lr 0.000138	time 0.8112 (0.7564)	model_time 0.8108 (0.7507)	loss 2.6739 (2.6423)	grad_norm 1.9474 (2.5398/1.1075)	mem 34604MB
[2025-01-19 19:59:04 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][280/312]	eta 0:00:24 lr 0.000138	time 0.7175 (0.7566)	model_time 0.7173 (0.7510)	loss 2.9960 (2.6496)	grad_norm 3.1542 (2.5204/1.1021)	mem 34604MB
[2025-01-19 19:59:12 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][290/312]	eta 0:00:16 lr 0.000137	time 0.7158 (0.7564)	model_time 0.7156 (0.7511)	loss 2.7240 (2.6501)	grad_norm 1.6019 (2.5301/1.0987)	mem 34604MB
[2025-01-19 19:59:19 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][300/312]	eta 0:00:09 lr 0.000137	time 0.7137 (0.7562)	model_time 0.7136 (0.7510)	loss 3.1428 (2.6483)	grad_norm 1.8185 (2.5320/1.0911)	mem 34604MB
[2025-01-19 19:59:26 internimage_b_1k_224] (main.py 510): INFO Train: [269/300][310/312]	eta 0:00:01 lr 0.000137	time 0.7175 (0.7552)	model_time 0.7174 (0.7502)	loss 2.8721 (2.6510)	grad_norm 2.5062 (2.5381/1.0845)	mem 34604MB
[2025-01-19 19:59:27 internimage_b_1k_224] (main.py 519): INFO EPOCH 269 training takes 0:03:55
[2025-01-19 19:59:27 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_269.pth saving......
[2025-01-19 19:59:30 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_269.pth saved !!!
[2025-01-19 19:59:38 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.614 (7.614)	Loss 0.7000 (0.7000)	Acc@1 86.377 (86.377)	Acc@5 97.998 (97.998)	Mem 34604MB
[2025-01-19 19:59:41 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.963)	Loss 0.9092 (0.7817)	Acc@1 81.030 (84.679)	Acc@5 95.850 (96.977)	Mem 34604MB
[2025-01-19 19:59:41 internimage_b_1k_224] (main.py 575): INFO [Epoch:269] * Acc@1 84.499 Acc@5 96.993
[2025-01-19 19:59:41 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.5%
[2025-01-19 19:59:41 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.55%
[2025-01-19 19:59:50 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.208 (9.208)	Loss 0.7099 (0.7099)	Acc@1 86.548 (86.548)	Acc@5 98.218 (98.218)	Mem 34604MB
[2025-01-19 19:59:55 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.256)	Loss 0.9082 (0.7953)	Acc@1 81.250 (84.659)	Acc@5 96.021 (97.057)	Mem 34604MB
[2025-01-19 19:59:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:269] * Acc@1 84.479 Acc@5 97.083
[2025-01-19 19:59:55 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.5%
[2025-01-19 19:59:55 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 19:59:59 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 19:59:59 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.48%
[2025-01-19 20:00:01 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][0/312]	eta 0:11:08 lr 0.000137	time 2.1431 (2.1431)	model_time 0.7437 (0.7437)	loss 2.4875 (2.4875)	grad_norm 2.7240 (2.7240/0.0000)	mem 34604MB
[2025-01-19 20:00:09 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][10/312]	eta 0:04:22 lr 0.000137	time 0.7385 (0.8682)	model_time 0.7383 (0.7406)	loss 2.5928 (2.6388)	grad_norm 1.6067 (3.1369/1.3873)	mem 34604MB
[2025-01-19 20:00:16 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][20/312]	eta 0:03:55 lr 0.000136	time 0.8192 (0.8076)	model_time 0.8190 (0.7406)	loss 2.9609 (2.6864)	grad_norm 2.6772 (2.8015/1.1279)	mem 34604MB
[2025-01-19 20:00:23 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][30/312]	eta 0:03:41 lr 0.000136	time 0.7228 (0.7838)	model_time 0.7226 (0.7384)	loss 1.8391 (2.6731)	grad_norm 1.4909 (2.5786/1.0323)	mem 34604MB
[2025-01-19 20:00:31 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][40/312]	eta 0:03:30 lr 0.000136	time 0.7374 (0.7723)	model_time 0.7372 (0.7378)	loss 1.9500 (2.6465)	grad_norm 1.3945 (2.4250/0.9881)	mem 34604MB
[2025-01-19 20:00:38 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][50/312]	eta 0:03:20 lr 0.000136	time 0.7251 (0.7656)	model_time 0.7249 (0.7378)	loss 2.0885 (2.6601)	grad_norm 4.0035 (2.5796/1.1444)	mem 34604MB
[2025-01-19 20:00:46 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][60/312]	eta 0:03:11 lr 0.000136	time 0.7261 (0.7611)	model_time 0.7256 (0.7378)	loss 2.7870 (2.6732)	grad_norm 2.8432 (2.5377/1.0662)	mem 34604MB
[2025-01-19 20:00:53 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][70/312]	eta 0:03:04 lr 0.000135	time 0.8144 (0.7633)	model_time 0.8142 (0.7433)	loss 2.6644 (2.6718)	grad_norm 5.8504 (2.6346/1.1243)	mem 34604MB
[2025-01-19 20:01:01 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][80/312]	eta 0:02:57 lr 0.000135	time 0.7661 (0.7630)	model_time 0.7660 (0.7454)	loss 1.8785 (2.6617)	grad_norm 2.2028 (2.6287/1.0793)	mem 34604MB
[2025-01-19 20:01:09 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][90/312]	eta 0:02:50 lr 0.000135	time 0.7164 (0.7658)	model_time 0.7162 (0.7501)	loss 2.7864 (2.6551)	grad_norm 2.0984 (2.6161/1.0618)	mem 34604MB
[2025-01-19 20:01:16 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][100/312]	eta 0:02:42 lr 0.000135	time 0.7169 (0.7647)	model_time 0.7168 (0.7505)	loss 2.8142 (2.6689)	grad_norm 4.3032 (2.6246/1.0804)	mem 34604MB
[2025-01-19 20:01:24 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][110/312]	eta 0:02:34 lr 0.000135	time 0.7219 (0.7633)	model_time 0.7214 (0.7503)	loss 2.9580 (2.6695)	grad_norm 1.4913 (2.7090/1.1297)	mem 34604MB
[2025-01-19 20:01:31 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][120/312]	eta 0:02:26 lr 0.000134	time 0.7212 (0.7605)	model_time 0.7210 (0.7486)	loss 2.8970 (2.6667)	grad_norm 1.7753 (2.7150/1.1538)	mem 34604MB
[2025-01-19 20:01:39 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][130/312]	eta 0:02:18 lr 0.000134	time 0.7160 (0.7586)	model_time 0.7155 (0.7476)	loss 2.9529 (2.6644)	grad_norm 3.2293 (2.6747/1.1267)	mem 34604MB
[2025-01-19 20:01:46 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][140/312]	eta 0:02:10 lr 0.000134	time 0.7168 (0.7566)	model_time 0.7167 (0.7463)	loss 1.9045 (2.6549)	grad_norm 4.1539 (2.6411/1.1190)	mem 34604MB
[2025-01-19 20:01:53 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][150/312]	eta 0:02:02 lr 0.000134	time 0.7212 (0.7555)	model_time 0.7207 (0.7458)	loss 2.2709 (2.6468)	grad_norm 1.5260 (2.6652/1.1339)	mem 34604MB
[2025-01-19 20:02:01 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][160/312]	eta 0:01:54 lr 0.000134	time 0.7309 (0.7537)	model_time 0.7305 (0.7447)	loss 2.3208 (2.6362)	grad_norm 1.9892 (2.6304/1.1236)	mem 34604MB
[2025-01-19 20:02:08 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][170/312]	eta 0:01:46 lr 0.000133	time 0.7258 (0.7525)	model_time 0.7257 (0.7439)	loss 2.8537 (2.6271)	grad_norm 3.0490 (2.6073/1.1113)	mem 34604MB
[2025-01-19 20:02:15 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][180/312]	eta 0:01:39 lr 0.000133	time 0.7347 (0.7516)	model_time 0.7343 (0.7435)	loss 1.6127 (2.6249)	grad_norm 3.4208 (2.5955/1.0970)	mem 34604MB
[2025-01-19 20:02:23 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][190/312]	eta 0:01:31 lr 0.000133	time 0.8022 (0.7532)	model_time 0.8020 (0.7454)	loss 2.9016 (2.6362)	grad_norm 3.7833 (2.5996/1.0846)	mem 34604MB
[2025-01-19 20:02:31 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][200/312]	eta 0:01:24 lr 0.000133	time 0.8087 (0.7537)	model_time 0.8082 (0.7464)	loss 1.7331 (2.6334)	grad_norm 2.9605 (2.6077/1.0740)	mem 34604MB
[2025-01-19 20:02:39 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][210/312]	eta 0:01:17 lr 0.000133	time 0.7154 (0.7561)	model_time 0.7149 (0.7491)	loss 2.6112 (2.6339)	grad_norm 3.0193 (2.6502/1.1239)	mem 34604MB
[2025-01-19 20:02:46 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][220/312]	eta 0:01:09 lr 0.000132	time 0.7270 (0.7558)	model_time 0.7266 (0.7491)	loss 1.8905 (2.6252)	grad_norm 2.9967 (2.6737/1.1366)	mem 34604MB
[2025-01-19 20:02:54 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][230/312]	eta 0:01:02 lr 0.000132	time 0.7252 (0.7564)	model_time 0.7250 (0.7500)	loss 2.8295 (2.6276)	grad_norm 1.7582 (2.6587/1.1222)	mem 34604MB
[2025-01-19 20:03:01 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][240/312]	eta 0:00:54 lr 0.000132	time 0.7297 (0.7555)	model_time 0.7295 (0.7493)	loss 2.9295 (2.6290)	grad_norm 1.7207 (2.6515/1.1180)	mem 34604MB
[2025-01-19 20:03:09 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][250/312]	eta 0:00:46 lr 0.000132	time 0.7176 (0.7545)	model_time 0.7172 (0.7486)	loss 2.7939 (2.6362)	grad_norm 1.2329 (2.6560/1.1211)	mem 34604MB
[2025-01-19 20:03:16 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][260/312]	eta 0:00:39 lr 0.000132	time 0.7630 (0.7537)	model_time 0.7626 (0.7480)	loss 2.5487 (2.6288)	grad_norm 1.6065 (2.6606/1.1173)	mem 34604MB
[2025-01-19 20:03:23 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][270/312]	eta 0:00:31 lr 0.000131	time 0.7206 (0.7530)	model_time 0.7204 (0.7475)	loss 2.3961 (2.6244)	grad_norm 3.4939 (2.6393/1.1150)	mem 34604MB
[2025-01-19 20:03:30 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][280/312]	eta 0:00:24 lr 0.000131	time 0.7261 (0.7521)	model_time 0.7259 (0.7467)	loss 2.8925 (2.6226)	grad_norm 2.8758 (2.6481/1.1050)	mem 34604MB
[2025-01-19 20:03:38 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][290/312]	eta 0:00:16 lr 0.000131	time 0.7192 (0.7514)	model_time 0.7190 (0.7462)	loss 2.8286 (2.6225)	grad_norm 3.2327 (2.6342/1.1046)	mem 34604MB
[2025-01-19 20:03:45 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][300/312]	eta 0:00:09 lr 0.000131	time 0.7150 (0.7507)	model_time 0.7149 (0.7457)	loss 2.5478 (2.6221)	grad_norm 2.2327 (2.6230/1.0970)	mem 34604MB
[2025-01-19 20:03:53 internimage_b_1k_224] (main.py 510): INFO Train: [270/300][310/312]	eta 0:00:01 lr 0.000131	time 0.7945 (0.7506)	model_time 0.7944 (0.7458)	loss 2.9009 (2.6204)	grad_norm 1.7825 (2.5923/1.0731)	mem 34604MB
[2025-01-19 20:03:53 internimage_b_1k_224] (main.py 519): INFO EPOCH 270 training takes 0:03:54
[2025-01-19 20:03:53 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_270.pth saving......
[2025-01-19 20:03:56 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_270.pth saved !!!
[2025-01-19 20:04:04 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.795 (7.795)	Loss 0.6847 (0.6847)	Acc@1 86.450 (86.450)	Acc@5 98.047 (98.047)	Mem 34604MB
[2025-01-19 20:04:08 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.024)	Loss 0.8842 (0.7689)	Acc@1 81.860 (84.737)	Acc@5 96.045 (96.999)	Mem 34604MB
[2025-01-19 20:04:08 internimage_b_1k_224] (main.py 575): INFO [Epoch:270] * Acc@1 84.573 Acc@5 97.003
[2025-01-19 20:04:08 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.6%
[2025-01-19 20:04:08 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 20:04:11 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 20:04:11 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.57%
[2025-01-19 20:04:20 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.004 (9.004)	Loss 0.7096 (0.7096)	Acc@1 86.597 (86.597)	Acc@5 98.242 (98.242)	Mem 34604MB
[2025-01-19 20:04:25 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.196)	Loss 0.9076 (0.7948)	Acc@1 81.250 (84.690)	Acc@5 96.045 (97.070)	Mem 34604MB
[2025-01-19 20:04:25 internimage_b_1k_224] (main.py 575): INFO [Epoch:270] * Acc@1 84.509 Acc@5 97.095
[2025-01-19 20:04:25 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.5%
[2025-01-19 20:04:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 20:04:31 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 20:04:31 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.51%
[2025-01-19 20:04:33 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][0/312]	eta 0:11:43 lr 0.000131	time 2.2538 (2.2538)	model_time 0.7404 (0.7404)	loss 2.8786 (2.8786)	grad_norm 3.2949 (3.2949/0.0000)	mem 34604MB
[2025-01-19 20:04:41 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][10/312]	eta 0:04:33 lr 0.000130	time 0.8077 (0.9054)	model_time 0.8076 (0.7675)	loss 3.2430 (2.8704)	grad_norm 2.9111 (2.1853/0.6803)	mem 34604MB
[2025-01-19 20:04:48 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][20/312]	eta 0:04:07 lr 0.000130	time 0.7377 (0.8464)	model_time 0.7376 (0.7740)	loss 2.2179 (2.7288)	grad_norm 1.6927 (2.0989/0.6048)	mem 34604MB
[2025-01-19 20:04:56 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][30/312]	eta 0:03:50 lr 0.000130	time 0.8117 (0.8169)	model_time 0.8112 (0.7678)	loss 2.1809 (2.6611)	grad_norm 2.0398 (2.1685/0.7053)	mem 34604MB
[2025-01-19 20:05:03 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][40/312]	eta 0:03:36 lr 0.000130	time 0.7222 (0.7978)	model_time 0.7221 (0.7605)	loss 3.0743 (2.6388)	grad_norm 2.4944 (2.4637/1.0268)	mem 34604MB
[2025-01-19 20:05:11 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][50/312]	eta 0:03:25 lr 0.000130	time 0.7463 (0.7846)	model_time 0.7458 (0.7546)	loss 3.0081 (2.6771)	grad_norm 2.2474 (2.4694/0.9891)	mem 34604MB
[2025-01-19 20:05:18 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][60/312]	eta 0:03:15 lr 0.000129	time 0.7210 (0.7770)	model_time 0.7209 (0.7518)	loss 2.6834 (2.6906)	grad_norm 5.0615 (2.4904/1.0349)	mem 34604MB
[2025-01-19 20:05:25 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][70/312]	eta 0:03:06 lr 0.000129	time 0.7209 (0.7703)	model_time 0.7204 (0.7486)	loss 3.1545 (2.6759)	grad_norm 2.5680 (2.4982/1.0389)	mem 34604MB
[2025-01-19 20:05:33 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][80/312]	eta 0:02:57 lr 0.000129	time 0.7515 (0.7653)	model_time 0.7513 (0.7462)	loss 2.4849 (2.6567)	grad_norm 1.3713 (2.4115/1.0214)	mem 34604MB
[2025-01-19 20:05:40 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][90/312]	eta 0:02:49 lr 0.000129	time 0.7300 (0.7619)	model_time 0.7296 (0.7449)	loss 2.2117 (2.6299)	grad_norm 1.2028 (2.3544/0.9990)	mem 34604MB
[2025-01-19 20:05:47 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][100/312]	eta 0:02:40 lr 0.000129	time 0.7223 (0.7590)	model_time 0.7222 (0.7437)	loss 3.1459 (2.6197)	grad_norm 2.8616 (2.2998/0.9717)	mem 34604MB
[2025-01-19 20:05:55 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][110/312]	eta 0:02:33 lr 0.000128	time 0.7088 (0.7576)	model_time 0.7083 (0.7436)	loss 2.9093 (2.6073)	grad_norm 2.8862 (2.2964/0.9428)	mem 34604MB
[2025-01-19 20:06:02 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][120/312]	eta 0:02:25 lr 0.000128	time 0.8402 (0.7585)	model_time 0.8401 (0.7456)	loss 2.5595 (2.6080)	grad_norm 2.1243 (2.2719/0.9248)	mem 34604MB
[2025-01-19 20:06:10 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][130/312]	eta 0:02:17 lr 0.000128	time 0.7281 (0.7577)	model_time 0.7277 (0.7458)	loss 2.9539 (2.6166)	grad_norm 3.3618 (2.2903/0.9221)	mem 34604MB
[2025-01-19 20:06:18 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][140/312]	eta 0:02:10 lr 0.000128	time 0.8337 (0.7612)	model_time 0.8335 (0.7501)	loss 1.8317 (2.6219)	grad_norm 2.0239 (2.2569/0.9097)	mem 34604MB
[2025-01-19 20:06:25 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][150/312]	eta 0:02:03 lr 0.000128	time 0.8119 (0.7605)	model_time 0.8118 (0.7501)	loss 1.7531 (2.6136)	grad_norm 3.3090 (2.3281/1.0098)	mem 34604MB
[2025-01-19 20:06:33 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][160/312]	eta 0:01:55 lr 0.000127	time 0.7237 (0.7592)	model_time 0.7235 (0.7494)	loss 2.8185 (2.6221)	grad_norm 0.9289 (2.3601/1.0297)	mem 34604MB
[2025-01-19 20:06:40 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][170/312]	eta 0:01:47 lr 0.000127	time 0.7240 (0.7577)	model_time 0.7239 (0.7485)	loss 3.0104 (2.6206)	grad_norm 1.2765 (2.3664/1.0170)	mem 34604MB
[2025-01-19 20:06:47 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][180/312]	eta 0:01:39 lr 0.000127	time 0.7470 (0.7564)	model_time 0.7465 (0.7477)	loss 3.0563 (2.6270)	grad_norm 2.2511 (2.3688/1.0052)	mem 34604MB
[2025-01-19 20:06:55 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][190/312]	eta 0:01:32 lr 0.000127	time 0.7093 (0.7550)	model_time 0.7088 (0.7468)	loss 2.3549 (2.6165)	grad_norm 1.7353 (2.3751/1.0036)	mem 34604MB
[2025-01-19 20:07:02 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][200/312]	eta 0:01:24 lr 0.000127	time 0.7246 (0.7537)	model_time 0.7245 (0.7458)	loss 2.5768 (2.6148)	grad_norm 2.5821 (2.3772/0.9993)	mem 34604MB
[2025-01-19 20:07:09 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][210/312]	eta 0:01:16 lr 0.000126	time 0.7197 (0.7528)	model_time 0.7196 (0.7453)	loss 2.7733 (2.6280)	grad_norm 4.3512 (2.4302/1.0504)	mem 34604MB
[2025-01-19 20:07:17 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][220/312]	eta 0:01:09 lr 0.000126	time 0.7207 (0.7521)	model_time 0.7206 (0.7449)	loss 2.5105 (2.6292)	grad_norm 2.4938 (2.4562/1.0725)	mem 34604MB
[2025-01-19 20:07:24 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][230/312]	eta 0:01:01 lr 0.000126	time 0.7325 (0.7514)	model_time 0.7324 (0.7445)	loss 3.0226 (2.6304)	grad_norm 3.1285 (2.4840/1.0745)	mem 34604MB
[2025-01-19 20:07:32 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][240/312]	eta 0:00:54 lr 0.000126	time 0.8008 (0.7516)	model_time 0.8004 (0.7450)	loss 2.0749 (2.6320)	grad_norm 4.0194 (2.4890/1.0677)	mem 34604MB
[2025-01-19 20:07:39 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][250/312]	eta 0:00:46 lr 0.000126	time 0.7180 (0.7516)	model_time 0.7178 (0.7452)	loss 2.4565 (2.6301)	grad_norm 2.8505 (2.5061/1.0975)	mem 34604MB
[2025-01-19 20:07:47 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][260/312]	eta 0:00:39 lr 0.000126	time 0.8082 (0.7532)	model_time 0.8080 (0.7470)	loss 3.3569 (2.6319)	grad_norm 1.3449 (2.5003/1.0938)	mem 34604MB
[2025-01-19 20:07:55 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][270/312]	eta 0:00:31 lr 0.000125	time 0.8363 (0.7533)	model_time 0.8361 (0.7473)	loss 2.6191 (2.6323)	grad_norm 1.9126 (2.5030/1.1081)	mem 34604MB
[2025-01-19 20:08:02 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][280/312]	eta 0:00:24 lr 0.000125	time 0.7397 (0.7529)	model_time 0.7393 (0.7471)	loss 2.7503 (2.6296)	grad_norm 2.6354 (2.4999/1.1048)	mem 34604MB
[2025-01-19 20:08:09 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][290/312]	eta 0:00:16 lr 0.000125	time 0.7241 (0.7520)	model_time 0.7239 (0.7464)	loss 3.0555 (2.6315)	grad_norm 1.6486 (2.5052/1.0919)	mem 34604MB
[2025-01-19 20:08:17 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][300/312]	eta 0:00:09 lr 0.000125	time 0.7121 (0.7514)	model_time 0.7120 (0.7459)	loss 1.9739 (2.6264)	grad_norm 3.4798 (2.5076/1.0896)	mem 34604MB
[2025-01-19 20:08:24 internimage_b_1k_224] (main.py 510): INFO Train: [271/300][310/312]	eta 0:00:01 lr 0.000125	time 0.7161 (0.7504)	model_time 0.7160 (0.7452)	loss 2.8944 (2.6230)	grad_norm 2.0517 (2.5142/1.1031)	mem 34604MB
[2025-01-19 20:08:25 internimage_b_1k_224] (main.py 519): INFO EPOCH 271 training takes 0:03:54
[2025-01-19 20:08:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_271.pth saving......
[2025-01-19 20:08:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_271.pth saved !!!
[2025-01-19 20:08:36 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.392 (7.392)	Loss 0.6887 (0.6887)	Acc@1 86.475 (86.475)	Acc@5 97.876 (97.876)	Mem 34604MB
[2025-01-19 20:08:39 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.951)	Loss 0.8884 (0.7717)	Acc@1 81.714 (84.715)	Acc@5 96.045 (97.008)	Mem 34604MB
[2025-01-19 20:08:39 internimage_b_1k_224] (main.py 575): INFO [Epoch:271] * Acc@1 84.565 Acc@5 97.019
[2025-01-19 20:08:39 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.6%
[2025-01-19 20:08:39 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.57%
[2025-01-19 20:08:48 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.211 (9.211)	Loss 0.7092 (0.7092)	Acc@1 86.572 (86.572)	Acc@5 98.242 (98.242)	Mem 34604MB
[2025-01-19 20:08:53 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.264)	Loss 0.9069 (0.7943)	Acc@1 81.299 (84.699)	Acc@5 96.045 (97.073)	Mem 34604MB
[2025-01-19 20:08:53 internimage_b_1k_224] (main.py 575): INFO [Epoch:271] * Acc@1 84.515 Acc@5 97.097
[2025-01-19 20:08:53 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.5%
[2025-01-19 20:08:53 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 20:08:57 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 20:08:57 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.51%
[2025-01-19 20:08:59 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][0/312]	eta 0:10:15 lr 0.000125	time 1.9742 (1.9742)	model_time 0.7519 (0.7519)	loss 2.9404 (2.9404)	grad_norm 2.7664 (2.7664/0.0000)	mem 34604MB
[2025-01-19 20:09:06 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][10/312]	eta 0:04:16 lr 0.000124	time 0.7218 (0.8494)	model_time 0.7214 (0.7373)	loss 2.5269 (2.6836)	grad_norm 4.0293 (2.8577/0.6566)	mem 34604MB
[2025-01-19 20:09:14 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][20/312]	eta 0:03:51 lr 0.000124	time 0.7533 (0.7939)	model_time 0.7531 (0.7346)	loss 2.8279 (2.7530)	grad_norm 4.8940 (2.9786/1.0270)	mem 34604MB
[2025-01-19 20:09:21 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][30/312]	eta 0:03:38 lr 0.000124	time 0.7223 (0.7762)	model_time 0.7221 (0.7353)	loss 3.0058 (2.7720)	grad_norm 2.9126 (2.8698/1.0874)	mem 34604MB
[2025-01-19 20:09:29 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][40/312]	eta 0:03:29 lr 0.000124	time 0.7978 (0.7685)	model_time 0.7973 (0.7374)	loss 2.8902 (2.8039)	grad_norm 2.6209 (2.7088/1.0395)	mem 34604MB
[2025-01-19 20:09:36 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][50/312]	eta 0:03:21 lr 0.000124	time 0.7679 (0.7672)	model_time 0.7677 (0.7418)	loss 2.3938 (2.7797)	grad_norm 1.5477 (2.5084/1.0347)	mem 34604MB
[2025-01-19 20:09:44 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][60/312]	eta 0:03:12 lr 0.000123	time 0.7245 (0.7653)	model_time 0.7241 (0.7441)	loss 3.1448 (2.7713)	grad_norm 2.3360 (2.4755/0.9891)	mem 34604MB
[2025-01-19 20:09:51 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][70/312]	eta 0:03:05 lr 0.000123	time 0.7165 (0.7658)	model_time 0.7164 (0.7474)	loss 2.3501 (2.7442)	grad_norm 0.9335 (2.4424/0.9925)	mem 34604MB
[2025-01-19 20:09:59 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][80/312]	eta 0:02:57 lr 0.000123	time 0.7365 (0.7634)	model_time 0.7361 (0.7471)	loss 2.7357 (2.7182)	grad_norm 2.5981 (2.4921/0.9769)	mem 34604MB
[2025-01-19 20:10:06 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][90/312]	eta 0:02:49 lr 0.000123	time 0.7203 (0.7622)	model_time 0.7201 (0.7476)	loss 2.3287 (2.6946)	grad_norm 1.4920 (2.5290/1.0180)	mem 34604MB
[2025-01-19 20:10:14 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][100/312]	eta 0:02:40 lr 0.000123	time 0.7261 (0.7584)	model_time 0.7256 (0.7452)	loss 2.0842 (2.6789)	grad_norm 2.6781 (2.5184/0.9903)	mem 34604MB
[2025-01-19 20:10:21 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][110/312]	eta 0:02:32 lr 0.000122	time 0.7357 (0.7565)	model_time 0.7355 (0.7444)	loss 2.5118 (2.6707)	grad_norm 3.6833 (2.4994/0.9668)	mem 34604MB
[2025-01-19 20:10:28 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][120/312]	eta 0:02:24 lr 0.000122	time 0.7227 (0.7544)	model_time 0.7225 (0.7432)	loss 2.7528 (2.6664)	grad_norm 3.1852 (2.4797/0.9411)	mem 34604MB
[2025-01-19 20:10:36 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][130/312]	eta 0:02:16 lr 0.000122	time 0.7205 (0.7522)	model_time 0.7203 (0.7418)	loss 2.5163 (2.6678)	grad_norm 3.3865 (2.4708/0.9422)	mem 34604MB
[2025-01-19 20:10:43 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][140/312]	eta 0:02:09 lr 0.000122	time 0.7330 (0.7510)	model_time 0.7325 (0.7414)	loss 2.8866 (2.6758)	grad_norm 2.6206 (2.4292/0.9318)	mem 34604MB
[2025-01-19 20:10:50 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][150/312]	eta 0:02:01 lr 0.000122	time 0.7262 (0.7495)	model_time 0.7261 (0.7405)	loss 2.1240 (2.6691)	grad_norm 1.8332 (2.3820/0.9200)	mem 34604MB
[2025-01-19 20:10:58 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][160/312]	eta 0:01:53 lr 0.000121	time 0.8077 (0.7497)	model_time 0.8075 (0.7412)	loss 2.6964 (2.6512)	grad_norm 1.5805 (2.3659/0.9155)	mem 34604MB
[2025-01-19 20:11:05 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][170/312]	eta 0:01:46 lr 0.000121	time 0.7232 (0.7503)	model_time 0.7231 (0.7423)	loss 3.1896 (2.6479)	grad_norm 4.3946 (2.3701/0.9153)	mem 34604MB
[2025-01-19 20:11:13 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][180/312]	eta 0:01:39 lr 0.000121	time 0.7219 (0.7508)	model_time 0.7218 (0.7432)	loss 2.4407 (2.6472)	grad_norm 1.6938 (2.3530/0.9066)	mem 34604MB
[2025-01-19 20:11:21 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][190/312]	eta 0:01:31 lr 0.000121	time 0.7492 (0.7525)	model_time 0.7491 (0.7453)	loss 1.7630 (2.6396)	grad_norm 1.2923 (2.3804/0.9355)	mem 34604MB
[2025-01-19 20:11:28 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][200/312]	eta 0:01:24 lr 0.000121	time 0.7150 (0.7522)	model_time 0.7148 (0.7454)	loss 3.0338 (2.6438)	grad_norm 1.2029 (2.3632/0.9314)	mem 34604MB
[2025-01-19 20:11:36 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][210/312]	eta 0:01:16 lr 0.000121	time 0.7246 (0.7518)	model_time 0.7242 (0.7452)	loss 2.8963 (2.6543)	grad_norm 1.5256 (2.4030/0.9622)	mem 34604MB
[2025-01-19 20:11:43 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][220/312]	eta 0:01:09 lr 0.000120	time 0.7269 (0.7509)	model_time 0.7264 (0.7446)	loss 2.1163 (2.6644)	grad_norm 3.1639 (2.3972/0.9464)	mem 34604MB
[2025-01-19 20:11:50 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][230/312]	eta 0:01:01 lr 0.000120	time 0.7196 (0.7502)	model_time 0.7195 (0.7442)	loss 3.1844 (2.6658)	grad_norm 1.9594 (2.3872/0.9332)	mem 34604MB
[2025-01-19 20:11:58 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][240/312]	eta 0:00:53 lr 0.000120	time 0.7160 (0.7495)	model_time 0.7156 (0.7437)	loss 2.7794 (2.6712)	grad_norm 3.0910 (2.3795/0.9247)	mem 34604MB
[2025-01-19 20:12:05 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][250/312]	eta 0:00:46 lr 0.000120	time 0.7228 (0.7486)	model_time 0.7226 (0.7430)	loss 2.1964 (2.6680)	grad_norm 3.7779 (2.3986/0.9565)	mem 34604MB
[2025-01-19 20:12:12 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][260/312]	eta 0:00:38 lr 0.000120	time 0.7365 (0.7480)	model_time 0.7363 (0.7426)	loss 2.6967 (2.6651)	grad_norm 4.5618 (2.4538/1.0298)	mem 34604MB
[2025-01-19 20:12:20 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][270/312]	eta 0:00:31 lr 0.000119	time 0.7138 (0.7470)	model_time 0.7136 (0.7418)	loss 2.8474 (2.6656)	grad_norm 2.8282 (2.4596/1.0315)	mem 34604MB
[2025-01-19 20:12:27 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][280/312]	eta 0:00:23 lr 0.000119	time 0.7872 (0.7468)	model_time 0.7867 (0.7417)	loss 2.7267 (2.6659)	grad_norm 1.7500 (2.4502/1.0217)	mem 34604MB
[2025-01-19 20:12:35 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][290/312]	eta 0:00:16 lr 0.000119	time 0.7127 (0.7475)	model_time 0.7125 (0.7427)	loss 2.7467 (2.6632)	grad_norm 2.9632 (2.4477/1.0123)	mem 34604MB
[2025-01-19 20:12:42 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][300/312]	eta 0:00:08 lr 0.000119	time 0.7131 (0.7477)	model_time 0.7130 (0.7430)	loss 2.1082 (2.6542)	grad_norm 1.4334 (2.4367/1.0177)	mem 34604MB
[2025-01-19 20:12:50 internimage_b_1k_224] (main.py 510): INFO Train: [272/300][310/312]	eta 0:00:01 lr 0.000119	time 1.0476 (0.7487)	model_time 1.0475 (0.7442)	loss 2.2080 (2.6472)	grad_norm 1.5465 (2.4108/1.0160)	mem 34604MB
[2025-01-19 20:12:51 internimage_b_1k_224] (main.py 519): INFO EPOCH 272 training takes 0:03:53
[2025-01-19 20:12:51 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_272.pth saving......
[2025-01-19 20:12:54 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_272.pth saved !!!
[2025-01-19 20:13:01 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.467 (7.467)	Loss 0.6843 (0.6843)	Acc@1 86.475 (86.475)	Acc@5 97.998 (97.998)	Mem 34604MB
[2025-01-19 20:13:04 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.952)	Loss 0.8794 (0.7680)	Acc@1 81.592 (84.657)	Acc@5 96.143 (96.990)	Mem 34604MB
[2025-01-19 20:13:05 internimage_b_1k_224] (main.py 575): INFO [Epoch:272] * Acc@1 84.485 Acc@5 96.995
[2025-01-19 20:13:05 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.5%
[2025-01-19 20:13:05 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.57%
[2025-01-19 20:13:14 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.181 (9.181)	Loss 0.7090 (0.7090)	Acc@1 86.597 (86.597)	Acc@5 98.218 (98.218)	Mem 34604MB
[2025-01-19 20:13:18 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.251)	Loss 0.9062 (0.7938)	Acc@1 81.299 (84.715)	Acc@5 96.045 (97.077)	Mem 34604MB
[2025-01-19 20:13:19 internimage_b_1k_224] (main.py 575): INFO [Epoch:272] * Acc@1 84.529 Acc@5 97.101
[2025-01-19 20:13:19 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.5%
[2025-01-19 20:13:19 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 20:13:22 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 20:13:22 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.53%
[2025-01-19 20:13:24 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][0/312]	eta 0:10:45 lr 0.000119	time 2.0695 (2.0695)	model_time 0.7362 (0.7362)	loss 2.4110 (2.4110)	grad_norm 3.6566 (3.6566/0.0000)	mem 34604MB
[2025-01-19 20:13:32 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][10/312]	eta 0:04:26 lr 0.000118	time 0.7184 (0.8828)	model_time 0.7180 (0.7613)	loss 2.7583 (2.7231)	grad_norm 2.2043 (2.4529/0.7163)	mem 34604MB
[2025-01-19 20:13:40 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][20/312]	eta 0:03:59 lr 0.000118	time 0.7222 (0.8186)	model_time 0.7218 (0.7548)	loss 2.9017 (2.7386)	grad_norm 2.5593 (2.3928/0.7345)	mem 34604MB
[2025-01-19 20:13:47 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][30/312]	eta 0:03:43 lr 0.000118	time 0.7213 (0.7925)	model_time 0.7211 (0.7491)	loss 2.4962 (2.6451)	grad_norm 1.9253 (2.3412/0.6654)	mem 34604MB
[2025-01-19 20:13:54 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][40/312]	eta 0:03:32 lr 0.000118	time 0.7198 (0.7809)	model_time 0.7193 (0.7481)	loss 2.8885 (2.6516)	grad_norm 4.1769 (2.4509/0.7740)	mem 34604MB
[2025-01-19 20:14:02 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][50/312]	eta 0:03:21 lr 0.000118	time 0.7383 (0.7709)	model_time 0.7379 (0.7444)	loss 2.7035 (2.6341)	grad_norm 1.6487 (2.3785/0.7410)	mem 34604MB
[2025-01-19 20:14:09 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][60/312]	eta 0:03:12 lr 0.000118	time 0.7279 (0.7642)	model_time 0.7274 (0.7419)	loss 2.7375 (2.6308)	grad_norm 2.7158 (2.3844/0.7430)	mem 34604MB
[2025-01-19 20:14:16 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][70/312]	eta 0:03:03 lr 0.000117	time 0.7208 (0.7598)	model_time 0.7204 (0.7406)	loss 2.2266 (2.6104)	grad_norm 3.4855 (2.4258/0.7597)	mem 34604MB
[2025-01-19 20:14:24 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][80/312]	eta 0:02:55 lr 0.000117	time 0.7255 (0.7559)	model_time 0.7253 (0.7390)	loss 2.7295 (2.6115)	grad_norm 3.6748 (2.4188/0.7938)	mem 34604MB
[2025-01-19 20:14:31 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][90/312]	eta 0:02:47 lr 0.000117	time 0.7188 (0.7547)	model_time 0.7187 (0.7397)	loss 3.0721 (2.6151)	grad_norm 3.9646 (2.4653/0.9041)	mem 34604MB
[2025-01-19 20:14:39 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][100/312]	eta 0:02:40 lr 0.000117	time 0.7259 (0.7558)	model_time 0.7257 (0.7422)	loss 2.6799 (2.6135)	grad_norm 3.2251 (2.4389/0.8877)	mem 34604MB
[2025-01-19 20:14:46 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][110/312]	eta 0:02:32 lr 0.000117	time 0.8367 (0.7561)	model_time 0.8362 (0.7437)	loss 2.9321 (2.6295)	grad_norm 1.4821 (2.4723/0.9427)	mem 34604MB
[2025-01-19 20:14:54 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][120/312]	eta 0:02:25 lr 0.000116	time 0.7174 (0.7567)	model_time 0.7172 (0.7453)	loss 2.4691 (2.6228)	grad_norm 1.7435 (2.5050/0.9683)	mem 34604MB
[2025-01-19 20:15:01 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][130/312]	eta 0:02:17 lr 0.000116	time 0.7195 (0.7563)	model_time 0.7190 (0.7458)	loss 3.2622 (2.6088)	grad_norm 3.4075 (2.6285/1.1642)	mem 34604MB
[2025-01-19 20:15:09 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][140/312]	eta 0:02:10 lr 0.000116	time 0.7317 (0.7558)	model_time 0.7315 (0.7460)	loss 1.8191 (2.5970)	grad_norm 2.7298 (2.6699/1.1858)	mem 34604MB
[2025-01-19 20:15:16 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][150/312]	eta 0:02:02 lr 0.000116	time 0.7362 (0.7546)	model_time 0.7357 (0.7454)	loss 2.6360 (2.5980)	grad_norm 1.1870 (2.6257/1.1805)	mem 34604MB
[2025-01-19 20:15:24 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][160/312]	eta 0:01:54 lr 0.000116	time 0.7245 (0.7534)	model_time 0.7244 (0.7447)	loss 2.5466 (2.6071)	grad_norm 1.2602 (2.5692/1.1684)	mem 34604MB
[2025-01-19 20:15:31 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][170/312]	eta 0:01:46 lr 0.000115	time 0.7224 (0.7523)	model_time 0.7220 (0.7441)	loss 2.2228 (2.6128)	grad_norm 2.5774 (2.5397/1.1483)	mem 34604MB
[2025-01-19 20:15:38 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][180/312]	eta 0:01:39 lr 0.000115	time 0.7075 (0.7511)	model_time 0.7074 (0.7433)	loss 1.9649 (2.6104)	grad_norm 4.1829 (2.5533/1.1337)	mem 34604MB
[2025-01-19 20:15:46 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][190/312]	eta 0:01:31 lr 0.000115	time 0.7258 (0.7498)	model_time 0.7254 (0.7425)	loss 2.9451 (2.6121)	grad_norm 1.5499 (2.5324/1.1195)	mem 34604MB
[2025-01-19 20:15:53 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][200/312]	eta 0:01:23 lr 0.000115	time 0.7352 (0.7488)	model_time 0.7350 (0.7417)	loss 2.5042 (2.6056)	grad_norm 3.5388 (2.5195/1.1065)	mem 34604MB
[2025-01-19 20:16:00 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][210/312]	eta 0:01:16 lr 0.000115	time 0.7194 (0.7485)	model_time 0.7189 (0.7418)	loss 2.2064 (2.6000)	grad_norm 4.2191 (2.5521/1.1177)	mem 34604MB
[2025-01-19 20:16:08 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][220/312]	eta 0:01:08 lr 0.000115	time 0.7234 (0.7492)	model_time 0.7233 (0.7428)	loss 2.0437 (2.5979)	grad_norm 1.6663 (2.5250/1.1171)	mem 34604MB
[2025-01-19 20:16:16 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][230/312]	eta 0:01:01 lr 0.000114	time 0.8431 (0.7498)	model_time 0.8427 (0.7437)	loss 2.6702 (2.5951)	grad_norm 4.8774 (2.5336/1.1201)	mem 34604MB
[2025-01-19 20:16:23 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][240/312]	eta 0:00:53 lr 0.000114	time 0.7169 (0.7499)	model_time 0.7168 (0.7440)	loss 2.9163 (2.5945)	grad_norm 2.0687 (2.5257/1.1069)	mem 34604MB
[2025-01-19 20:16:31 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][250/312]	eta 0:00:46 lr 0.000114	time 0.7179 (0.7496)	model_time 0.7177 (0.7439)	loss 3.0095 (2.5960)	grad_norm 2.2847 (2.5188/1.1034)	mem 34604MB
[2025-01-19 20:16:38 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][260/312]	eta 0:00:38 lr 0.000114	time 0.7195 (0.7494)	model_time 0.7193 (0.7439)	loss 2.5374 (2.5957)	grad_norm 2.2196 (2.5309/1.0957)	mem 34604MB
[2025-01-19 20:16:45 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][270/312]	eta 0:00:31 lr 0.000114	time 0.7236 (0.7490)	model_time 0.7234 (0.7437)	loss 3.0955 (2.5881)	grad_norm 2.2086 (2.5129/1.0847)	mem 34604MB
[2025-01-19 20:16:53 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][280/312]	eta 0:00:23 lr 0.000114	time 0.7215 (0.7491)	model_time 0.7213 (0.7440)	loss 2.7083 (2.5845)	grad_norm 2.6181 (2.4888/1.0791)	mem 34604MB
[2025-01-19 20:17:00 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][290/312]	eta 0:00:16 lr 0.000113	time 0.7098 (0.7483)	model_time 0.7096 (0.7433)	loss 2.6532 (2.5817)	grad_norm 2.9312 (2.4896/1.0681)	mem 34604MB
[2025-01-19 20:17:07 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][300/312]	eta 0:00:08 lr 0.000113	time 0.7148 (0.7475)	model_time 0.7147 (0.7427)	loss 2.4561 (2.5865)	grad_norm 1.6624 (2.4850/1.0835)	mem 34604MB
[2025-01-19 20:17:15 internimage_b_1k_224] (main.py 510): INFO Train: [273/300][310/312]	eta 0:00:01 lr 0.000113	time 0.7179 (0.7466)	model_time 0.7178 (0.7419)	loss 3.3028 (2.5940)	grad_norm 1.9648 (2.4887/1.0892)	mem 34604MB
[2025-01-19 20:17:15 internimage_b_1k_224] (main.py 519): INFO EPOCH 273 training takes 0:03:52
[2025-01-19 20:17:15 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_273.pth saving......
