[2025-01-18 12:14:20 internimage_s_1k_224] (main.py 665): INFO Full config saved to work_dirs/internimage_s_1k_224/config.json
[2025-01-18 12:14:20 internimage_s_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: 0.4
  DROP_PATH_TYPE: linear
  DROP_RATE: 0.0
  INTERN_IMAGE:
    CENTER_FEATURE_SCALE: false
    CHANNELS: 80
    CORE_OP: DCNv3
    DEPTHS:
    - 4
    - 4
    - 21
    - 4
    DW_KERNEL_SIZE: null
    GROUPS:
    - 5
    - 10
    - 20
    - 40
    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_s_1k_224
  NUM_CLASSES: 1000
  PRETRAINED: ''
  RESUME: ''
  TYPE: intern_image
OUTPUT: work_dirs/internimage_s_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 12:19:46 internimage_s_1k_224] (main.py 174): INFO Creating model:intern_image/internimage_s_1k_224
[2025-01-18 12:20:12 internimage_s_1k_224] (main.py 177): INFO InternImage(
  (patch_embed): StemLayer(
    (conv1): Conv2d(3, 40, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
    (norm1): Sequential(
      (0): to_channels_last()
      (1): LayerNorm((40,), eps=1e-06, elementwise_affine=True)
      (2): to_channels_first()
    )
    (act): GELU()
    (conv2): Conv2d(40, 80, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
    (norm2): Sequential(
      (0): to_channels_last()
      (1): LayerNorm((80,), 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((80,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=80)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((80,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=80, out_features=90, bias=True)
            (mask): Linear(in_features=80, out_features=45, bias=True)
            (input_proj): Linear(in_features=80, out_features=80, bias=True)
            (output_proj): Linear(in_features=80, out_features=80, bias=True)
          )
          (drop_path): Identity()
          (norm2): Sequential(
            (0): LayerNorm((80,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=80, out_features=320, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=320, out_features=80, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (1): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((80,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=80)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((80,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=80, out_features=90, bias=True)
            (mask): Linear(in_features=80, out_features=45, bias=True)
            (input_proj): Linear(in_features=80, out_features=80, bias=True)
            (output_proj): Linear(in_features=80, out_features=80, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.013)
          (norm2): Sequential(
            (0): LayerNorm((80,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=80, out_features=320, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=320, out_features=80, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (2): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((80,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=80)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((80,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=80, out_features=90, bias=True)
            (mask): Linear(in_features=80, out_features=45, bias=True)
            (input_proj): Linear(in_features=80, out_features=80, bias=True)
            (output_proj): Linear(in_features=80, out_features=80, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.025)
          (norm2): Sequential(
            (0): LayerNorm((80,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=80, out_features=320, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=320, out_features=80, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (3): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((80,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=80)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((80,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=80, out_features=90, bias=True)
            (mask): Linear(in_features=80, out_features=45, bias=True)
            (input_proj): Linear(in_features=80, out_features=80, bias=True)
            (output_proj): Linear(in_features=80, out_features=80, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.038)
          (norm2): Sequential(
            (0): LayerNorm((80,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=80, out_features=320, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=320, out_features=80, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
      )
      (downsample): DownsampleLayer(
        (conv): Conv2d(80, 160, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        (norm): Sequential(
          (0): to_channels_last()
          (1): LayerNorm((160,), eps=1e-06, elementwise_affine=True)
        )
      )
    )
    (1): InternImageBlock(
      (blocks): ModuleList(
        (0): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((160,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=160)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((160,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=160, out_features=180, bias=True)
            (mask): Linear(in_features=160, out_features=90, bias=True)
            (input_proj): Linear(in_features=160, out_features=160, bias=True)
            (output_proj): Linear(in_features=160, out_features=160, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.050)
          (norm2): Sequential(
            (0): LayerNorm((160,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=160, out_features=640, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=640, out_features=160, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (1): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((160,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=160)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((160,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=160, out_features=180, bias=True)
            (mask): Linear(in_features=160, out_features=90, bias=True)
            (input_proj): Linear(in_features=160, out_features=160, bias=True)
            (output_proj): Linear(in_features=160, out_features=160, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.062)
          (norm2): Sequential(
            (0): LayerNorm((160,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=160, out_features=640, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=640, out_features=160, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (2): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((160,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=160)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((160,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=160, out_features=180, bias=True)
            (mask): Linear(in_features=160, out_features=90, bias=True)
            (input_proj): Linear(in_features=160, out_features=160, bias=True)
            (output_proj): Linear(in_features=160, out_features=160, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.075)
          (norm2): Sequential(
            (0): LayerNorm((160,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=160, out_features=640, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=640, out_features=160, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (3): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((160,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=160)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((160,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=160, out_features=180, bias=True)
            (mask): Linear(in_features=160, out_features=90, bias=True)
            (input_proj): Linear(in_features=160, out_features=160, bias=True)
            (output_proj): Linear(in_features=160, out_features=160, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.087)
          (norm2): Sequential(
            (0): LayerNorm((160,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=160, out_features=640, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=640, out_features=160, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
      )
      (downsample): DownsampleLayer(
        (conv): Conv2d(160, 320, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        (norm): Sequential(
          (0): to_channels_last()
          (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
        )
      )
    )
    (2): InternImageBlock(
      (blocks): ModuleList(
        (0): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=320, out_features=360, bias=True)
            (mask): Linear(in_features=320, out_features=180, bias=True)
            (input_proj): Linear(in_features=320, out_features=320, bias=True)
            (output_proj): Linear(in_features=320, out_features=320, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.100)
          (norm2): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=320, out_features=1280, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1280, out_features=320, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (1): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=320, out_features=360, bias=True)
            (mask): Linear(in_features=320, out_features=180, bias=True)
            (input_proj): Linear(in_features=320, out_features=320, bias=True)
            (output_proj): Linear(in_features=320, out_features=320, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.113)
          (norm2): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=320, out_features=1280, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1280, out_features=320, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (2): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=320, out_features=360, bias=True)
            (mask): Linear(in_features=320, out_features=180, bias=True)
            (input_proj): Linear(in_features=320, out_features=320, bias=True)
            (output_proj): Linear(in_features=320, out_features=320, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.125)
          (norm2): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=320, out_features=1280, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1280, out_features=320, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (3): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=320, out_features=360, bias=True)
            (mask): Linear(in_features=320, out_features=180, bias=True)
            (input_proj): Linear(in_features=320, out_features=320, bias=True)
            (output_proj): Linear(in_features=320, out_features=320, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.138)
          (norm2): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=320, out_features=1280, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1280, out_features=320, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (4): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=320, out_features=360, bias=True)
            (mask): Linear(in_features=320, out_features=180, bias=True)
            (input_proj): Linear(in_features=320, out_features=320, bias=True)
            (output_proj): Linear(in_features=320, out_features=320, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.150)
          (norm2): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=320, out_features=1280, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1280, out_features=320, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (5): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=320, out_features=360, bias=True)
            (mask): Linear(in_features=320, out_features=180, bias=True)
            (input_proj): Linear(in_features=320, out_features=320, bias=True)
            (output_proj): Linear(in_features=320, out_features=320, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.162)
          (norm2): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=320, out_features=1280, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1280, out_features=320, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (6): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=320, out_features=360, bias=True)
            (mask): Linear(in_features=320, out_features=180, bias=True)
            (input_proj): Linear(in_features=320, out_features=320, bias=True)
            (output_proj): Linear(in_features=320, out_features=320, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.175)
          (norm2): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=320, out_features=1280, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1280, out_features=320, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (7): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=320, out_features=360, bias=True)
            (mask): Linear(in_features=320, out_features=180, bias=True)
            (input_proj): Linear(in_features=320, out_features=320, bias=True)
            (output_proj): Linear(in_features=320, out_features=320, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.188)
          (norm2): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=320, out_features=1280, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1280, out_features=320, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (8): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=320, out_features=360, bias=True)
            (mask): Linear(in_features=320, out_features=180, bias=True)
            (input_proj): Linear(in_features=320, out_features=320, bias=True)
            (output_proj): Linear(in_features=320, out_features=320, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.200)
          (norm2): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=320, out_features=1280, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1280, out_features=320, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (9): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=320, out_features=360, bias=True)
            (mask): Linear(in_features=320, out_features=180, bias=True)
            (input_proj): Linear(in_features=320, out_features=320, bias=True)
            (output_proj): Linear(in_features=320, out_features=320, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.213)
          (norm2): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=320, out_features=1280, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1280, out_features=320, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (10): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=320, out_features=360, bias=True)
            (mask): Linear(in_features=320, out_features=180, bias=True)
            (input_proj): Linear(in_features=320, out_features=320, bias=True)
            (output_proj): Linear(in_features=320, out_features=320, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.225)
          (norm2): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=320, out_features=1280, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1280, out_features=320, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (11): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=320, out_features=360, bias=True)
            (mask): Linear(in_features=320, out_features=180, bias=True)
            (input_proj): Linear(in_features=320, out_features=320, bias=True)
            (output_proj): Linear(in_features=320, out_features=320, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.238)
          (norm2): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=320, out_features=1280, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1280, out_features=320, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (12): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=320, out_features=360, bias=True)
            (mask): Linear(in_features=320, out_features=180, bias=True)
            (input_proj): Linear(in_features=320, out_features=320, bias=True)
            (output_proj): Linear(in_features=320, out_features=320, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.250)
          (norm2): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=320, out_features=1280, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1280, out_features=320, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (13): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=320, out_features=360, bias=True)
            (mask): Linear(in_features=320, out_features=180, bias=True)
            (input_proj): Linear(in_features=320, out_features=320, bias=True)
            (output_proj): Linear(in_features=320, out_features=320, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.262)
          (norm2): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=320, out_features=1280, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1280, out_features=320, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (14): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=320, out_features=360, bias=True)
            (mask): Linear(in_features=320, out_features=180, bias=True)
            (input_proj): Linear(in_features=320, out_features=320, bias=True)
            (output_proj): Linear(in_features=320, out_features=320, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.275)
          (norm2): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=320, out_features=1280, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1280, out_features=320, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (15): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=320, out_features=360, bias=True)
            (mask): Linear(in_features=320, out_features=180, bias=True)
            (input_proj): Linear(in_features=320, out_features=320, bias=True)
            (output_proj): Linear(in_features=320, out_features=320, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.287)
          (norm2): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=320, out_features=1280, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1280, out_features=320, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (16): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=320, out_features=360, bias=True)
            (mask): Linear(in_features=320, out_features=180, bias=True)
            (input_proj): Linear(in_features=320, out_features=320, bias=True)
            (output_proj): Linear(in_features=320, out_features=320, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.300)
          (norm2): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=320, out_features=1280, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1280, out_features=320, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (17): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=320, out_features=360, bias=True)
            (mask): Linear(in_features=320, out_features=180, bias=True)
            (input_proj): Linear(in_features=320, out_features=320, bias=True)
            (output_proj): Linear(in_features=320, out_features=320, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.312)
          (norm2): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=320, out_features=1280, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1280, out_features=320, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (18): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=320, out_features=360, bias=True)
            (mask): Linear(in_features=320, out_features=180, bias=True)
            (input_proj): Linear(in_features=320, out_features=320, bias=True)
            (output_proj): Linear(in_features=320, out_features=320, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.325)
          (norm2): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=320, out_features=1280, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1280, out_features=320, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (19): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=320, out_features=360, bias=True)
            (mask): Linear(in_features=320, out_features=180, bias=True)
            (input_proj): Linear(in_features=320, out_features=320, bias=True)
            (output_proj): Linear(in_features=320, out_features=320, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.338)
          (norm2): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=320, out_features=1280, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1280, out_features=320, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (20): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=320, out_features=360, bias=True)
            (mask): Linear(in_features=320, out_features=180, bias=True)
            (input_proj): Linear(in_features=320, out_features=320, bias=True)
            (output_proj): Linear(in_features=320, out_features=320, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.350)
          (norm2): Sequential(
            (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=320, out_features=1280, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=1280, out_features=320, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
      )
      (downsample): DownsampleLayer(
        (conv): Conv2d(320, 640, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        (norm): Sequential(
          (0): to_channels_last()
          (1): LayerNorm((640,), eps=1e-06, elementwise_affine=True)
        )
      )
    )
    (3): InternImageBlock(
      (blocks): ModuleList(
        (0): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((640,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=640)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((640,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=640, out_features=720, bias=True)
            (mask): Linear(in_features=640, out_features=360, bias=True)
            (input_proj): Linear(in_features=640, out_features=640, bias=True)
            (output_proj): Linear(in_features=640, out_features=640, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.363)
          (norm2): Sequential(
            (0): LayerNorm((640,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=640, out_features=2560, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=2560, out_features=640, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (1): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((640,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=640)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((640,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=640, out_features=720, bias=True)
            (mask): Linear(in_features=640, out_features=360, bias=True)
            (input_proj): Linear(in_features=640, out_features=640, bias=True)
            (output_proj): Linear(in_features=640, out_features=640, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.375)
          (norm2): Sequential(
            (0): LayerNorm((640,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=640, out_features=2560, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=2560, out_features=640, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (2): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((640,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=640)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((640,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=640, out_features=720, bias=True)
            (mask): Linear(in_features=640, out_features=360, bias=True)
            (input_proj): Linear(in_features=640, out_features=640, bias=True)
            (output_proj): Linear(in_features=640, out_features=640, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.388)
          (norm2): Sequential(
            (0): LayerNorm((640,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=640, out_features=2560, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=2560, out_features=640, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
        (3): InternImageLayer(
          (norm1): Sequential(
            (0): LayerNorm((640,), eps=1e-06, elementwise_affine=True)
          )
          (dcn): DCNv3(
            (dw_conv): Sequential(
              (0): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=640)
              (1): Sequential(
                (0): to_channels_last()
                (1): LayerNorm((640,), eps=1e-06, elementwise_affine=True)
              )
              (2): GELU()
            )
            (offset): Linear(in_features=640, out_features=720, bias=True)
            (mask): Linear(in_features=640, out_features=360, bias=True)
            (input_proj): Linear(in_features=640, out_features=640, bias=True)
            (output_proj): Linear(in_features=640, out_features=640, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.400)
          (norm2): Sequential(
            (0): LayerNorm((640,), eps=1e-06, elementwise_affine=True)
          )
          (mlp): MLPLayer(
            (fc1): Linear(in_features=640, out_features=2560, bias=True)
            (act): GELU()
            (fc2): Linear(in_features=2560, out_features=640, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
        )
      )
    )
  )
  (conv_head): Sequential(
    (0): Conv2d(640, 960, kernel_size=(1, 1), stride=(1, 1), bias=False)
    (1): Sequential(
      (0): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (2): GELU()
  )
  (head): Linear(in_features=960, out_features=1000, bias=True)
  (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
)
[2025-01-18 12:20:12 internimage_s_1k_224] (main.py 213): INFO Using native Torch AMP. Training in mixed precision.
[2025-01-18 12:20:12 internimage_s_1k_224] (main.py 225): INFO using fp16_compress_hook!
[2025-01-18 12:20:12 internimage_s_1k_224] (main.py 233): INFO number of params: 50079880
[2025-01-18 12:20:12 internimage_s_1k_224] (main.py 267): INFO no checkpoint found in work_dirs/internimage_s_1k_224, ignoring auto resume
[2025-01-18 12:20:14 internimage_s_1k_224] (main.py 308): INFO Start training
[2025-01-18 12:20:22 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][0/312]	eta 0:38:35 lr 0.000004	time 7.4225 (7.4225)	model_time 3.2736 (3.2736)	loss 6.9117 (6.9117)	grad_norm 0.3462 (0.3462/0.0000)	mem 23722MB
[2025-01-18 12:20:28 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][10/312]	eta 0:06:22 lr 0.000010	time 0.6256 (1.2676)	model_time 0.6251 (0.8901)	loss 6.8884 (6.9260)	grad_norm 0.3171 (0.3344/0.0098)	mem 24307MB
[2025-01-18 12:20:34 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][20/312]	eta 0:04:35 lr 0.000017	time 0.5934 (0.9426)	model_time 0.5932 (0.7447)	loss 6.9270 (6.9218)	grad_norm 0.3208 (0.3298/0.0106)	mem 24307MB
[2025-01-18 12:20:40 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][30/312]	eta 0:03:53 lr 0.000023	time 0.5909 (0.8294)	model_time 0.5908 (0.6952)	loss 6.9289 (6.9227)	grad_norm 0.3223 (0.3257/0.0114)	mem 24307MB
[2025-01-18 12:20:46 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][40/312]	eta 0:03:31 lr 0.000030	time 0.5764 (0.7763)	model_time 0.5760 (0.6748)	loss 6.9220 (6.9186)	grad_norm 0.3023 (0.3231/0.0117)	mem 24307MB
[2025-01-18 12:20:52 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][50/312]	eta 0:03:13 lr 0.000036	time 0.5851 (0.7402)	model_time 0.5849 (0.6585)	loss 6.8620 (6.9144)	grad_norm 0.3141 (0.3203/0.0123)	mem 24307MB
[2025-01-18 12:20:58 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][60/312]	eta 0:03:00 lr 0.000042	time 0.5908 (0.7149)	model_time 0.5906 (0.6466)	loss 6.9056 (6.9107)	grad_norm 0.3061 (0.3181/0.0127)	mem 24307MB
[2025-01-18 12:21:04 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][70/312]	eta 0:02:48 lr 0.000049	time 0.5862 (0.6971)	model_time 0.5861 (0.6383)	loss 6.8831 (6.9064)	grad_norm 0.3029 (0.3153/0.0139)	mem 24307MB
[2025-01-18 12:21:10 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][80/312]	eta 0:02:38 lr 0.000055	time 0.5850 (0.6838)	model_time 0.5848 (0.6323)	loss 6.8627 (6.9014)	grad_norm 0.2960 (0.3129/0.0147)	mem 24307MB
[2025-01-18 12:21:16 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][90/312]	eta 0:02:29 lr 0.000062	time 0.5911 (0.6734)	model_time 0.5907 (0.6275)	loss 6.8830 (6.8972)	grad_norm 0.3040 (0.3110/0.0152)	mem 24307MB
[2025-01-18 12:21:22 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][100/312]	eta 0:02:21 lr 0.000068	time 0.5843 (0.6652)	model_time 0.5842 (0.6238)	loss 6.8637 (6.8935)	grad_norm 0.2958 (0.3097/0.0154)	mem 24307MB
[2025-01-18 12:21:27 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][110/312]	eta 0:02:12 lr 0.000074	time 0.5782 (0.6579)	model_time 0.5780 (0.6202)	loss 6.7998 (6.8892)	grad_norm 0.2989 (0.3081/0.0159)	mem 24307MB
[2025-01-18 12:21:33 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][120/312]	eta 0:02:05 lr 0.000081	time 0.5832 (0.6521)	model_time 0.5830 (0.6175)	loss 6.8078 (6.8844)	grad_norm 0.3121 (0.3080/0.0161)	mem 24307MB
[2025-01-18 12:21:39 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][130/312]	eta 0:01:57 lr 0.000087	time 0.6032 (0.6473)	model_time 0.6027 (0.6153)	loss 6.8486 (6.8800)	grad_norm 0.3155 (0.3098/0.0227)	mem 24307MB
[2025-01-18 12:21:45 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][140/312]	eta 0:01:50 lr 0.000094	time 0.5889 (0.6430)	model_time 0.5887 (0.6133)	loss 6.7844 (6.8757)	grad_norm 0.3941 (0.3141/0.0294)	mem 24307MB
[2025-01-18 12:21:51 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][150/312]	eta 0:01:43 lr 0.000100	time 0.5939 (0.6394)	model_time 0.5937 (0.6116)	loss 6.7673 (6.8713)	grad_norm 0.3326 (0.3236/0.0520)	mem 24307MB
[2025-01-18 12:21:57 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][160/312]	eta 0:01:37 lr 0.000106	time 0.5757 (0.6385)	model_time 0.5755 (0.6124)	loss 6.8705 (6.8680)	grad_norm 0.7607 (0.3443/0.1096)	mem 24307MB
[2025-01-18 12:22:03 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][170/312]	eta 0:01:30 lr 0.000113	time 0.5924 (0.6355)	model_time 0.5921 (0.6110)	loss 6.7869 (6.8640)	grad_norm 0.5872 (0.3529/0.1158)	mem 24307MB
[2025-01-18 12:22:09 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][180/312]	eta 0:01:23 lr 0.000119	time 0.5901 (0.6329)	model_time 0.5897 (0.6097)	loss 6.8044 (6.8592)	grad_norm 0.4030 (0.3556/0.1140)	mem 24307MB
[2025-01-18 12:22:15 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][190/312]	eta 0:01:16 lr 0.000126	time 0.5783 (0.6307)	model_time 0.5782 (0.6087)	loss 6.7284 (6.8552)	grad_norm 0.7794 (0.3664/0.1294)	mem 24307MB
[2025-01-18 12:22:21 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][200/312]	eta 0:01:10 lr 0.000132	time 0.5840 (0.6287)	model_time 0.5838 (0.6078)	loss 6.7427 (6.8499)	grad_norm 0.7586 (0.3849/0.1616)	mem 24307MB
[2025-01-18 12:22:27 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][210/312]	eta 0:01:03 lr 0.000138	time 0.5835 (0.6267)	model_time 0.5834 (0.6067)	loss 6.7653 (6.8464)	grad_norm 0.9425 (0.4014/0.1804)	mem 24307MB
[2025-01-18 12:22:32 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][220/312]	eta 0:00:57 lr 0.000145	time 0.5865 (0.6250)	model_time 0.5864 (0.6059)	loss 6.7987 (6.8426)	grad_norm 1.0046 (0.4234/0.2108)	mem 24307MB
[2025-01-18 12:22:38 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][230/312]	eta 0:00:51 lr 0.000151	time 0.5888 (0.6233)	model_time 0.5886 (0.6051)	loss 6.7312 (6.8393)	grad_norm 1.1788 (0.4483/0.2395)	mem 24307MB
[2025-01-18 12:22:44 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][240/312]	eta 0:00:44 lr 0.000158	time 0.6126 (0.6220)	model_time 0.6124 (0.6045)	loss 6.7269 (6.8351)	grad_norm 1.0851 (0.4770/0.2784)	mem 24307MB
[2025-01-18 12:22:50 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][250/312]	eta 0:00:38 lr 0.000164	time 0.5833 (0.6206)	model_time 0.5830 (0.6037)	loss 6.6763 (6.8303)	grad_norm 1.4898 (0.4987/0.2955)	mem 24307MB
[2025-01-18 12:22:56 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][260/312]	eta 0:00:32 lr 0.000170	time 0.5838 (0.6193)	model_time 0.5837 (0.6031)	loss 6.6985 (6.8253)	grad_norm 0.9887 (0.5301/0.3344)	mem 24307MB
[2025-01-18 12:23:02 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][270/312]	eta 0:00:25 lr 0.000177	time 0.5902 (0.6182)	model_time 0.5901 (0.6026)	loss 6.7103 (6.8214)	grad_norm 0.8448 (0.5689/0.4075)	mem 24307MB
[2025-01-18 12:23:08 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][280/312]	eta 0:00:19 lr 0.000183	time 0.5720 (0.6179)	model_time 0.5718 (0.6028)	loss 6.7156 (6.8188)	grad_norm 1.6340 (0.6134/0.4809)	mem 24307MB
[2025-01-18 12:23:14 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][290/312]	eta 0:00:13 lr 0.000190	time 0.5806 (0.6170)	model_time 0.5804 (0.6024)	loss 6.6051 (6.8145)	grad_norm 1.3136 (0.6554/0.5363)	mem 24307MB
[2025-01-18 12:23:20 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][300/312]	eta 0:00:07 lr 0.000196	time 0.5795 (0.6159)	model_time 0.5791 (0.6018)	loss 6.6957 (6.8096)	grad_norm 2.8203 (0.7053/0.6134)	mem 24307MB
[2025-01-18 12:23:25 internimage_s_1k_224] (main.py 510): INFO Train: [0/300][310/312]	eta 0:00:01 lr 0.000203	time 0.5746 (0.6147)	model_time 0.5745 (0.6011)	loss 6.8031 (6.8080)	grad_norm 2.3550 (0.7860/0.7260)	mem 24307MB
[2025-01-18 12:23:26 internimage_s_1k_224] (main.py 519): INFO EPOCH 0 training takes 0:03:11
[2025-01-18 12:23:26 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_0.pth saving......
[2025-01-18 12:23:28 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_0.pth saved !!!
[2025-01-18 12:23:36 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.121 (8.121)	Loss 6.2715 (6.2715)	Acc@1 1.685 (1.685)	Acc@5 7.446 (7.446)	Mem 24307MB
[2025-01-18 12:23:39 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (1.008)	Loss 6.3636 (6.3701)	Acc@1 1.660 (1.403)	Acc@5 5.420 (5.389)	Mem 24307MB
[2025-01-18 12:23:39 internimage_s_1k_224] (main.py 575): INFO [Epoch:0] * Acc@1 1.839 Acc@5 6.474
[2025-01-18 12:23:39 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 1.8%
[2025-01-18 12:23:39 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 12:23:41 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 12:23:41 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 1.84%
[2025-01-18 12:23:48 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.154 (7.154)	Loss 6.9313 (6.9313)	Acc@1 0.024 (0.024)	Acc@5 0.439 (0.439)	Mem 24307MB
[2025-01-18 12:23:51 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.932)	Loss 6.9050 (6.9189)	Acc@1 0.244 (0.104)	Acc@5 1.416 (0.504)	Mem 24307MB
[2025-01-18 12:23:52 internimage_s_1k_224] (main.py 575): INFO [Epoch:0] * Acc@1 0.114 Acc@5 0.518
[2025-01-18 12:23:52 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.1%
[2025-01-18 12:23:52 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 12:23:54 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 12:23:54 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 0.11%
[2025-01-18 12:23:56 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][0/312]	eta 0:11:26 lr 0.000204	time 2.2005 (2.2005)	model_time 0.6814 (0.6814)	loss 6.7602 (6.7602)	grad_norm 2.3009 (2.3009/0.0000)	mem 24308MB
[2025-01-18 12:24:02 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][10/312]	eta 0:03:43 lr 0.000210	time 0.5964 (0.7405)	model_time 0.5962 (0.6020)	loss 6.7876 (6.7398)	grad_norm 1.9512 (2.0085/0.5716)	mem 24308MB
[2025-01-18 12:24:08 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][20/312]	eta 0:03:15 lr 0.000217	time 0.6182 (0.6688)	model_time 0.6177 (0.5957)	loss 6.7755 (6.7159)	grad_norm 2.4599 (2.0556/0.6014)	mem 24308MB
[2025-01-18 12:24:14 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][30/312]	eta 0:03:01 lr 0.000223	time 0.5974 (0.6422)	model_time 0.5972 (0.5926)	loss 6.7265 (6.7104)	grad_norm 1.5454 (2.0751/0.6159)	mem 24308MB
[2025-01-18 12:24:20 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][40/312]	eta 0:02:50 lr 0.000229	time 0.5867 (0.6284)	model_time 0.5866 (0.5908)	loss 6.6622 (6.7038)	grad_norm 2.6085 (2.2629/0.7959)	mem 24308MB
[2025-01-18 12:24:25 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][50/312]	eta 0:02:42 lr 0.000236	time 0.5836 (0.6197)	model_time 0.5834 (0.5894)	loss 6.6552 (6.6941)	grad_norm 1.8188 (2.3227/0.7747)	mem 24308MB
[2025-01-18 12:24:31 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][60/312]	eta 0:02:34 lr 0.000242	time 0.5874 (0.6139)	model_time 0.5869 (0.5884)	loss 6.6414 (6.6857)	grad_norm 2.7178 (2.3283/0.7205)	mem 24308MB
[2025-01-18 12:24:37 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][70/312]	eta 0:02:27 lr 0.000249	time 0.5824 (0.6099)	model_time 0.5819 (0.5879)	loss 6.5459 (6.6788)	grad_norm 4.4440 (2.3908/0.7535)	mem 24308MB
[2025-01-18 12:24:43 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][80/312]	eta 0:02:21 lr 0.000255	time 0.5693 (0.6093)	model_time 0.5688 (0.5900)	loss 6.7122 (6.6721)	grad_norm 2.1759 (2.4607/0.7983)	mem 24308MB
[2025-01-18 12:24:49 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][90/312]	eta 0:02:15 lr 0.000261	time 0.6077 (0.6106)	model_time 0.6075 (0.5934)	loss 6.5299 (6.6712)	grad_norm 2.6906 (2.4727/0.8077)	mem 24308MB
[2025-01-18 12:24:55 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][100/312]	eta 0:02:09 lr 0.000268	time 0.5737 (0.6085)	model_time 0.5731 (0.5930)	loss 6.6423 (6.6687)	grad_norm 4.7600 (2.5084/0.8476)	mem 24308MB
[2025-01-18 12:25:01 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][110/312]	eta 0:02:02 lr 0.000274	time 0.5807 (0.6060)	model_time 0.5802 (0.5918)	loss 6.3969 (6.6615)	grad_norm 2.5048 (2.6017/0.9562)	mem 24308MB
[2025-01-18 12:25:07 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][120/312]	eta 0:01:56 lr 0.000281	time 0.5882 (0.6047)	model_time 0.5877 (0.5916)	loss 6.8112 (6.6661)	grad_norm 1.5998 (2.6493/0.9966)	mem 24308MB
[2025-01-18 12:25:13 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][130/312]	eta 0:01:49 lr 0.000287	time 0.5862 (0.6029)	model_time 0.5857 (0.5908)	loss 6.6164 (6.6643)	grad_norm 3.5413 (2.6976/1.0107)	mem 24308MB
[2025-01-18 12:25:19 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][140/312]	eta 0:01:43 lr 0.000293	time 0.5910 (0.6016)	model_time 0.5908 (0.5903)	loss 6.4145 (6.6592)	grad_norm 3.0266 (2.7367/1.0287)	mem 24308MB
[2025-01-18 12:25:24 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][150/312]	eta 0:01:37 lr 0.000300	time 0.5761 (0.6005)	model_time 0.5756 (0.5899)	loss 6.5430 (6.6527)	grad_norm 2.9091 (2.7702/1.0262)	mem 24308MB
[2025-01-18 12:25:30 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][160/312]	eta 0:01:31 lr 0.000306	time 0.5820 (0.5997)	model_time 0.5815 (0.5898)	loss 6.3775 (6.6442)	grad_norm 1.3609 (2.7785/1.0370)	mem 24308MB
[2025-01-18 12:25:36 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][170/312]	eta 0:01:25 lr 0.000313	time 0.6029 (0.5988)	model_time 0.6027 (0.5894)	loss 6.7451 (6.6420)	grad_norm 4.1349 (2.8142/1.0409)	mem 24308MB
[2025-01-18 12:25:42 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][180/312]	eta 0:01:18 lr 0.000319	time 0.5806 (0.5980)	model_time 0.5804 (0.5890)	loss 6.2411 (6.6394)	grad_norm 1.9942 (2.8225/1.0468)	mem 24308MB
[2025-01-18 12:25:48 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][190/312]	eta 0:01:12 lr 0.000325	time 0.5796 (0.5974)	model_time 0.5791 (0.5889)	loss 6.3852 (6.6343)	grad_norm 2.2011 (2.8233/1.0332)	mem 24308MB
[2025-01-18 12:25:54 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][200/312]	eta 0:01:06 lr 0.000332	time 0.5794 (0.5975)	model_time 0.5792 (0.5894)	loss 6.6058 (6.6347)	grad_norm 3.9712 (2.8548/1.0331)	mem 24308MB
[2025-01-18 12:26:00 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][210/312]	eta 0:01:01 lr 0.000338	time 0.5724 (0.5991)	model_time 0.5722 (0.5914)	loss 6.4696 (6.6290)	grad_norm 2.3854 (2.8743/1.0428)	mem 24308MB
[2025-01-18 12:26:06 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][220/312]	eta 0:00:55 lr 0.000345	time 0.5831 (0.5983)	model_time 0.5829 (0.5909)	loss 6.6016 (6.6239)	grad_norm 2.2517 (2.8755/1.0333)	mem 24308MB
[2025-01-18 12:26:12 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][230/312]	eta 0:00:49 lr 0.000351	time 0.5896 (0.5978)	model_time 0.5895 (0.5907)	loss 6.6234 (6.6185)	grad_norm 6.2748 (2.9111/1.0661)	mem 24308MB
[2025-01-18 12:26:18 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][240/312]	eta 0:00:42 lr 0.000357	time 0.5766 (0.5971)	model_time 0.5764 (0.5903)	loss 6.5623 (6.6154)	grad_norm 4.3850 (2.9545/1.1208)	mem 24308MB
[2025-01-18 12:26:24 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][250/312]	eta 0:00:36 lr 0.000364	time 0.5883 (0.5966)	model_time 0.5878 (0.5901)	loss 6.5480 (6.6137)	grad_norm 3.0140 (2.9559/1.1000)	mem 24308MB
[2025-01-18 12:26:29 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][260/312]	eta 0:00:30 lr 0.000370	time 0.5881 (0.5960)	model_time 0.5876 (0.5897)	loss 6.4085 (6.6103)	grad_norm 3.3719 (2.9689/1.0920)	mem 24308MB
[2025-01-18 12:26:35 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][270/312]	eta 0:00:25 lr 0.000377	time 0.5786 (0.5955)	model_time 0.5781 (0.5894)	loss 6.6513 (6.6081)	grad_norm 2.3607 (2.9961/1.0934)	mem 24308MB
[2025-01-18 12:26:41 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][280/312]	eta 0:00:19 lr 0.000383	time 0.5837 (0.5952)	model_time 0.5835 (0.5893)	loss 6.3322 (6.6056)	grad_norm 4.5642 (3.0158/1.0949)	mem 24308MB
[2025-01-18 12:26:47 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][290/312]	eta 0:00:13 lr 0.000390	time 0.6005 (0.5948)	model_time 0.6003 (0.5891)	loss 6.2287 (6.5987)	grad_norm 2.9670 (3.0082/1.0826)	mem 24308MB
[2025-01-18 12:26:53 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][300/312]	eta 0:00:07 lr 0.000396	time 0.5664 (0.5942)	model_time 0.5663 (0.5887)	loss 6.6052 (6.5954)	grad_norm 4.5653 (3.0240/1.0747)	mem 24308MB
[2025-01-18 12:26:58 internimage_s_1k_224] (main.py 510): INFO Train: [1/300][310/312]	eta 0:00:01 lr 0.000402	time 0.5807 (0.5935)	model_time 0.5805 (0.5882)	loss 6.6230 (6.5948)	grad_norm 3.9426 (3.0797/1.0898)	mem 24308MB
[2025-01-18 12:26:59 internimage_s_1k_224] (main.py 519): INFO EPOCH 1 training takes 0:03:05
[2025-01-18 12:26:59 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_1.pth saving......
[2025-01-18 12:27:01 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_1.pth saved !!!
[2025-01-18 12:27:08 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.112 (7.112)	Loss 5.7216 (5.7216)	Acc@1 3.198 (3.198)	Acc@5 11.743 (11.743)	Mem 24308MB
[2025-01-18 12:27:11 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.944)	Loss 5.8690 (5.7811)	Acc@1 3.564 (3.864)	Acc@5 10.181 (12.984)	Mem 24308MB
[2025-01-18 12:27:11 internimage_s_1k_224] (main.py 575): INFO [Epoch:1] * Acc@1 4.577 Acc@5 14.407
[2025-01-18 12:27:11 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 4.6%
[2025-01-18 12:27:11 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 12:27:13 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 12:27:13 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 4.58%
[2025-01-18 12:27:21 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.311 (7.311)	Loss 6.9283 (6.9283)	Acc@1 0.000 (0.000)	Acc@5 0.244 (0.244)	Mem 24308MB
[2025-01-18 12:27:24 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.962)	Loss 6.8978 (6.9127)	Acc@1 0.293 (0.113)	Acc@5 1.660 (0.564)	Mem 24308MB
[2025-01-18 12:27:24 internimage_s_1k_224] (main.py 575): INFO [Epoch:1] * Acc@1 0.120 Acc@5 0.606
[2025-01-18 12:27:24 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.1%
[2025-01-18 12:27:24 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 12:27:26 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 12:27:26 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 0.12%
[2025-01-18 12:27:29 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][0/312]	eta 0:12:58 lr 0.000404	time 2.4943 (2.4943)	model_time 0.6069 (0.6069)	loss 6.5942 (6.5942)	grad_norm 2.4071 (2.4071/0.0000)	mem 24308MB
[2025-01-18 12:27:35 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][10/312]	eta 0:03:56 lr 0.000410	time 0.6508 (0.7816)	model_time 0.6504 (0.6097)	loss 6.3979 (6.4996)	grad_norm 3.5477 (4.0539/1.8774)	mem 24308MB
[2025-01-18 12:27:41 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][20/312]	eta 0:03:28 lr 0.000416	time 0.5782 (0.7136)	model_time 0.5781 (0.6234)	loss 6.2423 (6.4396)	grad_norm 2.1817 (3.8785/1.6100)	mem 24308MB
[2025-01-18 12:27:47 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][30/312]	eta 0:03:08 lr 0.000423	time 0.5802 (0.6695)	model_time 0.5797 (0.6083)	loss 6.3979 (6.4411)	grad_norm 8.5182 (4.4585/2.1483)	mem 24308MB
[2025-01-18 12:27:53 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][40/312]	eta 0:02:56 lr 0.000429	time 0.5812 (0.6492)	model_time 0.5810 (0.6028)	loss 6.3860 (6.4197)	grad_norm 2.3943 (4.2773/2.0261)	mem 24308MB
[2025-01-18 12:27:59 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][50/312]	eta 0:02:47 lr 0.000436	time 0.6024 (0.6376)	model_time 0.6022 (0.6002)	loss 6.5434 (6.4417)	grad_norm 4.5083 (3.9238/1.9809)	mem 24308MB
[2025-01-18 12:28:05 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][60/312]	eta 0:02:38 lr 0.000442	time 0.5748 (0.6279)	model_time 0.5746 (0.5966)	loss 6.5850 (6.4422)	grad_norm 3.5477 (3.8149/1.8654)	mem 24308MB
[2025-01-18 12:28:10 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][70/312]	eta 0:02:30 lr 0.000448	time 0.5904 (0.6214)	model_time 0.5903 (0.5945)	loss 6.3196 (6.4280)	grad_norm 3.3423 (3.7990/1.7479)	mem 24308MB
[2025-01-18 12:28:16 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][80/312]	eta 0:02:23 lr 0.000455	time 0.5748 (0.6172)	model_time 0.5746 (0.5935)	loss 6.5191 (6.4225)	grad_norm 2.7677 (3.7592/1.6699)	mem 24308MB
[2025-01-18 12:28:22 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][90/312]	eta 0:02:16 lr 0.000461	time 0.5666 (0.6138)	model_time 0.5665 (0.5926)	loss 6.5045 (6.4091)	grad_norm 1.8427 (3.6866/1.6108)	mem 24308MB
[2025-01-18 12:28:28 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][100/312]	eta 0:02:09 lr 0.000468	time 0.5941 (0.6112)	model_time 0.5939 (0.5921)	loss 6.1924 (6.3994)	grad_norm 2.6543 (3.7144/1.5575)	mem 24308MB
[2025-01-18 12:28:34 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][110/312]	eta 0:02:02 lr 0.000474	time 0.5789 (0.6086)	model_time 0.5784 (0.5912)	loss 6.4302 (6.4007)	grad_norm 3.1085 (3.6340/1.5133)	mem 24308MB
[2025-01-18 12:28:40 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][120/312]	eta 0:01:56 lr 0.000480	time 0.5899 (0.6063)	model_time 0.5893 (0.5903)	loss 6.5207 (6.4028)	grad_norm 3.6529 (3.6650/1.5267)	mem 24308MB
[2025-01-18 12:28:46 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][130/312]	eta 0:01:50 lr 0.000487	time 0.5829 (0.6055)	model_time 0.5825 (0.5907)	loss 6.0003 (6.3927)	grad_norm 4.3467 (3.6642/1.5075)	mem 24308MB
[2025-01-18 12:28:52 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][140/312]	eta 0:01:44 lr 0.000493	time 0.5763 (0.6076)	model_time 0.5762 (0.5938)	loss 6.3740 (6.3950)	grad_norm 3.1548 (3.6219/1.4697)	mem 24308MB
[2025-01-18 12:28:58 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][150/312]	eta 0:01:38 lr 0.000500	time 0.6083 (0.6058)	model_time 0.6081 (0.5929)	loss 5.9929 (6.3941)	grad_norm 2.0915 (3.5929/1.4407)	mem 24308MB
[2025-01-18 12:29:04 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][160/312]	eta 0:01:31 lr 0.000506	time 0.5751 (0.6044)	model_time 0.5747 (0.5923)	loss 6.2302 (6.3940)	grad_norm 4.1216 (3.6086/1.4104)	mem 24308MB
[2025-01-18 12:29:09 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][170/312]	eta 0:01:25 lr 0.000512	time 0.5871 (0.6032)	model_time 0.5866 (0.5917)	loss 6.2799 (6.3943)	grad_norm 2.2696 (3.5790/1.3809)	mem 24308MB
[2025-01-18 12:29:15 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][180/312]	eta 0:01:19 lr 0.000519	time 0.5681 (0.6019)	model_time 0.5679 (0.5910)	loss 6.6256 (6.3882)	grad_norm 5.1428 (3.6011/1.3692)	mem 24308MB
[2025-01-18 12:29:21 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][190/312]	eta 0:01:13 lr 0.000525	time 0.5701 (0.6009)	model_time 0.5700 (0.5906)	loss 6.4340 (6.3760)	grad_norm 2.8841 (3.6284/1.3595)	mem 24308MB
[2025-01-18 12:29:27 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][200/312]	eta 0:01:07 lr 0.000532	time 0.5800 (0.5999)	model_time 0.5795 (0.5901)	loss 5.9130 (6.3706)	grad_norm 3.5253 (3.6113/1.3380)	mem 24308MB
[2025-01-18 12:29:33 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][210/312]	eta 0:01:01 lr 0.000538	time 0.5716 (0.5991)	model_time 0.5712 (0.5897)	loss 5.9221 (6.3602)	grad_norm 2.5050 (3.5861/1.3293)	mem 24308MB
[2025-01-18 12:29:39 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][220/312]	eta 0:00:55 lr 0.000544	time 0.5680 (0.5983)	model_time 0.5678 (0.5893)	loss 5.8928 (6.3533)	grad_norm 6.1456 (3.6054/1.3322)	mem 24308MB
[2025-01-18 12:29:44 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][230/312]	eta 0:00:49 lr 0.000551	time 0.5877 (0.5977)	model_time 0.5875 (0.5890)	loss 6.3920 (6.3523)	grad_norm 4.9460 (3.6115/1.3159)	mem 24308MB
[2025-01-18 12:29:50 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][240/312]	eta 0:00:42 lr 0.000557	time 0.5805 (0.5969)	model_time 0.5800 (0.5886)	loss 6.1701 (6.3481)	grad_norm 6.5496 (3.6461/1.3229)	mem 24308MB
[2025-01-18 12:29:56 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][250/312]	eta 0:00:37 lr 0.000564	time 0.6724 (0.5969)	model_time 0.6722 (0.5889)	loss 6.1757 (6.3459)	grad_norm 2.6656 (3.6317/1.3133)	mem 24308MB
[2025-01-18 12:30:02 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][260/312]	eta 0:00:31 lr 0.000570	time 0.5790 (0.5978)	model_time 0.5789 (0.5901)	loss 5.9167 (6.3375)	grad_norm 2.4176 (3.6516/1.3112)	mem 24308MB
[2025-01-18 12:30:08 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][270/312]	eta 0:00:25 lr 0.000577	time 0.5772 (0.5976)	model_time 0.5768 (0.5901)	loss 6.3200 (6.3342)	grad_norm 3.8449 (3.6554/1.2997)	mem 24308MB
[2025-01-18 12:30:14 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][280/312]	eta 0:00:19 lr 0.000583	time 0.5748 (0.5971)	model_time 0.5743 (0.5899)	loss 6.2986 (6.3293)	grad_norm 4.1616 (3.6644/1.2912)	mem 24308MB
[2025-01-18 12:30:20 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][290/312]	eta 0:00:13 lr 0.000589	time 0.5787 (0.5965)	model_time 0.5783 (0.5896)	loss 6.4584 (6.3231)	grad_norm 3.1836 (3.6576/1.2730)	mem 24308MB
[2025-01-18 12:30:26 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][300/312]	eta 0:00:07 lr 0.000596	time 0.5684 (0.5958)	model_time 0.5683 (0.5891)	loss 6.4124 (6.3241)	grad_norm 3.0047 (3.6532/1.2659)	mem 24308MB
[2025-01-18 12:30:31 internimage_s_1k_224] (main.py 510): INFO Train: [2/300][310/312]	eta 0:00:01 lr 0.000602	time 0.5686 (0.5952)	model_time 0.5685 (0.5886)	loss 5.7739 (6.3208)	grad_norm 3.2632 (3.6207/1.2200)	mem 24308MB
[2025-01-18 12:30:32 internimage_s_1k_224] (main.py 519): INFO EPOCH 2 training takes 0:03:05
[2025-01-18 12:30:32 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_2.pth saving......
[2025-01-18 12:30:34 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_2.pth saved !!!
[2025-01-18 12:30:41 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.330 (7.330)	Loss 4.8834 (4.8834)	Acc@1 9.302 (9.302)	Acc@5 26.099 (26.099)	Mem 24308MB
[2025-01-18 12:30:44 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.962)	Loss 5.1474 (5.0515)	Acc@1 8.862 (9.506)	Acc@5 22.217 (24.663)	Mem 24308MB
[2025-01-18 12:30:45 internimage_s_1k_224] (main.py 575): INFO [Epoch:2] * Acc@1 10.397 Acc@5 25.910
[2025-01-18 12:30:45 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 10.4%
[2025-01-18 12:30:45 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 12:30:47 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 12:30:47 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 10.40%
[2025-01-18 12:30:54 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.000 (7.000)	Loss 6.9259 (6.9259)	Acc@1 0.000 (0.000)	Acc@5 0.024 (0.024)	Mem 24308MB
[2025-01-18 12:30:57 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.923)	Loss 6.8869 (6.9039)	Acc@1 0.342 (0.111)	Acc@5 1.855 (0.695)	Mem 24308MB
[2025-01-18 12:30:57 internimage_s_1k_224] (main.py 575): INFO [Epoch:2] * Acc@1 0.160 Acc@5 0.802
[2025-01-18 12:30:57 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.2%
[2025-01-18 12:30:57 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 12:30:59 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 12:30:59 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 0.16%
[2025-01-18 12:31:02 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][0/312]	eta 0:12:21 lr 0.000603	time 2.3763 (2.3763)	model_time 0.6043 (0.6043)	loss 6.3434 (6.3434)	grad_norm 6.4273 (6.4273/0.0000)	mem 24308MB
[2025-01-18 12:31:07 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][10/312]	eta 0:03:46 lr 0.000610	time 0.5680 (0.7488)	model_time 0.5678 (0.5875)	loss 5.8322 (6.1081)	grad_norm 2.1635 (4.0403/1.2416)	mem 24308MB
[2025-01-18 12:31:13 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][20/312]	eta 0:03:15 lr 0.000616	time 0.5827 (0.6712)	model_time 0.5826 (0.5865)	loss 6.1731 (6.0979)	grad_norm 5.5088 (4.2844/1.6988)	mem 24308MB
[2025-01-18 12:31:19 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][30/312]	eta 0:03:01 lr 0.000623	time 0.5687 (0.6434)	model_time 0.5685 (0.5860)	loss 6.2965 (6.1505)	grad_norm 2.1723 (4.2785/1.5767)	mem 24308MB
[2025-01-18 12:31:25 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][40/312]	eta 0:02:51 lr 0.000629	time 0.5738 (0.6294)	model_time 0.5736 (0.5859)	loss 5.7587 (6.1745)	grad_norm 2.2488 (4.0155/1.4705)	mem 24308MB
[2025-01-18 12:31:31 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][50/312]	eta 0:02:43 lr 0.000635	time 0.5807 (0.6247)	model_time 0.5803 (0.5897)	loss 6.5100 (6.1768)	grad_norm 3.2403 (3.9046/1.4578)	mem 24308MB
[2025-01-18 12:31:37 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][60/312]	eta 0:02:36 lr 0.000642	time 0.6748 (0.6201)	model_time 0.6746 (0.5907)	loss 5.7245 (6.1631)	grad_norm 3.7518 (3.8053/1.3712)	mem 24308MB
[2025-01-18 12:31:43 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][70/312]	eta 0:02:30 lr 0.000648	time 0.7192 (0.6216)	model_time 0.7188 (0.5963)	loss 6.1765 (6.1638)	grad_norm 3.1530 (3.9434/1.5360)	mem 24308MB
[2025-01-18 12:31:49 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][80/312]	eta 0:02:23 lr 0.000655	time 0.5707 (0.6182)	model_time 0.5702 (0.5959)	loss 5.7425 (6.1708)	grad_norm 3.8483 (4.1074/1.5641)	mem 24308MB
[2025-01-18 12:31:55 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][90/312]	eta 0:02:16 lr 0.000661	time 0.5760 (0.6141)	model_time 0.5758 (0.5943)	loss 6.1332 (6.1440)	grad_norm 5.1141 (4.1035/1.5501)	mem 24308MB
[2025-01-18 12:32:01 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][100/312]	eta 0:02:09 lr 0.000667	time 0.6079 (0.6115)	model_time 0.6077 (0.5936)	loss 6.3497 (6.1431)	grad_norm 4.0717 (4.0742/1.5091)	mem 24308MB
[2025-01-18 12:32:07 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][110/312]	eta 0:02:03 lr 0.000674	time 0.5865 (0.6089)	model_time 0.5863 (0.5926)	loss 6.0253 (6.1441)	grad_norm 5.7824 (4.2244/1.5542)	mem 24308MB
[2025-01-18 12:32:13 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][120/312]	eta 0:01:56 lr 0.000680	time 0.5789 (0.6067)	model_time 0.5787 (0.5916)	loss 6.2561 (6.1470)	grad_norm 3.8556 (4.1745/1.5679)	mem 24308MB
[2025-01-18 12:32:18 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][130/312]	eta 0:01:50 lr 0.000687	time 0.5898 (0.6046)	model_time 0.5896 (0.5907)	loss 5.7254 (6.1391)	grad_norm 7.0616 (4.1484/1.5603)	mem 24308MB
[2025-01-18 12:32:24 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][140/312]	eta 0:01:43 lr 0.000693	time 0.5760 (0.6027)	model_time 0.5756 (0.5897)	loss 6.3415 (6.1264)	grad_norm 3.2824 (4.1381/1.5285)	mem 24308MB
[2025-01-18 12:32:30 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][150/312]	eta 0:01:37 lr 0.000699	time 0.5834 (0.6017)	model_time 0.5829 (0.5896)	loss 6.0330 (6.1232)	grad_norm 3.9036 (4.0821/1.5105)	mem 24308MB
[2025-01-18 12:32:36 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][160/312]	eta 0:01:31 lr 0.000706	time 0.5820 (0.6004)	model_time 0.5815 (0.5891)	loss 6.3419 (6.1169)	grad_norm 3.3987 (4.1126/1.5110)	mem 24308MB
[2025-01-18 12:32:42 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][170/312]	eta 0:01:25 lr 0.000712	time 0.5823 (0.6001)	model_time 0.5821 (0.5893)	loss 6.1899 (6.1138)	grad_norm 3.1102 (4.1058/1.4876)	mem 24308MB
[2025-01-18 12:32:48 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][180/312]	eta 0:01:19 lr 0.000719	time 0.5842 (0.5990)	model_time 0.5840 (0.5889)	loss 6.1958 (6.1141)	grad_norm 3.7788 (4.1190/1.4861)	mem 24308MB
[2025-01-18 12:32:54 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][190/312]	eta 0:01:13 lr 0.000725	time 0.6635 (0.6008)	model_time 0.6630 (0.5912)	loss 6.0742 (6.1118)	grad_norm 3.4810 (4.1341/1.4802)	mem 24308MB
[2025-01-18 12:33:00 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][200/312]	eta 0:01:07 lr 0.000731	time 0.5814 (0.6011)	model_time 0.5812 (0.5919)	loss 5.8301 (6.1091)	grad_norm 6.9132 (4.1397/1.4661)	mem 24308MB
[2025-01-18 12:33:06 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][210/312]	eta 0:01:01 lr 0.000738	time 0.5895 (0.6001)	model_time 0.5889 (0.5914)	loss 6.4603 (6.1078)	grad_norm 3.9242 (4.0839/1.4574)	mem 24308MB
[2025-01-18 12:33:12 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][220/312]	eta 0:00:55 lr 0.000744	time 0.5795 (0.5992)	model_time 0.5793 (0.5908)	loss 5.9134 (6.1019)	grad_norm 3.7182 (4.0627/1.4391)	mem 24308MB
[2025-01-18 12:33:17 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][230/312]	eta 0:00:49 lr 0.000751	time 0.5701 (0.5986)	model_time 0.5696 (0.5906)	loss 6.0533 (6.0914)	grad_norm 3.6448 (4.0389/1.4324)	mem 24308MB
[2025-01-18 12:33:23 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][240/312]	eta 0:00:43 lr 0.000757	time 0.5816 (0.5978)	model_time 0.5811 (0.5901)	loss 6.3539 (6.0950)	grad_norm 5.4286 (4.0709/1.4434)	mem 24308MB
[2025-01-18 12:33:29 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][250/312]	eta 0:00:37 lr 0.000763	time 0.5742 (0.5972)	model_time 0.5741 (0.5897)	loss 6.1262 (6.0981)	grad_norm 3.3373 (4.0497/1.4319)	mem 24308MB
[2025-01-18 12:33:35 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][260/312]	eta 0:00:31 lr 0.000770	time 0.5753 (0.5965)	model_time 0.5751 (0.5894)	loss 6.0070 (6.0922)	grad_norm 3.1635 (4.0221/1.4178)	mem 24308MB
[2025-01-18 12:33:41 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][270/312]	eta 0:00:25 lr 0.000776	time 0.5816 (0.5960)	model_time 0.5813 (0.5891)	loss 6.2883 (6.0922)	grad_norm 4.9838 (4.0316/1.4010)	mem 24308MB
[2025-01-18 12:33:46 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][280/312]	eta 0:00:19 lr 0.000783	time 0.5878 (0.5955)	model_time 0.5876 (0.5888)	loss 6.4692 (6.0889)	grad_norm 3.3728 (3.9986/1.3943)	mem 24308MB
[2025-01-18 12:33:52 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][290/312]	eta 0:00:13 lr 0.000789	time 0.7815 (0.5957)	model_time 0.7813 (0.5892)	loss 5.8047 (6.0796)	grad_norm 4.5397 (4.0089/1.4111)	mem 24308MB
[2025-01-18 12:33:58 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][300/312]	eta 0:00:07 lr 0.000796	time 0.5656 (0.5949)	model_time 0.5656 (0.5887)	loss 6.0500 (6.0735)	grad_norm 2.7745 (3.9790/1.3921)	mem 24308MB
[2025-01-18 12:34:04 internimage_s_1k_224] (main.py 510): INFO Train: [3/300][310/312]	eta 0:00:01 lr 0.000802	time 0.6526 (0.5955)	model_time 0.6525 (0.5894)	loss 6.1155 (6.0718)	grad_norm 2.3477 (4.0331/1.4672)	mem 24308MB
[2025-01-18 12:34:05 internimage_s_1k_224] (main.py 519): INFO EPOCH 3 training takes 0:03:05
[2025-01-18 12:34:05 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_3.pth saving......
[2025-01-18 12:34:07 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_3.pth saved !!!
[2025-01-18 12:34:14 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.339 (7.339)	Loss 4.2693 (4.2693)	Acc@1 18.115 (18.115)	Acc@5 40.356 (40.356)	Mem 24308MB
[2025-01-18 12:34:17 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.959)	Loss 4.6971 (4.4469)	Acc@1 12.134 (15.696)	Acc@5 29.712 (36.015)	Mem 24308MB
[2025-01-18 12:34:18 internimage_s_1k_224] (main.py 575): INFO [Epoch:3] * Acc@1 16.593 Acc@5 37.346
[2025-01-18 12:34:18 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 16.6%
[2025-01-18 12:34:18 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 12:34:19 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 12:34:19 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 16.59%
[2025-01-18 12:34:27 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.247 (7.247)	Loss 6.9236 (6.9236)	Acc@1 0.000 (0.000)	Acc@5 0.000 (0.000)	Mem 24308MB
[2025-01-18 12:34:30 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.135 (0.957)	Loss 6.8723 (6.8918)	Acc@1 0.122 (0.138)	Acc@5 1.636 (0.819)	Mem 24308MB
[2025-01-18 12:34:30 internimage_s_1k_224] (main.py 575): INFO [Epoch:3] * Acc@1 0.220 Acc@5 0.998
[2025-01-18 12:34:30 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.2%
[2025-01-18 12:34:30 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 12:34:32 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 12:34:32 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 0.22%
[2025-01-18 12:34:35 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][0/312]	eta 0:11:01 lr 0.000803	time 2.1192 (2.1192)	model_time 0.5981 (0.5981)	loss 5.4427 (5.4427)	grad_norm 3.7826 (3.7826/0.0000)	mem 24308MB
[2025-01-18 12:34:41 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][10/312]	eta 0:03:46 lr 0.000810	time 0.5740 (0.7502)	model_time 0.5738 (0.6116)	loss 6.2203 (5.9640)	grad_norm 2.9794 (3.2484/0.5804)	mem 24308MB
[2025-01-18 12:34:47 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][20/312]	eta 0:03:16 lr 0.000816	time 0.5924 (0.6716)	model_time 0.5922 (0.5988)	loss 6.0293 (5.9945)	grad_norm 2.9242 (3.1618/0.7237)	mem 24308MB
[2025-01-18 12:34:52 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][30/312]	eta 0:03:01 lr 0.000822	time 0.6033 (0.6430)	model_time 0.6031 (0.5936)	loss 5.6326 (5.9851)	grad_norm 2.5418 (3.2287/0.7774)	mem 24308MB
[2025-01-18 12:34:58 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][40/312]	eta 0:02:50 lr 0.000829	time 0.5897 (0.6282)	model_time 0.5895 (0.5907)	loss 5.4941 (6.0068)	grad_norm 1.9314 (3.1627/0.7651)	mem 24308MB
[2025-01-18 12:35:04 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][50/312]	eta 0:02:42 lr 0.000835	time 0.5947 (0.6192)	model_time 0.5946 (0.5890)	loss 6.3636 (5.9984)	grad_norm 4.8108 (3.2125/0.9663)	mem 24308MB
[2025-01-18 12:35:10 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][60/312]	eta 0:02:34 lr 0.000842	time 0.5844 (0.6126)	model_time 0.5839 (0.5873)	loss 5.3315 (5.9696)	grad_norm 3.3496 (3.4119/1.1563)	mem 24308MB
[2025-01-18 12:35:16 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][70/312]	eta 0:02:27 lr 0.000848	time 0.5838 (0.6081)	model_time 0.5837 (0.5863)	loss 5.7559 (5.9276)	grad_norm 3.5099 (3.6158/1.4264)	mem 24308MB
[2025-01-18 12:35:21 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][80/312]	eta 0:02:20 lr 0.000854	time 0.5826 (0.6055)	model_time 0.5825 (0.5863)	loss 5.8804 (5.9155)	grad_norm 3.6695 (3.5468/1.3701)	mem 24308MB
[2025-01-18 12:35:27 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][90/312]	eta 0:02:13 lr 0.000861	time 0.5791 (0.6029)	model_time 0.5786 (0.5859)	loss 6.4506 (5.9118)	grad_norm 3.8571 (3.5086/1.3191)	mem 24308MB
[2025-01-18 12:35:33 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][100/312]	eta 0:02:07 lr 0.000867	time 0.5677 (0.6010)	model_time 0.5675 (0.5856)	loss 6.2111 (5.9094)	grad_norm 3.2380 (3.5839/1.3456)	mem 24308MB
[2025-01-18 12:35:39 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][110/312]	eta 0:02:01 lr 0.000874	time 0.5817 (0.5994)	model_time 0.5815 (0.5853)	loss 5.5860 (5.9161)	grad_norm 4.4530 (3.5481/1.3114)	mem 24308MB
[2025-01-18 12:35:45 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][120/312]	eta 0:01:55 lr 0.000880	time 0.6623 (0.6033)	model_time 0.6621 (0.5904)	loss 5.6682 (5.9194)	grad_norm 4.0018 (3.5447/1.2705)	mem 24308MB
[2025-01-18 12:35:52 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][130/312]	eta 0:01:50 lr 0.000886	time 0.5712 (0.6049)	model_time 0.5710 (0.5929)	loss 6.0113 (5.9231)	grad_norm 2.8884 (3.5992/1.2879)	mem 24308MB
[2025-01-18 12:35:57 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][140/312]	eta 0:01:43 lr 0.000893	time 0.5939 (0.6030)	model_time 0.5938 (0.5919)	loss 6.1907 (5.9223)	grad_norm 4.0781 (3.6279/1.2626)	mem 24308MB
[2025-01-18 12:36:03 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][150/312]	eta 0:01:37 lr 0.000899	time 0.5864 (0.6015)	model_time 0.5862 (0.5910)	loss 5.2867 (5.9142)	grad_norm 7.2118 (3.6721/1.2834)	mem 24308MB
[2025-01-18 12:36:09 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][160/312]	eta 0:01:31 lr 0.000906	time 0.5782 (0.6006)	model_time 0.5781 (0.5908)	loss 5.7754 (5.9155)	grad_norm 3.7006 (3.6621/1.2666)	mem 24308MB
[2025-01-18 12:36:15 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][170/312]	eta 0:01:25 lr 0.000912	time 0.5793 (0.6002)	model_time 0.5791 (0.5909)	loss 6.1486 (5.9094)	grad_norm 3.9689 (3.6712/1.2748)	mem 24308MB
[2025-01-18 12:36:21 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][180/312]	eta 0:01:19 lr 0.000918	time 0.5725 (0.5992)	model_time 0.5723 (0.5905)	loss 5.6506 (5.8980)	grad_norm 3.0125 (3.6568/1.2612)	mem 24308MB
[2025-01-18 12:36:27 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][190/312]	eta 0:01:13 lr 0.000925	time 0.5785 (0.5984)	model_time 0.5783 (0.5901)	loss 5.2767 (5.8896)	grad_norm 5.0987 (3.6679/1.2456)	mem 24308MB
[2025-01-18 12:36:33 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][200/312]	eta 0:01:06 lr 0.000931	time 0.5743 (0.5978)	model_time 0.5742 (0.5899)	loss 5.2794 (5.8844)	grad_norm 4.0282 (3.6832/1.2438)	mem 24308MB
[2025-01-18 12:36:38 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][210/312]	eta 0:01:00 lr 0.000938	time 0.5743 (0.5971)	model_time 0.5741 (0.5896)	loss 5.2381 (5.8838)	grad_norm 3.3494 (3.6874/1.2403)	mem 24308MB
[2025-01-18 12:36:44 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][220/312]	eta 0:00:54 lr 0.000944	time 0.5734 (0.5965)	model_time 0.5732 (0.5892)	loss 6.0112 (5.8824)	grad_norm 2.9859 (3.7206/1.2706)	mem 24308MB
[2025-01-18 12:36:50 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][230/312]	eta 0:00:48 lr 0.000950	time 0.5786 (0.5960)	model_time 0.5781 (0.5890)	loss 5.2996 (5.8689)	grad_norm 4.2117 (3.7148/1.2523)	mem 24308MB
[2025-01-18 12:36:57 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][240/312]	eta 0:00:43 lr 0.000957	time 0.6656 (0.5980)	model_time 0.6651 (0.5913)	loss 5.8864 (5.8480)	grad_norm 4.0895 (3.6965/1.2530)	mem 24308MB
[2025-01-18 12:37:03 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][250/312]	eta 0:00:37 lr 0.000963	time 0.5763 (0.5986)	model_time 0.5762 (0.5921)	loss 5.7512 (5.8377)	grad_norm 3.5177 (3.7151/1.2559)	mem 24308MB
[2025-01-18 12:37:09 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][260/312]	eta 0:00:31 lr 0.000970	time 0.5739 (0.5982)	model_time 0.5737 (0.5920)	loss 5.4996 (5.8406)	grad_norm 2.9996 (3.7009/1.2411)	mem 24308MB
[2025-01-18 12:37:14 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][270/312]	eta 0:00:25 lr 0.000976	time 0.6272 (0.5977)	model_time 0.6270 (0.5917)	loss 5.8967 (5.8402)	grad_norm 4.1049 (3.6806/1.2303)	mem 24308MB
[2025-01-18 12:37:20 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][280/312]	eta 0:00:19 lr 0.000983	time 0.5749 (0.5971)	model_time 0.5747 (0.5914)	loss 5.7351 (5.8343)	grad_norm 3.6232 (3.6561/1.2210)	mem 24308MB
[2025-01-18 12:37:26 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][290/312]	eta 0:00:13 lr 0.000989	time 0.5649 (0.5964)	model_time 0.5648 (0.5909)	loss 5.7266 (5.8283)	grad_norm 3.2766 (3.6449/1.2087)	mem 24308MB
[2025-01-18 12:37:32 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][300/312]	eta 0:00:07 lr 0.000995	time 0.5712 (0.5958)	model_time 0.5711 (0.5903)	loss 4.9012 (5.8182)	grad_norm 3.7269 (3.6391/1.2130)	mem 24308MB
[2025-01-18 12:37:37 internimage_s_1k_224] (main.py 510): INFO Train: [4/300][310/312]	eta 0:00:01 lr 0.001002	time 0.5833 (0.5950)	model_time 0.5832 (0.5897)	loss 5.8635 (5.8182)	grad_norm 2.0244 (3.6588/1.2593)	mem 24308MB
[2025-01-18 12:37:38 internimage_s_1k_224] (main.py 519): INFO EPOCH 4 training takes 0:03:05
[2025-01-18 12:37:38 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_4.pth saving......
[2025-01-18 12:37:40 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_4.pth saved !!!
[2025-01-18 12:37:47 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.203 (7.203)	Loss 3.6323 (3.6323)	Acc@1 26.538 (26.538)	Acc@5 54.004 (54.004)	Mem 24308MB
[2025-01-18 12:37:50 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.939)	Loss 4.1308 (3.8538)	Acc@1 18.481 (23.821)	Acc@5 41.479 (48.133)	Mem 24308MB
[2025-01-18 12:37:50 internimage_s_1k_224] (main.py 575): INFO [Epoch:4] * Acc@1 24.880 Acc@5 49.526
[2025-01-18 12:37:50 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 24.9%
[2025-01-18 12:37:50 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 12:37:52 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 12:37:52 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 24.88%
[2025-01-18 12:37:59 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.941 (6.941)	Loss 6.9214 (6.9214)	Acc@1 0.000 (0.000)	Acc@5 0.000 (0.000)	Mem 24308MB
[2025-01-18 12:38:03 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.927)	Loss 6.8556 (6.8771)	Acc@1 0.049 (0.178)	Acc@5 1.367 (0.886)	Mem 24308MB
[2025-01-18 12:38:03 internimage_s_1k_224] (main.py 575): INFO [Epoch:4] * Acc@1 0.332 Acc@5 1.148
[2025-01-18 12:38:03 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.3%
[2025-01-18 12:38:03 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 12:38:05 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 12:38:05 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 0.33%
[2025-01-18 12:38:07 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][0/312]	eta 0:11:02 lr 0.001003	time 2.1244 (2.1244)	model_time 0.6377 (0.6377)	loss 4.7706 (4.7706)	grad_norm 3.0764 (3.0764/0.0000)	mem 24308MB
[2025-01-18 12:38:13 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][10/312]	eta 0:03:41 lr 0.001009	time 0.5954 (0.7346)	model_time 0.5952 (0.5980)	loss 5.6810 (5.4051)	grad_norm 4.8968 (3.6123/0.8590)	mem 24308MB
[2025-01-18 12:38:19 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][20/312]	eta 0:03:15 lr 0.001016	time 0.5833 (0.6692)	model_time 0.5832 (0.5975)	loss 5.1002 (5.5284)	grad_norm 4.1333 (3.4963/0.8798)	mem 24308MB
[2025-01-18 12:38:25 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][30/312]	eta 0:03:00 lr 0.001022	time 0.5951 (0.6405)	model_time 0.5950 (0.5919)	loss 5.7807 (5.6090)	grad_norm 1.9924 (3.4213/0.8214)	mem 24308MB
[2025-01-18 12:38:31 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][40/312]	eta 0:02:50 lr 0.001029	time 0.5918 (0.6279)	model_time 0.5916 (0.5910)	loss 6.0470 (5.6786)	grad_norm 3.5661 (3.3037/0.7779)	mem 24308MB
[2025-01-18 12:38:37 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][50/312]	eta 0:02:45 lr 0.001035	time 0.5732 (0.6298)	model_time 0.5731 (0.6001)	loss 5.4344 (5.6860)	grad_norm 2.0654 (3.2947/0.8682)	mem 24308MB
[2025-01-18 12:38:43 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][60/312]	eta 0:02:39 lr 0.001041	time 0.5959 (0.6316)	model_time 0.5957 (0.6067)	loss 5.5116 (5.6719)	grad_norm 5.5774 (3.4207/0.9327)	mem 24308MB
[2025-01-18 12:38:49 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][70/312]	eta 0:02:31 lr 0.001048	time 0.5858 (0.6245)	model_time 0.5856 (0.6031)	loss 5.9840 (5.6690)	grad_norm 4.3026 (3.4079/0.8980)	mem 24308MB
[2025-01-18 12:38:55 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][80/312]	eta 0:02:23 lr 0.001054	time 0.5977 (0.6193)	model_time 0.5972 (0.6005)	loss 5.7592 (5.6630)	grad_norm 4.0595 (3.5176/1.0877)	mem 24308MB
[2025-01-18 12:39:01 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][90/312]	eta 0:02:16 lr 0.001061	time 0.5702 (0.6148)	model_time 0.5700 (0.5980)	loss 5.2324 (5.6201)	grad_norm 2.7616 (3.4924/1.0972)	mem 24308MB
[2025-01-18 12:39:07 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][100/312]	eta 0:02:09 lr 0.001067	time 0.5857 (0.6117)	model_time 0.5855 (0.5966)	loss 5.2663 (5.5866)	grad_norm 2.4176 (3.4199/1.0807)	mem 24308MB
[2025-01-18 12:39:13 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][110/312]	eta 0:02:03 lr 0.001073	time 0.5871 (0.6091)	model_time 0.5870 (0.5952)	loss 5.8228 (5.5883)	grad_norm 3.3082 (3.4432/1.0865)	mem 24308MB
[2025-01-18 12:39:18 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][120/312]	eta 0:01:56 lr 0.001080	time 0.6110 (0.6078)	model_time 0.6108 (0.5951)	loss 5.8980 (5.5845)	grad_norm 3.2570 (3.4288/1.0552)	mem 24308MB
[2025-01-18 12:39:24 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][130/312]	eta 0:01:50 lr 0.001086	time 0.5818 (0.6059)	model_time 0.5816 (0.5941)	loss 5.3532 (5.5869)	grad_norm 2.4960 (3.4600/1.0883)	mem 24308MB
[2025-01-18 12:39:30 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][140/312]	eta 0:01:43 lr 0.001093	time 0.5854 (0.6042)	model_time 0.5852 (0.5932)	loss 6.1017 (5.6092)	grad_norm 2.6633 (3.4547/1.0790)	mem 24308MB
[2025-01-18 12:39:36 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][150/312]	eta 0:01:37 lr 0.001099	time 0.5866 (0.6024)	model_time 0.5865 (0.5922)	loss 5.3942 (5.6012)	grad_norm 3.7008 (3.4675/1.1068)	mem 24308MB
[2025-01-18 12:39:42 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][160/312]	eta 0:01:31 lr 0.001105	time 0.5743 (0.6009)	model_time 0.5741 (0.5913)	loss 4.7256 (5.5854)	grad_norm 3.5494 (3.4726/1.1173)	mem 24308MB
[2025-01-18 12:39:48 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][170/312]	eta 0:01:25 lr 0.001112	time 0.5788 (0.6024)	model_time 0.5786 (0.5933)	loss 5.9971 (5.5972)	grad_norm 2.4646 (3.4500/1.0952)	mem 24308MB
[2025-01-18 12:39:54 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][180/312]	eta 0:01:19 lr 0.001118	time 0.6657 (0.6047)	model_time 0.6656 (0.5961)	loss 5.1977 (5.5883)	grad_norm 2.9663 (3.4308/1.0799)	mem 24308MB
[2025-01-18 12:40:00 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][190/312]	eta 0:01:13 lr 0.001125	time 0.5836 (0.6036)	model_time 0.5834 (0.5954)	loss 5.2245 (5.5779)	grad_norm 2.9944 (3.4206/1.0610)	mem 24308MB
[2025-01-18 12:40:06 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][200/312]	eta 0:01:07 lr 0.001131	time 0.5908 (0.6024)	model_time 0.5904 (0.5947)	loss 6.0544 (5.5734)	grad_norm 2.2039 (3.4677/1.1186)	mem 24308MB
[2025-01-18 12:40:12 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][210/312]	eta 0:01:01 lr 0.001137	time 0.5704 (0.6015)	model_time 0.5703 (0.5941)	loss 5.5582 (5.5736)	grad_norm 2.7107 (3.4572/1.1006)	mem 24308MB
[2025-01-18 12:40:18 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][220/312]	eta 0:00:55 lr 0.001144	time 0.5822 (0.6005)	model_time 0.5820 (0.5934)	loss 5.9282 (5.5737)	grad_norm 2.8357 (3.4675/1.1067)	mem 24308MB
[2025-01-18 12:40:23 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][230/312]	eta 0:00:49 lr 0.001150	time 0.5949 (0.5996)	model_time 0.5947 (0.5928)	loss 5.5397 (5.5639)	grad_norm 2.4094 (3.4309/1.1017)	mem 24308MB
[2025-01-18 12:40:29 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][240/312]	eta 0:00:43 lr 0.001157	time 0.5805 (0.5988)	model_time 0.5803 (0.5923)	loss 5.2434 (5.5675)	grad_norm 3.4850 (3.4091/1.0917)	mem 24308MB
[2025-01-18 12:40:35 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][250/312]	eta 0:00:37 lr 0.001163	time 0.6159 (0.5983)	model_time 0.6155 (0.5920)	loss 4.7245 (5.5578)	grad_norm 8.5848 (3.4556/1.1512)	mem 24308MB
[2025-01-18 12:40:41 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][260/312]	eta 0:00:31 lr 0.001170	time 0.5763 (0.5976)	model_time 0.5761 (0.5916)	loss 5.9506 (5.5624)	grad_norm 3.9843 (3.5040/1.2052)	mem 24308MB
[2025-01-18 12:40:47 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][270/312]	eta 0:00:25 lr 0.001176	time 0.5825 (0.5971)	model_time 0.5824 (0.5913)	loss 5.8338 (5.5662)	grad_norm 2.8153 (3.4677/1.2045)	mem 24308MB
[2025-01-18 12:40:53 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][280/312]	eta 0:00:19 lr 0.001182	time 0.5705 (0.5964)	model_time 0.5703 (0.5908)	loss 4.6194 (5.5595)	grad_norm 2.9292 (3.4477/1.1944)	mem 24308MB
[2025-01-18 12:40:59 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][290/312]	eta 0:00:13 lr 0.001189	time 0.7154 (0.5974)	model_time 0.7149 (0.5920)	loss 4.4286 (5.5497)	grad_norm 5.4821 (3.4629/1.2085)	mem 24308MB
[2025-01-18 12:41:05 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][300/312]	eta 0:00:07 lr 0.001195	time 0.6403 (0.5985)	model_time 0.6402 (0.5932)	loss 5.6329 (5.5464)	grad_norm 4.0447 (3.4506/1.1989)	mem 24308MB
[2025-01-18 12:41:11 internimage_s_1k_224] (main.py 510): INFO Train: [5/300][310/312]	eta 0:00:01 lr 0.001202	time 0.5670 (0.5975)	model_time 0.5669 (0.5924)	loss 5.6437 (5.5369)	grad_norm 2.1212 (3.4177/1.2037)	mem 24308MB
[2025-01-18 12:41:11 internimage_s_1k_224] (main.py 519): INFO EPOCH 5 training takes 0:03:06
[2025-01-18 12:41:11 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_5.pth saving......
[2025-01-18 12:41:13 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_5.pth saved !!!
[2025-01-18 12:41:20 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.114 (7.114)	Loss 3.0738 (3.0738)	Acc@1 35.303 (35.303)	Acc@5 62.695 (62.695)	Mem 24308MB
[2025-01-18 12:41:24 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.961)	Loss 3.6984 (3.3385)	Acc@1 25.830 (31.621)	Acc@5 50.586 (57.746)	Mem 24308MB
[2025-01-18 12:41:24 internimage_s_1k_224] (main.py 575): INFO [Epoch:5] * Acc@1 32.474 Acc@5 58.633
[2025-01-18 12:41:24 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 32.5%
[2025-01-18 12:41:24 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 12:41:26 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 12:41:26 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 32.47%
[2025-01-18 12:41:34 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.641 (7.641)	Loss 6.9202 (6.9202)	Acc@1 0.000 (0.000)	Acc@5 0.146 (0.146)	Mem 24308MB
[2025-01-18 12:41:37 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.004)	Loss 6.8400 (6.8624)	Acc@1 0.024 (0.158)	Acc@5 1.196 (1.010)	Mem 24308MB
[2025-01-18 12:41:37 internimage_s_1k_224] (main.py 575): INFO [Epoch:5] * Acc@1 0.338 Acc@5 1.372
[2025-01-18 12:41:37 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.3%
[2025-01-18 12:41:37 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 12:41:40 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 12:41:40 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 0.34%
[2025-01-18 12:41:42 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][0/312]	eta 0:10:42 lr 0.001203	time 2.0589 (2.0589)	model_time 0.6126 (0.6126)	loss 6.0842 (6.0842)	grad_norm 1.5419 (1.5419/0.0000)	mem 24308MB
[2025-01-18 12:41:47 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][10/312]	eta 0:03:36 lr 0.001209	time 0.5783 (0.7167)	model_time 0.5782 (0.5849)	loss 4.7585 (5.6477)	grad_norm 2.6267 (2.5853/0.7411)	mem 24308MB
[2025-01-18 12:41:53 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][20/312]	eta 0:03:11 lr 0.001216	time 0.5848 (0.6545)	model_time 0.5847 (0.5854)	loss 6.0145 (5.5350)	grad_norm 2.4367 (3.1358/1.0272)	mem 24308MB
[2025-01-18 12:41:59 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][30/312]	eta 0:02:58 lr 0.001222	time 0.5910 (0.6320)	model_time 0.5909 (0.5850)	loss 5.5670 (5.4631)	grad_norm 2.5299 (2.9972/0.9644)	mem 24308MB
[2025-01-18 12:42:05 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][40/312]	eta 0:02:48 lr 0.001228	time 0.5834 (0.6209)	model_time 0.5832 (0.5854)	loss 5.0760 (5.4495)	grad_norm 3.4398 (3.1233/0.9493)	mem 24308MB
[2025-01-18 12:42:11 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][50/312]	eta 0:02:40 lr 0.001235	time 0.5737 (0.6133)	model_time 0.5735 (0.5847)	loss 5.0157 (5.3799)	grad_norm 2.1896 (3.0071/0.9197)	mem 24308MB
[2025-01-18 12:42:17 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][60/312]	eta 0:02:33 lr 0.001241	time 0.5763 (0.6084)	model_time 0.5761 (0.5844)	loss 5.1501 (5.3580)	grad_norm 2.5762 (3.0340/0.9227)	mem 24308MB
[2025-01-18 12:42:22 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][70/312]	eta 0:02:26 lr 0.001248	time 0.5716 (0.6045)	model_time 0.5714 (0.5838)	loss 5.3598 (5.3695)	grad_norm 3.6998 (3.0799/0.9008)	mem 24308MB
[2025-01-18 12:42:28 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][80/312]	eta 0:02:19 lr 0.001254	time 0.5982 (0.6023)	model_time 0.5981 (0.5841)	loss 4.4737 (5.3433)	grad_norm 2.1008 (3.0864/0.8989)	mem 24308MB
[2025-01-18 12:42:34 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][90/312]	eta 0:02:13 lr 0.001260	time 0.6619 (0.6009)	model_time 0.6615 (0.5848)	loss 4.6728 (5.3342)	grad_norm 2.7955 (3.0247/0.8911)	mem 24308MB
[2025-01-18 12:42:41 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][100/312]	eta 0:02:08 lr 0.001267	time 0.6817 (0.6040)	model_time 0.6816 (0.5894)	loss 5.3076 (5.3147)	grad_norm 2.3460 (3.0454/0.9075)	mem 24308MB
[2025-01-18 12:42:47 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][110/312]	eta 0:02:02 lr 0.001273	time 0.5860 (0.6068)	model_time 0.5859 (0.5935)	loss 5.6206 (5.3042)	grad_norm 2.6455 (3.0289/0.8803)	mem 24308MB
[2025-01-18 12:42:53 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][120/312]	eta 0:01:56 lr 0.001280	time 0.5723 (0.6045)	model_time 0.5722 (0.5923)	loss 4.8153 (5.3017)	grad_norm 3.6480 (3.0615/0.8793)	mem 24308MB
[2025-01-18 12:42:58 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][130/312]	eta 0:01:49 lr 0.001286	time 0.5845 (0.6026)	model_time 0.5841 (0.5913)	loss 5.8363 (5.3028)	grad_norm 4.6902 (3.0757/0.8867)	mem 24308MB
[2025-01-18 12:43:04 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][140/312]	eta 0:01:43 lr 0.001292	time 0.5964 (0.6018)	model_time 0.5963 (0.5912)	loss 4.5017 (5.3197)	grad_norm 2.9983 (3.0670/0.8930)	mem 24308MB
[2025-01-18 12:43:10 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][150/312]	eta 0:01:37 lr 0.001299	time 0.5853 (0.6006)	model_time 0.5852 (0.5907)	loss 5.6781 (5.3211)	grad_norm 2.7133 (3.0809/0.8819)	mem 24308MB
[2025-01-18 12:43:16 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][160/312]	eta 0:01:31 lr 0.001305	time 0.5713 (0.5995)	model_time 0.5711 (0.5903)	loss 5.6557 (5.3359)	grad_norm 2.6058 (3.0940/0.8841)	mem 24308MB
[2025-01-18 12:43:22 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][170/312]	eta 0:01:24 lr 0.001312	time 0.5791 (0.5986)	model_time 0.5790 (0.5898)	loss 5.3577 (5.3370)	grad_norm 3.3095 (3.0703/0.8734)	mem 24308MB
[2025-01-18 12:43:28 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][180/312]	eta 0:01:18 lr 0.001318	time 0.5700 (0.5979)	model_time 0.5698 (0.5896)	loss 6.0236 (5.3330)	grad_norm 4.6516 (3.0857/0.8705)	mem 24308MB
[2025-01-18 12:43:34 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][190/312]	eta 0:01:12 lr 0.001324	time 0.5837 (0.5970)	model_time 0.5836 (0.5892)	loss 5.4012 (5.3207)	grad_norm 2.4761 (3.0904/0.9000)	mem 24308MB
[2025-01-18 12:43:39 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][200/312]	eta 0:01:06 lr 0.001331	time 0.5900 (0.5964)	model_time 0.5895 (0.5889)	loss 5.1864 (5.3311)	grad_norm 2.2395 (3.0494/0.9052)	mem 24308MB
[2025-01-18 12:43:45 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][210/312]	eta 0:01:00 lr 0.001337	time 0.6471 (0.5964)	model_time 0.6470 (0.5893)	loss 5.2959 (5.3200)	grad_norm 2.9559 (3.0141/0.9048)	mem 24308MB
[2025-01-18 12:43:52 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][220/312]	eta 0:00:55 lr 0.001344	time 0.6814 (0.5979)	model_time 0.6813 (0.5910)	loss 5.8460 (5.3316)	grad_norm 4.1155 (3.0067/0.8931)	mem 24308MB
[2025-01-18 12:43:58 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][230/312]	eta 0:00:49 lr 0.001350	time 0.6655 (0.5996)	model_time 0.6654 (0.5931)	loss 5.5098 (5.3247)	grad_norm 2.5639 (2.9985/0.8975)	mem 24308MB
[2025-01-18 12:44:04 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][240/312]	eta 0:00:43 lr 0.001356	time 0.5724 (0.5992)	model_time 0.5723 (0.5929)	loss 4.8978 (5.3232)	grad_norm 1.9854 (2.9575/0.9018)	mem 24308MB
[2025-01-18 12:44:10 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][250/312]	eta 0:00:37 lr 0.001363	time 0.5707 (0.5985)	model_time 0.5706 (0.5924)	loss 5.3627 (5.3244)	grad_norm 1.5998 (2.9831/0.9371)	mem 24308MB
[2025-01-18 12:44:16 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][260/312]	eta 0:00:31 lr 0.001369	time 0.5828 (0.5980)	model_time 0.5826 (0.5922)	loss 5.8175 (5.3305)	grad_norm 4.1800 (2.9894/0.9291)	mem 24308MB
[2025-01-18 12:44:21 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][270/312]	eta 0:00:25 lr 0.001376	time 0.5785 (0.5976)	model_time 0.5781 (0.5919)	loss 4.6368 (5.3325)	grad_norm 2.5867 (2.9885/0.9166)	mem 24308MB
[2025-01-18 12:44:27 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][280/312]	eta 0:00:19 lr 0.001382	time 0.5853 (0.5970)	model_time 0.5851 (0.5916)	loss 5.0362 (5.3315)	grad_norm 2.6162 (2.9958/0.9051)	mem 24308MB
[2025-01-18 12:44:33 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][290/312]	eta 0:00:13 lr 0.001389	time 0.5763 (0.5965)	model_time 0.5762 (0.5912)	loss 5.8701 (5.3337)	grad_norm 10.5970 (3.0147/1.0097)	mem 24308MB
[2025-01-18 12:44:39 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][300/312]	eta 0:00:07 lr 0.001395	time 0.5656 (0.5959)	model_time 0.5655 (0.5908)	loss 4.8738 (5.3334)	grad_norm 2.7779 (3.0293/1.0203)	mem 24308MB
[2025-01-18 12:44:45 internimage_s_1k_224] (main.py 510): INFO Train: [6/300][310/312]	eta 0:00:01 lr 0.001401	time 0.5684 (0.5950)	model_time 0.5683 (0.5900)	loss 5.0733 (5.3347)	grad_norm 3.0133 (3.0659/1.0528)	mem 24308MB
[2025-01-18 12:44:45 internimage_s_1k_224] (main.py 519): INFO EPOCH 6 training takes 0:03:05
[2025-01-18 12:44:45 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_6.pth saving......
[2025-01-18 12:44:47 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_6.pth saved !!!
[2025-01-18 12:44:54 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.206 (7.206)	Loss 2.7386 (2.7386)	Acc@1 43.457 (43.457)	Acc@5 68.652 (68.652)	Mem 24308MB
[2025-01-18 12:44:58 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.963)	Loss 3.4292 (3.0584)	Acc@1 28.662 (36.832)	Acc@5 55.908 (63.592)	Mem 24308MB
[2025-01-18 12:44:58 internimage_s_1k_224] (main.py 575): INFO [Epoch:6] * Acc@1 37.766 Acc@5 64.537
[2025-01-18 12:44:58 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 37.8%
[2025-01-18 12:44:58 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 12:45:00 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 12:45:00 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 37.77%
[2025-01-18 12:45:08 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.013 (8.013)	Loss 6.9164 (6.9164)	Acc@1 0.000 (0.000)	Acc@5 0.366 (0.366)	Mem 24308MB
[2025-01-18 12:45:12 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.068)	Loss 6.8275 (6.8497)	Acc@1 0.146 (0.158)	Acc@5 1.245 (1.065)	Mem 24308MB
[2025-01-18 12:45:12 internimage_s_1k_224] (main.py 575): INFO [Epoch:6] * Acc@1 0.368 Acc@5 1.518
[2025-01-18 12:45:12 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.4%
[2025-01-18 12:45:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 12:45:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 12:45:14 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 0.37%
[2025-01-18 12:45:16 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][0/312]	eta 0:11:10 lr 0.001403	time 2.1480 (2.1480)	model_time 0.5944 (0.5944)	loss 5.7015 (5.7015)	grad_norm 2.3194 (2.3194/0.0000)	mem 24308MB
[2025-01-18 12:45:22 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][10/312]	eta 0:03:40 lr 0.001409	time 0.5916 (0.7292)	model_time 0.5914 (0.5877)	loss 4.9552 (5.5012)	grad_norm 3.1684 (2.6907/0.7037)	mem 24308MB
[2025-01-18 12:45:28 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][20/312]	eta 0:03:16 lr 0.001415	time 0.6593 (0.6741)	model_time 0.6592 (0.5998)	loss 4.4722 (5.2256)	grad_norm 3.8189 (2.7820/0.7487)	mem 24308MB
[2025-01-18 12:45:35 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][30/312]	eta 0:03:05 lr 0.001422	time 0.6572 (0.6594)	model_time 0.6571 (0.6089)	loss 5.4985 (5.2398)	grad_norm 3.4481 (3.2839/1.6788)	mem 24308MB
[2025-01-18 12:45:41 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][40/312]	eta 0:02:58 lr 0.001428	time 0.5830 (0.6575)	model_time 0.5828 (0.6193)	loss 4.3395 (5.1530)	grad_norm 2.6140 (3.0443/1.5278)	mem 24308MB
[2025-01-18 12:45:47 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][50/312]	eta 0:02:48 lr 0.001435	time 0.5922 (0.6441)	model_time 0.5918 (0.6133)	loss 5.3720 (5.1480)	grad_norm 2.5256 (2.9946/1.4188)	mem 24308MB
[2025-01-18 12:45:53 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][60/312]	eta 0:02:39 lr 0.001441	time 0.5696 (0.6336)	model_time 0.5692 (0.6078)	loss 5.0281 (5.1435)	grad_norm 2.2336 (3.0523/1.3623)	mem 24308MB
[2025-01-18 12:45:59 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][70/312]	eta 0:02:31 lr 0.001447	time 0.5854 (0.6262)	model_time 0.5852 (0.6040)	loss 4.8756 (5.1433)	grad_norm 3.2357 (3.0282/1.2992)	mem 24308MB
[2025-01-18 12:46:04 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][80/312]	eta 0:02:23 lr 0.001454	time 0.5710 (0.6206)	model_time 0.5705 (0.6011)	loss 5.8193 (5.1652)	grad_norm 2.8139 (3.0470/1.2639)	mem 24308MB
[2025-01-18 12:46:10 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][90/312]	eta 0:02:17 lr 0.001460	time 0.5940 (0.6172)	model_time 0.5938 (0.5998)	loss 5.4750 (5.1781)	grad_norm 1.6561 (3.0239/1.2190)	mem 24308MB
[2025-01-18 12:46:16 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][100/312]	eta 0:02:10 lr 0.001467	time 0.5707 (0.6138)	model_time 0.5703 (0.5981)	loss 4.4483 (5.1619)	grad_norm 4.7162 (3.0047/1.1872)	mem 24308MB
[2025-01-18 12:46:22 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][110/312]	eta 0:02:03 lr 0.001473	time 0.5846 (0.6109)	model_time 0.5844 (0.5965)	loss 4.3904 (5.1678)	grad_norm 1.7686 (2.9181/1.1729)	mem 24308MB
[2025-01-18 12:46:28 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][120/312]	eta 0:01:56 lr 0.001479	time 0.5712 (0.6083)	model_time 0.5710 (0.5951)	loss 4.3821 (5.1634)	grad_norm 1.9463 (2.8700/1.1433)	mem 24308MB
[2025-01-18 12:46:34 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][130/312]	eta 0:01:50 lr 0.001486	time 0.5761 (0.6061)	model_time 0.5759 (0.5940)	loss 5.1802 (5.1641)	grad_norm 2.2266 (2.8871/1.1216)	mem 24308MB
[2025-01-18 12:46:39 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][140/312]	eta 0:01:44 lr 0.001492	time 0.5701 (0.6048)	model_time 0.5700 (0.5935)	loss 5.2823 (5.1761)	grad_norm 2.6769 (2.8981/1.0966)	mem 24308MB
[2025-01-18 12:46:46 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][150/312]	eta 0:01:38 lr 0.001499	time 0.6519 (0.6066)	model_time 0.6517 (0.5960)	loss 5.4640 (5.1796)	grad_norm 1.8593 (2.8616/1.0802)	mem 24308MB
[2025-01-18 12:46:52 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][160/312]	eta 0:01:32 lr 0.001505	time 0.6556 (0.6094)	model_time 0.6555 (0.5994)	loss 5.1677 (5.1772)	grad_norm 3.4412 (2.8907/1.1206)	mem 24308MB
[2025-01-18 12:46:58 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][170/312]	eta 0:01:26 lr 0.001511	time 0.5709 (0.6094)	model_time 0.5705 (0.6000)	loss 4.8546 (5.1766)	grad_norm 2.5283 (2.9104/1.1280)	mem 24308MB
[2025-01-18 12:47:04 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][180/312]	eta 0:01:20 lr 0.001518	time 0.5904 (0.6078)	model_time 0.5902 (0.5989)	loss 5.0472 (5.1717)	grad_norm 2.1629 (2.9234/1.1149)	mem 24308MB
[2025-01-18 12:47:10 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][190/312]	eta 0:01:14 lr 0.001524	time 0.5690 (0.6066)	model_time 0.5689 (0.5982)	loss 4.3078 (5.1668)	grad_norm 2.9760 (2.9214/1.1115)	mem 24308MB
[2025-01-18 12:47:16 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][200/312]	eta 0:01:07 lr 0.001531	time 0.5875 (0.6056)	model_time 0.5873 (0.5975)	loss 5.7238 (5.1733)	grad_norm 2.1631 (2.9141/1.0996)	mem 24308MB
[2025-01-18 12:47:22 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][210/312]	eta 0:01:01 lr 0.001537	time 0.6012 (0.6046)	model_time 0.6010 (0.5969)	loss 4.8477 (5.1612)	grad_norm 2.3037 (2.9036/1.0789)	mem 24308MB
[2025-01-18 12:47:28 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][220/312]	eta 0:00:55 lr 0.001543	time 0.6054 (0.6037)	model_time 0.6050 (0.5963)	loss 5.4905 (5.1643)	grad_norm 2.1388 (2.8969/1.0647)	mem 24308MB
[2025-01-18 12:47:33 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][230/312]	eta 0:00:49 lr 0.001550	time 0.5822 (0.6027)	model_time 0.5821 (0.5957)	loss 5.5455 (5.1621)	grad_norm 3.9623 (2.9126/1.0545)	mem 24308MB
[2025-01-18 12:47:39 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][240/312]	eta 0:00:43 lr 0.001556	time 0.5700 (0.6021)	model_time 0.5698 (0.5953)	loss 5.0922 (5.1532)	grad_norm 4.2651 (2.9192/1.0563)	mem 24308MB
[2025-01-18 12:47:45 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][250/312]	eta 0:00:37 lr 0.001563	time 0.6242 (0.6018)	model_time 0.6240 (0.5953)	loss 5.1646 (5.1571)	grad_norm 2.7394 (2.9088/1.0402)	mem 24308MB
[2025-01-18 12:47:51 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][260/312]	eta 0:00:31 lr 0.001569	time 0.5704 (0.6014)	model_time 0.5699 (0.5951)	loss 5.7352 (5.1610)	grad_norm 3.5644 (2.9199/1.0344)	mem 24308MB
[2025-01-18 12:47:57 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][270/312]	eta 0:00:25 lr 0.001576	time 0.5884 (0.6023)	model_time 0.5883 (0.5962)	loss 5.5466 (5.1709)	grad_norm 2.3379 (2.9314/1.0512)	mem 24308MB
[2025-01-18 12:48:04 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][280/312]	eta 0:00:19 lr 0.001582	time 0.5853 (0.6036)	model_time 0.5851 (0.5977)	loss 5.6084 (5.1577)	grad_norm 3.0916 (2.9358/1.0666)	mem 24308MB
[2025-01-18 12:48:10 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][290/312]	eta 0:00:13 lr 0.001588	time 0.5923 (0.6035)	model_time 0.5921 (0.5978)	loss 5.2720 (5.1547)	grad_norm 2.3307 (2.9174/1.0609)	mem 24308MB
[2025-01-18 12:48:16 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][300/312]	eta 0:00:07 lr 0.001595	time 0.5649 (0.6027)	model_time 0.5648 (0.5972)	loss 5.4174 (5.1545)	grad_norm 3.9468 (2.8979/1.0580)	mem 24308MB
[2025-01-18 12:48:21 internimage_s_1k_224] (main.py 510): INFO Train: [7/300][310/312]	eta 0:00:01 lr 0.001601	time 0.5679 (0.6015)	model_time 0.5678 (0.5962)	loss 5.1395 (5.1547)	grad_norm 2.5673 (2.8874/1.0585)	mem 24308MB
[2025-01-18 12:48:22 internimage_s_1k_224] (main.py 519): INFO EPOCH 7 training takes 0:03:07
[2025-01-18 12:48:22 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_7.pth saving......
[2025-01-18 12:48:24 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_7.pth saved !!!
[2025-01-18 12:48:31 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.339 (7.339)	Loss 2.5414 (2.5414)	Acc@1 46.851 (46.851)	Acc@5 73.022 (73.022)	Mem 24308MB
[2025-01-18 12:48:34 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.953)	Loss 3.1967 (2.8125)	Acc@1 33.521 (40.951)	Acc@5 60.229 (67.618)	Mem 24308MB
[2025-01-18 12:48:34 internimage_s_1k_224] (main.py 575): INFO [Epoch:7] * Acc@1 41.797 Acc@5 68.422
[2025-01-18 12:48:34 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 41.8%
[2025-01-18 12:48:34 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 12:48:36 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 12:48:36 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 41.80%
[2025-01-18 12:48:44 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.970 (7.970)	Loss 6.9082 (6.9082)	Acc@1 0.000 (0.000)	Acc@5 1.050 (1.050)	Mem 24308MB
[2025-01-18 12:48:48 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.048)	Loss 6.8169 (6.8384)	Acc@1 0.171 (0.162)	Acc@5 1.270 (1.112)	Mem 24308MB
[2025-01-18 12:48:48 internimage_s_1k_224] (main.py 575): INFO [Epoch:7] * Acc@1 0.452 Acc@5 1.583
[2025-01-18 12:48:48 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.5%
[2025-01-18 12:48:48 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 12:48:50 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 12:48:50 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 0.45%
[2025-01-18 12:48:52 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][0/312]	eta 0:10:47 lr 0.001602	time 2.0743 (2.0743)	model_time 0.6006 (0.6006)	loss 4.8430 (4.8430)	grad_norm 3.7960 (3.7960/0.0000)	mem 24308MB
[2025-01-18 12:48:58 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][10/312]	eta 0:03:39 lr 0.001609	time 0.5856 (0.7253)	model_time 0.5854 (0.5911)	loss 4.6020 (4.9925)	grad_norm 2.2983 (2.9931/0.6672)	mem 24308MB
[2025-01-18 12:49:04 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][20/312]	eta 0:03:12 lr 0.001615	time 0.5912 (0.6584)	model_time 0.5911 (0.5879)	loss 5.8100 (5.0910)	grad_norm 2.7895 (2.9330/0.9299)	mem 24308MB
[2025-01-18 12:49:10 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][30/312]	eta 0:02:58 lr 0.001622	time 0.5876 (0.6341)	model_time 0.5874 (0.5862)	loss 5.4423 (5.1593)	grad_norm 1.9040 (2.7678/0.8425)	mem 24308MB
[2025-01-18 12:49:16 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][40/312]	eta 0:02:49 lr 0.001628	time 0.5897 (0.6220)	model_time 0.5893 (0.5858)	loss 5.0988 (5.1396)	grad_norm 2.8351 (2.7024/0.7675)	mem 24308MB
[2025-01-18 12:49:22 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][50/312]	eta 0:02:41 lr 0.001634	time 0.5948 (0.6150)	model_time 0.5946 (0.5858)	loss 5.7035 (5.1145)	grad_norm 2.4616 (2.7120/0.7329)	mem 24308MB
[2025-01-18 12:49:27 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][60/312]	eta 0:02:33 lr 0.001641	time 0.6010 (0.6108)	model_time 0.6008 (0.5864)	loss 5.3653 (5.1560)	grad_norm 3.1735 (2.6968/0.6866)	mem 24308MB
[2025-01-18 12:49:34 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][70/312]	eta 0:02:27 lr 0.001647	time 0.5805 (0.6096)	model_time 0.5804 (0.5886)	loss 5.0754 (5.1729)	grad_norm 2.6790 (2.6529/0.7052)	mem 24308MB
[2025-01-18 12:49:40 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][80/312]	eta 0:02:21 lr 0.001654	time 0.5686 (0.6120)	model_time 0.5684 (0.5935)	loss 4.2955 (5.1684)	grad_norm 3.1090 (2.8512/0.9993)	mem 24308MB
[2025-01-18 12:49:46 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][90/312]	eta 0:02:16 lr 0.001660	time 0.5768 (0.6137)	model_time 0.5764 (0.5972)	loss 5.4497 (5.1663)	grad_norm 2.2102 (2.8328/0.9878)	mem 24308MB
[2025-01-18 12:49:52 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][100/312]	eta 0:02:10 lr 0.001666	time 0.5690 (0.6133)	model_time 0.5687 (0.5984)	loss 5.1234 (5.1383)	grad_norm 3.0379 (2.8233/0.9478)	mem 24308MB
[2025-01-18 12:49:58 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][110/312]	eta 0:02:03 lr 0.001673	time 0.5765 (0.6110)	model_time 0.5764 (0.5974)	loss 5.2464 (5.1345)	grad_norm 1.4398 (2.7998/0.9359)	mem 24308MB
[2025-01-18 12:50:04 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][120/312]	eta 0:01:56 lr 0.001679	time 0.5700 (0.6090)	model_time 0.5696 (0.5965)	loss 5.5269 (5.1225)	grad_norm 3.5448 (2.7691/0.9293)	mem 24308MB
[2025-01-18 12:50:10 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][130/312]	eta 0:01:50 lr 0.001686	time 0.5945 (0.6071)	model_time 0.5940 (0.5955)	loss 5.9586 (5.1221)	grad_norm 2.1383 (2.7482/0.9111)	mem 24308MB
[2025-01-18 12:50:16 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][140/312]	eta 0:01:44 lr 0.001692	time 0.5731 (0.6051)	model_time 0.5730 (0.5944)	loss 4.0565 (5.1180)	grad_norm 2.8630 (2.7333/0.8884)	mem 24308MB
[2025-01-18 12:50:21 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][150/312]	eta 0:01:37 lr 0.001698	time 0.5712 (0.6037)	model_time 0.5711 (0.5937)	loss 5.7580 (5.1320)	grad_norm 2.4775 (2.7486/0.9436)	mem 24308MB
[2025-01-18 12:50:27 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][160/312]	eta 0:01:31 lr 0.001705	time 0.5942 (0.6026)	model_time 0.5940 (0.5932)	loss 5.2246 (5.1155)	grad_norm 4.2904 (2.7695/0.9441)	mem 24308MB
[2025-01-18 12:50:33 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][170/312]	eta 0:01:25 lr 0.001711	time 0.6072 (0.6015)	model_time 0.6071 (0.5926)	loss 4.9178 (5.1134)	grad_norm 4.2616 (2.8007/1.0409)	mem 24308MB
[2025-01-18 12:50:39 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][180/312]	eta 0:01:19 lr 0.001718	time 0.5830 (0.6008)	model_time 0.5826 (0.5923)	loss 5.3886 (5.1144)	grad_norm 2.5882 (2.7930/1.0211)	mem 24308MB
[2025-01-18 12:50:45 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][190/312]	eta 0:01:13 lr 0.001724	time 0.5812 (0.6006)	model_time 0.5810 (0.5925)	loss 5.8423 (5.1176)	grad_norm 2.1020 (2.7990/1.0082)	mem 24308MB
[2025-01-18 12:50:51 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][200/312]	eta 0:01:07 lr 0.001730	time 0.5766 (0.6016)	model_time 0.5764 (0.5939)	loss 5.6059 (5.1189)	grad_norm 2.7810 (2.7850/0.9950)	mem 24308MB
[2025-01-18 12:50:57 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][210/312]	eta 0:01:01 lr 0.001737	time 0.6661 (0.6030)	model_time 0.6656 (0.5957)	loss 5.6997 (5.1347)	grad_norm 2.7804 (2.7577/0.9823)	mem 24308MB
[2025-01-18 12:51:04 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][220/312]	eta 0:00:55 lr 0.001743	time 0.5739 (0.6031)	model_time 0.5735 (0.5961)	loss 4.2435 (5.1291)	grad_norm 3.0565 (2.7792/0.9836)	mem 24308MB
[2025-01-18 12:51:09 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][230/312]	eta 0:00:49 lr 0.001750	time 0.5882 (0.6021)	model_time 0.5881 (0.5954)	loss 5.3185 (5.1287)	grad_norm 1.2891 (2.7884/0.9879)	mem 24308MB
[2025-01-18 12:51:15 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][240/312]	eta 0:00:43 lr 0.001756	time 0.5707 (0.6011)	model_time 0.5705 (0.5947)	loss 5.4170 (5.1174)	grad_norm 3.2264 (2.7699/0.9776)	mem 24308MB
[2025-01-18 12:51:21 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][250/312]	eta 0:00:37 lr 0.001762	time 0.5704 (0.6004)	model_time 0.5703 (0.5942)	loss 3.8367 (5.1041)	grad_norm 4.3846 (2.7971/0.9937)	mem 24308MB
[2025-01-18 12:51:27 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][260/312]	eta 0:00:31 lr 0.001769	time 0.6076 (0.5998)	model_time 0.6074 (0.5938)	loss 5.1986 (5.0928)	grad_norm 2.1007 (2.7735/0.9841)	mem 24308MB
[2025-01-18 12:51:33 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][270/312]	eta 0:00:25 lr 0.001775	time 0.5844 (0.5990)	model_time 0.5842 (0.5932)	loss 5.4241 (5.0920)	grad_norm 2.1888 (2.7810/0.9860)	mem 24308MB
[2025-01-18 12:51:38 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][280/312]	eta 0:00:19 lr 0.001782	time 0.5974 (0.5986)	model_time 0.5972 (0.5930)	loss 5.6518 (5.0918)	grad_norm 2.6720 (2.7991/1.0044)	mem 24308MB
[2025-01-18 12:51:44 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][290/312]	eta 0:00:13 lr 0.001788	time 0.5864 (0.5982)	model_time 0.5859 (0.5928)	loss 4.0404 (5.0770)	grad_norm 1.5241 (2.7912/0.9938)	mem 24308MB
[2025-01-18 12:51:50 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][300/312]	eta 0:00:07 lr 0.001795	time 0.5645 (0.5974)	model_time 0.5644 (0.5922)	loss 4.9349 (5.0674)	grad_norm 2.4080 (2.7863/0.9855)	mem 24308MB
[2025-01-18 12:51:56 internimage_s_1k_224] (main.py 510): INFO Train: [8/300][310/312]	eta 0:00:01 lr 0.001801	time 0.5712 (0.5967)	model_time 0.5711 (0.5916)	loss 5.2777 (5.0666)	grad_norm 5.3427 (2.7995/0.9944)	mem 24308MB
[2025-01-18 12:51:56 internimage_s_1k_224] (main.py 519): INFO EPOCH 8 training takes 0:03:06
[2025-01-18 12:51:56 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_8.pth saving......
[2025-01-18 12:51:58 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_8.pth saved !!!
[2025-01-18 12:52:05 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.219 (7.219)	Loss 2.2329 (2.2329)	Acc@1 53.247 (53.247)	Acc@5 78.662 (78.662)	Mem 24308MB
[2025-01-18 12:52:09 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.960)	Loss 2.9733 (2.5821)	Acc@1 38.110 (46.054)	Acc@5 65.088 (72.346)	Mem 24308MB
[2025-01-18 12:52:09 internimage_s_1k_224] (main.py 575): INFO [Epoch:8] * Acc@1 46.579 Acc@5 72.717
[2025-01-18 12:52:09 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 46.6%
[2025-01-18 12:52:09 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 12:52:11 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 12:52:11 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 46.58%
[2025-01-18 12:52:18 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.397 (7.397)	Loss 6.8982 (6.8982)	Acc@1 0.000 (0.000)	Acc@5 1.978 (1.978)	Mem 24308MB
[2025-01-18 12:52:21 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.969)	Loss 6.8062 (6.8280)	Acc@1 0.171 (0.158)	Acc@5 1.074 (1.290)	Mem 24308MB
[2025-01-18 12:52:22 internimage_s_1k_224] (main.py 575): INFO [Epoch:8] * Acc@1 0.462 Acc@5 1.767
[2025-01-18 12:52:22 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.5%
[2025-01-18 12:52:22 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 12:52:24 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 12:52:24 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 0.46%
[2025-01-18 12:52:26 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][0/312]	eta 0:11:49 lr 0.001802	time 2.2740 (2.2740)	model_time 0.5933 (0.5933)	loss 5.1256 (5.1256)	grad_norm 1.6409 (1.6409/0.0000)	mem 24308MB
[2025-01-18 12:52:33 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][10/312]	eta 0:03:58 lr 0.001809	time 0.6696 (0.7900)	model_time 0.6695 (0.6370)	loss 4.5701 (5.0069)	grad_norm 4.7126 (3.2223/1.2822)	mem 24308MB
[2025-01-18 12:52:39 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][20/312]	eta 0:03:29 lr 0.001815	time 0.6629 (0.7170)	model_time 0.6621 (0.6367)	loss 5.2722 (5.0021)	grad_norm 2.1590 (2.9818/1.0343)	mem 24308MB
[2025-01-18 12:52:45 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][30/312]	eta 0:03:12 lr 0.001821	time 0.5789 (0.6835)	model_time 0.5788 (0.6289)	loss 4.8317 (4.9538)	grad_norm 2.3593 (2.8180/0.9258)	mem 24308MB
[2025-01-18 12:52:51 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][40/312]	eta 0:02:59 lr 0.001828	time 0.5747 (0.6585)	model_time 0.5745 (0.6172)	loss 5.3202 (4.9156)	grad_norm 2.6647 (2.7079/0.8535)	mem 24308MB
[2025-01-18 12:52:57 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][50/312]	eta 0:02:48 lr 0.001834	time 0.6087 (0.6443)	model_time 0.6086 (0.6111)	loss 3.7762 (4.8261)	grad_norm 1.8939 (2.7220/0.8343)	mem 24308MB
[2025-01-18 12:53:03 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][60/312]	eta 0:02:39 lr 0.001841	time 0.5912 (0.6346)	model_time 0.5911 (0.6067)	loss 5.4993 (4.7868)	grad_norm 2.6373 (2.7086/0.8162)	mem 24308MB
[2025-01-18 12:53:08 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][70/312]	eta 0:02:31 lr 0.001847	time 0.5751 (0.6275)	model_time 0.5750 (0.6036)	loss 3.8586 (4.7857)	grad_norm 3.3861 (2.7095/0.8127)	mem 24308MB
[2025-01-18 12:53:14 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][80/312]	eta 0:02:24 lr 0.001853	time 0.5890 (0.6219)	model_time 0.5888 (0.6009)	loss 5.0093 (4.7612)	grad_norm 2.0289 (2.6901/0.8211)	mem 24308MB
[2025-01-18 12:53:20 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][90/312]	eta 0:02:17 lr 0.001860	time 0.6086 (0.6178)	model_time 0.6081 (0.5990)	loss 5.4684 (4.8066)	grad_norm 1.9004 (2.7079/0.8363)	mem 24308MB
[2025-01-18 12:53:26 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][100/312]	eta 0:02:10 lr 0.001866	time 0.6184 (0.6150)	model_time 0.6183 (0.5980)	loss 3.8808 (4.7914)	grad_norm 2.5588 (2.6556/0.8170)	mem 24308MB
[2025-01-18 12:53:32 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][110/312]	eta 0:02:03 lr 0.001873	time 0.5825 (0.6121)	model_time 0.5824 (0.5966)	loss 4.3707 (4.8120)	grad_norm 2.0125 (2.7286/0.9129)	mem 24308MB
[2025-01-18 12:53:38 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][120/312]	eta 0:01:57 lr 0.001879	time 0.6420 (0.6110)	model_time 0.6419 (0.5967)	loss 5.7559 (4.8297)	grad_norm 1.5777 (2.7016/0.9007)	mem 24308MB
[2025-01-18 12:53:44 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][130/312]	eta 0:01:51 lr 0.001885	time 0.6778 (0.6113)	model_time 0.6777 (0.5981)	loss 5.3564 (4.8609)	grad_norm 2.2949 (2.7216/0.9023)	mem 24308MB
[2025-01-18 12:53:50 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][140/312]	eta 0:01:45 lr 0.001892	time 0.5737 (0.6132)	model_time 0.5736 (0.6010)	loss 4.3959 (4.8491)	grad_norm 4.8966 (2.8132/1.0205)	mem 24308MB
[2025-01-18 12:53:57 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][150/312]	eta 0:01:39 lr 0.001898	time 0.6442 (0.6139)	model_time 0.6440 (0.6024)	loss 4.4375 (4.8492)	grad_norm 1.9228 (2.7791/1.0010)	mem 24308MB
[2025-01-18 12:54:02 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][160/312]	eta 0:01:33 lr 0.001905	time 0.5847 (0.6121)	model_time 0.5845 (0.6013)	loss 5.4528 (4.8497)	grad_norm 2.7521 (2.8102/1.0227)	mem 24308MB
[2025-01-18 12:54:08 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][170/312]	eta 0:01:26 lr 0.001911	time 0.5814 (0.6104)	model_time 0.5810 (0.6003)	loss 4.5538 (4.8619)	grad_norm 1.9626 (2.8320/1.0500)	mem 24308MB
[2025-01-18 12:54:14 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][180/312]	eta 0:01:20 lr 0.001917	time 0.5709 (0.6089)	model_time 0.5705 (0.5993)	loss 4.9194 (4.8553)	grad_norm 2.2185 (2.7984/1.0319)	mem 24308MB
[2025-01-18 12:54:20 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][190/312]	eta 0:01:14 lr 0.001924	time 0.5855 (0.6076)	model_time 0.5854 (0.5984)	loss 3.8569 (4.8542)	grad_norm 3.4374 (2.8313/1.0271)	mem 24308MB
[2025-01-18 12:54:26 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][200/312]	eta 0:01:07 lr 0.001930	time 0.5738 (0.6064)	model_time 0.5734 (0.5977)	loss 4.8366 (4.8531)	grad_norm 2.5759 (2.8134/1.0076)	mem 24308MB
[2025-01-18 12:54:32 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][210/312]	eta 0:01:01 lr 0.001937	time 0.5922 (0.6054)	model_time 0.5920 (0.5972)	loss 5.0192 (4.8624)	grad_norm 2.8910 (2.8287/0.9967)	mem 24308MB
[2025-01-18 12:54:38 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][220/312]	eta 0:00:55 lr 0.001943	time 0.5849 (0.6044)	model_time 0.5847 (0.5965)	loss 5.1932 (4.8554)	grad_norm 1.3040 (2.8351/0.9965)	mem 24308MB
[2025-01-18 12:54:43 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][230/312]	eta 0:00:49 lr 0.001949	time 0.5914 (0.6035)	model_time 0.5910 (0.5959)	loss 4.8680 (4.8656)	grad_norm 1.2835 (2.8069/0.9868)	mem 24308MB
[2025-01-18 12:54:49 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][240/312]	eta 0:00:43 lr 0.001956	time 0.5724 (0.6029)	model_time 0.5722 (0.5956)	loss 5.4665 (4.8609)	grad_norm 3.3229 (2.8002/0.9742)	mem 24308MB
[2025-01-18 12:54:55 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][250/312]	eta 0:00:37 lr 0.001962	time 0.6606 (0.6035)	model_time 0.6604 (0.5964)	loss 4.0094 (4.8618)	grad_norm 1.8653 (2.7898/0.9618)	mem 24308MB
[2025-01-18 12:55:02 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][260/312]	eta 0:00:31 lr 0.001969	time 0.6574 (0.6045)	model_time 0.6568 (0.5977)	loss 5.3940 (4.8525)	grad_norm 4.2554 (2.7810/0.9539)	mem 24308MB
[2025-01-18 12:55:08 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][270/312]	eta 0:00:25 lr 0.001975	time 0.6935 (0.6057)	model_time 0.6934 (0.5991)	loss 5.0059 (4.8492)	grad_norm 2.2056 (2.7898/0.9590)	mem 24308MB
[2025-01-18 12:55:14 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][280/312]	eta 0:00:19 lr 0.001982	time 0.5818 (0.6051)	model_time 0.5817 (0.5987)	loss 4.2170 (4.8425)	grad_norm 1.3597 (2.7565/0.9588)	mem 24308MB
[2025-01-18 12:55:20 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][290/312]	eta 0:00:13 lr 0.001988	time 0.5710 (0.6043)	model_time 0.5709 (0.5981)	loss 4.1773 (4.8500)	grad_norm 3.1039 (2.7403/0.9485)	mem 24308MB
[2025-01-18 12:55:26 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][300/312]	eta 0:00:07 lr 0.001994	time 0.5661 (0.6033)	model_time 0.5660 (0.5973)	loss 4.6006 (4.8474)	grad_norm 5.7763 (2.7577/0.9610)	mem 24308MB
[2025-01-18 12:55:31 internimage_s_1k_224] (main.py 510): INFO Train: [9/300][310/312]	eta 0:00:01 lr 0.002001	time 0.5657 (0.6022)	model_time 0.5656 (0.5964)	loss 4.6664 (4.8471)	grad_norm 2.3578 (2.7568/0.9756)	mem 24308MB
[2025-01-18 12:55:32 internimage_s_1k_224] (main.py 519): INFO EPOCH 9 training takes 0:03:07
[2025-01-18 12:55:32 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_9.pth saving......
[2025-01-18 12:55:33 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_9.pth saved !!!
[2025-01-18 12:55:41 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.345 (7.345)	Loss 2.0565 (2.0565)	Acc@1 55.420 (55.420)	Acc@5 80.542 (80.542)	Mem 24308MB
[2025-01-18 12:55:44 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.962)	Loss 2.8300 (2.4086)	Acc@1 41.040 (49.325)	Acc@5 67.847 (75.435)	Mem 24308MB
[2025-01-18 12:55:44 internimage_s_1k_224] (main.py 575): INFO [Epoch:9] * Acc@1 49.824 Acc@5 75.760
[2025-01-18 12:55:44 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 49.8%
[2025-01-18 12:55:44 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 12:55:46 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 12:55:46 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 49.82%
[2025-01-18 12:55:54 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.270 (7.270)	Loss 6.8884 (6.8884)	Acc@1 0.073 (0.073)	Acc@5 2.539 (2.539)	Mem 24308MB
[2025-01-18 12:55:57 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.951)	Loss 6.7937 (6.8171)	Acc@1 0.195 (0.160)	Acc@5 1.074 (1.409)	Mem 24308MB
[2025-01-18 12:55:57 internimage_s_1k_224] (main.py 575): INFO [Epoch:9] * Acc@1 0.468 Acc@5 1.877
[2025-01-18 12:55:57 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.5%
[2025-01-18 12:55:57 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 12:55:59 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 12:55:59 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 0.47%
[2025-01-18 12:56:01 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][0/312]	eta 0:12:03 lr 0.002002	time 2.3188 (2.3188)	model_time 0.5935 (0.5935)	loss 4.9679 (4.9679)	grad_norm 2.5188 (2.5188/0.0000)	mem 24308MB
[2025-01-18 12:56:07 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][10/312]	eta 0:03:45 lr 0.002008	time 0.5966 (0.7472)	model_time 0.5965 (0.5900)	loss 5.1432 (4.8824)	grad_norm 2.3423 (2.7303/0.9281)	mem 24308MB
[2025-01-18 12:56:13 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][20/312]	eta 0:03:17 lr 0.002015	time 0.6428 (0.6747)	model_time 0.6426 (0.5923)	loss 4.4788 (4.7215)	grad_norm 2.6389 (2.7789/0.9467)	mem 24308MB
[2025-01-18 12:56:19 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][30/312]	eta 0:03:02 lr 0.002021	time 0.5760 (0.6488)	model_time 0.5755 (0.5929)	loss 3.8460 (4.7298)	grad_norm 2.3986 (2.5964/0.8615)	mem 24308MB
[2025-01-18 12:56:25 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][40/312]	eta 0:02:51 lr 0.002028	time 0.5737 (0.6319)	model_time 0.5736 (0.5895)	loss 4.0883 (4.7311)	grad_norm 2.6334 (2.7599/1.0194)	mem 24308MB
[2025-01-18 12:56:31 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][50/312]	eta 0:02:43 lr 0.002034	time 0.5699 (0.6228)	model_time 0.5698 (0.5886)	loss 5.2139 (4.7605)	grad_norm 2.1525 (2.9187/1.1375)	mem 24308MB
[2025-01-18 12:56:37 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][60/312]	eta 0:02:36 lr 0.002040	time 0.5854 (0.6218)	model_time 0.5850 (0.5931)	loss 5.1492 (4.7726)	grad_norm 3.0030 (2.8465/1.0659)	mem 24308MB
[2025-01-18 12:56:44 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][70/312]	eta 0:02:31 lr 0.002047	time 0.8295 (0.6259)	model_time 0.8291 (0.6013)	loss 5.0422 (4.7480)	grad_norm 1.3132 (2.8015/1.0329)	mem 24308MB
[2025-01-18 12:56:50 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][80/312]	eta 0:02:24 lr 0.002053	time 0.5705 (0.6243)	model_time 0.5701 (0.6026)	loss 5.5194 (4.7675)	grad_norm 1.4911 (2.7780/1.0167)	mem 24308MB
[2025-01-18 12:56:56 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][90/312]	eta 0:02:17 lr 0.002060	time 0.5636 (0.6210)	model_time 0.5634 (0.6017)	loss 5.5658 (4.7819)	grad_norm 2.8910 (2.7418/1.0019)	mem 24308MB
[2025-01-18 12:57:01 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][100/312]	eta 0:02:10 lr 0.002066	time 0.5759 (0.6175)	model_time 0.5757 (0.6001)	loss 5.6485 (4.7945)	grad_norm 1.5527 (2.7073/0.9758)	mem 24308MB
[2025-01-18 12:57:07 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][110/312]	eta 0:02:04 lr 0.002072	time 0.5697 (0.6149)	model_time 0.5692 (0.5990)	loss 5.2524 (4.8075)	grad_norm 2.6487 (2.6974/0.9405)	mem 24308MB
[2025-01-18 12:57:13 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][120/312]	eta 0:01:57 lr 0.002079	time 0.5882 (0.6121)	model_time 0.5877 (0.5975)	loss 5.5767 (4.8491)	grad_norm 2.0905 (2.6452/0.9193)	mem 24308MB
[2025-01-18 12:57:19 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][130/312]	eta 0:01:51 lr 0.002085	time 0.5939 (0.6104)	model_time 0.5937 (0.5968)	loss 5.6842 (4.8445)	grad_norm 2.2220 (2.6223/0.9167)	mem 24308MB
[2025-01-18 12:57:25 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][140/312]	eta 0:01:44 lr 0.002092	time 0.5899 (0.6083)	model_time 0.5897 (0.5957)	loss 4.0781 (4.8419)	grad_norm 2.4397 (2.6518/0.9338)	mem 24308MB
[2025-01-18 12:57:31 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][150/312]	eta 0:01:38 lr 0.002098	time 0.5813 (0.6076)	model_time 0.5809 (0.5958)	loss 4.4708 (4.8314)	grad_norm 2.0641 (2.6626/0.9336)	mem 24308MB
[2025-01-18 12:57:37 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][160/312]	eta 0:01:32 lr 0.002104	time 0.5864 (0.6065)	model_time 0.5862 (0.5954)	loss 5.1271 (4.8232)	grad_norm 3.3196 (2.6492/0.9153)	mem 24308MB
[2025-01-18 12:57:43 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][170/312]	eta 0:01:25 lr 0.002111	time 0.5707 (0.6051)	model_time 0.5703 (0.5946)	loss 4.8270 (4.8195)	grad_norm 2.2457 (2.6669/0.9185)	mem 24308MB
[2025-01-18 12:57:49 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][180/312]	eta 0:01:19 lr 0.002117	time 0.6643 (0.6055)	model_time 0.6638 (0.5956)	loss 3.4981 (4.8180)	grad_norm 2.6724 (2.6753/0.9143)	mem 24308MB
[2025-01-18 12:57:55 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][190/312]	eta 0:01:14 lr 0.002124	time 0.6691 (0.6076)	model_time 0.6689 (0.5982)	loss 5.6306 (4.8310)	grad_norm 1.7850 (2.6450/0.9134)	mem 24308MB
[2025-01-18 12:58:02 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][200/312]	eta 0:01:08 lr 0.002130	time 0.5745 (0.6092)	model_time 0.5741 (0.6002)	loss 5.0351 (4.8380)	grad_norm 2.5786 (2.6656/0.9104)	mem 24308MB
[2025-01-18 12:58:08 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][210/312]	eta 0:01:02 lr 0.002136	time 0.5704 (0.6087)	model_time 0.5702 (0.6002)	loss 4.2840 (4.8191)	grad_norm 2.4895 (2.6586/0.8961)	mem 24308MB
[2025-01-18 12:58:13 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][220/312]	eta 0:00:55 lr 0.002143	time 0.5717 (0.6075)	model_time 0.5713 (0.5993)	loss 5.4754 (4.8016)	grad_norm 2.3518 (2.6781/0.9078)	mem 24308MB
[2025-01-18 12:58:19 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][230/312]	eta 0:00:49 lr 0.002149	time 0.5815 (0.6065)	model_time 0.5813 (0.5987)	loss 5.3242 (4.8024)	grad_norm 2.1760 (2.6856/0.9064)	mem 24308MB
[2025-01-18 12:58:25 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][240/312]	eta 0:00:43 lr 0.002156	time 0.6113 (0.6056)	model_time 0.6109 (0.5981)	loss 4.8499 (4.8019)	grad_norm 2.3720 (2.6910/0.9041)	mem 24308MB
[2025-01-18 12:58:31 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][250/312]	eta 0:00:37 lr 0.002162	time 0.6115 (0.6047)	model_time 0.6110 (0.5975)	loss 4.9875 (4.8009)	grad_norm 1.8317 (2.6803/0.9051)	mem 24308MB
[2025-01-18 12:58:37 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][260/312]	eta 0:00:31 lr 0.002169	time 0.5736 (0.6038)	model_time 0.5731 (0.5968)	loss 4.9531 (4.8044)	grad_norm 2.9295 (2.6688/0.8989)	mem 24308MB
[2025-01-18 12:58:43 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][270/312]	eta 0:00:25 lr 0.002175	time 0.5701 (0.6035)	model_time 0.5696 (0.5967)	loss 5.1227 (4.8082)	grad_norm 2.9709 (2.6740/0.8971)	mem 24308MB
[2025-01-18 12:58:49 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][280/312]	eta 0:00:19 lr 0.002181	time 0.5927 (0.6028)	model_time 0.5923 (0.5962)	loss 4.0187 (4.7957)	grad_norm 4.0373 (2.6738/0.8921)	mem 24308MB
[2025-01-18 12:58:54 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][290/312]	eta 0:00:13 lr 0.002188	time 0.5677 (0.6020)	model_time 0.5676 (0.5957)	loss 5.3992 (4.8016)	grad_norm 2.4259 (2.6649/0.8819)	mem 24308MB
[2025-01-18 12:59:00 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][300/312]	eta 0:00:07 lr 0.002194	time 0.6701 (0.6024)	model_time 0.6700 (0.5962)	loss 3.7363 (4.7990)	grad_norm 2.2302 (2.6624/0.8833)	mem 24308MB
[2025-01-18 12:59:06 internimage_s_1k_224] (main.py 510): INFO Train: [10/300][310/312]	eta 0:00:01 lr 0.002201	time 0.5670 (0.6023)	model_time 0.5669 (0.5963)	loss 4.5725 (4.7959)	grad_norm 2.8772 (2.6674/0.8865)	mem 24308MB
[2025-01-18 12:59:07 internimage_s_1k_224] (main.py 519): INFO EPOCH 10 training takes 0:03:08
[2025-01-18 12:59:07 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_10.pth saving......
[2025-01-18 12:59:09 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_10.pth saved !!!
[2025-01-18 12:59:16 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.267 (7.267)	Loss 1.9764 (1.9764)	Acc@1 58.228 (58.228)	Acc@5 81.982 (81.982)	Mem 24308MB
[2025-01-18 12:59:20 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.955)	Loss 2.7035 (2.2806)	Acc@1 45.117 (52.346)	Acc@5 70.972 (77.672)	Mem 24308MB
[2025-01-18 12:59:20 internimage_s_1k_224] (main.py 575): INFO [Epoch:10] * Acc@1 52.913 Acc@5 78.091
[2025-01-18 12:59:20 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 52.9%
[2025-01-18 12:59:20 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 12:59:22 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 12:59:22 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 52.91%
[2025-01-18 12:59:30 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.828 (7.828)	Loss 6.8764 (6.8764)	Acc@1 0.073 (0.073)	Acc@5 2.954 (2.954)	Mem 24308MB
[2025-01-18 12:59:33 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.056)	Loss 6.7812 (6.8052)	Acc@1 0.220 (0.164)	Acc@5 1.270 (1.518)	Mem 24308MB
[2025-01-18 12:59:34 internimage_s_1k_224] (main.py 575): INFO [Epoch:10] * Acc@1 0.472 Acc@5 1.993
[2025-01-18 12:59:34 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.5%
[2025-01-18 12:59:34 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 12:59:36 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 12:59:36 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 0.47%
[2025-01-18 12:59:38 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][0/312]	eta 0:12:03 lr 0.002202	time 2.3184 (2.3184)	model_time 0.5975 (0.5975)	loss 5.1576 (5.1576)	grad_norm 2.4931 (2.4931/0.0000)	mem 24308MB
[2025-01-18 12:59:44 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][10/312]	eta 0:03:58 lr 0.002208	time 0.5828 (0.7905)	model_time 0.5826 (0.6338)	loss 5.1645 (4.6710)	grad_norm 4.1036 (2.7045/0.8126)	mem 24308MB
[2025-01-18 12:59:50 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][20/312]	eta 0:03:24 lr 0.002215	time 0.6061 (0.7006)	model_time 0.6059 (0.6183)	loss 5.2454 (4.6777)	grad_norm 3.1472 (2.7200/1.1130)	mem 24308MB
[2025-01-18 12:59:56 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][30/312]	eta 0:03:06 lr 0.002221	time 0.5720 (0.6618)	model_time 0.5715 (0.6059)	loss 5.3750 (4.7388)	grad_norm 1.5105 (2.5880/0.9993)	mem 24308MB
[2025-01-18 13:00:02 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][40/312]	eta 0:02:55 lr 0.002227	time 0.6019 (0.6439)	model_time 0.6016 (0.6015)	loss 4.4692 (4.6428)	grad_norm 2.9028 (2.5696/0.9234)	mem 24308MB
[2025-01-18 13:00:08 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][50/312]	eta 0:02:45 lr 0.002234	time 0.5823 (0.6330)	model_time 0.5818 (0.5989)	loss 3.8963 (4.6502)	grad_norm 2.2239 (2.4511/0.8769)	mem 24308MB
[2025-01-18 13:00:14 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][60/312]	eta 0:02:37 lr 0.002240	time 0.5751 (0.6253)	model_time 0.5749 (0.5968)	loss 5.1667 (4.6658)	grad_norm 2.2725 (2.5415/0.9838)	mem 24308MB
[2025-01-18 13:00:20 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][70/312]	eta 0:02:29 lr 0.002247	time 0.5747 (0.6198)	model_time 0.5743 (0.5952)	loss 5.3808 (4.6771)	grad_norm 1.8486 (2.5565/0.9584)	mem 24308MB
[2025-01-18 13:00:26 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][80/312]	eta 0:02:22 lr 0.002253	time 0.5904 (0.6156)	model_time 0.5903 (0.5940)	loss 5.3564 (4.6932)	grad_norm 2.2568 (2.5469/0.9652)	mem 24308MB
[2025-01-18 13:00:32 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][90/312]	eta 0:02:16 lr 0.002259	time 0.5717 (0.6134)	model_time 0.5712 (0.5941)	loss 5.3060 (4.6684)	grad_norm 2.9860 (2.5631/0.9543)	mem 24308MB
[2025-01-18 13:00:37 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][100/312]	eta 0:02:09 lr 0.002266	time 0.5771 (0.6104)	model_time 0.5769 (0.5930)	loss 5.3264 (4.6794)	grad_norm 3.3069 (2.5464/0.9367)	mem 24308MB
[2025-01-18 13:00:44 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][110/312]	eta 0:02:03 lr 0.002272	time 0.5735 (0.6112)	model_time 0.5733 (0.5953)	loss 3.6391 (4.6638)	grad_norm 4.1787 (2.5446/0.9256)	mem 24308MB
[2025-01-18 13:00:50 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][120/312]	eta 0:01:57 lr 0.002279	time 0.5856 (0.6119)	model_time 0.5854 (0.5974)	loss 5.4587 (4.6648)	grad_norm 2.3870 (2.5162/0.9088)	mem 24308MB
[2025-01-18 13:00:56 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][130/312]	eta 0:01:51 lr 0.002285	time 0.6634 (0.6149)	model_time 0.6629 (0.6014)	loss 5.3710 (4.6941)	grad_norm 1.4565 (2.4930/0.8892)	mem 24308MB
[2025-01-18 13:01:02 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][140/312]	eta 0:01:45 lr 0.002291	time 0.6001 (0.6143)	model_time 0.5994 (0.6017)	loss 5.1070 (4.6942)	grad_norm 2.7828 (2.4698/0.8718)	mem 24308MB
[2025-01-18 13:01:08 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][150/312]	eta 0:01:39 lr 0.002298	time 0.5723 (0.6120)	model_time 0.5721 (0.6002)	loss 4.6308 (4.7051)	grad_norm 4.8588 (2.5060/0.8884)	mem 24308MB
[2025-01-18 13:01:14 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][160/312]	eta 0:01:32 lr 0.002304	time 0.5858 (0.6107)	model_time 0.5853 (0.5997)	loss 3.7004 (4.7077)	grad_norm 3.6224 (2.5175/0.8788)	mem 24308MB
[2025-01-18 13:01:20 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][170/312]	eta 0:01:26 lr 0.002311	time 0.5821 (0.6095)	model_time 0.5817 (0.5990)	loss 3.8624 (4.6930)	grad_norm 1.4299 (2.5112/0.8899)	mem 24308MB
[2025-01-18 13:01:26 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][180/312]	eta 0:01:20 lr 0.002317	time 0.5965 (0.6079)	model_time 0.5960 (0.5981)	loss 4.5868 (4.7080)	grad_norm 3.1014 (2.4900/0.8865)	mem 24308MB
[2025-01-18 13:01:32 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][190/312]	eta 0:01:14 lr 0.002323	time 0.5829 (0.6069)	model_time 0.5827 (0.5975)	loss 4.1104 (4.7114)	grad_norm 1.6163 (2.5070/0.8870)	mem 24308MB
[2025-01-18 13:01:37 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][200/312]	eta 0:01:07 lr 0.002330	time 0.5880 (0.6057)	model_time 0.5876 (0.5968)	loss 4.4585 (4.7247)	grad_norm 1.7396 (2.4999/0.8730)	mem 24308MB
[2025-01-18 13:01:43 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][210/312]	eta 0:01:01 lr 0.002336	time 0.5941 (0.6052)	model_time 0.5939 (0.5967)	loss 5.3540 (4.7240)	grad_norm 3.1723 (2.5131/0.8759)	mem 24308MB
[2025-01-18 13:01:49 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][220/312]	eta 0:00:55 lr 0.002343	time 0.6286 (0.6044)	model_time 0.6285 (0.5962)	loss 4.9480 (4.7272)	grad_norm 1.5802 (2.4882/0.8675)	mem 24308MB
[2025-01-18 13:01:55 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][230/312]	eta 0:00:49 lr 0.002349	time 0.5867 (0.6044)	model_time 0.5862 (0.5966)	loss 4.8412 (4.7241)	grad_norm 2.3297 (2.4801/0.8591)	mem 24308MB
[2025-01-18 13:02:02 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][240/312]	eta 0:00:43 lr 0.002355	time 0.7109 (0.6058)	model_time 0.7107 (0.5983)	loss 4.4501 (4.7246)	grad_norm 3.1707 (2.4642/0.8516)	mem 24308MB
[2025-01-18 13:02:08 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][250/312]	eta 0:00:37 lr 0.002362	time 0.6385 (0.6074)	model_time 0.6381 (0.6002)	loss 4.8012 (4.7272)	grad_norm 2.0376 (2.4565/0.8401)	mem 24308MB
[2025-01-18 13:02:14 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][260/312]	eta 0:00:31 lr 0.002368	time 0.5988 (0.6074)	model_time 0.5986 (0.6004)	loss 4.1836 (4.7252)	grad_norm 2.0746 (2.4779/0.8610)	mem 24308MB
[2025-01-18 13:02:20 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][270/312]	eta 0:00:25 lr 0.002375	time 0.5707 (0.6066)	model_time 0.5702 (0.5999)	loss 4.7209 (4.7195)	grad_norm 2.0115 (2.4598/0.8555)	mem 24308MB
[2025-01-18 13:02:26 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][280/312]	eta 0:00:19 lr 0.002381	time 0.6115 (0.6059)	model_time 0.6113 (0.5994)	loss 5.2442 (4.7139)	grad_norm 2.8430 (2.4533/0.8446)	mem 24308MB
[2025-01-18 13:02:32 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][290/312]	eta 0:00:13 lr 0.002388	time 0.5793 (0.6050)	model_time 0.5791 (0.5988)	loss 4.9626 (4.7172)	grad_norm 2.8932 (2.4822/0.8770)	mem 24308MB
[2025-01-18 13:02:38 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][300/312]	eta 0:00:07 lr 0.002394	time 0.5666 (0.6042)	model_time 0.5665 (0.5981)	loss 4.3434 (4.7178)	grad_norm 1.9244 (2.4831/0.8829)	mem 24308MB
[2025-01-18 13:02:43 internimage_s_1k_224] (main.py 510): INFO Train: [11/300][310/312]	eta 0:00:01 lr 0.002400	time 0.5671 (0.6032)	model_time 0.5671 (0.5973)	loss 4.8713 (4.7193)	grad_norm 2.8396 (2.4653/0.8749)	mem 24308MB
[2025-01-18 13:02:44 internimage_s_1k_224] (main.py 519): INFO EPOCH 11 training takes 0:03:08
[2025-01-18 13:02:44 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_11.pth saving......
[2025-01-18 13:02:46 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_11.pth saved !!!