[2025-01-19 20:17:18 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_273.pth saved !!!
[2025-01-19 20:17:26 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.362 (7.362)	Loss 0.6878 (0.6878)	Acc@1 86.816 (86.816)	Acc@5 98.022 (98.022)	Mem 34604MB
[2025-01-19 20:17:29 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.960)	Loss 0.8955 (0.7763)	Acc@1 81.445 (84.735)	Acc@5 96.216 (97.048)	Mem 34604MB
[2025-01-19 20:17:29 internimage_b_1k_224] (main.py 575): INFO [Epoch:273] * Acc@1 84.571 Acc@5 97.057
[2025-01-19 20:17:29 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.6%
[2025-01-19 20:17:29 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.57%
[2025-01-19 20:17:38 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.086 (9.086)	Loss 0.7087 (0.7087)	Acc@1 86.548 (86.548)	Acc@5 98.218 (98.218)	Mem 34604MB
[2025-01-19 20:17:43 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.237)	Loss 0.9054 (0.7932)	Acc@1 81.201 (84.701)	Acc@5 96.094 (97.090)	Mem 34604MB
[2025-01-19 20:17:43 internimage_b_1k_224] (main.py 575): INFO [Epoch:273] * Acc@1 84.523 Acc@5 97.113
[2025-01-19 20:17:43 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.5%
[2025-01-19 20:17:43 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.53%
[2025-01-19 20:17:46 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][0/312]	eta 0:16:01 lr 0.000113	time 3.0831 (3.0831)	model_time 1.4984 (1.4984)	loss 2.1348 (2.1348)	grad_norm 1.5702 (1.5702/0.0000)	mem 34604MB
[2025-01-19 20:17:54 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][10/312]	eta 0:04:48 lr 0.000113	time 0.7217 (0.9545)	model_time 0.7212 (0.8102)	loss 3.2978 (2.5909)	grad_norm 3.3436 (2.5700/1.1611)	mem 34604MB
[2025-01-19 20:18:01 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][20/312]	eta 0:04:11 lr 0.000113	time 0.8538 (0.8616)	model_time 0.8537 (0.7859)	loss 2.5686 (2.4952)	grad_norm 1.5030 (2.5297/0.9641)	mem 34604MB
[2025-01-19 20:18:09 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][30/312]	eta 0:03:53 lr 0.000112	time 0.7226 (0.8285)	model_time 0.7224 (0.7771)	loss 3.0373 (2.5794)	grad_norm 4.1300 (2.6149/1.0148)	mem 34604MB
[2025-01-19 20:18:17 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][40/312]	eta 0:03:41 lr 0.000112	time 0.7228 (0.8131)	model_time 0.7224 (0.7741)	loss 2.9321 (2.5410)	grad_norm 2.0012 (2.6751/1.0305)	mem 34604MB
[2025-01-19 20:18:25 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][50/312]	eta 0:03:32 lr 0.000112	time 0.8449 (0.8112)	model_time 0.8444 (0.7798)	loss 2.5175 (2.5654)	grad_norm 0.9703 (2.7035/1.0381)	mem 34604MB
[2025-01-19 20:18:32 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][60/312]	eta 0:03:22 lr 0.000112	time 0.8104 (0.8033)	model_time 0.8099 (0.7770)	loss 2.9384 (2.5645)	grad_norm 1.6186 (2.5940/1.0085)	mem 34604MB
[2025-01-19 20:18:40 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][70/312]	eta 0:03:12 lr 0.000112	time 0.7213 (0.7942)	model_time 0.7208 (0.7715)	loss 2.1674 (2.5401)	grad_norm 1.3123 (2.4997/1.0035)	mem 34604MB
[2025-01-19 20:18:47 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][80/312]	eta 0:03:02 lr 0.000112	time 0.7212 (0.7872)	model_time 0.7211 (0.7673)	loss 2.5601 (2.5462)	grad_norm 2.4407 (2.4710/0.9710)	mem 34604MB
[2025-01-19 20:18:54 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][90/312]	eta 0:02:53 lr 0.000111	time 0.7263 (0.7816)	model_time 0.7262 (0.7639)	loss 3.0884 (2.5573)	grad_norm 1.7582 (2.4542/0.9580)	mem 34604MB
[2025-01-19 20:19:02 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][100/312]	eta 0:02:44 lr 0.000111	time 0.7262 (0.7760)	model_time 0.7258 (0.7600)	loss 2.7603 (2.5558)	grad_norm 2.0470 (2.4487/0.9260)	mem 34604MB
[2025-01-19 20:19:09 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][110/312]	eta 0:02:35 lr 0.000111	time 0.7414 (0.7715)	model_time 0.7412 (0.7569)	loss 3.0210 (2.5665)	grad_norm 3.5578 (2.4538/0.9082)	mem 34604MB
[2025-01-19 20:19:16 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][120/312]	eta 0:02:27 lr 0.000111	time 0.7241 (0.7676)	model_time 0.7237 (0.7542)	loss 2.8669 (2.5742)	grad_norm 2.9193 (2.4408/0.8895)	mem 34604MB
[2025-01-19 20:19:23 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][130/312]	eta 0:02:19 lr 0.000111	time 0.7359 (0.7644)	model_time 0.7357 (0.7520)	loss 2.8533 (2.5706)	grad_norm 2.6915 (2.4252/0.8692)	mem 34604MB
[2025-01-19 20:19:31 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][140/312]	eta 0:02:11 lr 0.000110	time 0.7271 (0.7629)	model_time 0.7270 (0.7513)	loss 2.7205 (2.5793)	grad_norm 2.2054 (2.4306/0.8731)	mem 34604MB
[2025-01-19 20:19:38 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][150/312]	eta 0:02:03 lr 0.000110	time 0.7234 (0.7620)	model_time 0.7230 (0.7512)	loss 2.7573 (2.5883)	grad_norm 2.1865 (2.4202/0.8826)	mem 34604MB
[2025-01-19 20:19:46 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][160/312]	eta 0:01:55 lr 0.000110	time 0.7166 (0.7622)	model_time 0.7162 (0.7520)	loss 2.7151 (2.5995)	grad_norm 1.9266 (2.3956/0.8916)	mem 34604MB
[2025-01-19 20:19:54 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][170/312]	eta 0:01:48 lr 0.000110	time 0.9808 (0.7637)	model_time 0.9806 (0.7541)	loss 2.9356 (2.5989)	grad_norm 2.1248 (2.4118/0.8895)	mem 34604MB
[2025-01-19 20:20:01 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][180/312]	eta 0:01:40 lr 0.000110	time 0.8175 (0.7640)	model_time 0.8171 (0.7549)	loss 2.2552 (2.6051)	grad_norm 3.4693 (2.4233/0.8950)	mem 34604MB
[2025-01-19 20:20:09 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][190/312]	eta 0:01:33 lr 0.000110	time 0.7254 (0.7627)	model_time 0.7249 (0.7540)	loss 2.4271 (2.5988)	grad_norm 1.4943 (2.4460/0.9235)	mem 34604MB
[2025-01-19 20:20:16 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][200/312]	eta 0:01:25 lr 0.000109	time 0.7249 (0.7616)	model_time 0.7247 (0.7533)	loss 2.5405 (2.6071)	grad_norm 4.4208 (2.4709/0.9514)	mem 34604MB
[2025-01-19 20:20:24 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][210/312]	eta 0:01:17 lr 0.000109	time 0.7092 (0.7601)	model_time 0.7090 (0.7522)	loss 1.7889 (2.6069)	grad_norm 1.3944 (2.4593/0.9411)	mem 34604MB
[2025-01-19 20:20:31 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][220/312]	eta 0:01:09 lr 0.000109	time 0.7204 (0.7585)	model_time 0.7203 (0.7510)	loss 2.9031 (2.6145)	grad_norm 1.5454 (2.4318/0.9353)	mem 34604MB
[2025-01-19 20:20:38 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][230/312]	eta 0:01:02 lr 0.000109	time 0.7185 (0.7574)	model_time 0.7180 (0.7502)	loss 2.0558 (2.6221)	grad_norm 1.1906 (2.4208/0.9385)	mem 34604MB
[2025-01-19 20:20:45 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][240/312]	eta 0:00:54 lr 0.000109	time 0.7340 (0.7561)	model_time 0.7338 (0.7492)	loss 3.0542 (2.6246)	grad_norm 3.2767 (2.4569/0.9987)	mem 34604MB
[2025-01-19 20:20:53 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][250/312]	eta 0:00:46 lr 0.000109	time 0.7240 (0.7550)	model_time 0.7235 (0.7483)	loss 2.0921 (2.6247)	grad_norm 3.1851 (2.4833/1.0210)	mem 34604MB
[2025-01-19 20:21:00 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][260/312]	eta 0:00:39 lr 0.000108	time 0.7207 (0.7545)	model_time 0.7206 (0.7481)	loss 2.6836 (2.6255)	grad_norm 1.3571 (2.4787/1.0239)	mem 34604MB
[2025-01-19 20:21:08 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][270/312]	eta 0:00:31 lr 0.000108	time 0.7210 (0.7548)	model_time 0.7205 (0.7486)	loss 1.8637 (2.6350)	grad_norm 3.7056 (2.4994/1.0420)	mem 34604MB
[2025-01-19 20:21:15 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][280/312]	eta 0:00:24 lr 0.000108	time 0.7320 (0.7554)	model_time 0.7315 (0.7494)	loss 2.6064 (2.6380)	grad_norm 3.1821 (2.4958/1.0342)	mem 34604MB
[2025-01-19 20:21:23 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][290/312]	eta 0:00:16 lr 0.000108	time 0.8437 (0.7559)	model_time 0.8435 (0.7501)	loss 2.9280 (2.6370)	grad_norm 2.4344 (2.4830/1.0243)	mem 34604MB
[2025-01-19 20:21:31 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][300/312]	eta 0:00:09 lr 0.000108	time 0.7989 (0.7561)	model_time 0.7988 (0.7505)	loss 1.9116 (2.6365)	grad_norm 1.8733 (2.4973/1.0312)	mem 34604MB
[2025-01-19 20:21:38 internimage_b_1k_224] (main.py 510): INFO Train: [274/300][310/312]	eta 0:00:01 lr 0.000108	time 0.7077 (0.7551)	model_time 0.7076 (0.7497)	loss 2.8356 (2.6376)	grad_norm 2.7011 (2.4785/1.0214)	mem 34604MB
[2025-01-19 20:21:39 internimage_b_1k_224] (main.py 519): INFO EPOCH 274 training takes 0:03:55
[2025-01-19 20:21:39 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_274.pth saving......
[2025-01-19 20:21:42 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_274.pth saved !!!
[2025-01-19 20:21:50 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.462 (7.462)	Loss 0.6894 (0.6894)	Acc@1 86.548 (86.548)	Acc@5 98.071 (98.071)	Mem 34604MB
[2025-01-19 20:21:53 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.952)	Loss 0.8917 (0.7753)	Acc@1 81.323 (84.730)	Acc@5 95.996 (97.002)	Mem 34604MB
[2025-01-19 20:21:53 internimage_b_1k_224] (main.py 575): INFO [Epoch:274] * Acc@1 84.563 Acc@5 97.013
[2025-01-19 20:21:53 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.6%
[2025-01-19 20:21:53 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.57%
[2025-01-19 20:22:02 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.154 (9.154)	Loss 0.7084 (0.7084)	Acc@1 86.597 (86.597)	Acc@5 98.218 (98.218)	Mem 34604MB
[2025-01-19 20:22:06 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.238)	Loss 0.9048 (0.7927)	Acc@1 81.226 (84.721)	Acc@5 96.094 (97.086)	Mem 34604MB
[2025-01-19 20:22:07 internimage_b_1k_224] (main.py 575): INFO [Epoch:274] * Acc@1 84.543 Acc@5 97.109
[2025-01-19 20:22:07 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.5%
[2025-01-19 20:22:07 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 20:22:11 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 20:22:11 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.54%
[2025-01-19 20:22:12 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][0/312]	eta 0:10:10 lr 0.000107	time 1.9561 (1.9561)	model_time 0.7408 (0.7408)	loss 1.9923 (1.9923)	grad_norm 2.6828 (2.6828/0.0000)	mem 34604MB
[2025-01-19 20:22:20 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][10/312]	eta 0:04:14 lr 0.000107	time 0.7284 (0.8442)	model_time 0.7280 (0.7334)	loss 2.3881 (2.5950)	grad_norm 2.3949 (2.3387/0.7890)	mem 34604MB
[2025-01-19 20:22:27 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][20/312]	eta 0:03:51 lr 0.000107	time 0.7318 (0.7938)	model_time 0.7316 (0.7356)	loss 3.1717 (2.6311)	grad_norm 1.0134 (2.3962/0.8689)	mem 34604MB
[2025-01-19 20:22:35 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][30/312]	eta 0:03:38 lr 0.000107	time 0.7301 (0.7750)	model_time 0.7299 (0.7355)	loss 2.9639 (2.6592)	grad_norm 3.3995 (2.4129/0.9703)	mem 34604MB
[2025-01-19 20:22:42 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][40/312]	eta 0:03:27 lr 0.000107	time 0.7494 (0.7634)	model_time 0.7492 (0.7334)	loss 2.1237 (2.5985)	grad_norm 1.8149 (2.3844/0.9138)	mem 34604MB
[2025-01-19 20:22:49 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][50/312]	eta 0:03:18 lr 0.000107	time 0.7158 (0.7585)	model_time 0.7153 (0.7343)	loss 2.7260 (2.5805)	grad_norm 1.4927 (2.4354/0.9974)	mem 34604MB
[2025-01-19 20:22:57 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][60/312]	eta 0:03:10 lr 0.000106	time 0.7167 (0.7550)	model_time 0.7162 (0.7347)	loss 2.9302 (2.5876)	grad_norm 2.6094 (2.5074/0.9781)	mem 34604MB
[2025-01-19 20:23:04 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][70/312]	eta 0:03:02 lr 0.000106	time 0.7324 (0.7528)	model_time 0.7320 (0.7353)	loss 2.2179 (2.5764)	grad_norm 2.8514 (2.4732/0.9736)	mem 34604MB
[2025-01-19 20:23:12 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][80/312]	eta 0:02:55 lr 0.000106	time 0.7350 (0.7545)	model_time 0.7348 (0.7391)	loss 1.5928 (2.5766)	grad_norm 2.3115 (2.3948/0.9526)	mem 34604MB
[2025-01-19 20:23:19 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][90/312]	eta 0:02:47 lr 0.000106	time 0.7219 (0.7556)	model_time 0.7215 (0.7419)	loss 2.1147 (2.6002)	grad_norm 1.5966 (2.3590/0.9172)	mem 34604MB
[2025-01-19 20:23:27 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][100/312]	eta 0:02:41 lr 0.000106	time 0.8143 (0.7595)	model_time 0.8141 (0.7471)	loss 2.8877 (2.6248)	grad_norm 1.2330 (2.3215/0.9052)	mem 34604MB
[2025-01-19 20:23:35 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][110/312]	eta 0:02:33 lr 0.000106	time 0.7226 (0.7601)	model_time 0.7224 (0.7488)	loss 3.1639 (2.6283)	grad_norm 3.4517 (2.4013/0.9527)	mem 34604MB
[2025-01-19 20:23:42 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][120/312]	eta 0:02:25 lr 0.000105	time 0.7230 (0.7584)	model_time 0.7226 (0.7480)	loss 2.2191 (2.6336)	grad_norm 3.3175 (2.4384/0.9623)	mem 34604MB
[2025-01-19 20:23:50 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][130/312]	eta 0:02:17 lr 0.000105	time 0.7103 (0.7579)	model_time 0.7098 (0.7482)	loss 2.6835 (2.6296)	grad_norm 2.6255 (2.4844/0.9861)	mem 34604MB
[2025-01-19 20:23:57 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][140/312]	eta 0:02:10 lr 0.000105	time 0.7383 (0.7563)	model_time 0.7381 (0.7473)	loss 2.9551 (2.6188)	grad_norm 3.2197 (2.5411/1.0559)	mem 34604MB
[2025-01-19 20:24:04 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][150/312]	eta 0:02:02 lr 0.000105	time 0.7392 (0.7548)	model_time 0.7388 (0.7464)	loss 2.9592 (2.6150)	grad_norm 2.0436 (2.5166/1.0396)	mem 34604MB
[2025-01-19 20:24:12 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][160/312]	eta 0:01:54 lr 0.000105	time 0.7364 (0.7531)	model_time 0.7360 (0.7452)	loss 2.6786 (2.6018)	grad_norm 2.1851 (2.5197/1.0451)	mem 34604MB
[2025-01-19 20:24:19 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][170/312]	eta 0:01:46 lr 0.000105	time 0.7335 (0.7515)	model_time 0.7333 (0.7440)	loss 1.5467 (2.6014)	grad_norm 3.2024 (2.5230/1.0377)	mem 34604MB
[2025-01-19 20:24:26 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][180/312]	eta 0:01:39 lr 0.000104	time 0.7195 (0.7506)	model_time 0.7191 (0.7435)	loss 1.8728 (2.6093)	grad_norm 6.0072 (2.5634/1.0714)	mem 34604MB
[2025-01-19 20:24:34 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][190/312]	eta 0:01:31 lr 0.000104	time 0.7237 (0.7499)	model_time 0.7235 (0.7431)	loss 2.5080 (2.6128)	grad_norm 4.1302 (2.5782/1.0668)	mem 34604MB
[2025-01-19 20:24:41 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][200/312]	eta 0:01:24 lr 0.000104	time 0.7222 (0.7504)	model_time 0.7218 (0.7440)	loss 2.2405 (2.6165)	grad_norm 3.3937 (2.5773/1.0507)	mem 34604MB
[2025-01-19 20:24:49 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][210/312]	eta 0:01:16 lr 0.000104	time 0.7127 (0.7508)	model_time 0.7125 (0.7447)	loss 2.2502 (2.6176)	grad_norm 3.9085 (2.6207/1.0677)	mem 34604MB
[2025-01-19 20:24:57 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][220/312]	eta 0:01:09 lr 0.000104	time 0.8141 (0.7527)	model_time 0.8139 (0.7468)	loss 2.2779 (2.6179)	grad_norm 2.3780 (2.6159/1.0526)	mem 34604MB
[2025-01-19 20:25:04 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][230/312]	eta 0:01:01 lr 0.000104	time 0.8236 (0.7530)	model_time 0.8234 (0.7474)	loss 2.7640 (2.6204)	grad_norm 2.5648 (2.6070/1.0436)	mem 34604MB
[2025-01-19 20:25:12 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][240/312]	eta 0:00:54 lr 0.000103	time 0.7193 (0.7527)	model_time 0.7191 (0.7473)	loss 1.9109 (2.6093)	grad_norm 2.3802 (2.5983/1.0361)	mem 34604MB
[2025-01-19 20:25:19 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][250/312]	eta 0:00:46 lr 0.000103	time 0.7183 (0.7525)	model_time 0.7180 (0.7473)	loss 1.7932 (2.6079)	grad_norm 2.0838 (2.6126/1.0475)	mem 34604MB
[2025-01-19 20:25:27 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][260/312]	eta 0:00:39 lr 0.000103	time 0.7602 (0.7519)	model_time 0.7601 (0.7468)	loss 2.7181 (2.6121)	grad_norm 2.1851 (2.6398/1.0751)	mem 34604MB
[2025-01-19 20:25:34 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][270/312]	eta 0:00:31 lr 0.000103	time 0.7285 (0.7512)	model_time 0.7284 (0.7464)	loss 2.7335 (2.6089)	grad_norm 2.9150 (2.6366/1.0684)	mem 34604MB
[2025-01-19 20:25:41 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][280/312]	eta 0:00:24 lr 0.000103	time 0.7178 (0.7504)	model_time 0.7174 (0.7457)	loss 1.6687 (2.5989)	grad_norm 2.8483 (2.6292/1.0605)	mem 34604MB
[2025-01-19 20:25:49 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][290/312]	eta 0:00:16 lr 0.000103	time 0.7314 (0.7498)	model_time 0.7309 (0.7452)	loss 2.8543 (2.5972)	grad_norm 1.9143 (2.6068/1.0557)	mem 34604MB
[2025-01-19 20:25:56 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][300/312]	eta 0:00:08 lr 0.000102	time 0.7106 (0.7494)	model_time 0.7105 (0.7449)	loss 2.8327 (2.5958)	grad_norm 2.7859 (2.5972/1.0502)	mem 34604MB
[2025-01-19 20:26:03 internimage_b_1k_224] (main.py 510): INFO Train: [275/300][310/312]	eta 0:00:01 lr 0.000102	time 0.7946 (0.7487)	model_time 0.7945 (0.7444)	loss 2.8749 (2.5967)	grad_norm 3.1790 (2.6125/1.0488)	mem 34604MB
[2025-01-19 20:26:04 internimage_b_1k_224] (main.py 519): INFO EPOCH 275 training takes 0:03:53
[2025-01-19 20:26:04 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_275.pth saving......
[2025-01-19 20:26:07 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_275.pth saved !!!
[2025-01-19 20:26:14 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.096 (7.096)	Loss 0.6893 (0.6893)	Acc@1 86.475 (86.475)	Acc@5 98.047 (98.047)	Mem 34604MB
[2025-01-19 20:26:18 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.955)	Loss 0.8860 (0.7698)	Acc@1 81.177 (84.746)	Acc@5 96.216 (97.104)	Mem 34604MB
[2025-01-19 20:26:18 internimage_b_1k_224] (main.py 575): INFO [Epoch:275] * Acc@1 84.577 Acc@5 97.101
[2025-01-19 20:26:18 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.6%
[2025-01-19 20:26:18 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 20:26:22 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 20:26:22 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.58%
[2025-01-19 20:26:29 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.212 (7.212)	Loss 0.7082 (0.7082)	Acc@1 86.621 (86.621)	Acc@5 98.218 (98.218)	Mem 34604MB
[2025-01-19 20:26:32 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.931)	Loss 0.9041 (0.7922)	Acc@1 81.226 (84.739)	Acc@5 96.118 (97.099)	Mem 34604MB
[2025-01-19 20:26:32 internimage_b_1k_224] (main.py 575): INFO [Epoch:275] * Acc@1 84.553 Acc@5 97.121
[2025-01-19 20:26:32 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.6%
[2025-01-19 20:26:32 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 20:26:36 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 20:26:36 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.55%
[2025-01-19 20:26:38 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][0/312]	eta 0:10:02 lr 0.000102	time 1.9309 (1.9309)	model_time 0.7329 (0.7329)	loss 1.8479 (1.8479)	grad_norm 3.5974 (3.5974/0.0000)	mem 34604MB
[2025-01-19 20:26:45 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][10/312]	eta 0:04:21 lr 0.000102	time 0.7299 (0.8665)	model_time 0.7297 (0.7573)	loss 2.9257 (2.4065)	grad_norm 3.7461 (3.2312/1.2410)	mem 34604MB
[2025-01-19 20:26:53 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][20/312]	eta 0:03:59 lr 0.000102	time 0.7094 (0.8192)	model_time 0.7092 (0.7618)	loss 3.0797 (2.5493)	grad_norm 1.9980 (3.1998/1.2442)	mem 34604MB
[2025-01-19 20:27:01 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][30/312]	eta 0:03:49 lr 0.000102	time 0.7218 (0.8132)	model_time 0.7216 (0.7742)	loss 2.7551 (2.5114)	grad_norm 1.6094 (2.9096/1.2339)	mem 34604MB
[2025-01-19 20:27:09 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][40/312]	eta 0:03:37 lr 0.000102	time 0.7147 (0.8013)	model_time 0.7142 (0.7717)	loss 3.0136 (2.5204)	grad_norm 2.0365 (2.8079/1.2635)	mem 34604MB
[2025-01-19 20:27:16 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][50/312]	eta 0:03:27 lr 0.000101	time 0.7233 (0.7906)	model_time 0.7232 (0.7667)	loss 1.6551 (2.5226)	grad_norm 4.3742 (2.6989/1.2243)	mem 34604MB
[2025-01-19 20:27:23 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][60/312]	eta 0:03:17 lr 0.000101	time 0.7169 (0.7818)	model_time 0.7167 (0.7618)	loss 2.7941 (2.5323)	grad_norm 2.0220 (2.6870/1.1660)	mem 34604MB
[2025-01-19 20:27:31 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][70/312]	eta 0:03:07 lr 0.000101	time 0.7134 (0.7760)	model_time 0.7131 (0.7587)	loss 2.6518 (2.5868)	grad_norm 4.1032 (2.6630/1.1655)	mem 34604MB
[2025-01-19 20:27:38 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][80/312]	eta 0:02:58 lr 0.000101	time 0.7473 (0.7706)	model_time 0.7471 (0.7554)	loss 2.5858 (2.6049)	grad_norm 2.0990 (2.6061/1.1132)	mem 34604MB
[2025-01-19 20:27:46 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][90/312]	eta 0:02:50 lr 0.000101	time 0.7278 (0.7667)	model_time 0.7272 (0.7532)	loss 2.9153 (2.6234)	grad_norm 2.8080 (2.5146/1.0996)	mem 34604MB
[2025-01-19 20:27:53 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][100/312]	eta 0:02:41 lr 0.000101	time 0.7222 (0.7634)	model_time 0.7220 (0.7512)	loss 2.7065 (2.6264)	grad_norm 4.1074 (2.5323/1.0722)	mem 34604MB
[2025-01-19 20:28:00 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][110/312]	eta 0:02:33 lr 0.000100	time 0.8076 (0.7610)	model_time 0.8073 (0.7498)	loss 1.6508 (2.5992)	grad_norm 3.8819 (2.5847/1.1127)	mem 34604MB
[2025-01-19 20:28:08 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][120/312]	eta 0:02:25 lr 0.000100	time 0.7142 (0.7588)	model_time 0.7140 (0.7485)	loss 2.8772 (2.6020)	grad_norm 1.4616 (2.5600/1.0919)	mem 34604MB
[2025-01-19 20:28:15 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][130/312]	eta 0:02:18 lr 0.000100	time 0.8137 (0.7596)	model_time 0.8135 (0.7501)	loss 2.7476 (2.6068)	grad_norm 2.0104 (2.5264/1.0782)	mem 34604MB
[2025-01-19 20:28:23 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][140/312]	eta 0:02:10 lr 0.000100	time 0.8328 (0.7603)	model_time 0.8323 (0.7514)	loss 2.8936 (2.5964)	grad_norm 1.4040 (2.5036/1.0575)	mem 34604MB
[2025-01-19 20:28:31 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][150/312]	eta 0:02:03 lr 0.000100	time 0.7922 (0.7624)	model_time 0.7919 (0.7541)	loss 1.7198 (2.5787)	grad_norm 2.6931 (2.4551/1.0441)	mem 34604MB
[2025-01-19 20:28:39 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][160/312]	eta 0:01:56 lr 0.000100	time 0.7120 (0.7634)	model_time 0.7118 (0.7556)	loss 2.9644 (2.5847)	grad_norm 2.9072 (2.4713/1.0373)	mem 34604MB
[2025-01-19 20:28:46 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][170/312]	eta 0:01:48 lr 0.000099	time 0.7129 (0.7641)	model_time 0.7127 (0.7567)	loss 2.8828 (2.5843)	grad_norm 2.9289 (2.4982/1.0541)	mem 34604MB
[2025-01-19 20:28:54 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][180/312]	eta 0:01:40 lr 0.000099	time 0.7211 (0.7627)	model_time 0.7209 (0.7556)	loss 2.5477 (2.5872)	grad_norm 3.5634 (2.5171/1.0728)	mem 34604MB
[2025-01-19 20:29:01 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][190/312]	eta 0:01:32 lr 0.000099	time 0.7488 (0.7619)	model_time 0.7486 (0.7552)	loss 2.3307 (2.5846)	grad_norm 2.0568 (2.5069/1.0656)	mem 34604MB
[2025-01-19 20:29:09 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][200/312]	eta 0:01:25 lr 0.000099	time 0.7152 (0.7604)	model_time 0.7151 (0.7540)	loss 2.5418 (2.5883)	grad_norm 3.9931 (2.5260/1.0676)	mem 34604MB
[2025-01-19 20:29:16 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][210/312]	eta 0:01:17 lr 0.000099	time 0.7631 (0.7592)	model_time 0.7629 (0.7531)	loss 3.2904 (2.5811)	grad_norm 2.8043 (2.5366/1.0589)	mem 34604MB
[2025-01-19 20:29:23 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][220/312]	eta 0:01:09 lr 0.000099	time 0.7407 (0.7576)	model_time 0.7405 (0.7517)	loss 2.2605 (2.5792)	grad_norm 3.6455 (2.5691/1.0722)	mem 34604MB
[2025-01-19 20:29:31 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][230/312]	eta 0:01:02 lr 0.000098	time 0.7379 (0.7563)	model_time 0.7377 (0.7507)	loss 2.8079 (2.5762)	grad_norm 3.2836 (2.5838/1.0657)	mem 34604MB
[2025-01-19 20:29:38 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][240/312]	eta 0:00:54 lr 0.000098	time 0.7572 (0.7559)	model_time 0.7571 (0.7505)	loss 2.5701 (2.5735)	grad_norm 3.5121 (2.5669/1.0542)	mem 34604MB
[2025-01-19 20:29:46 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][250/312]	eta 0:00:46 lr 0.000098	time 0.8200 (0.7562)	model_time 0.8198 (0.7510)	loss 2.8227 (2.5772)	grad_norm 4.5880 (2.5575/1.0522)	mem 34604MB
[2025-01-19 20:29:53 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][260/312]	eta 0:00:39 lr 0.000098	time 0.8451 (0.7564)	model_time 0.8449 (0.7514)	loss 2.7145 (2.5725)	grad_norm 6.3310 (2.5778/1.0667)	mem 34604MB
[2025-01-19 20:30:01 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][270/312]	eta 0:00:31 lr 0.000098	time 0.7822 (0.7575)	model_time 0.7820 (0.7527)	loss 2.8388 (2.5711)	grad_norm 4.0874 (2.5904/1.0648)	mem 34604MB
[2025-01-19 20:30:09 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][280/312]	eta 0:00:24 lr 0.000098	time 0.7241 (0.7577)	model_time 0.7236 (0.7530)	loss 2.6851 (2.5677)	grad_norm 2.2334 (2.6046/1.0708)	mem 34604MB
[2025-01-19 20:30:16 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][290/312]	eta 0:00:16 lr 0.000098	time 0.7251 (0.7576)	model_time 0.7246 (0.7530)	loss 2.6704 (2.5702)	grad_norm 3.8926 (2.6176/1.0730)	mem 34604MB
[2025-01-19 20:30:24 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][300/312]	eta 0:00:09 lr 0.000097	time 0.7159 (0.7567)	model_time 0.7158 (0.7523)	loss 2.9361 (2.5732)	grad_norm 5.0231 (2.6211/1.0765)	mem 34604MB
[2025-01-19 20:30:31 internimage_b_1k_224] (main.py 510): INFO Train: [276/300][310/312]	eta 0:00:01 lr 0.000097	time 0.7150 (0.7557)	model_time 0.7150 (0.7515)	loss 2.6284 (2.5715)	grad_norm 1.1143 (2.5957/1.0611)	mem 34604MB
[2025-01-19 20:30:32 internimage_b_1k_224] (main.py 519): INFO EPOCH 276 training takes 0:03:55
[2025-01-19 20:30:32 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_276.pth saving......
[2025-01-19 20:30:35 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_276.pth saved !!!
[2025-01-19 20:30:42 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.099 (7.099)	Loss 0.6908 (0.6908)	Acc@1 86.450 (86.450)	Acc@5 97.998 (97.998)	Mem 34604MB
[2025-01-19 20:30:45 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.940)	Loss 0.9041 (0.7767)	Acc@1 81.177 (84.737)	Acc@5 95.801 (97.059)	Mem 34604MB
[2025-01-19 20:30:45 internimage_b_1k_224] (main.py 575): INFO [Epoch:276] * Acc@1 84.563 Acc@5 97.071
[2025-01-19 20:30:45 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.6%
[2025-01-19 20:30:45 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.58%
[2025-01-19 20:30:55 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.152 (9.152)	Loss 0.7078 (0.7078)	Acc@1 86.646 (86.646)	Acc@5 98.218 (98.218)	Mem 34604MB
[2025-01-19 20:30:59 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.234)	Loss 0.9036 (0.7917)	Acc@1 81.201 (84.750)	Acc@5 96.143 (97.108)	Mem 34604MB
[2025-01-19 20:30:59 internimage_b_1k_224] (main.py 575): INFO [Epoch:276] * Acc@1 84.561 Acc@5 97.129
[2025-01-19 20:30:59 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.6%
[2025-01-19 20:30:59 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 20:31:03 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 20:31:03 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.56%
[2025-01-19 20:31:05 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][0/312]	eta 0:11:43 lr 0.000097	time 2.2538 (2.2538)	model_time 0.7437 (0.7437)	loss 3.1148 (3.1148)	grad_norm 1.7393 (1.7393/0.0000)	mem 34604MB
[2025-01-19 20:31:12 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][10/312]	eta 0:04:26 lr 0.000097	time 0.7455 (0.8820)	model_time 0.7451 (0.7444)	loss 2.6674 (2.5244)	grad_norm 2.0869 (2.1568/0.9579)	mem 34604MB
[2025-01-19 20:31:20 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][20/312]	eta 0:03:55 lr 0.000097	time 0.7225 (0.8075)	model_time 0.7220 (0.7353)	loss 2.9955 (2.4691)	grad_norm 2.3562 (2.2151/0.9879)	mem 34604MB
[2025-01-19 20:31:27 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][30/312]	eta 0:03:40 lr 0.000097	time 0.7237 (0.7822)	model_time 0.7234 (0.7331)	loss 1.6987 (2.4474)	grad_norm 4.3158 (2.3379/1.0043)	mem 34604MB
[2025-01-19 20:31:34 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][40/312]	eta 0:03:29 lr 0.000097	time 0.7163 (0.7713)	model_time 0.7158 (0.7341)	loss 2.7519 (2.4916)	grad_norm 1.6167 (2.2237/1.0135)	mem 34604MB
[2025-01-19 20:31:42 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][50/312]	eta 0:03:20 lr 0.000096	time 0.7267 (0.7656)	model_time 0.7265 (0.7356)	loss 2.5638 (2.5201)	grad_norm 4.8965 (2.2226/1.0004)	mem 34604MB
[2025-01-19 20:31:49 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][60/312]	eta 0:03:12 lr 0.000096	time 0.7188 (0.7644)	model_time 0.7186 (0.7393)	loss 2.2220 (2.5173)	grad_norm 3.9050 (2.3532/1.0354)	mem 34604MB
[2025-01-19 20:31:57 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][70/312]	eta 0:03:05 lr 0.000096	time 0.8083 (0.7667)	model_time 0.8081 (0.7451)	loss 2.7821 (2.5407)	grad_norm 4.2899 (2.4977/1.0821)	mem 34604MB
[2025-01-19 20:32:05 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][80/312]	eta 0:02:58 lr 0.000096	time 0.7987 (0.7684)	model_time 0.7985 (0.7495)	loss 2.8562 (2.5553)	grad_norm 4.5037 (2.5530/1.1073)	mem 34604MB
[2025-01-19 20:32:13 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][90/312]	eta 0:02:50 lr 0.000096	time 0.7977 (0.7672)	model_time 0.7975 (0.7503)	loss 2.9611 (2.5634)	grad_norm 1.7203 (2.5224/1.1014)	mem 34604MB
[2025-01-19 20:32:20 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][100/312]	eta 0:02:41 lr 0.000096	time 0.8079 (0.7633)	model_time 0.8074 (0.7480)	loss 2.7739 (2.5950)	grad_norm 2.5647 (2.5581/1.1122)	mem 34604MB
[2025-01-19 20:32:27 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][110/312]	eta 0:02:34 lr 0.000095	time 0.7467 (0.7626)	model_time 0.7465 (0.7487)	loss 2.6201 (2.5947)	grad_norm 2.7067 (2.5648/1.1019)	mem 34604MB
[2025-01-19 20:32:35 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][120/312]	eta 0:02:25 lr 0.000095	time 0.7220 (0.7604)	model_time 0.7218 (0.7475)	loss 1.6161 (2.5910)	grad_norm 3.1651 (2.5370/1.0829)	mem 34604MB
[2025-01-19 20:32:42 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][130/312]	eta 0:02:18 lr 0.000095	time 0.7163 (0.7583)	model_time 0.7161 (0.7464)	loss 2.8794 (2.5884)	grad_norm 1.7551 (2.5163/1.0651)	mem 34604MB
[2025-01-19 20:32:49 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][140/312]	eta 0:02:10 lr 0.000095	time 0.7183 (0.7568)	model_time 0.7181 (0.7458)	loss 2.9503 (2.5955)	grad_norm 1.9556 (2.4948/1.0502)	mem 34604MB
[2025-01-19 20:32:57 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][150/312]	eta 0:02:02 lr 0.000095	time 0.7410 (0.7552)	model_time 0.7408 (0.7448)	loss 2.7283 (2.6104)	grad_norm 1.6911 (2.4584/1.0422)	mem 34604MB
[2025-01-19 20:33:04 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][160/312]	eta 0:01:54 lr 0.000095	time 0.7332 (0.7540)	model_time 0.7330 (0.7443)	loss 2.9080 (2.6108)	grad_norm 1.2404 (2.4470/1.0310)	mem 34604MB
[2025-01-19 20:33:12 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][170/312]	eta 0:01:46 lr 0.000094	time 0.7251 (0.7529)	model_time 0.7249 (0.7438)	loss 2.9273 (2.6044)	grad_norm 1.4962 (2.4802/1.0523)	mem 34604MB
[2025-01-19 20:33:19 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][180/312]	eta 0:01:39 lr 0.000094	time 0.7196 (0.7535)	model_time 0.7194 (0.7448)	loss 2.8584 (2.6201)	grad_norm 2.0818 (2.4519/1.0346)	mem 34604MB
[2025-01-19 20:33:27 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][190/312]	eta 0:01:32 lr 0.000094	time 0.7190 (0.7548)	model_time 0.7188 (0.7466)	loss 2.8908 (2.6164)	grad_norm 2.1019 (2.4458/1.0308)	mem 34604MB
[2025-01-19 20:33:35 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][200/312]	eta 0:01:24 lr 0.000094	time 0.8162 (0.7563)	model_time 0.8160 (0.7485)	loss 2.5309 (2.6193)	grad_norm 3.4469 (2.4475/1.0240)	mem 34604MB
[2025-01-19 20:33:43 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][210/312]	eta 0:01:17 lr 0.000094	time 0.8111 (0.7573)	model_time 0.8109 (0.7498)	loss 2.5971 (2.6081)	grad_norm 1.6322 (2.4444/1.0130)	mem 34604MB
[2025-01-19 20:33:50 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][220/312]	eta 0:01:09 lr 0.000094	time 0.8430 (0.7564)	model_time 0.8425 (0.7492)	loss 1.9280 (2.6083)	grad_norm 2.9323 (2.4532/1.0003)	mem 34604MB
[2025-01-19 20:33:57 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][230/312]	eta 0:01:01 lr 0.000094	time 0.7203 (0.7557)	model_time 0.7198 (0.7488)	loss 3.4598 (2.6178)	grad_norm 1.5974 (2.4362/0.9900)	mem 34604MB
[2025-01-19 20:34:05 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][240/312]	eta 0:00:54 lr 0.000093	time 0.7199 (0.7547)	model_time 0.7198 (0.7481)	loss 2.5417 (2.6203)	grad_norm 2.6658 (2.4429/0.9798)	mem 34604MB
[2025-01-19 20:34:12 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][250/312]	eta 0:00:46 lr 0.000093	time 0.7211 (0.7538)	model_time 0.7207 (0.7474)	loss 2.6764 (2.6234)	grad_norm 2.3196 (2.4561/0.9734)	mem 34604MB
[2025-01-19 20:34:19 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][260/312]	eta 0:00:39 lr 0.000093	time 0.7258 (0.7527)	model_time 0.7257 (0.7465)	loss 2.5058 (2.6247)	grad_norm 2.4097 (2.4541/0.9661)	mem 34604MB
[2025-01-19 20:34:27 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][270/312]	eta 0:00:31 lr 0.000093	time 0.7180 (0.7519)	model_time 0.7176 (0.7460)	loss 2.2862 (2.6209)	grad_norm 2.3510 (2.4419/0.9549)	mem 34604MB
[2025-01-19 20:34:34 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][280/312]	eta 0:00:24 lr 0.000093	time 0.7494 (0.7513)	model_time 0.7492 (0.7456)	loss 2.7704 (2.6189)	grad_norm 0.9798 (2.4814/1.0200)	mem 34604MB
[2025-01-19 20:34:41 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][290/312]	eta 0:00:16 lr 0.000093	time 0.7180 (0.7507)	model_time 0.7178 (0.7451)	loss 2.6711 (2.6108)	grad_norm 1.5975 (2.4643/1.0139)	mem 34604MB
[2025-01-19 20:34:49 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][300/312]	eta 0:00:09 lr 0.000092	time 0.7157 (0.7506)	model_time 0.7156 (0.7452)	loss 2.2467 (2.6106)	grad_norm 1.4376 (2.4611/1.0059)	mem 34604MB
[2025-01-19 20:34:56 internimage_b_1k_224] (main.py 510): INFO Train: [277/300][310/312]	eta 0:00:01 lr 0.000092	time 0.7129 (0.7510)	model_time 0.7128 (0.7458)	loss 2.7609 (2.6159)	grad_norm 3.0288 (2.4844/1.0018)	mem 34604MB
[2025-01-19 20:34:57 internimage_b_1k_224] (main.py 519): INFO EPOCH 277 training takes 0:03:54
[2025-01-19 20:34:57 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_277.pth saving......
[2025-01-19 20:35:00 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_277.pth saved !!!
[2025-01-19 20:35:08 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.255 (7.255)	Loss 0.6900 (0.6900)	Acc@1 86.499 (86.499)	Acc@5 97.949 (97.949)	Mem 34604MB
[2025-01-19 20:35:11 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.185 (0.940)	Loss 0.8957 (0.7761)	Acc@1 81.079 (84.684)	Acc@5 95.923 (97.073)	Mem 34604MB
[2025-01-19 20:35:11 internimage_b_1k_224] (main.py 575): INFO [Epoch:277] * Acc@1 84.509 Acc@5 97.085
[2025-01-19 20:35:11 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.5%
[2025-01-19 20:35:11 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.58%
[2025-01-19 20:35:20 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.079 (9.079)	Loss 0.7076 (0.7076)	Acc@1 86.670 (86.670)	Acc@5 98.218 (98.218)	Mem 34604MB
[2025-01-19 20:35:24 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.228)	Loss 0.9031 (0.7912)	Acc@1 81.201 (84.768)	Acc@5 96.143 (97.112)	Mem 34604MB
[2025-01-19 20:35:25 internimage_b_1k_224] (main.py 575): INFO [Epoch:277] * Acc@1 84.579 Acc@5 97.133
[2025-01-19 20:35:25 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.6%
[2025-01-19 20:35:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 20:35:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 20:35:28 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.58%
[2025-01-19 20:35:30 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][0/312]	eta 0:10:41 lr 0.000092	time 2.0554 (2.0554)	model_time 0.7313 (0.7313)	loss 2.9258 (2.9258)	grad_norm 2.7849 (2.7849/0.0000)	mem 34604MB
[2025-01-19 20:35:38 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][10/312]	eta 0:04:30 lr 0.000092	time 0.8750 (0.8947)	model_time 0.8748 (0.7741)	loss 2.2324 (2.4747)	grad_norm 1.0982 (3.0145/1.0325)	mem 34604MB
[2025-01-19 20:35:46 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][20/312]	eta 0:04:03 lr 0.000092	time 0.7250 (0.8348)	model_time 0.7249 (0.7714)	loss 2.1707 (2.6040)	grad_norm 1.8244 (2.6832/0.9889)	mem 34604MB
[2025-01-19 20:35:53 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][30/312]	eta 0:03:48 lr 0.000092	time 0.7533 (0.8109)	model_time 0.7530 (0.7679)	loss 2.5583 (2.6097)	grad_norm 3.1881 (2.5013/0.8996)	mem 34604MB
[2025-01-19 20:36:01 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][40/312]	eta 0:03:36 lr 0.000092	time 0.7248 (0.7944)	model_time 0.7242 (0.7618)	loss 2.1623 (2.5737)	grad_norm 2.2536 (2.7118/1.1300)	mem 34604MB
[2025-01-19 20:36:08 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][50/312]	eta 0:03:25 lr 0.000092	time 0.7316 (0.7838)	model_time 0.7314 (0.7574)	loss 2.7770 (2.5692)	grad_norm 2.1704 (2.6041/1.0728)	mem 34604MB
[2025-01-19 20:36:16 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][60/312]	eta 0:03:15 lr 0.000091	time 0.7173 (0.7745)	model_time 0.7171 (0.7525)	loss 2.8883 (2.6045)	grad_norm 1.9644 (2.5684/1.0431)	mem 34604MB
[2025-01-19 20:36:23 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][70/312]	eta 0:03:05 lr 0.000091	time 0.7199 (0.7684)	model_time 0.7197 (0.7494)	loss 2.7867 (2.6064)	grad_norm 2.3494 (2.5056/1.0221)	mem 34604MB
[2025-01-19 20:36:30 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][80/312]	eta 0:02:57 lr 0.000091	time 0.7331 (0.7638)	model_time 0.7329 (0.7471)	loss 1.9127 (2.6277)	grad_norm 2.1050 (2.5278/1.0745)	mem 34604MB
[2025-01-19 20:36:38 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][90/312]	eta 0:02:48 lr 0.000091	time 0.7278 (0.7605)	model_time 0.7273 (0.7456)	loss 1.6727 (2.6042)	grad_norm 3.4505 (2.5767/1.0703)	mem 34604MB
[2025-01-19 20:36:45 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][100/312]	eta 0:02:40 lr 0.000091	time 0.7266 (0.7578)	model_time 0.7265 (0.7443)	loss 2.3373 (2.6082)	grad_norm 1.0937 (2.5931/1.0871)	mem 34604MB
[2025-01-19 20:36:53 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][110/312]	eta 0:02:33 lr 0.000091	time 0.8008 (0.7588)	model_time 0.8006 (0.7465)	loss 2.6806 (2.6098)	grad_norm 2.6438 (2.6237/1.1218)	mem 34604MB
[2025-01-19 20:37:00 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][120/312]	eta 0:02:25 lr 0.000091	time 0.7283 (0.7600)	model_time 0.7278 (0.7487)	loss 2.4286 (2.6192)	grad_norm 2.8308 (2.6860/1.2172)	mem 34604MB
[2025-01-19 20:37:08 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][130/312]	eta 0:02:18 lr 0.000090	time 1.0355 (0.7625)	model_time 1.0353 (0.7520)	loss 3.1938 (2.6131)	grad_norm 2.0348 (2.7653/1.2453)	mem 34604MB
[2025-01-19 20:37:16 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][140/312]	eta 0:02:11 lr 0.000090	time 0.7153 (0.7629)	model_time 0.7151 (0.7531)	loss 2.8917 (2.6343)	grad_norm 2.1522 (2.7353/1.2436)	mem 34604MB
[2025-01-19 20:37:23 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][150/312]	eta 0:02:03 lr 0.000090	time 0.7242 (0.7610)	model_time 0.7237 (0.7519)	loss 2.0386 (2.6135)	grad_norm 3.8089 (2.7319/1.2218)	mem 34604MB
[2025-01-19 20:37:31 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][160/312]	eta 0:01:55 lr 0.000090	time 0.7147 (0.7596)	model_time 0.7144 (0.7510)	loss 2.8433 (2.6085)	grad_norm 3.3627 (2.7481/1.1980)	mem 34604MB
[2025-01-19 20:37:38 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][170/312]	eta 0:01:47 lr 0.000090	time 0.7142 (0.7582)	model_time 0.7140 (0.7501)	loss 1.7994 (2.5996)	grad_norm 1.2605 (2.7327/1.1938)	mem 34604MB
[2025-01-19 20:37:45 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][180/312]	eta 0:01:39 lr 0.000090	time 0.7166 (0.7563)	model_time 0.7161 (0.7486)	loss 2.8068 (2.5991)	grad_norm 2.5925 (2.7214/1.2019)	mem 34604MB
[2025-01-19 20:37:52 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][190/312]	eta 0:01:32 lr 0.000089	time 0.7236 (0.7547)	model_time 0.7234 (0.7474)	loss 2.1635 (2.6055)	grad_norm 2.7026 (2.7012/1.1775)	mem 34604MB
[2025-01-19 20:38:00 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][200/312]	eta 0:01:24 lr 0.000089	time 0.7195 (0.7535)	model_time 0.7191 (0.7465)	loss 2.9313 (2.6118)	grad_norm 1.3708 (2.6936/1.1553)	mem 34604MB
[2025-01-19 20:38:07 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][210/312]	eta 0:01:16 lr 0.000089	time 0.7462 (0.7527)	model_time 0.7456 (0.7460)	loss 2.7744 (2.6256)	grad_norm 2.4954 (2.6686/1.1464)	mem 34604MB
[2025-01-19 20:38:14 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][220/312]	eta 0:01:09 lr 0.000089	time 0.7289 (0.7514)	model_time 0.7284 (0.7451)	loss 2.8388 (2.6253)	grad_norm 1.4854 (2.6489/1.1357)	mem 34604MB
[2025-01-19 20:38:22 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][230/312]	eta 0:01:01 lr 0.000089	time 0.8025 (0.7522)	model_time 0.8023 (0.7461)	loss 3.0440 (2.6210)	grad_norm 4.2909 (2.6543/1.1424)	mem 34604MB
[2025-01-19 20:38:30 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][240/312]	eta 0:00:54 lr 0.000089	time 0.7527 (0.7525)	model_time 0.7525 (0.7466)	loss 1.9930 (2.6174)	grad_norm 1.3446 (2.6433/1.1382)	mem 34604MB
[2025-01-19 20:38:38 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][250/312]	eta 0:00:46 lr 0.000089	time 0.7996 (0.7538)	model_time 0.7994 (0.7481)	loss 2.5390 (2.6128)	grad_norm 1.7854 (2.6367/1.1285)	mem 34604MB
[2025-01-19 20:38:45 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][260/312]	eta 0:00:39 lr 0.000088	time 0.7389 (0.7548)	model_time 0.7387 (0.7494)	loss 2.8221 (2.6094)	grad_norm 2.6423 (2.6299/1.1250)	mem 34604MB
[2025-01-19 20:38:53 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][270/312]	eta 0:00:31 lr 0.000088	time 0.7155 (0.7545)	model_time 0.7153 (0.7492)	loss 2.4646 (2.6081)	grad_norm 2.0942 (2.6002/1.1204)	mem 34604MB
[2025-01-19 20:39:00 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][280/312]	eta 0:00:24 lr 0.000088	time 0.7165 (0.7537)	model_time 0.7163 (0.7486)	loss 2.8903 (2.6115)	grad_norm 3.5975 (2.5962/1.1150)	mem 34604MB
[2025-01-19 20:39:07 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][290/312]	eta 0:00:16 lr 0.000088	time 0.8138 (0.7531)	model_time 0.8136 (0.7482)	loss 3.2780 (2.6178)	grad_norm 2.8117 (2.5960/1.1016)	mem 34604MB
[2025-01-19 20:39:15 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][300/312]	eta 0:00:09 lr 0.000088	time 0.7111 (0.7522)	model_time 0.7110 (0.7474)	loss 2.6293 (2.6118)	grad_norm 3.0402 (2.5845/1.1011)	mem 34604MB
[2025-01-19 20:39:22 internimage_b_1k_224] (main.py 510): INFO Train: [278/300][310/312]	eta 0:00:01 lr 0.000088	time 0.7150 (0.7511)	model_time 0.7148 (0.7465)	loss 1.9840 (2.6123)	grad_norm 1.4532 (2.5520/1.0905)	mem 34604MB
[2025-01-19 20:39:23 internimage_b_1k_224] (main.py 519): INFO EPOCH 278 training takes 0:03:54
[2025-01-19 20:39:23 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_278.pth saving......
[2025-01-19 20:39:26 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_278.pth saved !!!
[2025-01-19 20:39:33 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.388 (7.388)	Loss 0.6921 (0.6921)	Acc@1 86.670 (86.670)	Acc@5 97.900 (97.900)	Mem 34604MB
[2025-01-19 20:39:36 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.927)	Loss 0.8887 (0.7703)	Acc@1 81.274 (84.783)	Acc@5 95.898 (97.024)	Mem 34604MB
[2025-01-19 20:39:37 internimage_b_1k_224] (main.py 575): INFO [Epoch:278] * Acc@1 84.617 Acc@5 97.025
[2025-01-19 20:39:37 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.6%
[2025-01-19 20:39:37 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 20:39:40 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 20:39:40 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.62%
[2025-01-19 20:39:47 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.625 (7.625)	Loss 0.7073 (0.7073)	Acc@1 86.694 (86.694)	Acc@5 98.218 (98.218)	Mem 34604MB
[2025-01-19 20:39:51 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.980)	Loss 0.9025 (0.7907)	Acc@1 81.226 (84.772)	Acc@5 96.094 (97.124)	Mem 34604MB
[2025-01-19 20:39:51 internimage_b_1k_224] (main.py 575): INFO [Epoch:278] * Acc@1 84.587 Acc@5 97.147
[2025-01-19 20:39:51 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.6%
[2025-01-19 20:39:51 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 20:39:54 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 20:39:54 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.59%
[2025-01-19 20:39:57 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][0/312]	eta 0:13:02 lr 0.000088	time 2.5085 (2.5085)	model_time 0.7717 (0.7717)	loss 2.9523 (2.9523)	grad_norm 2.2850 (2.2850/0.0000)	mem 34604MB
[2025-01-19 20:40:04 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][10/312]	eta 0:04:29 lr 0.000088	time 0.7412 (0.8933)	model_time 0.7410 (0.7352)	loss 2.1221 (2.5339)	grad_norm 1.7510 (2.0880/0.6892)	mem 34604MB
[2025-01-19 20:40:12 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][20/312]	eta 0:03:59 lr 0.000087	time 0.7171 (0.8188)	model_time 0.7169 (0.7358)	loss 2.1162 (2.6511)	grad_norm 2.9494 (2.2147/0.7414)	mem 34604MB
[2025-01-19 20:40:19 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][30/312]	eta 0:03:43 lr 0.000087	time 0.8057 (0.7921)	model_time 0.8055 (0.7358)	loss 2.9622 (2.6456)	grad_norm 2.0628 (2.1071/0.6667)	mem 34604MB
[2025-01-19 20:40:27 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][40/312]	eta 0:03:35 lr 0.000087	time 0.8088 (0.7926)	model_time 0.8086 (0.7500)	loss 2.7027 (2.6201)	grad_norm 7.2028 (2.5188/1.2726)	mem 34604MB
[2025-01-19 20:40:35 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][50/312]	eta 0:03:26 lr 0.000087	time 0.7235 (0.7880)	model_time 0.7233 (0.7537)	loss 2.7256 (2.6254)	grad_norm 3.4169 (2.6521/1.3926)	mem 34604MB
[2025-01-19 20:40:42 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][60/312]	eta 0:03:17 lr 0.000087	time 0.8001 (0.7835)	model_time 0.8000 (0.7547)	loss 3.0700 (2.6235)	grad_norm 2.9257 (2.6697/1.3340)	mem 34604MB
[2025-01-19 20:40:50 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][70/312]	eta 0:03:09 lr 0.000087	time 0.7198 (0.7819)	model_time 0.7196 (0.7571)	loss 2.8050 (2.6427)	grad_norm 3.5000 (2.6416/1.2705)	mem 34604MB
[2025-01-19 20:40:57 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][80/312]	eta 0:03:00 lr 0.000087	time 0.7540 (0.7763)	model_time 0.7538 (0.7545)	loss 2.4957 (2.6393)	grad_norm 3.3981 (2.5900/1.2264)	mem 34604MB
[2025-01-19 20:41:05 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][90/312]	eta 0:02:51 lr 0.000086	time 0.7400 (0.7723)	model_time 0.7394 (0.7529)	loss 2.3881 (2.6369)	grad_norm 2.3972 (2.6063/1.2019)	mem 34604MB
[2025-01-19 20:41:12 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][100/312]	eta 0:02:42 lr 0.000086	time 0.7191 (0.7686)	model_time 0.7189 (0.7511)	loss 2.5598 (2.6254)	grad_norm 3.4369 (2.6422/1.2065)	mem 34604MB
[2025-01-19 20:41:19 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][110/312]	eta 0:02:34 lr 0.000086	time 0.7281 (0.7648)	model_time 0.7279 (0.7488)	loss 3.3341 (2.6335)	grad_norm 1.2825 (2.6085/1.1875)	mem 34604MB
[2025-01-19 20:41:27 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][120/312]	eta 0:02:26 lr 0.000086	time 0.7263 (0.7615)	model_time 0.7261 (0.7468)	loss 2.2715 (2.6359)	grad_norm 3.3076 (2.5850/1.1743)	mem 34604MB
[2025-01-19 20:41:34 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][130/312]	eta 0:02:18 lr 0.000086	time 0.7200 (0.7584)	model_time 0.7195 (0.7448)	loss 1.6310 (2.5964)	grad_norm 3.8772 (2.6110/1.2184)	mem 34604MB
[2025-01-19 20:41:41 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][140/312]	eta 0:02:10 lr 0.000086	time 0.7503 (0.7568)	model_time 0.7497 (0.7441)	loss 2.5949 (2.6119)	grad_norm 3.2762 (2.5916/1.1855)	mem 34604MB
[2025-01-19 20:41:48 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][150/312]	eta 0:02:02 lr 0.000086	time 0.7207 (0.7554)	model_time 0.7206 (0.7435)	loss 2.6480 (2.6096)	grad_norm 3.9851 (2.5989/1.1724)	mem 34604MB
[2025-01-19 20:41:56 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][160/312]	eta 0:01:54 lr 0.000085	time 0.7677 (0.7563)	model_time 0.7672 (0.7452)	loss 2.5858 (2.6101)	grad_norm 2.2646 (2.5892/1.1575)	mem 34604MB
[2025-01-19 20:42:04 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][170/312]	eta 0:01:47 lr 0.000085	time 0.7184 (0.7572)	model_time 0.7179 (0.7467)	loss 2.7326 (2.6005)	grad_norm 2.2261 (2.6002/1.1624)	mem 34604MB
[2025-01-19 20:42:12 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][180/312]	eta 0:01:40 lr 0.000085	time 0.8002 (0.7579)	model_time 0.8000 (0.7479)	loss 2.3318 (2.5892)	grad_norm 3.8992 (2.5948/1.1558)	mem 34604MB
[2025-01-19 20:42:19 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][190/312]	eta 0:01:32 lr 0.000085	time 0.7182 (0.7590)	model_time 0.7181 (0.7496)	loss 2.2501 (2.5905)	grad_norm 3.2808 (2.5958/1.1424)	mem 34604MB
[2025-01-19 20:42:27 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][200/312]	eta 0:01:24 lr 0.000085	time 0.7254 (0.7578)	model_time 0.7253 (0.7488)	loss 2.5418 (2.5872)	grad_norm 1.8667 (2.6281/1.1754)	mem 34604MB
[2025-01-19 20:42:34 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][210/312]	eta 0:01:17 lr 0.000085	time 0.7157 (0.7570)	model_time 0.7151 (0.7484)	loss 1.9159 (2.5911)	grad_norm 5.4866 (2.6609/1.1968)	mem 34604MB
[2025-01-19 20:42:41 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][220/312]	eta 0:01:09 lr 0.000085	time 0.7639 (0.7560)	model_time 0.7637 (0.7478)	loss 2.7450 (2.6016)	grad_norm 2.3189 (2.6590/1.1834)	mem 34604MB
[2025-01-19 20:42:49 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][230/312]	eta 0:01:01 lr 0.000084	time 0.7178 (0.7547)	model_time 0.7176 (0.7468)	loss 2.4151 (2.5948)	grad_norm 1.3107 (2.6659/1.1817)	mem 34604MB
[2025-01-19 20:42:56 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][240/312]	eta 0:00:54 lr 0.000084	time 0.7196 (0.7535)	model_time 0.7191 (0.7459)	loss 2.7395 (2.5875)	grad_norm 1.5043 (2.6404/1.1708)	mem 34604MB
[2025-01-19 20:43:03 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][250/312]	eta 0:00:46 lr 0.000084	time 0.7391 (0.7525)	model_time 0.7386 (0.7452)	loss 2.4875 (2.5858)	grad_norm 3.2384 (2.6069/1.1662)	mem 34604MB
[2025-01-19 20:43:11 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][260/312]	eta 0:00:39 lr 0.000084	time 0.7144 (0.7520)	model_time 0.7143 (0.7449)	loss 2.3005 (2.5835)	grad_norm 2.1236 (2.5965/1.1584)	mem 34604MB
[2025-01-19 20:43:18 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][270/312]	eta 0:00:31 lr 0.000084	time 0.7204 (0.7510)	model_time 0.7199 (0.7442)	loss 2.8894 (2.5832)	grad_norm 1.3250 (2.5784/1.1606)	mem 34604MB
[2025-01-19 20:43:26 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][280/312]	eta 0:00:24 lr 0.000084	time 0.7436 (0.7518)	model_time 0.7434 (0.7452)	loss 2.6262 (2.5824)	grad_norm 3.1920 (2.5831/1.1510)	mem 34604MB
[2025-01-19 20:43:33 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][290/312]	eta 0:00:16 lr 0.000084	time 0.7181 (0.7522)	model_time 0.7176 (0.7459)	loss 1.9581 (2.5828)	grad_norm 5.8105 (2.6095/1.1731)	mem 34604MB
[2025-01-19 20:43:41 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][300/312]	eta 0:00:09 lr 0.000083	time 0.7227 (0.7525)	model_time 0.7226 (0.7463)	loss 2.7431 (2.5834)	grad_norm 1.6300 (2.5997/1.1650)	mem 34604MB
[2025-01-19 20:43:49 internimage_b_1k_224] (main.py 510): INFO Train: [279/300][310/312]	eta 0:00:01 lr 0.000083	time 0.8244 (0.7532)	model_time 0.8243 (0.7472)	loss 3.0752 (2.5889)	grad_norm 2.6293 (2.6127/1.1619)	mem 34604MB
[2025-01-19 20:43:49 internimage_b_1k_224] (main.py 519): INFO EPOCH 279 training takes 0:03:55
[2025-01-19 20:43:49 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_279.pth saving......
[2025-01-19 20:43:53 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_279.pth saved !!!
[2025-01-19 20:44:00 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.124 (7.124)	Loss 0.6834 (0.6834)	Acc@1 86.646 (86.646)	Acc@5 98.022 (98.022)	Mem 34604MB
[2025-01-19 20:44:03 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.927)	Loss 0.8969 (0.7697)	Acc@1 81.348 (84.737)	Acc@5 96.045 (97.070)	Mem 34604MB
[2025-01-19 20:44:03 internimage_b_1k_224] (main.py 575): INFO [Epoch:279] * Acc@1 84.573 Acc@5 97.073
[2025-01-19 20:44:03 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.6%
[2025-01-19 20:44:03 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.62%
[2025-01-19 20:44:12 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.149 (9.149)	Loss 0.7069 (0.7069)	Acc@1 86.694 (86.694)	Acc@5 98.218 (98.218)	Mem 34604MB
[2025-01-19 20:44:17 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.235)	Loss 0.9021 (0.7902)	Acc@1 81.177 (84.792)	Acc@5 96.143 (97.130)	Mem 34604MB
[2025-01-19 20:44:17 internimage_b_1k_224] (main.py 575): INFO [Epoch:279] * Acc@1 84.611 Acc@5 97.153
[2025-01-19 20:44:17 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.6%
[2025-01-19 20:44:17 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 20:44:21 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 20:44:21 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.61%
[2025-01-19 20:44:23 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][0/312]	eta 0:10:43 lr 0.000083	time 2.0617 (2.0617)	model_time 0.7358 (0.7358)	loss 2.9065 (2.9065)	grad_norm 1.6186 (1.6186/0.0000)	mem 34604MB
[2025-01-19 20:44:30 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][10/312]	eta 0:04:18 lr 0.000083	time 0.8231 (0.8567)	model_time 0.8230 (0.7359)	loss 1.6243 (2.5253)	grad_norm 1.7454 (3.1925/1.1706)	mem 34604MB
[2025-01-19 20:44:38 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][20/312]	eta 0:03:53 lr 0.000083	time 0.7219 (0.7985)	model_time 0.7217 (0.7350)	loss 2.8051 (2.5478)	grad_norm 3.5145 (3.5174/1.2982)	mem 34604MB
[2025-01-19 20:44:45 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][30/312]	eta 0:03:39 lr 0.000083	time 0.7170 (0.7784)	model_time 0.7164 (0.7353)	loss 2.8886 (2.5357)	grad_norm 3.2583 (3.4752/1.2586)	mem 34604MB
[2025-01-19 20:44:52 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][40/312]	eta 0:03:28 lr 0.000083	time 0.7210 (0.7667)	model_time 0.7208 (0.7341)	loss 3.0387 (2.5263)	grad_norm 4.0776 (3.3616/1.2711)	mem 34604MB
[2025-01-19 20:45:00 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][50/312]	eta 0:03:18 lr 0.000083	time 0.7308 (0.7595)	model_time 0.7304 (0.7331)	loss 2.4789 (2.5413)	grad_norm 2.7169 (3.2359/1.2822)	mem 34604MB
[2025-01-19 20:45:07 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][60/312]	eta 0:03:10 lr 0.000082	time 0.7298 (0.7551)	model_time 0.7294 (0.7330)	loss 2.8519 (2.5873)	grad_norm 1.7808 (3.1469/1.2483)	mem 34604MB
[2025-01-19 20:45:14 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][70/312]	eta 0:03:02 lr 0.000082	time 0.7347 (0.7531)	model_time 0.7345 (0.7341)	loss 1.6821 (2.5740)	grad_norm 1.2378 (3.0642/1.2220)	mem 34604MB
[2025-01-19 20:45:22 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][80/312]	eta 0:02:54 lr 0.000082	time 0.7189 (0.7500)	model_time 0.7184 (0.7333)	loss 2.6256 (2.5980)	grad_norm 1.5427 (2.9387/1.2126)	mem 34604MB
[2025-01-19 20:45:29 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][90/312]	eta 0:02:46 lr 0.000082	time 0.7223 (0.7504)	model_time 0.7218 (0.7355)	loss 2.6245 (2.5956)	grad_norm 3.8774 (2.8680/1.2283)	mem 34604MB
[2025-01-19 20:45:37 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][100/312]	eta 0:02:39 lr 0.000082	time 0.8090 (0.7534)	model_time 0.8089 (0.7399)	loss 2.9131 (2.5970)	grad_norm 3.1175 (2.8221/1.2343)	mem 34604MB
[2025-01-19 20:45:45 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][110/312]	eta 0:02:32 lr 0.000082	time 0.7187 (0.7552)	model_time 0.7185 (0.7428)	loss 2.7653 (2.5906)	grad_norm 1.5985 (2.7499/1.2114)	mem 34604MB
[2025-01-19 20:45:53 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][120/312]	eta 0:02:25 lr 0.000082	time 0.9925 (0.7580)	model_time 0.9924 (0.7467)	loss 2.4544 (2.5932)	grad_norm 1.8678 (2.7062/1.1916)	mem 34604MB
[2025-01-19 20:46:00 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][130/312]	eta 0:02:17 lr 0.000081	time 0.7468 (0.7569)	model_time 0.7466 (0.7464)	loss 2.7365 (2.6065)	grad_norm 1.5670 (2.6614/1.1690)	mem 34604MB
[2025-01-19 20:46:07 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][140/312]	eta 0:02:10 lr 0.000081	time 0.7170 (0.7560)	model_time 0.7168 (0.7462)	loss 2.8071 (2.6018)	grad_norm 1.0889 (2.6153/1.1571)	mem 34604MB
[2025-01-19 20:46:15 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][150/312]	eta 0:02:02 lr 0.000081	time 0.7276 (0.7542)	model_time 0.7274 (0.7450)	loss 2.0525 (2.5840)	grad_norm 1.8136 (2.6002/1.1346)	mem 34604MB
[2025-01-19 20:46:22 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][160/312]	eta 0:01:54 lr 0.000081	time 0.7496 (0.7530)	model_time 0.7491 (0.7444)	loss 3.1014 (2.5930)	grad_norm 1.9841 (2.5852/1.1438)	mem 34604MB
[2025-01-19 20:46:29 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][170/312]	eta 0:01:46 lr 0.000081	time 0.7208 (0.7514)	model_time 0.7205 (0.7433)	loss 3.2607 (2.5973)	grad_norm 2.1326 (2.5718/1.1221)	mem 34604MB
[2025-01-19 20:46:37 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][180/312]	eta 0:01:38 lr 0.000081	time 0.7252 (0.7499)	model_time 0.7248 (0.7422)	loss 3.1377 (2.5864)	grad_norm 2.5061 (2.5850/1.1143)	mem 34604MB
[2025-01-19 20:46:44 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][190/312]	eta 0:01:31 lr 0.000081	time 0.7165 (0.7491)	model_time 0.7162 (0.7418)	loss 1.9441 (2.5812)	grad_norm 2.2025 (2.5846/1.1048)	mem 34604MB
[2025-01-19 20:46:51 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][200/312]	eta 0:01:23 lr 0.000081	time 0.7158 (0.7482)	model_time 0.7153 (0.7412)	loss 1.8878 (2.5664)	grad_norm 1.3540 (2.5774/1.1144)	mem 34604MB
[2025-01-19 20:46:59 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][210/312]	eta 0:01:16 lr 0.000080	time 0.7225 (0.7486)	model_time 0.7223 (0.7420)	loss 2.8783 (2.5679)	grad_norm 2.1763 (2.5510/1.1001)	mem 34604MB
[2025-01-19 20:47:06 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][220/312]	eta 0:01:08 lr 0.000080	time 0.8305 (0.7495)	model_time 0.8300 (0.7431)	loss 2.6416 (2.5642)	grad_norm 1.6413 (2.5156/1.0899)	mem 34604MB
[2025-01-19 20:47:14 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][230/312]	eta 0:01:01 lr 0.000080	time 0.7157 (0.7506)	model_time 0.7155 (0.7445)	loss 1.7567 (2.5617)	grad_norm 3.7723 (2.5041/1.0777)	mem 34604MB
[2025-01-19 20:47:22 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][240/312]	eta 0:00:54 lr 0.000080	time 0.8861 (0.7517)	model_time 0.8860 (0.7458)	loss 2.3583 (2.5680)	grad_norm 1.5253 (2.4976/1.0689)	mem 34604MB
[2025-01-19 20:47:29 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][250/312]	eta 0:00:46 lr 0.000080	time 0.7313 (0.7516)	model_time 0.7308 (0.7460)	loss 1.6799 (2.5602)	grad_norm 3.1520 (2.4960/1.0722)	mem 34604MB
[2025-01-19 20:47:37 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][260/312]	eta 0:00:39 lr 0.000080	time 0.7171 (0.7510)	model_time 0.7169 (0.7456)	loss 2.0698 (2.5640)	grad_norm 1.4043 (2.4782/1.0634)	mem 34604MB
[2025-01-19 20:47:44 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][270/312]	eta 0:00:31 lr 0.000080	time 0.7591 (0.7507)	model_time 0.7589 (0.7454)	loss 2.9043 (2.5657)	grad_norm 1.7723 (2.4711/1.0591)	mem 34604MB
[2025-01-19 20:47:52 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][280/312]	eta 0:00:24 lr 0.000079	time 0.7167 (0.7503)	model_time 0.7165 (0.7452)	loss 2.8925 (2.5633)	grad_norm 2.5345 (2.4591/1.0457)	mem 34604MB
[2025-01-19 20:47:59 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][290/312]	eta 0:00:16 lr 0.000079	time 0.7168 (0.7497)	model_time 0.7166 (0.7447)	loss 3.1516 (2.5704)	grad_norm 2.0465 (2.4361/1.0388)	mem 34604MB
[2025-01-19 20:48:06 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][300/312]	eta 0:00:08 lr 0.000079	time 0.7637 (0.7489)	model_time 0.7636 (0.7441)	loss 2.7057 (2.5708)	grad_norm 4.7362 (2.4369/1.0403)	mem 34604MB
[2025-01-19 20:48:13 internimage_b_1k_224] (main.py 510): INFO Train: [280/300][310/312]	eta 0:00:01 lr 0.000079	time 0.7201 (0.7482)	model_time 0.7200 (0.7435)	loss 2.8791 (2.5712)	grad_norm 1.7733 (2.3986/1.0171)	mem 34604MB
[2025-01-19 20:48:14 internimage_b_1k_224] (main.py 519): INFO EPOCH 280 training takes 0:03:53
[2025-01-19 20:48:14 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_280.pth saving......
[2025-01-19 20:48:17 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_280.pth saved !!!