[2025-01-18 13:02:53 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.990 (6.990)	Loss 1.7746 (1.7746)	Acc@1 60.767 (60.767)	Acc@5 85.303 (85.303)	Mem 24308MB
[2025-01-18 13:02:56 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.936)	Loss 2.5022 (2.1107)	Acc@1 46.997 (54.614)	Acc@5 72.827 (79.887)	Mem 24308MB
[2025-01-18 13:02:56 internimage_s_1k_224] (main.py 575): INFO [Epoch:11] * Acc@1 55.082 Acc@5 80.182
[2025-01-18 13:02:56 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 55.1%
[2025-01-18 13:02:56 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 13:02:58 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 13:02:58 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 55.08%
[2025-01-18 13:03:05 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.148 (7.148)	Loss 6.8616 (6.8616)	Acc@1 0.073 (0.073)	Acc@5 3.394 (3.394)	Mem 24308MB
[2025-01-18 13:03:09 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.137 (0.954)	Loss 6.7685 (6.7919)	Acc@1 0.269 (0.155)	Acc@5 1.636 (1.682)	Mem 24308MB
[2025-01-18 13:03:09 internimage_s_1k_224] (main.py 575): INFO [Epoch:11] * Acc@1 0.450 Acc@5 2.155
[2025-01-18 13:03:09 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.4%
[2025-01-18 13:03:09 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 0.47%
[2025-01-18 13:03:12 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][0/312]	eta 0:15:35 lr 0.002402	time 2.9986 (2.9986)	model_time 1.5394 (1.5394)	loss 4.8788 (4.8788)	grad_norm 2.1640 (2.1640/0.0000)	mem 24308MB
[2025-01-18 13:03:18 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][10/312]	eta 0:04:05 lr 0.002408	time 0.5989 (0.8119)	model_time 0.5987 (0.6790)	loss 4.9992 (4.4212)	grad_norm 2.3457 (2.1268/0.4327)	mem 24308MB
[2025-01-18 13:03:24 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][20/312]	eta 0:03:24 lr 0.002414	time 0.5726 (0.7011)	model_time 0.5724 (0.6313)	loss 3.7874 (4.5381)	grad_norm 1.8540 (2.4846/0.9136)	mem 24308MB
[2025-01-18 13:03:29 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][30/312]	eta 0:03:07 lr 0.002421	time 0.5822 (0.6641)	model_time 0.5820 (0.6167)	loss 5.0006 (4.5830)	grad_norm 3.0894 (2.3554/0.8369)	mem 24308MB
[2025-01-18 13:03:36 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][40/312]	eta 0:02:56 lr 0.002427	time 0.5814 (0.6504)	model_time 0.5809 (0.6145)	loss 4.9987 (4.6033)	grad_norm 3.2486 (2.4761/0.9487)	mem 24308MB
[2025-01-18 13:03:42 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][50/312]	eta 0:02:49 lr 0.002434	time 0.7212 (0.6469)	model_time 0.7211 (0.6179)	loss 4.4872 (4.6287)	grad_norm 2.1318 (2.5887/1.0858)	mem 24308MB
[2025-01-18 13:03:48 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][60/312]	eta 0:02:42 lr 0.002440	time 0.6529 (0.6461)	model_time 0.6526 (0.6218)	loss 3.4832 (4.6293)	grad_norm 1.9470 (2.5559/1.0311)	mem 24308MB
[2025-01-18 13:03:54 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][70/312]	eta 0:02:34 lr 0.002446	time 0.5713 (0.6387)	model_time 0.5709 (0.6178)	loss 3.6122 (4.5892)	grad_norm 4.0490 (2.5610/0.9995)	mem 24308MB
[2025-01-18 13:04:00 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][80/312]	eta 0:02:26 lr 0.002453	time 0.5714 (0.6325)	model_time 0.5712 (0.6141)	loss 5.2169 (4.6225)	grad_norm 1.8992 (2.4976/0.9550)	mem 24308MB
[2025-01-18 13:04:06 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][90/312]	eta 0:02:19 lr 0.002459	time 0.5876 (0.6272)	model_time 0.5871 (0.6108)	loss 4.6952 (4.6283)	grad_norm 1.7282 (2.4385/0.9276)	mem 24308MB
[2025-01-18 13:04:12 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][100/312]	eta 0:02:12 lr 0.002466	time 0.5753 (0.6230)	model_time 0.5751 (0.6082)	loss 5.2922 (4.6074)	grad_norm 2.0710 (2.4142/0.9146)	mem 24308MB
[2025-01-18 13:04:18 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][110/312]	eta 0:02:05 lr 0.002472	time 0.5879 (0.6194)	model_time 0.5878 (0.6059)	loss 3.3991 (4.6172)	grad_norm 3.3407 (2.4557/0.9423)	mem 24308MB
[2025-01-18 13:04:24 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][120/312]	eta 0:01:58 lr 0.002478	time 0.6030 (0.6174)	model_time 0.6025 (0.6050)	loss 4.1318 (4.6073)	grad_norm 1.6000 (2.4539/0.9359)	mem 24308MB
[2025-01-18 13:04:29 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][130/312]	eta 0:01:51 lr 0.002485	time 0.5767 (0.6147)	model_time 0.5766 (0.6032)	loss 5.3584 (4.6113)	grad_norm 1.9182 (2.4098/0.9191)	mem 24308MB
[2025-01-18 13:04:35 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][140/312]	eta 0:01:45 lr 0.002491	time 0.5740 (0.6126)	model_time 0.5734 (0.6019)	loss 5.3074 (4.6019)	grad_norm 3.5361 (2.4332/0.9190)	mem 24308MB
[2025-01-18 13:04:41 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][150/312]	eta 0:01:38 lr 0.002498	time 0.5985 (0.6105)	model_time 0.5983 (0.6005)	loss 4.6766 (4.6038)	grad_norm 3.3907 (2.4337/0.9105)	mem 24308MB
[2025-01-18 13:04:47 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][160/312]	eta 0:01:32 lr 0.002504	time 0.6531 (0.6101)	model_time 0.6526 (0.6006)	loss 4.0514 (4.5949)	grad_norm 1.6217 (2.4004/0.8971)	mem 24308MB
[2025-01-18 13:04:53 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][170/312]	eta 0:01:26 lr 0.002510	time 0.5908 (0.6104)	model_time 0.5902 (0.6015)	loss 5.4598 (4.6031)	grad_norm 3.0113 (2.3892/0.8819)	mem 24308MB
[2025-01-18 13:05:00 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][180/312]	eta 0:01:20 lr 0.002517	time 0.5751 (0.6123)	model_time 0.5748 (0.6039)	loss 4.0390 (4.6035)	grad_norm 1.5405 (2.4044/0.8914)	mem 24308MB
[2025-01-18 13:05:06 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][190/312]	eta 0:01:14 lr 0.002523	time 0.5966 (0.6117)	model_time 0.5961 (0.6036)	loss 4.2468 (4.5998)	grad_norm 2.5301 (2.3853/0.8734)	mem 24308MB
[2025-01-18 13:05:12 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][200/312]	eta 0:01:08 lr 0.002530	time 0.5759 (0.6105)	model_time 0.5757 (0.6028)	loss 4.8932 (4.5922)	grad_norm 3.1903 (2.4075/0.8747)	mem 24308MB
[2025-01-18 13:05:17 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][210/312]	eta 0:01:02 lr 0.002536	time 0.5758 (0.6092)	model_time 0.5757 (0.6019)	loss 4.8371 (4.5910)	grad_norm 2.6121 (2.3947/0.8610)	mem 24308MB
[2025-01-18 13:05:23 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][220/312]	eta 0:00:55 lr 0.002542	time 0.5776 (0.6081)	model_time 0.5774 (0.6011)	loss 5.0365 (4.5977)	grad_norm 2.4336 (2.3726/0.8531)	mem 24308MB
[2025-01-18 13:05:29 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][230/312]	eta 0:00:49 lr 0.002549	time 0.5773 (0.6073)	model_time 0.5771 (0.6006)	loss 4.2519 (4.6014)	grad_norm 2.8190 (2.3834/0.8639)	mem 24308MB
[2025-01-18 13:05:35 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][240/312]	eta 0:00:43 lr 0.002555	time 0.6019 (0.6065)	model_time 0.6014 (0.6001)	loss 3.5492 (4.6025)	grad_norm 1.8115 (2.3668/0.8524)	mem 24308MB
[2025-01-18 13:05:41 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][250/312]	eta 0:00:37 lr 0.002562	time 0.5845 (0.6055)	model_time 0.5843 (0.5993)	loss 3.5362 (4.6060)	grad_norm 1.8127 (2.3422/0.8450)	mem 24308MB
[2025-01-18 13:05:47 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][260/312]	eta 0:00:31 lr 0.002568	time 0.5765 (0.6051)	model_time 0.5763 (0.5991)	loss 4.6043 (4.6036)	grad_norm 2.0331 (2.3271/0.8349)	mem 24308MB
[2025-01-18 13:05:53 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][270/312]	eta 0:00:25 lr 0.002575	time 0.5668 (0.6041)	model_time 0.5666 (0.5983)	loss 4.0202 (4.5937)	grad_norm 2.1317 (2.3270/0.8231)	mem 24308MB
[2025-01-18 13:05:59 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][280/312]	eta 0:00:19 lr 0.002581	time 0.5926 (0.6040)	model_time 0.5920 (0.5983)	loss 5.4574 (4.6026)	grad_norm 2.1392 (2.3088/0.8159)	mem 24308MB
[2025-01-18 13:06:05 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][290/312]	eta 0:00:13 lr 0.002587	time 0.5767 (0.6043)	model_time 0.5765 (0.5989)	loss 4.4892 (4.5932)	grad_norm 1.9835 (2.3057/0.8181)	mem 24308MB
[2025-01-18 13:06:11 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][300/312]	eta 0:00:07 lr 0.002594	time 0.7250 (0.6064)	model_time 0.7249 (0.6011)	loss 4.5822 (4.6047)	grad_norm 1.7128 (2.2966/0.8116)	mem 24308MB
[2025-01-18 13:06:17 internimage_s_1k_224] (main.py 510): INFO Train: [12/300][310/312]	eta 0:00:01 lr 0.002600	time 0.5687 (0.6060)	model_time 0.5686 (0.6009)	loss 5.5053 (4.6137)	grad_norm 3.8676 (2.3312/0.8734)	mem 24308MB
[2025-01-18 13:06:18 internimage_s_1k_224] (main.py 519): INFO EPOCH 12 training takes 0:03:09
[2025-01-18 13:06:18 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_12.pth saving......
[2025-01-18 13:06:20 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_12.pth saved !!!
[2025-01-18 13:06:27 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.209 (7.209)	Loss 1.7276 (1.7276)	Acc@1 63.794 (63.794)	Acc@5 85.889 (85.889)	Mem 24308MB
[2025-01-18 13:06:30 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.953)	Loss 2.4491 (2.0598)	Acc@1 48.999 (56.805)	Acc@5 74.634 (81.168)	Mem 24308MB
[2025-01-18 13:06:30 internimage_s_1k_224] (main.py 575): INFO [Epoch:12] * Acc@1 57.214 Acc@5 81.428
[2025-01-18 13:06:30 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 57.2%
[2025-01-18 13:06:30 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 13:06:32 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 13:06:32 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 57.21%
[2025-01-18 13:06:40 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.296 (7.296)	Loss 6.8412 (6.8412)	Acc@1 0.122 (0.122)	Acc@5 3.613 (3.613)	Mem 24308MB
[2025-01-18 13:06:43 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.980)	Loss 6.7569 (6.7765)	Acc@1 0.220 (0.162)	Acc@5 1.929 (1.760)	Mem 24308MB
[2025-01-18 13:06:43 internimage_s_1k_224] (main.py 575): INFO [Epoch:12] * Acc@1 0.456 Acc@5 2.243
[2025-01-18 13:06:43 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.5%
[2025-01-18 13:06:43 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 0.47%
[2025-01-18 13:06:46 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][0/312]	eta 0:14:29 lr 0.002601	time 2.7869 (2.7869)	model_time 1.3256 (1.3256)	loss 4.9208 (4.9208)	grad_norm 2.6795 (2.6795/0.0000)	mem 24308MB
[2025-01-18 13:06:52 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][10/312]	eta 0:04:04 lr 0.002608	time 0.5886 (0.8088)	model_time 0.5884 (0.6756)	loss 3.6427 (4.2417)	grad_norm 2.2129 (2.3430/0.3524)	mem 24308MB
[2025-01-18 13:06:58 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][20/312]	eta 0:03:24 lr 0.002614	time 0.5701 (0.6996)	model_time 0.5699 (0.6297)	loss 5.5005 (4.3658)	grad_norm 1.8352 (2.4862/0.8690)	mem 24308MB
[2025-01-18 13:07:04 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][30/312]	eta 0:03:06 lr 0.002621	time 0.5815 (0.6625)	model_time 0.5810 (0.6150)	loss 4.3130 (4.2906)	grad_norm 2.7136 (2.4927/0.8495)	mem 24308MB
[2025-01-18 13:07:10 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][40/312]	eta 0:02:55 lr 0.002627	time 0.5866 (0.6446)	model_time 0.5864 (0.6086)	loss 3.9652 (4.3648)	grad_norm 1.7660 (2.3381/0.8156)	mem 24308MB
[2025-01-18 13:07:15 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][50/312]	eta 0:02:45 lr 0.002633	time 0.5791 (0.6328)	model_time 0.5789 (0.6038)	loss 5.0570 (4.3348)	grad_norm 1.5687 (2.3450/0.7736)	mem 24308MB
[2025-01-18 13:07:21 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][60/312]	eta 0:02:37 lr 0.002640	time 0.6002 (0.6246)	model_time 0.6000 (0.6003)	loss 4.4618 (4.3791)	grad_norm 2.0209 (2.3487/0.7704)	mem 24308MB
[2025-01-18 13:07:27 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][70/312]	eta 0:02:29 lr 0.002646	time 0.5738 (0.6191)	model_time 0.5736 (0.5981)	loss 5.4806 (4.4091)	grad_norm 2.5296 (2.3029/0.7367)	mem 24308MB
[2025-01-18 13:07:33 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][80/312]	eta 0:02:22 lr 0.002653	time 0.6524 (0.6158)	model_time 0.6522 (0.5974)	loss 4.5413 (4.4034)	grad_norm 2.5487 (2.3111/0.7385)	mem 24308MB
[2025-01-18 13:07:39 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][90/312]	eta 0:02:16 lr 0.002659	time 0.6549 (0.6131)	model_time 0.6547 (0.5967)	loss 4.4709 (4.4073)	grad_norm 1.4702 (2.3218/0.7604)	mem 24308MB
[2025-01-18 13:07:45 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][100/312]	eta 0:02:10 lr 0.002665	time 0.5846 (0.6144)	model_time 0.5841 (0.5996)	loss 4.9473 (4.4481)	grad_norm 2.0208 (2.3762/0.8656)	mem 24308MB
[2025-01-18 13:07:52 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][110/312]	eta 0:02:04 lr 0.002672	time 0.5970 (0.6161)	model_time 0.5969 (0.6025)	loss 4.8734 (4.4605)	grad_norm 2.3650 (2.3606/0.8499)	mem 24308MB
[2025-01-18 13:07:58 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][120/312]	eta 0:01:57 lr 0.002678	time 0.6019 (0.6146)	model_time 0.6017 (0.6021)	loss 5.1167 (4.4850)	grad_norm 2.6030 (2.3467/0.8552)	mem 24308MB
[2025-01-18 13:08:04 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][130/312]	eta 0:01:51 lr 0.002685	time 0.5692 (0.6132)	model_time 0.5690 (0.6017)	loss 3.9155 (4.4851)	grad_norm 1.8263 (2.3518/0.8465)	mem 24308MB
[2025-01-18 13:08:09 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][140/312]	eta 0:01:45 lr 0.002691	time 0.6043 (0.6118)	model_time 0.6037 (0.6011)	loss 5.6913 (4.4906)	grad_norm 2.9320 (2.3237/0.8349)	mem 24308MB
[2025-01-18 13:08:15 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][150/312]	eta 0:01:38 lr 0.002697	time 0.5718 (0.6100)	model_time 0.5716 (0.5999)	loss 4.7510 (4.4918)	grad_norm 2.5308 (2.3228/0.8120)	mem 24308MB
[2025-01-18 13:08:21 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][160/312]	eta 0:01:32 lr 0.002704	time 0.5854 (0.6082)	model_time 0.5853 (0.5988)	loss 4.9457 (4.5020)	grad_norm 2.2756 (2.3553/0.8469)	mem 24308MB
[2025-01-18 13:08:27 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][170/312]	eta 0:01:26 lr 0.002710	time 0.5945 (0.6066)	model_time 0.5940 (0.5977)	loss 4.6522 (4.5012)	grad_norm 1.5601 (2.3332/0.8325)	mem 24308MB
[2025-01-18 13:08:33 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][180/312]	eta 0:01:19 lr 0.002717	time 0.5714 (0.6056)	model_time 0.5709 (0.5972)	loss 4.4861 (4.4903)	grad_norm 1.5478 (2.3339/0.8299)	mem 24308MB
[2025-01-18 13:08:39 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][190/312]	eta 0:01:13 lr 0.002723	time 0.5822 (0.6045)	model_time 0.5765 (0.5964)	loss 5.3300 (4.4969)	grad_norm 1.8918 (2.3600/0.8564)	mem 24308MB
[2025-01-18 13:08:45 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][200/312]	eta 0:01:07 lr 0.002729	time 0.6321 (0.6038)	model_time 0.6319 (0.5961)	loss 4.8863 (4.5091)	grad_norm 1.8155 (2.3407/0.8437)	mem 24308MB
[2025-01-18 13:08:51 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][210/312]	eta 0:01:01 lr 0.002736	time 0.6447 (0.6033)	model_time 0.6445 (0.5960)	loss 3.9610 (4.4969)	grad_norm 1.1925 (2.3006/0.8439)	mem 24308MB
[2025-01-18 13:08:57 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][220/312]	eta 0:00:55 lr 0.002742	time 0.5730 (0.6043)	model_time 0.5729 (0.5973)	loss 3.5173 (4.4877)	grad_norm 6.9369 (2.3356/0.8983)	mem 24308MB
[2025-01-18 13:09:03 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][230/312]	eta 0:00:49 lr 0.002749	time 0.6534 (0.6060)	model_time 0.6533 (0.5992)	loss 5.3604 (4.4924)	grad_norm 2.5307 (2.3539/0.9283)	mem 24308MB
[2025-01-18 13:09:09 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][240/312]	eta 0:00:43 lr 0.002755	time 0.5805 (0.6059)	model_time 0.5802 (0.5994)	loss 5.2099 (4.4955)	grad_norm 2.2024 (2.3301/0.9180)	mem 24308MB
[2025-01-18 13:09:15 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][250/312]	eta 0:00:37 lr 0.002761	time 0.5735 (0.6057)	model_time 0.5733 (0.5995)	loss 4.6567 (4.4852)	grad_norm 1.9854 (2.3329/0.9259)	mem 24308MB
[2025-01-18 13:09:21 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][260/312]	eta 0:00:31 lr 0.002768	time 0.5791 (0.6048)	model_time 0.5789 (0.5989)	loss 4.7426 (4.4949)	grad_norm 1.0301 (2.3254/0.9348)	mem 24308MB
[2025-01-18 13:09:27 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][270/312]	eta 0:00:25 lr 0.002774	time 0.5874 (0.6040)	model_time 0.5872 (0.5982)	loss 3.6118 (4.4974)	grad_norm 1.6038 (2.3195/0.9302)	mem 24308MB
[2025-01-18 13:09:33 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][280/312]	eta 0:00:19 lr 0.002781	time 0.5654 (0.6033)	model_time 0.5652 (0.5977)	loss 3.2284 (4.4918)	grad_norm 1.7792 (2.3083/0.9225)	mem 24308MB
[2025-01-18 13:09:39 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][290/312]	eta 0:00:13 lr 0.002787	time 0.6262 (0.6028)	model_time 0.6260 (0.5974)	loss 4.9421 (4.4873)	grad_norm 3.0645 (2.3269/0.9310)	mem 24308MB
[2025-01-18 13:09:44 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][300/312]	eta 0:00:07 lr 0.002794	time 0.5696 (0.6020)	model_time 0.5695 (0.5967)	loss 4.6120 (4.4887)	grad_norm 3.1196 (2.3196/0.9272)	mem 24308MB
[2025-01-18 13:09:50 internimage_s_1k_224] (main.py 510): INFO Train: [13/300][310/312]	eta 0:00:01 lr 0.002800	time 0.5619 (0.6008)	model_time 0.5618 (0.5957)	loss 4.8099 (4.4848)	grad_norm 2.8663 (2.3169/0.9300)	mem 24308MB
[2025-01-18 13:09:51 internimage_s_1k_224] (main.py 519): INFO EPOCH 13 training takes 0:03:07
[2025-01-18 13:09:51 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_13.pth saving......
[2025-01-18 13:09:52 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_13.pth saved !!!
[2025-01-18 13:10:00 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.219 (7.219)	Loss 1.7044 (1.7044)	Acc@1 63.354 (63.354)	Acc@5 86.328 (86.328)	Mem 24308MB
[2025-01-18 13:10:03 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.958)	Loss 2.3263 (1.9925)	Acc@1 51.294 (57.686)	Acc@5 76.514 (82.329)	Mem 24308MB
[2025-01-18 13:10:03 internimage_s_1k_224] (main.py 575): INFO [Epoch:13] * Acc@1 58.051 Acc@5 82.518
[2025-01-18 13:10:03 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 58.1%
[2025-01-18 13:10:03 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 13:10:05 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 13:10:05 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 58.05%
[2025-01-18 13:10:12 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.033 (7.033)	Loss 6.8191 (6.8191)	Acc@1 0.269 (0.269)	Acc@5 3.735 (3.735)	Mem 24308MB
[2025-01-18 13:10:15 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.930)	Loss 6.7488 (6.7598)	Acc@1 0.220 (0.200)	Acc@5 2.344 (1.855)	Mem 24308MB
[2025-01-18 13:10:16 internimage_s_1k_224] (main.py 575): INFO [Epoch:13] * Acc@1 0.504 Acc@5 2.363
[2025-01-18 13:10:16 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.5%
[2025-01-18 13:10:16 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 13:10:18 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 13:10:18 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 0.50%
[2025-01-18 13:10:20 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][0/312]	eta 0:12:00 lr 0.002801	time 2.3100 (2.3100)	model_time 0.5994 (0.5994)	loss 4.6597 (4.6597)	grad_norm 3.1280 (3.1280/0.0000)	mem 24308MB
[2025-01-18 13:10:26 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][10/312]	eta 0:03:44 lr 0.002808	time 0.6039 (0.7440)	model_time 0.6037 (0.5882)	loss 3.3582 (4.4101)	grad_norm 2.4146 (2.3847/0.6178)	mem 24308MB
[2025-01-18 13:10:32 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][20/312]	eta 0:03:16 lr 0.002814	time 0.5965 (0.6729)	model_time 0.5963 (0.5906)	loss 4.7607 (4.4381)	grad_norm 2.5413 (2.1313/0.6127)	mem 24308MB
[2025-01-18 13:10:38 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][30/312]	eta 0:03:06 lr 0.002820	time 0.6520 (0.6609)	model_time 0.6518 (0.6050)	loss 4.9354 (4.5330)	grad_norm 1.3385 (2.0205/0.5532)	mem 24308MB
[2025-01-18 13:10:45 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][40/312]	eta 0:02:59 lr 0.002827	time 0.6561 (0.6592)	model_time 0.6556 (0.6169)	loss 4.8846 (4.5566)	grad_norm 1.5911 (2.0755/0.5397)	mem 24308MB
[2025-01-18 13:10:51 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][50/312]	eta 0:02:49 lr 0.002833	time 0.6484 (0.6486)	model_time 0.6482 (0.6145)	loss 4.5956 (4.5210)	grad_norm 4.2668 (2.0976/0.5961)	mem 24308MB
[2025-01-18 13:10:57 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][60/312]	eta 0:02:41 lr 0.002840	time 0.5851 (0.6408)	model_time 0.5850 (0.6122)	loss 5.0189 (4.5134)	grad_norm 2.6577 (2.1559/0.6267)	mem 24308MB
[2025-01-18 13:11:03 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][70/312]	eta 0:02:33 lr 0.002846	time 0.5818 (0.6343)	model_time 0.5816 (0.6097)	loss 5.0137 (4.5380)	grad_norm 1.6718 (2.1425/0.6339)	mem 24308MB
[2025-01-18 13:11:09 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][80/312]	eta 0:02:25 lr 0.002852	time 0.5940 (0.6283)	model_time 0.5935 (0.6067)	loss 4.8314 (4.5516)	grad_norm 1.3072 (2.1200/0.6219)	mem 24308MB
[2025-01-18 13:11:14 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][90/312]	eta 0:02:18 lr 0.002859	time 0.5960 (0.6233)	model_time 0.5959 (0.6041)	loss 4.1915 (4.5153)	grad_norm 3.3855 (2.2220/0.8810)	mem 24308MB
[2025-01-18 13:11:20 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][100/312]	eta 0:02:11 lr 0.002865	time 0.6238 (0.6194)	model_time 0.6236 (0.6020)	loss 4.1372 (4.5345)	grad_norm 1.7281 (2.1964/0.8688)	mem 24308MB
[2025-01-18 13:11:26 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][110/312]	eta 0:02:04 lr 0.002872	time 0.5830 (0.6158)	model_time 0.5828 (0.6000)	loss 4.1091 (4.5348)	grad_norm 2.1601 (2.2161/0.9242)	mem 24308MB
[2025-01-18 13:11:32 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][120/312]	eta 0:01:57 lr 0.002878	time 0.5823 (0.6135)	model_time 0.5818 (0.5989)	loss 3.7780 (4.5229)	grad_norm 1.4000 (2.2277/0.9102)	mem 24308MB
[2025-01-18 13:11:38 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][130/312]	eta 0:01:51 lr 0.002884	time 0.5636 (0.6111)	model_time 0.5635 (0.5976)	loss 4.1259 (4.5248)	grad_norm 1.7717 (2.2197/0.8798)	mem 24308MB
[2025-01-18 13:11:44 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][140/312]	eta 0:01:44 lr 0.002891	time 0.5833 (0.6097)	model_time 0.5831 (0.5971)	loss 5.0094 (4.5308)	grad_norm 1.8356 (2.2394/0.8626)	mem 24308MB
[2025-01-18 13:11:50 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][150/312]	eta 0:01:39 lr 0.002897	time 0.6603 (0.6113)	model_time 0.6601 (0.5995)	loss 5.2387 (4.5275)	grad_norm 1.5804 (2.2266/0.8479)	mem 24308MB
[2025-01-18 13:11:56 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][160/312]	eta 0:01:33 lr 0.002904	time 0.6767 (0.6128)	model_time 0.6766 (0.6017)	loss 4.8034 (4.5300)	grad_norm 2.1476 (2.2601/0.8702)	mem 24308MB
[2025-01-18 13:12:02 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][170/312]	eta 0:01:27 lr 0.002910	time 0.5843 (0.6128)	model_time 0.5841 (0.6024)	loss 3.3782 (4.5096)	grad_norm 3.0220 (2.2523/0.8529)	mem 24308MB
[2025-01-18 13:12:09 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][180/312]	eta 0:01:20 lr 0.002916	time 0.5768 (0.6126)	model_time 0.5766 (0.6027)	loss 5.3677 (4.5165)	grad_norm 1.7812 (2.2669/0.8519)	mem 24308MB
[2025-01-18 13:12:15 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][190/312]	eta 0:01:14 lr 0.002923	time 0.5856 (0.6117)	model_time 0.5854 (0.6023)	loss 4.4209 (4.5256)	grad_norm 2.2409 (2.2538/0.8453)	mem 24308MB
[2025-01-18 13:12:20 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][200/312]	eta 0:01:08 lr 0.002929	time 0.5838 (0.6102)	model_time 0.5836 (0.6013)	loss 4.7776 (4.5268)	grad_norm 1.9012 (2.2495/0.8383)	mem 24308MB
[2025-01-18 13:12:26 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][210/312]	eta 0:01:02 lr 0.002936	time 0.5938 (0.6091)	model_time 0.5936 (0.6006)	loss 4.7675 (4.5235)	grad_norm 1.8585 (2.2406/0.8323)	mem 24308MB
[2025-01-18 13:12:32 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][220/312]	eta 0:00:55 lr 0.002942	time 0.5938 (0.6080)	model_time 0.5936 (0.5998)	loss 4.1009 (4.5319)	grad_norm 3.6332 (2.2415/0.8297)	mem 24308MB
[2025-01-18 13:12:38 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][230/312]	eta 0:00:49 lr 0.002948	time 0.5823 (0.6069)	model_time 0.5821 (0.5991)	loss 4.5234 (4.5319)	grad_norm 2.1464 (2.2405/0.8222)	mem 24308MB
[2025-01-18 13:12:44 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][240/312]	eta 0:00:43 lr 0.002955	time 0.5777 (0.6059)	model_time 0.5775 (0.5984)	loss 4.1007 (4.5185)	grad_norm 1.5477 (2.2441/0.8149)	mem 24308MB
[2025-01-18 13:12:50 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][250/312]	eta 0:00:37 lr 0.002961	time 0.5748 (0.6051)	model_time 0.5747 (0.5979)	loss 4.4826 (4.5296)	grad_norm 1.4173 (2.2654/0.8413)	mem 24308MB
[2025-01-18 13:12:56 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][260/312]	eta 0:00:31 lr 0.002968	time 0.5913 (0.6047)	model_time 0.5911 (0.5978)	loss 4.9824 (4.5226)	grad_norm 3.2408 (2.2747/0.8407)	mem 24308MB
[2025-01-18 13:13:02 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][270/312]	eta 0:00:25 lr 0.002974	time 0.6767 (0.6055)	model_time 0.6765 (0.5988)	loss 4.1734 (4.5261)	grad_norm 3.2018 (2.2900/0.8354)	mem 24308MB
[2025-01-18 13:13:08 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][280/312]	eta 0:00:19 lr 0.002981	time 0.6583 (0.6070)	model_time 0.6578 (0.6005)	loss 3.7496 (4.5251)	grad_norm 1.9630 (2.2837/0.8249)	mem 24308MB
[2025-01-18 13:13:15 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][290/312]	eta 0:00:13 lr 0.002987	time 0.5795 (0.6087)	model_time 0.5793 (0.6024)	loss 4.8164 (4.5327)	grad_norm 3.4580 (2.2710/0.8246)	mem 24308MB
[2025-01-18 13:13:21 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][300/312]	eta 0:00:07 lr 0.002993	time 0.5668 (0.6084)	model_time 0.5667 (0.6023)	loss 4.5041 (4.5372)	grad_norm 2.5633 (2.2611/0.8171)	mem 24308MB
[2025-01-18 13:13:27 internimage_s_1k_224] (main.py 510): INFO Train: [14/300][310/312]	eta 0:00:01 lr 0.003000	time 0.5709 (0.6075)	model_time 0.5708 (0.6016)	loss 5.4763 (4.5347)	grad_norm 2.1253 (2.2464/0.8173)	mem 24308MB
[2025-01-18 13:13:27 internimage_s_1k_224] (main.py 519): INFO EPOCH 14 training takes 0:03:09
[2025-01-18 13:13:27 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_14.pth saving......
[2025-01-18 13:13:29 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_14.pth saved !!!
[2025-01-18 13:13:36 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.103 (7.103)	Loss 1.5483 (1.5483)	Acc@1 65.527 (65.527)	Acc@5 88.257 (88.257)	Mem 24308MB
[2025-01-18 13:13:39 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.946)	Loss 2.3123 (1.8931)	Acc@1 51.294 (59.155)	Acc@5 75.952 (83.176)	Mem 24308MB
[2025-01-18 13:13:40 internimage_s_1k_224] (main.py 575): INFO [Epoch:14] * Acc@1 59.479 Acc@5 83.315
[2025-01-18 13:13:40 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 59.5%
[2025-01-18 13:13:40 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 13:13:41 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 13:13:41 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 59.48%
[2025-01-18 13:13:49 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.151 (7.151)	Loss 6.7882 (6.7882)	Acc@1 0.366 (0.366)	Acc@5 3.931 (3.931)	Mem 24308MB
[2025-01-18 13:13:52 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.954)	Loss 6.7454 (6.7418)	Acc@1 0.293 (0.269)	Acc@5 2.612 (1.995)	Mem 24308MB
[2025-01-18 13:13:52 internimage_s_1k_224] (main.py 575): INFO [Epoch:14] * Acc@1 0.570 Acc@5 2.529
[2025-01-18 13:13:52 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.6%
[2025-01-18 13:13:52 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 13:13:54 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 13:13:54 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 0.57%
[2025-01-18 13:13:57 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][0/312]	eta 0:11:26 lr 0.003001	time 2.1988 (2.1988)	model_time 0.5996 (0.5996)	loss 4.5362 (4.5362)	grad_norm 2.4074 (2.4074/0.0000)	mem 24308MB
[2025-01-18 13:14:02 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][10/312]	eta 0:03:42 lr 0.003007	time 0.5860 (0.7354)	model_time 0.5859 (0.5896)	loss 4.8765 (4.5921)	grad_norm 1.6489 (1.6465/0.3842)	mem 24308MB
[2025-01-18 13:14:08 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][20/312]	eta 0:03:13 lr 0.003014	time 0.5893 (0.6631)	model_time 0.5891 (0.5866)	loss 5.4662 (4.7091)	grad_norm 2.7167 (2.0600/0.9422)	mem 24308MB
[2025-01-18 13:14:14 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][30/312]	eta 0:03:00 lr 0.003020	time 0.5825 (0.6394)	model_time 0.5823 (0.5874)	loss 4.4759 (4.5894)	grad_norm 2.5465 (2.2999/1.0156)	mem 24308MB
[2025-01-18 13:14:20 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][40/312]	eta 0:02:50 lr 0.003027	time 0.5636 (0.6267)	model_time 0.5634 (0.5874)	loss 4.7584 (4.5723)	grad_norm 1.4978 (2.2280/0.9248)	mem 24308MB
[2025-01-18 13:14:26 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][50/312]	eta 0:02:42 lr 0.003033	time 0.5849 (0.6196)	model_time 0.5847 (0.5879)	loss 3.5069 (4.5182)	grad_norm 2.4779 (2.1416/0.8655)	mem 24308MB
[2025-01-18 13:14:32 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][60/312]	eta 0:02:34 lr 0.003039	time 0.5797 (0.6139)	model_time 0.5792 (0.5873)	loss 4.5839 (4.5411)	grad_norm 1.2362 (2.1154/0.8350)	mem 24308MB
[2025-01-18 13:14:38 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][70/312]	eta 0:02:27 lr 0.003046	time 0.5753 (0.6105)	model_time 0.5752 (0.5876)	loss 4.2362 (4.5197)	grad_norm 2.9291 (2.2008/0.9092)	mem 24308MB
[2025-01-18 13:14:44 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][80/312]	eta 0:02:22 lr 0.003052	time 0.6089 (0.6126)	model_time 0.6087 (0.5925)	loss 3.8825 (4.4788)	grad_norm 1.4168 (2.2482/0.9480)	mem 24308MB
[2025-01-18 13:14:50 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][90/312]	eta 0:02:16 lr 0.003059	time 0.5819 (0.6144)	model_time 0.5817 (0.5965)	loss 4.8016 (4.4646)	grad_norm 3.1105 (2.2343/0.9099)	mem 24308MB
[2025-01-18 13:14:57 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][100/312]	eta 0:02:10 lr 0.003065	time 0.5823 (0.6164)	model_time 0.5821 (0.6002)	loss 4.7246 (4.4631)	grad_norm 1.9058 (2.2268/0.8756)	mem 24308MB
[2025-01-18 13:15:03 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][110/312]	eta 0:02:04 lr 0.003071	time 0.5867 (0.6160)	model_time 0.5862 (0.6012)	loss 5.1393 (4.4707)	grad_norm 1.3890 (2.1778/0.8552)	mem 24308MB
[2025-01-18 13:15:09 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][120/312]	eta 0:01:57 lr 0.003078	time 0.5732 (0.6142)	model_time 0.5728 (0.6006)	loss 4.9491 (4.4704)	grad_norm 1.4340 (2.1504/0.8320)	mem 24308MB
[2025-01-18 13:15:14 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][130/312]	eta 0:01:51 lr 0.003084	time 0.5744 (0.6113)	model_time 0.5742 (0.5987)	loss 4.1164 (4.4686)	grad_norm 1.9724 (2.1407/0.8168)	mem 24308MB
[2025-01-18 13:15:20 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][140/312]	eta 0:01:44 lr 0.003091	time 0.5813 (0.6094)	model_time 0.5811 (0.5977)	loss 3.6867 (4.4673)	grad_norm 2.7457 (2.1258/0.8060)	mem 24308MB
[2025-01-18 13:15:26 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][150/312]	eta 0:01:38 lr 0.003097	time 0.5754 (0.6077)	model_time 0.5751 (0.5967)	loss 4.5050 (4.4552)	grad_norm 2.1401 (2.1614/0.8516)	mem 24308MB
[2025-01-18 13:15:32 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][160/312]	eta 0:01:32 lr 0.003103	time 0.5763 (0.6069)	model_time 0.5760 (0.5966)	loss 4.3901 (4.4644)	grad_norm 2.0983 (2.1198/0.8446)	mem 24308MB
[2025-01-18 13:15:38 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][170/312]	eta 0:01:25 lr 0.003110	time 0.5686 (0.6055)	model_time 0.5684 (0.5957)	loss 4.6261 (4.4584)	grad_norm 1.3661 (2.1349/0.8364)	mem 24308MB
[2025-01-18 13:15:44 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][180/312]	eta 0:01:19 lr 0.003116	time 0.5943 (0.6044)	model_time 0.5941 (0.5952)	loss 4.2520 (4.4420)	grad_norm 1.1812 (2.1516/0.8452)	mem 24308MB
[2025-01-18 13:15:50 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][190/312]	eta 0:01:13 lr 0.003123	time 0.5815 (0.6036)	model_time 0.5811 (0.5949)	loss 3.4552 (4.4236)	grad_norm 1.6324 (2.1339/0.8387)	mem 24308MB
[2025-01-18 13:15:56 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][200/312]	eta 0:01:07 lr 0.003129	time 0.6646 (0.6041)	model_time 0.6641 (0.5957)	loss 5.3539 (4.4182)	grad_norm 1.8950 (2.1311/0.8308)	mem 24308MB
[2025-01-18 13:16:02 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][210/312]	eta 0:01:01 lr 0.003135	time 0.5842 (0.6052)	model_time 0.5840 (0.5973)	loss 4.6279 (4.4111)	grad_norm 1.0105 (2.1232/0.8325)	mem 24308MB
[2025-01-18 13:16:09 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][220/312]	eta 0:00:55 lr 0.003142	time 0.5748 (0.6074)	model_time 0.5747 (0.5998)	loss 3.2610 (4.3999)	grad_norm 1.3747 (2.1070/0.8243)	mem 24308MB
[2025-01-18 13:16:15 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][230/312]	eta 0:00:49 lr 0.003148	time 0.5897 (0.6075)	model_time 0.5895 (0.6002)	loss 3.3942 (4.4017)	grad_norm 2.2941 (2.0933/0.8116)	mem 24308MB
[2025-01-18 13:16:21 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][240/312]	eta 0:00:43 lr 0.003155	time 0.6955 (0.6069)	model_time 0.6953 (0.5999)	loss 4.1515 (4.4072)	grad_norm 2.6314 (2.1079/0.8130)	mem 24308MB
[2025-01-18 13:16:26 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][250/312]	eta 0:00:37 lr 0.003161	time 0.6182 (0.6061)	model_time 0.6181 (0.5994)	loss 4.7732 (4.4055)	grad_norm 3.1264 (2.0953/0.8059)	mem 24308MB
[2025-01-18 13:16:32 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][260/312]	eta 0:00:31 lr 0.003168	time 0.5808 (0.6052)	model_time 0.5803 (0.5988)	loss 5.3021 (4.4219)	grad_norm 1.6734 (2.1108/0.8240)	mem 24308MB
[2025-01-18 13:16:38 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][270/312]	eta 0:00:25 lr 0.003174	time 0.5794 (0.6045)	model_time 0.5793 (0.5982)	loss 4.4379 (4.4248)	grad_norm 1.3971 (2.0993/0.8188)	mem 24308MB
[2025-01-18 13:16:44 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][280/312]	eta 0:00:19 lr 0.003180	time 0.5797 (0.6036)	model_time 0.5792 (0.5976)	loss 3.8155 (4.4272)	grad_norm 1.1699 (2.0940/0.8123)	mem 24308MB
[2025-01-18 13:16:50 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][290/312]	eta 0:00:13 lr 0.003187	time 0.5716 (0.6030)	model_time 0.5714 (0.5971)	loss 5.0847 (4.4194)	grad_norm 3.1740 (2.1108/0.8212)	mem 24308MB
[2025-01-18 13:16:56 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][300/312]	eta 0:00:07 lr 0.003193	time 0.5651 (0.6022)	model_time 0.5650 (0.5965)	loss 4.8238 (4.4291)	grad_norm 1.4803 (2.1016/0.8131)	mem 24308MB
[2025-01-18 13:17:01 internimage_s_1k_224] (main.py 510): INFO Train: [15/300][310/312]	eta 0:00:01 lr 0.003200	time 0.5730 (0.6015)	model_time 0.5729 (0.5960)	loss 4.2208 (4.4299)	grad_norm 2.0801 (2.1191/0.8132)	mem 24308MB
[2025-01-18 13:17:02 internimage_s_1k_224] (main.py 519): INFO EPOCH 15 training takes 0:03:07
[2025-01-18 13:17:02 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_15.pth saving......
[2025-01-18 13:17:04 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_15.pth saved !!!
[2025-01-18 13:17:11 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.281 (7.281)	Loss 1.5000 (1.5000)	Acc@1 67.432 (67.432)	Acc@5 88.477 (88.477)	Mem 24308MB
[2025-01-18 13:17:14 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.940)	Loss 2.2152 (1.8402)	Acc@1 53.223 (60.676)	Acc@5 77.734 (84.160)	Mem 24308MB
[2025-01-18 13:17:14 internimage_s_1k_224] (main.py 575): INFO [Epoch:15] * Acc@1 60.913 Acc@5 84.273
[2025-01-18 13:17:14 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 60.9%
[2025-01-18 13:17:14 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 13:17:16 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 13:17:16 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 60.91%
[2025-01-18 13:17:23 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.994 (6.994)	Loss 6.7555 (6.7555)	Acc@1 0.537 (0.537)	Acc@5 4.224 (4.224)	Mem 24308MB
[2025-01-18 13:17:26 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.931)	Loss 6.7460 (6.7237)	Acc@1 0.366 (0.364)	Acc@5 2.686 (2.188)	Mem 24308MB
[2025-01-18 13:17:27 internimage_s_1k_224] (main.py 575): INFO [Epoch:15] * Acc@1 0.658 Acc@5 2.765
[2025-01-18 13:17:27 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.7%
[2025-01-18 13:17:27 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 13:17:29 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 13:17:29 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 0.66%
[2025-01-18 13:17:31 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][0/312]	eta 0:11:47 lr 0.003201	time 2.2691 (2.2691)	model_time 0.5925 (0.5925)	loss 4.4421 (4.4421)	grad_norm 1.5073 (1.5073/0.0000)	mem 24308MB
[2025-01-18 13:17:37 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][10/312]	eta 0:03:50 lr 0.003207	time 0.5720 (0.7648)	model_time 0.5718 (0.6120)	loss 3.5294 (4.5299)	grad_norm 1.7252 (1.8838/0.3942)	mem 24308MB
[2025-01-18 13:17:44 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][20/312]	eta 0:03:25 lr 0.003214	time 0.5866 (0.7052)	model_time 0.5861 (0.6250)	loss 5.0161 (4.5154)	grad_norm 1.8828 (1.9183/0.5108)	mem 24308MB
[2025-01-18 13:17:50 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][30/312]	eta 0:03:13 lr 0.003220	time 0.5918 (0.6852)	model_time 0.5916 (0.6308)	loss 4.1983 (4.4409)	grad_norm 1.7218 (1.9979/0.5717)	mem 24308MB
[2025-01-18 13:17:56 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][40/312]	eta 0:03:01 lr 0.003226	time 0.6082 (0.6676)	model_time 0.6080 (0.6263)	loss 3.9471 (4.3938)	grad_norm 2.3586 (2.0218/0.6244)	mem 24308MB
[2025-01-18 13:18:02 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][50/312]	eta 0:02:50 lr 0.003233	time 0.5867 (0.6511)	model_time 0.5865 (0.6179)	loss 3.8443 (4.3835)	grad_norm 2.0534 (2.0085/0.5809)	mem 24308MB
[2025-01-18 13:18:08 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][60/312]	eta 0:02:41 lr 0.003239	time 0.5760 (0.6402)	model_time 0.5755 (0.6124)	loss 4.2335 (4.3622)	grad_norm 1.8128 (1.9822/0.5547)	mem 24308MB
[2025-01-18 13:18:14 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][70/312]	eta 0:02:33 lr 0.003246	time 0.6033 (0.6332)	model_time 0.6031 (0.6093)	loss 3.8498 (4.4021)	grad_norm 2.1488 (1.9874/0.5382)	mem 24308MB
[2025-01-18 13:18:20 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][80/312]	eta 0:02:25 lr 0.003252	time 0.5728 (0.6274)	model_time 0.5726 (0.6064)	loss 3.5997 (4.3760)	grad_norm 1.0789 (2.0417/0.6992)	mem 24308MB
[2025-01-18 13:18:25 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][90/312]	eta 0:02:18 lr 0.003258	time 0.5741 (0.6229)	model_time 0.5740 (0.6041)	loss 5.1881 (4.3861)	grad_norm 1.4285 (2.0246/0.6823)	mem 24308MB
[2025-01-18 13:18:31 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][100/312]	eta 0:02:11 lr 0.003265	time 0.5994 (0.6196)	model_time 0.5992 (0.6026)	loss 3.5041 (4.3524)	grad_norm 1.6250 (2.0435/0.6862)	mem 24308MB
[2025-01-18 13:18:37 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][110/312]	eta 0:02:04 lr 0.003271	time 0.5860 (0.6165)	model_time 0.5859 (0.6010)	loss 4.7924 (4.3554)	grad_norm 1.2731 (2.0257/0.6810)	mem 24308MB
[2025-01-18 13:18:43 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][120/312]	eta 0:01:57 lr 0.003278	time 0.5807 (0.6143)	model_time 0.5806 (0.6001)	loss 4.7363 (4.3637)	grad_norm 1.4034 (2.0736/0.7438)	mem 24308MB
[2025-01-18 13:18:49 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][130/312]	eta 0:01:51 lr 0.003284	time 0.5718 (0.6141)	model_time 0.5717 (0.6009)	loss 3.9275 (4.3541)	grad_norm 2.1118 (2.0723/0.7377)	mem 24308MB
[2025-01-18 13:18:56 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][140/312]	eta 0:01:45 lr 0.003290	time 0.6604 (0.6155)	model_time 0.6602 (0.6033)	loss 4.6949 (4.3752)	grad_norm 2.8437 (2.0471/0.7287)	mem 24308MB
[2025-01-18 13:19:02 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][150/312]	eta 0:01:39 lr 0.003297	time 0.5950 (0.6163)	model_time 0.5948 (0.6049)	loss 4.5297 (4.3889)	grad_norm 1.3553 (2.0167/0.7172)	mem 24308MB
[2025-01-18 13:19:08 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][160/312]	eta 0:01:33 lr 0.003303	time 0.5685 (0.6157)	model_time 0.5680 (0.6049)	loss 3.6517 (4.3854)	grad_norm 1.4980 (2.0651/0.8204)	mem 24308MB
[2025-01-18 13:19:14 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][170/312]	eta 0:01:27 lr 0.003310	time 0.5819 (0.6144)	model_time 0.5814 (0.6042)	loss 5.1600 (4.4029)	grad_norm 2.5959 (2.0757/0.8056)	mem 24308MB
[2025-01-18 13:19:20 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][180/312]	eta 0:01:20 lr 0.003316	time 0.5853 (0.6127)	model_time 0.5848 (0.6031)	loss 4.7868 (4.4019)	grad_norm 1.7479 (2.1165/0.8369)	mem 24308MB
[2025-01-18 13:19:26 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][190/312]	eta 0:01:14 lr 0.003322	time 0.5873 (0.6112)	model_time 0.5871 (0.6021)	loss 4.6612 (4.4112)	grad_norm 2.1141 (2.1067/0.8202)	mem 24308MB
[2025-01-18 13:19:31 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][200/312]	eta 0:01:08 lr 0.003329	time 0.5804 (0.6097)	model_time 0.5802 (0.6011)	loss 4.0498 (4.3964)	grad_norm 3.9923 (2.1373/0.8302)	mem 24308MB
[2025-01-18 13:19:37 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][210/312]	eta 0:01:02 lr 0.003335	time 0.5880 (0.6088)	model_time 0.5879 (0.6005)	loss 5.4528 (4.4076)	grad_norm 1.0350 (2.1167/0.8195)	mem 24308MB
[2025-01-18 13:19:43 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][220/312]	eta 0:00:55 lr 0.003342	time 0.5876 (0.6077)	model_time 0.5871 (0.5997)	loss 4.2248 (4.4116)	grad_norm 1.3567 (2.0859/0.8150)	mem 24308MB
[2025-01-18 13:19:49 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][230/312]	eta 0:00:49 lr 0.003348	time 0.5844 (0.6067)	model_time 0.5842 (0.5991)	loss 4.3654 (4.4249)	grad_norm 1.6017 (2.0820/0.8102)	mem 24308MB
[2025-01-18 13:19:55 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][240/312]	eta 0:00:43 lr 0.003354	time 0.5772 (0.6062)	model_time 0.5770 (0.5989)	loss 4.6437 (4.4170)	grad_norm 1.8266 (2.0715/0.7977)	mem 24308MB
[2025-01-18 13:20:01 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][250/312]	eta 0:00:37 lr 0.003361	time 0.6633 (0.6064)	model_time 0.6631 (0.5994)	loss 4.2629 (4.4265)	grad_norm 2.1615 (2.0723/0.7912)	mem 24308MB
[2025-01-18 13:20:07 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][260/312]	eta 0:00:31 lr 0.003367	time 0.5792 (0.6072)	model_time 0.5790 (0.6004)	loss 3.9460 (4.4268)	grad_norm 2.3818 (2.0715/0.7828)	mem 24308MB
[2025-01-18 13:20:14 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][270/312]	eta 0:00:25 lr 0.003374	time 0.6834 (0.6090)	model_time 0.6832 (0.6024)	loss 3.6378 (4.4296)	grad_norm 1.2116 (2.0745/0.7797)	mem 24308MB
[2025-01-18 13:20:20 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][280/312]	eta 0:00:19 lr 0.003380	time 0.6422 (0.6091)	model_time 0.6419 (0.6028)	loss 4.4962 (4.4288)	grad_norm 1.6187 (2.0717/0.7718)	mem 24308MB
[2025-01-18 13:20:26 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][290/312]	eta 0:00:13 lr 0.003387	time 0.5669 (0.6085)	model_time 0.5668 (0.6024)	loss 4.4732 (4.4290)	grad_norm 0.9868 (2.0717/0.7702)	mem 24308MB
[2025-01-18 13:20:32 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][300/312]	eta 0:00:07 lr 0.003393	time 0.5678 (0.6077)	model_time 0.5677 (0.6018)	loss 4.9091 (4.4363)	grad_norm 2.6486 (2.0772/0.7710)	mem 24308MB
[2025-01-18 13:20:37 internimage_s_1k_224] (main.py 510): INFO Train: [16/300][310/312]	eta 0:00:01 lr 0.003399	time 0.5700 (0.6066)	model_time 0.5699 (0.6008)	loss 4.7823 (4.4424)	grad_norm 2.0287 (2.1055/0.7905)	mem 24308MB
[2025-01-18 13:20:38 internimage_s_1k_224] (main.py 519): INFO EPOCH 16 training takes 0:03:09
[2025-01-18 13:20:38 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_16.pth saving......
[2025-01-18 13:20:40 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_16.pth saved !!!
[2025-01-18 13:20:47 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.236 (7.236)	Loss 1.4388 (1.4388)	Acc@1 68.335 (68.335)	Acc@5 89.844 (89.844)	Mem 24308MB
[2025-01-18 13:20:50 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.953)	Loss 2.1104 (1.7607)	Acc@1 55.200 (61.659)	Acc@5 78.857 (84.863)	Mem 24308MB
[2025-01-18 13:20:50 internimage_s_1k_224] (main.py 575): INFO [Epoch:16] * Acc@1 61.794 Acc@5 84.995
[2025-01-18 13:20:50 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 61.8%
[2025-01-18 13:20:50 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 13:20:52 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 13:20:52 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 61.79%
[2025-01-18 13:21:00 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.193 (7.193)	Loss 6.7189 (6.7189)	Acc@1 0.879 (0.879)	Acc@5 4.639 (4.639)	Mem 24308MB
[2025-01-18 13:21:03 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.946)	Loss 6.7536 (6.7066)	Acc@1 0.586 (0.477)	Acc@5 2.710 (2.362)	Mem 24308MB
[2025-01-18 13:21:03 internimage_s_1k_224] (main.py 575): INFO [Epoch:16] * Acc@1 0.748 Acc@5 2.985
[2025-01-18 13:21:03 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.7%
[2025-01-18 13:21:03 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 13:21:05 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 13:21:05 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 0.75%
[2025-01-18 13:21:07 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][0/312]	eta 0:12:11 lr 0.003401	time 2.3446 (2.3446)	model_time 0.5979 (0.5979)	loss 4.1750 (4.1750)	grad_norm 1.8183 (1.8183/0.0000)	mem 24308MB
[2025-01-18 13:21:13 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][10/312]	eta 0:03:46 lr 0.003407	time 0.5741 (0.7516)	model_time 0.5740 (0.5917)	loss 4.6499 (4.1544)	grad_norm 6.8219 (2.2303/1.5761)	mem 24308MB
[2025-01-18 13:21:19 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][20/312]	eta 0:03:16 lr 0.003413	time 0.6118 (0.6743)	model_time 0.6113 (0.5903)	loss 4.7791 (4.2392)	grad_norm 1.0517 (2.1458/1.4884)	mem 24308MB
[2025-01-18 13:21:25 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][30/312]	eta 0:03:02 lr 0.003420	time 0.5827 (0.6458)	model_time 0.5825 (0.5888)	loss 3.6530 (4.2187)	grad_norm 1.6567 (2.0878/1.2501)	mem 24308MB
[2025-01-18 13:21:31 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][40/312]	eta 0:02:51 lr 0.003426	time 0.5710 (0.6308)	model_time 0.5705 (0.5876)	loss 4.3233 (4.2698)	grad_norm 1.7200 (2.0587/1.1168)	mem 24308MB
[2025-01-18 13:21:37 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][50/312]	eta 0:02:43 lr 0.003433	time 0.5811 (0.6240)	model_time 0.5810 (0.5892)	loss 4.9759 (4.3232)	grad_norm 2.3663 (2.0766/1.0754)	mem 24308MB
[2025-01-18 13:21:43 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][60/312]	eta 0:02:36 lr 0.003439	time 0.6614 (0.6218)	model_time 0.6612 (0.5926)	loss 4.0450 (4.3225)	grad_norm 1.5052 (2.0453/0.9990)	mem 24308MB
[2025-01-18 13:21:49 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][70/312]	eta 0:02:30 lr 0.003445	time 0.6553 (0.6230)	model_time 0.6552 (0.5978)	loss 4.4941 (4.3175)	grad_norm 1.7704 (2.0139/0.9409)	mem 24308MB
[2025-01-18 13:21:56 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][80/312]	eta 0:02:25 lr 0.003452	time 0.6633 (0.6267)	model_time 0.6631 (0.6046)	loss 4.5769 (4.3079)	grad_norm 1.0036 (2.0878/1.0380)	mem 24308MB
[2025-01-18 13:22:02 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][90/312]	eta 0:02:18 lr 0.003458	time 0.5643 (0.6251)	model_time 0.5642 (0.6054)	loss 4.6710 (4.3088)	grad_norm 1.5236 (2.0625/1.0286)	mem 24308MB
[2025-01-18 13:22:08 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][100/312]	eta 0:02:11 lr 0.003465	time 0.5898 (0.6221)	model_time 0.5896 (0.6044)	loss 4.8880 (4.3348)	grad_norm 1.0236 (2.0256/1.0068)	mem 24308MB
[2025-01-18 13:22:14 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][110/312]	eta 0:02:05 lr 0.003471	time 0.5825 (0.6188)	model_time 0.5822 (0.6027)	loss 4.8222 (4.3478)	grad_norm 2.8049 (2.0260/0.9824)	mem 24308MB
[2025-01-18 13:22:20 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][120/312]	eta 0:01:58 lr 0.003477	time 0.5911 (0.6158)	model_time 0.5906 (0.6009)	loss 4.0002 (4.3186)	grad_norm 2.2703 (2.0143/0.9488)	mem 24308MB
[2025-01-18 13:22:25 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][130/312]	eta 0:01:51 lr 0.003484	time 0.5890 (0.6132)	model_time 0.5888 (0.5994)	loss 4.4811 (4.3206)	grad_norm 1.2699 (1.9970/0.9262)	mem 24308MB
[2025-01-18 13:22:31 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][140/312]	eta 0:01:45 lr 0.003490	time 0.5803 (0.6111)	model_time 0.5798 (0.5983)	loss 4.8887 (4.3226)	grad_norm 3.2380 (2.0306/0.9612)	mem 24308MB
[2025-01-18 13:22:37 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][150/312]	eta 0:01:38 lr 0.003497	time 0.5739 (0.6094)	model_time 0.5737 (0.5974)	loss 4.2295 (4.3307)	grad_norm 1.3970 (2.0057/0.9405)	mem 24308MB
[2025-01-18 13:22:43 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][160/312]	eta 0:01:32 lr 0.003503	time 0.6104 (0.6081)	model_time 0.6102 (0.5969)	loss 4.6279 (4.3442)	grad_norm 1.3926 (2.0011/0.9218)	mem 24308MB
[2025-01-18 13:22:49 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][170/312]	eta 0:01:26 lr 0.003509	time 0.5892 (0.6072)	model_time 0.5891 (0.5965)	loss 4.4798 (4.3503)	grad_norm 1.3893 (2.0108/0.9080)	mem 24308MB
[2025-01-18 13:22:55 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][180/312]	eta 0:01:20 lr 0.003516	time 0.5994 (0.6064)	model_time 0.5992 (0.5963)	loss 3.6641 (4.3357)	grad_norm 1.8086 (2.0069/0.8882)	mem 24308MB
[2025-01-18 13:23:01 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][190/312]	eta 0:01:14 lr 0.003522	time 0.6435 (0.6075)	model_time 0.6430 (0.5979)	loss 4.7472 (4.3476)	grad_norm 1.9303 (1.9898/0.8711)	mem 24308MB
[2025-01-18 13:23:08 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][200/312]	eta 0:01:08 lr 0.003529	time 0.7536 (0.6091)	model_time 0.7531 (0.6000)	loss 5.1534 (4.3451)	grad_norm 2.7474 (2.0088/0.8717)	mem 24308MB
[2025-01-18 13:23:14 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][210/312]	eta 0:01:02 lr 0.003535	time 0.6816 (0.6093)	model_time 0.6814 (0.6006)	loss 4.0121 (4.3362)	grad_norm 2.2071 (2.0028/0.8579)	mem 24308MB
[2025-01-18 13:23:20 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][220/312]	eta 0:00:55 lr 0.003541	time 0.5766 (0.6084)	model_time 0.5764 (0.6000)	loss 5.2421 (4.3485)	grad_norm 1.9709 (1.9946/0.8438)	mem 24308MB
[2025-01-18 13:23:25 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][230/312]	eta 0:00:49 lr 0.003548	time 0.5755 (0.6076)	model_time 0.5750 (0.5996)	loss 3.4587 (4.3340)	grad_norm 1.6066 (2.0010/0.8420)	mem 24308MB
[2025-01-18 13:23:31 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][240/312]	eta 0:00:43 lr 0.003554	time 0.5787 (0.6066)	model_time 0.5782 (0.5990)	loss 3.2668 (4.3310)	grad_norm 1.5298 (2.0027/0.8365)	mem 24308MB
[2025-01-18 13:23:37 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][250/312]	eta 0:00:37 lr 0.003561	time 0.5948 (0.6057)	model_time 0.5944 (0.5984)	loss 4.4252 (4.3266)	grad_norm 1.5578 (1.9936/0.8236)	mem 24308MB
[2025-01-18 13:23:43 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][260/312]	eta 0:00:31 lr 0.003567	time 0.5990 (0.6048)	model_time 0.5988 (0.5977)	loss 3.7594 (4.3314)	grad_norm 2.8628 (2.0177/0.8368)	mem 24308MB
[2025-01-18 13:23:49 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][270/312]	eta 0:00:25 lr 0.003574	time 0.5720 (0.6042)	model_time 0.5718 (0.5973)	loss 3.6712 (4.3265)	grad_norm 1.7360 (2.0318/0.8626)	mem 24308MB
[2025-01-18 13:23:55 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][280/312]	eta 0:00:19 lr 0.003580	time 0.5865 (0.6036)	model_time 0.5861 (0.5969)	loss 4.6043 (4.3279)	grad_norm 1.4652 (2.0241/0.8569)	mem 24308MB
[2025-01-18 13:24:01 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][290/312]	eta 0:00:13 lr 0.003586	time 0.5792 (0.6033)	model_time 0.5790 (0.5969)	loss 5.2259 (4.3395)	grad_norm 2.3688 (2.0183/0.8480)	mem 24308MB
[2025-01-18 13:24:07 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][300/312]	eta 0:00:07 lr 0.003593	time 0.5629 (0.6026)	model_time 0.5628 (0.5964)	loss 3.6995 (4.3320)	grad_norm 1.2810 (1.9980/0.8442)	mem 24308MB
[2025-01-18 13:24:13 internimage_s_1k_224] (main.py 510): INFO Train: [17/300][310/312]	eta 0:00:01 lr 0.003599	time 0.5762 (0.6031)	model_time 0.5760 (0.5971)	loss 5.0190 (4.3356)	grad_norm 1.2790 (1.9757/0.7934)	mem 24308MB
[2025-01-18 13:24:13 internimage_s_1k_224] (main.py 519): INFO EPOCH 17 training takes 0:03:08
[2025-01-18 13:24:13 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_17.pth saving......
[2025-01-18 13:24:15 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_17.pth saved !!!
[2025-01-18 13:24:23 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.298 (7.298)	Loss 1.3723 (1.3723)	Acc@1 69.263 (69.263)	Acc@5 90.381 (90.381)	Mem 24308MB
[2025-01-18 13:24:26 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.948)	Loss 2.0597 (1.7285)	Acc@1 55.737 (62.522)	Acc@5 80.566 (85.176)	Mem 24308MB
[2025-01-18 13:24:26 internimage_s_1k_224] (main.py 575): INFO [Epoch:17] * Acc@1 62.570 Acc@5 85.297
[2025-01-18 13:24:26 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 62.6%
[2025-01-18 13:24:26 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 13:24:28 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 13:24:28 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 62.57%
[2025-01-18 13:24:35 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.400 (7.400)	Loss 6.6814 (6.6814)	Acc@1 0.977 (0.977)	Acc@5 5.249 (5.249)	Mem 24308MB
[2025-01-18 13:24:39 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.973)	Loss 6.7740 (6.6935)	Acc@1 0.781 (0.579)	Acc@5 2.759 (2.603)	Mem 24308MB
[2025-01-18 13:24:39 internimage_s_1k_224] (main.py 575): INFO [Epoch:17] * Acc@1 0.852 Acc@5 3.257
[2025-01-18 13:24:39 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.9%
[2025-01-18 13:24:39 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 13:24:42 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 13:24:42 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 0.85%
[2025-01-18 13:24:44 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][0/312]	eta 0:09:53 lr 0.003600	time 1.9030 (1.9030)	model_time 0.6026 (0.6026)	loss 3.7689 (3.7689)	grad_norm 1.5546 (1.5546/0.0000)	mem 24308MB
[2025-01-18 13:24:50 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][10/312]	eta 0:03:52 lr 0.003607	time 0.5644 (0.7712)	model_time 0.5640 (0.6526)	loss 5.2883 (4.4465)	grad_norm 1.8857 (3.5124/2.4484)	mem 24308MB
[2025-01-18 13:24:56 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][20/312]	eta 0:03:23 lr 0.003613	time 0.5784 (0.6953)	model_time 0.5782 (0.6331)	loss 3.3087 (4.4910)	grad_norm 1.0455 (2.5691/2.0564)	mem 24308MB
[2025-01-18 13:25:02 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][30/312]	eta 0:03:07 lr 0.003620	time 0.5764 (0.6646)	model_time 0.5762 (0.6223)	loss 3.3653 (4.3697)	grad_norm 1.4818 (2.2699/1.7977)	mem 24308MB
[2025-01-18 13:25:08 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][40/312]	eta 0:02:55 lr 0.003626	time 0.5823 (0.6451)	model_time 0.5818 (0.6131)	loss 3.5760 (4.3250)	grad_norm 2.3794 (2.1210/1.5953)	mem 24308MB
[2025-01-18 13:25:14 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][50/312]	eta 0:02:45 lr 0.003632	time 0.5908 (0.6335)	model_time 0.5906 (0.6076)	loss 4.1008 (4.3431)	grad_norm 1.8393 (2.1632/1.4726)	mem 24308MB
[2025-01-18 13:25:20 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][60/312]	eta 0:02:37 lr 0.003639	time 0.5844 (0.6254)	model_time 0.5842 (0.6037)	loss 4.6738 (4.3312)	grad_norm 1.3530 (2.1653/1.3696)	mem 24308MB
[2025-01-18 13:25:26 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][70/312]	eta 0:02:30 lr 0.003645	time 0.6022 (0.6203)	model_time 0.6021 (0.6017)	loss 4.5576 (4.3423)	grad_norm 1.7469 (2.0894/1.2913)	mem 24308MB
[2025-01-18 13:25:32 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][80/312]	eta 0:02:22 lr 0.003652	time 0.5642 (0.6159)	model_time 0.5637 (0.5995)	loss 4.4135 (4.3439)	grad_norm 1.6486 (2.0664/1.2577)	mem 24308MB
[2025-01-18 13:25:37 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][90/312]	eta 0:02:15 lr 0.003658	time 0.6034 (0.6125)	model_time 0.6033 (0.5978)	loss 3.6291 (4.3489)	grad_norm 4.0528 (2.1297/1.2523)	mem 24308MB
[2025-01-18 13:25:43 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][100/312]	eta 0:02:09 lr 0.003664	time 0.5685 (0.6104)	model_time 0.5683 (0.5972)	loss 3.4491 (4.3239)	grad_norm 1.9732 (2.1131/1.2087)	mem 24308MB
[2025-01-18 13:25:49 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][110/312]	eta 0:02:03 lr 0.003671	time 0.6491 (0.6093)	model_time 0.6487 (0.5972)	loss 4.4736 (4.3194)	grad_norm 1.3974 (2.0704/1.1633)	mem 24308MB
[2025-01-18 13:25:56 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][120/312]	eta 0:01:57 lr 0.003677	time 0.6768 (0.6112)	model_time 0.6766 (0.6001)	loss 4.2676 (4.3082)	grad_norm 2.1749 (2.0460/1.1234)	mem 24308MB
[2025-01-18 13:26:02 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][130/312]	eta 0:01:51 lr 0.003684	time 0.5741 (0.6133)	model_time 0.5737 (0.6029)	loss 4.5618 (4.3101)	grad_norm 1.3738 (2.0434/1.0967)	mem 24308MB
[2025-01-18 13:26:08 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][140/312]	eta 0:01:45 lr 0.003690	time 0.5877 (0.6136)	model_time 0.5876 (0.6040)	loss 4.6590 (4.3255)	grad_norm 3.5354 (2.0474/1.0810)	mem 24308MB
[2025-01-18 13:26:14 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][150/312]	eta 0:01:39 lr 0.003696	time 0.6005 (0.6143)	model_time 0.6000 (0.6053)	loss 4.1371 (4.3364)	grad_norm 1.5309 (2.0112/1.0569)	mem 24308MB
[2025-01-18 13:26:20 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][160/312]	eta 0:01:33 lr 0.003703	time 0.5693 (0.6123)	model_time 0.5691 (0.6039)	loss 4.5658 (4.3360)	grad_norm 1.5158 (1.9880/1.0315)	mem 24308MB
[2025-01-18 13:26:26 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][170/312]	eta 0:01:26 lr 0.003709	time 0.6114 (0.6110)	model_time 0.6112 (0.6030)	loss 3.0182 (4.3252)	grad_norm 2.0124 (2.0153/1.0269)	mem 24308MB
[2025-01-18 13:26:32 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][180/312]	eta 0:01:20 lr 0.003716	time 0.5796 (0.6097)	model_time 0.5791 (0.6022)	loss 4.1361 (4.3171)	grad_norm 2.1070 (1.9893/1.0071)	mem 24308MB
[2025-01-18 13:26:38 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][190/312]	eta 0:01:14 lr 0.003722	time 0.5862 (0.6084)	model_time 0.5860 (0.6013)	loss 5.0680 (4.3267)	grad_norm 1.0372 (1.9727/0.9902)	mem 24308MB
[2025-01-18 13:26:44 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][200/312]	eta 0:01:08 lr 0.003728	time 0.5799 (0.6075)	model_time 0.5794 (0.6007)	loss 4.2560 (4.3177)	grad_norm 1.6142 (1.9600/0.9729)	mem 24308MB
[2025-01-18 13:26:50 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][210/312]	eta 0:01:01 lr 0.003735	time 0.5878 (0.6066)	model_time 0.5873 (0.6000)	loss 4.6313 (4.3371)	grad_norm 1.3812 (1.9734/0.9696)	mem 24308MB
[2025-01-18 13:26:56 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][220/312]	eta 0:00:55 lr 0.003741	time 0.5771 (0.6060)	model_time 0.5770 (0.5998)	loss 4.4473 (4.3451)	grad_norm 1.0364 (1.9575/0.9542)	mem 24308MB
[2025-01-18 13:27:02 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][230/312]	eta 0:00:49 lr 0.003748	time 0.5810 (0.6053)	model_time 0.5809 (0.5993)	loss 4.3983 (4.3413)	grad_norm 2.5550 (1.9572/0.9384)	mem 24308MB
[2025-01-18 13:27:08 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][240/312]	eta 0:00:43 lr 0.003754	time 0.6684 (0.6062)	model_time 0.6682 (0.6004)	loss 4.2754 (4.3341)	grad_norm 2.8022 (1.9513/0.9320)	mem 24308MB
[2025-01-18 13:27:14 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][250/312]	eta 0:00:37 lr 0.003760	time 0.6671 (0.6085)	model_time 0.6669 (0.6030)	loss 4.9260 (4.3492)	grad_norm 2.6822 (1.9650/0.9385)	mem 24308MB
[2025-01-18 13:27:21 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][260/312]	eta 0:00:31 lr 0.003767	time 0.5818 (0.6092)	model_time 0.5813 (0.6038)	loss 4.7115 (4.3677)	grad_norm 1.5979 (1.9647/0.9348)	mem 24308MB
[2025-01-18 13:27:27 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][270/312]	eta 0:00:25 lr 0.003773	time 0.5725 (0.6098)	model_time 0.5724 (0.6047)	loss 5.1196 (4.3695)	grad_norm 1.3239 (1.9613/0.9282)	mem 24308MB
[2025-01-18 13:27:33 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][280/312]	eta 0:00:19 lr 0.003780	time 0.5830 (0.6090)	model_time 0.5828 (0.6040)	loss 3.5308 (4.3562)	grad_norm 1.3073 (1.9491/0.9227)	mem 24308MB
[2025-01-18 13:27:39 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][290/312]	eta 0:00:13 lr 0.003786	time 0.5892 (0.6083)	model_time 0.5891 (0.6034)	loss 5.2275 (4.3569)	grad_norm 2.0876 (1.9413/0.9145)	mem 24308MB
[2025-01-18 13:27:45 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][300/312]	eta 0:00:07 lr 0.003793	time 0.5713 (0.6073)	model_time 0.5712 (0.6026)	loss 3.4063 (4.3559)	grad_norm 1.2327 (1.9322/0.9053)	mem 24308MB
[2025-01-18 13:27:50 internimage_s_1k_224] (main.py 510): INFO Train: [18/300][310/312]	eta 0:00:01 lr 0.003799	time 0.5670 (0.6061)	model_time 0.5670 (0.6015)	loss 3.2754 (4.3574)	grad_norm 0.7780 (1.8607/0.7158)	mem 24308MB
[2025-01-18 13:27:51 internimage_s_1k_224] (main.py 519): INFO EPOCH 18 training takes 0:03:09
[2025-01-18 13:27:51 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_18.pth saving......
[2025-01-18 13:27:53 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_18.pth saved !!!
[2025-01-18 13:28:01 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.076 (8.076)	Loss 1.4632 (1.4632)	Acc@1 67.969 (67.969)	Acc@5 89.526 (89.526)	Mem 24308MB
[2025-01-18 13:28:05 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.085)	Loss 2.0598 (1.7415)	Acc@1 56.763 (62.564)	Acc@5 80.664 (85.556)	Mem 24308MB
[2025-01-18 13:28:05 internimage_s_1k_224] (main.py 575): INFO [Epoch:18] * Acc@1 62.892 Acc@5 85.785
[2025-01-18 13:28:05 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 62.9%
[2025-01-18 13:28:05 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 13:28:07 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 13:28:07 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 62.89%
[2025-01-18 13:28:15 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.564 (8.564)	Loss 6.6495 (6.6495)	Acc@1 0.952 (0.952)	Acc@5 5.493 (5.493)	Mem 24308MB
[2025-01-18 13:28:19 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.145)	Loss 6.8053 (6.6863)	Acc@1 0.903 (0.630)	Acc@5 2.563 (2.748)	Mem 24308MB
[2025-01-18 13:28:20 internimage_s_1k_224] (main.py 575): INFO [Epoch:18] * Acc@1 0.922 Acc@5 3.439
[2025-01-18 13:28:20 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 0.9%
[2025-01-18 13:28:20 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 13:28:22 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 13:28:22 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 0.92%
[2025-01-18 13:28:24 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][0/312]	eta 0:10:12 lr 0.003800	time 1.9646 (1.9646)	model_time 0.6416 (0.6416)	loss 4.5210 (4.5210)	grad_norm 1.7603 (1.7603/0.0000)	mem 24308MB
[2025-01-18 13:28:30 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][10/312]	eta 0:03:36 lr 0.003807	time 0.5833 (0.7162)	model_time 0.5832 (0.5956)	loss 4.7244 (4.5439)	grad_norm 2.8615 (1.9488/0.3814)	mem 24308MB
[2025-01-18 13:28:36 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][20/312]	eta 0:03:10 lr 0.003813	time 0.5895 (0.6538)	model_time 0.5891 (0.5905)	loss 4.6990 (4.4532)	grad_norm 1.4136 (1.6778/0.4308)	mem 24308MB
[2025-01-18 13:28:42 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][30/312]	eta 0:02:58 lr 0.003819	time 0.5886 (0.6347)	model_time 0.5884 (0.5917)	loss 3.5953 (4.3157)	grad_norm 1.6234 (1.8912/0.7527)	mem 24308MB
[2025-01-18 13:28:48 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][40/312]	eta 0:02:50 lr 0.003826	time 0.6688 (0.6269)	model_time 0.6686 (0.5943)	loss 4.9594 (4.3668)	grad_norm 1.3245 (1.8698/0.7009)	mem 24308MB
[2025-01-18 13:28:54 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][50/312]	eta 0:02:44 lr 0.003832	time 0.6827 (0.6271)	model_time 0.6825 (0.6008)	loss 4.8259 (4.3564)	grad_norm 2.1662 (1.8498/0.6538)	mem 24308MB
[2025-01-18 13:29:01 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][60/312]	eta 0:02:39 lr 0.003839	time 0.7704 (0.6316)	model_time 0.7703 (0.6096)	loss 4.6783 (4.3626)	grad_norm 2.6400 (1.8734/0.6343)	mem 24308MB
[2025-01-18 13:29:07 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][70/312]	eta 0:02:32 lr 0.003845	time 0.5844 (0.6295)	model_time 0.5840 (0.6105)	loss 3.6284 (4.3496)	grad_norm 3.0047 (1.8782/0.6593)	mem 24308MB
[2025-01-18 13:29:13 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][80/312]	eta 0:02:25 lr 0.003851	time 0.6178 (0.6253)	model_time 0.6176 (0.6087)	loss 4.6523 (4.3542)	grad_norm 2.1035 (1.9455/0.7542)	mem 24308MB
[2025-01-18 13:29:19 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][90/312]	eta 0:02:17 lr 0.003858	time 0.5950 (0.6211)	model_time 0.5948 (0.6062)	loss 3.9482 (4.3611)	grad_norm 2.5407 (1.8971/0.7469)	mem 24308MB
[2025-01-18 13:29:24 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][100/312]	eta 0:02:10 lr 0.003864	time 0.5795 (0.6173)	model_time 0.5793 (0.6038)	loss 3.5518 (4.3406)	grad_norm 1.4740 (1.8607/0.7263)	mem 24308MB
[2025-01-18 13:29:30 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][110/312]	eta 0:02:04 lr 0.003871	time 0.5866 (0.6146)	model_time 0.5865 (0.6023)	loss 4.2929 (4.3257)	grad_norm 1.5246 (1.8546/0.7087)	mem 24308MB
[2025-01-18 13:29:36 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][120/312]	eta 0:01:57 lr 0.003877	time 0.5686 (0.6122)	model_time 0.5684 (0.6010)	loss 3.4447 (4.3146)	grad_norm 1.5951 (1.9190/0.8203)	mem 24308MB
[2025-01-18 13:29:42 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][130/312]	eta 0:01:51 lr 0.003883	time 0.6101 (0.6103)	model_time 0.6098 (0.5999)	loss 3.7640 (4.3082)	grad_norm 1.1659 (1.9354/0.8312)	mem 24308MB
[2025-01-18 13:29:48 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][140/312]	eta 0:01:44 lr 0.003890	time 0.5815 (0.6084)	model_time 0.5810 (0.5986)	loss 4.6467 (4.3339)	grad_norm 0.9580 (1.9096/0.8146)	mem 24308MB
[2025-01-18 13:29:54 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][150/312]	eta 0:01:38 lr 0.003896	time 0.5902 (0.6074)	model_time 0.5900 (0.5982)	loss 4.8197 (4.3350)	grad_norm 1.0458 (1.8713/0.8015)	mem 24308MB
[2025-01-18 13:30:00 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][160/312]	eta 0:01:32 lr 0.003903	time 0.5619 (0.6064)	model_time 0.5615 (0.5977)	loss 3.6637 (4.3316)	grad_norm 1.6573 (1.9238/0.8700)	mem 24308MB
[2025-01-18 13:30:06 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][170/312]	eta 0:01:26 lr 0.003909	time 0.8366 (0.6088)	model_time 0.8364 (0.6006)	loss 3.5874 (4.3303)	grad_norm 1.3140 (1.9292/0.8525)	mem 24308MB
[2025-01-18 13:30:13 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][180/312]	eta 0:01:20 lr 0.003915	time 0.7911 (0.6117)	model_time 0.7906 (0.6040)	loss 3.8010 (4.3209)	grad_norm 2.2537 (1.9114/0.8402)	mem 24308MB
[2025-01-18 13:30:19 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][190/312]	eta 0:01:14 lr 0.003922	time 0.5979 (0.6113)	model_time 0.5977 (0.6039)	loss 5.0345 (4.3189)	grad_norm 1.5786 (1.9401/0.8788)	mem 24308MB
[2025-01-18 13:30:25 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][200/312]	eta 0:01:08 lr 0.003928	time 0.5787 (0.6110)	model_time 0.5785 (0.6040)	loss 4.8893 (4.3134)	grad_norm 1.8041 (1.9180/0.8653)	mem 24308MB
[2025-01-18 13:30:31 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][210/312]	eta 0:01:02 lr 0.003935	time 0.5739 (0.6097)	model_time 0.5735 (0.6030)	loss 3.9040 (4.3056)	grad_norm 2.2501 (1.9055/0.8520)	mem 24308MB
[2025-01-18 13:30:37 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][220/312]	eta 0:00:56 lr 0.003941	time 0.5841 (0.6087)	model_time 0.5837 (0.6023)	loss 5.2007 (4.3013)	grad_norm 2.7854 (1.9091/0.8403)	mem 24308MB
[2025-01-18 13:30:42 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][230/312]	eta 0:00:49 lr 0.003947	time 0.5824 (0.6077)	model_time 0.5822 (0.6015)	loss 3.2872 (4.2995)	grad_norm 1.4451 (1.9115/0.8286)	mem 24308MB
[2025-01-18 13:30:48 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][240/312]	eta 0:00:43 lr 0.003954	time 0.5732 (0.6068)	model_time 0.5728 (0.6009)	loss 3.9257 (4.3020)	grad_norm 1.8646 (1.8880/0.8213)	mem 24308MB
[2025-01-18 13:30:54 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][250/312]	eta 0:00:37 lr 0.003960	time 0.5884 (0.6059)	model_time 0.5879 (0.6002)	loss 3.9731 (4.3106)	grad_norm 1.1170 (1.8798/0.8114)	mem 24308MB
[2025-01-18 13:31:00 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][260/312]	eta 0:00:31 lr 0.003967	time 0.5790 (0.6051)	model_time 0.5789 (0.5996)	loss 5.1424 (4.3123)	grad_norm 1.6685 (1.9084/0.8629)	mem 24308MB
[2025-01-18 13:31:06 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][270/312]	eta 0:00:25 lr 0.003973	time 0.5929 (0.6044)	model_time 0.5924 (0.5991)	loss 4.5729 (4.3153)	grad_norm 1.4948 (1.9158/0.8556)	mem 24308MB
[2025-01-18 13:31:12 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][280/312]	eta 0:00:19 lr 0.003980	time 0.5746 (0.6042)	model_time 0.5742 (0.5991)	loss 3.4186 (4.3041)	grad_norm 1.7639 (1.9121/0.8428)	mem 24308MB
[2025-01-18 13:31:18 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][290/312]	eta 0:00:13 lr 0.003986	time 0.6593 (0.6047)	model_time 0.6591 (0.5997)	loss 4.0355 (4.2964)	grad_norm 1.5429 (1.9047/0.8328)	mem 24308MB
[2025-01-18 13:31:24 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][300/312]	eta 0:00:07 lr 0.003992	time 0.5646 (0.6057)	model_time 0.5645 (0.6009)	loss 4.1770 (4.2938)	grad_norm 2.0013 (1.9090/0.8315)	mem 24308MB
[2025-01-18 13:31:31 internimage_s_1k_224] (main.py 510): INFO Train: [19/300][310/312]	eta 0:00:01 lr 0.003999	time 0.5645 (0.6062)	model_time 0.5644 (0.6016)	loss 4.4532 (4.2997)	grad_norm 1.9749 (1.9161/0.8460)	mem 24308MB
[2025-01-18 13:31:31 internimage_s_1k_224] (main.py 519): INFO EPOCH 19 training takes 0:03:09
[2025-01-18 13:31:31 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_19.pth saving......
[2025-01-18 13:31:33 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_19.pth saved !!!
[2025-01-18 13:31:42 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.742 (8.742)	Loss 1.4240 (1.4240)	Acc@1 68.823 (68.823)	Acc@5 89.453 (89.453)	Mem 24308MB
[2025-01-18 13:31:46 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.154)	Loss 1.9680 (1.6586)	Acc@1 57.129 (63.483)	Acc@5 81.226 (86.122)	Mem 24308MB
[2025-01-18 13:31:46 internimage_s_1k_224] (main.py 575): INFO [Epoch:19] * Acc@1 63.664 Acc@5 86.212
[2025-01-18 13:31:46 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 63.7%
[2025-01-18 13:31:46 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 13:31:48 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 13:31:48 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 63.66%
[2025-01-18 13:31:57 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.845 (8.845)	Loss 6.6285 (6.6285)	Acc@1 1.099 (1.099)	Acc@5 5.859 (5.859)	Mem 24308MB
[2025-01-18 13:32:01 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.170)	Loss 6.8538 (6.6886)	Acc@1 0.757 (0.668)	Acc@5 2.026 (2.743)	Mem 24308MB
[2025-01-18 13:32:01 internimage_s_1k_224] (main.py 575): INFO [Epoch:19] * Acc@1 0.954 Acc@5 3.465
[2025-01-18 13:32:01 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 1.0%
[2025-01-18 13:32:01 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 13:32:03 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 13:32:03 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 0.95%
[2025-01-18 13:32:05 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][0/312]	eta 0:11:02 lr 0.003957	time 2.1223 (2.1223)	model_time 0.5938 (0.5938)	loss 4.6391 (4.6391)	grad_norm 1.0700 (1.0700/0.0000)	mem 24308MB
[2025-01-18 13:32:11 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][10/312]	eta 0:03:44 lr 0.003957	time 0.5869 (0.7436)	model_time 0.5868 (0.6042)	loss 5.2627 (4.6730)	grad_norm 1.3805 (1.1490/0.2278)	mem 24308MB
[2025-01-18 13:32:17 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][20/312]	eta 0:03:15 lr 0.003956	time 0.5942 (0.6685)	model_time 0.5937 (0.5953)	loss 5.0982 (4.4987)	grad_norm 2.4854 (1.6890/0.9250)	mem 24308MB
[2025-01-18 13:32:23 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][30/312]	eta 0:03:01 lr 0.003956	time 0.5871 (0.6423)	model_time 0.5867 (0.5927)	loss 4.5234 (4.5478)	grad_norm 2.4209 (1.7077/0.8056)	mem 24308MB
[2025-01-18 13:32:29 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][40/312]	eta 0:02:51 lr 0.003956	time 0.5914 (0.6293)	model_time 0.5909 (0.5917)	loss 5.2869 (4.4808)	grad_norm 2.0754 (1.8351/0.8632)	mem 24308MB
[2025-01-18 13:32:35 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][50/312]	eta 0:02:42 lr 0.003956	time 0.5791 (0.6218)	model_time 0.5786 (0.5915)	loss 5.1982 (4.4780)	grad_norm 2.9079 (1.8805/0.8558)	mem 24308MB
[2025-01-18 13:32:41 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][60/312]	eta 0:02:35 lr 0.003956	time 0.5779 (0.6156)	model_time 0.5776 (0.5902)	loss 4.6971 (4.4843)	grad_norm 1.4709 (1.8484/0.8214)	mem 24308MB
[2025-01-18 13:32:47 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][70/312]	eta 0:02:27 lr 0.003956	time 0.5875 (0.6113)	model_time 0.5871 (0.5894)	loss 5.2023 (4.5219)	grad_norm 3.8028 (1.8837/0.8383)	mem 24308MB
[2025-01-18 13:32:52 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][80/312]	eta 0:02:21 lr 0.003956	time 0.5797 (0.6094)	model_time 0.5795 (0.5901)	loss 3.7376 (4.4886)	grad_norm 1.3044 (1.9367/0.8948)	mem 24308MB
[2025-01-18 13:32:58 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][90/312]	eta 0:02:14 lr 0.003955	time 0.5741 (0.6073)	model_time 0.5737 (0.5901)	loss 4.5579 (4.4781)	grad_norm 2.2456 (1.8930/0.8708)	mem 24308MB
[2025-01-18 13:33:05 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][100/312]	eta 0:02:09 lr 0.003955	time 0.6635 (0.6098)	model_time 0.6634 (0.5943)	loss 3.0513 (4.4594)	grad_norm 1.3207 (1.8565/0.8460)	mem 24308MB
[2025-01-18 13:33:11 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][110/312]	eta 0:02:03 lr 0.003955	time 0.5843 (0.6127)	model_time 0.5839 (0.5985)	loss 3.5294 (4.4384)	grad_norm 2.9858 (1.8258/0.8282)	mem 24308MB
[2025-01-18 13:33:17 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][120/312]	eta 0:01:57 lr 0.003955	time 0.5864 (0.6125)	model_time 0.5862 (0.5995)	loss 5.2094 (4.4288)	grad_norm 0.9694 (1.8390/0.8107)	mem 24308MB
[2025-01-18 13:33:23 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][130/312]	eta 0:01:51 lr 0.003955	time 0.5718 (0.6116)	model_time 0.5717 (0.5995)	loss 4.3811 (4.4217)	grad_norm 1.6259 (1.8036/0.7921)	mem 24308MB
[2025-01-18 13:33:29 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][140/312]	eta 0:01:44 lr 0.003955	time 0.5842 (0.6099)	model_time 0.5841 (0.5987)	loss 5.0949 (4.4343)	grad_norm 1.3394 (1.7979/0.7735)	mem 24308MB
[2025-01-18 13:33:35 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][150/312]	eta 0:01:38 lr 0.003955	time 0.5977 (0.6083)	model_time 0.5976 (0.5978)	loss 5.1150 (4.4168)	grad_norm 1.2525 (1.7827/0.7557)	mem 24308MB
[2025-01-18 13:33:41 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][160/312]	eta 0:01:32 lr 0.003954	time 0.5884 (0.6070)	model_time 0.5882 (0.5972)	loss 2.9377 (4.4039)	grad_norm 2.4772 (1.8427/0.8251)	mem 24308MB
[2025-01-18 13:33:47 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][170/312]	eta 0:01:26 lr 0.003954	time 0.5782 (0.6061)	model_time 0.5777 (0.5968)	loss 3.6909 (4.3952)	grad_norm 1.5362 (1.8165/0.8137)	mem 24308MB
[2025-01-18 13:33:53 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][180/312]	eta 0:01:19 lr 0.003954	time 0.5947 (0.6053)	model_time 0.5943 (0.5964)	loss 4.8104 (4.4052)	grad_norm 2.4381 (1.8694/0.8845)	mem 24308MB
[2025-01-18 13:33:59 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][190/312]	eta 0:01:13 lr 0.003954	time 0.5890 (0.6042)	model_time 0.5886 (0.5958)	loss 4.0920 (4.3809)	grad_norm 1.0529 (1.8452/0.8737)	mem 24308MB
[2025-01-18 13:34:04 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][200/312]	eta 0:01:07 lr 0.003954	time 0.5802 (0.6037)	model_time 0.5797 (0.5957)	loss 4.5732 (4.3730)	grad_norm 0.9453 (1.8118/0.8662)	mem 24308MB
[2025-01-18 13:34:10 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][210/312]	eta 0:01:01 lr 0.003954	time 0.5790 (0.6032)	model_time 0.5786 (0.5955)	loss 4.7225 (4.3528)	grad_norm 4.1217 (1.8260/0.8856)	mem 24308MB
[2025-01-18 13:34:16 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][220/312]	eta 0:00:55 lr 0.003954	time 0.6911 (0.6034)	model_time 0.6905 (0.5961)	loss 3.5022 (4.3424)	grad_norm 0.8634 (1.8166/0.8728)	mem 24308MB
[2025-01-18 13:34:23 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][230/312]	eta 0:00:49 lr 0.003953	time 0.6790 (0.6069)	model_time 0.6786 (0.5999)	loss 3.5648 (4.3293)	grad_norm 1.2299 (1.7938/0.8619)	mem 24308MB
[2025-01-18 13:34:30 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][240/312]	eta 0:00:43 lr 0.003953	time 0.5960 (0.6074)	model_time 0.5956 (0.6007)	loss 4.4859 (4.3157)	grad_norm 1.4234 (1.7813/0.8466)	mem 24308MB
[2025-01-18 13:34:36 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][250/312]	eta 0:00:37 lr 0.003953	time 0.5785 (0.6077)	model_time 0.5781 (0.6013)	loss 5.0695 (4.3153)	grad_norm 2.2506 (1.7867/0.8347)	mem 24308MB
[2025-01-18 13:34:42 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][260/312]	eta 0:00:31 lr 0.003953	time 0.5896 (0.6069)	model_time 0.5892 (0.6007)	loss 4.2645 (4.3049)	grad_norm 1.2494 (1.7994/0.8351)	mem 24308MB
[2025-01-18 13:34:47 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][270/312]	eta 0:00:25 lr 0.003953	time 0.5706 (0.6060)	model_time 0.5705 (0.6000)	loss 4.6157 (4.3107)	grad_norm 1.3634 (1.7859/0.8282)	mem 24308MB
[2025-01-18 13:34:53 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][280/312]	eta 0:00:19 lr 0.003953	time 0.5910 (0.6054)	model_time 0.5908 (0.5995)	loss 3.5711 (4.3106)	grad_norm 1.7920 (1.7714/0.8192)	mem 24308MB
[2025-01-18 13:34:59 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][290/312]	eta 0:00:13 lr 0.003953	time 0.5689 (0.6049)	model_time 0.5688 (0.5992)	loss 3.5387 (4.3115)	grad_norm 1.7934 (1.7626/0.8099)	mem 24308MB
[2025-01-18 13:35:05 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][300/312]	eta 0:00:07 lr 0.003952	time 0.5658 (0.6040)	model_time 0.5658 (0.5985)	loss 4.9540 (4.3163)	grad_norm 1.2328 (1.7749/0.8065)	mem 24308MB
[2025-01-18 13:35:11 internimage_s_1k_224] (main.py 510): INFO Train: [20/300][310/312]	eta 0:00:01 lr 0.003952	time 0.5659 (0.6029)	model_time 0.5658 (0.5976)	loss 5.0627 (4.3184)	grad_norm 2.0809 (1.8108/0.8076)	mem 24308MB
[2025-01-18 13:35:11 internimage_s_1k_224] (main.py 519): INFO EPOCH 20 training takes 0:03:08
[2025-01-18 13:35:11 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_20.pth saving......
[2025-01-18 13:35:13 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_20.pth saved !!!
[2025-01-18 13:35:20 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.092 (7.092)	Loss 1.3870 (1.3870)	Acc@1 70.850 (70.850)	Acc@5 90.405 (90.405)	Mem 24308MB
[2025-01-18 13:35:24 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.942)	Loss 2.0682 (1.7021)	Acc@1 56.128 (64.049)	Acc@5 80.542 (86.535)	Mem 24308MB
[2025-01-18 13:35:24 internimage_s_1k_224] (main.py 575): INFO [Epoch:20] * Acc@1 64.413 Acc@5 86.754
[2025-01-18 13:35:24 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 64.4%
[2025-01-18 13:35:24 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 13:35:26 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 13:35:26 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 64.41%
[2025-01-18 13:35:33 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.357 (7.357)	Loss 6.6216 (6.6216)	Acc@1 1.245 (1.245)	Acc@5 6.055 (6.055)	Mem 24308MB
[2025-01-18 13:35:36 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.963)	Loss 6.9071 (6.7014)	Acc@1 0.610 (0.686)	Acc@5 1.978 (2.797)	Mem 24308MB
[2025-01-18 13:35:36 internimage_s_1k_224] (main.py 575): INFO [Epoch:20] * Acc@1 0.960 Acc@5 3.511
[2025-01-18 13:35:36 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 1.0%
[2025-01-18 13:35:36 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 13:35:39 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 13:35:39 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 0.96%
[2025-01-18 13:35:41 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][0/312]	eta 0:11:41 lr 0.003952	time 2.2484 (2.2484)	model_time 0.5866 (0.5866)	loss 3.5421 (3.5421)	grad_norm 1.1280 (1.1280/0.0000)	mem 24308MB
[2025-01-18 13:35:47 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][10/312]	eta 0:03:45 lr 0.003952	time 0.6819 (0.7454)	model_time 0.6814 (0.5940)	loss 3.3358 (4.0662)	grad_norm 3.2122 (1.6597/0.7183)	mem 24308MB
[2025-01-18 13:35:53 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][20/312]	eta 0:03:16 lr 0.003952	time 0.5900 (0.6743)	model_time 0.5899 (0.5949)	loss 4.8555 (4.3143)	grad_norm 2.7914 (1.7879/0.7234)	mem 24308MB
[2025-01-18 13:35:59 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][30/312]	eta 0:03:04 lr 0.003952	time 0.5813 (0.6532)	model_time 0.5809 (0.5993)	loss 4.3432 (4.2016)	grad_norm 1.7789 (1.9017/0.7466)	mem 24308MB
[2025-01-18 13:36:05 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][40/312]	eta 0:02:58 lr 0.003952	time 0.7122 (0.6555)	model_time 0.7120 (0.6146)	loss 4.5727 (4.2620)	grad_norm 1.3677 (1.8646/0.6746)	mem 24308MB
[2025-01-18 13:36:12 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][50/312]	eta 0:02:50 lr 0.003952	time 0.5695 (0.6497)	model_time 0.5693 (0.6167)	loss 3.4364 (4.2550)	grad_norm 3.3194 (1.8941/0.6917)	mem 24308MB
[2025-01-18 13:36:18 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][60/312]	eta 0:02:41 lr 0.003951	time 0.5778 (0.6419)	model_time 0.5774 (0.6143)	loss 3.9476 (4.2053)	grad_norm 1.3733 (1.8902/0.6620)	mem 24308MB
[2025-01-18 13:36:24 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][70/312]	eta 0:02:33 lr 0.003951	time 0.5900 (0.6344)	model_time 0.5899 (0.6107)	loss 4.6702 (4.2489)	grad_norm 2.0788 (1.8988/0.6379)	mem 24308MB
[2025-01-18 13:36:29 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][80/312]	eta 0:02:25 lr 0.003951	time 0.5764 (0.6281)	model_time 0.5762 (0.6072)	loss 3.9894 (4.2120)	grad_norm 1.6667 (1.8848/0.6329)	mem 24308MB
[2025-01-18 13:36:35 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][90/312]	eta 0:02:18 lr 0.003951	time 0.5818 (0.6236)	model_time 0.5816 (0.6050)	loss 4.7038 (4.2145)	grad_norm 0.9140 (1.8510/0.6118)	mem 24308MB
[2025-01-18 13:36:41 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][100/312]	eta 0:02:11 lr 0.003951	time 0.5839 (0.6199)	model_time 0.5838 (0.6031)	loss 4.2317 (4.2170)	grad_norm 1.3884 (1.8847/0.6238)	mem 24308MB
[2025-01-18 13:36:47 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][110/312]	eta 0:02:04 lr 0.003951	time 0.5704 (0.6171)	model_time 0.5702 (0.6018)	loss 3.5167 (4.2104)	grad_norm 3.5293 (1.8564/0.6382)	mem 24308MB
[2025-01-18 13:36:53 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][120/312]	eta 0:01:57 lr 0.003951	time 0.5907 (0.6144)	model_time 0.5906 (0.6004)	loss 4.1378 (4.1915)	grad_norm 1.3995 (1.8661/0.6577)	mem 24308MB
[2025-01-18 13:36:59 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][130/312]	eta 0:01:51 lr 0.003950	time 0.6761 (0.6129)	model_time 0.6760 (0.5999)	loss 4.3441 (4.1767)	grad_norm 1.8128 (1.8469/0.6487)	mem 24308MB
[2025-01-18 13:37:05 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][140/312]	eta 0:01:45 lr 0.003950	time 0.5652 (0.6117)	model_time 0.5647 (0.5995)	loss 4.4880 (4.1664)	grad_norm 4.2019 (1.8698/0.7000)	mem 24308MB
[2025-01-18 13:37:11 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][150/312]	eta 0:01:39 lr 0.003950	time 0.5754 (0.6116)	model_time 0.5752 (0.6003)	loss 4.8616 (4.1880)	grad_norm 2.4645 (1.9272/0.7953)	mem 24308MB
[2025-01-18 13:37:18 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][160/312]	eta 0:01:33 lr 0.003950	time 0.6844 (0.6147)	model_time 0.6842 (0.6040)	loss 4.4969 (4.1991)	grad_norm 1.7416 (1.9062/0.7804)	mem 24308MB
[2025-01-18 13:37:24 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][170/312]	eta 0:01:27 lr 0.003950	time 0.5783 (0.6149)	model_time 0.5779 (0.6048)	loss 4.8905 (4.2226)	grad_norm 1.7511 (1.8765/0.7702)	mem 24308MB
[2025-01-18 13:37:30 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][180/312]	eta 0:01:21 lr 0.003950	time 0.5798 (0.6144)	model_time 0.5797 (0.6049)	loss 3.7817 (4.2217)	grad_norm 1.5045 (1.8936/0.7896)	mem 24308MB
[2025-01-18 13:37:36 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][190/312]	eta 0:01:14 lr 0.003950	time 0.5996 (0.6132)	model_time 0.5991 (0.6041)	loss 3.7994 (4.2146)	grad_norm 1.2122 (1.8817/0.7760)	mem 24308MB
[2025-01-18 13:37:42 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][200/312]	eta 0:01:08 lr 0.003949	time 0.5726 (0.6118)	model_time 0.5721 (0.6031)	loss 4.7846 (4.1975)	grad_norm 1.3724 (1.8615/0.7638)	mem 24308MB
[2025-01-18 13:37:47 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][210/312]	eta 0:01:02 lr 0.003949	time 0.5862 (0.6108)	model_time 0.5858 (0.6025)	loss 5.2435 (4.1996)	grad_norm 0.9432 (1.8467/0.7562)	mem 24308MB
[2025-01-18 13:37:53 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][220/312]	eta 0:00:56 lr 0.003949	time 0.6035 (0.6098)	model_time 0.6030 (0.6019)	loss 4.1246 (4.1876)	grad_norm 1.7379 (1.8429/0.7445)	mem 24308MB
[2025-01-18 13:37:59 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][230/312]	eta 0:00:49 lr 0.003949	time 0.5872 (0.6089)	model_time 0.5871 (0.6013)	loss 3.1118 (4.1912)	grad_norm 1.3365 (1.8376/0.7376)	mem 24308MB
[2025-01-18 13:38:05 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][240/312]	eta 0:00:43 lr 0.003949	time 0.5928 (0.6080)	model_time 0.5923 (0.6007)	loss 4.7225 (4.2064)	grad_norm 2.9638 (1.8359/0.7364)	mem 24308MB
[2025-01-18 13:38:11 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][250/312]	eta 0:00:37 lr 0.003949	time 0.6594 (0.6074)	model_time 0.6590 (0.6004)	loss 4.7021 (4.2095)	grad_norm 1.3293 (1.8288/0.7381)	mem 24308MB
[2025-01-18 13:38:17 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][260/312]	eta 0:00:31 lr 0.003948	time 0.5878 (0.6072)	model_time 0.5874 (0.6005)	loss 3.1756 (4.2076)	grad_norm 1.8022 (1.8193/0.7278)	mem 24308MB
[2025-01-18 13:38:23 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][270/312]	eta 0:00:25 lr 0.003948	time 0.6738 (0.6069)	model_time 0.6737 (0.6004)	loss 3.2546 (4.2077)	grad_norm 4.5545 (1.8300/0.7439)	mem 24308MB
[2025-01-18 13:38:30 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][280/312]	eta 0:00:19 lr 0.003948	time 0.6495 (0.6086)	model_time 0.6489 (0.6023)	loss 2.8780 (4.2005)	grad_norm 1.7087 (1.8248/0.7513)	mem 24308MB
[2025-01-18 13:38:36 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][290/312]	eta 0:00:13 lr 0.003948	time 0.6022 (0.6095)	model_time 0.6020 (0.6034)	loss 5.0240 (4.2031)	grad_norm 1.0830 (1.8192/0.7449)	mem 24308MB
[2025-01-18 13:38:42 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][300/312]	eta 0:00:07 lr 0.003948	time 0.6279 (0.6091)	model_time 0.6278 (0.6032)	loss 3.7716 (4.1922)	grad_norm 1.5535 (1.8292/0.7460)	mem 24308MB
[2025-01-18 13:38:48 internimage_s_1k_224] (main.py 510): INFO Train: [21/300][310/312]	eta 0:00:01 lr 0.003948	time 0.5693 (0.6081)	model_time 0.5692 (0.6024)	loss 4.5340 (4.1895)	grad_norm 1.7662 (1.8344/0.7439)	mem 24308MB
[2025-01-18 13:38:48 internimage_s_1k_224] (main.py 519): INFO EPOCH 21 training takes 0:03:09
[2025-01-18 13:38:48 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_21.pth saving......
[2025-01-18 13:38:50 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_21.pth saved !!!
[2025-01-18 13:38:59 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.020 (9.020)	Loss 1.3057 (1.3057)	Acc@1 70.972 (70.972)	Acc@5 91.479 (91.479)	Mem 24308MB
[2025-01-18 13:39:04 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.207)	Loss 1.9027 (1.5891)	Acc@1 58.032 (65.121)	Acc@5 82.178 (87.256)	Mem 24308MB
[2025-01-18 13:39:04 internimage_s_1k_224] (main.py 575): INFO [Epoch:21] * Acc@1 65.323 Acc@5 87.492
[2025-01-18 13:39:04 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 65.3%
[2025-01-18 13:39:04 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 13:39:06 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 13:39:06 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 65.32%
[2025-01-18 13:39:15 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.772 (8.772)	Loss 6.6258 (6.6258)	Acc@1 1.343 (1.343)	Acc@5 6.421 (6.421)	Mem 24308MB
[2025-01-18 13:39:18 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.129)	Loss 6.9716 (6.7235)	Acc@1 0.439 (0.706)	Acc@5 1.611 (2.930)	Mem 24308MB
[2025-01-18 13:39:18 internimage_s_1k_224] (main.py 575): INFO [Epoch:21] * Acc@1 1.002 Acc@5 3.651
[2025-01-18 13:39:18 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 1.0%
[2025-01-18 13:39:18 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 13:39:20 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 13:39:20 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 1.00%
[2025-01-18 13:39:22 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][0/312]	eta 0:10:44 lr 0.003948	time 2.0652 (2.0652)	model_time 0.6066 (0.6066)	loss 4.1715 (4.1715)	grad_norm 1.9515 (1.9515/0.0000)	mem 24308MB
[2025-01-18 13:39:28 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][10/312]	eta 0:03:37 lr 0.003948	time 0.5764 (0.7188)	model_time 0.5761 (0.5857)	loss 4.3708 (4.3343)	grad_norm 1.1792 (1.5183/0.3478)	mem 24308MB
[2025-01-18 13:39:34 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][20/312]	eta 0:03:11 lr 0.003947	time 0.5825 (0.6569)	model_time 0.5823 (0.5870)	loss 3.4708 (4.2147)	grad_norm 1.6806 (1.6811/0.6467)	mem 24308MB
[2025-01-18 13:39:40 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][30/312]	eta 0:02:58 lr 0.003947	time 0.5757 (0.6335)	model_time 0.5755 (0.5861)	loss 4.5182 (4.2155)	grad_norm 1.2899 (1.6243/0.5729)	mem 24308MB
[2025-01-18 13:39:46 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][40/312]	eta 0:02:49 lr 0.003947	time 0.5738 (0.6218)	model_time 0.5736 (0.5859)	loss 3.2769 (4.1493)	grad_norm 1.2444 (1.6737/0.6061)	mem 24308MB
[2025-01-18 13:39:52 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][50/312]	eta 0:02:40 lr 0.003947	time 0.5808 (0.6138)	model_time 0.5806 (0.5848)	loss 4.9265 (4.1544)	grad_norm 1.2337 (1.7402/0.6297)	mem 24308MB
[2025-01-18 13:39:58 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][60/312]	eta 0:02:33 lr 0.003947	time 0.5862 (0.6102)	model_time 0.5860 (0.5859)	loss 3.5231 (4.1247)	grad_norm 1.1402 (1.6845/0.6081)	mem 24308MB
[2025-01-18 13:40:04 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][70/312]	eta 0:02:27 lr 0.003947	time 0.5877 (0.6105)	model_time 0.5875 (0.5896)	loss 4.0262 (4.1534)	grad_norm 1.5388 (1.7181/0.6212)	mem 24308MB
[2025-01-18 13:40:10 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][80/312]	eta 0:02:21 lr 0.003946	time 0.5911 (0.6109)	model_time 0.5909 (0.5926)	loss 3.2922 (4.1293)	grad_norm 1.1554 (1.7358/0.6386)	mem 24308MB
[2025-01-18 13:40:16 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][90/312]	eta 0:02:16 lr 0.003946	time 0.6620 (0.6161)	model_time 0.6618 (0.5997)	loss 3.2713 (4.1027)	grad_norm 1.9022 (1.6949/0.6241)	mem 24308MB
[2025-01-18 13:40:23 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][100/312]	eta 0:02:10 lr 0.003946	time 0.5740 (0.6172)	model_time 0.5736 (0.6024)	loss 4.7665 (4.1198)	grad_norm 1.1774 (1.7020/0.6224)	mem 24308MB
[2025-01-18 13:40:29 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][110/312]	eta 0:02:04 lr 0.003946	time 0.6554 (0.6160)	model_time 0.6552 (0.6025)	loss 3.2606 (4.1196)	grad_norm 1.8585 (1.7009/0.6105)	mem 24308MB
[2025-01-18 13:40:35 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][120/312]	eta 0:01:57 lr 0.003946	time 0.5881 (0.6142)	model_time 0.5879 (0.6018)	loss 4.8882 (4.1298)	grad_norm 2.2555 (1.7426/0.6152)	mem 24308MB
[2025-01-18 13:40:41 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][130/312]	eta 0:01:51 lr 0.003946	time 0.5866 (0.6120)	model_time 0.5864 (0.6005)	loss 4.0622 (4.1275)	grad_norm 1.2877 (1.7211/0.6025)	mem 24308MB
[2025-01-18 13:40:46 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][140/312]	eta 0:01:44 lr 0.003946	time 0.5879 (0.6101)	model_time 0.5875 (0.5994)	loss 3.9531 (4.0980)	grad_norm 5.0082 (1.7477/0.7117)	mem 24308MB
[2025-01-18 13:40:52 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][150/312]	eta 0:01:38 lr 0.003945	time 0.5880 (0.6081)	model_time 0.5876 (0.5981)	loss 4.5976 (4.0942)	grad_norm 1.8528 (1.7455/0.7047)	mem 24308MB
[2025-01-18 13:40:58 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][160/312]	eta 0:01:32 lr 0.003945	time 0.5738 (0.6068)	model_time 0.5737 (0.5974)	loss 2.9024 (4.0979)	grad_norm 2.5780 (1.7546/0.6966)	mem 24308MB
[2025-01-18 13:41:04 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][170/312]	eta 0:01:25 lr 0.003945	time 0.5843 (0.6055)	model_time 0.5841 (0.5966)	loss 4.5485 (4.1039)	grad_norm 1.7053 (1.7565/0.6818)	mem 24308MB
[2025-01-18 13:41:10 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][180/312]	eta 0:01:19 lr 0.003945	time 0.5904 (0.6044)	model_time 0.5902 (0.5960)	loss 4.3679 (4.0955)	grad_norm 2.3089 (1.7440/0.6755)	mem 24308MB
[2025-01-18 13:41:16 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][190/312]	eta 0:01:13 lr 0.003945	time 0.5812 (0.6046)	model_time 0.5811 (0.5966)	loss 3.1620 (4.0949)	grad_norm 1.2285 (1.7408/0.6699)	mem 24308MB
[2025-01-18 13:41:22 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][200/312]	eta 0:01:07 lr 0.003945	time 0.5829 (0.6045)	model_time 0.5824 (0.5969)	loss 4.1881 (4.1137)	grad_norm 1.4615 (1.7781/0.7173)	mem 24308MB
[2025-01-18 13:41:28 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][210/312]	eta 0:01:01 lr 0.003944	time 0.6586 (0.6058)	model_time 0.6582 (0.5985)	loss 3.5339 (4.1071)	grad_norm 1.1161 (1.7590/0.7098)	mem 24308MB
[2025-01-18 13:41:34 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][220/312]	eta 0:00:55 lr 0.003944	time 0.5769 (0.6066)	model_time 0.5764 (0.5996)	loss 4.2285 (4.0983)	grad_norm 1.4442 (1.7500/0.7026)	mem 24308MB
[2025-01-18 13:41:41 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][230/312]	eta 0:00:49 lr 0.003944	time 0.5907 (0.6071)	model_time 0.5902 (0.6004)	loss 3.2494 (4.1072)	grad_norm 1.1273 (1.7391/0.6969)	mem 24308MB
[2025-01-18 13:41:47 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][240/312]	eta 0:00:43 lr 0.003944	time 0.5889 (0.6068)	model_time 0.5887 (0.6004)	loss 4.4360 (4.1121)	grad_norm 1.1777 (1.7445/0.7029)	mem 24308MB
[2025-01-18 13:41:53 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][250/312]	eta 0:00:37 lr 0.003944	time 0.5925 (0.6061)	model_time 0.5921 (0.5999)	loss 4.3501 (4.1065)	grad_norm 1.2332 (1.7358/0.6954)	mem 24308MB
[2025-01-18 13:41:58 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][260/312]	eta 0:00:31 lr 0.003944	time 0.5784 (0.6053)	model_time 0.5782 (0.5994)	loss 3.9857 (4.1064)	grad_norm 1.8446 (1.7385/0.6852)	mem 24308MB
[2025-01-18 13:42:04 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][270/312]	eta 0:00:25 lr 0.003944	time 0.5669 (0.6045)	model_time 0.5664 (0.5988)	loss 3.3403 (4.1138)	grad_norm 1.3972 (1.7380/0.6785)	mem 24308MB
[2025-01-18 13:42:10 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][280/312]	eta 0:00:19 lr 0.003943	time 0.5830 (0.6037)	model_time 0.5825 (0.5982)	loss 4.5558 (4.1136)	grad_norm 0.8894 (1.7414/0.6848)	mem 24308MB
[2025-01-18 13:42:16 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][290/312]	eta 0:00:13 lr 0.003943	time 0.5928 (0.6031)	model_time 0.5924 (0.5977)	loss 4.7965 (4.1338)	grad_norm 1.1980 (1.7373/0.6881)	mem 24308MB
[2025-01-18 13:42:22 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][300/312]	eta 0:00:07 lr 0.003943	time 0.5660 (0.6023)	model_time 0.5659 (0.5971)	loss 4.2547 (4.1471)	grad_norm 1.3189 (1.7418/0.6835)	mem 24308MB
[2025-01-18 13:42:28 internimage_s_1k_224] (main.py 510): INFO Train: [22/300][310/312]	eta 0:00:01 lr 0.003943	time 0.5674 (0.6023)	model_time 0.5673 (0.5972)	loss 4.4079 (4.1546)	grad_norm 0.9973 (1.7496/0.6888)	mem 24308MB
[2025-01-18 13:42:28 internimage_s_1k_224] (main.py 519): INFO EPOCH 22 training takes 0:03:07
[2025-01-18 13:42:28 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_22.pth saving......
[2025-01-18 13:42:30 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_22.pth saved !!!
[2025-01-18 13:42:38 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.203 (8.203)	Loss 1.3234 (1.3234)	Acc@1 71.143 (71.143)	Acc@5 91.382 (91.382)	Mem 24308MB
[2025-01-18 13:42:42 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.085)	Loss 1.8970 (1.5849)	Acc@1 59.155 (65.714)	Acc@5 83.154 (87.536)	Mem 24308MB
[2025-01-18 13:42:42 internimage_s_1k_224] (main.py 575): INFO [Epoch:22] * Acc@1 65.899 Acc@5 87.656
[2025-01-18 13:42:42 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 65.9%
[2025-01-18 13:42:42 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 13:42:44 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 13:42:44 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 65.90%
[2025-01-18 13:42:52 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.095 (8.095)	Loss 6.6379 (6.6379)	Acc@1 1.636 (1.636)	Acc@5 6.665 (6.665)	Mem 24308MB
[2025-01-18 13:42:56 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.061)	Loss 7.0350 (6.7513)	Acc@1 0.415 (0.770)	Acc@5 1.440 (2.967)	Mem 24308MB
[2025-01-18 13:42:56 internimage_s_1k_224] (main.py 575): INFO [Epoch:22] * Acc@1 1.082 Acc@5 3.737
[2025-01-18 13:42:56 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 1.1%
[2025-01-18 13:42:56 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 13:42:59 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 13:42:59 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 1.08%
[2025-01-18 13:43:01 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][0/312]	eta 0:10:26 lr 0.003943	time 2.0090 (2.0090)	model_time 0.5908 (0.5908)	loss 4.1474 (4.1474)	grad_norm 1.1156 (1.1156/0.0000)	mem 24308MB
[2025-01-18 13:43:07 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][10/312]	eta 0:03:41 lr 0.003943	time 0.5830 (0.7340)	model_time 0.5825 (0.6047)	loss 3.1042 (3.7440)	grad_norm 1.4067 (1.4788/0.3703)	mem 24308MB
[2025-01-18 13:43:13 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][20/312]	eta 0:03:19 lr 0.003943	time 0.5832 (0.6815)	model_time 0.5830 (0.6136)	loss 4.9603 (4.0303)	grad_norm 1.8282 (1.7255/0.5693)	mem 24308MB
[2025-01-18 13:43:19 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][30/312]	eta 0:03:09 lr 0.003942	time 0.7018 (0.6727)	model_time 0.7013 (0.6265)	loss 3.7086 (4.0030)	grad_norm 2.2979 (1.8468/0.6082)	mem 24308MB
[2025-01-18 13:43:25 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][40/312]	eta 0:02:58 lr 0.003942	time 0.6641 (0.6551)	model_time 0.6639 (0.6201)	loss 4.8847 (4.0648)	grad_norm 2.4920 (1.8454/0.6314)	mem 24308MB
[2025-01-18 13:43:31 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][50/312]	eta 0:02:48 lr 0.003942	time 0.5929 (0.6449)	model_time 0.5927 (0.6167)	loss 3.8506 (4.0962)	grad_norm 2.4815 (1.8828/0.6967)	mem 24308MB
[2025-01-18 13:43:37 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][60/312]	eta 0:02:40 lr 0.003942	time 0.5806 (0.6352)	model_time 0.5804 (0.6115)	loss 4.2190 (4.1249)	grad_norm 1.0024 (1.7972/0.6860)	mem 24308MB
[2025-01-18 13:43:43 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][70/312]	eta 0:02:31 lr 0.003942	time 0.5894 (0.6278)	model_time 0.5890 (0.6075)	loss 3.2503 (4.1226)	grad_norm 2.7663 (1.8057/0.6945)	mem 24308MB
[2025-01-18 13:43:49 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][80/312]	eta 0:02:24 lr 0.003942	time 0.5685 (0.6227)	model_time 0.5683 (0.6048)	loss 4.8068 (4.1361)	grad_norm 2.0048 (1.8008/0.6870)	mem 24308MB
[2025-01-18 13:43:55 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][90/312]	eta 0:02:17 lr 0.003941	time 0.5956 (0.6184)	model_time 0.5954 (0.6024)	loss 4.3205 (4.1744)	grad_norm 1.4266 (1.7662/0.6698)	mem 24308MB
[2025-01-18 13:44:01 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][100/312]	eta 0:02:10 lr 0.003941	time 0.5763 (0.6152)	model_time 0.5761 (0.6008)	loss 5.1423 (4.1856)	grad_norm 1.6486 (1.7679/0.6627)	mem 24308MB
[2025-01-18 13:44:07 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][110/312]	eta 0:02:03 lr 0.003941	time 0.5926 (0.6135)	model_time 0.5924 (0.6004)	loss 4.2461 (4.1442)	grad_norm 1.0528 (1.8099/0.7038)	mem 24308MB
[2025-01-18 13:44:13 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][120/312]	eta 0:01:57 lr 0.003941	time 0.6029 (0.6130)	model_time 0.6024 (0.6009)	loss 4.3690 (4.1481)	grad_norm 1.2014 (1.7594/0.6976)	mem 24308MB
[2025-01-18 13:44:19 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][130/312]	eta 0:01:51 lr 0.003941	time 0.6563 (0.6124)	model_time 0.6561 (0.6012)	loss 3.9426 (4.1561)	grad_norm 1.2938 (1.7602/0.7016)	mem 24308MB
[2025-01-18 13:44:25 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][140/312]	eta 0:01:45 lr 0.003941	time 0.5815 (0.6132)	model_time 0.5814 (0.6028)	loss 3.7869 (4.1632)	grad_norm 1.2364 (1.7932/0.7362)	mem 24308MB
[2025-01-18 13:44:32 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][150/312]	eta 0:01:39 lr 0.003940	time 0.8748 (0.6171)	model_time 0.8746 (0.6073)	loss 3.8520 (4.1547)	grad_norm 2.6333 (1.7755/0.7255)	mem 24308MB
[2025-01-18 13:44:38 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][160/312]	eta 0:01:33 lr 0.003940	time 0.5796 (0.6172)	model_time 0.5794 (0.6080)	loss 4.3707 (4.1396)	grad_norm 2.7326 (1.7627/0.7239)	mem 24308MB
[2025-01-18 13:44:44 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][170/312]	eta 0:01:27 lr 0.003940	time 0.5796 (0.6159)	model_time 0.5794 (0.6073)	loss 5.0228 (4.1604)	grad_norm 1.3928 (1.7386/0.7121)	mem 24308MB
[2025-01-18 13:44:50 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][180/312]	eta 0:01:21 lr 0.003940	time 0.5888 (0.6141)	model_time 0.5886 (0.6059)	loss 4.9423 (4.1595)	grad_norm 1.6522 (1.7510/0.7073)	mem 24308MB
[2025-01-18 13:44:56 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][190/312]	eta 0:01:14 lr 0.003940	time 0.5859 (0.6127)	model_time 0.5855 (0.6049)	loss 3.8137 (4.1593)	grad_norm 1.4692 (1.7467/0.7008)	mem 24308MB
[2025-01-18 13:45:01 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][200/312]	eta 0:01:08 lr 0.003940	time 0.5805 (0.6113)	model_time 0.5798 (0.6039)	loss 5.0000 (4.1600)	grad_norm 1.2672 (1.7440/0.6909)	mem 24308MB
[2025-01-18 13:45:07 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][210/312]	eta 0:01:02 lr 0.003939	time 0.6035 (0.6102)	model_time 0.6031 (0.6031)	loss 4.9409 (4.1618)	grad_norm 1.2191 (1.7272/0.6820)	mem 24308MB
[2025-01-18 13:45:13 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][220/312]	eta 0:00:56 lr 0.003939	time 0.5816 (0.6092)	model_time 0.5814 (0.6024)	loss 4.1324 (4.1539)	grad_norm 1.2374 (1.7075/0.6764)	mem 24308MB
[2025-01-18 13:45:19 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][230/312]	eta 0:00:49 lr 0.003939	time 0.5764 (0.6085)	model_time 0.5758 (0.6020)	loss 4.2296 (4.1392)	grad_norm 1.9275 (1.7105/0.6762)	mem 24308MB
[2025-01-18 13:45:25 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][240/312]	eta 0:00:43 lr 0.003939	time 0.5669 (0.6080)	model_time 0.5667 (0.6017)	loss 4.3028 (4.1414)	grad_norm 2.1134 (1.7039/0.6737)	mem 24308MB
[2025-01-18 13:45:31 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][250/312]	eta 0:00:37 lr 0.003939	time 0.6646 (0.6082)	model_time 0.6643 (0.6021)	loss 3.9471 (4.1454)	grad_norm 2.2380 (1.7312/0.7089)	mem 24308MB
[2025-01-18 13:45:37 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][260/312]	eta 0:00:31 lr 0.003939	time 0.5832 (0.6083)	model_time 0.5828 (0.6025)	loss 3.5120 (4.1380)	grad_norm 1.4313 (1.7246/0.6990)	mem 24308MB
[2025-01-18 13:45:44 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][270/312]	eta 0:00:25 lr 0.003938	time 0.6741 (0.6092)	model_time 0.6739 (0.6036)	loss 5.1614 (4.1345)	grad_norm 1.0911 (1.7141/0.6926)	mem 24308MB
[2025-01-18 13:45:50 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][280/312]	eta 0:00:19 lr 0.003938	time 0.5800 (0.6092)	model_time 0.5795 (0.6038)	loss 3.1127 (4.1302)	grad_norm 1.9476 (1.7090/0.6859)	mem 24308MB
[2025-01-18 13:45:56 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][290/312]	eta 0:00:13 lr 0.003938	time 0.5788 (0.6088)	model_time 0.5786 (0.6035)	loss 5.2687 (4.1408)	grad_norm 1.0134 (1.7052/0.6866)	mem 24308MB
[2025-01-18 13:46:02 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][300/312]	eta 0:00:07 lr 0.003938	time 0.5750 (0.6079)	model_time 0.5749 (0.6028)	loss 4.2267 (4.1422)	grad_norm 2.0613 (1.7142/0.6969)	mem 24308MB
[2025-01-18 13:46:07 internimage_s_1k_224] (main.py 510): INFO Train: [23/300][310/312]	eta 0:00:01 lr 0.003938	time 0.5709 (0.6068)	model_time 0.5708 (0.6018)	loss 3.5495 (4.1420)	grad_norm 1.1958 (1.7265/0.7075)	mem 24308MB
[2025-01-18 13:46:08 internimage_s_1k_224] (main.py 519): INFO EPOCH 23 training takes 0:03:09
[2025-01-18 13:46:08 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_23.pth saving......
[2025-01-18 13:46:10 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_23.pth saved !!!
[2025-01-18 13:46:17 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.147 (7.147)	Loss 1.2881 (1.2881)	Acc@1 71.240 (71.240)	Acc@5 90.869 (90.869)	Mem 24308MB
[2025-01-18 13:46:20 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.924)	Loss 1.9051 (1.5633)	Acc@1 58.887 (66.329)	Acc@5 82.495 (87.684)	Mem 24308MB
[2025-01-18 13:46:20 internimage_s_1k_224] (main.py 575): INFO [Epoch:23] * Acc@1 66.397 Acc@5 87.816
[2025-01-18 13:46:20 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 66.4%
[2025-01-18 13:46:20 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 13:46:22 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 13:46:22 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 66.40%
[2025-01-18 13:46:29 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.015 (7.015)	Loss 6.6603 (6.6603)	Acc@1 1.733 (1.733)	Acc@5 6.665 (6.665)	Mem 24308MB
[2025-01-18 13:46:32 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.926)	Loss 7.0955 (6.7808)	Acc@1 0.195 (0.828)	Acc@5 1.147 (3.016)	Mem 24308MB
[2025-01-18 13:46:33 internimage_s_1k_224] (main.py 575): INFO [Epoch:23] * Acc@1 1.162 Acc@5 3.813
[2025-01-18 13:46:33 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 1.2%
[2025-01-18 13:46:33 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 13:46:35 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 13:46:35 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 1.16%
[2025-01-18 13:46:37 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][0/312]	eta 0:11:13 lr 0.003938	time 2.1594 (2.1594)	model_time 0.5939 (0.5939)	loss 4.3410 (4.3410)	grad_norm 2.1843 (2.1843/0.0000)	mem 24308MB
[2025-01-18 13:46:43 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][10/312]	eta 0:03:39 lr 0.003938	time 0.5810 (0.7281)	model_time 0.5809 (0.5855)	loss 4.3435 (4.1787)	grad_norm 1.9443 (1.6429/0.4850)	mem 24308MB
[2025-01-18 13:46:48 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][20/312]	eta 0:03:12 lr 0.003937	time 0.5689 (0.6594)	model_time 0.5687 (0.5845)	loss 4.1943 (4.0517)	grad_norm 1.0105 (1.7046/0.5619)	mem 24308MB
[2025-01-18 13:46:54 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][30/312]	eta 0:03:00 lr 0.003937	time 0.5780 (0.6395)	model_time 0.5775 (0.5886)	loss 4.5758 (4.0418)	grad_norm 1.0704 (1.6431/0.5349)	mem 24308MB
[2025-01-18 13:47:00 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][40/312]	eta 0:02:51 lr 0.003937	time 0.5788 (0.6298)	model_time 0.5786 (0.5912)	loss 4.3546 (4.0440)	grad_norm 1.8865 (1.5756/0.4963)	mem 24308MB
[2025-01-18 13:47:06 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][50/312]	eta 0:02:43 lr 0.003937	time 0.5946 (0.6226)	model_time 0.5944 (0.5915)	loss 3.8768 (4.0320)	grad_norm 1.5967 (1.6994/0.5898)	mem 24308MB
[2025-01-18 13:47:12 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][60/312]	eta 0:02:36 lr 0.003937	time 0.5995 (0.6200)	model_time 0.5990 (0.5939)	loss 4.7828 (4.0876)	grad_norm 1.4923 (1.6658/0.5524)	mem 24308MB
[2025-01-18 13:47:19 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][70/312]	eta 0:02:30 lr 0.003937	time 0.5691 (0.6211)	model_time 0.5689 (0.5986)	loss 4.2290 (4.0417)	grad_norm 1.6698 (1.7076/0.5777)	mem 24308MB
[2025-01-18 13:47:25 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][80/312]	eta 0:02:24 lr 0.003936	time 0.5849 (0.6214)	model_time 0.5847 (0.6017)	loss 4.5137 (3.9977)	grad_norm 0.9686 (1.7254/0.6127)	mem 24308MB
[2025-01-18 13:47:31 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][90/312]	eta 0:02:18 lr 0.003936	time 0.6484 (0.6224)	model_time 0.6482 (0.6049)	loss 4.4228 (4.0169)	grad_norm 1.5939 (1.6981/0.6059)	mem 24308MB
[2025-01-18 13:47:37 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][100/312]	eta 0:02:11 lr 0.003936	time 0.5750 (0.6195)	model_time 0.5746 (0.6036)	loss 3.0114 (4.0378)	grad_norm 1.0948 (1.6688/0.5978)	mem 24308MB
[2025-01-18 13:47:43 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][110/312]	eta 0:02:04 lr 0.003936	time 0.5655 (0.6164)	model_time 0.5653 (0.6019)	loss 4.5629 (4.0426)	grad_norm 1.7520 (1.6577/0.5875)	mem 24308MB
[2025-01-18 13:47:49 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][120/312]	eta 0:01:57 lr 0.003936	time 0.5847 (0.6144)	model_time 0.5845 (0.6011)	loss 3.8020 (4.0530)	grad_norm 3.2546 (1.6986/0.6292)	mem 24308MB
[2025-01-18 13:47:55 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][130/312]	eta 0:01:51 lr 0.003936	time 0.6018 (0.6125)	model_time 0.6016 (0.6002)	loss 4.7545 (4.0516)	grad_norm 1.1352 (1.7221/0.6496)	mem 24308MB
[2025-01-18 13:48:01 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][140/312]	eta 0:01:45 lr 0.003935	time 0.6047 (0.6110)	model_time 0.6043 (0.5996)	loss 4.3949 (4.0615)	grad_norm 1.2300 (1.6924/0.6467)	mem 24308MB
[2025-01-18 13:48:07 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][150/312]	eta 0:01:38 lr 0.003935	time 0.5613 (0.6103)	model_time 0.5609 (0.5996)	loss 4.4416 (4.0713)	grad_norm 1.4523 (1.6730/0.6424)	mem 24308MB
[2025-01-18 13:48:13 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][160/312]	eta 0:01:32 lr 0.003935	time 0.5805 (0.6088)	model_time 0.5803 (0.5987)	loss 4.1974 (4.0803)	grad_norm 2.3579 (1.6906/0.6385)	mem 24308MB
[2025-01-18 13:48:19 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][170/312]	eta 0:01:26 lr 0.003935	time 0.6002 (0.6081)	model_time 0.5997 (0.5985)	loss 4.2878 (4.0837)	grad_norm 1.8971 (1.6883/0.6268)	mem 24308MB
[2025-01-18 13:48:25 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][180/312]	eta 0:01:20 lr 0.003935	time 0.5729 (0.6083)	model_time 0.5725 (0.5993)	loss 4.5467 (4.1081)	grad_norm 1.3623 (1.6764/0.6129)	mem 24308MB
[2025-01-18 13:48:31 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][190/312]	eta 0:01:14 lr 0.003935	time 0.5800 (0.6090)	model_time 0.5795 (0.6004)	loss 4.5467 (4.0942)	grad_norm 1.8468 (1.6620/0.6034)	mem 24308MB
[2025-01-18 13:48:37 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][200/312]	eta 0:01:08 lr 0.003934	time 0.7277 (0.6106)	model_time 0.7273 (0.6024)	loss 4.6204 (4.0977)	grad_norm 1.0026 (1.6624/0.6025)	mem 24308MB
[2025-01-18 13:48:43 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][210/312]	eta 0:01:02 lr 0.003934	time 0.5830 (0.6106)	model_time 0.5826 (0.6028)	loss 4.0541 (4.1065)	grad_norm 1.4596 (1.6635/0.5935)	mem 24308MB
[2025-01-18 13:48:49 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][220/312]	eta 0:00:56 lr 0.003934	time 0.5923 (0.6102)	model_time 0.5919 (0.6027)	loss 4.3082 (4.1193)	grad_norm 1.0533 (1.6510/0.5857)	mem 24308MB
[2025-01-18 13:48:55 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][230/312]	eta 0:00:49 lr 0.003934	time 0.5632 (0.6089)	model_time 0.5630 (0.6017)	loss 2.9517 (4.1022)	grad_norm 2.3731 (1.6544/0.5813)	mem 24308MB
[2025-01-18 13:49:01 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][240/312]	eta 0:00:43 lr 0.003934	time 0.6008 (0.6083)	model_time 0.6006 (0.6014)	loss 3.8742 (4.0882)	grad_norm 2.2969 (1.6865/0.6113)	mem 24308MB
[2025-01-18 13:49:07 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][250/312]	eta 0:00:37 lr 0.003934	time 0.5725 (0.6073)	model_time 0.5724 (0.6006)	loss 4.6413 (4.0895)	grad_norm 1.9412 (1.6702/0.6082)	mem 24308MB
[2025-01-18 13:49:13 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][260/312]	eta 0:00:31 lr 0.003933	time 0.5817 (0.6066)	model_time 0.5816 (0.6002)	loss 3.8015 (4.0876)	grad_norm 2.2186 (1.6735/0.6067)	mem 24308MB
[2025-01-18 13:49:19 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][270/312]	eta 0:00:25 lr 0.003933	time 0.5818 (0.6059)	model_time 0.5817 (0.5997)	loss 4.3618 (4.0850)	grad_norm 2.5745 (1.6889/0.6106)	mem 24308MB
[2025-01-18 13:49:25 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][280/312]	eta 0:00:19 lr 0.003933	time 0.5778 (0.6054)	model_time 0.5776 (0.5994)	loss 3.7697 (4.0831)	grad_norm 1.3185 (1.6810/0.6091)	mem 24308MB
[2025-01-18 13:49:31 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][290/312]	eta 0:00:13 lr 0.003933	time 0.5879 (0.6050)	model_time 0.5875 (0.5992)	loss 3.5305 (4.0825)	grad_norm 2.4926 (1.6835/0.6063)	mem 24308MB
[2025-01-18 13:49:37 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][300/312]	eta 0:00:07 lr 0.003933	time 0.6432 (0.6049)	model_time 0.6431 (0.5993)	loss 4.7432 (4.0870)	grad_norm 1.5046 (1.6937/0.6226)	mem 24308MB
[2025-01-18 13:49:43 internimage_s_1k_224] (main.py 510): INFO Train: [24/300][310/312]	eta 0:00:01 lr 0.003933	time 0.6713 (0.6047)	model_time 0.6712 (0.5993)	loss 2.8364 (4.0889)	grad_norm 1.8041 (1.6917/0.6227)	mem 24308MB
[2025-01-18 13:49:43 internimage_s_1k_224] (main.py 519): INFO EPOCH 24 training takes 0:03:08
[2025-01-18 13:49:43 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_24.pth saving......
[2025-01-18 13:49:45 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_24.pth saved !!!