[2025-01-19 20:48:25 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.293 (7.293)	Loss 0.6832 (0.6832)	Acc@1 86.646 (86.646)	Acc@5 98.145 (98.145)	Mem 34604MB
[2025-01-19 20:48:28 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.943)	Loss 0.8912 (0.7697)	Acc@1 81.372 (84.794)	Acc@5 96.094 (97.081)	Mem 34604MB
[2025-01-19 20:48:28 internimage_b_1k_224] (main.py 575): INFO [Epoch:280] * Acc@1 84.605 Acc@5 97.077
[2025-01-19 20:48:28 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.6%
[2025-01-19 20:48:28 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.62%
[2025-01-19 20:48:37 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.236 (9.236)	Loss 0.7066 (0.7066)	Acc@1 86.719 (86.719)	Acc@5 98.218 (98.218)	Mem 34604MB
[2025-01-19 20:48:42 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.244)	Loss 0.9016 (0.7897)	Acc@1 81.201 (84.812)	Acc@5 96.143 (97.130)	Mem 34604MB
[2025-01-19 20:48:42 internimage_b_1k_224] (main.py 575): INFO [Epoch:280] * Acc@1 84.631 Acc@5 97.153
[2025-01-19 20:48:42 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.6%
[2025-01-19 20:48:42 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 20:48:46 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 20:48:46 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.63%
[2025-01-19 20:48:48 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][0/312]	eta 0:10:59 lr 0.000079	time 2.1134 (2.1134)	model_time 0.7580 (0.7580)	loss 2.6407 (2.6407)	grad_norm 2.9652 (2.9652/0.0000)	mem 34604MB
[2025-01-19 20:48:55 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][10/312]	eta 0:04:20 lr 0.000079	time 0.7426 (0.8617)	model_time 0.7425 (0.7382)	loss 2.0436 (2.5894)	grad_norm 1.3843 (2.9450/1.1414)	mem 34604MB
[2025-01-19 20:49:03 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][20/312]	eta 0:03:58 lr 0.000079	time 0.7682 (0.8153)	model_time 0.7678 (0.7504)	loss 3.0068 (2.6736)	grad_norm 1.3052 (2.5689/1.0384)	mem 34604MB
[2025-01-19 20:49:11 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][30/312]	eta 0:03:46 lr 0.000079	time 0.8117 (0.8017)	model_time 0.8114 (0.7577)	loss 3.0718 (2.7012)	grad_norm 1.3521 (2.5623/1.0397)	mem 34604MB
[2025-01-19 20:49:18 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][40/312]	eta 0:03:35 lr 0.000079	time 0.7282 (0.7935)	model_time 0.7280 (0.7601)	loss 2.9897 (2.7073)	grad_norm 1.4218 (2.5307/1.0530)	mem 34604MB
[2025-01-19 20:49:26 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][50/312]	eta 0:03:26 lr 0.000078	time 0.7225 (0.7876)	model_time 0.7219 (0.7606)	loss 2.7964 (2.6845)	grad_norm 2.5668 (2.6668/1.0290)	mem 34604MB
[2025-01-19 20:49:33 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][60/312]	eta 0:03:16 lr 0.000078	time 0.7219 (0.7812)	model_time 0.7216 (0.7586)	loss 3.1011 (2.6975)	grad_norm 2.9247 (2.6073/1.0023)	mem 34604MB
[2025-01-19 20:49:41 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][70/312]	eta 0:03:07 lr 0.000078	time 0.7224 (0.7757)	model_time 0.7219 (0.7562)	loss 2.9333 (2.6793)	grad_norm 1.6467 (2.5836/0.9861)	mem 34604MB
[2025-01-19 20:49:48 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][80/312]	eta 0:02:58 lr 0.000078	time 0.7167 (0.7709)	model_time 0.7165 (0.7538)	loss 1.9257 (2.6457)	grad_norm 2.5816 (2.5219/0.9491)	mem 34604MB
[2025-01-19 20:49:56 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][90/312]	eta 0:02:50 lr 0.000078	time 0.7412 (0.7660)	model_time 0.7407 (0.7507)	loss 3.0684 (2.6503)	grad_norm 2.9430 (2.6018/1.0016)	mem 34604MB
[2025-01-19 20:50:03 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][100/312]	eta 0:02:41 lr 0.000078	time 0.7339 (0.7622)	model_time 0.7337 (0.7484)	loss 2.4532 (2.6280)	grad_norm 3.7845 (2.6326/1.0167)	mem 34604MB
[2025-01-19 20:50:10 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][110/312]	eta 0:02:33 lr 0.000078	time 0.7248 (0.7589)	model_time 0.7243 (0.7463)	loss 2.5473 (2.6131)	grad_norm 2.1511 (2.5851/1.0200)	mem 34604MB
[2025-01-19 20:50:17 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][120/312]	eta 0:02:25 lr 0.000078	time 0.7145 (0.7571)	model_time 0.7143 (0.7456)	loss 3.0894 (2.6346)	grad_norm 1.4606 (2.5524/1.0300)	mem 34604MB
[2025-01-19 20:50:25 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][130/312]	eta 0:02:17 lr 0.000077	time 0.7204 (0.7549)	model_time 0.7202 (0.7442)	loss 2.8437 (2.6321)	grad_norm 2.5581 (2.5201/1.0218)	mem 34604MB
[2025-01-19 20:50:32 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][140/312]	eta 0:02:09 lr 0.000077	time 0.8082 (0.7551)	model_time 0.8080 (0.7451)	loss 2.6386 (2.6329)	grad_norm 2.2310 (2.5004/0.9954)	mem 34604MB
[2025-01-19 20:50:40 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][150/312]	eta 0:02:02 lr 0.000077	time 0.8073 (0.7561)	model_time 0.8071 (0.7467)	loss 2.2047 (2.6338)	grad_norm 4.3555 (2.4737/1.0025)	mem 34604MB
[2025-01-19 20:50:48 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][160/312]	eta 0:01:54 lr 0.000077	time 0.7187 (0.7565)	model_time 0.7185 (0.7477)	loss 2.4771 (2.6376)	grad_norm 3.5157 (2.4887/1.0062)	mem 34604MB
[2025-01-19 20:50:55 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][170/312]	eta 0:01:47 lr 0.000077	time 0.7235 (0.7568)	model_time 0.7230 (0.7486)	loss 1.4990 (2.6295)	grad_norm 2.8215 (2.4451/1.0023)	mem 34604MB
[2025-01-19 20:51:03 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][180/312]	eta 0:01:39 lr 0.000077	time 0.7229 (0.7563)	model_time 0.7228 (0.7484)	loss 3.0473 (2.6403)	grad_norm 1.8414 (2.4438/0.9909)	mem 34604MB
[2025-01-19 20:51:10 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][190/312]	eta 0:01:32 lr 0.000077	time 0.7204 (0.7555)	model_time 0.7202 (0.7480)	loss 2.2956 (2.6488)	grad_norm 3.2453 (2.4254/0.9808)	mem 34604MB
[2025-01-19 20:51:17 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][200/312]	eta 0:01:24 lr 0.000076	time 0.7191 (0.7544)	model_time 0.7186 (0.7473)	loss 2.8496 (2.6583)	grad_norm 1.5478 (2.4379/0.9883)	mem 34604MB
[2025-01-19 20:51:25 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][210/312]	eta 0:01:16 lr 0.000076	time 0.7180 (0.7532)	model_time 0.7178 (0.7464)	loss 2.8507 (2.6525)	grad_norm 2.1837 (2.4213/0.9729)	mem 34604MB
[2025-01-19 20:51:32 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][220/312]	eta 0:01:09 lr 0.000076	time 0.7306 (0.7520)	model_time 0.7304 (0.7455)	loss 3.0210 (2.6488)	grad_norm 2.9209 (2.4252/0.9765)	mem 34604MB
[2025-01-19 20:51:39 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][230/312]	eta 0:01:01 lr 0.000076	time 0.7166 (0.7509)	model_time 0.7164 (0.7446)	loss 2.4573 (2.6502)	grad_norm 2.0060 (2.4189/0.9628)	mem 34604MB
[2025-01-19 20:51:47 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][240/312]	eta 0:00:54 lr 0.000076	time 0.7190 (0.7505)	model_time 0.7185 (0.7445)	loss 2.9651 (2.6539)	grad_norm 2.0465 (2.3937/0.9558)	mem 34604MB
[2025-01-19 20:51:54 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][250/312]	eta 0:00:46 lr 0.000076	time 0.7196 (0.7498)	model_time 0.7192 (0.7440)	loss 2.8778 (2.6396)	grad_norm 2.5077 (2.4030/0.9583)	mem 34604MB
[2025-01-19 20:52:01 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][260/312]	eta 0:00:38 lr 0.000076	time 0.8070 (0.7497)	model_time 0.8063 (0.7442)	loss 1.8284 (2.6413)	grad_norm 1.6836 (2.3880/0.9539)	mem 34604MB
[2025-01-19 20:52:09 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][270/312]	eta 0:00:31 lr 0.000076	time 0.8165 (0.7502)	model_time 0.8163 (0.7448)	loss 2.7925 (2.6392)	grad_norm 2.6575 (2.3813/0.9582)	mem 34604MB
[2025-01-19 20:52:17 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][280/312]	eta 0:00:24 lr 0.000075	time 0.7186 (0.7512)	model_time 0.7182 (0.7460)	loss 2.7478 (2.6384)	grad_norm 2.7135 (2.3929/0.9563)	mem 34604MB
[2025-01-19 20:52:25 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][290/312]	eta 0:00:16 lr 0.000075	time 0.7292 (0.7519)	model_time 0.7287 (0.7469)	loss 2.5930 (2.6416)	grad_norm 4.1104 (2.4069/0.9597)	mem 34604MB
[2025-01-19 20:52:32 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][300/312]	eta 0:00:09 lr 0.000075	time 0.7136 (0.7515)	model_time 0.7135 (0.7466)	loss 2.8315 (2.6360)	grad_norm 4.9004 (2.4337/0.9925)	mem 34604MB
[2025-01-19 20:52:39 internimage_b_1k_224] (main.py 510): INFO Train: [281/300][310/312]	eta 0:00:01 lr 0.000075	time 0.7128 (0.7508)	model_time 0.7127 (0.7460)	loss 3.0970 (2.6322)	grad_norm 1.8544 (2.4169/0.9716)	mem 34604MB
[2025-01-19 20:52:40 internimage_b_1k_224] (main.py 519): INFO EPOCH 281 training takes 0:03:54
[2025-01-19 20:52:40 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_281.pth saving......
[2025-01-19 20:52:43 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_281.pth saved !!!
[2025-01-19 20:52:51 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.806 (7.806)	Loss 0.6922 (0.6922)	Acc@1 86.646 (86.646)	Acc@5 98.096 (98.096)	Mem 34604MB
[2025-01-19 20:52:55 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.009)	Loss 0.8904 (0.7697)	Acc@1 81.201 (84.737)	Acc@5 96.143 (97.055)	Mem 34604MB
[2025-01-19 20:52:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:281] * Acc@1 84.563 Acc@5 97.069
[2025-01-19 20:52:55 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.6%
[2025-01-19 20:52:55 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.62%
[2025-01-19 20:53:05 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.836 (9.836)	Loss 0.7063 (0.7063)	Acc@1 86.719 (86.719)	Acc@5 98.193 (98.193)	Mem 34604MB
[2025-01-19 20:53:09 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.295)	Loss 0.9012 (0.7892)	Acc@1 81.226 (84.808)	Acc@5 96.167 (97.141)	Mem 34604MB
[2025-01-19 20:53:09 internimage_b_1k_224] (main.py 575): INFO [Epoch:281] * Acc@1 84.625 Acc@5 97.163
[2025-01-19 20:53:09 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.6%
[2025-01-19 20:53:09 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.63%
[2025-01-19 20:53:13 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][0/312]	eta 0:18:34 lr 0.000075	time 3.5717 (3.5717)	model_time 1.8806 (1.8806)	loss 3.1932 (3.1932)	grad_norm 1.2757 (1.2757/0.0000)	mem 34604MB
[2025-01-19 20:53:20 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][10/312]	eta 0:05:00 lr 0.000075	time 0.8065 (0.9946)	model_time 0.8064 (0.8406)	loss 2.8422 (2.5646)	grad_norm 2.9887 (2.2227/0.6248)	mem 34604MB
[2025-01-19 20:53:28 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][20/312]	eta 0:04:13 lr 0.000075	time 0.7232 (0.8691)	model_time 0.7230 (0.7882)	loss 2.0770 (2.6555)	grad_norm 2.3890 (2.3338/0.6723)	mem 34604MB
[2025-01-19 20:53:35 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][30/312]	eta 0:03:52 lr 0.000075	time 0.7334 (0.8254)	model_time 0.7332 (0.7705)	loss 2.9756 (2.6155)	grad_norm 6.0202 (2.3700/0.9190)	mem 34604MB
[2025-01-19 20:53:42 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][40/312]	eta 0:03:38 lr 0.000075	time 0.7196 (0.8024)	model_time 0.7194 (0.7608)	loss 2.5310 (2.6196)	grad_norm 2.7327 (2.4894/0.9396)	mem 34604MB
[2025-01-19 20:53:50 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][50/312]	eta 0:03:26 lr 0.000074	time 0.7253 (0.7894)	model_time 0.7251 (0.7558)	loss 2.8386 (2.6168)	grad_norm 2.3537 (2.4983/0.9053)	mem 34604MB
[2025-01-19 20:53:57 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][60/312]	eta 0:03:16 lr 0.000074	time 0.7290 (0.7802)	model_time 0.7288 (0.7521)	loss 2.8828 (2.6373)	grad_norm 1.5179 (2.4673/0.8673)	mem 34604MB
[2025-01-19 20:54:04 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][70/312]	eta 0:03:07 lr 0.000074	time 0.7209 (0.7762)	model_time 0.7207 (0.7520)	loss 2.5737 (2.6349)	grad_norm 3.6115 (2.4940/0.8770)	mem 34604MB
[2025-01-19 20:54:12 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][80/312]	eta 0:02:59 lr 0.000074	time 0.7158 (0.7746)	model_time 0.7155 (0.7534)	loss 2.4060 (2.6371)	grad_norm 3.2091 (2.4590/0.8665)	mem 34604MB
[2025-01-19 20:54:20 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][90/312]	eta 0:02:52 lr 0.000074	time 0.7171 (0.7756)	model_time 0.7166 (0.7566)	loss 2.8222 (2.6494)	grad_norm 3.7014 (2.4438/0.8550)	mem 34604MB
[2025-01-19 20:54:27 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][100/312]	eta 0:02:44 lr 0.000074	time 0.7227 (0.7739)	model_time 0.7225 (0.7568)	loss 2.9510 (2.6393)	grad_norm 2.0697 (2.4887/0.8694)	mem 34604MB
[2025-01-19 20:54:35 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][110/312]	eta 0:02:35 lr 0.000074	time 0.7202 (0.7708)	model_time 0.7200 (0.7552)	loss 2.6894 (2.6365)	grad_norm 4.2030 (2.5357/0.9066)	mem 34604MB
[2025-01-19 20:54:42 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][120/312]	eta 0:02:27 lr 0.000074	time 0.7243 (0.7687)	model_time 0.7241 (0.7544)	loss 2.6804 (2.6228)	grad_norm 3.3748 (2.5901/0.9169)	mem 34604MB
[2025-01-19 20:54:50 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][130/312]	eta 0:02:19 lr 0.000073	time 0.7989 (0.7667)	model_time 0.7987 (0.7534)	loss 2.1827 (2.6080)	grad_norm 1.6804 (2.5762/0.9151)	mem 34604MB
[2025-01-19 20:54:57 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][140/312]	eta 0:02:11 lr 0.000073	time 0.7148 (0.7642)	model_time 0.7146 (0.7518)	loss 2.6793 (2.6107)	grad_norm 3.7529 (2.5657/0.8993)	mem 34604MB
[2025-01-19 20:55:04 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][150/312]	eta 0:02:03 lr 0.000073	time 0.7227 (0.7614)	model_time 0.7226 (0.7499)	loss 2.0777 (2.6021)	grad_norm 1.4752 (2.5580/0.8926)	mem 34604MB
[2025-01-19 20:55:12 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][160/312]	eta 0:01:55 lr 0.000073	time 0.7208 (0.7590)	model_time 0.7206 (0.7481)	loss 1.6354 (2.6017)	grad_norm 1.6809 (2.5496/0.8897)	mem 34604MB
[2025-01-19 20:55:19 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][170/312]	eta 0:01:47 lr 0.000073	time 0.7155 (0.7575)	model_time 0.7150 (0.7472)	loss 3.0293 (2.6021)	grad_norm 2.2671 (2.5166/0.8824)	mem 34604MB
[2025-01-19 20:55:26 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][180/312]	eta 0:01:39 lr 0.000073	time 0.7152 (0.7558)	model_time 0.7150 (0.7461)	loss 2.8590 (2.6070)	grad_norm 3.2606 (2.5298/0.8881)	mem 34604MB
[2025-01-19 20:55:34 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][190/312]	eta 0:01:32 lr 0.000073	time 0.7169 (0.7558)	model_time 0.7166 (0.7466)	loss 2.2689 (2.6102)	grad_norm 3.5006 (2.5473/0.9037)	mem 34604MB
[2025-01-19 20:55:41 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][200/312]	eta 0:01:24 lr 0.000073	time 0.7194 (0.7565)	model_time 0.7192 (0.7477)	loss 2.6534 (2.6064)	grad_norm 2.6402 (2.5653/0.9458)	mem 34604MB
[2025-01-19 20:55:49 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][210/312]	eta 0:01:17 lr 0.000073	time 0.7149 (0.7571)	model_time 0.7145 (0.7487)	loss 2.2692 (2.5993)	grad_norm 1.4701 (2.5657/0.9582)	mem 34604MB
[2025-01-19 20:55:57 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][220/312]	eta 0:01:09 lr 0.000072	time 0.7179 (0.7573)	model_time 0.7175 (0.7493)	loss 2.7621 (2.5977)	grad_norm 4.2305 (2.5715/0.9572)	mem 34604MB
[2025-01-19 20:56:04 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][230/312]	eta 0:01:02 lr 0.000072	time 0.7361 (0.7566)	model_time 0.7360 (0.7489)	loss 2.8286 (2.6023)	grad_norm 7.0393 (2.6073/1.0178)	mem 34604MB
[2025-01-19 20:56:12 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][240/312]	eta 0:00:54 lr 0.000072	time 0.7354 (0.7560)	model_time 0.7350 (0.7486)	loss 2.9862 (2.6023)	grad_norm 3.0920 (2.6228/1.0340)	mem 34604MB
[2025-01-19 20:56:19 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][250/312]	eta 0:00:46 lr 0.000072	time 0.8038 (0.7552)	model_time 0.8033 (0.7481)	loss 2.2012 (2.6002)	grad_norm 3.7869 (2.6488/1.0601)	mem 34604MB
[2025-01-19 20:56:26 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][260/312]	eta 0:00:39 lr 0.000072	time 0.7193 (0.7543)	model_time 0.7189 (0.7474)	loss 2.9061 (2.5948)	grad_norm 4.1442 (2.6777/1.0634)	mem 34604MB
[2025-01-19 20:56:34 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][270/312]	eta 0:00:31 lr 0.000072	time 0.7208 (0.7535)	model_time 0.7203 (0.7468)	loss 1.8571 (2.5873)	grad_norm 4.2503 (2.6868/1.0612)	mem 34604MB
[2025-01-19 20:56:41 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][280/312]	eta 0:00:24 lr 0.000072	time 0.7295 (0.7528)	model_time 0.7291 (0.7464)	loss 2.6708 (2.5953)	grad_norm 2.1151 (2.7026/1.0878)	mem 34604MB
[2025-01-19 20:56:48 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][290/312]	eta 0:00:16 lr 0.000072	time 0.7239 (0.7523)	model_time 0.7234 (0.7460)	loss 2.6110 (2.5951)	grad_norm 2.4659 (2.7083/1.1066)	mem 34604MB
[2025-01-19 20:56:55 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][300/312]	eta 0:00:09 lr 0.000071	time 0.7259 (0.7514)	model_time 0.7258 (0.7453)	loss 2.7930 (2.5996)	grad_norm 1.7153 (2.7053/1.1044)	mem 34604MB
[2025-01-19 20:57:03 internimage_b_1k_224] (main.py 510): INFO Train: [282/300][310/312]	eta 0:00:01 lr 0.000071	time 0.7165 (0.7507)	model_time 0.7164 (0.7449)	loss 2.3578 (2.5984)	grad_norm 1.0386 (2.6988/1.1098)	mem 34604MB
[2025-01-19 20:57:04 internimage_b_1k_224] (main.py 519): INFO EPOCH 282 training takes 0:03:54
[2025-01-19 20:57:04 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_282.pth saving......
[2025-01-19 20:57:07 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_282.pth saved !!!
[2025-01-19 20:57:14 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.367 (7.367)	Loss 0.6863 (0.6863)	Acc@1 86.548 (86.548)	Acc@5 97.949 (97.949)	Mem 34604MB
[2025-01-19 20:57:17 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.958)	Loss 0.8899 (0.7712)	Acc@1 81.689 (84.746)	Acc@5 96.045 (97.073)	Mem 34604MB
[2025-01-19 20:57:18 internimage_b_1k_224] (main.py 575): INFO [Epoch:282] * Acc@1 84.591 Acc@5 97.067
[2025-01-19 20:57:18 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.6%
[2025-01-19 20:57:18 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.62%
[2025-01-19 20:57:27 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.172 (9.172)	Loss 0.7058 (0.7058)	Acc@1 86.768 (86.768)	Acc@5 98.193 (98.193)	Mem 34604MB
[2025-01-19 20:57:31 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.242)	Loss 0.9007 (0.7887)	Acc@1 81.226 (84.803)	Acc@5 96.167 (97.141)	Mem 34604MB
[2025-01-19 20:57:32 internimage_b_1k_224] (main.py 575): INFO [Epoch:282] * Acc@1 84.627 Acc@5 97.163
[2025-01-19 20:57:32 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.6%
[2025-01-19 20:57:32 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.63%
[2025-01-19 20:57:35 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][0/312]	eta 0:18:26 lr 0.000071	time 3.5456 (3.5456)	model_time 2.0860 (2.0860)	loss 2.1892 (2.1892)	grad_norm 2.8666 (2.8666/0.0000)	mem 34604MB
[2025-01-19 20:57:43 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][10/312]	eta 0:05:13 lr 0.000071	time 0.8185 (1.0378)	model_time 0.8180 (0.9048)	loss 2.8133 (2.7287)	grad_norm 2.6131 (3.5321/1.6416)	mem 34604MB
[2025-01-19 20:57:51 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][20/312]	eta 0:04:25 lr 0.000071	time 0.7414 (0.9087)	model_time 0.7411 (0.8389)	loss 2.1471 (2.7137)	grad_norm 2.4484 (3.1751/1.4686)	mem 34604MB
[2025-01-19 20:57:59 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][30/312]	eta 0:04:04 lr 0.000071	time 0.8327 (0.8684)	model_time 0.8323 (0.8210)	loss 2.7149 (2.6647)	grad_norm 2.7348 (3.0173/1.4011)	mem 34604MB
[2025-01-19 20:58:06 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][40/312]	eta 0:03:47 lr 0.000071	time 0.7172 (0.8379)	model_time 0.7171 (0.8019)	loss 2.6853 (2.6870)	grad_norm 1.6020 (2.8342/1.3783)	mem 34604MB
[2025-01-19 20:58:13 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][50/312]	eta 0:03:34 lr 0.000071	time 0.7263 (0.8193)	model_time 0.7261 (0.7903)	loss 3.1570 (2.6396)	grad_norm 2.4874 (2.7359/1.2964)	mem 34604MB
[2025-01-19 20:58:21 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][60/312]	eta 0:03:22 lr 0.000071	time 0.7452 (0.8041)	model_time 0.7447 (0.7798)	loss 2.9416 (2.6312)	grad_norm 4.1504 (2.6970/1.2297)	mem 34604MB
[2025-01-19 20:58:28 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][70/312]	eta 0:03:12 lr 0.000070	time 0.7189 (0.7937)	model_time 0.7188 (0.7728)	loss 2.1890 (2.6251)	grad_norm 1.7336 (2.6535/1.1768)	mem 34604MB
[2025-01-19 20:58:35 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][80/312]	eta 0:03:02 lr 0.000070	time 0.7304 (0.7862)	model_time 0.7299 (0.7678)	loss 2.8095 (2.6309)	grad_norm 2.2642 (2.5621/1.1446)	mem 34604MB
[2025-01-19 20:58:43 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][90/312]	eta 0:02:53 lr 0.000070	time 0.7221 (0.7796)	model_time 0.7219 (0.7632)	loss 2.9349 (2.6025)	grad_norm 2.8194 (2.4921/1.1135)	mem 34604MB
[2025-01-19 20:58:50 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][100/312]	eta 0:02:44 lr 0.000070	time 0.7204 (0.7758)	model_time 0.7199 (0.7609)	loss 2.6305 (2.5988)	grad_norm 4.6656 (2.5765/1.1489)	mem 34604MB
[2025-01-19 20:58:57 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][110/312]	eta 0:02:35 lr 0.000070	time 0.7159 (0.7716)	model_time 0.7157 (0.7580)	loss 2.7832 (2.6045)	grad_norm 3.0622 (2.5928/1.1606)	mem 34604MB
[2025-01-19 20:59:05 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][120/312]	eta 0:02:27 lr 0.000070	time 0.7158 (0.7702)	model_time 0.7153 (0.7578)	loss 2.1430 (2.5792)	grad_norm 1.7986 (2.5918/1.1394)	mem 34604MB
[2025-01-19 20:59:13 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][130/312]	eta 0:02:20 lr 0.000070	time 0.8139 (0.7707)	model_time 0.8137 (0.7591)	loss 2.3778 (2.5756)	grad_norm 4.1499 (2.5897/1.1300)	mem 34604MB
[2025-01-19 20:59:20 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][140/312]	eta 0:02:12 lr 0.000070	time 0.8191 (0.7702)	model_time 0.8189 (0.7595)	loss 2.9147 (2.5914)	grad_norm 2.5343 (2.6425/1.2039)	mem 34604MB
[2025-01-19 20:59:28 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][150/312]	eta 0:02:04 lr 0.000070	time 0.8004 (0.7705)	model_time 0.7999 (0.7605)	loss 2.7864 (2.5966)	grad_norm 2.9330 (2.6821/1.2296)	mem 34604MB
[2025-01-19 20:59:35 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][160/312]	eta 0:01:56 lr 0.000069	time 0.7611 (0.7691)	model_time 0.7610 (0.7597)	loss 3.1890 (2.5913)	grad_norm 1.0742 (2.7325/1.2571)	mem 34604MB
[2025-01-19 20:59:43 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][170/312]	eta 0:01:48 lr 0.000069	time 0.7304 (0.7675)	model_time 0.7299 (0.7585)	loss 3.0204 (2.6000)	grad_norm 2.2372 (2.7341/1.2634)	mem 34604MB
[2025-01-19 20:59:50 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][180/312]	eta 0:01:41 lr 0.000069	time 0.7152 (0.7654)	model_time 0.7151 (0.7569)	loss 3.1601 (2.6016)	grad_norm 2.4722 (2.6885/1.2514)	mem 34604MB
[2025-01-19 20:59:57 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][190/312]	eta 0:01:33 lr 0.000069	time 0.7274 (0.7639)	model_time 0.7272 (0.7558)	loss 2.4920 (2.5938)	grad_norm 1.4486 (2.6754/1.2395)	mem 34604MB
[2025-01-19 21:00:05 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][200/312]	eta 0:01:25 lr 0.000069	time 0.7524 (0.7624)	model_time 0.7519 (0.7547)	loss 2.0355 (2.5940)	grad_norm 2.4560 (2.6423/1.2211)	mem 34604MB
[2025-01-19 21:00:12 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][210/312]	eta 0:01:17 lr 0.000069	time 0.7660 (0.7610)	model_time 0.7659 (0.7537)	loss 1.7585 (2.5889)	grad_norm 1.1664 (2.5991/1.2107)	mem 34604MB
[2025-01-19 21:00:20 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][220/312]	eta 0:01:09 lr 0.000069	time 0.7190 (0.7599)	model_time 0.7185 (0.7529)	loss 2.2598 (2.5861)	grad_norm 1.8879 (2.5793/1.1999)	mem 34604MB
[2025-01-19 21:00:27 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][230/312]	eta 0:01:02 lr 0.000069	time 0.7168 (0.7583)	model_time 0.7167 (0.7516)	loss 2.7687 (2.5940)	grad_norm 3.1018 (2.5785/1.1802)	mem 34604MB
[2025-01-19 21:00:34 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][240/312]	eta 0:00:54 lr 0.000069	time 0.7199 (0.7580)	model_time 0.7195 (0.7516)	loss 2.7935 (2.6031)	grad_norm 1.8799 (2.5867/1.1758)	mem 34604MB
[2025-01-19 21:00:42 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][250/312]	eta 0:00:47 lr 0.000068	time 0.8236 (0.7591)	model_time 0.8231 (0.7529)	loss 2.6789 (2.6097)	grad_norm 1.6636 (2.5706/1.1663)	mem 34604MB
[2025-01-19 21:00:50 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][260/312]	eta 0:00:39 lr 0.000068	time 0.7425 (0.7599)	model_time 0.7420 (0.7539)	loss 2.0868 (2.6058)	grad_norm 5.5185 (2.5861/1.1717)	mem 34604MB
[2025-01-19 21:00:58 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][270/312]	eta 0:00:31 lr 0.000068	time 0.7995 (0.7606)	model_time 0.7991 (0.7548)	loss 2.5599 (2.6030)	grad_norm 2.3993 (2.5903/1.1618)	mem 34604MB
[2025-01-19 21:01:05 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][280/312]	eta 0:00:24 lr 0.000068	time 0.7217 (0.7602)	model_time 0.7215 (0.7546)	loss 2.7424 (2.5983)	grad_norm 2.8905 (2.5805/1.1557)	mem 34604MB
[2025-01-19 21:01:13 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][290/312]	eta 0:00:16 lr 0.000068	time 0.7233 (0.7597)	model_time 0.7229 (0.7543)	loss 2.8003 (2.6016)	grad_norm 3.0622 (2.5651/1.1438)	mem 34604MB
[2025-01-19 21:01:20 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][300/312]	eta 0:00:09 lr 0.000068	time 0.7154 (0.7584)	model_time 0.7153 (0.7531)	loss 2.9480 (2.6070)	grad_norm 1.2631 (2.5431/1.1442)	mem 34604MB
[2025-01-19 21:01:27 internimage_b_1k_224] (main.py 510): INFO Train: [283/300][310/312]	eta 0:00:01 lr 0.000068	time 0.7142 (0.7575)	model_time 0.7141 (0.7524)	loss 2.6648 (2.6046)	grad_norm 2.7668 (2.5021/1.0975)	mem 34604MB
[2025-01-19 21:01:28 internimage_b_1k_224] (main.py 519): INFO EPOCH 283 training takes 0:03:56
[2025-01-19 21:01:28 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_283.pth saving......
[2025-01-19 21:01:31 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_283.pth saved !!!
[2025-01-19 21:01:39 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.361 (7.361)	Loss 0.6798 (0.6798)	Acc@1 86.670 (86.670)	Acc@5 98.022 (98.022)	Mem 34604MB
[2025-01-19 21:01:42 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.928)	Loss 0.8843 (0.7627)	Acc@1 81.250 (84.741)	Acc@5 96.021 (97.073)	Mem 34604MB
[2025-01-19 21:01:42 internimage_b_1k_224] (main.py 575): INFO [Epoch:283] * Acc@1 84.593 Acc@5 97.075
[2025-01-19 21:01:42 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.6%
[2025-01-19 21:01:42 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.62%
[2025-01-19 21:01:51 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.482 (9.482)	Loss 0.7056 (0.7056)	Acc@1 86.792 (86.792)	Acc@5 98.193 (98.193)	Mem 34604MB
[2025-01-19 21:01:56 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.259)	Loss 0.9002 (0.7882)	Acc@1 81.250 (84.812)	Acc@5 96.143 (97.137)	Mem 34604MB
[2025-01-19 21:01:56 internimage_b_1k_224] (main.py 575): INFO [Epoch:283] * Acc@1 84.635 Acc@5 97.155
[2025-01-19 21:01:56 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.6%
[2025-01-19 21:01:56 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 21:02:00 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 21:02:00 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.63%
[2025-01-19 21:02:02 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][0/312]	eta 0:12:01 lr 0.000068	time 2.3136 (2.3136)	model_time 0.7535 (0.7535)	loss 2.9433 (2.9433)	grad_norm 2.9264 (2.9264/0.0000)	mem 34604MB
[2025-01-19 21:02:09 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][10/312]	eta 0:04:22 lr 0.000068	time 0.7222 (0.8703)	model_time 0.7221 (0.7282)	loss 3.1703 (2.7065)	grad_norm 4.9797 (2.6989/1.0873)	mem 34604MB
[2025-01-19 21:02:17 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][20/312]	eta 0:03:55 lr 0.000068	time 0.7354 (0.8053)	model_time 0.7349 (0.7307)	loss 2.1345 (2.6380)	grad_norm 1.8327 (2.5383/1.0240)	mem 34604MB
[2025-01-19 21:02:24 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][30/312]	eta 0:03:41 lr 0.000067	time 0.7250 (0.7837)	model_time 0.7248 (0.7331)	loss 2.3492 (2.5633)	grad_norm 3.3176 (2.6642/1.0100)	mem 34604MB
[2025-01-19 21:02:31 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][40/312]	eta 0:03:29 lr 0.000067	time 0.7244 (0.7710)	model_time 0.7242 (0.7325)	loss 2.9901 (2.6133)	grad_norm 1.0451 (2.8627/1.2374)	mem 34604MB
[2025-01-19 21:02:39 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][50/312]	eta 0:03:20 lr 0.000067	time 0.7182 (0.7664)	model_time 0.7177 (0.7354)	loss 2.8296 (2.6473)	grad_norm 4.0954 (3.0454/1.3236)	mem 34604MB
[2025-01-19 21:02:47 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][60/312]	eta 0:03:13 lr 0.000067	time 0.8186 (0.7683)	model_time 0.8185 (0.7424)	loss 3.0967 (2.6361)	grad_norm 2.6113 (2.9593/1.2515)	mem 34604MB
[2025-01-19 21:02:54 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][70/312]	eta 0:03:05 lr 0.000067	time 0.7166 (0.7674)	model_time 0.7162 (0.7450)	loss 2.8137 (2.6283)	grad_norm 1.5663 (2.8649/1.2185)	mem 34604MB
[2025-01-19 21:03:02 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][80/312]	eta 0:02:57 lr 0.000067	time 0.7295 (0.7670)	model_time 0.7291 (0.7473)	loss 2.3729 (2.6395)	grad_norm 1.4022 (2.7618/1.1886)	mem 34604MB
[2025-01-19 21:03:09 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][90/312]	eta 0:02:49 lr 0.000067	time 0.7304 (0.7647)	model_time 0.7302 (0.7471)	loss 3.2132 (2.6442)	grad_norm 1.6378 (2.6811/1.1573)	mem 34604MB
[2025-01-19 21:03:17 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][100/312]	eta 0:02:41 lr 0.000067	time 0.7240 (0.7628)	model_time 0.7236 (0.7469)	loss 2.9621 (2.6273)	grad_norm 2.6076 (2.6377/1.1450)	mem 34604MB
[2025-01-19 21:03:24 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][110/312]	eta 0:02:33 lr 0.000067	time 0.7157 (0.7594)	model_time 0.7153 (0.7449)	loss 2.1474 (2.6338)	grad_norm 3.0705 (2.6057/1.1159)	mem 34604MB
[2025-01-19 21:03:31 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][120/312]	eta 0:02:25 lr 0.000066	time 0.7287 (0.7587)	model_time 0.7286 (0.7454)	loss 2.5601 (2.6461)	grad_norm 2.9534 (2.6146/1.1138)	mem 34604MB
[2025-01-19 21:03:39 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][130/312]	eta 0:02:17 lr 0.000066	time 0.7310 (0.7559)	model_time 0.7305 (0.7436)	loss 2.8930 (2.6574)	grad_norm 2.6072 (2.6141/1.0913)	mem 34604MB
[2025-01-19 21:03:46 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][140/312]	eta 0:02:09 lr 0.000066	time 0.7227 (0.7542)	model_time 0.7225 (0.7427)	loss 2.6921 (2.6558)	grad_norm 2.7142 (2.6168/1.0806)	mem 34604MB
[2025-01-19 21:03:53 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][150/312]	eta 0:02:01 lr 0.000066	time 0.7184 (0.7527)	model_time 0.7179 (0.7420)	loss 2.7270 (2.6505)	grad_norm 1.1581 (2.5954/1.0846)	mem 34604MB
[2025-01-19 21:04:01 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][160/312]	eta 0:01:54 lr 0.000066	time 0.7327 (0.7513)	model_time 0.7326 (0.7412)	loss 2.6264 (2.6515)	grad_norm 1.7613 (2.5977/1.0703)	mem 34604MB
[2025-01-19 21:04:08 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][170/312]	eta 0:01:46 lr 0.000066	time 0.7169 (0.7513)	model_time 0.7164 (0.7417)	loss 2.6222 (2.6564)	grad_norm 1.6022 (2.5944/1.0808)	mem 34604MB
[2025-01-19 21:04:16 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][180/312]	eta 0:01:39 lr 0.000066	time 0.8552 (0.7532)	model_time 0.8548 (0.7441)	loss 3.0164 (2.6546)	grad_norm 3.5891 (2.6250/1.1039)	mem 34604MB
[2025-01-19 21:04:24 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][190/312]	eta 0:01:31 lr 0.000066	time 0.7324 (0.7538)	model_time 0.7322 (0.7452)	loss 2.8630 (2.6536)	grad_norm 3.7417 (2.6208/1.1124)	mem 34604MB
[2025-01-19 21:04:31 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][200/312]	eta 0:01:24 lr 0.000066	time 0.7336 (0.7544)	model_time 0.7334 (0.7462)	loss 2.8681 (2.6608)	grad_norm 4.3363 (2.6619/1.1265)	mem 34604MB
[2025-01-19 21:04:39 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][210/312]	eta 0:01:16 lr 0.000065	time 0.7292 (0.7541)	model_time 0.7287 (0.7463)	loss 1.7882 (2.6662)	grad_norm 1.9276 (2.6635/1.1520)	mem 34604MB
[2025-01-19 21:04:46 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][220/312]	eta 0:01:09 lr 0.000065	time 0.7166 (0.7535)	model_time 0.7164 (0.7460)	loss 2.5115 (2.6590)	grad_norm 1.3005 (2.6677/1.1662)	mem 34604MB
[2025-01-19 21:04:53 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][230/312]	eta 0:01:01 lr 0.000065	time 0.7177 (0.7525)	model_time 0.7175 (0.7453)	loss 2.4592 (2.6577)	grad_norm 1.4859 (2.6804/1.1666)	mem 34604MB
[2025-01-19 21:05:01 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][240/312]	eta 0:00:54 lr 0.000065	time 0.7176 (0.7522)	model_time 0.7175 (0.7453)	loss 2.6099 (2.6524)	grad_norm 1.9419 (2.6822/1.1548)	mem 34604MB
[2025-01-19 21:05:08 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][250/312]	eta 0:00:46 lr 0.000065	time 0.7205 (0.7512)	model_time 0.7200 (0.7446)	loss 2.6770 (2.6526)	grad_norm 1.6934 (2.6674/1.1510)	mem 34604MB
[2025-01-19 21:05:16 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][260/312]	eta 0:00:39 lr 0.000065	time 0.7217 (0.7515)	model_time 0.7215 (0.7451)	loss 2.5044 (2.6528)	grad_norm 3.3402 (2.6530/1.1351)	mem 34604MB
[2025-01-19 21:05:23 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][270/312]	eta 0:00:31 lr 0.000065	time 0.8079 (0.7509)	model_time 0.8074 (0.7447)	loss 2.4579 (2.6481)	grad_norm 5.0911 (2.6673/1.1319)	mem 34604MB
[2025-01-19 21:05:30 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][280/312]	eta 0:00:23 lr 0.000065	time 0.7182 (0.7499)	model_time 0.7177 (0.7440)	loss 2.9587 (2.6515)	grad_norm 2.4073 (2.6974/1.1600)	mem 34604MB
[2025-01-19 21:05:38 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][290/312]	eta 0:00:16 lr 0.000065	time 0.7985 (0.7500)	model_time 0.7984 (0.7442)	loss 2.7495 (2.6442)	grad_norm 2.9412 (2.7275/1.1829)	mem 34604MB
[2025-01-19 21:05:46 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][300/312]	eta 0:00:09 lr 0.000065	time 0.7897 (0.7506)	model_time 0.7896 (0.7450)	loss 2.4404 (2.6382)	grad_norm 3.8357 (2.7391/1.1856)	mem 34604MB
[2025-01-19 21:05:53 internimage_b_1k_224] (main.py 510): INFO Train: [284/300][310/312]	eta 0:00:01 lr 0.000064	time 0.7139 (0.7515)	model_time 0.7137 (0.7461)	loss 2.6660 (2.6413)	grad_norm 1.5058 (2.7318/1.1817)	mem 34604MB
[2025-01-19 21:05:54 internimage_b_1k_224] (main.py 519): INFO EPOCH 284 training takes 0:03:54
[2025-01-19 21:05:54 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_284.pth saving......
[2025-01-19 21:05:57 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_284.pth saved !!!