[2025-01-18 13:49:52 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.314 (7.314)	Loss 1.3368 (1.3368)	Acc@1 71.802 (71.802)	Acc@5 90.820 (90.820)	Mem 24308MB
[2025-01-18 13:49:56 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.960)	Loss 1.8553 (1.5425)	Acc@1 60.840 (67.097)	Acc@5 83.618 (88.317)	Mem 24308MB
[2025-01-18 13:49:56 internimage_s_1k_224] (main.py 575): INFO [Epoch:24] * Acc@1 67.188 Acc@5 88.422
[2025-01-18 13:49:56 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 67.2%
[2025-01-18 13:49:56 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 13:49:58 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 13:49:58 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 67.19%
[2025-01-18 13:50:05 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.000 (7.000)	Loss 6.6748 (6.6748)	Acc@1 1.782 (1.782)	Acc@5 6.519 (6.519)	Mem 24308MB
[2025-01-18 13:50:08 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.134 (0.914)	Loss 7.1379 (6.7992)	Acc@1 0.146 (0.854)	Acc@5 0.952 (3.103)	Mem 24308MB
[2025-01-18 13:50:08 internimage_s_1k_224] (main.py 575): INFO [Epoch:24] * Acc@1 1.212 Acc@5 3.949
[2025-01-18 13:50:08 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 1.2%
[2025-01-18 13:50:08 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 13:50:10 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 13:50:10 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 1.21%
[2025-01-18 13:50:13 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][0/312]	eta 0:11:47 lr 0.003933	time 2.2661 (2.2661)	model_time 0.5922 (0.5922)	loss 4.9179 (4.9179)	grad_norm 1.0801 (1.0801/0.0000)	mem 24308MB
[2025-01-18 13:50:19 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][10/312]	eta 0:03:56 lr 0.003932	time 0.5707 (0.7843)	model_time 0.5706 (0.6319)	loss 4.3038 (4.2573)	grad_norm 1.3786 (1.7460/0.4535)	mem 24308MB
[2025-01-18 13:50:25 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][20/312]	eta 0:03:26 lr 0.003932	time 0.5799 (0.7077)	model_time 0.5795 (0.6277)	loss 4.3386 (4.2470)	grad_norm 1.8530 (1.8222/0.5744)	mem 24308MB
[2025-01-18 13:50:31 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][30/312]	eta 0:03:10 lr 0.003932	time 0.5860 (0.6745)	model_time 0.5856 (0.6202)	loss 3.5109 (4.1427)	grad_norm 1.7915 (1.6720/0.5430)	mem 24308MB
[2025-01-18 13:50:37 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][40/312]	eta 0:02:57 lr 0.003932	time 0.5694 (0.6529)	model_time 0.5692 (0.6118)	loss 5.0015 (4.1462)	grad_norm 1.4469 (1.6674/0.6236)	mem 24308MB
[2025-01-18 13:50:43 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][50/312]	eta 0:02:47 lr 0.003932	time 0.5803 (0.6402)	model_time 0.5802 (0.6071)	loss 3.2197 (4.1802)	grad_norm 1.7613 (1.7551/0.8056)	mem 24308MB
[2025-01-18 13:50:49 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][60/312]	eta 0:02:39 lr 0.003931	time 0.5806 (0.6312)	model_time 0.5804 (0.6034)	loss 3.7056 (4.1489)	grad_norm 1.6234 (1.7029/0.7769)	mem 24308MB
[2025-01-18 13:50:55 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][70/312]	eta 0:02:31 lr 0.003931	time 0.5931 (0.6250)	model_time 0.5929 (0.6011)	loss 4.3184 (4.1847)	grad_norm 2.6520 (1.7518/0.8371)	mem 24308MB
[2025-01-18 13:51:01 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][80/312]	eta 0:02:24 lr 0.003931	time 0.5800 (0.6210)	model_time 0.5798 (0.6000)	loss 4.0731 (4.1727)	grad_norm 0.9681 (1.7227/0.8088)	mem 24308MB
[2025-01-18 13:51:06 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][90/312]	eta 0:02:16 lr 0.003931	time 0.5758 (0.6171)	model_time 0.5756 (0.5984)	loss 4.2114 (4.1656)	grad_norm 1.9471 (1.7196/0.7746)	mem 24308MB
[2025-01-18 13:51:12 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][100/312]	eta 0:02:10 lr 0.003931	time 0.5801 (0.6147)	model_time 0.5799 (0.5978)	loss 4.2439 (4.1714)	grad_norm 1.3327 (1.6900/0.7489)	mem 24308MB
[2025-01-18 13:51:18 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][110/312]	eta 0:02:04 lr 0.003931	time 0.6601 (0.6146)	model_time 0.6596 (0.5992)	loss 4.1188 (4.1870)	grad_norm 2.1911 (1.7173/0.7651)	mem 24308MB
[2025-01-18 13:51:25 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][120/312]	eta 0:01:58 lr 0.003930	time 0.6712 (0.6150)	model_time 0.6707 (0.6008)	loss 3.5545 (4.1508)	grad_norm 2.1023 (1.6902/0.7521)	mem 24308MB
[2025-01-18 13:51:31 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][130/312]	eta 0:01:52 lr 0.003930	time 0.6683 (0.6166)	model_time 0.6682 (0.6035)	loss 4.1928 (4.1519)	grad_norm 1.2388 (1.7133/0.7810)	mem 24308MB
[2025-01-18 13:51:37 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][140/312]	eta 0:01:46 lr 0.003930	time 0.5804 (0.6187)	model_time 0.5803 (0.6065)	loss 4.8621 (4.1594)	grad_norm 2.0615 (1.7356/0.7993)	mem 24308MB
[2025-01-18 13:51:43 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][150/312]	eta 0:01:39 lr 0.003930	time 0.5900 (0.6173)	model_time 0.5898 (0.6058)	loss 3.8058 (4.1636)	grad_norm 1.5537 (1.6968/0.7882)	mem 24308MB
[2025-01-18 13:51:49 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][160/312]	eta 0:01:33 lr 0.003930	time 0.5861 (0.6151)	model_time 0.5859 (0.6044)	loss 4.2716 (4.1515)	grad_norm 1.4000 (1.7081/0.8016)	mem 24308MB
[2025-01-18 13:51:55 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][170/312]	eta 0:01:27 lr 0.003930	time 0.5866 (0.6133)	model_time 0.5864 (0.6031)	loss 3.2142 (4.1249)	grad_norm 1.0546 (1.6896/0.7852)	mem 24308MB
[2025-01-18 13:52:01 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][180/312]	eta 0:01:20 lr 0.003929	time 0.5980 (0.6116)	model_time 0.5976 (0.6020)	loss 4.3515 (4.1198)	grad_norm 1.1508 (1.6699/0.7722)	mem 24308MB
[2025-01-18 13:52:07 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][190/312]	eta 0:01:14 lr 0.003929	time 0.5934 (0.6101)	model_time 0.5932 (0.6009)	loss 2.8193 (4.1152)	grad_norm 0.9766 (1.6513/0.7609)	mem 24308MB
[2025-01-18 13:52:13 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][200/312]	eta 0:01:08 lr 0.003929	time 0.5800 (0.6091)	model_time 0.5796 (0.6004)	loss 4.4008 (4.1129)	grad_norm 1.6699 (1.6536/0.7517)	mem 24308MB
[2025-01-18 13:52:19 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][210/312]	eta 0:01:02 lr 0.003929	time 0.5836 (0.6079)	model_time 0.5832 (0.5996)	loss 4.1744 (4.1068)	grad_norm 1.7092 (1.6840/0.7766)	mem 24308MB
[2025-01-18 13:52:24 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][220/312]	eta 0:00:55 lr 0.003929	time 0.5795 (0.6072)	model_time 0.5791 (0.5992)	loss 3.3526 (4.1092)	grad_norm 1.1775 (1.6760/0.7670)	mem 24308MB
[2025-01-18 13:52:30 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][230/312]	eta 0:00:49 lr 0.003929	time 0.6561 (0.6068)	model_time 0.6560 (0.5992)	loss 3.3552 (4.0976)	grad_norm 0.6509 (1.6592/0.7613)	mem 24308MB
[2025-01-18 13:52:37 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][240/312]	eta 0:00:43 lr 0.003928	time 0.6703 (0.6083)	model_time 0.6701 (0.6010)	loss 3.8211 (4.0971)	grad_norm 1.0811 (1.6457/0.7499)	mem 24308MB
[2025-01-18 13:52:43 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][250/312]	eta 0:00:37 lr 0.003928	time 0.6793 (0.6097)	model_time 0.6791 (0.6027)	loss 3.8530 (4.0814)	grad_norm 1.5916 (1.6537/0.7539)	mem 24308MB
[2025-01-18 13:52:50 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][260/312]	eta 0:00:31 lr 0.003928	time 0.5753 (0.6107)	model_time 0.5751 (0.6039)	loss 4.2063 (4.0791)	grad_norm 2.3795 (1.6698/0.7625)	mem 24308MB
[2025-01-18 13:52:56 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][270/312]	eta 0:00:25 lr 0.003928	time 0.5908 (0.6104)	model_time 0.5903 (0.6039)	loss 4.8082 (4.0885)	grad_norm 1.3703 (1.6646/0.7606)	mem 24308MB
[2025-01-18 13:53:02 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][280/312]	eta 0:00:19 lr 0.003928	time 0.5799 (0.6095)	model_time 0.5798 (0.6032)	loss 4.0933 (4.0891)	grad_norm 1.9076 (1.6661/0.7512)	mem 24308MB
[2025-01-18 13:53:07 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][290/312]	eta 0:00:13 lr 0.003927	time 0.5633 (0.6086)	model_time 0.5632 (0.6025)	loss 5.2718 (4.0971)	grad_norm 1.6655 (1.6666/0.7477)	mem 24308MB
[2025-01-18 13:53:13 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][300/312]	eta 0:00:07 lr 0.003927	time 0.5675 (0.6077)	model_time 0.5674 (0.6017)	loss 4.5377 (4.0994)	grad_norm 1.3049 (1.6555/0.7407)	mem 24308MB
[2025-01-18 13:53:19 internimage_s_1k_224] (main.py 510): INFO Train: [25/300][310/312]	eta 0:00:01 lr 0.003927	time 0.5715 (0.6066)	model_time 0.5714 (0.6009)	loss 3.5766 (4.0948)	grad_norm 3.0259 (1.6556/0.7455)	mem 24308MB
[2025-01-18 13:53:19 internimage_s_1k_224] (main.py 519): INFO EPOCH 25 training takes 0:03:09
[2025-01-18 13:53:19 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_25.pth saving......
[2025-01-18 13:53:21 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_25.pth saved !!!
[2025-01-18 13:53:28 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.059 (7.059)	Loss 1.2130 (1.2130)	Acc@1 72.632 (72.632)	Acc@5 91.968 (91.968)	Mem 24308MB
[2025-01-18 13:53:31 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.915)	Loss 1.7949 (1.4877)	Acc@1 60.571 (67.283)	Acc@5 83.789 (88.634)	Mem 24308MB
[2025-01-18 13:53:32 internimage_s_1k_224] (main.py 575): INFO [Epoch:25] * Acc@1 67.430 Acc@5 88.764
[2025-01-18 13:53:32 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 67.4%
[2025-01-18 13:53:32 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 13:53:33 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 13:53:33 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 67.43%
[2025-01-18 13:53:41 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.161 (7.161)	Loss 6.6841 (6.6841)	Acc@1 1.660 (1.660)	Acc@5 6.592 (6.592)	Mem 24308MB
[2025-01-18 13:53:44 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.941)	Loss 7.1664 (6.8105)	Acc@1 0.098 (0.841)	Acc@5 0.684 (3.220)	Mem 24308MB
[2025-01-18 13:53:44 internimage_s_1k_224] (main.py 575): INFO [Epoch:25] * Acc@1 1.220 Acc@5 4.111
[2025-01-18 13:53:44 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 1.2%
[2025-01-18 13:53:44 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 13:53:46 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 13:53:46 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 1.22%
[2025-01-18 13:53:48 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][0/312]	eta 0:11:44 lr 0.003927	time 2.2569 (2.2569)	model_time 0.5940 (0.5940)	loss 4.5289 (4.5289)	grad_norm 3.5525 (3.5525/0.0000)	mem 24308MB
[2025-01-18 13:53:54 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][10/312]	eta 0:03:44 lr 0.003927	time 0.5767 (0.7443)	model_time 0.5766 (0.5929)	loss 4.1574 (4.0894)	grad_norm 1.3413 (1.7328/0.7250)	mem 24308MB
[2025-01-18 13:54:00 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][20/312]	eta 0:03:15 lr 0.003927	time 0.5621 (0.6687)	model_time 0.5619 (0.5893)	loss 3.2912 (4.0596)	grad_norm 2.2191 (1.6512/0.6734)	mem 24308MB
[2025-01-18 13:54:06 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][30/312]	eta 0:03:01 lr 0.003927	time 0.5822 (0.6441)	model_time 0.5820 (0.5902)	loss 3.9920 (4.0790)	grad_norm 1.0338 (1.6799/0.6235)	mem 24308MB
[2025-01-18 13:54:12 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][40/312]	eta 0:02:52 lr 0.003926	time 0.5834 (0.6334)	model_time 0.5833 (0.5925)	loss 3.0555 (4.0446)	grad_norm 0.9158 (1.6479/0.6090)	mem 24308MB
[2025-01-18 13:54:19 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][50/312]	eta 0:02:47 lr 0.003926	time 0.6857 (0.6392)	model_time 0.6856 (0.6063)	loss 2.7097 (4.0292)	grad_norm 2.0066 (1.6762/0.6044)	mem 24308MB
[2025-01-18 13:54:25 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][60/312]	eta 0:02:40 lr 0.003926	time 0.6793 (0.6384)	model_time 0.6791 (0.6109)	loss 3.0507 (4.0532)	grad_norm 1.6494 (1.7130/0.6161)	mem 24308MB
[2025-01-18 13:54:31 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][70/312]	eta 0:02:33 lr 0.003926	time 0.5857 (0.6352)	model_time 0.5852 (0.6115)	loss 3.3119 (4.0661)	grad_norm 1.4903 (1.6716/0.5925)	mem 24308MB
[2025-01-18 13:54:37 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][80/312]	eta 0:02:26 lr 0.003926	time 0.5801 (0.6310)	model_time 0.5799 (0.6101)	loss 4.2628 (4.0634)	grad_norm 1.5648 (1.6652/0.5709)	mem 24308MB
[2025-01-18 13:54:43 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][90/312]	eta 0:02:18 lr 0.003925	time 0.5738 (0.6260)	model_time 0.5736 (0.6074)	loss 4.3512 (4.0642)	grad_norm 1.8080 (1.7032/0.6013)	mem 24308MB
[2025-01-18 13:54:49 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][100/312]	eta 0:02:11 lr 0.003925	time 0.5735 (0.6220)	model_time 0.5731 (0.6052)	loss 2.9487 (4.0708)	grad_norm 0.9824 (1.6719/0.6021)	mem 24308MB
[2025-01-18 13:54:55 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][110/312]	eta 0:02:05 lr 0.003925	time 0.5861 (0.6188)	model_time 0.5859 (0.6035)	loss 3.8819 (4.0677)	grad_norm 2.4676 (1.6895/0.6295)	mem 24308MB
[2025-01-18 13:55:00 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][120/312]	eta 0:01:58 lr 0.003925	time 0.5916 (0.6157)	model_time 0.5911 (0.6017)	loss 3.5240 (4.0424)	grad_norm 1.3014 (1.6935/0.6181)	mem 24308MB
[2025-01-18 13:55:06 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][130/312]	eta 0:01:51 lr 0.003925	time 0.6900 (0.6140)	model_time 0.6898 (0.6009)	loss 2.9155 (4.0423)	grad_norm 0.9014 (1.6776/0.6079)	mem 24308MB
[2025-01-18 13:55:12 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][140/312]	eta 0:01:45 lr 0.003925	time 0.5833 (0.6116)	model_time 0.5829 (0.5995)	loss 4.8627 (4.0457)	grad_norm 2.4879 (1.6670/0.6085)	mem 24308MB
[2025-01-18 13:55:18 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][150/312]	eta 0:01:38 lr 0.003924	time 0.5838 (0.6106)	model_time 0.5833 (0.5992)	loss 4.4977 (4.0667)	grad_norm 1.8870 (1.6530/0.6039)	mem 24308MB
[2025-01-18 13:55:24 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][160/312]	eta 0:01:32 lr 0.003924	time 0.5803 (0.6092)	model_time 0.5802 (0.5985)	loss 4.4227 (4.0824)	grad_norm 1.0864 (1.6354/0.5950)	mem 24308MB
[2025-01-18 13:55:31 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][170/312]	eta 0:01:26 lr 0.003924	time 0.6804 (0.6125)	model_time 0.6802 (0.6024)	loss 4.3855 (4.0876)	grad_norm 1.9269 (1.6631/0.6023)	mem 24308MB
[2025-01-18 13:55:37 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][180/312]	eta 0:01:20 lr 0.003924	time 0.6675 (0.6128)	model_time 0.6671 (0.6033)	loss 4.8510 (4.1008)	grad_norm 1.5773 (1.6475/0.5933)	mem 24308MB
[2025-01-18 13:55:43 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][190/312]	eta 0:01:14 lr 0.003924	time 0.5684 (0.6126)	model_time 0.5683 (0.6036)	loss 3.4288 (4.0911)	grad_norm 1.6487 (1.6653/0.5973)	mem 24308MB
[2025-01-18 13:55:49 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][200/312]	eta 0:01:08 lr 0.003923	time 0.5958 (0.6122)	model_time 0.5954 (0.6035)	loss 4.0991 (4.0857)	grad_norm 2.1751 (1.6757/0.6018)	mem 24308MB
[2025-01-18 13:55:55 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][210/312]	eta 0:01:02 lr 0.003923	time 0.5833 (0.6108)	model_time 0.5829 (0.6026)	loss 5.1297 (4.0871)	grad_norm 1.7987 (1.6945/0.6181)	mem 24308MB
[2025-01-18 13:56:01 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][220/312]	eta 0:00:56 lr 0.003923	time 0.5792 (0.6097)	model_time 0.5790 (0.6018)	loss 3.8803 (4.0790)	grad_norm 0.7189 (1.6744/0.6168)	mem 24308MB
[2025-01-18 13:56:07 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][230/312]	eta 0:00:49 lr 0.003923	time 0.5732 (0.6088)	model_time 0.5730 (0.6012)	loss 4.8646 (4.0856)	grad_norm 1.6112 (1.6533/0.6179)	mem 24308MB
[2025-01-18 13:56:12 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][240/312]	eta 0:00:43 lr 0.003923	time 0.5790 (0.6078)	model_time 0.5788 (0.6005)	loss 4.5494 (4.0812)	grad_norm 1.5538 (1.6696/0.6371)	mem 24308MB
[2025-01-18 13:56:18 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][250/312]	eta 0:00:37 lr 0.003923	time 0.6781 (0.6074)	model_time 0.6779 (0.6004)	loss 4.9633 (4.0908)	grad_norm 1.4140 (1.6639/0.6355)	mem 24308MB
[2025-01-18 13:56:24 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][260/312]	eta 0:00:31 lr 0.003922	time 0.5815 (0.6063)	model_time 0.5813 (0.5995)	loss 4.3126 (4.0852)	grad_norm 1.4912 (1.6673/0.6366)	mem 24308MB
[2025-01-18 13:56:30 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][270/312]	eta 0:00:25 lr 0.003922	time 0.5979 (0.6061)	model_time 0.5974 (0.5996)	loss 4.0397 (4.0870)	grad_norm 1.8582 (1.6535/0.6320)	mem 24308MB
[2025-01-18 13:56:36 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][280/312]	eta 0:00:19 lr 0.003922	time 0.5970 (0.6057)	model_time 0.5968 (0.5994)	loss 3.7550 (4.0920)	grad_norm 1.3752 (1.6646/0.6417)	mem 24308MB
[2025-01-18 13:56:42 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][290/312]	eta 0:00:13 lr 0.003922	time 0.7440 (0.6067)	model_time 0.7438 (0.6006)	loss 5.1317 (4.0949)	grad_norm 2.0922 (1.6844/0.6583)	mem 24308MB
[2025-01-18 13:56:49 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][300/312]	eta 0:00:07 lr 0.003922	time 0.5657 (0.6071)	model_time 0.5656 (0.6012)	loss 3.4574 (4.0930)	grad_norm 1.9058 (1.6750/0.6555)	mem 24308MB
[2025-01-18 13:56:55 internimage_s_1k_224] (main.py 510): INFO Train: [26/300][310/312]	eta 0:00:01 lr 0.003921	time 0.5698 (0.6084)	model_time 0.5697 (0.6027)	loss 4.1930 (4.0825)	grad_norm 1.3413 (1.6858/0.6605)	mem 24308MB
[2025-01-18 13:56:56 internimage_s_1k_224] (main.py 519): INFO EPOCH 26 training takes 0:03:09
[2025-01-18 13:56:56 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_26.pth saving......
[2025-01-18 13:56:58 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_26.pth saved !!!
[2025-01-18 13:57:05 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.849 (6.849)	Loss 1.1972 (1.1972)	Acc@1 72.705 (72.705)	Acc@5 91.821 (91.821)	Mem 24308MB
[2025-01-18 13:57:08 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.922)	Loss 1.7009 (1.4199)	Acc@1 61.768 (67.982)	Acc@5 84.863 (88.807)	Mem 24308MB
[2025-01-18 13:57:08 internimage_s_1k_224] (main.py 575): INFO [Epoch:26] * Acc@1 68.038 Acc@5 88.950
[2025-01-18 13:57:08 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 68.0%
[2025-01-18 13:57:08 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 13:57:10 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 13:57:10 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 68.04%
[2025-01-18 13:57:17 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.067 (7.067)	Loss 6.6903 (6.6903)	Acc@1 1.562 (1.562)	Acc@5 6.738 (6.738)	Mem 24308MB
[2025-01-18 13:57:20 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.917)	Loss 7.1811 (6.8122)	Acc@1 0.073 (0.874)	Acc@5 0.562 (3.389)	Mem 24308MB
[2025-01-18 13:57:20 internimage_s_1k_224] (main.py 575): INFO [Epoch:26] * Acc@1 1.280 Acc@5 4.313
[2025-01-18 13:57:20 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 1.3%
[2025-01-18 13:57:20 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 13:57:22 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 13:57:22 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 1.28%
[2025-01-18 13:57:24 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][0/312]	eta 0:11:43 lr 0.003921	time 2.2545 (2.2545)	model_time 0.5980 (0.5980)	loss 3.9325 (3.9325)	grad_norm 1.4487 (1.4487/0.0000)	mem 24308MB
[2025-01-18 13:57:30 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][10/312]	eta 0:03:46 lr 0.003921	time 0.6058 (0.7488)	model_time 0.6056 (0.5979)	loss 3.3723 (3.8121)	grad_norm 1.4982 (1.2976/0.3016)	mem 24308MB
[2025-01-18 13:57:36 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][20/312]	eta 0:03:16 lr 0.003921	time 0.6016 (0.6715)	model_time 0.6014 (0.5923)	loss 4.4314 (4.0489)	grad_norm 1.4313 (1.2729/0.2830)	mem 24308MB
[2025-01-18 13:57:42 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][30/312]	eta 0:03:01 lr 0.003921	time 0.5753 (0.6429)	model_time 0.5752 (0.5892)	loss 4.1768 (4.1230)	grad_norm 2.3523 (1.3935/0.3886)	mem 24308MB
[2025-01-18 13:57:48 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][40/312]	eta 0:02:51 lr 0.003921	time 0.5754 (0.6298)	model_time 0.5752 (0.5891)	loss 3.5452 (4.1397)	grad_norm 1.8349 (1.4495/0.4057)	mem 24308MB
[2025-01-18 13:57:54 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][50/312]	eta 0:02:42 lr 0.003920	time 0.5909 (0.6210)	model_time 0.5908 (0.5882)	loss 4.9009 (4.0745)	grad_norm 3.5061 (1.5204/0.5183)	mem 24308MB
[2025-01-18 13:58:00 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][60/312]	eta 0:02:35 lr 0.003920	time 0.5842 (0.6152)	model_time 0.5837 (0.5877)	loss 3.6157 (4.0360)	grad_norm 1.1061 (1.5096/0.5101)	mem 24308MB
[2025-01-18 13:58:06 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][70/312]	eta 0:02:27 lr 0.003920	time 0.5829 (0.6112)	model_time 0.5827 (0.5875)	loss 4.4874 (4.0988)	grad_norm 1.4980 (1.6054/0.6398)	mem 24308MB
[2025-01-18 13:58:12 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][80/312]	eta 0:02:21 lr 0.003920	time 0.5750 (0.6104)	model_time 0.5748 (0.5896)	loss 4.3479 (4.1140)	grad_norm 2.2758 (1.6075/0.6199)	mem 24308MB
[2025-01-18 13:58:18 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][90/312]	eta 0:02:15 lr 0.003920	time 0.5775 (0.6091)	model_time 0.5773 (0.5906)	loss 3.4890 (4.1234)	grad_norm 2.0847 (1.6164/0.6177)	mem 24308MB
[2025-01-18 13:58:24 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][100/312]	eta 0:02:09 lr 0.003920	time 0.5749 (0.6101)	model_time 0.5745 (0.5933)	loss 4.4146 (4.1189)	grad_norm 1.1937 (1.5790/0.6040)	mem 24308MB
[2025-01-18 13:58:30 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][110/312]	eta 0:02:03 lr 0.003919	time 0.5913 (0.6112)	model_time 0.5910 (0.5960)	loss 3.6979 (4.1170)	grad_norm 2.5999 (1.5801/0.5935)	mem 24308MB
[2025-01-18 13:58:37 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][120/312]	eta 0:01:58 lr 0.003919	time 0.5752 (0.6147)	model_time 0.5748 (0.6007)	loss 3.4158 (4.1320)	grad_norm 1.9107 (1.5924/0.6076)	mem 24308MB
[2025-01-18 13:58:43 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][130/312]	eta 0:01:51 lr 0.003919	time 0.6015 (0.6142)	model_time 0.6013 (0.6012)	loss 3.4440 (4.1477)	grad_norm 1.8746 (1.5876/0.5980)	mem 24308MB
[2025-01-18 13:58:49 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][140/312]	eta 0:01:45 lr 0.003919	time 0.5888 (0.6125)	model_time 0.5884 (0.6004)	loss 4.3583 (4.1483)	grad_norm 0.9470 (1.5950/0.6081)	mem 24308MB
[2025-01-18 13:58:54 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][150/312]	eta 0:01:38 lr 0.003919	time 0.5891 (0.6107)	model_time 0.5888 (0.5994)	loss 4.6642 (4.1417)	grad_norm 1.9625 (1.5911/0.5947)	mem 24308MB
[2025-01-18 13:59:00 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][160/312]	eta 0:01:32 lr 0.003918	time 0.5850 (0.6089)	model_time 0.5845 (0.5983)	loss 2.9475 (4.1197)	grad_norm 2.1459 (1.5991/0.5893)	mem 24308MB
[2025-01-18 13:59:06 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][170/312]	eta 0:01:26 lr 0.003918	time 0.5801 (0.6078)	model_time 0.5796 (0.5977)	loss 4.7994 (4.1398)	grad_norm 1.8516 (1.6038/0.5988)	mem 24308MB
[2025-01-18 13:59:12 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][180/312]	eta 0:01:20 lr 0.003918	time 0.5827 (0.6065)	model_time 0.5826 (0.5969)	loss 4.8212 (4.1478)	grad_norm 1.0321 (1.6068/0.6024)	mem 24308MB
[2025-01-18 13:59:18 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][190/312]	eta 0:01:13 lr 0.003918	time 0.6010 (0.6057)	model_time 0.6008 (0.5966)	loss 4.1571 (4.1416)	grad_norm 0.9613 (1.6031/0.6106)	mem 24308MB
[2025-01-18 13:59:24 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][200/312]	eta 0:01:07 lr 0.003918	time 0.5892 (0.6054)	model_time 0.5890 (0.5968)	loss 3.2304 (4.1425)	grad_norm 1.6646 (1.5993/0.6052)	mem 24308MB
[2025-01-18 13:59:30 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][210/312]	eta 0:01:01 lr 0.003917	time 0.5736 (0.6054)	model_time 0.5731 (0.5972)	loss 3.0603 (4.1296)	grad_norm 1.6898 (1.6011/0.5979)	mem 24308MB
[2025-01-18 13:59:36 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][220/312]	eta 0:00:55 lr 0.003917	time 0.5753 (0.6068)	model_time 0.5751 (0.5989)	loss 4.0893 (4.1337)	grad_norm 1.9858 (1.5915/0.5935)	mem 24308MB
[2025-01-18 13:59:43 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][230/312]	eta 0:00:49 lr 0.003917	time 0.5656 (0.6076)	model_time 0.5654 (0.6001)	loss 4.4391 (4.1326)	grad_norm 1.1873 (1.6054/0.6110)	mem 24308MB
[2025-01-18 13:59:49 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][240/312]	eta 0:00:43 lr 0.003917	time 0.5803 (0.6081)	model_time 0.5798 (0.6009)	loss 3.0691 (4.1179)	grad_norm 2.5375 (1.6086/0.6177)	mem 24308MB
[2025-01-18 13:59:55 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][250/312]	eta 0:00:37 lr 0.003917	time 0.5881 (0.6088)	model_time 0.5880 (0.6018)	loss 4.1338 (4.1154)	grad_norm 1.5137 (1.6172/0.6147)	mem 24308MB
[2025-01-18 14:00:01 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][260/312]	eta 0:00:31 lr 0.003916	time 0.5900 (0.6080)	model_time 0.5895 (0.6013)	loss 3.2986 (4.1007)	grad_norm 1.8657 (1.6080/0.6072)	mem 24308MB
[2025-01-18 14:00:07 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][270/312]	eta 0:00:25 lr 0.003916	time 0.6016 (0.6072)	model_time 0.6011 (0.6008)	loss 3.6085 (4.0969)	grad_norm 0.9328 (1.6079/0.6105)	mem 24308MB
[2025-01-18 14:00:13 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][280/312]	eta 0:00:19 lr 0.003916	time 0.5864 (0.6065)	model_time 0.5862 (0.6002)	loss 4.1458 (4.1010)	grad_norm 4.8941 (1.6209/0.6432)	mem 24308MB
[2025-01-18 14:00:19 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][290/312]	eta 0:00:13 lr 0.003916	time 0.6237 (0.6059)	model_time 0.6236 (0.5998)	loss 3.9219 (4.0930)	grad_norm 2.0160 (1.6386/0.6725)	mem 24308MB
[2025-01-18 14:00:24 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][300/312]	eta 0:00:07 lr 0.003916	time 0.5647 (0.6049)	model_time 0.5646 (0.5991)	loss 4.5286 (4.0941)	grad_norm 1.1217 (1.6332/0.6690)	mem 24308MB
[2025-01-18 14:00:30 internimage_s_1k_224] (main.py 510): INFO Train: [27/300][310/312]	eta 0:00:01 lr 0.003916	time 0.5689 (0.6039)	model_time 0.5687 (0.5983)	loss 3.5434 (4.0952)	grad_norm 1.2406 (1.6392/0.6675)	mem 24308MB
[2025-01-18 14:00:31 internimage_s_1k_224] (main.py 519): INFO EPOCH 27 training takes 0:03:08
[2025-01-18 14:00:31 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_27.pth saving......
[2025-01-18 14:00:32 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_27.pth saved !!!
[2025-01-18 14:00:40 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.476 (7.476)	Loss 1.2090 (1.2090)	Acc@1 73.633 (73.633)	Acc@5 92.700 (92.700)	Mem 24308MB
[2025-01-18 14:00:43 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.973)	Loss 1.7362 (1.4559)	Acc@1 63.184 (68.384)	Acc@5 85.352 (89.165)	Mem 24308MB
[2025-01-18 14:00:43 internimage_s_1k_224] (main.py 575): INFO [Epoch:27] * Acc@1 68.476 Acc@5 89.239
[2025-01-18 14:00:43 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 68.5%
[2025-01-18 14:00:43 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 14:00:45 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 14:00:45 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 68.48%
[2025-01-18 14:00:53 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.306 (7.306)	Loss 6.6762 (6.6762)	Acc@1 1.733 (1.733)	Acc@5 7.031 (7.031)	Mem 24308MB
[2025-01-18 14:00:56 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.964)	Loss 7.1790 (6.7979)	Acc@1 0.073 (0.979)	Acc@5 0.635 (3.680)	Mem 24308MB
[2025-01-18 14:00:56 internimage_s_1k_224] (main.py 575): INFO [Epoch:27] * Acc@1 1.392 Acc@5 4.665
[2025-01-18 14:00:56 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 1.4%
[2025-01-18 14:00:56 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 14:00:58 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 14:00:58 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 1.39%
[2025-01-18 14:01:00 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][0/312]	eta 0:11:29 lr 0.003915	time 2.2095 (2.2095)	model_time 0.6041 (0.6041)	loss 5.0773 (5.0773)	grad_norm 1.2699 (1.2699/0.0000)	mem 24308MB
[2025-01-18 14:01:06 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][10/312]	eta 0:03:47 lr 0.003915	time 0.5828 (0.7521)	model_time 0.5824 (0.6058)	loss 4.4937 (4.2740)	grad_norm 3.3519 (1.6924/0.6502)	mem 24308MB
[2025-01-18 14:01:12 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][20/312]	eta 0:03:18 lr 0.003915	time 0.5755 (0.6782)	model_time 0.5753 (0.6014)	loss 4.3137 (4.2646)	grad_norm 1.0545 (1.6672/0.7252)	mem 24308MB
[2025-01-18 14:01:19 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][30/312]	eta 0:03:07 lr 0.003915	time 0.6794 (0.6645)	model_time 0.6792 (0.6123)	loss 4.9343 (4.2288)	grad_norm 1.4233 (1.6985/0.6696)	mem 24308MB
[2025-01-18 14:01:25 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][40/312]	eta 0:03:00 lr 0.003915	time 0.8676 (0.6619)	model_time 0.8671 (0.6224)	loss 3.6905 (4.2037)	grad_norm 1.3717 (1.7135/0.6633)	mem 24308MB
[2025-01-18 14:01:32 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][50/312]	eta 0:02:51 lr 0.003915	time 0.5758 (0.6560)	model_time 0.5757 (0.6242)	loss 4.9494 (4.1755)	grad_norm 2.2094 (1.7689/0.6958)	mem 24308MB
[2025-01-18 14:01:38 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][60/312]	eta 0:02:43 lr 0.003914	time 0.5822 (0.6497)	model_time 0.5820 (0.6230)	loss 3.3777 (4.1715)	grad_norm 2.7155 (1.8467/0.7173)	mem 24308MB
[2025-01-18 14:01:44 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][70/312]	eta 0:02:35 lr 0.003914	time 0.5869 (0.6407)	model_time 0.5868 (0.6177)	loss 3.7641 (4.1356)	grad_norm 1.2968 (1.8087/0.7026)	mem 24308MB
[2025-01-18 14:01:49 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][80/312]	eta 0:02:27 lr 0.003914	time 0.6022 (0.6339)	model_time 0.6020 (0.6137)	loss 4.5359 (4.1325)	grad_norm 0.8287 (1.7515/0.6898)	mem 24308MB
[2025-01-18 14:01:55 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][90/312]	eta 0:02:19 lr 0.003914	time 0.5786 (0.6290)	model_time 0.5782 (0.6110)	loss 4.1731 (4.1305)	grad_norm 1.5727 (1.7544/0.6928)	mem 24308MB
[2025-01-18 14:02:01 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][100/312]	eta 0:02:12 lr 0.003914	time 0.5754 (0.6246)	model_time 0.5753 (0.6084)	loss 4.6347 (4.1277)	grad_norm 1.5848 (1.7681/0.7182)	mem 24308MB
[2025-01-18 14:02:07 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][110/312]	eta 0:02:05 lr 0.003913	time 0.5702 (0.6212)	model_time 0.5697 (0.6064)	loss 4.4643 (4.1418)	grad_norm 1.0996 (1.7547/0.7022)	mem 24308MB
[2025-01-18 14:02:13 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][120/312]	eta 0:01:58 lr 0.003913	time 0.5893 (0.6180)	model_time 0.5892 (0.6044)	loss 4.3828 (4.1239)	grad_norm 1.2279 (1.7082/0.6954)	mem 24308MB
[2025-01-18 14:02:19 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][130/312]	eta 0:01:52 lr 0.003913	time 0.7799 (0.6170)	model_time 0.7797 (0.6044)	loss 2.9591 (4.1096)	grad_norm 1.1497 (1.6732/0.6879)	mem 24308MB
[2025-01-18 14:02:25 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][140/312]	eta 0:01:45 lr 0.003913	time 0.6623 (0.6155)	model_time 0.6622 (0.6037)	loss 2.6670 (4.1030)	grad_norm 1.1865 (1.6636/0.6745)	mem 24308MB
[2025-01-18 14:02:31 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][150/312]	eta 0:01:39 lr 0.003913	time 0.6721 (0.6154)	model_time 0.6719 (0.6044)	loss 3.5052 (4.0958)	grad_norm 2.7668 (1.6668/0.6712)	mem 24308MB
[2025-01-18 14:02:38 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][160/312]	eta 0:01:33 lr 0.003912	time 0.6758 (0.6180)	model_time 0.6756 (0.6076)	loss 4.2630 (4.0839)	grad_norm 1.7961 (1.6590/0.6587)	mem 24308MB
[2025-01-18 14:02:44 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][170/312]	eta 0:01:27 lr 0.003912	time 0.5769 (0.6186)	model_time 0.5763 (0.6088)	loss 3.5781 (4.0714)	grad_norm 2.2028 (1.6650/0.6582)	mem 24308MB
[2025-01-18 14:02:50 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][180/312]	eta 0:01:21 lr 0.003912	time 0.5729 (0.6186)	model_time 0.5727 (0.6093)	loss 2.8309 (4.0870)	grad_norm 1.0222 (1.6889/0.7020)	mem 24308MB
[2025-01-18 14:02:56 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][190/312]	eta 0:01:15 lr 0.003912	time 0.5942 (0.6169)	model_time 0.5941 (0.6081)	loss 4.4678 (4.0916)	grad_norm 1.6101 (1.6743/0.6884)	mem 24308MB
[2025-01-18 14:03:02 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][200/312]	eta 0:01:08 lr 0.003912	time 0.5739 (0.6155)	model_time 0.5738 (0.6072)	loss 4.8251 (4.1028)	grad_norm 0.8244 (1.6570/0.6808)	mem 24308MB
[2025-01-18 14:03:08 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][210/312]	eta 0:01:02 lr 0.003911	time 0.5829 (0.6140)	model_time 0.5825 (0.6060)	loss 3.9657 (4.0899)	grad_norm 1.2400 (1.6384/0.6733)	mem 24308MB
[2025-01-18 14:03:13 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][220/312]	eta 0:00:56 lr 0.003911	time 0.5981 (0.6129)	model_time 0.5977 (0.6052)	loss 4.5564 (4.0858)	grad_norm 0.8871 (1.6388/0.6747)	mem 24308MB
[2025-01-18 14:03:19 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][230/312]	eta 0:00:50 lr 0.003911	time 0.5762 (0.6116)	model_time 0.5761 (0.6043)	loss 4.3412 (4.1049)	grad_norm 1.5096 (1.6317/0.6656)	mem 24308MB
[2025-01-18 14:03:25 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][240/312]	eta 0:00:43 lr 0.003911	time 0.5804 (0.6105)	model_time 0.5802 (0.6034)	loss 3.1365 (4.0955)	grad_norm 1.7670 (1.6275/0.6565)	mem 24308MB
[2025-01-18 14:03:31 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][250/312]	eta 0:00:37 lr 0.003911	time 0.6783 (0.6098)	model_time 0.6777 (0.6030)	loss 4.9163 (4.0961)	grad_norm 1.0997 (1.6181/0.6481)	mem 24308MB
[2025-01-18 14:03:37 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][260/312]	eta 0:00:31 lr 0.003910	time 0.6605 (0.6098)	model_time 0.6601 (0.6032)	loss 3.9799 (4.0920)	grad_norm 2.1933 (1.6172/0.6430)	mem 24308MB
[2025-01-18 14:03:43 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][270/312]	eta 0:00:25 lr 0.003910	time 0.6675 (0.6103)	model_time 0.6671 (0.6040)	loss 4.3159 (4.0733)	grad_norm 1.9178 (1.6121/0.6364)	mem 24308MB
[2025-01-18 14:03:50 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][280/312]	eta 0:00:19 lr 0.003910	time 0.5352 (0.6116)	model_time 0.5347 (0.6055)	loss 4.3491 (4.0647)	grad_norm inf (1.6286/0.6522)	mem 24308MB
[2025-01-18 14:03:56 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][290/312]	eta 0:00:13 lr 0.003910	time 0.6692 (0.6127)	model_time 0.6688 (0.6068)	loss 4.4567 (4.0724)	grad_norm 1.7226 (1.6438/0.6715)	mem 24308MB
[2025-01-18 14:04:02 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][300/312]	eta 0:00:07 lr 0.003910	time 0.5611 (0.6122)	model_time 0.5610 (0.6065)	loss 3.8143 (4.0740)	grad_norm 1.3663 (1.6357/0.6642)	mem 24308MB
[2025-01-18 14:04:08 internimage_s_1k_224] (main.py 510): INFO Train: [28/300][310/312]	eta 0:00:01 lr 0.003909	time 0.5695 (0.6109)	model_time 0.5694 (0.6054)	loss 4.4262 (4.0653)	grad_norm 2.9709 (1.6371/0.6670)	mem 24308MB
[2025-01-18 14:04:09 internimage_s_1k_224] (main.py 519): INFO EPOCH 28 training takes 0:03:10
[2025-01-18 14:04:09 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_28.pth saving......
[2025-01-18 14:04:10 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_28.pth saved !!!
[2025-01-18 14:04:17 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.068 (7.068)	Loss 1.1616 (1.1616)	Acc@1 74.390 (74.390)	Acc@5 92.725 (92.725)	Mem 24308MB
[2025-01-18 14:04:21 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.931)	Loss 1.7361 (1.4057)	Acc@1 62.012 (69.103)	Acc@5 85.034 (89.504)	Mem 24308MB
[2025-01-18 14:04:21 internimage_s_1k_224] (main.py 575): INFO [Epoch:28] * Acc@1 69.092 Acc@5 89.583
[2025-01-18 14:04:21 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 69.1%
[2025-01-18 14:04:21 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 14:04:23 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 14:04:23 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 69.09%
[2025-01-18 14:04:30 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.917 (6.917)	Loss 6.6594 (6.6594)	Acc@1 1.782 (1.782)	Acc@5 7.324 (7.324)	Mem 24308MB
[2025-01-18 14:04:33 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.889)	Loss 7.1494 (6.7663)	Acc@1 0.122 (1.036)	Acc@5 0.781 (4.148)	Mem 24308MB
[2025-01-18 14:04:33 internimage_s_1k_224] (main.py 575): INFO [Epoch:28] * Acc@1 1.472 Acc@5 5.200
[2025-01-18 14:04:33 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 1.5%
[2025-01-18 14:04:33 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 14:04:35 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 14:04:35 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 1.47%
[2025-01-18 14:04:38 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][0/312]	eta 0:11:38 lr 0.003909	time 2.2403 (2.2403)	model_time 0.6157 (0.6157)	loss 3.1201 (3.1201)	grad_norm 2.3213 (2.3213/0.0000)	mem 24308MB
[2025-01-18 14:04:43 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][10/312]	eta 0:03:41 lr 0.003909	time 0.5745 (0.7341)	model_time 0.5741 (0.5861)	loss 3.0352 (3.8980)	grad_norm 2.1570 (1.8715/0.7707)	mem 24308MB
[2025-01-18 14:04:49 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][20/312]	eta 0:03:14 lr 0.003909	time 0.5956 (0.6654)	model_time 0.5954 (0.5877)	loss 3.3404 (3.9327)	grad_norm 0.9187 (1.5976/0.6479)	mem 24308MB
[2025-01-18 14:04:55 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][30/312]	eta 0:03:00 lr 0.003909	time 0.5924 (0.6405)	model_time 0.5922 (0.5877)	loss 3.4559 (3.9658)	grad_norm 1.6583 (1.5136/0.5751)	mem 24308MB
[2025-01-18 14:05:01 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][40/312]	eta 0:02:50 lr 0.003909	time 0.5946 (0.6279)	model_time 0.5944 (0.5879)	loss 4.1879 (3.9927)	grad_norm 1.9764 (1.4388/0.5502)	mem 24308MB
[2025-01-18 14:05:07 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][50/312]	eta 0:02:42 lr 0.003908	time 0.5877 (0.6212)	model_time 0.5876 (0.5890)	loss 4.8381 (4.0121)	grad_norm 1.2952 (1.4714/0.5524)	mem 24308MB
[2025-01-18 14:05:13 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][60/312]	eta 0:02:35 lr 0.003908	time 0.5869 (0.6155)	model_time 0.5868 (0.5885)	loss 4.1615 (4.0647)	grad_norm 2.6163 (1.5333/0.5624)	mem 24308MB
[2025-01-18 14:05:19 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][70/312]	eta 0:02:28 lr 0.003908	time 0.5859 (0.6152)	model_time 0.5857 (0.5920)	loss 3.5902 (4.0005)	grad_norm 2.4915 (1.5310/0.5583)	mem 24308MB
[2025-01-18 14:05:25 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][80/312]	eta 0:02:22 lr 0.003908	time 0.5816 (0.6151)	model_time 0.5814 (0.5947)	loss 3.6555 (4.0034)	grad_norm 0.8709 (1.5906/0.6951)	mem 24308MB
[2025-01-18 14:05:32 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][90/312]	eta 0:02:17 lr 0.003908	time 0.6016 (0.6188)	model_time 0.6014 (0.6006)	loss 3.7903 (4.0022)	grad_norm 1.7289 (1.6197/0.7054)	mem 24308MB
[2025-01-18 14:05:38 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][100/312]	eta 0:02:11 lr 0.003907	time 0.5825 (0.6200)	model_time 0.5823 (0.6036)	loss 3.0418 (3.9931)	grad_norm 1.0702 (1.6152/0.6985)	mem 24308MB
[2025-01-18 14:05:44 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][110/312]	eta 0:02:05 lr 0.003907	time 0.6725 (0.6191)	model_time 0.6723 (0.6041)	loss 2.8234 (3.9737)	grad_norm 3.0769 (1.6217/0.6928)	mem 24308MB
[2025-01-18 14:05:50 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][120/312]	eta 0:01:58 lr 0.003907	time 0.5945 (0.6166)	model_time 0.5943 (0.6029)	loss 3.0854 (3.9874)	grad_norm 1.7088 (1.6764/0.7326)	mem 24308MB
[2025-01-18 14:05:56 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][130/312]	eta 0:01:51 lr 0.003907	time 0.5807 (0.6145)	model_time 0.5725 (0.6018)	loss 3.5220 (3.9655)	grad_norm 0.7734 (1.6498/0.7263)	mem 24308MB
[2025-01-18 14:06:02 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][140/312]	eta 0:01:45 lr 0.003907	time 0.5917 (0.6124)	model_time 0.5915 (0.6005)	loss 4.2849 (3.9593)	grad_norm 1.9845 (1.6161/0.7167)	mem 24308MB
[2025-01-18 14:06:08 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][150/312]	eta 0:01:38 lr 0.003906	time 0.5766 (0.6109)	model_time 0.5764 (0.5998)	loss 3.5451 (3.9700)	grad_norm 1.6970 (1.6238/0.7071)	mem 24308MB
[2025-01-18 14:06:13 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][160/312]	eta 0:01:32 lr 0.003906	time 0.5824 (0.6096)	model_time 0.5822 (0.5991)	loss 4.6537 (3.9660)	grad_norm 2.2331 (1.6310/0.6954)	mem 24308MB
[2025-01-18 14:06:19 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][170/312]	eta 0:01:26 lr 0.003906	time 0.5899 (0.6093)	model_time 0.5897 (0.5994)	loss 4.7506 (3.9823)	grad_norm 1.2117 (1.6051/0.6859)	mem 24308MB
[2025-01-18 14:06:25 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][180/312]	eta 0:01:20 lr 0.003906	time 0.5775 (0.6080)	model_time 0.5771 (0.5986)	loss 3.6098 (3.9848)	grad_norm 1.2451 (1.5928/0.6745)	mem 24308MB
[2025-01-18 14:06:31 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][190/312]	eta 0:01:14 lr 0.003906	time 0.5741 (0.6077)	model_time 0.5739 (0.5989)	loss 4.3123 (3.9843)	grad_norm 2.3552 (1.5939/0.6631)	mem 24308MB
[2025-01-18 14:06:38 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][200/312]	eta 0:01:08 lr 0.003905	time 0.6293 (0.6084)	model_time 0.6290 (0.6000)	loss 4.2830 (3.9729)	grad_norm 1.6153 (1.6044/0.6741)	mem 24308MB
[2025-01-18 14:06:44 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][210/312]	eta 0:01:02 lr 0.003905	time 0.5754 (0.6100)	model_time 0.5753 (0.6019)	loss 3.9822 (3.9776)	grad_norm 1.3044 (1.5949/0.6670)	mem 24308MB
[2025-01-18 14:06:50 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][220/312]	eta 0:00:56 lr 0.003905	time 0.5862 (0.6107)	model_time 0.5860 (0.6030)	loss 3.4717 (3.9891)	grad_norm 1.0060 (1.6117/0.6782)	mem 24308MB
[2025-01-18 14:06:56 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][230/312]	eta 0:00:50 lr 0.003905	time 0.6623 (0.6109)	model_time 0.6621 (0.6035)	loss 4.8248 (3.9996)	grad_norm 2.4285 (1.6311/0.7315)	mem 24308MB
[2025-01-18 14:07:02 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][240/312]	eta 0:00:43 lr 0.003905	time 0.5749 (0.6097)	model_time 0.5747 (0.6026)	loss 4.2200 (4.0015)	grad_norm 0.9604 (1.6347/0.7252)	mem 24308MB
[2025-01-18 14:07:08 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][250/312]	eta 0:00:37 lr 0.003904	time 0.5756 (0.6088)	model_time 0.5751 (0.6019)	loss 4.6354 (3.9915)	grad_norm 1.8480 (1.6269/0.7197)	mem 24308MB
[2025-01-18 14:07:14 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][260/312]	eta 0:00:31 lr 0.003904	time 0.5725 (0.6079)	model_time 0.5723 (0.6013)	loss 4.4216 (4.0017)	grad_norm 2.4664 (1.6254/0.7152)	mem 24308MB
[2025-01-18 14:07:20 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][270/312]	eta 0:00:25 lr 0.003904	time 0.5794 (0.6070)	model_time 0.5793 (0.6007)	loss 4.8285 (3.9954)	grad_norm 1.8065 (1.6330/0.7173)	mem 24308MB
[2025-01-18 14:07:26 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][280/312]	eta 0:00:19 lr 0.003904	time 0.5824 (0.6062)	model_time 0.5822 (0.6001)	loss 4.0551 (3.9907)	grad_norm 1.2953 (1.6339/0.7083)	mem 24308MB
[2025-01-18 14:07:32 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][290/312]	eta 0:00:13 lr 0.003904	time 0.5891 (0.6059)	model_time 0.5889 (0.6000)	loss 3.9455 (3.9846)	grad_norm 1.7888 (1.6471/0.7097)	mem 24308MB
[2025-01-18 14:07:37 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][300/312]	eta 0:00:07 lr 0.003903	time 0.5690 (0.6051)	model_time 0.5689 (0.5993)	loss 3.1909 (3.9771)	grad_norm 1.3544 (1.6445/0.7085)	mem 24308MB
[2025-01-18 14:07:43 internimage_s_1k_224] (main.py 510): INFO Train: [29/300][310/312]	eta 0:00:01 lr 0.003903	time 0.5689 (0.6045)	model_time 0.5687 (0.5989)	loss 4.4447 (3.9819)	grad_norm 2.0152 (1.6308/0.6995)	mem 24308MB
[2025-01-18 14:07:44 internimage_s_1k_224] (main.py 519): INFO EPOCH 29 training takes 0:03:08
[2025-01-18 14:07:44 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_29.pth saving......
[2025-01-18 14:07:46 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_29.pth saved !!!
[2025-01-18 14:07:53 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.187 (7.187)	Loss 1.1838 (1.1838)	Acc@1 72.803 (72.803)	Acc@5 92.139 (92.139)	Mem 24308MB
[2025-01-18 14:07:56 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.933)	Loss 1.6381 (1.4036)	Acc@1 63.232 (68.854)	Acc@5 86.255 (89.566)	Mem 24308MB
[2025-01-18 14:07:56 internimage_s_1k_224] (main.py 575): INFO [Epoch:29] * Acc@1 68.968 Acc@5 89.655
[2025-01-18 14:07:56 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 69.0%
[2025-01-18 14:07:56 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 69.09%
[2025-01-18 14:08:04 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.215 (8.215)	Loss 6.6282 (6.6282)	Acc@1 1.855 (1.855)	Acc@5 7.349 (7.349)	Mem 24308MB
[2025-01-18 14:08:08 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.103)	Loss 7.1020 (6.7211)	Acc@1 0.146 (1.181)	Acc@5 0.952 (4.614)	Mem 24308MB
[2025-01-18 14:08:09 internimage_s_1k_224] (main.py 575): INFO [Epoch:29] * Acc@1 1.631 Acc@5 5.758
[2025-01-18 14:08:09 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 1.6%
[2025-01-18 14:08:09 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 14:08:11 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 14:08:11 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 1.63%
[2025-01-18 14:08:13 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][0/312]	eta 0:11:35 lr 0.003903	time 2.2280 (2.2280)	model_time 0.5986 (0.5986)	loss 4.8786 (4.8786)	grad_norm 1.9330 (1.9330/0.0000)	mem 24308MB
[2025-01-18 14:08:19 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][10/312]	eta 0:03:53 lr 0.003903	time 0.6022 (0.7737)	model_time 0.6021 (0.6254)	loss 4.2755 (4.2832)	grad_norm 1.0079 (1.4163/0.4737)	mem 24308MB
[2025-01-18 14:08:25 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][20/312]	eta 0:03:25 lr 0.003903	time 0.5820 (0.7045)	model_time 0.5815 (0.6261)	loss 4.9090 (4.1287)	grad_norm 0.8808 (1.4791/0.4318)	mem 24308MB
[2025-01-18 14:08:32 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][30/312]	eta 0:03:11 lr 0.003902	time 0.7010 (0.6801)	model_time 0.7008 (0.6270)	loss 4.6166 (4.1476)	grad_norm 1.0665 (1.4676/0.4049)	mem 24308MB
[2025-01-18 14:08:38 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][40/312]	eta 0:03:01 lr 0.003902	time 0.5818 (0.6657)	model_time 0.5813 (0.6255)	loss 3.8931 (4.0829)	grad_norm 2.2985 (1.6568/0.5529)	mem 24308MB
[2025-01-18 14:08:44 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][50/312]	eta 0:02:50 lr 0.003902	time 0.5905 (0.6514)	model_time 0.5903 (0.6189)	loss 4.2142 (4.1109)	grad_norm 1.7449 (1.6887/0.5873)	mem 24308MB
[2025-01-18 14:08:50 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][60/312]	eta 0:02:41 lr 0.003902	time 0.5873 (0.6405)	model_time 0.5871 (0.6133)	loss 4.3191 (4.1365)	grad_norm 3.8666 (1.7102/0.6508)	mem 24308MB
[2025-01-18 14:08:56 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][70/312]	eta 0:02:33 lr 0.003902	time 0.5849 (0.6328)	model_time 0.5847 (0.6095)	loss 4.4633 (4.1451)	grad_norm 0.9699 (1.7064/0.6274)	mem 24308MB
[2025-01-18 14:09:01 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][80/312]	eta 0:02:25 lr 0.003901	time 0.5932 (0.6271)	model_time 0.5931 (0.6066)	loss 4.5291 (4.1249)	grad_norm 0.9349 (1.6251/0.6321)	mem 24308MB
[2025-01-18 14:09:07 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][90/312]	eta 0:02:18 lr 0.003901	time 0.5814 (0.6224)	model_time 0.5812 (0.6041)	loss 3.7419 (4.1168)	grad_norm 2.0940 (1.5888/0.6269)	mem 24308MB
[2025-01-18 14:09:13 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][100/312]	eta 0:02:11 lr 0.003901	time 0.5732 (0.6186)	model_time 0.5730 (0.6020)	loss 3.3487 (4.0854)	grad_norm 1.3450 (1.5735/0.6103)	mem 24308MB
[2025-01-18 14:09:19 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][110/312]	eta 0:02:04 lr 0.003901	time 0.5902 (0.6158)	model_time 0.5900 (0.6007)	loss 4.2344 (4.0887)	grad_norm 1.7551 (1.5593/0.5982)	mem 24308MB
[2025-01-18 14:09:25 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][120/312]	eta 0:01:58 lr 0.003901	time 0.6592 (0.6152)	model_time 0.6587 (0.6012)	loss 3.9909 (4.0962)	grad_norm 1.6348 (1.5575/0.5766)	mem 24308MB
[2025-01-18 14:09:31 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][130/312]	eta 0:01:52 lr 0.003900	time 0.6997 (0.6166)	model_time 0.6995 (0.6037)	loss 2.8679 (4.0960)	grad_norm 0.9998 (1.5808/0.5978)	mem 24308MB
[2025-01-18 14:09:38 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][140/312]	eta 0:01:46 lr 0.003900	time 0.5909 (0.6167)	model_time 0.5904 (0.6047)	loss 3.8986 (4.0918)	grad_norm 1.0730 (1.5725/0.5959)	mem 24308MB
[2025-01-18 14:09:44 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][150/312]	eta 0:01:40 lr 0.003900	time 0.7150 (0.6175)	model_time 0.7149 (0.6063)	loss 3.7996 (4.0444)	grad_norm 1.7442 (1.5766/0.5826)	mem 24308MB
[2025-01-18 14:09:50 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][160/312]	eta 0:01:33 lr 0.003900	time 0.5814 (0.6174)	model_time 0.5812 (0.6068)	loss 4.2683 (4.0376)	grad_norm 1.0053 (1.5874/0.6141)	mem 24308MB
[2025-01-18 14:09:56 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][170/312]	eta 0:01:27 lr 0.003900	time 0.5830 (0.6163)	model_time 0.5828 (0.6064)	loss 4.0881 (4.0381)	grad_norm 1.8828 (1.5832/0.6074)	mem 24308MB
[2025-01-18 14:10:02 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][180/312]	eta 0:01:21 lr 0.003899	time 0.5920 (0.6149)	model_time 0.5918 (0.6054)	loss 4.4100 (4.0522)	grad_norm 2.4289 (1.6193/0.6437)	mem 24308MB
[2025-01-18 14:10:08 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][190/312]	eta 0:01:14 lr 0.003899	time 0.5742 (0.6132)	model_time 0.5740 (0.6043)	loss 4.2379 (4.0421)	grad_norm 1.2562 (1.6145/0.6423)	mem 24308MB
[2025-01-18 14:10:14 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][200/312]	eta 0:01:08 lr 0.003899	time 0.6333 (0.6121)	model_time 0.6332 (0.6036)	loss 2.9529 (4.0462)	grad_norm 1.1233 (1.5999/0.6366)	mem 24308MB
[2025-01-18 14:10:20 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][210/312]	eta 0:01:02 lr 0.003899	time 0.5821 (0.6109)	model_time 0.5819 (0.6027)	loss 3.7392 (4.0470)	grad_norm 1.4167 (1.5812/0.6298)	mem 24308MB
[2025-01-18 14:10:25 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][220/312]	eta 0:00:56 lr 0.003899	time 0.5930 (0.6099)	model_time 0.5929 (0.6021)	loss 3.5076 (4.0418)	grad_norm 2.0373 (1.5813/0.6207)	mem 24308MB
[2025-01-18 14:10:31 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][230/312]	eta 0:00:49 lr 0.003898	time 0.5843 (0.6088)	model_time 0.5842 (0.6013)	loss 4.2688 (4.0411)	grad_norm 1.1577 (1.5641/0.6144)	mem 24308MB
[2025-01-18 14:10:37 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][240/312]	eta 0:00:43 lr 0.003898	time 0.6594 (0.6088)	model_time 0.6593 (0.6017)	loss 4.6601 (4.0358)	grad_norm 0.9823 (1.5697/0.6198)	mem 24308MB
[2025-01-18 14:10:44 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][250/312]	eta 0:00:37 lr 0.003898	time 0.5788 (0.6092)	model_time 0.5786 (0.6023)	loss 4.6428 (4.0350)	grad_norm 0.8137 (1.5710/0.6192)	mem 24308MB
[2025-01-18 14:10:50 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][260/312]	eta 0:00:31 lr 0.003898	time 0.6632 (0.6105)	model_time 0.6630 (0.6038)	loss 4.5185 (4.0241)	grad_norm 1.6899 (1.5845/0.6290)	mem 24308MB
[2025-01-18 14:10:56 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][270/312]	eta 0:00:25 lr 0.003897	time 0.6758 (0.6119)	model_time 0.6757 (0.6055)	loss 4.4158 (4.0316)	grad_norm 1.4940 (1.5927/0.6326)	mem 24308MB
[2025-01-18 14:11:03 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][280/312]	eta 0:00:19 lr 0.003897	time 0.5812 (0.6125)	model_time 0.5811 (0.6063)	loss 3.2057 (4.0134)	grad_norm 1.4647 (1.5862/0.6300)	mem 24308MB
[2025-01-18 14:11:09 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][290/312]	eta 0:00:13 lr 0.003897	time 0.5823 (0.6120)	model_time 0.5818 (0.6060)	loss 4.3798 (4.0142)	grad_norm 0.7415 (1.6083/0.6654)	mem 24308MB
[2025-01-18 14:11:15 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][300/312]	eta 0:00:07 lr 0.003897	time 0.5691 (0.6108)	model_time 0.5690 (0.6050)	loss 4.9851 (4.0175)	grad_norm 1.2768 (1.6017/0.6572)	mem 24308MB
[2025-01-18 14:11:20 internimage_s_1k_224] (main.py 510): INFO Train: [30/300][310/312]	eta 0:00:01 lr 0.003897	time 0.5690 (0.6096)	model_time 0.5689 (0.6040)	loss 4.3098 (4.0259)	grad_norm 1.4799 (1.6133/0.6582)	mem 24308MB
[2025-01-18 14:11:21 internimage_s_1k_224] (main.py 519): INFO EPOCH 30 training takes 0:03:10
[2025-01-18 14:11:21 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_30.pth saving......
[2025-01-18 14:11:23 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_30.pth saved !!!
[2025-01-18 14:11:30 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.249 (7.249)	Loss 1.2001 (1.2001)	Acc@1 74.023 (74.023)	Acc@5 93.091 (93.091)	Mem 24308MB
[2025-01-18 14:11:33 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.135 (0.939)	Loss 1.7464 (1.4279)	Acc@1 62.500 (69.363)	Acc@5 85.620 (89.733)	Mem 24308MB
[2025-01-18 14:11:33 internimage_s_1k_224] (main.py 575): INFO [Epoch:30] * Acc@1 69.360 Acc@5 89.821
[2025-01-18 14:11:33 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 69.4%
[2025-01-18 14:11:33 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 14:11:35 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 14:11:35 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 69.36%
[2025-01-18 14:11:42 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.075 (7.075)	Loss 6.5741 (6.5741)	Acc@1 2.002 (2.002)	Acc@5 7.642 (7.642)	Mem 24308MB
[2025-01-18 14:11:45 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.928)	Loss 7.0072 (6.6416)	Acc@1 0.244 (1.414)	Acc@5 1.489 (5.407)	Mem 24308MB
[2025-01-18 14:11:46 internimage_s_1k_224] (main.py 575): INFO [Epoch:30] * Acc@1 1.891 Acc@5 6.586
[2025-01-18 14:11:46 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 1.9%
[2025-01-18 14:11:46 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 14:11:48 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 14:11:48 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 1.89%
[2025-01-18 14:11:50 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][0/312]	eta 0:11:59 lr 0.003897	time 2.3075 (2.3075)	model_time 0.5978 (0.5978)	loss 3.5810 (3.5810)	grad_norm 1.1084 (1.1084/0.0000)	mem 24308MB
[2025-01-18 14:11:56 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][10/312]	eta 0:03:44 lr 0.003896	time 0.5750 (0.7442)	model_time 0.5749 (0.5885)	loss 4.5754 (4.1428)	grad_norm 0.8059 (1.7262/0.7270)	mem 24308MB
[2025-01-18 14:12:02 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][20/312]	eta 0:03:15 lr 0.003896	time 0.5831 (0.6681)	model_time 0.5827 (0.5864)	loss 4.0587 (4.1068)	grad_norm 1.3659 (1.5828/0.6863)	mem 24308MB
[2025-01-18 14:12:07 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][30/312]	eta 0:03:01 lr 0.003896	time 0.5908 (0.6432)	model_time 0.5906 (0.5877)	loss 3.9590 (4.1370)	grad_norm 0.6920 (1.5172/0.6176)	mem 24308MB
[2025-01-18 14:12:13 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][40/312]	eta 0:02:51 lr 0.003896	time 0.5932 (0.6294)	model_time 0.5931 (0.5874)	loss 4.0226 (4.1733)	grad_norm 1.1640 (1.5066/0.5795)	mem 24308MB
[2025-01-18 14:12:19 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][50/312]	eta 0:02:44 lr 0.003896	time 0.7004 (0.6262)	model_time 0.7000 (0.5923)	loss 4.3602 (4.0728)	grad_norm 1.2491 (1.5983/0.6286)	mem 24308MB
[2025-01-18 14:12:26 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][60/312]	eta 0:02:37 lr 0.003895	time 0.6865 (0.6264)	model_time 0.6860 (0.5981)	loss 4.2655 (4.0847)	grad_norm 1.5259 (1.6332/0.6290)	mem 24308MB
[2025-01-18 14:12:32 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][70/312]	eta 0:02:31 lr 0.003895	time 0.6905 (0.6265)	model_time 0.6900 (0.6020)	loss 3.5002 (4.0577)	grad_norm 1.0655 (1.5806/0.6253)	mem 24308MB
[2025-01-18 14:12:38 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][80/312]	eta 0:02:25 lr 0.003895	time 0.5947 (0.6255)	model_time 0.5942 (0.6040)	loss 2.8734 (4.0267)	grad_norm 2.2737 (1.5544/0.6119)	mem 24308MB
[2025-01-18 14:12:44 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][90/312]	eta 0:02:18 lr 0.003895	time 0.5851 (0.6248)	model_time 0.5847 (0.6057)	loss 4.1296 (4.0183)	grad_norm 3.1672 (1.5844/0.6480)	mem 24308MB
[2025-01-18 14:12:50 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][100/312]	eta 0:02:12 lr 0.003894	time 0.5797 (0.6228)	model_time 0.5796 (0.6055)	loss 4.1164 (3.9822)	grad_norm 1.9918 (1.5835/0.6418)	mem 24308MB
[2025-01-18 14:12:56 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][110/312]	eta 0:02:05 lr 0.003894	time 0.5877 (0.6196)	model_time 0.5873 (0.6039)	loss 4.2183 (3.9804)	grad_norm 1.0990 (1.5804/0.6271)	mem 24308MB
[2025-01-18 14:13:02 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][120/312]	eta 0:01:58 lr 0.003894	time 0.5807 (0.6172)	model_time 0.5806 (0.6027)	loss 3.2995 (3.9909)	grad_norm 1.2903 (1.5840/0.6244)	mem 24308MB
[2025-01-18 14:13:08 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][130/312]	eta 0:01:51 lr 0.003894	time 0.5830 (0.6149)	model_time 0.5829 (0.6015)	loss 3.0109 (3.9868)	grad_norm 1.3094 (1.5702/0.6119)	mem 24308MB
[2025-01-18 14:13:14 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][140/312]	eta 0:01:45 lr 0.003894	time 0.5865 (0.6129)	model_time 0.5861 (0.6004)	loss 3.1390 (3.9734)	grad_norm 1.3486 (1.5761/0.6227)	mem 24308MB
[2025-01-18 14:13:20 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][150/312]	eta 0:01:39 lr 0.003893	time 0.5850 (0.6113)	model_time 0.5848 (0.5996)	loss 3.1091 (3.9774)	grad_norm 2.2585 (1.5888/0.6209)	mem 24308MB
[2025-01-18 14:13:26 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][160/312]	eta 0:01:32 lr 0.003893	time 0.5875 (0.6098)	model_time 0.5874 (0.5988)	loss 4.1708 (3.9705)	grad_norm 1.5476 (1.5704/0.6169)	mem 24308MB
[2025-01-18 14:13:32 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][170/312]	eta 0:01:26 lr 0.003893	time 0.7041 (0.6097)	model_time 0.7037 (0.5993)	loss 3.3558 (3.9702)	grad_norm 2.3368 (1.6052/0.6445)	mem 24308MB
[2025-01-18 14:13:38 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][180/312]	eta 0:01:20 lr 0.003893	time 0.6009 (0.6109)	model_time 0.6005 (0.6011)	loss 3.1353 (3.9527)	grad_norm 1.8378 (1.5837/0.6409)	mem 24308MB
[2025-01-18 14:13:44 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][190/312]	eta 0:01:14 lr 0.003893	time 0.5759 (0.6111)	model_time 0.5758 (0.6018)	loss 4.3759 (3.9475)	grad_norm 1.9972 (1.5786/0.6284)	mem 24308MB
[2025-01-18 14:13:51 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][200/312]	eta 0:01:08 lr 0.003892	time 0.5968 (0.6125)	model_time 0.5966 (0.6036)	loss 2.9787 (3.9446)	grad_norm 0.8848 (1.5754/0.6274)	mem 24308MB
[2025-01-18 14:13:57 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][210/312]	eta 0:01:02 lr 0.003892	time 0.5813 (0.6130)	model_time 0.5812 (0.6045)	loss 4.1397 (3.9485)	grad_norm 1.0231 (1.5525/0.6227)	mem 24308MB
[2025-01-18 14:14:03 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][220/312]	eta 0:00:56 lr 0.003892	time 0.5850 (0.6124)	model_time 0.5849 (0.6043)	loss 3.6743 (3.9570)	grad_norm 3.7625 (1.5813/0.6566)	mem 24308MB
[2025-01-18 14:14:09 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][230/312]	eta 0:00:50 lr 0.003892	time 0.5739 (0.6112)	model_time 0.5735 (0.6035)	loss 3.5819 (3.9479)	grad_norm 1.8984 (1.6130/0.7211)	mem 24308MB
[2025-01-18 14:14:15 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][240/312]	eta 0:00:43 lr 0.003891	time 0.5744 (0.6103)	model_time 0.5743 (0.6028)	loss 4.8278 (3.9517)	grad_norm 0.8983 (1.6194/0.7319)	mem 24308MB
[2025-01-18 14:14:21 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][250/312]	eta 0:00:37 lr 0.003891	time 0.6196 (0.6094)	model_time 0.6194 (0.6022)	loss 4.3445 (3.9524)	grad_norm 1.5958 (1.6060/0.7225)	mem 24308MB
[2025-01-18 14:14:26 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][260/312]	eta 0:00:31 lr 0.003891	time 0.5925 (0.6085)	model_time 0.5921 (0.6016)	loss 4.3207 (3.9583)	grad_norm 1.0189 (1.5975/0.7121)	mem 24308MB
[2025-01-18 14:14:32 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][270/312]	eta 0:00:25 lr 0.003891	time 0.5865 (0.6077)	model_time 0.5864 (0.6010)	loss 3.8982 (3.9570)	grad_norm 0.9737 (1.5834/0.7040)	mem 24308MB
[2025-01-18 14:14:38 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][280/312]	eta 0:00:19 lr 0.003891	time 0.5821 (0.6069)	model_time 0.5820 (0.6005)	loss 3.9790 (3.9588)	grad_norm 0.7646 (1.5842/0.7002)	mem 24308MB
[2025-01-18 14:14:44 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][290/312]	eta 0:00:13 lr 0.003890	time 0.5742 (0.6064)	model_time 0.5738 (0.6001)	loss 3.6646 (3.9505)	grad_norm 1.1940 (1.5878/0.6957)	mem 24308MB
[2025-01-18 14:14:50 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][300/312]	eta 0:00:07 lr 0.003890	time 0.5668 (0.6071)	model_time 0.5667 (0.6011)	loss 2.6968 (3.9515)	grad_norm 4.2153 (1.5970/0.7071)	mem 24308MB
[2025-01-18 14:14:56 internimage_s_1k_224] (main.py 510): INFO Train: [31/300][310/312]	eta 0:00:01 lr 0.003890	time 0.5694 (0.6075)	model_time 0.5693 (0.6016)	loss 4.1499 (3.9582)	grad_norm 1.2128 (1.5863/0.7044)	mem 24308MB
[2025-01-18 14:14:57 internimage_s_1k_224] (main.py 519): INFO EPOCH 31 training takes 0:03:09
[2025-01-18 14:14:57 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_31.pth saving......
[2025-01-18 14:14:59 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_31.pth saved !!!
[2025-01-18 14:15:06 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.307 (7.307)	Loss 1.1395 (1.1395)	Acc@1 74.683 (74.683)	Acc@5 93.188 (93.188)	Mem 24308MB
[2025-01-18 14:15:10 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.983)	Loss 1.6286 (1.3570)	Acc@1 63.867 (69.604)	Acc@5 85.718 (89.910)	Mem 24308MB
[2025-01-18 14:15:10 internimage_s_1k_224] (main.py 575): INFO [Epoch:31] * Acc@1 69.636 Acc@5 89.985
[2025-01-18 14:15:10 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 69.6%
[2025-01-18 14:15:10 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 14:15:12 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 14:15:12 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 69.64%
[2025-01-18 14:15:19 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.063 (7.063)	Loss 6.4805 (6.4805)	Acc@1 2.222 (2.222)	Acc@5 8.350 (8.350)	Mem 24308MB
[2025-01-18 14:15:22 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.983)	Loss 6.8629 (6.5202)	Acc@1 0.439 (1.725)	Acc@5 2.637 (6.667)	Mem 24308MB
[2025-01-18 14:15:23 internimage_s_1k_224] (main.py 575): INFO [Epoch:31] * Acc@1 2.229 Acc@5 7.915
[2025-01-18 14:15:23 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 2.2%
[2025-01-18 14:15:23 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 14:15:25 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 14:15:25 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 2.23%
[2025-01-18 14:15:27 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][0/312]	eta 0:10:01 lr 0.003890	time 1.9290 (1.9290)	model_time 0.6059 (0.6059)	loss 3.5100 (3.5100)	grad_norm 0.8977 (0.8977/0.0000)	mem 24308MB
[2025-01-18 14:15:33 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][10/312]	eta 0:03:47 lr 0.003890	time 0.5789 (0.7530)	model_time 0.5784 (0.6323)	loss 3.3836 (3.8029)	grad_norm 2.2149 (1.8184/0.5993)	mem 24308MB
[2025-01-18 14:15:40 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][20/312]	eta 0:03:22 lr 0.003889	time 0.5975 (0.6947)	model_time 0.5970 (0.6314)	loss 4.8231 (3.8591)	grad_norm 1.8859 (1.6398/0.5399)	mem 24308MB
[2025-01-18 14:15:46 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][30/312]	eta 0:03:07 lr 0.003889	time 0.6057 (0.6665)	model_time 0.6055 (0.6235)	loss 4.0449 (3.9751)	grad_norm 1.5605 (1.5412/0.5019)	mem 24308MB
[2025-01-18 14:15:51 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][40/312]	eta 0:02:56 lr 0.003889	time 0.5711 (0.6477)	model_time 0.5710 (0.6152)	loss 4.2466 (3.9811)	grad_norm 1.6025 (1.5985/0.5648)	mem 24308MB
[2025-01-18 14:15:57 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][50/312]	eta 0:02:46 lr 0.003889	time 0.5932 (0.6364)	model_time 0.5930 (0.6101)	loss 4.2402 (4.0208)	grad_norm 2.1016 (1.6059/0.5401)	mem 24308MB
[2025-01-18 14:16:03 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][60/312]	eta 0:02:38 lr 0.003889	time 0.5858 (0.6281)	model_time 0.5853 (0.6061)	loss 3.6522 (4.0312)	grad_norm 2.1856 (1.6247/0.5495)	mem 24308MB
[2025-01-18 14:16:09 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][70/312]	eta 0:02:30 lr 0.003888	time 0.5862 (0.6222)	model_time 0.5860 (0.6033)	loss 4.7752 (4.0266)	grad_norm 1.6804 (1.6765/0.5940)	mem 24308MB
[2025-01-18 14:16:15 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][80/312]	eta 0:02:23 lr 0.003888	time 0.5857 (0.6177)	model_time 0.5852 (0.6011)	loss 4.3611 (4.0506)	grad_norm 1.1143 (1.6488/0.5843)	mem 24308MB
[2025-01-18 14:16:21 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][90/312]	eta 0:02:16 lr 0.003888	time 0.5783 (0.6140)	model_time 0.5779 (0.5991)	loss 4.8561 (4.0477)	grad_norm 1.2998 (1.5971/0.5748)	mem 24308MB
[2025-01-18 14:16:27 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][100/312]	eta 0:02:10 lr 0.003888	time 0.5803 (0.6136)	model_time 0.5798 (0.6001)	loss 3.6194 (4.0548)	grad_norm 2.0459 (1.6139/0.5670)	mem 24308MB
[2025-01-18 14:16:33 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][110/312]	eta 0:02:03 lr 0.003887	time 0.5920 (0.6132)	model_time 0.5918 (0.6009)	loss 4.5765 (4.0499)	grad_norm 1.2645 (1.6337/0.5688)	mem 24308MB
[2025-01-18 14:16:39 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][120/312]	eta 0:01:58 lr 0.003887	time 0.5816 (0.6147)	model_time 0.5814 (0.6034)	loss 4.2954 (4.0320)	grad_norm 1.0314 (1.5942/0.5681)	mem 24308MB
[2025-01-18 14:16:46 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][130/312]	eta 0:01:52 lr 0.003887	time 0.5857 (0.6177)	model_time 0.5855 (0.6072)	loss 4.4208 (4.0487)	grad_norm 2.9643 (1.6049/0.5699)	mem 24308MB
[2025-01-18 14:16:52 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][140/312]	eta 0:01:46 lr 0.003887	time 0.6519 (0.6205)	model_time 0.6517 (0.6107)	loss 4.6202 (4.0501)	grad_norm 1.2603 (1.6535/0.6678)	mem 24308MB
[2025-01-18 14:16:58 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][150/312]	eta 0:01:40 lr 0.003887	time 0.5955 (0.6191)	model_time 0.5951 (0.6100)	loss 3.9296 (4.0347)	grad_norm 0.8692 (1.6293/0.6578)	mem 24308MB
[2025-01-18 14:17:04 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][160/312]	eta 0:01:33 lr 0.003886	time 0.5810 (0.6170)	model_time 0.5809 (0.6085)	loss 4.8587 (4.0305)	grad_norm 4.5690 (1.6509/0.7252)	mem 24308MB
[2025-01-18 14:17:10 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][170/312]	eta 0:01:27 lr 0.003886	time 0.5784 (0.6153)	model_time 0.5780 (0.6072)	loss 3.2081 (4.0197)	grad_norm 0.8998 (1.6459/0.7262)	mem 24308MB
[2025-01-18 14:17:16 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][180/312]	eta 0:01:21 lr 0.003886	time 0.5929 (0.6137)	model_time 0.5927 (0.6060)	loss 4.1681 (4.0055)	grad_norm 0.8663 (1.6497/0.7161)	mem 24308MB
[2025-01-18 14:17:22 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][190/312]	eta 0:01:14 lr 0.003886	time 0.5719 (0.6122)	model_time 0.5714 (0.6049)	loss 4.9825 (4.0197)	grad_norm 3.0845 (1.6608/0.7228)	mem 24308MB
[2025-01-18 14:17:28 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][200/312]	eta 0:01:08 lr 0.003885	time 0.5780 (0.6111)	model_time 0.5778 (0.6042)	loss 4.4718 (4.0174)	grad_norm 1.7467 (1.6483/0.7124)	mem 24308MB
[2025-01-18 14:17:34 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][210/312]	eta 0:01:02 lr 0.003885	time 0.5966 (0.6100)	model_time 0.5964 (0.6034)	loss 3.5596 (4.0185)	grad_norm 0.8441 (1.6330/0.7043)	mem 24308MB
[2025-01-18 14:17:40 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][220/312]	eta 0:00:56 lr 0.003885	time 0.5774 (0.6107)	model_time 0.5772 (0.6044)	loss 3.8319 (4.0272)	grad_norm 2.0926 (1.6380/0.7004)	mem 24308MB
[2025-01-18 14:17:46 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][230/312]	eta 0:00:50 lr 0.003885	time 0.6649 (0.6107)	model_time 0.6644 (0.6046)	loss 3.0725 (4.0211)	grad_norm 0.9117 (1.6275/0.6908)	mem 24308MB
[2025-01-18 14:17:52 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][240/312]	eta 0:00:44 lr 0.003885	time 0.6850 (0.6114)	model_time 0.6849 (0.6055)	loss 4.1402 (4.0128)	grad_norm 1.7317 (1.6149/0.6853)	mem 24308MB
[2025-01-18 14:17:59 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][250/312]	eta 0:00:37 lr 0.003884	time 0.5848 (0.6122)	model_time 0.5847 (0.6065)	loss 4.2370 (4.0028)	grad_norm 3.2061 (1.6330/0.6859)	mem 24308MB
[2025-01-18 14:18:05 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][260/312]	eta 0:00:31 lr 0.003884	time 0.5856 (0.6124)	model_time 0.5852 (0.6070)	loss 4.6024 (4.0033)	grad_norm 1.0760 (1.6473/0.6941)	mem 24308MB
[2025-01-18 14:18:11 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][270/312]	eta 0:00:25 lr 0.003884	time 0.5864 (0.6123)	model_time 0.5862 (0.6071)	loss 4.2812 (4.0187)	grad_norm 0.8712 (1.6344/0.6858)	mem 24308MB
[2025-01-18 14:18:17 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][280/312]	eta 0:00:19 lr 0.003884	time 0.5841 (0.6115)	model_time 0.5840 (0.6064)	loss 4.9820 (4.0258)	grad_norm 1.0215 (1.6159/0.6812)	mem 24308MB
[2025-01-18 14:18:23 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][290/312]	eta 0:00:13 lr 0.003883	time 0.5869 (0.6105)	model_time 0.5865 (0.6056)	loss 3.3619 (4.0122)	grad_norm 0.9919 (1.6240/0.6871)	mem 24308MB
[2025-01-18 14:18:28 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][300/312]	eta 0:00:07 lr 0.003883	time 0.5697 (0.6096)	model_time 0.5696 (0.6049)	loss 4.3684 (4.0163)	grad_norm 1.8577 (1.6130/0.6839)	mem 24308MB
[2025-01-18 14:18:34 internimage_s_1k_224] (main.py 510): INFO Train: [32/300][310/312]	eta 0:00:01 lr 0.003883	time 0.5667 (0.6084)	model_time 0.5666 (0.6038)	loss 3.1826 (4.0132)	grad_norm 1.8358 (1.5986/0.6796)	mem 24308MB
[2025-01-18 14:18:35 internimage_s_1k_224] (main.py 519): INFO EPOCH 32 training takes 0:03:09
[2025-01-18 14:18:35 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_32.pth saving......
[2025-01-18 14:18:37 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_32.pth saved !!!
[2025-01-18 14:18:44 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.012 (7.012)	Loss 1.1364 (1.1364)	Acc@1 74.194 (74.194)	Acc@5 93.359 (93.359)	Mem 24308MB
[2025-01-18 14:18:47 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.919)	Loss 1.6724 (1.3675)	Acc@1 63.281 (69.971)	Acc@5 86.060 (90.228)	Mem 24308MB
[2025-01-18 14:18:47 internimage_s_1k_224] (main.py 575): INFO [Epoch:32] * Acc@1 70.064 Acc@5 90.351
[2025-01-18 14:18:47 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 70.1%
[2025-01-18 14:18:47 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 14:18:49 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 14:18:49 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 70.06%
[2025-01-18 14:18:56 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.176 (7.176)	Loss 6.3610 (6.3610)	Acc@1 2.539 (2.539)	Acc@5 9.668 (9.668)	Mem 24308MB
[2025-01-18 14:18:59 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.958)	Loss 6.7083 (6.3772)	Acc@1 0.708 (2.202)	Acc@5 4.248 (8.279)	Mem 24308MB
[2025-01-18 14:18:59 internimage_s_1k_224] (main.py 575): INFO [Epoch:32] * Acc@1 2.759 Acc@5 9.597
[2025-01-18 14:18:59 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 2.8%
[2025-01-18 14:18:59 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 14:19:02 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 14:19:02 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 2.76%
[2025-01-18 14:19:04 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][0/312]	eta 0:11:04 lr 0.003883	time 2.1303 (2.1303)	model_time 0.5931 (0.5931)	loss 3.7452 (3.7452)	grad_norm 0.9341 (0.9341/0.0000)	mem 24308MB
[2025-01-18 14:19:10 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][10/312]	eta 0:03:41 lr 0.003883	time 0.5926 (0.7329)	model_time 0.5925 (0.5929)	loss 4.8848 (4.3494)	grad_norm 2.2495 (1.5836/0.4476)	mem 24308MB
[2025-01-18 14:19:16 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][20/312]	eta 0:03:15 lr 0.003882	time 0.6131 (0.6698)	model_time 0.6127 (0.5962)	loss 4.4202 (4.0004)	grad_norm 0.9918 (1.8186/0.7761)	mem 24308MB
[2025-01-18 14:19:22 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][30/312]	eta 0:03:03 lr 0.003882	time 0.5742 (0.6495)	model_time 0.5738 (0.5996)	loss 4.1769 (3.9396)	grad_norm 1.1649 (1.6484/0.7416)	mem 24308MB
[2025-01-18 14:19:28 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][40/312]	eta 0:02:53 lr 0.003882	time 0.5881 (0.6395)	model_time 0.5879 (0.6017)	loss 4.2532 (3.9302)	grad_norm 1.3546 (1.6623/0.6969)	mem 24308MB
[2025-01-18 14:19:34 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][50/312]	eta 0:02:46 lr 0.003882	time 0.6713 (0.6370)	model_time 0.6709 (0.6065)	loss 3.8457 (3.9611)	grad_norm 0.9334 (1.5676/0.6745)	mem 24308MB
[2025-01-18 14:19:40 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][60/312]	eta 0:02:40 lr 0.003882	time 0.7113 (0.6358)	model_time 0.7112 (0.6102)	loss 4.4167 (3.9740)	grad_norm 2.0395 (1.5466/0.6373)	mem 24308MB
[2025-01-18 14:19:47 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][70/312]	eta 0:02:32 lr 0.003881	time 0.6760 (0.6322)	model_time 0.6755 (0.6102)	loss 4.8551 (3.9681)	grad_norm 1.5747 (1.5857/0.6552)	mem 24308MB
[2025-01-18 14:19:53 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][80/312]	eta 0:02:25 lr 0.003881	time 0.5906 (0.6290)	model_time 0.5905 (0.6096)	loss 3.4106 (3.9299)	grad_norm 1.0367 (1.6223/0.6512)	mem 24308MB
[2025-01-18 14:19:58 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][90/312]	eta 0:02:18 lr 0.003881	time 0.6024 (0.6246)	model_time 0.6023 (0.6072)	loss 3.1266 (3.9038)	grad_norm 0.8304 (1.5926/0.6305)	mem 24308MB
[2025-01-18 14:20:04 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][100/312]	eta 0:02:11 lr 0.003881	time 0.6152 (0.6214)	model_time 0.6147 (0.6056)	loss 3.4773 (3.9235)	grad_norm 1.1829 (1.5624/0.6130)	mem 24308MB
[2025-01-18 14:20:10 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][110/312]	eta 0:02:04 lr 0.003880	time 0.5816 (0.6181)	model_time 0.5814 (0.6037)	loss 3.5792 (3.8975)	grad_norm 1.0510 (1.5800/0.6441)	mem 24308MB
[2025-01-18 14:20:16 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][120/312]	eta 0:01:58 lr 0.003880	time 0.5992 (0.6158)	model_time 0.5991 (0.6026)	loss 3.7317 (3.9130)	grad_norm 2.0074 (1.5445/0.6373)	mem 24308MB
[2025-01-18 14:20:22 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][130/312]	eta 0:01:51 lr 0.003880	time 0.5980 (0.6136)	model_time 0.5976 (0.6014)	loss 3.4904 (3.9102)	grad_norm 1.5158 (1.5920/0.7071)	mem 24308MB
[2025-01-18 14:20:28 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][140/312]	eta 0:01:45 lr 0.003880	time 0.5848 (0.6127)	model_time 0.5846 (0.6013)	loss 3.7978 (3.9050)	grad_norm 2.3253 (1.6160/0.6961)	mem 24308MB
[2025-01-18 14:20:34 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][150/312]	eta 0:01:39 lr 0.003880	time 0.8190 (0.6123)	model_time 0.8189 (0.6017)	loss 4.1694 (3.9086)	grad_norm 1.0584 (1.6133/0.6779)	mem 24308MB
[2025-01-18 14:20:40 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][160/312]	eta 0:01:33 lr 0.003879	time 0.5809 (0.6132)	model_time 0.5807 (0.6032)	loss 2.7303 (3.9135)	grad_norm 1.3821 (1.6270/0.6838)	mem 24308MB
[2025-01-18 14:20:47 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][170/312]	eta 0:01:27 lr 0.003879	time 0.6724 (0.6137)	model_time 0.6720 (0.6043)	loss 4.3848 (3.9038)	grad_norm 1.0530 (1.6049/0.6735)	mem 24308MB
[2025-01-18 14:20:53 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][180/312]	eta 0:01:21 lr 0.003879	time 0.6994 (0.6150)	model_time 0.6993 (0.6061)	loss 4.0988 (3.9202)	grad_norm 1.4184 (1.6451/0.6960)	mem 24308MB
[2025-01-18 14:20:59 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][190/312]	eta 0:01:15 lr 0.003879	time 0.6033 (0.6151)	model_time 0.6029 (0.6066)	loss 4.2212 (3.9215)	grad_norm 1.1918 (1.6247/0.6864)	mem 24308MB
[2025-01-18 14:21:05 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][200/312]	eta 0:01:08 lr 0.003878	time 0.5776 (0.6150)	model_time 0.5775 (0.6069)	loss 2.8633 (3.9121)	grad_norm 2.3205 (1.6169/0.6764)	mem 24308MB
[2025-01-18 14:21:11 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][210/312]	eta 0:01:02 lr 0.003878	time 0.5888 (0.6140)	model_time 0.5886 (0.6063)	loss 4.0879 (3.9269)	grad_norm 1.6120 (1.5970/0.6708)	mem 24308MB
[2025-01-18 14:21:17 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][220/312]	eta 0:00:56 lr 0.003878	time 0.5723 (0.6128)	model_time 0.5719 (0.6054)	loss 3.8949 (3.9319)	grad_norm 1.7477 (1.6139/0.6683)	mem 24308MB
[2025-01-18 14:21:23 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][230/312]	eta 0:00:50 lr 0.003878	time 0.5703 (0.6118)	model_time 0.5701 (0.6048)	loss 3.6159 (3.9258)	grad_norm 1.1977 (1.6092/0.6600)	mem 24308MB
[2025-01-18 14:21:29 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][240/312]	eta 0:00:43 lr 0.003877	time 0.5853 (0.6109)	model_time 0.5851 (0.6041)	loss 4.7083 (3.9287)	grad_norm 1.0757 (1.6036/0.6526)	mem 24308MB
[2025-01-18 14:21:35 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][250/312]	eta 0:00:37 lr 0.003877	time 0.5963 (0.6100)	model_time 0.5961 (0.6035)	loss 3.4061 (3.9228)	grad_norm 2.9465 (1.6083/0.6488)	mem 24308MB
[2025-01-18 14:21:41 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][260/312]	eta 0:00:31 lr 0.003877	time 0.5720 (0.6093)	model_time 0.5719 (0.6030)	loss 3.7559 (3.9251)	grad_norm 1.7317 (1.6204/0.6548)	mem 24308MB
[2025-01-18 14:21:47 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][270/312]	eta 0:00:25 lr 0.003877	time 0.6662 (0.6089)	model_time 0.6657 (0.6028)	loss 2.8422 (3.9049)	grad_norm 0.9440 (1.6209/0.6508)	mem 24308MB
[2025-01-18 14:21:53 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][280/312]	eta 0:00:19 lr 0.003877	time 0.5798 (0.6089)	model_time 0.5797 (0.6030)	loss 4.1000 (3.9038)	grad_norm 1.3078 (1.6095/0.6499)	mem 24308MB
[2025-01-18 14:21:59 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][290/312]	eta 0:00:13 lr 0.003876	time 0.6641 (0.6095)	model_time 0.6640 (0.6038)	loss 3.5683 (3.9094)	grad_norm 0.8011 (1.6018/0.6430)	mem 24308MB
[2025-01-18 14:22:05 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][300/312]	eta 0:00:07 lr 0.003876	time 0.6566 (0.6101)	model_time 0.6565 (0.6046)	loss 3.1820 (3.9008)	grad_norm 1.2029 (1.6072/0.6403)	mem 24308MB
[2025-01-18 14:22:11 internimage_s_1k_224] (main.py 510): INFO Train: [33/300][310/312]	eta 0:00:01 lr 0.003876	time 0.5673 (0.6100)	model_time 0.5672 (0.6046)	loss 3.9683 (3.8975)	grad_norm 2.7679 (1.5919/0.6481)	mem 24308MB
[2025-01-18 14:22:12 internimage_s_1k_224] (main.py 519): INFO EPOCH 33 training takes 0:03:10
[2025-01-18 14:22:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_33.pth saving......
[2025-01-18 14:22:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_33.pth saved !!!
[2025-01-18 14:22:21 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.965 (6.965)	Loss 1.0763 (1.0763)	Acc@1 75.415 (75.415)	Acc@5 93.604 (93.604)	Mem 24308MB
[2025-01-18 14:22:24 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.928)	Loss 1.6231 (1.3375)	Acc@1 63.330 (70.255)	Acc@5 86.914 (90.259)	Mem 24308MB
[2025-01-18 14:22:24 internimage_s_1k_224] (main.py 575): INFO [Epoch:33] * Acc@1 70.409 Acc@5 90.429
[2025-01-18 14:22:24 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 70.4%
[2025-01-18 14:22:24 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 14:22:26 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 14:22:26 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 70.41%
[2025-01-18 14:22:33 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.925 (6.925)	Loss 6.2116 (6.2116)	Acc@1 3.198 (3.198)	Acc@5 11.694 (11.694)	Mem 24308MB
[2025-01-18 14:22:36 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.902)	Loss 6.5267 (6.2061)	Acc@1 1.367 (2.925)	Acc@5 6.396 (10.387)	Mem 24308MB
[2025-01-18 14:22:36 internimage_s_1k_224] (main.py 575): INFO [Epoch:33] * Acc@1 3.509 Acc@5 11.758
[2025-01-18 14:22:36 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 3.5%
[2025-01-18 14:22:36 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 14:22:38 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 14:22:38 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 3.51%
[2025-01-18 14:22:40 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][0/312]	eta 0:11:38 lr 0.003876	time 2.2372 (2.2372)	model_time 0.6018 (0.6018)	loss 4.2498 (4.2498)	grad_norm 2.2974 (2.2974/0.0000)	mem 24308MB
[2025-01-18 14:22:47 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][10/312]	eta 0:03:48 lr 0.003876	time 0.5925 (0.7568)	model_time 0.5924 (0.6079)	loss 3.8744 (3.8617)	grad_norm 0.8848 (1.5621/0.4950)	mem 24308MB
[2025-01-18 14:22:52 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][20/312]	eta 0:03:17 lr 0.003875	time 0.5742 (0.6750)	model_time 0.5737 (0.5968)	loss 4.6471 (3.8347)	grad_norm 1.8751 (1.4710/0.4119)	mem 24308MB
[2025-01-18 14:22:58 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][30/312]	eta 0:03:02 lr 0.003875	time 0.5736 (0.6473)	model_time 0.5732 (0.5942)	loss 3.8516 (4.0109)	grad_norm 1.0645 (1.3813/0.4576)	mem 24308MB
[2025-01-18 14:23:04 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][40/312]	eta 0:02:52 lr 0.003875	time 0.5823 (0.6328)	model_time 0.5821 (0.5926)	loss 4.4366 (3.9560)	grad_norm 2.2131 (1.4997/0.5088)	mem 24308MB
[2025-01-18 14:23:10 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][50/312]	eta 0:02:43 lr 0.003875	time 0.5745 (0.6246)	model_time 0.5743 (0.5922)	loss 3.8621 (3.9131)	grad_norm 1.8003 (1.5587/0.5064)	mem 24308MB
[2025-01-18 14:23:16 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][60/312]	eta 0:02:35 lr 0.003874	time 0.5836 (0.6187)	model_time 0.5832 (0.5916)	loss 3.9923 (3.9219)	grad_norm 1.6861 (1.5801/0.5264)	mem 24308MB
[2025-01-18 14:23:22 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][70/312]	eta 0:02:29 lr 0.003874	time 0.5877 (0.6162)	model_time 0.5876 (0.5928)	loss 4.0877 (3.9139)	grad_norm 1.3292 (1.5923/0.5104)	mem 24308MB
[2025-01-18 14:23:28 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][80/312]	eta 0:02:22 lr 0.003874	time 0.5795 (0.6133)	model_time 0.5794 (0.5928)	loss 4.4081 (3.9617)	grad_norm 1.3471 (1.5679/0.5071)	mem 24308MB
[2025-01-18 14:23:34 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][90/312]	eta 0:02:15 lr 0.003874	time 0.5748 (0.6119)	model_time 0.5747 (0.5936)	loss 4.1454 (3.9669)	grad_norm 1.3862 (1.5261/0.5026)	mem 24308MB
[2025-01-18 14:23:40 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][100/312]	eta 0:02:09 lr 0.003873	time 0.6714 (0.6118)	model_time 0.6713 (0.5953)	loss 3.0836 (3.9660)	grad_norm 1.0469 (1.5073/0.5083)	mem 24308MB
[2025-01-18 14:23:46 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][110/312]	eta 0:02:03 lr 0.003873	time 0.6496 (0.6137)	model_time 0.6492 (0.5986)	loss 2.7660 (3.9553)	grad_norm 3.1393 (1.6030/0.6688)	mem 24308MB
[2025-01-18 14:23:53 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][120/312]	eta 0:01:57 lr 0.003873	time 0.5801 (0.6143)	model_time 0.5799 (0.6005)	loss 4.4046 (3.9495)	grad_norm 1.4116 (1.5886/0.6553)	mem 24308MB
[2025-01-18 14:23:59 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][130/312]	eta 0:01:51 lr 0.003873	time 0.5897 (0.6143)	model_time 0.5895 (0.6015)	loss 4.9892 (3.9690)	grad_norm 1.6587 (1.5906/0.6363)	mem 24308MB
[2025-01-18 14:24:05 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][140/312]	eta 0:01:45 lr 0.003873	time 0.5931 (0.6131)	model_time 0.5930 (0.6011)	loss 3.7529 (3.9650)	grad_norm 0.8731 (1.5883/0.6342)	mem 24308MB
[2025-01-18 14:24:11 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][150/312]	eta 0:01:39 lr 0.003872	time 0.5852 (0.6114)	model_time 0.5847 (0.6002)	loss 3.1895 (3.9635)	grad_norm 1.1687 (1.5654/0.6262)	mem 24308MB
[2025-01-18 14:24:16 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][160/312]	eta 0:01:32 lr 0.003872	time 0.5875 (0.6098)	model_time 0.5873 (0.5993)	loss 4.0866 (3.9594)	grad_norm 3.4879 (1.5911/0.6599)	mem 24308MB
[2025-01-18 14:24:22 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][170/312]	eta 0:01:26 lr 0.003872	time 0.5990 (0.6083)	model_time 0.5988 (0.5983)	loss 3.7033 (3.9492)	grad_norm 0.7083 (1.6115/0.6890)	mem 24308MB
[2025-01-18 14:24:28 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][180/312]	eta 0:01:20 lr 0.003872	time 0.6010 (0.6072)	model_time 0.6005 (0.5977)	loss 4.1597 (3.9593)	grad_norm 1.9223 (1.6007/0.6801)	mem 24308MB
[2025-01-18 14:24:34 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][190/312]	eta 0:01:13 lr 0.003871	time 0.5760 (0.6065)	model_time 0.5759 (0.5974)	loss 3.0737 (3.9394)	grad_norm 0.8117 (1.5907/0.6801)	mem 24308MB
[2025-01-18 14:24:40 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][200/312]	eta 0:01:07 lr 0.003871	time 0.7280 (0.6068)	model_time 0.7278 (0.5982)	loss 3.8490 (3.9405)	grad_norm 1.5975 (1.5845/0.6705)	mem 24308MB
[2025-01-18 14:24:46 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][210/312]	eta 0:01:01 lr 0.003871	time 0.5863 (0.6075)	model_time 0.5859 (0.5993)	loss 4.1822 (3.9445)	grad_norm 1.5767 (1.5706/0.6613)	mem 24308MB
[2025-01-18 14:24:53 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][220/312]	eta 0:00:55 lr 0.003871	time 0.6621 (0.6087)	model_time 0.6617 (0.6008)	loss 3.4889 (3.9337)	grad_norm 1.3819 (1.5656/0.6563)	mem 24308MB
[2025-01-18 14:24:59 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][230/312]	eta 0:00:49 lr 0.003870	time 0.5728 (0.6093)	model_time 0.5727 (0.6017)	loss 4.2122 (3.9380)	grad_norm 0.9886 (1.5488/0.6488)	mem 24308MB
[2025-01-18 14:25:05 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][240/312]	eta 0:00:43 lr 0.003870	time 0.5790 (0.6100)	model_time 0.5789 (0.6027)	loss 4.2039 (3.9389)	grad_norm 1.3082 (1.5417/0.6382)	mem 24308MB
[2025-01-18 14:25:11 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][250/312]	eta 0:00:37 lr 0.003870	time 0.5776 (0.6101)	model_time 0.5775 (0.6031)	loss 4.0387 (3.9384)	grad_norm 1.7092 (1.5872/0.7051)	mem 24308MB
[2025-01-18 14:25:17 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][260/312]	eta 0:00:31 lr 0.003870	time 0.5723 (0.6095)	model_time 0.5722 (0.6028)	loss 3.8085 (3.9456)	grad_norm 0.9673 (1.5911/0.7046)	mem 24308MB
[2025-01-18 14:25:23 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][270/312]	eta 0:00:25 lr 0.003869	time 0.5856 (0.6087)	model_time 0.5855 (0.6022)	loss 5.0282 (3.9453)	grad_norm 1.8761 (1.5942/0.6961)	mem 24308MB
[2025-01-18 14:25:29 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][280/312]	eta 0:00:19 lr 0.003869	time 0.5836 (0.6080)	model_time 0.5834 (0.6017)	loss 4.0136 (3.9461)	grad_norm 1.5463 (1.5945/0.6900)	mem 24308MB
[2025-01-18 14:25:35 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][290/312]	eta 0:00:13 lr 0.003869	time 0.5752 (0.6072)	model_time 0.5751 (0.6011)	loss 4.0167 (3.9411)	grad_norm 1.0432 (1.5957/0.6860)	mem 24308MB
[2025-01-18 14:25:41 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][300/312]	eta 0:00:07 lr 0.003869	time 0.5684 (0.6063)	model_time 0.5683 (0.6004)	loss 3.8771 (3.9419)	grad_norm 2.9325 (1.6044/0.6863)	mem 24308MB
[2025-01-18 14:25:47 internimage_s_1k_224] (main.py 510): INFO Train: [34/300][310/312]	eta 0:00:01 lr 0.003869	time 0.5680 (0.6054)	model_time 0.5679 (0.5997)	loss 4.3160 (3.9329)	grad_norm 0.7001 (1.6002/0.6903)	mem 24308MB
[2025-01-18 14:25:47 internimage_s_1k_224] (main.py 519): INFO EPOCH 34 training takes 0:03:08
[2025-01-18 14:25:47 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_34.pth saving......
[2025-01-18 14:25:49 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_34.pth saved !!!
[2025-01-18 14:25:56 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.032 (7.032)	Loss 1.1018 (1.1018)	Acc@1 76.025 (76.025)	Acc@5 93.433 (93.433)	Mem 24308MB
[2025-01-18 14:25:59 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.942)	Loss 1.5883 (1.3283)	Acc@1 65.381 (70.830)	Acc@5 87.183 (90.614)	Mem 24308MB
[2025-01-18 14:25:59 internimage_s_1k_224] (main.py 575): INFO [Epoch:34] * Acc@1 70.893 Acc@5 90.731
[2025-01-18 14:25:59 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 70.9%
[2025-01-18 14:25:59 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 14:26:01 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 14:26:01 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 70.89%
[2025-01-18 14:26:08 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.071 (7.071)	Loss 6.0279 (6.0279)	Acc@1 4.077 (4.077)	Acc@5 13.574 (13.574)	Mem 24308MB
[2025-01-18 14:26:11 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.930)	Loss 6.3205 (6.0058)	Acc@1 2.051 (3.924)	Acc@5 8.911 (12.991)	Mem 24308MB
[2025-01-18 14:26:12 internimage_s_1k_224] (main.py 575): INFO [Epoch:34] * Acc@1 4.557 Acc@5 14.401
[2025-01-18 14:26:12 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 4.6%
[2025-01-18 14:26:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 14:26:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 14:26:14 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 4.56%
[2025-01-18 14:26:16 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][0/312]	eta 0:11:13 lr 0.003868	time 2.1595 (2.1595)	model_time 0.6158 (0.6158)	loss 3.5192 (3.5192)	grad_norm 0.8039 (0.8039/0.0000)	mem 24308MB
[2025-01-18 14:26:22 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][10/312]	eta 0:03:44 lr 0.003868	time 0.5825 (0.7426)	model_time 0.5824 (0.6020)	loss 3.8159 (3.8647)	grad_norm 1.8554 (1.4701/0.4462)	mem 24308MB
[2025-01-18 14:26:28 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][20/312]	eta 0:03:18 lr 0.003868	time 0.5795 (0.6812)	model_time 0.5793 (0.6074)	loss 3.6234 (3.8274)	grad_norm 1.1983 (1.6478/0.6028)	mem 24308MB
[2025-01-18 14:26:34 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][30/312]	eta 0:03:07 lr 0.003868	time 0.5733 (0.6635)	model_time 0.5731 (0.6134)	loss 4.4898 (3.9431)	grad_norm 2.2351 (1.5892/0.5739)	mem 24308MB
[2025-01-18 14:26:41 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][40/312]	eta 0:02:58 lr 0.003868	time 0.5981 (0.6556)	model_time 0.5980 (0.6176)	loss 4.2748 (3.9228)	grad_norm 1.3621 (1.6436/0.5954)	mem 24308MB
[2025-01-18 14:26:47 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][50/312]	eta 0:02:49 lr 0.003867	time 0.5697 (0.6483)	model_time 0.5695 (0.6177)	loss 2.8915 (3.9357)	grad_norm 1.6675 (1.6746/0.5616)	mem 24308MB
[2025-01-18 14:26:53 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][60/312]	eta 0:02:41 lr 0.003867	time 0.5819 (0.6401)	model_time 0.5815 (0.6145)	loss 3.9666 (3.9606)	grad_norm 1.0704 (1.5964/0.5702)	mem 24308MB
[2025-01-18 14:26:59 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][70/312]	eta 0:02:33 lr 0.003867	time 0.5920 (0.6348)	model_time 0.5919 (0.6128)	loss 2.4490 (3.9184)	grad_norm 1.4899 (1.5742/0.5389)	mem 24308MB
[2025-01-18 14:27:05 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][80/312]	eta 0:02:25 lr 0.003867	time 0.5841 (0.6290)	model_time 0.5839 (0.6097)	loss 3.9542 (3.9369)	grad_norm 1.4596 (1.5596/0.5243)	mem 24308MB
[2025-01-18 14:27:11 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][90/312]	eta 0:02:18 lr 0.003866	time 0.5941 (0.6244)	model_time 0.5936 (0.6069)	loss 4.0972 (3.9575)	grad_norm 1.8736 (1.5699/0.5082)	mem 24308MB
[2025-01-18 14:27:17 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][100/312]	eta 0:02:11 lr 0.003866	time 0.5818 (0.6208)	model_time 0.5816 (0.6050)	loss 3.7139 (3.9804)	grad_norm 2.4062 (1.5944/0.5122)	mem 24308MB
[2025-01-18 14:27:22 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][110/312]	eta 0:02:04 lr 0.003866	time 0.5830 (0.6170)	model_time 0.5825 (0.6027)	loss 4.5612 (3.9739)	grad_norm 1.5427 (1.6153/0.5919)	mem 24308MB
[2025-01-18 14:27:28 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][120/312]	eta 0:01:58 lr 0.003866	time 0.5989 (0.6151)	model_time 0.5988 (0.6019)	loss 3.9489 (3.9587)	grad_norm 2.6368 (1.6343/0.6161)	mem 24308MB
[2025-01-18 14:27:34 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][130/312]	eta 0:01:51 lr 0.003865	time 0.5710 (0.6135)	model_time 0.5707 (0.6013)	loss 3.3971 (3.9690)	grad_norm 1.1280 (1.6418/0.6288)	mem 24308MB
[2025-01-18 14:27:40 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][140/312]	eta 0:01:45 lr 0.003865	time 0.5732 (0.6133)	model_time 0.5730 (0.6019)	loss 4.1472 (3.9626)	grad_norm 1.0795 (1.6079/0.6240)	mem 24308MB
[2025-01-18 14:27:47 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][150/312]	eta 0:01:39 lr 0.003865	time 0.5762 (0.6143)	model_time 0.5758 (0.6037)	loss 4.1922 (3.9708)	grad_norm 1.2246 (1.6048/0.6186)	mem 24308MB
[2025-01-18 14:27:53 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][160/312]	eta 0:01:33 lr 0.003865	time 0.5897 (0.6168)	model_time 0.5895 (0.6068)	loss 3.3021 (3.9527)	grad_norm 3.2128 (1.6146/0.6191)	mem 24308MB
[2025-01-18 14:27:59 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][170/312]	eta 0:01:27 lr 0.003864	time 0.6520 (0.6178)	model_time 0.6518 (0.6083)	loss 4.1511 (3.9468)	grad_norm 1.1521 (1.6452/0.6485)	mem 24308MB
[2025-01-18 14:28:06 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][180/312]	eta 0:01:21 lr 0.003864	time 0.5899 (0.6173)	model_time 0.5897 (0.6083)	loss 3.1609 (3.9524)	grad_norm 1.7534 (1.6499/0.6484)	mem 24308MB
[2025-01-18 14:28:12 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][190/312]	eta 0:01:15 lr 0.003864	time 0.5981 (0.6162)	model_time 0.5977 (0.6077)	loss 3.6400 (3.9405)	grad_norm 2.2751 (1.6369/0.6389)	mem 24308MB
[2025-01-18 14:28:17 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][200/312]	eta 0:01:08 lr 0.003864	time 0.5764 (0.6144)	model_time 0.5762 (0.6063)	loss 3.9064 (3.9312)	grad_norm 1.5848 (1.6308/0.6329)	mem 24308MB
[2025-01-18 14:28:23 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][210/312]	eta 0:01:02 lr 0.003863	time 0.5955 (0.6133)	model_time 0.5951 (0.6056)	loss 5.0432 (3.9413)	grad_norm 1.1763 (1.6164/0.6231)	mem 24308MB
[2025-01-18 14:28:29 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][220/312]	eta 0:00:56 lr 0.003863	time 0.5988 (0.6122)	model_time 0.5986 (0.6048)	loss 3.7302 (3.9372)	grad_norm 1.1980 (1.6075/0.6175)	mem 24308MB
[2025-01-18 14:28:35 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][230/312]	eta 0:00:50 lr 0.003863	time 0.5867 (0.6113)	model_time 0.5862 (0.6042)	loss 4.1342 (3.9502)	grad_norm 2.6219 (1.6041/0.6144)	mem 24308MB
[2025-01-18 14:28:41 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][240/312]	eta 0:00:43 lr 0.003863	time 0.5718 (0.6105)	model_time 0.5716 (0.6037)	loss 4.0252 (3.9446)	grad_norm 1.4203 (1.6108/0.6308)	mem 24308MB
[2025-01-18 14:28:47 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][250/312]	eta 0:00:37 lr 0.003862	time 0.6850 (0.6100)	model_time 0.6848 (0.6034)	loss 4.0929 (3.9446)	grad_norm 0.9658 (1.6284/0.6460)	mem 24308MB
[2025-01-18 14:28:53 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][260/312]	eta 0:00:31 lr 0.003862	time 0.5749 (0.6101)	model_time 0.5747 (0.6038)	loss 2.8801 (3.9428)	grad_norm 1.4548 (1.6285/0.6455)	mem 24308MB
[2025-01-18 14:28:59 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][270/312]	eta 0:00:25 lr 0.003862	time 0.7623 (0.6104)	model_time 0.7621 (0.6043)	loss 3.8219 (3.9327)	grad_norm 1.1895 (1.6121/0.6405)	mem 24308MB
[2025-01-18 14:29:06 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][280/312]	eta 0:00:19 lr 0.003862	time 0.5815 (0.6115)	model_time 0.5813 (0.6056)	loss 5.0042 (3.9389)	grad_norm 1.9867 (1.6156/0.6473)	mem 24308MB
[2025-01-18 14:29:12 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][290/312]	eta 0:00:13 lr 0.003861	time 0.5789 (0.6122)	model_time 0.5785 (0.6065)	loss 4.2444 (3.9325)	grad_norm 0.7460 (1.5920/0.6491)	mem 24308MB
[2025-01-18 14:29:18 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][300/312]	eta 0:00:07 lr 0.003861	time 0.6638 (0.6127)	model_time 0.6637 (0.6072)	loss 3.6286 (3.9350)	grad_norm 0.8066 (1.5821/0.6479)	mem 24308MB
[2025-01-18 14:29:24 internimage_s_1k_224] (main.py 510): INFO Train: [35/300][310/312]	eta 0:00:01 lr 0.003861	time 0.5679 (0.6116)	model_time 0.5678 (0.6063)	loss 4.7282 (3.9426)	grad_norm 1.4779 (1.5925/0.6529)	mem 24308MB
[2025-01-18 14:29:25 internimage_s_1k_224] (main.py 519): INFO EPOCH 35 training takes 0:03:10
[2025-01-18 14:29:25 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_35.pth saving......
[2025-01-18 14:29:27 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_35.pth saved !!!
[2025-01-18 14:29:34 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.199 (7.199)	Loss 1.1986 (1.1986)	Acc@1 75.562 (75.562)	Acc@5 93.311 (93.311)	Mem 24308MB
[2025-01-18 14:29:37 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.958)	Loss 1.6870 (1.3763)	Acc@1 63.550 (70.858)	Acc@5 86.914 (90.638)	Mem 24308MB
[2025-01-18 14:29:37 internimage_s_1k_224] (main.py 575): INFO [Epoch:35] * Acc@1 70.899 Acc@5 90.745
[2025-01-18 14:29:37 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 70.9%
[2025-01-18 14:29:37 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 14:29:39 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 14:29:39 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 70.90%
[2025-01-18 14:29:47 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.435 (7.435)	Loss 5.8094 (5.8094)	Acc@1 5.396 (5.396)	Acc@5 16.309 (16.309)	Mem 24308MB
[2025-01-18 14:29:50 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.970)	Loss 6.0987 (5.7819)	Acc@1 3.223 (5.242)	Acc@5 12.427 (16.009)	Mem 24308MB
[2025-01-18 14:29:50 internimage_s_1k_224] (main.py 575): INFO [Epoch:35] * Acc@1 5.896 Acc@5 17.482
[2025-01-18 14:29:50 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 5.9%
[2025-01-18 14:29:50 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 14:29:52 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 14:29:52 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 5.90%
[2025-01-18 14:29:55 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][0/312]	eta 0:12:04 lr 0.003861	time 2.3213 (2.3213)	model_time 0.6146 (0.6146)	loss 4.1508 (4.1508)	grad_norm 1.6236 (1.6236/0.0000)	mem 24308MB
[2025-01-18 14:30:01 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][10/312]	eta 0:03:44 lr 0.003861	time 0.5835 (0.7435)	model_time 0.5830 (0.5881)	loss 4.2026 (3.7898)	grad_norm 1.7645 (1.4376/0.2506)	mem 24308MB
[2025-01-18 14:30:06 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][20/312]	eta 0:03:15 lr 0.003860	time 0.5731 (0.6698)	model_time 0.5727 (0.5877)	loss 3.7404 (3.8040)	grad_norm 0.6971 (1.5075/0.4882)	mem 24308MB
[2025-01-18 14:30:12 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][30/312]	eta 0:03:01 lr 0.003860	time 0.5845 (0.6433)	model_time 0.5840 (0.5876)	loss 2.8350 (3.7893)	grad_norm 1.9938 (1.4437/0.4945)	mem 24308MB
[2025-01-18 14:30:18 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][40/312]	eta 0:02:51 lr 0.003860	time 0.5789 (0.6293)	model_time 0.5785 (0.5871)	loss 4.7769 (3.8313)	grad_norm 1.9922 (1.4813/0.4922)	mem 24308MB
[2025-01-18 14:30:24 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][50/312]	eta 0:02:42 lr 0.003860	time 0.6012 (0.6215)	model_time 0.6010 (0.5875)	loss 4.1735 (3.7881)	grad_norm 1.1232 (1.4675/0.4850)	mem 24308MB
[2025-01-18 14:30:30 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][60/312]	eta 0:02:35 lr 0.003859	time 0.5866 (0.6185)	model_time 0.5864 (0.5900)	loss 4.5183 (3.8481)	grad_norm 0.9834 (1.4070/0.4789)	mem 24308MB
[2025-01-18 14:30:36 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][70/312]	eta 0:02:29 lr 0.003859	time 0.5778 (0.6162)	model_time 0.5773 (0.5917)	loss 4.1613 (3.8663)	grad_norm 1.8206 (1.4118/0.4571)	mem 24308MB
[2025-01-18 14:30:42 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][80/312]	eta 0:02:22 lr 0.003859	time 0.5725 (0.6143)	model_time 0.5723 (0.5927)	loss 3.8226 (3.8651)	grad_norm 0.9915 (1.4212/0.4563)	mem 24308MB
[2025-01-18 14:30:49 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][90/312]	eta 0:02:16 lr 0.003859	time 0.6817 (0.6165)	model_time 0.6816 (0.5973)	loss 4.1309 (3.8694)	grad_norm 1.0768 (1.4345/0.4478)	mem 24308MB
[2025-01-18 14:30:55 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][100/312]	eta 0:02:11 lr 0.003859	time 0.6573 (0.6209)	model_time 0.6569 (0.6035)	loss 4.3091 (3.8624)	grad_norm 2.7885 (1.4546/0.4818)	mem 24308MB
[2025-01-18 14:31:01 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][110/312]	eta 0:02:05 lr 0.003858	time 0.5902 (0.6225)	model_time 0.5898 (0.6067)	loss 4.1970 (3.8873)	grad_norm 1.5005 (1.4595/0.4755)	mem 24308MB
[2025-01-18 14:31:07 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][120/312]	eta 0:01:59 lr 0.003858	time 0.6503 (0.6206)	model_time 0.6499 (0.6060)	loss 2.8339 (3.9014)	grad_norm 1.6453 (1.4772/0.4839)	mem 24308MB
[2025-01-18 14:31:13 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][130/312]	eta 0:01:52 lr 0.003858	time 0.5779 (0.6177)	model_time 0.5778 (0.6043)	loss 4.2398 (3.8980)	grad_norm 1.3568 (1.5001/0.4905)	mem 24308MB
[2025-01-18 14:31:19 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][140/312]	eta 0:01:45 lr 0.003858	time 0.5927 (0.6155)	model_time 0.5926 (0.6029)	loss 4.8671 (3.9150)	grad_norm 1.7025 (1.4904/0.4786)	mem 24308MB
[2025-01-18 14:31:25 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][150/312]	eta 0:01:39 lr 0.003857	time 0.5771 (0.6134)	model_time 0.5769 (0.6016)	loss 3.2512 (3.9124)	grad_norm 1.4668 (1.5138/0.4874)	mem 24308MB
[2025-01-18 14:31:31 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][160/312]	eta 0:01:33 lr 0.003857	time 0.5732 (0.6121)	model_time 0.5728 (0.6010)	loss 4.0872 (3.9044)	grad_norm 1.0787 (1.5211/0.5001)	mem 24308MB
[2025-01-18 14:31:37 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][170/312]	eta 0:01:26 lr 0.003857	time 0.5842 (0.6108)	model_time 0.5838 (0.6003)	loss 2.9692 (3.9002)	grad_norm 3.2904 (1.5259/0.5326)	mem 24308MB
[2025-01-18 14:31:43 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][180/312]	eta 0:01:20 lr 0.003857	time 0.5912 (0.6100)	model_time 0.5910 (0.6001)	loss 4.1110 (3.8951)	grad_norm 2.2707 (1.5409/0.5528)	mem 24308MB
[2025-01-18 14:31:49 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][190/312]	eta 0:01:14 lr 0.003856	time 0.5785 (0.6100)	model_time 0.5781 (0.6006)	loss 3.1588 (3.9110)	grad_norm 3.7255 (1.5483/0.5726)	mem 24308MB
[2025-01-18 14:31:55 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][200/312]	eta 0:01:08 lr 0.003856	time 0.5919 (0.6097)	model_time 0.5914 (0.6007)	loss 4.6846 (3.9123)	grad_norm 0.9444 (1.5630/0.5834)	mem 24308MB
[2025-01-18 14:32:01 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][210/312]	eta 0:01:02 lr 0.003856	time 0.6539 (0.6111)	model_time 0.6537 (0.6025)	loss 3.7126 (3.9078)	grad_norm 0.9029 (1.5620/0.5840)	mem 24308MB
[2025-01-18 14:32:08 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][220/312]	eta 0:00:56 lr 0.003856	time 0.6732 (0.6118)	model_time 0.6728 (0.6036)	loss 2.5750 (3.9078)	grad_norm 1.4847 (1.5547/0.5845)	mem 24308MB
[2025-01-18 14:32:14 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][230/312]	eta 0:00:50 lr 0.003855	time 0.5925 (0.6120)	model_time 0.5923 (0.6041)	loss 4.2869 (3.9190)	grad_norm 2.3443 (1.5653/0.5947)	mem 24308MB
[2025-01-18 14:32:20 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][240/312]	eta 0:00:44 lr 0.003855	time 0.6858 (0.6113)	model_time 0.6857 (0.6037)	loss 4.6183 (3.9145)	grad_norm 0.9608 (1.5536/0.5874)	mem 24308MB
[2025-01-18 14:32:26 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][250/312]	eta 0:00:37 lr 0.003855	time 0.5754 (0.6104)	model_time 0.5753 (0.6031)	loss 4.8662 (3.9187)	grad_norm 1.8859 (1.5647/0.5828)	mem 24308MB
[2025-01-18 14:32:32 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][260/312]	eta 0:00:31 lr 0.003855	time 0.6075 (0.6098)	model_time 0.6074 (0.6027)	loss 3.7982 (3.9247)	grad_norm 0.9395 (1.5523/0.5779)	mem 24308MB
[2025-01-18 14:32:37 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][270/312]	eta 0:00:25 lr 0.003854	time 0.5857 (0.6090)	model_time 0.5853 (0.6022)	loss 4.2019 (3.9395)	grad_norm 1.6989 (1.5400/0.5729)	mem 24308MB
[2025-01-18 14:32:43 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][280/312]	eta 0:00:19 lr 0.003854	time 0.5790 (0.6082)	model_time 0.5788 (0.6016)	loss 4.3202 (3.9464)	grad_norm 1.5633 (1.5466/0.5667)	mem 24308MB
[2025-01-18 14:32:49 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][290/312]	eta 0:00:13 lr 0.003854	time 0.5866 (0.6075)	model_time 0.5865 (0.6011)	loss 4.1278 (3.9373)	grad_norm 1.5264 (1.5401/0.5612)	mem 24308MB
[2025-01-18 14:32:55 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][300/312]	eta 0:00:07 lr 0.003854	time 0.5677 (0.6066)	model_time 0.5676 (0.6004)	loss 4.6267 (3.9299)	grad_norm 2.2633 (1.5466/0.5627)	mem 24308MB
[2025-01-18 14:33:01 internimage_s_1k_224] (main.py 510): INFO Train: [36/300][310/312]	eta 0:00:01 lr 0.003853	time 0.5670 (0.6062)	model_time 0.5669 (0.6002)	loss 3.4459 (3.9327)	grad_norm 1.1739 (1.5601/0.5747)	mem 24308MB
[2025-01-18 14:33:01 internimage_s_1k_224] (main.py 519): INFO EPOCH 36 training takes 0:03:09
[2025-01-18 14:33:02 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_36.pth saving......
[2025-01-18 14:33:03 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_36.pth saved !!!
[2025-01-18 14:33:11 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.271 (7.271)	Loss 1.0578 (1.0578)	Acc@1 76.270 (76.270)	Acc@5 93.701 (93.701)	Mem 24308MB
[2025-01-18 14:33:14 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.954)	Loss 1.5809 (1.3016)	Acc@1 64.648 (71.045)	Acc@5 87.231 (90.823)	Mem 24308MB
[2025-01-18 14:33:14 internimage_s_1k_224] (main.py 575): INFO [Epoch:36] * Acc@1 71.119 Acc@5 90.901
[2025-01-18 14:33:14 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 71.1%
[2025-01-18 14:33:14 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 14:33:16 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 14:33:16 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 71.12%
[2025-01-18 14:33:23 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.164 (7.164)	Loss 5.5622 (5.5622)	Acc@1 7.422 (7.422)	Acc@5 19.897 (19.897)	Mem 24308MB
[2025-01-18 14:33:26 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.958)	Loss 5.8582 (5.5364)	Acc@1 4.858 (7.018)	Acc@5 15.747 (19.618)	Mem 24308MB
[2025-01-18 14:33:27 internimage_s_1k_224] (main.py 575): INFO [Epoch:36] * Acc@1 7.654 Acc@5 21.037
[2025-01-18 14:33:27 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 7.7%
[2025-01-18 14:33:27 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 14:33:29 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 14:33:29 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 7.65%
[2025-01-18 14:33:31 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][0/312]	eta 0:11:23 lr 0.003853	time 2.1893 (2.1893)	model_time 0.6071 (0.6071)	loss 4.6927 (4.6927)	grad_norm 0.9994 (0.9994/0.0000)	mem 24308MB
[2025-01-18 14:33:37 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][10/312]	eta 0:03:48 lr 0.003853	time 0.6666 (0.7555)	model_time 0.6664 (0.6114)	loss 3.1525 (4.1067)	grad_norm 0.9320 (2.0524/0.7489)	mem 24308MB
[2025-01-18 14:33:44 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][20/312]	eta 0:03:24 lr 0.003853	time 0.5727 (0.7020)	model_time 0.5723 (0.6263)	loss 4.1732 (3.9039)	grad_norm 1.0421 (1.7276/0.6852)	mem 24308MB
[2025-01-18 14:33:50 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][30/312]	eta 0:03:12 lr 0.003852	time 0.5956 (0.6818)	model_time 0.5954 (0.6304)	loss 3.7814 (3.8860)	grad_norm 1.1463 (1.6199/0.6079)	mem 24308MB
[2025-01-18 14:33:56 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][40/312]	eta 0:03:00 lr 0.003852	time 0.6032 (0.6654)	model_time 0.6027 (0.6264)	loss 4.1747 (3.8225)	grad_norm 3.9373 (1.8560/0.9207)	mem 24308MB
[2025-01-18 14:34:02 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][50/312]	eta 0:02:50 lr 0.003852	time 0.5809 (0.6519)	model_time 0.5804 (0.6205)	loss 2.7428 (3.8067)	grad_norm 2.1486 (1.8272/0.8891)	mem 24308MB
[2025-01-18 14:34:08 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][60/312]	eta 0:02:41 lr 0.003852	time 0.5945 (0.6413)	model_time 0.5940 (0.6149)	loss 3.7615 (3.8307)	grad_norm 1.0769 (1.7408/0.8469)	mem 24308MB
[2025-01-18 14:34:14 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][70/312]	eta 0:02:33 lr 0.003851	time 0.5999 (0.6344)	model_time 0.5997 (0.6117)	loss 3.7980 (3.8384)	grad_norm 1.4763 (1.6739/0.8085)	mem 24308MB
[2025-01-18 14:34:20 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][80/312]	eta 0:02:25 lr 0.003851	time 0.5850 (0.6286)	model_time 0.5845 (0.6087)	loss 4.3501 (3.8055)	grad_norm 1.3720 (1.6347/0.7743)	mem 24308MB
[2025-01-18 14:34:26 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][90/312]	eta 0:02:18 lr 0.003851	time 0.5833 (0.6237)	model_time 0.5831 (0.6059)	loss 4.1304 (3.8074)	grad_norm 2.4629 (1.6889/0.7923)	mem 24308MB
[2025-01-18 14:34:32 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][100/312]	eta 0:02:11 lr 0.003851	time 0.5842 (0.6203)	model_time 0.5841 (0.6042)	loss 3.4199 (3.8255)	grad_norm 1.3304 (1.6669/0.7781)	mem 24308MB
[2025-01-18 14:34:38 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][110/312]	eta 0:02:05 lr 0.003850	time 0.6753 (0.6196)	model_time 0.6748 (0.6049)	loss 4.1491 (3.8284)	grad_norm 1.0728 (1.6241/0.7594)	mem 24308MB
[2025-01-18 14:34:44 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][120/312]	eta 0:01:58 lr 0.003850	time 0.6608 (0.6176)	model_time 0.6607 (0.6041)	loss 5.0012 (3.8714)	grad_norm 2.0571 (1.6101/0.7387)	mem 24308MB
[2025-01-18 14:34:50 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][130/312]	eta 0:01:52 lr 0.003850	time 0.6663 (0.6172)	model_time 0.6662 (0.6048)	loss 4.4824 (3.8566)	grad_norm 1.1468 (1.6316/0.7551)	mem 24308MB
[2025-01-18 14:34:56 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][140/312]	eta 0:01:46 lr 0.003850	time 0.5819 (0.6180)	model_time 0.5813 (0.6064)	loss 3.2519 (3.8553)	grad_norm 1.1617 (1.6231/0.7528)	mem 24308MB
[2025-01-18 14:35:03 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][150/312]	eta 0:01:40 lr 0.003849	time 0.6569 (0.6198)	model_time 0.6568 (0.6090)	loss 3.9040 (3.8593)	grad_norm 0.7773 (1.5972/0.7385)	mem 24308MB
[2025-01-18 14:35:09 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][160/312]	eta 0:01:34 lr 0.003849	time 0.6684 (0.6200)	model_time 0.6682 (0.6098)	loss 3.3139 (3.8594)	grad_norm 1.9263 (1.6060/0.7356)	mem 24308MB
[2025-01-18 14:35:15 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][170/312]	eta 0:01:27 lr 0.003849	time 0.5818 (0.6181)	model_time 0.5816 (0.6085)	loss 3.0096 (3.8604)	grad_norm 1.4976 (1.6210/0.7459)	mem 24308MB
[2025-01-18 14:35:21 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][180/312]	eta 0:01:21 lr 0.003849	time 0.5773 (0.6171)	model_time 0.5771 (0.6080)	loss 3.5104 (3.8381)	grad_norm 1.1910 (1.6014/0.7327)	mem 24308MB
[2025-01-18 14:35:27 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][190/312]	eta 0:01:15 lr 0.003848	time 0.5903 (0.6156)	model_time 0.5899 (0.6070)	loss 3.9353 (3.8353)	grad_norm 2.0844 (1.5918/0.7299)	mem 24308MB
[2025-01-18 14:35:32 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][200/312]	eta 0:01:08 lr 0.003848	time 0.5850 (0.6142)	model_time 0.5849 (0.6060)	loss 4.8024 (3.8413)	grad_norm 2.1659 (1.6133/0.7335)	mem 24308MB
[2025-01-18 14:35:38 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][210/312]	eta 0:01:02 lr 0.003848	time 0.5711 (0.6130)	model_time 0.5707 (0.6051)	loss 3.0962 (3.8288)	grad_norm 1.3292 (1.6076/0.7254)	mem 24308MB
[2025-01-18 14:35:44 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][220/312]	eta 0:00:56 lr 0.003848	time 0.5821 (0.6118)	model_time 0.5815 (0.6043)	loss 4.1008 (3.8322)	grad_norm 0.7354 (1.5969/0.7134)	mem 24308MB
[2025-01-18 14:35:50 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][230/312]	eta 0:00:50 lr 0.003847	time 0.6757 (0.6116)	model_time 0.6755 (0.6044)	loss 4.3665 (3.8294)	grad_norm 1.0545 (1.5991/0.7034)	mem 24308MB
[2025-01-18 14:35:56 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][240/312]	eta 0:00:43 lr 0.003847	time 0.6799 (0.6110)	model_time 0.6798 (0.6041)	loss 4.0448 (3.8348)	grad_norm 0.7969 (1.5977/0.6975)	mem 24308MB
[2025-01-18 14:36:02 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][250/312]	eta 0:00:37 lr 0.003847	time 0.6533 (0.6110)	model_time 0.6529 (0.6044)	loss 3.8246 (3.8296)	grad_norm 1.5016 (1.5840/0.6886)	mem 24308MB
[2025-01-18 14:36:09 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][260/312]	eta 0:00:31 lr 0.003847	time 0.5833 (0.6117)	model_time 0.5832 (0.6052)	loss 4.7396 (3.8357)	grad_norm 2.4498 (1.6039/0.7048)	mem 24308MB
[2025-01-18 14:36:15 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][270/312]	eta 0:00:25 lr 0.003846	time 0.6793 (0.6125)	model_time 0.6792 (0.6063)	loss 4.0891 (3.8462)	grad_norm 2.5356 (1.5968/0.6978)	mem 24308MB
[2025-01-18 14:36:21 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][280/312]	eta 0:00:19 lr 0.003846	time 0.6682 (0.6134)	model_time 0.6681 (0.6074)	loss 2.8446 (3.8480)	grad_norm 1.0534 (1.5923/0.6923)	mem 24308MB
[2025-01-18 14:36:27 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][290/312]	eta 0:00:13 lr 0.003846	time 0.6199 (0.6126)	model_time 0.6195 (0.6068)	loss 4.2167 (3.8456)	grad_norm 0.8923 (1.5830/0.6889)	mem 24308MB
[2025-01-18 14:36:33 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][300/312]	eta 0:00:07 lr 0.003846	time 0.5685 (0.6120)	model_time 0.5683 (0.6063)	loss 4.4463 (3.8476)	grad_norm 3.1263 (1.5972/0.6894)	mem 24308MB
[2025-01-18 14:36:39 internimage_s_1k_224] (main.py 510): INFO Train: [37/300][310/312]	eta 0:00:01 lr 0.003845	time 0.5605 (0.6107)	model_time 0.5604 (0.6053)	loss 4.5262 (3.8571)	grad_norm 1.8853 (1.5847/0.6869)	mem 24308MB
[2025-01-18 14:36:40 internimage_s_1k_224] (main.py 519): INFO EPOCH 37 training takes 0:03:10
[2025-01-18 14:36:40 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_37.pth saving......
[2025-01-18 14:36:41 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_37.pth saved !!!
[2025-01-18 14:36:49 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.122 (7.122)	Loss 1.0853 (1.0853)	Acc@1 76.318 (76.318)	Acc@5 93.726 (93.726)	Mem 24308MB
[2025-01-18 14:36:52 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.947)	Loss 1.5564 (1.3042)	Acc@1 66.504 (71.651)	Acc@5 87.671 (91.000)	Mem 24308MB
[2025-01-18 14:36:52 internimage_s_1k_224] (main.py 575): INFO [Epoch:37] * Acc@1 71.623 Acc@5 91.029
[2025-01-18 14:36:52 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 71.6%
[2025-01-18 14:36:52 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 14:36:54 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 14:36:54 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 71.62%
[2025-01-18 14:37:01 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.096 (7.096)	Loss 5.2880 (5.2880)	Acc@1 9.668 (9.668)	Acc@5 24.805 (24.805)	Mem 24308MB
[2025-01-18 14:37:04 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.939)	Loss 5.5968 (5.2718)	Acc@1 6.372 (9.155)	Acc@5 19.336 (23.688)	Mem 24308MB
[2025-01-18 14:37:04 internimage_s_1k_224] (main.py 575): INFO [Epoch:37] * Acc@1 9.829 Acc@5 25.080
[2025-01-18 14:37:04 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 9.8%
[2025-01-18 14:37:04 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 14:37:06 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 14:37:06 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 9.83%
[2025-01-18 14:37:09 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][0/312]	eta 0:11:12 lr 0.003845	time 2.1557 (2.1557)	model_time 0.6088 (0.6088)	loss 3.1580 (3.1580)	grad_norm 2.5408 (2.5408/0.0000)	mem 24308MB
[2025-01-18 14:37:15 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][10/312]	eta 0:03:39 lr 0.003845	time 0.5720 (0.7270)	model_time 0.5714 (0.5860)	loss 3.1560 (3.6858)	grad_norm 1.6220 (2.1734/1.0536)	mem 24308MB
[2025-01-18 14:37:20 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][20/312]	eta 0:03:13 lr 0.003845	time 0.6204 (0.6616)	model_time 0.6201 (0.5876)	loss 3.4013 (3.8114)	grad_norm 1.9661 (1.8169/0.8914)	mem 24308MB
[2025-01-18 14:37:26 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][30/312]	eta 0:03:00 lr 0.003845	time 0.6043 (0.6394)	model_time 0.6041 (0.5891)	loss 2.7202 (3.7642)	grad_norm 1.4013 (1.8091/0.8020)	mem 24308MB
[2025-01-18 14:37:32 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][40/312]	eta 0:02:51 lr 0.003844	time 0.6669 (0.6309)	model_time 0.6668 (0.5929)	loss 4.1432 (3.8188)	grad_norm 1.2289 (1.5994/0.7933)	mem 24308MB
[2025-01-18 14:37:38 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][50/312]	eta 0:02:43 lr 0.003844	time 0.5713 (0.6236)	model_time 0.5711 (0.5930)	loss 2.7075 (3.8841)	grad_norm 1.2809 (1.5374/0.7282)	mem 24308MB
[2025-01-18 14:37:44 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][60/312]	eta 0:02:36 lr 0.003844	time 0.5950 (0.6205)	model_time 0.5948 (0.5948)	loss 4.2323 (3.8665)	grad_norm 1.1673 (1.6171/0.7621)	mem 24308MB
[2025-01-18 14:37:51 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][70/312]	eta 0:02:30 lr 0.003843	time 0.6447 (0.6223)	model_time 0.6443 (0.6001)	loss 4.1607 (3.8814)	grad_norm 1.1863 (1.6254/0.7348)	mem 24308MB
[2025-01-18 14:37:57 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][80/312]	eta 0:02:24 lr 0.003843	time 0.6616 (0.6236)	model_time 0.6615 (0.6042)	loss 3.1709 (3.8559)	grad_norm 1.0906 (1.6330/0.7192)	mem 24308MB
[2025-01-18 14:38:03 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][90/312]	eta 0:02:18 lr 0.003843	time 0.6576 (0.6239)	model_time 0.6574 (0.6065)	loss 4.1589 (3.8615)	grad_norm 1.0990 (1.5908/0.7001)	mem 24308MB
[2025-01-18 14:38:09 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][100/312]	eta 0:02:11 lr 0.003843	time 0.5753 (0.6218)	model_time 0.5752 (0.6062)	loss 3.2278 (3.8503)	grad_norm 1.0549 (1.5554/0.6844)	mem 24308MB
[2025-01-18 14:38:15 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][110/312]	eta 0:02:04 lr 0.003842	time 0.5819 (0.6184)	model_time 0.5817 (0.6041)	loss 4.4438 (3.8562)	grad_norm 2.3219 (1.5764/0.6816)	mem 24308MB
[2025-01-18 14:38:21 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][120/312]	eta 0:01:58 lr 0.003842	time 0.5816 (0.6156)	model_time 0.5815 (0.6025)	loss 3.2006 (3.8561)	grad_norm 1.0882 (1.5582/0.6701)	mem 24308MB
[2025-01-18 14:38:27 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][130/312]	eta 0:01:51 lr 0.003842	time 0.5803 (0.6133)	model_time 0.5801 (0.6011)	loss 3.5840 (3.8315)	grad_norm 1.8858 (1.5409/0.6538)	mem 24308MB
[2025-01-18 14:38:33 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][140/312]	eta 0:01:45 lr 0.003842	time 0.5842 (0.6120)	model_time 0.5838 (0.6007)	loss 4.4120 (3.8280)	grad_norm 0.9526 (1.6051/0.7582)	mem 24308MB
[2025-01-18 14:38:39 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][150/312]	eta 0:01:38 lr 0.003841	time 0.5915 (0.6103)	model_time 0.5913 (0.5998)	loss 3.1248 (3.8423)	grad_norm 1.1516 (1.5989/0.7469)	mem 24308MB
[2025-01-18 14:38:45 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][160/312]	eta 0:01:32 lr 0.003841	time 0.5973 (0.6098)	model_time 0.5971 (0.5998)	loss 4.4774 (3.8498)	grad_norm 2.9627 (1.6007/0.7437)	mem 24308MB
[2025-01-18 14:38:51 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][170/312]	eta 0:01:26 lr 0.003841	time 0.6065 (0.6095)	model_time 0.6063 (0.6001)	loss 3.8895 (3.8485)	grad_norm 0.8876 (1.5824/0.7332)	mem 24308MB
[2025-01-18 14:38:57 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][180/312]	eta 0:01:20 lr 0.003841	time 0.6305 (0.6098)	model_time 0.6301 (0.6009)	loss 4.1468 (3.8502)	grad_norm 0.8788 (1.5863/0.7215)	mem 24308MB
[2025-01-18 14:39:03 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][190/312]	eta 0:01:14 lr 0.003840	time 0.7068 (0.6112)	model_time 0.7066 (0.6027)	loss 3.3889 (3.8532)	grad_norm 1.2729 (1.5759/0.7056)	mem 24308MB
[2025-01-18 14:39:10 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][200/312]	eta 0:01:08 lr 0.003840	time 0.6558 (0.6126)	model_time 0.6556 (0.6045)	loss 4.3123 (3.8569)	grad_norm 1.5682 (1.5669/0.6915)	mem 24308MB
[2025-01-18 14:39:16 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][210/312]	eta 0:01:02 lr 0.003840	time 0.6976 (0.6134)	model_time 0.6974 (0.6057)	loss 3.2954 (3.8593)	grad_norm 1.2743 (1.5572/0.6816)	mem 24308MB
[2025-01-18 14:39:22 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][220/312]	eta 0:00:56 lr 0.003840	time 0.5831 (0.6123)	model_time 0.5827 (0.6049)	loss 3.1866 (3.8704)	grad_norm 2.4844 (1.5600/0.6783)	mem 24308MB
[2025-01-18 14:39:28 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][230/312]	eta 0:00:50 lr 0.003839	time 0.5743 (0.6118)	model_time 0.5741 (0.6047)	loss 3.8490 (3.8649)	grad_norm 2.2018 (1.5867/0.6957)	mem 24308MB
[2025-01-18 14:39:34 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][240/312]	eta 0:00:43 lr 0.003839	time 0.5843 (0.6107)	model_time 0.5841 (0.6039)	loss 2.7753 (3.8519)	grad_norm 0.7558 (1.5733/0.6860)	mem 24308MB
[2025-01-18 14:39:40 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][250/312]	eta 0:00:37 lr 0.003839	time 0.5710 (0.6100)	model_time 0.5708 (0.6034)	loss 3.7517 (3.8465)	grad_norm 1.6284 (1.5733/0.6787)	mem 24308MB
[2025-01-18 14:39:46 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][260/312]	eta 0:00:31 lr 0.003839	time 0.6033 (0.6093)	model_time 0.6032 (0.6029)	loss 2.6053 (3.8497)	grad_norm 2.1812 (1.5904/0.6987)	mem 24308MB
[2025-01-18 14:39:51 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][270/312]	eta 0:00:25 lr 0.003838	time 0.5863 (0.6083)	model_time 0.5859 (0.6022)	loss 3.1332 (3.8423)	grad_norm 1.6922 (1.5777/0.6917)	mem 24308MB
[2025-01-18 14:39:57 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][280/312]	eta 0:00:19 lr 0.003838	time 0.5782 (0.6080)	model_time 0.5780 (0.6021)	loss 2.9651 (3.8315)	grad_norm 3.1274 (1.6096/0.7156)	mem 24308MB
[2025-01-18 14:40:03 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][290/312]	eta 0:00:13 lr 0.003838	time 0.5824 (0.6079)	model_time 0.5822 (0.6022)	loss 4.2003 (3.8345)	grad_norm 1.0000 (1.6124/0.7254)	mem 24308MB
[2025-01-18 14:40:09 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][300/312]	eta 0:00:07 lr 0.003837	time 0.5694 (0.6075)	model_time 0.5693 (0.6020)	loss 3.9264 (3.8313)	grad_norm 1.1078 (1.5955/0.7181)	mem 24308MB
[2025-01-18 14:40:15 internimage_s_1k_224] (main.py 510): INFO Train: [38/300][310/312]	eta 0:00:01 lr 0.003837	time 0.6521 (0.6077)	model_time 0.6520 (0.6023)	loss 3.9394 (3.8345)	grad_norm 1.2643 (1.5647/0.6868)	mem 24308MB
[2025-01-18 14:40:16 internimage_s_1k_224] (main.py 519): INFO EPOCH 38 training takes 0:03:09
[2025-01-18 14:40:16 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_38.pth saving......
[2025-01-18 14:40:18 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_38.pth saved !!!
[2025-01-18 14:40:25 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.991 (6.991)	Loss 1.0708 (1.0708)	Acc@1 76.465 (76.465)	Acc@5 94.092 (94.092)	Mem 24308MB
[2025-01-18 14:40:28 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.934)	Loss 1.5732 (1.3096)	Acc@1 64.990 (71.618)	Acc@5 87.769 (91.253)	Mem 24308MB
[2025-01-18 14:40:28 internimage_s_1k_224] (main.py 575): INFO [Epoch:38] * Acc@1 71.627 Acc@5 91.299
[2025-01-18 14:40:28 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 71.6%
[2025-01-18 14:40:28 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 14:40:30 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 14:40:30 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 71.63%
[2025-01-18 14:40:37 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.998 (6.998)	Loss 4.9954 (4.9954)	Acc@1 12.451 (12.451)	Acc@5 30.249 (30.249)	Mem 24308MB
[2025-01-18 14:40:40 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.134 (0.929)	Loss 5.3336 (4.9991)	Acc@1 8.569 (11.748)	Acc@5 22.998 (28.052)	Mem 24308MB
[2025-01-18 14:40:41 internimage_s_1k_224] (main.py 575): INFO [Epoch:38] * Acc@1 12.374 Acc@5 29.427
[2025-01-18 14:40:41 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 12.4%
[2025-01-18 14:40:41 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 14:40:43 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 14:40:43 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 12.37%
[2025-01-18 14:40:45 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][0/312]	eta 0:11:56 lr 0.003837	time 2.2962 (2.2962)	model_time 0.5949 (0.5949)	loss 4.0510 (4.0510)	grad_norm 1.4677 (1.4677/0.0000)	mem 24308MB
[2025-01-18 14:40:51 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][10/312]	eta 0:03:57 lr 0.003837	time 0.7114 (0.7863)	model_time 0.7113 (0.6313)	loss 4.5800 (3.6270)	grad_norm 1.7453 (2.0194/1.2619)	mem 24308MB
[2025-01-18 14:40:58 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][20/312]	eta 0:03:27 lr 0.003837	time 0.5850 (0.7121)	model_time 0.5848 (0.6307)	loss 2.7888 (3.6513)	grad_norm 1.0598 (1.7585/1.0266)	mem 24308MB
[2025-01-18 14:41:04 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][30/312]	eta 0:03:09 lr 0.003836	time 0.5922 (0.6728)	model_time 0.5920 (0.6176)	loss 2.5446 (3.6123)	grad_norm 1.6852 (1.6471/0.8973)	mem 24308MB
[2025-01-18 14:41:10 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][40/312]	eta 0:02:58 lr 0.003836	time 0.5835 (0.6547)	model_time 0.5833 (0.6129)	loss 2.3784 (3.6039)	grad_norm 1.8453 (1.5466/0.8252)	mem 24308MB
[2025-01-18 14:41:15 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][50/312]	eta 0:02:48 lr 0.003836	time 0.5845 (0.6413)	model_time 0.5843 (0.6076)	loss 3.9868 (3.6430)	grad_norm 1.1016 (1.4930/0.7638)	mem 24308MB
[2025-01-18 14:41:21 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][60/312]	eta 0:02:39 lr 0.003836	time 0.5876 (0.6325)	model_time 0.5875 (0.6043)	loss 4.3065 (3.6744)	grad_norm 1.7571 (1.5761/0.8061)	mem 24308MB
[2025-01-18 14:41:27 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][70/312]	eta 0:02:31 lr 0.003835	time 0.5874 (0.6262)	model_time 0.5870 (0.6019)	loss 2.6913 (3.6994)	grad_norm 0.7897 (1.5583/0.7665)	mem 24308MB
[2025-01-18 14:41:33 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][80/312]	eta 0:02:24 lr 0.003835	time 0.5944 (0.6212)	model_time 0.5942 (0.5999)	loss 4.6128 (3.7263)	grad_norm 1.2950 (1.5450/0.7318)	mem 24308MB
[2025-01-18 14:41:39 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][90/312]	eta 0:02:17 lr 0.003835	time 0.5849 (0.6187)	model_time 0.5846 (0.5997)	loss 3.2563 (3.7503)	grad_norm 1.7641 (1.5294/0.7005)	mem 24308MB
[2025-01-18 14:41:45 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][100/312]	eta 0:02:10 lr 0.003835	time 0.5844 (0.6172)	model_time 0.5840 (0.6001)	loss 3.6410 (3.7784)	grad_norm 3.0607 (1.5512/0.6890)	mem 24308MB
[2025-01-18 14:41:51 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][110/312]	eta 0:02:04 lr 0.003834	time 0.5900 (0.6152)	model_time 0.5895 (0.5996)	loss 4.0165 (3.7552)	grad_norm 2.6030 (1.5842/0.7207)	mem 24308MB
[2025-01-18 14:41:57 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][120/312]	eta 0:01:58 lr 0.003834	time 0.6666 (0.6164)	model_time 0.6661 (0.6020)	loss 3.3960 (3.7885)	grad_norm 0.9354 (1.5945/0.7395)	mem 24308MB
[2025-01-18 14:42:04 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][130/312]	eta 0:01:52 lr 0.003834	time 0.7575 (0.6186)	model_time 0.7573 (0.6053)	loss 4.1911 (3.8043)	grad_norm 2.0255 (1.5675/0.7240)	mem 24308MB
[2025-01-18 14:42:10 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][140/312]	eta 0:01:46 lr 0.003833	time 0.5758 (0.6192)	model_time 0.5756 (0.6067)	loss 4.0886 (3.8097)	grad_norm 2.1921 (1.5769/0.7220)	mem 24308MB
[2025-01-18 14:42:16 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][150/312]	eta 0:01:40 lr 0.003833	time 0.5862 (0.6177)	model_time 0.5857 (0.6061)	loss 3.8077 (3.8189)	grad_norm 0.8026 (1.5872/0.7274)	mem 24308MB
[2025-01-18 14:42:22 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][160/312]	eta 0:01:33 lr 0.003833	time 0.5815 (0.6162)	model_time 0.5813 (0.6053)	loss 2.7843 (3.8318)	grad_norm 0.8112 (1.5703/0.7127)	mem 24308MB
[2025-01-18 14:42:28 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][170/312]	eta 0:01:27 lr 0.003833	time 0.6090 (0.6145)	model_time 0.6086 (0.6042)	loss 4.2939 (3.8229)	grad_norm 1.5027 (1.5709/0.7034)	mem 24308MB
[2025-01-18 14:42:34 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][180/312]	eta 0:01:20 lr 0.003832	time 0.5811 (0.6128)	model_time 0.5810 (0.6031)	loss 3.4063 (3.8369)	grad_norm 1.5068 (1.5743/0.6938)	mem 24308MB
[2025-01-18 14:42:39 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][190/312]	eta 0:01:14 lr 0.003832	time 0.5714 (0.6115)	model_time 0.5709 (0.6022)	loss 3.9605 (3.8288)	grad_norm 1.1972 (1.5817/0.6995)	mem 24308MB
[2025-01-18 14:42:45 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][200/312]	eta 0:01:08 lr 0.003832	time 0.5882 (0.6103)	model_time 0.5880 (0.6015)	loss 2.8175 (3.8103)	grad_norm 0.9231 (1.5670/0.6926)	mem 24308MB
[2025-01-18 14:42:51 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][210/312]	eta 0:01:02 lr 0.003832	time 0.5911 (0.6093)	model_time 0.5907 (0.6009)	loss 4.3726 (3.8064)	grad_norm 1.2615 (1.5711/0.6971)	mem 24308MB
[2025-01-18 14:42:57 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][220/312]	eta 0:00:56 lr 0.003831	time 0.5831 (0.6090)	model_time 0.5827 (0.6010)	loss 2.9520 (3.8067)	grad_norm 1.4640 (1.5666/0.6833)	mem 24308MB
[2025-01-18 14:43:03 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][230/312]	eta 0:00:49 lr 0.003831	time 0.5800 (0.6087)	model_time 0.5795 (0.6010)	loss 3.9522 (3.7975)	grad_norm 1.7381 (1.5472/0.6787)	mem 24308MB
[2025-01-18 14:43:10 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][240/312]	eta 0:00:43 lr 0.003831	time 0.6532 (0.6096)	model_time 0.6531 (0.6021)	loss 4.6880 (3.8032)	grad_norm 2.2050 (1.5521/0.6689)	mem 24308MB
[2025-01-18 14:43:16 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][250/312]	eta 0:00:37 lr 0.003830	time 0.6576 (0.6102)	model_time 0.6572 (0.6031)	loss 4.7582 (3.7952)	grad_norm 1.6382 (1.5549/0.6605)	mem 24308MB
[2025-01-18 14:43:22 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][260/312]	eta 0:00:31 lr 0.003830	time 0.5875 (0.6105)	model_time 0.5871 (0.6037)	loss 4.2170 (3.7980)	grad_norm 0.8069 (1.5476/0.6567)	mem 24308MB
[2025-01-18 14:43:28 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][270/312]	eta 0:00:25 lr 0.003830	time 0.5742 (0.6101)	model_time 0.5737 (0.6035)	loss 3.8703 (3.7881)	grad_norm 1.0340 (1.5356/0.6490)	mem 24308MB
[2025-01-18 14:43:34 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][280/312]	eta 0:00:19 lr 0.003830	time 0.5925 (0.6096)	model_time 0.5924 (0.6032)	loss 3.9140 (3.7896)	grad_norm 1.0616 (1.5258/0.6437)	mem 24308MB
[2025-01-18 14:43:40 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][290/312]	eta 0:00:13 lr 0.003829	time 0.5743 (0.6088)	model_time 0.5741 (0.6026)	loss 4.2200 (3.7856)	grad_norm 1.1716 (1.5329/0.6418)	mem 24308MB
[2025-01-18 14:43:46 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][300/312]	eta 0:00:07 lr 0.003829	time 0.5677 (0.6080)	model_time 0.5676 (0.6020)	loss 3.9709 (3.7924)	grad_norm 1.8844 (1.5557/0.6613)	mem 24308MB
[2025-01-18 14:43:51 internimage_s_1k_224] (main.py 510): INFO Train: [39/300][310/312]	eta 0:00:01 lr 0.003829	time 0.5675 (0.6066)	model_time 0.5674 (0.6008)	loss 3.5852 (3.7930)	grad_norm 2.4891 (1.5420/0.6172)	mem 24308MB
[2025-01-18 14:43:52 internimage_s_1k_224] (main.py 519): INFO EPOCH 39 training takes 0:03:09
[2025-01-18 14:43:52 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_39.pth saving......
[2025-01-18 14:43:54 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_39.pth saved !!!
[2025-01-18 14:44:01 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.131 (7.131)	Loss 1.0660 (1.0660)	Acc@1 75.488 (75.488)	Acc@5 93.359 (93.359)	Mem 24308MB
[2025-01-18 14:44:04 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.931)	Loss 1.5785 (1.2787)	Acc@1 64.917 (71.469)	Acc@5 87.622 (91.013)	Mem 24308MB
[2025-01-18 14:44:04 internimage_s_1k_224] (main.py 575): INFO [Epoch:39] * Acc@1 71.499 Acc@5 91.131
[2025-01-18 14:44:04 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 71.5%
[2025-01-18 14:44:04 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 71.63%
[2025-01-18 14:44:12 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.031 (8.031)	Loss 4.6868 (4.6868)	Acc@1 15.503 (15.503)	Acc@5 35.791 (35.791)	Mem 24308MB
[2025-01-18 14:44:16 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (1.095)	Loss 5.0665 (4.7199)	Acc@1 11.157 (14.577)	Acc@5 27.026 (32.806)	Mem 24308MB
[2025-01-18 14:44:16 internimage_s_1k_224] (main.py 575): INFO [Epoch:39] * Acc@1 15.191 Acc@5 34.119
[2025-01-18 14:44:16 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 15.2%
[2025-01-18 14:44:16 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 14:44:19 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 14:44:19 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 15.19%
[2025-01-18 14:44:21 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][0/312]	eta 0:11:26 lr 0.003829	time 2.1993 (2.1993)	model_time 0.5886 (0.5886)	loss 3.5634 (3.5634)	grad_norm 1.8938 (1.8938/0.0000)	mem 24308MB
[2025-01-18 14:44:27 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][10/312]	eta 0:03:41 lr 0.003829	time 0.5789 (0.7336)	model_time 0.5785 (0.5868)	loss 3.2675 (3.6398)	grad_norm 1.4726 (1.3017/0.3050)	mem 24308MB
[2025-01-18 14:44:33 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][20/312]	eta 0:03:14 lr 0.003828	time 0.5922 (0.6659)	model_time 0.5921 (0.5889)	loss 4.1828 (3.8017)	grad_norm 1.1483 (1.2508/0.3754)	mem 24308MB
[2025-01-18 14:44:39 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][30/312]	eta 0:03:02 lr 0.003828	time 0.5714 (0.6463)	model_time 0.5709 (0.5940)	loss 4.4017 (3.8504)	grad_norm 1.3942 (1.4323/0.5169)	mem 24308MB
[2025-01-18 14:44:45 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][40/312]	eta 0:02:53 lr 0.003828	time 0.6005 (0.6369)	model_time 0.6003 (0.5973)	loss 4.1228 (3.8922)	grad_norm 2.6912 (1.5682/0.6417)	mem 24308MB
[2025-01-18 14:44:51 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][50/312]	eta 0:02:46 lr 0.003827	time 0.5750 (0.6342)	model_time 0.5745 (0.6023)	loss 3.0638 (3.9081)	grad_norm 1.6479 (1.5827/0.6413)	mem 24308MB
[2025-01-18 14:44:58 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][60/312]	eta 0:02:39 lr 0.003827	time 0.5974 (0.6336)	model_time 0.5972 (0.6069)	loss 4.7700 (3.8771)	grad_norm 1.1296 (1.5289/0.6105)	mem 24308MB
[2025-01-18 14:45:04 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][70/312]	eta 0:02:33 lr 0.003827	time 0.5840 (0.6334)	model_time 0.5835 (0.6104)	loss 4.1878 (3.8793)	grad_norm 2.4982 (1.5640/0.6084)	mem 24308MB
[2025-01-18 14:45:10 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][80/312]	eta 0:02:25 lr 0.003827	time 0.5805 (0.6284)	model_time 0.5803 (0.6082)	loss 3.1916 (3.8642)	grad_norm 1.1790 (1.5471/0.5803)	mem 24308MB
[2025-01-18 14:45:16 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][90/312]	eta 0:02:18 lr 0.003826	time 0.5750 (0.6250)	model_time 0.5748 (0.6069)	loss 4.0155 (3.8478)	grad_norm 2.1089 (1.6267/0.6254)	mem 24308MB
[2025-01-18 14:45:22 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][100/312]	eta 0:02:11 lr 0.003826	time 0.5819 (0.6210)	model_time 0.5817 (0.6047)	loss 2.9057 (3.8632)	grad_norm 1.5319 (1.6206/0.6243)	mem 24308MB
[2025-01-18 14:45:28 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][110/312]	eta 0:02:04 lr 0.003826	time 0.6782 (0.6186)	model_time 0.6777 (0.6038)	loss 4.1433 (3.8841)	grad_norm 1.4147 (1.6806/0.7255)	mem 24308MB
[2025-01-18 14:45:33 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][120/312]	eta 0:01:58 lr 0.003826	time 0.5906 (0.6157)	model_time 0.5904 (0.6021)	loss 4.3666 (3.8772)	grad_norm 0.6692 (1.6821/0.7333)	mem 24308MB
[2025-01-18 14:45:39 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][130/312]	eta 0:01:51 lr 0.003825	time 0.5918 (0.6139)	model_time 0.5913 (0.6012)	loss 3.6785 (3.8677)	grad_norm 2.3255 (1.6904/0.7215)	mem 24308MB
[2025-01-18 14:45:45 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][140/312]	eta 0:01:45 lr 0.003825	time 0.5714 (0.6117)	model_time 0.5713 (0.5999)	loss 3.2062 (3.8732)	grad_norm 1.2800 (1.6876/0.7184)	mem 24308MB
[2025-01-18 14:45:51 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][150/312]	eta 0:01:39 lr 0.003825	time 0.6868 (0.6120)	model_time 0.6866 (0.6010)	loss 4.3130 (3.8760)	grad_norm 1.6959 (1.6652/0.7058)	mem 24308MB
[2025-01-18 14:45:57 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][160/312]	eta 0:01:32 lr 0.003824	time 0.6752 (0.6115)	model_time 0.6751 (0.6011)	loss 4.2027 (3.8681)	grad_norm 1.0016 (1.6562/0.7021)	mem 24308MB
[2025-01-18 14:46:03 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][170/312]	eta 0:01:26 lr 0.003824	time 0.5978 (0.6116)	model_time 0.5973 (0.6018)	loss 3.8093 (3.8686)	grad_norm 1.1082 (1.6261/0.6944)	mem 24308MB
[2025-01-18 14:46:10 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][180/312]	eta 0:01:20 lr 0.003824	time 0.5723 (0.6127)	model_time 0.5719 (0.6034)	loss 4.1360 (3.8724)	grad_norm 1.1795 (1.6136/0.6826)	mem 24308MB
[2025-01-18 14:46:16 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][190/312]	eta 0:01:14 lr 0.003824	time 0.6583 (0.6143)	model_time 0.6582 (0.6055)	loss 4.3505 (3.8776)	grad_norm 1.2191 (1.6188/0.6796)	mem 24308MB
[2025-01-18 14:46:22 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][200/312]	eta 0:01:08 lr 0.003823	time 0.5877 (0.6135)	model_time 0.5875 (0.6051)	loss 4.0882 (3.8830)	grad_norm 1.3749 (1.6092/0.6705)	mem 24308MB
[2025-01-18 14:46:28 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][210/312]	eta 0:01:02 lr 0.003823	time 0.6041 (0.6128)	model_time 0.6039 (0.6047)	loss 4.5064 (3.8847)	grad_norm 1.1664 (1.6095/0.6618)	mem 24308MB
[2025-01-18 14:46:34 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][220/312]	eta 0:00:56 lr 0.003823	time 0.5935 (0.6115)	model_time 0.5931 (0.6039)	loss 3.9174 (3.8849)	grad_norm 2.3671 (1.6149/0.6695)	mem 24308MB
[2025-01-18 14:46:40 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][230/312]	eta 0:00:50 lr 0.003823	time 0.6832 (0.6109)	model_time 0.6827 (0.6035)	loss 4.0362 (3.8782)	grad_norm 0.8372 (1.6162/0.6659)	mem 24308MB
[2025-01-18 14:46:46 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][240/312]	eta 0:00:43 lr 0.003822	time 0.5829 (0.6100)	model_time 0.5828 (0.6029)	loss 4.6272 (3.8898)	grad_norm 1.6984 (1.6080/0.6596)	mem 24308MB
[2025-01-18 14:46:52 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][250/312]	eta 0:00:37 lr 0.003822	time 0.5868 (0.6090)	model_time 0.5866 (0.6022)	loss 3.4415 (3.8922)	grad_norm 1.2376 (1.5930/0.6529)	mem 24308MB
[2025-01-18 14:46:58 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][260/312]	eta 0:00:31 lr 0.003822	time 0.5922 (0.6083)	model_time 0.5917 (0.6017)	loss 4.9104 (3.8939)	grad_norm 2.6523 (1.5942/0.6486)	mem 24308MB
[2025-01-18 14:47:04 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][270/312]	eta 0:00:25 lr 0.003821	time 0.6763 (0.6082)	model_time 0.6759 (0.6019)	loss 3.2840 (3.8777)	grad_norm 0.9010 (1.5805/0.6452)	mem 24308MB
[2025-01-18 14:47:10 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][280/312]	eta 0:00:19 lr 0.003821	time 0.6787 (0.6084)	model_time 0.6785 (0.6023)	loss 2.8800 (3.8742)	grad_norm 1.2945 (1.5769/0.6382)	mem 24308MB
[2025-01-18 14:47:16 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][290/312]	eta 0:00:13 lr 0.003821	time 0.6533 (0.6085)	model_time 0.6529 (0.6025)	loss 4.8828 (3.8850)	grad_norm 1.1657 (1.5931/0.6479)	mem 24308MB
[2025-01-18 14:47:22 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][300/312]	eta 0:00:07 lr 0.003821	time 0.5646 (0.6091)	model_time 0.5645 (0.6033)	loss 3.5203 (3.8774)	grad_norm 0.9955 (1.5868/0.6424)	mem 24308MB
[2025-01-18 14:47:28 internimage_s_1k_224] (main.py 510): INFO Train: [40/300][310/312]	eta 0:00:01 lr 0.003820	time 0.6524 (0.6096)	model_time 0.6523 (0.6040)	loss 3.8167 (3.8696)	grad_norm 1.2241 (1.5844/0.6432)	mem 24308MB
[2025-01-18 14:47:29 internimage_s_1k_224] (main.py 519): INFO EPOCH 40 training takes 0:03:10
[2025-01-18 14:47:29 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_40.pth saving......
[2025-01-18 14:47:31 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_40.pth saved !!!
[2025-01-18 14:47:38 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.109 (7.109)	Loss 1.0910 (1.0910)	Acc@1 76.050 (76.050)	Acc@5 93.896 (93.896)	Mem 24308MB
[2025-01-18 14:47:41 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.924)	Loss 1.5832 (1.3299)	Acc@1 66.357 (71.682)	Acc@5 87.646 (90.865)	Mem 24308MB
[2025-01-18 14:47:41 internimage_s_1k_224] (main.py 575): INFO [Epoch:40] * Acc@1 71.727 Acc@5 90.993
[2025-01-18 14:47:41 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 71.7%
[2025-01-18 14:47:41 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 14:47:43 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 14:47:43 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 71.73%
[2025-01-18 14:47:50 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.011 (7.011)	Loss 4.3821 (4.3821)	Acc@1 19.922 (19.922)	Acc@5 41.138 (41.138)	Mem 24308MB
[2025-01-18 14:47:53 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.931)	Loss 4.8034 (4.4452)	Acc@1 13.647 (17.758)	Acc@5 31.934 (37.835)	Mem 24308MB
[2025-01-18 14:47:53 internimage_s_1k_224] (main.py 575): INFO [Epoch:40] * Acc@1 18.366 Acc@5 39.038
[2025-01-18 14:47:53 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 18.4%
[2025-01-18 14:47:53 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 14:47:56 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 14:47:56 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 18.37%
[2025-01-18 14:47:58 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][0/312]	eta 0:10:58 lr 0.003820	time 2.1102 (2.1102)	model_time 0.6030 (0.6030)	loss 3.1481 (3.1481)	grad_norm 1.7892 (1.7892/0.0000)	mem 24308MB
[2025-01-18 14:48:04 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][10/312]	eta 0:03:43 lr 0.003820	time 0.5854 (0.7388)	model_time 0.5850 (0.6015)	loss 3.0036 (3.5956)	grad_norm 2.4680 (1.4987/0.4960)	mem 24308MB
[2025-01-18 14:48:10 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][20/312]	eta 0:03:15 lr 0.003820	time 0.5762 (0.6693)	model_time 0.5761 (0.5972)	loss 3.9889 (3.8077)	grad_norm 2.8350 (1.6995/0.6016)	mem 24308MB
[2025-01-18 14:48:16 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][30/312]	eta 0:03:01 lr 0.003819	time 0.5722 (0.6427)	model_time 0.5720 (0.5937)	loss 3.7216 (3.8086)	grad_norm 1.5081 (1.6292/0.5433)	mem 24308MB
[2025-01-18 14:48:22 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][40/312]	eta 0:02:51 lr 0.003819	time 0.5725 (0.6310)	model_time 0.5723 (0.5939)	loss 4.5451 (3.8765)	grad_norm 1.0323 (1.4988/0.5342)	mem 24308MB
[2025-01-18 14:48:28 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][50/312]	eta 0:02:43 lr 0.003819	time 0.5866 (0.6241)	model_time 0.5864 (0.5942)	loss 3.9006 (3.8301)	grad_norm 1.2006 (1.5723/0.6243)	mem 24308MB
[2025-01-18 14:48:33 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][60/312]	eta 0:02:35 lr 0.003819	time 0.5896 (0.6179)	model_time 0.5891 (0.5929)	loss 4.2618 (3.8692)	grad_norm 3.8355 (1.6109/0.6600)	mem 24308MB
[2025-01-18 14:48:39 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][70/312]	eta 0:02:28 lr 0.003818	time 0.5718 (0.6136)	model_time 0.5716 (0.5920)	loss 3.5271 (3.8125)	grad_norm 1.6754 (1.6378/0.6690)	mem 24308MB
[2025-01-18 14:48:45 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][80/312]	eta 0:02:22 lr 0.003818	time 0.6568 (0.6130)	model_time 0.6566 (0.5940)	loss 3.2968 (3.8431)	grad_norm 1.0797 (1.6154/0.6377)	mem 24308MB
[2025-01-18 14:48:51 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][90/312]	eta 0:02:15 lr 0.003818	time 0.6782 (0.6115)	model_time 0.6780 (0.5946)	loss 4.2211 (3.8336)	grad_norm 1.5115 (1.6038/0.6494)	mem 24308MB
[2025-01-18 14:48:58 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][100/312]	eta 0:02:09 lr 0.003818	time 0.5740 (0.6124)	model_time 0.5736 (0.5971)	loss 4.3868 (3.8312)	grad_norm 0.9763 (1.6254/0.6350)	mem 24308MB
[2025-01-18 14:49:04 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][110/312]	eta 0:02:03 lr 0.003817	time 0.5774 (0.6132)	model_time 0.5773 (0.5992)	loss 4.6296 (3.8449)	grad_norm 2.3987 (1.6177/0.6165)	mem 24308MB
[2025-01-18 14:49:10 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][120/312]	eta 0:01:58 lr 0.003817	time 0.5746 (0.6147)	model_time 0.5745 (0.6019)	loss 4.6952 (3.8632)	grad_norm 2.2566 (1.6219/0.6049)	mem 24308MB
[2025-01-18 14:49:16 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][130/312]	eta 0:01:51 lr 0.003817	time 0.5869 (0.6141)	model_time 0.5864 (0.6023)	loss 4.1684 (3.8886)	grad_norm 1.5833 (1.6333/0.5932)	mem 24308MB
[2025-01-18 14:49:22 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][140/312]	eta 0:01:45 lr 0.003816	time 0.5717 (0.6131)	model_time 0.5712 (0.6020)	loss 3.9979 (3.8766)	grad_norm 0.9394 (1.6103/0.5857)	mem 24308MB
[2025-01-18 14:49:28 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][150/312]	eta 0:01:39 lr 0.003816	time 0.5916 (0.6116)	model_time 0.5914 (0.6012)	loss 4.7654 (3.8809)	grad_norm 1.5460 (1.6243/0.5867)	mem 24308MB
[2025-01-18 14:49:34 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][160/312]	eta 0:01:32 lr 0.003816	time 0.5843 (0.6098)	model_time 0.5842 (0.6001)	loss 3.6587 (3.8744)	grad_norm 1.2601 (1.6350/0.6090)	mem 24308MB
[2025-01-18 14:49:40 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][170/312]	eta 0:01:26 lr 0.003816	time 0.5834 (0.6092)	model_time 0.5829 (0.6000)	loss 4.0683 (3.8788)	grad_norm 2.0739 (1.6460/0.6125)	mem 24308MB
[2025-01-18 14:49:46 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][180/312]	eta 0:01:20 lr 0.003815	time 0.5822 (0.6078)	model_time 0.5821 (0.5990)	loss 3.9997 (3.8749)	grad_norm 1.5539 (1.6386/0.6074)	mem 24308MB
[2025-01-18 14:49:52 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][190/312]	eta 0:01:14 lr 0.003815	time 0.5752 (0.6066)	model_time 0.5750 (0.5983)	loss 3.0828 (3.8580)	grad_norm 0.9522 (1.6160/0.6019)	mem 24308MB
[2025-01-18 14:49:58 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][200/312]	eta 0:01:07 lr 0.003815	time 0.5930 (0.6063)	model_time 0.5929 (0.5983)	loss 4.6006 (3.8452)	grad_norm 1.0718 (1.6182/0.6063)	mem 24308MB
[2025-01-18 14:50:04 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][210/312]	eta 0:01:01 lr 0.003814	time 0.6640 (0.6064)	model_time 0.6639 (0.5989)	loss 3.0780 (3.8315)	grad_norm 2.5458 (1.6134/0.5998)	mem 24308MB
[2025-01-18 14:50:10 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][220/312]	eta 0:00:55 lr 0.003814	time 0.5751 (0.6070)	model_time 0.5749 (0.5998)	loss 2.7765 (3.8446)	grad_norm 2.1508 (1.6244/0.6230)	mem 24308MB
[2025-01-18 14:50:16 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][230/312]	eta 0:00:49 lr 0.003814	time 0.6593 (0.6081)	model_time 0.6592 (0.6012)	loss 4.7058 (3.8653)	grad_norm 1.8877 (1.6150/0.6176)	mem 24308MB
[2025-01-18 14:50:22 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][240/312]	eta 0:00:43 lr 0.003814	time 0.5948 (0.6089)	model_time 0.5943 (0.6022)	loss 4.8487 (3.8663)	grad_norm 0.8197 (1.6143/0.6231)	mem 24308MB
[2025-01-18 14:50:29 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][250/312]	eta 0:00:37 lr 0.003813	time 0.5970 (0.6088)	model_time 0.5966 (0.6024)	loss 4.7728 (3.8707)	grad_norm 1.5322 (1.6094/0.6150)	mem 24308MB
[2025-01-18 14:50:35 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][260/312]	eta 0:00:31 lr 0.003813	time 0.6017 (0.6084)	model_time 0.6015 (0.6022)	loss 3.5522 (3.8763)	grad_norm 1.1021 (1.6030/0.6105)	mem 24308MB
[2025-01-18 14:50:40 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][270/312]	eta 0:00:25 lr 0.003813	time 0.5718 (0.6075)	model_time 0.5716 (0.6015)	loss 4.6928 (3.8740)	grad_norm 3.8338 (1.6297/0.6413)	mem 24308MB
[2025-01-18 14:50:46 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][280/312]	eta 0:00:19 lr 0.003812	time 0.6084 (0.6068)	model_time 0.6082 (0.6010)	loss 2.7201 (3.8626)	grad_norm 1.0306 (1.6547/0.6998)	mem 24308MB
[2025-01-18 14:50:52 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][290/312]	eta 0:00:13 lr 0.003812	time 0.5975 (0.6066)	model_time 0.5973 (0.6011)	loss 4.7064 (3.8571)	grad_norm 0.9093 (1.6443/0.6938)	mem 24308MB
[2025-01-18 14:50:58 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][300/312]	eta 0:00:07 lr 0.003812	time 0.5639 (0.6057)	model_time 0.5638 (0.6003)	loss 3.9194 (3.8656)	grad_norm 1.1880 (1.6307/0.6928)	mem 24308MB
[2025-01-18 14:51:04 internimage_s_1k_224] (main.py 510): INFO Train: [41/300][310/312]	eta 0:00:01 lr 0.003812	time 0.5672 (0.6045)	model_time 0.5671 (0.5992)	loss 4.5395 (3.8691)	grad_norm 1.4311 (1.6246/0.6939)	mem 24308MB
[2025-01-18 14:51:04 internimage_s_1k_224] (main.py 519): INFO EPOCH 41 training takes 0:03:08
[2025-01-18 14:51:04 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_41.pth saving......
[2025-01-18 14:51:06 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_41.pth saved !!!
[2025-01-18 14:51:13 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.162 (7.162)	Loss 1.0819 (1.0819)	Acc@1 76.294 (76.294)	Acc@5 93.506 (93.506)	Mem 24308MB
[2025-01-18 14:51:17 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (0.953)	Loss 1.5282 (1.2868)	Acc@1 66.821 (72.097)	Acc@5 88.428 (91.342)	Mem 24308MB
[2025-01-18 14:51:17 internimage_s_1k_224] (main.py 575): INFO [Epoch:41] * Acc@1 72.193 Acc@5 91.443
[2025-01-18 14:51:17 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 72.2%
[2025-01-18 14:51:17 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 14:51:19 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 14:51:19 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 72.19%
[2025-01-18 14:51:26 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.485 (7.485)	Loss 4.0807 (4.0807)	Acc@1 23.755 (23.755)	Acc@5 45.947 (45.947)	Mem 24308MB
[2025-01-18 14:51:29 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.968)	Loss 4.5488 (4.1775)	Acc@1 16.333 (21.096)	Acc@5 36.230 (42.722)	Mem 24308MB
[2025-01-18 14:51:30 internimage_s_1k_224] (main.py 575): INFO [Epoch:41] * Acc@1 21.695 Acc@5 43.808
[2025-01-18 14:51:30 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 21.7%
[2025-01-18 14:51:30 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 14:51:32 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 14:51:32 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 21.70%
[2025-01-18 14:51:34 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][0/312]	eta 0:11:03 lr 0.003812	time 2.1258 (2.1258)	model_time 0.6216 (0.6216)	loss 4.8438 (4.8438)	grad_norm 0.8940 (0.8940/0.0000)	mem 24308MB
[2025-01-18 14:51:40 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][10/312]	eta 0:03:52 lr 0.003811	time 0.6008 (0.7701)	model_time 0.6004 (0.6007)	loss 3.9042 (3.7171)	grad_norm 1.4348 (1.3409/0.3938)	mem 24308MB
[2025-01-18 14:51:46 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][20/312]	eta 0:03:23 lr 0.003811	time 0.5891 (0.6976)	model_time 0.5889 (0.6087)	loss 4.7273 (3.7934)	grad_norm 1.9677 (1.7162/0.7287)	mem 24308MB
[2025-01-18 14:51:52 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][30/312]	eta 0:03:09 lr 0.003811	time 0.5784 (0.6710)	model_time 0.5782 (0.6106)	loss 3.9926 (3.7551)	grad_norm 0.9840 (1.7070/0.7966)	mem 24308MB
[2025-01-18 14:51:59 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][40/312]	eta 0:03:00 lr 0.003810	time 0.6561 (0.6631)	model_time 0.6559 (0.6171)	loss 4.1408 (3.7832)	grad_norm 1.9109 (1.6352/0.7732)	mem 24308MB
[2025-01-18 14:52:05 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][50/312]	eta 0:02:52 lr 0.003810	time 0.6911 (0.6578)	model_time 0.6909 (0.6207)	loss 3.6752 (3.8680)	grad_norm 1.1211 (1.5514/0.7409)	mem 24308MB
[2025-01-18 14:52:11 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][60/312]	eta 0:02:43 lr 0.003810	time 0.5754 (0.6504)	model_time 0.5749 (0.6194)	loss 4.0755 (3.8311)	grad_norm 1.2969 (1.5009/0.6944)	mem 24308MB
[2025-01-18 14:52:17 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][70/312]	eta 0:02:35 lr 0.003810	time 0.6625 (0.6429)	model_time 0.6621 (0.6162)	loss 4.7564 (3.8319)	grad_norm 2.0350 (1.5200/0.6846)	mem 24308MB
[2025-01-18 14:52:23 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][80/312]	eta 0:02:27 lr 0.003809	time 0.5932 (0.6356)	model_time 0.5930 (0.6121)	loss 4.0179 (3.8552)	grad_norm 1.0983 (1.5090/0.6950)	mem 24308MB
[2025-01-18 14:52:29 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][90/312]	eta 0:02:20 lr 0.003809	time 0.6216 (0.6312)	model_time 0.6212 (0.6102)	loss 3.5671 (3.8215)	grad_norm 2.2996 (1.5302/0.6973)	mem 24308MB
[2025-01-18 14:52:35 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][100/312]	eta 0:02:13 lr 0.003809	time 0.6118 (0.6280)	model_time 0.6116 (0.6091)	loss 3.6311 (3.8119)	grad_norm 0.9308 (1.5758/0.7077)	mem 24308MB
[2025-01-18 14:52:41 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][110/312]	eta 0:02:06 lr 0.003808	time 0.5743 (0.6244)	model_time 0.5740 (0.6071)	loss 4.0131 (3.8571)	grad_norm 0.9645 (1.5752/0.6963)	mem 24308MB
[2025-01-18 14:52:47 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][120/312]	eta 0:01:59 lr 0.003808	time 0.5882 (0.6216)	model_time 0.5880 (0.6058)	loss 3.8545 (3.8593)	grad_norm 0.9916 (1.5554/0.6860)	mem 24308MB
[2025-01-18 14:52:53 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][130/312]	eta 0:01:52 lr 0.003808	time 0.5889 (0.6207)	model_time 0.5888 (0.6061)	loss 3.3378 (3.8590)	grad_norm 2.0898 (1.5284/0.6741)	mem 24308MB
[2025-01-18 14:52:59 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][140/312]	eta 0:01:46 lr 0.003808	time 0.5841 (0.6202)	model_time 0.5839 (0.6066)	loss 3.5121 (3.8277)	grad_norm 1.6179 (1.5466/0.6809)	mem 24308MB
[2025-01-18 14:53:05 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][150/312]	eta 0:01:40 lr 0.003807	time 0.6819 (0.6201)	model_time 0.6817 (0.6073)	loss 3.5998 (3.8292)	grad_norm 1.5799 (1.5199/0.6700)	mem 24308MB
[2025-01-18 14:53:12 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][160/312]	eta 0:01:34 lr 0.003807	time 0.6495 (0.6212)	model_time 0.6494 (0.6091)	loss 4.0314 (3.8328)	grad_norm 1.1108 (1.5157/0.6529)	mem 24308MB
[2025-01-18 14:53:18 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][170/312]	eta 0:01:28 lr 0.003807	time 0.7046 (0.6216)	model_time 0.7045 (0.6102)	loss 3.3572 (3.8171)	grad_norm 1.6718 (1.5368/0.6565)	mem 24308MB
[2025-01-18 14:53:24 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][180/312]	eta 0:01:22 lr 0.003806	time 0.5728 (0.6214)	model_time 0.5724 (0.6107)	loss 2.5789 (3.8168)	grad_norm 1.6741 (1.5349/0.6547)	mem 24308MB
[2025-01-18 14:53:30 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][190/312]	eta 0:01:15 lr 0.003806	time 0.6869 (0.6205)	model_time 0.6864 (0.6103)	loss 2.5403 (3.8284)	grad_norm 0.8694 (1.5384/0.6496)	mem 24308MB
[2025-01-18 14:53:36 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][200/312]	eta 0:01:09 lr 0.003806	time 0.5768 (0.6187)	model_time 0.5766 (0.6089)	loss 2.7346 (3.8110)	grad_norm 2.0859 (1.5346/0.6368)	mem 24308MB
[2025-01-18 14:53:42 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][210/312]	eta 0:01:02 lr 0.003806	time 0.5729 (0.6172)	model_time 0.5728 (0.6078)	loss 4.4051 (3.7984)	grad_norm 1.7275 (1.5452/0.6440)	mem 24308MB
[2025-01-18 14:53:48 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][220/312]	eta 0:00:56 lr 0.003805	time 0.5744 (0.6161)	model_time 0.5742 (0.6072)	loss 4.1879 (3.8043)	grad_norm 1.9924 (1.5362/0.6373)	mem 24308MB
[2025-01-18 14:53:54 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][230/312]	eta 0:00:50 lr 0.003805	time 0.5873 (0.6148)	model_time 0.5868 (0.6063)	loss 4.4441 (3.8017)	grad_norm 2.0093 (1.5391/0.6348)	mem 24308MB
[2025-01-18 14:54:00 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][240/312]	eta 0:00:44 lr 0.003805	time 0.5821 (0.6137)	model_time 0.5820 (0.6056)	loss 4.2297 (3.8020)	grad_norm 3.3700 (1.5411/0.6386)	mem 24308MB
[2025-01-18 14:54:06 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][250/312]	eta 0:00:38 lr 0.003804	time 0.5791 (0.6130)	model_time 0.5790 (0.6052)	loss 4.2450 (3.8065)	grad_norm 2.3704 (1.5467/0.6388)	mem 24308MB
[2025-01-18 14:54:12 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][260/312]	eta 0:00:31 lr 0.003804	time 0.5924 (0.6126)	model_time 0.5922 (0.6051)	loss 3.8296 (3.8044)	grad_norm 0.7990 (1.5339/0.6311)	mem 24308MB
[2025-01-18 14:54:18 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][270/312]	eta 0:00:25 lr 0.003804	time 0.6471 (0.6127)	model_time 0.6470 (0.6054)	loss 4.3605 (3.8173)	grad_norm 2.7151 (1.5333/0.6309)	mem 24308MB
[2025-01-18 14:54:24 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][280/312]	eta 0:00:19 lr 0.003804	time 0.5865 (0.6136)	model_time 0.5864 (0.6065)	loss 3.0909 (3.8211)	grad_norm 2.3386 (1.5336/0.6256)	mem 24308MB
[2025-01-18 14:54:30 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][290/312]	eta 0:00:13 lr 0.003803	time 0.6633 (0.6139)	model_time 0.6631 (0.6071)	loss 3.2041 (3.8149)	grad_norm 0.8935 (1.5366/0.6328)	mem 24308MB
[2025-01-18 14:54:36 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][300/312]	eta 0:00:07 lr 0.003803	time 0.5700 (0.6139)	model_time 0.5699 (0.6073)	loss 3.2745 (3.7967)	grad_norm 1.6205 (1.5365/0.6324)	mem 24308MB
[2025-01-18 14:54:42 internimage_s_1k_224] (main.py 510): INFO Train: [42/300][310/312]	eta 0:00:01 lr 0.003803	time 0.5688 (0.6129)	model_time 0.5687 (0.6065)	loss 4.8527 (3.7950)	grad_norm 1.5037 (1.5369/0.6304)	mem 24308MB
[2025-01-18 14:54:43 internimage_s_1k_224] (main.py 519): INFO EPOCH 42 training takes 0:03:11
[2025-01-18 14:54:43 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_42.pth saving......
[2025-01-18 14:54:45 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_42.pth saved !!!
[2025-01-18 14:54:52 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.355 (7.355)	Loss 1.1013 (1.1013)	Acc@1 76.904 (76.904)	Acc@5 93.872 (93.872)	Mem 24308MB
[2025-01-18 14:54:55 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.938)	Loss 1.5365 (1.2851)	Acc@1 66.968 (72.698)	Acc@5 88.257 (91.528)	Mem 24308MB
[2025-01-18 14:54:55 internimage_s_1k_224] (main.py 575): INFO [Epoch:42] * Acc@1 72.657 Acc@5 91.591
[2025-01-18 14:54:55 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 72.7%
[2025-01-18 14:54:55 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 14:54:57 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 14:54:57 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 72.66%
[2025-01-18 14:55:04 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.072 (7.072)	Loss 3.7998 (3.7998)	Acc@1 27.832 (27.832)	Acc@5 50.635 (50.635)	Mem 24308MB
[2025-01-18 14:55:08 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.935)	Loss 4.3086 (3.9263)	Acc@1 19.092 (24.476)	Acc@5 40.356 (47.073)	Mem 24308MB
[2025-01-18 14:55:08 internimage_s_1k_224] (main.py 575): INFO [Epoch:42] * Acc@1 25.060 Acc@5 48.087
[2025-01-18 14:55:08 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 25.1%
[2025-01-18 14:55:08 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 14:55:10 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 14:55:10 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 25.06%
[2025-01-18 14:55:12 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][0/312]	eta 0:10:32 lr 0.003803	time 2.0265 (2.0265)	model_time 0.5975 (0.5975)	loss 3.8247 (3.8247)	grad_norm 0.8670 (0.8670/0.0000)	mem 24308MB
[2025-01-18 14:55:18 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][10/312]	eta 0:03:37 lr 0.003802	time 0.5746 (0.7202)	model_time 0.5740 (0.5899)	loss 4.5950 (3.7138)	grad_norm 1.7703 (2.3639/0.9751)	mem 24308MB
[2025-01-18 14:55:24 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][20/312]	eta 0:03:11 lr 0.003802	time 0.6057 (0.6567)	model_time 0.6055 (0.5884)	loss 4.5706 (3.9732)	grad_norm 1.1285 (1.8601/0.9197)	mem 24308MB
[2025-01-18 14:55:30 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][30/312]	eta 0:02:59 lr 0.003802	time 0.5818 (0.6371)	model_time 0.5816 (0.5904)	loss 3.9826 (3.9704)	grad_norm 0.8558 (1.6558/0.8290)	mem 24308MB
[2025-01-18 14:55:36 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][40/312]	eta 0:02:50 lr 0.003801	time 0.6200 (0.6272)	model_time 0.6199 (0.5916)	loss 3.4825 (3.9225)	grad_norm 1.5945 (1.5859/0.7506)	mem 24308MB
[2025-01-18 14:55:41 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][50/312]	eta 0:02:42 lr 0.003801	time 0.5831 (0.6188)	model_time 0.5830 (0.5901)	loss 4.1968 (3.9333)	grad_norm 2.2807 (1.5777/0.7214)	mem 24308MB
[2025-01-18 14:55:47 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][60/312]	eta 0:02:35 lr 0.003801	time 0.5736 (0.6151)	model_time 0.5735 (0.5910)	loss 3.3448 (3.8855)	grad_norm 1.4906 (1.5694/0.7269)	mem 24308MB
[2025-01-18 14:55:53 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][70/312]	eta 0:02:28 lr 0.003801	time 0.5813 (0.6139)	model_time 0.5811 (0.5931)	loss 3.5183 (3.8493)	grad_norm 2.0628 (1.5161/0.6998)	mem 24308MB
[2025-01-18 14:56:00 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][80/312]	eta 0:02:22 lr 0.003800	time 0.6649 (0.6144)	model_time 0.6648 (0.5962)	loss 3.6049 (3.8669)	grad_norm 2.6834 (1.5392/0.6870)	mem 24308MB
[2025-01-18 14:56:06 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][90/312]	eta 0:02:16 lr 0.003800	time 0.6901 (0.6165)	model_time 0.6899 (0.6003)	loss 4.0931 (3.8636)	grad_norm 1.4788 (1.5353/0.6625)	mem 24308MB
[2025-01-18 14:56:12 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][100/312]	eta 0:02:11 lr 0.003800	time 0.6786 (0.6180)	model_time 0.6784 (0.6033)	loss 3.9350 (3.8551)	grad_norm 3.1195 (1.6045/0.7326)	mem 24308MB
[2025-01-18 14:56:18 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][110/312]	eta 0:02:04 lr 0.003799	time 0.6496 (0.6178)	model_time 0.6495 (0.6044)	loss 3.9115 (3.7906)	grad_norm 1.6606 (1.5871/0.7087)	mem 24308MB
[2025-01-18 14:56:24 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][120/312]	eta 0:01:58 lr 0.003799	time 0.5835 (0.6159)	model_time 0.5833 (0.6036)	loss 4.2242 (3.7951)	grad_norm 1.0285 (1.5628/0.6909)	mem 24308MB
[2025-01-18 14:56:30 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][130/312]	eta 0:01:51 lr 0.003799	time 0.5890 (0.6147)	model_time 0.5888 (0.6034)	loss 4.1862 (3.7862)	grad_norm 1.8622 (1.5740/0.6757)	mem 24308MB
[2025-01-18 14:56:36 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][140/312]	eta 0:01:45 lr 0.003799	time 0.5821 (0.6134)	model_time 0.5819 (0.6028)	loss 2.7788 (3.7931)	grad_norm 2.1789 (1.5679/0.6639)	mem 24308MB
[2025-01-18 14:56:42 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][150/312]	eta 0:01:39 lr 0.003798	time 0.6932 (0.6126)	model_time 0.6930 (0.6027)	loss 3.8201 (3.7753)	grad_norm 1.1719 (1.5830/0.6481)	mem 24308MB
[2025-01-18 14:56:48 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][160/312]	eta 0:01:32 lr 0.003798	time 0.6157 (0.6113)	model_time 0.6155 (0.6020)	loss 4.6130 (3.7876)	grad_norm 1.4153 (1.5629/0.6371)	mem 24308MB
[2025-01-18 14:56:54 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][170/312]	eta 0:01:26 lr 0.003798	time 0.5901 (0.6100)	model_time 0.5899 (0.6013)	loss 4.2321 (3.7837)	grad_norm 1.4778 (1.5695/0.6471)	mem 24308MB
[2025-01-18 14:57:00 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][180/312]	eta 0:01:20 lr 0.003797	time 0.5947 (0.6087)	model_time 0.5946 (0.6003)	loss 4.3530 (3.7737)	grad_norm 1.0219 (1.5678/0.6359)	mem 24308MB
[2025-01-18 14:57:06 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][190/312]	eta 0:01:14 lr 0.003797	time 0.5812 (0.6084)	model_time 0.5810 (0.6005)	loss 3.2389 (3.7733)	grad_norm 0.8232 (1.5556/0.6309)	mem 24308MB
[2025-01-18 14:57:12 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][200/312]	eta 0:01:08 lr 0.003797	time 0.5871 (0.6080)	model_time 0.5870 (0.6005)	loss 3.0476 (3.7786)	grad_norm 1.4953 (1.5954/0.6856)	mem 24308MB
[2025-01-18 14:57:18 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][210/312]	eta 0:01:02 lr 0.003797	time 0.5839 (0.6089)	model_time 0.5838 (0.6017)	loss 4.2607 (3.7844)	grad_norm 1.1462 (1.5766/0.6765)	mem 24308MB
[2025-01-18 14:57:25 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][220/312]	eta 0:00:56 lr 0.003796	time 0.6537 (0.6101)	model_time 0.6535 (0.6032)	loss 4.6739 (3.7808)	grad_norm 0.7763 (1.5538/0.6714)	mem 24308MB
[2025-01-18 14:57:31 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][230/312]	eta 0:00:50 lr 0.003796	time 0.5931 (0.6103)	model_time 0.5927 (0.6037)	loss 4.1480 (3.7668)	grad_norm 2.0096 (1.5519/0.6615)	mem 24308MB
[2025-01-18 14:57:37 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][240/312]	eta 0:00:43 lr 0.003796	time 0.5816 (0.6099)	model_time 0.5814 (0.6035)	loss 3.9857 (3.7494)	grad_norm 0.9038 (1.5636/0.6658)	mem 24308MB
[2025-01-18 14:57:43 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][250/312]	eta 0:00:37 lr 0.003795	time 0.5814 (0.6093)	model_time 0.5810 (0.6032)	loss 4.2974 (3.7544)	grad_norm 1.2022 (1.5487/0.6610)	mem 24308MB
[2025-01-18 14:57:49 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][260/312]	eta 0:00:31 lr 0.003795	time 0.6004 (0.6085)	model_time 0.6002 (0.6027)	loss 3.1078 (3.7603)	grad_norm 1.6368 (1.5352/0.6539)	mem 24308MB
[2025-01-18 14:57:55 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][270/312]	eta 0:00:25 lr 0.003795	time 0.5902 (0.6078)	model_time 0.5897 (0.6022)	loss 2.7441 (3.7660)	grad_norm 1.0446 (1.5291/0.6477)	mem 24308MB
[2025-01-18 14:58:01 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][280/312]	eta 0:00:19 lr 0.003794	time 0.5747 (0.6073)	model_time 0.5745 (0.6018)	loss 3.9175 (3.7681)	grad_norm 0.7941 (1.5370/0.6457)	mem 24308MB
[2025-01-18 14:58:06 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][290/312]	eta 0:00:13 lr 0.003794	time 0.5753 (0.6066)	model_time 0.5749 (0.6013)	loss 3.1962 (3.7634)	grad_norm 0.8624 (1.5414/0.6472)	mem 24308MB
[2025-01-18 14:58:12 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][300/312]	eta 0:00:07 lr 0.003794	time 0.6087 (0.6058)	model_time 0.6086 (0.6007)	loss 4.2876 (3.7693)	grad_norm 1.3237 (1.5411/0.6432)	mem 24308MB
[2025-01-18 14:58:18 internimage_s_1k_224] (main.py 510): INFO Train: [43/300][310/312]	eta 0:00:01 lr 0.003794	time 0.5705 (0.6056)	model_time 0.5704 (0.6006)	loss 3.8778 (3.7726)	grad_norm 1.2214 (1.5108/0.6048)	mem 24308MB
[2025-01-18 14:58:19 internimage_s_1k_224] (main.py 519): INFO EPOCH 43 training takes 0:03:08
[2025-01-18 14:58:19 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_43.pth saving......
[2025-01-18 14:58:20 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_43.pth saved !!!
[2025-01-18 14:58:28 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.185 (7.185)	Loss 1.0717 (1.0717)	Acc@1 76.172 (76.172)	Acc@5 94.189 (94.189)	Mem 24308MB
[2025-01-18 14:58:31 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.947)	Loss 1.5880 (1.2780)	Acc@1 67.017 (72.545)	Acc@5 88.110 (91.599)	Mem 24308MB
[2025-01-18 14:58:31 internimage_s_1k_224] (main.py 575): INFO [Epoch:43] * Acc@1 72.633 Acc@5 91.707
[2025-01-18 14:58:31 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 72.6%
[2025-01-18 14:58:31 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 72.66%
[2025-01-18 14:58:39 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.244 (8.244)	Loss 3.5332 (3.5332)	Acc@1 31.641 (31.641)	Acc@5 54.980 (54.980)	Mem 24308MB
[2025-01-18 14:58:43 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.137 (1.110)	Loss 4.0784 (3.6868)	Acc@1 21.997 (27.788)	Acc@5 44.165 (51.312)	Mem 24308MB
[2025-01-18 14:58:44 internimage_s_1k_224] (main.py 575): INFO [Epoch:43] * Acc@1 28.353 Acc@5 52.229
[2025-01-18 14:58:44 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 28.4%
[2025-01-18 14:58:44 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 14:58:46 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 14:58:46 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 28.35%
[2025-01-18 14:58:48 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][0/312]	eta 0:10:56 lr 0.003794	time 2.1044 (2.1044)	model_time 0.5961 (0.5961)	loss 3.9309 (3.9309)	grad_norm 2.3423 (2.3423/0.0000)	mem 24308MB
[2025-01-18 14:58:54 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][10/312]	eta 0:03:46 lr 0.003793	time 0.6894 (0.7498)	model_time 0.6893 (0.6124)	loss 3.6916 (3.7866)	grad_norm 1.6527 (1.5146/0.5175)	mem 24308MB
[2025-01-18 14:59:01 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][20/312]	eta 0:03:22 lr 0.003793	time 0.6844 (0.6943)	model_time 0.6841 (0.6222)	loss 3.5523 (3.8786)	grad_norm 2.0036 (1.4773/0.4610)	mem 24308MB
[2025-01-18 14:59:07 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][30/312]	eta 0:03:10 lr 0.003793	time 0.6086 (0.6743)	model_time 0.6084 (0.6254)	loss 4.2868 (3.8897)	grad_norm 0.8926 (1.4297/0.4653)	mem 24308MB
[2025-01-18 14:59:13 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][40/312]	eta 0:02:59 lr 0.003792	time 0.5968 (0.6598)	model_time 0.5966 (0.6227)	loss 3.6817 (3.8771)	grad_norm 3.1292 (1.4967/0.5621)	mem 24308MB
[2025-01-18 14:59:19 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][50/312]	eta 0:02:50 lr 0.003792	time 0.5793 (0.6516)	model_time 0.5791 (0.6216)	loss 4.8034 (3.9454)	grad_norm 1.7129 (1.6425/0.7756)	mem 24308MB
[2025-01-18 14:59:25 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][60/312]	eta 0:02:41 lr 0.003792	time 0.5855 (0.6411)	model_time 0.5853 (0.6160)	loss 4.9196 (3.9197)	grad_norm 1.0179 (1.6258/0.7784)	mem 24308MB
[2025-01-18 14:59:31 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][70/312]	eta 0:02:33 lr 0.003791	time 0.5788 (0.6344)	model_time 0.5784 (0.6128)	loss 4.9329 (3.9161)	grad_norm 1.4666 (1.6006/0.7513)	mem 24308MB
[2025-01-18 14:59:37 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][80/312]	eta 0:02:25 lr 0.003791	time 0.5841 (0.6286)	model_time 0.5840 (0.6096)	loss 2.6072 (3.8634)	grad_norm 1.8817 (1.5681/0.7181)	mem 24308MB
[2025-01-18 14:59:43 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][90/312]	eta 0:02:18 lr 0.003791	time 0.5928 (0.6243)	model_time 0.5926 (0.6074)	loss 3.9531 (3.8365)	grad_norm 2.3567 (1.5736/0.7035)	mem 24308MB
[2025-01-18 14:59:49 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][100/312]	eta 0:02:11 lr 0.003791	time 0.5735 (0.6204)	model_time 0.5730 (0.6051)	loss 3.7622 (3.8278)	grad_norm 0.6415 (1.6048/0.7219)	mem 24308MB
[2025-01-18 14:59:55 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][110/312]	eta 0:02:04 lr 0.003790	time 0.5846 (0.6173)	model_time 0.5844 (0.6033)	loss 4.0666 (3.8189)	grad_norm 1.0779 (1.5982/0.7051)	mem 24308MB
[2025-01-18 15:00:01 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][120/312]	eta 0:01:58 lr 0.003790	time 0.5771 (0.6167)	model_time 0.5770 (0.6039)	loss 3.7556 (3.8188)	grad_norm 2.0561 (1.5806/0.6850)	mem 24308MB
[2025-01-18 15:00:07 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][130/312]	eta 0:01:52 lr 0.003790	time 0.6846 (0.6167)	model_time 0.6841 (0.6048)	loss 3.6717 (3.8385)	grad_norm 2.2466 (1.5682/0.6818)	mem 24308MB
[2025-01-18 15:00:13 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][140/312]	eta 0:01:46 lr 0.003789	time 0.6809 (0.6182)	model_time 0.6804 (0.6071)	loss 4.6147 (3.8341)	grad_norm 1.0934 (1.5994/0.7412)	mem 24308MB
[2025-01-18 15:00:20 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][150/312]	eta 0:01:40 lr 0.003789	time 0.6656 (0.6193)	model_time 0.6652 (0.6089)	loss 4.2028 (3.8328)	grad_norm 0.8199 (1.5744/0.7310)	mem 24308MB
[2025-01-18 15:00:26 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][160/312]	eta 0:01:34 lr 0.003789	time 0.5725 (0.6196)	model_time 0.5723 (0.6098)	loss 4.1266 (3.8245)	grad_norm 1.0402 (1.5502/0.7164)	mem 24308MB
[2025-01-18 15:00:32 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][170/312]	eta 0:01:27 lr 0.003788	time 0.5885 (0.6186)	model_time 0.5883 (0.6094)	loss 3.9745 (3.8354)	grad_norm 2.3831 (1.5602/0.7124)	mem 24308MB
[2025-01-18 15:00:38 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][180/312]	eta 0:01:21 lr 0.003788	time 0.6274 (0.6175)	model_time 0.6270 (0.6088)	loss 4.1993 (3.8281)	grad_norm 1.4320 (1.5600/0.7008)	mem 24308MB
[2025-01-18 15:00:44 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][190/312]	eta 0:01:15 lr 0.003788	time 0.5771 (0.6160)	model_time 0.5769 (0.6077)	loss 2.9905 (3.8225)	grad_norm 2.9638 (1.5541/0.6971)	mem 24308MB
[2025-01-18 15:00:50 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][200/312]	eta 0:01:08 lr 0.003788	time 0.5768 (0.6148)	model_time 0.5766 (0.6069)	loss 3.7663 (3.8167)	grad_norm 1.6549 (1.5497/0.6828)	mem 24308MB
[2025-01-18 15:00:56 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][210/312]	eta 0:01:02 lr 0.003787	time 0.5867 (0.6136)	model_time 0.5866 (0.6061)	loss 4.3389 (3.8120)	grad_norm 3.4941 (1.5537/0.6857)	mem 24308MB
[2025-01-18 15:01:02 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][220/312]	eta 0:00:56 lr 0.003787	time 0.5892 (0.6124)	model_time 0.5890 (0.6052)	loss 3.9656 (3.8073)	grad_norm 1.1843 (1.5574/0.6750)	mem 24308MB
[2025-01-18 15:01:07 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][230/312]	eta 0:00:50 lr 0.003787	time 0.5763 (0.6113)	model_time 0.5759 (0.6044)	loss 3.4912 (3.7994)	grad_norm 0.7846 (1.5541/0.6721)	mem 24308MB
[2025-01-18 15:01:14 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][240/312]	eta 0:00:44 lr 0.003786	time 0.6991 (0.6115)	model_time 0.6987 (0.6049)	loss 4.0778 (3.8020)	grad_norm 1.0000 (1.5478/0.6657)	mem 24308MB
[2025-01-18 15:01:20 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][250/312]	eta 0:00:37 lr 0.003786	time 0.5999 (0.6111)	model_time 0.5997 (0.6047)	loss 3.5516 (3.7915)	grad_norm 3.5920 (1.5578/0.6748)	mem 24308MB
[2025-01-18 15:01:26 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][260/312]	eta 0:00:31 lr 0.003786	time 0.5898 (0.6112)	model_time 0.5897 (0.6050)	loss 3.9781 (3.7978)	grad_norm 1.9443 (1.5688/0.6812)	mem 24308MB
[2025-01-18 15:01:32 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][270/312]	eta 0:00:25 lr 0.003785	time 0.5707 (0.6116)	model_time 0.5705 (0.6056)	loss 3.9949 (3.8139)	grad_norm 0.7658 (1.5552/0.6746)	mem 24308MB
[2025-01-18 15:01:38 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][280/312]	eta 0:00:19 lr 0.003785	time 0.5743 (0.6121)	model_time 0.5742 (0.6064)	loss 4.1695 (3.8170)	grad_norm 2.5658 (1.5637/0.6829)	mem 24308MB
[2025-01-18 15:01:44 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][290/312]	eta 0:00:13 lr 0.003785	time 0.5839 (0.6120)	model_time 0.5833 (0.6064)	loss 4.4515 (3.8225)	grad_norm 0.8727 (1.5550/0.6778)	mem 24308MB
[2025-01-18 15:01:50 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][300/312]	eta 0:00:07 lr 0.003785	time 0.6181 (0.6113)	model_time 0.6180 (0.6059)	loss 3.6926 (3.8250)	grad_norm 1.2090 (1.5379/0.6716)	mem 24308MB
[2025-01-18 15:01:56 internimage_s_1k_224] (main.py 510): INFO Train: [44/300][310/312]	eta 0:00:01 lr 0.003784	time 0.5748 (0.6103)	model_time 0.5746 (0.6051)	loss 3.4346 (3.8260)	grad_norm 1.0700 (1.5441/0.6748)	mem 24308MB
[2025-01-18 15:01:57 internimage_s_1k_224] (main.py 519): INFO EPOCH 44 training takes 0:03:10
[2025-01-18 15:01:57 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_44.pth saving......
[2025-01-18 15:01:58 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_44.pth saved !!!
[2025-01-18 15:02:06 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.195 (7.195)	Loss 1.0037 (1.0037)	Acc@1 76.855 (76.855)	Acc@5 94.482 (94.482)	Mem 24308MB
[2025-01-18 15:02:09 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.138 (0.932)	Loss 1.5133 (1.2222)	Acc@1 65.430 (72.632)	Acc@5 87.891 (91.653)	Mem 24308MB
[2025-01-18 15:02:09 internimage_s_1k_224] (main.py 575): INFO [Epoch:44] * Acc@1 72.733 Acc@5 91.761
[2025-01-18 15:02:09 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 72.7%
[2025-01-18 15:02:09 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 15:02:11 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 15:02:11 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 72.73%
[2025-01-18 15:02:18 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.911 (6.911)	Loss 3.2876 (3.2876)	Acc@1 35.083 (35.083)	Acc@5 58.594 (58.594)	Mem 24308MB
[2025-01-18 15:02:21 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.912)	Loss 3.8604 (3.4627)	Acc@1 24.780 (30.950)	Acc@5 47.754 (55.233)	Mem 24308MB
[2025-01-18 15:02:21 internimage_s_1k_224] (main.py 575): INFO [Epoch:44] * Acc@1 31.480 Acc@5 56.104
[2025-01-18 15:02:21 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 31.5%
[2025-01-18 15:02:21 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 15:02:23 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 15:02:23 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 31.48%
[2025-01-18 15:02:25 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][0/312]	eta 0:11:34 lr 0.003784	time 2.2258 (2.2258)	model_time 0.6069 (0.6069)	loss 2.7706 (2.7706)	grad_norm 1.8690 (1.8690/0.0000)	mem 24308MB
[2025-01-18 15:02:31 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][10/312]	eta 0:03:44 lr 0.003784	time 0.6443 (0.7425)	model_time 0.6441 (0.5951)	loss 4.1737 (3.8599)	grad_norm 1.2291 (1.2990/0.4880)	mem 24308MB
[2025-01-18 15:02:37 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][20/312]	eta 0:03:15 lr 0.003784	time 0.5897 (0.6698)	model_time 0.5895 (0.5924)	loss 3.8741 (3.7628)	grad_norm 1.2670 (1.3721/0.5360)	mem 24308MB
[2025-01-18 15:02:43 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][30/312]	eta 0:03:01 lr 0.003783	time 0.5752 (0.6429)	model_time 0.5750 (0.5904)	loss 4.3082 (3.8879)	grad_norm 1.5062 (1.3866/0.5014)	mem 24308MB
[2025-01-18 15:02:49 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][40/312]	eta 0:02:51 lr 0.003783	time 0.5785 (0.6290)	model_time 0.5780 (0.5891)	loss 4.6498 (3.9015)	grad_norm 1.2828 (1.4409/0.4933)	mem 24308MB
[2025-01-18 15:02:55 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][50/312]	eta 0:02:44 lr 0.003783	time 0.7346 (0.6292)	model_time 0.7345 (0.5971)	loss 3.7532 (3.9476)	grad_norm 1.4596 (1.5281/0.6697)	mem 24308MB
[2025-01-18 15:03:01 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][60/312]	eta 0:02:38 lr 0.003782	time 0.6009 (0.6277)	model_time 0.6005 (0.6008)	loss 2.8462 (3.9280)	grad_norm 1.2573 (1.4945/0.6228)	mem 24308MB
[2025-01-18 15:03:08 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][70/312]	eta 0:02:31 lr 0.003782	time 0.6018 (0.6273)	model_time 0.6016 (0.6042)	loss 4.6717 (3.8955)	grad_norm 1.1880 (1.5323/0.6273)	mem 24308MB
[2025-01-18 15:03:14 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][80/312]	eta 0:02:25 lr 0.003782	time 0.5837 (0.6274)	model_time 0.5836 (0.6071)	loss 2.9812 (3.8689)	grad_norm 1.2041 (1.5309/0.5993)	mem 24308MB
[2025-01-18 15:03:20 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][90/312]	eta 0:02:19 lr 0.003781	time 0.5932 (0.6278)	model_time 0.5930 (0.6097)	loss 3.0775 (3.8728)	grad_norm 2.9896 (1.5980/0.6862)	mem 24308MB
[2025-01-18 15:03:26 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][100/312]	eta 0:02:12 lr 0.003781	time 0.5806 (0.6269)	model_time 0.5804 (0.6105)	loss 3.9763 (3.8698)	grad_norm 1.1571 (1.6258/0.7449)	mem 24308MB
[2025-01-18 15:03:32 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][110/312]	eta 0:02:06 lr 0.003781	time 0.6252 (0.6239)	model_time 0.6248 (0.6089)	loss 2.7252 (3.8814)	grad_norm 2.4002 (1.6060/0.7321)	mem 24308MB
[2025-01-18 15:03:38 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][120/312]	eta 0:01:59 lr 0.003781	time 0.5994 (0.6209)	model_time 0.5993 (0.6072)	loss 2.8981 (3.8714)	grad_norm 1.9139 (1.6406/0.7339)	mem 24308MB
[2025-01-18 15:03:44 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][130/312]	eta 0:01:52 lr 0.003780	time 0.5759 (0.6179)	model_time 0.5755 (0.6052)	loss 2.7702 (3.8620)	grad_norm 0.9187 (1.6218/0.7176)	mem 24308MB
[2025-01-18 15:03:50 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][140/312]	eta 0:01:45 lr 0.003780	time 0.5761 (0.6157)	model_time 0.5759 (0.6039)	loss 2.4785 (3.8461)	grad_norm 1.1006 (1.6083/0.7132)	mem 24308MB
[2025-01-18 15:03:56 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][150/312]	eta 0:01:39 lr 0.003780	time 0.5826 (0.6144)	model_time 0.5824 (0.6034)	loss 4.3862 (3.8651)	grad_norm 0.9392 (1.5778/0.7053)	mem 24308MB
[2025-01-18 15:04:02 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][160/312]	eta 0:01:33 lr 0.003779	time 0.5734 (0.6125)	model_time 0.5733 (0.6021)	loss 3.6200 (3.8768)	grad_norm 1.6030 (1.5655/0.6905)	mem 24308MB
[2025-01-18 15:04:08 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][170/312]	eta 0:01:26 lr 0.003779	time 0.5798 (0.6125)	model_time 0.5797 (0.6026)	loss 3.7373 (3.8430)	grad_norm 2.2369 (1.5732/0.6897)	mem 24308MB
[2025-01-18 15:04:14 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][180/312]	eta 0:01:20 lr 0.003779	time 0.7141 (0.6127)	model_time 0.7139 (0.6034)	loss 3.9286 (3.8314)	grad_norm 0.8516 (1.5577/0.6886)	mem 24308MB
[2025-01-18 15:04:20 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][190/312]	eta 0:01:14 lr 0.003778	time 0.6872 (0.6140)	model_time 0.6870 (0.6052)	loss 4.2539 (3.8251)	grad_norm 2.2352 (1.5422/0.6827)	mem 24308MB
[2025-01-18 15:04:27 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][200/312]	eta 0:01:08 lr 0.003778	time 0.6620 (0.6152)	model_time 0.6619 (0.6068)	loss 4.0770 (3.8290)	grad_norm 1.6624 (1.5309/0.6721)	mem 24308MB
[2025-01-18 15:04:33 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][210/312]	eta 0:01:02 lr 0.003778	time 0.5827 (0.6154)	model_time 0.5825 (0.6074)	loss 4.0199 (3.8307)	grad_norm 1.7098 (1.5205/0.6601)	mem 24308MB
[2025-01-18 15:04:39 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][220/312]	eta 0:00:56 lr 0.003778	time 0.5766 (0.6153)	model_time 0.5761 (0.6076)	loss 4.1526 (3.8253)	grad_norm 1.4822 (1.5109/0.6506)	mem 24308MB
[2025-01-18 15:04:45 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][230/312]	eta 0:00:50 lr 0.003777	time 0.5826 (0.6146)	model_time 0.5822 (0.6073)	loss 4.1624 (3.8221)	grad_norm 1.0912 (1.5212/0.6491)	mem 24308MB
[2025-01-18 15:04:51 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][240/312]	eta 0:00:44 lr 0.003777	time 0.5802 (0.6136)	model_time 0.5796 (0.6065)	loss 3.1182 (3.8158)	grad_norm 3.2429 (1.5357/0.6537)	mem 24308MB
[2025-01-18 15:04:57 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][250/312]	eta 0:00:37 lr 0.003777	time 0.5754 (0.6125)	model_time 0.5749 (0.6057)	loss 4.5990 (3.8220)	grad_norm 1.6715 (1.5401/0.6519)	mem 24308MB
[2025-01-18 15:05:03 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][260/312]	eta 0:00:31 lr 0.003776	time 0.5907 (0.6118)	model_time 0.5903 (0.6052)	loss 4.2610 (3.8178)	grad_norm 2.3322 (1.5429/0.6523)	mem 24308MB
[2025-01-18 15:05:09 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][270/312]	eta 0:00:25 lr 0.003776	time 0.5800 (0.6110)	model_time 0.5798 (0.6047)	loss 2.6572 (3.8052)	grad_norm 1.0736 (1.5461/0.6496)	mem 24308MB
[2025-01-18 15:05:15 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][280/312]	eta 0:00:19 lr 0.003776	time 0.5854 (0.6103)	model_time 0.5853 (0.6042)	loss 4.0084 (3.8113)	grad_norm 1.7633 (1.5408/0.6417)	mem 24308MB
[2025-01-18 15:05:21 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][290/312]	eta 0:00:13 lr 0.003775	time 0.6631 (0.6102)	model_time 0.6629 (0.6043)	loss 4.1621 (3.8111)	grad_norm 1.5940 (1.5425/0.6379)	mem 24308MB
[2025-01-18 15:05:27 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][300/312]	eta 0:00:07 lr 0.003775	time 0.5670 (0.6102)	model_time 0.5669 (0.6045)	loss 3.9902 (3.8099)	grad_norm 1.2659 (1.5406/0.6379)	mem 24308MB
[2025-01-18 15:05:33 internimage_s_1k_224] (main.py 510): INFO Train: [45/300][310/312]	eta 0:00:01 lr 0.003775	time 0.6487 (0.6101)	model_time 0.6486 (0.6045)	loss 4.1473 (3.8124)	grad_norm 1.6209 (1.5453/0.6354)	mem 24308MB
[2025-01-18 15:05:33 internimage_s_1k_224] (main.py 519): INFO EPOCH 45 training takes 0:03:10
[2025-01-18 15:05:33 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_45.pth saving......
[2025-01-18 15:05:35 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_45.pth saved !!!
[2025-01-18 15:05:42 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.219 (7.219)	Loss 0.9747 (0.9747)	Acc@1 77.734 (77.734)	Acc@5 94.751 (94.751)	Mem 24308MB
[2025-01-18 15:05:46 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.945)	Loss 1.5349 (1.2321)	Acc@1 66.797 (72.916)	Acc@5 88.159 (91.868)	Mem 24308MB
[2025-01-18 15:05:46 internimage_s_1k_224] (main.py 575): INFO [Epoch:45] * Acc@1 73.007 Acc@5 91.887
[2025-01-18 15:05:46 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 73.0%
[2025-01-18 15:05:46 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 15:05:48 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 15:05:48 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 73.01%
[2025-01-18 15:05:55 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.277 (7.277)	Loss 3.0582 (3.0582)	Acc@1 38.525 (38.525)	Acc@5 62.109 (62.109)	Mem 24308MB
[2025-01-18 15:05:58 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.961)	Loss 3.6590 (3.2542)	Acc@1 27.856 (34.300)	Acc@5 51.880 (58.951)	Mem 24308MB
[2025-01-18 15:05:58 internimage_s_1k_224] (main.py 575): INFO [Epoch:45] * Acc@1 34.833 Acc@5 59.759
[2025-01-18 15:05:58 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 34.8%
[2025-01-18 15:05:58 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 15:06:01 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 15:06:01 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 34.83%
[2025-01-18 15:06:03 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][0/312]	eta 0:11:00 lr 0.003775	time 2.1186 (2.1186)	model_time 0.5992 (0.5992)	loss 3.5735 (3.5735)	grad_norm 1.1342 (1.1342/0.0000)	mem 24308MB
[2025-01-18 15:06:09 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][10/312]	eta 0:03:48 lr 0.003774	time 0.6382 (0.7559)	model_time 0.6381 (0.6174)	loss 4.2366 (3.7179)	grad_norm 1.2373 (1.0877/0.1419)	mem 24308MB
[2025-01-18 15:06:15 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][20/312]	eta 0:03:21 lr 0.003774	time 0.5852 (0.6891)	model_time 0.5851 (0.6164)	loss 3.5986 (3.8137)	grad_norm 2.3089 (1.5297/0.7888)	mem 24308MB
[2025-01-18 15:06:21 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][30/312]	eta 0:03:07 lr 0.003774	time 0.5737 (0.6660)	model_time 0.5735 (0.6166)	loss 4.2529 (3.8474)	grad_norm 0.8595 (1.5157/0.6955)	mem 24308MB
[2025-01-18 15:06:27 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][40/312]	eta 0:02:56 lr 0.003773	time 0.6131 (0.6503)	model_time 0.6129 (0.6128)	loss 3.5094 (3.8273)	grad_norm 1.2216 (1.4501/0.6248)	mem 24308MB
[2025-01-18 15:06:33 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][50/312]	eta 0:02:47 lr 0.003773	time 0.5857 (0.6383)	model_time 0.5853 (0.6081)	loss 3.9806 (3.8916)	grad_norm 1.0859 (1.4167/0.5887)	mem 24308MB
[2025-01-18 15:06:39 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][60/312]	eta 0:02:38 lr 0.003773	time 0.5991 (0.6304)	model_time 0.5989 (0.6051)	loss 3.5752 (3.8901)	grad_norm 0.7381 (1.4032/0.5910)	mem 24308MB
[2025-01-18 15:06:45 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][70/312]	eta 0:02:31 lr 0.003773	time 0.5828 (0.6248)	model_time 0.5823 (0.6030)	loss 4.6047 (3.8753)	grad_norm 1.8445 (1.3768/0.5606)	mem 24308MB
[2025-01-18 15:06:51 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][80/312]	eta 0:02:24 lr 0.003772	time 0.5812 (0.6211)	model_time 0.5811 (0.6019)	loss 3.8317 (3.8765)	grad_norm 1.0791 (1.4201/0.5868)	mem 24308MB
[2025-01-18 15:06:57 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][90/312]	eta 0:02:17 lr 0.003772	time 0.5728 (0.6175)	model_time 0.5723 (0.6004)	loss 3.3170 (3.8664)	grad_norm 1.8206 (1.3979/0.5663)	mem 24308MB
[2025-01-18 15:07:03 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][100/312]	eta 0:02:10 lr 0.003772	time 0.5769 (0.6158)	model_time 0.5767 (0.6004)	loss 4.7618 (3.8694)	grad_norm 1.9530 (1.4057/0.5557)	mem 24308MB
[2025-01-18 15:07:09 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][110/312]	eta 0:02:04 lr 0.003771	time 0.6678 (0.6156)	model_time 0.6676 (0.6016)	loss 4.1612 (3.8720)	grad_norm 1.0061 (1.4322/0.5661)	mem 24308MB
[2025-01-18 15:07:15 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][120/312]	eta 0:01:58 lr 0.003771	time 0.6529 (0.6165)	model_time 0.6528 (0.6036)	loss 3.9517 (3.9071)	grad_norm 1.8757 (1.4856/0.5922)	mem 24308MB
[2025-01-18 15:07:22 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][130/312]	eta 0:01:52 lr 0.003771	time 0.6760 (0.6172)	model_time 0.6758 (0.6052)	loss 3.9862 (3.9033)	grad_norm 1.0293 (1.4659/0.5786)	mem 24308MB
[2025-01-18 15:07:28 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][140/312]	eta 0:01:46 lr 0.003770	time 0.5873 (0.6168)	model_time 0.5869 (0.6057)	loss 3.0930 (3.9212)	grad_norm 2.3769 (1.4514/0.5705)	mem 24308MB
[2025-01-18 15:07:34 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][150/312]	eta 0:01:39 lr 0.003770	time 0.6694 (0.6166)	model_time 0.6692 (0.6062)	loss 2.7886 (3.9101)	grad_norm 2.9116 (1.4497/0.5676)	mem 24308MB
[2025-01-18 15:07:40 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][160/312]	eta 0:01:33 lr 0.003770	time 0.5841 (0.6151)	model_time 0.5836 (0.6053)	loss 3.9764 (3.9062)	grad_norm 0.6837 (1.4654/0.5777)	mem 24308MB
[2025-01-18 15:07:46 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][170/312]	eta 0:01:27 lr 0.003769	time 0.5811 (0.6136)	model_time 0.5809 (0.6043)	loss 3.0826 (3.9149)	grad_norm 3.3126 (1.4888/0.6193)	mem 24308MB
[2025-01-18 15:07:51 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][180/312]	eta 0:01:20 lr 0.003769	time 0.5859 (0.6122)	model_time 0.5857 (0.6034)	loss 3.4704 (3.9209)	grad_norm 0.8580 (1.4990/0.6233)	mem 24308MB
[2025-01-18 15:07:57 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][190/312]	eta 0:01:14 lr 0.003769	time 0.5745 (0.6109)	model_time 0.5744 (0.6026)	loss 4.4963 (3.9132)	grad_norm 0.9648 (1.4842/0.6150)	mem 24308MB
[2025-01-18 15:08:03 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][200/312]	eta 0:01:08 lr 0.003768	time 0.5743 (0.6097)	model_time 0.5741 (0.6018)	loss 4.6656 (3.9105)	grad_norm 0.8075 (1.4565/0.6123)	mem 24308MB
[2025-01-18 15:08:09 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][210/312]	eta 0:01:02 lr 0.003768	time 0.5925 (0.6086)	model_time 0.5920 (0.6010)	loss 2.6891 (3.8986)	grad_norm 1.7019 (1.4604/0.6046)	mem 24308MB
[2025-01-18 15:08:15 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][220/312]	eta 0:00:55 lr 0.003768	time 0.5733 (0.6085)	model_time 0.5732 (0.6013)	loss 4.3074 (3.8917)	grad_norm 0.7914 (1.4572/0.5974)	mem 24308MB
[2025-01-18 15:08:21 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][230/312]	eta 0:00:49 lr 0.003768	time 0.5890 (0.6086)	model_time 0.5885 (0.6016)	loss 4.5299 (3.8921)	grad_norm 0.9804 (1.4726/0.6190)	mem 24308MB
[2025-01-18 15:08:28 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][240/312]	eta 0:00:43 lr 0.003767	time 0.6686 (0.6094)	model_time 0.6685 (0.6028)	loss 3.6603 (3.8908)	grad_norm 1.1399 (1.4663/0.6101)	mem 24308MB
[2025-01-18 15:08:34 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][250/312]	eta 0:00:37 lr 0.003767	time 0.6667 (0.6103)	model_time 0.6665 (0.6039)	loss 4.1177 (3.8954)	grad_norm 2.3653 (1.4639/0.6050)	mem 24308MB
[2025-01-18 15:08:40 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][260/312]	eta 0:00:31 lr 0.003767	time 0.6680 (0.6110)	model_time 0.6678 (0.6048)	loss 4.5333 (3.9076)	grad_norm 3.4728 (1.4818/0.6240)	mem 24308MB
[2025-01-18 15:08:46 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][270/312]	eta 0:00:25 lr 0.003766	time 0.5758 (0.6104)	model_time 0.5757 (0.6044)	loss 3.4326 (3.9042)	grad_norm 1.0893 (1.4875/0.6279)	mem 24308MB
[2025-01-18 15:08:52 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][280/312]	eta 0:00:19 lr 0.003766	time 0.5818 (0.6104)	model_time 0.5816 (0.6047)	loss 2.4151 (3.8986)	grad_norm 1.3666 (1.4877/0.6216)	mem 24308MB
[2025-01-18 15:08:58 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][290/312]	eta 0:00:13 lr 0.003766	time 0.6306 (0.6098)	model_time 0.6305 (0.6042)	loss 4.7265 (3.8915)	grad_norm 2.2070 (1.4976/0.6165)	mem 24308MB
[2025-01-18 15:09:04 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][300/312]	eta 0:00:07 lr 0.003765	time 0.5712 (0.6088)	model_time 0.5711 (0.6034)	loss 4.5557 (3.8831)	grad_norm 1.3458 (1.5072/0.6189)	mem 24308MB
[2025-01-18 15:09:10 internimage_s_1k_224] (main.py 510): INFO Train: [46/300][310/312]	eta 0:00:01 lr 0.003765	time 0.5686 (0.6076)	model_time 0.5685 (0.6023)	loss 3.0411 (3.8805)	grad_norm 1.0644 (1.5216/0.6218)	mem 24308MB
[2025-01-18 15:09:10 internimage_s_1k_224] (main.py 519): INFO EPOCH 46 training takes 0:03:09
[2025-01-18 15:09:10 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_46.pth saving......
[2025-01-18 15:09:12 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_46.pth saved !!!
[2025-01-18 15:09:19 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.084 (7.084)	Loss 0.9946 (0.9946)	Acc@1 77.026 (77.026)	Acc@5 94.507 (94.507)	Mem 24308MB
[2025-01-18 15:09:22 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.924)	Loss 1.4842 (1.2228)	Acc@1 66.333 (72.827)	Acc@5 88.403 (91.684)	Mem 24308MB
[2025-01-18 15:09:23 internimage_s_1k_224] (main.py 575): INFO [Epoch:46] * Acc@1 72.895 Acc@5 91.799
[2025-01-18 15:09:23 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 72.9%
[2025-01-18 15:09:23 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 73.01%
[2025-01-18 15:09:31 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.991 (7.991)	Loss 2.8503 (2.8503)	Acc@1 41.724 (41.724)	Acc@5 65.845 (65.845)	Mem 24308MB
[2025-01-18 15:09:34 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.086)	Loss 3.4720 (3.0621)	Acc@1 30.811 (37.338)	Acc@5 54.883 (62.385)	Mem 24308MB
[2025-01-18 15:09:35 internimage_s_1k_224] (main.py 575): INFO [Epoch:46] * Acc@1 37.816 Acc@5 63.122
[2025-01-18 15:09:35 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 37.8%
[2025-01-18 15:09:35 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 15:09:37 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 15:09:37 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 37.82%
[2025-01-18 15:09:39 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][0/312]	eta 0:10:54 lr 0.003765	time 2.0962 (2.0962)	model_time 0.6350 (0.6350)	loss 4.2633 (4.2633)	grad_norm 1.6701 (1.6701/0.0000)	mem 24308MB
[2025-01-18 15:09:45 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][10/312]	eta 0:03:38 lr 0.003765	time 0.5948 (0.7234)	model_time 0.5946 (0.5902)	loss 4.0093 (3.6938)	grad_norm 0.8721 (1.3562/0.3688)	mem 24308MB
[2025-01-18 15:09:51 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][20/312]	eta 0:03:12 lr 0.003764	time 0.5738 (0.6597)	model_time 0.5733 (0.5897)	loss 3.6251 (3.5920)	grad_norm 1.4427 (1.4538/0.4293)	mem 24308MB
[2025-01-18 15:09:57 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][30/312]	eta 0:03:00 lr 0.003764	time 0.6309 (0.6399)	model_time 0.6307 (0.5924)	loss 2.5928 (3.4976)	grad_norm 3.2297 (1.5416/0.5395)	mem 24308MB
[2025-01-18 15:10:03 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][40/312]	eta 0:02:51 lr 0.003764	time 0.5724 (0.6317)	model_time 0.5720 (0.5957)	loss 3.9202 (3.5209)	grad_norm 1.2021 (1.4774/0.5236)	mem 24308MB
[2025-01-18 15:10:09 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][50/312]	eta 0:02:44 lr 0.003763	time 0.6148 (0.6281)	model_time 0.6147 (0.5991)	loss 4.6571 (3.5556)	grad_norm 2.0417 (1.5065/0.5425)	mem 24308MB
[2025-01-18 15:10:15 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][60/312]	eta 0:02:38 lr 0.003763	time 0.5825 (0.6291)	model_time 0.5823 (0.6046)	loss 4.5364 (3.5644)	grad_norm 2.0540 (1.5116/0.5189)	mem 24308MB
[2025-01-18 15:10:21 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][70/312]	eta 0:02:32 lr 0.003763	time 0.5964 (0.6290)	model_time 0.5959 (0.6079)	loss 3.8646 (3.5828)	grad_norm 1.1256 (1.5410/0.5188)	mem 24308MB
[2025-01-18 15:10:27 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][80/312]	eta 0:02:25 lr 0.003762	time 0.6678 (0.6253)	model_time 0.6676 (0.6068)	loss 4.0867 (3.6060)	grad_norm 0.8443 (1.5448/0.5150)	mem 24308MB
[2025-01-18 15:10:33 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][90/312]	eta 0:02:18 lr 0.003762	time 0.5750 (0.6228)	model_time 0.5748 (0.6063)	loss 4.1599 (3.6225)	grad_norm 3.4260 (1.5449/0.5453)	mem 24308MB
[2025-01-18 15:10:39 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][100/312]	eta 0:02:11 lr 0.003762	time 0.5765 (0.6195)	model_time 0.5763 (0.6046)	loss 4.0806 (3.6315)	grad_norm 1.5259 (1.5776/0.5658)	mem 24308MB
[2025-01-18 15:10:45 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][110/312]	eta 0:02:04 lr 0.003762	time 0.5809 (0.6171)	model_time 0.5807 (0.6035)	loss 3.7394 (3.6220)	grad_norm 0.9661 (1.5300/0.5638)	mem 24308MB
[2025-01-18 15:10:51 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][120/312]	eta 0:01:58 lr 0.003761	time 0.6182 (0.6150)	model_time 0.6179 (0.6024)	loss 3.6265 (3.6210)	grad_norm 1.3735 (1.5355/0.5510)	mem 24308MB
[2025-01-18 15:10:57 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][130/312]	eta 0:01:51 lr 0.003761	time 0.5846 (0.6130)	model_time 0.5844 (0.6014)	loss 3.5457 (3.6557)	grad_norm 1.7466 (1.5418/0.5590)	mem 24308MB
[2025-01-18 15:11:03 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][140/312]	eta 0:01:45 lr 0.003761	time 0.5645 (0.6114)	model_time 0.5642 (0.6006)	loss 3.7912 (3.6691)	grad_norm 1.2980 (1.5592/0.5700)	mem 24308MB
[2025-01-18 15:11:09 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][150/312]	eta 0:01:38 lr 0.003760	time 0.5980 (0.6102)	model_time 0.5978 (0.6001)	loss 3.7257 (3.6788)	grad_norm 1.3226 (1.5370/0.5649)	mem 24308MB
[2025-01-18 15:11:15 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][160/312]	eta 0:01:32 lr 0.003760	time 0.5725 (0.6111)	model_time 0.5723 (0.6016)	loss 3.3812 (3.6590)	grad_norm 0.9364 (1.5112/0.5607)	mem 24308MB
[2025-01-18 15:11:21 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][170/312]	eta 0:01:26 lr 0.003760	time 0.5812 (0.6117)	model_time 0.5806 (0.6027)	loss 4.8896 (3.6811)	grad_norm 2.9252 (1.5432/0.5997)	mem 24308MB
[2025-01-18 15:11:28 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][180/312]	eta 0:01:21 lr 0.003759	time 0.5793 (0.6146)	model_time 0.5791 (0.6061)	loss 4.6214 (3.6905)	grad_norm 1.7637 (1.5547/0.5993)	mem 24308MB
[2025-01-18 15:11:34 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][190/312]	eta 0:01:15 lr 0.003759	time 0.6707 (0.6152)	model_time 0.6706 (0.6071)	loss 3.8631 (3.6930)	grad_norm 1.8632 (1.5841/0.6175)	mem 24308MB
[2025-01-18 15:11:40 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][200/312]	eta 0:01:08 lr 0.003759	time 0.5856 (0.6140)	model_time 0.5854 (0.6063)	loss 4.2896 (3.7064)	grad_norm 1.5792 (1.5773/0.6086)	mem 24308MB
[2025-01-18 15:11:46 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][210/312]	eta 0:01:02 lr 0.003758	time 0.5830 (0.6140)	model_time 0.5829 (0.6067)	loss 4.2488 (3.7103)	grad_norm 1.2021 (1.5638/0.6037)	mem 24308MB
[2025-01-18 15:11:52 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][220/312]	eta 0:00:56 lr 0.003758	time 0.6082 (0.6130)	model_time 0.6080 (0.6060)	loss 3.2167 (3.7146)	grad_norm 1.2469 (1.5497/0.5951)	mem 24308MB
[2025-01-18 15:11:58 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][230/312]	eta 0:00:50 lr 0.003758	time 0.6018 (0.6123)	model_time 0.6013 (0.6055)	loss 3.5704 (3.7138)	grad_norm 1.2694 (1.5347/0.5873)	mem 24308MB
[2025-01-18 15:12:04 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][240/312]	eta 0:00:44 lr 0.003757	time 0.6132 (0.6117)	model_time 0.6130 (0.6052)	loss 4.2610 (3.7163)	grad_norm 2.2003 (1.5404/0.5819)	mem 24308MB
[2025-01-18 15:12:10 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][250/312]	eta 0:00:37 lr 0.003757	time 0.5842 (0.6110)	model_time 0.5840 (0.6048)	loss 4.0306 (3.7302)	grad_norm 2.1178 (1.5654/0.6054)	mem 24308MB
[2025-01-18 15:12:16 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][260/312]	eta 0:00:31 lr 0.003757	time 0.5699 (0.6101)	model_time 0.5694 (0.6041)	loss 4.0224 (3.7289)	grad_norm 0.9433 (1.5655/0.6117)	mem 24308MB
[2025-01-18 15:12:22 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][270/312]	eta 0:00:25 lr 0.003756	time 0.5929 (0.6097)	model_time 0.5927 (0.6039)	loss 4.5725 (3.7213)	grad_norm 2.7515 (1.5635/0.6084)	mem 24308MB
[2025-01-18 15:12:28 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][280/312]	eta 0:00:19 lr 0.003756	time 0.6562 (0.6103)	model_time 0.6560 (0.6046)	loss 3.1254 (3.7272)	grad_norm 1.1025 (1.5521/0.6016)	mem 24308MB
[2025-01-18 15:12:34 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][290/312]	eta 0:00:13 lr 0.003756	time 0.5732 (0.6104)	model_time 0.5730 (0.6050)	loss 3.2585 (3.7323)	grad_norm 2.3484 (1.5629/0.6355)	mem 24308MB
[2025-01-18 15:12:41 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][300/312]	eta 0:00:07 lr 0.003755	time 0.5650 (0.6110)	model_time 0.5649 (0.6057)	loss 3.8983 (3.7349)	grad_norm 0.8101 (1.5737/0.6654)	mem 24308MB
[2025-01-18 15:12:47 internimage_s_1k_224] (main.py 510): INFO Train: [47/300][310/312]	eta 0:00:01 lr 0.003755	time 0.6708 (0.6114)	model_time 0.6707 (0.6063)	loss 4.0565 (3.7307)	grad_norm 0.9226 (1.5821/0.6663)	mem 24308MB
[2025-01-18 15:12:47 internimage_s_1k_224] (main.py 519): INFO EPOCH 47 training takes 0:03:10
[2025-01-18 15:12:47 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_47.pth saving......
[2025-01-18 15:12:49 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_47.pth saved !!!
[2025-01-18 15:12:56 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.011 (7.011)	Loss 1.0467 (1.0467)	Acc@1 77.466 (77.466)	Acc@5 94.434 (94.434)	Mem 24308MB
[2025-01-18 15:12:59 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.924)	Loss 1.5285 (1.2512)	Acc@1 67.676 (73.298)	Acc@5 88.281 (91.815)	Mem 24308MB
[2025-01-18 15:13:00 internimage_s_1k_224] (main.py 575): INFO [Epoch:47] * Acc@1 73.335 Acc@5 91.907
[2025-01-18 15:13:00 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 73.3%
[2025-01-18 15:13:00 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 15:13:01 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 15:13:01 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 73.33%
[2025-01-18 15:13:08 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.968 (6.968)	Loss 2.6658 (2.6658)	Acc@1 45.044 (45.044)	Acc@5 69.092 (69.092)	Mem 24308MB
[2025-01-18 15:13:12 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.927)	Loss 3.3046 (2.8907)	Acc@1 33.472 (40.316)	Acc@5 57.715 (65.321)	Mem 24308MB
[2025-01-18 15:13:12 internimage_s_1k_224] (main.py 575): INFO [Epoch:47] * Acc@1 40.695 Acc@5 65.981
[2025-01-18 15:13:12 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 40.7%
[2025-01-18 15:13:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 15:13:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 15:13:14 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 40.69%
[2025-01-18 15:13:16 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][0/312]	eta 0:10:22 lr 0.003755	time 1.9950 (1.9950)	model_time 0.5948 (0.5948)	loss 3.5458 (3.5458)	grad_norm 1.1739 (1.1739/0.0000)	mem 24308MB
[2025-01-18 15:13:22 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][10/312]	eta 0:03:43 lr 0.003755	time 0.5759 (0.7407)	model_time 0.5758 (0.6131)	loss 2.5868 (3.8097)	grad_norm 1.5485 (1.1989/0.2721)	mem 24308MB
[2025-01-18 15:13:28 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][20/312]	eta 0:03:16 lr 0.003754	time 0.5795 (0.6730)	model_time 0.5794 (0.6059)	loss 4.2316 (3.7693)	grad_norm 1.2197 (1.5037/0.6493)	mem 24308MB
[2025-01-18 15:13:34 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][30/312]	eta 0:03:02 lr 0.003754	time 0.5741 (0.6458)	model_time 0.5736 (0.6003)	loss 4.3060 (3.8349)	grad_norm 1.2898 (1.6460/0.7850)	mem 24308MB
[2025-01-18 15:13:40 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][40/312]	eta 0:02:52 lr 0.003754	time 0.5940 (0.6326)	model_time 0.5938 (0.5980)	loss 4.3209 (3.8331)	grad_norm 1.0041 (1.5905/0.7186)	mem 24308MB
[2025-01-18 15:13:46 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][50/312]	eta 0:02:43 lr 0.003753	time 0.5952 (0.6247)	model_time 0.5950 (0.5969)	loss 2.9441 (3.8007)	grad_norm 1.8489 (1.5729/0.6794)	mem 24308MB
[2025-01-18 15:13:52 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][60/312]	eta 0:02:35 lr 0.003753	time 0.5904 (0.6187)	model_time 0.5900 (0.5953)	loss 3.6318 (3.8073)	grad_norm 1.3435 (1.6389/0.7454)	mem 24308MB
[2025-01-18 15:13:58 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][70/312]	eta 0:02:28 lr 0.003753	time 0.5858 (0.6144)	model_time 0.5853 (0.5942)	loss 3.1009 (3.7839)	grad_norm 1.4527 (1.6178/0.7383)	mem 24308MB
[2025-01-18 15:14:04 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][80/312]	eta 0:02:21 lr 0.003753	time 0.5711 (0.6113)	model_time 0.5710 (0.5936)	loss 3.1294 (3.7649)	grad_norm 1.3581 (1.6130/0.7165)	mem 24308MB
[2025-01-18 15:14:10 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][90/312]	eta 0:02:15 lr 0.003752	time 0.6578 (0.6124)	model_time 0.6577 (0.5966)	loss 4.1145 (3.7374)	grad_norm 1.3480 (1.5768/0.7010)	mem 24308MB
[2025-01-18 15:14:16 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][100/312]	eta 0:02:10 lr 0.003752	time 0.6625 (0.6138)	model_time 0.6620 (0.5996)	loss 3.9593 (3.7461)	grad_norm 1.3006 (1.5201/0.6915)	mem 24308MB
[2025-01-18 15:14:23 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][110/312]	eta 0:02:04 lr 0.003752	time 0.6662 (0.6159)	model_time 0.6660 (0.6029)	loss 2.7312 (3.7401)	grad_norm 1.1855 (1.4883/0.6747)	mem 24308MB
[2025-01-18 15:14:29 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][120/312]	eta 0:01:58 lr 0.003751	time 0.5898 (0.6156)	model_time 0.5894 (0.6037)	loss 4.4907 (3.7742)	grad_norm 1.1275 (1.4526/0.6606)	mem 24308MB
[2025-01-18 15:14:35 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][130/312]	eta 0:01:51 lr 0.003751	time 0.5928 (0.6151)	model_time 0.5924 (0.6041)	loss 4.1908 (3.7511)	grad_norm 0.7370 (1.4401/0.6449)	mem 24308MB
[2025-01-18 15:14:41 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][140/312]	eta 0:01:45 lr 0.003751	time 0.6268 (0.6160)	model_time 0.6266 (0.6057)	loss 3.9880 (3.7693)	grad_norm 3.4090 (1.4567/0.6537)	mem 24308MB
[2025-01-18 15:14:47 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][150/312]	eta 0:01:39 lr 0.003750	time 0.5769 (0.6135)	model_time 0.5768 (0.6039)	loss 4.6270 (3.7735)	grad_norm 1.3145 (1.4532/0.6415)	mem 24308MB
[2025-01-18 15:14:53 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][160/312]	eta 0:01:33 lr 0.003750	time 0.5774 (0.6119)	model_time 0.5769 (0.6028)	loss 4.3923 (3.7544)	grad_norm 1.3502 (1.4770/0.6454)	mem 24308MB
[2025-01-18 15:14:59 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][170/312]	eta 0:01:26 lr 0.003750	time 0.5865 (0.6107)	model_time 0.5861 (0.6021)	loss 4.6306 (3.7647)	grad_norm 1.1696 (1.4567/0.6337)	mem 24308MB
[2025-01-18 15:15:05 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][180/312]	eta 0:01:20 lr 0.003749	time 0.6449 (0.6101)	model_time 0.6447 (0.6020)	loss 4.2785 (3.7787)	grad_norm 1.4444 (1.4534/0.6211)	mem 24308MB
[2025-01-18 15:15:10 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][190/312]	eta 0:01:14 lr 0.003749	time 0.5816 (0.6086)	model_time 0.5812 (0.6009)	loss 3.8867 (3.7734)	grad_norm 1.4824 (1.4570/0.6130)	mem 24308MB
[2025-01-18 15:15:16 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][200/312]	eta 0:01:08 lr 0.003749	time 0.5694 (0.6075)	model_time 0.5692 (0.6001)	loss 3.4685 (3.7743)	grad_norm 1.0206 (1.4523/0.6042)	mem 24308MB
[2025-01-18 15:15:23 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][210/312]	eta 0:01:02 lr 0.003748	time 0.6729 (0.6081)	model_time 0.6727 (0.6011)	loss 4.2372 (3.7815)	grad_norm 1.1877 (1.4710/0.6152)	mem 24308MB
[2025-01-18 15:15:29 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][220/312]	eta 0:00:56 lr 0.003748	time 0.6714 (0.6093)	model_time 0.6709 (0.6026)	loss 3.1340 (3.7748)	grad_norm 1.9239 (1.4865/0.6207)	mem 24308MB
[2025-01-18 15:15:35 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][230/312]	eta 0:00:50 lr 0.003748	time 0.6775 (0.6105)	model_time 0.6771 (0.6041)	loss 3.3128 (3.7722)	grad_norm 0.9770 (1.4689/0.6156)	mem 24308MB
[2025-01-18 15:15:41 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][240/312]	eta 0:00:43 lr 0.003747	time 0.5841 (0.6106)	model_time 0.5837 (0.6044)	loss 3.1081 (3.7680)	grad_norm 1.4788 (1.4651/0.6060)	mem 24308MB
[2025-01-18 15:15:47 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][250/312]	eta 0:00:37 lr 0.003747	time 0.5775 (0.6101)	model_time 0.5771 (0.6042)	loss 4.6686 (3.7745)	grad_norm 1.6923 (1.4904/0.6266)	mem 24308MB
[2025-01-18 15:15:53 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][260/312]	eta 0:00:31 lr 0.003747	time 0.5750 (0.6098)	model_time 0.5749 (0.6040)	loss 4.2399 (3.7759)	grad_norm 1.2082 (1.4988/0.6247)	mem 24308MB
[2025-01-18 15:15:59 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][270/312]	eta 0:00:25 lr 0.003746	time 0.5713 (0.6093)	model_time 0.5709 (0.6037)	loss 4.7060 (3.7798)	grad_norm 1.0592 (1.5051/0.6292)	mem 24308MB
[2025-01-18 15:16:05 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][280/312]	eta 0:00:19 lr 0.003746	time 0.5968 (0.6086)	model_time 0.5963 (0.6033)	loss 3.7006 (3.7786)	grad_norm 2.0913 (1.4914/0.6259)	mem 24308MB
[2025-01-18 15:16:11 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][290/312]	eta 0:00:13 lr 0.003746	time 0.5800 (0.6079)	model_time 0.5798 (0.6027)	loss 3.3333 (3.7788)	grad_norm 1.1933 (1.5174/0.6702)	mem 24308MB
[2025-01-18 15:16:17 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][300/312]	eta 0:00:07 lr 0.003745	time 0.5668 (0.6070)	model_time 0.5667 (0.6020)	loss 4.5651 (3.7853)	grad_norm 1.2456 (1.5156/0.6651)	mem 24308MB
[2025-01-18 15:16:23 internimage_s_1k_224] (main.py 510): INFO Train: [48/300][310/312]	eta 0:00:01 lr 0.003745	time 0.5616 (0.6061)	model_time 0.5615 (0.6012)	loss 4.1880 (3.7836)	grad_norm 2.2225 (1.5287/0.6680)	mem 24308MB
[2025-01-18 15:16:23 internimage_s_1k_224] (main.py 519): INFO EPOCH 48 training takes 0:03:09
[2025-01-18 15:16:23 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_48.pth saving......
[2025-01-18 15:16:25 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_48.pth saved !!!
[2025-01-18 15:16:32 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.810 (6.810)	Loss 1.0118 (1.0118)	Acc@1 77.588 (77.588)	Acc@5 94.849 (94.849)	Mem 24308MB
[2025-01-18 15:16:35 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.908)	Loss 1.4921 (1.2252)	Acc@1 67.603 (73.060)	Acc@5 88.477 (91.886)	Mem 24308MB
[2025-01-18 15:16:35 internimage_s_1k_224] (main.py 575): INFO [Epoch:48] * Acc@1 73.079 Acc@5 91.917
[2025-01-18 15:16:35 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 73.1%
[2025-01-18 15:16:35 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 73.33%
[2025-01-18 15:16:43 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.924 (7.924)	Loss 2.5022 (2.5022)	Acc@1 47.754 (47.754)	Acc@5 72.046 (72.046)	Mem 24308MB
[2025-01-18 15:16:47 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.083)	Loss 3.1514 (2.7364)	Acc@1 35.498 (42.898)	Acc@5 60.132 (67.836)	Mem 24308MB
[2025-01-18 15:16:47 internimage_s_1k_224] (main.py 575): INFO [Epoch:48] * Acc@1 43.256 Acc@5 68.444
[2025-01-18 15:16:47 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 43.3%
[2025-01-18 15:16:47 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 15:16:50 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 15:16:50 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 43.26%
[2025-01-18 15:16:52 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][0/312]	eta 0:10:39 lr 0.003745	time 2.0499 (2.0499)	model_time 0.6002 (0.6002)	loss 4.0127 (4.0127)	grad_norm 1.6199 (1.6199/0.0000)	mem 24308MB
[2025-01-18 15:16:58 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][10/312]	eta 0:03:38 lr 0.003745	time 0.5910 (0.7236)	model_time 0.5909 (0.5914)	loss 3.0450 (3.9715)	grad_norm 1.0667 (1.6453/0.7263)	mem 24308MB
[2025-01-18 15:17:04 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][20/312]	eta 0:03:15 lr 0.003744	time 0.6697 (0.6711)	model_time 0.6695 (0.6017)	loss 2.7519 (3.6955)	grad_norm 0.9255 (1.6379/0.7615)	mem 24308MB
[2025-01-18 15:17:10 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][30/312]	eta 0:03:06 lr 0.003744	time 0.6863 (0.6608)	model_time 0.6861 (0.6137)	loss 2.3841 (3.7241)	grad_norm 1.0271 (1.4881/0.6683)	mem 24308MB
[2025-01-18 15:17:17 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][40/312]	eta 0:02:58 lr 0.003744	time 0.6540 (0.6556)	model_time 0.6538 (0.6198)	loss 4.1475 (3.6806)	grad_norm 2.2045 (1.4764/0.6167)	mem 24308MB
[2025-01-18 15:17:23 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][50/312]	eta 0:02:50 lr 0.003743	time 0.5833 (0.6524)	model_time 0.5831 (0.6236)	loss 3.4395 (3.6757)	grad_norm 1.3510 (1.5678/0.6331)	mem 24308MB
[2025-01-18 15:17:29 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][60/312]	eta 0:02:42 lr 0.003743	time 0.5861 (0.6448)	model_time 0.5857 (0.6206)	loss 2.7414 (3.6679)	grad_norm 1.6794 (1.5482/0.6105)	mem 24308MB
[2025-01-18 15:17:35 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][70/312]	eta 0:02:34 lr 0.003743	time 0.5904 (0.6402)	model_time 0.5900 (0.6193)	loss 3.9207 (3.7424)	grad_norm 1.1061 (1.6028/0.6588)	mem 24308MB
[2025-01-18 15:17:41 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][80/312]	eta 0:02:27 lr 0.003742	time 0.5829 (0.6342)	model_time 0.5825 (0.6159)	loss 3.8670 (3.7471)	grad_norm 0.9569 (1.5826/0.6482)	mem 24308MB
[2025-01-18 15:17:47 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][90/312]	eta 0:02:19 lr 0.003742	time 0.5852 (0.6299)	model_time 0.5851 (0.6136)	loss 2.8330 (3.7747)	grad_norm 0.8633 (1.6685/0.7732)	mem 24308MB
[2025-01-18 15:17:53 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][100/312]	eta 0:02:12 lr 0.003742	time 0.5816 (0.6259)	model_time 0.5812 (0.6111)	loss 3.3917 (3.7739)	grad_norm 1.1028 (1.6161/0.7595)	mem 24308MB
[2025-01-18 15:17:59 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][110/312]	eta 0:02:05 lr 0.003741	time 0.5829 (0.6224)	model_time 0.5825 (0.6090)	loss 4.7193 (3.7443)	grad_norm 1.8248 (1.6140/0.7397)	mem 24308MB
[2025-01-18 15:18:05 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][120/312]	eta 0:01:59 lr 0.003741	time 0.5856 (0.6198)	model_time 0.5854 (0.6074)	loss 3.9882 (3.7483)	grad_norm 0.9673 (1.5769/0.7209)	mem 24308MB
[2025-01-18 15:18:10 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][130/312]	eta 0:01:52 lr 0.003741	time 0.5717 (0.6170)	model_time 0.5715 (0.6056)	loss 4.6777 (3.7637)	grad_norm 3.3758 (1.5659/0.7218)	mem 24308MB
[2025-01-18 15:18:16 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][140/312]	eta 0:01:45 lr 0.003740	time 0.5797 (0.6159)	model_time 0.5793 (0.6053)	loss 3.8944 (3.7502)	grad_norm 0.7430 (1.5674/0.7130)	mem 24308MB
[2025-01-18 15:18:23 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][150/312]	eta 0:01:40 lr 0.003740	time 0.6773 (0.6175)	model_time 0.6772 (0.6075)	loss 3.6392 (3.7523)	grad_norm 1.5639 (1.5713/0.6966)	mem 24308MB
[2025-01-18 15:18:29 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][160/312]	eta 0:01:34 lr 0.003740	time 0.6675 (0.6188)	model_time 0.6671 (0.6094)	loss 4.0372 (3.7583)	grad_norm 1.7983 (1.5488/0.6829)	mem 24308MB
[2025-01-18 15:18:36 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][170/312]	eta 0:01:27 lr 0.003739	time 0.6811 (0.6195)	model_time 0.6806 (0.6106)	loss 2.8099 (3.7418)	grad_norm 2.3306 (1.5590/0.6848)	mem 24308MB
[2025-01-18 15:18:42 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][180/312]	eta 0:01:21 lr 0.003739	time 0.5820 (0.6188)	model_time 0.5818 (0.6104)	loss 3.2603 (3.7386)	grad_norm 1.4083 (1.6014/0.7619)	mem 24308MB
[2025-01-18 15:18:48 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][190/312]	eta 0:01:15 lr 0.003739	time 0.5878 (0.6179)	model_time 0.5874 (0.6099)	loss 2.8578 (3.7327)	grad_norm 0.7207 (1.5768/0.7518)	mem 24308MB
[2025-01-18 15:18:54 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][200/312]	eta 0:01:09 lr 0.003738	time 0.5880 (0.6168)	model_time 0.5876 (0.6092)	loss 4.2973 (3.7449)	grad_norm 0.9759 (1.5572/0.7406)	mem 24308MB
[2025-01-18 15:19:00 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][210/312]	eta 0:01:02 lr 0.003738	time 0.5864 (0.6157)	model_time 0.5862 (0.6084)	loss 4.1273 (3.7593)	grad_norm 0.9572 (1.5699/0.7371)	mem 24308MB
[2025-01-18 15:19:05 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][220/312]	eta 0:00:56 lr 0.003738	time 0.5910 (0.6145)	model_time 0.5909 (0.6075)	loss 3.1583 (3.7555)	grad_norm 1.1101 (1.5573/0.7248)	mem 24308MB
[2025-01-18 15:19:11 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][230/312]	eta 0:00:50 lr 0.003737	time 0.5838 (0.6134)	model_time 0.5833 (0.6067)	loss 3.9077 (3.7605)	grad_norm 1.6478 (1.5660/0.7174)	mem 24308MB
[2025-01-18 15:19:17 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][240/312]	eta 0:00:44 lr 0.003737	time 0.5831 (0.6124)	model_time 0.5829 (0.6060)	loss 3.1341 (3.7655)	grad_norm 1.1579 (1.5611/0.7075)	mem 24308MB
[2025-01-18 15:19:23 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][250/312]	eta 0:00:37 lr 0.003737	time 0.6033 (0.6116)	model_time 0.6029 (0.6054)	loss 2.9473 (3.7628)	grad_norm 1.3371 (1.5623/0.7054)	mem 24308MB
[2025-01-18 15:19:29 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][260/312]	eta 0:00:31 lr 0.003736	time 0.5784 (0.6112)	model_time 0.5782 (0.6053)	loss 3.4593 (3.7656)	grad_norm 1.4935 (1.5449/0.6986)	mem 24308MB
[2025-01-18 15:19:36 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][270/312]	eta 0:00:25 lr 0.003736	time 0.6953 (0.6122)	model_time 0.6952 (0.6065)	loss 2.9542 (3.7628)	grad_norm 3.9875 (1.5610/0.7186)	mem 24308MB
[2025-01-18 15:19:42 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][280/312]	eta 0:00:19 lr 0.003736	time 0.6703 (0.6130)	model_time 0.6699 (0.6075)	loss 4.1912 (3.7762)	grad_norm 1.5022 (1.5882/0.7364)	mem 24308MB
[2025-01-18 15:19:48 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][290/312]	eta 0:00:13 lr 0.003735	time 0.6660 (0.6134)	model_time 0.6656 (0.6080)	loss 4.1665 (3.7817)	grad_norm 0.7312 (1.5842/0.7313)	mem 24308MB
[2025-01-18 15:19:54 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][300/312]	eta 0:00:07 lr 0.003735	time 0.5704 (0.6129)	model_time 0.5703 (0.6077)	loss 3.7125 (3.7721)	grad_norm 1.2157 (1.5710/0.7293)	mem 24308MB
[2025-01-18 15:20:00 internimage_s_1k_224] (main.py 510): INFO Train: [49/300][310/312]	eta 0:00:01 lr 0.003735	time 0.5561 (0.6122)	model_time 0.5560 (0.6071)	loss 4.1906 (3.7658)	grad_norm 1.0471 (1.5681/0.7234)	mem 24308MB
[2025-01-18 15:20:01 internimage_s_1k_224] (main.py 519): INFO EPOCH 49 training takes 0:03:10
[2025-01-18 15:20:01 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_49.pth saving......
[2025-01-18 15:20:02 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_49.pth saved !!!
[2025-01-18 15:20:10 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.039 (7.039)	Loss 1.0256 (1.0256)	Acc@1 77.490 (77.490)	Acc@5 94.385 (94.385)	Mem 24308MB
[2025-01-18 15:20:13 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.913)	Loss 1.4575 (1.2105)	Acc@1 67.285 (73.067)	Acc@5 88.672 (91.901)	Mem 24308MB
[2025-01-18 15:20:13 internimage_s_1k_224] (main.py 575): INFO [Epoch:49] * Acc@1 73.223 Acc@5 92.015
[2025-01-18 15:20:13 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 73.2%
[2025-01-18 15:20:13 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 73.33%
[2025-01-18 15:20:21 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.854 (7.854)	Loss 2.3505 (2.3505)	Acc@1 50.220 (50.220)	Acc@5 74.463 (74.463)	Mem 24308MB
[2025-01-18 15:20:25 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (1.071)	Loss 3.0105 (2.5945)	Acc@1 37.793 (45.335)	Acc@5 62.354 (70.162)	Mem 24308MB
[2025-01-18 15:20:25 internimage_s_1k_224] (main.py 575): INFO [Epoch:49] * Acc@1 45.687 Acc@5 70.711
[2025-01-18 15:20:25 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 45.7%
[2025-01-18 15:20:25 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 15:20:27 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 15:20:27 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 45.69%
[2025-01-18 15:20:29 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][0/312]	eta 0:10:59 lr 0.003735	time 2.1125 (2.1125)	model_time 0.6022 (0.6022)	loss 3.4046 (3.4046)	grad_norm 1.5711 (1.5711/0.0000)	mem 24308MB
[2025-01-18 15:20:35 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][10/312]	eta 0:03:41 lr 0.003734	time 0.5934 (0.7334)	model_time 0.5932 (0.5958)	loss 3.0221 (3.7623)	grad_norm 2.1197 (1.4915/0.4502)	mem 24308MB
[2025-01-18 15:20:41 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][20/312]	eta 0:03:14 lr 0.003734	time 0.5982 (0.6674)	model_time 0.5980 (0.5952)	loss 4.8331 (3.8708)	grad_norm 1.1206 (1.5599/0.5626)	mem 24308MB
[2025-01-18 15:20:47 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][30/312]	eta 0:03:01 lr 0.003734	time 0.5842 (0.6449)	model_time 0.5837 (0.5959)	loss 3.7531 (3.8997)	grad_norm 1.6656 (1.5701/0.5654)	mem 24308MB
[2025-01-18 15:20:53 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][40/312]	eta 0:02:51 lr 0.003733	time 0.5932 (0.6308)	model_time 0.5928 (0.5936)	loss 4.6860 (3.8750)	grad_norm 0.7008 (1.4690/0.5459)	mem 24308MB
[2025-01-18 15:20:59 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][50/312]	eta 0:02:43 lr 0.003733	time 0.5908 (0.6229)	model_time 0.5904 (0.5930)	loss 3.3195 (3.7842)	grad_norm 2.8386 (1.5458/0.5656)	mem 24308MB
[2025-01-18 15:21:04 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][60/312]	eta 0:02:35 lr 0.003733	time 0.5923 (0.6166)	model_time 0.5918 (0.5915)	loss 3.8456 (3.8066)	grad_norm 2.1274 (1.6174/0.6526)	mem 24308MB
[2025-01-18 15:21:10 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][70/312]	eta 0:02:28 lr 0.003732	time 0.6789 (0.6146)	model_time 0.6787 (0.5930)	loss 4.0603 (3.7980)	grad_norm 0.8724 (1.5915/0.6327)	mem 24308MB
[2025-01-18 15:21:17 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][80/312]	eta 0:02:22 lr 0.003732	time 0.5898 (0.6149)	model_time 0.5894 (0.5959)	loss 2.8832 (3.7917)	grad_norm 1.4830 (1.5436/0.6120)	mem 24308MB
[2025-01-18 15:21:23 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][90/312]	eta 0:02:16 lr 0.003732	time 0.5954 (0.6162)	model_time 0.5952 (0.5992)	loss 3.5533 (3.7611)	grad_norm 0.9771 (1.5270/0.5984)	mem 24308MB
[2025-01-18 15:21:29 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][100/312]	eta 0:02:11 lr 0.003731	time 0.6557 (0.6190)	model_time 0.6555 (0.6037)	loss 4.0435 (3.7650)	grad_norm 1.0762 (1.5011/0.5840)	mem 24308MB
[2025-01-18 15:21:36 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][110/312]	eta 0:02:05 lr 0.003731	time 0.6093 (0.6196)	model_time 0.6088 (0.6056)	loss 3.9548 (3.7706)	grad_norm 1.1577 (1.5032/0.5910)	mem 24308MB
[2025-01-18 15:21:42 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][120/312]	eta 0:01:58 lr 0.003731	time 0.5854 (0.6184)	model_time 0.5850 (0.6055)	loss 3.3993 (3.7852)	grad_norm 0.9387 (1.5392/0.6098)	mem 24308MB
[2025-01-18 15:21:48 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][130/312]	eta 0:01:52 lr 0.003730	time 0.5723 (0.6174)	model_time 0.5721 (0.6055)	loss 3.1053 (3.7664)	grad_norm 1.4572 (1.5243/0.5996)	mem 24308MB
[2025-01-18 15:21:54 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][140/312]	eta 0:01:45 lr 0.003730	time 0.5827 (0.6158)	model_time 0.5826 (0.6047)	loss 2.8671 (3.7701)	grad_norm 0.9048 (1.5247/0.6047)	mem 24308MB
[2025-01-18 15:22:00 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][150/312]	eta 0:01:39 lr 0.003730	time 0.6853 (0.6142)	model_time 0.6851 (0.6038)	loss 3.6357 (3.7834)	grad_norm 3.2237 (1.5318/0.6102)	mem 24308MB
[2025-01-18 15:22:05 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][160/312]	eta 0:01:33 lr 0.003729	time 0.5880 (0.6121)	model_time 0.5875 (0.6024)	loss 3.8080 (3.7863)	grad_norm 1.1680 (1.5610/0.6517)	mem 24308MB
[2025-01-18 15:22:11 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][170/312]	eta 0:01:26 lr 0.003729	time 0.5919 (0.6108)	model_time 0.5917 (0.6015)	loss 4.4287 (3.7814)	grad_norm 1.1914 (1.5449/0.6451)	mem 24308MB
[2025-01-18 15:22:17 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][180/312]	eta 0:01:20 lr 0.003729	time 0.5961 (0.6097)	model_time 0.5959 (0.6010)	loss 3.9178 (3.7713)	grad_norm 1.1122 (1.5280/0.6351)	mem 24308MB
[2025-01-18 15:22:23 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][190/312]	eta 0:01:14 lr 0.003728	time 0.6775 (0.6095)	model_time 0.6773 (0.6012)	loss 2.2503 (3.7666)	grad_norm 1.7497 (1.5331/0.6322)	mem 24308MB
[2025-01-18 15:22:29 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][200/312]	eta 0:01:08 lr 0.003728	time 0.6473 (0.6095)	model_time 0.6468 (0.6016)	loss 3.9375 (3.7753)	grad_norm 1.3875 (1.5246/0.6262)	mem 24308MB
[2025-01-18 15:22:36 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][210/312]	eta 0:01:02 lr 0.003728	time 0.5851 (0.6112)	model_time 0.5850 (0.6037)	loss 3.3047 (3.7686)	grad_norm 1.8644 (1.5427/0.6358)	mem 24308MB
[2025-01-18 15:22:42 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][220/312]	eta 0:00:56 lr 0.003727	time 0.6665 (0.6132)	model_time 0.6661 (0.6059)	loss 3.3211 (3.7772)	grad_norm 1.8894 (1.5533/0.6338)	mem 24308MB
[2025-01-18 15:22:48 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][230/312]	eta 0:00:50 lr 0.003727	time 0.5896 (0.6132)	model_time 0.5892 (0.6063)	loss 3.4384 (3.7834)	grad_norm 2.0559 (1.5502/0.6311)	mem 24308MB
[2025-01-18 15:22:54 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][240/312]	eta 0:00:44 lr 0.003727	time 0.5789 (0.6124)	model_time 0.5787 (0.6058)	loss 4.1394 (3.7883)	grad_norm 1.0304 (1.5525/0.6280)	mem 24308MB
[2025-01-18 15:23:00 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][250/312]	eta 0:00:37 lr 0.003726	time 0.5866 (0.6122)	model_time 0.5861 (0.6058)	loss 2.7878 (3.7838)	grad_norm 1.4881 (1.5428/0.6207)	mem 24308MB
[2025-01-18 15:23:06 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][260/312]	eta 0:00:31 lr 0.003726	time 0.5945 (0.6112)	model_time 0.5941 (0.6050)	loss 3.5723 (3.7940)	grad_norm 2.2267 (1.5504/0.6250)	mem 24308MB
[2025-01-18 15:23:12 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][270/312]	eta 0:00:25 lr 0.003726	time 0.7014 (0.6107)	model_time 0.7012 (0.6047)	loss 3.6967 (3.7963)	grad_norm 1.0642 (1.5399/0.6219)	mem 24308MB
[2025-01-18 15:23:18 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][280/312]	eta 0:00:19 lr 0.003725	time 0.5831 (0.6098)	model_time 0.5829 (0.6040)	loss 4.7193 (3.8045)	grad_norm 0.7962 (1.5541/0.6511)	mem 24308MB
[2025-01-18 15:23:24 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][290/312]	eta 0:00:13 lr 0.003725	time 0.5900 (0.6092)	model_time 0.5895 (0.6036)	loss 4.4184 (3.8036)	grad_norm 1.1585 (1.5677/0.6599)	mem 24308MB
[2025-01-18 15:23:30 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][300/312]	eta 0:00:07 lr 0.003725	time 0.5675 (0.6082)	model_time 0.5674 (0.6028)	loss 3.5725 (3.8060)	grad_norm 1.5994 (1.5624/0.6559)	mem 24308MB
[2025-01-18 15:23:36 internimage_s_1k_224] (main.py 510): INFO Train: [50/300][310/312]	eta 0:00:01 lr 0.003724	time 0.5576 (0.6072)	model_time 0.5575 (0.6020)	loss 3.0726 (3.8033)	grad_norm 1.2128 (1.5648/0.6565)	mem 24308MB
[2025-01-18 15:23:36 internimage_s_1k_224] (main.py 519): INFO EPOCH 50 training takes 0:03:09
[2025-01-18 15:23:36 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_50.pth saving......
[2025-01-18 15:23:38 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_50.pth saved !!!
[2025-01-18 15:23:46 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.325 (7.325)	Loss 1.0292 (1.0292)	Acc@1 77.466 (77.466)	Acc@5 94.653 (94.653)	Mem 24308MB
[2025-01-18 15:23:49 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.959)	Loss 1.5050 (1.2326)	Acc@1 67.188 (73.315)	Acc@5 88.428 (92.168)	Mem 24308MB
[2025-01-18 15:23:49 internimage_s_1k_224] (main.py 575): INFO [Epoch:50] * Acc@1 73.363 Acc@5 92.240
[2025-01-18 15:23:49 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 73.4%
[2025-01-18 15:23:49 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 15:23:51 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 15:23:51 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 73.36%
[2025-01-18 15:23:59 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.550 (7.550)	Loss 2.2158 (2.2158)	Acc@1 52.856 (52.856)	Acc@5 76.050 (76.050)	Mem 24308MB
[2025-01-18 15:24:02 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.962)	Loss 2.8819 (2.4652)	Acc@1 40.039 (47.574)	Acc@5 64.868 (72.266)	Mem 24308MB
[2025-01-18 15:24:02 internimage_s_1k_224] (main.py 575): INFO [Epoch:50] * Acc@1 47.899 Acc@5 72.795
[2025-01-18 15:24:02 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 47.9%
[2025-01-18 15:24:02 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 15:24:04 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 15:24:04 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 47.90%
[2025-01-18 15:24:06 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][0/312]	eta 0:11:20 lr 0.003724	time 2.1814 (2.1814)	model_time 0.6073 (0.6073)	loss 4.0292 (4.0292)	grad_norm 1.7284 (1.7284/0.0000)	mem 24308MB
[2025-01-18 15:24:12 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][10/312]	eta 0:03:51 lr 0.003724	time 0.5837 (0.7681)	model_time 0.5833 (0.6246)	loss 4.6065 (3.7013)	grad_norm 1.1544 (1.1100/0.2603)	mem 24308MB
[2025-01-18 15:24:19 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][20/312]	eta 0:03:23 lr 0.003724	time 0.5726 (0.6960)	model_time 0.5722 (0.6207)	loss 3.4934 (3.5282)	grad_norm 1.2823 (1.2374/0.3135)	mem 24308MB
[2025-01-18 15:24:25 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][30/312]	eta 0:03:13 lr 0.003723	time 0.6751 (0.6850)	model_time 0.6746 (0.6338)	loss 4.2884 (3.6110)	grad_norm 0.7688 (1.3235/0.5663)	mem 24308MB
[2025-01-18 15:24:31 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][40/312]	eta 0:03:01 lr 0.003723	time 0.5646 (0.6674)	model_time 0.5643 (0.6286)	loss 3.5361 (3.5775)	grad_norm 1.1664 (1.4240/0.6429)	mem 24308MB
[2025-01-18 15:24:37 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][50/312]	eta 0:02:51 lr 0.003723	time 0.7090 (0.6553)	model_time 0.7088 (0.6241)	loss 4.4045 (3.6089)	grad_norm 1.9456 (1.6497/1.0610)	mem 24308MB
[2025-01-18 15:24:43 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][60/312]	eta 0:02:43 lr 0.003722	time 0.5914 (0.6471)	model_time 0.5912 (0.6209)	loss 3.9529 (3.6109)	grad_norm 1.1028 (1.6875/1.0469)	mem 24308MB
[2025-01-18 15:24:49 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][70/312]	eta 0:02:34 lr 0.003722	time 0.5815 (0.6392)	model_time 0.5810 (0.6167)	loss 2.6924 (3.6072)	grad_norm 0.8307 (1.6573/0.9923)	mem 24308MB
[2025-01-18 15:24:55 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][80/312]	eta 0:02:26 lr 0.003722	time 0.5685 (0.6327)	model_time 0.5684 (0.6129)	loss 3.8876 (3.5967)	grad_norm 1.2195 (1.5785/0.9550)	mem 24308MB
[2025-01-18 15:25:01 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][90/312]	eta 0:02:19 lr 0.003721	time 0.5764 (0.6288)	model_time 0.5760 (0.6111)	loss 4.4812 (3.6343)	grad_norm 0.8597 (1.5368/0.9132)	mem 24308MB
[2025-01-18 15:25:07 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][100/312]	eta 0:02:12 lr 0.003721	time 0.5714 (0.6246)	model_time 0.5712 (0.6086)	loss 3.8898 (3.6349)	grad_norm 2.9492 (1.5434/0.9048)	mem 24308MB
[2025-01-18 15:25:13 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][110/312]	eta 0:02:05 lr 0.003721	time 0.5795 (0.6217)	model_time 0.5790 (0.6072)	loss 2.9415 (3.6530)	grad_norm 3.2935 (1.5391/0.8882)	mem 24308MB
[2025-01-18 15:25:19 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][120/312]	eta 0:01:58 lr 0.003720	time 0.6614 (0.6194)	model_time 0.6612 (0.6060)	loss 3.8870 (3.6511)	grad_norm 1.1683 (1.5488/0.8928)	mem 24308MB
[2025-01-18 15:25:25 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][130/312]	eta 0:01:52 lr 0.003720	time 0.6478 (0.6198)	model_time 0.6476 (0.6074)	loss 3.4615 (3.6603)	grad_norm 1.4259 (1.5245/0.8670)	mem 24308MB
[2025-01-18 15:25:31 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][140/312]	eta 0:01:46 lr 0.003720	time 0.5864 (0.6200)	model_time 0.5859 (0.6085)	loss 2.8962 (3.6561)	grad_norm 2.6380 (1.5235/0.8449)	mem 24308MB
[2025-01-18 15:25:38 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][150/312]	eta 0:01:40 lr 0.003719	time 0.6613 (0.6214)	model_time 0.6611 (0.6106)	loss 4.3167 (3.6548)	grad_norm 1.8425 (1.5382/0.8226)	mem 24308MB
[2025-01-18 15:25:44 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][160/312]	eta 0:01:34 lr 0.003719	time 0.5925 (0.6200)	model_time 0.5923 (0.6098)	loss 4.1142 (3.6654)	grad_norm 1.5519 (1.5322/0.8132)	mem 24308MB
[2025-01-18 15:25:50 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][170/312]	eta 0:01:27 lr 0.003718	time 0.5802 (0.6185)	model_time 0.5797 (0.6089)	loss 4.5195 (3.6823)	grad_norm 0.6286 (1.5147/0.7997)	mem 24308MB
[2025-01-18 15:25:56 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][180/312]	eta 0:01:21 lr 0.003718	time 0.5852 (0.6181)	model_time 0.5851 (0.6090)	loss 3.0898 (3.6770)	grad_norm 1.8063 (1.5306/0.7989)	mem 24308MB
[2025-01-18 15:26:02 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][190/312]	eta 0:01:15 lr 0.003718	time 0.5896 (0.6165)	model_time 0.5894 (0.6079)	loss 3.8059 (3.6702)	grad_norm 1.1167 (1.5190/0.7840)	mem 24308MB
[2025-01-18 15:26:08 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][200/312]	eta 0:01:08 lr 0.003717	time 0.5855 (0.6152)	model_time 0.5850 (0.6069)	loss 3.2411 (3.6723)	grad_norm 1.0376 (1.5017/0.7723)	mem 24308MB
[2025-01-18 15:26:14 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][210/312]	eta 0:01:02 lr 0.003717	time 0.5838 (0.6141)	model_time 0.5837 (0.6062)	loss 2.3353 (3.6775)	grad_norm 0.8667 (1.4825/0.7629)	mem 24308MB
[2025-01-18 15:26:19 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][220/312]	eta 0:00:56 lr 0.003717	time 0.5831 (0.6133)	model_time 0.5830 (0.6058)	loss 3.4788 (3.6788)	grad_norm 1.5112 (1.4900/0.7506)	mem 24308MB
[2025-01-18 15:26:25 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][230/312]	eta 0:00:50 lr 0.003716	time 0.5911 (0.6122)	model_time 0.5907 (0.6050)	loss 3.1172 (3.6882)	grad_norm 1.2337 (1.4760/0.7381)	mem 24308MB
[2025-01-18 15:26:31 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][240/312]	eta 0:00:44 lr 0.003716	time 0.5802 (0.6113)	model_time 0.5800 (0.6044)	loss 3.6225 (3.6995)	grad_norm 2.8643 (1.4938/0.7473)	mem 24308MB
[2025-01-18 15:26:37 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][250/312]	eta 0:00:37 lr 0.003716	time 0.5811 (0.6114)	model_time 0.5809 (0.6048)	loss 2.9786 (3.7003)	grad_norm 1.2788 (1.4924/0.7391)	mem 24308MB
[2025-01-18 15:26:44 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][260/312]	eta 0:00:31 lr 0.003715	time 0.5726 (0.6121)	model_time 0.5724 (0.6057)	loss 4.0879 (3.7037)	grad_norm 0.8477 (1.4931/0.7365)	mem 24308MB
[2025-01-18 15:26:50 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][270/312]	eta 0:00:25 lr 0.003715	time 0.6662 (0.6130)	model_time 0.6660 (0.6068)	loss 3.4373 (3.6915)	grad_norm 1.0220 (1.4972/0.7314)	mem 24308MB
[2025-01-18 15:26:56 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][280/312]	eta 0:00:19 lr 0.003715	time 0.5772 (0.6132)	model_time 0.5767 (0.6072)	loss 4.2693 (3.6975)	grad_norm 1.0089 (1.5036/0.7296)	mem 24308MB
[2025-01-18 15:27:02 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][290/312]	eta 0:00:13 lr 0.003714	time 0.5814 (0.6125)	model_time 0.5810 (0.6067)	loss 4.5693 (3.7098)	grad_norm 2.3434 (1.5033/0.7217)	mem 24308MB
[2025-01-18 15:27:08 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][300/312]	eta 0:00:07 lr 0.003714	time 0.5686 (0.6122)	model_time 0.5685 (0.6066)	loss 2.8063 (3.7138)	grad_norm 1.1068 (1.5057/0.7172)	mem 24308MB
[2025-01-18 15:27:14 internimage_s_1k_224] (main.py 510): INFO Train: [51/300][310/312]	eta 0:00:01 lr 0.003714	time 0.5675 (0.6111)	model_time 0.5674 (0.6056)	loss 3.9998 (3.7126)	grad_norm 1.0436 (1.5089/0.7161)	mem 24308MB
[2025-01-18 15:27:15 internimage_s_1k_224] (main.py 519): INFO EPOCH 51 training takes 0:03:10
[2025-01-18 15:27:15 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_51.pth saving......