[2025-01-19 21:06:05 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.300 (7.300)	Loss 0.6818 (0.6818)	Acc@1 86.743 (86.743)	Acc@5 98.022 (98.022)	Mem 34604MB
[2025-01-19 21:06:08 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.945)	Loss 0.8910 (0.7693)	Acc@1 81.323 (84.877)	Acc@5 96.216 (97.090)	Mem 34604MB
[2025-01-19 21:06:08 internimage_b_1k_224] (main.py 575): INFO [Epoch:284] * Acc@1 84.699 Acc@5 97.099
[2025-01-19 21:06:08 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.7%
[2025-01-19 21:06:08 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 21:06:11 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 21:06:11 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.70%
[2025-01-19 21:06:19 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.403 (7.403)	Loss 0.7051 (0.7051)	Acc@1 86.792 (86.792)	Acc@5 98.193 (98.193)	Mem 34604MB
[2025-01-19 21:06:22 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.969)	Loss 0.8998 (0.7877)	Acc@1 81.274 (84.819)	Acc@5 96.143 (97.141)	Mem 34604MB
[2025-01-19 21:06:22 internimage_b_1k_224] (main.py 575): INFO [Epoch:284] * Acc@1 84.645 Acc@5 97.159
[2025-01-19 21:06:22 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.6%
[2025-01-19 21:06:22 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 21:06:26 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 21:06:26 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.64%
[2025-01-19 21:06:28 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][0/312]	eta 0:11:51 lr 0.000064	time 2.2808 (2.2808)	model_time 0.7561 (0.7561)	loss 1.8538 (1.8538)	grad_norm 2.8602 (2.8602/0.0000)	mem 34604MB
[2025-01-19 21:06:36 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][10/312]	eta 0:04:32 lr 0.000064	time 0.7218 (0.9027)	model_time 0.7212 (0.7638)	loss 2.7022 (2.5615)	grad_norm 1.3848 (2.2800/0.5623)	mem 34604MB
[2025-01-19 21:06:43 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][20/312]	eta 0:04:02 lr 0.000064	time 0.7362 (0.8293)	model_time 0.7360 (0.7564)	loss 2.3053 (2.5583)	grad_norm 2.8599 (2.3356/0.6795)	mem 34604MB
[2025-01-19 21:06:51 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][30/312]	eta 0:03:47 lr 0.000064	time 0.8173 (0.8050)	model_time 0.8170 (0.7554)	loss 2.5120 (2.6094)	grad_norm 2.4398 (2.5125/0.8780)	mem 34604MB
[2025-01-19 21:06:58 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][40/312]	eta 0:03:33 lr 0.000064	time 0.7252 (0.7852)	model_time 0.7250 (0.7477)	loss 2.8999 (2.5725)	grad_norm 1.5908 (2.4789/0.9071)	mem 34604MB
[2025-01-19 21:07:06 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][50/312]	eta 0:03:23 lr 0.000064	time 0.7270 (0.7762)	model_time 0.7268 (0.7459)	loss 2.9912 (2.6401)	grad_norm 1.4280 (2.4136/0.8782)	mem 34604MB
[2025-01-19 21:07:13 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][60/312]	eta 0:03:13 lr 0.000064	time 0.7251 (0.7681)	model_time 0.7246 (0.7427)	loss 2.9871 (2.6495)	grad_norm 1.8032 (2.4890/0.9280)	mem 34604MB
[2025-01-19 21:07:20 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][70/312]	eta 0:03:04 lr 0.000064	time 0.7216 (0.7621)	model_time 0.7214 (0.7402)	loss 2.6852 (2.6245)	grad_norm 1.6998 (2.4646/0.8749)	mem 34604MB
[2025-01-19 21:07:28 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][80/312]	eta 0:02:56 lr 0.000064	time 0.8077 (0.7588)	model_time 0.8075 (0.7395)	loss 2.6847 (2.6424)	grad_norm 1.8208 (2.5131/0.8778)	mem 34604MB
[2025-01-19 21:07:35 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][90/312]	eta 0:02:47 lr 0.000063	time 0.7209 (0.7551)	model_time 0.7204 (0.7380)	loss 2.7898 (2.6357)	grad_norm 1.5861 (2.4973/0.8644)	mem 34604MB
[2025-01-19 21:07:42 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][100/312]	eta 0:02:39 lr 0.000063	time 0.8104 (0.7541)	model_time 0.8099 (0.7386)	loss 2.9107 (2.6217)	grad_norm 3.7478 (2.4930/0.8690)	mem 34604MB
[2025-01-19 21:07:50 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][110/312]	eta 0:02:32 lr 0.000063	time 0.8368 (0.7564)	model_time 0.8366 (0.7422)	loss 2.3044 (2.5955)	grad_norm 3.2117 (2.5328/0.9272)	mem 34604MB
[2025-01-19 21:07:58 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][120/312]	eta 0:02:25 lr 0.000063	time 0.8036 (0.7593)	model_time 0.8031 (0.7463)	loss 2.1560 (2.5857)	grad_norm 2.1711 (2.5730/0.9641)	mem 34604MB
[2025-01-19 21:08:06 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][130/312]	eta 0:02:18 lr 0.000063	time 0.7182 (0.7604)	model_time 0.7177 (0.7484)	loss 2.2244 (2.5924)	grad_norm 2.3212 (2.5613/0.9570)	mem 34604MB
[2025-01-19 21:08:13 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][140/312]	eta 0:02:10 lr 0.000063	time 0.7307 (0.7598)	model_time 0.7305 (0.7486)	loss 2.6397 (2.5915)	grad_norm 4.4692 (2.5982/0.9753)	mem 34604MB
[2025-01-19 21:08:21 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][150/312]	eta 0:02:02 lr 0.000063	time 0.8230 (0.7588)	model_time 0.8228 (0.7482)	loss 2.5020 (2.5812)	grad_norm 3.9998 (2.6397/0.9856)	mem 34604MB
[2025-01-19 21:08:28 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][160/312]	eta 0:01:54 lr 0.000063	time 0.7207 (0.7564)	model_time 0.7205 (0.7465)	loss 2.8320 (2.5875)	grad_norm 2.3558 (2.6339/0.9978)	mem 34604MB
[2025-01-19 21:08:35 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][170/312]	eta 0:01:47 lr 0.000063	time 0.7395 (0.7555)	model_time 0.7390 (0.7462)	loss 1.7350 (2.5818)	grad_norm 4.0699 (2.5970/0.9958)	mem 34604MB
[2025-01-19 21:08:43 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][180/312]	eta 0:01:39 lr 0.000063	time 0.7189 (0.7540)	model_time 0.7184 (0.7452)	loss 1.7690 (2.5762)	grad_norm 2.5521 (2.5687/0.9815)	mem 34604MB
[2025-01-19 21:08:50 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][190/312]	eta 0:01:31 lr 0.000062	time 0.7190 (0.7528)	model_time 0.7188 (0.7444)	loss 2.6935 (2.5841)	grad_norm 1.5947 (2.5452/0.9758)	mem 34604MB
[2025-01-19 21:08:57 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][200/312]	eta 0:01:24 lr 0.000062	time 0.7241 (0.7514)	model_time 0.7237 (0.7434)	loss 1.8409 (2.5835)	grad_norm 2.0416 (2.5378/0.9568)	mem 34604MB
[2025-01-19 21:09:04 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][210/312]	eta 0:01:16 lr 0.000062	time 0.7212 (0.7507)	model_time 0.7210 (0.7431)	loss 3.2584 (2.5826)	grad_norm 3.1789 (2.5289/0.9501)	mem 34604MB
[2025-01-19 21:09:12 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][220/312]	eta 0:01:09 lr 0.000062	time 0.8167 (0.7504)	model_time 0.8165 (0.7430)	loss 2.1711 (2.5756)	grad_norm 3.8832 (2.5275/0.9619)	mem 34604MB
[2025-01-19 21:09:20 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][230/312]	eta 0:01:01 lr 0.000062	time 0.7952 (0.7516)	model_time 0.7950 (0.7446)	loss 2.9483 (2.5679)	grad_norm 2.7685 (2.5620/0.9869)	mem 34604MB
[2025-01-19 21:09:28 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][240/312]	eta 0:00:54 lr 0.000062	time 0.8099 (0.7529)	model_time 0.8097 (0.7461)	loss 2.4970 (2.5782)	grad_norm 2.8828 (2.5634/0.9738)	mem 34604MB
[2025-01-19 21:09:35 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][250/312]	eta 0:00:46 lr 0.000062	time 0.7236 (0.7532)	model_time 0.7232 (0.7467)	loss 2.0061 (2.5762)	grad_norm 2.5285 (2.5534/0.9657)	mem 34604MB
[2025-01-19 21:09:43 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][260/312]	eta 0:00:39 lr 0.000062	time 0.7595 (0.7536)	model_time 0.7590 (0.7473)	loss 2.1810 (2.5740)	grad_norm 2.7748 (2.5538/0.9569)	mem 34604MB
[2025-01-19 21:09:50 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][270/312]	eta 0:00:31 lr 0.000062	time 0.8333 (0.7531)	model_time 0.8331 (0.7471)	loss 2.7305 (2.5743)	grad_norm 3.0112 (2.5373/0.9510)	mem 34604MB
[2025-01-19 21:09:57 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][280/312]	eta 0:00:24 lr 0.000062	time 0.7346 (0.7520)	model_time 0.7341 (0.7462)	loss 3.1348 (2.5767)	grad_norm 1.2910 (2.5240/0.9463)	mem 34604MB
[2025-01-19 21:10:05 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][290/312]	eta 0:00:16 lr 0.000061	time 0.7179 (0.7514)	model_time 0.7177 (0.7457)	loss 2.4911 (2.5787)	grad_norm 4.2415 (2.5109/0.9451)	mem 34604MB
[2025-01-19 21:10:12 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][300/312]	eta 0:00:09 lr 0.000061	time 0.7129 (0.7505)	model_time 0.7128 (0.7450)	loss 2.7534 (2.5814)	grad_norm 4.0213 (2.5245/0.9611)	mem 34604MB
[2025-01-19 21:10:19 internimage_b_1k_224] (main.py 510): INFO Train: [285/300][310/312]	eta 0:00:01 lr 0.000061	time 0.7196 (0.7495)	model_time 0.7195 (0.7442)	loss 2.7400 (2.5838)	grad_norm 3.3976 (2.5116/0.9687)	mem 34604MB
[2025-01-19 21:10:20 internimage_b_1k_224] (main.py 519): INFO EPOCH 285 training takes 0:03:53
[2025-01-19 21:10:20 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_285.pth saving......
[2025-01-19 21:10:23 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_285.pth saved !!!
[2025-01-19 21:10:31 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.525 (7.525)	Loss 0.6840 (0.6840)	Acc@1 86.792 (86.792)	Acc@5 98.022 (98.022)	Mem 34604MB
[2025-01-19 21:10:34 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.959)	Loss 0.8942 (0.7691)	Acc@1 81.226 (84.739)	Acc@5 96.094 (97.084)	Mem 34604MB
[2025-01-19 21:10:34 internimage_b_1k_224] (main.py 575): INFO [Epoch:285] * Acc@1 84.587 Acc@5 97.077
[2025-01-19 21:10:34 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.6%
[2025-01-19 21:10:34 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.70%
[2025-01-19 21:10:43 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.116 (9.116)	Loss 0.7048 (0.7048)	Acc@1 86.816 (86.816)	Acc@5 98.193 (98.193)	Mem 34604MB
[2025-01-19 21:10:48 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.261)	Loss 0.8995 (0.7872)	Acc@1 81.226 (84.837)	Acc@5 96.143 (97.141)	Mem 34604MB
[2025-01-19 21:10:48 internimage_b_1k_224] (main.py 575): INFO [Epoch:285] * Acc@1 84.659 Acc@5 97.157
[2025-01-19 21:10:48 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.7%
[2025-01-19 21:10:48 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 21:10:52 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 21:10:52 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.66%
[2025-01-19 21:10:54 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][0/312]	eta 0:11:33 lr 0.000061	time 2.2229 (2.2229)	model_time 0.7547 (0.7547)	loss 2.1484 (2.1484)	grad_norm 1.8063 (1.8063/0.0000)	mem 34604MB
[2025-01-19 21:11:01 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][10/312]	eta 0:04:20 lr 0.000061	time 0.7120 (0.8640)	model_time 0.7119 (0.7302)	loss 2.8600 (2.5292)	grad_norm 2.2487 (2.2620/0.4341)	mem 34604MB
[2025-01-19 21:11:09 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][20/312]	eta 0:03:55 lr 0.000061	time 0.7673 (0.8066)	model_time 0.7671 (0.7363)	loss 2.4945 (2.5002)	grad_norm 3.0451 (2.1244/0.5342)	mem 34604MB
[2025-01-19 21:11:16 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][30/312]	eta 0:03:42 lr 0.000061	time 0.7132 (0.7876)	model_time 0.7130 (0.7399)	loss 2.7338 (2.5689)	grad_norm 3.0035 (2.2298/0.6432)	mem 34604MB
[2025-01-19 21:11:24 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][40/312]	eta 0:03:33 lr 0.000061	time 0.8003 (0.7842)	model_time 0.8001 (0.7481)	loss 1.7270 (2.5648)	grad_norm 3.4071 (2.2515/0.6336)	mem 34604MB
[2025-01-19 21:11:32 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][50/312]	eta 0:03:24 lr 0.000061	time 0.7181 (0.7795)	model_time 0.7176 (0.7504)	loss 2.4947 (2.5963)	grad_norm 3.1226 (2.2483/0.6200)	mem 34604MB
[2025-01-19 21:11:39 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][60/312]	eta 0:03:16 lr 0.000061	time 0.8045 (0.7783)	model_time 0.8044 (0.7539)	loss 2.2374 (2.5642)	grad_norm 3.7141 (2.2806/0.6574)	mem 34604MB
[2025-01-19 21:11:47 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][70/312]	eta 0:03:06 lr 0.000061	time 0.7194 (0.7718)	model_time 0.7192 (0.7508)	loss 2.8600 (2.5713)	grad_norm 1.0735 (2.2284/0.6670)	mem 34604MB
[2025-01-19 21:11:54 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][80/312]	eta 0:02:57 lr 0.000060	time 0.7286 (0.7670)	model_time 0.7285 (0.7485)	loss 1.6781 (2.5508)	grad_norm 3.1200 (2.3050/0.8277)	mem 34604MB
[2025-01-19 21:12:01 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][90/312]	eta 0:02:49 lr 0.000060	time 0.7363 (0.7636)	model_time 0.7361 (0.7471)	loss 2.2813 (2.5652)	grad_norm 4.5048 (2.4396/0.9489)	mem 34604MB
[2025-01-19 21:12:09 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][100/312]	eta 0:02:41 lr 0.000060	time 0.7243 (0.7612)	model_time 0.7242 (0.7463)	loss 2.4812 (2.5809)	grad_norm 2.3267 (2.4050/0.9315)	mem 34604MB
[2025-01-19 21:12:16 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][110/312]	eta 0:02:33 lr 0.000060	time 0.7167 (0.7578)	model_time 0.7163 (0.7442)	loss 2.8036 (2.5965)	grad_norm 2.4989 (2.3902/0.8991)	mem 34604MB
[2025-01-19 21:12:23 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][120/312]	eta 0:02:24 lr 0.000060	time 0.7298 (0.7550)	model_time 0.7296 (0.7425)	loss 2.0020 (2.5975)	grad_norm 2.2808 (2.4318/1.0080)	mem 34604MB
[2025-01-19 21:12:31 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][130/312]	eta 0:02:17 lr 0.000060	time 0.8271 (0.7539)	model_time 0.8269 (0.7423)	loss 2.9355 (2.6078)	grad_norm 1.5565 (2.4413/0.9955)	mem 34604MB
[2025-01-19 21:12:38 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][140/312]	eta 0:02:09 lr 0.000060	time 0.7289 (0.7523)	model_time 0.7287 (0.7415)	loss 3.0435 (2.6105)	grad_norm 2.7442 (2.4385/0.9912)	mem 34604MB
[2025-01-19 21:12:45 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][150/312]	eta 0:02:01 lr 0.000060	time 0.7278 (0.7521)	model_time 0.7273 (0.7420)	loss 2.6803 (2.6021)	grad_norm 2.0971 (2.4261/0.9904)	mem 34604MB
[2025-01-19 21:12:53 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][160/312]	eta 0:01:54 lr 0.000060	time 0.7168 (0.7531)	model_time 0.7165 (0.7436)	loss 2.9683 (2.6050)	grad_norm 2.4531 (2.3960/0.9737)	mem 34604MB
[2025-01-19 21:13:01 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][170/312]	eta 0:01:47 lr 0.000060	time 0.7273 (0.7540)	model_time 0.7268 (0.7451)	loss 2.6097 (2.6071)	grad_norm 2.6802 (2.3939/0.9531)	mem 34604MB
[2025-01-19 21:13:09 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][180/312]	eta 0:01:39 lr 0.000060	time 0.8056 (0.7558)	model_time 0.8054 (0.7473)	loss 2.7264 (2.6048)	grad_norm 1.8708 (2.4018/0.9476)	mem 34604MB
[2025-01-19 21:13:16 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][190/312]	eta 0:01:32 lr 0.000059	time 0.7169 (0.7546)	model_time 0.7167 (0.7466)	loss 2.1578 (2.6083)	grad_norm 2.1509 (2.3991/0.9501)	mem 34604MB
[2025-01-19 21:13:23 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][200/312]	eta 0:01:24 lr 0.000059	time 0.7230 (0.7539)	model_time 0.7228 (0.7462)	loss 2.7723 (2.5993)	grad_norm 1.7459 (2.4336/0.9980)	mem 34604MB
[2025-01-19 21:13:31 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][210/312]	eta 0:01:16 lr 0.000059	time 0.7298 (0.7527)	model_time 0.7296 (0.7454)	loss 2.6926 (2.5932)	grad_norm 2.4165 (2.4236/0.9942)	mem 34604MB
[2025-01-19 21:13:38 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][220/312]	eta 0:01:09 lr 0.000059	time 0.7318 (0.7521)	model_time 0.7316 (0.7451)	loss 1.6190 (2.5924)	grad_norm 1.8643 (2.4338/0.9909)	mem 34604MB
[2025-01-19 21:13:45 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][230/312]	eta 0:01:01 lr 0.000059	time 0.7367 (0.7512)	model_time 0.7362 (0.7445)	loss 2.6991 (2.5912)	grad_norm 1.6184 (2.4145/0.9797)	mem 34604MB
[2025-01-19 21:13:53 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][240/312]	eta 0:00:54 lr 0.000059	time 0.7229 (0.7501)	model_time 0.7227 (0.7436)	loss 2.1234 (2.5894)	grad_norm 1.7475 (2.4168/0.9715)	mem 34604MB
[2025-01-19 21:14:00 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][250/312]	eta 0:00:46 lr 0.000059	time 0.7290 (0.7492)	model_time 0.7286 (0.7430)	loss 1.7158 (2.5788)	grad_norm 2.6229 (2.4000/0.9631)	mem 34604MB
[2025-01-19 21:14:07 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][260/312]	eta 0:00:38 lr 0.000059	time 0.7631 (0.7492)	model_time 0.7627 (0.7432)	loss 2.9365 (2.5805)	grad_norm 2.6136 (2.4041/0.9585)	mem 34604MB
[2025-01-19 21:14:15 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][270/312]	eta 0:00:31 lr 0.000059	time 0.7403 (0.7493)	model_time 0.7401 (0.7436)	loss 2.5186 (2.5815)	grad_norm 2.7757 (2.4073/0.9543)	mem 34604MB
[2025-01-19 21:14:23 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][280/312]	eta 0:00:23 lr 0.000059	time 0.7211 (0.7500)	model_time 0.7210 (0.7444)	loss 1.7291 (2.5820)	grad_norm 1.7637 (2.4039/0.9592)	mem 34604MB
[2025-01-19 21:14:30 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][290/312]	eta 0:00:16 lr 0.000059	time 0.7977 (0.7509)	model_time 0.7972 (0.7455)	loss 2.2536 (2.5758)	grad_norm 2.0538 (2.4066/0.9611)	mem 34604MB
[2025-01-19 21:14:38 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][300/312]	eta 0:00:09 lr 0.000058	time 0.7217 (0.7515)	model_time 0.7216 (0.7462)	loss 2.9972 (2.5785)	grad_norm 2.5597 (2.4451/0.9870)	mem 34604MB
[2025-01-19 21:14:45 internimage_b_1k_224] (main.py 510): INFO Train: [286/300][310/312]	eta 0:00:01 lr 0.000058	time 0.7212 (0.7512)	model_time 0.7210 (0.7461)	loss 2.3031 (2.5758)	grad_norm 1.4343 (2.4711/1.0421)	mem 34604MB
[2025-01-19 21:14:46 internimage_b_1k_224] (main.py 519): INFO EPOCH 286 training takes 0:03:54
[2025-01-19 21:14:46 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_286.pth saving......
[2025-01-19 21:14:49 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_286.pth saved !!!
[2025-01-19 21:14:57 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.496 (7.496)	Loss 0.6817 (0.6817)	Acc@1 86.719 (86.719)	Acc@5 98.120 (98.120)	Mem 34604MB
[2025-01-19 21:15:00 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.983)	Loss 0.8827 (0.7648)	Acc@1 81.445 (84.801)	Acc@5 96.118 (97.061)	Mem 34604MB
[2025-01-19 21:15:00 internimage_b_1k_224] (main.py 575): INFO [Epoch:286] * Acc@1 84.627 Acc@5 97.073
[2025-01-19 21:15:00 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.6%
[2025-01-19 21:15:00 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.70%
[2025-01-19 21:15:10 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.303 (9.303)	Loss 0.7043 (0.7043)	Acc@1 86.841 (86.841)	Acc@5 98.169 (98.169)	Mem 34604MB
[2025-01-19 21:15:14 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.249)	Loss 0.8990 (0.7866)	Acc@1 81.201 (84.834)	Acc@5 96.143 (97.130)	Mem 34604MB
[2025-01-19 21:15:14 internimage_b_1k_224] (main.py 575): INFO [Epoch:286] * Acc@1 84.657 Acc@5 97.147
[2025-01-19 21:15:14 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.7%
[2025-01-19 21:15:14 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.66%
[2025-01-19 21:15:18 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][0/312]	eta 0:17:09 lr 0.000058	time 3.2987 (3.2987)	model_time 1.6770 (1.6770)	loss 2.8840 (2.8840)	grad_norm 2.1602 (2.1602/0.0000)	mem 34604MB
[2025-01-19 21:15:25 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][10/312]	eta 0:04:59 lr 0.000058	time 0.7566 (0.9914)	model_time 0.7565 (0.8437)	loss 3.1673 (2.5570)	grad_norm 3.4208 (2.3208/0.5944)	mem 34604MB
[2025-01-19 21:15:33 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][20/312]	eta 0:04:15 lr 0.000058	time 0.7380 (0.8743)	model_time 0.7378 (0.7968)	loss 2.8689 (2.6567)	grad_norm 1.7326 (2.1473/0.5670)	mem 34604MB
[2025-01-19 21:15:40 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][30/312]	eta 0:03:54 lr 0.000058	time 0.7583 (0.8310)	model_time 0.7578 (0.7783)	loss 2.5736 (2.6736)	grad_norm 2.2427 (2.2335/0.6854)	mem 34604MB
[2025-01-19 21:15:47 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][40/312]	eta 0:03:39 lr 0.000058	time 0.7253 (0.8054)	model_time 0.7252 (0.7655)	loss 2.6242 (2.6424)	grad_norm 1.6788 (2.1744/0.6693)	mem 34604MB
[2025-01-19 21:15:55 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][50/312]	eta 0:03:26 lr 0.000058	time 0.7223 (0.7894)	model_time 0.7221 (0.7573)	loss 2.5443 (2.6346)	grad_norm 1.5126 (2.1235/0.6476)	mem 34604MB
[2025-01-19 21:16:02 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][60/312]	eta 0:03:16 lr 0.000058	time 0.7342 (0.7786)	model_time 0.7337 (0.7517)	loss 2.4778 (2.6121)	grad_norm 2.1966 (2.1327/0.6474)	mem 34604MB
[2025-01-19 21:16:09 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][70/312]	eta 0:03:07 lr 0.000058	time 0.7190 (0.7736)	model_time 0.7188 (0.7504)	loss 3.0002 (2.6233)	grad_norm 1.5760 (2.1262/0.6193)	mem 34604MB
[2025-01-19 21:16:17 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][80/312]	eta 0:02:58 lr 0.000058	time 0.7188 (0.7709)	model_time 0.7186 (0.7506)	loss 3.1661 (2.6393)	grad_norm 3.9514 (2.1281/0.6658)	mem 34604MB
[2025-01-19 21:16:25 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][90/312]	eta 0:02:51 lr 0.000058	time 0.7279 (0.7704)	model_time 0.7277 (0.7522)	loss 2.0152 (2.6314)	grad_norm 2.7603 (2.1192/0.6570)	mem 34604MB
[2025-01-19 21:16:32 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][100/312]	eta 0:02:43 lr 0.000057	time 0.7149 (0.7709)	model_time 0.7144 (0.7545)	loss 2.7045 (2.6264)	grad_norm 3.7657 (2.1644/0.7089)	mem 34604MB
[2025-01-19 21:16:40 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][110/312]	eta 0:02:35 lr 0.000057	time 0.7193 (0.7700)	model_time 0.7191 (0.7550)	loss 2.8823 (2.6352)	grad_norm 1.9049 (2.2502/0.7986)	mem 34604MB
[2025-01-19 21:16:47 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][120/312]	eta 0:02:27 lr 0.000057	time 0.7208 (0.7685)	model_time 0.7204 (0.7547)	loss 3.3234 (2.6380)	grad_norm 3.2641 (2.3273/0.8941)	mem 34604MB
[2025-01-19 21:16:55 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][130/312]	eta 0:02:19 lr 0.000057	time 0.7222 (0.7666)	model_time 0.7217 (0.7538)	loss 2.7673 (2.6332)	grad_norm 2.2606 (2.3329/0.8987)	mem 34604MB
[2025-01-19 21:17:02 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][140/312]	eta 0:02:11 lr 0.000057	time 0.7246 (0.7646)	model_time 0.7244 (0.7528)	loss 2.1944 (2.6297)	grad_norm 1.2433 (2.3237/0.8894)	mem 34604MB
[2025-01-19 21:17:10 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][150/312]	eta 0:02:03 lr 0.000057	time 0.7198 (0.7622)	model_time 0.7194 (0.7511)	loss 3.0481 (2.6403)	grad_norm 2.8415 (2.2895/0.8774)	mem 34604MB
[2025-01-19 21:17:17 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][160/312]	eta 0:01:55 lr 0.000057	time 0.7205 (0.7609)	model_time 0.7203 (0.7505)	loss 2.6278 (2.6512)	grad_norm 2.0616 (2.2910/0.8761)	mem 34604MB
[2025-01-19 21:17:24 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][170/312]	eta 0:01:47 lr 0.000057	time 0.7234 (0.7590)	model_time 0.7229 (0.7492)	loss 3.0728 (2.6590)	grad_norm 2.3175 (2.3006/0.8726)	mem 34604MB
[2025-01-19 21:17:32 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][180/312]	eta 0:01:39 lr 0.000057	time 0.7275 (0.7572)	model_time 0.7274 (0.7479)	loss 2.8779 (2.6519)	grad_norm 1.3350 (2.3264/0.8854)	mem 34604MB
[2025-01-19 21:17:39 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][190/312]	eta 0:01:32 lr 0.000057	time 0.7356 (0.7560)	model_time 0.7351 (0.7472)	loss 2.8607 (2.6492)	grad_norm 2.1692 (2.3426/0.8934)	mem 34604MB
[2025-01-19 21:17:46 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][200/312]	eta 0:01:24 lr 0.000057	time 0.7157 (0.7557)	model_time 0.7153 (0.7472)	loss 2.7072 (2.6461)	grad_norm 1.5572 (2.3287/0.8821)	mem 34604MB
[2025-01-19 21:17:54 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][210/312]	eta 0:01:17 lr 0.000056	time 0.7151 (0.7555)	model_time 0.7148 (0.7474)	loss 2.2153 (2.6430)	grad_norm 1.8331 (2.3351/0.8798)	mem 34604MB
[2025-01-19 21:18:02 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][220/312]	eta 0:01:09 lr 0.000056	time 0.7217 (0.7573)	model_time 0.7216 (0.7496)	loss 2.9385 (2.6461)	grad_norm 1.9960 (2.3296/0.8795)	mem 34604MB
[2025-01-19 21:18:09 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][230/312]	eta 0:01:02 lr 0.000056	time 0.7165 (0.7576)	model_time 0.7163 (0.7502)	loss 1.5989 (2.6337)	grad_norm 2.3936 (2.3244/0.8758)	mem 34604MB
[2025-01-19 21:18:17 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][240/312]	eta 0:00:54 lr 0.000056	time 0.7198 (0.7574)	model_time 0.7193 (0.7502)	loss 2.2104 (2.6317)	grad_norm 2.4965 (2.3007/0.8705)	mem 34604MB
[2025-01-19 21:18:24 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][250/312]	eta 0:00:46 lr 0.000056	time 0.7268 (0.7566)	model_time 0.7267 (0.7497)	loss 2.5726 (2.6337)	grad_norm 2.5326 (2.3142/0.8834)	mem 34604MB
[2025-01-19 21:18:32 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][260/312]	eta 0:00:39 lr 0.000056	time 0.7183 (0.7561)	model_time 0.7178 (0.7495)	loss 2.4344 (2.6345)	grad_norm 2.5383 (2.3270/0.8958)	mem 34604MB
[2025-01-19 21:18:39 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][270/312]	eta 0:00:31 lr 0.000056	time 0.7204 (0.7551)	model_time 0.7202 (0.7488)	loss 2.7394 (2.6282)	grad_norm 3.5234 (2.3620/0.9216)	mem 34604MB
[2025-01-19 21:18:47 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][280/312]	eta 0:00:24 lr 0.000056	time 0.7341 (0.7549)	model_time 0.7339 (0.7487)	loss 2.5849 (2.6286)	grad_norm 3.1188 (2.3700/0.9335)	mem 34604MB
[2025-01-19 21:18:54 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][290/312]	eta 0:00:16 lr 0.000056	time 0.7144 (0.7539)	model_time 0.7139 (0.7480)	loss 3.0452 (2.6276)	grad_norm 1.5914 (2.3739/0.9382)	mem 34604MB
[2025-01-19 21:19:01 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][300/312]	eta 0:00:09 lr 0.000056	time 0.7156 (0.7528)	model_time 0.7154 (0.7470)	loss 2.5737 (2.6235)	grad_norm 2.1580 (2.3683/0.9345)	mem 34604MB
[2025-01-19 21:19:08 internimage_b_1k_224] (main.py 510): INFO Train: [287/300][310/312]	eta 0:00:01 lr 0.000056	time 0.7999 (0.7519)	model_time 0.7998 (0.7463)	loss 2.7580 (2.6231)	grad_norm 3.8605 (2.3753/0.9352)	mem 34604MB
[2025-01-19 21:19:09 internimage_b_1k_224] (main.py 519): INFO EPOCH 287 training takes 0:03:54
[2025-01-19 21:19:09 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_287.pth saving......
[2025-01-19 21:19:12 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_287.pth saved !!!
[2025-01-19 21:19:20 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.429 (7.429)	Loss 0.6863 (0.6863)	Acc@1 86.597 (86.597)	Acc@5 98.096 (98.096)	Mem 34604MB
[2025-01-19 21:19:23 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.943)	Loss 0.8903 (0.7673)	Acc@1 81.274 (84.817)	Acc@5 96.265 (97.095)	Mem 34604MB
[2025-01-19 21:19:23 internimage_b_1k_224] (main.py 575): INFO [Epoch:287] * Acc@1 84.637 Acc@5 97.087
[2025-01-19 21:19:23 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.6%
[2025-01-19 21:19:23 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.70%
[2025-01-19 21:19:32 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.205 (9.205)	Loss 0.7040 (0.7040)	Acc@1 86.841 (86.841)	Acc@5 98.169 (98.169)	Mem 34604MB
[2025-01-19 21:19:37 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.250)	Loss 0.8985 (0.7861)	Acc@1 81.299 (84.854)	Acc@5 96.167 (97.144)	Mem 34604MB
[2025-01-19 21:19:37 internimage_b_1k_224] (main.py 575): INFO [Epoch:287] * Acc@1 84.677 Acc@5 97.161
[2025-01-19 21:19:37 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.7%
[2025-01-19 21:19:37 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 21:19:41 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 21:19:41 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.68%
[2025-01-19 21:19:43 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][0/312]	eta 0:11:36 lr 0.000056	time 2.2321 (2.2321)	model_time 0.7560 (0.7560)	loss 1.6874 (1.6874)	grad_norm 2.2792 (2.2792/0.0000)	mem 34604MB
[2025-01-19 21:19:50 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][10/312]	eta 0:04:29 lr 0.000056	time 0.7184 (0.8938)	model_time 0.7182 (0.7593)	loss 2.1978 (2.3002)	grad_norm 3.1705 (2.1898/0.6786)	mem 34604MB
[2025-01-19 21:19:58 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][20/312]	eta 0:04:01 lr 0.000055	time 0.8106 (0.8284)	model_time 0.8104 (0.7578)	loss 1.7306 (2.4627)	grad_norm 1.9093 (1.9463/0.6037)	mem 34604MB
[2025-01-19 21:20:06 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][30/312]	eta 0:03:50 lr 0.000055	time 0.8051 (0.8161)	model_time 0.8049 (0.7681)	loss 2.7832 (2.5300)	grad_norm 2.1990 (2.0217/0.6590)	mem 34604MB
[2025-01-19 21:20:14 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][40/312]	eta 0:03:39 lr 0.000055	time 0.7170 (0.8060)	model_time 0.7168 (0.7696)	loss 3.0893 (2.5592)	grad_norm 3.2429 (2.2102/0.7622)	mem 34604MB
[2025-01-19 21:20:21 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][50/312]	eta 0:03:28 lr 0.000055	time 0.7352 (0.7949)	model_time 0.7347 (0.7656)	loss 2.6690 (2.5697)	grad_norm 2.9159 (2.2814/0.8313)	mem 34604MB
[2025-01-19 21:20:29 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][60/312]	eta 0:03:19 lr 0.000055	time 0.8209 (0.7899)	model_time 0.8204 (0.7653)	loss 2.7413 (2.5979)	grad_norm 3.4499 (2.3120/0.8310)	mem 34604MB
[2025-01-19 21:20:36 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][70/312]	eta 0:03:08 lr 0.000055	time 0.7183 (0.7807)	model_time 0.7181 (0.7596)	loss 2.5918 (2.6259)	grad_norm 2.0986 (2.3324/0.8190)	mem 34604MB
[2025-01-19 21:20:43 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][80/312]	eta 0:02:59 lr 0.000055	time 0.7155 (0.7740)	model_time 0.7153 (0.7554)	loss 1.9125 (2.6200)	grad_norm 3.8348 (2.3726/0.8727)	mem 34604MB
[2025-01-19 21:20:51 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][90/312]	eta 0:02:50 lr 0.000055	time 0.7192 (0.7700)	model_time 0.7190 (0.7534)	loss 2.7471 (2.5847)	grad_norm 1.9800 (2.4312/0.9066)	mem 34604MB
[2025-01-19 21:20:58 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][100/312]	eta 0:02:42 lr 0.000055	time 0.7303 (0.7657)	model_time 0.7302 (0.7508)	loss 3.1061 (2.5874)	grad_norm 4.4284 (2.4413/0.9358)	mem 34604MB
[2025-01-19 21:21:05 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][110/312]	eta 0:02:34 lr 0.000055	time 0.7409 (0.7626)	model_time 0.7407 (0.7490)	loss 2.0411 (2.5815)	grad_norm 1.9920 (2.4660/0.9246)	mem 34604MB
[2025-01-19 21:21:13 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][120/312]	eta 0:02:25 lr 0.000055	time 0.7156 (0.7601)	model_time 0.7154 (0.7475)	loss 2.9202 (2.5697)	grad_norm 1.3078 (2.4477/0.9160)	mem 34604MB
[2025-01-19 21:21:20 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][130/312]	eta 0:02:18 lr 0.000055	time 1.0707 (0.7622)	model_time 1.0705 (0.7506)	loss 3.0923 (2.5633)	grad_norm 2.7780 (2.4427/0.8994)	mem 34604MB
[2025-01-19 21:21:28 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][140/312]	eta 0:02:11 lr 0.000054	time 0.7251 (0.7618)	model_time 0.7246 (0.7510)	loss 2.0774 (2.5353)	grad_norm 2.1394 (2.4864/0.9460)	mem 34604MB
[2025-01-19 21:21:36 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][150/312]	eta 0:02:03 lr 0.000054	time 0.8191 (0.7637)	model_time 0.8189 (0.7536)	loss 2.3118 (2.5566)	grad_norm 2.8302 (2.4764/0.9213)	mem 34604MB
[2025-01-19 21:21:44 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][160/312]	eta 0:01:56 lr 0.000054	time 0.7089 (0.7646)	model_time 0.7087 (0.7551)	loss 3.1115 (2.5676)	grad_norm 2.1855 (2.4528/0.9205)	mem 34604MB
[2025-01-19 21:21:51 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][170/312]	eta 0:01:48 lr 0.000054	time 0.7489 (0.7632)	model_time 0.7487 (0.7543)	loss 2.6086 (2.5610)	grad_norm 4.7537 (2.4671/0.9346)	mem 34604MB
[2025-01-19 21:21:59 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][180/312]	eta 0:01:40 lr 0.000054	time 0.8082 (0.7630)	model_time 0.8080 (0.7545)	loss 2.1342 (2.5632)	grad_norm 2.5166 (2.5067/0.9806)	mem 34604MB
[2025-01-19 21:22:06 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][190/312]	eta 0:01:32 lr 0.000054	time 0.7300 (0.7613)	model_time 0.7298 (0.7532)	loss 2.6864 (2.5641)	grad_norm 1.6851 (2.5958/1.1367)	mem 34604MB
[2025-01-19 21:22:13 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][200/312]	eta 0:01:25 lr 0.000054	time 0.7229 (0.7595)	model_time 0.7227 (0.7518)	loss 2.6611 (2.5646)	grad_norm 4.6102 (2.6533/1.1792)	mem 34604MB
[2025-01-19 21:22:21 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][210/312]	eta 0:01:17 lr 0.000054	time 0.7351 (0.7584)	model_time 0.7349 (0.7511)	loss 2.1984 (2.5630)	grad_norm 1.6675 (2.7047/1.2514)	mem 34604MB
[2025-01-19 21:22:28 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][220/312]	eta 0:01:09 lr 0.000054	time 0.7243 (0.7571)	model_time 0.7241 (0.7501)	loss 2.0818 (2.5648)	grad_norm 3.9176 (2.7416/1.2810)	mem 34604MB
[2025-01-19 21:22:35 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][230/312]	eta 0:01:01 lr 0.000054	time 0.7224 (0.7557)	model_time 0.7221 (0.7489)	loss 1.9378 (2.5622)	grad_norm 1.7535 (2.7148/1.2714)	mem 34604MB
[2025-01-19 21:22:42 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][240/312]	eta 0:00:54 lr 0.000054	time 0.7294 (0.7549)	model_time 0.7290 (0.7485)	loss 2.8402 (2.5652)	grad_norm 2.5457 (2.6928/1.2562)	mem 34604MB
[2025-01-19 21:22:50 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][250/312]	eta 0:00:46 lr 0.000054	time 0.8039 (0.7546)	model_time 0.8037 (0.7484)	loss 1.6782 (2.5744)	grad_norm 4.7284 (2.6961/1.2526)	mem 34604MB
[2025-01-19 21:22:57 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][260/312]	eta 0:00:39 lr 0.000054	time 0.7206 (0.7546)	model_time 0.7205 (0.7486)	loss 3.0591 (2.5685)	grad_norm 2.6147 (2.7210/1.2620)	mem 34604MB
[2025-01-19 21:23:06 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][270/312]	eta 0:00:31 lr 0.000053	time 0.8079 (0.7564)	model_time 0.8073 (0.7506)	loss 2.2310 (2.5703)	grad_norm 1.0198 (2.7173/1.2526)	mem 34604MB
[2025-01-19 21:23:13 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][280/312]	eta 0:00:24 lr 0.000053	time 0.8153 (0.7569)	model_time 0.8148 (0.7513)	loss 2.0527 (2.5635)	grad_norm 2.6354 (2.7226/1.2519)	mem 34604MB
[2025-01-19 21:23:21 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][290/312]	eta 0:00:16 lr 0.000053	time 0.7404 (0.7567)	model_time 0.7403 (0.7512)	loss 2.7781 (2.5594)	grad_norm 2.9029 (2.7090/1.2478)	mem 34604MB
[2025-01-19 21:23:28 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][300/312]	eta 0:00:09 lr 0.000053	time 0.7209 (0.7557)	model_time 0.7208 (0.7505)	loss 2.1552 (2.5523)	grad_norm 1.2053 (2.6911/1.2464)	mem 34604MB
[2025-01-19 21:23:35 internimage_b_1k_224] (main.py 510): INFO Train: [288/300][310/312]	eta 0:00:01 lr 0.000053	time 0.7168 (0.7548)	model_time 0.7167 (0.7497)	loss 1.9486 (2.5559)	grad_norm 1.6905 (2.6896/1.2462)	mem 34604MB
[2025-01-19 21:23:36 internimage_b_1k_224] (main.py 519): INFO EPOCH 288 training takes 0:03:55
[2025-01-19 21:23:36 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_288.pth saving......