[2025-01-18 15:27:16 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_51.pth saved !!!
[2025-01-18 15:27:24 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.995 (6.995)	Loss 1.0111 (1.0111)	Acc@1 78.247 (78.247)	Acc@5 95.312 (95.312)	Mem 24308MB
[2025-01-18 15:27:27 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.920)	Loss 1.4392 (1.2177)	Acc@1 68.457 (73.553)	Acc@5 89.185 (92.172)	Mem 24308MB
[2025-01-18 15:27:27 internimage_s_1k_224] (main.py 575): INFO [Epoch:51] * Acc@1 73.566 Acc@5 92.248
[2025-01-18 15:27:27 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 73.6%
[2025-01-18 15:27:27 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 15:27:29 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 15:27:29 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 73.57%
[2025-01-18 15:27:36 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.005 (7.005)	Loss 2.0945 (2.0945)	Acc@1 54.663 (54.663)	Acc@5 78.369 (78.369)	Mem 24308MB
[2025-01-18 15:27:39 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.919)	Loss 2.7640 (2.3480)	Acc@1 41.772 (49.587)	Acc@5 66.870 (74.272)	Mem 24308MB
[2025-01-18 15:27:39 internimage_s_1k_224] (main.py 575): INFO [Epoch:51] * Acc@1 49.902 Acc@5 74.734
[2025-01-18 15:27:39 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 49.9%
[2025-01-18 15:27:39 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 15:27:41 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 15:27:41 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 49.90%
[2025-01-18 15:27:43 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][0/312]	eta 0:10:58 lr 0.003714	time 2.1114 (2.1114)	model_time 0.6047 (0.6047)	loss 3.9259 (3.9259)	grad_norm 1.1662 (1.1662/0.0000)	mem 24308MB
[2025-01-18 15:27:49 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][10/312]	eta 0:03:40 lr 0.003713	time 0.6074 (0.7298)	model_time 0.6073 (0.5925)	loss 2.6799 (3.7791)	grad_norm 1.8826 (1.5803/0.2837)	mem 24308MB
[2025-01-18 15:27:55 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][20/312]	eta 0:03:13 lr 0.003713	time 0.5819 (0.6630)	model_time 0.5814 (0.5909)	loss 4.4832 (3.7227)	grad_norm 3.7295 (1.9184/0.7976)	mem 24308MB
[2025-01-18 15:28:01 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][30/312]	eta 0:03:00 lr 0.003713	time 0.5957 (0.6407)	model_time 0.5952 (0.5917)	loss 3.2925 (3.6956)	grad_norm 0.6968 (1.8535/0.8130)	mem 24308MB
[2025-01-18 15:28:07 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][40/312]	eta 0:02:50 lr 0.003712	time 0.5797 (0.6267)	model_time 0.5795 (0.5896)	loss 4.1843 (3.7268)	grad_norm 1.7087 (1.7935/0.7487)	mem 24308MB
[2025-01-18 15:28:13 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][50/312]	eta 0:02:42 lr 0.003712	time 0.5783 (0.6192)	model_time 0.5781 (0.5894)	loss 4.3761 (3.6798)	grad_norm 1.4519 (1.7227/0.7276)	mem 24308MB
[2025-01-18 15:28:19 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][60/312]	eta 0:02:35 lr 0.003712	time 0.6976 (0.6179)	model_time 0.6975 (0.5929)	loss 3.4689 (3.6856)	grad_norm 1.3290 (1.6183/0.7116)	mem 24308MB
[2025-01-18 15:28:25 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][70/312]	eta 0:02:29 lr 0.003711	time 0.5774 (0.6173)	model_time 0.5770 (0.5958)	loss 4.0081 (3.6830)	grad_norm 0.7033 (1.5793/0.6824)	mem 24308MB
[2025-01-18 15:28:31 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][80/312]	eta 0:02:23 lr 0.003711	time 0.6400 (0.6181)	model_time 0.6399 (0.5991)	loss 3.9481 (3.6625)	grad_norm 1.0440 (1.6197/0.7604)	mem 24308MB
[2025-01-18 15:28:38 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][90/312]	eta 0:02:17 lr 0.003711	time 0.5770 (0.6194)	model_time 0.5768 (0.6025)	loss 4.7357 (3.6901)	grad_norm 1.0959 (1.5922/0.7362)	mem 24308MB
[2025-01-18 15:28:44 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][100/312]	eta 0:02:10 lr 0.003710	time 0.5711 (0.6166)	model_time 0.5709 (0.6013)	loss 3.4695 (3.7069)	grad_norm 3.3704 (1.6209/0.7452)	mem 24308MB
[2025-01-18 15:28:50 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][110/312]	eta 0:02:04 lr 0.003710	time 0.5827 (0.6157)	model_time 0.5825 (0.6018)	loss 4.5139 (3.7097)	grad_norm 1.5570 (1.6123/0.7456)	mem 24308MB
[2025-01-18 15:28:55 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][120/312]	eta 0:01:57 lr 0.003709	time 0.5825 (0.6131)	model_time 0.5824 (0.6003)	loss 3.0294 (3.6989)	grad_norm 2.6234 (1.6219/0.7481)	mem 24308MB
[2025-01-18 15:29:01 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][130/312]	eta 0:01:51 lr 0.003709	time 0.5888 (0.6114)	model_time 0.5886 (0.5995)	loss 2.4044 (3.6805)	grad_norm 1.1134 (1.6205/0.7417)	mem 24308MB
[2025-01-18 15:29:07 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][140/312]	eta 0:01:44 lr 0.003709	time 0.5900 (0.6097)	model_time 0.5899 (0.5986)	loss 3.7738 (3.6828)	grad_norm 0.9461 (1.5904/0.7300)	mem 24308MB
[2025-01-18 15:29:13 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][150/312]	eta 0:01:38 lr 0.003708	time 0.5774 (0.6084)	model_time 0.5770 (0.5980)	loss 4.3333 (3.6836)	grad_norm 1.1424 (1.5734/0.7146)	mem 24308MB
[2025-01-18 15:29:19 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][160/312]	eta 0:01:32 lr 0.003708	time 0.6021 (0.6072)	model_time 0.6020 (0.5976)	loss 3.9059 (3.6787)	grad_norm 1.5296 (1.5646/0.6966)	mem 24308MB
[2025-01-18 15:29:25 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][170/312]	eta 0:01:26 lr 0.003708	time 0.5934 (0.6062)	model_time 0.5933 (0.5971)	loss 4.2460 (3.6935)	grad_norm 1.3762 (1.5796/0.6992)	mem 24308MB
[2025-01-18 15:29:31 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][180/312]	eta 0:01:19 lr 0.003707	time 0.6258 (0.6057)	model_time 0.6254 (0.5970)	loss 3.3376 (3.6907)	grad_norm 2.3044 (1.5867/0.7056)	mem 24308MB
[2025-01-18 15:29:37 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][190/312]	eta 0:01:14 lr 0.003707	time 0.5733 (0.6077)	model_time 0.5729 (0.5994)	loss 3.7921 (3.6984)	grad_norm 0.9582 (1.5749/0.7075)	mem 24308MB
[2025-01-18 15:29:44 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][200/312]	eta 0:01:08 lr 0.003707	time 0.6908 (0.6091)	model_time 0.6906 (0.6013)	loss 4.2256 (3.6942)	grad_norm 2.9913 (1.5692/0.7033)	mem 24308MB
[2025-01-18 15:29:50 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][210/312]	eta 0:01:02 lr 0.003706	time 0.5745 (0.6107)	model_time 0.5743 (0.6033)	loss 4.5634 (3.6930)	grad_norm 1.4805 (1.5638/0.6901)	mem 24308MB
[2025-01-18 15:29:56 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][220/312]	eta 0:00:56 lr 0.003706	time 0.5760 (0.6096)	model_time 0.5755 (0.6024)	loss 4.6335 (3.7177)	grad_norm 2.1260 (1.5565/0.6814)	mem 24308MB
[2025-01-18 15:30:02 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][230/312]	eta 0:00:50 lr 0.003706	time 0.5859 (0.6103)	model_time 0.5854 (0.6034)	loss 3.5105 (3.7050)	grad_norm 1.2329 (1.5447/0.6712)	mem 24308MB
[2025-01-18 15:30:08 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][240/312]	eta 0:00:43 lr 0.003705	time 0.5769 (0.6092)	model_time 0.5765 (0.6026)	loss 3.7124 (3.6998)	grad_norm 0.7568 (1.5313/0.6679)	mem 24308MB
[2025-01-18 15:30:14 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][250/312]	eta 0:00:37 lr 0.003705	time 0.5834 (0.6083)	model_time 0.5832 (0.6020)	loss 3.5341 (3.7039)	grad_norm 1.0875 (1.5603/0.6952)	mem 24308MB
[2025-01-18 15:30:20 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][260/312]	eta 0:00:31 lr 0.003705	time 0.5965 (0.6076)	model_time 0.5961 (0.6014)	loss 4.5715 (3.7038)	grad_norm 0.7999 (1.5597/0.6869)	mem 24308MB
[2025-01-18 15:30:26 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][270/312]	eta 0:00:25 lr 0.003704	time 0.5719 (0.6071)	model_time 0.5716 (0.6011)	loss 4.2672 (3.7019)	grad_norm 3.4996 (1.5620/0.6920)	mem 24308MB
[2025-01-18 15:30:32 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][280/312]	eta 0:00:19 lr 0.003704	time 0.5924 (0.6065)	model_time 0.5922 (0.6007)	loss 4.5004 (3.7149)	grad_norm 0.7474 (1.5754/0.7033)	mem 24308MB
[2025-01-18 15:30:38 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][290/312]	eta 0:00:13 lr 0.003704	time 0.5940 (0.6058)	model_time 0.5936 (0.6002)	loss 3.9177 (3.7214)	grad_norm 1.2926 (1.5742/0.6941)	mem 24308MB
[2025-01-18 15:30:44 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][300/312]	eta 0:00:07 lr 0.003703	time 0.5658 (0.6054)	model_time 0.5657 (0.6000)	loss 4.0600 (3.7163)	grad_norm 2.5324 (1.5891/0.7119)	mem 24308MB
[2025-01-18 15:30:50 internimage_s_1k_224] (main.py 510): INFO Train: [52/300][310/312]	eta 0:00:01 lr 0.003703	time 0.6483 (0.6056)	model_time 0.6482 (0.6004)	loss 3.7067 (3.7107)	grad_norm 3.0507 (1.6017/0.7318)	mem 24308MB
[2025-01-18 15:30:50 internimage_s_1k_224] (main.py 519): INFO EPOCH 52 training takes 0:03:08
[2025-01-18 15:30:50 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_52.pth saving......
[2025-01-18 15:30:52 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_52.pth saved !!!
[2025-01-18 15:30:59 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.124 (7.124)	Loss 0.9528 (0.9528)	Acc@1 78.516 (78.516)	Acc@5 94.751 (94.751)	Mem 24308MB
[2025-01-18 15:31:02 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.931)	Loss 1.4328 (1.1782)	Acc@1 68.604 (74.046)	Acc@5 88.599 (92.203)	Mem 24308MB
[2025-01-18 15:31:03 internimage_s_1k_224] (main.py 575): INFO [Epoch:52] * Acc@1 74.024 Acc@5 92.278
[2025-01-18 15:31:03 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 74.0%
[2025-01-18 15:31:03 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 15:31:05 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 15:31:05 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 74.02%
[2025-01-18 15:31:12 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.954 (6.954)	Loss 1.9876 (1.9876)	Acc@1 56.812 (56.812)	Acc@5 79.810 (79.810)	Mem 24308MB
[2025-01-18 15:31:15 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.135 (0.907)	Loss 2.6592 (2.2428)	Acc@1 43.311 (51.496)	Acc@5 68.408 (75.866)	Mem 24308MB
[2025-01-18 15:31:15 internimage_s_1k_224] (main.py 575): INFO [Epoch:52] * Acc@1 51.759 Acc@5 76.306
[2025-01-18 15:31:15 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 51.8%
[2025-01-18 15:31:15 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 15:31:17 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 15:31:17 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 51.76%
[2025-01-18 15:31:19 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][0/312]	eta 0:10:56 lr 0.003703	time 2.1034 (2.1034)	model_time 0.5952 (0.5952)	loss 3.7052 (3.7052)	grad_norm 1.7265 (1.7265/0.0000)	mem 24308MB
[2025-01-18 15:31:25 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][10/312]	eta 0:03:48 lr 0.003702	time 0.5781 (0.7571)	model_time 0.5779 (0.6197)	loss 2.7555 (3.5999)	grad_norm 1.4244 (1.3278/0.3658)	mem 24308MB
[2025-01-18 15:31:31 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][20/312]	eta 0:03:23 lr 0.003702	time 0.6740 (0.6969)	model_time 0.6735 (0.6247)	loss 3.8346 (3.5160)	grad_norm 1.2013 (1.3486/0.3782)	mem 24308MB
[2025-01-18 15:31:37 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][30/312]	eta 0:03:06 lr 0.003702	time 0.5643 (0.6608)	model_time 0.5637 (0.6118)	loss 3.6521 (3.5885)	grad_norm 1.3768 (1.2819/0.3678)	mem 24308MB
[2025-01-18 15:31:43 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][40/312]	eta 0:02:56 lr 0.003701	time 0.5738 (0.6472)	model_time 0.5733 (0.6101)	loss 4.3191 (3.6153)	grad_norm 2.0286 (1.3648/0.3899)	mem 24308MB
[2025-01-18 15:31:49 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][50/312]	eta 0:02:46 lr 0.003701	time 0.6127 (0.6365)	model_time 0.6126 (0.6066)	loss 3.9354 (3.7020)	grad_norm 2.5487 (1.4268/0.4946)	mem 24308MB
[2025-01-18 15:31:55 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][60/312]	eta 0:02:38 lr 0.003701	time 0.5783 (0.6281)	model_time 0.5781 (0.6030)	loss 2.8968 (3.6781)	grad_norm 1.1505 (1.4506/0.5057)	mem 24308MB
[2025-01-18 15:32:01 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][70/312]	eta 0:02:30 lr 0.003700	time 0.5805 (0.6226)	model_time 0.5800 (0.6010)	loss 3.7456 (3.6813)	grad_norm 2.1356 (1.4072/0.5038)	mem 24308MB
[2025-01-18 15:32:07 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][80/312]	eta 0:02:23 lr 0.003700	time 0.5945 (0.6182)	model_time 0.5941 (0.5992)	loss 4.0357 (3.6808)	grad_norm 1.8015 (1.5020/0.6553)	mem 24308MB
[2025-01-18 15:32:13 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][90/312]	eta 0:02:16 lr 0.003700	time 0.5895 (0.6151)	model_time 0.5893 (0.5981)	loss 4.1156 (3.6781)	grad_norm 0.8346 (1.5013/0.6521)	mem 24308MB
[2025-01-18 15:32:19 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][100/312]	eta 0:02:09 lr 0.003699	time 0.5903 (0.6123)	model_time 0.5899 (0.5970)	loss 3.3243 (3.6797)	grad_norm 1.3580 (1.4605/0.6358)	mem 24308MB
[2025-01-18 15:32:25 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][110/312]	eta 0:02:03 lr 0.003699	time 0.5817 (0.6123)	model_time 0.5815 (0.5984)	loss 3.8847 (3.6967)	grad_norm 1.3171 (1.4482/0.6167)	mem 24308MB
[2025-01-18 15:32:31 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][120/312]	eta 0:01:57 lr 0.003699	time 0.5945 (0.6138)	model_time 0.5941 (0.6010)	loss 3.5366 (3.6923)	grad_norm 1.3667 (1.4425/0.5996)	mem 24308MB
[2025-01-18 15:32:37 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][130/312]	eta 0:01:51 lr 0.003698	time 0.5935 (0.6154)	model_time 0.5930 (0.6035)	loss 3.9029 (3.6857)	grad_norm 1.7511 (1.4363/0.5839)	mem 24308MB
[2025-01-18 15:32:44 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][140/312]	eta 0:01:46 lr 0.003698	time 0.5875 (0.6165)	model_time 0.5874 (0.6054)	loss 3.6769 (3.6820)	grad_norm 1.4045 (1.4407/0.5706)	mem 24308MB
[2025-01-18 15:32:50 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][150/312]	eta 0:01:39 lr 0.003698	time 0.5751 (0.6165)	model_time 0.5746 (0.6061)	loss 3.5784 (3.6945)	grad_norm 3.2463 (1.4663/0.5876)	mem 24308MB
[2025-01-18 15:32:56 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][160/312]	eta 0:01:33 lr 0.003697	time 0.5787 (0.6162)	model_time 0.5785 (0.6065)	loss 3.9677 (3.7117)	grad_norm 1.0624 (1.4857/0.6002)	mem 24308MB
[2025-01-18 15:33:02 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][170/312]	eta 0:01:27 lr 0.003697	time 0.5754 (0.6147)	model_time 0.5750 (0.6055)	loss 4.4075 (3.7314)	grad_norm 1.4079 (1.4853/0.5963)	mem 24308MB
[2025-01-18 15:33:08 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][180/312]	eta 0:01:20 lr 0.003696	time 0.5851 (0.6133)	model_time 0.5847 (0.6046)	loss 4.0016 (3.7342)	grad_norm 1.2472 (1.4712/0.5904)	mem 24308MB
[2025-01-18 15:33:14 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][190/312]	eta 0:01:14 lr 0.003696	time 0.5719 (0.6120)	model_time 0.5717 (0.6037)	loss 4.1344 (3.7206)	grad_norm 2.0243 (1.4830/0.6096)	mem 24308MB
[2025-01-18 15:33:20 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][200/312]	eta 0:01:08 lr 0.003696	time 0.6140 (0.6107)	model_time 0.6136 (0.6029)	loss 3.7964 (3.7162)	grad_norm 1.5611 (1.4885/0.6034)	mem 24308MB
[2025-01-18 15:33:26 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][210/312]	eta 0:01:02 lr 0.003695	time 0.5893 (0.6099)	model_time 0.5889 (0.6024)	loss 4.5809 (3.7235)	grad_norm 1.3223 (1.4867/0.6031)	mem 24308MB
[2025-01-18 15:33:31 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][220/312]	eta 0:00:56 lr 0.003695	time 0.5949 (0.6089)	model_time 0.5945 (0.6017)	loss 3.9610 (3.7366)	grad_norm 1.7369 (1.4698/0.5993)	mem 24308MB
[2025-01-18 15:33:38 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][230/312]	eta 0:00:49 lr 0.003695	time 0.5911 (0.6090)	model_time 0.5907 (0.6021)	loss 3.4513 (3.7462)	grad_norm 1.6359 (1.4831/0.5997)	mem 24308MB
[2025-01-18 15:33:44 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][240/312]	eta 0:00:43 lr 0.003694	time 0.6616 (0.6095)	model_time 0.6614 (0.6029)	loss 3.7478 (3.7581)	grad_norm 1.6283 (1.4836/0.5963)	mem 24308MB
[2025-01-18 15:33:50 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][250/312]	eta 0:00:37 lr 0.003694	time 0.5734 (0.6100)	model_time 0.5733 (0.6034)	loss 3.6889 (3.7465)	grad_norm 1.2582 (1.4866/0.5886)	mem 24308MB
[2025-01-18 15:33:56 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][260/312]	eta 0:00:31 lr 0.003694	time 0.5848 (0.6108)	model_time 0.5846 (0.6045)	loss 3.4422 (3.7311)	grad_norm 0.7549 (1.4760/0.5838)	mem 24308MB
[2025-01-18 15:34:02 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][270/312]	eta 0:00:25 lr 0.003693	time 0.5838 (0.6107)	model_time 0.5836 (0.6046)	loss 4.3597 (3.7302)	grad_norm 2.6397 (1.4784/0.5834)	mem 24308MB
[2025-01-18 15:34:08 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][280/312]	eta 0:00:19 lr 0.003693	time 0.6630 (0.6106)	model_time 0.6625 (0.6047)	loss 2.4615 (3.7141)	grad_norm 2.4742 (1.5062/0.6186)	mem 24308MB
[2025-01-18 15:34:14 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][290/312]	eta 0:00:13 lr 0.003693	time 0.6080 (0.6101)	model_time 0.6078 (0.6044)	loss 4.1511 (3.7222)	grad_norm 1.3234 (1.5084/0.6187)	mem 24308MB
[2025-01-18 15:34:20 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][300/312]	eta 0:00:07 lr 0.003692	time 0.5653 (0.6090)	model_time 0.5652 (0.6035)	loss 3.9806 (3.7276)	grad_norm 0.8439 (1.5023/0.6175)	mem 24308MB
[2025-01-18 15:34:26 internimage_s_1k_224] (main.py 510): INFO Train: [53/300][310/312]	eta 0:00:01 lr 0.003692	time 0.5704 (0.6078)	model_time 0.5703 (0.6025)	loss 3.7801 (3.7331)	grad_norm 1.2923 (1.5157/0.6156)	mem 24308MB
[2025-01-18 15:34:26 internimage_s_1k_224] (main.py 519): INFO EPOCH 53 training takes 0:03:09
[2025-01-18 15:34:26 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_53.pth saving......
[2025-01-18 15:34:28 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_53.pth saved !!!
[2025-01-18 15:34:35 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.063 (7.063)	Loss 1.0108 (1.0108)	Acc@1 78.027 (78.027)	Acc@5 94.995 (94.995)	Mem 24308MB
[2025-01-18 15:34:39 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.934)	Loss 1.4809 (1.2205)	Acc@1 66.992 (73.695)	Acc@5 88.672 (92.203)	Mem 24308MB
[2025-01-18 15:34:39 internimage_s_1k_224] (main.py 575): INFO [Epoch:53] * Acc@1 73.766 Acc@5 92.326
[2025-01-18 15:34:39 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 73.8%
[2025-01-18 15:34:39 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 74.02%
[2025-01-18 15:34:47 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.162 (8.162)	Loss 1.8914 (1.8914)	Acc@1 58.618 (58.618)	Acc@5 81.201 (81.201)	Mem 24308MB
[2025-01-18 15:34:51 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.101)	Loss 2.5611 (2.1456)	Acc@1 45.020 (53.287)	Acc@5 70.142 (77.410)	Mem 24308MB
[2025-01-18 15:34:51 internimage_s_1k_224] (main.py 575): INFO [Epoch:53] * Acc@1 53.539 Acc@5 77.815
[2025-01-18 15:34:51 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 53.5%
[2025-01-18 15:34:51 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 15:34:53 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 15:34:53 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 53.54%
[2025-01-18 15:34:55 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][0/312]	eta 0:10:36 lr 0.003692	time 2.0413 (2.0413)	model_time 0.5800 (0.5800)	loss 4.5009 (4.5009)	grad_norm 1.5782 (1.5782/0.0000)	mem 24308MB
[2025-01-18 15:35:01 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][10/312]	eta 0:03:37 lr 0.003691	time 0.5989 (0.7208)	model_time 0.5988 (0.5867)	loss 2.3222 (3.5273)	grad_norm 1.9806 (1.5985/0.3793)	mem 24308MB
[2025-01-18 15:35:07 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][20/312]	eta 0:03:12 lr 0.003691	time 0.5909 (0.6584)	model_time 0.5908 (0.5879)	loss 3.5026 (3.7291)	grad_norm 0.8913 (1.4928/0.4646)	mem 24308MB
[2025-01-18 15:35:13 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][30/312]	eta 0:03:00 lr 0.003691	time 0.6714 (0.6399)	model_time 0.6713 (0.5921)	loss 4.6571 (3.7414)	grad_norm 2.3738 (1.5368/0.4558)	mem 24308MB
[2025-01-18 15:35:19 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][40/312]	eta 0:02:51 lr 0.003690	time 0.5882 (0.6312)	model_time 0.5880 (0.5949)	loss 2.9997 (3.7232)	grad_norm 1.3229 (1.5419/0.4709)	mem 24308MB
[2025-01-18 15:35:25 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][50/312]	eta 0:02:45 lr 0.003690	time 0.6667 (0.6319)	model_time 0.6666 (0.6026)	loss 4.4575 (3.7327)	grad_norm 1.7965 (1.5143/0.4396)	mem 24308MB
[2025-01-18 15:35:32 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][60/312]	eta 0:02:39 lr 0.003690	time 0.6622 (0.6334)	model_time 0.6621 (0.6089)	loss 3.2695 (3.6797)	grad_norm 1.9697 (1.4740/0.4607)	mem 24308MB
[2025-01-18 15:35:38 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][70/312]	eta 0:02:33 lr 0.003689	time 0.6007 (0.6348)	model_time 0.6003 (0.6137)	loss 4.1272 (3.7168)	grad_norm 1.2154 (1.4379/0.4409)	mem 24308MB
[2025-01-18 15:35:44 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][80/312]	eta 0:02:26 lr 0.003689	time 0.5820 (0.6316)	model_time 0.5818 (0.6131)	loss 3.0751 (3.6905)	grad_norm 1.2898 (1.4290/0.4502)	mem 24308MB
[2025-01-18 15:35:50 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][90/312]	eta 0:02:19 lr 0.003689	time 0.5761 (0.6300)	model_time 0.5756 (0.6135)	loss 3.9285 (3.6584)	grad_norm 2.3717 (1.5079/0.5464)	mem 24308MB
[2025-01-18 15:35:56 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][100/312]	eta 0:02:12 lr 0.003688	time 0.5849 (0.6263)	model_time 0.5848 (0.6114)	loss 4.0335 (3.6843)	grad_norm 1.4337 (1.5035/0.5365)	mem 24308MB
[2025-01-18 15:36:02 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][110/312]	eta 0:02:05 lr 0.003688	time 0.5836 (0.6228)	model_time 0.5831 (0.6092)	loss 3.2612 (3.6966)	grad_norm 0.9512 (1.4804/0.5273)	mem 24308MB
[2025-01-18 15:36:08 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][120/312]	eta 0:01:59 lr 0.003687	time 0.5819 (0.6199)	model_time 0.5814 (0.6074)	loss 3.2659 (3.6830)	grad_norm 0.9198 (1.4671/0.5254)	mem 24308MB
[2025-01-18 15:36:14 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][130/312]	eta 0:01:52 lr 0.003687	time 0.5722 (0.6173)	model_time 0.5720 (0.6057)	loss 2.5647 (3.6979)	grad_norm 1.5005 (1.4618/0.5184)	mem 24308MB
[2025-01-18 15:36:20 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][140/312]	eta 0:01:45 lr 0.003687	time 0.5950 (0.6152)	model_time 0.5945 (0.6044)	loss 3.2560 (3.6814)	grad_norm 1.7796 (1.4717/0.5302)	mem 24308MB
[2025-01-18 15:36:26 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][150/312]	eta 0:01:39 lr 0.003686	time 0.6722 (0.6142)	model_time 0.6721 (0.6041)	loss 3.3959 (3.6867)	grad_norm 2.5383 (1.4817/0.5429)	mem 24308MB
[2025-01-18 15:36:32 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][160/312]	eta 0:01:33 lr 0.003686	time 0.5804 (0.6131)	model_time 0.5802 (0.6036)	loss 4.6370 (3.6894)	grad_norm 1.3413 (1.4846/0.5302)	mem 24308MB
[2025-01-18 15:36:38 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][170/312]	eta 0:01:27 lr 0.003686	time 0.6769 (0.6140)	model_time 0.6768 (0.6051)	loss 3.8061 (3.6802)	grad_norm 1.7830 (1.4785/0.5198)	mem 24308MB
[2025-01-18 15:36:45 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][180/312]	eta 0:01:21 lr 0.003685	time 0.7679 (0.6161)	model_time 0.7677 (0.6077)	loss 2.6137 (3.6653)	grad_norm 2.0331 (1.4765/0.5168)	mem 24308MB
[2025-01-18 15:36:51 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][190/312]	eta 0:01:15 lr 0.003685	time 0.5826 (0.6189)	model_time 0.5824 (0.6109)	loss 3.9099 (3.6526)	grad_norm 1.3323 (1.4689/0.5087)	mem 24308MB
[2025-01-18 15:36:57 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][200/312]	eta 0:01:09 lr 0.003685	time 0.5995 (0.6181)	model_time 0.5993 (0.6104)	loss 2.4340 (3.6543)	grad_norm 2.0172 (1.4827/0.5232)	mem 24308MB
[2025-01-18 15:37:03 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][210/312]	eta 0:01:02 lr 0.003684	time 0.5651 (0.6173)	model_time 0.5649 (0.6100)	loss 4.0148 (3.6545)	grad_norm 2.1949 (1.4967/0.5239)	mem 24308MB
[2025-01-18 15:37:09 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][220/312]	eta 0:00:56 lr 0.003684	time 0.5787 (0.6164)	model_time 0.5783 (0.6094)	loss 3.0306 (3.6591)	grad_norm 1.0274 (1.5009/0.5279)	mem 24308MB
[2025-01-18 15:37:15 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][230/312]	eta 0:00:50 lr 0.003684	time 0.5777 (0.6151)	model_time 0.5775 (0.6084)	loss 3.1767 (3.6614)	grad_norm 1.4937 (1.4972/0.5253)	mem 24308MB
[2025-01-18 15:37:21 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][240/312]	eta 0:00:44 lr 0.003683	time 0.5812 (0.6142)	model_time 0.5810 (0.6078)	loss 3.6483 (3.6772)	grad_norm 0.8519 (1.4923/0.5238)	mem 24308MB
[2025-01-18 15:37:27 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][250/312]	eta 0:00:38 lr 0.003683	time 0.5828 (0.6131)	model_time 0.5827 (0.6069)	loss 4.0687 (3.6809)	grad_norm 1.2567 (1.4907/0.5217)	mem 24308MB
[2025-01-18 15:37:33 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][260/312]	eta 0:00:31 lr 0.003682	time 0.6086 (0.6122)	model_time 0.6085 (0.6062)	loss 3.9514 (3.6849)	grad_norm 1.7646 (1.5264/0.5654)	mem 24308MB
[2025-01-18 15:37:39 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][270/312]	eta 0:00:25 lr 0.003682	time 0.5827 (0.6112)	model_time 0.5825 (0.6054)	loss 3.9203 (3.6983)	grad_norm 1.7952 (1.5342/0.5689)	mem 24308MB
[2025-01-18 15:37:45 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][280/312]	eta 0:00:19 lr 0.003682	time 0.6623 (0.6108)	model_time 0.6621 (0.6052)	loss 2.8738 (3.6908)	grad_norm 0.7440 (1.5307/0.5652)	mem 24308MB
[2025-01-18 15:37:51 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][290/312]	eta 0:00:13 lr 0.003681	time 0.6411 (0.6114)	model_time 0.6410 (0.6060)	loss 4.1486 (3.6953)	grad_norm 1.0628 (1.5387/0.5843)	mem 24308MB
[2025-01-18 15:37:57 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][300/312]	eta 0:00:07 lr 0.003681	time 0.5686 (0.6115)	model_time 0.5686 (0.6062)	loss 4.7081 (3.6992)	grad_norm 2.6274 (1.5439/0.5893)	mem 24308MB
[2025-01-18 15:38:03 internimage_s_1k_224] (main.py 510): INFO Train: [54/300][310/312]	eta 0:00:01 lr 0.003681	time 0.5629 (0.6118)	model_time 0.5628 (0.6067)	loss 4.3957 (3.7091)	grad_norm 1.5549 (1.5322/0.5908)	mem 24308MB
[2025-01-18 15:38:04 internimage_s_1k_224] (main.py 519): INFO EPOCH 54 training takes 0:03:10
[2025-01-18 15:38:04 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_54.pth saving......
[2025-01-18 15:38:06 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_54.pth saved !!!
[2025-01-18 15:38:13 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.130 (7.130)	Loss 0.9952 (0.9952)	Acc@1 77.856 (77.856)	Acc@5 94.775 (94.775)	Mem 24308MB
[2025-01-18 15:38:16 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.930)	Loss 1.4160 (1.1948)	Acc@1 68.945 (73.817)	Acc@5 89.868 (92.443)	Mem 24308MB
[2025-01-18 15:38:16 internimage_s_1k_224] (main.py 575): INFO [Epoch:54] * Acc@1 73.848 Acc@5 92.504
[2025-01-18 15:38:16 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 73.8%
[2025-01-18 15:38:16 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 74.02%
[2025-01-18 15:38:24 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.125 (8.125)	Loss 1.8028 (1.8028)	Acc@1 60.449 (60.449)	Acc@5 82.422 (82.422)	Mem 24308MB
[2025-01-18 15:38:28 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (1.104)	Loss 2.4695 (2.0563)	Acc@1 46.558 (54.954)	Acc@5 71.948 (78.729)	Mem 24308MB
[2025-01-18 15:38:28 internimage_s_1k_224] (main.py 575): INFO [Epoch:54] * Acc@1 55.246 Acc@5 79.105
[2025-01-18 15:38:28 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 55.2%
[2025-01-18 15:38:28 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 15:38:30 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 15:38:30 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 55.25%
[2025-01-18 15:38:33 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][0/312]	eta 0:11:51 lr 0.003681	time 2.2808 (2.2808)	model_time 0.5999 (0.5999)	loss 4.8484 (4.8484)	grad_norm 1.8113 (1.8113/0.0000)	mem 24308MB
[2025-01-18 15:38:39 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][10/312]	eta 0:03:52 lr 0.003680	time 0.5766 (0.7712)	model_time 0.5763 (0.6181)	loss 3.7259 (3.7888)	grad_norm 0.7876 (1.4650/0.5121)	mem 24308MB
[2025-01-18 15:38:45 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][20/312]	eta 0:03:21 lr 0.003680	time 0.5858 (0.6906)	model_time 0.5853 (0.6102)	loss 2.4329 (3.6848)	grad_norm 1.4423 (1.5479/0.6096)	mem 24308MB
[2025-01-18 15:38:51 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][30/312]	eta 0:03:06 lr 0.003679	time 0.5819 (0.6630)	model_time 0.5816 (0.6082)	loss 3.8085 (3.5860)	grad_norm 1.3313 (1.3886/0.5667)	mem 24308MB
[2025-01-18 15:38:57 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][40/312]	eta 0:02:56 lr 0.003679	time 0.5927 (0.6481)	model_time 0.5922 (0.6066)	loss 3.4774 (3.6378)	grad_norm 0.9541 (1.3522/0.5228)	mem 24308MB
[2025-01-18 15:39:03 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][50/312]	eta 0:02:46 lr 0.003679	time 0.5796 (0.6364)	model_time 0.5794 (0.6029)	loss 3.9021 (3.6606)	grad_norm 2.4124 (1.3894/0.5193)	mem 24308MB
[2025-01-18 15:39:09 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][60/312]	eta 0:02:38 lr 0.003678	time 0.5830 (0.6291)	model_time 0.5828 (0.6011)	loss 4.4327 (3.6743)	grad_norm 2.6207 (1.5073/0.6070)	mem 24308MB
[2025-01-18 15:39:15 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][70/312]	eta 0:02:30 lr 0.003678	time 0.5861 (0.6232)	model_time 0.5857 (0.5990)	loss 2.9980 (3.6470)	grad_norm 1.3622 (1.5749/0.6790)	mem 24308MB
[2025-01-18 15:39:21 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][80/312]	eta 0:02:23 lr 0.003678	time 0.5865 (0.6189)	model_time 0.5863 (0.5977)	loss 3.3040 (3.6622)	grad_norm 1.0249 (1.5381/0.6553)	mem 24308MB
[2025-01-18 15:39:27 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][90/312]	eta 0:02:17 lr 0.003677	time 0.5909 (0.6177)	model_time 0.5908 (0.5988)	loss 3.5795 (3.6885)	grad_norm 2.7185 (1.5436/0.6486)	mem 24308MB
[2025-01-18 15:39:33 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][100/312]	eta 0:02:11 lr 0.003677	time 0.5949 (0.6179)	model_time 0.5947 (0.6009)	loss 4.5614 (3.7056)	grad_norm 1.6293 (1.5248/0.6391)	mem 24308MB
[2025-01-18 15:39:39 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][110/312]	eta 0:02:05 lr 0.003677	time 0.6933 (0.6193)	model_time 0.6931 (0.6037)	loss 2.6787 (3.7025)	grad_norm 0.9020 (1.5007/0.6183)	mem 24308MB
[2025-01-18 15:39:45 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][120/312]	eta 0:01:59 lr 0.003676	time 0.5754 (0.6202)	model_time 0.5753 (0.6059)	loss 3.8022 (3.6888)	grad_norm 1.2756 (1.4947/0.6364)	mem 24308MB
[2025-01-18 15:39:52 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][130/312]	eta 0:01:52 lr 0.003676	time 0.6059 (0.6193)	model_time 0.6057 (0.6061)	loss 3.8039 (3.7114)	grad_norm 0.8738 (1.5191/0.6671)	mem 24308MB
[2025-01-18 15:39:57 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][140/312]	eta 0:01:46 lr 0.003675	time 0.6059 (0.6178)	model_time 0.6054 (0.6055)	loss 3.8675 (3.7119)	grad_norm 1.7677 (1.4896/0.6558)	mem 24308MB
[2025-01-18 15:40:03 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][150/312]	eta 0:01:39 lr 0.003675	time 0.5737 (0.6166)	model_time 0.5735 (0.6051)	loss 3.5660 (3.7149)	grad_norm 1.5149 (1.5015/0.6625)	mem 24308MB
[2025-01-18 15:40:09 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][160/312]	eta 0:01:33 lr 0.003675	time 0.5808 (0.6151)	model_time 0.5807 (0.6042)	loss 4.1886 (3.7205)	grad_norm 1.8847 (1.5078/0.6512)	mem 24308MB
[2025-01-18 15:40:15 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][170/312]	eta 0:01:27 lr 0.003674	time 0.5900 (0.6138)	model_time 0.5899 (0.6036)	loss 3.8069 (3.7282)	grad_norm 2.2135 (1.5125/0.6414)	mem 24308MB
[2025-01-18 15:40:21 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][180/312]	eta 0:01:20 lr 0.003674	time 0.5823 (0.6122)	model_time 0.5821 (0.6025)	loss 2.8829 (3.7186)	grad_norm 1.1826 (1.5454/0.6676)	mem 24308MB
[2025-01-18 15:40:27 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][190/312]	eta 0:01:14 lr 0.003674	time 0.5926 (0.6108)	model_time 0.5924 (0.6016)	loss 4.2488 (3.7114)	grad_norm 1.1214 (1.5272/0.6588)	mem 24308MB
[2025-01-18 15:40:33 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][200/312]	eta 0:01:08 lr 0.003673	time 0.5703 (0.6098)	model_time 0.5698 (0.6010)	loss 3.7556 (3.7081)	grad_norm 1.8676 (1.5141/0.6489)	mem 24308MB
[2025-01-18 15:40:39 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][210/312]	eta 0:01:02 lr 0.003673	time 0.5818 (0.6093)	model_time 0.5817 (0.6009)	loss 4.5319 (3.7086)	grad_norm 1.1455 (1.4985/0.6390)	mem 24308MB
[2025-01-18 15:40:45 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][220/312]	eta 0:00:56 lr 0.003673	time 0.5665 (0.6097)	model_time 0.5663 (0.6017)	loss 2.5972 (3.6963)	grad_norm 2.3738 (1.4961/0.6355)	mem 24308MB
[2025-01-18 15:40:51 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][230/312]	eta 0:00:50 lr 0.003672	time 0.6516 (0.6102)	model_time 0.6512 (0.6025)	loss 4.5650 (3.6977)	grad_norm 1.2809 (1.5060/0.6342)	mem 24308MB
[2025-01-18 15:40:58 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][240/312]	eta 0:00:43 lr 0.003672	time 0.5734 (0.6111)	model_time 0.5733 (0.6037)	loss 3.9536 (3.7021)	grad_norm 0.9494 (1.4958/0.6249)	mem 24308MB
[2025-01-18 15:41:04 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][250/312]	eta 0:00:37 lr 0.003671	time 0.5905 (0.6111)	model_time 0.5903 (0.6040)	loss 3.4239 (3.7035)	grad_norm 0.8052 (1.4733/0.6242)	mem 24308MB
[2025-01-18 15:41:10 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][260/312]	eta 0:00:31 lr 0.003671	time 0.5731 (0.6105)	model_time 0.5729 (0.6037)	loss 4.4886 (3.7097)	grad_norm 3.8013 (1.4951/0.6578)	mem 24308MB
[2025-01-18 15:41:16 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][270/312]	eta 0:00:25 lr 0.003671	time 0.5906 (0.6102)	model_time 0.5904 (0.6036)	loss 4.1768 (3.7092)	grad_norm 1.3473 (1.5074/0.6691)	mem 24308MB
[2025-01-18 15:41:22 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][280/312]	eta 0:00:19 lr 0.003670	time 0.5693 (0.6096)	model_time 0.5689 (0.6032)	loss 3.5775 (3.7134)	grad_norm 1.5173 (1.5069/0.6593)	mem 24308MB
[2025-01-18 15:41:28 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][290/312]	eta 0:00:13 lr 0.003670	time 0.6083 (0.6091)	model_time 0.6078 (0.6029)	loss 3.0324 (3.7023)	grad_norm 0.8847 (1.4966/0.6520)	mem 24308MB
[2025-01-18 15:41:33 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][300/312]	eta 0:00:07 lr 0.003670	time 0.5643 (0.6082)	model_time 0.5641 (0.6022)	loss 4.0088 (3.6941)	grad_norm 1.8215 (1.4920/0.6452)	mem 24308MB
[2025-01-18 15:41:39 internimage_s_1k_224] (main.py 510): INFO Train: [55/300][310/312]	eta 0:00:01 lr 0.003669	time 0.5675 (0.6070)	model_time 0.5674 (0.6012)	loss 4.5766 (3.7012)	grad_norm 0.8191 (1.4890/0.6430)	mem 24308MB
[2025-01-18 15:41:40 internimage_s_1k_224] (main.py 519): INFO EPOCH 55 training takes 0:03:09
[2025-01-18 15:41:40 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_55.pth saving......
[2025-01-18 15:41:41 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_55.pth saved !!!
[2025-01-18 15:41:49 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.124 (7.124)	Loss 0.9518 (0.9518)	Acc@1 78.687 (78.687)	Acc@5 95.264 (95.264)	Mem 24308MB
[2025-01-18 15:41:52 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.950)	Loss 1.4425 (1.1781)	Acc@1 67.358 (73.888)	Acc@5 89.551 (92.463)	Mem 24308MB
[2025-01-18 15:41:52 internimage_s_1k_224] (main.py 575): INFO [Epoch:55] * Acc@1 73.936 Acc@5 92.530
[2025-01-18 15:41:52 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 73.9%
[2025-01-18 15:41:52 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 74.02%
[2025-01-18 15:42:00 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.192 (8.192)	Loss 1.7242 (1.7242)	Acc@1 61.841 (61.841)	Acc@5 83.862 (83.862)	Mem 24308MB
[2025-01-18 15:42:04 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.103)	Loss 2.3877 (1.9765)	Acc@1 48.145 (56.425)	Acc@5 73.242 (79.918)	Mem 24308MB
[2025-01-18 15:42:04 internimage_s_1k_224] (main.py 575): INFO [Epoch:55] * Acc@1 56.690 Acc@5 80.288
[2025-01-18 15:42:04 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 56.7%
[2025-01-18 15:42:05 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 15:42:07 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 15:42:07 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 56.69%
[2025-01-18 15:42:09 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][0/312]	eta 0:10:48 lr 0.003669	time 2.0770 (2.0770)	model_time 0.6052 (0.6052)	loss 3.3981 (3.3981)	grad_norm 1.4440 (1.4440/0.0000)	mem 24308MB
[2025-01-18 15:42:15 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][10/312]	eta 0:03:36 lr 0.003669	time 0.5800 (0.7180)	model_time 0.5798 (0.5840)	loss 3.9377 (3.6341)	grad_norm 0.7158 (1.5544/0.5473)	mem 24308MB
[2025-01-18 15:42:21 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][20/312]	eta 0:03:13 lr 0.003668	time 0.5817 (0.6634)	model_time 0.5815 (0.5929)	loss 2.5663 (3.6612)	grad_norm 1.3486 (1.4550/0.4646)	mem 24308MB
[2025-01-18 15:42:27 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][30/312]	eta 0:03:02 lr 0.003668	time 0.5831 (0.6476)	model_time 0.5828 (0.5997)	loss 3.0568 (3.5706)	grad_norm 1.0016 (1.4500/0.4310)	mem 24308MB
[2025-01-18 15:42:33 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][40/312]	eta 0:02:55 lr 0.003668	time 0.6639 (0.6444)	model_time 0.6637 (0.6082)	loss 2.7518 (3.6287)	grad_norm 0.7426 (1.4493/0.4582)	mem 24308MB
[2025-01-18 15:42:40 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][50/312]	eta 0:02:48 lr 0.003667	time 0.6528 (0.6418)	model_time 0.6527 (0.6126)	loss 4.5476 (3.6873)	grad_norm 4.2422 (1.4905/0.6378)	mem 24308MB
[2025-01-18 15:42:46 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][60/312]	eta 0:02:40 lr 0.003667	time 0.5863 (0.6354)	model_time 0.5859 (0.6109)	loss 3.0794 (3.6422)	grad_norm 1.2473 (1.5340/0.7200)	mem 24308MB
[2025-01-18 15:42:52 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][70/312]	eta 0:02:32 lr 0.003667	time 0.6000 (0.6303)	model_time 0.5996 (0.6092)	loss 4.0936 (3.6809)	grad_norm 2.1595 (1.4917/0.6902)	mem 24308MB
[2025-01-18 15:42:58 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][80/312]	eta 0:02:25 lr 0.003666	time 0.5889 (0.6264)	model_time 0.5888 (0.6079)	loss 4.6606 (3.6529)	grad_norm 1.8531 (1.5316/0.7032)	mem 24308MB
[2025-01-18 15:43:03 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][90/312]	eta 0:02:18 lr 0.003666	time 0.5838 (0.6222)	model_time 0.5834 (0.6057)	loss 3.1685 (3.6367)	grad_norm 0.9597 (1.4976/0.6919)	mem 24308MB
[2025-01-18 15:43:09 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][100/312]	eta 0:02:11 lr 0.003665	time 0.5781 (0.6185)	model_time 0.5780 (0.6036)	loss 4.4013 (3.6757)	grad_norm 1.6439 (1.4753/0.6708)	mem 24308MB
[2025-01-18 15:43:15 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][110/312]	eta 0:02:04 lr 0.003665	time 0.5823 (0.6155)	model_time 0.5822 (0.6019)	loss 4.0983 (3.6810)	grad_norm 1.3273 (1.4460/0.6509)	mem 24308MB
[2025-01-18 15:43:21 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][120/312]	eta 0:01:57 lr 0.003665	time 0.5806 (0.6137)	model_time 0.5802 (0.6011)	loss 3.8927 (3.6985)	grad_norm 1.4574 (1.4904/0.6583)	mem 24308MB
[2025-01-18 15:43:27 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][130/312]	eta 0:01:51 lr 0.003664	time 0.5865 (0.6117)	model_time 0.5860 (0.6001)	loss 3.7001 (3.7023)	grad_norm 0.9342 (1.5260/0.7166)	mem 24308MB
[2025-01-18 15:43:33 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][140/312]	eta 0:01:45 lr 0.003664	time 0.6579 (0.6116)	model_time 0.6577 (0.6008)	loss 3.8823 (3.7023)	grad_norm 1.0678 (1.5082/0.7048)	mem 24308MB
[2025-01-18 15:43:39 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][150/312]	eta 0:01:39 lr 0.003664	time 0.5879 (0.6120)	model_time 0.5875 (0.6019)	loss 4.3431 (3.7041)	grad_norm 0.8926 (1.5034/0.6935)	mem 24308MB
[2025-01-18 15:43:46 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][160/312]	eta 0:01:33 lr 0.003663	time 0.6743 (0.6129)	model_time 0.6739 (0.6034)	loss 2.6697 (3.6923)	grad_norm 2.3859 (1.4945/0.6811)	mem 24308MB
[2025-01-18 15:43:52 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][170/312]	eta 0:01:27 lr 0.003663	time 0.5914 (0.6143)	model_time 0.5912 (0.6054)	loss 4.0861 (3.7121)	grad_norm 1.5664 (1.5198/0.6817)	mem 24308MB
[2025-01-18 15:43:58 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][180/312]	eta 0:01:21 lr 0.003663	time 0.5939 (0.6158)	model_time 0.5938 (0.6073)	loss 4.1668 (3.7009)	grad_norm 1.7443 (1.5240/0.6842)	mem 24308MB
[2025-01-18 15:44:04 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][190/312]	eta 0:01:15 lr 0.003662	time 0.5823 (0.6150)	model_time 0.5822 (0.6070)	loss 3.7799 (3.7038)	grad_norm 0.5885 (1.5210/0.6814)	mem 24308MB
[2025-01-18 15:44:10 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][200/312]	eta 0:01:08 lr 0.003662	time 0.5892 (0.6139)	model_time 0.5891 (0.6063)	loss 3.7771 (3.7090)	grad_norm 0.8478 (1.5215/0.6845)	mem 24308MB
[2025-01-18 15:44:16 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][210/312]	eta 0:01:02 lr 0.003661	time 0.5926 (0.6131)	model_time 0.5925 (0.6058)	loss 4.4936 (3.7021)	grad_norm 1.3020 (1.5221/0.6751)	mem 24308MB
[2025-01-18 15:44:22 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][220/312]	eta 0:00:56 lr 0.003661	time 0.5771 (0.6116)	model_time 0.5767 (0.6046)	loss 2.6723 (3.6824)	grad_norm 1.0906 (1.5232/0.6826)	mem 24308MB
[2025-01-18 15:44:28 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][230/312]	eta 0:00:50 lr 0.003661	time 0.5857 (0.6106)	model_time 0.5852 (0.6039)	loss 3.7249 (3.6881)	grad_norm 0.9204 (1.5248/0.6776)	mem 24308MB
[2025-01-18 15:44:34 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][240/312]	eta 0:00:43 lr 0.003660	time 0.5841 (0.6096)	model_time 0.5840 (0.6031)	loss 4.4623 (3.6858)	grad_norm 2.4347 (1.5291/0.6747)	mem 24308MB
[2025-01-18 15:44:40 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][250/312]	eta 0:00:37 lr 0.003660	time 0.6727 (0.6091)	model_time 0.6725 (0.6029)	loss 3.7771 (3.6873)	grad_norm 1.5833 (1.5425/0.6723)	mem 24308MB
[2025-01-18 15:44:46 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][260/312]	eta 0:00:31 lr 0.003660	time 0.6645 (0.6089)	model_time 0.6641 (0.6029)	loss 3.1246 (3.6853)	grad_norm 1.2207 (1.5498/0.6723)	mem 24308MB
[2025-01-18 15:44:52 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][270/312]	eta 0:00:25 lr 0.003659	time 0.6343 (0.6090)	model_time 0.6341 (0.6032)	loss 4.3692 (3.6924)	grad_norm 1.5917 (1.5431/0.6671)	mem 24308MB
[2025-01-18 15:44:58 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][280/312]	eta 0:00:19 lr 0.003659	time 0.5819 (0.6093)	model_time 0.5814 (0.6037)	loss 4.8133 (3.6973)	grad_norm 1.2295 (1.5424/0.6670)	mem 24308MB
[2025-01-18 15:45:04 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][290/312]	eta 0:00:13 lr 0.003658	time 0.6726 (0.6102)	model_time 0.6722 (0.6048)	loss 4.1595 (3.7007)	grad_norm 0.8572 (1.5241/0.6634)	mem 24308MB
[2025-01-18 15:45:10 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][300/312]	eta 0:00:07 lr 0.003658	time 0.6772 (0.6101)	model_time 0.6771 (0.6048)	loss 4.4077 (3.7044)	grad_norm 3.0778 (1.5220/0.6728)	mem 24308MB
[2025-01-18 15:45:16 internimage_s_1k_224] (main.py 510): INFO Train: [56/300][310/312]	eta 0:00:01 lr 0.003658	time 0.6706 (0.6093)	model_time 0.6706 (0.6042)	loss 3.5823 (3.6980)	grad_norm 1.2788 (1.5121/0.6693)	mem 24308MB
[2025-01-18 15:45:17 internimage_s_1k_224] (main.py 519): INFO EPOCH 56 training takes 0:03:10
[2025-01-18 15:45:17 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_56.pth saving......
[2025-01-18 15:45:19 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_56.pth saved !!!
[2025-01-18 15:45:26 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.094 (7.094)	Loss 1.0085 (1.0085)	Acc@1 78.101 (78.101)	Acc@5 95.166 (95.166)	Mem 24308MB
[2025-01-18 15:45:29 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.918)	Loss 1.4092 (1.1985)	Acc@1 70.044 (74.026)	Acc@5 89.526 (92.487)	Mem 24308MB
[2025-01-18 15:45:29 internimage_s_1k_224] (main.py 575): INFO [Epoch:56] * Acc@1 74.022 Acc@5 92.520
[2025-01-18 15:45:29 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 74.0%
[2025-01-18 15:45:29 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 74.02%
[2025-01-18 15:45:37 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.149 (8.149)	Loss 1.6536 (1.6536)	Acc@1 63.184 (63.184)	Acc@5 84.521 (84.521)	Mem 24308MB
[2025-01-18 15:45:41 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.100)	Loss 2.3120 (1.9038)	Acc@1 49.756 (57.830)	Acc@5 74.146 (80.913)	Mem 24308MB
[2025-01-18 15:45:41 internimage_s_1k_224] (main.py 575): INFO [Epoch:56] * Acc@1 58.061 Acc@5 81.276
[2025-01-18 15:45:41 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 58.1%
[2025-01-18 15:45:41 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 15:45:43 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 15:45:43 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 58.06%
[2025-01-18 15:45:46 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][0/312]	eta 0:11:09 lr 0.003658	time 2.1471 (2.1471)	model_time 0.5806 (0.5806)	loss 2.6398 (2.6398)	grad_norm 1.5498 (1.5498/0.0000)	mem 24308MB
[2025-01-18 15:45:52 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][10/312]	eta 0:03:44 lr 0.003657	time 0.5770 (0.7443)	model_time 0.5768 (0.6015)	loss 3.5195 (3.5510)	grad_norm 1.1392 (1.1664/0.3537)	mem 24308MB
[2025-01-18 15:45:58 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][20/312]	eta 0:03:15 lr 0.003657	time 0.5808 (0.6704)	model_time 0.5803 (0.5955)	loss 3.9403 (3.5953)	grad_norm 1.5818 (1.2713/0.4284)	mem 24308MB
[2025-01-18 15:46:03 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][30/312]	eta 0:03:01 lr 0.003656	time 0.5856 (0.6426)	model_time 0.5854 (0.5918)	loss 3.1596 (3.6521)	grad_norm 1.8730 (1.2518/0.4076)	mem 24308MB
[2025-01-18 15:46:09 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][40/312]	eta 0:02:51 lr 0.003656	time 0.6002 (0.6295)	model_time 0.6000 (0.5910)	loss 3.2685 (3.5788)	grad_norm 2.5753 (1.3400/0.5220)	mem 24308MB
[2025-01-18 15:46:15 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][50/312]	eta 0:02:42 lr 0.003656	time 0.6073 (0.6214)	model_time 0.6071 (0.5903)	loss 4.2744 (3.5957)	grad_norm 2.7620 (1.4744/0.6366)	mem 24308MB
[2025-01-18 15:46:21 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][60/312]	eta 0:02:35 lr 0.003655	time 0.5823 (0.6157)	model_time 0.5821 (0.5897)	loss 3.5609 (3.6231)	grad_norm 0.9569 (1.5081/0.6617)	mem 24308MB
[2025-01-18 15:46:27 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][70/312]	eta 0:02:28 lr 0.003655	time 0.6747 (0.6146)	model_time 0.6746 (0.5922)	loss 3.5358 (3.5995)	grad_norm 1.9741 (1.5338/0.6646)	mem 24308MB
[2025-01-18 15:46:33 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][80/312]	eta 0:02:22 lr 0.003655	time 0.5837 (0.6147)	model_time 0.5835 (0.5950)	loss 3.0213 (3.6077)	grad_norm 1.3380 (1.5180/0.6499)	mem 24308MB
[2025-01-18 15:46:40 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][90/312]	eta 0:02:16 lr 0.003654	time 0.5909 (0.6165)	model_time 0.5908 (0.5989)	loss 4.7159 (3.6304)	grad_norm 1.4836 (1.5044/0.6255)	mem 24308MB
[2025-01-18 15:46:46 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][100/312]	eta 0:02:10 lr 0.003654	time 0.6802 (0.6170)	model_time 0.6801 (0.6012)	loss 4.2066 (3.6185)	grad_norm 0.8535 (1.4646/0.6139)	mem 24308MB
[2025-01-18 15:46:52 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][110/312]	eta 0:02:04 lr 0.003653	time 0.5924 (0.6160)	model_time 0.5922 (0.6015)	loss 3.1676 (3.6348)	grad_norm 1.5984 (1.4643/0.5979)	mem 24308MB
[2025-01-18 15:46:58 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][120/312]	eta 0:01:58 lr 0.003653	time 0.5857 (0.6155)	model_time 0.5852 (0.6022)	loss 4.5293 (3.6406)	grad_norm 2.7067 (1.4715/0.5961)	mem 24308MB
[2025-01-18 15:47:04 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][130/312]	eta 0:01:51 lr 0.003653	time 0.5806 (0.6145)	model_time 0.5804 (0.6022)	loss 3.9140 (3.6552)	grad_norm 1.3721 (1.5004/0.6019)	mem 24308MB
[2025-01-18 15:47:10 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][140/312]	eta 0:01:45 lr 0.003652	time 0.5896 (0.6123)	model_time 0.5894 (0.6009)	loss 4.3260 (3.6623)	grad_norm 1.1068 (1.4742/0.5900)	mem 24308MB
[2025-01-18 15:47:16 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][150/312]	eta 0:01:38 lr 0.003652	time 0.5815 (0.6104)	model_time 0.5813 (0.5997)	loss 3.0901 (3.6463)	grad_norm 1.1849 (1.4467/0.5831)	mem 24308MB
[2025-01-18 15:47:22 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][160/312]	eta 0:01:32 lr 0.003652	time 0.5821 (0.6090)	model_time 0.5817 (0.5989)	loss 3.7708 (3.6601)	grad_norm 1.6496 (1.4650/0.5908)	mem 24308MB
[2025-01-18 15:47:27 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][170/312]	eta 0:01:26 lr 0.003651	time 0.5775 (0.6077)	model_time 0.5774 (0.5982)	loss 3.9837 (3.6439)	grad_norm 2.2142 (1.4842/0.6035)	mem 24308MB
[2025-01-18 15:47:33 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][180/312]	eta 0:01:20 lr 0.003651	time 0.5883 (0.6066)	model_time 0.5879 (0.5976)	loss 3.6437 (3.6450)	grad_norm 0.8702 (1.4717/0.5917)	mem 24308MB
[2025-01-18 15:47:39 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][190/312]	eta 0:01:13 lr 0.003650	time 0.6859 (0.6064)	model_time 0.6858 (0.5978)	loss 3.8706 (3.6574)	grad_norm 1.0963 (1.4635/0.5850)	mem 24308MB
[2025-01-18 15:47:45 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][200/312]	eta 0:01:07 lr 0.003650	time 0.5874 (0.6066)	model_time 0.5869 (0.5985)	loss 4.5520 (3.6434)	grad_norm 1.7370 (1.4513/0.5776)	mem 24308MB
[2025-01-18 15:47:52 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][210/312]	eta 0:01:02 lr 0.003650	time 0.5814 (0.6079)	model_time 0.5809 (0.6001)	loss 3.1099 (3.6401)	grad_norm 1.6398 (1.4682/0.5770)	mem 24308MB
[2025-01-18 15:47:58 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][220/312]	eta 0:00:56 lr 0.003649	time 0.6691 (0.6091)	model_time 0.6689 (0.6017)	loss 3.6833 (3.6489)	grad_norm 0.8053 (1.4705/0.5753)	mem 24308MB
[2025-01-18 15:48:04 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][230/312]	eta 0:00:50 lr 0.003649	time 0.5794 (0.6101)	model_time 0.5790 (0.6030)	loss 4.6380 (3.6573)	grad_norm 1.0940 (1.4973/0.6312)	mem 24308MB
[2025-01-18 15:48:10 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][240/312]	eta 0:00:43 lr 0.003649	time 0.6691 (0.6101)	model_time 0.6689 (0.6032)	loss 3.1107 (3.6619)	grad_norm 0.6687 (1.4850/0.6249)	mem 24308MB
[2025-01-18 15:48:16 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][250/312]	eta 0:00:37 lr 0.003648	time 0.5690 (0.6096)	model_time 0.5686 (0.6031)	loss 3.7987 (3.6581)	grad_norm 0.9634 (1.4677/0.6194)	mem 24308MB
[2025-01-18 15:48:22 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][260/312]	eta 0:00:31 lr 0.003648	time 0.5778 (0.6090)	model_time 0.5776 (0.6026)	loss 3.9100 (3.6600)	grad_norm 0.6812 (1.4662/0.6152)	mem 24308MB
[2025-01-18 15:48:28 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][270/312]	eta 0:00:25 lr 0.003647	time 0.5884 (0.6081)	model_time 0.5880 (0.6019)	loss 2.3315 (3.6517)	grad_norm 1.3352 (1.4591/0.6121)	mem 24308MB
[2025-01-18 15:48:34 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][280/312]	eta 0:00:19 lr 0.003647	time 0.5679 (0.6073)	model_time 0.5677 (0.6014)	loss 2.7705 (3.6547)	grad_norm 3.5388 (1.4895/0.6540)	mem 24308MB
[2025-01-18 15:48:40 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][290/312]	eta 0:00:13 lr 0.003647	time 0.5867 (0.6067)	model_time 0.5866 (0.6010)	loss 3.1705 (3.6643)	grad_norm 1.2700 (1.4889/0.6564)	mem 24308MB
[2025-01-18 15:48:46 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][300/312]	eta 0:00:07 lr 0.003646	time 0.5630 (0.6058)	model_time 0.5629 (0.6003)	loss 3.4603 (3.6686)	grad_norm 0.9156 (1.4746/0.6533)	mem 24308MB
[2025-01-18 15:48:52 internimage_s_1k_224] (main.py 510): INFO Train: [57/300][310/312]	eta 0:00:01 lr 0.003646	time 0.5673 (0.6047)	model_time 0.5673 (0.5993)	loss 4.5530 (3.6805)	grad_norm 1.3015 (1.4779/0.6512)	mem 24308MB
[2025-01-18 15:48:52 internimage_s_1k_224] (main.py 519): INFO EPOCH 57 training takes 0:03:08
[2025-01-18 15:48:52 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_57.pth saving......
[2025-01-18 15:48:54 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_57.pth saved !!!
[2025-01-18 15:49:01 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.067 (7.067)	Loss 0.9401 (0.9401)	Acc@1 78.613 (78.613)	Acc@5 95.044 (95.044)	Mem 24308MB
[2025-01-18 15:49:04 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.134 (0.945)	Loss 1.4298 (1.1611)	Acc@1 67.871 (74.245)	Acc@5 89.624 (92.460)	Mem 24308MB
[2025-01-18 15:49:05 internimage_s_1k_224] (main.py 575): INFO [Epoch:57] * Acc@1 74.228 Acc@5 92.464
[2025-01-18 15:49:05 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 74.2%
[2025-01-18 15:49:05 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 15:49:06 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 15:49:06 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 74.23%
[2025-01-18 15:49:14 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.141 (7.141)	Loss 1.5890 (1.5890)	Acc@1 64.062 (64.062)	Acc@5 85.327 (85.327)	Mem 24308MB
[2025-01-18 15:49:17 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.937)	Loss 2.2435 (1.8379)	Acc@1 50.928 (59.031)	Acc@5 75.220 (81.818)	Mem 24308MB
[2025-01-18 15:49:17 internimage_s_1k_224] (main.py 575): INFO [Epoch:57] * Acc@1 59.231 Acc@5 82.170
[2025-01-18 15:49:17 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 59.2%
[2025-01-18 15:49:17 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 15:49:19 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 15:49:19 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 59.23%
[2025-01-18 15:49:21 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][0/312]	eta 0:12:41 lr 0.003646	time 2.4407 (2.4407)	model_time 0.6198 (0.6198)	loss 4.1084 (4.1084)	grad_norm 0.7386 (0.7386/0.0000)	mem 24308MB
[2025-01-18 15:49:27 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][10/312]	eta 0:03:55 lr 0.003645	time 0.6970 (0.7782)	model_time 0.6969 (0.6124)	loss 3.0175 (3.8716)	grad_norm 1.8869 (1.6384/0.5299)	mem 24308MB
[2025-01-18 15:49:34 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][20/312]	eta 0:03:27 lr 0.003645	time 0.6593 (0.7091)	model_time 0.6591 (0.6221)	loss 2.6359 (3.7914)	grad_norm 2.1005 (1.7232/0.6260)	mem 24308MB
[2025-01-18 15:49:40 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][30/312]	eta 0:03:13 lr 0.003645	time 0.5794 (0.6856)	model_time 0.5790 (0.6265)	loss 4.1438 (3.7828)	grad_norm 1.6208 (1.7206/0.6087)	mem 24308MB
[2025-01-18 15:49:46 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][40/312]	eta 0:03:02 lr 0.003644	time 0.6028 (0.6727)	model_time 0.6022 (0.6280)	loss 4.1198 (3.7389)	grad_norm 0.9821 (1.5845/0.5963)	mem 24308MB
[2025-01-18 15:49:52 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][50/312]	eta 0:02:52 lr 0.003644	time 0.5749 (0.6571)	model_time 0.5747 (0.6211)	loss 3.5245 (3.7203)	grad_norm 1.0708 (1.5292/0.5641)	mem 24308MB
[2025-01-18 15:49:58 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][60/312]	eta 0:02:43 lr 0.003644	time 0.5821 (0.6488)	model_time 0.5819 (0.6186)	loss 3.8504 (3.7070)	grad_norm 0.7431 (1.4923/0.5726)	mem 24308MB
[2025-01-18 15:50:04 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][70/312]	eta 0:02:35 lr 0.003643	time 0.6050 (0.6406)	model_time 0.6049 (0.6146)	loss 3.9228 (3.6881)	grad_norm 1.4776 (1.5579/0.6232)	mem 24308MB
[2025-01-18 15:50:10 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][80/312]	eta 0:02:26 lr 0.003643	time 0.5826 (0.6335)	model_time 0.5824 (0.6106)	loss 3.3855 (3.7185)	grad_norm 1.4904 (1.5194/0.6036)	mem 24308MB
[2025-01-18 15:50:16 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][90/312]	eta 0:02:19 lr 0.003642	time 0.5962 (0.6288)	model_time 0.5960 (0.6085)	loss 3.5525 (3.7031)	grad_norm 1.0397 (1.4656/0.5923)	mem 24308MB
[2025-01-18 15:50:22 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][100/312]	eta 0:02:12 lr 0.003642	time 0.5843 (0.6244)	model_time 0.5838 (0.6060)	loss 3.9246 (3.7157)	grad_norm 2.2171 (1.4626/0.5763)	mem 24308MB
[2025-01-18 15:50:28 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][110/312]	eta 0:02:05 lr 0.003642	time 0.5724 (0.6209)	model_time 0.5722 (0.6041)	loss 3.5001 (3.7199)	grad_norm 1.3966 (1.4762/0.5730)	mem 24308MB
[2025-01-18 15:50:34 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][120/312]	eta 0:01:58 lr 0.003641	time 0.5861 (0.6185)	model_time 0.5859 (0.6031)	loss 4.3542 (3.7341)	grad_norm 0.8249 (1.4788/0.5622)	mem 24308MB
[2025-01-18 15:50:40 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][130/312]	eta 0:01:52 lr 0.003641	time 0.6897 (0.6182)	model_time 0.6893 (0.6039)	loss 4.2406 (3.7411)	grad_norm 3.3901 (1.4995/0.5916)	mem 24308MB
[2025-01-18 15:50:46 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][140/312]	eta 0:01:46 lr 0.003641	time 0.6516 (0.6185)	model_time 0.6512 (0.6052)	loss 3.4743 (3.7440)	grad_norm 1.5988 (1.5268/0.6193)	mem 24308MB
[2025-01-18 15:50:53 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][150/312]	eta 0:01:40 lr 0.003640	time 0.5873 (0.6228)	model_time 0.5869 (0.6104)	loss 3.4666 (3.7530)	grad_norm 1.3591 (1.5121/0.6070)	mem 24308MB
[2025-01-18 15:50:59 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][160/312]	eta 0:01:34 lr 0.003640	time 0.6755 (0.6221)	model_time 0.6752 (0.6104)	loss 4.2341 (3.7741)	grad_norm 1.7677 (1.5005/0.5970)	mem 24308MB
[2025-01-18 15:51:05 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][170/312]	eta 0:01:28 lr 0.003639	time 0.5844 (0.6204)	model_time 0.5842 (0.6094)	loss 3.9305 (3.7838)	grad_norm 0.9327 (1.4913/0.5896)	mem 24308MB
[2025-01-18 15:51:11 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][180/312]	eta 0:01:21 lr 0.003639	time 0.6853 (0.6196)	model_time 0.6851 (0.6091)	loss 3.9948 (3.7917)	grad_norm 1.1208 (1.4826/0.5811)	mem 24308MB
[2025-01-18 15:51:17 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][190/312]	eta 0:01:15 lr 0.003639	time 0.5715 (0.6183)	model_time 0.5714 (0.6083)	loss 4.2823 (3.7973)	grad_norm 1.0293 (1.4671/0.5734)	mem 24308MB
[2025-01-18 15:51:23 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][200/312]	eta 0:01:09 lr 0.003638	time 0.5971 (0.6168)	model_time 0.5969 (0.6073)	loss 3.9215 (3.7833)	grad_norm 1.2194 (1.4759/0.5760)	mem 24308MB
[2025-01-18 15:51:29 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][210/312]	eta 0:01:02 lr 0.003638	time 0.5847 (0.6152)	model_time 0.5845 (0.6062)	loss 3.2240 (3.7860)	grad_norm 2.0592 (1.4853/0.5768)	mem 24308MB
[2025-01-18 15:51:35 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][220/312]	eta 0:00:56 lr 0.003637	time 0.5811 (0.6139)	model_time 0.5809 (0.6052)	loss 3.8572 (3.7827)	grad_norm 1.7627 (1.4881/0.5766)	mem 24308MB
[2025-01-18 15:51:40 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][230/312]	eta 0:00:50 lr 0.003637	time 0.5792 (0.6127)	model_time 0.5790 (0.6044)	loss 2.8223 (3.7842)	grad_norm 0.9928 (1.4933/0.5750)	mem 24308MB
[2025-01-18 15:51:46 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][240/312]	eta 0:00:44 lr 0.003637	time 0.5663 (0.6116)	model_time 0.5658 (0.6037)	loss 4.5814 (3.7853)	grad_norm 1.0277 (1.4855/0.5719)	mem 24308MB
[2025-01-18 15:51:52 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][250/312]	eta 0:00:37 lr 0.003636	time 0.5810 (0.6118)	model_time 0.5808 (0.6041)	loss 3.7506 (3.7715)	grad_norm 1.4574 (1.4752/0.5698)	mem 24308MB
[2025-01-18 15:51:59 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][260/312]	eta 0:00:31 lr 0.003636	time 0.6716 (0.6122)	model_time 0.6715 (0.6049)	loss 3.0240 (3.7643)	grad_norm 2.1299 (1.4791/0.5629)	mem 24308MB
[2025-01-18 15:52:05 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][270/312]	eta 0:00:25 lr 0.003636	time 0.5755 (0.6127)	model_time 0.5754 (0.6056)	loss 3.1579 (3.7613)	grad_norm 1.1591 (1.4770/0.5584)	mem 24308MB
[2025-01-18 15:52:11 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][280/312]	eta 0:00:19 lr 0.003635	time 0.6855 (0.6137)	model_time 0.6853 (0.6068)	loss 3.9874 (3.7620)	grad_norm 1.3946 (1.4677/0.5534)	mem 24308MB
[2025-01-18 15:52:17 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][290/312]	eta 0:00:13 lr 0.003635	time 0.5929 (0.6130)	model_time 0.5927 (0.6064)	loss 3.9241 (3.7684)	grad_norm 1.3128 (1.4725/0.5552)	mem 24308MB
[2025-01-18 15:52:23 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][300/312]	eta 0:00:07 lr 0.003634	time 0.5676 (0.6122)	model_time 0.5676 (0.6058)	loss 3.5461 (3.7676)	grad_norm 0.9638 (1.5030/0.5971)	mem 24308MB
[2025-01-18 15:52:29 internimage_s_1k_224] (main.py 510): INFO Train: [58/300][310/312]	eta 0:00:01 lr 0.003634	time 0.5639 (0.6116)	model_time 0.5638 (0.6054)	loss 4.0209 (3.7680)	grad_norm 1.1287 (1.4870/0.5937)	mem 24308MB
[2025-01-18 15:52:30 internimage_s_1k_224] (main.py 519): INFO EPOCH 58 training takes 0:03:10
[2025-01-18 15:52:30 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_58.pth saving......
[2025-01-18 15:52:31 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_58.pth saved !!!
[2025-01-18 15:52:39 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.156 (7.156)	Loss 1.0106 (1.0106)	Acc@1 78.198 (78.198)	Acc@5 95.239 (95.239)	Mem 24308MB
[2025-01-18 15:52:42 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.930)	Loss 1.4490 (1.2093)	Acc@1 68.530 (74.394)	Acc@5 89.746 (92.596)	Mem 24308MB
[2025-01-18 15:52:42 internimage_s_1k_224] (main.py 575): INFO [Epoch:58] * Acc@1 74.382 Acc@5 92.632
[2025-01-18 15:52:42 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 74.4%
[2025-01-18 15:52:42 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 15:52:44 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 15:52:44 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 74.38%
[2025-01-18 15:52:51 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.082 (7.082)	Loss 1.5316 (1.5316)	Acc@1 64.917 (64.917)	Acc@5 86.133 (86.133)	Mem 24308MB
[2025-01-18 15:52:54 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.922)	Loss 2.1802 (1.7779)	Acc@1 52.124 (60.203)	Acc@5 76.367 (82.657)	Mem 24308MB
[2025-01-18 15:52:54 internimage_s_1k_224] (main.py 575): INFO [Epoch:58] * Acc@1 60.365 Acc@5 82.981
[2025-01-18 15:52:54 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 60.4%
[2025-01-18 15:52:54 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 15:52:57 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 15:52:57 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 60.36%
[2025-01-18 15:52:59 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][0/312]	eta 0:12:45 lr 0.003634	time 2.4526 (2.4526)	model_time 0.6010 (0.6010)	loss 3.6052 (3.6052)	grad_norm 1.1284 (1.1284/0.0000)	mem 24308MB
[2025-01-18 15:53:05 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][10/312]	eta 0:03:48 lr 0.003634	time 0.5748 (0.7581)	model_time 0.5746 (0.5895)	loss 3.6755 (3.8606)	grad_norm 1.7084 (1.5980/0.4979)	mem 24308MB
[2025-01-18 15:53:11 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][20/312]	eta 0:03:18 lr 0.003633	time 0.5773 (0.6785)	model_time 0.5769 (0.5900)	loss 2.5733 (3.7300)	grad_norm 0.9229 (1.4277/0.4509)	mem 24308MB
[2025-01-18 15:53:17 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][30/312]	eta 0:03:02 lr 0.003633	time 0.5872 (0.6484)	model_time 0.5867 (0.5883)	loss 2.6989 (3.7233)	grad_norm 0.8918 (1.4374/0.5063)	mem 24308MB
[2025-01-18 15:53:23 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][40/312]	eta 0:02:52 lr 0.003632	time 0.5815 (0.6330)	model_time 0.5814 (0.5875)	loss 2.7540 (3.6634)	grad_norm 0.7441 (1.4952/0.5917)	mem 24308MB
[2025-01-18 15:53:28 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][50/312]	eta 0:02:43 lr 0.003632	time 0.5817 (0.6238)	model_time 0.5815 (0.5871)	loss 4.2616 (3.6549)	grad_norm 0.8881 (1.4001/0.5775)	mem 24308MB
[2025-01-18 15:53:34 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][60/312]	eta 0:02:36 lr 0.003632	time 0.5821 (0.6212)	model_time 0.5819 (0.5905)	loss 3.8514 (3.6265)	grad_norm 1.1658 (1.3429/0.5506)	mem 24308MB
[2025-01-18 15:53:41 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][70/312]	eta 0:02:30 lr 0.003631	time 0.7265 (0.6203)	model_time 0.7261 (0.5939)	loss 3.6403 (3.6823)	grad_norm 1.4875 (1.3935/0.5779)	mem 24308MB
[2025-01-18 15:53:47 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][80/312]	eta 0:02:24 lr 0.003631	time 0.6736 (0.6221)	model_time 0.6732 (0.5989)	loss 3.0929 (3.6745)	grad_norm 1.8717 (1.4071/0.5615)	mem 24308MB
[2025-01-18 15:53:53 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][90/312]	eta 0:02:18 lr 0.003630	time 0.5702 (0.6220)	model_time 0.5701 (0.6013)	loss 4.2417 (3.6852)	grad_norm 0.8361 (1.4034/0.5517)	mem 24308MB
[2025-01-18 15:53:59 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][100/312]	eta 0:02:11 lr 0.003630	time 0.6076 (0.6197)	model_time 0.6074 (0.6010)	loss 2.4606 (3.6978)	grad_norm 2.9670 (1.4898/0.6446)	mem 24308MB
[2025-01-18 15:54:05 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][110/312]	eta 0:02:04 lr 0.003630	time 0.5877 (0.6183)	model_time 0.5875 (0.6013)	loss 3.8688 (3.7116)	grad_norm 1.2088 (1.4788/0.6214)	mem 24308MB
[2025-01-18 15:54:11 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][120/312]	eta 0:01:58 lr 0.003629	time 0.5896 (0.6160)	model_time 0.5891 (0.6003)	loss 4.2804 (3.7122)	grad_norm 1.4789 (1.4728/0.6019)	mem 24308MB
[2025-01-18 15:54:17 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][130/312]	eta 0:01:51 lr 0.003629	time 0.5868 (0.6139)	model_time 0.5863 (0.5993)	loss 4.2144 (3.6905)	grad_norm 1.7286 (1.4736/0.6078)	mem 24308MB
[2025-01-18 15:54:23 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][140/312]	eta 0:01:45 lr 0.003629	time 0.5918 (0.6118)	model_time 0.5916 (0.5983)	loss 3.8738 (3.6694)	grad_norm 2.6901 (1.4639/0.6070)	mem 24308MB
[2025-01-18 15:54:29 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][150/312]	eta 0:01:38 lr 0.003628	time 0.5992 (0.6100)	model_time 0.5990 (0.5973)	loss 3.7229 (3.6827)	grad_norm 0.8708 (1.4635/0.6036)	mem 24308MB
[2025-01-18 15:54:35 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][160/312]	eta 0:01:32 lr 0.003628	time 0.5852 (0.6087)	model_time 0.5847 (0.5969)	loss 2.9326 (3.6600)	grad_norm 0.8473 (1.4648/0.6093)	mem 24308MB
[2025-01-18 15:54:40 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][170/312]	eta 0:01:26 lr 0.003627	time 0.5766 (0.6077)	model_time 0.5765 (0.5965)	loss 3.2303 (3.6646)	grad_norm 1.0342 (1.4490/0.5979)	mem 24308MB
[2025-01-18 15:54:47 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][180/312]	eta 0:01:20 lr 0.003627	time 0.5904 (0.6081)	model_time 0.5903 (0.5975)	loss 2.8184 (3.6637)	grad_norm 1.2890 (1.4436/0.5873)	mem 24308MB
[2025-01-18 15:54:53 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][190/312]	eta 0:01:14 lr 0.003627	time 0.5794 (0.6078)	model_time 0.5793 (0.5977)	loss 2.8369 (3.6591)	grad_norm 1.2434 (1.4441/0.5738)	mem 24308MB
[2025-01-18 15:54:59 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][200/312]	eta 0:01:08 lr 0.003626	time 0.6530 (0.6095)	model_time 0.6526 (0.5999)	loss 3.9603 (3.6683)	grad_norm 1.7938 (1.4525/0.5726)	mem 24308MB
[2025-01-18 15:55:05 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][210/312]	eta 0:01:02 lr 0.003626	time 0.6645 (0.6103)	model_time 0.6643 (0.6011)	loss 3.5766 (3.6622)	grad_norm 0.8160 (1.4457/0.5674)	mem 24308MB
[2025-01-18 15:55:11 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][220/312]	eta 0:00:56 lr 0.003625	time 0.5638 (0.6094)	model_time 0.5637 (0.6007)	loss 3.9471 (3.6401)	grad_norm 2.0811 (1.4486/0.5646)	mem 24308MB
[2025-01-18 15:55:17 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][230/312]	eta 0:00:49 lr 0.003625	time 0.5735 (0.6088)	model_time 0.5733 (0.6004)	loss 4.2690 (3.6424)	grad_norm 1.4661 (1.4512/0.5616)	mem 24308MB
[2025-01-18 15:55:23 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][240/312]	eta 0:00:43 lr 0.003625	time 0.5789 (0.6081)	model_time 0.5785 (0.6001)	loss 3.7821 (3.6529)	grad_norm 1.0172 (1.4355/0.5612)	mem 24308MB
[2025-01-18 15:55:29 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][250/312]	eta 0:00:37 lr 0.003624	time 0.5768 (0.6073)	model_time 0.5764 (0.5995)	loss 4.4348 (3.6618)	grad_norm 2.0100 (1.4307/0.5551)	mem 24308MB
[2025-01-18 15:55:35 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][260/312]	eta 0:00:31 lr 0.003624	time 0.5780 (0.6064)	model_time 0.5779 (0.5989)	loss 3.2606 (3.6659)	grad_norm 2.0412 (1.4498/0.5764)	mem 24308MB
[2025-01-18 15:55:41 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][270/312]	eta 0:00:25 lr 0.003623	time 0.6028 (0.6058)	model_time 0.6026 (0.5986)	loss 4.0381 (3.6545)	grad_norm 0.8885 (1.4552/0.5759)	mem 24308MB
[2025-01-18 15:55:47 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][280/312]	eta 0:00:19 lr 0.003623	time 0.5774 (0.6051)	model_time 0.5772 (0.5981)	loss 4.5194 (3.6608)	grad_norm 1.0251 (1.4518/0.5713)	mem 24308MB
[2025-01-18 15:55:52 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][290/312]	eta 0:00:13 lr 0.003623	time 0.5819 (0.6045)	model_time 0.5808 (0.5978)	loss 3.9427 (3.6667)	grad_norm 2.1127 (1.4501/0.5676)	mem 24308MB
[2025-01-18 15:55:59 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][300/312]	eta 0:00:07 lr 0.003622	time 0.6401 (0.6050)	model_time 0.6399 (0.5985)	loss 2.9956 (3.6621)	grad_norm 2.9171 (1.4880/0.6168)	mem 24308MB
[2025-01-18 15:56:05 internimage_s_1k_224] (main.py 510): INFO Train: [59/300][310/312]	eta 0:00:01 lr 0.003622	time 0.5663 (0.6048)	model_time 0.5662 (0.5985)	loss 3.0555 (3.6566)	grad_norm 0.9458 (1.4708/0.6144)	mem 24308MB
[2025-01-18 15:56:05 internimage_s_1k_224] (main.py 519): INFO EPOCH 59 training takes 0:03:08
[2025-01-18 15:56:05 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_59.pth saving......
[2025-01-18 15:56:07 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_59.pth saved !!!
[2025-01-18 15:56:14 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.926 (6.926)	Loss 0.9707 (0.9707)	Acc@1 78.467 (78.467)	Acc@5 94.849 (94.849)	Mem 24308MB
[2025-01-18 15:56:17 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.900)	Loss 1.4109 (1.1673)	Acc@1 68.823 (74.452)	Acc@5 89.648 (92.631)	Mem 24308MB
[2025-01-18 15:56:17 internimage_s_1k_224] (main.py 575): INFO [Epoch:59] * Acc@1 74.512 Acc@5 92.692
[2025-01-18 15:56:17 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 74.5%
[2025-01-18 15:56:17 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 15:56:19 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 15:56:19 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 74.51%
[2025-01-18 15:56:26 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.954 (6.954)	Loss 1.4786 (1.4786)	Acc@1 66.089 (66.089)	Acc@5 87.012 (87.012)	Mem 24308MB
[2025-01-18 15:56:29 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.927)	Loss 2.1200 (1.7215)	Acc@1 53.003 (61.279)	Acc@5 77.271 (83.534)	Mem 24308MB
[2025-01-18 15:56:29 internimage_s_1k_224] (main.py 575): INFO [Epoch:59] * Acc@1 61.422 Acc@5 83.827
[2025-01-18 15:56:29 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 61.4%
[2025-01-18 15:56:30 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 15:56:31 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 15:56:31 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 61.42%
[2025-01-18 15:56:34 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][0/312]	eta 0:11:36 lr 0.003622	time 2.2335 (2.2335)	model_time 0.5970 (0.5970)	loss 3.7079 (3.7079)	grad_norm 1.6658 (1.6658/0.0000)	mem 24308MB
[2025-01-18 15:56:40 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][10/312]	eta 0:03:56 lr 0.003621	time 0.5888 (0.7815)	model_time 0.5886 (0.6323)	loss 3.0476 (3.6580)	grad_norm 0.8614 (1.2392/0.2556)	mem 24308MB
[2025-01-18 15:56:46 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][20/312]	eta 0:03:24 lr 0.003621	time 0.5939 (0.7008)	model_time 0.5937 (0.6225)	loss 3.4200 (3.5221)	grad_norm 1.0444 (1.1826/0.2804)	mem 24308MB
[2025-01-18 15:56:52 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][30/312]	eta 0:03:09 lr 0.003621	time 0.5843 (0.6735)	model_time 0.5838 (0.6204)	loss 2.1866 (3.5345)	grad_norm 1.2724 (1.2783/0.4775)	mem 24308MB
[2025-01-18 15:56:58 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][40/312]	eta 0:02:58 lr 0.003620	time 0.6646 (0.6566)	model_time 0.6645 (0.6163)	loss 3.0612 (3.5234)	grad_norm 0.9253 (1.3364/0.5044)	mem 24308MB
[2025-01-18 15:57:04 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][50/312]	eta 0:02:48 lr 0.003620	time 0.5815 (0.6423)	model_time 0.5814 (0.6098)	loss 3.9004 (3.5640)	grad_norm 2.3370 (1.4687/0.6235)	mem 24308MB
[2025-01-18 15:57:10 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][60/312]	eta 0:02:39 lr 0.003620	time 0.5825 (0.6332)	model_time 0.5824 (0.6060)	loss 4.0222 (3.5960)	grad_norm 1.4928 (1.5190/0.6465)	mem 24308MB
[2025-01-18 15:57:16 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][70/312]	eta 0:02:31 lr 0.003619	time 0.5958 (0.6269)	model_time 0.5953 (0.6035)	loss 2.9173 (3.6087)	grad_norm 0.6750 (1.5240/0.6245)	mem 24308MB
[2025-01-18 15:57:22 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][80/312]	eta 0:02:24 lr 0.003619	time 0.5753 (0.6219)	model_time 0.5749 (0.6013)	loss 4.6882 (3.6426)	grad_norm 1.1938 (1.5340/0.6037)	mem 24308MB
[2025-01-18 15:57:28 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][90/312]	eta 0:02:17 lr 0.003618	time 0.5930 (0.6184)	model_time 0.5928 (0.6000)	loss 3.7313 (3.6526)	grad_norm 1.4218 (1.4919/0.5891)	mem 24308MB
[2025-01-18 15:57:34 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][100/312]	eta 0:02:10 lr 0.003618	time 0.5806 (0.6148)	model_time 0.5804 (0.5982)	loss 3.1211 (3.6450)	grad_norm 1.0536 (1.5317/0.6917)	mem 24308MB
[2025-01-18 15:57:40 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][110/312]	eta 0:02:04 lr 0.003618	time 0.5752 (0.6146)	model_time 0.5748 (0.5994)	loss 3.0676 (3.6434)	grad_norm 0.8835 (1.5258/0.6831)	mem 24308MB
[2025-01-18 15:57:46 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][120/312]	eta 0:01:57 lr 0.003617	time 0.5862 (0.6135)	model_time 0.5860 (0.5996)	loss 2.8337 (3.6450)	grad_norm 1.6885 (1.5193/0.6691)	mem 24308MB
[2025-01-18 15:57:52 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][130/312]	eta 0:01:52 lr 0.003617	time 0.7356 (0.6159)	model_time 0.7354 (0.6030)	loss 3.6489 (3.6270)	grad_norm 1.7941 (1.5118/0.6504)	mem 24308MB
[2025-01-18 15:57:59 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][140/312]	eta 0:01:46 lr 0.003616	time 0.6604 (0.6172)	model_time 0.6602 (0.6053)	loss 3.8943 (3.6301)	grad_norm 1.1388 (1.4975/0.6417)	mem 24308MB
[2025-01-18 15:58:05 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][150/312]	eta 0:01:39 lr 0.003616	time 0.5921 (0.6162)	model_time 0.5916 (0.6050)	loss 4.1102 (3.6425)	grad_norm 2.0810 (1.4934/0.6352)	mem 24308MB
[2025-01-18 15:58:10 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][160/312]	eta 0:01:33 lr 0.003616	time 0.5837 (0.6150)	model_time 0.5835 (0.6044)	loss 2.5606 (3.6466)	grad_norm 1.5353 (1.5028/0.6375)	mem 24308MB
[2025-01-18 15:58:16 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][170/312]	eta 0:01:27 lr 0.003615	time 0.5796 (0.6137)	model_time 0.5794 (0.6038)	loss 3.7800 (3.6706)	grad_norm 1.3297 (1.4932/0.6228)	mem 24308MB
[2025-01-18 15:58:22 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][180/312]	eta 0:01:20 lr 0.003615	time 0.5753 (0.6121)	model_time 0.5751 (0.6027)	loss 4.3613 (3.6788)	grad_norm 2.3929 (1.5042/0.6278)	mem 24308MB
[2025-01-18 15:58:28 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][190/312]	eta 0:01:14 lr 0.003614	time 0.5899 (0.6110)	model_time 0.5897 (0.6021)	loss 3.6070 (3.6675)	grad_norm 1.2442 (1.4961/0.6216)	mem 24308MB
[2025-01-18 15:58:34 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][200/312]	eta 0:01:08 lr 0.003614	time 0.5779 (0.6097)	model_time 0.5774 (0.6012)	loss 3.5288 (3.6615)	grad_norm 0.9182 (1.4903/0.6146)	mem 24308MB
[2025-01-18 15:58:40 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][210/312]	eta 0:01:02 lr 0.003614	time 0.6076 (0.6089)	model_time 0.6074 (0.6007)	loss 3.0552 (3.6721)	grad_norm 1.9116 (1.4788/0.6065)	mem 24308MB
[2025-01-18 15:58:46 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][220/312]	eta 0:00:55 lr 0.003613	time 0.5863 (0.6077)	model_time 0.5861 (0.5999)	loss 3.0503 (3.6652)	grad_norm 1.2584 (1.4821/0.6016)	mem 24308MB
[2025-01-18 15:58:52 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][230/312]	eta 0:00:49 lr 0.003613	time 0.6656 (0.6073)	model_time 0.6649 (0.5999)	loss 3.7649 (3.6662)	grad_norm 1.0109 (1.4825/0.5958)	mem 24308MB
[2025-01-18 15:58:58 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][240/312]	eta 0:00:43 lr 0.003612	time 0.5722 (0.6075)	model_time 0.5720 (0.6003)	loss 3.2096 (3.6517)	grad_norm 1.1187 (1.4791/0.5990)	mem 24308MB
[2025-01-18 15:59:04 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][250/312]	eta 0:00:37 lr 0.003612	time 0.7504 (0.6096)	model_time 0.7503 (0.6027)	loss 3.8840 (3.6562)	grad_norm 1.2744 (1.4729/0.5915)	mem 24308MB
[2025-01-18 15:59:11 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][260/312]	eta 0:00:31 lr 0.003612	time 0.6589 (0.6096)	model_time 0.6588 (0.6029)	loss 2.9123 (3.6601)	grad_norm 0.6696 (1.4548/0.5889)	mem 24308MB
[2025-01-18 15:59:17 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][270/312]	eta 0:00:25 lr 0.003611	time 0.5750 (0.6095)	model_time 0.5749 (0.6031)	loss 4.0140 (3.6543)	grad_norm 0.9980 (1.4591/0.5864)	mem 24308MB
[2025-01-18 15:59:23 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][280/312]	eta 0:00:19 lr 0.003611	time 0.5737 (0.6088)	model_time 0.5735 (0.6026)	loss 4.0594 (3.6461)	grad_norm 1.0767 (1.4555/0.5817)	mem 24308MB
[2025-01-18 15:59:29 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][290/312]	eta 0:00:13 lr 0.003610	time 0.5938 (0.6084)	model_time 0.5934 (0.6024)	loss 3.8734 (3.6543)	grad_norm 1.8350 (1.4753/0.6207)	mem 24308MB
[2025-01-18 15:59:34 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][300/312]	eta 0:00:07 lr 0.003610	time 0.5672 (0.6073)	model_time 0.5671 (0.6015)	loss 3.7935 (3.6529)	grad_norm 1.4247 (1.4787/0.6260)	mem 24308MB
[2025-01-18 15:59:40 internimage_s_1k_224] (main.py 510): INFO Train: [60/300][310/312]	eta 0:00:01 lr 0.003610	time 0.5694 (0.6063)	model_time 0.5693 (0.6007)	loss 3.5275 (3.6500)	grad_norm 0.8698 (1.4809/0.6276)	mem 24308MB
[2025-01-18 15:59:41 internimage_s_1k_224] (main.py 519): INFO EPOCH 60 training takes 0:03:09
[2025-01-18 15:59:41 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_60.pth saving......
[2025-01-18 15:59:42 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_60.pth saved !!!
[2025-01-18 15:59:49 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.924 (6.924)	Loss 0.9817 (0.9817)	Acc@1 79.028 (79.028)	Acc@5 95.337 (95.337)	Mem 24308MB
[2025-01-18 15:59:53 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.921)	Loss 1.4240 (1.1735)	Acc@1 68.701 (74.467)	Acc@5 90.039 (92.649)	Mem 24308MB
[2025-01-18 15:59:53 internimage_s_1k_224] (main.py 575): INFO [Epoch:60] * Acc@1 74.504 Acc@5 92.716
[2025-01-18 15:59:53 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 74.5%
[2025-01-18 15:59:53 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 74.51%
[2025-01-18 16:00:01 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.165 (8.165)	Loss 1.4298 (1.4298)	Acc@1 67.041 (67.041)	Acc@5 87.646 (87.646)	Mem 24308MB
[2025-01-18 16:00:05 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.108)	Loss 2.0648 (1.6699)	Acc@1 54.126 (62.267)	Acc@5 78.076 (84.315)	Mem 24308MB
[2025-01-18 16:00:05 internimage_s_1k_224] (main.py 575): INFO [Epoch:60] * Acc@1 62.390 Acc@5 84.579
[2025-01-18 16:00:05 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 62.4%
[2025-01-18 16:00:05 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 16:00:07 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 16:00:07 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 62.39%
[2025-01-18 16:00:09 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][0/312]	eta 0:11:14 lr 0.003610	time 2.1610 (2.1610)	model_time 0.5950 (0.5950)	loss 3.8631 (3.8631)	grad_norm 0.8185 (0.8185/0.0000)	mem 24308MB
[2025-01-18 16:00:15 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][10/312]	eta 0:03:41 lr 0.003609	time 0.5743 (0.7344)	model_time 0.5742 (0.5917)	loss 2.6897 (3.4416)	grad_norm 0.7871 (1.3430/0.3305)	mem 24308MB
[2025-01-18 16:00:21 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][20/312]	eta 0:03:13 lr 0.003609	time 0.5873 (0.6642)	model_time 0.5867 (0.5893)	loss 4.0157 (3.5854)	grad_norm 2.0601 (1.3650/0.3807)	mem 24308MB
[2025-01-18 16:00:27 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][30/312]	eta 0:03:00 lr 0.003608	time 0.5937 (0.6403)	model_time 0.5935 (0.5894)	loss 3.4653 (3.6250)	grad_norm 1.4540 (1.4980/0.5872)	mem 24308MB
[2025-01-18 16:00:33 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][40/312]	eta 0:02:52 lr 0.003608	time 0.6584 (0.6331)	model_time 0.6582 (0.5946)	loss 3.5195 (3.6937)	grad_norm 1.2193 (1.4730/0.5596)	mem 24308MB
[2025-01-18 16:00:39 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][50/312]	eta 0:02:44 lr 0.003608	time 0.5837 (0.6270)	model_time 0.5835 (0.5960)	loss 3.7584 (3.7205)	grad_norm 1.0375 (1.4014/0.5322)	mem 24308MB
[2025-01-18 16:00:45 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][60/312]	eta 0:02:37 lr 0.003607	time 0.5832 (0.6257)	model_time 0.5830 (0.5997)	loss 4.4840 (3.6687)	grad_norm 0.7883 (1.3333/0.5196)	mem 24308MB
[2025-01-18 16:00:52 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][70/312]	eta 0:02:32 lr 0.003607	time 0.6684 (0.6289)	model_time 0.6682 (0.6065)	loss 3.9764 (3.7212)	grad_norm 0.9543 (1.3398/0.5030)	mem 24308MB
[2025-01-18 16:00:58 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][80/312]	eta 0:02:25 lr 0.003606	time 0.5857 (0.6252)	model_time 0.5855 (0.6056)	loss 2.7411 (3.7591)	grad_norm 1.0022 (1.3421/0.5013)	mem 24308MB
[2025-01-18 16:01:04 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][90/312]	eta 0:02:18 lr 0.003606	time 0.6635 (0.6218)	model_time 0.6634 (0.6042)	loss 3.3211 (3.7381)	grad_norm 2.4180 (1.4130/0.5639)	mem 24308MB
[2025-01-18 16:01:10 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][100/312]	eta 0:02:11 lr 0.003606	time 0.5765 (0.6200)	model_time 0.5762 (0.6042)	loss 2.2560 (3.6876)	grad_norm 0.8798 (1.4048/0.5470)	mem 24308MB
[2025-01-18 16:01:16 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][110/312]	eta 0:02:04 lr 0.003605	time 0.5833 (0.6175)	model_time 0.5828 (0.6030)	loss 4.0679 (3.6776)	grad_norm 1.6212 (1.3787/0.5348)	mem 24308MB
[2025-01-18 16:01:22 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][120/312]	eta 0:01:58 lr 0.003605	time 0.5899 (0.6154)	model_time 0.5895 (0.6021)	loss 3.6109 (3.6820)	grad_norm 2.2513 (1.4120/0.5586)	mem 24308MB
[2025-01-18 16:01:28 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][130/312]	eta 0:01:51 lr 0.003604	time 0.5878 (0.6133)	model_time 0.5876 (0.6010)	loss 4.1057 (3.6732)	grad_norm 1.0789 (1.4507/0.5849)	mem 24308MB
[2025-01-18 16:01:33 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][140/312]	eta 0:01:45 lr 0.003604	time 0.6179 (0.6118)	model_time 0.6177 (0.6004)	loss 3.2956 (3.6919)	grad_norm 1.4793 (1.4711/0.5999)	mem 24308MB
[2025-01-18 16:01:39 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][150/312]	eta 0:01:38 lr 0.003604	time 0.5769 (0.6099)	model_time 0.5765 (0.5992)	loss 3.5879 (3.6992)	grad_norm 1.7679 (1.4806/0.5961)	mem 24308MB
[2025-01-18 16:01:45 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][160/312]	eta 0:01:32 lr 0.003603	time 0.6586 (0.6098)	model_time 0.6584 (0.5998)	loss 3.9521 (3.7025)	grad_norm 1.4769 (1.4674/0.5846)	mem 24308MB
[2025-01-18 16:01:51 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][170/312]	eta 0:01:26 lr 0.003603	time 0.5825 (0.6098)	model_time 0.5824 (0.6003)	loss 4.0705 (3.7074)	grad_norm 1.5901 (1.4529/0.5730)	mem 24308MB
[2025-01-18 16:01:58 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][180/312]	eta 0:01:20 lr 0.003602	time 0.6759 (0.6109)	model_time 0.6757 (0.6019)	loss 3.4998 (3.7111)	grad_norm 1.1082 (1.4524/0.5674)	mem 24308MB
[2025-01-18 16:02:04 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][190/312]	eta 0:01:14 lr 0.003602	time 0.6005 (0.6114)	model_time 0.6003 (0.6028)	loss 4.1915 (3.7280)	grad_norm 1.3512 (1.4608/0.5666)	mem 24308MB
[2025-01-18 16:02:10 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][200/312]	eta 0:01:08 lr 0.003602	time 0.5781 (0.6116)	model_time 0.5776 (0.6034)	loss 4.6506 (3.7395)	grad_norm 1.2527 (1.4427/0.5593)	mem 24308MB
[2025-01-18 16:02:16 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][210/312]	eta 0:01:02 lr 0.003601	time 0.5830 (0.6104)	model_time 0.5828 (0.6026)	loss 3.3944 (3.7362)	grad_norm 1.5378 (1.4576/0.5726)	mem 24308MB
[2025-01-18 16:02:22 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][220/312]	eta 0:00:56 lr 0.003601	time 0.5813 (0.6099)	model_time 0.5811 (0.6025)	loss 2.9444 (3.7216)	grad_norm 1.6615 (1.4758/0.5826)	mem 24308MB
[2025-01-18 16:02:28 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][230/312]	eta 0:00:49 lr 0.003600	time 0.5855 (0.6089)	model_time 0.5854 (0.6017)	loss 4.0351 (3.7166)	grad_norm 0.7019 (1.4724/0.5762)	mem 24308MB
[2025-01-18 16:02:34 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][240/312]	eta 0:00:43 lr 0.003600	time 0.5801 (0.6083)	model_time 0.5796 (0.6015)	loss 3.2045 (3.7085)	grad_norm 2.0699 (1.4795/0.5825)	mem 24308MB
[2025-01-18 16:02:40 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][250/312]	eta 0:00:37 lr 0.003600	time 0.6005 (0.6075)	model_time 0.6003 (0.6009)	loss 2.7604 (3.6965)	grad_norm 1.1400 (1.4873/0.5854)	mem 24308MB
[2025-01-18 16:02:46 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][260/312]	eta 0:00:31 lr 0.003599	time 0.5771 (0.6066)	model_time 0.5766 (0.6003)	loss 3.8500 (3.7012)	grad_norm 1.1762 (1.4949/0.5845)	mem 24308MB
[2025-01-18 16:02:51 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][270/312]	eta 0:00:25 lr 0.003599	time 0.5859 (0.6059)	model_time 0.5855 (0.5997)	loss 3.7665 (3.6980)	grad_norm 0.8767 (1.4872/0.5806)	mem 24308MB
[2025-01-18 16:02:57 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][280/312]	eta 0:00:19 lr 0.003598	time 0.5899 (0.6054)	model_time 0.5895 (0.5994)	loss 4.8401 (3.6982)	grad_norm 1.6162 (1.4811/0.5752)	mem 24308MB
[2025-01-18 16:03:04 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][290/312]	eta 0:00:13 lr 0.003598	time 0.5943 (0.6061)	model_time 0.5941 (0.6004)	loss 3.9744 (3.6938)	grad_norm 1.5111 (1.4763/0.5686)	mem 24308MB
[2025-01-18 16:03:10 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][300/312]	eta 0:00:07 lr 0.003598	time 0.6417 (0.6064)	model_time 0.6416 (0.6008)	loss 3.4229 (3.6860)	grad_norm 1.1404 (1.5100/0.6254)	mem 24308MB
[2025-01-18 16:03:16 internimage_s_1k_224] (main.py 510): INFO Train: [61/300][310/312]	eta 0:00:01 lr 0.003597	time 0.5638 (0.6062)	model_time 0.5636 (0.6009)	loss 4.1124 (3.6924)	grad_norm 2.0322 (1.5146/0.6283)	mem 24308MB
[2025-01-18 16:03:16 internimage_s_1k_224] (main.py 519): INFO EPOCH 61 training takes 0:03:09
[2025-01-18 16:03:16 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_61.pth saving......
[2025-01-18 16:03:18 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_61.pth saved !!!
[2025-01-18 16:03:25 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.025 (7.025)	Loss 1.0114 (1.0114)	Acc@1 78.345 (78.345)	Acc@5 94.556 (94.556)	Mem 24308MB
[2025-01-18 16:03:28 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.940)	Loss 1.4074 (1.1746)	Acc@1 68.384 (74.501)	Acc@5 89.941 (92.503)	Mem 24308MB
[2025-01-18 16:03:29 internimage_s_1k_224] (main.py 575): INFO [Epoch:61] * Acc@1 74.558 Acc@5 92.582
[2025-01-18 16:03:29 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 74.6%
[2025-01-18 16:03:29 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 16:03:31 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 16:03:31 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 74.56%
[2025-01-18 16:03:38 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.992 (6.992)	Loss 1.3847 (1.3847)	Acc@1 68.042 (68.042)	Acc@5 88.062 (88.062)	Mem 24308MB
[2025-01-18 16:03:41 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.134 (0.922)	Loss 2.0134 (1.6223)	Acc@1 54.858 (63.139)	Acc@5 79.077 (84.990)	Mem 24308MB
[2025-01-18 16:03:41 internimage_s_1k_224] (main.py 575): INFO [Epoch:61] * Acc@1 63.272 Acc@5 85.229
[2025-01-18 16:03:41 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 63.3%
[2025-01-18 16:03:41 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 16:03:43 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 16:03:43 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 63.27%
[2025-01-18 16:03:45 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][0/312]	eta 0:11:00 lr 0.003597	time 2.1171 (2.1171)	model_time 0.6022 (0.6022)	loss 3.9751 (3.9751)	grad_norm 1.6146 (1.6146/0.0000)	mem 24308MB
[2025-01-18 16:03:52 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][10/312]	eta 0:03:49 lr 0.003597	time 0.5982 (0.7595)	model_time 0.5980 (0.6215)	loss 4.2617 (3.7640)	grad_norm 1.2080 (1.5301/0.3651)	mem 24308MB
[2025-01-18 16:03:57 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][20/312]	eta 0:03:17 lr 0.003596	time 0.6152 (0.6772)	model_time 0.6148 (0.6047)	loss 3.8064 (3.7640)	grad_norm 1.3588 (1.3627/0.3962)	mem 24308MB
[2025-01-18 16:04:04 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][30/312]	eta 0:03:04 lr 0.003596	time 0.5714 (0.6538)	model_time 0.5710 (0.6046)	loss 3.9081 (3.6386)	grad_norm 1.3371 (1.3008/0.3741)	mem 24308MB
[2025-01-18 16:04:10 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][40/312]	eta 0:02:54 lr 0.003596	time 0.5736 (0.6414)	model_time 0.5734 (0.6041)	loss 3.9657 (3.5988)	grad_norm 0.8436 (1.2857/0.3880)	mem 24308MB
[2025-01-18 16:04:15 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][50/312]	eta 0:02:45 lr 0.003595	time 0.5777 (0.6308)	model_time 0.5775 (0.6008)	loss 2.8377 (3.5469)	grad_norm 1.3423 (1.3478/0.4028)	mem 24308MB
[2025-01-18 16:04:21 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][60/312]	eta 0:02:37 lr 0.003595	time 0.5897 (0.6235)	model_time 0.5892 (0.5983)	loss 4.2317 (3.6036)	grad_norm 1.6827 (1.4232/0.4427)	mem 24308MB
[2025-01-18 16:04:27 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][70/312]	eta 0:02:29 lr 0.003594	time 0.5724 (0.6181)	model_time 0.5723 (0.5964)	loss 3.1806 (3.6354)	grad_norm 0.8485 (1.3821/0.4380)	mem 24308MB
[2025-01-18 16:04:33 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][80/312]	eta 0:02:22 lr 0.003594	time 0.5894 (0.6143)	model_time 0.5890 (0.5953)	loss 4.2464 (3.6998)	grad_norm 2.2407 (1.4098/0.4508)	mem 24308MB
[2025-01-18 16:04:39 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][90/312]	eta 0:02:15 lr 0.003594	time 0.5767 (0.6121)	model_time 0.5765 (0.5951)	loss 3.6493 (3.6961)	grad_norm 1.3530 (1.4075/0.4720)	mem 24308MB
[2025-01-18 16:04:45 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][100/312]	eta 0:02:10 lr 0.003593	time 0.5814 (0.6136)	model_time 0.5812 (0.5982)	loss 2.6414 (3.7195)	grad_norm 1.9541 (1.4018/0.4609)	mem 24308MB
[2025-01-18 16:04:51 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][110/312]	eta 0:02:04 lr 0.003593	time 0.5810 (0.6142)	model_time 0.5808 (0.6001)	loss 4.2008 (3.7362)	grad_norm 1.0070 (1.4075/0.4562)	mem 24308MB
[2025-01-18 16:04:58 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][120/312]	eta 0:01:58 lr 0.003592	time 0.6782 (0.6154)	model_time 0.6778 (0.6025)	loss 2.6796 (3.7299)	grad_norm 1.3096 (1.4166/0.4818)	mem 24308MB
[2025-01-18 16:05:04 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][130/312]	eta 0:01:52 lr 0.003592	time 0.5747 (0.6159)	model_time 0.5745 (0.6039)	loss 3.2945 (3.7272)	grad_norm 0.7560 (1.4167/0.4823)	mem 24308MB
[2025-01-18 16:05:10 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][140/312]	eta 0:01:45 lr 0.003591	time 0.5892 (0.6137)	model_time 0.5887 (0.6026)	loss 3.6784 (3.7418)	grad_norm 2.2419 (1.4275/0.4794)	mem 24308MB
[2025-01-18 16:05:16 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][150/312]	eta 0:01:39 lr 0.003591	time 0.5899 (0.6136)	model_time 0.5894 (0.6032)	loss 4.0407 (3.7370)	grad_norm 0.7794 (1.4318/0.4826)	mem 24308MB
[2025-01-18 16:05:22 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][160/312]	eta 0:01:33 lr 0.003591	time 0.5900 (0.6120)	model_time 0.5896 (0.6022)	loss 2.5208 (3.7276)	grad_norm 2.8097 (1.4793/0.5666)	mem 24308MB
[2025-01-18 16:05:28 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][170/312]	eta 0:01:26 lr 0.003590	time 0.5992 (0.6111)	model_time 0.5990 (0.6018)	loss 4.1101 (3.7140)	grad_norm 1.2538 (1.4690/0.5591)	mem 24308MB
[2025-01-18 16:05:34 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][180/312]	eta 0:01:20 lr 0.003590	time 0.5769 (0.6096)	model_time 0.5765 (0.6008)	loss 4.3326 (3.7213)	grad_norm 1.5525 (1.4704/0.5532)	mem 24308MB
[2025-01-18 16:05:39 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][190/312]	eta 0:01:14 lr 0.003589	time 0.5715 (0.6085)	model_time 0.5709 (0.6002)	loss 4.5405 (3.7273)	grad_norm 1.0922 (1.4776/0.5572)	mem 24308MB
[2025-01-18 16:05:45 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][200/312]	eta 0:01:08 lr 0.003589	time 0.5991 (0.6077)	model_time 0.5990 (0.5997)	loss 3.0188 (3.7271)	grad_norm 1.1126 (1.4601/0.5528)	mem 24308MB
[2025-01-18 16:05:51 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][210/312]	eta 0:01:01 lr 0.003589	time 0.5766 (0.6073)	model_time 0.5762 (0.5997)	loss 3.9610 (3.7233)	grad_norm 1.0160 (1.4558/0.5562)	mem 24308MB
[2025-01-18 16:05:58 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][220/312]	eta 0:00:55 lr 0.003588	time 0.5835 (0.6082)	model_time 0.5834 (0.6009)	loss 4.2722 (3.7235)	grad_norm 1.1588 (1.4403/0.5546)	mem 24308MB
[2025-01-18 16:06:04 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][230/312]	eta 0:00:49 lr 0.003588	time 0.5762 (0.6089)	model_time 0.5757 (0.6019)	loss 4.1279 (3.7314)	grad_norm 0.9545 (1.4627/0.5899)	mem 24308MB
[2025-01-18 16:06:10 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][240/312]	eta 0:00:43 lr 0.003587	time 0.5902 (0.6095)	model_time 0.5900 (0.6028)	loss 2.4134 (3.7263)	grad_norm 1.3120 (1.4555/0.5834)	mem 24308MB
[2025-01-18 16:06:16 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][250/312]	eta 0:00:37 lr 0.003587	time 0.6640 (0.6106)	model_time 0.6639 (0.6041)	loss 3.7568 (3.7298)	grad_norm 2.2173 (1.4485/0.5784)	mem 24308MB
[2025-01-18 16:06:22 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][260/312]	eta 0:00:31 lr 0.003587	time 0.5841 (0.6096)	model_time 0.5840 (0.6034)	loss 3.8676 (3.7273)	grad_norm 1.6284 (1.4443/0.5704)	mem 24308MB
[2025-01-18 16:06:29 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][270/312]	eta 0:00:25 lr 0.003586	time 0.6569 (0.6105)	model_time 0.6567 (0.6045)	loss 3.8022 (3.7284)	grad_norm 0.9331 (1.4565/0.5793)	mem 24308MB
[2025-01-18 16:06:35 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][280/312]	eta 0:00:19 lr 0.003586	time 0.5767 (0.6095)	model_time 0.5765 (0.6037)	loss 4.5088 (3.7294)	grad_norm 1.0570 (1.4655/0.5807)	mem 24308MB
[2025-01-18 16:06:40 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][290/312]	eta 0:00:13 lr 0.003585	time 0.5896 (0.6088)	model_time 0.5891 (0.6032)	loss 4.1103 (3.7307)	grad_norm 1.1558 (1.4631/0.5795)	mem 24308MB
[2025-01-18 16:06:46 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][300/312]	eta 0:00:07 lr 0.003585	time 0.5675 (0.6079)	model_time 0.5674 (0.6025)	loss 3.4496 (3.7228)	grad_norm 1.2161 (1.4670/0.5817)	mem 24308MB
[2025-01-18 16:06:52 internimage_s_1k_224] (main.py 510): INFO Train: [62/300][310/312]	eta 0:00:01 lr 0.003585	time 0.5668 (0.6066)	model_time 0.5667 (0.6013)	loss 4.5289 (3.7158)	grad_norm 0.8139 (1.4695/0.5888)	mem 24308MB
[2025-01-18 16:06:52 internimage_s_1k_224] (main.py 519): INFO EPOCH 62 training takes 0:03:09
[2025-01-18 16:06:52 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_62.pth saving......
[2025-01-18 16:06:54 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_62.pth saved !!!
[2025-01-18 16:07:01 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.139 (7.139)	Loss 0.9756 (0.9756)	Acc@1 78.687 (78.687)	Acc@5 95.044 (95.044)	Mem 24308MB
[2025-01-18 16:07:05 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.136 (0.940)	Loss 1.3852 (1.1699)	Acc@1 68.945 (74.485)	Acc@5 89.746 (92.571)	Mem 24308MB
[2025-01-18 16:07:05 internimage_s_1k_224] (main.py 575): INFO [Epoch:62] * Acc@1 74.574 Acc@5 92.700
[2025-01-18 16:07:05 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 74.6%
[2025-01-18 16:07:05 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 16:07:07 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 16:07:07 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 74.57%
[2025-01-18 16:07:14 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.046 (7.046)	Loss 1.3432 (1.3432)	Acc@1 68.652 (68.652)	Acc@5 88.452 (88.452)	Mem 24308MB
[2025-01-18 16:07:17 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.918)	Loss 1.9653 (1.5786)	Acc@1 55.640 (64.005)	Acc@5 79.761 (85.565)	Mem 24308MB
[2025-01-18 16:07:17 internimage_s_1k_224] (main.py 575): INFO [Epoch:62] * Acc@1 64.115 Acc@5 85.789
[2025-01-18 16:07:17 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 64.1%
[2025-01-18 16:07:17 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 16:07:19 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 16:07:19 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 64.12%
[2025-01-18 16:07:21 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][0/312]	eta 0:10:58 lr 0.003585	time 2.1115 (2.1115)	model_time 0.6241 (0.6241)	loss 2.8638 (2.8638)	grad_norm 0.9222 (0.9222/0.0000)	mem 24308MB
[2025-01-18 16:07:27 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][10/312]	eta 0:03:38 lr 0.003584	time 0.5960 (0.7251)	model_time 0.5958 (0.5896)	loss 4.0913 (3.5295)	grad_norm 0.8854 (1.4834/0.5859)	mem 24308MB
[2025-01-18 16:07:33 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][20/312]	eta 0:03:15 lr 0.003584	time 0.6620 (0.6679)	model_time 0.6618 (0.5968)	loss 2.6518 (3.5898)	grad_norm 1.3425 (1.4193/0.4884)	mem 24308MB
[2025-01-18 16:07:40 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][30/312]	eta 0:03:03 lr 0.003583	time 0.5678 (0.6517)	model_time 0.5677 (0.6034)	loss 2.5048 (3.6087)	grad_norm 1.2314 (1.4406/0.4976)	mem 24308MB
[2025-01-18 16:07:46 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][40/312]	eta 0:02:55 lr 0.003583	time 0.5786 (0.6445)	model_time 0.5785 (0.6079)	loss 4.1346 (3.6382)	grad_norm 1.4849 (1.3721/0.4909)	mem 24308MB
[2025-01-18 16:07:52 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][50/312]	eta 0:02:48 lr 0.003582	time 0.6334 (0.6414)	model_time 0.6332 (0.6119)	loss 3.7743 (3.6682)	grad_norm 2.2115 (1.4918/0.5423)	mem 24308MB
[2025-01-18 16:07:58 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][60/312]	eta 0:02:41 lr 0.003582	time 0.6036 (0.6399)	model_time 0.6031 (0.6152)	loss 3.6243 (3.5973)	grad_norm 1.2077 (1.4860/0.5355)	mem 24308MB
[2025-01-18 16:08:04 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][70/312]	eta 0:02:33 lr 0.003582	time 0.5752 (0.6329)	model_time 0.5750 (0.6116)	loss 3.3748 (3.6372)	grad_norm 4.3394 (1.5310/0.6475)	mem 24308MB
[2025-01-18 16:08:10 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][80/312]	eta 0:02:26 lr 0.003581	time 0.5832 (0.6299)	model_time 0.5830 (0.6112)	loss 3.1265 (3.6500)	grad_norm 1.5232 (1.5985/0.7175)	mem 24308MB
[2025-01-18 16:08:16 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][90/312]	eta 0:02:19 lr 0.003581	time 0.5917 (0.6282)	model_time 0.5915 (0.6115)	loss 3.6722 (3.6556)	grad_norm 1.1453 (1.6075/0.7114)	mem 24308MB
[2025-01-18 16:08:22 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][100/312]	eta 0:02:12 lr 0.003580	time 0.6078 (0.6246)	model_time 0.6074 (0.6095)	loss 2.5851 (3.6475)	grad_norm 0.7327 (1.5520/0.6998)	mem 24308MB
[2025-01-18 16:08:28 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][110/312]	eta 0:02:05 lr 0.003580	time 0.5770 (0.6210)	model_time 0.5768 (0.6073)	loss 3.8859 (3.6706)	grad_norm 0.9346 (1.5165/0.6858)	mem 24308MB
[2025-01-18 16:08:34 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][120/312]	eta 0:01:58 lr 0.003580	time 0.5832 (0.6183)	model_time 0.5830 (0.6057)	loss 3.5333 (3.6516)	grad_norm 1.4977 (1.5067/0.6683)	mem 24308MB
[2025-01-18 16:08:40 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][130/312]	eta 0:01:52 lr 0.003579	time 0.5817 (0.6162)	model_time 0.5815 (0.6045)	loss 4.4898 (3.6455)	grad_norm 1.4954 (1.5380/0.6697)	mem 24308MB
[2025-01-18 16:08:46 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][140/312]	eta 0:01:45 lr 0.003579	time 0.6200 (0.6152)	model_time 0.6198 (0.6043)	loss 2.5892 (3.6297)	grad_norm 1.0234 (1.5245/0.6511)	mem 24308MB
[2025-01-18 16:08:52 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][150/312]	eta 0:01:39 lr 0.003578	time 0.5909 (0.6145)	model_time 0.5908 (0.6043)	loss 2.8610 (3.6277)	grad_norm 0.9077 (1.5201/0.6405)	mem 24308MB
[2025-01-18 16:08:58 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][160/312]	eta 0:01:33 lr 0.003578	time 0.5826 (0.6157)	model_time 0.5824 (0.6061)	loss 3.8271 (3.6172)	grad_norm 0.8127 (1.4924/0.6360)	mem 24308MB
[2025-01-18 16:09:05 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][170/312]	eta 0:01:27 lr 0.003578	time 0.6843 (0.6161)	model_time 0.6841 (0.6071)	loss 3.9171 (3.6094)	grad_norm 2.2602 (1.4899/0.6319)	mem 24308MB
[2025-01-18 16:09:11 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][180/312]	eta 0:01:21 lr 0.003577	time 0.5941 (0.6168)	model_time 0.5939 (0.6082)	loss 4.2417 (3.6176)	grad_norm 0.9608 (1.4764/0.6232)	mem 24308MB
[2025-01-18 16:09:17 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][190/312]	eta 0:01:15 lr 0.003577	time 0.5867 (0.6158)	model_time 0.5865 (0.6077)	loss 2.5952 (3.6168)	grad_norm 2.7178 (1.4786/0.6295)	mem 24308MB
[2025-01-18 16:09:23 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][200/312]	eta 0:01:08 lr 0.003576	time 0.5693 (0.6157)	model_time 0.5691 (0.6079)	loss 4.0436 (3.6130)	grad_norm 1.7201 (1.5000/0.6417)	mem 24308MB
[2025-01-18 16:09:29 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][210/312]	eta 0:01:02 lr 0.003576	time 0.5909 (0.6147)	model_time 0.5907 (0.6074)	loss 3.4176 (3.6246)	grad_norm 1.2868 (1.5135/0.6497)	mem 24308MB
[2025-01-18 16:09:35 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][220/312]	eta 0:00:56 lr 0.003576	time 0.5743 (0.6136)	model_time 0.5741 (0.6066)	loss 2.7919 (3.6207)	grad_norm 0.8700 (1.5145/0.6462)	mem 24308MB
[2025-01-18 16:09:41 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][230/312]	eta 0:00:50 lr 0.003575	time 0.5813 (0.6126)	model_time 0.5811 (0.6058)	loss 3.9584 (3.6339)	grad_norm 1.9938 (1.5117/0.6386)	mem 24308MB
[2025-01-18 16:09:47 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][240/312]	eta 0:00:44 lr 0.003575	time 0.5887 (0.6117)	model_time 0.5885 (0.6052)	loss 3.9058 (3.6416)	grad_norm 1.9331 (1.5243/0.6329)	mem 24308MB
[2025-01-18 16:09:53 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][250/312]	eta 0:00:37 lr 0.003574	time 0.5858 (0.6108)	model_time 0.5856 (0.6045)	loss 3.9439 (3.6397)	grad_norm 0.9509 (1.5141/0.6238)	mem 24308MB
[2025-01-18 16:09:59 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][260/312]	eta 0:00:31 lr 0.003574	time 0.6615 (0.6105)	model_time 0.6613 (0.6045)	loss 4.3251 (3.6447)	grad_norm 1.4321 (1.5056/0.6172)	mem 24308MB
[2025-01-18 16:10:05 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][270/312]	eta 0:00:25 lr 0.003573	time 0.5881 (0.6107)	model_time 0.5879 (0.6049)	loss 3.3997 (3.6481)	grad_norm 1.8730 (1.4950/0.6116)	mem 24308MB
[2025-01-18 16:10:11 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][280/312]	eta 0:00:19 lr 0.003573	time 0.5910 (0.6114)	model_time 0.5908 (0.6058)	loss 4.4732 (3.6545)	grad_norm 1.1765 (1.4968/0.6096)	mem 24308MB
[2025-01-18 16:10:17 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][290/312]	eta 0:00:13 lr 0.003573	time 0.5720 (0.6115)	model_time 0.5718 (0.6061)	loss 3.4265 (3.6478)	grad_norm 1.2842 (1.5240/0.6612)	mem 24308MB
[2025-01-18 16:10:24 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][300/312]	eta 0:00:07 lr 0.003572	time 0.6503 (0.6121)	model_time 0.6502 (0.6068)	loss 3.9452 (3.6523)	grad_norm 1.1783 (1.5242/0.6545)	mem 24308MB
[2025-01-18 16:10:30 internimage_s_1k_224] (main.py 510): INFO Train: [63/300][310/312]	eta 0:00:01 lr 0.003572	time 0.5684 (0.6116)	model_time 0.5683 (0.6065)	loss 3.8294 (3.6528)	grad_norm 0.7410 (1.5087/0.6520)	mem 24308MB
[2025-01-18 16:10:30 internimage_s_1k_224] (main.py 519): INFO EPOCH 63 training takes 0:03:10
[2025-01-18 16:10:30 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_63.pth saving......
[2025-01-18 16:10:32 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_63.pth saved !!!
[2025-01-18 16:10:39 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.920 (6.920)	Loss 0.9132 (0.9132)	Acc@1 78.833 (78.833)	Acc@5 95.142 (95.142)	Mem 24308MB
[2025-01-18 16:10:42 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.908)	Loss 1.3794 (1.1306)	Acc@1 69.653 (74.723)	Acc@5 89.868 (92.858)	Mem 24308MB
[2025-01-18 16:10:42 internimage_s_1k_224] (main.py 575): INFO [Epoch:63] * Acc@1 74.746 Acc@5 92.942
[2025-01-18 16:10:42 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 74.7%
[2025-01-18 16:10:42 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 16:10:44 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 16:10:44 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 74.75%
[2025-01-18 16:10:51 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.953 (6.953)	Loss 1.3056 (1.3056)	Acc@1 69.336 (69.336)	Acc@5 88.989 (88.989)	Mem 24308MB
[2025-01-18 16:10:55 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.940)	Loss 1.9211 (1.5385)	Acc@1 56.543 (64.766)	Acc@5 80.566 (86.135)	Mem 24308MB
[2025-01-18 16:10:55 internimage_s_1k_224] (main.py 575): INFO [Epoch:63] * Acc@1 64.871 Acc@5 86.356
[2025-01-18 16:10:55 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 64.9%
[2025-01-18 16:10:55 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 16:10:57 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 16:10:57 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 64.87%
[2025-01-18 16:10:59 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][0/312]	eta 0:12:11 lr 0.003572	time 2.3453 (2.3453)	model_time 0.5889 (0.5889)	loss 3.4874 (3.4874)	grad_norm 0.9964 (0.9964/0.0000)	mem 24308MB
[2025-01-18 16:11:05 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][10/312]	eta 0:03:50 lr 0.003571	time 0.5963 (0.7643)	model_time 0.5961 (0.6044)	loss 4.3683 (3.6124)	grad_norm 1.0160 (1.2168/0.2730)	mem 24308MB
[2025-01-18 16:11:11 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][20/312]	eta 0:03:18 lr 0.003571	time 0.5885 (0.6797)	model_time 0.5883 (0.5958)	loss 3.8657 (3.5597)	grad_norm 1.1686 (1.2753/0.2993)	mem 24308MB
[2025-01-18 16:11:17 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][30/312]	eta 0:03:03 lr 0.003570	time 0.5723 (0.6524)	model_time 0.5717 (0.5954)	loss 3.2845 (3.5629)	grad_norm 0.8247 (1.2703/0.3265)	mem 24308MB
[2025-01-18 16:11:23 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][40/312]	eta 0:02:53 lr 0.003570	time 0.5815 (0.6360)	model_time 0.5814 (0.5929)	loss 2.3288 (3.5521)	grad_norm 1.1872 (1.2853/0.3296)	mem 24308MB
[2025-01-18 16:11:29 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][50/312]	eta 0:02:44 lr 0.003570	time 0.5785 (0.6265)	model_time 0.5784 (0.5918)	loss 3.9395 (3.6157)	grad_norm 1.9193 (1.3213/0.4170)	mem 24308MB
[2025-01-18 16:11:35 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][60/312]	eta 0:02:36 lr 0.003569	time 0.5888 (0.6210)	model_time 0.5887 (0.5917)	loss 4.3247 (3.6004)	grad_norm 1.8074 (1.4068/0.5334)	mem 24308MB
[2025-01-18 16:11:41 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][70/312]	eta 0:02:29 lr 0.003569	time 0.5881 (0.6175)	model_time 0.5879 (0.5923)	loss 3.9931 (3.6626)	grad_norm 1.1687 (1.4128/0.5323)	mem 24308MB
[2025-01-18 16:11:47 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][80/312]	eta 0:02:23 lr 0.003568	time 0.5748 (0.6181)	model_time 0.5743 (0.5960)	loss 3.9640 (3.6760)	grad_norm 2.0541 (1.4298/0.5297)	mem 24308MB
[2025-01-18 16:11:53 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][90/312]	eta 0:02:17 lr 0.003568	time 0.6629 (0.6206)	model_time 0.6628 (0.6009)	loss 3.8705 (3.6625)	grad_norm 0.9133 (1.3927/0.5132)	mem 24308MB
[2025-01-18 16:12:00 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][100/312]	eta 0:02:11 lr 0.003568	time 0.6725 (0.6214)	model_time 0.6723 (0.6036)	loss 4.1146 (3.6792)	grad_norm 1.1139 (1.3876/0.5001)	mem 24308MB
[2025-01-18 16:12:06 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][110/312]	eta 0:02:05 lr 0.003567	time 0.6778 (0.6215)	model_time 0.6773 (0.6053)	loss 3.9533 (3.7007)	grad_norm 1.0165 (1.3855/0.4944)	mem 24308MB
[2025-01-18 16:12:12 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][120/312]	eta 0:01:59 lr 0.003567	time 0.6049 (0.6208)	model_time 0.6047 (0.6059)	loss 2.5494 (3.6894)	grad_norm 0.9623 (1.3806/0.4929)	mem 24308MB
[2025-01-18 16:12:18 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][130/312]	eta 0:01:52 lr 0.003566	time 0.5786 (0.6196)	model_time 0.5784 (0.6058)	loss 4.2229 (3.7128)	grad_norm 1.9586 (1.3869/0.5061)	mem 24308MB
[2025-01-18 16:12:24 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][140/312]	eta 0:01:46 lr 0.003566	time 0.5892 (0.6177)	model_time 0.5887 (0.6049)	loss 3.0978 (3.7020)	grad_norm 2.2518 (1.3923/0.5080)	mem 24308MB
[2025-01-18 16:12:30 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][150/312]	eta 0:01:39 lr 0.003566	time 0.5735 (0.6165)	model_time 0.5731 (0.6045)	loss 2.4725 (3.6832)	grad_norm 1.4786 (1.4056/0.5113)	mem 24308MB
[2025-01-18 16:12:36 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][160/312]	eta 0:01:33 lr 0.003565	time 0.5797 (0.6146)	model_time 0.5795 (0.6034)	loss 2.7252 (3.6754)	grad_norm 1.3764 (1.3915/0.5021)	mem 24308MB
[2025-01-18 16:12:42 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][170/312]	eta 0:01:27 lr 0.003565	time 0.5848 (0.6129)	model_time 0.5843 (0.6023)	loss 4.1434 (3.6711)	grad_norm 3.1222 (1.4067/0.5128)	mem 24308MB
[2025-01-18 16:12:47 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][180/312]	eta 0:01:20 lr 0.003564	time 0.5751 (0.6113)	model_time 0.5746 (0.6013)	loss 4.1437 (3.6697)	grad_norm 1.2492 (1.4316/0.5410)	mem 24308MB
[2025-01-18 16:12:53 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][190/312]	eta 0:01:14 lr 0.003564	time 0.5829 (0.6104)	model_time 0.5827 (0.6009)	loss 3.2008 (3.6680)	grad_norm 3.2120 (1.4563/0.5911)	mem 24308MB
[2025-01-18 16:13:00 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][200/312]	eta 0:01:08 lr 0.003563	time 0.6678 (0.6113)	model_time 0.6677 (0.6022)	loss 2.3673 (3.6607)	grad_norm 0.7683 (1.4456/0.5853)	mem 24308MB
[2025-01-18 16:13:06 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][210/312]	eta 0:01:02 lr 0.003563	time 0.5942 (0.6123)	model_time 0.5938 (0.6036)	loss 2.3342 (3.6570)	grad_norm 0.8403 (1.4390/0.5765)	mem 24308MB
[2025-01-18 16:13:12 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][220/312]	eta 0:00:56 lr 0.003563	time 0.6627 (0.6131)	model_time 0.6625 (0.6048)	loss 3.7591 (3.6473)	grad_norm 1.2779 (1.4280/0.5688)	mem 24308MB
[2025-01-18 16:13:19 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][230/312]	eta 0:00:50 lr 0.003562	time 0.6626 (0.6138)	model_time 0.6622 (0.6059)	loss 4.0853 (3.6502)	grad_norm 1.5145 (1.4405/0.5657)	mem 24308MB
[2025-01-18 16:13:25 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][240/312]	eta 0:00:44 lr 0.003562	time 0.5722 (0.6137)	model_time 0.5720 (0.6061)	loss 4.0264 (3.6468)	grad_norm 1.4057 (1.4503/0.5689)	mem 24308MB
[2025-01-18 16:13:31 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][250/312]	eta 0:00:37 lr 0.003561	time 0.5807 (0.6128)	model_time 0.5806 (0.6055)	loss 3.4332 (3.6443)	grad_norm 1.0701 (1.4380/0.5642)	mem 24308MB
[2025-01-18 16:13:37 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][260/312]	eta 0:00:31 lr 0.003561	time 0.5778 (0.6126)	model_time 0.5773 (0.6056)	loss 4.1016 (3.6483)	grad_norm 1.1430 (1.4416/0.5664)	mem 24308MB
[2025-01-18 16:13:43 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][270/312]	eta 0:00:25 lr 0.003561	time 0.5720 (0.6121)	model_time 0.5719 (0.6053)	loss 4.2648 (3.6472)	grad_norm 1.1911 (1.4427/0.5586)	mem 24308MB
[2025-01-18 16:13:49 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][280/312]	eta 0:00:19 lr 0.003560	time 0.5854 (0.6112)	model_time 0.5852 (0.6046)	loss 2.5838 (3.6490)	grad_norm 1.0312 (1.4453/0.5587)	mem 24308MB
[2025-01-18 16:13:54 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][290/312]	eta 0:00:13 lr 0.003560	time 0.5920 (0.6103)	model_time 0.5919 (0.6039)	loss 4.6829 (3.6421)	grad_norm 1.6360 (1.4408/0.5512)	mem 24308MB
[2025-01-18 16:14:00 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][300/312]	eta 0:00:07 lr 0.003559	time 0.5674 (0.6093)	model_time 0.5673 (0.6031)	loss 3.5180 (3.6383)	grad_norm 1.6169 (1.4529/0.5547)	mem 24308MB
[2025-01-18 16:14:06 internimage_s_1k_224] (main.py 510): INFO Train: [64/300][310/312]	eta 0:00:01 lr 0.003559	time 0.5678 (0.6082)	model_time 0.5677 (0.6022)	loss 3.9791 (3.6406)	grad_norm 1.8159 (1.4760/0.5672)	mem 24308MB
[2025-01-18 16:14:07 internimage_s_1k_224] (main.py 519): INFO EPOCH 64 training takes 0:03:09
[2025-01-18 16:14:07 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_64.pth saving......
[2025-01-18 16:14:08 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_64.pth saved !!!
[2025-01-18 16:14:15 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.035 (7.035)	Loss 0.9705 (0.9705)	Acc@1 78.516 (78.516)	Acc@5 95.630 (95.630)	Mem 24308MB
[2025-01-18 16:14:19 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.930)	Loss 1.4287 (1.1761)	Acc@1 69.458 (74.603)	Acc@5 89.746 (92.813)	Mem 24308MB
[2025-01-18 16:14:19 internimage_s_1k_224] (main.py 575): INFO [Epoch:64] * Acc@1 74.646 Acc@5 92.924
[2025-01-18 16:14:19 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 74.6%
[2025-01-18 16:14:19 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 74.75%
[2025-01-18 16:14:27 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.229 (8.229)	Loss 1.2708 (1.2708)	Acc@1 70.117 (70.117)	Acc@5 89.575 (89.575)	Mem 24308MB
[2025-01-18 16:14:31 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.110)	Loss 1.8790 (1.5013)	Acc@1 57.275 (65.547)	Acc@5 81.201 (86.614)	Mem 24308MB
[2025-01-18 16:14:31 internimage_s_1k_224] (main.py 575): INFO [Epoch:64] * Acc@1 65.623 Acc@5 86.810
[2025-01-18 16:14:31 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 65.6%
[2025-01-18 16:14:31 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 16:14:33 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 16:14:33 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 65.62%
[2025-01-18 16:14:36 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][0/312]	eta 0:11:14 lr 0.003559	time 2.1627 (2.1627)	model_time 0.5926 (0.5926)	loss 4.2996 (4.2996)	grad_norm 1.0570 (1.0570/0.0000)	mem 24308MB
[2025-01-18 16:14:42 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][10/312]	eta 0:03:49 lr 0.003558	time 0.5929 (0.7606)	model_time 0.5927 (0.6176)	loss 3.5202 (3.8733)	grad_norm 1.2618 (1.2660/0.2308)	mem 24308MB
[2025-01-18 16:14:48 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][20/312]	eta 0:03:23 lr 0.003558	time 0.5825 (0.6982)	model_time 0.5823 (0.6231)	loss 2.4795 (3.7889)	grad_norm 2.3973 (1.4046/0.5205)	mem 24308MB
[2025-01-18 16:14:54 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][30/312]	eta 0:03:09 lr 0.003557	time 0.5903 (0.6708)	model_time 0.5899 (0.6199)	loss 4.0513 (3.6902)	grad_norm 1.2204 (1.4279/0.4933)	mem 24308MB
[2025-01-18 16:15:01 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][40/312]	eta 0:02:59 lr 0.003557	time 0.5717 (0.6588)	model_time 0.5716 (0.6201)	loss 3.8180 (3.6675)	grad_norm 1.5899 (1.3659/0.4836)	mem 24308MB
[2025-01-18 16:15:07 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][50/312]	eta 0:02:50 lr 0.003557	time 0.5929 (0.6515)	model_time 0.5928 (0.6203)	loss 3.6032 (3.6589)	grad_norm 2.0146 (1.3921/0.4957)	mem 24308MB
[2025-01-18 16:15:13 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][60/312]	eta 0:02:42 lr 0.003556	time 0.5848 (0.6431)	model_time 0.5844 (0.6170)	loss 4.5889 (3.7096)	grad_norm 0.9669 (1.3482/0.4743)	mem 24308MB
[2025-01-18 16:15:19 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][70/312]	eta 0:02:34 lr 0.003556	time 0.5773 (0.6377)	model_time 0.5769 (0.6152)	loss 3.3508 (3.6509)	grad_norm 1.6683 (1.3820/0.5360)	mem 24308MB
[2025-01-18 16:15:25 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][80/312]	eta 0:02:26 lr 0.003555	time 0.5786 (0.6312)	model_time 0.5784 (0.6115)	loss 3.3939 (3.6192)	grad_norm 1.0065 (1.4185/0.5518)	mem 24308MB
[2025-01-18 16:15:30 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][90/312]	eta 0:02:19 lr 0.003555	time 0.5761 (0.6262)	model_time 0.5757 (0.6084)	loss 3.8567 (3.6445)	grad_norm 1.2844 (1.3999/0.5324)	mem 24308MB
[2025-01-18 16:15:36 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][100/312]	eta 0:02:11 lr 0.003555	time 0.5838 (0.6224)	model_time 0.5836 (0.6063)	loss 3.8244 (3.6526)	grad_norm 0.7679 (1.4035/0.5400)	mem 24308MB
[2025-01-18 16:15:42 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][110/312]	eta 0:02:05 lr 0.003554	time 0.5717 (0.6195)	model_time 0.5713 (0.6048)	loss 4.1185 (3.6597)	grad_norm 3.0868 (1.4620/0.5977)	mem 24308MB
[2025-01-18 16:15:48 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][120/312]	eta 0:01:58 lr 0.003554	time 0.5776 (0.6171)	model_time 0.5775 (0.6036)	loss 3.0034 (3.6587)	grad_norm 1.2010 (1.4691/0.5958)	mem 24308MB
[2025-01-18 16:15:54 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][130/312]	eta 0:01:52 lr 0.003553	time 0.7998 (0.6175)	model_time 0.7993 (0.6049)	loss 4.4471 (3.6396)	grad_norm 1.1485 (1.4458/0.5800)	mem 24308MB
[2025-01-18 16:16:01 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][140/312]	eta 0:01:46 lr 0.003553	time 0.6506 (0.6192)	model_time 0.6504 (0.6076)	loss 3.7899 (3.6510)	grad_norm 1.0618 (1.4323/0.5681)	mem 24308MB
[2025-01-18 16:16:07 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][150/312]	eta 0:01:40 lr 0.003552	time 0.6545 (0.6190)	model_time 0.6543 (0.6081)	loss 2.8712 (3.6632)	grad_norm 1.9763 (1.4330/0.5592)	mem 24308MB
[2025-01-18 16:16:13 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][160/312]	eta 0:01:34 lr 0.003552	time 0.5996 (0.6196)	model_time 0.5994 (0.6093)	loss 3.0975 (3.6507)	grad_norm 1.4946 (1.4160/0.5497)	mem 24308MB
[2025-01-18 16:16:19 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][170/312]	eta 0:01:27 lr 0.003552	time 0.5865 (0.6190)	model_time 0.5863 (0.6094)	loss 3.5376 (3.6440)	grad_norm 1.5330 (1.4186/0.5491)	mem 24308MB
[2025-01-18 16:16:25 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][180/312]	eta 0:01:21 lr 0.003551	time 0.5845 (0.6180)	model_time 0.5844 (0.6088)	loss 3.8739 (3.6523)	grad_norm 1.4857 (1.4199/0.5480)	mem 24308MB
[2025-01-18 16:16:31 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][190/312]	eta 0:01:15 lr 0.003551	time 0.5921 (0.6172)	model_time 0.5916 (0.6085)	loss 3.6325 (3.6560)	grad_norm 0.9273 (1.4123/0.5390)	mem 24308MB
[2025-01-18 16:16:37 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][200/312]	eta 0:01:08 lr 0.003550	time 0.5934 (0.6157)	model_time 0.5932 (0.6074)	loss 4.1282 (3.6649)	grad_norm 1.4552 (1.3887/0.5375)	mem 24308MB
[2025-01-18 16:16:43 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][210/312]	eta 0:01:02 lr 0.003550	time 0.5879 (0.6145)	model_time 0.5874 (0.6066)	loss 4.3693 (3.6684)	grad_norm 1.1237 (1.3869/0.5322)	mem 24308MB
[2025-01-18 16:16:49 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][220/312]	eta 0:00:56 lr 0.003550	time 0.5848 (0.6134)	model_time 0.5846 (0.6058)	loss 2.7929 (3.6594)	grad_norm 0.8168 (1.3895/0.5386)	mem 24308MB
[2025-01-18 16:16:55 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][230/312]	eta 0:00:50 lr 0.003549	time 0.5881 (0.6122)	model_time 0.5879 (0.6049)	loss 3.8061 (3.6638)	grad_norm 0.7597 (1.3925/0.5569)	mem 24308MB
[2025-01-18 16:17:01 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][240/312]	eta 0:00:43 lr 0.003549	time 0.5743 (0.6110)	model_time 0.5742 (0.6040)	loss 3.6389 (3.6671)	grad_norm 1.1871 (1.4144/0.5818)	mem 24308MB
[2025-01-18 16:17:07 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][250/312]	eta 0:00:37 lr 0.003548	time 0.5832 (0.6114)	model_time 0.5831 (0.6047)	loss 3.8982 (3.6648)	grad_norm 0.7376 (1.4070/0.5763)	mem 24308MB
[2025-01-18 16:17:13 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][260/312]	eta 0:00:31 lr 0.003548	time 0.5810 (0.6122)	model_time 0.5809 (0.6057)	loss 3.8716 (3.6781)	grad_norm 1.2288 (1.4088/0.5782)	mem 24308MB
[2025-01-18 16:17:20 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][270/312]	eta 0:00:25 lr 0.003547	time 0.5788 (0.6127)	model_time 0.5787 (0.6065)	loss 4.1446 (3.6775)	grad_norm 1.9666 (1.4157/0.5781)	mem 24308MB
[2025-01-18 16:17:26 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][280/312]	eta 0:00:19 lr 0.003547	time 0.5869 (0.6134)	model_time 0.5867 (0.6073)	loss 3.7961 (3.6723)	grad_norm 1.4048 (1.4164/0.5736)	mem 24308MB
[2025-01-18 16:17:32 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][290/312]	eta 0:00:13 lr 0.003547	time 0.5716 (0.6134)	model_time 0.5711 (0.6076)	loss 4.0665 (3.6807)	grad_norm 0.9546 (1.4309/0.5854)	mem 24308MB
[2025-01-18 16:17:38 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][300/312]	eta 0:00:07 lr 0.003546	time 0.5700 (0.6127)	model_time 0.5699 (0.6070)	loss 3.9127 (3.6811)	grad_norm 1.2998 (1.4457/0.5999)	mem 24308MB
[2025-01-18 16:17:44 internimage_s_1k_224] (main.py 510): INFO Train: [65/300][310/312]	eta 0:00:01 lr 0.003546	time 0.5675 (0.6117)	model_time 0.5674 (0.6062)	loss 3.6855 (3.6921)	grad_norm 6.0890 (1.4671/0.6669)	mem 24308MB
[2025-01-18 16:17:44 internimage_s_1k_224] (main.py 519): INFO EPOCH 65 training takes 0:03:10
[2025-01-18 16:17:44 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_65.pth saving......
[2025-01-18 16:17:46 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_65.pth saved !!!
[2025-01-18 16:17:53 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.269 (7.269)	Loss 1.0087 (1.0087)	Acc@1 78.784 (78.784)	Acc@5 94.775 (94.775)	Mem 24308MB
[2025-01-18 16:17:57 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.951)	Loss 1.4153 (1.1754)	Acc@1 68.726 (74.814)	Acc@5 89.722 (92.747)	Mem 24308MB
[2025-01-18 16:17:57 internimage_s_1k_224] (main.py 575): INFO [Epoch:65] * Acc@1 74.796 Acc@5 92.804
[2025-01-18 16:17:57 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 74.8%
[2025-01-18 16:17:57 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 16:17:59 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 16:17:59 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 74.80%
[2025-01-18 16:18:06 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.040 (7.040)	Loss 1.2388 (1.2388)	Acc@1 70.825 (70.825)	Acc@5 90.137 (90.137)	Mem 24308MB
[2025-01-18 16:18:09 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.946)	Loss 1.8400 (1.4663)	Acc@1 58.154 (66.224)	Acc@5 81.665 (87.094)	Mem 24308MB
[2025-01-18 16:18:09 internimage_s_1k_224] (main.py 575): INFO [Epoch:65] * Acc@1 66.305 Acc@5 87.276
[2025-01-18 16:18:09 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 66.3%
[2025-01-18 16:18:09 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 16:18:11 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 16:18:11 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 66.30%
[2025-01-18 16:18:13 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][0/312]	eta 0:10:31 lr 0.003546	time 2.0244 (2.0244)	model_time 0.5979 (0.5979)	loss 3.9235 (3.9235)	grad_norm 4.1873 (4.1873/0.0000)	mem 24308MB
[2025-01-18 16:18:19 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][10/312]	eta 0:03:37 lr 0.003545	time 0.6134 (0.7188)	model_time 0.6132 (0.5889)	loss 4.4658 (3.8798)	grad_norm 0.8584 (1.4242/1.0122)	mem 24308MB
[2025-01-18 16:18:25 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][20/312]	eta 0:03:11 lr 0.003545	time 0.5804 (0.6575)	model_time 0.5803 (0.5892)	loss 4.3080 (3.8754)	grad_norm 1.1029 (1.4960/0.8803)	mem 24308MB
[2025-01-18 16:18:31 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][30/312]	eta 0:02:58 lr 0.003544	time 0.5807 (0.6339)	model_time 0.5803 (0.5876)	loss 3.9236 (3.8302)	grad_norm 1.5651 (1.4720/0.7636)	mem 24308MB
[2025-01-18 16:18:37 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][40/312]	eta 0:02:49 lr 0.003544	time 0.5777 (0.6233)	model_time 0.5776 (0.5882)	loss 3.4176 (3.7417)	grad_norm 1.2650 (1.5543/0.7228)	mem 24308MB
[2025-01-18 16:18:43 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][50/312]	eta 0:02:42 lr 0.003543	time 0.5801 (0.6193)	model_time 0.5800 (0.5910)	loss 4.6211 (3.7218)	grad_norm 1.6717 (1.4648/0.6856)	mem 24308MB
[2025-01-18 16:18:49 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][60/312]	eta 0:02:36 lr 0.003543	time 0.5933 (0.6193)	model_time 0.5931 (0.5956)	loss 3.9853 (3.7487)	grad_norm 2.3202 (1.4718/0.6791)	mem 24308MB
[2025-01-18 16:18:55 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][70/312]	eta 0:02:30 lr 0.003543	time 0.6272 (0.6202)	model_time 0.6270 (0.5998)	loss 4.1503 (3.7518)	grad_norm 0.7173 (1.4629/0.6623)	mem 24308MB
[2025-01-18 16:19:02 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][80/312]	eta 0:02:23 lr 0.003542	time 0.5765 (0.6198)	model_time 0.5763 (0.6019)	loss 2.9102 (3.7286)	grad_norm 1.2009 (1.4988/0.6617)	mem 24308MB
[2025-01-18 16:19:08 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][90/312]	eta 0:02:17 lr 0.003542	time 0.5801 (0.6208)	model_time 0.5796 (0.6048)	loss 3.5992 (3.7475)	grad_norm 1.4599 (1.4930/0.6331)	mem 24308MB
[2025-01-18 16:19:14 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][100/312]	eta 0:02:11 lr 0.003541	time 0.6224 (0.6215)	model_time 0.6221 (0.6070)	loss 3.8510 (3.7292)	grad_norm 1.3907 (1.4551/0.6233)	mem 24308MB
[2025-01-18 16:19:20 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][110/312]	eta 0:02:05 lr 0.003541	time 0.5980 (0.6189)	model_time 0.5976 (0.6057)	loss 4.2050 (3.7295)	grad_norm 2.3448 (1.4482/0.6177)	mem 24308MB
[2025-01-18 16:19:26 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][120/312]	eta 0:01:58 lr 0.003541	time 0.5812 (0.6173)	model_time 0.5811 (0.6051)	loss 2.9985 (3.7156)	grad_norm 1.0174 (1.4843/0.6396)	mem 24308MB
[2025-01-18 16:19:32 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][130/312]	eta 0:01:52 lr 0.003540	time 0.6004 (0.6157)	model_time 0.6002 (0.6044)	loss 3.9734 (3.7101)	grad_norm 0.6110 (1.4595/0.6324)	mem 24308MB
[2025-01-18 16:19:38 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][140/312]	eta 0:01:45 lr 0.003540	time 0.5919 (0.6134)	model_time 0.5917 (0.6029)	loss 3.8622 (3.7102)	grad_norm 3.7711 (1.4762/0.6670)	mem 24308MB
[2025-01-18 16:19:44 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][150/312]	eta 0:01:39 lr 0.003539	time 0.5771 (0.6114)	model_time 0.5769 (0.6016)	loss 4.4357 (3.6955)	grad_norm 2.4810 (1.5257/0.7180)	mem 24308MB
[2025-01-18 16:19:50 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][160/312]	eta 0:01:32 lr 0.003539	time 0.5813 (0.6101)	model_time 0.5811 (0.6008)	loss 3.8601 (3.7022)	grad_norm 1.3401 (1.5246/0.7054)	mem 24308MB
[2025-01-18 16:19:56 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][170/312]	eta 0:01:26 lr 0.003538	time 0.5859 (0.6094)	model_time 0.5855 (0.6007)	loss 4.1821 (3.7072)	grad_norm 1.7846 (1.5228/0.6936)	mem 24308MB
[2025-01-18 16:20:02 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][180/312]	eta 0:01:20 lr 0.003538	time 0.5905 (0.6096)	model_time 0.5900 (0.6013)	loss 3.9302 (3.7071)	grad_norm 0.9334 (1.5086/0.6835)	mem 24308MB
[2025-01-18 16:20:08 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][190/312]	eta 0:01:14 lr 0.003538	time 0.5869 (0.6100)	model_time 0.5868 (0.6022)	loss 4.0146 (3.7056)	grad_norm 1.3456 (1.4949/0.6713)	mem 24308MB
[2025-01-18 16:20:14 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][200/312]	eta 0:01:08 lr 0.003537	time 0.5902 (0.6122)	model_time 0.5900 (0.6047)	loss 4.4162 (3.7058)	grad_norm 1.0191 (1.5029/0.6698)	mem 24308MB
[2025-01-18 16:20:21 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][210/312]	eta 0:01:02 lr 0.003537	time 0.6513 (0.6137)	model_time 0.6508 (0.6066)	loss 2.5867 (3.6844)	grad_norm 1.2286 (1.5047/0.6679)	mem 24308MB
[2025-01-18 16:20:27 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][220/312]	eta 0:00:56 lr 0.003536	time 0.5842 (0.6137)	model_time 0.5840 (0.6069)	loss 3.8143 (3.6919)	grad_norm 1.4112 (1.5073/0.6584)	mem 24308MB
[2025-01-18 16:20:33 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][230/312]	eta 0:00:50 lr 0.003536	time 0.6513 (0.6127)	model_time 0.6508 (0.6061)	loss 3.2836 (3.6958)	grad_norm 1.3368 (1.5208/0.6789)	mem 24308MB
[2025-01-18 16:20:39 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][240/312]	eta 0:00:44 lr 0.003535	time 0.6086 (0.6120)	model_time 0.6084 (0.6057)	loss 3.5737 (3.6930)	grad_norm 2.2993 (1.5251/0.6784)	mem 24308MB
[2025-01-18 16:20:45 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][250/312]	eta 0:00:37 lr 0.003535	time 0.5768 (0.6109)	model_time 0.5767 (0.6048)	loss 3.3474 (3.6989)	grad_norm 0.9770 (1.5104/0.6746)	mem 24308MB
[2025-01-18 16:20:51 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][260/312]	eta 0:00:31 lr 0.003535	time 0.5901 (0.6101)	model_time 0.5897 (0.6043)	loss 3.2905 (3.6864)	grad_norm 0.7240 (1.4930/0.6699)	mem 24308MB
[2025-01-18 16:20:57 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][270/312]	eta 0:00:25 lr 0.003534	time 0.5709 (0.6093)	model_time 0.5704 (0.6037)	loss 3.5856 (3.6803)	grad_norm 0.8293 (1.4799/0.6631)	mem 24308MB
[2025-01-18 16:21:02 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][280/312]	eta 0:00:19 lr 0.003534	time 0.5790 (0.6085)	model_time 0.5788 (0.6030)	loss 2.6667 (3.6733)	grad_norm 0.8477 (1.4674/0.6560)	mem 24308MB
[2025-01-18 16:21:08 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][290/312]	eta 0:00:13 lr 0.003533	time 0.5881 (0.6080)	model_time 0.5879 (0.6027)	loss 2.5748 (3.6746)	grad_norm 1.1857 (1.4532/0.6499)	mem 24308MB
[2025-01-18 16:21:14 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][300/312]	eta 0:00:07 lr 0.003533	time 0.6529 (0.6082)	model_time 0.6528 (0.6031)	loss 4.3465 (3.6778)	grad_norm 0.9790 (1.4601/0.6397)	mem 24308MB
[2025-01-18 16:21:21 internimage_s_1k_224] (main.py 510): INFO Train: [66/300][310/312]	eta 0:00:01 lr 0.003532	time 0.7903 (0.6082)	model_time 0.7902 (0.6032)	loss 4.5783 (3.6759)	grad_norm 1.7655 (1.4720/0.6351)	mem 24308MB
[2025-01-18 16:21:21 internimage_s_1k_224] (main.py 519): INFO EPOCH 66 training takes 0:03:09
[2025-01-18 16:21:21 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_66.pth saving......
[2025-01-18 16:21:23 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_66.pth saved !!!
[2025-01-18 16:21:30 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.365 (7.365)	Loss 0.9856 (0.9856)	Acc@1 78.711 (78.711)	Acc@5 94.849 (94.849)	Mem 24308MB
[2025-01-18 16:21:34 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.134 (0.960)	Loss 1.3480 (1.1298)	Acc@1 69.531 (75.075)	Acc@5 90.186 (92.867)	Mem 24308MB
[2025-01-18 16:21:34 internimage_s_1k_224] (main.py 575): INFO [Epoch:66] * Acc@1 75.082 Acc@5 92.956
[2025-01-18 16:21:34 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.1%
[2025-01-18 16:21:34 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 16:21:36 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 16:21:36 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 75.08%
[2025-01-18 16:21:43 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.220 (7.220)	Loss 1.2092 (1.2092)	Acc@1 71.411 (71.411)	Acc@5 90.649 (90.649)	Mem 24308MB
[2025-01-18 16:21:46 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.937)	Loss 1.8028 (1.4335)	Acc@1 58.960 (66.848)	Acc@5 82.422 (87.589)	Mem 24308MB
[2025-01-18 16:21:46 internimage_s_1k_224] (main.py 575): INFO [Epoch:66] * Acc@1 66.923 Acc@5 87.760
[2025-01-18 16:21:46 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 66.9%
[2025-01-18 16:21:46 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 16:21:48 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 16:21:48 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 66.92%
[2025-01-18 16:21:50 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][0/312]	eta 0:10:47 lr 0.003532	time 2.0755 (2.0755)	model_time 0.6179 (0.6179)	loss 3.6701 (3.6701)	grad_norm 3.4212 (3.4212/0.0000)	mem 24308MB
[2025-01-18 16:21:57 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][10/312]	eta 0:03:56 lr 0.003532	time 0.7126 (0.7836)	model_time 0.7124 (0.6509)	loss 3.9003 (3.5654)	grad_norm 1.0505 (1.8796/0.9816)	mem 24308MB
[2025-01-18 16:22:03 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][20/312]	eta 0:03:28 lr 0.003531	time 0.5735 (0.7125)	model_time 0.5731 (0.6428)	loss 3.3547 (3.6436)	grad_norm 2.0468 (1.7646/0.8215)	mem 24308MB
[2025-01-18 16:22:10 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][30/312]	eta 0:03:13 lr 0.003531	time 0.5798 (0.6859)	model_time 0.5796 (0.6386)	loss 3.8885 (3.5891)	grad_norm 1.2311 (1.5977/0.7455)	mem 24308MB
[2025-01-18 16:22:15 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][40/312]	eta 0:03:00 lr 0.003531	time 0.5714 (0.6621)	model_time 0.5712 (0.6263)	loss 3.2655 (3.5353)	grad_norm 1.5881 (1.7025/0.7559)	mem 24308MB
[2025-01-18 16:22:22 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][50/312]	eta 0:02:50 lr 0.003530	time 0.5779 (0.6512)	model_time 0.5774 (0.6223)	loss 4.3771 (3.5987)	grad_norm 0.6256 (1.6347/0.7268)	mem 24308MB
[2025-01-18 16:22:27 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][60/312]	eta 0:02:41 lr 0.003530	time 0.5712 (0.6406)	model_time 0.5708 (0.6164)	loss 2.4110 (3.5707)	grad_norm 0.9845 (1.6021/0.6842)	mem 24308MB
[2025-01-18 16:22:33 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][70/312]	eta 0:02:33 lr 0.003529	time 0.5717 (0.6336)	model_time 0.5713 (0.6127)	loss 4.0597 (3.5553)	grad_norm 1.6519 (1.5607/0.6599)	mem 24308MB
[2025-01-18 16:22:39 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][80/312]	eta 0:02:25 lr 0.003529	time 0.6053 (0.6281)	model_time 0.5905 (0.6096)	loss 4.5666 (3.5580)	grad_norm 1.8703 (1.5421/0.6314)	mem 24308MB
[2025-01-18 16:22:45 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][90/312]	eta 0:02:18 lr 0.003528	time 0.6275 (0.6242)	model_time 0.6271 (0.6077)	loss 3.7445 (3.5693)	grad_norm 0.8559 (1.5197/0.6142)	mem 24308MB
[2025-01-18 16:22:51 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][100/312]	eta 0:02:11 lr 0.003528	time 0.5816 (0.6210)	model_time 0.5814 (0.6061)	loss 3.7862 (3.5870)	grad_norm 1.8920 (1.5112/0.6025)	mem 24308MB
[2025-01-18 16:22:57 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][110/312]	eta 0:02:05 lr 0.003528	time 0.6711 (0.6201)	model_time 0.6709 (0.6065)	loss 2.6108 (3.5795)	grad_norm 1.2539 (1.5255/0.6031)	mem 24308MB
[2025-01-18 16:23:03 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][120/312]	eta 0:01:58 lr 0.003527	time 0.5825 (0.6193)	model_time 0.5823 (0.6068)	loss 3.7963 (3.5585)	grad_norm 1.2557 (1.5096/0.5974)	mem 24308MB
[2025-01-18 16:23:10 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][130/312]	eta 0:01:53 lr 0.003527	time 0.6600 (0.6212)	model_time 0.6596 (0.6097)	loss 3.2632 (3.5574)	grad_norm 1.7038 (1.4959/0.5869)	mem 24308MB
[2025-01-18 16:23:16 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][140/312]	eta 0:01:47 lr 0.003526	time 0.6653 (0.6228)	model_time 0.6651 (0.6120)	loss 3.5082 (3.5715)	grad_norm 0.5916 (1.4866/0.5875)	mem 24308MB
[2025-01-18 16:23:22 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][150/312]	eta 0:01:40 lr 0.003526	time 0.6648 (0.6234)	model_time 0.6644 (0.6133)	loss 4.5838 (3.5724)	grad_norm 1.5474 (1.4947/0.5763)	mem 24308MB
[2025-01-18 16:23:28 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][160/312]	eta 0:01:34 lr 0.003525	time 0.5875 (0.6213)	model_time 0.5874 (0.6118)	loss 4.5096 (3.5842)	grad_norm 1.0267 (1.4777/0.5671)	mem 24308MB
[2025-01-18 16:23:34 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][170/312]	eta 0:01:28 lr 0.003525	time 0.5871 (0.6203)	model_time 0.5867 (0.6114)	loss 3.8458 (3.5771)	grad_norm 2.1951 (1.4971/0.5800)	mem 24308MB
[2025-01-18 16:23:40 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][180/312]	eta 0:01:21 lr 0.003525	time 0.5765 (0.6184)	model_time 0.5764 (0.6099)	loss 3.2645 (3.5724)	grad_norm 0.7884 (1.5046/0.5841)	mem 24308MB
[2025-01-18 16:23:46 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][190/312]	eta 0:01:15 lr 0.003524	time 0.5868 (0.6169)	model_time 0.5863 (0.6088)	loss 4.0046 (3.5782)	grad_norm 1.3675 (1.4895/0.5746)	mem 24308MB
[2025-01-18 16:23:52 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][200/312]	eta 0:01:08 lr 0.003524	time 0.5740 (0.6154)	model_time 0.5738 (0.6077)	loss 3.7046 (3.5776)	grad_norm 2.8516 (1.5214/0.6227)	mem 24308MB
[2025-01-18 16:23:58 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][210/312]	eta 0:01:02 lr 0.003523	time 0.5894 (0.6139)	model_time 0.5893 (0.6066)	loss 4.5183 (3.5742)	grad_norm 1.0556 (1.5138/0.6129)	mem 24308MB
[2025-01-18 16:24:04 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][220/312]	eta 0:00:56 lr 0.003523	time 0.5722 (0.6133)	model_time 0.5720 (0.6062)	loss 4.2103 (3.5635)	grad_norm 1.5393 (1.5027/0.6039)	mem 24308MB
[2025-01-18 16:24:10 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][230/312]	eta 0:00:50 lr 0.003522	time 0.5934 (0.6135)	model_time 0.5932 (0.6067)	loss 4.5161 (3.5651)	grad_norm 0.7403 (1.4890/0.6036)	mem 24308MB
[2025-01-18 16:24:16 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][240/312]	eta 0:00:44 lr 0.003522	time 0.6530 (0.6145)	model_time 0.6528 (0.6080)	loss 3.8425 (3.5675)	grad_norm 1.8051 (1.4933/0.5999)	mem 24308MB
[2025-01-18 16:24:23 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][250/312]	eta 0:00:38 lr 0.003522	time 0.6666 (0.6150)	model_time 0.6660 (0.6088)	loss 2.5132 (3.5760)	grad_norm 2.1771 (1.5129/0.6120)	mem 24308MB
[2025-01-18 16:24:29 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][260/312]	eta 0:00:32 lr 0.003521	time 0.6611 (0.6157)	model_time 0.6606 (0.6096)	loss 3.1338 (3.5762)	grad_norm 1.7737 (1.5204/0.6230)	mem 24308MB
[2025-01-18 16:24:35 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][270/312]	eta 0:00:25 lr 0.003521	time 0.6641 (0.6161)	model_time 0.6636 (0.6103)	loss 2.7350 (3.5724)	grad_norm 1.3074 (1.5150/0.6168)	mem 24308MB
[2025-01-18 16:24:41 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][280/312]	eta 0:00:19 lr 0.003520	time 0.5799 (0.6151)	model_time 0.5798 (0.6094)	loss 4.3537 (3.5732)	grad_norm 3.7743 (1.5256/0.6371)	mem 24308MB
[2025-01-18 16:24:47 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][290/312]	eta 0:00:13 lr 0.003520	time 0.5907 (0.6144)	model_time 0.5905 (0.6090)	loss 4.3964 (3.5876)	grad_norm 0.7352 (1.5319/0.6365)	mem 24308MB
[2025-01-18 16:24:53 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][300/312]	eta 0:00:07 lr 0.003519	time 0.5673 (0.6136)	model_time 0.5672 (0.6083)	loss 3.6071 (3.5941)	grad_norm 0.8343 (1.5260/0.6276)	mem 24308MB
[2025-01-18 16:24:59 internimage_s_1k_224] (main.py 510): INFO Train: [67/300][310/312]	eta 0:00:01 lr 0.003519	time 0.5675 (0.6123)	model_time 0.5674 (0.6072)	loss 2.7459 (3.5947)	grad_norm 1.2352 (1.5090/0.6102)	mem 24308MB
[2025-01-18 16:24:59 internimage_s_1k_224] (main.py 519): INFO EPOCH 67 training takes 0:03:10
[2025-01-18 16:24:59 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_67.pth saving......
[2025-01-18 16:25:01 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_67.pth saved !!!
[2025-01-18 16:25:08 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.046 (7.046)	Loss 0.9373 (0.9373)	Acc@1 79.028 (79.028)	Acc@5 95.215 (95.215)	Mem 24308MB
[2025-01-18 16:25:11 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.923)	Loss 1.3589 (1.1245)	Acc@1 69.775 (75.178)	Acc@5 90.527 (93.093)	Mem 24308MB
[2025-01-18 16:25:12 internimage_s_1k_224] (main.py 575): INFO [Epoch:67] * Acc@1 75.108 Acc@5 93.104
[2025-01-18 16:25:12 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.1%
[2025-01-18 16:25:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 16:25:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 16:25:14 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 75.11%
[2025-01-18 16:25:21 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.043 (7.043)	Loss 1.1815 (1.1815)	Acc@1 72.046 (72.046)	Acc@5 91.089 (91.089)	Mem 24308MB
[2025-01-18 16:25:24 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.135 (0.931)	Loss 1.7677 (1.4032)	Acc@1 59.424 (67.356)	Acc@5 82.910 (88.022)	Mem 24308MB
[2025-01-18 16:25:24 internimage_s_1k_224] (main.py 575): INFO [Epoch:67] * Acc@1 67.448 Acc@5 88.170
[2025-01-18 16:25:24 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 67.4%
[2025-01-18 16:25:24 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 16:25:26 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 16:25:26 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 67.45%
[2025-01-18 16:25:29 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][0/312]	eta 0:15:00 lr 0.003519	time 2.8872 (2.8872)	model_time 0.6038 (0.6038)	loss 3.8149 (3.8149)	grad_norm 0.7977 (0.7977/0.0000)	mem 24308MB
[2025-01-18 16:25:35 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][10/312]	eta 0:04:02 lr 0.003518	time 0.6152 (0.8034)	model_time 0.6151 (0.5956)	loss 4.1533 (3.6580)	grad_norm 1.0169 (1.8940/1.3287)	mem 24308MB
[2025-01-18 16:25:41 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][20/312]	eta 0:03:25 lr 0.003518	time 0.6074 (0.7021)	model_time 0.6072 (0.5931)	loss 3.2690 (3.6562)	grad_norm 1.2192 (1.5445/1.0449)	mem 24308MB
[2025-01-18 16:25:47 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][30/312]	eta 0:03:08 lr 0.003518	time 0.5998 (0.6689)	model_time 0.5996 (0.5949)	loss 3.9203 (3.6838)	grad_norm 1.4110 (1.4630/0.8904)	mem 24308MB
[2025-01-18 16:25:53 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][40/312]	eta 0:02:58 lr 0.003517	time 0.6162 (0.6580)	model_time 0.6161 (0.6020)	loss 3.8578 (3.6791)	grad_norm 1.9344 (1.5756/0.9270)	mem 24308MB
[2025-01-18 16:25:59 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][50/312]	eta 0:02:49 lr 0.003517	time 0.6826 (0.6487)	model_time 0.6825 (0.6036)	loss 3.8129 (3.6782)	grad_norm 0.7778 (1.4934/0.8667)	mem 24308MB
[2025-01-18 16:26:06 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][60/312]	eta 0:02:42 lr 0.003516	time 0.6009 (0.6450)	model_time 0.6007 (0.6073)	loss 3.1291 (3.6758)	grad_norm 1.9949 (1.5400/0.8494)	mem 24308MB
[2025-01-18 16:26:12 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][70/312]	eta 0:02:36 lr 0.003516	time 0.5746 (0.6451)	model_time 0.5742 (0.6123)	loss 3.9474 (3.6832)	grad_norm 1.6172 (1.5881/0.8486)	mem 24308MB
[2025-01-18 16:26:18 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][80/312]	eta 0:02:29 lr 0.003515	time 0.5835 (0.6435)	model_time 0.5834 (0.6147)	loss 3.6892 (3.6397)	grad_norm 1.4080 (1.6044/0.8555)	mem 24308MB
[2025-01-18 16:26:24 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][90/312]	eta 0:02:21 lr 0.003515	time 0.5900 (0.6390)	model_time 0.5898 (0.6134)	loss 2.5546 (3.6159)	grad_norm 1.1049 (1.5564/0.8267)	mem 24308MB
[2025-01-18 16:26:31 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][100/312]	eta 0:02:14 lr 0.003514	time 0.6971 (0.6362)	model_time 0.6966 (0.6130)	loss 3.1562 (3.5533)	grad_norm 1.3657 (1.5448/0.7905)	mem 24308MB
[2025-01-18 16:26:36 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][110/312]	eta 0:02:07 lr 0.003514	time 0.5876 (0.6317)	model_time 0.5874 (0.6106)	loss 3.7920 (3.5656)	grad_norm 0.9978 (1.5374/0.7690)	mem 24308MB
[2025-01-18 16:26:42 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][120/312]	eta 0:02:00 lr 0.003514	time 0.5757 (0.6280)	model_time 0.5756 (0.6086)	loss 3.9638 (3.5745)	grad_norm 1.9768 (1.5153/0.7504)	mem 24308MB
[2025-01-18 16:26:48 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][130/312]	eta 0:01:53 lr 0.003513	time 0.6056 (0.6249)	model_time 0.6054 (0.6069)	loss 2.9960 (3.5847)	grad_norm 1.3848 (1.5294/0.7413)	mem 24308MB
[2025-01-18 16:26:54 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][140/312]	eta 0:01:47 lr 0.003513	time 0.5765 (0.6222)	model_time 0.5763 (0.6055)	loss 3.5919 (3.6013)	grad_norm 1.4925 (1.5443/0.7427)	mem 24308MB
[2025-01-18 16:27:00 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][150/312]	eta 0:01:40 lr 0.003512	time 0.5869 (0.6206)	model_time 0.5864 (0.6050)	loss 2.9009 (3.6164)	grad_norm 0.9242 (1.5520/0.7312)	mem 24308MB
[2025-01-18 16:27:06 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][160/312]	eta 0:01:34 lr 0.003512	time 0.5770 (0.6193)	model_time 0.5769 (0.6046)	loss 3.6938 (3.6176)	grad_norm 0.6335 (1.5492/0.7298)	mem 24308MB
[2025-01-18 16:27:12 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][170/312]	eta 0:01:27 lr 0.003511	time 0.5739 (0.6192)	model_time 0.5738 (0.6053)	loss 4.1636 (3.6018)	grad_norm 1.3626 (1.5555/0.7434)	mem 24308MB
[2025-01-18 16:27:18 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][180/312]	eta 0:01:21 lr 0.003511	time 0.6539 (0.6198)	model_time 0.6535 (0.6067)	loss 3.3680 (3.6069)	grad_norm 1.5587 (1.5367/0.7310)	mem 24308MB
[2025-01-18 16:27:25 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][190/312]	eta 0:01:15 lr 0.003511	time 0.5797 (0.6201)	model_time 0.5796 (0.6077)	loss 3.5122 (3.6035)	grad_norm 1.3800 (1.5300/0.7198)	mem 24308MB
[2025-01-18 16:27:31 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][200/312]	eta 0:01:09 lr 0.003510	time 0.5905 (0.6205)	model_time 0.5903 (0.6087)	loss 2.7758 (3.5993)	grad_norm 1.3628 (1.5156/0.7083)	mem 24308MB
[2025-01-18 16:27:37 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][210/312]	eta 0:01:03 lr 0.003510	time 0.5852 (0.6193)	model_time 0.5850 (0.6080)	loss 3.8652 (3.5982)	grad_norm 1.2659 (1.5006/0.6967)	mem 24308MB
[2025-01-18 16:27:43 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][220/312]	eta 0:00:56 lr 0.003509	time 0.5984 (0.6195)	model_time 0.5979 (0.6087)	loss 3.3944 (3.5951)	grad_norm 3.8527 (1.5345/0.7347)	mem 24308MB
[2025-01-18 16:27:49 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][230/312]	eta 0:00:50 lr 0.003509	time 0.5967 (0.6186)	model_time 0.5963 (0.6083)	loss 3.6087 (3.5929)	grad_norm 0.9321 (1.5208/0.7252)	mem 24308MB
[2025-01-18 16:27:55 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][240/312]	eta 0:00:44 lr 0.003508	time 0.5731 (0.6174)	model_time 0.5730 (0.6075)	loss 3.9180 (3.5921)	grad_norm 0.9502 (1.5102/0.7150)	mem 24308MB
[2025-01-18 16:28:01 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][250/312]	eta 0:00:38 lr 0.003508	time 0.5863 (0.6163)	model_time 0.5861 (0.6067)	loss 3.8456 (3.5851)	grad_norm 1.1453 (1.5090/0.7094)	mem 24308MB
[2025-01-18 16:28:07 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][260/312]	eta 0:00:31 lr 0.003508	time 0.5869 (0.6152)	model_time 0.5868 (0.6060)	loss 3.8169 (3.5926)	grad_norm 2.2141 (1.5352/0.7214)	mem 24308MB
[2025-01-18 16:28:13 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][270/312]	eta 0:00:25 lr 0.003507	time 0.6044 (0.6148)	model_time 0.6040 (0.6059)	loss 3.6771 (3.5962)	grad_norm 1.4679 (1.5347/0.7153)	mem 24308MB
[2025-01-18 16:28:19 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][280/312]	eta 0:00:19 lr 0.003507	time 0.5848 (0.6141)	model_time 0.5847 (0.6056)	loss 2.8277 (3.5882)	grad_norm 1.3483 (1.5324/0.7106)	mem 24308MB
[2025-01-18 16:28:25 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][290/312]	eta 0:00:13 lr 0.003506	time 0.5844 (0.6145)	model_time 0.5843 (0.6062)	loss 2.9147 (3.5849)	grad_norm 1.6356 (1.5255/0.7040)	mem 24308MB
[2025-01-18 16:28:31 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][300/312]	eta 0:00:07 lr 0.003506	time 0.5774 (0.6143)	model_time 0.5773 (0.6063)	loss 2.5524 (3.5824)	grad_norm 1.5352 (1.5170/0.6960)	mem 24308MB
[2025-01-18 16:28:37 internimage_s_1k_224] (main.py 510): INFO Train: [68/300][310/312]	eta 0:00:01 lr 0.003505	time 0.6511 (0.6142)	model_time 0.6509 (0.6064)	loss 3.6173 (3.5895)	grad_norm 1.8115 (1.4943/0.6481)	mem 24308MB
[2025-01-18 16:28:38 internimage_s_1k_224] (main.py 519): INFO EPOCH 68 training takes 0:03:11
[2025-01-18 16:28:38 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_68.pth saving......
[2025-01-18 16:28:40 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_68.pth saved !!!
[2025-01-18 16:28:47 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.942 (6.942)	Loss 0.8951 (0.8951)	Acc@1 80.005 (80.005)	Acc@5 95.703 (95.703)	Mem 24308MB
[2025-01-18 16:28:50 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.931)	Loss 1.3114 (1.1167)	Acc@1 70.459 (75.397)	Acc@5 90.796 (93.100)	Mem 24308MB
[2025-01-18 16:28:50 internimage_s_1k_224] (main.py 575): INFO [Epoch:68] * Acc@1 75.356 Acc@5 93.094
[2025-01-18 16:28:50 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.4%
[2025-01-18 16:28:50 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 16:28:52 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 16:28:52 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 75.36%
[2025-01-18 16:29:00 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.726 (7.726)	Loss 1.1564 (1.1564)	Acc@1 72.534 (72.534)	Acc@5 91.284 (91.284)	Mem 24308MB
[2025-01-18 16:29:03 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (1.000)	Loss 1.7347 (1.3748)	Acc@1 59.937 (67.973)	Acc@5 83.325 (88.386)	Mem 24308MB
[2025-01-18 16:29:03 internimage_s_1k_224] (main.py 575): INFO [Epoch:68] * Acc@1 68.064 Acc@5 88.528
[2025-01-18 16:29:03 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 68.1%
[2025-01-18 16:29:03 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 16:29:06 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 16:29:06 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 68.06%
[2025-01-18 16:29:08 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][0/312]	eta 0:11:05 lr 0.003505	time 2.1345 (2.1345)	model_time 0.6176 (0.6176)	loss 2.9776 (2.9776)	grad_norm 2.3598 (2.3598/0.0000)	mem 24308MB
[2025-01-18 16:29:14 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][10/312]	eta 0:03:51 lr 0.003505	time 0.5720 (0.7661)	model_time 0.5719 (0.6279)	loss 3.0901 (3.2501)	grad_norm 1.0276 (1.2751/0.4698)	mem 24308MB
[2025-01-18 16:29:20 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][20/312]	eta 0:03:18 lr 0.003504	time 0.5812 (0.6806)	model_time 0.5810 (0.6080)	loss 3.5047 (3.3672)	grad_norm 0.6717 (1.2649/0.4648)	mem 24308MB
[2025-01-18 16:29:26 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][30/312]	eta 0:03:05 lr 0.003504	time 0.6352 (0.6588)	model_time 0.6348 (0.6096)	loss 2.8955 (3.3305)	grad_norm 1.3741 (1.3317/0.5180)	mem 24308MB
[2025-01-18 16:29:32 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][40/312]	eta 0:02:55 lr 0.003503	time 0.5857 (0.6440)	model_time 0.5855 (0.6066)	loss 4.1960 (3.4481)	grad_norm 1.7973 (1.3503/0.4929)	mem 24308MB
[2025-01-18 16:29:38 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][50/312]	eta 0:02:45 lr 0.003503	time 0.5868 (0.6331)	model_time 0.5867 (0.6030)	loss 3.4878 (3.4766)	grad_norm 1.4577 (1.3938/0.4969)	mem 24308MB
[2025-01-18 16:29:44 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][60/312]	eta 0:02:37 lr 0.003503	time 0.5890 (0.6259)	model_time 0.5886 (0.6007)	loss 3.2960 (3.4999)	grad_norm 1.3241 (1.4254/0.5110)	mem 24308MB
[2025-01-18 16:29:50 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][70/312]	eta 0:02:30 lr 0.003502	time 0.5834 (0.6201)	model_time 0.5832 (0.5984)	loss 3.7697 (3.4450)	grad_norm 1.7612 (1.4113/0.5015)	mem 24308MB
[2025-01-18 16:29:56 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][80/312]	eta 0:02:23 lr 0.003502	time 0.5976 (0.6175)	model_time 0.5974 (0.5985)	loss 2.5955 (3.4437)	grad_norm 2.0618 (1.4216/0.5004)	mem 24308MB
[2025-01-18 16:30:02 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][90/312]	eta 0:02:17 lr 0.003501	time 0.6925 (0.6179)	model_time 0.6920 (0.6009)	loss 4.4430 (3.4413)	grad_norm 0.9544 (1.4450/0.5452)	mem 24308MB
[2025-01-18 16:30:08 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][100/312]	eta 0:02:10 lr 0.003501	time 0.5841 (0.6164)	model_time 0.5839 (0.6010)	loss 3.8043 (3.4741)	grad_norm 0.6682 (1.3835/0.5511)	mem 24308MB
[2025-01-18 16:30:14 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][110/312]	eta 0:02:04 lr 0.003500	time 0.5864 (0.6168)	model_time 0.5859 (0.6027)	loss 3.6199 (3.5001)	grad_norm 1.4872 (1.3517/0.5428)	mem 24308MB
[2025-01-18 16:30:21 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][120/312]	eta 0:01:58 lr 0.003500	time 0.5783 (0.6183)	model_time 0.5781 (0.6054)	loss 4.0456 (3.5238)	grad_norm 1.2119 (1.3409/0.5326)	mem 24308MB
[2025-01-18 16:30:27 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][130/312]	eta 0:01:52 lr 0.003499	time 0.5835 (0.6187)	model_time 0.5834 (0.6068)	loss 2.9747 (3.5178)	grad_norm 2.2439 (1.3489/0.5429)	mem 24308MB
[2025-01-18 16:30:33 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][140/312]	eta 0:01:46 lr 0.003499	time 0.5867 (0.6171)	model_time 0.5865 (0.6060)	loss 3.4338 (3.5260)	grad_norm 1.3514 (1.3739/0.5659)	mem 24308MB
[2025-01-18 16:30:39 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][150/312]	eta 0:01:39 lr 0.003499	time 0.5865 (0.6161)	model_time 0.5864 (0.6057)	loss 4.3890 (3.5422)	grad_norm 0.9996 (1.3834/0.5566)	mem 24308MB
[2025-01-18 16:30:45 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][160/312]	eta 0:01:33 lr 0.003498	time 0.5838 (0.6148)	model_time 0.5836 (0.6050)	loss 3.4763 (3.5423)	grad_norm 1.4548 (1.3945/0.5564)	mem 24308MB
[2025-01-18 16:30:51 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][170/312]	eta 0:01:27 lr 0.003498	time 0.5887 (0.6135)	model_time 0.5886 (0.6042)	loss 3.2626 (3.5546)	grad_norm 1.0334 (1.3938/0.5464)	mem 24308MB
[2025-01-18 16:30:57 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][180/312]	eta 0:01:20 lr 0.003497	time 0.5842 (0.6121)	model_time 0.5837 (0.6033)	loss 4.0088 (3.5568)	grad_norm 0.9286 (1.3738/0.5381)	mem 24308MB
[2025-01-18 16:31:02 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][190/312]	eta 0:01:14 lr 0.003497	time 0.5764 (0.6105)	model_time 0.5760 (0.6022)	loss 3.9238 (3.5744)	grad_norm 0.9530 (1.3730/0.5366)	mem 24308MB
[2025-01-18 16:31:08 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][200/312]	eta 0:01:08 lr 0.003496	time 0.5940 (0.6101)	model_time 0.5939 (0.6021)	loss 2.9198 (3.5794)	grad_norm 1.0505 (1.3781/0.5483)	mem 24308MB
[2025-01-18 16:31:15 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][210/312]	eta 0:01:02 lr 0.003496	time 0.6921 (0.6104)	model_time 0.6919 (0.6029)	loss 3.8582 (3.5842)	grad_norm 2.4190 (1.4015/0.5598)	mem 24308MB
[2025-01-18 16:31:21 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][220/312]	eta 0:00:56 lr 0.003496	time 0.5770 (0.6100)	model_time 0.5769 (0.6028)	loss 2.7529 (3.5792)	grad_norm 1.2704 (1.4029/0.5570)	mem 24308MB
[2025-01-18 16:31:27 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][230/312]	eta 0:00:50 lr 0.003495	time 0.5914 (0.6111)	model_time 0.5909 (0.6041)	loss 3.9069 (3.5839)	grad_norm 1.6588 (1.4107/0.5530)	mem 24308MB
[2025-01-18 16:31:33 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][240/312]	eta 0:00:44 lr 0.003495	time 0.5744 (0.6117)	model_time 0.5742 (0.6050)	loss 3.0576 (3.5928)	grad_norm 1.8011 (1.4297/0.5702)	mem 24308MB
[2025-01-18 16:31:40 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][250/312]	eta 0:00:37 lr 0.003494	time 0.5707 (0.6127)	model_time 0.5706 (0.6063)	loss 4.0221 (3.5930)	grad_norm 1.7313 (1.4472/0.5958)	mem 24308MB
[2025-01-18 16:31:46 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][260/312]	eta 0:00:31 lr 0.003494	time 0.5776 (0.6124)	model_time 0.5772 (0.6062)	loss 3.0883 (3.5982)	grad_norm 0.9126 (1.4330/0.5911)	mem 24308MB
[2025-01-18 16:31:52 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][270/312]	eta 0:00:25 lr 0.003493	time 0.6152 (0.6123)	model_time 0.6150 (0.6063)	loss 4.0322 (3.5888)	grad_norm 1.0505 (1.4212/0.5861)	mem 24308MB
[2025-01-18 16:31:58 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][280/312]	eta 0:00:19 lr 0.003493	time 0.5831 (0.6117)	model_time 0.5827 (0.6059)	loss 4.2265 (3.5970)	grad_norm 1.2164 (1.4132/0.5787)	mem 24308MB
[2025-01-18 16:32:04 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][290/312]	eta 0:00:13 lr 0.003492	time 0.5831 (0.6110)	model_time 0.5830 (0.6054)	loss 4.1874 (3.6095)	grad_norm 1.1466 (1.4121/0.5740)	mem 24308MB
[2025-01-18 16:32:09 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][300/312]	eta 0:00:07 lr 0.003492	time 0.5711 (0.6100)	model_time 0.5710 (0.6045)	loss 4.8040 (3.6195)	grad_norm 1.6855 (1.3986/0.5692)	mem 24308MB
[2025-01-18 16:32:15 internimage_s_1k_224] (main.py 510): INFO Train: [69/300][310/312]	eta 0:00:01 lr 0.003492	time 0.5677 (0.6088)	model_time 0.5676 (0.6035)	loss 3.7630 (3.6141)	grad_norm 0.9335 (1.4122/0.5834)	mem 24308MB
[2025-01-18 16:32:16 internimage_s_1k_224] (main.py 519): INFO EPOCH 69 training takes 0:03:09
[2025-01-18 16:32:16 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_69.pth saving......
[2025-01-18 16:32:18 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_69.pth saved !!!
[2025-01-18 16:32:25 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.078 (7.078)	Loss 0.9696 (0.9696)	Acc@1 78.760 (78.760)	Acc@5 95.215 (95.215)	Mem 24308MB
[2025-01-18 16:32:28 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.931)	Loss 1.3929 (1.1387)	Acc@1 69.067 (75.051)	Acc@5 89.697 (93.020)	Mem 24308MB
[2025-01-18 16:32:28 internimage_s_1k_224] (main.py 575): INFO [Epoch:69] * Acc@1 75.038 Acc@5 93.102
[2025-01-18 16:32:28 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.0%
[2025-01-18 16:32:28 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 75.36%
[2025-01-18 16:32:36 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.129 (8.129)	Loss 1.1334 (1.1334)	Acc@1 72.852 (72.852)	Acc@5 91.479 (91.479)	Mem 24308MB
[2025-01-18 16:32:40 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.102)	Loss 1.7042 (1.3490)	Acc@1 60.352 (68.461)	Acc@5 83.862 (88.723)	Mem 24308MB
[2025-01-18 16:32:40 internimage_s_1k_224] (main.py 575): INFO [Epoch:69] * Acc@1 68.566 Acc@5 88.864
[2025-01-18 16:32:40 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 68.6%
[2025-01-18 16:32:40 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 16:32:42 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 16:32:42 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 68.57%
[2025-01-18 16:32:45 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][0/312]	eta 0:12:02 lr 0.003491	time 2.3173 (2.3173)	model_time 0.6149 (0.6149)	loss 4.1344 (4.1344)	grad_norm 1.4460 (1.4460/0.0000)	mem 24308MB
[2025-01-18 16:32:51 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][10/312]	eta 0:03:44 lr 0.003491	time 0.5862 (0.7437)	model_time 0.5860 (0.5887)	loss 3.8830 (3.5391)	grad_norm 1.7897 (1.4631/0.5099)	mem 24308MB
[2025-01-18 16:32:57 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][20/312]	eta 0:03:20 lr 0.003491	time 0.5763 (0.6857)	model_time 0.5759 (0.6044)	loss 3.5105 (3.5409)	grad_norm 2.4623 (1.6253/0.5877)	mem 24308MB
[2025-01-18 16:33:03 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][30/312]	eta 0:03:06 lr 0.003490	time 0.6620 (0.6609)	model_time 0.6614 (0.6057)	loss 4.5448 (3.6589)	grad_norm 0.8601 (1.6926/0.5675)	mem 24308MB
[2025-01-18 16:33:09 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][40/312]	eta 0:02:58 lr 0.003490	time 0.6633 (0.6580)	model_time 0.6628 (0.6162)	loss 2.9262 (3.6607)	grad_norm 1.0196 (1.6129/0.5593)	mem 24308MB
[2025-01-18 16:33:16 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][50/312]	eta 0:02:49 lr 0.003489	time 0.6678 (0.6488)	model_time 0.6676 (0.6151)	loss 4.4969 (3.6541)	grad_norm 3.5834 (1.5621/0.6316)	mem 24308MB
[2025-01-18 16:33:22 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][60/312]	eta 0:02:41 lr 0.003489	time 0.6356 (0.6428)	model_time 0.6352 (0.6146)	loss 4.0245 (3.7001)	grad_norm 1.4774 (1.7154/0.7870)	mem 24308MB
[2025-01-18 16:33:28 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][70/312]	eta 0:02:34 lr 0.003488	time 0.5871 (0.6379)	model_time 0.5870 (0.6136)	loss 2.8699 (3.6347)	grad_norm 1.6311 (1.6717/0.7476)	mem 24308MB
[2025-01-18 16:33:34 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][80/312]	eta 0:02:27 lr 0.003488	time 0.5726 (0.6343)	model_time 0.5722 (0.6130)	loss 3.1389 (3.6708)	grad_norm 1.5521 (1.6493/0.7272)	mem 24308MB
[2025-01-18 16:33:40 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][90/312]	eta 0:02:19 lr 0.003487	time 0.5827 (0.6295)	model_time 0.5825 (0.6105)	loss 3.1528 (3.6900)	grad_norm 0.9365 (1.6116/0.7149)	mem 24308MB
[2025-01-18 16:33:46 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][100/312]	eta 0:02:12 lr 0.003487	time 0.6190 (0.6257)	model_time 0.6188 (0.6085)	loss 4.3292 (3.6876)	grad_norm 0.8450 (1.5546/0.7035)	mem 24308MB
[2025-01-18 16:33:52 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][110/312]	eta 0:02:05 lr 0.003487	time 0.5951 (0.6225)	model_time 0.5946 (0.6068)	loss 3.8497 (3.6630)	grad_norm 0.8380 (1.5190/0.6908)	mem 24308MB
[2025-01-18 16:33:57 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][120/312]	eta 0:01:59 lr 0.003486	time 0.6043 (0.6198)	model_time 0.6040 (0.6054)	loss 4.0449 (3.6621)	grad_norm 1.8848 (1.5458/0.7045)	mem 24308MB
[2025-01-18 16:34:03 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][130/312]	eta 0:01:52 lr 0.003486	time 0.5909 (0.6177)	model_time 0.5904 (0.6043)	loss 3.1228 (3.6508)	grad_norm 2.3725 (1.5554/0.6989)	mem 24308MB
[2025-01-18 16:34:09 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][140/312]	eta 0:01:46 lr 0.003485	time 0.6014 (0.6171)	model_time 0.6012 (0.6047)	loss 2.7969 (3.6660)	grad_norm 1.8252 (1.5600/0.7012)	mem 24308MB
[2025-01-18 16:34:16 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][150/312]	eta 0:01:39 lr 0.003485	time 0.6459 (0.6169)	model_time 0.6454 (0.6053)	loss 2.7341 (3.6717)	grad_norm 1.0838 (1.5510/0.6885)	mem 24308MB
[2025-01-18 16:34:22 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][160/312]	eta 0:01:33 lr 0.003484	time 0.6394 (0.6180)	model_time 0.6390 (0.6070)	loss 3.1109 (3.6668)	grad_norm 2.1307 (1.5467/0.6739)	mem 24308MB
[2025-01-18 16:34:28 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][170/312]	eta 0:01:27 lr 0.003484	time 0.6936 (0.6181)	model_time 0.6934 (0.6078)	loss 3.2351 (3.6825)	grad_norm 1.1318 (1.5397/0.6663)	mem 24308MB
[2025-01-18 16:34:34 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][180/312]	eta 0:01:21 lr 0.003483	time 0.5782 (0.6178)	model_time 0.5781 (0.6079)	loss 3.4886 (3.6769)	grad_norm 1.1362 (1.5113/0.6587)	mem 24308MB
[2025-01-18 16:34:40 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][190/312]	eta 0:01:15 lr 0.003483	time 0.5807 (0.6178)	model_time 0.5803 (0.6085)	loss 2.4114 (3.6605)	grad_norm 0.9236 (1.5036/0.6525)	mem 24308MB
[2025-01-18 16:34:46 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][200/312]	eta 0:01:09 lr 0.003483	time 0.5739 (0.6170)	model_time 0.5737 (0.6081)	loss 4.3106 (3.6446)	grad_norm 2.2901 (1.4958/0.6481)	mem 24308MB
[2025-01-18 16:34:53 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][210/312]	eta 0:01:02 lr 0.003482	time 0.5956 (0.6165)	model_time 0.5954 (0.6080)	loss 2.9397 (3.6481)	grad_norm 0.6945 (1.4774/0.6445)	mem 24308MB
[2025-01-18 16:34:58 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][220/312]	eta 0:00:56 lr 0.003482	time 0.5722 (0.6153)	model_time 0.5717 (0.6072)	loss 2.7886 (3.6484)	grad_norm 1.7034 (1.4679/0.6330)	mem 24308MB
[2025-01-18 16:35:04 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][230/312]	eta 0:00:50 lr 0.003481	time 0.5823 (0.6139)	model_time 0.5822 (0.6061)	loss 3.8220 (3.6588)	grad_norm 1.0887 (1.4586/0.6252)	mem 24308MB
[2025-01-18 16:35:10 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][240/312]	eta 0:00:44 lr 0.003481	time 0.5947 (0.6131)	model_time 0.5945 (0.6056)	loss 4.0446 (3.6504)	grad_norm 1.1382 (1.4485/0.6183)	mem 24308MB
[2025-01-18 16:35:16 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][250/312]	eta 0:00:37 lr 0.003480	time 0.5767 (0.6120)	model_time 0.5766 (0.6048)	loss 4.3698 (3.6469)	grad_norm 1.0816 (1.4539/0.6225)	mem 24308MB
[2025-01-18 16:35:22 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][260/312]	eta 0:00:31 lr 0.003480	time 0.7069 (0.6120)	model_time 0.7064 (0.6050)	loss 3.7006 (3.6416)	grad_norm 2.8361 (1.4557/0.6206)	mem 24308MB
[2025-01-18 16:35:28 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][270/312]	eta 0:00:25 lr 0.003479	time 0.5945 (0.6117)	model_time 0.5944 (0.6050)	loss 3.7167 (3.6467)	grad_norm 1.3747 (1.4644/0.6272)	mem 24308MB
[2025-01-18 16:35:35 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][280/312]	eta 0:00:19 lr 0.003479	time 0.5803 (0.6129)	model_time 0.5802 (0.6064)	loss 2.7987 (3.6362)	grad_norm 1.5219 (1.4509/0.6214)	mem 24308MB
[2025-01-18 16:35:41 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][290/312]	eta 0:00:13 lr 0.003478	time 0.6674 (0.6134)	model_time 0.6673 (0.6071)	loss 3.1813 (3.6304)	grad_norm 2.2823 (1.4517/0.6198)	mem 24308MB
[2025-01-18 16:35:47 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][300/312]	eta 0:00:07 lr 0.003478	time 0.5693 (0.6134)	model_time 0.5692 (0.6073)	loss 3.6750 (3.6262)	grad_norm 1.7648 (1.4452/0.6143)	mem 24308MB
[2025-01-18 16:35:53 internimage_s_1k_224] (main.py 510): INFO Train: [70/300][310/312]	eta 0:00:01 lr 0.003478	time 0.5684 (0.6130)	model_time 0.5682 (0.6071)	loss 4.3369 (3.6294)	grad_norm 1.4856 (1.4746/0.6623)	mem 24308MB
[2025-01-18 16:35:54 internimage_s_1k_224] (main.py 519): INFO EPOCH 70 training takes 0:03:11
[2025-01-18 16:35:54 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_70.pth saving......
[2025-01-18 16:35:56 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_70.pth saved !!!
[2025-01-18 16:36:03 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.040 (7.040)	Loss 0.9716 (0.9716)	Acc@1 79.297 (79.297)	Acc@5 95.679 (95.679)	Mem 24308MB
[2025-01-18 16:36:06 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.910)	Loss 1.3522 (1.1311)	Acc@1 70.312 (75.661)	Acc@5 90.454 (93.317)	Mem 24308MB
[2025-01-18 16:36:06 internimage_s_1k_224] (main.py 575): INFO [Epoch:70] * Acc@1 75.602 Acc@5 93.384
[2025-01-18 16:36:06 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.6%
[2025-01-18 16:36:06 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 16:36:08 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 16:36:08 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 75.60%
[2025-01-18 16:36:15 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.000 (7.000)	Loss 1.1124 (1.1124)	Acc@1 73.218 (73.218)	Acc@5 91.748 (91.748)	Mem 24308MB
[2025-01-18 16:36:18 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.929)	Loss 1.6755 (1.3247)	Acc@1 60.889 (68.916)	Acc@5 84.180 (89.016)	Mem 24308MB
[2025-01-18 16:36:18 internimage_s_1k_224] (main.py 575): INFO [Epoch:70] * Acc@1 69.000 Acc@5 89.147
[2025-01-18 16:36:18 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 69.0%
[2025-01-18 16:36:18 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 16:36:20 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 16:36:20 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 69.00%
[2025-01-18 16:36:23 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][0/312]	eta 0:12:31 lr 0.003477	time 2.4097 (2.4097)	model_time 0.6140 (0.6140)	loss 3.0288 (3.0288)	grad_norm 1.5977 (1.5977/0.0000)	mem 24308MB
[2025-01-18 16:36:29 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][10/312]	eta 0:03:53 lr 0.003477	time 0.5778 (0.7729)	model_time 0.5776 (0.6094)	loss 4.0955 (3.4813)	grad_norm 1.3103 (1.6380/0.4309)	mem 24308MB
[2025-01-18 16:36:35 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][20/312]	eta 0:03:21 lr 0.003477	time 0.5773 (0.6887)	model_time 0.5771 (0.6028)	loss 3.7706 (3.5986)	grad_norm 1.4032 (1.5223/0.4489)	mem 24308MB
[2025-01-18 16:36:41 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][30/312]	eta 0:03:05 lr 0.003476	time 0.5913 (0.6587)	model_time 0.5909 (0.6004)	loss 4.0421 (3.7201)	grad_norm 0.7722 (1.5663/0.5805)	mem 24308MB
[2025-01-18 16:36:47 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][40/312]	eta 0:02:54 lr 0.003476	time 0.6008 (0.6415)	model_time 0.6006 (0.5973)	loss 3.2746 (3.6609)	grad_norm 1.5927 (1.5638/0.5682)	mem 24308MB
[2025-01-18 16:36:53 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][50/312]	eta 0:02:45 lr 0.003475	time 0.5933 (0.6314)	model_time 0.5931 (0.5958)	loss 3.9100 (3.6490)	grad_norm 1.4371 (1.4994/0.5473)	mem 24308MB
[2025-01-18 16:36:58 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][60/312]	eta 0:02:37 lr 0.003475	time 0.5877 (0.6241)	model_time 0.5873 (0.5943)	loss 3.9784 (3.6384)	grad_norm 1.6665 (1.4464/0.5261)	mem 24308MB
[2025-01-18 16:37:05 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][70/312]	eta 0:02:30 lr 0.003474	time 0.6672 (0.6227)	model_time 0.6671 (0.5970)	loss 4.2987 (3.6499)	grad_norm 1.7712 (1.4288/0.5017)	mem 24308MB
[2025-01-18 16:37:11 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][80/312]	eta 0:02:23 lr 0.003474	time 0.5895 (0.6193)	model_time 0.5894 (0.5968)	loss 4.2478 (3.6415)	grad_norm 1.5257 (1.4570/0.5124)	mem 24308MB
[2025-01-18 16:37:17 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][90/312]	eta 0:02:17 lr 0.003473	time 0.6544 (0.6207)	model_time 0.6540 (0.6006)	loss 3.5473 (3.6300)	grad_norm 0.9782 (1.4463/0.5034)	mem 24308MB
[2025-01-18 16:37:23 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][100/312]	eta 0:02:11 lr 0.003473	time 0.5857 (0.6196)	model_time 0.5855 (0.6014)	loss 3.8663 (3.6545)	grad_norm 0.9493 (1.4342/0.4995)	mem 24308MB
[2025-01-18 16:37:29 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][110/312]	eta 0:02:05 lr 0.003473	time 0.6609 (0.6203)	model_time 0.6608 (0.6038)	loss 4.3919 (3.6880)	grad_norm 1.7111 (1.4648/0.5309)	mem 24308MB
[2025-01-18 16:37:35 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][120/312]	eta 0:01:59 lr 0.003472	time 0.5742 (0.6202)	model_time 0.5741 (0.6050)	loss 3.6605 (3.7100)	grad_norm 1.6087 (1.4698/0.5266)	mem 24308MB
[2025-01-18 16:37:41 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][130/312]	eta 0:01:52 lr 0.003472	time 0.5790 (0.6189)	model_time 0.5785 (0.6049)	loss 3.8328 (3.7316)	grad_norm 1.3498 (1.4414/0.5175)	mem 24308MB
[2025-01-18 16:37:47 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][140/312]	eta 0:01:46 lr 0.003471	time 0.5875 (0.6170)	model_time 0.5873 (0.6039)	loss 3.8755 (3.7055)	grad_norm 2.6716 (1.4887/0.5714)	mem 24308MB
[2025-01-18 16:37:53 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][150/312]	eta 0:01:39 lr 0.003471	time 0.5828 (0.6152)	model_time 0.5826 (0.6029)	loss 4.6845 (3.6893)	grad_norm 0.6585 (1.4690/0.5717)	mem 24308MB
[2025-01-18 16:37:59 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][160/312]	eta 0:01:33 lr 0.003470	time 0.6107 (0.6139)	model_time 0.6106 (0.6023)	loss 3.8312 (3.6953)	grad_norm 1.4586 (1.4788/0.5857)	mem 24308MB
[2025-01-18 16:38:05 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][170/312]	eta 0:01:26 lr 0.003470	time 0.5780 (0.6124)	model_time 0.5775 (0.6015)	loss 4.2845 (3.6977)	grad_norm 2.4057 (1.4894/0.5902)	mem 24308MB
[2025-01-18 16:38:11 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][180/312]	eta 0:01:20 lr 0.003469	time 0.5872 (0.6112)	model_time 0.5867 (0.6009)	loss 4.1555 (3.7171)	grad_norm 1.2815 (1.4726/0.5822)	mem 24308MB
[2025-01-18 16:38:17 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][190/312]	eta 0:01:14 lr 0.003469	time 0.5750 (0.6105)	model_time 0.5748 (0.6007)	loss 3.6845 (3.7214)	grad_norm 1.0990 (1.4636/0.5781)	mem 24308MB
[2025-01-18 16:38:23 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][200/312]	eta 0:01:08 lr 0.003468	time 0.5876 (0.6112)	model_time 0.5872 (0.6019)	loss 3.3476 (3.7202)	grad_norm 1.8539 (1.4564/0.5736)	mem 24308MB
[2025-01-18 16:38:29 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][210/312]	eta 0:01:02 lr 0.003468	time 0.6602 (0.6119)	model_time 0.6600 (0.6030)	loss 4.0389 (3.7236)	grad_norm 1.4333 (1.4591/0.5613)	mem 24308MB
[2025-01-18 16:38:36 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][220/312]	eta 0:00:56 lr 0.003468	time 0.5722 (0.6122)	model_time 0.5718 (0.6037)	loss 4.2330 (3.7117)	grad_norm 1.4723 (1.4747/0.5680)	mem 24308MB
[2025-01-18 16:38:42 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][230/312]	eta 0:00:50 lr 0.003467	time 0.6652 (0.6128)	model_time 0.6650 (0.6047)	loss 3.7623 (3.7133)	grad_norm 1.1648 (1.4658/0.5615)	mem 24308MB
[2025-01-18 16:38:48 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][240/312]	eta 0:00:44 lr 0.003467	time 0.6585 (0.6137)	model_time 0.6581 (0.6059)	loss 3.4886 (3.7148)	grad_norm 0.9504 (1.4669/0.5606)	mem 24308MB
[2025-01-18 16:38:54 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][250/312]	eta 0:00:38 lr 0.003466	time 0.5909 (0.6133)	model_time 0.5908 (0.6057)	loss 4.5531 (3.7172)	grad_norm 1.3004 (1.4522/0.5564)	mem 24308MB
[2025-01-18 16:39:00 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][260/312]	eta 0:00:31 lr 0.003466	time 0.5798 (0.6127)	model_time 0.5797 (0.6055)	loss 2.8091 (3.7091)	grad_norm 1.9592 (1.4658/0.5833)	mem 24308MB
[2025-01-18 16:39:06 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][270/312]	eta 0:00:25 lr 0.003465	time 0.6025 (0.6119)	model_time 0.6023 (0.6049)	loss 3.5570 (3.7112)	grad_norm 1.4504 (1.4728/0.5798)	mem 24308MB
[2025-01-18 16:39:12 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][280/312]	eta 0:00:19 lr 0.003465	time 0.6009 (0.6111)	model_time 0.6008 (0.6043)	loss 3.7461 (3.7088)	grad_norm 1.0330 (1.4762/0.5760)	mem 24308MB
[2025-01-18 16:39:18 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][290/312]	eta 0:00:13 lr 0.003464	time 0.5917 (0.6105)	model_time 0.5915 (0.6039)	loss 3.0675 (3.7134)	grad_norm 1.4635 (1.4912/0.5872)	mem 24308MB
[2025-01-18 16:39:24 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][300/312]	eta 0:00:07 lr 0.003464	time 0.5694 (0.6094)	model_time 0.5693 (0.6031)	loss 3.6581 (3.7153)	grad_norm 0.9099 (1.4907/0.5861)	mem 24308MB
[2025-01-18 16:39:29 internimage_s_1k_224] (main.py 510): INFO Train: [71/300][310/312]	eta 0:00:01 lr 0.003463	time 0.5688 (0.6081)	model_time 0.5687 (0.6020)	loss 4.1024 (3.7180)	grad_norm 1.2125 (1.4751/0.5853)	mem 24308MB
[2025-01-18 16:39:30 internimage_s_1k_224] (main.py 519): INFO EPOCH 71 training takes 0:03:09
[2025-01-18 16:39:30 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_71.pth saving......
[2025-01-18 16:39:32 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_71.pth saved !!!
[2025-01-18 16:39:39 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.860 (6.860)	Loss 0.9341 (0.9341)	Acc@1 79.028 (79.028)	Acc@5 95.483 (95.483)	Mem 24308MB
[2025-01-18 16:39:42 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.901)	Loss 1.3228 (1.0941)	Acc@1 70.044 (75.628)	Acc@5 90.259 (93.184)	Mem 24308MB
[2025-01-18 16:39:42 internimage_s_1k_224] (main.py 575): INFO [Epoch:71] * Acc@1 75.618 Acc@5 93.198
[2025-01-18 16:39:42 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.6%
[2025-01-18 16:39:42 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 16:39:44 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 16:39:44 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 75.62%
[2025-01-18 16:39:51 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.112 (7.112)	Loss 1.0928 (1.0928)	Acc@1 73.560 (73.560)	Acc@5 91.992 (91.992)	Mem 24308MB
[2025-01-18 16:39:54 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.136 (0.938)	Loss 1.6478 (1.3019)	Acc@1 61.133 (69.378)	Acc@5 84.717 (89.302)	Mem 24308MB
[2025-01-18 16:39:54 internimage_s_1k_224] (main.py 575): INFO [Epoch:71] * Acc@1 69.448 Acc@5 89.429
[2025-01-18 16:39:54 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 69.4%
[2025-01-18 16:39:54 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 16:39:57 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 16:39:57 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 69.45%
[2025-01-18 16:39:59 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][0/312]	eta 0:14:00 lr 0.003463	time 2.6932 (2.6932)	model_time 0.6405 (0.6405)	loss 2.8909 (2.8909)	grad_norm 1.2944 (1.2944/0.0000)	mem 24308MB
[2025-01-18 16:40:05 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][10/312]	eta 0:04:03 lr 0.003463	time 0.5718 (0.8050)	model_time 0.5716 (0.6182)	loss 3.9759 (3.4351)	grad_norm 1.8429 (1.4968/0.5695)	mem 24308MB
[2025-01-18 16:40:12 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][20/312]	eta 0:03:29 lr 0.003462	time 0.6149 (0.7174)	model_time 0.6147 (0.6194)	loss 4.2973 (3.5653)	grad_norm 3.2646 (1.5544/0.6003)	mem 24308MB
[2025-01-18 16:40:18 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][30/312]	eta 0:03:15 lr 0.003462	time 0.5767 (0.6923)	model_time 0.5765 (0.6258)	loss 3.3921 (3.5625)	grad_norm 1.1729 (1.6932/0.8609)	mem 24308MB
[2025-01-18 16:40:24 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][40/312]	eta 0:03:03 lr 0.003462	time 0.5904 (0.6742)	model_time 0.5900 (0.6238)	loss 3.9625 (3.5866)	grad_norm 0.7040 (1.5857/0.8205)	mem 24308MB
[2025-01-18 16:40:30 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][50/312]	eta 0:02:53 lr 0.003461	time 0.6738 (0.6639)	model_time 0.6736 (0.6233)	loss 3.8012 (3.6714)	grad_norm 1.7723 (1.5851/0.7837)	mem 24308MB
[2025-01-18 16:40:36 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][60/312]	eta 0:02:44 lr 0.003461	time 0.6784 (0.6538)	model_time 0.6783 (0.6198)	loss 4.0384 (3.6742)	grad_norm 1.9150 (1.5400/0.7407)	mem 24308MB
[2025-01-18 16:40:42 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][70/312]	eta 0:02:36 lr 0.003460	time 0.5764 (0.6450)	model_time 0.5762 (0.6157)	loss 2.2474 (3.6593)	grad_norm 0.7465 (1.4986/0.7055)	mem 24308MB
[2025-01-18 16:40:48 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][80/312]	eta 0:02:28 lr 0.003460	time 0.5795 (0.6386)	model_time 0.5790 (0.6129)	loss 2.3326 (3.6295)	grad_norm 1.2166 (1.4916/0.6965)	mem 24308MB
[2025-01-18 16:40:54 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][90/312]	eta 0:02:20 lr 0.003459	time 0.5967 (0.6331)	model_time 0.5965 (0.6102)	loss 4.5086 (3.6322)	grad_norm 2.3154 (1.5292/0.7014)	mem 24308MB
[2025-01-18 16:41:00 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][100/312]	eta 0:02:13 lr 0.003459	time 0.5701 (0.6290)	model_time 0.5697 (0.6084)	loss 3.9203 (3.6146)	grad_norm 2.4858 (1.5768/0.7222)	mem 24308MB
[2025-01-18 16:41:06 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][110/312]	eta 0:02:06 lr 0.003458	time 0.5779 (0.6251)	model_time 0.5777 (0.6063)	loss 4.6431 (3.6248)	grad_norm 1.0543 (1.5716/0.7122)	mem 24308MB
[2025-01-18 16:41:12 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][120/312]	eta 0:01:59 lr 0.003458	time 0.6726 (0.6225)	model_time 0.6724 (0.6052)	loss 4.4217 (3.6286)	grad_norm 0.9141 (1.5549/0.6937)	mem 24308MB
[2025-01-18 16:41:18 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][130/312]	eta 0:01:53 lr 0.003457	time 0.5715 (0.6219)	model_time 0.5711 (0.6059)	loss 3.9654 (3.6023)	grad_norm 1.6030 (1.5513/0.6734)	mem 24308MB
[2025-01-18 16:41:24 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][140/312]	eta 0:01:46 lr 0.003457	time 0.5720 (0.6215)	model_time 0.5718 (0.6066)	loss 3.4222 (3.6169)	grad_norm 0.8144 (1.5465/0.6603)	mem 24308MB
[2025-01-18 16:41:31 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][150/312]	eta 0:01:40 lr 0.003457	time 0.5825 (0.6223)	model_time 0.5824 (0.6084)	loss 4.5231 (3.6201)	grad_norm 0.9028 (1.5600/0.6698)	mem 24308MB
[2025-01-18 16:41:37 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][160/312]	eta 0:01:34 lr 0.003456	time 0.6880 (0.6234)	model_time 0.6876 (0.6103)	loss 3.4065 (3.6270)	grad_norm 1.2781 (1.5365/0.6559)	mem 24308MB
[2025-01-18 16:41:43 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][170/312]	eta 0:01:28 lr 0.003456	time 0.5915 (0.6226)	model_time 0.5910 (0.6102)	loss 3.8117 (3.6408)	grad_norm 1.3534 (1.5100/0.6490)	mem 24308MB
[2025-01-18 16:41:49 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][180/312]	eta 0:01:22 lr 0.003455	time 0.6515 (0.6220)	model_time 0.6510 (0.6103)	loss 3.4562 (3.6421)	grad_norm 2.3623 (1.5394/0.6780)	mem 24308MB
[2025-01-18 16:41:55 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][190/312]	eta 0:01:15 lr 0.003455	time 0.6178 (0.6207)	model_time 0.6174 (0.6096)	loss 4.0446 (3.6461)	grad_norm 1.7299 (1.5348/0.6686)	mem 24308MB
[2025-01-18 16:42:01 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][200/312]	eta 0:01:09 lr 0.003454	time 0.6344 (0.6197)	model_time 0.6339 (0.6091)	loss 2.8228 (3.6432)	grad_norm 1.3569 (1.5386/0.6604)	mem 24308MB
[2025-01-18 16:42:07 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][210/312]	eta 0:01:03 lr 0.003454	time 0.5762 (0.6183)	model_time 0.5758 (0.6082)	loss 3.1176 (3.6320)	grad_norm 1.3774 (1.5236/0.6508)	mem 24308MB
[2025-01-18 16:42:13 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][220/312]	eta 0:00:56 lr 0.003453	time 0.5766 (0.6169)	model_time 0.5764 (0.6072)	loss 3.3937 (3.6199)	grad_norm 2.9862 (1.5271/0.6478)	mem 24308MB
[2025-01-18 16:42:19 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][230/312]	eta 0:00:50 lr 0.003453	time 0.5813 (0.6156)	model_time 0.5811 (0.6064)	loss 3.3404 (3.6071)	grad_norm 0.7885 (1.5329/0.6685)	mem 24308MB
[2025-01-18 16:42:25 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][240/312]	eta 0:00:44 lr 0.003452	time 0.6872 (0.6152)	model_time 0.6867 (0.6063)	loss 2.7336 (3.6025)	grad_norm 2.6170 (1.5309/0.6634)	mem 24308MB
[2025-01-18 16:42:31 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][250/312]	eta 0:00:38 lr 0.003452	time 0.6185 (0.6155)	model_time 0.6183 (0.6070)	loss 2.8079 (3.6042)	grad_norm 1.5028 (1.5388/0.6618)	mem 24308MB
[2025-01-18 16:42:37 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][260/312]	eta 0:00:32 lr 0.003451	time 0.5950 (0.6155)	model_time 0.5946 (0.6072)	loss 4.7226 (3.6074)	grad_norm 1.9274 (1.5321/0.6553)	mem 24308MB
[2025-01-18 16:42:44 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][270/312]	eta 0:00:25 lr 0.003451	time 0.5711 (0.6159)	model_time 0.5707 (0.6080)	loss 2.5736 (3.6094)	grad_norm 1.4935 (1.5357/0.6566)	mem 24308MB
[2025-01-18 16:42:50 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][280/312]	eta 0:00:19 lr 0.003451	time 0.6562 (0.6162)	model_time 0.6558 (0.6086)	loss 3.9235 (3.6157)	grad_norm 1.3976 (1.5324/0.6526)	mem 24308MB
[2025-01-18 16:42:56 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][290/312]	eta 0:00:13 lr 0.003450	time 0.5842 (0.6165)	model_time 0.5840 (0.6091)	loss 3.4502 (3.6182)	grad_norm 0.8606 (1.5459/0.6674)	mem 24308MB
[2025-01-18 16:43:02 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][300/312]	eta 0:00:07 lr 0.003450	time 0.5672 (0.6159)	model_time 0.5671 (0.6087)	loss 3.0420 (3.6222)	grad_norm 1.6568 (1.5317/0.6640)	mem 24308MB
[2025-01-18 16:43:08 internimage_s_1k_224] (main.py 510): INFO Train: [72/300][310/312]	eta 0:00:01 lr 0.003449	time 0.5688 (0.6151)	model_time 0.5687 (0.6081)	loss 3.6997 (3.6126)	grad_norm 2.8805 (1.5337/0.6659)	mem 24308MB
[2025-01-18 16:43:08 internimage_s_1k_224] (main.py 519): INFO EPOCH 72 training takes 0:03:11
[2025-01-18 16:43:08 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_72.pth saving......
[2025-01-18 16:43:10 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_72.pth saved !!!
[2025-01-18 16:43:18 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.349 (7.349)	Loss 0.9904 (0.9904)	Acc@1 79.370 (79.370)	Acc@5 95.654 (95.654)	Mem 24308MB
[2025-01-18 16:43:21 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.957)	Loss 1.3602 (1.1551)	Acc@1 71.387 (75.672)	Acc@5 90.503 (93.226)	Mem 24308MB
[2025-01-18 16:43:21 internimage_s_1k_224] (main.py 575): INFO [Epoch:72] * Acc@1 75.664 Acc@5 93.240
[2025-01-18 16:43:21 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.7%
[2025-01-18 16:43:21 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 16:43:23 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 16:43:23 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 75.66%
[2025-01-18 16:43:30 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.062 (7.062)	Loss 1.0742 (1.0742)	Acc@1 73.877 (73.877)	Acc@5 92.261 (92.261)	Mem 24308MB
[2025-01-18 16:43:34 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.950)	Loss 1.6213 (1.2802)	Acc@1 61.768 (69.806)	Acc@5 85.107 (89.580)	Mem 24308MB
[2025-01-18 16:43:34 internimage_s_1k_224] (main.py 575): INFO [Epoch:72] * Acc@1 69.874 Acc@5 89.717
[2025-01-18 16:43:34 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 69.9%
[2025-01-18 16:43:34 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 16:43:36 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 16:43:36 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 69.87%
[2025-01-18 16:43:38 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][0/312]	eta 0:12:15 lr 0.003449	time 2.3568 (2.3568)	model_time 0.6025 (0.6025)	loss 4.2889 (4.2889)	grad_norm 1.9396 (1.9396/0.0000)	mem 24308MB
[2025-01-18 16:43:44 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][10/312]	eta 0:03:46 lr 0.003449	time 0.5852 (0.7490)	model_time 0.5851 (0.5893)	loss 4.3733 (3.9412)	grad_norm 1.3799 (1.4176/0.4821)	mem 24308MB
[2025-01-18 16:43:50 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][20/312]	eta 0:03:16 lr 0.003448	time 0.5754 (0.6726)	model_time 0.5752 (0.5887)	loss 3.5323 (3.7109)	grad_norm 1.7848 (1.3541/0.4395)	mem 24308MB
[2025-01-18 16:43:56 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][30/312]	eta 0:03:01 lr 0.003448	time 0.5876 (0.6453)	model_time 0.5874 (0.5884)	loss 3.6975 (3.7730)	grad_norm 2.0677 (1.4015/0.4811)	mem 24308MB
[2025-01-18 16:44:02 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][40/312]	eta 0:02:51 lr 0.003447	time 0.5784 (0.6313)	model_time 0.5783 (0.5879)	loss 4.5505 (3.7545)	grad_norm 2.0287 (1.4685/0.4969)	mem 24308MB
[2025-01-18 16:44:08 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][50/312]	eta 0:02:43 lr 0.003447	time 0.5761 (0.6230)	model_time 0.5759 (0.5880)	loss 3.5007 (3.6688)	grad_norm 0.6713 (1.4421/0.5389)	mem 24308MB
[2025-01-18 16:44:14 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][60/312]	eta 0:02:37 lr 0.003446	time 0.6334 (0.6233)	model_time 0.6330 (0.5939)	loss 3.3832 (3.6688)	grad_norm 1.1916 (1.5393/0.6834)	mem 24308MB
[2025-01-18 16:44:20 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][70/312]	eta 0:02:30 lr 0.003446	time 0.5775 (0.6238)	model_time 0.5771 (0.5985)	loss 3.4499 (3.6544)	grad_norm 0.8094 (1.5013/0.6534)	mem 24308MB
[2025-01-18 16:44:27 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][80/312]	eta 0:02:25 lr 0.003445	time 0.6042 (0.6254)	model_time 0.6040 (0.6033)	loss 3.9529 (3.6483)	grad_norm 2.2129 (1.4977/0.6342)	mem 24308MB
[2025-01-18 16:44:33 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][90/312]	eta 0:02:19 lr 0.003445	time 0.5791 (0.6261)	model_time 0.5789 (0.6064)	loss 4.0389 (3.6181)	grad_norm 1.5068 (1.5127/0.6310)	mem 24308MB
[2025-01-18 16:44:39 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][100/312]	eta 0:02:12 lr 0.003444	time 0.5894 (0.6245)	model_time 0.5892 (0.6066)	loss 3.2778 (3.5913)	grad_norm 1.8166 (1.5302/0.6324)	mem 24308MB
[2025-01-18 16:44:45 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][110/312]	eta 0:02:05 lr 0.003444	time 0.5848 (0.6226)	model_time 0.5844 (0.6063)	loss 3.3315 (3.5866)	grad_norm 1.0809 (1.5009/0.6207)	mem 24308MB
[2025-01-18 16:44:51 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][120/312]	eta 0:01:59 lr 0.003444	time 0.5861 (0.6210)	model_time 0.5857 (0.6060)	loss 2.4984 (3.5921)	grad_norm 1.3446 (1.5435/0.6343)	mem 24308MB
[2025-01-18 16:44:57 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][130/312]	eta 0:01:52 lr 0.003443	time 0.6102 (0.6184)	model_time 0.6101 (0.6045)	loss 3.7421 (3.5881)	grad_norm 1.5980 (1.5294/0.6191)	mem 24308MB
[2025-01-18 16:45:03 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][140/312]	eta 0:01:45 lr 0.003443	time 0.5922 (0.6162)	model_time 0.5921 (0.6033)	loss 3.6282 (3.6065)	grad_norm 3.1511 (1.5215/0.6241)	mem 24308MB
[2025-01-18 16:45:09 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][150/312]	eta 0:01:39 lr 0.003442	time 0.5843 (0.6144)	model_time 0.5841 (0.6023)	loss 3.5581 (3.5982)	grad_norm 1.4823 (1.5281/0.6217)	mem 24308MB
[2025-01-18 16:45:15 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][160/312]	eta 0:01:33 lr 0.003442	time 0.5833 (0.6129)	model_time 0.5828 (0.6016)	loss 3.8565 (3.6012)	grad_norm 1.6027 (1.5235/0.6303)	mem 24308MB
[2025-01-18 16:45:21 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][170/312]	eta 0:01:26 lr 0.003441	time 0.5975 (0.6115)	model_time 0.5973 (0.6008)	loss 3.9231 (3.6052)	grad_norm 1.4982 (1.4995/0.6237)	mem 24308MB
[2025-01-18 16:45:27 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][180/312]	eta 0:01:20 lr 0.003441	time 0.6546 (0.6114)	model_time 0.6543 (0.6013)	loss 3.2558 (3.6001)	grad_norm 2.3909 (1.5169/0.6379)	mem 24308MB
[2025-01-18 16:45:33 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][190/312]	eta 0:01:14 lr 0.003440	time 0.5766 (0.6123)	model_time 0.5765 (0.6027)	loss 2.8094 (3.6081)	grad_norm 1.7422 (1.5129/0.6241)	mem 24308MB
[2025-01-18 16:45:39 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][200/312]	eta 0:01:08 lr 0.003440	time 0.5820 (0.6128)	model_time 0.5818 (0.6037)	loss 4.0352 (3.6052)	grad_norm 0.9310 (1.5181/0.6282)	mem 24308MB
[2025-01-18 16:45:46 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][210/312]	eta 0:01:02 lr 0.003439	time 0.6590 (0.6141)	model_time 0.6586 (0.6054)	loss 3.8993 (3.6094)	grad_norm 1.5201 (1.5145/0.6182)	mem 24308MB
[2025-01-18 16:45:52 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][220/312]	eta 0:00:56 lr 0.003439	time 0.5873 (0.6141)	model_time 0.5869 (0.6058)	loss 3.7915 (3.6130)	grad_norm 2.1387 (1.5037/0.6118)	mem 24308MB
[2025-01-18 16:45:58 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][230/312]	eta 0:00:50 lr 0.003438	time 0.5833 (0.6134)	model_time 0.5831 (0.6054)	loss 3.5651 (3.6139)	grad_norm 0.9320 (1.4986/0.6043)	mem 24308MB
[2025-01-18 16:46:04 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][240/312]	eta 0:00:44 lr 0.003438	time 0.5797 (0.6133)	model_time 0.5795 (0.6056)	loss 4.1650 (3.6243)	grad_norm 1.3694 (1.4851/0.5990)	mem 24308MB
[2025-01-18 16:46:10 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][250/312]	eta 0:00:37 lr 0.003438	time 0.5883 (0.6123)	model_time 0.5881 (0.6048)	loss 3.7769 (3.6157)	grad_norm 1.0068 (1.4764/0.5914)	mem 24308MB
[2025-01-18 16:46:16 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][260/312]	eta 0:00:31 lr 0.003437	time 0.5765 (0.6116)	model_time 0.5760 (0.6045)	loss 4.4343 (3.6145)	grad_norm 2.0242 (1.4861/0.5922)	mem 24308MB
[2025-01-18 16:46:21 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][270/312]	eta 0:00:25 lr 0.003437	time 0.5832 (0.6106)	model_time 0.5828 (0.6037)	loss 3.1873 (3.6104)	grad_norm 0.6716 (1.4900/0.5966)	mem 24308MB
[2025-01-18 16:46:27 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][280/312]	eta 0:00:19 lr 0.003436	time 0.6049 (0.6097)	model_time 0.6045 (0.6030)	loss 2.5730 (3.6016)	grad_norm 2.8311 (1.5054/0.6055)	mem 24308MB
[2025-01-18 16:46:33 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][290/312]	eta 0:00:13 lr 0.003436	time 0.5915 (0.6092)	model_time 0.5914 (0.6027)	loss 3.8428 (3.5983)	grad_norm 1.3761 (1.5041/0.6046)	mem 24308MB
[2025-01-18 16:46:39 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][300/312]	eta 0:00:07 lr 0.003435	time 0.5757 (0.6086)	model_time 0.5756 (0.6024)	loss 2.5969 (3.5978)	grad_norm 1.8856 (1.4968/0.5990)	mem 24308MB
[2025-01-18 16:46:45 internimage_s_1k_224] (main.py 510): INFO Train: [73/300][310/312]	eta 0:00:01 lr 0.003435	time 0.6410 (0.6089)	model_time 0.6409 (0.6028)	loss 3.7567 (3.6081)	grad_norm 1.1145 (1.5068/0.6033)	mem 24308MB
[2025-01-18 16:46:46 internimage_s_1k_224] (main.py 519): INFO EPOCH 73 training takes 0:03:09
[2025-01-18 16:46:46 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_73.pth saving......
[2025-01-18 16:46:48 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_73.pth saved !!!
[2025-01-18 16:46:55 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.365 (7.365)	Loss 0.9443 (0.9443)	Acc@1 79.932 (79.932)	Acc@5 95.874 (95.874)	Mem 24308MB
[2025-01-18 16:46:59 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.134 (0.978)	Loss 1.3641 (1.1139)	Acc@1 69.727 (75.639)	Acc@5 90.063 (93.233)	Mem 24308MB
[2025-01-18 16:46:59 internimage_s_1k_224] (main.py 575): INFO [Epoch:73] * Acc@1 75.590 Acc@5 93.284
[2025-01-18 16:46:59 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.6%
[2025-01-18 16:46:59 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 75.66%
[2025-01-18 16:47:07 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.523 (8.523)	Loss 1.0564 (1.0564)	Acc@1 74.365 (74.365)	Acc@5 92.676 (92.676)	Mem 24308MB
[2025-01-18 16:47:11 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.144)	Loss 1.5963 (1.2600)	Acc@1 61.914 (70.204)	Acc@5 85.522 (89.888)	Mem 24308MB
[2025-01-18 16:47:11 internimage_s_1k_224] (main.py 575): INFO [Epoch:73] * Acc@1 70.274 Acc@5 90.025
[2025-01-18 16:47:11 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 70.3%
[2025-01-18 16:47:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 16:47:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 16:47:14 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 70.27%
[2025-01-18 16:47:16 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][0/312]	eta 0:11:56 lr 0.003435	time 2.2974 (2.2974)	model_time 0.5951 (0.5951)	loss 3.4619 (3.4619)	grad_norm 0.8722 (0.8722/0.0000)	mem 24308MB
[2025-01-18 16:47:23 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][10/312]	eta 0:03:55 lr 0.003434	time 0.5882 (0.7794)	model_time 0.5880 (0.6244)	loss 4.0760 (3.6219)	grad_norm 1.5281 (1.5635/0.4867)	mem 24308MB
[2025-01-18 16:47:29 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][20/312]	eta 0:03:28 lr 0.003434	time 0.5958 (0.7124)	model_time 0.5955 (0.6311)	loss 3.6926 (3.7224)	grad_norm 2.0773 (1.8906/0.8350)	mem 24308MB
[2025-01-18 16:47:35 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][30/312]	eta 0:03:12 lr 0.003433	time 0.5942 (0.6843)	model_time 0.5937 (0.6291)	loss 4.3834 (3.5851)	grad_norm 1.0477 (1.7510/0.7824)	mem 24308MB
[2025-01-18 16:47:41 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][40/312]	eta 0:03:00 lr 0.003433	time 0.5860 (0.6652)	model_time 0.5857 (0.6234)	loss 3.3633 (3.6196)	grad_norm 1.1624 (1.7801/0.7987)	mem 24308MB
[2025-01-18 16:47:47 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][50/312]	eta 0:02:51 lr 0.003432	time 0.5892 (0.6527)	model_time 0.5888 (0.6190)	loss 4.3813 (3.6060)	grad_norm 1.9195 (1.6990/0.7431)	mem 24308MB
[2025-01-18 16:47:53 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][60/312]	eta 0:02:41 lr 0.003432	time 0.5755 (0.6411)	model_time 0.5750 (0.6128)	loss 3.7692 (3.6028)	grad_norm 1.6228 (1.6290/0.7115)	mem 24308MB
[2025-01-18 16:47:59 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][70/312]	eta 0:02:33 lr 0.003431	time 0.5882 (0.6333)	model_time 0.5880 (0.6090)	loss 3.8048 (3.6156)	grad_norm 1.2345 (1.5432/0.6996)	mem 24308MB
[2025-01-18 16:48:05 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][80/312]	eta 0:02:25 lr 0.003431	time 0.5983 (0.6275)	model_time 0.5982 (0.6061)	loss 2.6153 (3.5939)	grad_norm 2.1584 (1.6116/0.7460)	mem 24308MB
[2025-01-18 16:48:11 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][90/312]	eta 0:02:18 lr 0.003430	time 0.5729 (0.6236)	model_time 0.5727 (0.6046)	loss 4.3195 (3.6050)	grad_norm 0.7150 (1.5461/0.7333)	mem 24308MB
[2025-01-18 16:48:17 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][100/312]	eta 0:02:11 lr 0.003430	time 0.6050 (0.6199)	model_time 0.6048 (0.6027)	loss 3.6993 (3.5824)	grad_norm 0.9129 (1.5249/0.7124)	mem 24308MB
[2025-01-18 16:48:23 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][110/312]	eta 0:02:05 lr 0.003430	time 0.5748 (0.6196)	model_time 0.5747 (0.6039)	loss 4.3983 (3.5963)	grad_norm 1.0703 (1.4938/0.6982)	mem 24308MB
[2025-01-18 16:48:29 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][120/312]	eta 0:01:59 lr 0.003429	time 0.6597 (0.6202)	model_time 0.6596 (0.6058)	loss 4.4835 (3.5888)	grad_norm 1.6883 (1.4610/0.6837)	mem 24308MB
[2025-01-18 16:48:35 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][130/312]	eta 0:01:52 lr 0.003429	time 0.5778 (0.6204)	model_time 0.5776 (0.6071)	loss 3.8650 (3.5936)	grad_norm 0.9640 (1.4855/0.7072)	mem 24308MB
[2025-01-18 16:48:42 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][140/312]	eta 0:01:46 lr 0.003428	time 0.6735 (0.6220)	model_time 0.6731 (0.6095)	loss 4.2082 (3.6119)	grad_norm 1.4564 (1.4928/0.6963)	mem 24308MB
[2025-01-18 16:48:48 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][150/312]	eta 0:01:40 lr 0.003428	time 0.5748 (0.6225)	model_time 0.5747 (0.6108)	loss 3.7239 (3.6223)	grad_norm 2.4383 (1.5411/0.7531)	mem 24308MB
[2025-01-18 16:48:54 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][160/312]	eta 0:01:34 lr 0.003427	time 0.5792 (0.6217)	model_time 0.5791 (0.6107)	loss 3.4445 (3.6136)	grad_norm 1.2194 (1.5135/0.7384)	mem 24308MB
[2025-01-18 16:49:00 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][170/312]	eta 0:01:28 lr 0.003427	time 0.5841 (0.6199)	model_time 0.5836 (0.6095)	loss 3.9434 (3.6138)	grad_norm 0.8936 (1.5070/0.7223)	mem 24308MB
[2025-01-18 16:49:06 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][180/312]	eta 0:01:21 lr 0.003426	time 0.5997 (0.6185)	model_time 0.5996 (0.6087)	loss 3.0104 (3.6294)	grad_norm 0.8395 (1.4836/0.7111)	mem 24308MB
[2025-01-18 16:49:12 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][190/312]	eta 0:01:15 lr 0.003426	time 0.5921 (0.6170)	model_time 0.5919 (0.6077)	loss 4.7243 (3.6358)	grad_norm 1.5274 (1.4705/0.6984)	mem 24308MB
[2025-01-18 16:49:18 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][200/312]	eta 0:01:08 lr 0.003425	time 0.5804 (0.6156)	model_time 0.5803 (0.6068)	loss 2.2915 (3.6094)	grad_norm 0.7848 (1.4773/0.7087)	mem 24308MB
[2025-01-18 16:49:24 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][210/312]	eta 0:01:02 lr 0.003425	time 0.5716 (0.6148)	model_time 0.5714 (0.6063)	loss 2.2779 (3.6058)	grad_norm 1.2454 (1.4626/0.6971)	mem 24308MB
[2025-01-18 16:49:30 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][220/312]	eta 0:00:56 lr 0.003424	time 0.5840 (0.6136)	model_time 0.5838 (0.6055)	loss 4.0880 (3.6150)	grad_norm 1.4687 (1.4527/0.6855)	mem 24308MB
[2025-01-18 16:49:36 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][230/312]	eta 0:00:50 lr 0.003424	time 0.5768 (0.6131)	model_time 0.5764 (0.6054)	loss 3.3443 (3.6237)	grad_norm 1.3679 (1.4655/0.7022)	mem 24308MB
[2025-01-18 16:49:42 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][240/312]	eta 0:00:44 lr 0.003423	time 0.5833 (0.6130)	model_time 0.5829 (0.6055)	loss 3.8125 (3.6246)	grad_norm 0.7893 (1.4465/0.6960)	mem 24308MB
[2025-01-18 16:49:48 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][250/312]	eta 0:00:38 lr 0.003423	time 0.6632 (0.6137)	model_time 0.6628 (0.6065)	loss 3.3693 (3.6154)	grad_norm 1.4575 (1.4424/0.6870)	mem 24308MB
[2025-01-18 16:49:54 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][260/312]	eta 0:00:31 lr 0.003423	time 0.5755 (0.6138)	model_time 0.5753 (0.6069)	loss 3.7434 (3.6228)	grad_norm 2.0345 (1.4465/0.6798)	mem 24308MB
[2025-01-18 16:50:01 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][270/312]	eta 0:00:25 lr 0.003422	time 0.5905 (0.6150)	model_time 0.5903 (0.6083)	loss 3.6767 (3.6200)	grad_norm 1.4987 (1.4527/0.6813)	mem 24308MB
[2025-01-18 16:50:07 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][280/312]	eta 0:00:19 lr 0.003422	time 0.5783 (0.6148)	model_time 0.5781 (0.6083)	loss 3.8680 (3.6213)	grad_norm 0.8900 (1.4403/0.6732)	mem 24308MB
[2025-01-18 16:50:13 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][290/312]	eta 0:00:13 lr 0.003421	time 0.5851 (0.6140)	model_time 0.5849 (0.6077)	loss 3.8758 (3.6167)	grad_norm 0.9788 (1.4300/0.6650)	mem 24308MB
[2025-01-18 16:50:19 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][300/312]	eta 0:00:07 lr 0.003421	time 0.5672 (0.6133)	model_time 0.5671 (0.6072)	loss 3.0017 (3.6136)	grad_norm 1.8109 (1.4524/0.7031)	mem 24308MB
[2025-01-18 16:50:24 internimage_s_1k_224] (main.py 510): INFO Train: [74/300][310/312]	eta 0:00:01 lr 0.003420	time 0.6276 (0.6121)	model_time 0.6275 (0.6062)	loss 3.8878 (3.6066)	grad_norm 4.2294 (1.4617/0.7375)	mem 24308MB
[2025-01-18 16:50:25 internimage_s_1k_224] (main.py 519): INFO EPOCH 74 training takes 0:03:10
[2025-01-18 16:50:25 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_74.pth saving......
[2025-01-18 16:50:27 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_74.pth saved !!!
[2025-01-18 16:50:34 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.142 (7.142)	Loss 0.9246 (0.9246)	Acc@1 79.541 (79.541)	Acc@5 95.459 (95.459)	Mem 24308MB
[2025-01-18 16:50:37 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.945)	Loss 1.3107 (1.1048)	Acc@1 70.386 (75.555)	Acc@5 90.771 (93.308)	Mem 24308MB
[2025-01-18 16:50:37 internimage_s_1k_224] (main.py 575): INFO [Epoch:74] * Acc@1 75.520 Acc@5 93.370
[2025-01-18 16:50:37 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.5%
[2025-01-18 16:50:37 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 75.66%
[2025-01-18 16:50:46 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.157 (8.157)	Loss 1.0395 (1.0395)	Acc@1 74.731 (74.731)	Acc@5 93.042 (93.042)	Mem 24308MB
[2025-01-18 16:50:50 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.103)	Loss 1.5727 (1.2408)	Acc@1 62.476 (70.552)	Acc@5 85.718 (90.152)	Mem 24308MB
[2025-01-18 16:50:50 internimage_s_1k_224] (main.py 575): INFO [Epoch:74] * Acc@1 70.613 Acc@5 90.299
[2025-01-18 16:50:50 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 70.6%
[2025-01-18 16:50:50 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 16:50:52 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 16:50:52 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 70.61%
[2025-01-18 16:50:54 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][0/312]	eta 0:10:49 lr 0.003420	time 2.0808 (2.0808)	model_time 0.6118 (0.6118)	loss 3.8571 (3.8571)	grad_norm 2.8471 (2.8471/0.0000)	mem 24308MB
[2025-01-18 16:51:00 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][10/312]	eta 0:03:38 lr 0.003420	time 0.5866 (0.7250)	model_time 0.5864 (0.5912)	loss 3.2173 (3.3838)	grad_norm 1.0987 (1.4682/0.6321)	mem 24308MB
[2025-01-18 16:51:06 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][20/312]	eta 0:03:13 lr 0.003419	time 0.5842 (0.6622)	model_time 0.5837 (0.5919)	loss 3.9921 (3.3532)	grad_norm 0.7121 (1.2925/0.5224)	mem 24308MB
[2025-01-18 16:51:12 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][30/312]	eta 0:03:00 lr 0.003419	time 0.5916 (0.6412)	model_time 0.5914 (0.5934)	loss 4.1158 (3.3753)	grad_norm 0.8839 (1.3156/0.5461)	mem 24308MB
[2025-01-18 16:51:18 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][40/312]	eta 0:02:52 lr 0.003418	time 0.7137 (0.6354)	model_time 0.7132 (0.5992)	loss 2.8541 (3.4152)	grad_norm 1.9997 (1.3762/0.5730)	mem 24308MB
[2025-01-18 16:51:24 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][50/312]	eta 0:02:45 lr 0.003418	time 0.6625 (0.6311)	model_time 0.6623 (0.6020)	loss 3.4800 (3.4776)	grad_norm 2.2890 (1.4174/0.5632)	mem 24308MB
[2025-01-18 16:51:31 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][60/312]	eta 0:02:38 lr 0.003417	time 0.5799 (0.6308)	model_time 0.5794 (0.6063)	loss 4.1502 (3.5617)	grad_norm 0.9817 (1.4158/0.5444)	mem 24308MB
[2025-01-18 16:51:37 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][70/312]	eta 0:02:32 lr 0.003417	time 0.5831 (0.6298)	model_time 0.5826 (0.6087)	loss 3.6236 (3.5684)	grad_norm 2.1626 (1.3952/0.5306)	mem 24308MB
[2025-01-18 16:51:43 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][80/312]	eta 0:02:25 lr 0.003416	time 0.6634 (0.6293)	model_time 0.6629 (0.6108)	loss 3.2763 (3.5832)	grad_norm 2.1360 (1.4248/0.5712)	mem 24308MB
[2025-01-18 16:51:49 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][90/312]	eta 0:02:19 lr 0.003416	time 0.6897 (0.6267)	model_time 0.6895 (0.6102)	loss 3.3108 (3.5779)	grad_norm 1.5007 (1.4401/0.5785)	mem 24308MB
[2025-01-18 16:51:55 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][100/312]	eta 0:02:12 lr 0.003415	time 0.5868 (0.6229)	model_time 0.5863 (0.6080)	loss 2.9082 (3.5544)	grad_norm 1.4008 (1.4198/0.5695)	mem 24308MB
[2025-01-18 16:52:01 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][110/312]	eta 0:02:05 lr 0.003415	time 0.5842 (0.6206)	model_time 0.5840 (0.6070)	loss 2.7884 (3.5578)	grad_norm 1.0779 (1.4027/0.5585)	mem 24308MB
[2025-01-18 16:52:07 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][120/312]	eta 0:01:58 lr 0.003414	time 0.5776 (0.6183)	model_time 0.5774 (0.6058)	loss 3.0789 (3.5603)	grad_norm 1.0128 (1.4186/0.5774)	mem 24308MB
[2025-01-18 16:52:13 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][130/312]	eta 0:01:52 lr 0.003414	time 0.5741 (0.6163)	model_time 0.5739 (0.6047)	loss 3.8604 (3.5694)	grad_norm 1.3946 (1.4468/0.5956)	mem 24308MB
[2025-01-18 16:52:19 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][140/312]	eta 0:01:45 lr 0.003413	time 0.5963 (0.6151)	model_time 0.5961 (0.6044)	loss 4.2150 (3.5675)	grad_norm 4.4188 (1.4926/0.6679)	mem 24308MB
[2025-01-18 16:52:25 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][150/312]	eta 0:01:39 lr 0.003413	time 0.5876 (0.6134)	model_time 0.5874 (0.6033)	loss 4.5910 (3.5774)	grad_norm 1.5701 (1.4954/0.6627)	mem 24308MB
[2025-01-18 16:52:31 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][160/312]	eta 0:01:33 lr 0.003413	time 0.6762 (0.6127)	model_time 0.6758 (0.6032)	loss 3.8684 (3.5920)	grad_norm 1.2056 (1.4830/0.6517)	mem 24308MB
[2025-01-18 16:52:37 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][170/312]	eta 0:01:27 lr 0.003412	time 0.6584 (0.6132)	model_time 0.6582 (0.6042)	loss 3.8445 (3.5980)	grad_norm 1.1244 (1.4717/0.6392)	mem 24308MB
[2025-01-18 16:52:43 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][180/312]	eta 0:01:21 lr 0.003412	time 0.5775 (0.6141)	model_time 0.5771 (0.6056)	loss 4.1402 (3.6084)	grad_norm 1.5745 (1.4780/0.6399)	mem 24308MB
[2025-01-18 16:52:49 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][190/312]	eta 0:01:14 lr 0.003411	time 0.5712 (0.6142)	model_time 0.5710 (0.6062)	loss 4.3043 (3.6097)	grad_norm 1.0451 (1.4779/0.6375)	mem 24308MB
[2025-01-18 16:52:56 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][200/312]	eta 0:01:08 lr 0.003411	time 0.5720 (0.6152)	model_time 0.5719 (0.6075)	loss 3.7354 (3.6173)	grad_norm 1.1774 (1.4675/0.6312)	mem 24308MB
[2025-01-18 16:53:02 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][210/312]	eta 0:01:02 lr 0.003410	time 0.5968 (0.6146)	model_time 0.5966 (0.6073)	loss 3.7924 (3.6279)	grad_norm 1.8161 (1.4612/0.6299)	mem 24308MB
[2025-01-18 16:53:08 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][220/312]	eta 0:00:56 lr 0.003410	time 0.6421 (0.6143)	model_time 0.6419 (0.6073)	loss 3.5722 (3.6338)	grad_norm 0.8716 (1.4511/0.6223)	mem 24308MB
[2025-01-18 16:53:14 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][230/312]	eta 0:00:50 lr 0.003409	time 0.5729 (0.6134)	model_time 0.5727 (0.6067)	loss 3.5611 (3.6325)	grad_norm 1.4868 (1.4703/0.6307)	mem 24308MB
[2025-01-18 16:53:20 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][240/312]	eta 0:00:44 lr 0.003409	time 0.5786 (0.6122)	model_time 0.5781 (0.6058)	loss 2.6455 (3.6320)	grad_norm 1.2010 (1.4580/0.6252)	mem 24308MB
[2025-01-18 16:53:26 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][250/312]	eta 0:00:37 lr 0.003408	time 0.5814 (0.6114)	model_time 0.5812 (0.6051)	loss 2.9563 (3.6240)	grad_norm 1.0025 (1.4562/0.6226)	mem 24308MB
[2025-01-18 16:53:32 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][260/312]	eta 0:00:31 lr 0.003408	time 0.5840 (0.6108)	model_time 0.5838 (0.6048)	loss 2.9054 (3.6199)	grad_norm 0.9861 (1.4571/0.6292)	mem 24308MB
[2025-01-18 16:53:37 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][270/312]	eta 0:00:25 lr 0.003407	time 0.6001 (0.6100)	model_time 0.5999 (0.6042)	loss 3.0226 (3.6225)	grad_norm 1.4125 (1.4576/0.6271)	mem 24308MB
[2025-01-18 16:53:43 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][280/312]	eta 0:00:19 lr 0.003407	time 0.7161 (0.6098)	model_time 0.7156 (0.6042)	loss 3.1008 (3.6342)	grad_norm 1.2313 (1.4487/0.6199)	mem 24308MB
[2025-01-18 16:53:50 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][290/312]	eta 0:00:13 lr 0.003406	time 0.5829 (0.6097)	model_time 0.5827 (0.6043)	loss 4.4897 (3.6351)	grad_norm 1.7348 (1.4444/0.6152)	mem 24308MB
[2025-01-18 16:53:56 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][300/312]	eta 0:00:07 lr 0.003406	time 0.5712 (0.6104)	model_time 0.5711 (0.6051)	loss 3.8264 (3.6346)	grad_norm 0.7267 (1.4323/0.6049)	mem 24308MB
[2025-01-18 16:54:02 internimage_s_1k_224] (main.py 510): INFO Train: [75/300][310/312]	eta 0:00:01 lr 0.003405	time 0.5951 (0.6103)	model_time 0.5950 (0.6052)	loss 3.1851 (3.6313)	grad_norm 1.6284 (1.4481/0.6279)	mem 24308MB
[2025-01-18 16:54:03 internimage_s_1k_224] (main.py 519): INFO EPOCH 75 training takes 0:03:10
[2025-01-18 16:54:03 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_75.pth saving......
[2025-01-18 16:54:05 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_75.pth saved !!!
[2025-01-18 16:54:12 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.260 (7.260)	Loss 0.9327 (0.9327)	Acc@1 80.005 (80.005)	Acc@5 95.337 (95.337)	Mem 24308MB
[2025-01-18 16:54:15 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.956)	Loss 1.3688 (1.1206)	Acc@1 70.020 (75.395)	Acc@5 90.063 (93.080)	Mem 24308MB
[2025-01-18 16:54:15 internimage_s_1k_224] (main.py 575): INFO [Epoch:75] * Acc@1 75.314 Acc@5 93.074
[2025-01-18 16:54:15 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.3%
[2025-01-18 16:54:15 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 75.66%
[2025-01-18 16:54:24 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.352 (8.352)	Loss 1.0238 (1.0238)	Acc@1 75.073 (75.073)	Acc@5 93.213 (93.213)	Mem 24308MB
[2025-01-18 16:54:28 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.134)	Loss 1.5511 (1.2230)	Acc@1 63.159 (70.949)	Acc@5 85.913 (90.361)	Mem 24308MB
[2025-01-18 16:54:28 internimage_s_1k_224] (main.py 575): INFO [Epoch:75] * Acc@1 71.019 Acc@5 90.523
[2025-01-18 16:54:28 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 71.0%
[2025-01-18 16:54:28 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 16:54:31 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 16:54:31 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 71.02%
[2025-01-18 16:54:33 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][0/312]	eta 0:12:13 lr 0.003405	time 2.3496 (2.3496)	model_time 0.5986 (0.5986)	loss 3.6976 (3.6976)	grad_norm 0.9370 (0.9370/0.0000)	mem 24308MB
[2025-01-18 16:54:39 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][10/312]	eta 0:03:57 lr 0.003405	time 0.5884 (0.7880)	model_time 0.5883 (0.6286)	loss 3.7386 (3.7244)	grad_norm 2.2294 (1.6217/0.5818)	mem 24308MB
[2025-01-18 16:54:45 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][20/312]	eta 0:03:25 lr 0.003404	time 0.5907 (0.7055)	model_time 0.5902 (0.6218)	loss 3.7628 (3.5767)	grad_norm 1.0679 (1.5064/0.5227)	mem 24308MB
[2025-01-18 16:54:51 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][30/312]	eta 0:03:09 lr 0.003404	time 0.5785 (0.6722)	model_time 0.5781 (0.6154)	loss 3.2696 (3.5557)	grad_norm 1.4282 (1.4379/0.5099)	mem 24308MB
[2025-01-18 16:54:57 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][40/312]	eta 0:02:57 lr 0.003403	time 0.5797 (0.6531)	model_time 0.5795 (0.6101)	loss 4.4658 (3.5646)	grad_norm 1.1854 (1.4107/0.4768)	mem 24308MB
[2025-01-18 16:55:03 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][50/312]	eta 0:02:47 lr 0.003403	time 0.5816 (0.6407)	model_time 0.5815 (0.6060)	loss 3.7196 (3.5569)	grad_norm 1.2554 (1.4853/0.5725)	mem 24308MB
[2025-01-18 16:55:09 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][60/312]	eta 0:02:39 lr 0.003402	time 0.5726 (0.6325)	model_time 0.5722 (0.6035)	loss 3.6015 (3.5770)	grad_norm 1.0360 (1.5121/0.6148)	mem 24308MB
[2025-01-18 16:55:15 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][70/312]	eta 0:02:31 lr 0.003402	time 0.5922 (0.6262)	model_time 0.5920 (0.6012)	loss 2.7459 (3.5779)	grad_norm 0.7989 (1.4628/0.5999)	mem 24308MB
[2025-01-18 16:55:21 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][80/312]	eta 0:02:24 lr 0.003402	time 0.5742 (0.6213)	model_time 0.5740 (0.5993)	loss 3.4249 (3.5515)	grad_norm 1.4293 (1.4363/0.5760)	mem 24308MB
[2025-01-18 16:55:27 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][90/312]	eta 0:02:17 lr 0.003401	time 0.5848 (0.6187)	model_time 0.5846 (0.5991)	loss 3.8810 (3.5510)	grad_norm 0.9751 (1.4364/0.5711)	mem 24308MB
[2025-01-18 16:55:33 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][100/312]	eta 0:02:11 lr 0.003401	time 0.7099 (0.6203)	model_time 0.7095 (0.6026)	loss 3.9376 (3.5570)	grad_norm 2.5890 (1.4629/0.6071)	mem 24308MB
[2025-01-18 16:55:40 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][110/312]	eta 0:02:05 lr 0.003400	time 0.7822 (0.6217)	model_time 0.7821 (0.6056)	loss 4.4813 (3.5559)	grad_norm 1.2769 (1.4799/0.6172)	mem 24308MB
[2025-01-18 16:55:46 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][120/312]	eta 0:01:59 lr 0.003400	time 0.5864 (0.6212)	model_time 0.5862 (0.6064)	loss 4.0519 (3.5735)	grad_norm 1.0251 (1.4597/0.6139)	mem 24308MB
[2025-01-18 16:55:52 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][130/312]	eta 0:01:52 lr 0.003399	time 0.6599 (0.6207)	model_time 0.6594 (0.6069)	loss 2.8268 (3.5737)	grad_norm 1.5680 (1.4506/0.5960)	mem 24308MB
[2025-01-18 16:55:58 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][140/312]	eta 0:01:46 lr 0.003399	time 0.5829 (0.6200)	model_time 0.5828 (0.6072)	loss 2.8174 (3.5565)	grad_norm 2.1481 (1.4634/0.5928)	mem 24308MB
[2025-01-18 16:56:04 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][150/312]	eta 0:01:40 lr 0.003398	time 0.5717 (0.6187)	model_time 0.5712 (0.6068)	loss 3.3453 (3.5750)	grad_norm 1.6568 (1.4711/0.5983)	mem 24308MB
[2025-01-18 16:56:10 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][160/312]	eta 0:01:33 lr 0.003398	time 0.5797 (0.6175)	model_time 0.5795 (0.6062)	loss 2.2341 (3.5952)	grad_norm 0.9916 (1.4609/0.5871)	mem 24308MB
[2025-01-18 16:56:16 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][170/312]	eta 0:01:27 lr 0.003397	time 0.5835 (0.6155)	model_time 0.5833 (0.6049)	loss 4.4172 (3.5905)	grad_norm 1.2920 (1.4435/0.5785)	mem 24308MB
[2025-01-18 16:56:22 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][180/312]	eta 0:01:21 lr 0.003397	time 0.6145 (0.6142)	model_time 0.6142 (0.6042)	loss 2.5222 (3.5976)	grad_norm 2.3363 (1.4745/0.5965)	mem 24308MB
[2025-01-18 16:56:28 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][190/312]	eta 0:01:14 lr 0.003396	time 0.5950 (0.6129)	model_time 0.5946 (0.6033)	loss 3.9166 (3.6012)	grad_norm 1.8879 (1.5045/0.6257)	mem 24308MB
[2025-01-18 16:56:34 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][200/312]	eta 0:01:08 lr 0.003396	time 0.5836 (0.6117)	model_time 0.5831 (0.6027)	loss 3.6153 (3.5940)	grad_norm 1.0074 (1.4819/0.6190)	mem 24308MB
[2025-01-18 16:56:39 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][210/312]	eta 0:01:02 lr 0.003395	time 0.6777 (0.6110)	model_time 0.6775 (0.6024)	loss 3.0933 (3.6008)	grad_norm 1.7511 (1.4903/0.6126)	mem 24308MB
[2025-01-18 16:56:46 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][220/312]	eta 0:00:56 lr 0.003395	time 0.5842 (0.6113)	model_time 0.5840 (0.6030)	loss 3.7677 (3.6057)	grad_norm 1.7310 (1.4957/0.6066)	mem 24308MB
[2025-01-18 16:56:52 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][230/312]	eta 0:00:50 lr 0.003394	time 0.7513 (0.6125)	model_time 0.7508 (0.6046)	loss 2.8123 (3.6022)	grad_norm 1.3870 (1.4863/0.5988)	mem 24308MB
[2025-01-18 16:56:58 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][240/312]	eta 0:00:44 lr 0.003394	time 0.6637 (0.6125)	model_time 0.6635 (0.6049)	loss 3.8428 (3.6009)	grad_norm 1.1473 (1.4745/0.5914)	mem 24308MB
[2025-01-18 16:57:04 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][250/312]	eta 0:00:38 lr 0.003393	time 0.6821 (0.6131)	model_time 0.6819 (0.6057)	loss 4.3458 (3.6100)	grad_norm 2.7012 (1.4907/0.5979)	mem 24308MB
[2025-01-18 16:57:11 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][260/312]	eta 0:00:31 lr 0.003393	time 0.5771 (0.6131)	model_time 0.5770 (0.6060)	loss 2.4137 (3.6051)	grad_norm 2.5179 (1.4906/0.5939)	mem 24308MB
[2025-01-18 16:57:17 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][270/312]	eta 0:00:25 lr 0.003392	time 0.5752 (0.6129)	model_time 0.5750 (0.6061)	loss 3.9485 (3.6130)	grad_norm 1.4216 (1.4794/0.5871)	mem 24308MB
[2025-01-18 16:57:23 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][280/312]	eta 0:00:19 lr 0.003392	time 0.5757 (0.6124)	model_time 0.5756 (0.6058)	loss 4.1299 (3.6106)	grad_norm 2.8997 (1.5109/0.6489)	mem 24308MB
[2025-01-18 16:57:29 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][290/312]	eta 0:00:13 lr 0.003391	time 0.5751 (0.6116)	model_time 0.5749 (0.6053)	loss 3.9853 (3.6125)	grad_norm 0.8118 (1.5064/0.6477)	mem 24308MB
[2025-01-18 16:57:34 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][300/312]	eta 0:00:07 lr 0.003391	time 0.5673 (0.6106)	model_time 0.5672 (0.6044)	loss 3.7375 (3.6184)	grad_norm 0.9528 (1.4907/0.6456)	mem 24308MB
[2025-01-18 16:57:40 internimage_s_1k_224] (main.py 510): INFO Train: [76/300][310/312]	eta 0:00:01 lr 0.003391	time 0.5689 (0.6093)	model_time 0.5688 (0.6033)	loss 3.8571 (3.6100)	grad_norm 1.0256 (1.4670/0.6430)	mem 24308MB
[2025-01-18 16:57:41 internimage_s_1k_224] (main.py 519): INFO EPOCH 76 training takes 0:03:10
[2025-01-18 16:57:41 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_76.pth saving......
[2025-01-18 16:57:43 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_76.pth saved !!!
[2025-01-18 16:57:50 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.148 (7.148)	Loss 0.9806 (0.9806)	Acc@1 78.809 (78.809)	Acc@5 95.410 (95.410)	Mem 24308MB
[2025-01-18 16:57:53 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.928)	Loss 1.3526 (1.1338)	Acc@1 70.264 (75.779)	Acc@5 90.747 (93.184)	Mem 24308MB
[2025-01-18 16:57:53 internimage_s_1k_224] (main.py 575): INFO [Epoch:76] * Acc@1 75.766 Acc@5 93.262
[2025-01-18 16:57:53 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.8%
[2025-01-18 16:57:53 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 16:57:55 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 16:57:55 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 75.77%
[2025-01-18 16:58:02 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.330 (7.330)	Loss 1.0090 (1.0090)	Acc@1 75.366 (75.366)	Acc@5 93.481 (93.481)	Mem 24308MB
[2025-01-18 16:58:06 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.964)	Loss 1.5302 (1.2063)	Acc@1 63.501 (71.302)	Acc@5 86.255 (90.603)	Mem 24308MB
[2025-01-18 16:58:06 internimage_s_1k_224] (main.py 575): INFO [Epoch:76] * Acc@1 71.355 Acc@5 90.769
[2025-01-18 16:58:06 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 71.4%
[2025-01-18 16:58:06 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 16:58:08 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 16:58:08 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 71.36%
[2025-01-18 16:58:10 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][0/312]	eta 0:11:21 lr 0.003390	time 2.1841 (2.1841)	model_time 0.5915 (0.5915)	loss 4.3686 (4.3686)	grad_norm 1.4485 (1.4485/0.0000)	mem 24308MB
[2025-01-18 16:58:16 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][10/312]	eta 0:03:44 lr 0.003390	time 0.6145 (0.7445)	model_time 0.6143 (0.5994)	loss 3.2470 (3.3293)	grad_norm 2.7060 (1.3546/0.5664)	mem 24308MB
[2025-01-18 16:58:22 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][20/312]	eta 0:03:16 lr 0.003389	time 0.5984 (0.6716)	model_time 0.5982 (0.5954)	loss 4.0351 (3.4954)	grad_norm 0.8355 (1.3880/0.5358)	mem 24308MB
[2025-01-18 16:58:28 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][30/312]	eta 0:03:04 lr 0.003389	time 0.5879 (0.6533)	model_time 0.5875 (0.6016)	loss 3.7515 (3.5509)	grad_norm 1.3503 (1.4429/0.5941)	mem 24308MB
[2025-01-18 16:58:35 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][40/312]	eta 0:02:56 lr 0.003389	time 0.6462 (0.6476)	model_time 0.6460 (0.6084)	loss 3.1432 (3.5190)	grad_norm 2.4332 (1.5199/0.6693)	mem 24308MB
[2025-01-18 16:58:41 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][50/312]	eta 0:02:48 lr 0.003388	time 0.6535 (0.6432)	model_time 0.6529 (0.6117)	loss 4.2884 (3.5394)	grad_norm 1.6024 (1.5183/0.6287)	mem 24308MB
[2025-01-18 16:58:47 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][60/312]	eta 0:02:40 lr 0.003388	time 0.5922 (0.6361)	model_time 0.5920 (0.6096)	loss 3.4914 (3.5520)	grad_norm 2.3094 (1.5136/0.5940)	mem 24308MB
[2025-01-18 16:58:53 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][70/312]	eta 0:02:33 lr 0.003387	time 0.6528 (0.6324)	model_time 0.6523 (0.6096)	loss 4.4810 (3.6074)	grad_norm 2.1410 (1.4990/0.5673)	mem 24308MB
[2025-01-18 16:58:59 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][80/312]	eta 0:02:26 lr 0.003387	time 0.5833 (0.6294)	model_time 0.5829 (0.6094)	loss 3.3193 (3.6067)	grad_norm 2.4407 (1.5224/0.5719)	mem 24308MB
[2025-01-18 16:59:05 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][90/312]	eta 0:02:19 lr 0.003386	time 0.5769 (0.6262)	model_time 0.5767 (0.6084)	loss 4.3130 (3.6088)	grad_norm 2.0405 (1.5205/0.5543)	mem 24308MB
[2025-01-18 16:59:11 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][100/312]	eta 0:02:11 lr 0.003386	time 0.5848 (0.6225)	model_time 0.5843 (0.6064)	loss 3.8008 (3.5891)	grad_norm 1.7987 (1.5243/0.5472)	mem 24308MB
[2025-01-18 16:59:17 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][110/312]	eta 0:02:05 lr 0.003385	time 0.5826 (0.6196)	model_time 0.5825 (0.6048)	loss 4.5606 (3.6028)	grad_norm 0.9528 (1.4943/0.5384)	mem 24308MB
[2025-01-18 16:59:23 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][120/312]	eta 0:01:58 lr 0.003385	time 0.6095 (0.6168)	model_time 0.6094 (0.6032)	loss 2.6935 (3.6269)	grad_norm 1.9728 (1.5036/0.5653)	mem 24308MB
[2025-01-18 16:59:28 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][130/312]	eta 0:01:51 lr 0.003384	time 0.5745 (0.6139)	model_time 0.5744 (0.6013)	loss 2.7941 (3.6193)	grad_norm 0.8987 (1.5416/0.6724)	mem 24308MB
[2025-01-18 16:59:34 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][140/312]	eta 0:01:45 lr 0.003384	time 0.5735 (0.6124)	model_time 0.5731 (0.6007)	loss 4.7484 (3.6468)	grad_norm 1.0040 (1.5512/0.7102)	mem 24308MB
[2025-01-18 16:59:41 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][150/312]	eta 0:01:39 lr 0.003383	time 0.5770 (0.6135)	model_time 0.5766 (0.6026)	loss 3.0714 (3.6276)	grad_norm 1.6733 (1.5406/0.6951)	mem 24308MB
[2025-01-18 16:59:47 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][160/312]	eta 0:01:33 lr 0.003383	time 0.6738 (0.6150)	model_time 0.6737 (0.6048)	loss 3.8952 (3.6354)	grad_norm 0.9859 (1.5113/0.6859)	mem 24308MB
[2025-01-18 16:59:53 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][170/312]	eta 0:01:27 lr 0.003382	time 0.5925 (0.6159)	model_time 0.5923 (0.6062)	loss 3.7203 (3.6344)	grad_norm 1.0698 (1.5167/0.6747)	mem 24308MB
[2025-01-18 16:59:59 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][180/312]	eta 0:01:21 lr 0.003382	time 0.6155 (0.6158)	model_time 0.6153 (0.6066)	loss 4.3556 (3.6349)	grad_norm 2.4379 (1.5151/0.6680)	mem 24308MB
[2025-01-18 17:00:06 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][190/312]	eta 0:01:15 lr 0.003381	time 0.6544 (0.6153)	model_time 0.6543 (0.6066)	loss 2.9231 (3.6339)	grad_norm 1.5494 (1.5264/0.6709)	mem 24308MB
[2025-01-18 17:00:12 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][200/312]	eta 0:01:08 lr 0.003381	time 0.5703 (0.6150)	model_time 0.5702 (0.6067)	loss 3.7514 (3.6329)	grad_norm 1.4072 (1.5206/0.6664)	mem 24308MB
[2025-01-18 17:00:18 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][210/312]	eta 0:01:02 lr 0.003380	time 0.5682 (0.6139)	model_time 0.5680 (0.6060)	loss 3.5415 (3.6152)	grad_norm 1.5131 (1.5185/0.6587)	mem 24308MB
[2025-01-18 17:00:23 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][220/312]	eta 0:00:56 lr 0.003380	time 0.5792 (0.6129)	model_time 0.5788 (0.6053)	loss 4.0693 (3.6178)	grad_norm 0.6794 (1.5019/0.6512)	mem 24308MB
[2025-01-18 17:00:29 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][230/312]	eta 0:00:50 lr 0.003379	time 0.5831 (0.6119)	model_time 0.5829 (0.6046)	loss 3.6621 (3.6167)	grad_norm 1.6848 (1.4907/0.6421)	mem 24308MB
[2025-01-18 17:00:35 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][240/312]	eta 0:00:43 lr 0.003379	time 0.5869 (0.6109)	model_time 0.5867 (0.6040)	loss 3.8395 (3.6245)	grad_norm 0.7137 (1.4832/0.6353)	mem 24308MB
[2025-01-18 17:00:41 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][250/312]	eta 0:00:37 lr 0.003378	time 0.5743 (0.6100)	model_time 0.5741 (0.6033)	loss 3.6775 (3.6208)	grad_norm 1.3975 (1.4647/0.6304)	mem 24308MB
[2025-01-18 17:00:47 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][260/312]	eta 0:00:31 lr 0.003378	time 0.6230 (0.6092)	model_time 0.6228 (0.6027)	loss 3.0036 (3.6169)	grad_norm 1.9470 (1.4799/0.6645)	mem 24308MB
[2025-01-18 17:00:53 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][270/312]	eta 0:00:25 lr 0.003377	time 0.6659 (0.6094)	model_time 0.6657 (0.6032)	loss 3.9247 (3.6181)	grad_norm 1.5275 (1.4787/0.6604)	mem 24308MB
[2025-01-18 17:00:59 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][280/312]	eta 0:00:19 lr 0.003377	time 0.6663 (0.6098)	model_time 0.6662 (0.6038)	loss 3.8885 (3.6256)	grad_norm 0.9776 (1.4722/0.6538)	mem 24308MB
[2025-01-18 17:01:06 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][290/312]	eta 0:00:13 lr 0.003376	time 0.5902 (0.6104)	model_time 0.5901 (0.6045)	loss 3.6424 (3.6273)	grad_norm 1.9673 (1.4661/0.6484)	mem 24308MB
[2025-01-18 17:01:12 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][300/312]	eta 0:00:07 lr 0.003376	time 0.5673 (0.6103)	model_time 0.5672 (0.6046)	loss 3.6332 (3.6300)	grad_norm 0.7722 (1.4676/0.6425)	mem 24308MB
[2025-01-18 17:01:18 internimage_s_1k_224] (main.py 510): INFO Train: [77/300][310/312]	eta 0:00:01 lr 0.003376	time 0.6407 (0.6098)	model_time 0.6407 (0.6044)	loss 2.9767 (3.6253)	grad_norm 2.2985 (1.4749/0.6417)	mem 24308MB
[2025-01-18 17:01:18 internimage_s_1k_224] (main.py 519): INFO EPOCH 77 training takes 0:03:10
[2025-01-18 17:01:18 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_77.pth saving......
[2025-01-18 17:01:20 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_77.pth saved !!!
[2025-01-18 17:01:27 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.219 (7.219)	Loss 0.9314 (0.9314)	Acc@1 78.979 (78.979)	Acc@5 95.532 (95.532)	Mem 24308MB
[2025-01-18 17:01:30 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.946)	Loss 1.3459 (1.1100)	Acc@1 70.215 (75.637)	Acc@5 90.747 (93.282)	Mem 24308MB
[2025-01-18 17:01:31 internimage_s_1k_224] (main.py 575): INFO [Epoch:77] * Acc@1 75.566 Acc@5 93.326
[2025-01-18 17:01:31 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.6%
[2025-01-18 17:01:31 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 75.77%
[2025-01-18 17:01:39 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.272 (8.272)	Loss 0.9952 (0.9952)	Acc@1 75.732 (75.732)	Acc@5 93.579 (93.579)	Mem 24308MB
[2025-01-18 17:01:43 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (1.117)	Loss 1.5105 (1.1907)	Acc@1 63.892 (71.602)	Acc@5 86.646 (90.789)	Mem 24308MB
[2025-01-18 17:01:43 internimage_s_1k_224] (main.py 575): INFO [Epoch:77] * Acc@1 71.673 Acc@5 90.949
[2025-01-18 17:01:43 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 71.7%
[2025-01-18 17:01:43 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 17:01:45 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 17:01:45 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 71.67%
[2025-01-18 17:01:48 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][0/312]	eta 0:11:34 lr 0.003375	time 2.2266 (2.2266)	model_time 0.7001 (0.7001)	loss 2.5689 (2.5689)	grad_norm 1.5251 (1.5251/0.0000)	mem 24308MB
[2025-01-18 17:01:54 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][10/312]	eta 0:03:46 lr 0.003375	time 0.6843 (0.7511)	model_time 0.6842 (0.6122)	loss 3.9701 (3.6802)	grad_norm 1.1327 (1.3283/0.2401)	mem 24308MB
[2025-01-18 17:02:00 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][20/312]	eta 0:03:17 lr 0.003374	time 0.5727 (0.6778)	model_time 0.5722 (0.6049)	loss 3.3224 (3.4914)	grad_norm 1.7552 (1.4680/0.3292)	mem 24308MB
[2025-01-18 17:02:06 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][30/312]	eta 0:03:03 lr 0.003374	time 0.5768 (0.6502)	model_time 0.5767 (0.6006)	loss 2.7042 (3.5257)	grad_norm 1.2115 (1.6336/0.6001)	mem 24308MB
[2025-01-18 17:02:11 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][40/312]	eta 0:02:52 lr 0.003373	time 0.5936 (0.6348)	model_time 0.5934 (0.5972)	loss 3.5748 (3.5540)	grad_norm 1.3484 (1.5464/0.5852)	mem 24308MB
[2025-01-18 17:02:17 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][50/312]	eta 0:02:44 lr 0.003373	time 0.5989 (0.6266)	model_time 0.5988 (0.5963)	loss 2.8890 (3.4880)	grad_norm 3.4856 (1.5718/0.6322)	mem 24308MB
[2025-01-18 17:02:23 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][60/312]	eta 0:02:36 lr 0.003372	time 0.5729 (0.6195)	model_time 0.5725 (0.5942)	loss 4.0660 (3.5340)	grad_norm 1.6688 (1.5453/0.6192)	mem 24308MB
[2025-01-18 17:02:29 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][70/312]	eta 0:02:29 lr 0.003372	time 0.5722 (0.6168)	model_time 0.5718 (0.5950)	loss 4.1481 (3.5419)	grad_norm 0.9857 (1.4961/0.6286)	mem 24308MB
[2025-01-18 17:02:35 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][80/312]	eta 0:02:22 lr 0.003372	time 0.5707 (0.6155)	model_time 0.5706 (0.5963)	loss 2.5985 (3.5539)	grad_norm 1.1048 (1.5237/0.6335)	mem 24308MB
[2025-01-18 17:02:41 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][90/312]	eta 0:02:16 lr 0.003371	time 0.5800 (0.6153)	model_time 0.5799 (0.5982)	loss 4.1532 (3.5423)	grad_norm 1.1585 (1.5004/0.6050)	mem 24308MB
[2025-01-18 17:02:48 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][100/312]	eta 0:02:10 lr 0.003371	time 0.6773 (0.6176)	model_time 0.6771 (0.6021)	loss 2.4980 (3.5352)	grad_norm 1.3113 (1.5347/0.6391)	mem 24308MB
[2025-01-18 17:02:54 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][110/312]	eta 0:02:04 lr 0.003370	time 0.5791 (0.6182)	model_time 0.5787 (0.6041)	loss 3.7969 (3.5167)	grad_norm 1.6288 (1.5903/0.7254)	mem 24308MB
[2025-01-18 17:03:00 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][120/312]	eta 0:01:58 lr 0.003370	time 0.6992 (0.6174)	model_time 0.6987 (0.6045)	loss 4.3100 (3.5046)	grad_norm 1.1449 (1.5442/0.7151)	mem 24308MB
[2025-01-18 17:03:06 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][130/312]	eta 0:01:52 lr 0.003369	time 0.5997 (0.6157)	model_time 0.5993 (0.6037)	loss 4.0538 (3.5090)	grad_norm 1.0414 (1.5043/0.7028)	mem 24308MB
[2025-01-18 17:03:12 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][140/312]	eta 0:01:45 lr 0.003369	time 0.6848 (0.6151)	model_time 0.6847 (0.6039)	loss 4.4953 (3.5317)	grad_norm 1.4792 (1.5355/0.7095)	mem 24308MB
[2025-01-18 17:03:18 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][150/312]	eta 0:01:39 lr 0.003368	time 0.5724 (0.6132)	model_time 0.5722 (0.6026)	loss 3.0472 (3.5326)	grad_norm 2.7886 (1.5516/0.7014)	mem 24308MB
[2025-01-18 17:03:24 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][160/312]	eta 0:01:32 lr 0.003368	time 0.6189 (0.6116)	model_time 0.6185 (0.6017)	loss 2.6064 (3.5412)	grad_norm 1.1133 (1.5417/0.6906)	mem 24308MB
[2025-01-18 17:03:30 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][170/312]	eta 0:01:26 lr 0.003367	time 0.5831 (0.6101)	model_time 0.5829 (0.6007)	loss 3.8082 (3.5498)	grad_norm 1.1122 (1.5179/0.6813)	mem 24308MB
[2025-01-18 17:03:36 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][180/312]	eta 0:01:20 lr 0.003367	time 0.5749 (0.6088)	model_time 0.5744 (0.6000)	loss 3.9305 (3.5509)	grad_norm 1.4003 (1.4964/0.6713)	mem 24308MB
[2025-01-18 17:03:42 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][190/312]	eta 0:01:14 lr 0.003366	time 0.5915 (0.6082)	model_time 0.5910 (0.5998)	loss 3.8202 (3.5538)	grad_norm 3.0091 (1.5108/0.6786)	mem 24308MB
[2025-01-18 17:03:47 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][200/312]	eta 0:01:08 lr 0.003366	time 0.5850 (0.6073)	model_time 0.5845 (0.5992)	loss 4.4076 (3.5691)	grad_norm 1.5118 (1.5136/0.6673)	mem 24308MB
[2025-01-18 17:03:54 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][210/312]	eta 0:01:02 lr 0.003365	time 0.5922 (0.6084)	model_time 0.5921 (0.6007)	loss 4.1707 (3.5794)	grad_norm 0.8566 (1.4995/0.6583)	mem 24308MB
[2025-01-18 17:04:00 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][220/312]	eta 0:00:56 lr 0.003365	time 0.8635 (0.6112)	model_time 0.8630 (0.6038)	loss 4.2756 (3.5801)	grad_norm 1.4513 (1.5022/0.6588)	mem 24308MB
[2025-01-18 17:04:07 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][230/312]	eta 0:00:50 lr 0.003364	time 0.5930 (0.6111)	model_time 0.5929 (0.6041)	loss 3.7869 (3.5748)	grad_norm 1.0570 (1.4875/0.6527)	mem 24308MB
[2025-01-18 17:04:13 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][240/312]	eta 0:00:44 lr 0.003364	time 0.6894 (0.6112)	model_time 0.6889 (0.6044)	loss 4.0106 (3.5805)	grad_norm 3.9344 (1.5092/0.6770)	mem 24308MB
[2025-01-18 17:04:19 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][250/312]	eta 0:00:37 lr 0.003363	time 0.6161 (0.6105)	model_time 0.6159 (0.6040)	loss 2.7308 (3.5776)	grad_norm 2.4189 (1.5262/0.6786)	mem 24308MB
[2025-01-18 17:04:25 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][260/312]	eta 0:00:31 lr 0.003363	time 0.7094 (0.6105)	model_time 0.7090 (0.6043)	loss 3.8208 (3.5832)	grad_norm 1.7028 (1.5338/0.6805)	mem 24308MB
[2025-01-18 17:04:31 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][270/312]	eta 0:00:25 lr 0.003362	time 0.5798 (0.6096)	model_time 0.5796 (0.6035)	loss 2.9766 (3.5797)	grad_norm 1.8852 (1.5257/0.6740)	mem 24308MB
[2025-01-18 17:04:36 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][280/312]	eta 0:00:19 lr 0.003362	time 0.5742 (0.6089)	model_time 0.5738 (0.6031)	loss 3.7547 (3.5749)	grad_norm 1.5502 (1.5197/0.6678)	mem 24308MB
[2025-01-18 17:04:42 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][290/312]	eta 0:00:13 lr 0.003361	time 0.5829 (0.6082)	model_time 0.5827 (0.6025)	loss 3.7090 (3.5867)	grad_norm 0.8136 (1.5148/0.6678)	mem 24308MB
[2025-01-18 17:04:48 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][300/312]	eta 0:00:07 lr 0.003361	time 0.5799 (0.6074)	model_time 0.5798 (0.6020)	loss 3.1884 (3.5885)	grad_norm 1.3300 (1.5154/0.6685)	mem 24308MB
[2025-01-18 17:04:54 internimage_s_1k_224] (main.py 510): INFO Train: [78/300][310/312]	eta 0:00:01 lr 0.003360	time 0.5681 (0.6062)	model_time 0.5681 (0.6009)	loss 3.7111 (3.5896)	grad_norm 1.3988 (1.5272/0.6754)	mem 24308MB
[2025-01-18 17:04:54 internimage_s_1k_224] (main.py 519): INFO EPOCH 78 training takes 0:03:09
[2025-01-18 17:04:54 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_78.pth saving......