[2025-01-19 21:23:39 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_288.pth saved !!!
[2025-01-19 21:23:47 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.338 (7.338)	Loss 0.6894 (0.6894)	Acc@1 86.646 (86.646)	Acc@5 97.974 (97.974)	Mem 34604MB
[2025-01-19 21:23:50 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.961)	Loss 0.8920 (0.7714)	Acc@1 81.128 (84.821)	Acc@5 96.216 (97.097)	Mem 34604MB
[2025-01-19 21:23:50 internimage_b_1k_224] (main.py 575): INFO [Epoch:288] * Acc@1 84.665 Acc@5 97.099
[2025-01-19 21:23:50 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.7%
[2025-01-19 21:23:50 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.70%
[2025-01-19 21:23:59 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.237 (9.237)	Loss 0.7036 (0.7036)	Acc@1 86.841 (86.841)	Acc@5 98.169 (98.169)	Mem 34604MB
[2025-01-19 21:24:04 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.256)	Loss 0.8979 (0.7855)	Acc@1 81.274 (84.861)	Acc@5 96.167 (97.137)	Mem 34604MB
[2025-01-19 21:24:04 internimage_b_1k_224] (main.py 575): INFO [Epoch:288] * Acc@1 84.683 Acc@5 97.153
[2025-01-19 21:24:04 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.7%
[2025-01-19 21:24:04 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 21:24:08 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 21:24:08 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.68%
[2025-01-19 21:24:10 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][0/312]	eta 0:11:26 lr 0.000053	time 2.2007 (2.2007)	model_time 0.7517 (0.7517)	loss 3.1358 (3.1358)	grad_norm 4.4249 (4.4249/0.0000)	mem 34604MB
[2025-01-19 21:24:17 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][10/312]	eta 0:04:20 lr 0.000053	time 0.7205 (0.8616)	model_time 0.7203 (0.7296)	loss 3.0715 (2.7494)	grad_norm 3.8187 (3.5191/1.2880)	mem 34604MB
[2025-01-19 21:24:24 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][20/312]	eta 0:03:53 lr 0.000053	time 0.7243 (0.8011)	model_time 0.7239 (0.7317)	loss 2.0977 (2.5390)	grad_norm 3.2404 (3.0877/1.2014)	mem 34604MB
[2025-01-19 21:24:32 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][30/312]	eta 0:03:39 lr 0.000053	time 0.7624 (0.7792)	model_time 0.7623 (0.7321)	loss 2.8223 (2.5519)	grad_norm 1.9452 (2.8862/1.0859)	mem 34604MB
[2025-01-19 21:24:39 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][40/312]	eta 0:03:28 lr 0.000053	time 0.7156 (0.7672)	model_time 0.7154 (0.7315)	loss 2.8860 (2.5891)	grad_norm 1.8505 (2.7904/1.0999)	mem 34604MB
[2025-01-19 21:24:46 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][50/312]	eta 0:03:19 lr 0.000053	time 0.7300 (0.7616)	model_time 0.7296 (0.7329)	loss 3.0771 (2.5678)	grad_norm 1.7112 (2.7840/1.0590)	mem 34604MB
[2025-01-19 21:24:54 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][60/312]	eta 0:03:12 lr 0.000053	time 0.8045 (0.7632)	model_time 0.8044 (0.7391)	loss 2.7750 (2.5805)	grad_norm 3.0816 (2.6653/1.0633)	mem 34604MB
[2025-01-19 21:25:02 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][70/312]	eta 0:03:04 lr 0.000053	time 0.8048 (0.7615)	model_time 0.8044 (0.7407)	loss 2.3796 (2.5800)	grad_norm 3.1146 (2.7007/1.1266)	mem 34604MB
[2025-01-19 21:25:10 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][80/312]	eta 0:02:57 lr 0.000053	time 0.8089 (0.7663)	model_time 0.8084 (0.7481)	loss 2.2059 (2.5757)	grad_norm 1.6458 (2.6369/1.1045)	mem 34604MB
[2025-01-19 21:25:17 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][90/312]	eta 0:02:50 lr 0.000052	time 0.7267 (0.7664)	model_time 0.7266 (0.7501)	loss 2.9845 (2.5698)	grad_norm 1.5475 (2.6258/1.0887)	mem 34604MB
[2025-01-19 21:25:25 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][100/312]	eta 0:02:42 lr 0.000052	time 0.7129 (0.7642)	model_time 0.7125 (0.7495)	loss 2.3120 (2.5408)	grad_norm 3.1206 (2.6003/1.0652)	mem 34604MB
[2025-01-19 21:25:32 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][110/312]	eta 0:02:34 lr 0.000052	time 0.7220 (0.7627)	model_time 0.7216 (0.7492)	loss 3.2459 (2.5577)	grad_norm 3.3005 (2.6174/1.0441)	mem 34604MB
[2025-01-19 21:25:40 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][120/312]	eta 0:02:25 lr 0.000052	time 0.7163 (0.7603)	model_time 0.7159 (0.7480)	loss 3.0721 (2.5688)	grad_norm 3.7595 (2.6418/1.0346)	mem 34604MB
[2025-01-19 21:25:47 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][130/312]	eta 0:02:17 lr 0.000052	time 0.7345 (0.7580)	model_time 0.7344 (0.7465)	loss 2.7323 (2.5722)	grad_norm 1.9193 (2.6447/1.0370)	mem 34604MB
[2025-01-19 21:25:54 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][140/312]	eta 0:02:10 lr 0.000052	time 0.7245 (0.7562)	model_time 0.7241 (0.7456)	loss 2.9443 (2.5755)	grad_norm 1.4267 (2.5973/1.0264)	mem 34604MB
[2025-01-19 21:26:02 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][150/312]	eta 0:02:02 lr 0.000052	time 0.7255 (0.7542)	model_time 0.7254 (0.7443)	loss 2.8903 (2.5934)	grad_norm 4.9537 (2.6453/1.0883)	mem 34604MB
[2025-01-19 21:26:09 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][160/312]	eta 0:01:54 lr 0.000052	time 0.7215 (0.7526)	model_time 0.7211 (0.7432)	loss 2.5083 (2.5758)	grad_norm 1.6043 (2.6712/1.1237)	mem 34604MB
[2025-01-19 21:26:16 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][170/312]	eta 0:01:46 lr 0.000052	time 0.7304 (0.7517)	model_time 0.7299 (0.7428)	loss 3.1241 (2.5841)	grad_norm 1.4581 (2.6342/1.1110)	mem 34604MB
[2025-01-19 21:26:24 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][180/312]	eta 0:01:39 lr 0.000052	time 0.7155 (0.7520)	model_time 0.7151 (0.7437)	loss 2.4638 (2.5858)	grad_norm 3.0681 (2.6395/1.1026)	mem 34604MB
[2025-01-19 21:26:31 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][190/312]	eta 0:01:31 lr 0.000052	time 0.8050 (0.7521)	model_time 0.8049 (0.7442)	loss 1.7881 (2.5856)	grad_norm 1.8810 (2.6366/1.0843)	mem 34604MB
[2025-01-19 21:26:39 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][200/312]	eta 0:01:24 lr 0.000052	time 0.8398 (0.7538)	model_time 0.8394 (0.7462)	loss 3.0241 (2.5820)	grad_norm 2.2386 (2.6385/1.0760)	mem 34604MB
[2025-01-19 21:26:47 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][210/312]	eta 0:01:16 lr 0.000052	time 0.7243 (0.7548)	model_time 0.7239 (0.7475)	loss 2.4077 (2.5824)	grad_norm 3.1397 (2.6101/1.0682)	mem 34604MB
[2025-01-19 21:26:54 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][220/312]	eta 0:01:09 lr 0.000051	time 0.7224 (0.7542)	model_time 0.7222 (0.7473)	loss 3.0979 (2.5805)	grad_norm 1.9318 (2.5843/1.0551)	mem 34604MB
[2025-01-19 21:27:02 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][230/312]	eta 0:01:01 lr 0.000051	time 0.7228 (0.7538)	model_time 0.7227 (0.7471)	loss 2.7455 (2.5817)	grad_norm 3.2451 (2.5887/1.0408)	mem 34604MB
[2025-01-19 21:27:09 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][240/312]	eta 0:00:54 lr 0.000051	time 0.7210 (0.7528)	model_time 0.7206 (0.7464)	loss 2.0168 (2.5797)	grad_norm 2.6103 (2.5786/1.0401)	mem 34604MB
[2025-01-19 21:27:16 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][250/312]	eta 0:00:46 lr 0.000051	time 0.7196 (0.7518)	model_time 0.7191 (0.7457)	loss 2.9421 (2.5742)	grad_norm 2.7808 (2.5701/1.0338)	mem 34604MB
[2025-01-19 21:27:24 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][260/312]	eta 0:00:39 lr 0.000051	time 0.7439 (0.7513)	model_time 0.7437 (0.7454)	loss 2.3960 (2.5697)	grad_norm 1.9759 (2.5653/1.0225)	mem 34604MB
[2025-01-19 21:27:31 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][270/312]	eta 0:00:31 lr 0.000051	time 0.7276 (0.7504)	model_time 0.7272 (0.7447)	loss 3.2182 (2.5719)	grad_norm 1.3895 (2.5613/1.0248)	mem 34604MB
[2025-01-19 21:27:38 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][280/312]	eta 0:00:23 lr 0.000051	time 0.7175 (0.7495)	model_time 0.7171 (0.7440)	loss 2.8399 (2.5741)	grad_norm 2.3377 (2.5631/1.0135)	mem 34604MB
[2025-01-19 21:27:46 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][290/312]	eta 0:00:16 lr 0.000051	time 0.7175 (0.7490)	model_time 0.7171 (0.7437)	loss 2.2446 (2.5701)	grad_norm 2.7174 (2.5473/1.0040)	mem 34604MB
[2025-01-19 21:27:53 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][300/312]	eta 0:00:08 lr 0.000051	time 0.7143 (0.7493)	model_time 0.7142 (0.7441)	loss 2.7779 (2.5714)	grad_norm 4.0514 (2.5505/0.9956)	mem 34604MB
[2025-01-19 21:28:01 internimage_b_1k_224] (main.py 510): INFO Train: [289/300][310/312]	eta 0:00:01 lr 0.000051	time 0.7146 (0.7487)	model_time 0.7145 (0.7437)	loss 2.4784 (2.5638)	grad_norm 2.0594 (2.5208/0.9868)	mem 34604MB
[2025-01-19 21:28:01 internimage_b_1k_224] (main.py 519): INFO EPOCH 289 training takes 0:03:53
[2025-01-19 21:28:01 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_289.pth saving......
[2025-01-19 21:28:04 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_289.pth saved !!!
[2025-01-19 21:28:12 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.416 (7.416)	Loss 0.6841 (0.6841)	Acc@1 86.841 (86.841)	Acc@5 98.022 (98.022)	Mem 34604MB
[2025-01-19 21:28:15 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.943)	Loss 0.8833 (0.7659)	Acc@1 81.177 (84.817)	Acc@5 96.045 (97.059)	Mem 34604MB
[2025-01-19 21:28:15 internimage_b_1k_224] (main.py 575): INFO [Epoch:289] * Acc@1 84.645 Acc@5 97.061
[2025-01-19 21:28:15 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.6%
[2025-01-19 21:28:15 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.70%
[2025-01-19 21:28:24 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.228 (9.228)	Loss 0.7032 (0.7032)	Acc@1 86.816 (86.816)	Acc@5 98.169 (98.169)	Mem 34604MB
[2025-01-19 21:28:29 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.248)	Loss 0.8975 (0.7850)	Acc@1 81.348 (84.861)	Acc@5 96.167 (97.139)	Mem 34604MB
[2025-01-19 21:28:29 internimage_b_1k_224] (main.py 575): INFO [Epoch:289] * Acc@1 84.683 Acc@5 97.153
[2025-01-19 21:28:29 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.7%
[2025-01-19 21:28:29 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.68%
[2025-01-19 21:28:32 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][0/312]	eta 0:17:04 lr 0.000051	time 3.2845 (3.2845)	model_time 1.8452 (1.8452)	loss 1.9649 (1.9649)	grad_norm 2.3380 (2.3380/0.0000)	mem 34604MB
[2025-01-19 21:28:40 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][10/312]	eta 0:05:05 lr 0.000051	time 0.7138 (1.0126)	model_time 0.7134 (0.8815)	loss 2.9102 (2.3309)	grad_norm 2.3172 (2.3649/0.9639)	mem 34604MB
[2025-01-19 21:28:48 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][20/312]	eta 0:04:23 lr 0.000051	time 0.7238 (0.9008)	model_time 0.7237 (0.8320)	loss 2.7948 (2.4667)	grad_norm 2.5916 (2.1904/0.7975)	mem 34604MB
[2025-01-19 21:28:55 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][30/312]	eta 0:03:58 lr 0.000051	time 0.7284 (0.8472)	model_time 0.7282 (0.8004)	loss 2.4357 (2.4815)	grad_norm 3.3925 (2.1026/0.7611)	mem 34604MB
[2025-01-19 21:29:03 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][40/312]	eta 0:03:44 lr 0.000051	time 0.7120 (0.8247)	model_time 0.7115 (0.7893)	loss 2.9246 (2.4897)	grad_norm 1.7943 (2.2286/0.7385)	mem 34604MB
[2025-01-19 21:29:10 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][50/312]	eta 0:03:31 lr 0.000051	time 0.7390 (0.8064)	model_time 0.7386 (0.7778)	loss 2.7338 (2.4887)	grad_norm 3.9577 (2.2744/0.7854)	mem 34604MB
[2025-01-19 21:29:18 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][60/312]	eta 0:03:19 lr 0.000050	time 0.7427 (0.7935)	model_time 0.7425 (0.7695)	loss 1.4457 (2.5099)	grad_norm 2.3596 (2.2557/0.7499)	mem 34604MB
[2025-01-19 21:29:25 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][70/312]	eta 0:03:10 lr 0.000050	time 0.7187 (0.7859)	model_time 0.7185 (0.7653)	loss 2.6990 (2.5278)	grad_norm 1.6487 (2.2931/0.7918)	mem 34604MB
[2025-01-19 21:29:32 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][80/312]	eta 0:03:00 lr 0.000050	time 0.7327 (0.7791)	model_time 0.7322 (0.7610)	loss 2.9015 (2.5407)	grad_norm 2.3897 (2.3563/0.8387)	mem 34604MB
[2025-01-19 21:29:39 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][90/312]	eta 0:02:51 lr 0.000050	time 0.7212 (0.7734)	model_time 0.7208 (0.7573)	loss 2.4444 (2.5487)	grad_norm 2.1980 (2.4357/0.9047)	mem 34604MB
[2025-01-19 21:29:47 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][100/312]	eta 0:02:43 lr 0.000050	time 0.7314 (0.7697)	model_time 0.7313 (0.7551)	loss 2.9434 (2.5547)	grad_norm 1.2337 (2.4750/0.9481)	mem 34604MB
[2025-01-19 21:29:54 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][110/312]	eta 0:02:35 lr 0.000050	time 0.7197 (0.7691)	model_time 0.7193 (0.7558)	loss 3.0967 (2.5598)	grad_norm 4.1879 (2.5065/0.9927)	mem 34604MB
[2025-01-19 21:30:02 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][120/312]	eta 0:02:27 lr 0.000050	time 0.8080 (0.7676)	model_time 0.8076 (0.7554)	loss 2.7258 (2.5496)	grad_norm 3.8376 (2.5395/1.0244)	mem 34604MB
[2025-01-19 21:30:10 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][130/312]	eta 0:02:19 lr 0.000050	time 0.7192 (0.7682)	model_time 0.7187 (0.7569)	loss 1.8726 (2.5508)	grad_norm 2.6999 (2.6217/1.0911)	mem 34604MB
[2025-01-19 21:30:18 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][140/312]	eta 0:02:12 lr 0.000050	time 0.7148 (0.7689)	model_time 0.7147 (0.7584)	loss 2.7083 (2.5582)	grad_norm 2.1057 (2.6401/1.0768)	mem 34604MB
[2025-01-19 21:30:25 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][150/312]	eta 0:02:04 lr 0.000050	time 0.7194 (0.7662)	model_time 0.7192 (0.7563)	loss 2.7372 (2.5548)	grad_norm 1.4539 (2.6210/1.0859)	mem 34604MB
[2025-01-19 21:30:32 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][160/312]	eta 0:01:56 lr 0.000050	time 0.7254 (0.7653)	model_time 0.7252 (0.7559)	loss 2.0384 (2.5633)	grad_norm 4.2357 (2.6646/1.0975)	mem 34604MB
[2025-01-19 21:30:40 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][170/312]	eta 0:01:48 lr 0.000050	time 0.7216 (0.7629)	model_time 0.7211 (0.7541)	loss 2.9251 (2.5755)	grad_norm 1.1219 (2.6462/1.0782)	mem 34604MB
[2025-01-19 21:30:47 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][180/312]	eta 0:01:40 lr 0.000050	time 0.7213 (0.7610)	model_time 0.7212 (0.7527)	loss 2.2509 (2.5609)	grad_norm 1.5461 (2.6142/1.0620)	mem 34604MB
[2025-01-19 21:30:54 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][190/312]	eta 0:01:32 lr 0.000050	time 0.7178 (0.7591)	model_time 0.7176 (0.7512)	loss 3.3185 (2.5697)	grad_norm 2.5248 (2.5813/1.0490)	mem 34604MB
[2025-01-19 21:31:01 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][200/312]	eta 0:01:24 lr 0.000050	time 0.7235 (0.7581)	model_time 0.7231 (0.7506)	loss 2.3176 (2.5671)	grad_norm 2.7002 (2.5613/1.0417)	mem 34604MB
[2025-01-19 21:31:09 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][210/312]	eta 0:01:17 lr 0.000049	time 0.7228 (0.7567)	model_time 0.7223 (0.7495)	loss 2.7453 (2.5663)	grad_norm 1.8332 (2.5463/1.0295)	mem 34604MB
[2025-01-19 21:31:16 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][220/312]	eta 0:01:09 lr 0.000049	time 0.7474 (0.7559)	model_time 0.7472 (0.7490)	loss 2.1005 (2.5682)	grad_norm 2.5902 (2.5222/1.0206)	mem 34604MB
[2025-01-19 21:31:24 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][230/312]	eta 0:01:02 lr 0.000049	time 0.7178 (0.7570)	model_time 0.7176 (0.7504)	loss 2.0733 (2.5704)	grad_norm 1.2243 (2.5174/1.0130)	mem 34604MB
[2025-01-19 21:31:31 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][240/312]	eta 0:00:54 lr 0.000049	time 0.8105 (0.7566)	model_time 0.8100 (0.7503)	loss 2.4328 (2.5688)	grad_norm 2.8286 (2.5054/0.9982)	mem 34604MB
[2025-01-19 21:31:39 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][250/312]	eta 0:00:46 lr 0.000049	time 0.8397 (0.7577)	model_time 0.8393 (0.7516)	loss 3.0533 (2.5709)	grad_norm 3.3073 (2.5053/0.9899)	mem 34604MB
[2025-01-19 21:31:47 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][260/312]	eta 0:00:39 lr 0.000049	time 0.8341 (0.7590)	model_time 0.8336 (0.7531)	loss 2.5872 (2.5754)	grad_norm 2.6250 (2.5199/1.0000)	mem 34604MB
[2025-01-19 21:31:55 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][270/312]	eta 0:00:31 lr 0.000049	time 0.7298 (0.7579)	model_time 0.7296 (0.7522)	loss 2.6189 (2.5704)	grad_norm 1.6788 (2.5349/1.0198)	mem 34604MB
[2025-01-19 21:32:02 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][280/312]	eta 0:00:24 lr 0.000049	time 0.7185 (0.7582)	model_time 0.7181 (0.7527)	loss 2.4744 (2.5799)	grad_norm 2.7706 (2.5233/1.0066)	mem 34604MB
[2025-01-19 21:32:09 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][290/312]	eta 0:00:16 lr 0.000049	time 0.7255 (0.7571)	model_time 0.7251 (0.7518)	loss 2.3146 (2.5812)	grad_norm 2.1633 (2.5304/0.9959)	mem 34604MB
[2025-01-19 21:32:17 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][300/312]	eta 0:00:09 lr 0.000049	time 0.7155 (0.7560)	model_time 0.7154 (0.7509)	loss 2.9993 (2.5805)	grad_norm 2.2287 (2.5236/0.9928)	mem 34604MB
[2025-01-19 21:32:24 internimage_b_1k_224] (main.py 510): INFO Train: [290/300][310/312]	eta 0:00:01 lr 0.000049	time 0.7152 (0.7547)	model_time 0.7151 (0.7497)	loss 2.9607 (2.5879)	grad_norm 2.3305 (2.5317/0.9907)	mem 34604MB
[2025-01-19 21:32:25 internimage_b_1k_224] (main.py 519): INFO EPOCH 290 training takes 0:03:55
[2025-01-19 21:32:25 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_290.pth saving......
[2025-01-19 21:32:28 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_290.pth saved !!!
[2025-01-19 21:32:35 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.302 (7.302)	Loss 0.6815 (0.6815)	Acc@1 86.743 (86.743)	Acc@5 98.096 (98.096)	Mem 34604MB
[2025-01-19 21:32:38 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.938)	Loss 0.8843 (0.7664)	Acc@1 81.177 (84.801)	Acc@5 95.996 (97.044)	Mem 34604MB
[2025-01-19 21:32:38 internimage_b_1k_224] (main.py 575): INFO [Epoch:290] * Acc@1 84.653 Acc@5 97.039
[2025-01-19 21:32:38 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.7%
[2025-01-19 21:32:38 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.70%
[2025-01-19 21:32:47 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.022 (9.022)	Loss 0.7028 (0.7028)	Acc@1 86.816 (86.816)	Acc@5 98.169 (98.169)	Mem 34604MB
[2025-01-19 21:32:52 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.239)	Loss 0.8970 (0.7845)	Acc@1 81.323 (84.859)	Acc@5 96.167 (97.132)	Mem 34604MB
[2025-01-19 21:32:52 internimage_b_1k_224] (main.py 575): INFO [Epoch:290] * Acc@1 84.687 Acc@5 97.143
[2025-01-19 21:32:52 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.7%
[2025-01-19 21:32:52 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 21:32:56 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 21:32:56 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.69%
[2025-01-19 21:32:58 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][0/312]	eta 0:10:03 lr 0.000049	time 1.9335 (1.9335)	model_time 0.7306 (0.7306)	loss 2.5836 (2.5836)	grad_norm 1.3377 (1.3377/0.0000)	mem 34604MB
[2025-01-19 21:33:05 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][10/312]	eta 0:04:13 lr 0.000049	time 0.7214 (0.8389)	model_time 0.7210 (0.7292)	loss 2.8398 (2.5662)	grad_norm 2.8048 (2.4158/0.8200)	mem 34604MB
[2025-01-19 21:33:12 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][20/312]	eta 0:03:49 lr 0.000049	time 0.7183 (0.7876)	model_time 0.7181 (0.7300)	loss 3.0581 (2.7193)	grad_norm 3.2130 (2.8002/1.0269)	mem 34604MB
[2025-01-19 21:33:20 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][30/312]	eta 0:03:37 lr 0.000049	time 0.7618 (0.7721)	model_time 0.7613 (0.7329)	loss 3.0328 (2.6556)	grad_norm 2.5208 (2.6165/1.0922)	mem 34604MB
[2025-01-19 21:33:27 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][40/312]	eta 0:03:29 lr 0.000049	time 0.7241 (0.7700)	model_time 0.7240 (0.7403)	loss 2.3098 (2.6407)	grad_norm 1.5937 (2.6056/1.0583)	mem 34604MB
[2025-01-19 21:33:35 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][50/312]	eta 0:03:21 lr 0.000048	time 0.7237 (0.7689)	model_time 0.7232 (0.7449)	loss 2.7774 (2.6387)	grad_norm 2.6765 (2.7901/1.1272)	mem 34604MB
[2025-01-19 21:33:43 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][60/312]	eta 0:03:14 lr 0.000048	time 0.7294 (0.7737)	model_time 0.7293 (0.7536)	loss 2.7305 (2.6175)	grad_norm 1.2786 (2.6770/1.1033)	mem 34604MB
[2025-01-19 21:33:51 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][70/312]	eta 0:03:06 lr 0.000048	time 0.8236 (0.7712)	model_time 0.8234 (0.7539)	loss 2.5342 (2.5927)	grad_norm 1.1844 (2.6288/1.0942)	mem 34604MB
[2025-01-19 21:33:58 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][80/312]	eta 0:02:57 lr 0.000048	time 0.7219 (0.7665)	model_time 0.7218 (0.7513)	loss 3.2513 (2.5961)	grad_norm 1.7109 (2.6187/1.0399)	mem 34604MB
[2025-01-19 21:34:05 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][90/312]	eta 0:02:49 lr 0.000048	time 0.8777 (0.7648)	model_time 0.8773 (0.7513)	loss 1.9035 (2.5989)	grad_norm 5.0231 (2.7501/1.1641)	mem 34604MB
[2025-01-19 21:34:13 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][100/312]	eta 0:02:41 lr 0.000048	time 0.7237 (0.7616)	model_time 0.7236 (0.7493)	loss 3.0894 (2.5925)	grad_norm 2.3706 (2.7687/1.1629)	mem 34604MB
[2025-01-19 21:34:20 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][110/312]	eta 0:02:33 lr 0.000048	time 0.7311 (0.7587)	model_time 0.7306 (0.7475)	loss 2.8570 (2.6083)	grad_norm 1.4251 (2.7453/1.1385)	mem 34604MB
[2025-01-19 21:34:27 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][120/312]	eta 0:02:25 lr 0.000048	time 0.7188 (0.7567)	model_time 0.7186 (0.7464)	loss 1.9543 (2.6197)	grad_norm 3.8203 (2.7443/1.1199)	mem 34604MB
[2025-01-19 21:34:35 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][130/312]	eta 0:02:17 lr 0.000048	time 0.7306 (0.7553)	model_time 0.7302 (0.7458)	loss 1.7175 (2.5998)	grad_norm 1.9034 (2.7821/1.1282)	mem 34604MB
[2025-01-19 21:34:42 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][140/312]	eta 0:02:09 lr 0.000048	time 0.7477 (0.7532)	model_time 0.7473 (0.7443)	loss 2.9848 (2.6126)	grad_norm 1.8464 (2.8301/1.1686)	mem 34604MB
[2025-01-19 21:34:49 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][150/312]	eta 0:02:01 lr 0.000048	time 0.7225 (0.7523)	model_time 0.7221 (0.7439)	loss 2.6830 (2.6151)	grad_norm 1.8864 (2.8011/1.1673)	mem 34604MB
[2025-01-19 21:34:57 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][160/312]	eta 0:01:54 lr 0.000048	time 0.7294 (0.7528)	model_time 0.7293 (0.7449)	loss 2.5327 (2.6212)	grad_norm 1.4436 (2.7581/1.1572)	mem 34604MB
[2025-01-19 21:35:05 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][170/312]	eta 0:01:47 lr 0.000048	time 0.7132 (0.7544)	model_time 0.7128 (0.7470)	loss 2.4675 (2.6180)	grad_norm 2.2528 (2.7291/1.1327)	mem 34604MB
[2025-01-19 21:35:13 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][180/312]	eta 0:01:39 lr 0.000048	time 0.7374 (0.7551)	model_time 0.7369 (0.7481)	loss 3.3164 (2.6143)	grad_norm 4.0646 (2.7324/1.1128)	mem 34604MB
[2025-01-19 21:35:21 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][190/312]	eta 0:01:32 lr 0.000048	time 0.8054 (0.7581)	model_time 0.8053 (0.7514)	loss 3.0937 (2.6157)	grad_norm 1.2342 (2.6966/1.1039)	mem 34604MB
[2025-01-19 21:35:28 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][200/312]	eta 0:01:24 lr 0.000048	time 0.7081 (0.7575)	model_time 0.7076 (0.7511)	loss 1.6289 (2.6168)	grad_norm 1.9417 (2.6517/1.1012)	mem 34604MB
[2025-01-19 21:35:36 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][210/312]	eta 0:01:17 lr 0.000048	time 0.8096 (0.7567)	model_time 0.8095 (0.7507)	loss 1.8728 (2.6152)	grad_norm 1.5860 (2.6466/1.1074)	mem 34604MB
[2025-01-19 21:35:43 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][220/312]	eta 0:01:09 lr 0.000047	time 0.7190 (0.7555)	model_time 0.7186 (0.7497)	loss 2.3292 (2.6191)	grad_norm 1.3738 (2.6188/1.0969)	mem 34604MB
[2025-01-19 21:35:50 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][230/312]	eta 0:01:01 lr 0.000047	time 0.7337 (0.7544)	model_time 0.7336 (0.7488)	loss 3.0318 (2.6223)	grad_norm 1.8264 (2.5992/1.0813)	mem 34604MB
[2025-01-19 21:35:57 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][240/312]	eta 0:00:54 lr 0.000047	time 0.7160 (0.7535)	model_time 0.7158 (0.7481)	loss 2.7812 (2.6217)	grad_norm 2.7317 (2.6050/1.0758)	mem 34604MB
[2025-01-19 21:36:05 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][250/312]	eta 0:00:46 lr 0.000047	time 0.7206 (0.7527)	model_time 0.7201 (0.7475)	loss 2.5591 (2.6175)	grad_norm 1.2621 (2.6249/1.0837)	mem 34604MB
[2025-01-19 21:36:12 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][260/312]	eta 0:00:39 lr 0.000047	time 0.7234 (0.7517)	model_time 0.7233 (0.7467)	loss 2.0915 (2.6078)	grad_norm 1.0912 (2.6419/1.0916)	mem 34604MB
[2025-01-19 21:36:19 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][270/312]	eta 0:00:31 lr 0.000047	time 0.7157 (0.7511)	model_time 0.7156 (0.7463)	loss 1.8407 (2.6021)	grad_norm 1.7356 (2.6548/1.0987)	mem 34604MB
[2025-01-19 21:36:27 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][280/312]	eta 0:00:24 lr 0.000047	time 0.8020 (0.7512)	model_time 0.8016 (0.7466)	loss 1.9632 (2.6072)	grad_norm 1.3845 (2.6556/1.1042)	mem 34604MB
[2025-01-19 21:36:35 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][290/312]	eta 0:00:16 lr 0.000047	time 0.7170 (0.7517)	model_time 0.7169 (0.7472)	loss 2.7286 (2.6106)	grad_norm 3.9950 (2.7008/1.1454)	mem 34604MB
[2025-01-19 21:36:42 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][300/312]	eta 0:00:09 lr 0.000047	time 0.7131 (0.7527)	model_time 0.7130 (0.7484)	loss 1.8441 (2.6056)	grad_norm 2.4647 (2.6949/1.1437)	mem 34604MB
[2025-01-19 21:36:50 internimage_b_1k_224] (main.py 510): INFO Train: [291/300][310/312]	eta 0:00:01 lr 0.000047	time 0.7116 (0.7537)	model_time 0.7115 (0.7495)	loss 2.1092 (2.6035)	grad_norm 1.6065 (2.6867/1.1739)	mem 34604MB
[2025-01-19 21:36:51 internimage_b_1k_224] (main.py 519): INFO EPOCH 291 training takes 0:03:55
[2025-01-19 21:36:51 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_291.pth saving......
[2025-01-19 21:36:54 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_291.pth saved !!!
[2025-01-19 21:37:02 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.160 (7.160)	Loss 0.6876 (0.6876)	Acc@1 86.743 (86.743)	Acc@5 98.047 (98.047)	Mem 34604MB
[2025-01-19 21:37:05 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.937)	Loss 0.8851 (0.7693)	Acc@1 81.421 (84.859)	Acc@5 96.118 (97.044)	Mem 34604MB
[2025-01-19 21:37:05 internimage_b_1k_224] (main.py 575): INFO [Epoch:291] * Acc@1 84.681 Acc@5 97.055
[2025-01-19 21:37:05 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.7%
[2025-01-19 21:37:05 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.70%
[2025-01-19 21:37:14 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.193 (9.193)	Loss 0.7026 (0.7026)	Acc@1 86.865 (86.865)	Acc@5 98.169 (98.169)	Mem 34604MB
[2025-01-19 21:37:19 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.246)	Loss 0.8964 (0.7840)	Acc@1 81.299 (84.859)	Acc@5 96.167 (97.126)	Mem 34604MB
[2025-01-19 21:37:19 internimage_b_1k_224] (main.py 575): INFO [Epoch:291] * Acc@1 84.687 Acc@5 97.135
[2025-01-19 21:37:19 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.7%
[2025-01-19 21:37:19 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.69%
[2025-01-19 21:37:23 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][0/312]	eta 0:19:01 lr 0.000047	time 3.6579 (3.6579)	model_time 1.4920 (1.4920)	loss 2.7904 (2.7904)	grad_norm 1.3330 (1.3330/0.0000)	mem 34604MB
[2025-01-19 21:37:30 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][10/312]	eta 0:05:10 lr 0.000047	time 0.8140 (1.0288)	model_time 0.8136 (0.8305)	loss 2.1101 (2.4371)	grad_norm 1.4963 (2.4343/0.7780)	mem 34604MB
[2025-01-19 21:37:38 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][20/312]	eta 0:04:20 lr 0.000047	time 0.7289 (0.8927)	model_time 0.7285 (0.7886)	loss 1.7642 (2.4512)	grad_norm 2.4093 (2.3665/0.8116)	mem 34604MB
[2025-01-19 21:37:45 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][30/312]	eta 0:03:57 lr 0.000047	time 0.7248 (0.8438)	model_time 0.7246 (0.7732)	loss 2.9051 (2.5094)	grad_norm 1.5914 (2.2795/0.8293)	mem 34604MB
[2025-01-19 21:37:52 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][40/312]	eta 0:03:41 lr 0.000047	time 0.7632 (0.8154)	model_time 0.7631 (0.7619)	loss 3.0054 (2.5328)	grad_norm 2.8024 (2.2200/0.7698)	mem 34604MB
[2025-01-19 21:38:00 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][50/312]	eta 0:03:29 lr 0.000047	time 0.7337 (0.7980)	model_time 0.7334 (0.7550)	loss 2.8631 (2.5517)	grad_norm 1.1061 (2.1690/0.7870)	mem 34604MB
[2025-01-19 21:38:07 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][60/312]	eta 0:03:18 lr 0.000047	time 0.7366 (0.7877)	model_time 0.7364 (0.7516)	loss 2.7706 (2.5566)	grad_norm 1.6613 (2.1816/0.8934)	mem 34604MB
[2025-01-19 21:38:14 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][70/312]	eta 0:03:08 lr 0.000047	time 0.7538 (0.7792)	model_time 0.7533 (0.7482)	loss 1.6431 (2.5363)	grad_norm 2.1454 (2.2254/0.8727)	mem 34604MB
[2025-01-19 21:38:22 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][80/312]	eta 0:02:59 lr 0.000047	time 0.7427 (0.7738)	model_time 0.7423 (0.7465)	loss 1.8391 (2.5507)	grad_norm 2.3357 (2.2998/0.8521)	mem 34604MB
[2025-01-19 21:38:29 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][90/312]	eta 0:02:51 lr 0.000046	time 0.7283 (0.7720)	model_time 0.7282 (0.7477)	loss 2.6479 (2.5690)	grad_norm 2.3058 (2.2957/0.8551)	mem 34604MB
[2025-01-19 21:38:37 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][100/312]	eta 0:02:43 lr 0.000046	time 0.8078 (0.7723)	model_time 0.8073 (0.7504)	loss 2.9419 (2.5707)	grad_norm 1.9457 (2.2944/0.8507)	mem 34604MB
[2025-01-19 21:38:45 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][110/312]	eta 0:02:35 lr 0.000046	time 0.8246 (0.7721)	model_time 0.8242 (0.7521)	loss 1.8155 (2.5766)	grad_norm 1.6896 (2.3294/0.8777)	mem 34604MB
[2025-01-19 21:38:52 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][120/312]	eta 0:02:28 lr 0.000046	time 0.9098 (0.7725)	model_time 0.9093 (0.7541)	loss 2.9306 (2.5858)	grad_norm 1.2450 (2.4169/1.0309)	mem 34604MB
[2025-01-19 21:39:00 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][130/312]	eta 0:02:20 lr 0.000046	time 0.8125 (0.7704)	model_time 0.8124 (0.7534)	loss 2.3639 (2.5716)	grad_norm 1.4812 (2.4101/1.0086)	mem 34604MB
[2025-01-19 21:39:07 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][140/312]	eta 0:02:12 lr 0.000046	time 0.7181 (0.7678)	model_time 0.7177 (0.7520)	loss 2.4462 (2.5680)	grad_norm 1.0314 (2.3877/0.9896)	mem 34604MB
[2025-01-19 21:39:14 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][150/312]	eta 0:02:04 lr 0.000046	time 0.7224 (0.7656)	model_time 0.7220 (0.7508)	loss 2.8817 (2.5848)	grad_norm 1.3643 (2.3679/0.9904)	mem 34604MB
[2025-01-19 21:39:22 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][160/312]	eta 0:01:56 lr 0.000046	time 0.7469 (0.7637)	model_time 0.7464 (0.7498)	loss 2.7514 (2.5893)	grad_norm 2.4023 (2.3698/1.0045)	mem 34604MB
[2025-01-19 21:39:29 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][170/312]	eta 0:01:48 lr 0.000046	time 0.7252 (0.7614)	model_time 0.7251 (0.7483)	loss 1.6012 (2.5731)	grad_norm 1.6907 (2.3986/1.0301)	mem 34604MB
[2025-01-19 21:39:36 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][180/312]	eta 0:01:40 lr 0.000046	time 0.7225 (0.7599)	model_time 0.7220 (0.7475)	loss 2.8472 (2.5807)	grad_norm 2.1226 (2.4079/1.0288)	mem 34604MB
[2025-01-19 21:39:44 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][190/312]	eta 0:01:32 lr 0.000046	time 0.7195 (0.7583)	model_time 0.7193 (0.7465)	loss 2.6892 (2.5804)	grad_norm 2.3364 (2.4124/1.0176)	mem 34604MB
[2025-01-19 21:39:51 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][200/312]	eta 0:01:24 lr 0.000046	time 0.7132 (0.7571)	model_time 0.7130 (0.7459)	loss 2.6448 (2.5770)	grad_norm 1.6857 (2.4172/1.0101)	mem 34604MB
[2025-01-19 21:39:59 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][210/312]	eta 0:01:17 lr 0.000046	time 0.7464 (0.7576)	model_time 0.7463 (0.7469)	loss 2.1822 (2.5756)	grad_norm 2.1538 (2.4146/0.9959)	mem 34604MB
[2025-01-19 21:40:06 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][220/312]	eta 0:01:09 lr 0.000046	time 0.8089 (0.7583)	model_time 0.8085 (0.7481)	loss 2.3221 (2.5614)	grad_norm 6.5370 (2.4193/1.0201)	mem 34604MB
[2025-01-19 21:40:14 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][230/312]	eta 0:01:02 lr 0.000046	time 0.8302 (0.7589)	model_time 0.8301 (0.7491)	loss 3.0682 (2.5684)	grad_norm 1.8906 (2.4024/1.0089)	mem 34604MB
[2025-01-19 21:40:22 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][240/312]	eta 0:00:54 lr 0.000046	time 0.8157 (0.7596)	model_time 0.8156 (0.7502)	loss 2.9946 (2.5680)	grad_norm 1.8840 (2.4343/1.0413)	mem 34604MB
[2025-01-19 21:40:30 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][250/312]	eta 0:00:47 lr 0.000046	time 0.8149 (0.7596)	model_time 0.8148 (0.7506)	loss 2.7535 (2.5634)	grad_norm 1.7510 (2.4222/1.0426)	mem 34604MB
[2025-01-19 21:40:37 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][260/312]	eta 0:00:39 lr 0.000046	time 0.7373 (0.7589)	model_time 0.7371 (0.7502)	loss 2.7249 (2.5551)	grad_norm 3.4491 (2.4424/1.0537)	mem 34604MB
[2025-01-19 21:40:44 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][270/312]	eta 0:00:31 lr 0.000046	time 0.7295 (0.7579)	model_time 0.7291 (0.7495)	loss 2.8323 (2.5522)	grad_norm 1.3099 (2.4369/1.0454)	mem 34604MB
[2025-01-19 21:40:52 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][280/312]	eta 0:00:24 lr 0.000045	time 0.7308 (0.7569)	model_time 0.7306 (0.7488)	loss 2.1203 (2.5584)	grad_norm 4.2994 (2.4397/1.0444)	mem 34604MB
[2025-01-19 21:40:59 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][290/312]	eta 0:00:16 lr 0.000045	time 0.7210 (0.7561)	model_time 0.7208 (0.7483)	loss 3.2070 (2.5691)	grad_norm 1.5495 (2.4361/1.0367)	mem 34604MB
[2025-01-19 21:41:06 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][300/312]	eta 0:00:09 lr 0.000045	time 0.7160 (0.7553)	model_time 0.7159 (0.7477)	loss 2.7505 (2.5756)	grad_norm 2.8813 (2.4822/1.1287)	mem 34604MB
[2025-01-19 21:41:13 internimage_b_1k_224] (main.py 510): INFO Train: [292/300][310/312]	eta 0:00:01 lr 0.000045	time 0.7188 (0.7541)	model_time 0.7186 (0.7468)	loss 3.0557 (2.5816)	grad_norm 1.8636 (2.4904/1.1424)	mem 34604MB
[2025-01-19 21:41:14 internimage_b_1k_224] (main.py 519): INFO EPOCH 292 training takes 0:03:55
[2025-01-19 21:41:14 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_292.pth saving......
[2025-01-19 21:41:17 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_292.pth saved !!!
[2025-01-19 21:41:25 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.095 (7.095)	Loss 0.6889 (0.6889)	Acc@1 86.743 (86.743)	Acc@5 98.096 (98.096)	Mem 34604MB
[2025-01-19 21:41:28 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.914)	Loss 0.8808 (0.7647)	Acc@1 81.348 (84.883)	Acc@5 95.972 (97.044)	Mem 34604MB
[2025-01-19 21:41:28 internimage_b_1k_224] (main.py 575): INFO [Epoch:292] * Acc@1 84.717 Acc@5 97.055
[2025-01-19 21:41:28 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.7%
[2025-01-19 21:41:28 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 21:41:31 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 21:41:31 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.72%
[2025-01-19 21:41:39 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.388 (7.388)	Loss 0.7023 (0.7023)	Acc@1 86.890 (86.890)	Acc@5 98.193 (98.193)	Mem 34604MB
[2025-01-19 21:41:42 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.933)	Loss 0.8960 (0.7836)	Acc@1 81.299 (84.872)	Acc@5 96.167 (97.124)	Mem 34604MB
[2025-01-19 21:41:42 internimage_b_1k_224] (main.py 575): INFO [Epoch:292] * Acc@1 84.699 Acc@5 97.133
[2025-01-19 21:41:42 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.7%
[2025-01-19 21:41:42 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 21:41:46 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 21:41:46 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.70%
[2025-01-19 21:41:48 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][0/312]	eta 0:11:13 lr 0.000045	time 2.1588 (2.1588)	model_time 0.7253 (0.7253)	loss 1.9179 (1.9179)	grad_norm 2.4743 (2.4743/0.0000)	mem 34604MB
[2025-01-19 21:41:55 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][10/312]	eta 0:04:21 lr 0.000045	time 0.7258 (0.8655)	model_time 0.7256 (0.7350)	loss 2.8503 (2.4880)	grad_norm 1.7246 (2.1784/0.6012)	mem 34604MB
[2025-01-19 21:42:03 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][20/312]	eta 0:04:00 lr 0.000045	time 0.7188 (0.8231)	model_time 0.7184 (0.7546)	loss 2.8885 (2.5884)	grad_norm 3.2771 (2.6497/0.9486)	mem 34604MB
[2025-01-19 21:42:11 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][30/312]	eta 0:03:47 lr 0.000045	time 0.7235 (0.8072)	model_time 0.7233 (0.7606)	loss 2.9194 (2.6668)	grad_norm 1.3809 (2.6261/1.0369)	mem 34604MB
[2025-01-19 21:42:19 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][40/312]	eta 0:03:39 lr 0.000045	time 0.9991 (0.8061)	model_time 0.9989 (0.7708)	loss 2.9389 (2.6691)	grad_norm 3.1979 (2.7572/1.0733)	mem 34604MB
[2025-01-19 21:42:27 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][50/312]	eta 0:03:30 lr 0.000045	time 0.7083 (0.8025)	model_time 0.7082 (0.7741)	loss 1.9145 (2.6174)	grad_norm 1.4696 (2.6377/1.0459)	mem 34604MB
[2025-01-19 21:42:34 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][60/312]	eta 0:03:19 lr 0.000045	time 0.7324 (0.7925)	model_time 0.7319 (0.7687)	loss 2.5426 (2.6208)	grad_norm 3.6471 (2.7381/1.1033)	mem 34604MB
[2025-01-19 21:42:41 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][70/312]	eta 0:03:09 lr 0.000045	time 0.7195 (0.7847)	model_time 0.7193 (0.7642)	loss 2.6689 (2.6034)	grad_norm 1.9621 (2.7805/1.1453)	mem 34604MB
[2025-01-19 21:42:49 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][80/312]	eta 0:03:00 lr 0.000045	time 0.7177 (0.7783)	model_time 0.7175 (0.7603)	loss 2.7772 (2.5846)	grad_norm 2.1113 (2.7091/1.1115)	mem 34604MB
[2025-01-19 21:42:56 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][90/312]	eta 0:02:51 lr 0.000045	time 0.7263 (0.7729)	model_time 0.7261 (0.7568)	loss 2.7187 (2.6057)	grad_norm 1.7352 (2.6931/1.0757)	mem 34604MB
[2025-01-19 21:43:03 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][100/312]	eta 0:02:42 lr 0.000045	time 0.7758 (0.7684)	model_time 0.7756 (0.7539)	loss 3.0906 (2.5869)	grad_norm 2.0082 (2.6378/1.0624)	mem 34604MB
[2025-01-19 21:43:11 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][110/312]	eta 0:02:34 lr 0.000045	time 0.7281 (0.7660)	model_time 0.7279 (0.7528)	loss 1.8896 (2.5763)	grad_norm 1.5591 (2.6083/1.0528)	mem 34604MB
[2025-01-19 21:43:18 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][120/312]	eta 0:02:26 lr 0.000045	time 0.7205 (0.7628)	model_time 0.7203 (0.7506)	loss 2.9888 (2.5639)	grad_norm 2.3430 (2.5896/1.0308)	mem 34604MB
[2025-01-19 21:43:25 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][130/312]	eta 0:02:18 lr 0.000045	time 0.7188 (0.7608)	model_time 0.7186 (0.7495)	loss 2.4412 (2.5640)	grad_norm 2.3271 (2.5733/1.0103)	mem 34604MB
[2025-01-19 21:43:33 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][140/312]	eta 0:02:10 lr 0.000045	time 0.7209 (0.7609)	model_time 0.7207 (0.7504)	loss 2.8300 (2.5871)	grad_norm 1.4888 (2.5823/1.0529)	mem 34604MB
[2025-01-19 21:43:41 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][150/312]	eta 0:02:03 lr 0.000045	time 0.7693 (0.7611)	model_time 0.7688 (0.7513)	loss 2.1967 (2.5931)	grad_norm 1.6300 (2.5517/1.0324)	mem 34604MB
[2025-01-19 21:43:48 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][160/312]	eta 0:01:55 lr 0.000045	time 0.7197 (0.7616)	model_time 0.7196 (0.7524)	loss 3.0033 (2.6064)	grad_norm 2.3496 (2.5340/1.0168)	mem 34604MB
[2025-01-19 21:43:56 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][170/312]	eta 0:01:48 lr 0.000045	time 0.7087 (0.7625)	model_time 0.7086 (0.7538)	loss 2.4786 (2.6110)	grad_norm 2.7660 (2.5464/0.9999)	mem 34604MB
[2025-01-19 21:44:04 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][180/312]	eta 0:01:40 lr 0.000044	time 0.7241 (0.7619)	model_time 0.7239 (0.7536)	loss 1.8330 (2.6073)	grad_norm 2.5049 (2.5425/0.9961)	mem 34604MB
[2025-01-19 21:44:11 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][190/312]	eta 0:01:32 lr 0.000044	time 0.7339 (0.7607)	model_time 0.7337 (0.7528)	loss 2.7155 (2.5967)	grad_norm 1.7777 (2.5572/0.9932)	mem 34604MB
[2025-01-19 21:44:18 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][200/312]	eta 0:01:25 lr 0.000044	time 0.7270 (0.7595)	model_time 0.7269 (0.7520)	loss 2.9479 (2.6018)	grad_norm 4.1201 (2.5639/0.9835)	mem 34604MB
[2025-01-19 21:44:26 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][210/312]	eta 0:01:17 lr 0.000044	time 0.7260 (0.7579)	model_time 0.7256 (0.7508)	loss 2.8058 (2.6102)	grad_norm 3.0158 (2.5590/0.9752)	mem 34604MB
[2025-01-19 21:44:33 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][220/312]	eta 0:01:09 lr 0.000044	time 0.7221 (0.7564)	model_time 0.7219 (0.7496)	loss 2.8188 (2.6135)	grad_norm 3.5907 (2.5656/0.9621)	mem 34604MB
[2025-01-19 21:44:40 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][230/312]	eta 0:01:01 lr 0.000044	time 0.7267 (0.7554)	model_time 0.7266 (0.7489)	loss 1.7708 (2.6085)	grad_norm 2.6671 (2.6192/1.0073)	mem 34604MB
[2025-01-19 21:44:47 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][240/312]	eta 0:00:54 lr 0.000044	time 0.7263 (0.7544)	model_time 0.7262 (0.7482)	loss 2.8179 (2.6156)	grad_norm 2.4787 (2.6562/1.0479)	mem 34604MB
[2025-01-19 21:44:55 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][250/312]	eta 0:00:46 lr 0.000044	time 0.7411 (0.7537)	model_time 0.7410 (0.7477)	loss 2.4528 (2.6128)	grad_norm 2.5740 (2.6539/1.0421)	mem 34604MB
[2025-01-19 21:45:02 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][260/312]	eta 0:00:39 lr 0.000044	time 0.7181 (0.7538)	model_time 0.7180 (0.7480)	loss 2.5187 (2.6038)	grad_norm 2.5956 (2.6927/1.0936)	mem 34604MB
[2025-01-19 21:45:10 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][270/312]	eta 0:00:31 lr 0.000044	time 0.7176 (0.7544)	model_time 0.7174 (0.7488)	loss 2.6695 (2.5963)	grad_norm 5.6906 (2.7033/1.0934)	mem 34604MB
[2025-01-19 21:45:18 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][280/312]	eta 0:00:24 lr 0.000044	time 0.7137 (0.7554)	model_time 0.7133 (0.7500)	loss 2.6265 (2.5985)	grad_norm 1.9627 (2.7014/1.1003)	mem 34604MB
[2025-01-19 21:45:26 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][290/312]	eta 0:00:16 lr 0.000044	time 0.7086 (0.7560)	model_time 0.7085 (0.7508)	loss 2.4442 (2.5972)	grad_norm 2.1500 (2.6976/1.0975)	mem 34604MB
[2025-01-19 21:45:33 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][300/312]	eta 0:00:09 lr 0.000044	time 0.7638 (0.7558)	model_time 0.7637 (0.7508)	loss 2.6137 (2.5991)	grad_norm 2.2438 (2.6990/1.1101)	mem 34604MB
[2025-01-19 21:45:40 internimage_b_1k_224] (main.py 510): INFO Train: [293/300][310/312]	eta 0:00:01 lr 0.000044	time 0.8112 (0.7551)	model_time 0.8111 (0.7502)	loss 2.7779 (2.5982)	grad_norm 1.2070 (2.6996/1.1148)	mem 34604MB
[2025-01-19 21:45:41 internimage_b_1k_224] (main.py 519): INFO EPOCH 293 training takes 0:03:55
[2025-01-19 21:45:41 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_293.pth saving......
[2025-01-19 21:45:44 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_293.pth saved !!!
[2025-01-19 21:45:52 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.516 (7.516)	Loss 0.6892 (0.6892)	Acc@1 86.475 (86.475)	Acc@5 98.193 (98.193)	Mem 34604MB
[2025-01-19 21:45:55 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.942)	Loss 0.8939 (0.7718)	Acc@1 81.128 (84.854)	Acc@5 96.069 (97.095)	Mem 34604MB
[2025-01-19 21:45:55 internimage_b_1k_224] (main.py 575): INFO [Epoch:293] * Acc@1 84.689 Acc@5 97.103
[2025-01-19 21:45:55 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.7%
[2025-01-19 21:45:55 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.72%
[2025-01-19 21:46:04 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.125 (9.125)	Loss 0.7019 (0.7019)	Acc@1 86.841 (86.841)	Acc@5 98.193 (98.193)	Mem 34604MB
[2025-01-19 21:46:09 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.242)	Loss 0.8955 (0.7831)	Acc@1 81.299 (84.883)	Acc@5 96.167 (97.137)	Mem 34604MB
[2025-01-19 21:46:09 internimage_b_1k_224] (main.py 575): INFO [Epoch:293] * Acc@1 84.713 Acc@5 97.143
[2025-01-19 21:46:09 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.7%
[2025-01-19 21:46:09 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 21:46:13 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 21:46:13 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.71%
[2025-01-19 21:46:15 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][0/312]	eta 0:11:30 lr 0.000044	time 2.2144 (2.2144)	model_time 0.7439 (0.7439)	loss 2.3359 (2.3359)	grad_norm 1.4632 (1.4632/0.0000)	mem 34604MB
[2025-01-19 21:46:23 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][10/312]	eta 0:04:27 lr 0.000044	time 0.7219 (0.8850)	model_time 0.7217 (0.7510)	loss 2.7793 (2.4183)	grad_norm 2.0016 (2.0375/0.7457)	mem 34604MB
[2025-01-19 21:46:30 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][20/312]	eta 0:03:56 lr 0.000044	time 0.7258 (0.8112)	model_time 0.7256 (0.7408)	loss 1.9461 (2.4355)	grad_norm 1.6411 (2.2545/0.8234)	mem 34604MB
[2025-01-19 21:46:37 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][30/312]	eta 0:03:40 lr 0.000044	time 0.7197 (0.7830)	model_time 0.7195 (0.7353)	loss 2.2489 (2.5548)	grad_norm 1.6112 (2.2001/0.7493)	mem 34604MB
[2025-01-19 21:46:44 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][40/312]	eta 0:03:29 lr 0.000044	time 0.7565 (0.7718)	model_time 0.7560 (0.7356)	loss 2.9314 (2.5375)	grad_norm 2.1274 (2.4747/0.9401)	mem 34604MB
[2025-01-19 21:46:52 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][50/312]	eta 0:03:20 lr 0.000044	time 0.7317 (0.7636)	model_time 0.7315 (0.7344)	loss 2.8656 (2.5743)	grad_norm 1.4957 (2.5264/0.9839)	mem 34604MB
[2025-01-19 21:46:59 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][60/312]	eta 0:03:11 lr 0.000044	time 0.7203 (0.7587)	model_time 0.7199 (0.7343)	loss 2.7448 (2.5644)	grad_norm 3.2346 (2.7188/1.1663)	mem 34604MB
[2025-01-19 21:47:07 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][70/312]	eta 0:03:03 lr 0.000044	time 0.8070 (0.7585)	model_time 0.8069 (0.7375)	loss 2.8181 (2.5793)	grad_norm 3.2797 (2.7229/1.1124)	mem 34604MB
[2025-01-19 21:47:14 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][80/312]	eta 0:02:56 lr 0.000044	time 0.7162 (0.7592)	model_time 0.7160 (0.7407)	loss 2.6868 (2.5414)	grad_norm 1.9775 (2.6855/1.0898)	mem 34604MB
[2025-01-19 21:47:22 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][90/312]	eta 0:02:49 lr 0.000044	time 0.8135 (0.7618)	model_time 0.8134 (0.7453)	loss 2.9132 (2.5436)	grad_norm 3.2384 (2.6302/1.0640)	mem 34604MB
[2025-01-19 21:47:30 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][100/312]	eta 0:02:41 lr 0.000044	time 0.7232 (0.7623)	model_time 0.7228 (0.7474)	loss 1.9752 (2.5369)	grad_norm 2.0428 (2.5635/1.0439)	mem 34604MB
[2025-01-19 21:47:37 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][110/312]	eta 0:02:33 lr 0.000043	time 0.7360 (0.7608)	model_time 0.7358 (0.7472)	loss 2.6147 (2.5569)	grad_norm 3.4887 (2.5501/1.0431)	mem 34604MB
[2025-01-19 21:47:45 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][120/312]	eta 0:02:25 lr 0.000043	time 0.7273 (0.7579)	model_time 0.7269 (0.7454)	loss 1.9363 (2.5523)	grad_norm 3.7866 (2.5189/1.0260)	mem 34604MB
[2025-01-19 21:47:52 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][130/312]	eta 0:02:17 lr 0.000043	time 0.7354 (0.7567)	model_time 0.7350 (0.7451)	loss 1.6622 (2.5605)	grad_norm 2.2414 (2.5332/1.0160)	mem 34604MB
[2025-01-19 21:47:59 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][140/312]	eta 0:02:09 lr 0.000043	time 0.7216 (0.7548)	model_time 0.7212 (0.7440)	loss 3.0642 (2.5578)	grad_norm 3.6073 (2.5473/0.9973)	mem 34604MB
[2025-01-19 21:48:06 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][150/312]	eta 0:02:01 lr 0.000043	time 0.7269 (0.7529)	model_time 0.7268 (0.7428)	loss 2.9676 (2.5675)	grad_norm 1.5167 (2.5713/1.0039)	mem 34604MB
[2025-01-19 21:48:14 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][160/312]	eta 0:01:54 lr 0.000043	time 0.7202 (0.7515)	model_time 0.7198 (0.7421)	loss 2.6791 (2.5695)	grad_norm 2.0971 (2.5555/0.9938)	mem 34604MB
[2025-01-19 21:48:21 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][170/312]	eta 0:01:46 lr 0.000043	time 0.7365 (0.7503)	model_time 0.7364 (0.7413)	loss 2.7064 (2.5696)	grad_norm 1.4788 (2.5597/1.0193)	mem 34604MB
[2025-01-19 21:48:28 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][180/312]	eta 0:01:38 lr 0.000043	time 0.7248 (0.7495)	model_time 0.7247 (0.7411)	loss 2.7082 (2.5758)	grad_norm 5.1781 (2.5562/1.0283)	mem 34604MB
[2025-01-19 21:48:36 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][190/312]	eta 0:01:31 lr 0.000043	time 0.8418 (0.7503)	model_time 0.8417 (0.7422)	loss 2.7345 (2.5651)	grad_norm 1.3070 (2.5311/1.0203)	mem 34604MB
[2025-01-19 21:48:44 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][200/312]	eta 0:01:24 lr 0.000043	time 0.7163 (0.7509)	model_time 0.7158 (0.7432)	loss 2.0750 (2.5642)	grad_norm 2.3166 (2.5025/1.0049)	mem 34604MB
[2025-01-19 21:48:52 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][210/312]	eta 0:01:16 lr 0.000043	time 0.8111 (0.7524)	model_time 0.8110 (0.7451)	loss 2.5474 (2.5596)	grad_norm 1.5221 (2.5207/1.0215)	mem 34604MB
[2025-01-19 21:48:59 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][220/312]	eta 0:01:09 lr 0.000043	time 0.7241 (0.7532)	model_time 0.7236 (0.7462)	loss 2.5461 (2.5677)	grad_norm 2.4306 (2.5002/1.0092)	mem 34604MB
[2025-01-19 21:49:07 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][230/312]	eta 0:01:01 lr 0.000043	time 0.7235 (0.7534)	model_time 0.7234 (0.7467)	loss 3.1249 (2.5723)	grad_norm 1.4318 (2.4899/0.9955)	mem 34604MB
[2025-01-19 21:49:14 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][240/312]	eta 0:00:54 lr 0.000043	time 0.7466 (0.7523)	model_time 0.7461 (0.7459)	loss 3.0461 (2.5754)	grad_norm 2.0201 (2.4757/0.9894)	mem 34604MB
[2025-01-19 21:49:22 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][250/312]	eta 0:00:46 lr 0.000043	time 0.7192 (0.7519)	model_time 0.7187 (0.7457)	loss 2.8656 (2.5808)	grad_norm 2.8882 (2.4704/0.9770)	mem 34604MB
[2025-01-19 21:49:29 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][260/312]	eta 0:00:39 lr 0.000043	time 0.7350 (0.7510)	model_time 0.7346 (0.7450)	loss 2.8175 (2.5801)	grad_norm 3.4898 (2.4842/1.0174)	mem 34604MB
[2025-01-19 21:49:36 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][270/312]	eta 0:00:31 lr 0.000043	time 0.7104 (0.7500)	model_time 0.7102 (0.7443)	loss 2.9752 (2.5803)	grad_norm 1.1789 (2.5000/1.0223)	mem 34604MB
[2025-01-19 21:49:43 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][280/312]	eta 0:00:23 lr 0.000043	time 0.7296 (0.7495)	model_time 0.7292 (0.7439)	loss 3.2580 (2.5817)	grad_norm 1.2484 (2.4901/1.0202)	mem 34604MB
[2025-01-19 21:49:51 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][290/312]	eta 0:00:16 lr 0.000043	time 0.7130 (0.7487)	model_time 0.7125 (0.7433)	loss 2.7451 (2.5846)	grad_norm 2.0963 (2.5014/1.0377)	mem 34604MB
[2025-01-19 21:49:58 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][300/312]	eta 0:00:08 lr 0.000043	time 0.7127 (0.7481)	model_time 0.7126 (0.7428)	loss 3.1257 (2.5876)	grad_norm 2.3913 (2.5021/1.0335)	mem 34604MB
[2025-01-19 21:50:05 internimage_b_1k_224] (main.py 510): INFO Train: [294/300][310/312]	eta 0:00:01 lr 0.000043	time 0.7292 (0.7478)	model_time 0.7291 (0.7428)	loss 2.2906 (2.5889)	grad_norm 2.8446 (2.5189/1.0288)	mem 34604MB
[2025-01-19 21:50:06 internimage_b_1k_224] (main.py 519): INFO EPOCH 294 training takes 0:03:53
[2025-01-19 21:50:06 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_294.pth saving......
[2025-01-19 21:50:09 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_294.pth saved !!!
[2025-01-19 21:50:17 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.346 (7.346)	Loss 0.6892 (0.6892)	Acc@1 86.450 (86.450)	Acc@5 98.047 (98.047)	Mem 34604MB
[2025-01-19 21:50:20 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.938)	Loss 0.8917 (0.7718)	Acc@1 81.055 (84.759)	Acc@5 96.021 (97.044)	Mem 34604MB
[2025-01-19 21:50:20 internimage_b_1k_224] (main.py 575): INFO [Epoch:294] * Acc@1 84.575 Acc@5 97.047
[2025-01-19 21:50:20 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.6%
[2025-01-19 21:50:20 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.72%
[2025-01-19 21:50:29 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.088 (9.088)	Loss 0.7015 (0.7015)	Acc@1 86.792 (86.792)	Acc@5 98.193 (98.193)	Mem 34604MB
[2025-01-19 21:50:33 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.231)	Loss 0.8951 (0.7826)	Acc@1 81.323 (84.885)	Acc@5 96.167 (97.135)	Mem 34604MB
[2025-01-19 21:50:34 internimage_b_1k_224] (main.py 575): INFO [Epoch:294] * Acc@1 84.717 Acc@5 97.141
[2025-01-19 21:50:34 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.7%
[2025-01-19 21:50:34 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 21:50:37 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 21:50:38 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.72%
[2025-01-19 21:50:40 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][0/312]	eta 0:10:40 lr 0.000043	time 2.0522 (2.0522)	model_time 0.7297 (0.7297)	loss 3.1205 (3.1205)	grad_norm 2.1195 (2.1195/0.0000)	mem 34604MB
[2025-01-19 21:50:47 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][10/312]	eta 0:04:29 lr 0.000043	time 0.7326 (0.8927)	model_time 0.7325 (0.7722)	loss 2.5747 (2.7199)	grad_norm 3.6315 (3.0249/0.7777)	mem 34604MB
[2025-01-19 21:50:55 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][20/312]	eta 0:04:05 lr 0.000043	time 0.7180 (0.8402)	model_time 0.7176 (0.7769)	loss 2.7432 (2.6423)	grad_norm 3.1469 (2.6917/0.9439)	mem 34604MB
[2025-01-19 21:51:03 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][30/312]	eta 0:03:51 lr 0.000043	time 0.8173 (0.8212)	model_time 0.8168 (0.7781)	loss 2.4065 (2.5437)	grad_norm 6.0299 (2.8807/1.0710)	mem 34604MB
[2025-01-19 21:51:11 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][40/312]	eta 0:03:39 lr 0.000043	time 0.7276 (0.8054)	model_time 0.7274 (0.7728)	loss 2.5728 (2.5297)	grad_norm 5.0642 (2.9836/1.2400)	mem 34604MB
[2025-01-19 21:51:18 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][50/312]	eta 0:03:27 lr 0.000043	time 0.7273 (0.7902)	model_time 0.7271 (0.7639)	loss 3.0053 (2.5843)	grad_norm 1.4003 (2.9244/1.2900)	mem 34604MB
[2025-01-19 21:51:25 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][60/312]	eta 0:03:17 lr 0.000043	time 0.7294 (0.7819)	model_time 0.7290 (0.7598)	loss 2.3374 (2.5891)	grad_norm 2.4448 (2.8080/1.2423)	mem 34604MB
[2025-01-19 21:51:33 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][70/312]	eta 0:03:07 lr 0.000042	time 0.7303 (0.7746)	model_time 0.7299 (0.7556)	loss 2.9868 (2.5975)	grad_norm 2.1363 (2.7479/1.1910)	mem 34604MB
[2025-01-19 21:51:40 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][80/312]	eta 0:02:58 lr 0.000042	time 0.7272 (0.7690)	model_time 0.7268 (0.7523)	loss 1.7758 (2.5787)	grad_norm 2.0651 (2.7620/1.1789)	mem 34604MB
[2025-01-19 21:51:47 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][90/312]	eta 0:02:49 lr 0.000042	time 0.7307 (0.7655)	model_time 0.7305 (0.7506)	loss 1.7388 (2.5557)	grad_norm 3.1970 (2.7626/1.1389)	mem 34604MB
[2025-01-19 21:51:55 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][100/312]	eta 0:02:41 lr 0.000042	time 0.7471 (0.7624)	model_time 0.7467 (0.7490)	loss 1.9080 (2.5613)	grad_norm 2.5428 (2.7062/1.1084)	mem 34604MB
[2025-01-19 21:52:02 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][110/312]	eta 0:02:33 lr 0.000042	time 0.7210 (0.7607)	model_time 0.7206 (0.7485)	loss 2.9049 (2.5788)	grad_norm 3.0570 (2.7287/1.1009)	mem 34604MB
[2025-01-19 21:52:09 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][120/312]	eta 0:02:25 lr 0.000042	time 0.8043 (0.7597)	model_time 0.8039 (0.7484)	loss 2.6754 (2.5893)	grad_norm 3.5600 (2.7092/1.0708)	mem 34604MB
[2025-01-19 21:52:17 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][130/312]	eta 0:02:18 lr 0.000042	time 0.8116 (0.7611)	model_time 0.8114 (0.7506)	loss 2.8992 (2.5874)	grad_norm 1.3316 (2.6839/1.0627)	mem 34604MB
[2025-01-19 21:52:25 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][140/312]	eta 0:02:11 lr 0.000042	time 0.7135 (0.7618)	model_time 0.7131 (0.7520)	loss 2.7048 (2.5875)	grad_norm 2.7441 (2.6827/1.0575)	mem 34604MB
[2025-01-19 21:52:33 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][150/312]	eta 0:02:03 lr 0.000042	time 0.8168 (0.7619)	model_time 0.8167 (0.7528)	loss 2.5548 (2.5761)	grad_norm 1.2322 (2.6977/1.0514)	mem 34604MB
[2025-01-19 21:52:40 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][160/312]	eta 0:01:55 lr 0.000042	time 0.7198 (0.7612)	model_time 0.7194 (0.7526)	loss 2.8192 (2.5824)	grad_norm 1.6747 (2.6943/1.0536)	mem 34604MB
[2025-01-19 21:52:47 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][170/312]	eta 0:01:47 lr 0.000042	time 0.7705 (0.7592)	model_time 0.7703 (0.7511)	loss 3.0248 (2.5854)	grad_norm 1.3510 (2.6759/1.0476)	mem 34604MB
[2025-01-19 21:52:55 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][180/312]	eta 0:01:40 lr 0.000042	time 0.7468 (0.7579)	model_time 0.7466 (0.7502)	loss 2.5269 (2.5918)	grad_norm 1.1467 (2.6214/1.0484)	mem 34604MB
[2025-01-19 21:53:02 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][190/312]	eta 0:01:32 lr 0.000042	time 0.7153 (0.7563)	model_time 0.7148 (0.7490)	loss 2.4473 (2.5888)	grad_norm 2.5146 (2.6042/1.0490)	mem 34604MB
[2025-01-19 21:53:09 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][200/312]	eta 0:01:24 lr 0.000042	time 0.7232 (0.7550)	model_time 0.7231 (0.7480)	loss 3.1355 (2.5901)	grad_norm 2.4974 (2.6064/1.0455)	mem 34604MB
[2025-01-19 21:53:17 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][210/312]	eta 0:01:16 lr 0.000042	time 0.7186 (0.7541)	model_time 0.7185 (0.7475)	loss 2.6728 (2.5877)	grad_norm 4.1731 (2.5952/1.0341)	mem 34604MB
[2025-01-19 21:53:24 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][220/312]	eta 0:01:09 lr 0.000042	time 0.7221 (0.7532)	model_time 0.7216 (0.7468)	loss 2.2253 (2.5937)	grad_norm 4.0872 (2.5866/1.0290)	mem 34604MB
[2025-01-19 21:53:32 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][230/312]	eta 0:01:01 lr 0.000042	time 0.7149 (0.7533)	model_time 0.7147 (0.7472)	loss 2.1371 (2.5869)	grad_norm 2.9748 (2.5660/1.0206)	mem 34604MB
[2025-01-19 21:53:39 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][240/312]	eta 0:00:54 lr 0.000042	time 0.8261 (0.7533)	model_time 0.8260 (0.7474)	loss 2.6489 (2.5896)	grad_norm 2.0811 (2.5429/1.0089)	mem 34604MB
[2025-01-19 21:53:47 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][250/312]	eta 0:00:46 lr 0.000042	time 0.7776 (0.7538)	model_time 0.7772 (0.7482)	loss 2.3593 (2.5950)	grad_norm 3.2148 (2.5485/0.9964)	mem 34604MB
[2025-01-19 21:53:55 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][260/312]	eta 0:00:39 lr 0.000042	time 0.8080 (0.7555)	model_time 0.8075 (0.7500)	loss 2.9662 (2.5887)	grad_norm 3.0862 (2.5485/0.9902)	mem 34604MB
[2025-01-19 21:54:02 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][270/312]	eta 0:00:31 lr 0.000042	time 0.8045 (0.7558)	model_time 0.8044 (0.7506)	loss 3.1074 (2.5975)	grad_norm 1.7943 (2.5675/1.0175)	mem 34604MB
[2025-01-19 21:54:10 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][280/312]	eta 0:00:24 lr 0.000042	time 0.7158 (0.7557)	model_time 0.7154 (0.7506)	loss 2.4819 (2.5987)	grad_norm 2.2796 (2.5730/1.0134)	mem 34604MB
[2025-01-19 21:54:17 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][290/312]	eta 0:00:16 lr 0.000042	time 0.7194 (0.7546)	model_time 0.7189 (0.7497)	loss 2.8601 (2.6030)	grad_norm 1.5563 (2.5546/1.0113)	mem 34604MB
[2025-01-19 21:54:25 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][300/312]	eta 0:00:09 lr 0.000042	time 0.7149 (0.7541)	model_time 0.7148 (0.7494)	loss 2.0940 (2.6052)	grad_norm 3.7001 (2.5463/1.0176)	mem 34604MB
[2025-01-19 21:54:32 internimage_b_1k_224] (main.py 510): INFO Train: [295/300][310/312]	eta 0:00:01 lr 0.000042	time 0.7191 (0.7530)	model_time 0.7190 (0.7484)	loss 2.3226 (2.6011)	grad_norm 2.8984 (2.5402/1.0162)	mem 34604MB
[2025-01-19 21:54:32 internimage_b_1k_224] (main.py 519): INFO EPOCH 295 training takes 0:03:54
[2025-01-19 21:54:32 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_295.pth saving......
[2025-01-19 21:54:36 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_295.pth saved !!!