[2025-01-18 17:04:56 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_78.pth saved !!!
[2025-01-18 17:05:04 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.356 (7.356)	Loss 0.9447 (0.9447)	Acc@1 78.833 (78.833)	Acc@5 95.581 (95.581)	Mem 24308MB
[2025-01-18 17:05:07 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.961)	Loss 1.2693 (1.0986)	Acc@1 71.069 (75.897)	Acc@5 91.187 (93.459)	Mem 24308MB
[2025-01-18 17:05:07 internimage_s_1k_224] (main.py 575): INFO [Epoch:78] * Acc@1 75.878 Acc@5 93.492
[2025-01-18 17:05:07 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.9%
[2025-01-18 17:05:07 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 17:05:09 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 17:05:09 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 75.88%
[2025-01-18 17:05:16 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.101 (7.101)	Loss 0.9823 (0.9823)	Acc@1 76.221 (76.221)	Acc@5 93.652 (93.652)	Mem 24308MB
[2025-01-18 17:05:19 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.939)	Loss 1.4917 (1.1760)	Acc@1 64.331 (71.948)	Acc@5 86.914 (90.998)	Mem 24308MB
[2025-01-18 17:05:20 internimage_s_1k_224] (main.py 575): INFO [Epoch:78] * Acc@1 72.021 Acc@5 91.139
[2025-01-18 17:05:20 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 72.0%
[2025-01-18 17:05:20 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 17:05:22 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 17:05:22 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 72.02%
[2025-01-18 17:05:24 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][0/312]	eta 0:11:48 lr 0.003360	time 2.2692 (2.2692)	model_time 0.6033 (0.6033)	loss 3.3692 (3.3692)	grad_norm 1.0628 (1.0628/0.0000)	mem 24308MB
[2025-01-18 17:05:30 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][10/312]	eta 0:03:49 lr 0.003360	time 0.5799 (0.7584)	model_time 0.5797 (0.6068)	loss 4.3250 (3.7786)	grad_norm 1.0941 (1.4584/0.5977)	mem 24308MB
[2025-01-18 17:05:36 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][20/312]	eta 0:03:23 lr 0.003359	time 0.5801 (0.6965)	model_time 0.5799 (0.6162)	loss 2.9847 (3.7467)	grad_norm 0.9174 (1.4468/0.5171)	mem 24308MB
[2025-01-18 17:05:43 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][30/312]	eta 0:03:11 lr 0.003359	time 0.5845 (0.6805)	model_time 0.5843 (0.6260)	loss 4.2224 (3.6929)	grad_norm 1.6823 (1.4763/0.4632)	mem 24308MB
[2025-01-18 17:05:49 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][40/312]	eta 0:03:02 lr 0.003358	time 0.6904 (0.6700)	model_time 0.6899 (0.6287)	loss 3.3500 (3.6745)	grad_norm 1.5716 (1.4042/0.4599)	mem 24308MB
[2025-01-18 17:05:55 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][50/312]	eta 0:02:52 lr 0.003358	time 0.5862 (0.6565)	model_time 0.5858 (0.6232)	loss 4.5216 (3.6700)	grad_norm 0.8335 (1.3597/0.4414)	mem 24308MB
[2025-01-18 17:06:01 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][60/312]	eta 0:02:43 lr 0.003357	time 0.6000 (0.6486)	model_time 0.5999 (0.6208)	loss 2.8006 (3.6366)	grad_norm 0.8251 (1.4009/0.4838)	mem 24308MB
[2025-01-18 17:06:07 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][70/312]	eta 0:02:35 lr 0.003357	time 0.5838 (0.6426)	model_time 0.5833 (0.6186)	loss 3.8918 (3.6443)	grad_norm 1.2841 (1.4508/0.5324)	mem 24308MB
[2025-01-18 17:06:13 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][80/312]	eta 0:02:27 lr 0.003356	time 0.6017 (0.6366)	model_time 0.6011 (0.6155)	loss 3.7319 (3.6479)	grad_norm 1.6357 (1.4488/0.5524)	mem 24308MB
[2025-01-18 17:06:19 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][90/312]	eta 0:02:20 lr 0.003356	time 0.5722 (0.6314)	model_time 0.5720 (0.6125)	loss 3.6518 (3.6955)	grad_norm 1.8152 (1.4681/0.5496)	mem 24308MB
[2025-01-18 17:06:25 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][100/312]	eta 0:02:13 lr 0.003355	time 0.5891 (0.6274)	model_time 0.5887 (0.6104)	loss 3.8302 (3.7182)	grad_norm 0.8895 (1.4924/0.5591)	mem 24308MB
[2025-01-18 17:06:31 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][110/312]	eta 0:02:06 lr 0.003355	time 0.5914 (0.6243)	model_time 0.5912 (0.6088)	loss 4.3525 (3.7117)	grad_norm 1.1557 (1.4789/0.5582)	mem 24308MB
[2025-01-18 17:06:37 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][120/312]	eta 0:01:59 lr 0.003354	time 0.6817 (0.6218)	model_time 0.6815 (0.6076)	loss 3.1086 (3.7001)	grad_norm 2.1308 (1.4775/0.5507)	mem 24308MB
[2025-01-18 17:06:43 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][130/312]	eta 0:01:52 lr 0.003354	time 0.5867 (0.6204)	model_time 0.5865 (0.6072)	loss 4.5932 (3.7113)	grad_norm 1.2111 (1.4872/0.5450)	mem 24308MB
[2025-01-18 17:06:49 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][140/312]	eta 0:01:46 lr 0.003353	time 0.6610 (0.6195)	model_time 0.6605 (0.6072)	loss 2.8745 (3.6500)	grad_norm 1.7537 (1.4738/0.5402)	mem 24308MB
[2025-01-18 17:06:56 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][150/312]	eta 0:01:40 lr 0.003353	time 0.5763 (0.6207)	model_time 0.5759 (0.6092)	loss 2.4322 (3.6406)	grad_norm 1.5300 (1.4828/0.5499)	mem 24308MB
[2025-01-18 17:07:02 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][160/312]	eta 0:01:34 lr 0.003352	time 0.6664 (0.6238)	model_time 0.6662 (0.6130)	loss 2.3813 (3.6241)	grad_norm 0.7094 (1.4687/0.5493)	mem 24308MB
[2025-01-18 17:07:08 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][170/312]	eta 0:01:28 lr 0.003352	time 0.5833 (0.6219)	model_time 0.5832 (0.6117)	loss 3.7606 (3.6308)	grad_norm 1.0296 (1.4601/0.5445)	mem 24308MB
[2025-01-18 17:07:14 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][180/312]	eta 0:01:21 lr 0.003351	time 0.6001 (0.6211)	model_time 0.5997 (0.6115)	loss 3.2727 (3.6246)	grad_norm 0.9249 (1.4408/0.5373)	mem 24308MB
[2025-01-18 17:07:20 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][190/312]	eta 0:01:15 lr 0.003351	time 0.5841 (0.6197)	model_time 0.5840 (0.6105)	loss 3.6495 (3.6215)	grad_norm 2.8495 (1.4859/0.6015)	mem 24308MB
[2025-01-18 17:07:26 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][200/312]	eta 0:01:09 lr 0.003350	time 0.5832 (0.6186)	model_time 0.5827 (0.6098)	loss 3.7184 (3.6198)	grad_norm 0.7361 (1.4723/0.5938)	mem 24308MB
[2025-01-18 17:07:32 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][210/312]	eta 0:01:02 lr 0.003350	time 0.5807 (0.6170)	model_time 0.5805 (0.6086)	loss 3.6989 (3.6238)	grad_norm 1.4619 (1.4737/0.6031)	mem 24308MB
[2025-01-18 17:07:38 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][220/312]	eta 0:00:56 lr 0.003349	time 0.5855 (0.6156)	model_time 0.5850 (0.6076)	loss 4.2045 (3.6306)	grad_norm 1.5006 (1.4661/0.5953)	mem 24308MB
[2025-01-18 17:07:44 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][230/312]	eta 0:00:50 lr 0.003349	time 0.5896 (0.6146)	model_time 0.5892 (0.6070)	loss 2.9495 (3.6276)	grad_norm 0.9197 (1.5041/0.6330)	mem 24308MB
[2025-01-18 17:07:50 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][240/312]	eta 0:00:44 lr 0.003348	time 0.5998 (0.6135)	model_time 0.5992 (0.6062)	loss 3.9860 (3.6369)	grad_norm 1.6701 (1.5089/0.6251)	mem 24308MB
[2025-01-18 17:07:56 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][250/312]	eta 0:00:38 lr 0.003348	time 0.6513 (0.6135)	model_time 0.6512 (0.6065)	loss 4.0251 (3.6255)	grad_norm 1.8295 (1.5042/0.6164)	mem 24308MB
[2025-01-18 17:08:02 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][260/312]	eta 0:00:31 lr 0.003347	time 0.6561 (0.6135)	model_time 0.6556 (0.6067)	loss 3.6434 (3.6181)	grad_norm 0.9614 (1.4958/0.6090)	mem 24308MB
[2025-01-18 17:08:08 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][270/312]	eta 0:00:25 lr 0.003347	time 0.6571 (0.6142)	model_time 0.6569 (0.6076)	loss 3.4416 (3.6082)	grad_norm 1.5792 (1.4866/0.6037)	mem 24308MB
[2025-01-18 17:08:15 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][280/312]	eta 0:00:19 lr 0.003346	time 0.6780 (0.6151)	model_time 0.6778 (0.6087)	loss 3.8521 (3.6097)	grad_norm 1.0628 (1.5095/0.6434)	mem 24308MB
[2025-01-18 17:08:21 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][290/312]	eta 0:00:13 lr 0.003346	time 0.5735 (0.6149)	model_time 0.5733 (0.6088)	loss 2.4827 (3.6047)	grad_norm 0.8290 (1.5143/0.6517)	mem 24308MB
[2025-01-18 17:08:27 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][300/312]	eta 0:00:07 lr 0.003345	time 0.5674 (0.6145)	model_time 0.5673 (0.6085)	loss 3.0058 (3.6070)	grad_norm 1.4948 (1.5211/0.6490)	mem 24308MB
[2025-01-18 17:08:33 internimage_s_1k_224] (main.py 510): INFO Train: [79/300][310/312]	eta 0:00:01 lr 0.003345	time 0.5653 (0.6135)	model_time 0.5652 (0.6077)	loss 4.0299 (3.6161)	grad_norm 1.0197 (1.5111/0.6445)	mem 24308MB
[2025-01-18 17:08:33 internimage_s_1k_224] (main.py 519): INFO EPOCH 79 training takes 0:03:11
[2025-01-18 17:08:33 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_79.pth saving......
[2025-01-18 17:08:35 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_79.pth saved !!!
[2025-01-18 17:08:42 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.246 (7.246)	Loss 0.9224 (0.9224)	Acc@1 79.761 (79.761)	Acc@5 95.459 (95.459)	Mem 24308MB
[2025-01-18 17:08:46 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.955)	Loss 1.3011 (1.1019)	Acc@1 71.948 (76.185)	Acc@5 90.771 (93.402)	Mem 24308MB
[2025-01-18 17:08:46 internimage_s_1k_224] (main.py 575): INFO [Epoch:79] * Acc@1 76.182 Acc@5 93.494
[2025-01-18 17:08:46 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.2%
[2025-01-18 17:08:46 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 17:08:48 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 17:08:48 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 76.18%
[2025-01-18 17:08:55 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.079 (7.079)	Loss 0.9697 (0.9697)	Acc@1 76.294 (76.294)	Acc@5 93.823 (93.823)	Mem 24308MB
[2025-01-18 17:08:58 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.955)	Loss 1.4745 (1.1621)	Acc@1 64.624 (72.277)	Acc@5 87.134 (91.200)	Mem 24308MB
[2025-01-18 17:08:58 internimage_s_1k_224] (main.py 575): INFO [Epoch:79] * Acc@1 72.337 Acc@5 91.331
[2025-01-18 17:08:58 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 72.3%
[2025-01-18 17:08:58 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 17:09:01 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 17:09:01 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 72.34%
[2025-01-18 17:09:03 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][0/312]	eta 0:12:30 lr 0.003345	time 2.4059 (2.4059)	model_time 0.5889 (0.5889)	loss 4.0564 (4.0564)	grad_norm 0.8264 (0.8264/0.0000)	mem 24308MB
[2025-01-18 17:09:09 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][10/312]	eta 0:03:50 lr 0.003344	time 0.5814 (0.7625)	model_time 0.5812 (0.5971)	loss 4.3969 (3.6959)	grad_norm 2.6551 (1.7198/0.5798)	mem 24308MB
[2025-01-18 17:09:15 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][20/312]	eta 0:03:18 lr 0.003344	time 0.5727 (0.6796)	model_time 0.5725 (0.5928)	loss 3.4715 (3.8007)	grad_norm 1.9606 (1.5840/0.5031)	mem 24308MB
[2025-01-18 17:09:21 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][30/312]	eta 0:03:03 lr 0.003343	time 0.6104 (0.6511)	model_time 0.6100 (0.5922)	loss 3.2486 (3.6196)	grad_norm 0.7205 (1.5025/0.5123)	mem 24308MB
[2025-01-18 17:09:27 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][40/312]	eta 0:02:52 lr 0.003343	time 0.5730 (0.6359)	model_time 0.5728 (0.5912)	loss 3.8516 (3.6512)	grad_norm 2.2549 (1.3760/0.5456)	mem 24308MB
[2025-01-18 17:09:33 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][50/312]	eta 0:02:44 lr 0.003342	time 0.6126 (0.6271)	model_time 0.6125 (0.5912)	loss 4.3036 (3.6556)	grad_norm 1.3318 (1.4790/0.6429)	mem 24308MB
[2025-01-18 17:09:39 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][60/312]	eta 0:02:37 lr 0.003342	time 0.5867 (0.6242)	model_time 0.5865 (0.5941)	loss 3.1909 (3.6234)	grad_norm 1.0791 (1.4837/0.6160)	mem 24308MB
[2025-01-18 17:09:45 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][70/312]	eta 0:02:30 lr 0.003341	time 0.6659 (0.6230)	model_time 0.6657 (0.5970)	loss 2.9148 (3.6313)	grad_norm 1.3425 (1.4483/0.5917)	mem 24308MB
[2025-01-18 17:09:51 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][80/312]	eta 0:02:24 lr 0.003341	time 0.5787 (0.6239)	model_time 0.5785 (0.6012)	loss 2.6993 (3.6419)	grad_norm 1.0118 (1.4656/0.5934)	mem 24308MB
[2025-01-18 17:09:58 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][90/312]	eta 0:02:18 lr 0.003340	time 0.6877 (0.6257)	model_time 0.6873 (0.6054)	loss 4.7297 (3.6305)	grad_norm 1.3987 (1.4757/0.5857)	mem 24308MB
[2025-01-18 17:10:04 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][100/312]	eta 0:02:12 lr 0.003340	time 0.6790 (0.6243)	model_time 0.6786 (0.6059)	loss 2.8652 (3.6000)	grad_norm 1.0583 (1.4380/0.5720)	mem 24308MB
[2025-01-18 17:10:10 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][110/312]	eta 0:02:05 lr 0.003339	time 0.5856 (0.6218)	model_time 0.5851 (0.6051)	loss 2.6427 (3.5841)	grad_norm 2.3693 (1.4363/0.5635)	mem 24308MB
[2025-01-18 17:10:16 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][120/312]	eta 0:01:58 lr 0.003339	time 0.5830 (0.6195)	model_time 0.5828 (0.6041)	loss 3.1343 (3.5848)	grad_norm 1.9265 (1.4209/0.5513)	mem 24308MB
[2025-01-18 17:10:22 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][130/312]	eta 0:01:52 lr 0.003338	time 0.5790 (0.6181)	model_time 0.5789 (0.6038)	loss 3.6916 (3.6011)	grad_norm 1.8215 (1.4331/0.5573)	mem 24308MB
[2025-01-18 17:10:27 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][140/312]	eta 0:01:45 lr 0.003338	time 0.5889 (0.6161)	model_time 0.5887 (0.6028)	loss 3.6983 (3.5992)	grad_norm 1.0399 (1.4607/0.5872)	mem 24308MB
[2025-01-18 17:10:33 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][150/312]	eta 0:01:39 lr 0.003337	time 0.6036 (0.6144)	model_time 0.6032 (0.6020)	loss 2.9959 (3.5826)	grad_norm 1.2316 (1.4573/0.5756)	mem 24308MB
[2025-01-18 17:10:39 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][160/312]	eta 0:01:33 lr 0.003337	time 0.5805 (0.6126)	model_time 0.5804 (0.6010)	loss 3.6173 (3.5510)	grad_norm 1.1096 (1.4397/0.5657)	mem 24308MB
[2025-01-18 17:10:45 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][170/312]	eta 0:01:26 lr 0.003336	time 0.5947 (0.6111)	model_time 0.5945 (0.6001)	loss 4.4542 (3.5576)	grad_norm 0.7956 (1.4215/0.5569)	mem 24308MB
[2025-01-18 17:10:51 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][180/312]	eta 0:01:20 lr 0.003336	time 0.5850 (0.6113)	model_time 0.5849 (0.6009)	loss 3.8750 (3.5539)	grad_norm 1.4658 (1.4347/0.5567)	mem 24308MB
[2025-01-18 17:10:57 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][190/312]	eta 0:01:14 lr 0.003335	time 0.5716 (0.6115)	model_time 0.5711 (0.6016)	loss 2.6515 (3.5461)	grad_norm 1.2333 (1.4334/0.5460)	mem 24308MB
[2025-01-18 17:11:04 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][200/312]	eta 0:01:08 lr 0.003335	time 0.6438 (0.6125)	model_time 0.6436 (0.6031)	loss 3.4759 (3.5388)	grad_norm 1.5487 (1.4308/0.5364)	mem 24308MB
[2025-01-18 17:11:10 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][210/312]	eta 0:01:02 lr 0.003334	time 0.6714 (0.6149)	model_time 0.6710 (0.6059)	loss 3.4011 (3.5488)	grad_norm 1.9586 (1.4364/0.5390)	mem 24308MB
[2025-01-18 17:11:17 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][220/312]	eta 0:00:56 lr 0.003334	time 0.6479 (0.6150)	model_time 0.6474 (0.6064)	loss 3.9659 (3.5528)	grad_norm 2.6745 (1.4523/0.5490)	mem 24308MB
[2025-01-18 17:11:22 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][230/312]	eta 0:00:50 lr 0.003333	time 0.5817 (0.6140)	model_time 0.5815 (0.6058)	loss 2.9281 (3.5382)	grad_norm 0.9655 (1.4476/0.5472)	mem 24308MB
[2025-01-18 17:11:28 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][240/312]	eta 0:00:44 lr 0.003333	time 0.5965 (0.6133)	model_time 0.5960 (0.6054)	loss 3.7965 (3.5489)	grad_norm 0.7284 (1.4474/0.5426)	mem 24308MB
[2025-01-18 17:11:34 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][250/312]	eta 0:00:37 lr 0.003332	time 0.6012 (0.6127)	model_time 0.6010 (0.6050)	loss 3.1786 (3.5621)	grad_norm 1.3637 (1.4645/0.5572)	mem 24308MB
[2025-01-18 17:11:40 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][260/312]	eta 0:00:31 lr 0.003332	time 0.5852 (0.6115)	model_time 0.5848 (0.6041)	loss 3.3053 (3.5783)	grad_norm 1.3974 (1.4730/0.5562)	mem 24308MB
[2025-01-18 17:11:46 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][270/312]	eta 0:00:25 lr 0.003331	time 0.6040 (0.6107)	model_time 0.6039 (0.6036)	loss 3.0905 (3.5837)	grad_norm 0.7085 (1.4734/0.5518)	mem 24308MB
[2025-01-18 17:11:52 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][280/312]	eta 0:00:19 lr 0.003331	time 0.6021 (0.6100)	model_time 0.6019 (0.6031)	loss 2.7175 (3.5873)	grad_norm 1.0545 (1.4647/0.5468)	mem 24308MB
[2025-01-18 17:11:58 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][290/312]	eta 0:00:13 lr 0.003330	time 0.5843 (0.6090)	model_time 0.5839 (0.6024)	loss 3.7074 (3.5909)	grad_norm 2.8977 (1.4780/0.5661)	mem 24308MB
[2025-01-18 17:12:04 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][300/312]	eta 0:00:07 lr 0.003330	time 0.5744 (0.6087)	model_time 0.5743 (0.6023)	loss 2.5795 (3.5883)	grad_norm 1.7690 (1.4937/0.5884)	mem 24308MB
[2025-01-18 17:12:10 internimage_s_1k_224] (main.py 510): INFO Train: [80/300][310/312]	eta 0:00:01 lr 0.003329	time 0.6420 (0.6085)	model_time 0.6418 (0.6023)	loss 3.8013 (3.5874)	grad_norm 1.5892 (1.4816/0.5799)	mem 24308MB
[2025-01-18 17:12:10 internimage_s_1k_224] (main.py 519): INFO EPOCH 80 training takes 0:03:09
[2025-01-18 17:12:10 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_80.pth saving......
[2025-01-18 17:12:12 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_80.pth saved !!!
[2025-01-18 17:12:20 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.342 (7.342)	Loss 0.9341 (0.9341)	Acc@1 79.858 (79.858)	Acc@5 95.361 (95.361)	Mem 24308MB
[2025-01-18 17:12:23 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.954)	Loss 1.3075 (1.0959)	Acc@1 70.581 (75.957)	Acc@5 90.845 (93.435)	Mem 24308MB
[2025-01-18 17:12:23 internimage_s_1k_224] (main.py 575): INFO [Epoch:80] * Acc@1 75.896 Acc@5 93.462
[2025-01-18 17:12:23 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 75.9%
[2025-01-18 17:12:23 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 76.18%
[2025-01-18 17:12:31 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.103 (8.103)	Loss 0.9577 (0.9577)	Acc@1 76.562 (76.562)	Acc@5 93.994 (93.994)	Mem 24308MB
[2025-01-18 17:12:35 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.098)	Loss 1.4578 (1.1489)	Acc@1 65.088 (72.621)	Acc@5 87.451 (91.369)	Mem 24308MB
[2025-01-18 17:12:35 internimage_s_1k_224] (main.py 575): INFO [Epoch:80] * Acc@1 72.677 Acc@5 91.485
[2025-01-18 17:12:35 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 72.7%
[2025-01-18 17:12:35 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 17:12:38 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 17:12:38 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 72.68%
[2025-01-18 17:12:40 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][0/312]	eta 0:11:42 lr 0.003329	time 2.2513 (2.2513)	model_time 0.5984 (0.5984)	loss 4.4970 (4.4970)	grad_norm 0.6688 (0.6688/0.0000)	mem 24308MB
[2025-01-18 17:12:46 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][10/312]	eta 0:03:54 lr 0.003329	time 0.6758 (0.7771)	model_time 0.6757 (0.6264)	loss 3.6116 (3.7686)	grad_norm 0.9360 (1.5084/0.6046)	mem 24308MB
[2025-01-18 17:12:52 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][20/312]	eta 0:03:25 lr 0.003328	time 0.5814 (0.7054)	model_time 0.5809 (0.6263)	loss 3.5687 (3.6200)	grad_norm 2.6940 (1.4493/0.5568)	mem 24308MB
[2025-01-18 17:12:59 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][30/312]	eta 0:03:10 lr 0.003328	time 0.6803 (0.6756)	model_time 0.6797 (0.6219)	loss 3.5384 (3.6149)	grad_norm 1.4452 (1.4302/0.5422)	mem 24308MB
[2025-01-18 17:13:05 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][40/312]	eta 0:02:59 lr 0.003327	time 0.6741 (0.6582)	model_time 0.6739 (0.6175)	loss 4.4324 (3.6073)	grad_norm 2.0723 (1.3883/0.5050)	mem 24308MB
[2025-01-18 17:13:11 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][50/312]	eta 0:02:49 lr 0.003327	time 0.5779 (0.6455)	model_time 0.5773 (0.6127)	loss 3.4412 (3.5943)	grad_norm 1.0567 (1.4154/0.5644)	mem 24308MB
[2025-01-18 17:13:17 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][60/312]	eta 0:02:40 lr 0.003326	time 0.5868 (0.6381)	model_time 0.5866 (0.6107)	loss 3.6618 (3.5810)	grad_norm 2.2056 (1.4062/0.5568)	mem 24308MB
[2025-01-18 17:13:22 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][70/312]	eta 0:02:32 lr 0.003326	time 0.5808 (0.6309)	model_time 0.5803 (0.6070)	loss 2.5200 (3.5695)	grad_norm 1.2258 (1.3642/0.5355)	mem 24308MB
[2025-01-18 17:13:28 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][80/312]	eta 0:02:25 lr 0.003325	time 0.5791 (0.6266)	model_time 0.5789 (0.6057)	loss 3.9639 (3.5926)	grad_norm 0.5489 (1.3795/0.5704)	mem 24308MB
[2025-01-18 17:13:34 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][90/312]	eta 0:02:18 lr 0.003325	time 0.6083 (0.6228)	model_time 0.6081 (0.6041)	loss 3.8151 (3.5986)	grad_norm 1.8184 (1.3482/0.5584)	mem 24308MB
[2025-01-18 17:13:40 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][100/312]	eta 0:02:11 lr 0.003324	time 0.5880 (0.6191)	model_time 0.5876 (0.6022)	loss 3.4558 (3.5782)	grad_norm 1.6472 (1.3589/0.5440)	mem 24308MB
[2025-01-18 17:13:46 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][110/312]	eta 0:02:04 lr 0.003324	time 0.5770 (0.6179)	model_time 0.5768 (0.6025)	loss 2.6304 (3.5568)	grad_norm 2.0333 (1.3885/0.5678)	mem 24308MB
[2025-01-18 17:13:52 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][120/312]	eta 0:01:58 lr 0.003323	time 0.6328 (0.6181)	model_time 0.6324 (0.6039)	loss 2.8485 (3.5505)	grad_norm 1.6718 (1.3898/0.5663)	mem 24308MB
[2025-01-18 17:13:59 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][130/312]	eta 0:01:52 lr 0.003323	time 0.5910 (0.6192)	model_time 0.5906 (0.6061)	loss 3.4896 (3.5593)	grad_norm 2.6316 (1.4219/0.6072)	mem 24308MB
[2025-01-18 17:14:05 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][140/312]	eta 0:01:47 lr 0.003322	time 0.5950 (0.6224)	model_time 0.5948 (0.6102)	loss 4.1269 (3.5511)	grad_norm 1.4514 (1.4398/0.6212)	mem 24308MB
[2025-01-18 17:14:12 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][150/312]	eta 0:01:40 lr 0.003322	time 0.6033 (0.6218)	model_time 0.6028 (0.6104)	loss 2.7115 (3.5351)	grad_norm 1.5240 (1.4331/0.6086)	mem 24308MB
[2025-01-18 17:14:18 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][160/312]	eta 0:01:34 lr 0.003321	time 0.5730 (0.6208)	model_time 0.5726 (0.6101)	loss 4.2826 (3.5545)	grad_norm 1.5155 (1.4105/0.5997)	mem 24308MB
[2025-01-18 17:14:24 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][170/312]	eta 0:01:28 lr 0.003321	time 0.7396 (0.6206)	model_time 0.7391 (0.6105)	loss 3.6519 (3.5797)	grad_norm 1.1261 (1.4244/0.5985)	mem 24308MB
[2025-01-18 17:14:30 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][180/312]	eta 0:01:21 lr 0.003320	time 0.5873 (0.6194)	model_time 0.5872 (0.6098)	loss 2.4209 (3.5828)	grad_norm 2.3592 (1.4358/0.5987)	mem 24308MB
[2025-01-18 17:14:36 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][190/312]	eta 0:01:15 lr 0.003320	time 0.5938 (0.6177)	model_time 0.5936 (0.6085)	loss 3.6964 (3.5728)	grad_norm 1.6273 (1.4327/0.5880)	mem 24308MB
[2025-01-18 17:14:42 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][200/312]	eta 0:01:09 lr 0.003319	time 0.6070 (0.6165)	model_time 0.6066 (0.6078)	loss 3.9878 (3.5596)	grad_norm 1.0540 (1.4506/0.5970)	mem 24308MB
[2025-01-18 17:14:47 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][210/312]	eta 0:01:02 lr 0.003319	time 0.5902 (0.6151)	model_time 0.5898 (0.6069)	loss 3.7674 (3.5708)	grad_norm 1.6885 (1.4561/0.5915)	mem 24308MB
[2025-01-18 17:14:53 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][220/312]	eta 0:00:56 lr 0.003318	time 0.5765 (0.6139)	model_time 0.5764 (0.6060)	loss 3.7661 (3.5706)	grad_norm 1.4774 (1.4472/0.5843)	mem 24308MB
[2025-01-18 17:14:59 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][230/312]	eta 0:00:50 lr 0.003318	time 0.5793 (0.6133)	model_time 0.5792 (0.6057)	loss 3.8342 (3.5565)	grad_norm 1.8331 (1.4453/0.5866)	mem 24308MB
[2025-01-18 17:15:06 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][240/312]	eta 0:00:44 lr 0.003317	time 0.6751 (0.6137)	model_time 0.6750 (0.6064)	loss 3.9237 (3.5488)	grad_norm 2.1109 (1.4515/0.5873)	mem 24308MB
[2025-01-18 17:15:12 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][250/312]	eta 0:00:38 lr 0.003317	time 0.5865 (0.6148)	model_time 0.5863 (0.6078)	loss 3.7175 (3.5428)	grad_norm 0.7173 (1.4517/0.5854)	mem 24308MB
[2025-01-18 17:15:18 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][260/312]	eta 0:00:32 lr 0.003316	time 0.6731 (0.6154)	model_time 0.6729 (0.6087)	loss 3.0644 (3.5269)	grad_norm 1.6055 (1.4638/0.5844)	mem 24308MB
[2025-01-18 17:15:25 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][270/312]	eta 0:00:25 lr 0.003316	time 0.6982 (0.6159)	model_time 0.6977 (0.6094)	loss 3.0056 (3.5218)	grad_norm 2.5524 (1.4760/0.5967)	mem 24308MB
[2025-01-18 17:15:31 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][280/312]	eta 0:00:19 lr 0.003315	time 0.5820 (0.6153)	model_time 0.5819 (0.6090)	loss 2.3305 (3.5235)	grad_norm 1.0285 (1.4710/0.5906)	mem 24308MB
[2025-01-18 17:15:37 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][290/312]	eta 0:00:13 lr 0.003315	time 0.7621 (0.6154)	model_time 0.7620 (0.6092)	loss 3.9195 (3.5229)	grad_norm 1.0144 (1.4584/0.5868)	mem 24308MB
[2025-01-18 17:15:43 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][300/312]	eta 0:00:07 lr 0.003314	time 0.5733 (0.6144)	model_time 0.5732 (0.6085)	loss 3.0518 (3.5253)	grad_norm 1.2152 (1.4611/0.5788)	mem 24308MB
[2025-01-18 17:15:48 internimage_s_1k_224] (main.py 510): INFO Train: [81/300][310/312]	eta 0:00:01 lr 0.003314	time 0.5725 (0.6132)	model_time 0.5724 (0.6074)	loss 3.5253 (3.5308)	grad_norm 2.3994 (1.4767/0.5908)	mem 24308MB
[2025-01-18 17:15:49 internimage_s_1k_224] (main.py 519): INFO EPOCH 81 training takes 0:03:11
[2025-01-18 17:15:49 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_81.pth saving......
[2025-01-18 17:15:51 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_81.pth saved !!!
[2025-01-18 17:15:58 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.125 (7.125)	Loss 0.9190 (0.9190)	Acc@1 79.565 (79.565)	Acc@5 95.996 (95.996)	Mem 24308MB
[2025-01-18 17:16:01 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.972)	Loss 1.3117 (1.0928)	Acc@1 70.898 (76.143)	Acc@5 90.820 (93.413)	Mem 24308MB
[2025-01-18 17:16:02 internimage_s_1k_224] (main.py 575): INFO [Epoch:81] * Acc@1 76.056 Acc@5 93.448
[2025-01-18 17:16:02 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.1%
[2025-01-18 17:16:02 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 76.18%
[2025-01-18 17:16:10 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.093 (8.093)	Loss 0.9463 (0.9463)	Acc@1 76.831 (76.831)	Acc@5 94.019 (94.019)	Mem 24308MB
[2025-01-18 17:16:14 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.096)	Loss 1.4419 (1.1364)	Acc@1 65.356 (72.894)	Acc@5 87.744 (91.555)	Mem 24308MB
[2025-01-18 17:16:14 internimage_s_1k_224] (main.py 575): INFO [Epoch:81] * Acc@1 72.925 Acc@5 91.661
[2025-01-18 17:16:14 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 72.9%
[2025-01-18 17:16:14 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 17:16:16 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 17:16:16 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 72.92%
[2025-01-18 17:16:18 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][0/312]	eta 0:10:26 lr 0.003314	time 2.0073 (2.0073)	model_time 0.5936 (0.5936)	loss 2.9965 (2.9965)	grad_norm 1.3727 (1.3727/0.0000)	mem 24308MB
[2025-01-18 17:16:24 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][10/312]	eta 0:03:40 lr 0.003313	time 0.7169 (0.7311)	model_time 0.7168 (0.6023)	loss 3.7739 (3.6990)	grad_norm 0.8326 (1.3546/0.6596)	mem 24308MB
[2025-01-18 17:16:30 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][20/312]	eta 0:03:13 lr 0.003313	time 0.5786 (0.6639)	model_time 0.5782 (0.5962)	loss 3.7491 (3.5472)	grad_norm 0.9842 (1.2563/0.5215)	mem 24308MB
[2025-01-18 17:16:36 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][30/312]	eta 0:03:00 lr 0.003312	time 0.5796 (0.6408)	model_time 0.5795 (0.5948)	loss 4.1122 (3.6963)	grad_norm 1.6077 (1.5164/0.8515)	mem 24308MB
[2025-01-18 17:16:42 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][40/312]	eta 0:02:52 lr 0.003312	time 0.6409 (0.6326)	model_time 0.6408 (0.5978)	loss 2.7678 (3.6862)	grad_norm 1.3829 (1.4674/0.7668)	mem 24308MB
[2025-01-18 17:16:48 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][50/312]	eta 0:02:44 lr 0.003311	time 0.5858 (0.6286)	model_time 0.5856 (0.6005)	loss 2.8404 (3.6706)	grad_norm 0.8975 (1.5310/0.7781)	mem 24308MB
[2025-01-18 17:16:54 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][60/312]	eta 0:02:37 lr 0.003311	time 0.5867 (0.6269)	model_time 0.5862 (0.6034)	loss 3.7128 (3.6194)	grad_norm 1.7038 (1.5140/0.7324)	mem 24308MB
[2025-01-18 17:17:01 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][70/312]	eta 0:02:31 lr 0.003310	time 0.6559 (0.6280)	model_time 0.6555 (0.6077)	loss 3.5076 (3.6138)	grad_norm 2.1407 (1.5431/0.6998)	mem 24308MB
[2025-01-18 17:17:07 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][80/312]	eta 0:02:25 lr 0.003310	time 0.6274 (0.6278)	model_time 0.6273 (0.6098)	loss 3.7628 (3.5988)	grad_norm 1.7378 (1.5590/0.6882)	mem 24308MB
[2025-01-18 17:17:13 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][90/312]	eta 0:02:18 lr 0.003309	time 0.5793 (0.6249)	model_time 0.5791 (0.6089)	loss 3.9073 (3.5774)	grad_norm 1.2612 (1.5211/0.6661)	mem 24308MB
[2025-01-18 17:17:19 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][100/312]	eta 0:02:12 lr 0.003309	time 0.5740 (0.6227)	model_time 0.5735 (0.6082)	loss 3.3891 (3.5535)	grad_norm 1.7949 (1.5561/0.6731)	mem 24308MB
[2025-01-18 17:17:25 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][110/312]	eta 0:02:05 lr 0.003308	time 0.5738 (0.6214)	model_time 0.5734 (0.6082)	loss 4.3058 (3.5393)	grad_norm 2.2464 (1.5849/0.6743)	mem 24308MB
[2025-01-18 17:17:31 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][120/312]	eta 0:01:58 lr 0.003308	time 0.5993 (0.6189)	model_time 0.5991 (0.6067)	loss 4.3894 (3.5530)	grad_norm 1.0810 (1.5851/0.6807)	mem 24308MB
[2025-01-18 17:17:37 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][130/312]	eta 0:01:52 lr 0.003307	time 0.5912 (0.6165)	model_time 0.5907 (0.6052)	loss 3.1782 (3.5601)	grad_norm 1.7924 (1.5762/0.6771)	mem 24308MB
[2025-01-18 17:17:43 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][140/312]	eta 0:01:45 lr 0.003307	time 0.5918 (0.6150)	model_time 0.5916 (0.6045)	loss 3.1914 (3.5748)	grad_norm 1.6958 (1.5774/0.6559)	mem 24308MB
[2025-01-18 17:17:49 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][150/312]	eta 0:01:39 lr 0.003306	time 0.5997 (0.6133)	model_time 0.5993 (0.6035)	loss 4.3190 (3.5868)	grad_norm 1.7822 (1.5651/0.6404)	mem 24308MB
[2025-01-18 17:17:55 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][160/312]	eta 0:01:33 lr 0.003306	time 0.7065 (0.6125)	model_time 0.7063 (0.6032)	loss 3.0451 (3.5864)	grad_norm 1.0492 (1.5481/0.6308)	mem 24308MB
[2025-01-18 17:18:01 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][170/312]	eta 0:01:26 lr 0.003305	time 0.5899 (0.6124)	model_time 0.5897 (0.6037)	loss 3.8300 (3.5756)	grad_norm 0.9350 (1.5285/0.6270)	mem 24308MB
[2025-01-18 17:18:07 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][180/312]	eta 0:01:21 lr 0.003305	time 0.5781 (0.6138)	model_time 0.5776 (0.6055)	loss 2.5012 (3.5669)	grad_norm 1.7975 (1.5200/0.6157)	mem 24308MB
[2025-01-18 17:18:13 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][190/312]	eta 0:01:15 lr 0.003304	time 0.6792 (0.6149)	model_time 0.6790 (0.6071)	loss 4.2165 (3.5579)	grad_norm 2.7320 (1.5062/0.6147)	mem 24308MB
[2025-01-18 17:18:20 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][200/312]	eta 0:01:08 lr 0.003304	time 0.5722 (0.6152)	model_time 0.5720 (0.6078)	loss 3.4125 (3.5612)	grad_norm 2.0691 (1.5232/0.6144)	mem 24308MB
[2025-01-18 17:18:26 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][210/312]	eta 0:01:02 lr 0.003303	time 0.6050 (0.6147)	model_time 0.6048 (0.6076)	loss 2.6834 (3.5556)	grad_norm 0.9720 (1.5157/0.6087)	mem 24308MB
[2025-01-18 17:18:32 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][220/312]	eta 0:00:56 lr 0.003303	time 0.5895 (0.6145)	model_time 0.5893 (0.6077)	loss 3.5052 (3.5651)	grad_norm 1.0617 (1.4979/0.6017)	mem 24308MB
[2025-01-18 17:18:38 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][230/312]	eta 0:00:50 lr 0.003302	time 0.6053 (0.6142)	model_time 0.6049 (0.6076)	loss 3.8167 (3.5620)	grad_norm 1.9943 (1.5075/0.5999)	mem 24308MB
[2025-01-18 17:18:44 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][240/312]	eta 0:00:44 lr 0.003302	time 0.5885 (0.6131)	model_time 0.5883 (0.6068)	loss 3.6513 (3.5572)	grad_norm 1.3018 (1.5003/0.5995)	mem 24308MB
[2025-01-18 17:18:50 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][250/312]	eta 0:00:37 lr 0.003301	time 0.6130 (0.6123)	model_time 0.6128 (0.6063)	loss 2.9497 (3.5601)	grad_norm 2.0536 (1.5250/0.6309)	mem 24308MB
[2025-01-18 17:18:56 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][260/312]	eta 0:00:31 lr 0.003301	time 0.5820 (0.6117)	model_time 0.5818 (0.6059)	loss 3.6955 (3.5607)	grad_norm 1.1584 (1.5154/0.6232)	mem 24308MB
[2025-01-18 17:19:02 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][270/312]	eta 0:00:25 lr 0.003300	time 0.5845 (0.6108)	model_time 0.5843 (0.6051)	loss 4.0775 (3.5754)	grad_norm 0.6831 (1.5080/0.6215)	mem 24308MB
[2025-01-18 17:19:08 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][280/312]	eta 0:00:19 lr 0.003300	time 0.6575 (0.6103)	model_time 0.6574 (0.6048)	loss 3.8740 (3.5786)	grad_norm 1.1046 (1.5023/0.6159)	mem 24308MB
[2025-01-18 17:19:14 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][290/312]	eta 0:00:13 lr 0.003299	time 0.5831 (0.6106)	model_time 0.5826 (0.6053)	loss 4.3377 (3.5845)	grad_norm 1.6293 (1.4944/0.6094)	mem 24308MB
[2025-01-18 17:19:20 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][300/312]	eta 0:00:07 lr 0.003299	time 0.5751 (0.6108)	model_time 0.5750 (0.6057)	loss 3.3192 (3.5669)	grad_norm 1.8399 (1.4868/0.6061)	mem 24308MB
[2025-01-18 17:19:26 internimage_s_1k_224] (main.py 510): INFO Train: [82/300][310/312]	eta 0:00:01 lr 0.003298	time 0.5692 (0.6105)	model_time 0.5691 (0.6055)	loss 3.9954 (3.5615)	grad_norm 0.8407 (1.4957/0.6073)	mem 24308MB
[2025-01-18 17:19:27 internimage_s_1k_224] (main.py 519): INFO EPOCH 82 training takes 0:03:10
[2025-01-18 17:19:27 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_82.pth saving......
[2025-01-18 17:19:28 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_82.pth saved !!!
[2025-01-18 17:19:36 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.208 (7.208)	Loss 0.9609 (0.9609)	Acc@1 79.761 (79.761)	Acc@5 95.483 (95.483)	Mem 24308MB
[2025-01-18 17:19:39 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.944)	Loss 1.3455 (1.1218)	Acc@1 70.361 (76.176)	Acc@5 90.552 (93.464)	Mem 24308MB
[2025-01-18 17:19:39 internimage_s_1k_224] (main.py 575): INFO [Epoch:82] * Acc@1 76.150 Acc@5 93.550
[2025-01-18 17:19:39 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.1%
[2025-01-18 17:19:39 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 76.18%
[2025-01-18 17:19:47 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.154 (8.154)	Loss 0.9363 (0.9363)	Acc@1 77.051 (77.051)	Acc@5 94.092 (94.092)	Mem 24308MB
[2025-01-18 17:19:51 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.118)	Loss 1.4267 (1.1248)	Acc@1 65.527 (73.056)	Acc@5 87.793 (91.688)	Mem 24308MB
[2025-01-18 17:19:51 internimage_s_1k_224] (main.py 575): INFO [Epoch:82] * Acc@1 73.085 Acc@5 91.793
[2025-01-18 17:19:51 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 73.1%
[2025-01-18 17:19:51 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 17:19:54 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 17:19:54 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 73.08%
[2025-01-18 17:19:57 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][0/312]	eta 0:14:01 lr 0.003298	time 2.6956 (2.6956)	model_time 0.6451 (0.6451)	loss 3.6239 (3.6239)	grad_norm 0.8878 (0.8878/0.0000)	mem 24308MB
[2025-01-18 17:20:03 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][10/312]	eta 0:04:06 lr 0.003297	time 0.5864 (0.8157)	model_time 0.5862 (0.6290)	loss 3.5881 (3.2566)	grad_norm 1.8897 (1.2233/0.2678)	mem 24308MB
[2025-01-18 17:20:09 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][20/312]	eta 0:03:27 lr 0.003297	time 0.5748 (0.7103)	model_time 0.5746 (0.6123)	loss 3.4507 (3.4497)	grad_norm 2.9921 (1.4702/0.6622)	mem 24308MB
[2025-01-18 17:20:15 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][30/312]	eta 0:03:10 lr 0.003296	time 0.5814 (0.6749)	model_time 0.5812 (0.6084)	loss 3.5266 (3.4582)	grad_norm 3.8691 (1.6496/0.8018)	mem 24308MB
[2025-01-18 17:20:21 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][40/312]	eta 0:02:58 lr 0.003296	time 0.5750 (0.6565)	model_time 0.5748 (0.6061)	loss 2.2722 (3.4546)	grad_norm 0.6211 (1.6979/0.8326)	mem 24308MB
[2025-01-18 17:20:27 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][50/312]	eta 0:02:48 lr 0.003295	time 0.5812 (0.6425)	model_time 0.5810 (0.6020)	loss 3.4805 (3.4746)	grad_norm 0.6453 (1.5602/0.8026)	mem 24308MB
[2025-01-18 17:20:33 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][60/312]	eta 0:02:39 lr 0.003295	time 0.5793 (0.6342)	model_time 0.5792 (0.6002)	loss 3.1851 (3.4320)	grad_norm 1.0760 (1.4829/0.7643)	mem 24308MB
[2025-01-18 17:20:39 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][70/312]	eta 0:02:31 lr 0.003294	time 0.5880 (0.6281)	model_time 0.5876 (0.5989)	loss 4.3117 (3.4579)	grad_norm 1.3464 (1.5330/0.7920)	mem 24308MB
[2025-01-18 17:20:44 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][80/312]	eta 0:02:24 lr 0.003294	time 0.5847 (0.6234)	model_time 0.5842 (0.5977)	loss 3.3823 (3.4549)	grad_norm 1.1552 (1.5540/0.7824)	mem 24308MB
[2025-01-18 17:20:50 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][90/312]	eta 0:02:17 lr 0.003293	time 0.6104 (0.6203)	model_time 0.6103 (0.5974)	loss 3.3597 (3.4405)	grad_norm 1.6120 (1.4967/0.7688)	mem 24308MB
[2025-01-18 17:20:57 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][100/312]	eta 0:02:11 lr 0.003293	time 0.5981 (0.6202)	model_time 0.5977 (0.5995)	loss 3.3588 (3.4325)	grad_norm 1.4363 (1.5265/0.7832)	mem 24308MB
[2025-01-18 17:21:03 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][110/312]	eta 0:02:05 lr 0.003292	time 0.5898 (0.6199)	model_time 0.5894 (0.6010)	loss 3.3780 (3.4412)	grad_norm 2.1373 (1.5211/0.7696)	mem 24308MB
[2025-01-18 17:21:09 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][120/312]	eta 0:01:59 lr 0.003292	time 0.6764 (0.6203)	model_time 0.6763 (0.6030)	loss 2.7465 (3.4384)	grad_norm 2.7259 (1.5306/0.7591)	mem 24308MB
[2025-01-18 17:21:15 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][130/312]	eta 0:01:53 lr 0.003291	time 0.5846 (0.6218)	model_time 0.5841 (0.6058)	loss 4.6108 (3.4693)	grad_norm 0.8466 (1.5299/0.7555)	mem 24308MB
[2025-01-18 17:21:21 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][140/312]	eta 0:01:46 lr 0.003291	time 0.5832 (0.6207)	model_time 0.5830 (0.6058)	loss 3.8951 (3.4749)	grad_norm 1.4830 (1.5234/0.7398)	mem 24308MB
[2025-01-18 17:21:27 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][150/312]	eta 0:01:40 lr 0.003290	time 0.5801 (0.6192)	model_time 0.5799 (0.6053)	loss 2.9662 (3.4681)	grad_norm 0.9192 (1.5316/0.7306)	mem 24308MB
[2025-01-18 17:21:33 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][160/312]	eta 0:01:33 lr 0.003290	time 0.5752 (0.6179)	model_time 0.5748 (0.6048)	loss 2.7774 (3.4642)	grad_norm 1.3136 (1.5211/0.7167)	mem 24308MB
[2025-01-18 17:21:39 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][170/312]	eta 0:01:27 lr 0.003289	time 0.6012 (0.6165)	model_time 0.6008 (0.6041)	loss 3.7830 (3.4628)	grad_norm 0.9386 (1.5046/0.7064)	mem 24308MB
[2025-01-18 17:21:45 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][180/312]	eta 0:01:21 lr 0.003289	time 0.5945 (0.6151)	model_time 0.5940 (0.6034)	loss 3.9085 (3.4756)	grad_norm 1.7079 (1.4912/0.6914)	mem 24308MB
[2025-01-18 17:21:51 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][190/312]	eta 0:01:14 lr 0.003288	time 0.5928 (0.6138)	model_time 0.5926 (0.6026)	loss 4.3384 (3.4916)	grad_norm 1.6853 (1.4899/0.6783)	mem 24308MB
[2025-01-18 17:21:57 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][200/312]	eta 0:01:08 lr 0.003288	time 0.5808 (0.6124)	model_time 0.5806 (0.6017)	loss 3.7187 (3.4939)	grad_norm 1.1520 (1.5513/0.7795)	mem 24308MB
[2025-01-18 17:22:03 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][210/312]	eta 0:01:02 lr 0.003287	time 0.5736 (0.6117)	model_time 0.5735 (0.6016)	loss 3.9471 (3.4912)	grad_norm 1.0358 (1.5333/0.7679)	mem 24308MB
[2025-01-18 17:22:09 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][220/312]	eta 0:00:56 lr 0.003287	time 0.6175 (0.6119)	model_time 0.6174 (0.6022)	loss 3.2920 (3.4906)	grad_norm 1.2122 (1.5070/0.7620)	mem 24308MB
[2025-01-18 17:22:15 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][230/312]	eta 0:00:50 lr 0.003286	time 0.5989 (0.6120)	model_time 0.5984 (0.6027)	loss 2.8014 (3.4952)	grad_norm 2.2199 (1.5340/0.7680)	mem 24308MB
[2025-01-18 17:22:21 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][240/312]	eta 0:00:44 lr 0.003286	time 0.5731 (0.6121)	model_time 0.5729 (0.6032)	loss 3.6149 (3.4977)	grad_norm 0.9021 (1.5311/0.7562)	mem 24308MB
[2025-01-18 17:22:28 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][250/312]	eta 0:00:37 lr 0.003285	time 0.5785 (0.6125)	model_time 0.5783 (0.6039)	loss 2.8379 (3.4899)	grad_norm 1.1791 (1.5168/0.7451)	mem 24308MB
[2025-01-18 17:22:34 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][260/312]	eta 0:00:31 lr 0.003285	time 0.5775 (0.6130)	model_time 0.5774 (0.6047)	loss 2.7023 (3.4903)	grad_norm 0.7846 (1.5041/0.7403)	mem 24308MB
[2025-01-18 17:22:40 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][270/312]	eta 0:00:25 lr 0.003284	time 0.5776 (0.6125)	model_time 0.5772 (0.6045)	loss 2.4356 (3.4897)	grad_norm 2.1089 (1.4980/0.7359)	mem 24308MB
[2025-01-18 17:22:46 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][280/312]	eta 0:00:19 lr 0.003284	time 0.5865 (0.6118)	model_time 0.5861 (0.6041)	loss 4.1067 (3.5028)	grad_norm 1.6533 (1.5025/0.7277)	mem 24308MB
[2025-01-18 17:22:52 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][290/312]	eta 0:00:13 lr 0.003283	time 0.6048 (0.6113)	model_time 0.6044 (0.6038)	loss 3.7868 (3.5030)	grad_norm 3.3660 (1.5065/0.7370)	mem 24308MB
[2025-01-18 17:22:58 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][300/312]	eta 0:00:07 lr 0.003283	time 0.5634 (0.6102)	model_time 0.5633 (0.6030)	loss 3.7560 (3.5019)	grad_norm 1.1047 (1.5053/0.7335)	mem 24308MB
[2025-01-18 17:23:03 internimage_s_1k_224] (main.py 510): INFO Train: [83/300][310/312]	eta 0:00:01 lr 0.003282	time 0.5671 (0.6089)	model_time 0.5670 (0.6019)	loss 3.5029 (3.4992)	grad_norm 1.5797 (1.5070/0.7364)	mem 24308MB
[2025-01-18 17:23:04 internimage_s_1k_224] (main.py 519): INFO EPOCH 83 training takes 0:03:09
[2025-01-18 17:23:04 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_83.pth saving......
[2025-01-18 17:23:06 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_83.pth saved !!!
[2025-01-18 17:23:13 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.995 (6.995)	Loss 0.9076 (0.9076)	Acc@1 79.810 (79.810)	Acc@5 95.312 (95.312)	Mem 24308MB
[2025-01-18 17:23:16 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.921)	Loss 1.3040 (1.0877)	Acc@1 70.996 (76.285)	Acc@5 90.771 (93.459)	Mem 24308MB
[2025-01-18 17:23:16 internimage_s_1k_224] (main.py 575): INFO [Epoch:83] * Acc@1 76.182 Acc@5 93.516
[2025-01-18 17:23:16 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.2%
[2025-01-18 17:23:16 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 17:23:18 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 17:23:18 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 76.18%
[2025-01-18 17:23:25 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.075 (7.075)	Loss 0.9262 (0.9262)	Acc@1 77.344 (77.344)	Acc@5 94.189 (94.189)	Mem 24308MB
[2025-01-18 17:23:28 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.941)	Loss 1.4117 (1.1134)	Acc@1 65.918 (73.304)	Acc@5 88.037 (91.839)	Mem 24308MB
[2025-01-18 17:23:28 internimage_s_1k_224] (main.py 575): INFO [Epoch:83] * Acc@1 73.317 Acc@5 91.941
[2025-01-18 17:23:29 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 73.3%
[2025-01-18 17:23:29 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 17:23:31 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 17:23:31 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 73.32%
[2025-01-18 17:23:33 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][0/312]	eta 0:10:51 lr 0.003282	time 2.0895 (2.0895)	model_time 0.6129 (0.6129)	loss 3.4357 (3.4357)	grad_norm 1.3013 (1.3013/0.0000)	mem 24308MB
[2025-01-18 17:23:39 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][10/312]	eta 0:03:40 lr 0.003282	time 0.5735 (0.7285)	model_time 0.5731 (0.5939)	loss 2.6919 (3.6765)	grad_norm 1.1129 (1.0737/0.2740)	mem 24308MB
[2025-01-18 17:23:45 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][20/312]	eta 0:03:14 lr 0.003281	time 0.5903 (0.6659)	model_time 0.5898 (0.5952)	loss 2.4702 (3.6211)	grad_norm 4.4179 (1.6387/1.0193)	mem 24308MB
[2025-01-18 17:23:51 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][30/312]	eta 0:03:03 lr 0.003281	time 0.6597 (0.6496)	model_time 0.6592 (0.6016)	loss 3.6865 (3.5930)	grad_norm 1.2308 (1.6021/0.9166)	mem 24308MB
[2025-01-18 17:23:57 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][40/312]	eta 0:02:54 lr 0.003280	time 0.5878 (0.6416)	model_time 0.5876 (0.6052)	loss 3.9633 (3.6134)	grad_norm 1.0889 (1.4621/0.8370)	mem 24308MB
[2025-01-18 17:24:03 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][50/312]	eta 0:02:46 lr 0.003280	time 0.5801 (0.6354)	model_time 0.5797 (0.6061)	loss 4.4219 (3.6649)	grad_norm 1.0414 (1.5545/0.8285)	mem 24308MB
[2025-01-18 17:24:09 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][60/312]	eta 0:02:40 lr 0.003279	time 0.6570 (0.6370)	model_time 0.6568 (0.6125)	loss 3.4782 (3.6701)	grad_norm 1.2381 (1.6242/0.8619)	mem 24308MB
[2025-01-18 17:24:16 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][70/312]	eta 0:02:33 lr 0.003279	time 0.6287 (0.6332)	model_time 0.6283 (0.6120)	loss 2.9694 (3.6763)	grad_norm 0.9032 (1.6151/0.8403)	mem 24308MB
[2025-01-18 17:24:22 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][80/312]	eta 0:02:25 lr 0.003278	time 0.5820 (0.6291)	model_time 0.5818 (0.6105)	loss 3.8589 (3.7029)	grad_norm 2.5314 (1.6080/0.8277)	mem 24308MB
[2025-01-18 17:24:28 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][90/312]	eta 0:02:19 lr 0.003277	time 0.7210 (0.6270)	model_time 0.7208 (0.6104)	loss 4.2567 (3.6566)	grad_norm 0.6222 (1.5798/0.8022)	mem 24308MB
[2025-01-18 17:24:34 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][100/312]	eta 0:02:12 lr 0.003277	time 0.5802 (0.6231)	model_time 0.5800 (0.6081)	loss 4.1632 (3.6669)	grad_norm 0.8710 (1.5352/0.7766)	mem 24308MB
[2025-01-18 17:24:39 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][110/312]	eta 0:02:05 lr 0.003276	time 0.6047 (0.6201)	model_time 0.6043 (0.6064)	loss 4.1106 (3.6489)	grad_norm 1.7488 (1.5166/0.7532)	mem 24308MB
[2025-01-18 17:24:45 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][120/312]	eta 0:01:58 lr 0.003276	time 0.6015 (0.6177)	model_time 0.6013 (0.6051)	loss 4.2958 (3.6590)	grad_norm 1.4797 (1.5067/0.7272)	mem 24308MB
[2025-01-18 17:24:51 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][130/312]	eta 0:01:51 lr 0.003275	time 0.5862 (0.6153)	model_time 0.5861 (0.6036)	loss 4.3072 (3.6550)	grad_norm 1.1805 (1.5066/0.7274)	mem 24308MB
[2025-01-18 17:24:57 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][140/312]	eta 0:01:45 lr 0.003275	time 0.5788 (0.6136)	model_time 0.5784 (0.6028)	loss 3.2230 (3.6607)	grad_norm 1.9106 (1.5324/0.7198)	mem 24308MB
[2025-01-18 17:25:03 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][150/312]	eta 0:01:39 lr 0.003274	time 0.5783 (0.6137)	model_time 0.5778 (0.6035)	loss 4.5900 (3.6464)	grad_norm 1.0206 (1.5205/0.7025)	mem 24308MB
[2025-01-18 17:25:10 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][160/312]	eta 0:01:33 lr 0.003274	time 0.6864 (0.6147)	model_time 0.6863 (0.6050)	loss 4.0208 (3.6473)	grad_norm 1.2502 (1.4985/0.6884)	mem 24308MB
[2025-01-18 17:25:16 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][170/312]	eta 0:01:27 lr 0.003273	time 0.5900 (0.6147)	model_time 0.5898 (0.6057)	loss 3.1854 (3.6494)	grad_norm 1.7408 (1.5307/0.8300)	mem 24308MB
[2025-01-18 17:25:22 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][180/312]	eta 0:01:21 lr 0.003273	time 0.6660 (0.6175)	model_time 0.6656 (0.6089)	loss 3.1672 (3.6471)	grad_norm 1.4124 (1.5428/0.8161)	mem 24308MB
[2025-01-18 17:25:28 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][190/312]	eta 0:01:15 lr 0.003272	time 0.6053 (0.6169)	model_time 0.6052 (0.6087)	loss 3.4417 (3.6413)	grad_norm 0.8426 (1.5331/0.7983)	mem 24308MB
[2025-01-18 17:25:34 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][200/312]	eta 0:01:09 lr 0.003272	time 0.6527 (0.6163)	model_time 0.6525 (0.6085)	loss 4.3410 (3.6351)	grad_norm 1.4460 (1.5317/0.7898)	mem 24308MB
[2025-01-18 17:25:41 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][210/312]	eta 0:01:02 lr 0.003271	time 0.7136 (0.6159)	model_time 0.7134 (0.6084)	loss 4.0776 (3.6431)	grad_norm 1.0013 (1.5270/0.7768)	mem 24308MB
[2025-01-18 17:25:46 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][220/312]	eta 0:00:56 lr 0.003271	time 0.6050 (0.6145)	model_time 0.6046 (0.6074)	loss 3.9599 (3.6378)	grad_norm 1.1705 (1.5239/0.7652)	mem 24308MB
[2025-01-18 17:25:52 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][230/312]	eta 0:00:50 lr 0.003270	time 0.5909 (0.6133)	model_time 0.5907 (0.6064)	loss 3.7229 (3.6407)	grad_norm 1.4056 (1.5371/0.7609)	mem 24308MB
[2025-01-18 17:25:58 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][240/312]	eta 0:00:44 lr 0.003270	time 0.5850 (0.6121)	model_time 0.5844 (0.6056)	loss 3.9290 (3.6394)	grad_norm 1.3548 (1.5388/0.7563)	mem 24308MB
[2025-01-18 17:26:04 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][250/312]	eta 0:00:37 lr 0.003269	time 0.5805 (0.6111)	model_time 0.5803 (0.6048)	loss 3.6020 (3.6396)	grad_norm 1.8550 (1.5326/0.7494)	mem 24308MB
[2025-01-18 17:26:10 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][260/312]	eta 0:00:31 lr 0.003269	time 0.5753 (0.6106)	model_time 0.5748 (0.6046)	loss 4.3063 (3.6420)	grad_norm 2.0695 (1.5516/0.7637)	mem 24308MB
[2025-01-18 17:26:16 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][270/312]	eta 0:00:25 lr 0.003268	time 0.5810 (0.6108)	model_time 0.5809 (0.6049)	loss 3.7205 (3.6269)	grad_norm 1.8751 (1.5506/0.7546)	mem 24308MB
[2025-01-18 17:26:22 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][280/312]	eta 0:00:19 lr 0.003268	time 0.5758 (0.6114)	model_time 0.5756 (0.6058)	loss 3.1202 (3.6274)	grad_norm 1.3556 (1.5382/0.7451)	mem 24308MB
[2025-01-18 17:26:29 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][290/312]	eta 0:00:13 lr 0.003267	time 0.6709 (0.6122)	model_time 0.6708 (0.6067)	loss 4.3098 (3.6248)	grad_norm 1.1787 (1.5249/0.7364)	mem 24308MB
[2025-01-18 17:26:35 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][300/312]	eta 0:00:07 lr 0.003267	time 0.6468 (0.6130)	model_time 0.6467 (0.6077)	loss 3.7707 (3.6264)	grad_norm 1.0568 (1.5217/0.7303)	mem 24308MB
[2025-01-18 17:26:41 internimage_s_1k_224] (main.py 510): INFO Train: [84/300][310/312]	eta 0:00:01 lr 0.003266	time 0.5724 (0.6122)	model_time 0.5723 (0.6071)	loss 3.9573 (3.6213)	grad_norm 1.5274 (1.5292/0.7273)	mem 24308MB
[2025-01-18 17:26:42 internimage_s_1k_224] (main.py 519): INFO EPOCH 84 training takes 0:03:10
[2025-01-18 17:26:42 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_84.pth saving......
[2025-01-18 17:26:43 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_84.pth saved !!!
[2025-01-18 17:26:50 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.839 (6.839)	Loss 0.8896 (0.8896)	Acc@1 80.078 (80.078)	Acc@5 96.045 (96.045)	Mem 24308MB
[2025-01-18 17:26:53 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.920)	Loss 1.3034 (1.0826)	Acc@1 70.874 (76.556)	Acc@5 90.820 (93.521)	Mem 24308MB
[2025-01-18 17:26:54 internimage_s_1k_224] (main.py 575): INFO [Epoch:84] * Acc@1 76.524 Acc@5 93.578
[2025-01-18 17:26:54 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.5%
[2025-01-18 17:26:54 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 17:26:56 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 17:26:56 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 76.52%
[2025-01-18 17:27:03 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.973 (6.973)	Loss 0.9165 (0.9165)	Acc@1 77.441 (77.441)	Acc@5 94.360 (94.360)	Mem 24308MB
[2025-01-18 17:27:06 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.906)	Loss 1.3974 (1.1026)	Acc@1 66.138 (73.477)	Acc@5 88.135 (91.981)	Mem 24308MB
[2025-01-18 17:27:06 internimage_s_1k_224] (main.py 575): INFO [Epoch:84] * Acc@1 73.478 Acc@5 92.079
[2025-01-18 17:27:06 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 73.5%
[2025-01-18 17:27:06 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 17:27:08 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 17:27:08 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 73.48%
[2025-01-18 17:27:10 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][0/312]	eta 0:11:45 lr 0.003266	time 2.2600 (2.2600)	model_time 0.5949 (0.5949)	loss 3.3977 (3.3977)	grad_norm 1.2065 (1.2065/0.0000)	mem 24308MB
[2025-01-18 17:27:16 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][10/312]	eta 0:03:48 lr 0.003266	time 0.5907 (0.7562)	model_time 0.5906 (0.6045)	loss 3.6701 (3.6387)	grad_norm 1.7218 (1.5394/0.6291)	mem 24308MB
[2025-01-18 17:27:22 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][20/312]	eta 0:03:18 lr 0.003265	time 0.5853 (0.6807)	model_time 0.5849 (0.6011)	loss 4.0741 (3.7749)	grad_norm 2.3130 (1.5809/0.5395)	mem 24308MB
[2025-01-18 17:27:28 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][30/312]	eta 0:03:04 lr 0.003265	time 0.6063 (0.6543)	model_time 0.6061 (0.6002)	loss 3.6685 (3.7591)	grad_norm 2.3021 (1.5649/0.5077)	mem 24308MB
[2025-01-18 17:27:34 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][40/312]	eta 0:02:53 lr 0.003264	time 0.5768 (0.6388)	model_time 0.5766 (0.5978)	loss 4.2833 (3.7160)	grad_norm 1.7648 (1.6042/0.5441)	mem 24308MB
[2025-01-18 17:27:40 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][50/312]	eta 0:02:45 lr 0.003263	time 0.5976 (0.6302)	model_time 0.5972 (0.5972)	loss 4.0702 (3.7084)	grad_norm 1.1093 (1.5370/0.5196)	mem 24308MB
[2025-01-18 17:27:46 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][60/312]	eta 0:02:36 lr 0.003263	time 0.5767 (0.6226)	model_time 0.5763 (0.5949)	loss 3.4201 (3.6856)	grad_norm 1.9924 (1.4717/0.5160)	mem 24308MB
[2025-01-18 17:27:52 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][70/312]	eta 0:02:29 lr 0.003262	time 0.5861 (0.6194)	model_time 0.5859 (0.5956)	loss 3.8172 (3.6635)	grad_norm 1.6014 (1.4898/0.5495)	mem 24308MB
[2025-01-18 17:27:58 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][80/312]	eta 0:02:23 lr 0.003262	time 0.5888 (0.6172)	model_time 0.5883 (0.5963)	loss 3.5371 (3.6399)	grad_norm 1.2531 (1.5376/0.5826)	mem 24308MB
[2025-01-18 17:28:04 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][90/312]	eta 0:02:17 lr 0.003261	time 0.6395 (0.6188)	model_time 0.6394 (0.6001)	loss 2.5049 (3.6188)	grad_norm 2.7882 (1.5500/0.6270)	mem 24308MB
[2025-01-18 17:28:11 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][100/312]	eta 0:02:11 lr 0.003261	time 0.6591 (0.6221)	model_time 0.6589 (0.6053)	loss 3.1874 (3.6046)	grad_norm 0.9882 (1.5614/0.6195)	mem 24308MB
[2025-01-18 17:28:17 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][110/312]	eta 0:02:05 lr 0.003260	time 0.6657 (0.6219)	model_time 0.6652 (0.6066)	loss 3.8223 (3.5876)	grad_norm 1.1267 (1.5570/0.6107)	mem 24308MB
[2025-01-18 17:28:23 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][120/312]	eta 0:01:59 lr 0.003260	time 0.5717 (0.6204)	model_time 0.5715 (0.6063)	loss 2.6302 (3.5544)	grad_norm 1.3525 (1.5345/0.6114)	mem 24308MB
[2025-01-18 17:28:29 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][130/312]	eta 0:01:52 lr 0.003259	time 0.5841 (0.6192)	model_time 0.5839 (0.6061)	loss 3.8258 (3.5618)	grad_norm 2.0371 (1.5427/0.6021)	mem 24308MB
[2025-01-18 17:28:35 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][140/312]	eta 0:01:46 lr 0.003259	time 0.5758 (0.6175)	model_time 0.5756 (0.6054)	loss 3.5691 (3.5912)	grad_norm 2.1189 (1.5822/0.6081)	mem 24308MB
[2025-01-18 17:28:41 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][150/312]	eta 0:01:39 lr 0.003258	time 0.5815 (0.6160)	model_time 0.5813 (0.6046)	loss 3.0225 (3.6011)	grad_norm 0.9472 (1.5604/0.6042)	mem 24308MB
[2025-01-18 17:28:47 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][160/312]	eta 0:01:33 lr 0.003258	time 0.5914 (0.6142)	model_time 0.5910 (0.6034)	loss 4.1084 (3.6116)	grad_norm 1.1854 (1.5431/0.6018)	mem 24308MB
[2025-01-18 17:28:53 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][170/312]	eta 0:01:27 lr 0.003257	time 0.5980 (0.6129)	model_time 0.5978 (0.6028)	loss 3.0819 (3.6124)	grad_norm 1.5228 (1.5178/0.5968)	mem 24308MB
[2025-01-18 17:28:59 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][180/312]	eta 0:01:20 lr 0.003257	time 0.5752 (0.6117)	model_time 0.5750 (0.6021)	loss 4.3629 (3.6139)	grad_norm 0.9327 (1.5267/0.5999)	mem 24308MB
[2025-01-18 17:29:05 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][190/312]	eta 0:01:14 lr 0.003256	time 0.5980 (0.6110)	model_time 0.5979 (0.6018)	loss 3.4353 (3.6135)	grad_norm 1.4815 (1.5218/0.6180)	mem 24308MB
[2025-01-18 17:29:11 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][200/312]	eta 0:01:08 lr 0.003256	time 0.5922 (0.6113)	model_time 0.5921 (0.6026)	loss 3.7333 (3.6165)	grad_norm 1.3152 (1.5261/0.6120)	mem 24308MB
[2025-01-18 17:29:17 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][210/312]	eta 0:01:02 lr 0.003255	time 0.6570 (0.6122)	model_time 0.6568 (0.6039)	loss 3.9252 (3.6230)	grad_norm 1.0997 (1.5154/0.6068)	mem 24308MB
[2025-01-18 17:29:23 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][220/312]	eta 0:00:56 lr 0.003255	time 0.5778 (0.6130)	model_time 0.5777 (0.6050)	loss 3.2026 (3.6189)	grad_norm 0.8523 (1.5168/0.6059)	mem 24308MB
[2025-01-18 17:29:30 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][230/312]	eta 0:00:50 lr 0.003254	time 0.6765 (0.6130)	model_time 0.6763 (0.6054)	loss 4.1732 (3.6157)	grad_norm 1.2822 (1.5079/0.6044)	mem 24308MB
[2025-01-18 17:29:36 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][240/312]	eta 0:00:44 lr 0.003254	time 0.5786 (0.6132)	model_time 0.5782 (0.6059)	loss 3.4081 (3.6016)	grad_norm 1.4099 (1.5220/0.6468)	mem 24308MB
[2025-01-18 17:29:42 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][250/312]	eta 0:00:38 lr 0.003253	time 0.5857 (0.6131)	model_time 0.5852 (0.6061)	loss 3.8724 (3.6053)	grad_norm 1.1847 (1.5162/0.6414)	mem 24308MB
[2025-01-18 17:29:48 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][260/312]	eta 0:00:31 lr 0.003253	time 0.5671 (0.6126)	model_time 0.5668 (0.6058)	loss 4.1572 (3.6026)	grad_norm 1.0836 (1.5151/0.6378)	mem 24308MB
[2025-01-18 17:29:54 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][270/312]	eta 0:00:25 lr 0.003252	time 0.5926 (0.6121)	model_time 0.5925 (0.6055)	loss 3.9636 (3.6083)	grad_norm 2.0318 (1.5160/0.6326)	mem 24308MB
[2025-01-18 17:30:00 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][280/312]	eta 0:00:19 lr 0.003252	time 0.6000 (0.6114)	model_time 0.5998 (0.6050)	loss 3.5379 (3.6057)	grad_norm 1.5265 (1.5011/0.6294)	mem 24308MB
[2025-01-18 17:30:06 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][290/312]	eta 0:00:13 lr 0.003251	time 0.5672 (0.6106)	model_time 0.5670 (0.6045)	loss 3.4100 (3.6105)	grad_norm 0.7641 (1.4994/0.6274)	mem 24308MB
[2025-01-18 17:30:11 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][300/312]	eta 0:00:07 lr 0.003250	time 0.5684 (0.6096)	model_time 0.5683 (0.6036)	loss 3.6347 (3.6128)	grad_norm 1.5820 (1.4857/0.6249)	mem 24308MB
[2025-01-18 17:30:17 internimage_s_1k_224] (main.py 510): INFO Train: [85/300][310/312]	eta 0:00:01 lr 0.003250	time 0.5675 (0.6086)	model_time 0.5674 (0.6029)	loss 3.5255 (3.6163)	grad_norm 2.8279 (1.4804/0.6210)	mem 24308MB
[2025-01-18 17:30:18 internimage_s_1k_224] (main.py 519): INFO EPOCH 85 training takes 0:03:09
[2025-01-18 17:30:18 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_85.pth saving......
[2025-01-18 17:30:20 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_85.pth saved !!!
[2025-01-18 17:30:27 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.123 (7.123)	Loss 0.9469 (0.9469)	Acc@1 80.542 (80.542)	Acc@5 95.923 (95.923)	Mem 24308MB
[2025-01-18 17:30:30 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.931)	Loss 1.3156 (1.1131)	Acc@1 71.582 (76.389)	Acc@5 91.064 (93.661)	Mem 24308MB
[2025-01-18 17:30:30 internimage_s_1k_224] (main.py 575): INFO [Epoch:85] * Acc@1 76.410 Acc@5 93.736
[2025-01-18 17:30:30 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.4%
[2025-01-18 17:30:30 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 76.52%
[2025-01-18 17:30:39 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.516 (8.516)	Loss 0.9068 (0.9068)	Acc@1 77.710 (77.710)	Acc@5 94.458 (94.458)	Mem 24308MB
[2025-01-18 17:30:43 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.153)	Loss 1.3841 (1.0923)	Acc@1 66.553 (73.750)	Acc@5 88.477 (92.114)	Mem 24308MB
[2025-01-18 17:30:43 internimage_s_1k_224] (main.py 575): INFO [Epoch:85] * Acc@1 73.744 Acc@5 92.204
[2025-01-18 17:30:43 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 73.7%
[2025-01-18 17:30:43 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 17:30:45 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 17:30:45 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 73.74%
[2025-01-18 17:30:47 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][0/312]	eta 0:12:05 lr 0.003250	time 2.3254 (2.3254)	model_time 0.6132 (0.6132)	loss 2.2007 (2.2007)	grad_norm 2.0007 (2.0007/0.0000)	mem 24308MB
[2025-01-18 17:30:54 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][10/312]	eta 0:03:50 lr 0.003249	time 0.6714 (0.7648)	model_time 0.6712 (0.6087)	loss 3.1625 (3.2482)	grad_norm 1.5713 (1.7897/0.8610)	mem 24308MB
[2025-01-18 17:31:00 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][20/312]	eta 0:03:26 lr 0.003249	time 0.8622 (0.7085)	model_time 0.8620 (0.6267)	loss 3.9904 (3.4902)	grad_norm 1.0751 (1.8661/0.9981)	mem 24308MB
[2025-01-18 17:31:06 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][30/312]	eta 0:03:12 lr 0.003248	time 0.6778 (0.6828)	model_time 0.6776 (0.6272)	loss 4.1559 (3.5907)	grad_norm 2.0811 (1.7190/0.8715)	mem 24308MB
[2025-01-18 17:31:12 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][40/312]	eta 0:03:00 lr 0.003248	time 0.6009 (0.6650)	model_time 0.6007 (0.6229)	loss 4.4585 (3.6147)	grad_norm 1.4130 (1.6553/0.8618)	mem 24308MB
[2025-01-18 17:31:18 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][50/312]	eta 0:02:51 lr 0.003247	time 0.5864 (0.6541)	model_time 0.5858 (0.6202)	loss 4.1293 (3.6234)	grad_norm 0.9335 (1.6747/0.8382)	mem 24308MB
[2025-01-18 17:31:25 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][60/312]	eta 0:02:42 lr 0.003247	time 0.5718 (0.6465)	model_time 0.5716 (0.6180)	loss 2.7334 (3.5680)	grad_norm 2.3643 (1.6610/0.8252)	mem 24308MB
[2025-01-18 17:31:31 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][70/312]	eta 0:02:35 lr 0.003246	time 0.5810 (0.6425)	model_time 0.5808 (0.6180)	loss 3.2788 (3.5963)	grad_norm 1.6175 (1.6305/0.7825)	mem 24308MB
[2025-01-18 17:31:37 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][80/312]	eta 0:02:27 lr 0.003246	time 0.5799 (0.6356)	model_time 0.5796 (0.6141)	loss 3.3936 (3.5926)	grad_norm 1.9045 (1.5901/0.7528)	mem 24308MB
[2025-01-18 17:31:42 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][90/312]	eta 0:02:19 lr 0.003245	time 0.5817 (0.6302)	model_time 0.5815 (0.6110)	loss 3.5625 (3.5937)	grad_norm 1.0140 (1.5653/0.7236)	mem 24308MB
[2025-01-18 17:31:48 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][100/312]	eta 0:02:12 lr 0.003245	time 0.5672 (0.6258)	model_time 0.5670 (0.6085)	loss 3.7920 (3.5714)	grad_norm 1.4020 (1.5424/0.7023)	mem 24308MB
[2025-01-18 17:31:54 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][110/312]	eta 0:02:05 lr 0.003244	time 0.5849 (0.6224)	model_time 0.5845 (0.6067)	loss 3.6087 (3.5726)	grad_norm 1.1897 (1.5124/0.6792)	mem 24308MB
[2025-01-18 17:32:00 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][120/312]	eta 0:01:59 lr 0.003244	time 0.6295 (0.6201)	model_time 0.6293 (0.6056)	loss 3.7083 (3.5832)	grad_norm 1.2213 (1.4917/0.6576)	mem 24308MB
[2025-01-18 17:32:06 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][130/312]	eta 0:01:52 lr 0.003243	time 0.5866 (0.6187)	model_time 0.5865 (0.6052)	loss 2.8073 (3.5882)	grad_norm 0.9570 (1.5464/0.7203)	mem 24308MB
[2025-01-18 17:32:13 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][140/312]	eta 0:01:46 lr 0.003243	time 0.6606 (0.6200)	model_time 0.6604 (0.6075)	loss 2.9720 (3.5758)	grad_norm 1.5633 (1.5519/0.7007)	mem 24308MB
[2025-01-18 17:32:19 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][150/312]	eta 0:01:40 lr 0.003242	time 0.6160 (0.6205)	model_time 0.6157 (0.6087)	loss 3.2702 (3.5640)	grad_norm 1.0898 (1.5432/0.6850)	mem 24308MB
[2025-01-18 17:32:25 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][160/312]	eta 0:01:34 lr 0.003242	time 0.6747 (0.6209)	model_time 0.6746 (0.6099)	loss 3.8561 (3.5687)	grad_norm 1.7395 (1.5293/0.6716)	mem 24308MB
[2025-01-18 17:32:31 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][170/312]	eta 0:01:28 lr 0.003241	time 0.5796 (0.6207)	model_time 0.5794 (0.6103)	loss 4.3962 (3.5754)	grad_norm 1.5790 (1.5226/0.6599)	mem 24308MB
[2025-01-18 17:32:37 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][180/312]	eta 0:01:21 lr 0.003240	time 0.5736 (0.6198)	model_time 0.5734 (0.6099)	loss 3.5921 (3.5587)	grad_norm 1.7347 (1.5253/0.6537)	mem 24308MB
[2025-01-18 17:32:44 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][190/312]	eta 0:01:15 lr 0.003240	time 0.5763 (0.6200)	model_time 0.5759 (0.6106)	loss 3.0397 (3.5511)	grad_norm 0.9223 (1.5173/0.6424)	mem 24308MB
[2025-01-18 17:32:49 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][200/312]	eta 0:01:09 lr 0.003239	time 0.5670 (0.6187)	model_time 0.5669 (0.6098)	loss 3.6556 (3.5589)	grad_norm 1.9642 (1.5082/0.6308)	mem 24308MB
[2025-01-18 17:32:55 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][210/312]	eta 0:01:02 lr 0.003239	time 0.5910 (0.6172)	model_time 0.5909 (0.6087)	loss 3.7825 (3.5558)	grad_norm 1.5934 (1.5228/0.6273)	mem 24308MB
[2025-01-18 17:33:01 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][220/312]	eta 0:00:56 lr 0.003238	time 0.6088 (0.6160)	model_time 0.6084 (0.6078)	loss 3.8343 (3.5666)	grad_norm 1.8836 (1.5226/0.6247)	mem 24308MB
[2025-01-18 17:33:07 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][230/312]	eta 0:00:50 lr 0.003238	time 0.5694 (0.6147)	model_time 0.5690 (0.6069)	loss 4.0844 (3.5601)	grad_norm 4.0098 (1.5296/0.6383)	mem 24308MB
[2025-01-18 17:33:13 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][240/312]	eta 0:00:44 lr 0.003237	time 0.5813 (0.6136)	model_time 0.5812 (0.6061)	loss 3.3432 (3.5507)	grad_norm 0.8474 (1.5344/0.6478)	mem 24308MB
[2025-01-18 17:33:19 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][250/312]	eta 0:00:38 lr 0.003237	time 0.5776 (0.6132)	model_time 0.5774 (0.6060)	loss 4.4358 (3.5527)	grad_norm 1.8328 (1.5327/0.6410)	mem 24308MB
[2025-01-18 17:33:25 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][260/312]	eta 0:00:31 lr 0.003236	time 0.5751 (0.6137)	model_time 0.5749 (0.6068)	loss 4.4358 (3.5663)	grad_norm 1.3479 (1.5320/0.6406)	mem 24308MB
[2025-01-18 17:33:32 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][270/312]	eta 0:00:25 lr 0.003236	time 0.5945 (0.6153)	model_time 0.5943 (0.6086)	loss 3.5050 (3.5670)	grad_norm 1.0332 (1.5421/0.6605)	mem 24308MB
[2025-01-18 17:33:38 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][280/312]	eta 0:00:19 lr 0.003235	time 0.8469 (0.6170)	model_time 0.8465 (0.6105)	loss 3.8188 (3.5763)	grad_norm 1.7708 (1.5587/0.6922)	mem 24308MB
[2025-01-18 17:33:45 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][290/312]	eta 0:00:13 lr 0.003235	time 0.6021 (0.6169)	model_time 0.6019 (0.6107)	loss 4.0191 (3.5809)	grad_norm 1.6152 (1.5484/0.6855)	mem 24308MB
[2025-01-18 17:33:51 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][300/312]	eta 0:00:07 lr 0.003234	time 0.5701 (0.6163)	model_time 0.5700 (0.6102)	loss 3.8738 (3.5791)	grad_norm 1.7532 (1.5462/0.6885)	mem 24308MB
[2025-01-18 17:33:57 internimage_s_1k_224] (main.py 510): INFO Train: [86/300][310/312]	eta 0:00:01 lr 0.003234	time 0.6384 (0.6157)	model_time 0.6383 (0.6098)	loss 3.5955 (3.5778)	grad_norm 1.0033 (1.5241/0.6725)	mem 24308MB
[2025-01-18 17:33:57 internimage_s_1k_224] (main.py 519): INFO EPOCH 86 training takes 0:03:12
[2025-01-18 17:33:57 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_86.pth saving......
[2025-01-18 17:33:59 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_86.pth saved !!!
[2025-01-18 17:34:06 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.313 (7.313)	Loss 0.9815 (0.9815)	Acc@1 80.273 (80.273)	Acc@5 95.239 (95.239)	Mem 24308MB
[2025-01-18 17:34:10 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.958)	Loss 1.3573 (1.1135)	Acc@1 71.021 (76.392)	Acc@5 90.771 (93.550)	Mem 24308MB
[2025-01-18 17:34:10 internimage_s_1k_224] (main.py 575): INFO [Epoch:86] * Acc@1 76.260 Acc@5 93.590
[2025-01-18 17:34:10 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.3%
[2025-01-18 17:34:10 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 76.52%
[2025-01-18 17:34:18 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.152 (8.152)	Loss 0.8976 (0.8976)	Acc@1 78.052 (78.052)	Acc@5 94.580 (94.580)	Mem 24308MB
[2025-01-18 17:34:22 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (1.115)	Loss 1.3709 (1.0823)	Acc@1 66.846 (73.970)	Acc@5 88.696 (92.219)	Mem 24308MB
[2025-01-18 17:34:22 internimage_s_1k_224] (main.py 575): INFO [Epoch:86] * Acc@1 73.964 Acc@5 92.308
[2025-01-18 17:34:22 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 74.0%
[2025-01-18 17:34:22 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 17:34:25 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 17:34:25 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 73.96%
[2025-01-18 17:34:27 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][0/312]	eta 0:10:16 lr 0.003234	time 1.9752 (1.9752)	model_time 0.6147 (0.6147)	loss 3.5605 (3.5605)	grad_norm 2.0830 (2.0830/0.0000)	mem 24308MB
[2025-01-18 17:34:33 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][10/312]	eta 0:03:39 lr 0.003233	time 0.5809 (0.7258)	model_time 0.5808 (0.6018)	loss 3.4803 (3.7751)	grad_norm 1.2911 (1.4742/0.3073)	mem 24308MB
[2025-01-18 17:34:39 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][20/312]	eta 0:03:13 lr 0.003233	time 0.5815 (0.6617)	model_time 0.5813 (0.5965)	loss 3.9636 (3.7419)	grad_norm 1.2820 (1.7169/0.5309)	mem 24308MB
[2025-01-18 17:34:45 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][30/312]	eta 0:02:59 lr 0.003232	time 0.5847 (0.6380)	model_time 0.5843 (0.5938)	loss 3.4104 (3.6488)	grad_norm 0.9842 (1.6598/0.5319)	mem 24308MB
[2025-01-18 17:34:50 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][40/312]	eta 0:02:50 lr 0.003231	time 0.5639 (0.6251)	model_time 0.5632 (0.5916)	loss 3.0009 (3.6060)	grad_norm 2.2528 (1.5885/0.5384)	mem 24308MB
[2025-01-18 17:34:56 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][50/312]	eta 0:02:41 lr 0.003231	time 0.5954 (0.6176)	model_time 0.5952 (0.5906)	loss 4.1980 (3.6186)	grad_norm 1.5546 (1.5592/0.4956)	mem 24308MB
[2025-01-18 17:35:02 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][60/312]	eta 0:02:35 lr 0.003230	time 0.5875 (0.6153)	model_time 0.5874 (0.5926)	loss 3.3047 (3.6255)	grad_norm 2.2481 (1.6060/0.4905)	mem 24308MB
[2025-01-18 17:35:09 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][70/312]	eta 0:02:29 lr 0.003230	time 0.6910 (0.6163)	model_time 0.6906 (0.5968)	loss 3.8669 (3.5837)	grad_norm 1.4261 (1.5765/0.4931)	mem 24308MB
[2025-01-18 17:35:15 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][80/312]	eta 0:02:23 lr 0.003229	time 0.5894 (0.6171)	model_time 0.5890 (0.6000)	loss 3.1850 (3.5504)	grad_norm 1.3987 (1.5338/0.4966)	mem 24308MB
[2025-01-18 17:35:21 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][90/312]	eta 0:02:17 lr 0.003229	time 0.6620 (0.6192)	model_time 0.6618 (0.6039)	loss 4.4936 (3.5229)	grad_norm 2.3757 (1.5107/0.5010)	mem 24308MB
[2025-01-18 17:35:27 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][100/312]	eta 0:02:10 lr 0.003228	time 0.5815 (0.6175)	model_time 0.5814 (0.6037)	loss 2.5240 (3.4960)	grad_norm 1.6914 (1.5413/0.5329)	mem 24308MB
[2025-01-18 17:35:33 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][110/312]	eta 0:02:04 lr 0.003228	time 0.5874 (0.6169)	model_time 0.5872 (0.6043)	loss 4.1921 (3.5217)	grad_norm 2.4037 (1.5796/0.5590)	mem 24308MB
[2025-01-18 17:35:39 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][120/312]	eta 0:01:58 lr 0.003227	time 0.5815 (0.6162)	model_time 0.5811 (0.6046)	loss 3.6014 (3.5385)	grad_norm 2.8512 (1.5680/0.5686)	mem 24308MB
[2025-01-18 17:35:45 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][130/312]	eta 0:01:51 lr 0.003227	time 0.5811 (0.6150)	model_time 0.5810 (0.6042)	loss 2.7594 (3.5444)	grad_norm 1.1110 (1.5377/0.5639)	mem 24308MB
[2025-01-18 17:35:51 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][140/312]	eta 0:01:45 lr 0.003226	time 0.5702 (0.6137)	model_time 0.5700 (0.6036)	loss 3.6948 (3.5350)	grad_norm 0.9789 (1.5204/0.5559)	mem 24308MB
[2025-01-18 17:35:57 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][150/312]	eta 0:01:39 lr 0.003226	time 0.6015 (0.6121)	model_time 0.6011 (0.6027)	loss 2.3544 (3.5327)	grad_norm 3.2674 (1.5350/0.5769)	mem 24308MB
[2025-01-18 17:36:03 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][160/312]	eta 0:01:32 lr 0.003225	time 0.5880 (0.6105)	model_time 0.5875 (0.6017)	loss 3.4957 (3.5251)	grad_norm 1.6659 (1.5611/0.6212)	mem 24308MB
[2025-01-18 17:36:09 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][170/312]	eta 0:01:26 lr 0.003225	time 0.5905 (0.6092)	model_time 0.5903 (0.6009)	loss 2.8447 (3.5214)	grad_norm 1.3020 (1.5664/0.6279)	mem 24308MB
[2025-01-18 17:36:15 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][180/312]	eta 0:01:20 lr 0.003224	time 0.5732 (0.6084)	model_time 0.5728 (0.6005)	loss 4.3070 (3.5418)	grad_norm 1.4622 (1.5467/0.6191)	mem 24308MB
[2025-01-18 17:36:21 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][190/312]	eta 0:01:14 lr 0.003224	time 0.5828 (0.6086)	model_time 0.5826 (0.6011)	loss 2.8679 (3.5377)	grad_norm 0.9741 (1.5397/0.6088)	mem 24308MB
[2025-01-18 17:36:28 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][200/312]	eta 0:01:08 lr 0.003223	time 0.5854 (0.6104)	model_time 0.5852 (0.6033)	loss 4.2880 (3.5314)	grad_norm 0.8681 (1.5411/0.6095)	mem 24308MB
[2025-01-18 17:36:34 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][210/312]	eta 0:01:02 lr 0.003222	time 0.6728 (0.6107)	model_time 0.6727 (0.6039)	loss 2.5385 (3.5259)	grad_norm 2.0756 (1.5638/0.6289)	mem 24308MB
[2025-01-18 17:36:40 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][220/312]	eta 0:00:56 lr 0.003222	time 0.5831 (0.6117)	model_time 0.5829 (0.6052)	loss 3.3899 (3.5340)	grad_norm 0.9056 (1.5479/0.6221)	mem 24308MB
[2025-01-18 17:36:46 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][230/312]	eta 0:00:50 lr 0.003221	time 0.5981 (0.6112)	model_time 0.5980 (0.6049)	loss 3.1564 (3.5360)	grad_norm 2.0962 (1.5363/0.6155)	mem 24308MB
[2025-01-18 17:36:52 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][240/312]	eta 0:00:43 lr 0.003221	time 0.6541 (0.6111)	model_time 0.6539 (0.6051)	loss 3.8061 (3.5351)	grad_norm 0.8410 (1.5489/0.6338)	mem 24308MB
[2025-01-18 17:36:58 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][250/312]	eta 0:00:37 lr 0.003220	time 0.5735 (0.6104)	model_time 0.5730 (0.6047)	loss 3.3361 (3.5443)	grad_norm 1.1684 (1.5588/0.6303)	mem 24308MB
[2025-01-18 17:37:04 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][260/312]	eta 0:00:31 lr 0.003220	time 0.5888 (0.6100)	model_time 0.5886 (0.6044)	loss 3.8802 (3.5431)	grad_norm 1.8088 (1.5631/0.6297)	mem 24308MB
[2025-01-18 17:37:10 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][270/312]	eta 0:00:25 lr 0.003219	time 0.5753 (0.6094)	model_time 0.5748 (0.6040)	loss 3.7588 (3.5402)	grad_norm 1.6508 (1.5760/0.6374)	mem 24308MB
[2025-01-18 17:37:16 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][280/312]	eta 0:00:19 lr 0.003219	time 0.5832 (0.6085)	model_time 0.5828 (0.6033)	loss 4.4132 (3.5404)	grad_norm 1.8996 (1.5745/0.6352)	mem 24308MB
[2025-01-18 17:37:22 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][290/312]	eta 0:00:13 lr 0.003218	time 0.5764 (0.6081)	model_time 0.5763 (0.6031)	loss 3.4922 (3.5342)	grad_norm 1.3001 (1.5596/0.6300)	mem 24308MB
[2025-01-18 17:37:28 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][300/312]	eta 0:00:07 lr 0.003218	time 0.5631 (0.6072)	model_time 0.5630 (0.6024)	loss 3.7523 (3.5379)	grad_norm 1.0126 (1.5476/0.6244)	mem 24308MB
[2025-01-18 17:37:34 internimage_s_1k_224] (main.py 510): INFO Train: [87/300][310/312]	eta 0:00:01 lr 0.003217	time 0.6472 (0.6071)	model_time 0.6471 (0.6024)	loss 2.9718 (3.5364)	grad_norm 1.6051 (1.5412/0.6293)	mem 24308MB
[2025-01-18 17:37:34 internimage_s_1k_224] (main.py 519): INFO EPOCH 87 training takes 0:03:09
[2025-01-18 17:37:34 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_87.pth saving......
[2025-01-18 17:37:36 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_87.pth saved !!!
[2025-01-18 17:37:43 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.882 (6.882)	Loss 0.9965 (0.9965)	Acc@1 80.518 (80.518)	Acc@5 95.508 (95.508)	Mem 24308MB
[2025-01-18 17:37:46 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.924)	Loss 1.3691 (1.1551)	Acc@1 70.679 (76.094)	Acc@5 90.527 (93.393)	Mem 24308MB
[2025-01-18 17:37:46 internimage_s_1k_224] (main.py 575): INFO [Epoch:87] * Acc@1 76.110 Acc@5 93.478
[2025-01-18 17:37:46 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.1%
[2025-01-18 17:37:46 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 76.52%
[2025-01-18 17:37:55 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.109 (8.109)	Loss 0.8888 (0.8888)	Acc@1 78.223 (78.223)	Acc@5 94.751 (94.751)	Mem 24308MB
[2025-01-18 17:37:59 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.106)	Loss 1.3580 (1.0726)	Acc@1 66.943 (74.170)	Acc@5 88.794 (92.296)	Mem 24308MB
[2025-01-18 17:37:59 internimage_s_1k_224] (main.py 575): INFO [Epoch:87] * Acc@1 74.152 Acc@5 92.382
[2025-01-18 17:37:59 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 74.2%
[2025-01-18 17:37:59 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 17:38:01 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 17:38:01 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 74.15%
[2025-01-18 17:38:03 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][0/312]	eta 0:11:32 lr 0.003217	time 2.2194 (2.2194)	model_time 0.6013 (0.6013)	loss 2.5903 (2.5903)	grad_norm 1.2631 (1.2631/0.0000)	mem 24308MB
[2025-01-18 17:38:10 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][10/312]	eta 0:03:58 lr 0.003217	time 0.8330 (0.7893)	model_time 0.8328 (0.6419)	loss 3.2316 (3.2020)	grad_norm 1.1982 (1.4486/0.3872)	mem 24308MB
[2025-01-18 17:38:16 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][20/312]	eta 0:03:27 lr 0.003216	time 0.6735 (0.7118)	model_time 0.6730 (0.6344)	loss 2.5052 (3.2883)	grad_norm 2.8773 (1.4225/0.5019)	mem 24308MB
[2025-01-18 17:38:22 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][30/312]	eta 0:03:12 lr 0.003216	time 0.5846 (0.6821)	model_time 0.5844 (0.6296)	loss 3.1817 (3.4118)	grad_norm 1.2700 (1.4823/0.5397)	mem 24308MB
[2025-01-18 17:38:29 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][40/312]	eta 0:03:01 lr 0.003215	time 0.5790 (0.6666)	model_time 0.5788 (0.6268)	loss 4.1874 (3.4584)	grad_norm 2.0047 (1.4933/0.5048)	mem 24308MB
[2025-01-18 17:38:35 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][50/312]	eta 0:02:51 lr 0.003214	time 0.5819 (0.6534)	model_time 0.5817 (0.6214)	loss 3.6573 (3.4613)	grad_norm 1.3145 (1.5165/0.5274)	mem 24308MB
[2025-01-18 17:38:41 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][60/312]	eta 0:02:42 lr 0.003214	time 0.5917 (0.6456)	model_time 0.5916 (0.6188)	loss 3.0381 (3.4429)	grad_norm 0.9435 (1.5177/0.5492)	mem 24308MB
[2025-01-18 17:38:47 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][70/312]	eta 0:02:34 lr 0.003213	time 0.5812 (0.6380)	model_time 0.5807 (0.6149)	loss 3.3276 (3.4680)	grad_norm 1.4144 (1.5581/0.5767)	mem 24308MB
[2025-01-18 17:38:52 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][80/312]	eta 0:02:26 lr 0.003213	time 0.5759 (0.6323)	model_time 0.5758 (0.6120)	loss 2.7300 (3.4877)	grad_norm 1.0428 (1.5338/0.5768)	mem 24308MB
[2025-01-18 17:38:58 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][90/312]	eta 0:02:19 lr 0.003212	time 0.5896 (0.6271)	model_time 0.5895 (0.6090)	loss 3.9419 (3.5088)	grad_norm 1.4316 (1.5197/0.5564)	mem 24308MB
[2025-01-18 17:39:04 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][100/312]	eta 0:02:12 lr 0.003212	time 0.5718 (0.6232)	model_time 0.5714 (0.6069)	loss 4.4823 (3.5290)	grad_norm 0.9858 (1.5002/0.5459)	mem 24308MB
[2025-01-18 17:39:10 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][110/312]	eta 0:02:05 lr 0.003211	time 0.7905 (0.6220)	model_time 0.7900 (0.6071)	loss 2.3697 (3.5106)	grad_norm 0.8577 (1.5068/0.5620)	mem 24308MB
[2025-01-18 17:39:16 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][120/312]	eta 0:01:59 lr 0.003211	time 0.5803 (0.6198)	model_time 0.5801 (0.6061)	loss 3.6150 (3.4960)	grad_norm 1.9858 (1.5027/0.5483)	mem 24308MB
[2025-01-18 17:39:22 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][130/312]	eta 0:01:52 lr 0.003210	time 0.6610 (0.6201)	model_time 0.6608 (0.6074)	loss 4.0504 (3.5051)	grad_norm 3.0669 (1.5418/0.5694)	mem 24308MB
[2025-01-18 17:39:29 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][140/312]	eta 0:01:46 lr 0.003210	time 0.6697 (0.6209)	model_time 0.6695 (0.6090)	loss 3.7673 (3.5030)	grad_norm 1.4700 (1.5263/0.5594)	mem 24308MB
[2025-01-18 17:39:35 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][150/312]	eta 0:01:40 lr 0.003209	time 0.6831 (0.6212)	model_time 0.6827 (0.6101)	loss 3.9742 (3.5207)	grad_norm 0.9686 (1.5085/0.5566)	mem 24308MB
[2025-01-18 17:39:41 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][160/312]	eta 0:01:34 lr 0.003209	time 0.6789 (0.6213)	model_time 0.6786 (0.6109)	loss 3.8979 (3.5189)	grad_norm 0.7269 (1.4936/0.5601)	mem 24308MB
[2025-01-18 17:39:47 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][170/312]	eta 0:01:28 lr 0.003208	time 0.6013 (0.6198)	model_time 0.6011 (0.6099)	loss 3.6743 (3.5143)	grad_norm 1.3196 (1.5196/0.5939)	mem 24308MB
[2025-01-18 17:39:53 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][180/312]	eta 0:01:21 lr 0.003208	time 0.5799 (0.6183)	model_time 0.5797 (0.6090)	loss 2.9747 (3.5268)	grad_norm 2.3312 (1.5255/0.5853)	mem 24308MB
[2025-01-18 17:39:59 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][190/312]	eta 0:01:15 lr 0.003207	time 0.6287 (0.6174)	model_time 0.6283 (0.6086)	loss 3.3420 (3.5173)	grad_norm 1.8217 (1.5241/0.5816)	mem 24308MB
[2025-01-18 17:40:05 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][200/312]	eta 0:01:08 lr 0.003206	time 0.5862 (0.6157)	model_time 0.5857 (0.6073)	loss 4.2533 (3.5273)	grad_norm 1.4509 (1.5174/0.5725)	mem 24308MB
[2025-01-18 17:40:11 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][210/312]	eta 0:01:02 lr 0.003206	time 0.5716 (0.6144)	model_time 0.5715 (0.6064)	loss 4.0988 (3.5360)	grad_norm 1.8493 (1.5206/0.5732)	mem 24308MB
[2025-01-18 17:40:17 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][220/312]	eta 0:00:56 lr 0.003205	time 0.6002 (0.6136)	model_time 0.6001 (0.6060)	loss 2.7231 (3.5198)	grad_norm 1.7396 (1.5318/0.5820)	mem 24308MB
[2025-01-18 17:40:23 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][230/312]	eta 0:00:50 lr 0.003205	time 0.5940 (0.6128)	model_time 0.5935 (0.6055)	loss 3.8458 (3.5185)	grad_norm 1.0581 (1.5351/0.5943)	mem 24308MB
[2025-01-18 17:40:29 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][240/312]	eta 0:00:44 lr 0.003204	time 0.6382 (0.6130)	model_time 0.6380 (0.6059)	loss 3.6685 (3.5243)	grad_norm 0.8862 (1.5290/0.5867)	mem 24308MB
[2025-01-18 17:40:35 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][250/312]	eta 0:00:38 lr 0.003204	time 0.5856 (0.6129)	model_time 0.5854 (0.6061)	loss 3.1138 (3.5280)	grad_norm 2.0280 (1.5334/0.5819)	mem 24308MB
[2025-01-18 17:40:41 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][260/312]	eta 0:00:31 lr 0.003203	time 0.5889 (0.6138)	model_time 0.5888 (0.6072)	loss 3.6806 (3.5226)	grad_norm 1.6003 (1.5277/0.5749)	mem 24308MB
[2025-01-18 17:40:48 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][270/312]	eta 0:00:25 lr 0.003203	time 0.5947 (0.6144)	model_time 0.5946 (0.6081)	loss 3.6066 (3.5274)	grad_norm 0.9164 (1.5246/0.5722)	mem 24308MB
[2025-01-18 17:40:54 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][280/312]	eta 0:00:19 lr 0.003202	time 0.7142 (0.6145)	model_time 0.7138 (0.6084)	loss 3.0163 (3.5231)	grad_norm 2.4967 (1.5459/0.5872)	mem 24308MB
[2025-01-18 17:41:00 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][290/312]	eta 0:00:13 lr 0.003202	time 0.5849 (0.6141)	model_time 0.5848 (0.6082)	loss 3.3488 (3.5223)	grad_norm 1.8631 (1.5422/0.5846)	mem 24308MB
[2025-01-18 17:41:06 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][300/312]	eta 0:00:07 lr 0.003201	time 0.5665 (0.6133)	model_time 0.5664 (0.6075)	loss 3.4941 (3.5178)	grad_norm 0.9386 (1.5344/0.5823)	mem 24308MB
[2025-01-18 17:41:12 internimage_s_1k_224] (main.py 510): INFO Train: [88/300][310/312]	eta 0:00:01 lr 0.003201	time 0.5939 (0.6122)	model_time 0.5939 (0.6067)	loss 2.9011 (3.5139)	grad_norm 1.0174 (1.5262/0.5813)	mem 24308MB
[2025-01-18 17:41:12 internimage_s_1k_224] (main.py 519): INFO EPOCH 88 training takes 0:03:10
[2025-01-18 17:41:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_88.pth saving......
[2025-01-18 17:41:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_88.pth saved !!!
[2025-01-18 17:41:21 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.647 (6.647)	Loss 0.9254 (0.9254)	Acc@1 80.615 (80.615)	Acc@5 95.874 (95.874)	Mem 24308MB
[2025-01-18 17:41:24 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.913)	Loss 1.3061 (1.0945)	Acc@1 71.118 (76.551)	Acc@5 90.747 (93.564)	Mem 24308MB
[2025-01-18 17:41:24 internimage_s_1k_224] (main.py 575): INFO [Epoch:88] * Acc@1 76.558 Acc@5 93.614
[2025-01-18 17:41:24 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.6%
[2025-01-18 17:41:24 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 17:41:26 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 17:41:26 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 76.56%
[2025-01-18 17:41:33 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.960 (6.960)	Loss 0.8807 (0.8807)	Acc@1 78.394 (78.394)	Acc@5 94.946 (94.946)	Mem 24308MB
[2025-01-18 17:41:37 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.946)	Loss 1.3456 (1.0634)	Acc@1 67.212 (74.359)	Acc@5 88.989 (92.407)	Mem 24308MB
[2025-01-18 17:41:37 internimage_s_1k_224] (main.py 575): INFO [Epoch:88] * Acc@1 74.332 Acc@5 92.492
[2025-01-18 17:41:37 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 74.3%
[2025-01-18 17:41:37 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 17:41:39 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 17:41:39 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 74.33%
[2025-01-18 17:41:41 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][0/312]	eta 0:10:47 lr 0.003201	time 2.0758 (2.0758)	model_time 0.5931 (0.5931)	loss 4.1020 (4.1020)	grad_norm 1.1135 (1.1135/0.0000)	mem 24308MB
[2025-01-18 17:41:47 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][10/312]	eta 0:03:39 lr 0.003200	time 0.5770 (0.7265)	model_time 0.5769 (0.5915)	loss 3.2007 (3.6633)	grad_norm 1.4565 (1.6108/0.5461)	mem 24308MB
[2025-01-18 17:41:53 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][20/312]	eta 0:03:13 lr 0.003199	time 0.5933 (0.6621)	model_time 0.5929 (0.5912)	loss 3.7869 (3.5730)	grad_norm 1.4320 (1.5448/0.4778)	mem 24308MB
[2025-01-18 17:41:59 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][30/312]	eta 0:02:59 lr 0.003199	time 0.6202 (0.6379)	model_time 0.6201 (0.5897)	loss 4.3611 (3.5715)	grad_norm 0.9290 (1.5222/0.4723)	mem 24308MB
[2025-01-18 17:42:05 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][40/312]	eta 0:02:50 lr 0.003198	time 0.5782 (0.6260)	model_time 0.5780 (0.5895)	loss 4.2696 (3.6014)	grad_norm 1.2955 (1.6036/0.5806)	mem 24308MB
[2025-01-18 17:42:11 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][50/312]	eta 0:02:44 lr 0.003198	time 0.5787 (0.6279)	model_time 0.5783 (0.5984)	loss 4.3404 (3.5815)	grad_norm 1.6395 (1.6221/0.5781)	mem 24308MB
[2025-01-18 17:42:17 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][60/312]	eta 0:02:37 lr 0.003197	time 0.5884 (0.6264)	model_time 0.5882 (0.6018)	loss 4.0366 (3.6134)	grad_norm 0.9204 (1.5791/0.5569)	mem 24308MB
[2025-01-18 17:42:23 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][70/312]	eta 0:02:31 lr 0.003197	time 0.6517 (0.6259)	model_time 0.6515 (0.6047)	loss 3.9876 (3.6018)	grad_norm 1.3334 (1.5470/0.5499)	mem 24308MB
[2025-01-18 17:42:30 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][80/312]	eta 0:02:25 lr 0.003196	time 0.6043 (0.6259)	model_time 0.6041 (0.6073)	loss 3.8942 (3.6165)	grad_norm 1.1660 (1.5216/0.5339)	mem 24308MB
[2025-01-18 17:42:36 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][90/312]	eta 0:02:18 lr 0.003196	time 0.5660 (0.6236)	model_time 0.5658 (0.6069)	loss 4.0647 (3.6317)	grad_norm 1.3680 (1.4836/0.5241)	mem 24308MB
[2025-01-18 17:42:42 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][100/312]	eta 0:02:11 lr 0.003195	time 0.5803 (0.6223)	model_time 0.5798 (0.6072)	loss 3.2107 (3.6393)	grad_norm 1.7427 (1.4996/0.5171)	mem 24308MB
[2025-01-18 17:42:48 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][110/312]	eta 0:02:05 lr 0.003195	time 0.5883 (0.6207)	model_time 0.5881 (0.6069)	loss 3.7383 (3.6559)	grad_norm 1.4071 (1.5562/0.5797)	mem 24308MB
[2025-01-18 17:42:54 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][120/312]	eta 0:01:58 lr 0.003194	time 0.5846 (0.6180)	model_time 0.5836 (0.6053)	loss 3.9621 (3.6462)	grad_norm 2.3427 (1.5832/0.5765)	mem 24308MB
[2025-01-18 17:43:00 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][130/312]	eta 0:01:52 lr 0.003194	time 0.5842 (0.6157)	model_time 0.5840 (0.6040)	loss 2.8361 (3.6270)	grad_norm 1.0895 (1.5517/0.5696)	mem 24308MB
[2025-01-18 17:43:06 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][140/312]	eta 0:01:45 lr 0.003193	time 0.5716 (0.6143)	model_time 0.5714 (0.6033)	loss 3.3983 (3.6036)	grad_norm 0.8750 (1.5374/0.5591)	mem 24308MB
[2025-01-18 17:43:11 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][150/312]	eta 0:01:39 lr 0.003193	time 0.5970 (0.6127)	model_time 0.5969 (0.6024)	loss 3.8566 (3.6027)	grad_norm 1.8315 (1.5577/0.5667)	mem 24308MB
[2025-01-18 17:43:17 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][160/312]	eta 0:01:32 lr 0.003192	time 0.5691 (0.6111)	model_time 0.5689 (0.6015)	loss 3.2212 (3.6007)	grad_norm 1.9796 (1.5672/0.5772)	mem 24308MB
[2025-01-18 17:43:24 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][170/312]	eta 0:01:26 lr 0.003191	time 0.5762 (0.6116)	model_time 0.5761 (0.6025)	loss 2.6054 (3.5873)	grad_norm 0.7871 (1.5526/0.5700)	mem 24308MB
[2025-01-18 17:43:30 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][180/312]	eta 0:01:20 lr 0.003191	time 0.6958 (0.6125)	model_time 0.6956 (0.6039)	loss 4.4472 (3.5944)	grad_norm 1.7547 (1.5355/0.5640)	mem 24308MB
[2025-01-18 17:43:36 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][190/312]	eta 0:01:14 lr 0.003190	time 0.6524 (0.6133)	model_time 0.6522 (0.6051)	loss 3.2946 (3.5891)	grad_norm 1.1369 (1.5191/0.5580)	mem 24308MB
[2025-01-18 17:43:42 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][200/312]	eta 0:01:08 lr 0.003190	time 0.5758 (0.6144)	model_time 0.5754 (0.6066)	loss 3.7969 (3.5991)	grad_norm 1.2531 (1.5196/0.5554)	mem 24308MB
[2025-01-18 17:43:49 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][210/312]	eta 0:01:02 lr 0.003189	time 0.5953 (0.6143)	model_time 0.5948 (0.6068)	loss 3.2894 (3.5999)	grad_norm 1.4489 (1.5408/0.5725)	mem 24308MB
[2025-01-18 17:43:55 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][220/312]	eta 0:00:56 lr 0.003189	time 0.5803 (0.6138)	model_time 0.5801 (0.6067)	loss 3.0274 (3.5908)	grad_norm 1.1563 (1.5442/0.5723)	mem 24308MB
[2025-01-18 17:44:01 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][230/312]	eta 0:00:50 lr 0.003188	time 0.5811 (0.6137)	model_time 0.5809 (0.6069)	loss 4.2418 (3.5869)	grad_norm 0.8627 (1.5443/0.5688)	mem 24308MB
[2025-01-18 17:44:07 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][240/312]	eta 0:00:44 lr 0.003188	time 0.5863 (0.6125)	model_time 0.5859 (0.6060)	loss 4.6548 (3.5916)	grad_norm 2.3782 (1.5333/0.5657)	mem 24308MB
[2025-01-18 17:44:12 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][250/312]	eta 0:00:37 lr 0.003187	time 0.5742 (0.6114)	model_time 0.5741 (0.6051)	loss 3.1230 (3.5868)	grad_norm 1.0103 (1.5325/0.5679)	mem 24308MB
[2025-01-18 17:44:18 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][260/312]	eta 0:00:31 lr 0.003187	time 0.5799 (0.6106)	model_time 0.5793 (0.6045)	loss 3.0802 (3.5740)	grad_norm 1.6937 (1.5277/0.5637)	mem 24308MB
[2025-01-18 17:44:24 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][270/312]	eta 0:00:25 lr 0.003186	time 0.5770 (0.6098)	model_time 0.5768 (0.6039)	loss 3.0944 (3.5770)	grad_norm 3.7825 (1.5337/0.5812)	mem 24308MB
[2025-01-18 17:44:30 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][280/312]	eta 0:00:19 lr 0.003186	time 0.5801 (0.6089)	model_time 0.5796 (0.6033)	loss 3.7533 (3.5781)	grad_norm 1.4835 (1.5536/0.6355)	mem 24308MB
[2025-01-18 17:44:36 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][290/312]	eta 0:00:13 lr 0.003185	time 0.5749 (0.6095)	model_time 0.5747 (0.6040)	loss 4.4831 (3.5777)	grad_norm 0.8261 (1.5331/0.6350)	mem 24308MB
[2025-01-18 17:44:42 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][300/312]	eta 0:00:07 lr 0.003184	time 0.6465 (0.6096)	model_time 0.6464 (0.6043)	loss 4.0662 (3.5699)	grad_norm 1.2337 (1.5476/0.6534)	mem 24308MB
[2025-01-18 17:44:49 internimage_s_1k_224] (main.py 510): INFO Train: [89/300][310/312]	eta 0:00:01 lr 0.003184	time 0.5676 (0.6101)	model_time 0.5675 (0.6050)	loss 4.3266 (3.5767)	grad_norm 1.8195 (1.5372/0.6484)	mem 24308MB
[2025-01-18 17:44:49 internimage_s_1k_224] (main.py 519): INFO EPOCH 89 training takes 0:03:10
[2025-01-18 17:44:49 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_89.pth saving......
[2025-01-18 17:44:51 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_89.pth saved !!!
[2025-01-18 17:44:58 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.994 (6.994)	Loss 0.8696 (0.8696)	Acc@1 80.859 (80.859)	Acc@5 96.094 (96.094)	Mem 24308MB
[2025-01-18 17:45:02 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.939)	Loss 1.2976 (1.0644)	Acc@1 70.532 (76.463)	Acc@5 90.747 (93.495)	Mem 24308MB
[2025-01-18 17:45:02 internimage_s_1k_224] (main.py 575): INFO [Epoch:89] * Acc@1 76.446 Acc@5 93.564
[2025-01-18 17:45:02 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.4%
[2025-01-18 17:45:02 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 76.56%
[2025-01-18 17:45:10 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.087 (8.087)	Loss 0.8729 (0.8729)	Acc@1 78.589 (78.589)	Acc@5 94.971 (94.971)	Mem 24308MB
[2025-01-18 17:45:14 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (1.100)	Loss 1.3336 (1.0547)	Acc@1 67.456 (74.529)	Acc@5 89.087 (92.487)	Mem 24308MB
[2025-01-18 17:45:14 internimage_s_1k_224] (main.py 575): INFO [Epoch:89] * Acc@1 74.498 Acc@5 92.568
[2025-01-18 17:45:14 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 74.5%
[2025-01-18 17:45:14 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 17:45:16 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 17:45:16 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 74.50%
[2025-01-18 17:45:18 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][0/312]	eta 0:10:28 lr 0.003184	time 2.0150 (2.0150)	model_time 0.6085 (0.6085)	loss 2.7387 (2.7387)	grad_norm 2.6752 (2.6752/0.0000)	mem 24308MB
[2025-01-18 17:45:25 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][10/312]	eta 0:03:50 lr 0.003183	time 0.5764 (0.7630)	model_time 0.5763 (0.6348)	loss 4.1983 (3.7880)	grad_norm 2.6509 (1.7162/0.7025)	mem 24308MB
[2025-01-18 17:45:31 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][20/312]	eta 0:03:20 lr 0.003183	time 0.5987 (0.6867)	model_time 0.5982 (0.6194)	loss 3.5612 (3.5121)	grad_norm 1.1619 (1.6077/0.6561)	mem 24308MB
[2025-01-18 17:45:37 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][30/312]	eta 0:03:07 lr 0.003182	time 0.5791 (0.6651)	model_time 0.5789 (0.6194)	loss 3.6293 (3.5309)	grad_norm 1.2555 (1.5900/0.5932)	mem 24308MB
[2025-01-18 17:45:43 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][40/312]	eta 0:02:56 lr 0.003182	time 0.5961 (0.6506)	model_time 0.5956 (0.6159)	loss 2.9179 (3.5223)	grad_norm 1.4888 (1.6730/0.7467)	mem 24308MB
[2025-01-18 17:45:49 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][50/312]	eta 0:02:47 lr 0.003181	time 0.5793 (0.6380)	model_time 0.5790 (0.6100)	loss 3.6962 (3.5141)	grad_norm 1.8837 (1.5697/0.7118)	mem 24308MB
[2025-01-18 17:45:55 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][60/312]	eta 0:02:38 lr 0.003181	time 0.6092 (0.6301)	model_time 0.6090 (0.6066)	loss 4.1843 (3.4773)	grad_norm 2.6764 (1.6753/0.7486)	mem 24308MB
[2025-01-18 17:46:01 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][70/312]	eta 0:02:31 lr 0.003180	time 0.5938 (0.6242)	model_time 0.5936 (0.6040)	loss 3.7792 (3.5335)	grad_norm 1.3438 (1.5963/0.7291)	mem 24308MB
[2025-01-18 17:46:06 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][80/312]	eta 0:02:23 lr 0.003180	time 0.5793 (0.6194)	model_time 0.5788 (0.6016)	loss 4.1138 (3.5318)	grad_norm 1.9868 (1.6000/0.7180)	mem 24308MB
[2025-01-18 17:46:12 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][90/312]	eta 0:02:16 lr 0.003179	time 0.5736 (0.6155)	model_time 0.5732 (0.5996)	loss 4.2604 (3.5384)	grad_norm 1.3509 (1.5996/0.6922)	mem 24308MB
[2025-01-18 17:46:18 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][100/312]	eta 0:02:10 lr 0.003178	time 0.6805 (0.6156)	model_time 0.6803 (0.6013)	loss 3.5874 (3.5485)	grad_norm 1.6004 (1.5726/0.6725)	mem 24308MB
[2025-01-18 17:46:25 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][110/312]	eta 0:02:04 lr 0.003178	time 0.5993 (0.6151)	model_time 0.5992 (0.6020)	loss 3.3690 (3.5400)	grad_norm 1.0116 (1.5470/0.6799)	mem 24308MB
[2025-01-18 17:46:31 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][120/312]	eta 0:01:58 lr 0.003177	time 0.5676 (0.6150)	model_time 0.5675 (0.6030)	loss 3.8447 (3.5362)	grad_norm 0.7986 (1.5588/0.6680)	mem 24308MB
[2025-01-18 17:46:37 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][130/312]	eta 0:01:52 lr 0.003177	time 0.5779 (0.6173)	model_time 0.5778 (0.6062)	loss 3.4850 (3.5395)	grad_norm 0.9250 (1.5382/0.6597)	mem 24308MB
[2025-01-18 17:46:43 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][140/312]	eta 0:01:46 lr 0.003176	time 0.5785 (0.6168)	model_time 0.5784 (0.6064)	loss 3.3127 (3.5231)	grad_norm 1.1137 (1.5339/0.6546)	mem 24308MB
[2025-01-18 17:46:49 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][150/312]	eta 0:01:39 lr 0.003176	time 0.5953 (0.6161)	model_time 0.5949 (0.6064)	loss 3.7992 (3.5383)	grad_norm 1.3888 (1.5528/0.6674)	mem 24308MB
[2025-01-18 17:46:55 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][160/312]	eta 0:01:33 lr 0.003175	time 0.5708 (0.6147)	model_time 0.5703 (0.6056)	loss 2.2596 (3.5311)	grad_norm 1.2328 (1.5485/0.6563)	mem 24308MB
[2025-01-18 17:47:01 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][170/312]	eta 0:01:27 lr 0.003175	time 0.5697 (0.6138)	model_time 0.5695 (0.6052)	loss 3.5573 (3.5283)	grad_norm 0.8822 (1.5391/0.6475)	mem 24308MB
[2025-01-18 17:47:07 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][180/312]	eta 0:01:20 lr 0.003174	time 0.6083 (0.6126)	model_time 0.6079 (0.6045)	loss 4.1933 (3.5421)	grad_norm 1.9220 (1.5565/0.6608)	mem 24308MB
[2025-01-18 17:47:13 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][190/312]	eta 0:01:14 lr 0.003174	time 0.5735 (0.6112)	model_time 0.5731 (0.6035)	loss 3.6029 (3.5478)	grad_norm 1.2108 (1.5341/0.6545)	mem 24308MB
[2025-01-18 17:47:19 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][200/312]	eta 0:01:08 lr 0.003173	time 0.5869 (0.6101)	model_time 0.5867 (0.6027)	loss 3.5593 (3.5545)	grad_norm 2.4542 (1.5582/0.6530)	mem 24308MB
[2025-01-18 17:47:25 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][210/312]	eta 0:01:02 lr 0.003172	time 0.5809 (0.6090)	model_time 0.5808 (0.6019)	loss 4.2449 (3.5451)	grad_norm 1.6311 (1.5481/0.6472)	mem 24308MB
[2025-01-18 17:47:31 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][220/312]	eta 0:00:56 lr 0.003172	time 0.6618 (0.6090)	model_time 0.6614 (0.6023)	loss 3.8568 (3.5383)	grad_norm 1.4105 (1.5672/0.6558)	mem 24308MB
[2025-01-18 17:47:37 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][230/312]	eta 0:00:50 lr 0.003171	time 0.5675 (0.6098)	model_time 0.5671 (0.6033)	loss 4.0013 (3.5435)	grad_norm 0.9609 (1.5708/0.6527)	mem 24308MB
[2025-01-18 17:47:44 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][240/312]	eta 0:00:43 lr 0.003171	time 0.5916 (0.6109)	model_time 0.5915 (0.6046)	loss 3.9405 (3.5402)	grad_norm 1.3576 (1.5642/0.6438)	mem 24308MB
[2025-01-18 17:47:50 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][250/312]	eta 0:00:37 lr 0.003170	time 0.5751 (0.6125)	model_time 0.5750 (0.6065)	loss 2.7911 (3.5413)	grad_norm 0.8981 (1.5503/0.6376)	mem 24308MB
[2025-01-18 17:47:56 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][260/312]	eta 0:00:31 lr 0.003170	time 0.5872 (0.6129)	model_time 0.5868 (0.6071)	loss 3.2872 (3.5386)	grad_norm 1.4595 (1.5444/0.6287)	mem 24308MB
[2025-01-18 17:48:02 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][270/312]	eta 0:00:25 lr 0.003169	time 0.6836 (0.6122)	model_time 0.6834 (0.6066)	loss 3.2421 (3.5244)	grad_norm 1.2500 (1.5307/0.6218)	mem 24308MB
[2025-01-18 17:48:08 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][280/312]	eta 0:00:19 lr 0.003169	time 0.5932 (0.6116)	model_time 0.5928 (0.6062)	loss 2.6383 (3.5297)	grad_norm 2.0147 (1.5265/0.6158)	mem 24308MB
[2025-01-18 17:48:14 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][290/312]	eta 0:00:13 lr 0.003168	time 0.5881 (0.6110)	model_time 0.5879 (0.6058)	loss 4.0455 (3.5352)	grad_norm 1.1896 (1.5289/0.6124)	mem 24308MB
[2025-01-18 17:48:20 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][300/312]	eta 0:00:07 lr 0.003168	time 0.5701 (0.6100)	model_time 0.5700 (0.6049)	loss 3.3324 (3.5344)	grad_norm 0.8475 (1.5110/0.6074)	mem 24308MB
[2025-01-18 17:48:26 internimage_s_1k_224] (main.py 510): INFO Train: [90/300][310/312]	eta 0:00:01 lr 0.003167	time 0.5732 (0.6087)	model_time 0.5731 (0.6038)	loss 3.0159 (3.5312)	grad_norm 0.9845 (1.4977/0.5977)	mem 24308MB
[2025-01-18 17:48:26 internimage_s_1k_224] (main.py 519): INFO EPOCH 90 training takes 0:03:09
[2025-01-18 17:48:26 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_90.pth saving......
[2025-01-18 17:48:28 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_90.pth saved !!!
[2025-01-18 17:48:35 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.708 (6.708)	Loss 0.8921 (0.8921)	Acc@1 80.396 (80.396)	Acc@5 95.947 (95.947)	Mem 24308MB
[2025-01-18 17:48:38 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.136 (0.908)	Loss 1.2513 (1.0610)	Acc@1 72.607 (76.676)	Acc@5 91.309 (93.777)	Mem 24308MB
[2025-01-18 17:48:38 internimage_s_1k_224] (main.py 575): INFO [Epoch:90] * Acc@1 76.563 Acc@5 93.794
[2025-01-18 17:48:38 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.6%
[2025-01-18 17:48:38 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 17:48:40 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 17:48:40 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 76.56%
[2025-01-18 17:48:47 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.658 (6.658)	Loss 0.8654 (0.8654)	Acc@1 78.687 (78.687)	Acc@5 95.093 (95.093)	Mem 24308MB
[2025-01-18 17:48:50 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.909)	Loss 1.3222 (1.0463)	Acc@1 67.651 (74.687)	Acc@5 89.087 (92.605)	Mem 24308MB
[2025-01-18 17:48:51 internimage_s_1k_224] (main.py 575): INFO [Epoch:90] * Acc@1 74.654 Acc@5 92.680
[2025-01-18 17:48:51 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 74.7%
[2025-01-18 17:48:51 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 17:48:53 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 17:48:53 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 74.65%
[2025-01-18 17:48:55 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][0/312]	eta 0:10:29 lr 0.003167	time 2.0182 (2.0182)	model_time 0.5918 (0.5918)	loss 3.2207 (3.2207)	grad_norm 1.4781 (1.4781/0.0000)	mem 24308MB
[2025-01-18 17:49:01 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][10/312]	eta 0:03:36 lr 0.003166	time 0.5728 (0.7159)	model_time 0.5726 (0.5859)	loss 4.4356 (3.5162)	grad_norm 1.3849 (1.8103/0.5679)	mem 24308MB
[2025-01-18 17:49:06 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][20/312]	eta 0:03:11 lr 0.003166	time 0.5969 (0.6561)	model_time 0.5967 (0.5878)	loss 3.9349 (3.5239)	grad_norm 2.2573 (1.9086/0.5959)	mem 24308MB
[2025-01-18 17:49:13 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][30/312]	eta 0:03:00 lr 0.003165	time 0.5858 (0.6410)	model_time 0.5854 (0.5946)	loss 3.4309 (3.5022)	grad_norm 2.8000 (1.9976/0.6354)	mem 24308MB
[2025-01-18 17:49:19 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][40/312]	eta 0:02:53 lr 0.003165	time 0.6641 (0.6377)	model_time 0.6636 (0.6026)	loss 2.7892 (3.4878)	grad_norm 0.9503 (1.8190/0.6539)	mem 24308MB
[2025-01-18 17:49:25 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][50/312]	eta 0:02:46 lr 0.003164	time 0.5908 (0.6336)	model_time 0.5904 (0.6053)	loss 3.8064 (3.4562)	grad_norm 1.7085 (1.7213/0.6472)	mem 24308MB
[2025-01-18 17:49:31 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][60/312]	eta 0:02:40 lr 0.003164	time 0.5854 (0.6360)	model_time 0.5853 (0.6122)	loss 2.9467 (3.4684)	grad_norm 1.3523 (1.7506/0.7108)	mem 24308MB
[2025-01-18 17:49:37 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][70/312]	eta 0:02:32 lr 0.003163	time 0.5867 (0.6310)	model_time 0.5866 (0.6105)	loss 3.6389 (3.4898)	grad_norm 1.9394 (1.7690/0.6718)	mem 24308MB
[2025-01-18 17:49:43 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][80/312]	eta 0:02:25 lr 0.003163	time 0.5739 (0.6260)	model_time 0.5738 (0.6080)	loss 3.5412 (3.4873)	grad_norm 1.6249 (1.6885/0.6723)	mem 24308MB
[2025-01-18 17:49:49 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][90/312]	eta 0:02:18 lr 0.003162	time 0.5837 (0.6226)	model_time 0.5836 (0.6066)	loss 3.9685 (3.4814)	grad_norm 1.2921 (1.7245/0.7257)	mem 24308MB
[2025-01-18 17:49:55 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][100/312]	eta 0:02:11 lr 0.003162	time 0.5974 (0.6203)	model_time 0.5972 (0.6058)	loss 3.0514 (3.4946)	grad_norm 1.4292 (1.7040/0.7056)	mem 24308MB
[2025-01-18 17:50:01 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][110/312]	eta 0:02:04 lr 0.003161	time 0.5794 (0.6172)	model_time 0.5793 (0.6040)	loss 3.9829 (3.5052)	grad_norm 1.3100 (1.6605/0.6930)	mem 24308MB
[2025-01-18 17:50:07 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][120/312]	eta 0:01:57 lr 0.003160	time 0.5723 (0.6145)	model_time 0.5721 (0.6023)	loss 3.8884 (3.5291)	grad_norm 1.3816 (1.6495/0.6697)	mem 24308MB
[2025-01-18 17:50:13 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][130/312]	eta 0:01:51 lr 0.003160	time 0.6059 (0.6124)	model_time 0.6055 (0.6011)	loss 3.6212 (3.5189)	grad_norm 2.2937 (1.6334/0.6630)	mem 24308MB
[2025-01-18 17:50:19 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][140/312]	eta 0:01:45 lr 0.003159	time 0.5802 (0.6109)	model_time 0.5801 (0.6004)	loss 3.9310 (3.5229)	grad_norm 1.4920 (1.6378/0.6551)	mem 24308MB
[2025-01-18 17:50:25 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][150/312]	eta 0:01:38 lr 0.003159	time 0.5908 (0.6110)	model_time 0.5906 (0.6012)	loss 4.1090 (3.5282)	grad_norm 1.1506 (1.6377/0.6480)	mem 24308MB
[2025-01-18 17:50:31 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][160/312]	eta 0:01:32 lr 0.003158	time 0.5871 (0.6116)	model_time 0.5866 (0.6023)	loss 4.3149 (3.5299)	grad_norm 2.0692 (1.6546/0.6591)	mem 24308MB
[2025-01-18 17:50:37 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][170/312]	eta 0:01:26 lr 0.003158	time 0.5816 (0.6114)	model_time 0.5811 (0.6027)	loss 3.7052 (3.5437)	grad_norm 0.6420 (1.6392/0.6561)	mem 24308MB
[2025-01-18 17:50:44 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][180/312]	eta 0:01:20 lr 0.003157	time 0.5743 (0.6123)	model_time 0.5741 (0.6041)	loss 4.2008 (3.5339)	grad_norm 2.4258 (1.6310/0.6543)	mem 24308MB
[2025-01-18 17:50:50 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][190/312]	eta 0:01:14 lr 0.003157	time 0.5904 (0.6125)	model_time 0.5899 (0.6047)	loss 3.6289 (3.5409)	grad_norm 0.9997 (1.6036/0.6508)	mem 24308MB
[2025-01-18 17:50:56 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][200/312]	eta 0:01:08 lr 0.003156	time 0.5793 (0.6120)	model_time 0.5792 (0.6046)	loss 3.7453 (3.5416)	grad_norm 2.7374 (1.6111/0.6484)	mem 24308MB
[2025-01-18 17:51:02 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][210/312]	eta 0:01:02 lr 0.003156	time 0.5904 (0.6112)	model_time 0.5902 (0.6041)	loss 4.0054 (3.5456)	grad_norm 0.6725 (1.6313/0.6746)	mem 24308MB
[2025-01-18 17:51:08 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][220/312]	eta 0:00:56 lr 0.003155	time 0.5966 (0.6107)	model_time 0.5964 (0.6039)	loss 4.2554 (3.5571)	grad_norm 0.8240 (1.6181/0.6668)	mem 24308MB
[2025-01-18 17:51:13 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][230/312]	eta 0:00:49 lr 0.003154	time 0.5937 (0.6095)	model_time 0.5935 (0.6030)	loss 4.6818 (3.5758)	grad_norm 1.8752 (1.5998/0.6624)	mem 24308MB
[2025-01-18 17:51:19 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][240/312]	eta 0:00:43 lr 0.003154	time 0.5852 (0.6085)	model_time 0.5850 (0.6022)	loss 3.8854 (3.5690)	grad_norm 2.0434 (1.5931/0.6540)	mem 24308MB
[2025-01-18 17:51:25 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][250/312]	eta 0:00:37 lr 0.003153	time 0.5731 (0.6076)	model_time 0.5729 (0.6015)	loss 2.5141 (3.5717)	grad_norm 1.8678 (1.5796/0.6468)	mem 24308MB
[2025-01-18 17:51:31 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][260/312]	eta 0:00:31 lr 0.003153	time 0.5823 (0.6069)	model_time 0.5819 (0.6010)	loss 2.8015 (3.5718)	grad_norm 1.4410 (1.5916/0.6509)	mem 24308MB
[2025-01-18 17:51:37 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][270/312]	eta 0:00:25 lr 0.003152	time 0.5790 (0.6068)	model_time 0.5789 (0.6012)	loss 3.4955 (3.5765)	grad_norm 1.4626 (1.5876/0.6405)	mem 24308MB
[2025-01-18 17:51:43 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][280/312]	eta 0:00:19 lr 0.003152	time 0.5753 (0.6078)	model_time 0.5748 (0.6024)	loss 3.0807 (3.5688)	grad_norm 2.3464 (1.5902/0.6379)	mem 24308MB
[2025-01-18 17:51:50 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][290/312]	eta 0:00:13 lr 0.003151	time 0.5999 (0.6079)	model_time 0.5998 (0.6026)	loss 3.7199 (3.5727)	grad_norm 0.9995 (1.5831/0.6343)	mem 24308MB
[2025-01-18 17:51:56 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][300/312]	eta 0:00:07 lr 0.003151	time 0.6509 (0.6084)	model_time 0.6508 (0.6033)	loss 4.0358 (3.5758)	grad_norm 1.1824 (1.5872/0.6294)	mem 24308MB
[2025-01-18 17:52:02 internimage_s_1k_224] (main.py 510): INFO Train: [91/300][310/312]	eta 0:00:01 lr 0.003150	time 0.5680 (0.6094)	model_time 0.5680 (0.6044)	loss 4.3032 (3.5804)	grad_norm 1.4381 (1.5727/0.6242)	mem 24308MB
[2025-01-18 17:52:03 internimage_s_1k_224] (main.py 519): INFO EPOCH 91 training takes 0:03:10
[2025-01-18 17:52:03 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_91.pth saving......