[2025-01-19 21:54:43 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.482 (7.482)	Loss 0.6908 (0.6908)	Acc@1 86.914 (86.914)	Acc@5 98.047 (98.047)	Mem 34604MB
[2025-01-19 21:54:46 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.955)	Loss 0.8921 (0.7748)	Acc@1 81.128 (84.808)	Acc@5 96.143 (97.079)	Mem 34604MB
[2025-01-19 21:54:47 internimage_b_1k_224] (main.py 575): INFO [Epoch:295] * Acc@1 84.645 Acc@5 97.071
[2025-01-19 21:54:47 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.6%
[2025-01-19 21:54:47 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.72%
[2025-01-19 21:54:56 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.149 (9.149)	Loss 0.7012 (0.7012)	Acc@1 86.792 (86.792)	Acc@5 98.218 (98.218)	Mem 34604MB
[2025-01-19 21:55:00 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.235)	Loss 0.8946 (0.7822)	Acc@1 81.348 (84.892)	Acc@5 96.143 (97.141)	Mem 34604MB
[2025-01-19 21:55:00 internimage_b_1k_224] (main.py 575): INFO [Epoch:295] * Acc@1 84.727 Acc@5 97.147
[2025-01-19 21:55:00 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.7%
[2025-01-19 21:55:00 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 21:55:04 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 21:55:04 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.73%
[2025-01-19 21:55:06 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][0/312]	eta 0:10:15 lr 0.000042	time 1.9728 (1.9728)	model_time 0.7304 (0.7304)	loss 2.3469 (2.3469)	grad_norm 3.9081 (3.9081/0.0000)	mem 34604MB
[2025-01-19 21:55:14 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][10/312]	eta 0:04:14 lr 0.000042	time 0.7174 (0.8443)	model_time 0.7172 (0.7310)	loss 2.6118 (2.6857)	grad_norm 1.2518 (2.7026/1.0051)	mem 34604MB
[2025-01-19 21:55:21 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][20/312]	eta 0:03:51 lr 0.000042	time 0.7218 (0.7931)	model_time 0.7213 (0.7335)	loss 2.0865 (2.7221)	grad_norm 3.8931 (2.5792/1.0401)	mem 34604MB
[2025-01-19 21:55:28 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][30/312]	eta 0:03:37 lr 0.000042	time 0.7206 (0.7714)	model_time 0.7202 (0.7310)	loss 1.7368 (2.7063)	grad_norm 4.1082 (2.5748/1.0245)	mem 34604MB
[2025-01-19 21:55:36 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][40/312]	eta 0:03:27 lr 0.000042	time 0.8127 (0.7621)	model_time 0.8125 (0.7315)	loss 2.4302 (2.7275)	grad_norm 2.0101 (2.5977/0.9507)	mem 34604MB
[2025-01-19 21:55:43 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][50/312]	eta 0:03:18 lr 0.000042	time 0.7378 (0.7594)	model_time 0.7376 (0.7347)	loss 2.2712 (2.7105)	grad_norm 1.2625 (2.4241/0.9431)	mem 34604MB
[2025-01-19 21:55:51 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][60/312]	eta 0:03:11 lr 0.000042	time 0.7230 (0.7592)	model_time 0.7228 (0.7385)	loss 3.0128 (2.7283)	grad_norm 2.7503 (2.4328/0.9103)	mem 34604MB
[2025-01-19 21:55:58 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][70/312]	eta 0:03:04 lr 0.000042	time 0.7210 (0.7620)	model_time 0.7205 (0.7442)	loss 2.6084 (2.6878)	grad_norm 2.2816 (2.4139/0.8870)	mem 34604MB
[2025-01-19 21:56:06 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][80/312]	eta 0:02:57 lr 0.000042	time 0.7199 (0.7638)	model_time 0.7195 (0.7482)	loss 2.2536 (2.6669)	grad_norm 1.8822 (2.3984/0.8667)	mem 34604MB
[2025-01-19 21:56:14 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][90/312]	eta 0:02:49 lr 0.000041	time 0.7205 (0.7632)	model_time 0.7201 (0.7492)	loss 2.9600 (2.6723)	grad_norm 2.1642 (2.3734/0.8400)	mem 34604MB
[2025-01-19 21:56:21 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][100/312]	eta 0:02:41 lr 0.000041	time 0.7240 (0.7597)	model_time 0.7238 (0.7470)	loss 2.5620 (2.6626)	grad_norm 1.5946 (2.3890/0.8273)	mem 34604MB
[2025-01-19 21:56:28 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][110/312]	eta 0:02:33 lr 0.000041	time 0.7262 (0.7577)	model_time 0.7258 (0.7461)	loss 2.7766 (2.6526)	grad_norm 4.1119 (2.4319/0.8514)	mem 34604MB
[2025-01-19 21:56:36 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][120/312]	eta 0:02:25 lr 0.000041	time 0.7213 (0.7554)	model_time 0.7212 (0.7448)	loss 2.6273 (2.6543)	grad_norm 1.0837 (2.4210/0.8756)	mem 34604MB
[2025-01-19 21:56:43 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][130/312]	eta 0:02:17 lr 0.000041	time 0.7191 (0.7529)	model_time 0.7186 (0.7431)	loss 2.8293 (2.6474)	grad_norm 2.4837 (2.4133/0.8529)	mem 34604MB
[2025-01-19 21:56:50 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][140/312]	eta 0:02:09 lr 0.000041	time 0.7199 (0.7518)	model_time 0.7194 (0.7426)	loss 2.8807 (2.6489)	grad_norm 1.9773 (2.4099/0.8418)	mem 34604MB
[2025-01-19 21:56:58 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][150/312]	eta 0:02:01 lr 0.000041	time 0.7408 (0.7504)	model_time 0.7406 (0.7419)	loss 3.0650 (2.6466)	grad_norm 3.3146 (2.3983/0.8326)	mem 34604MB
[2025-01-19 21:57:05 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][160/312]	eta 0:01:53 lr 0.000041	time 0.8042 (0.7498)	model_time 0.8040 (0.7418)	loss 2.7820 (2.6399)	grad_norm 1.3667 (2.4083/0.8255)	mem 34604MB
[2025-01-19 21:57:13 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][170/312]	eta 0:01:46 lr 0.000041	time 0.7202 (0.7499)	model_time 0.7197 (0.7423)	loss 2.9003 (2.6482)	grad_norm 1.9195 (2.3975/0.8205)	mem 34604MB
[2025-01-19 21:57:20 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][180/312]	eta 0:01:39 lr 0.000041	time 0.7158 (0.7500)	model_time 0.7154 (0.7428)	loss 2.4393 (2.6422)	grad_norm 1.8338 (2.3980/0.8138)	mem 34604MB
[2025-01-19 21:57:28 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][190/312]	eta 0:01:31 lr 0.000041	time 0.7187 (0.7522)	model_time 0.7186 (0.7453)	loss 2.9484 (2.6323)	grad_norm 2.6855 (2.3945/0.8171)	mem 34604MB
[2025-01-19 21:57:36 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][200/312]	eta 0:01:24 lr 0.000041	time 0.8150 (0.7534)	model_time 0.8145 (0.7469)	loss 2.8910 (2.6326)	grad_norm 2.1139 (2.4053/0.8116)	mem 34604MB
[2025-01-19 21:57:43 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][210/312]	eta 0:01:16 lr 0.000041	time 0.7174 (0.7533)	model_time 0.7173 (0.7470)	loss 2.5238 (2.6299)	grad_norm 3.2040 (2.3898/0.8051)	mem 34604MB
[2025-01-19 21:57:51 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][220/312]	eta 0:01:09 lr 0.000041	time 0.7176 (0.7524)	model_time 0.7174 (0.7464)	loss 2.3641 (2.6256)	grad_norm 1.6406 (2.3926/0.8031)	mem 34604MB
[2025-01-19 21:57:58 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][230/312]	eta 0:01:01 lr 0.000041	time 0.7340 (0.7521)	model_time 0.7339 (0.7464)	loss 2.7223 (2.6231)	grad_norm 2.9531 (2.4381/0.8871)	mem 34604MB
[2025-01-19 21:58:05 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][240/312]	eta 0:00:54 lr 0.000041	time 0.7295 (0.7512)	model_time 0.7293 (0.7456)	loss 2.3528 (2.6147)	grad_norm 2.8753 (2.4507/0.8814)	mem 34604MB
[2025-01-19 21:58:13 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][250/312]	eta 0:00:46 lr 0.000041	time 0.7238 (0.7502)	model_time 0.7233 (0.7449)	loss 2.7856 (2.6126)	grad_norm 3.2949 (2.4579/0.8927)	mem 34604MB
[2025-01-19 21:58:20 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][260/312]	eta 0:00:38 lr 0.000041	time 0.7270 (0.7499)	model_time 0.7265 (0.7447)	loss 2.0941 (2.6137)	grad_norm 2.1541 (2.4555/0.8930)	mem 34604MB
[2025-01-19 21:58:27 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][270/312]	eta 0:00:31 lr 0.000041	time 0.7325 (0.7489)	model_time 0.7324 (0.7440)	loss 3.0206 (2.6167)	grad_norm 2.3660 (2.4407/0.8944)	mem 34604MB
[2025-01-19 21:58:35 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][280/312]	eta 0:00:23 lr 0.000041	time 0.8022 (0.7483)	model_time 0.8020 (0.7436)	loss 2.6463 (2.6209)	grad_norm 1.4116 (2.4269/0.8941)	mem 34604MB
[2025-01-19 21:58:42 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][290/312]	eta 0:00:16 lr 0.000041	time 0.7177 (0.7483)	model_time 0.7172 (0.7437)	loss 3.0949 (2.6168)	grad_norm 4.5034 (2.4488/0.9067)	mem 34604MB
[2025-01-19 21:58:50 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][300/312]	eta 0:00:08 lr 0.000041	time 0.7128 (0.7482)	model_time 0.7127 (0.7437)	loss 3.0995 (2.6201)	grad_norm 1.8961 (2.4723/0.9324)	mem 34604MB
[2025-01-19 21:58:57 internimage_b_1k_224] (main.py 510): INFO Train: [296/300][310/312]	eta 0:00:01 lr 0.000041	time 0.9891 (0.7493)	model_time 0.9890 (0.7449)	loss 2.9579 (2.6224)	grad_norm 1.9248 (2.4920/0.9402)	mem 34604MB
[2025-01-19 21:58:58 internimage_b_1k_224] (main.py 519): INFO EPOCH 296 training takes 0:03:53
[2025-01-19 21:58:58 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_296.pth saving......
[2025-01-19 21:59:01 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_296.pth saved !!!
[2025-01-19 21:59:09 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.299 (7.299)	Loss 0.6828 (0.6828)	Acc@1 86.816 (86.816)	Acc@5 97.900 (97.900)	Mem 34604MB
[2025-01-19 21:59:12 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.935)	Loss 0.8798 (0.7654)	Acc@1 81.274 (84.866)	Acc@5 96.094 (97.053)	Mem 34604MB
[2025-01-19 21:59:12 internimage_b_1k_224] (main.py 575): INFO [Epoch:296] * Acc@1 84.695 Acc@5 97.057
[2025-01-19 21:59:12 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.7%
[2025-01-19 21:59:12 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.72%
[2025-01-19 21:59:21 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.126 (9.126)	Loss 0.7007 (0.7007)	Acc@1 86.792 (86.792)	Acc@5 98.218 (98.218)	Mem 34604MB
[2025-01-19 21:59:26 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (1.240)	Loss 0.8941 (0.7817)	Acc@1 81.299 (84.883)	Acc@5 96.143 (97.137)	Mem 34604MB
[2025-01-19 21:59:26 internimage_b_1k_224] (main.py 575): INFO [Epoch:296] * Acc@1 84.723 Acc@5 97.139
[2025-01-19 21:59:26 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.7%
[2025-01-19 21:59:26 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.73%
[2025-01-19 21:59:29 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][0/312]	eta 0:18:23 lr 0.000041	time 3.5359 (3.5359)	model_time 1.3723 (1.3723)	loss 2.6443 (2.6443)	grad_norm 2.1661 (2.1661/0.0000)	mem 34604MB
[2025-01-19 21:59:37 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][10/312]	eta 0:05:12 lr 0.000041	time 0.7187 (1.0347)	model_time 0.7183 (0.8375)	loss 3.0074 (2.5930)	grad_norm 3.7591 (3.5748/0.9426)	mem 34604MB
[2025-01-19 21:59:45 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][20/312]	eta 0:04:21 lr 0.000041	time 0.7217 (0.8939)	model_time 0.7214 (0.7905)	loss 3.1255 (2.5741)	grad_norm 1.9867 (3.1878/0.9602)	mem 34604MB
[2025-01-19 21:59:52 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][30/312]	eta 0:04:00 lr 0.000041	time 0.7247 (0.8515)	model_time 0.7245 (0.7813)	loss 2.0222 (2.5437)	grad_norm 3.7363 (2.9075/0.9979)	mem 34604MB
[2025-01-19 22:00:00 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][40/312]	eta 0:03:43 lr 0.000041	time 0.7239 (0.8230)	model_time 0.7234 (0.7698)	loss 2.0490 (2.5359)	grad_norm 3.2258 (2.7826/0.9771)	mem 34604MB
[2025-01-19 22:00:07 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][50/312]	eta 0:03:30 lr 0.000041	time 0.7261 (0.8038)	model_time 0.7257 (0.7610)	loss 1.9476 (2.4935)	grad_norm 1.9943 (2.6056/0.9594)	mem 34604MB
[2025-01-19 22:00:14 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][60/312]	eta 0:03:19 lr 0.000041	time 0.7405 (0.7910)	model_time 0.7403 (0.7551)	loss 2.8518 (2.5108)	grad_norm 1.8959 (2.5764/0.9479)	mem 34604MB
[2025-01-19 22:00:21 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][70/312]	eta 0:03:09 lr 0.000041	time 0.7177 (0.7826)	model_time 0.7173 (0.7517)	loss 2.6210 (2.4974)	grad_norm 6.0258 (2.6290/0.9909)	mem 34604MB
[2025-01-19 22:00:29 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][80/312]	eta 0:02:59 lr 0.000041	time 0.7244 (0.7755)	model_time 0.7240 (0.7484)	loss 2.6568 (2.5252)	grad_norm 1.2509 (2.5963/0.9948)	mem 34604MB
[2025-01-19 22:00:36 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][90/312]	eta 0:02:51 lr 0.000041	time 0.7242 (0.7711)	model_time 0.7237 (0.7469)	loss 2.9874 (2.5209)	grad_norm 2.0137 (2.5661/0.9605)	mem 34604MB
[2025-01-19 22:00:44 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][100/312]	eta 0:02:43 lr 0.000041	time 0.7173 (0.7690)	model_time 0.7171 (0.7472)	loss 2.7559 (2.5200)	grad_norm 3.9265 (2.5399/0.9386)	mem 34604MB
[2025-01-19 22:00:51 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][110/312]	eta 0:02:35 lr 0.000041	time 0.8088 (0.7683)	model_time 0.8083 (0.7484)	loss 2.9588 (2.5454)	grad_norm 2.0037 (2.5577/0.9355)	mem 34604MB
[2025-01-19 22:00:59 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][120/312]	eta 0:02:27 lr 0.000041	time 0.8183 (0.7679)	model_time 0.8179 (0.7496)	loss 2.9282 (2.5555)	grad_norm 3.6341 (2.5600/0.9671)	mem 34604MB
[2025-01-19 22:01:07 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][130/312]	eta 0:02:20 lr 0.000041	time 0.7221 (0.7693)	model_time 0.7219 (0.7524)	loss 2.1587 (2.5435)	grad_norm 2.3502 (2.5462/0.9553)	mem 34604MB
[2025-01-19 22:01:14 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][140/312]	eta 0:02:11 lr 0.000041	time 0.8105 (0.7672)	model_time 0.8100 (0.7514)	loss 3.0843 (2.5592)	grad_norm 1.2459 (2.5104/0.9636)	mem 34604MB
[2025-01-19 22:01:21 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][150/312]	eta 0:02:04 lr 0.000041	time 0.7099 (0.7654)	model_time 0.7098 (0.7507)	loss 2.6476 (2.5403)	grad_norm 1.5521 (2.5004/0.9548)	mem 34604MB
[2025-01-19 22:01:29 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][160/312]	eta 0:01:56 lr 0.000041	time 0.7229 (0.7640)	model_time 0.7227 (0.7502)	loss 2.6940 (2.5497)	grad_norm 2.5663 (2.4797/0.9456)	mem 34604MB
[2025-01-19 22:01:36 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][170/312]	eta 0:01:48 lr 0.000041	time 0.7398 (0.7621)	model_time 0.7396 (0.7491)	loss 1.8963 (2.5589)	grad_norm 1.5232 (2.4772/0.9604)	mem 34604MB
[2025-01-19 22:01:43 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][180/312]	eta 0:01:40 lr 0.000041	time 0.7371 (0.7604)	model_time 0.7366 (0.7481)	loss 2.2755 (2.5602)	grad_norm 2.5464 (2.4586/0.9458)	mem 34604MB
[2025-01-19 22:01:51 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][190/312]	eta 0:01:32 lr 0.000041	time 0.7408 (0.7592)	model_time 0.7403 (0.7475)	loss 3.1194 (2.5781)	grad_norm 2.0203 (2.4538/0.9423)	mem 34604MB
[2025-01-19 22:01:58 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][200/312]	eta 0:01:24 lr 0.000041	time 0.7186 (0.7576)	model_time 0.7184 (0.7464)	loss 2.7257 (2.5847)	grad_norm 4.2714 (2.4985/0.9861)	mem 34604MB
[2025-01-19 22:02:05 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][210/312]	eta 0:01:17 lr 0.000041	time 0.7268 (0.7564)	model_time 0.7266 (0.7458)	loss 2.8513 (2.5807)	grad_norm 3.2908 (2.5286/0.9979)	mem 34604MB
[2025-01-19 22:02:13 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][220/312]	eta 0:01:09 lr 0.000041	time 0.7187 (0.7567)	model_time 0.7182 (0.7466)	loss 2.9238 (2.5749)	grad_norm 6.3683 (2.5972/1.1099)	mem 34604MB
[2025-01-19 22:02:21 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][230/312]	eta 0:01:02 lr 0.000041	time 0.8467 (0.7565)	model_time 0.8462 (0.7468)	loss 2.0124 (2.5767)	grad_norm 2.1904 (2.5857/1.0983)	mem 34604MB
[2025-01-19 22:02:29 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][240/312]	eta 0:00:54 lr 0.000041	time 0.8146 (0.7589)	model_time 0.8145 (0.7495)	loss 2.9296 (2.5866)	grad_norm 4.9692 (2.5777/1.0950)	mem 34604MB
[2025-01-19 22:02:37 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][250/312]	eta 0:00:47 lr 0.000041	time 0.8296 (0.7600)	model_time 0.8294 (0.7510)	loss 1.9657 (2.5836)	grad_norm 3.3268 (2.5642/1.0850)	mem 34604MB
[2025-01-19 22:02:44 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][260/312]	eta 0:00:39 lr 0.000041	time 0.8053 (0.7595)	model_time 0.8051 (0.7508)	loss 2.6420 (2.5782)	grad_norm 2.8088 (2.5576/1.0762)	mem 34604MB
[2025-01-19 22:02:52 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][270/312]	eta 0:00:31 lr 0.000040	time 0.7178 (0.7589)	model_time 0.7177 (0.7506)	loss 2.5660 (2.5686)	grad_norm 4.8935 (2.5736/1.0802)	mem 34604MB
[2025-01-19 22:02:59 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][280/312]	eta 0:00:24 lr 0.000040	time 0.7265 (0.7579)	model_time 0.7260 (0.7499)	loss 1.8778 (2.5678)	grad_norm 1.8310 (2.5609/1.0693)	mem 34604MB
[2025-01-19 22:03:06 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][290/312]	eta 0:00:16 lr 0.000040	time 0.7550 (0.7570)	model_time 0.7546 (0.7492)	loss 2.4322 (2.5741)	grad_norm 2.5950 (2.5600/1.0560)	mem 34604MB
[2025-01-19 22:03:13 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][300/312]	eta 0:00:09 lr 0.000040	time 0.7160 (0.7559)	model_time 0.7159 (0.7483)	loss 1.7206 (2.5713)	grad_norm 2.5020 (2.5593/1.0484)	mem 34604MB
[2025-01-19 22:03:21 internimage_b_1k_224] (main.py 510): INFO Train: [297/300][310/312]	eta 0:00:01 lr 0.000040	time 0.7180 (0.7553)	model_time 0.7179 (0.7479)	loss 2.6153 (2.5718)	grad_norm 2.3679 (2.5162/1.0222)	mem 34604MB
[2025-01-19 22:03:21 internimage_b_1k_224] (main.py 519): INFO EPOCH 297 training takes 0:03:55
[2025-01-19 22:03:21 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_297.pth saving......
[2025-01-19 22:03:25 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_297.pth saved !!!
[2025-01-19 22:03:32 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.348 (7.348)	Loss 0.6850 (0.6850)	Acc@1 86.792 (86.792)	Acc@5 98.047 (98.047)	Mem 34604MB
[2025-01-19 22:03:35 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.932)	Loss 0.8789 (0.7691)	Acc@1 81.494 (84.888)	Acc@5 96.094 (97.086)	Mem 34604MB
[2025-01-19 22:03:35 internimage_b_1k_224] (main.py 575): INFO [Epoch:297] * Acc@1 84.721 Acc@5 97.087
[2025-01-19 22:03:35 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.7%
[2025-01-19 22:03:35 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 22:03:39 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 22:03:39 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.72%
[2025-01-19 22:03:46 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.246 (7.246)	Loss 0.7003 (0.7003)	Acc@1 86.792 (86.792)	Acc@5 98.218 (98.218)	Mem 34604MB
[2025-01-19 22:03:49 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.941)	Loss 0.8936 (0.7813)	Acc@1 81.348 (84.883)	Acc@5 96.143 (97.141)	Mem 34604MB
[2025-01-19 22:03:49 internimage_b_1k_224] (main.py 575): INFO [Epoch:297] * Acc@1 84.723 Acc@5 97.143
[2025-01-19 22:03:49 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.7%
[2025-01-19 22:03:49 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.73%
[2025-01-19 22:03:53 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][0/312]	eta 0:17:56 lr 0.000040	time 3.4500 (3.4500)	model_time 1.7373 (1.7373)	loss 2.6507 (2.6507)	grad_norm 3.0045 (3.0045/0.0000)	mem 34604MB
[2025-01-19 22:04:00 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][10/312]	eta 0:04:55 lr 0.000040	time 0.7407 (0.9800)	model_time 0.7405 (0.8240)	loss 2.7945 (2.6853)	grad_norm 2.0312 (3.0247/0.8852)	mem 34604MB
[2025-01-19 22:04:07 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][20/312]	eta 0:04:13 lr 0.000040	time 0.7427 (0.8679)	model_time 0.7423 (0.7860)	loss 2.1272 (2.6917)	grad_norm 3.2548 (3.2092/1.0215)	mem 34604MB
[2025-01-19 22:04:15 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][30/312]	eta 0:03:53 lr 0.000040	time 0.7196 (0.8286)	model_time 0.7192 (0.7730)	loss 2.1794 (2.6521)	grad_norm 2.6628 (2.9358/0.9926)	mem 34604MB
[2025-01-19 22:04:22 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][40/312]	eta 0:03:40 lr 0.000040	time 0.7365 (0.8098)	model_time 0.7363 (0.7677)	loss 3.1270 (2.7181)	grad_norm 2.1675 (2.8232/0.9788)	mem 34604MB
[2025-01-19 22:04:30 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][50/312]	eta 0:03:31 lr 0.000040	time 0.8030 (0.8074)	model_time 0.8028 (0.7735)	loss 3.1411 (2.6693)	grad_norm 3.9008 (2.7741/0.9493)	mem 34604MB
[2025-01-19 22:04:38 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][60/312]	eta 0:03:21 lr 0.000040	time 0.7161 (0.8012)	model_time 0.7157 (0.7728)	loss 3.0792 (2.6703)	grad_norm 1.9923 (2.7302/0.9530)	mem 34604MB
[2025-01-19 22:04:46 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][70/312]	eta 0:03:12 lr 0.000040	time 0.7114 (0.7937)	model_time 0.7112 (0.7693)	loss 2.8549 (2.6361)	grad_norm 3.2840 (2.7299/0.9788)	mem 34604MB
[2025-01-19 22:04:53 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][80/312]	eta 0:03:02 lr 0.000040	time 0.7968 (0.7868)	model_time 0.7964 (0.7653)	loss 3.2373 (2.6657)	grad_norm 2.3002 (2.6878/0.9413)	mem 34604MB
[2025-01-19 22:05:00 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][90/312]	eta 0:02:53 lr 0.000040	time 0.7190 (0.7810)	model_time 0.7185 (0.7618)	loss 2.2869 (2.6674)	grad_norm 2.8735 (2.6694/0.9086)	mem 34604MB
[2025-01-19 22:05:08 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][100/312]	eta 0:02:44 lr 0.000040	time 0.7175 (0.7762)	model_time 0.7174 (0.7589)	loss 2.8492 (2.6622)	grad_norm 2.4403 (2.6660/0.9162)	mem 34604MB
[2025-01-19 22:05:15 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][110/312]	eta 0:02:35 lr 0.000040	time 0.7369 (0.7722)	model_time 0.7365 (0.7564)	loss 1.6465 (2.6409)	grad_norm 2.4924 (2.6577/0.9097)	mem 34604MB
[2025-01-19 22:05:22 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][120/312]	eta 0:02:27 lr 0.000040	time 0.7188 (0.7689)	model_time 0.7186 (0.7544)	loss 2.7410 (2.6479)	grad_norm 2.2028 (2.5927/0.9316)	mem 34604MB
[2025-01-19 22:05:30 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][130/312]	eta 0:02:19 lr 0.000040	time 0.7213 (0.7656)	model_time 0.7209 (0.7522)	loss 2.4992 (2.6449)	grad_norm 1.3918 (2.5531/0.9238)	mem 34604MB
[2025-01-19 22:05:37 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][140/312]	eta 0:02:11 lr 0.000040	time 0.7307 (0.7632)	model_time 0.7303 (0.7508)	loss 2.3000 (2.6373)	grad_norm 3.9650 (2.5790/0.9402)	mem 34604MB
[2025-01-19 22:05:44 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][150/312]	eta 0:02:03 lr 0.000040	time 0.7239 (0.7622)	model_time 0.7238 (0.7505)	loss 2.1857 (2.6407)	grad_norm 2.0149 (2.6058/0.9432)	mem 34604MB
[2025-01-19 22:05:52 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][160/312]	eta 0:01:55 lr 0.000040	time 0.7166 (0.7616)	model_time 0.7164 (0.7506)	loss 2.1444 (2.6279)	grad_norm 2.2888 (2.5867/0.9350)	mem 34604MB
[2025-01-19 22:06:00 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][170/312]	eta 0:01:48 lr 0.000040	time 0.7153 (0.7627)	model_time 0.7151 (0.7524)	loss 2.7396 (2.6214)	grad_norm 2.1593 (2.5809/0.9564)	mem 34604MB
[2025-01-19 22:06:07 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][180/312]	eta 0:01:40 lr 0.000040	time 0.7166 (0.7637)	model_time 0.7164 (0.7538)	loss 1.6040 (2.6114)	grad_norm 1.6368 (2.5505/0.9506)	mem 34604MB
[2025-01-19 22:06:15 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][190/312]	eta 0:01:32 lr 0.000040	time 0.7245 (0.7623)	model_time 0.7243 (0.7529)	loss 2.0887 (2.6030)	grad_norm 1.6883 (2.5373/0.9370)	mem 34604MB
[2025-01-19 22:06:22 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][200/312]	eta 0:01:25 lr 0.000040	time 0.8032 (0.7615)	model_time 0.8031 (0.7527)	loss 2.8017 (2.6107)	grad_norm 3.6973 (2.5785/0.9676)	mem 34604MB
[2025-01-19 22:06:30 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][210/312]	eta 0:01:17 lr 0.000040	time 0.7171 (0.7602)	model_time 0.7169 (0.7517)	loss 3.1398 (2.6038)	grad_norm 4.2646 (2.5856/0.9544)	mem 34604MB
[2025-01-19 22:06:37 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][220/312]	eta 0:01:09 lr 0.000040	time 0.7171 (0.7587)	model_time 0.7167 (0.7506)	loss 2.3896 (2.6021)	grad_norm 2.3779 (2.6200/0.9919)	mem 34604MB
[2025-01-19 22:06:44 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][230/312]	eta 0:01:02 lr 0.000040	time 0.7148 (0.7575)	model_time 0.7146 (0.7497)	loss 2.5379 (2.6010)	grad_norm 3.1780 (2.6451/1.0020)	mem 34604MB
[2025-01-19 22:06:52 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][240/312]	eta 0:00:54 lr 0.000040	time 0.7188 (0.7564)	model_time 0.7187 (0.7490)	loss 2.7235 (2.5967)	grad_norm 1.7357 (2.6339/0.9962)	mem 34604MB
[2025-01-19 22:06:59 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][250/312]	eta 0:00:46 lr 0.000040	time 0.7553 (0.7553)	model_time 0.7551 (0.7481)	loss 2.7487 (2.5981)	grad_norm 2.9675 (2.6381/1.0117)	mem 34604MB
[2025-01-19 22:07:06 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][260/312]	eta 0:00:39 lr 0.000040	time 0.7294 (0.7545)	model_time 0.7292 (0.7476)	loss 2.4831 (2.6035)	grad_norm 1.7330 (2.6563/1.0270)	mem 34604MB
[2025-01-19 22:07:14 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][270/312]	eta 0:00:31 lr 0.000040	time 0.8119 (0.7543)	model_time 0.8114 (0.7476)	loss 2.4261 (2.6075)	grad_norm 2.9295 (2.6637/1.0237)	mem 34604MB
[2025-01-19 22:07:21 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][280/312]	eta 0:00:24 lr 0.000040	time 0.7461 (0.7541)	model_time 0.7459 (0.7477)	loss 3.1669 (2.6024)	grad_norm 1.4930 (2.6736/1.0304)	mem 34604MB
[2025-01-19 22:07:29 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][290/312]	eta 0:00:16 lr 0.000040	time 0.7182 (0.7550)	model_time 0.7181 (0.7488)	loss 2.8389 (2.6032)	grad_norm 3.9825 (2.6737/1.0237)	mem 34604MB
[2025-01-19 22:07:37 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][300/312]	eta 0:00:09 lr 0.000040	time 0.8215 (0.7556)	model_time 0.8214 (0.7496)	loss 2.6010 (2.5959)	grad_norm 1.7152 (2.6759/1.0288)	mem 34604MB
[2025-01-19 22:07:44 internimage_b_1k_224] (main.py 510): INFO Train: [298/300][310/312]	eta 0:00:01 lr 0.000040	time 0.7153 (0.7549)	model_time 0.7152 (0.7491)	loss 2.8708 (2.5892)	grad_norm 2.2795 (2.6380/1.0268)	mem 34604MB
[2025-01-19 22:07:45 internimage_b_1k_224] (main.py 519): INFO EPOCH 298 training takes 0:03:55
[2025-01-19 22:07:45 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_298.pth saving......
[2025-01-19 22:07:48 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_298.pth saved !!!
[2025-01-19 22:07:56 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.364 (7.364)	Loss 0.6859 (0.6859)	Acc@1 86.426 (86.426)	Acc@5 97.998 (97.998)	Mem 34604MB
[2025-01-19 22:07:59 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.182 (0.955)	Loss 0.8814 (0.7703)	Acc@1 81.641 (84.846)	Acc@5 96.167 (97.053)	Mem 34604MB
[2025-01-19 22:07:59 internimage_b_1k_224] (main.py 575): INFO [Epoch:298] * Acc@1 84.651 Acc@5 97.055
[2025-01-19 22:07:59 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.7%
[2025-01-19 22:07:59 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.72%
[2025-01-19 22:08:08 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.500 (9.500)	Loss 0.7000 (0.7000)	Acc@1 86.792 (86.792)	Acc@5 98.218 (98.218)	Mem 34604MB
[2025-01-19 22:08:13 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.276)	Loss 0.8932 (0.7809)	Acc@1 81.348 (84.885)	Acc@5 96.167 (97.148)	Mem 34604MB
[2025-01-19 22:08:13 internimage_b_1k_224] (main.py 575): INFO [Epoch:298] * Acc@1 84.721 Acc@5 97.147
[2025-01-19 22:08:13 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.7%
[2025-01-19 22:08:13 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.73%
[2025-01-19 22:08:16 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][0/312]	eta 0:16:46 lr 0.000040	time 3.2247 (3.2247)	model_time 1.2935 (1.2935)	loss 2.8951 (2.8951)	grad_norm 2.1248 (2.1248/0.0000)	mem 34604MB
[2025-01-19 22:08:24 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][10/312]	eta 0:04:56 lr 0.000040	time 0.7275 (0.9804)	model_time 0.7271 (0.8045)	loss 2.8650 (2.8348)	grad_norm 2.5629 (2.2133/0.5079)	mem 34604MB
[2025-01-19 22:08:31 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][20/312]	eta 0:04:12 lr 0.000040	time 0.7326 (0.8642)	model_time 0.7321 (0.7720)	loss 2.2861 (2.6785)	grad_norm 2.9241 (2.1496/0.7171)	mem 34604MB
[2025-01-19 22:08:39 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][30/312]	eta 0:03:51 lr 0.000040	time 0.7404 (0.8198)	model_time 0.7400 (0.7571)	loss 2.5755 (2.6095)	grad_norm 3.3765 (2.2370/0.7220)	mem 34604MB
[2025-01-19 22:08:46 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][40/312]	eta 0:03:37 lr 0.000040	time 0.7172 (0.7982)	model_time 0.7171 (0.7508)	loss 2.3026 (2.5803)	grad_norm 3.4423 (2.2646/0.7501)	mem 34604MB
[2025-01-19 22:08:53 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][50/312]	eta 0:03:25 lr 0.000040	time 0.7193 (0.7857)	model_time 0.7192 (0.7475)	loss 2.9866 (2.5600)	grad_norm 2.4048 (2.2822/0.8887)	mem 34604MB
[2025-01-19 22:09:01 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][60/312]	eta 0:03:15 lr 0.000040	time 0.7192 (0.7759)	model_time 0.7190 (0.7439)	loss 2.7073 (2.5575)	grad_norm 5.2101 (2.4264/1.0767)	mem 34604MB
[2025-01-19 22:09:08 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][70/312]	eta 0:03:06 lr 0.000040	time 0.7117 (0.7697)	model_time 0.7113 (0.7422)	loss 2.5569 (2.5711)	grad_norm 4.1218 (2.4175/1.0594)	mem 34604MB
[2025-01-19 22:09:15 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][80/312]	eta 0:02:58 lr 0.000040	time 0.8168 (0.7686)	model_time 0.8166 (0.7444)	loss 2.2251 (2.5763)	grad_norm 2.0234 (2.4480/1.0341)	mem 34604MB
[2025-01-19 22:09:23 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][90/312]	eta 0:02:49 lr 0.000040	time 0.7300 (0.7655)	model_time 0.7299 (0.7440)	loss 3.0147 (2.5954)	grad_norm 1.8760 (2.4781/1.0320)	mem 34604MB
[2025-01-19 22:09:31 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][100/312]	eta 0:02:42 lr 0.000040	time 0.8213 (0.7669)	model_time 0.8209 (0.7474)	loss 2.3586 (2.5858)	grad_norm 1.6305 (2.5436/1.0711)	mem 34604MB
[2025-01-19 22:09:39 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][110/312]	eta 0:02:35 lr 0.000040	time 0.8131 (0.7695)	model_time 0.8129 (0.7518)	loss 2.2024 (2.5901)	grad_norm 6.5219 (2.6896/1.2609)	mem 34604MB
[2025-01-19 22:09:46 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][120/312]	eta 0:02:27 lr 0.000040	time 0.7248 (0.7661)	model_time 0.7246 (0.7498)	loss 2.8435 (2.5750)	grad_norm 3.7911 (2.7091/1.2504)	mem 34604MB
[2025-01-19 22:09:53 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][130/312]	eta 0:02:19 lr 0.000040	time 0.7247 (0.7648)	model_time 0.7246 (0.7497)	loss 2.9265 (2.5830)	grad_norm 2.0290 (2.6868/1.2350)	mem 34604MB
[2025-01-19 22:10:01 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][140/312]	eta 0:02:11 lr 0.000040	time 0.8104 (0.7628)	model_time 0.8099 (0.7488)	loss 2.6892 (2.5891)	grad_norm 2.7636 (2.6453/1.2157)	mem 34604MB
[2025-01-19 22:10:08 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][150/312]	eta 0:02:03 lr 0.000040	time 0.7283 (0.7603)	model_time 0.7281 (0.7471)	loss 1.8993 (2.5950)	grad_norm 2.5693 (2.6847/1.2413)	mem 34604MB
[2025-01-19 22:10:15 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][160/312]	eta 0:01:55 lr 0.000040	time 0.7570 (0.7587)	model_time 0.7568 (0.7464)	loss 2.9546 (2.5828)	grad_norm 2.3385 (2.6709/1.2380)	mem 34604MB
[2025-01-19 22:10:23 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][170/312]	eta 0:01:47 lr 0.000040	time 0.7162 (0.7571)	model_time 0.7157 (0.7455)	loss 1.9541 (2.5744)	grad_norm 1.7043 (2.6757/1.2561)	mem 34604MB
[2025-01-19 22:10:30 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][180/312]	eta 0:01:39 lr 0.000040	time 0.7196 (0.7553)	model_time 0.7191 (0.7443)	loss 2.2532 (2.5708)	grad_norm 2.6546 (2.6863/1.2512)	mem 34604MB
[2025-01-19 22:10:37 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][190/312]	eta 0:01:31 lr 0.000040	time 0.7315 (0.7541)	model_time 0.7310 (0.7436)	loss 2.3453 (2.5691)	grad_norm 1.7192 (2.6770/1.2266)	mem 34604MB
[2025-01-19 22:10:45 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][200/312]	eta 0:01:24 lr 0.000040	time 0.7267 (0.7539)	model_time 0.7265 (0.7440)	loss 2.5141 (2.5625)	grad_norm 2.4557 (2.6483/1.2129)	mem 34604MB
[2025-01-19 22:10:53 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][210/312]	eta 0:01:17 lr 0.000040	time 0.7140 (0.7550)	model_time 0.7139 (0.7455)	loss 3.0419 (2.5747)	grad_norm 1.5186 (2.6517/1.2027)	mem 34604MB
[2025-01-19 22:11:00 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][220/312]	eta 0:01:09 lr 0.000040	time 0.8219 (0.7566)	model_time 0.8215 (0.7475)	loss 2.8883 (2.5842)	grad_norm 1.5966 (2.6562/1.1932)	mem 34604MB
[2025-01-19 22:11:08 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][230/312]	eta 0:01:02 lr 0.000040	time 0.8179 (0.7579)	model_time 0.8177 (0.7492)	loss 2.6310 (2.5830)	grad_norm 2.0325 (2.6291/1.1786)	mem 34604MB
[2025-01-19 22:11:16 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][240/312]	eta 0:00:54 lr 0.000040	time 0.7163 (0.7567)	model_time 0.7162 (0.7483)	loss 2.7354 (2.5923)	grad_norm 1.7994 (2.6314/1.1647)	mem 34604MB
[2025-01-19 22:11:23 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][250/312]	eta 0:00:46 lr 0.000040	time 0.7229 (0.7564)	model_time 0.7224 (0.7484)	loss 2.6490 (2.5987)	grad_norm 5.2280 (2.6264/1.1575)	mem 34604MB
[2025-01-19 22:11:30 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][260/312]	eta 0:00:39 lr 0.000040	time 0.8176 (0.7554)	model_time 0.8174 (0.7477)	loss 2.8268 (2.5969)	grad_norm 3.2298 (2.6231/1.1452)	mem 34604MB
[2025-01-19 22:11:38 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][270/312]	eta 0:00:31 lr 0.000040	time 0.7467 (0.7545)	model_time 0.7465 (0.7471)	loss 2.9181 (2.6017)	grad_norm 2.5210 (2.6213/1.1420)	mem 34604MB
[2025-01-19 22:11:45 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][280/312]	eta 0:00:24 lr 0.000040	time 0.7257 (0.7537)	model_time 0.7255 (0.7465)	loss 1.9577 (2.5955)	grad_norm 4.2052 (2.6229/1.1322)	mem 34604MB
[2025-01-19 22:11:52 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][290/312]	eta 0:00:16 lr 0.000040	time 0.7222 (0.7530)	model_time 0.7220 (0.7460)	loss 2.3559 (2.5995)	grad_norm 1.5918 (2.6005/1.1272)	mem 34604MB
[2025-01-19 22:12:00 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][300/312]	eta 0:00:09 lr 0.000040	time 0.7137 (0.7521)	model_time 0.7136 (0.7453)	loss 2.1009 (2.6010)	grad_norm 1.7927 (2.5775/1.1220)	mem 34604MB
[2025-01-19 22:12:07 internimage_b_1k_224] (main.py 510): INFO Train: [299/300][310/312]	eta 0:00:01 lr 0.000040	time 0.7176 (0.7514)	model_time 0.7175 (0.7449)	loss 2.7759 (2.6067)	grad_norm 2.9771 (2.6024/1.1359)	mem 34604MB
[2025-01-19 22:12:08 internimage_b_1k_224] (main.py 519): INFO EPOCH 299 training takes 0:03:54
[2025-01-19 22:12:08 internimage_b_1k_224] (utils.py 359): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_299.pth saving......
[2025-01-19 22:12:11 internimage_b_1k_224] (utils.py 361): INFO work_dirs/internimage_b_1k_224/ckpt_epoch_299.pth saved !!!
[2025-01-19 22:12:18 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.271 (7.271)	Loss 0.6923 (0.6923)	Acc@1 86.768 (86.768)	Acc@5 97.974 (97.974)	Mem 34604MB
[2025-01-19 22:12:21 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (0.929)	Loss 0.8858 (0.7721)	Acc@1 81.470 (84.854)	Acc@5 96.143 (97.057)	Mem 34604MB
[2025-01-19 22:12:22 internimage_b_1k_224] (main.py 575): INFO [Epoch:299] * Acc@1 84.671 Acc@5 97.063
[2025-01-19 22:12:22 internimage_b_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.7%
[2025-01-19 22:12:22 internimage_b_1k_224] (main.py 355): INFO Max accuracy: 84.72%
[2025-01-19 22:12:31 internimage_b_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.356 (9.356)	Loss 0.6996 (0.6996)	Acc@1 86.768 (86.768)	Acc@5 98.242 (98.242)	Mem 34604MB
[2025-01-19 22:12:35 internimage_b_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.181 (1.261)	Loss 0.8928 (0.7805)	Acc@1 81.323 (84.892)	Acc@5 96.167 (97.150)	Mem 34604MB
[2025-01-19 22:12:36 internimage_b_1k_224] (main.py 575): INFO [Epoch:299] * Acc@1 84.727 Acc@5 97.147
[2025-01-19 22:12:36 internimage_b_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.7%
[2025-01-19 22:12:36 internimage_b_1k_224] (main.py 375): INFO Max ema accuracy: 84.73%
[2025-01-19 22:12:36 internimage_b_1k_224] (main.py 379): INFO Training time 11:49:07