[2025-01-18 17:52:05 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_91.pth saved !!!
[2025-01-18 17:52:12 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.940 (6.940)	Loss 0.8586 (0.8586)	Acc@1 80.322 (80.322)	Acc@5 95.972 (95.972)	Mem 24308MB
[2025-01-18 17:52:15 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.909)	Loss 1.2468 (1.0411)	Acc@1 72.021 (76.562)	Acc@5 91.699 (93.781)	Mem 24308MB
[2025-01-18 17:52:15 internimage_s_1k_224] (main.py 575): INFO [Epoch:91] * Acc@1 76.406 Acc@5 93.810
[2025-01-18 17:52:15 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.4%
[2025-01-18 17:52:15 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 76.56%
[2025-01-18 17:52:23 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.875 (7.875)	Loss 0.8586 (0.8586)	Acc@1 78.784 (78.784)	Acc@5 95.166 (95.166)	Mem 24308MB
[2025-01-18 17:52:27 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.085)	Loss 1.3119 (1.0387)	Acc@1 67.993 (74.858)	Acc@5 89.282 (92.702)	Mem 24308MB
[2025-01-18 17:52:27 internimage_s_1k_224] (main.py 575): INFO [Epoch:91] * Acc@1 74.824 Acc@5 92.780
[2025-01-18 17:52:27 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 74.8%
[2025-01-18 17:52:27 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 17:52:29 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 17:52:29 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 74.82%
[2025-01-18 17:52:31 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][0/312]	eta 0:10:23 lr 0.003150	time 1.9984 (1.9984)	model_time 0.5906 (0.5906)	loss 4.2708 (4.2708)	grad_norm 1.5036 (1.5036/0.0000)	mem 24308MB
[2025-01-18 17:52:37 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][10/312]	eta 0:03:41 lr 0.003149	time 0.5926 (0.7332)	model_time 0.5924 (0.6049)	loss 3.8911 (3.4251)	grad_norm 0.9512 (1.2116/0.2331)	mem 24308MB
[2025-01-18 17:52:43 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][20/312]	eta 0:03:15 lr 0.003149	time 0.5860 (0.6682)	model_time 0.5856 (0.6008)	loss 2.7022 (3.5291)	grad_norm 3.2148 (1.5462/0.8728)	mem 24308MB
[2025-01-18 17:52:49 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][30/312]	eta 0:03:02 lr 0.003148	time 0.5752 (0.6470)	model_time 0.5750 (0.6013)	loss 4.6112 (3.6357)	grad_norm 2.2596 (1.6000/0.8260)	mem 24308MB
[2025-01-18 17:52:55 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][40/312]	eta 0:02:52 lr 0.003148	time 0.5800 (0.6336)	model_time 0.5798 (0.5989)	loss 4.4385 (3.5728)	grad_norm 0.9712 (1.5572/0.7661)	mem 24308MB
[2025-01-18 17:53:01 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][50/312]	eta 0:02:43 lr 0.003147	time 0.5921 (0.6250)	model_time 0.5919 (0.5971)	loss 2.8749 (3.5741)	grad_norm 0.9901 (1.5773/0.7578)	mem 24308MB
[2025-01-18 17:53:07 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][60/312]	eta 0:02:35 lr 0.003147	time 0.5864 (0.6188)	model_time 0.5858 (0.5954)	loss 3.0062 (3.5240)	grad_norm 1.4428 (1.5787/0.7817)	mem 24308MB
[2025-01-18 17:53:13 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][70/312]	eta 0:02:28 lr 0.003146	time 0.5790 (0.6143)	model_time 0.5788 (0.5941)	loss 3.1153 (3.4895)	grad_norm 0.9607 (1.4974/0.7545)	mem 24308MB
[2025-01-18 17:53:19 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][80/312]	eta 0:02:22 lr 0.003146	time 0.5820 (0.6137)	model_time 0.5816 (0.5960)	loss 2.8594 (3.4843)	grad_norm 1.1446 (1.4695/0.7129)	mem 24308MB
[2025-01-18 17:53:25 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][90/312]	eta 0:02:16 lr 0.003145	time 0.6954 (0.6152)	model_time 0.6952 (0.5993)	loss 2.6936 (3.4970)	grad_norm 1.1298 (1.4967/0.7131)	mem 24308MB
[2025-01-18 17:53:31 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][100/312]	eta 0:02:10 lr 0.003145	time 0.5739 (0.6170)	model_time 0.5738 (0.6027)	loss 3.4684 (3.5036)	grad_norm 1.1238 (1.4962/0.7123)	mem 24308MB
[2025-01-18 17:53:38 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][110/312]	eta 0:02:04 lr 0.003144	time 0.6759 (0.6175)	model_time 0.6757 (0.6045)	loss 3.8395 (3.4969)	grad_norm 1.6547 (1.5195/0.7153)	mem 24308MB
[2025-01-18 17:53:44 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][120/312]	eta 0:01:59 lr 0.003143	time 0.5802 (0.6199)	model_time 0.5798 (0.6079)	loss 3.2674 (3.4957)	grad_norm 1.6170 (1.5023/0.6978)	mem 24308MB
[2025-01-18 17:53:50 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][130/312]	eta 0:01:52 lr 0.003143	time 0.5914 (0.6182)	model_time 0.5912 (0.6071)	loss 3.7167 (3.4951)	grad_norm 0.9857 (1.4879/0.6788)	mem 24308MB
[2025-01-18 17:53:56 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][140/312]	eta 0:01:46 lr 0.003142	time 0.5831 (0.6169)	model_time 0.5829 (0.6066)	loss 3.2593 (3.4863)	grad_norm 1.5104 (1.5138/0.6867)	mem 24308MB
[2025-01-18 17:54:02 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][150/312]	eta 0:01:39 lr 0.003142	time 0.5823 (0.6159)	model_time 0.5821 (0.6062)	loss 3.5743 (3.5032)	grad_norm 1.5946 (1.5280/0.6778)	mem 24308MB
[2025-01-18 17:54:08 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][160/312]	eta 0:01:33 lr 0.003141	time 0.5693 (0.6142)	model_time 0.5689 (0.6051)	loss 3.8654 (3.5245)	grad_norm 1.2306 (1.5057/0.6646)	mem 24308MB
[2025-01-18 17:54:14 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][170/312]	eta 0:01:26 lr 0.003141	time 0.5810 (0.6126)	model_time 0.5809 (0.6040)	loss 3.2053 (3.5400)	grad_norm 0.9317 (1.4813/0.6614)	mem 24308MB
[2025-01-18 17:54:20 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][180/312]	eta 0:01:20 lr 0.003140	time 0.6064 (0.6114)	model_time 0.6059 (0.6032)	loss 2.5869 (3.5349)	grad_norm 1.0997 (1.4780/0.6491)	mem 24308MB
[2025-01-18 17:54:26 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][190/312]	eta 0:01:14 lr 0.003140	time 0.5862 (0.6104)	model_time 0.5860 (0.6026)	loss 2.6234 (3.5233)	grad_norm 1.1302 (1.4686/0.6371)	mem 24308MB
[2025-01-18 17:54:32 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][200/312]	eta 0:01:08 lr 0.003139	time 0.5763 (0.6103)	model_time 0.5759 (0.6030)	loss 3.3168 (3.5191)	grad_norm 4.0511 (1.4768/0.6567)	mem 24308MB
[2025-01-18 17:54:38 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][210/312]	eta 0:01:02 lr 0.003139	time 0.6676 (0.6111)	model_time 0.6674 (0.6040)	loss 3.7350 (3.5165)	grad_norm 0.8064 (1.5053/0.6779)	mem 24308MB
[2025-01-18 17:54:44 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][220/312]	eta 0:00:56 lr 0.003138	time 0.5833 (0.6118)	model_time 0.5828 (0.6050)	loss 2.9857 (3.5057)	grad_norm 1.1145 (1.4900/0.6674)	mem 24308MB
[2025-01-18 17:54:51 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][230/312]	eta 0:00:50 lr 0.003137	time 0.7075 (0.6123)	model_time 0.7071 (0.6058)	loss 3.7728 (3.5098)	grad_norm 1.9607 (1.4996/0.6617)	mem 24308MB
[2025-01-18 17:54:57 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][240/312]	eta 0:00:44 lr 0.003137	time 0.5847 (0.6129)	model_time 0.5846 (0.6067)	loss 3.1611 (3.5079)	grad_norm 3.6001 (1.5242/0.6795)	mem 24308MB
[2025-01-18 17:55:03 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][250/312]	eta 0:00:37 lr 0.003136	time 0.5934 (0.6121)	model_time 0.5930 (0.6062)	loss 3.9747 (3.5012)	grad_norm 1.5868 (1.5232/0.6739)	mem 24308MB
[2025-01-18 17:55:09 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][260/312]	eta 0:00:31 lr 0.003136	time 0.5753 (0.6115)	model_time 0.5749 (0.6057)	loss 4.2567 (3.5132)	grad_norm 1.4197 (1.5156/0.6641)	mem 24308MB
[2025-01-18 17:55:15 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][270/312]	eta 0:00:25 lr 0.003135	time 0.5706 (0.6110)	model_time 0.5705 (0.6054)	loss 2.5819 (3.5119)	grad_norm 1.8353 (1.5285/0.6666)	mem 24308MB
[2025-01-18 17:55:21 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][280/312]	eta 0:00:19 lr 0.003135	time 0.6042 (0.6100)	model_time 0.6038 (0.6046)	loss 4.3008 (3.5206)	grad_norm 0.7720 (1.5184/0.6637)	mem 24308MB
[2025-01-18 17:55:26 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][290/312]	eta 0:00:13 lr 0.003134	time 0.5872 (0.6092)	model_time 0.5868 (0.6040)	loss 4.1759 (3.5190)	grad_norm 0.8430 (1.5086/0.6564)	mem 24308MB
[2025-01-18 17:55:32 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][300/312]	eta 0:00:07 lr 0.003134	time 0.5635 (0.6083)	model_time 0.5635 (0.6032)	loss 4.1270 (3.5195)	grad_norm 1.1548 (1.5020/0.6507)	mem 24308MB
[2025-01-18 17:55:38 internimage_s_1k_224] (main.py 510): INFO Train: [92/300][310/312]	eta 0:00:01 lr 0.003133	time 0.5599 (0.6073)	model_time 0.5598 (0.6024)	loss 3.6011 (3.5130)	grad_norm 2.4979 (1.5215/0.6524)	mem 24308MB
[2025-01-18 17:55:39 internimage_s_1k_224] (main.py 519): INFO EPOCH 92 training takes 0:03:09
[2025-01-18 17:55:39 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_92.pth saving......
[2025-01-18 17:55:40 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_92.pth saved !!!
[2025-01-18 17:55:47 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.822 (6.822)	Loss 0.9062 (0.9062)	Acc@1 80.151 (80.151)	Acc@5 95.703 (95.703)	Mem 24308MB
[2025-01-18 17:55:50 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.907)	Loss 1.3352 (1.1029)	Acc@1 71.118 (76.527)	Acc@5 91.064 (93.619)	Mem 24308MB
[2025-01-18 17:55:51 internimage_s_1k_224] (main.py 575): INFO [Epoch:92] * Acc@1 76.446 Acc@5 93.644
[2025-01-18 17:55:51 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.4%
[2025-01-18 17:55:51 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 76.56%
[2025-01-18 17:55:58 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.851 (7.851)	Loss 0.8517 (0.8517)	Acc@1 79.102 (79.102)	Acc@5 95.264 (95.264)	Mem 24308MB
[2025-01-18 17:56:02 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.072)	Loss 1.3019 (1.0311)	Acc@1 68.213 (75.033)	Acc@5 89.258 (92.773)	Mem 24308MB
[2025-01-18 17:56:03 internimage_s_1k_224] (main.py 575): INFO [Epoch:92] * Acc@1 75.000 Acc@5 92.854
[2025-01-18 17:56:03 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 75.0%
[2025-01-18 17:56:03 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 17:56:05 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 17:56:05 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 75.00%
[2025-01-18 17:56:07 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][0/312]	eta 0:11:08 lr 0.003133	time 2.1440 (2.1440)	model_time 0.5883 (0.5883)	loss 3.7181 (3.7181)	grad_norm 2.0814 (2.0814/0.0000)	mem 24308MB
[2025-01-18 17:56:13 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][10/312]	eta 0:03:46 lr 0.003132	time 0.5964 (0.7513)	model_time 0.5962 (0.6060)	loss 3.9401 (3.6386)	grad_norm 1.9980 (1.9787/0.7447)	mem 24308MB
[2025-01-18 17:56:19 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][20/312]	eta 0:03:20 lr 0.003132	time 0.6047 (0.6874)	model_time 0.6046 (0.6112)	loss 3.2200 (3.6034)	grad_norm 1.8390 (1.8650/0.7428)	mem 24308MB
[2025-01-18 17:56:26 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][30/312]	eta 0:03:08 lr 0.003131	time 0.6065 (0.6690)	model_time 0.6063 (0.6173)	loss 3.6148 (3.5790)	grad_norm 0.9392 (1.6517/0.6923)	mem 24308MB
[2025-01-18 17:56:32 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][40/312]	eta 0:02:58 lr 0.003131	time 0.6466 (0.6565)	model_time 0.6462 (0.6173)	loss 2.7332 (3.5609)	grad_norm 1.3488 (1.5571/0.6396)	mem 24308MB
[2025-01-18 17:56:38 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][50/312]	eta 0:02:50 lr 0.003130	time 0.6720 (0.6501)	model_time 0.6715 (0.6185)	loss 2.6384 (3.6022)	grad_norm 1.3566 (1.5090/0.6213)	mem 24308MB
[2025-01-18 17:56:44 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][60/312]	eta 0:02:41 lr 0.003130	time 0.5665 (0.6413)	model_time 0.5663 (0.6148)	loss 3.3154 (3.5481)	grad_norm 0.7506 (1.5460/0.6337)	mem 24308MB
[2025-01-18 17:56:50 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][70/312]	eta 0:02:33 lr 0.003129	time 0.5847 (0.6346)	model_time 0.5846 (0.6118)	loss 4.4303 (3.5867)	grad_norm 1.0211 (1.5222/0.6159)	mem 24308MB
[2025-01-18 17:56:56 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][80/312]	eta 0:02:26 lr 0.003129	time 0.5970 (0.6301)	model_time 0.5965 (0.6101)	loss 3.2148 (3.5726)	grad_norm 0.9018 (1.5029/0.6151)	mem 24308MB
[2025-01-18 17:57:02 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][90/312]	eta 0:02:18 lr 0.003128	time 0.5802 (0.6255)	model_time 0.5801 (0.6076)	loss 2.2189 (3.5526)	grad_norm 1.9986 (1.5488/0.6377)	mem 24308MB
[2025-01-18 17:57:08 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][100/312]	eta 0:02:11 lr 0.003127	time 0.5812 (0.6218)	model_time 0.5807 (0.6057)	loss 2.4795 (3.5445)	grad_norm 1.9693 (1.5823/0.6571)	mem 24308MB
[2025-01-18 17:57:14 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][110/312]	eta 0:02:05 lr 0.003127	time 0.5826 (0.6189)	model_time 0.5821 (0.6042)	loss 3.3047 (3.5272)	grad_norm 1.9717 (1.5454/0.6447)	mem 24308MB
[2025-01-18 17:57:19 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][120/312]	eta 0:01:58 lr 0.003126	time 0.5974 (0.6166)	model_time 0.5973 (0.6031)	loss 3.5744 (3.5115)	grad_norm 0.9789 (1.5380/0.6233)	mem 24308MB
[2025-01-18 17:57:26 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][130/312]	eta 0:01:52 lr 0.003126	time 0.7611 (0.6169)	model_time 0.7609 (0.6044)	loss 3.8970 (3.5320)	grad_norm 1.7337 (1.5474/0.6239)	mem 24308MB
[2025-01-18 17:57:32 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][140/312]	eta 0:01:46 lr 0.003125	time 0.5761 (0.6169)	model_time 0.5756 (0.6052)	loss 3.7777 (3.5336)	grad_norm 1.4874 (1.5533/0.6084)	mem 24308MB
[2025-01-18 17:57:38 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][150/312]	eta 0:01:40 lr 0.003125	time 0.6621 (0.6183)	model_time 0.6616 (0.6074)	loss 3.6255 (3.5299)	grad_norm 0.9572 (1.5670/0.6221)	mem 24308MB
[2025-01-18 17:57:44 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][160/312]	eta 0:01:34 lr 0.003124	time 0.6882 (0.6190)	model_time 0.6881 (0.6087)	loss 3.4681 (3.5233)	grad_norm 1.0301 (1.5709/0.6234)	mem 24308MB
[2025-01-18 17:57:51 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][170/312]	eta 0:01:28 lr 0.003124	time 0.5713 (0.6216)	model_time 0.5711 (0.6119)	loss 4.4069 (3.5278)	grad_norm 1.0836 (1.5560/0.6110)	mem 24308MB
[2025-01-18 17:57:57 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][180/312]	eta 0:01:21 lr 0.003123	time 0.5908 (0.6205)	model_time 0.5904 (0.6114)	loss 3.4713 (3.5144)	grad_norm 0.9131 (1.5605/0.6071)	mem 24308MB
[2025-01-18 17:58:03 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][190/312]	eta 0:01:15 lr 0.003122	time 0.5710 (0.6194)	model_time 0.5706 (0.6106)	loss 3.8738 (3.5226)	grad_norm 1.1677 (1.5567/0.6130)	mem 24308MB
[2025-01-18 17:58:09 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][200/312]	eta 0:01:09 lr 0.003122	time 0.5879 (0.6182)	model_time 0.5877 (0.6099)	loss 3.6790 (3.5141)	grad_norm 2.0579 (1.5568/0.6068)	mem 24308MB
[2025-01-18 17:58:15 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][210/312]	eta 0:01:02 lr 0.003121	time 0.5866 (0.6168)	model_time 0.5864 (0.6089)	loss 3.7795 (3.5092)	grad_norm 1.1021 (1.5398/0.6022)	mem 24308MB
[2025-01-18 17:58:21 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][220/312]	eta 0:00:56 lr 0.003121	time 0.5752 (0.6156)	model_time 0.5748 (0.6080)	loss 3.5958 (3.5146)	grad_norm 1.4325 (1.5238/0.5943)	mem 24308MB
[2025-01-18 17:58:27 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][230/312]	eta 0:00:50 lr 0.003120	time 0.5806 (0.6142)	model_time 0.5805 (0.6069)	loss 3.9729 (3.5035)	grad_norm 1.7734 (1.5159/0.5883)	mem 24308MB
[2025-01-18 17:58:33 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][240/312]	eta 0:00:44 lr 0.003120	time 0.5933 (0.6130)	model_time 0.5931 (0.6060)	loss 3.6427 (3.5140)	grad_norm 2.0348 (1.5248/0.5872)	mem 24308MB
[2025-01-18 17:58:39 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][250/312]	eta 0:00:37 lr 0.003119	time 0.6603 (0.6126)	model_time 0.6602 (0.6058)	loss 3.5380 (3.5053)	grad_norm 2.8478 (1.5488/0.6074)	mem 24308MB
[2025-01-18 17:58:45 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][260/312]	eta 0:00:31 lr 0.003119	time 0.6661 (0.6126)	model_time 0.6657 (0.6061)	loss 4.3444 (3.5234)	grad_norm 1.3063 (1.5554/0.6046)	mem 24308MB
[2025-01-18 17:58:51 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][270/312]	eta 0:00:25 lr 0.003118	time 0.6685 (0.6132)	model_time 0.6684 (0.6070)	loss 3.8501 (3.5356)	grad_norm 2.1769 (1.5484/0.6030)	mem 24308MB
[2025-01-18 17:58:57 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][280/312]	eta 0:00:19 lr 0.003117	time 0.5719 (0.6133)	model_time 0.5714 (0.6072)	loss 4.2833 (3.5401)	grad_norm 1.5167 (1.5402/0.5993)	mem 24308MB
[2025-01-18 17:59:04 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][290/312]	eta 0:00:13 lr 0.003117	time 0.5674 (0.6151)	model_time 0.5670 (0.6092)	loss 3.4426 (3.5400)	grad_norm 2.8342 (1.5497/0.6012)	mem 24308MB
[2025-01-18 17:59:10 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][300/312]	eta 0:00:07 lr 0.003116	time 0.5662 (0.6148)	model_time 0.5661 (0.6091)	loss 3.1781 (3.5428)	grad_norm 2.4370 (1.5489/0.5954)	mem 24308MB
[2025-01-18 17:59:16 internimage_s_1k_224] (main.py 510): INFO Train: [93/300][310/312]	eta 0:00:01 lr 0.003116	time 0.5826 (0.6139)	model_time 0.5825 (0.6084)	loss 4.3170 (3.5408)	grad_norm 1.0347 (1.5436/0.5896)	mem 24308MB
[2025-01-18 17:59:16 internimage_s_1k_224] (main.py 519): INFO EPOCH 93 training takes 0:03:11
[2025-01-18 17:59:16 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_93.pth saving......
[2025-01-18 17:59:18 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_93.pth saved !!!
[2025-01-18 17:59:25 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.595 (6.595)	Loss 0.9070 (0.9070)	Acc@1 80.249 (80.249)	Acc@5 96.094 (96.094)	Mem 24308MB
[2025-01-18 17:59:28 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.908)	Loss 1.3099 (1.0941)	Acc@1 71.704 (76.529)	Acc@5 90.894 (93.632)	Mem 24308MB
[2025-01-18 17:59:28 internimage_s_1k_224] (main.py 575): INFO [Epoch:93] * Acc@1 76.484 Acc@5 93.664
[2025-01-18 17:59:28 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.5%
[2025-01-18 17:59:28 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 76.56%
[2025-01-18 17:59:36 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.903 (7.903)	Loss 0.8453 (0.8453)	Acc@1 79.126 (79.126)	Acc@5 95.312 (95.312)	Mem 24308MB
[2025-01-18 17:59:40 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.070)	Loss 1.2923 (1.0239)	Acc@1 68.286 (75.149)	Acc@5 89.453 (92.864)	Mem 24308MB
[2025-01-18 17:59:40 internimage_s_1k_224] (main.py 575): INFO [Epoch:93] * Acc@1 75.114 Acc@5 92.944
[2025-01-18 17:59:40 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 75.1%
[2025-01-18 17:59:40 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 17:59:43 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 17:59:43 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 75.11%
[2025-01-18 17:59:45 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][0/312]	eta 0:10:35 lr 0.003116	time 2.0383 (2.0383)	model_time 0.6022 (0.6022)	loss 4.1861 (4.1861)	grad_norm 0.9637 (0.9637/0.0000)	mem 24308MB
[2025-01-18 17:59:51 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][10/312]	eta 0:03:40 lr 0.003115	time 0.5811 (0.7299)	model_time 0.5809 (0.5990)	loss 4.2644 (3.8099)	grad_norm 2.3197 (1.1068/0.4236)	mem 24308MB
[2025-01-18 17:59:57 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][20/312]	eta 0:03:13 lr 0.003115	time 0.5861 (0.6634)	model_time 0.5859 (0.5947)	loss 2.8072 (3.7861)	grad_norm 2.8059 (1.5761/0.6812)	mem 24308MB
[2025-01-18 18:00:03 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][30/312]	eta 0:03:00 lr 0.003114	time 0.5973 (0.6400)	model_time 0.5969 (0.5934)	loss 3.6772 (3.6772)	grad_norm 2.8255 (1.6448/0.6670)	mem 24308MB
[2025-01-18 18:00:08 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][40/312]	eta 0:02:50 lr 0.003114	time 0.5984 (0.6278)	model_time 0.5982 (0.5924)	loss 3.3872 (3.6335)	grad_norm 0.8772 (1.5296/0.6330)	mem 24308MB
[2025-01-18 18:00:14 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][50/312]	eta 0:02:42 lr 0.003113	time 0.5829 (0.6196)	model_time 0.5827 (0.5911)	loss 3.2467 (3.6064)	grad_norm 2.9913 (1.4889/0.6282)	mem 24308MB
[2025-01-18 18:00:20 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][60/312]	eta 0:02:35 lr 0.003112	time 0.5744 (0.6155)	model_time 0.5743 (0.5916)	loss 4.4617 (3.5489)	grad_norm 0.9876 (1.4808/0.6132)	mem 24308MB
[2025-01-18 18:00:26 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][70/312]	eta 0:02:28 lr 0.003112	time 0.6882 (0.6156)	model_time 0.6880 (0.5950)	loss 2.8226 (3.5813)	grad_norm 1.5636 (1.4518/0.5821)	mem 24308MB
[2025-01-18 18:00:33 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][80/312]	eta 0:02:24 lr 0.003111	time 0.7290 (0.6209)	model_time 0.7286 (0.6028)	loss 3.3121 (3.5562)	grad_norm 2.1535 (1.5175/0.6268)	mem 24308MB
[2025-01-18 18:00:39 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][90/312]	eta 0:02:17 lr 0.003111	time 0.5802 (0.6189)	model_time 0.5798 (0.6027)	loss 2.9817 (3.5568)	grad_norm 0.9447 (1.5172/0.6275)	mem 24308MB
[2025-01-18 18:00:46 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][100/312]	eta 0:02:11 lr 0.003110	time 0.6952 (0.6218)	model_time 0.6950 (0.6072)	loss 4.3247 (3.5620)	grad_norm 2.6278 (1.5532/0.6647)	mem 24308MB
[2025-01-18 18:00:52 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][110/312]	eta 0:02:05 lr 0.003110	time 0.5724 (0.6202)	model_time 0.5720 (0.6069)	loss 3.6062 (3.5628)	grad_norm 1.8723 (1.5602/0.6449)	mem 24308MB
[2025-01-18 18:00:58 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][120/312]	eta 0:01:58 lr 0.003109	time 0.5854 (0.6185)	model_time 0.5850 (0.6063)	loss 3.1467 (3.5324)	grad_norm 1.3303 (1.5231/0.6393)	mem 24308MB
[2025-01-18 18:01:04 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][130/312]	eta 0:01:52 lr 0.003109	time 0.5718 (0.6168)	model_time 0.5716 (0.6055)	loss 4.1429 (3.5299)	grad_norm 2.1612 (1.5303/0.6341)	mem 24308MB
[2025-01-18 18:01:09 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][140/312]	eta 0:01:45 lr 0.003108	time 0.5812 (0.6148)	model_time 0.5808 (0.6042)	loss 4.0313 (3.5295)	grad_norm 1.8323 (1.5235/0.6245)	mem 24308MB
[2025-01-18 18:01:15 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][150/312]	eta 0:01:39 lr 0.003107	time 0.5956 (0.6131)	model_time 0.5954 (0.6032)	loss 4.2877 (3.5393)	grad_norm 1.2130 (1.5406/0.6556)	mem 24308MB
[2025-01-18 18:01:21 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][160/312]	eta 0:01:32 lr 0.003107	time 0.5907 (0.6114)	model_time 0.5905 (0.6021)	loss 3.4775 (3.5342)	grad_norm 0.9742 (1.5108/0.6496)	mem 24308MB
[2025-01-18 18:01:27 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][170/312]	eta 0:01:26 lr 0.003106	time 0.5697 (0.6101)	model_time 0.5693 (0.6014)	loss 3.6024 (3.5562)	grad_norm 1.3028 (1.4934/0.6380)	mem 24308MB
[2025-01-18 18:01:33 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][180/312]	eta 0:01:20 lr 0.003106	time 0.5822 (0.6091)	model_time 0.5818 (0.6008)	loss 4.2261 (3.5594)	grad_norm 1.1648 (1.5070/0.6561)	mem 24308MB
[2025-01-18 18:01:39 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][190/312]	eta 0:01:14 lr 0.003105	time 0.6613 (0.6096)	model_time 0.6612 (0.6017)	loss 2.8321 (3.5498)	grad_norm 1.2549 (1.5225/0.6517)	mem 24308MB
[2025-01-18 18:01:45 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][200/312]	eta 0:01:08 lr 0.003105	time 0.5817 (0.6096)	model_time 0.5813 (0.6021)	loss 3.8173 (3.5448)	grad_norm 1.0073 (1.5108/0.6441)	mem 24308MB
[2025-01-18 18:01:51 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][210/312]	eta 0:01:02 lr 0.003104	time 0.5788 (0.6102)	model_time 0.5786 (0.6031)	loss 3.9065 (3.5404)	grad_norm 1.0819 (1.5064/0.6350)	mem 24308MB
[2025-01-18 18:01:58 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][220/312]	eta 0:00:56 lr 0.003104	time 0.7269 (0.6117)	model_time 0.7267 (0.6048)	loss 3.0564 (3.5334)	grad_norm 1.2256 (1.5127/0.6390)	mem 24308MB
[2025-01-18 18:02:04 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][230/312]	eta 0:00:50 lr 0.003103	time 0.5708 (0.6118)	model_time 0.5704 (0.6052)	loss 3.4641 (3.5385)	grad_norm 0.8745 (1.5070/0.6295)	mem 24308MB
[2025-01-18 18:02:10 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][240/312]	eta 0:00:44 lr 0.003102	time 0.5749 (0.6112)	model_time 0.5747 (0.6049)	loss 3.3273 (3.5379)	grad_norm 2.4487 (1.5047/0.6253)	mem 24308MB
[2025-01-18 18:02:16 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][250/312]	eta 0:00:37 lr 0.003102	time 0.5717 (0.6104)	model_time 0.5713 (0.6043)	loss 4.0086 (3.5459)	grad_norm 1.0942 (1.5093/0.6227)	mem 24308MB
[2025-01-18 18:02:22 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][260/312]	eta 0:00:31 lr 0.003101	time 0.5856 (0.6100)	model_time 0.5854 (0.6041)	loss 4.3594 (3.5429)	grad_norm 1.0357 (1.5045/0.6209)	mem 24308MB
[2025-01-18 18:02:28 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][270/312]	eta 0:00:25 lr 0.003101	time 0.5796 (0.6093)	model_time 0.5790 (0.6036)	loss 3.5591 (3.5359)	grad_norm 2.7951 (1.5067/0.6167)	mem 24308MB
[2025-01-18 18:02:34 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][280/312]	eta 0:00:19 lr 0.003100	time 0.5909 (0.6086)	model_time 0.5905 (0.6031)	loss 3.0844 (3.5283)	grad_norm 1.3164 (1.5061/0.6100)	mem 24308MB
[2025-01-18 18:02:40 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][290/312]	eta 0:00:13 lr 0.003100	time 0.5786 (0.6079)	model_time 0.5782 (0.6026)	loss 3.0972 (3.5183)	grad_norm 1.0923 (1.4888/0.6076)	mem 24308MB
[2025-01-18 18:02:46 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][300/312]	eta 0:00:07 lr 0.003099	time 0.6520 (0.6073)	model_time 0.6519 (0.6022)	loss 4.0944 (3.5128)	grad_norm 1.5520 (1.4886/0.6024)	mem 24308MB
[2025-01-18 18:02:51 internimage_s_1k_224] (main.py 510): INFO Train: [94/300][310/312]	eta 0:00:01 lr 0.003098	time 0.5727 (0.6069)	model_time 0.5726 (0.6019)	loss 3.8256 (3.5240)	grad_norm 1.4485 (1.5177/0.6092)	mem 24308MB
[2025-01-18 18:02:52 internimage_s_1k_224] (main.py 519): INFO EPOCH 94 training takes 0:03:09
[2025-01-18 18:02:52 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_94.pth saving......
[2025-01-18 18:02:54 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_94.pth saved !!!
[2025-01-18 18:03:01 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.324 (7.324)	Loss 0.8816 (0.8816)	Acc@1 80.493 (80.493)	Acc@5 95.898 (95.898)	Mem 24308MB
[2025-01-18 18:03:05 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.985)	Loss 1.2429 (1.0331)	Acc@1 72.314 (77.035)	Acc@5 91.577 (93.932)	Mem 24308MB
[2025-01-18 18:03:05 internimage_s_1k_224] (main.py 575): INFO [Epoch:94] * Acc@1 77.029 Acc@5 94.006
[2025-01-18 18:03:05 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.0%
[2025-01-18 18:03:05 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 18:03:07 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 18:03:07 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.03%
[2025-01-18 18:03:14 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.355 (7.355)	Loss 0.8387 (0.8387)	Acc@1 79.370 (79.370)	Acc@5 95.337 (95.337)	Mem 24308MB
[2025-01-18 18:03:18 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.979)	Loss 1.2828 (1.0168)	Acc@1 68.408 (75.357)	Acc@5 89.648 (92.951)	Mem 24308MB
[2025-01-18 18:03:18 internimage_s_1k_224] (main.py 575): INFO [Epoch:94] * Acc@1 75.316 Acc@5 93.030
[2025-01-18 18:03:18 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 75.3%
[2025-01-18 18:03:18 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 18:03:20 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 18:03:20 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 75.32%
[2025-01-18 18:03:22 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][0/312]	eta 0:11:24 lr 0.003098	time 2.1938 (2.1938)	model_time 0.5972 (0.5972)	loss 3.5877 (3.5877)	grad_norm 1.7506 (1.7506/0.0000)	mem 24308MB
[2025-01-18 18:03:29 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][10/312]	eta 0:03:52 lr 0.003098	time 0.6551 (0.7692)	model_time 0.6547 (0.6238)	loss 4.0973 (3.6137)	grad_norm 0.7927 (1.5421/0.5925)	mem 24308MB
[2025-01-18 18:03:35 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][20/312]	eta 0:03:24 lr 0.003097	time 0.5743 (0.7011)	model_time 0.5738 (0.6247)	loss 2.8811 (3.5258)	grad_norm 1.0443 (1.8362/1.0255)	mem 24308MB
[2025-01-18 18:03:41 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][30/312]	eta 0:03:11 lr 0.003097	time 0.5909 (0.6804)	model_time 0.5907 (0.6286)	loss 3.8291 (3.5415)	grad_norm 2.6082 (1.6244/0.9516)	mem 24308MB
[2025-01-18 18:03:47 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][40/312]	eta 0:02:59 lr 0.003096	time 0.5683 (0.6614)	model_time 0.5679 (0.6221)	loss 3.6741 (3.5701)	grad_norm 0.7896 (1.5993/0.8939)	mem 24308MB
[2025-01-18 18:03:53 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][50/312]	eta 0:02:50 lr 0.003096	time 0.5889 (0.6498)	model_time 0.5885 (0.6181)	loss 4.0879 (3.6016)	grad_norm 1.7894 (1.6417/0.8270)	mem 24308MB
[2025-01-18 18:03:59 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][60/312]	eta 0:02:41 lr 0.003095	time 0.5809 (0.6396)	model_time 0.5807 (0.6131)	loss 4.4564 (3.6106)	grad_norm 1.2223 (1.6691/0.8177)	mem 24308MB
[2025-01-18 18:04:05 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][70/312]	eta 0:02:33 lr 0.003094	time 0.5790 (0.6332)	model_time 0.5785 (0.6104)	loss 3.2689 (3.5975)	grad_norm 1.3529 (1.6185/0.7828)	mem 24308MB
[2025-01-18 18:04:11 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][80/312]	eta 0:02:25 lr 0.003094	time 0.5941 (0.6280)	model_time 0.5937 (0.6079)	loss 3.9491 (3.6049)	grad_norm 1.1503 (1.5986/0.7496)	mem 24308MB
[2025-01-18 18:04:17 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][90/312]	eta 0:02:18 lr 0.003093	time 0.5930 (0.6236)	model_time 0.5928 (0.6057)	loss 2.5339 (3.5917)	grad_norm 1.3109 (1.5683/0.7287)	mem 24308MB
[2025-01-18 18:04:23 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][100/312]	eta 0:02:11 lr 0.003093	time 0.5897 (0.6202)	model_time 0.5895 (0.6041)	loss 3.3061 (3.5826)	grad_norm 2.2197 (1.5780/0.7132)	mem 24308MB
[2025-01-18 18:04:29 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][110/312]	eta 0:02:04 lr 0.003092	time 0.5891 (0.6185)	model_time 0.5887 (0.6038)	loss 3.4569 (3.5758)	grad_norm 2.3208 (1.5801/0.7113)	mem 24308MB
[2025-01-18 18:04:35 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][120/312]	eta 0:01:58 lr 0.003092	time 0.6687 (0.6184)	model_time 0.6685 (0.6048)	loss 3.0601 (3.5648)	grad_norm 1.6637 (1.5566/0.6907)	mem 24308MB
[2025-01-18 18:04:41 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][130/312]	eta 0:01:52 lr 0.003091	time 0.6913 (0.6199)	model_time 0.6912 (0.6073)	loss 3.4340 (3.5616)	grad_norm 1.0261 (1.6019/0.7215)	mem 24308MB
[2025-01-18 18:04:47 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][140/312]	eta 0:01:46 lr 0.003091	time 0.5664 (0.6187)	model_time 0.5660 (0.6070)	loss 2.5352 (3.5339)	grad_norm 1.7240 (1.6275/0.7230)	mem 24308MB
[2025-01-18 18:04:54 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][150/312]	eta 0:01:40 lr 0.003090	time 0.6674 (0.6198)	model_time 0.6672 (0.6089)	loss 4.3203 (3.5373)	grad_norm 1.0512 (1.5977/0.7101)	mem 24308MB
[2025-01-18 18:05:00 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][160/312]	eta 0:01:34 lr 0.003089	time 0.5928 (0.6195)	model_time 0.5926 (0.6092)	loss 3.7064 (3.5448)	grad_norm 1.4269 (1.5708/0.6999)	mem 24308MB
[2025-01-18 18:05:06 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][170/312]	eta 0:01:27 lr 0.003089	time 0.5836 (0.6178)	model_time 0.5834 (0.6081)	loss 3.0228 (3.5511)	grad_norm 0.8641 (1.5746/0.7043)	mem 24308MB
[2025-01-18 18:05:12 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][180/312]	eta 0:01:21 lr 0.003088	time 0.5855 (0.6164)	model_time 0.5853 (0.6072)	loss 3.7490 (3.5443)	grad_norm 0.9655 (1.5757/0.7141)	mem 24308MB
[2025-01-18 18:05:18 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][190/312]	eta 0:01:15 lr 0.003088	time 0.5773 (0.6153)	model_time 0.5772 (0.6066)	loss 3.7439 (3.5472)	grad_norm 1.9285 (1.5705/0.7166)	mem 24308MB
[2025-01-18 18:05:23 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][200/312]	eta 0:01:08 lr 0.003087	time 0.5785 (0.6137)	model_time 0.5783 (0.6054)	loss 3.2475 (3.5494)	grad_norm 1.1873 (1.5722/0.7241)	mem 24308MB
[2025-01-18 18:05:29 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][210/312]	eta 0:01:02 lr 0.003087	time 0.5856 (0.6123)	model_time 0.5854 (0.6043)	loss 3.7856 (3.5459)	grad_norm 1.0505 (1.5561/0.7153)	mem 24308MB
[2025-01-18 18:05:35 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][220/312]	eta 0:00:56 lr 0.003086	time 0.5760 (0.6111)	model_time 0.5758 (0.6035)	loss 3.5406 (3.5455)	grad_norm 1.8664 (1.5638/0.7065)	mem 24308MB
[2025-01-18 18:05:41 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][230/312]	eta 0:00:50 lr 0.003086	time 0.5760 (0.6109)	model_time 0.5758 (0.6037)	loss 2.5370 (3.5390)	grad_norm 2.5995 (1.5730/0.7093)	mem 24308MB
[2025-01-18 18:05:47 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][240/312]	eta 0:00:44 lr 0.003085	time 0.6674 (0.6111)	model_time 0.6669 (0.6041)	loss 3.2413 (3.5413)	grad_norm 1.3003 (1.5846/0.7131)	mem 24308MB
[2025-01-18 18:05:54 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][250/312]	eta 0:00:37 lr 0.003084	time 0.6654 (0.6117)	model_time 0.6653 (0.6050)	loss 3.8146 (3.5299)	grad_norm 1.0896 (1.5750/0.7085)	mem 24308MB
[2025-01-18 18:06:00 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][260/312]	eta 0:00:31 lr 0.003084	time 0.5833 (0.6118)	model_time 0.5828 (0.6053)	loss 3.3210 (3.5214)	grad_norm 2.2973 (1.5804/0.7097)	mem 24308MB
[2025-01-18 18:06:06 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][270/312]	eta 0:00:25 lr 0.003083	time 0.6716 (0.6124)	model_time 0.6714 (0.6061)	loss 2.6508 (3.5223)	grad_norm 0.9054 (1.5671/0.7048)	mem 24308MB
[2025-01-18 18:06:12 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][280/312]	eta 0:00:19 lr 0.003083	time 0.5690 (0.6126)	model_time 0.5688 (0.6066)	loss 3.8789 (3.5136)	grad_norm 1.7848 (1.5851/0.7430)	mem 24308MB
[2025-01-18 18:06:18 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][290/312]	eta 0:00:13 lr 0.003082	time 0.5917 (0.6119)	model_time 0.5913 (0.6060)	loss 3.0907 (3.5125)	grad_norm 0.9595 (1.5705/0.7355)	mem 24308MB
[2025-01-18 18:06:24 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][300/312]	eta 0:00:07 lr 0.003082	time 0.5669 (0.6110)	model_time 0.5668 (0.6053)	loss 3.9548 (3.5157)	grad_norm 1.0547 (1.5563/0.7302)	mem 24308MB
[2025-01-18 18:06:30 internimage_s_1k_224] (main.py 510): INFO Train: [95/300][310/312]	eta 0:00:01 lr 0.003081	time 0.5704 (0.6100)	model_time 0.5702 (0.6045)	loss 4.1882 (3.5178)	grad_norm 2.0723 (1.5504/0.7257)	mem 24308MB
[2025-01-18 18:06:30 internimage_s_1k_224] (main.py 519): INFO EPOCH 95 training takes 0:03:10
[2025-01-18 18:06:30 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_95.pth saving......
[2025-01-18 18:06:32 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_95.pth saved !!!
[2025-01-18 18:06:39 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.078 (7.078)	Loss 0.9092 (0.9092)	Acc@1 80.811 (80.811)	Acc@5 96.045 (96.045)	Mem 24308MB
[2025-01-18 18:06:43 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.981)	Loss 1.2426 (1.0471)	Acc@1 72.339 (77.040)	Acc@5 91.504 (93.945)	Mem 24308MB
[2025-01-18 18:06:43 internimage_s_1k_224] (main.py 575): INFO [Epoch:95] * Acc@1 76.917 Acc@5 93.926
[2025-01-18 18:06:43 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.9%
[2025-01-18 18:06:43 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.03%
[2025-01-18 18:06:51 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.267 (8.267)	Loss 0.8325 (0.8325)	Acc@1 79.492 (79.492)	Acc@5 95.410 (95.410)	Mem 24308MB
[2025-01-18 18:06:56 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.128)	Loss 1.2736 (1.0099)	Acc@1 68.677 (75.544)	Acc@5 89.771 (93.033)	Mem 24308MB
[2025-01-18 18:06:56 internimage_s_1k_224] (main.py 575): INFO [Epoch:95] * Acc@1 75.502 Acc@5 93.106
[2025-01-18 18:06:56 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 75.5%
[2025-01-18 18:06:56 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 18:06:58 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 18:06:58 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 75.50%
[2025-01-18 18:07:00 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][0/312]	eta 0:11:03 lr 0.003081	time 2.1264 (2.1264)	model_time 0.6048 (0.6048)	loss 4.2737 (4.2737)	grad_norm 0.9247 (0.9247/0.0000)	mem 24308MB
[2025-01-18 18:07:06 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][10/312]	eta 0:03:38 lr 0.003080	time 0.5838 (0.7229)	model_time 0.5836 (0.5843)	loss 3.9404 (3.6145)	grad_norm 2.2894 (1.5536/0.5980)	mem 24308MB
[2025-01-18 18:07:12 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][20/312]	eta 0:03:12 lr 0.003080	time 0.5967 (0.6595)	model_time 0.5965 (0.5868)	loss 4.2162 (3.7243)	grad_norm 2.9299 (1.6799/0.6950)	mem 24308MB
[2025-01-18 18:07:18 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][30/312]	eta 0:02:59 lr 0.003079	time 0.5847 (0.6375)	model_time 0.5846 (0.5882)	loss 2.5776 (3.5705)	grad_norm 0.9981 (1.5780/0.6311)	mem 24308MB
[2025-01-18 18:07:24 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][40/312]	eta 0:02:52 lr 0.003079	time 0.8008 (0.6332)	model_time 0.8006 (0.5958)	loss 3.9533 (3.5819)	grad_norm 0.8070 (1.5639/0.6331)	mem 24308MB
[2025-01-18 18:07:30 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][50/312]	eta 0:02:44 lr 0.003078	time 0.5814 (0.6282)	model_time 0.5812 (0.5981)	loss 3.1380 (3.6122)	grad_norm 1.0376 (1.6274/0.6954)	mem 24308MB
[2025-01-18 18:07:37 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][60/312]	eta 0:02:38 lr 0.003078	time 0.5728 (0.6293)	model_time 0.5727 (0.6040)	loss 3.2363 (3.5824)	grad_norm 1.7747 (1.6011/0.6668)	mem 24308MB
[2025-01-18 18:07:43 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][70/312]	eta 0:02:32 lr 0.003077	time 0.5927 (0.6288)	model_time 0.5923 (0.6070)	loss 3.3209 (3.5806)	grad_norm 2.0741 (1.6010/0.6665)	mem 24308MB
[2025-01-18 18:07:49 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][80/312]	eta 0:02:25 lr 0.003076	time 0.5818 (0.6281)	model_time 0.5816 (0.6090)	loss 3.5686 (3.5537)	grad_norm 1.7571 (1.6545/0.6573)	mem 24308MB
[2025-01-18 18:07:55 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][90/312]	eta 0:02:19 lr 0.003076	time 0.5906 (0.6271)	model_time 0.5902 (0.6101)	loss 2.9054 (3.5263)	grad_norm 1.8891 (1.6679/0.6776)	mem 24308MB
[2025-01-18 18:08:01 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][100/312]	eta 0:02:12 lr 0.003075	time 0.5944 (0.6239)	model_time 0.5940 (0.6085)	loss 3.7268 (3.5312)	grad_norm 1.0351 (1.6774/0.7017)	mem 24308MB
[2025-01-18 18:08:07 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][110/312]	eta 0:02:05 lr 0.003075	time 0.5773 (0.6210)	model_time 0.5771 (0.6070)	loss 4.0991 (3.5562)	grad_norm 1.2957 (1.6835/0.6978)	mem 24308MB
[2025-01-18 18:08:13 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][120/312]	eta 0:01:58 lr 0.003074	time 0.5765 (0.6192)	model_time 0.5760 (0.6063)	loss 2.7583 (3.5433)	grad_norm 1.3265 (1.6436/0.6878)	mem 24308MB
[2025-01-18 18:08:19 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][130/312]	eta 0:01:52 lr 0.003074	time 0.5957 (0.6169)	model_time 0.5956 (0.6049)	loss 3.1434 (3.5274)	grad_norm 2.0839 (1.6235/0.6801)	mem 24308MB
[2025-01-18 18:08:25 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][140/312]	eta 0:01:46 lr 0.003073	time 0.6059 (0.6169)	model_time 0.6057 (0.6058)	loss 2.5914 (3.5277)	grad_norm 0.8261 (1.6090/0.6684)	mem 24308MB
[2025-01-18 18:08:31 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][150/312]	eta 0:01:39 lr 0.003073	time 0.5932 (0.6150)	model_time 0.5930 (0.6045)	loss 3.9109 (3.5485)	grad_norm 1.0441 (1.5847/0.6663)	mem 24308MB
[2025-01-18 18:08:37 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][160/312]	eta 0:01:33 lr 0.003072	time 0.6854 (0.6136)	model_time 0.6852 (0.6038)	loss 4.4071 (3.5583)	grad_norm 2.4825 (1.5977/0.6828)	mem 24308MB
[2025-01-18 18:08:43 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][170/312]	eta 0:01:27 lr 0.003071	time 0.5921 (0.6133)	model_time 0.5917 (0.6040)	loss 4.0510 (3.5596)	grad_norm 1.3329 (1.5878/0.6661)	mem 24308MB
[2025-01-18 18:08:49 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][180/312]	eta 0:01:21 lr 0.003071	time 0.5696 (0.6146)	model_time 0.5691 (0.6059)	loss 3.7751 (3.5722)	grad_norm 1.5874 (1.5742/0.6548)	mem 24308MB
[2025-01-18 18:08:56 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][190/312]	eta 0:01:15 lr 0.003070	time 0.5798 (0.6148)	model_time 0.5797 (0.6065)	loss 2.6557 (3.5701)	grad_norm 1.4136 (1.5719/0.6435)	mem 24308MB
[2025-01-18 18:09:02 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][200/312]	eta 0:01:08 lr 0.003070	time 0.5781 (0.6150)	model_time 0.5777 (0.6071)	loss 3.9739 (3.5723)	grad_norm 0.7588 (1.5617/0.6369)	mem 24308MB
[2025-01-18 18:09:08 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][210/312]	eta 0:01:02 lr 0.003069	time 0.6999 (0.6156)	model_time 0.6997 (0.6081)	loss 3.7389 (3.5733)	grad_norm 1.2406 (1.5616/0.6334)	mem 24308MB
[2025-01-18 18:09:14 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][220/312]	eta 0:00:56 lr 0.003069	time 0.5816 (0.6148)	model_time 0.5814 (0.6075)	loss 4.1311 (3.5749)	grad_norm 1.4685 (1.5745/0.6339)	mem 24308MB
[2025-01-18 18:09:20 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][230/312]	eta 0:00:50 lr 0.003068	time 0.5947 (0.6139)	model_time 0.5945 (0.6070)	loss 3.1449 (3.5693)	grad_norm 1.9873 (1.5753/0.6309)	mem 24308MB
[2025-01-18 18:09:26 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][240/312]	eta 0:00:44 lr 0.003067	time 0.5866 (0.6131)	model_time 0.5862 (0.6065)	loss 3.3259 (3.5761)	grad_norm 2.5699 (1.5734/0.6341)	mem 24308MB
[2025-01-18 18:09:32 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][250/312]	eta 0:00:37 lr 0.003067	time 0.5860 (0.6123)	model_time 0.5856 (0.6058)	loss 3.1810 (3.5750)	grad_norm 2.1278 (1.5713/0.6334)	mem 24308MB
[2025-01-18 18:09:38 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][260/312]	eta 0:00:31 lr 0.003066	time 0.5745 (0.6116)	model_time 0.5743 (0.6054)	loss 2.8449 (3.5804)	grad_norm 0.7750 (1.5814/0.6389)	mem 24308MB
[2025-01-18 18:09:44 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][270/312]	eta 0:00:25 lr 0.003066	time 0.6023 (0.6106)	model_time 0.6019 (0.6046)	loss 2.6142 (3.5661)	grad_norm 2.2915 (1.5705/0.6357)	mem 24308MB
[2025-01-18 18:09:50 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][280/312]	eta 0:00:19 lr 0.003065	time 0.5782 (0.6101)	model_time 0.5780 (0.6043)	loss 4.2816 (3.5555)	grad_norm 1.3247 (1.5567/0.6316)	mem 24308MB
[2025-01-18 18:09:56 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][290/312]	eta 0:00:13 lr 0.003065	time 0.6449 (0.6107)	model_time 0.6447 (0.6051)	loss 3.5212 (3.5515)	grad_norm 1.7035 (1.5552/0.6273)	mem 24308MB
[2025-01-18 18:10:02 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][300/312]	eta 0:00:07 lr 0.003064	time 0.5617 (0.6106)	model_time 0.5616 (0.6052)	loss 3.8800 (3.5593)	grad_norm 1.6748 (1.5678/0.6254)	mem 24308MB
[2025-01-18 18:10:08 internimage_s_1k_224] (main.py 510): INFO Train: [96/300][310/312]	eta 0:00:01 lr 0.003063	time 0.5692 (0.6106)	model_time 0.5690 (0.6053)	loss 3.4058 (3.5604)	grad_norm 2.3574 (1.5690/0.6184)	mem 24308MB
[2025-01-18 18:10:09 internimage_s_1k_224] (main.py 519): INFO EPOCH 96 training takes 0:03:10
[2025-01-18 18:10:09 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_96.pth saving......
[2025-01-18 18:10:10 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_96.pth saved !!!
[2025-01-18 18:10:18 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.305 (7.305)	Loss 0.9371 (0.9371)	Acc@1 80.151 (80.151)	Acc@5 95.605 (95.605)	Mem 24308MB
[2025-01-18 18:10:21 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.965)	Loss 1.2582 (1.0701)	Acc@1 71.362 (76.529)	Acc@5 91.016 (93.699)	Mem 24308MB
[2025-01-18 18:10:21 internimage_s_1k_224] (main.py 575): INFO [Epoch:96] * Acc@1 76.554 Acc@5 93.780
[2025-01-18 18:10:21 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.6%
[2025-01-18 18:10:21 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.03%
[2025-01-18 18:10:30 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.304 (8.304)	Loss 0.8268 (0.8268)	Acc@1 79.590 (79.590)	Acc@5 95.508 (95.508)	Mem 24308MB
[2025-01-18 18:10:34 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.132)	Loss 1.2643 (1.0034)	Acc@1 68.896 (75.657)	Acc@5 89.917 (93.146)	Mem 24308MB
[2025-01-18 18:10:34 internimage_s_1k_224] (main.py 575): INFO [Epoch:96] * Acc@1 75.614 Acc@5 93.214
[2025-01-18 18:10:34 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 75.6%
[2025-01-18 18:10:34 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 18:10:36 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 18:10:36 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 75.61%
[2025-01-18 18:10:39 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][0/312]	eta 0:11:57 lr 0.003063	time 2.2984 (2.2984)	model_time 0.6091 (0.6091)	loss 3.4590 (3.4590)	grad_norm 1.5216 (1.5216/0.0000)	mem 24308MB
[2025-01-18 18:10:45 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][10/312]	eta 0:03:54 lr 0.003063	time 0.6613 (0.7777)	model_time 0.6609 (0.6238)	loss 3.0951 (3.4212)	grad_norm 1.0700 (1.3764/0.3507)	mem 24308MB
[2025-01-18 18:10:51 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][20/312]	eta 0:03:23 lr 0.003062	time 0.6155 (0.6958)	model_time 0.6153 (0.6150)	loss 2.7294 (3.4011)	grad_norm 2.0253 (1.4323/0.4374)	mem 24308MB
[2025-01-18 18:10:57 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][30/312]	eta 0:03:08 lr 0.003062	time 0.5769 (0.6676)	model_time 0.5767 (0.6127)	loss 3.5926 (3.3997)	grad_norm 1.4159 (1.5007/0.4673)	mem 24308MB
[2025-01-18 18:11:03 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][40/312]	eta 0:02:56 lr 0.003061	time 0.5809 (0.6487)	model_time 0.5807 (0.6071)	loss 2.6120 (3.4777)	grad_norm 1.2302 (1.6256/0.5481)	mem 24308MB
[2025-01-18 18:11:09 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][50/312]	eta 0:02:47 lr 0.003061	time 0.5905 (0.6388)	model_time 0.5903 (0.6053)	loss 3.3671 (3.4818)	grad_norm 3.1206 (1.6553/0.5928)	mem 24308MB
[2025-01-18 18:11:15 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][60/312]	eta 0:02:38 lr 0.003060	time 0.5865 (0.6306)	model_time 0.5863 (0.6026)	loss 3.1859 (3.5164)	grad_norm 0.7819 (1.6295/0.5934)	mem 24308MB
[2025-01-18 18:11:21 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][70/312]	eta 0:02:30 lr 0.003059	time 0.5795 (0.6238)	model_time 0.5793 (0.5997)	loss 2.8277 (3.5190)	grad_norm 0.8410 (1.5907/0.5827)	mem 24308MB
[2025-01-18 18:11:26 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][80/312]	eta 0:02:23 lr 0.003059	time 0.5843 (0.6191)	model_time 0.5842 (0.5980)	loss 3.7258 (3.5221)	grad_norm 1.2245 (1.5702/0.5620)	mem 24308MB
[2025-01-18 18:11:32 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][90/312]	eta 0:02:16 lr 0.003058	time 0.5849 (0.6155)	model_time 0.5848 (0.5966)	loss 2.9072 (3.5039)	grad_norm 2.1105 (1.5232/0.5673)	mem 24308MB
[2025-01-18 18:11:38 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][100/312]	eta 0:02:10 lr 0.003058	time 0.6640 (0.6160)	model_time 0.6637 (0.5990)	loss 2.6258 (3.5179)	grad_norm 2.2871 (1.6166/0.6912)	mem 24308MB
[2025-01-18 18:11:45 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][110/312]	eta 0:02:05 lr 0.003057	time 0.6580 (0.6191)	model_time 0.6578 (0.6035)	loss 2.6349 (3.5058)	grad_norm 1.2301 (1.5958/0.6759)	mem 24308MB
[2025-01-18 18:11:51 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][120/312]	eta 0:01:58 lr 0.003057	time 0.5872 (0.6188)	model_time 0.5870 (0.6045)	loss 3.0417 (3.5066)	grad_norm 0.8827 (1.5645/0.6635)	mem 24308MB
[2025-01-18 18:11:57 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][130/312]	eta 0:01:52 lr 0.003056	time 0.5858 (0.6192)	model_time 0.5855 (0.6060)	loss 3.9956 (3.5157)	grad_norm 1.2890 (1.5621/0.6625)	mem 24308MB
[2025-01-18 18:12:04 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][140/312]	eta 0:01:46 lr 0.003055	time 0.5772 (0.6192)	model_time 0.5771 (0.6069)	loss 4.1110 (3.5087)	grad_norm 1.1875 (1.5387/0.6511)	mem 24308MB
[2025-01-18 18:12:09 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][150/312]	eta 0:01:40 lr 0.003055	time 0.5770 (0.6176)	model_time 0.5758 (0.6061)	loss 3.2770 (3.4935)	grad_norm 1.2230 (1.5303/0.6367)	mem 24308MB
[2025-01-18 18:12:16 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][160/312]	eta 0:01:33 lr 0.003054	time 0.5909 (0.6176)	model_time 0.5907 (0.6068)	loss 3.5611 (3.5094)	grad_norm 1.1467 (1.5299/0.6282)	mem 24308MB
[2025-01-18 18:12:22 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][170/312]	eta 0:01:27 lr 0.003054	time 0.5789 (0.6166)	model_time 0.5788 (0.6064)	loss 3.5798 (3.5144)	grad_norm 0.9083 (1.5602/0.6608)	mem 24308MB
[2025-01-18 18:12:28 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][180/312]	eta 0:01:21 lr 0.003053	time 0.5834 (0.6148)	model_time 0.5829 (0.6051)	loss 3.2164 (3.5232)	grad_norm 2.0365 (1.5561/0.6460)	mem 24308MB
[2025-01-18 18:12:33 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][190/312]	eta 0:01:14 lr 0.003053	time 0.5818 (0.6132)	model_time 0.5814 (0.6041)	loss 3.4061 (3.5035)	grad_norm 2.5293 (1.5478/0.6432)	mem 24308MB
[2025-01-18 18:12:39 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][200/312]	eta 0:01:08 lr 0.003052	time 0.5892 (0.6121)	model_time 0.5889 (0.6033)	loss 3.8800 (3.5055)	grad_norm 0.8369 (1.5464/0.6324)	mem 24308MB
[2025-01-18 18:12:45 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][210/312]	eta 0:01:02 lr 0.003051	time 0.5796 (0.6111)	model_time 0.5795 (0.6028)	loss 3.5660 (3.5086)	grad_norm 1.6952 (1.5715/0.6613)	mem 24308MB
[2025-01-18 18:12:51 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][220/312]	eta 0:00:56 lr 0.003051	time 0.5912 (0.6114)	model_time 0.5910 (0.6034)	loss 4.1833 (3.5191)	grad_norm 1.0351 (1.5664/0.6524)	mem 24308MB
[2025-01-18 18:12:58 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][230/312]	eta 0:00:50 lr 0.003050	time 0.5789 (0.6130)	model_time 0.5788 (0.6054)	loss 2.7785 (3.5232)	grad_norm 1.4123 (1.5687/0.6493)	mem 24308MB
[2025-01-18 18:13:04 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][240/312]	eta 0:00:44 lr 0.003050	time 0.5737 (0.6140)	model_time 0.5735 (0.6067)	loss 4.1029 (3.5226)	grad_norm 1.1836 (1.5525/0.6436)	mem 24308MB
[2025-01-18 18:13:10 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][250/312]	eta 0:00:38 lr 0.003049	time 0.5742 (0.6143)	model_time 0.5741 (0.6073)	loss 3.7995 (3.5114)	grad_norm 2.5242 (1.5528/0.6417)	mem 24308MB
[2025-01-18 18:13:16 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][260/312]	eta 0:00:31 lr 0.003049	time 0.5809 (0.6138)	model_time 0.5807 (0.6070)	loss 2.4962 (3.5013)	grad_norm 0.9072 (1.5460/0.6409)	mem 24308MB
[2025-01-18 18:13:22 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][270/312]	eta 0:00:25 lr 0.003048	time 0.6159 (0.6134)	model_time 0.6154 (0.6069)	loss 4.0398 (3.4947)	grad_norm 1.1635 (1.5231/0.6409)	mem 24308MB
[2025-01-18 18:13:29 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][280/312]	eta 0:00:19 lr 0.003048	time 0.6617 (0.6131)	model_time 0.6616 (0.6067)	loss 3.7925 (3.4966)	grad_norm 1.3398 (1.5341/0.6508)	mem 24308MB
[2025-01-18 18:13:34 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][290/312]	eta 0:00:13 lr 0.003047	time 0.5796 (0.6125)	model_time 0.5794 (0.6063)	loss 3.7965 (3.4977)	grad_norm 1.7508 (1.5331/0.6455)	mem 24308MB
[2025-01-18 18:13:40 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][300/312]	eta 0:00:07 lr 0.003046	time 0.5685 (0.6114)	model_time 0.5684 (0.6055)	loss 3.1092 (3.4908)	grad_norm 2.5676 (1.5317/0.6485)	mem 24308MB
[2025-01-18 18:13:46 internimage_s_1k_224] (main.py 510): INFO Train: [97/300][310/312]	eta 0:00:01 lr 0.003046	time 0.5692 (0.6101)	model_time 0.5691 (0.6044)	loss 4.2334 (3.4837)	grad_norm 2.8546 (1.5407/0.6589)	mem 24308MB
[2025-01-18 18:13:47 internimage_s_1k_224] (main.py 519): INFO EPOCH 97 training takes 0:03:10
[2025-01-18 18:13:47 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_97.pth saving......
[2025-01-18 18:13:48 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_97.pth saved !!!
[2025-01-18 18:13:56 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.325 (7.325)	Loss 0.9073 (0.9073)	Acc@1 80.273 (80.273)	Acc@5 95.801 (95.801)	Mem 24308MB
[2025-01-18 18:13:59 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.970)	Loss 1.2559 (1.0837)	Acc@1 73.413 (76.922)	Acc@5 91.357 (93.819)	Mem 24308MB
[2025-01-18 18:13:59 internimage_s_1k_224] (main.py 575): INFO [Epoch:97] * Acc@1 76.795 Acc@5 93.814
[2025-01-18 18:13:59 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 76.8%
[2025-01-18 18:13:59 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.03%
[2025-01-18 18:14:08 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.282 (8.282)	Loss 0.8211 (0.8211)	Acc@1 79.834 (79.834)	Acc@5 95.630 (95.630)	Mem 24308MB
[2025-01-18 18:14:12 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.114)	Loss 1.2554 (0.9970)	Acc@1 68.994 (75.783)	Acc@5 89.941 (93.200)	Mem 24308MB
[2025-01-18 18:14:12 internimage_s_1k_224] (main.py 575): INFO [Epoch:97] * Acc@1 75.746 Acc@5 93.262
[2025-01-18 18:14:12 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 75.7%
[2025-01-18 18:14:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 18:14:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 18:14:14 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 75.75%
[2025-01-18 18:14:16 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][0/312]	eta 0:11:27 lr 0.003046	time 2.2048 (2.2048)	model_time 0.5922 (0.5922)	loss 3.7114 (3.7114)	grad_norm 2.1635 (2.1635/0.0000)	mem 24308MB
[2025-01-18 18:14:22 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][10/312]	eta 0:03:42 lr 0.003045	time 0.5852 (0.7375)	model_time 0.5851 (0.5906)	loss 3.4438 (3.4996)	grad_norm 1.2468 (1.5183/0.4275)	mem 24308MB
[2025-01-18 18:14:28 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][20/312]	eta 0:03:16 lr 0.003045	time 0.5809 (0.6717)	model_time 0.5807 (0.5946)	loss 2.7962 (3.5533)	grad_norm 1.2377 (1.4440/0.3829)	mem 24308MB
[2025-01-18 18:14:34 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][30/312]	eta 0:03:03 lr 0.003044	time 0.5943 (0.6492)	model_time 0.5941 (0.5969)	loss 3.6828 (3.5582)	grad_norm 2.5972 (1.5979/0.6413)	mem 24308MB
[2025-01-18 18:14:40 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][40/312]	eta 0:02:55 lr 0.003043	time 0.6684 (0.6445)	model_time 0.6682 (0.6048)	loss 3.4510 (3.5445)	grad_norm 1.2494 (1.5805/0.6799)	mem 24308MB
[2025-01-18 18:14:47 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][50/312]	eta 0:02:49 lr 0.003043	time 0.5872 (0.6458)	model_time 0.5870 (0.6138)	loss 3.4504 (3.5654)	grad_norm 0.9865 (1.5386/0.6325)	mem 24308MB
[2025-01-18 18:14:53 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][60/312]	eta 0:02:41 lr 0.003042	time 0.6682 (0.6403)	model_time 0.6680 (0.6136)	loss 2.8659 (3.5390)	grad_norm 1.3996 (1.5469/0.6486)	mem 24308MB
[2025-01-18 18:14:59 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][70/312]	eta 0:02:34 lr 0.003042	time 0.6644 (0.6366)	model_time 0.6643 (0.6136)	loss 2.1804 (3.5134)	grad_norm 0.7610 (1.5018/0.6175)	mem 24308MB
[2025-01-18 18:15:05 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][80/312]	eta 0:02:26 lr 0.003041	time 0.5723 (0.6329)	model_time 0.5721 (0.6127)	loss 4.2620 (3.5630)	grad_norm 2.1634 (1.5587/0.6657)	mem 24308MB
[2025-01-18 18:15:11 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][90/312]	eta 0:02:19 lr 0.003041	time 0.5905 (0.6291)	model_time 0.5901 (0.6111)	loss 2.3895 (3.5710)	grad_norm 1.3908 (1.5567/0.6464)	mem 24308MB
[2025-01-18 18:15:17 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][100/312]	eta 0:02:12 lr 0.003040	time 0.5795 (0.6261)	model_time 0.5794 (0.6098)	loss 2.8462 (3.5472)	grad_norm 2.9758 (1.5471/0.6494)	mem 24308MB
[2025-01-18 18:15:23 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][110/312]	eta 0:02:05 lr 0.003039	time 0.5934 (0.6226)	model_time 0.5933 (0.6077)	loss 2.3910 (3.5091)	grad_norm 1.8537 (1.5769/0.6572)	mem 24308MB
[2025-01-18 18:15:29 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][120/312]	eta 0:01:58 lr 0.003039	time 0.5816 (0.6197)	model_time 0.5812 (0.6061)	loss 4.1778 (3.5114)	grad_norm 2.2206 (1.5922/0.6653)	mem 24308MB
[2025-01-18 18:15:35 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][130/312]	eta 0:01:52 lr 0.003038	time 0.5745 (0.6171)	model_time 0.5743 (0.6044)	loss 2.5262 (3.5021)	grad_norm 1.3124 (1.5716/0.6566)	mem 24308MB
[2025-01-18 18:15:41 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][140/312]	eta 0:01:45 lr 0.003038	time 0.5767 (0.6155)	model_time 0.5763 (0.6037)	loss 3.6976 (3.5123)	grad_norm 0.9298 (1.5768/0.6436)	mem 24308MB
[2025-01-18 18:15:47 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][150/312]	eta 0:01:39 lr 0.003037	time 0.5739 (0.6151)	model_time 0.5737 (0.6041)	loss 3.9791 (3.5216)	grad_norm 0.7555 (1.5804/0.6444)	mem 24308MB
[2025-01-18 18:15:53 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][160/312]	eta 0:01:33 lr 0.003037	time 0.6560 (0.6163)	model_time 0.6559 (0.6060)	loss 3.4121 (3.5184)	grad_norm 0.9501 (1.5867/0.6452)	mem 24308MB
[2025-01-18 18:15:59 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][170/312]	eta 0:01:27 lr 0.003036	time 0.5727 (0.6164)	model_time 0.5725 (0.6067)	loss 3.7507 (3.5138)	grad_norm 2.5445 (1.5972/0.6529)	mem 24308MB
[2025-01-18 18:16:06 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][180/312]	eta 0:01:21 lr 0.003035	time 0.6707 (0.6166)	model_time 0.6703 (0.6074)	loss 3.6239 (3.5226)	grad_norm 1.0239 (1.5788/0.6448)	mem 24308MB
[2025-01-18 18:16:12 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][190/312]	eta 0:01:15 lr 0.003035	time 0.5894 (0.6163)	model_time 0.5892 (0.6076)	loss 3.8643 (3.5290)	grad_norm 1.4457 (1.5657/0.6355)	mem 24308MB
[2025-01-18 18:16:18 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][200/312]	eta 0:01:09 lr 0.003034	time 0.5699 (0.6162)	model_time 0.5695 (0.6078)	loss 3.0750 (3.5322)	grad_norm 1.5321 (1.5819/0.6322)	mem 24308MB
[2025-01-18 18:16:24 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][210/312]	eta 0:01:02 lr 0.003034	time 0.5779 (0.6151)	model_time 0.5774 (0.6071)	loss 3.5150 (3.5318)	grad_norm 0.8624 (1.5852/0.6252)	mem 24308MB
[2025-01-18 18:16:30 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][220/312]	eta 0:00:56 lr 0.003033	time 0.5809 (0.6142)	model_time 0.5808 (0.6065)	loss 3.5236 (3.5397)	grad_norm 1.4433 (1.5647/0.6214)	mem 24308MB
[2025-01-18 18:16:36 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][230/312]	eta 0:00:50 lr 0.003033	time 0.5745 (0.6135)	model_time 0.5743 (0.6062)	loss 3.4611 (3.5478)	grad_norm 0.8328 (1.5568/0.6193)	mem 24308MB
[2025-01-18 18:16:41 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][240/312]	eta 0:00:44 lr 0.003032	time 0.5833 (0.6123)	model_time 0.5831 (0.6052)	loss 3.3081 (3.5624)	grad_norm 1.1831 (1.5592/0.6202)	mem 24308MB
[2025-01-18 18:16:47 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][250/312]	eta 0:00:37 lr 0.003031	time 0.5936 (0.6112)	model_time 0.5934 (0.6044)	loss 4.0352 (3.5682)	grad_norm 1.1426 (1.5825/0.6430)	mem 24308MB
[2025-01-18 18:16:53 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][260/312]	eta 0:00:31 lr 0.003031	time 0.5729 (0.6104)	model_time 0.5725 (0.6039)	loss 3.9571 (3.5621)	grad_norm 1.0227 (1.5738/0.6364)	mem 24308MB
[2025-01-18 18:16:59 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][270/312]	eta 0:00:25 lr 0.003030	time 0.5849 (0.6106)	model_time 0.5845 (0.6043)	loss 3.8712 (3.5646)	grad_norm 1.2311 (1.5680/0.6261)	mem 24308MB
[2025-01-18 18:17:06 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][280/312]	eta 0:00:19 lr 0.003030	time 0.7727 (0.6119)	model_time 0.7725 (0.6058)	loss 4.0066 (3.5679)	grad_norm 1.2109 (1.5514/0.6226)	mem 24308MB
[2025-01-18 18:17:12 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][290/312]	eta 0:00:13 lr 0.003029	time 0.6580 (0.6123)	model_time 0.6576 (0.6064)	loss 3.8689 (3.5770)	grad_norm 4.1020 (1.5708/0.6539)	mem 24308MB
[2025-01-18 18:17:18 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][300/312]	eta 0:00:07 lr 0.003029	time 0.6417 (0.6121)	model_time 0.6416 (0.6064)	loss 3.5191 (3.5772)	grad_norm 1.9033 (1.5912/0.6643)	mem 24308MB
[2025-01-18 18:17:24 internimage_s_1k_224] (main.py 510): INFO Train: [98/300][310/312]	eta 0:00:01 lr 0.003028	time 0.6471 (0.6123)	model_time 0.6470 (0.6067)	loss 2.9070 (3.5746)	grad_norm 1.1158 (1.5783/0.6671)	mem 24308MB
[2025-01-18 18:17:25 internimage_s_1k_224] (main.py 519): INFO EPOCH 98 training takes 0:03:10
[2025-01-18 18:17:25 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_98.pth saving......
[2025-01-18 18:17:27 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_98.pth saved !!!
[2025-01-18 18:17:34 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.117 (7.117)	Loss 0.8720 (0.8720)	Acc@1 80.566 (80.566)	Acc@5 96.069 (96.069)	Mem 24308MB
[2025-01-18 18:17:37 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.951)	Loss 1.1976 (1.0280)	Acc@1 72.729 (77.040)	Acc@5 91.724 (93.908)	Mem 24308MB
[2025-01-18 18:17:38 internimage_s_1k_224] (main.py 575): INFO [Epoch:98] * Acc@1 76.957 Acc@5 93.984
[2025-01-18 18:17:38 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.0%
[2025-01-18 18:17:38 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.03%
[2025-01-18 18:17:46 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.281 (8.281)	Loss 0.8157 (0.8157)	Acc@1 79.858 (79.858)	Acc@5 95.703 (95.703)	Mem 24308MB
[2025-01-18 18:17:50 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.126)	Loss 1.2475 (0.9910)	Acc@1 69.336 (75.961)	Acc@5 90.088 (93.286)	Mem 24308MB
[2025-01-18 18:17:50 internimage_s_1k_224] (main.py 575): INFO [Epoch:98] * Acc@1 75.914 Acc@5 93.344
[2025-01-18 18:17:50 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 75.9%
[2025-01-18 18:17:50 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 18:17:52 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 18:17:52 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 75.91%
[2025-01-18 18:17:55 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][0/312]	eta 0:11:59 lr 0.003028	time 2.3057 (2.3057)	model_time 0.6098 (0.6098)	loss 3.6296 (3.6296)	grad_norm 0.8198 (0.8198/0.0000)	mem 24308MB
[2025-01-18 18:18:01 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][10/312]	eta 0:03:49 lr 0.003027	time 0.5929 (0.7585)	model_time 0.5928 (0.6041)	loss 3.4145 (3.3846)	grad_norm 1.4812 (1.1897/0.4547)	mem 24308MB
[2025-01-18 18:18:07 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][20/312]	eta 0:03:19 lr 0.003027	time 0.5976 (0.6833)	model_time 0.5974 (0.6023)	loss 3.7764 (3.4948)	grad_norm 1.2164 (1.4157/0.7374)	mem 24308MB
[2025-01-18 18:18:13 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][30/312]	eta 0:03:04 lr 0.003026	time 0.6708 (0.6554)	model_time 0.6703 (0.6004)	loss 2.8010 (3.5361)	grad_norm 0.8387 (1.5076/0.7108)	mem 24308MB
[2025-01-18 18:18:19 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][40/312]	eta 0:02:53 lr 0.003026	time 0.5830 (0.6394)	model_time 0.5828 (0.5978)	loss 4.2595 (3.5128)	grad_norm 2.0294 (1.4945/0.6390)	mem 24308MB
[2025-01-18 18:18:24 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][50/312]	eta 0:02:45 lr 0.003025	time 0.5749 (0.6311)	model_time 0.5744 (0.5975)	loss 2.2500 (3.5180)	grad_norm 1.8431 (1.5785/0.6833)	mem 24308MB
[2025-01-18 18:18:30 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][60/312]	eta 0:02:37 lr 0.003024	time 0.6015 (0.6239)	model_time 0.6010 (0.5958)	loss 3.8518 (3.4928)	grad_norm 0.7155 (1.5318/0.6759)	mem 24308MB
[2025-01-18 18:18:36 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][70/312]	eta 0:02:29 lr 0.003024	time 0.5911 (0.6188)	model_time 0.5910 (0.5946)	loss 3.8906 (3.4660)	grad_norm 2.2885 (1.5067/0.6522)	mem 24308MB
[2025-01-18 18:18:43 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][80/312]	eta 0:02:23 lr 0.003023	time 0.5809 (0.6201)	model_time 0.5808 (0.5988)	loss 2.9710 (3.4560)	grad_norm 2.8657 (1.5333/0.6730)	mem 24308MB
[2025-01-18 18:18:49 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][90/312]	eta 0:02:17 lr 0.003023	time 0.5912 (0.6210)	model_time 0.5911 (0.6019)	loss 3.5021 (3.4703)	grad_norm 0.5864 (1.4869/0.6596)	mem 24308MB
[2025-01-18 18:18:55 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][100/312]	eta 0:02:11 lr 0.003022	time 0.6547 (0.6215)	model_time 0.6543 (0.6042)	loss 3.3983 (3.4620)	grad_norm 1.8826 (1.4775/0.6363)	mem 24308MB
[2025-01-18 18:19:01 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][110/312]	eta 0:02:05 lr 0.003022	time 0.5804 (0.6202)	model_time 0.5800 (0.6044)	loss 3.6089 (3.4503)	grad_norm 1.6510 (1.4583/0.6190)	mem 24308MB
[2025-01-18 18:19:07 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][120/312]	eta 0:01:59 lr 0.003021	time 0.5794 (0.6211)	model_time 0.5789 (0.6066)	loss 2.7007 (3.4377)	grad_norm 1.2948 (1.5081/0.6430)	mem 24308MB
[2025-01-18 18:19:14 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][130/312]	eta 0:01:52 lr 0.003020	time 0.5898 (0.6208)	model_time 0.5893 (0.6074)	loss 4.0280 (3.4539)	grad_norm 0.9301 (1.5222/0.6502)	mem 24308MB
[2025-01-18 18:19:20 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][140/312]	eta 0:01:46 lr 0.003020	time 0.5826 (0.6196)	model_time 0.5824 (0.6072)	loss 3.6893 (3.4548)	grad_norm 3.0419 (1.5281/0.6584)	mem 24308MB
[2025-01-18 18:19:26 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][150/312]	eta 0:01:40 lr 0.003019	time 0.5972 (0.6176)	model_time 0.5971 (0.6059)	loss 4.0940 (3.4589)	grad_norm 1.3710 (1.5569/0.6612)	mem 24308MB
[2025-01-18 18:19:32 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][160/312]	eta 0:01:33 lr 0.003019	time 0.5866 (0.6163)	model_time 0.5865 (0.6054)	loss 3.6506 (3.4862)	grad_norm 0.9511 (1.5378/0.6491)	mem 24308MB
[2025-01-18 18:19:38 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][170/312]	eta 0:01:27 lr 0.003018	time 0.5791 (0.6152)	model_time 0.5787 (0.6049)	loss 3.7127 (3.4979)	grad_norm 2.4298 (1.5357/0.6394)	mem 24308MB
[2025-01-18 18:19:43 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][180/312]	eta 0:01:20 lr 0.003018	time 0.5973 (0.6136)	model_time 0.5969 (0.6038)	loss 4.1273 (3.5066)	grad_norm 1.6877 (1.5352/0.6395)	mem 24308MB
[2025-01-18 18:19:49 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][190/312]	eta 0:01:14 lr 0.003017	time 0.6011 (0.6123)	model_time 0.6007 (0.6029)	loss 3.5167 (3.5045)	grad_norm 1.3904 (1.5515/0.6355)	mem 24308MB
[2025-01-18 18:19:55 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][200/312]	eta 0:01:08 lr 0.003016	time 0.6922 (0.6125)	model_time 0.6918 (0.6035)	loss 4.0993 (3.5134)	grad_norm 0.7962 (1.5425/0.6270)	mem 24308MB
[2025-01-18 18:20:02 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][210/312]	eta 0:01:02 lr 0.003016	time 0.5748 (0.6135)	model_time 0.5747 (0.6050)	loss 3.2304 (3.5206)	grad_norm 2.6486 (1.5472/0.6240)	mem 24308MB
[2025-01-18 18:20:08 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][220/312]	eta 0:00:56 lr 0.003015	time 0.5865 (0.6144)	model_time 0.5863 (0.6062)	loss 3.2143 (3.5300)	grad_norm 2.6139 (1.5640/0.6292)	mem 24308MB
[2025-01-18 18:20:14 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][230/312]	eta 0:00:50 lr 0.003015	time 0.6630 (0.6145)	model_time 0.6626 (0.6066)	loss 3.6122 (3.5316)	grad_norm 0.9120 (1.5485/0.6229)	mem 24308MB
[2025-01-18 18:20:21 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][240/312]	eta 0:00:44 lr 0.003014	time 0.6712 (0.6155)	model_time 0.6708 (0.6080)	loss 4.3656 (3.5421)	grad_norm 0.8016 (1.5365/0.6203)	mem 24308MB
[2025-01-18 18:20:27 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][250/312]	eta 0:00:38 lr 0.003014	time 0.5868 (0.6154)	model_time 0.5864 (0.6082)	loss 3.4970 (3.5501)	grad_norm 1.1773 (1.5424/0.6204)	mem 24308MB
[2025-01-18 18:20:33 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][260/312]	eta 0:00:31 lr 0.003013	time 0.5729 (0.6149)	model_time 0.5727 (0.6080)	loss 3.8485 (3.5523)	grad_norm 1.5193 (1.5512/0.6191)	mem 24308MB
[2025-01-18 18:20:39 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][270/312]	eta 0:00:25 lr 0.003012	time 0.5835 (0.6139)	model_time 0.5834 (0.6072)	loss 2.9125 (3.5557)	grad_norm 1.1266 (1.5442/0.6177)	mem 24308MB
[2025-01-18 18:20:45 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][280/312]	eta 0:00:19 lr 0.003012	time 0.5943 (0.6136)	model_time 0.5942 (0.6071)	loss 3.8869 (3.5460)	grad_norm 1.8530 (1.5722/0.6756)	mem 24308MB
[2025-01-18 18:20:51 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][290/312]	eta 0:00:13 lr 0.003011	time 0.7313 (0.6133)	model_time 0.7311 (0.6070)	loss 2.8569 (3.5432)	grad_norm 1.0934 (1.5750/0.6902)	mem 24308MB
[2025-01-18 18:20:57 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][300/312]	eta 0:00:07 lr 0.003011	time 0.5686 (0.6121)	model_time 0.5685 (0.6060)	loss 2.8185 (3.5403)	grad_norm 1.6947 (1.5704/0.6839)	mem 24308MB
[2025-01-18 18:21:02 internimage_s_1k_224] (main.py 510): INFO Train: [99/300][310/312]	eta 0:00:01 lr 0.003010	time 0.5706 (0.6108)	model_time 0.5705 (0.6049)	loss 3.7071 (3.5359)	grad_norm 1.7378 (1.5753/0.6804)	mem 24308MB
[2025-01-18 18:21:03 internimage_s_1k_224] (main.py 519): INFO EPOCH 99 training takes 0:03:10
[2025-01-18 18:21:03 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_99.pth saving......
[2025-01-18 18:21:05 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_99.pth saved !!!
[2025-01-18 18:21:12 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.279 (7.279)	Loss 0.8709 (0.8709)	Acc@1 80.688 (80.688)	Acc@5 96.289 (96.289)	Mem 24308MB
[2025-01-18 18:21:15 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.961)	Loss 1.2681 (1.0565)	Acc@1 71.802 (77.275)	Acc@5 91.797 (93.905)	Mem 24308MB
[2025-01-18 18:21:16 internimage_s_1k_224] (main.py 575): INFO [Epoch:99] * Acc@1 77.215 Acc@5 93.976
[2025-01-18 18:21:16 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.2%
[2025-01-18 18:21:16 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 18:21:18 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 18:21:18 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.22%
[2025-01-18 18:21:25 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.332 (7.332)	Loss 0.8107 (0.8107)	Acc@1 79.907 (79.907)	Acc@5 95.776 (95.776)	Mem 24308MB
[2025-01-18 18:21:28 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.964)	Loss 1.2397 (0.9854)	Acc@1 69.531 (76.099)	Acc@5 90.234 (93.373)	Mem 24308MB
[2025-01-18 18:21:28 internimage_s_1k_224] (main.py 575): INFO [Epoch:99] * Acc@1 76.058 Acc@5 93.426
[2025-01-18 18:21:28 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 76.1%
[2025-01-18 18:21:28 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 18:21:31 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 18:21:31 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 76.06%
[2025-01-18 18:21:33 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][0/312]	eta 0:11:39 lr 0.003010	time 2.2425 (2.2425)	model_time 0.5919 (0.5919)	loss 2.7833 (2.7833)	grad_norm 0.9151 (0.9151/0.0000)	mem 24308MB
[2025-01-18 18:21:39 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][10/312]	eta 0:03:50 lr 0.003009	time 0.6568 (0.7648)	model_time 0.6567 (0.6144)	loss 2.6475 (3.2975)	grad_norm 1.1819 (1.4587/0.6690)	mem 24308MB
[2025-01-18 18:21:45 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][20/312]	eta 0:03:24 lr 0.003009	time 0.7004 (0.7008)	model_time 0.7002 (0.6218)	loss 2.9861 (3.3998)	grad_norm 1.6784 (1.5651/0.5900)	mem 24308MB
[2025-01-18 18:21:52 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][30/312]	eta 0:03:10 lr 0.003008	time 0.5839 (0.6741)	model_time 0.5837 (0.6205)	loss 4.3243 (3.4600)	grad_norm 0.9524 (1.4821/0.5415)	mem 24308MB
[2025-01-18 18:21:58 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][40/312]	eta 0:02:59 lr 0.003008	time 0.5719 (0.6607)	model_time 0.5715 (0.6201)	loss 2.9634 (3.5045)	grad_norm 3.4246 (1.6700/0.6278)	mem 24308MB
[2025-01-18 18:22:04 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][50/312]	eta 0:02:50 lr 0.003007	time 0.5745 (0.6523)	model_time 0.5740 (0.6196)	loss 3.9232 (3.5347)	grad_norm 1.2471 (1.5900/0.6320)	mem 24308MB
[2025-01-18 18:22:10 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][60/312]	eta 0:02:43 lr 0.003007	time 0.6498 (0.6468)	model_time 0.6493 (0.6194)	loss 2.1192 (3.5145)	grad_norm 1.2482 (1.5695/0.6298)	mem 24308MB
[2025-01-18 18:22:16 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][70/312]	eta 0:02:35 lr 0.003006	time 0.5906 (0.6428)	model_time 0.5900 (0.6192)	loss 3.3055 (3.5027)	grad_norm 1.4852 (1.5252/0.6002)	mem 24308MB
[2025-01-18 18:22:22 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][80/312]	eta 0:02:27 lr 0.003005	time 0.5804 (0.6362)	model_time 0.5803 (0.6155)	loss 3.6437 (3.5199)	grad_norm 1.6130 (1.5111/0.5702)	mem 24308MB
[2025-01-18 18:22:28 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][90/312]	eta 0:02:20 lr 0.003005	time 0.5747 (0.6326)	model_time 0.5746 (0.6141)	loss 3.2818 (3.5197)	grad_norm 1.7539 (1.5192/0.5619)	mem 24308MB
[2025-01-18 18:22:34 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][100/312]	eta 0:02:13 lr 0.003004	time 0.5751 (0.6294)	model_time 0.5746 (0.6127)	loss 3.8402 (3.4766)	grad_norm 1.1074 (1.4974/0.5461)	mem 24308MB
[2025-01-18 18:22:40 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][110/312]	eta 0:02:06 lr 0.003004	time 0.5917 (0.6256)	model_time 0.5912 (0.6103)	loss 3.3316 (3.4757)	grad_norm 1.1799 (1.4803/0.5459)	mem 24308MB
[2025-01-18 18:22:46 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][120/312]	eta 0:01:59 lr 0.003003	time 0.5894 (0.6228)	model_time 0.5890 (0.6088)	loss 2.7870 (3.4459)	grad_norm 0.9971 (1.4416/0.5404)	mem 24308MB
[2025-01-18 18:22:52 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][130/312]	eta 0:01:53 lr 0.003003	time 0.6561 (0.6215)	model_time 0.6560 (0.6085)	loss 3.7213 (3.4607)	grad_norm 2.4109 (1.4675/0.5963)	mem 24308MB
[2025-01-18 18:22:58 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][140/312]	eta 0:01:46 lr 0.003002	time 0.6670 (0.6218)	model_time 0.6665 (0.6098)	loss 4.3186 (3.4906)	grad_norm 2.9453 (1.4917/0.6060)	mem 24308MB
[2025-01-18 18:23:04 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][150/312]	eta 0:01:40 lr 0.003001	time 0.5791 (0.6210)	model_time 0.5789 (0.6097)	loss 3.6201 (3.4765)	grad_norm 2.1176 (1.4996/0.6046)	mem 24308MB
[2025-01-18 18:23:10 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][160/312]	eta 0:01:34 lr 0.003001	time 0.5751 (0.6197)	model_time 0.5746 (0.6091)	loss 4.2012 (3.4858)	grad_norm 0.8843 (1.5134/0.6169)	mem 24308MB
[2025-01-18 18:23:17 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][170/312]	eta 0:01:28 lr 0.003000	time 0.5817 (0.6202)	model_time 0.5812 (0.6102)	loss 3.8316 (3.4863)	grad_norm 6.0110 (1.5601/0.7303)	mem 24308MB
[2025-01-18 18:23:23 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][180/312]	eta 0:01:21 lr 0.003000	time 0.5846 (0.6191)	model_time 0.5845 (0.6096)	loss 3.2693 (3.4830)	grad_norm 1.4623 (1.5792/0.7460)	mem 24308MB
[2025-01-18 18:23:29 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][190/312]	eta 0:01:15 lr 0.002999	time 0.6930 (0.6187)	model_time 0.6926 (0.6097)	loss 4.1508 (3.5063)	grad_norm 1.6945 (1.5687/0.7339)	mem 24308MB
[2025-01-18 18:23:35 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][200/312]	eta 0:01:09 lr 0.002998	time 0.6168 (0.6174)	model_time 0.6166 (0.6088)	loss 2.8326 (3.4965)	grad_norm 1.0868 (1.5550/0.7258)	mem 24308MB
[2025-01-18 18:23:41 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][210/312]	eta 0:01:02 lr 0.002998	time 0.6003 (0.6163)	model_time 0.6001 (0.6081)	loss 2.8852 (3.4946)	grad_norm 0.9406 (1.5473/0.7136)	mem 24308MB
[2025-01-18 18:23:47 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][220/312]	eta 0:00:56 lr 0.002997	time 0.5796 (0.6153)	model_time 0.5794 (0.6074)	loss 3.6834 (3.5000)	grad_norm 0.9304 (1.5458/0.7088)	mem 24308MB
[2025-01-18 18:23:53 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][230/312]	eta 0:00:50 lr 0.002997	time 0.5948 (0.6142)	model_time 0.5946 (0.6067)	loss 2.6472 (3.5106)	grad_norm 1.7715 (1.5448/0.6982)	mem 24308MB
[2025-01-18 18:23:58 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][240/312]	eta 0:00:44 lr 0.002996	time 0.5808 (0.6131)	model_time 0.5807 (0.6059)	loss 3.8385 (3.5203)	grad_norm 1.3695 (1.5413/0.6999)	mem 24308MB
[2025-01-18 18:24:05 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][250/312]	eta 0:00:38 lr 0.002996	time 0.6812 (0.6137)	model_time 0.6811 (0.6067)	loss 3.9447 (3.5172)	grad_norm 1.3426 (1.5298/0.6909)	mem 24308MB
[2025-01-18 18:24:11 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][260/312]	eta 0:00:31 lr 0.002995	time 0.5721 (0.6132)	model_time 0.5719 (0.6065)	loss 4.3963 (3.5217)	grad_norm 1.3071 (1.5274/0.6828)	mem 24308MB
[2025-01-18 18:24:17 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][270/312]	eta 0:00:25 lr 0.002994	time 0.5902 (0.6138)	model_time 0.5897 (0.6072)	loss 3.1296 (3.5170)	grad_norm 2.0975 (1.5378/0.6800)	mem 24308MB
[2025-01-18 18:24:23 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][280/312]	eta 0:00:19 lr 0.002994	time 0.5902 (0.6134)	model_time 0.5897 (0.6070)	loss 3.7286 (3.5221)	grad_norm 2.3440 (1.5469/0.6827)	mem 24308MB
[2025-01-18 18:24:29 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][290/312]	eta 0:00:13 lr 0.002993	time 0.5793 (0.6138)	model_time 0.5792 (0.6076)	loss 4.1567 (3.5178)	grad_norm 1.4659 (1.5533/0.6892)	mem 24308MB
[2025-01-18 18:24:35 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][300/312]	eta 0:00:07 lr 0.002993	time 0.5654 (0.6134)	model_time 0.5653 (0.6074)	loss 3.6543 (3.5186)	grad_norm 2.0739 (1.5508/0.6841)	mem 24308MB
[2025-01-18 18:24:41 internimage_s_1k_224] (main.py 510): INFO Train: [100/300][310/312]	eta 0:00:01 lr 0.002992	time 0.6410 (0.6126)	model_time 0.6409 (0.6068)	loss 4.4142 (3.5194)	grad_norm 1.1499 (1.5373/0.6796)	mem 24308MB
[2025-01-18 18:24:42 internimage_s_1k_224] (main.py 519): INFO EPOCH 100 training takes 0:03:11
[2025-01-18 18:24:42 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_100.pth saving......
[2025-01-18 18:24:44 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_100.pth saved !!!
[2025-01-18 18:24:51 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.341 (7.341)	Loss 0.8592 (0.8592)	Acc@1 80.420 (80.420)	Acc@5 96.094 (96.094)	Mem 24308MB
[2025-01-18 18:24:55 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.996)	Loss 1.2225 (1.0244)	Acc@1 72.559 (77.091)	Acc@5 91.821 (94.010)	Mem 24308MB
[2025-01-18 18:24:55 internimage_s_1k_224] (main.py 575): INFO [Epoch:100] * Acc@1 77.025 Acc@5 94.074
[2025-01-18 18:24:55 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.0%
[2025-01-18 18:24:55 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.22%
[2025-01-18 18:25:04 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.769 (8.769)	Loss 0.8057 (0.8057)	Acc@1 80.127 (80.127)	Acc@5 95.825 (95.825)	Mem 24308MB
[2025-01-18 18:25:08 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.175)	Loss 1.2320 (0.9799)	Acc@1 69.702 (76.225)	Acc@5 90.308 (93.419)	Mem 24308MB
[2025-01-18 18:25:08 internimage_s_1k_224] (main.py 575): INFO [Epoch:100] * Acc@1 76.178 Acc@5 93.470
[2025-01-18 18:25:08 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 76.2%
[2025-01-18 18:25:08 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 18:25:10 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 18:25:10 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 76.18%
[2025-01-18 18:25:13 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][0/312]	eta 0:12:04 lr 0.002992	time 2.3206 (2.3206)	model_time 0.5987 (0.5987)	loss 3.3660 (3.3660)	grad_norm 1.1205 (1.1205/0.0000)	mem 24308MB
[2025-01-18 18:25:19 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][10/312]	eta 0:03:46 lr 0.002991	time 0.5832 (0.7509)	model_time 0.5830 (0.5941)	loss 3.4802 (3.7074)	grad_norm 1.6854 (1.5740/0.5264)	mem 24308MB
[2025-01-18 18:25:25 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][20/312]	eta 0:03:17 lr 0.002991	time 0.5751 (0.6780)	model_time 0.5747 (0.5957)	loss 3.3602 (3.6197)	grad_norm 1.9872 (1.5940/0.5695)	mem 24308MB
[2025-01-18 18:25:30 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][30/312]	eta 0:03:03 lr 0.002990	time 0.5848 (0.6501)	model_time 0.5844 (0.5943)	loss 2.6174 (3.5001)	grad_norm 2.6858 (1.5821/0.5692)	mem 24308MB
[2025-01-18 18:25:36 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][40/312]	eta 0:02:52 lr 0.002990	time 0.5902 (0.6347)	model_time 0.5897 (0.5924)	loss 2.6289 (3.4420)	grad_norm 1.4746 (1.6148/0.5637)	mem 24308MB
[2025-01-18 18:25:42 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][50/312]	eta 0:02:44 lr 0.002989	time 0.6090 (0.6271)	model_time 0.6085 (0.5929)	loss 3.6260 (3.4231)	grad_norm 0.7049 (1.5466/0.5552)	mem 24308MB
[2025-01-18 18:25:48 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][60/312]	eta 0:02:37 lr 0.002989	time 0.5718 (0.6240)	model_time 0.5714 (0.5954)	loss 3.1814 (3.4427)	grad_norm 1.4001 (1.5548/0.5476)	mem 24308MB
[2025-01-18 18:25:55 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][70/312]	eta 0:02:30 lr 0.002988	time 0.6860 (0.6230)	model_time 0.6855 (0.5984)	loss 3.3924 (3.4894)	grad_norm 0.9628 (1.6069/0.5918)	mem 24308MB
[2025-01-18 18:26:01 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][80/312]	eta 0:02:25 lr 0.002987	time 0.5760 (0.6263)	model_time 0.5759 (0.6047)	loss 4.3505 (3.5201)	grad_norm 1.3334 (1.5520/0.5779)	mem 24308MB
[2025-01-18 18:26:07 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][90/312]	eta 0:02:18 lr 0.002987	time 0.5783 (0.6245)	model_time 0.5781 (0.6052)	loss 2.8290 (3.5169)	grad_norm 1.8092 (1.5633/0.5788)	mem 24308MB
[2025-01-18 18:26:13 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][100/312]	eta 0:02:12 lr 0.002986	time 0.5829 (0.6254)	model_time 0.5825 (0.6080)	loss 2.8466 (3.4925)	grad_norm 1.2462 (1.5752/0.5711)	mem 24308MB
[2025-01-18 18:26:19 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][110/312]	eta 0:02:05 lr 0.002986	time 0.5845 (0.6234)	model_time 0.5843 (0.6075)	loss 2.7199 (3.4855)	grad_norm 0.8354 (1.5734/0.5818)	mem 24308MB
[2025-01-18 18:26:26 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][120/312]	eta 0:01:59 lr 0.002985	time 0.6812 (0.6226)	model_time 0.6807 (0.6079)	loss 2.7979 (3.4793)	grad_norm 1.1688 (1.5252/0.5821)	mem 24308MB
[2025-01-18 18:26:31 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][130/312]	eta 0:01:52 lr 0.002984	time 0.5852 (0.6198)	model_time 0.5850 (0.6063)	loss 2.5624 (3.4843)	grad_norm 2.6982 (1.5430/0.6084)	mem 24308MB
[2025-01-18 18:26:37 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][140/312]	eta 0:01:46 lr 0.002984	time 0.6111 (0.6182)	model_time 0.6107 (0.6056)	loss 4.4843 (3.5032)	grad_norm 0.9527 (1.5621/0.6259)	mem 24308MB
[2025-01-18 18:26:43 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][150/312]	eta 0:01:39 lr 0.002983	time 0.5946 (0.6161)	model_time 0.5944 (0.6042)	loss 3.8188 (3.4988)	grad_norm 1.7628 (1.5678/0.6161)	mem 24308MB
[2025-01-18 18:26:49 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][160/312]	eta 0:01:33 lr 0.002983	time 0.5904 (0.6142)	model_time 0.5900 (0.6030)	loss 4.2065 (3.5044)	grad_norm 1.4505 (1.5593/0.6062)	mem 24308MB
[2025-01-18 18:26:55 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][170/312]	eta 0:01:27 lr 0.002982	time 0.5732 (0.6128)	model_time 0.5731 (0.6023)	loss 3.8523 (3.5188)	grad_norm 1.0376 (1.5418/0.5997)	mem 24308MB
[2025-01-18 18:27:01 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][180/312]	eta 0:01:20 lr 0.002982	time 0.6154 (0.6124)	model_time 0.6150 (0.6024)	loss 3.9105 (3.5100)	grad_norm 0.8073 (1.5104/0.5982)	mem 24308MB
[2025-01-18 18:27:07 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][190/312]	eta 0:01:14 lr 0.002981	time 0.6589 (0.6135)	model_time 0.6585 (0.6040)	loss 3.5045 (3.5233)	grad_norm 1.7618 (1.5182/0.5890)	mem 24308MB
[2025-01-18 18:27:14 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][200/312]	eta 0:01:08 lr 0.002980	time 0.5892 (0.6138)	model_time 0.5888 (0.6048)	loss 3.7860 (3.5237)	grad_norm 1.9854 (1.5267/0.5856)	mem 24308MB
[2025-01-18 18:27:20 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][210/312]	eta 0:01:02 lr 0.002980	time 0.5914 (0.6140)	model_time 0.5912 (0.6054)	loss 2.8646 (3.5255)	grad_norm 1.1488 (1.5156/0.5795)	mem 24308MB
[2025-01-18 18:27:26 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][220/312]	eta 0:00:56 lr 0.002979	time 0.6616 (0.6159)	model_time 0.6611 (0.6077)	loss 3.0373 (3.5211)	grad_norm 1.5296 (1.5328/0.5884)	mem 24308MB
[2025-01-18 18:27:32 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][230/312]	eta 0:00:50 lr 0.002979	time 0.5992 (0.6153)	model_time 0.5990 (0.6074)	loss 3.6685 (3.5121)	grad_norm 1.0914 (1.5516/0.6012)	mem 24308MB
[2025-01-18 18:27:38 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][240/312]	eta 0:00:44 lr 0.002978	time 0.5764 (0.6147)	model_time 0.5759 (0.6071)	loss 3.6655 (3.5186)	grad_norm 1.2585 (1.5423/0.5950)	mem 24308MB
[2025-01-18 18:27:44 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][250/312]	eta 0:00:38 lr 0.002977	time 0.5779 (0.6140)	model_time 0.5777 (0.6067)	loss 3.6607 (3.5241)	grad_norm 0.6769 (1.5459/0.6055)	mem 24308MB
[2025-01-18 18:27:50 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][260/312]	eta 0:00:31 lr 0.002977	time 0.5735 (0.6135)	model_time 0.5730 (0.6065)	loss 3.8375 (3.5335)	grad_norm 1.1810 (1.5524/0.6135)	mem 24308MB
[2025-01-18 18:27:56 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][270/312]	eta 0:00:25 lr 0.002976	time 0.5920 (0.6125)	model_time 0.5918 (0.6057)	loss 4.2111 (3.5345)	grad_norm 1.3437 (1.5474/0.6080)	mem 24308MB
[2025-01-18 18:28:02 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][280/312]	eta 0:00:19 lr 0.002976	time 0.6434 (0.6119)	model_time 0.6431 (0.6053)	loss 4.3531 (3.5409)	grad_norm 1.9950 (1.5627/0.6110)	mem 24308MB
[2025-01-18 18:28:08 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][290/312]	eta 0:00:13 lr 0.002975	time 0.5758 (0.6111)	model_time 0.5756 (0.6047)	loss 3.5791 (3.5438)	grad_norm 1.2436 (1.5682/0.6144)	mem 24308MB
[2025-01-18 18:28:14 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][300/312]	eta 0:00:07 lr 0.002975	time 0.5692 (0.6107)	model_time 0.5691 (0.6045)	loss 3.9320 (3.5395)	grad_norm 0.9889 (1.5554/0.6110)	mem 24308MB
[2025-01-18 18:28:20 internimage_s_1k_224] (main.py 510): INFO Train: [101/300][310/312]	eta 0:00:01 lr 0.002974	time 0.5682 (0.6107)	model_time 0.5681 (0.6048)	loss 4.2149 (3.5405)	grad_norm 3.0657 (1.5638/0.6334)	mem 24308MB
[2025-01-18 18:28:21 internimage_s_1k_224] (main.py 519): INFO EPOCH 101 training takes 0:03:10
[2025-01-18 18:28:21 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_101.pth saving......
[2025-01-18 18:28:23 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_101.pth saved !!!
[2025-01-18 18:28:30 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.464 (7.464)	Loss 0.9171 (0.9171)	Acc@1 80.176 (80.176)	Acc@5 95.654 (95.654)	Mem 24308MB
[2025-01-18 18:28:34 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.987)	Loss 1.2683 (1.0695)	Acc@1 72.437 (77.122)	Acc@5 91.650 (93.877)	Mem 24308MB
[2025-01-18 18:28:34 internimage_s_1k_224] (main.py 575): INFO [Epoch:101] * Acc@1 77.103 Acc@5 93.918
[2025-01-18 18:28:34 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.1%
[2025-01-18 18:28:34 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.22%
[2025-01-18 18:28:42 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.454 (8.454)	Loss 0.8009 (0.8009)	Acc@1 80.347 (80.347)	Acc@5 95.923 (95.923)	Mem 24308MB
[2025-01-18 18:28:46 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.150)	Loss 1.2245 (0.9744)	Acc@1 70.044 (76.381)	Acc@5 90.405 (93.524)	Mem 24308MB
[2025-01-18 18:28:46 internimage_s_1k_224] (main.py 575): INFO [Epoch:101] * Acc@1 76.328 Acc@5 93.570
[2025-01-18 18:28:46 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 76.3%
[2025-01-18 18:28:47 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 18:28:49 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 18:28:49 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 76.33%
[2025-01-18 18:28:51 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][0/312]	eta 0:12:36 lr 0.002974	time 2.4261 (2.4261)	model_time 0.5972 (0.5972)	loss 4.1293 (4.1293)	grad_norm 1.3180 (1.3180/0.0000)	mem 24308MB
[2025-01-18 18:28:57 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][10/312]	eta 0:04:03 lr 0.002973	time 0.7280 (0.8066)	model_time 0.7278 (0.6401)	loss 3.8032 (3.7093)	grad_norm 1.5941 (1.6583/0.6261)	mem 24308MB
[2025-01-18 18:29:04 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][20/312]	eta 0:03:32 lr 0.002973	time 0.6885 (0.7261)	model_time 0.6880 (0.6388)	loss 4.0486 (3.5429)	grad_norm 1.3977 (1.7621/0.7133)	mem 24308MB
[2025-01-18 18:29:10 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][30/312]	eta 0:03:16 lr 0.002972	time 0.5887 (0.6956)	model_time 0.5883 (0.6362)	loss 2.3048 (3.4182)	grad_norm 0.8616 (1.5653/0.6941)	mem 24308MB
[2025-01-18 18:29:16 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][40/312]	eta 0:03:03 lr 0.002972	time 0.6392 (0.6732)	model_time 0.6391 (0.6283)	loss 3.6318 (3.4406)	grad_norm 2.8797 (1.5879/0.6562)	mem 24308MB
[2025-01-18 18:29:22 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][50/312]	eta 0:02:52 lr 0.002971	time 0.5873 (0.6592)	model_time 0.5871 (0.6230)	loss 3.4886 (3.4544)	grad_norm 1.5329 (1.6204/0.6665)	mem 24308MB
[2025-01-18 18:29:28 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][60/312]	eta 0:02:43 lr 0.002970	time 0.5910 (0.6492)	model_time 0.5906 (0.6189)	loss 3.6924 (3.4500)	grad_norm 2.6116 (1.7158/0.6908)	mem 24308MB
[2025-01-18 18:29:34 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][70/312]	eta 0:02:35 lr 0.002970	time 0.5731 (0.6415)	model_time 0.5727 (0.6154)	loss 2.6928 (3.4366)	grad_norm 0.8339 (1.6468/0.6791)	mem 24308MB
[2025-01-18 18:29:40 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][80/312]	eta 0:02:27 lr 0.002969	time 0.5948 (0.6354)	model_time 0.5947 (0.6125)	loss 2.8173 (3.4429)	grad_norm 0.9766 (1.5616/0.6787)	mem 24308MB
[2025-01-18 18:29:46 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][90/312]	eta 0:02:19 lr 0.002969	time 0.5719 (0.6298)	model_time 0.5715 (0.6093)	loss 3.6631 (3.4613)	grad_norm 1.5720 (1.5417/0.6473)	mem 24308MB
[2025-01-18 18:29:52 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][100/312]	eta 0:02:12 lr 0.002968	time 0.5806 (0.6261)	model_time 0.5802 (0.6076)	loss 3.7849 (3.4913)	grad_norm 1.2928 (1.5410/0.6300)	mem 24308MB
[2025-01-18 18:29:58 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][110/312]	eta 0:02:06 lr 0.002967	time 0.5863 (0.6247)	model_time 0.5862 (0.6078)	loss 2.7005 (3.5050)	grad_norm 1.6684 (1.5444/0.6202)	mem 24308MB
[2025-01-18 18:30:04 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][120/312]	eta 0:01:59 lr 0.002967	time 0.5734 (0.6234)	model_time 0.5730 (0.6079)	loss 3.8813 (3.5144)	grad_norm 1.0827 (1.5436/0.6223)	mem 24308MB
[2025-01-18 18:30:11 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][130/312]	eta 0:01:53 lr 0.002966	time 0.6613 (0.6259)	model_time 0.6611 (0.6116)	loss 4.0281 (3.5243)	grad_norm 1.2489 (1.5706/0.6474)	mem 24308MB
[2025-01-18 18:30:17 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][140/312]	eta 0:01:47 lr 0.002966	time 0.5809 (0.6267)	model_time 0.5805 (0.6134)	loss 3.7286 (3.5120)	grad_norm 3.0428 (1.5754/0.6461)	mem 24308MB
[2025-01-18 18:30:23 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][150/312]	eta 0:01:41 lr 0.002965	time 0.7061 (0.6266)	model_time 0.7057 (0.6142)	loss 3.4221 (3.5097)	grad_norm 0.7652 (1.5751/0.6485)	mem 24308MB
[2025-01-18 18:30:29 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][160/312]	eta 0:01:35 lr 0.002965	time 0.5960 (0.6252)	model_time 0.5958 (0.6134)	loss 2.7230 (3.4878)	grad_norm 0.9955 (1.5574/0.6348)	mem 24308MB
[2025-01-18 18:30:35 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][170/312]	eta 0:01:28 lr 0.002964	time 0.5837 (0.6237)	model_time 0.5835 (0.6126)	loss 2.8087 (3.4882)	grad_norm 1.2997 (1.5487/0.6224)	mem 24308MB
[2025-01-18 18:30:41 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][180/312]	eta 0:01:22 lr 0.002963	time 0.5788 (0.6232)	model_time 0.5787 (0.6127)	loss 4.1091 (3.4934)	grad_norm 1.1243 (1.5387/0.6097)	mem 24308MB
[2025-01-18 18:30:47 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][190/312]	eta 0:01:15 lr 0.002963	time 0.5835 (0.6219)	model_time 0.5834 (0.6119)	loss 3.2468 (3.4805)	grad_norm 2.7189 (1.5410/0.6118)	mem 24308MB
[2025-01-18 18:30:53 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][200/312]	eta 0:01:09 lr 0.002962	time 0.5742 (0.6206)	model_time 0.5737 (0.6110)	loss 4.4393 (3.4882)	grad_norm 1.9439 (1.5502/0.6051)	mem 24308MB
[2025-01-18 18:30:59 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][210/312]	eta 0:01:03 lr 0.002962	time 0.5749 (0.6190)	model_time 0.5744 (0.6098)	loss 2.7641 (3.4844)	grad_norm 1.0810 (1.5657/0.6484)	mem 24308MB
[2025-01-18 18:31:05 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][220/312]	eta 0:00:56 lr 0.002961	time 0.5813 (0.6178)	model_time 0.5812 (0.6090)	loss 2.8591 (3.4746)	grad_norm 1.2920 (1.5641/0.6665)	mem 24308MB
[2025-01-18 18:31:11 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][230/312]	eta 0:00:50 lr 0.002960	time 0.6583 (0.6172)	model_time 0.6579 (0.6088)	loss 3.1977 (3.4713)	grad_norm 1.6938 (1.5797/0.6869)	mem 24308MB
[2025-01-18 18:31:17 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][240/312]	eta 0:00:44 lr 0.002960	time 0.6659 (0.6175)	model_time 0.6654 (0.6095)	loss 3.7887 (3.4740)	grad_norm 1.9146 (1.5978/0.6880)	mem 24308MB
[2025-01-18 18:31:24 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][250/312]	eta 0:00:38 lr 0.002959	time 0.5931 (0.6174)	model_time 0.5927 (0.6097)	loss 3.6064 (3.4780)	grad_norm 1.5895 (1.5852/0.6784)	mem 24308MB
[2025-01-18 18:31:30 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][260/312]	eta 0:00:32 lr 0.002959	time 0.5753 (0.6182)	model_time 0.5751 (0.6107)	loss 2.7123 (3.4809)	grad_norm 2.1638 (1.5848/0.6716)	mem 24308MB
[2025-01-18 18:31:36 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][270/312]	eta 0:00:25 lr 0.002958	time 0.6616 (0.6187)	model_time 0.6615 (0.6115)	loss 3.3243 (3.4810)	grad_norm 1.3972 (1.5954/0.6761)	mem 24308MB
[2025-01-18 18:31:42 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][280/312]	eta 0:00:19 lr 0.002958	time 0.5958 (0.6183)	model_time 0.5953 (0.6114)	loss 3.6726 (3.4864)	grad_norm 1.1726 (1.5839/0.6694)	mem 24308MB
[2025-01-18 18:31:48 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][290/312]	eta 0:00:13 lr 0.002957	time 0.5797 (0.6179)	model_time 0.5792 (0.6111)	loss 3.6785 (3.4914)	grad_norm 2.0827 (1.5872/0.6624)	mem 24308MB
[2025-01-18 18:31:54 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][300/312]	eta 0:00:07 lr 0.002956	time 0.6252 (0.6173)	model_time 0.6251 (0.6108)	loss 4.1309 (3.5059)	grad_norm 1.4279 (1.5773/0.6575)	mem 24308MB
[2025-01-18 18:32:00 internimage_s_1k_224] (main.py 510): INFO Train: [102/300][310/312]	eta 0:00:01 lr 0.002956	time 0.5716 (0.6158)	model_time 0.5715 (0.6095)	loss 3.4827 (3.5029)	grad_norm 1.2778 (1.5746/0.6557)	mem 24308MB
[2025-01-18 18:32:01 internimage_s_1k_224] (main.py 519): INFO EPOCH 102 training takes 0:03:12
[2025-01-18 18:32:01 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_102.pth saving......
[2025-01-18 18:32:02 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_102.pth saved !!!
[2025-01-18 18:32:10 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.443 (7.443)	Loss 0.8794 (0.8794)	Acc@1 80.078 (80.078)	Acc@5 95.703 (95.703)	Mem 24308MB
[2025-01-18 18:32:14 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.022)	Loss 1.2718 (1.0571)	Acc@1 72.192 (77.111)	Acc@5 91.406 (93.896)	Mem 24308MB
[2025-01-18 18:32:14 internimage_s_1k_224] (main.py 575): INFO [Epoch:102] * Acc@1 77.039 Acc@5 93.932
[2025-01-18 18:32:14 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.0%
[2025-01-18 18:32:14 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.22%
[2025-01-18 18:32:23 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.814 (8.814)	Loss 0.7963 (0.7963)	Acc@1 80.396 (80.396)	Acc@5 96.021 (96.021)	Mem 24308MB
[2025-01-18 18:32:27 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.200)	Loss 1.2170 (0.9691)	Acc@1 70.264 (76.494)	Acc@5 90.527 (93.575)	Mem 24308MB
[2025-01-18 18:32:27 internimage_s_1k_224] (main.py 575): INFO [Epoch:102] * Acc@1 76.436 Acc@5 93.618
[2025-01-18 18:32:27 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 76.4%
[2025-01-18 18:32:27 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 18:32:30 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 18:32:30 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 76.44%
[2025-01-18 18:32:33 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][0/312]	eta 0:13:32 lr 0.002956	time 2.6026 (2.6026)	model_time 0.5957 (0.5957)	loss 4.2900 (4.2900)	grad_norm 1.7492 (1.7492/0.0000)	mem 24308MB
[2025-01-18 18:32:39 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][10/312]	eta 0:03:53 lr 0.002955	time 0.5879 (0.7723)	model_time 0.5875 (0.5895)	loss 3.9070 (3.6502)	grad_norm 1.6098 (1.4165/0.2804)	mem 24308MB
[2025-01-18 18:32:44 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][20/312]	eta 0:03:20 lr 0.002954	time 0.5742 (0.6852)	model_time 0.5740 (0.5894)	loss 2.8462 (3.5606)	grad_norm 2.0215 (1.6145/0.4591)	mem 24308MB
[2025-01-18 18:32:50 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][30/312]	eta 0:03:04 lr 0.002954	time 0.5964 (0.6550)	model_time 0.5962 (0.5900)	loss 3.7749 (3.6032)	grad_norm 0.7412 (1.7749/0.7760)	mem 24308MB
[2025-01-18 18:32:56 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][40/312]	eta 0:02:54 lr 0.002953	time 0.5845 (0.6422)	model_time 0.5843 (0.5929)	loss 3.8767 (3.6034)	grad_norm 2.7394 (1.7993/0.8355)	mem 24308MB
[2025-01-18 18:33:03 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][50/312]	eta 0:02:48 lr 0.002953	time 0.5883 (0.6413)	model_time 0.5881 (0.6016)	loss 3.7511 (3.5982)	grad_norm 0.6603 (1.6526/0.8102)	mem 24308MB
[2025-01-18 18:33:09 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][60/312]	eta 0:02:41 lr 0.002952	time 0.5768 (0.6401)	model_time 0.5764 (0.6068)	loss 3.7665 (3.5954)	grad_norm 0.7734 (1.5475/0.7860)	mem 24308MB
[2025-01-18 18:33:15 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][70/312]	eta 0:02:35 lr 0.002952	time 0.7464 (0.6405)	model_time 0.7463 (0.6119)	loss 3.5688 (3.5877)	grad_norm 2.8717 (1.5260/0.7653)	mem 24308MB
[2025-01-18 18:33:22 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][80/312]	eta 0:02:28 lr 0.002951	time 0.5959 (0.6386)	model_time 0.5957 (0.6134)	loss 3.1643 (3.6051)	grad_norm 1.7984 (1.5739/0.7534)	mem 24308MB
[2025-01-18 18:33:28 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][90/312]	eta 0:02:20 lr 0.002950	time 0.5760 (0.6351)	model_time 0.5758 (0.6127)	loss 4.0971 (3.5946)	grad_norm 1.1017 (1.5654/0.7232)	mem 24308MB
[2025-01-18 18:33:34 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][100/312]	eta 0:02:14 lr 0.002950	time 0.6471 (0.6324)	model_time 0.6470 (0.6122)	loss 3.0588 (3.5707)	grad_norm 1.3831 (1.5422/0.7169)	mem 24308MB
[2025-01-18 18:33:40 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][110/312]	eta 0:02:07 lr 0.002949	time 0.6043 (0.6301)	model_time 0.6041 (0.6117)	loss 2.3671 (3.5725)	grad_norm 1.1039 (1.5090/0.6941)	mem 24308MB
[2025-01-18 18:33:46 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][120/312]	eta 0:02:00 lr 0.002949	time 0.5879 (0.6276)	model_time 0.5877 (0.6106)	loss 2.4090 (3.5660)	grad_norm 0.8122 (1.5065/0.6862)	mem 24308MB
[2025-01-18 18:33:52 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][130/312]	eta 0:01:53 lr 0.002948	time 0.7085 (0.6257)	model_time 0.7081 (0.6100)	loss 3.0706 (3.5692)	grad_norm 2.1443 (1.5615/0.7389)	mem 24308MB
[2025-01-18 18:33:58 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][140/312]	eta 0:01:47 lr 0.002947	time 0.5739 (0.6228)	model_time 0.5738 (0.6082)	loss 3.9921 (3.5711)	grad_norm 2.1402 (1.5746/0.7296)	mem 24308MB
[2025-01-18 18:34:04 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][150/312]	eta 0:01:40 lr 0.002947	time 0.5752 (0.6203)	model_time 0.5748 (0.6067)	loss 3.0753 (3.5635)	grad_norm 0.8320 (1.5601/0.7095)	mem 24308MB
[2025-01-18 18:34:10 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][160/312]	eta 0:01:34 lr 0.002946	time 0.5881 (0.6190)	model_time 0.5880 (0.6062)	loss 4.2274 (3.5528)	grad_norm 1.1692 (1.5604/0.6960)	mem 24308MB
[2025-01-18 18:34:16 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][170/312]	eta 0:01:27 lr 0.002946	time 0.5830 (0.6192)	model_time 0.5828 (0.6071)	loss 3.8137 (3.5624)	grad_norm 1.9540 (1.5509/0.6950)	mem 24308MB
[2025-01-18 18:34:22 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][180/312]	eta 0:01:21 lr 0.002945	time 0.5812 (0.6197)	model_time 0.5808 (0.6083)	loss 3.6729 (3.5656)	grad_norm 1.2705 (1.5407/0.6794)	mem 24308MB
[2025-01-18 18:34:28 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][190/312]	eta 0:01:15 lr 0.002945	time 0.6882 (0.6202)	model_time 0.6877 (0.6094)	loss 3.7297 (3.5659)	grad_norm 2.0445 (1.5374/0.6699)	mem 24308MB
[2025-01-18 18:34:35 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][200/312]	eta 0:01:09 lr 0.002944	time 0.5731 (0.6202)	model_time 0.5729 (0.6099)	loss 2.9755 (3.5703)	grad_norm 2.0087 (1.5388/0.6580)	mem 24308MB
[2025-01-18 18:34:41 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][210/312]	eta 0:01:03 lr 0.002943	time 0.5954 (0.6195)	model_time 0.5952 (0.6097)	loss 4.4646 (3.5874)	grad_norm 0.8281 (1.5187/0.6498)	mem 24308MB
[2025-01-18 18:34:47 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][220/312]	eta 0:00:56 lr 0.002943	time 0.5763 (0.6187)	model_time 0.5761 (0.6092)	loss 2.7821 (3.5786)	grad_norm 2.0459 (1.5203/0.6489)	mem 24308MB
[2025-01-18 18:34:53 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][230/312]	eta 0:00:50 lr 0.002942	time 0.5799 (0.6180)	model_time 0.5798 (0.6089)	loss 2.6128 (3.5679)	grad_norm 2.3362 (1.5566/0.6722)	mem 24308MB
[2025-01-18 18:34:59 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][240/312]	eta 0:00:44 lr 0.002942	time 0.5829 (0.6171)	model_time 0.5825 (0.6084)	loss 3.3314 (3.5646)	grad_norm 1.6941 (1.5656/0.6629)	mem 24308MB
[2025-01-18 18:35:05 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][250/312]	eta 0:00:38 lr 0.002941	time 0.5800 (0.6158)	model_time 0.5798 (0.6075)	loss 4.2642 (3.5689)	grad_norm 1.2549 (1.5620/0.6631)	mem 24308MB
[2025-01-18 18:35:11 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][260/312]	eta 0:00:31 lr 0.002940	time 0.5871 (0.6151)	model_time 0.5870 (0.6071)	loss 3.7066 (3.5648)	grad_norm 0.5813 (1.5465/0.6608)	mem 24308MB
[2025-01-18 18:35:16 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][270/312]	eta 0:00:25 lr 0.002940	time 0.5715 (0.6141)	model_time 0.5713 (0.6063)	loss 3.7892 (3.5670)	grad_norm 2.4365 (1.5563/0.6646)	mem 24308MB
[2025-01-18 18:35:22 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][280/312]	eta 0:00:19 lr 0.002939	time 0.5717 (0.6135)	model_time 0.5715 (0.6060)	loss 3.6179 (3.5580)	grad_norm 1.3366 (1.5619/0.6558)	mem 24308MB
[2025-01-18 18:35:29 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][290/312]	eta 0:00:13 lr 0.002939	time 0.5880 (0.6135)	model_time 0.5725 (0.6062)	loss 3.8856 (3.5601)	grad_norm 2.0275 (1.5522/0.6497)	mem 24308MB
[2025-01-18 18:35:35 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][300/312]	eta 0:00:07 lr 0.002938	time 0.6595 (0.6136)	model_time 0.6593 (0.6065)	loss 3.6118 (3.5532)	grad_norm 0.6222 (1.5449/0.6524)	mem 24308MB
[2025-01-18 18:35:41 internimage_s_1k_224] (main.py 510): INFO Train: [103/300][310/312]	eta 0:00:01 lr 0.002937	time 0.6426 (0.6131)	model_time 0.6425 (0.6062)	loss 2.9399 (3.5610)	grad_norm 1.3647 (1.5373/0.6573)	mem 24308MB
[2025-01-18 18:35:41 internimage_s_1k_224] (main.py 519): INFO EPOCH 103 training takes 0:03:11
[2025-01-18 18:35:41 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_103.pth saving......
[2025-01-18 18:35:43 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_103.pth saved !!!
[2025-01-18 18:35:50 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.096 (7.096)	Loss 0.9263 (0.9263)	Acc@1 80.640 (80.640)	Acc@5 95.435 (95.435)	Mem 24308MB
[2025-01-18 18:35:54 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.963)	Loss 1.2323 (1.0585)	Acc@1 72.388 (77.115)	Acc@5 91.943 (93.954)	Mem 24308MB
[2025-01-18 18:35:54 internimage_s_1k_224] (main.py 575): INFO [Epoch:103] * Acc@1 77.065 Acc@5 93.992
[2025-01-18 18:35:54 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.1%
[2025-01-18 18:35:54 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.22%
[2025-01-18 18:36:03 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.603 (8.603)	Loss 0.7922 (0.7922)	Acc@1 80.493 (80.493)	Acc@5 96.021 (96.021)	Mem 24308MB
[2025-01-18 18:36:07 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.162)	Loss 1.2102 (0.9640)	Acc@1 70.264 (76.649)	Acc@5 90.479 (93.626)	Mem 24308MB
[2025-01-18 18:36:07 internimage_s_1k_224] (main.py 575): INFO [Epoch:103] * Acc@1 76.583 Acc@5 93.674
[2025-01-18 18:36:07 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 76.6%
[2025-01-18 18:36:07 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 18:36:09 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 18:36:09 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 76.58%
[2025-01-18 18:36:12 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][0/312]	eta 0:14:22 lr 0.002937	time 2.7641 (2.7641)	model_time 0.6132 (0.6132)	loss 2.8031 (2.8031)	grad_norm 1.1082 (1.1082/0.0000)	mem 24308MB
[2025-01-18 18:36:19 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][10/312]	eta 0:04:11 lr 0.002937	time 0.6862 (0.8337)	model_time 0.6860 (0.6379)	loss 3.9647 (3.3805)	grad_norm 1.3175 (1.1744/0.2898)	mem 24308MB
[2025-01-18 18:36:25 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][20/312]	eta 0:03:31 lr 0.002936	time 0.6033 (0.7246)	model_time 0.6031 (0.6219)	loss 3.3850 (3.4610)	grad_norm 1.5525 (1.2181/0.3333)	mem 24308MB
[2025-01-18 18:36:31 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][30/312]	eta 0:03:13 lr 0.002936	time 0.5870 (0.6850)	model_time 0.5868 (0.6153)	loss 3.9404 (3.4508)	grad_norm 2.8956 (1.3920/0.5147)	mem 24308MB
[2025-01-18 18:36:37 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][40/312]	eta 0:03:00 lr 0.002935	time 0.5842 (0.6653)	model_time 0.5841 (0.6126)	loss 2.8500 (3.4114)	grad_norm 1.1473 (1.4341/0.4923)	mem 24308MB
[2025-01-18 18:36:43 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][50/312]	eta 0:02:51 lr 0.002934	time 0.5890 (0.6530)	model_time 0.5886 (0.6105)	loss 2.9197 (3.3860)	grad_norm 1.2663 (1.4577/0.5613)	mem 24308MB
[2025-01-18 18:36:49 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][60/312]	eta 0:02:41 lr 0.002934	time 0.5842 (0.6422)	model_time 0.5840 (0.6067)	loss 2.9556 (3.4090)	grad_norm 0.9225 (1.4267/0.5300)	mem 24308MB
[2025-01-18 18:36:55 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][70/312]	eta 0:02:33 lr 0.002933	time 0.5964 (0.6351)	model_time 0.5959 (0.6045)	loss 3.2377 (3.4140)	grad_norm 1.4773 (1.4284/0.5355)	mem 24308MB
[2025-01-18 18:37:00 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][80/312]	eta 0:02:26 lr 0.002933	time 0.6298 (0.6296)	model_time 0.6297 (0.6027)	loss 3.1784 (3.4178)	grad_norm 2.1590 (1.5157/0.6194)	mem 24308MB
[2025-01-18 18:37:06 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][90/312]	eta 0:02:18 lr 0.002932	time 0.5790 (0.6255)	model_time 0.5789 (0.6015)	loss 4.0256 (3.4151)	grad_norm 1.7052 (1.5168/0.6094)	mem 24308MB
[2025-01-18 18:37:13 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][100/312]	eta 0:02:12 lr 0.002931	time 0.5852 (0.6251)	model_time 0.5847 (0.6033)	loss 3.4590 (3.4079)	grad_norm 1.8389 (1.5089/0.5883)	mem 24308MB
[2025-01-18 18:37:19 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][110/312]	eta 0:02:06 lr 0.002931	time 0.6977 (0.6252)	model_time 0.6976 (0.6054)	loss 2.1353 (3.3894)	grad_norm 1.1004 (1.5191/0.5790)	mem 24308MB
[2025-01-18 18:37:25 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][120/312]	eta 0:02:00 lr 0.002930	time 0.6435 (0.6251)	model_time 0.6433 (0.6069)	loss 3.6855 (3.4185)	grad_norm 1.2503 (1.5321/0.5809)	mem 24308MB
[2025-01-18 18:37:31 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][130/312]	eta 0:01:53 lr 0.002930	time 0.6874 (0.6261)	model_time 0.6872 (0.6093)	loss 3.6988 (3.4414)	grad_norm 1.9950 (1.5321/0.5705)	mem 24308MB
[2025-01-18 18:37:38 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][140/312]	eta 0:01:47 lr 0.002929	time 0.5790 (0.6252)	model_time 0.5788 (0.6095)	loss 3.6336 (3.4465)	grad_norm 2.0815 (1.5607/0.5774)	mem 24308MB
[2025-01-18 18:37:44 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][150/312]	eta 0:01:41 lr 0.002928	time 0.5726 (0.6236)	model_time 0.5721 (0.6089)	loss 3.0595 (3.4403)	grad_norm 1.1283 (1.5439/0.5684)	mem 24308MB
[2025-01-18 18:37:50 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][160/312]	eta 0:01:34 lr 0.002928	time 0.5920 (0.6226)	model_time 0.5915 (0.6088)	loss 3.4060 (3.4376)	grad_norm 1.0194 (1.5405/0.5658)	mem 24308MB
[2025-01-18 18:37:56 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][170/312]	eta 0:01:28 lr 0.002927	time 0.5904 (0.6212)	model_time 0.5900 (0.6082)	loss 2.4317 (3.4310)	grad_norm 2.0669 (1.5501/0.5596)	mem 24308MB
[2025-01-18 18:38:02 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][180/312]	eta 0:01:21 lr 0.002927	time 0.5748 (0.6195)	model_time 0.5747 (0.6072)	loss 2.5617 (3.4298)	grad_norm 1.7251 (1.5533/0.5655)	mem 24308MB
[2025-01-18 18:38:07 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][190/312]	eta 0:01:15 lr 0.002926	time 0.5931 (0.6177)	model_time 0.5926 (0.6060)	loss 3.9013 (3.4472)	grad_norm 1.2049 (1.5349/0.5612)	mem 24308MB
[2025-01-18 18:38:13 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][200/312]	eta 0:01:09 lr 0.002926	time 0.5909 (0.6165)	model_time 0.5904 (0.6053)	loss 3.4956 (3.4531)	grad_norm 0.7945 (1.5140/0.5588)	mem 24308MB
[2025-01-18 18:38:19 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][210/312]	eta 0:01:02 lr 0.002925	time 0.5883 (0.6155)	model_time 0.5881 (0.6048)	loss 3.6349 (3.4470)	grad_norm 1.4188 (1.5096/0.5502)	mem 24308MB
[2025-01-18 18:38:25 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][220/312]	eta 0:00:56 lr 0.002924	time 0.5787 (0.6153)	model_time 0.5783 (0.6052)	loss 3.5531 (3.4497)	grad_norm 0.9821 (1.5052/0.5448)	mem 24308MB
[2025-01-18 18:38:32 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][230/312]	eta 0:00:50 lr 0.002924	time 0.6819 (0.6166)	model_time 0.6818 (0.6069)	loss 4.0013 (3.4541)	grad_norm 1.0824 (1.4928/0.5512)	mem 24308MB
[2025-01-18 18:38:38 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][240/312]	eta 0:00:44 lr 0.002923	time 0.6790 (0.6171)	model_time 0.6786 (0.6078)	loss 2.5169 (3.4538)	grad_norm 1.4068 (1.5044/0.5478)	mem 24308MB
[2025-01-18 18:38:44 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][250/312]	eta 0:00:38 lr 0.002923	time 0.6521 (0.6173)	model_time 0.6520 (0.6083)	loss 2.4762 (3.4478)	grad_norm 1.7256 (1.5025/0.5434)	mem 24308MB
[2025-01-18 18:38:51 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][260/312]	eta 0:00:32 lr 0.002922	time 0.7088 (0.6178)	model_time 0.7083 (0.6091)	loss 3.7142 (3.4436)	grad_norm 1.2412 (1.5100/0.5376)	mem 24308MB
[2025-01-18 18:38:57 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][270/312]	eta 0:00:25 lr 0.002921	time 0.5834 (0.6171)	model_time 0.5830 (0.6087)	loss 3.5760 (3.4531)	grad_norm 0.7609 (1.5072/0.5413)	mem 24308MB
[2025-01-18 18:39:03 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][280/312]	eta 0:00:19 lr 0.002921	time 0.5769 (0.6168)	model_time 0.5764 (0.6087)	loss 3.6606 (3.4602)	grad_norm 1.3209 (1.5187/0.5623)	mem 24308MB
[2025-01-18 18:39:09 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][290/312]	eta 0:00:13 lr 0.002920	time 0.6756 (0.6162)	model_time 0.6755 (0.6084)	loss 2.2718 (3.4650)	grad_norm 1.9868 (1.5201/0.5601)	mem 24308MB
[2025-01-18 18:39:15 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][300/312]	eta 0:00:07 lr 0.002920	time 0.5871 (0.6150)	model_time 0.5870 (0.6074)	loss 3.2371 (3.4638)	grad_norm 1.7312 (1.5182/0.5574)	mem 24308MB
[2025-01-18 18:39:20 internimage_s_1k_224] (main.py 510): INFO Train: [104/300][310/312]	eta 0:00:01 lr 0.002919	time 0.5702 (0.6140)	model_time 0.5701 (0.6066)	loss 3.5434 (3.4639)	grad_norm 1.3244 (1.5182/0.5571)	mem 24308MB
[2025-01-18 18:39:21 internimage_s_1k_224] (main.py 519): INFO EPOCH 104 training takes 0:03:11
[2025-01-18 18:39:21 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_104.pth saving......
[2025-01-18 18:39:23 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_104.pth saved !!!
[2025-01-18 18:39:30 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.371 (7.371)	Loss 0.8824 (0.8824)	Acc@1 80.762 (80.762)	Acc@5 96.143 (96.143)	Mem 24308MB
[2025-01-18 18:39:34 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.977)	Loss 1.2524 (1.0544)	Acc@1 71.899 (77.282)	Acc@5 91.748 (93.968)	Mem 24308MB
[2025-01-18 18:39:34 internimage_s_1k_224] (main.py 575): INFO [Epoch:104] * Acc@1 77.231 Acc@5 93.974
[2025-01-18 18:39:34 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.2%
[2025-01-18 18:39:34 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 18:39:36 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 18:39:36 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.23%
[2025-01-18 18:39:43 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.157 (7.157)	Loss 0.7885 (0.7885)	Acc@1 80.444 (80.444)	Acc@5 96.143 (96.143)	Mem 24308MB
[2025-01-18 18:39:46 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.957)	Loss 1.2030 (0.9591)	Acc@1 70.459 (76.758)	Acc@5 90.674 (93.728)	Mem 24308MB
[2025-01-18 18:39:46 internimage_s_1k_224] (main.py 575): INFO [Epoch:104] * Acc@1 76.687 Acc@5 93.776
[2025-01-18 18:39:46 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 76.7%
[2025-01-18 18:39:46 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 18:39:49 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 18:39:49 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 76.69%
[2025-01-18 18:39:51 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][0/312]	eta 0:12:13 lr 0.002919	time 2.3508 (2.3508)	model_time 0.6144 (0.6144)	loss 2.3492 (2.3492)	grad_norm 1.1821 (1.1821/0.0000)	mem 24308MB
[2025-01-18 18:39:57 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][10/312]	eta 0:03:46 lr 0.002918	time 0.5734 (0.7508)	model_time 0.5732 (0.5928)	loss 3.4105 (3.4097)	grad_norm 1.7373 (1.2853/0.4032)	mem 24308MB
[2025-01-18 18:40:03 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][20/312]	eta 0:03:18 lr 0.002918	time 0.5746 (0.6786)	model_time 0.5741 (0.5956)	loss 3.5742 (3.4753)	grad_norm 3.1677 (1.8160/0.9160)	mem 24308MB
[2025-01-18 18:40:09 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][30/312]	eta 0:03:05 lr 0.002917	time 0.6701 (0.6563)	model_time 0.6696 (0.6000)	loss 3.5754 (3.5018)	grad_norm 0.9202 (1.7852/0.8172)	mem 24308MB
[2025-01-18 18:40:15 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][40/312]	eta 0:02:55 lr 0.002917	time 0.6968 (0.6469)	model_time 0.6967 (0.6042)	loss 3.8549 (3.5082)	grad_norm 0.8813 (1.6872/0.7731)	mem 24308MB
[2025-01-18 18:40:21 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][50/312]	eta 0:02:47 lr 0.002916	time 0.5893 (0.6408)	model_time 0.5891 (0.6065)	loss 3.5949 (3.4890)	grad_norm 1.6018 (1.5821/0.7384)	mem 24308MB
[2025-01-18 18:40:28 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][60/312]	eta 0:02:41 lr 0.002915	time 0.6679 (0.6401)	model_time 0.6677 (0.6113)	loss 3.5573 (3.5070)	grad_norm 1.5027 (1.4945/0.7095)	mem 24308MB
[2025-01-18 18:40:34 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][70/312]	eta 0:02:34 lr 0.002915	time 0.5825 (0.6364)	model_time 0.5821 (0.6116)	loss 3.4137 (3.5600)	grad_norm 0.8402 (1.5114/0.6917)	mem 24308MB
[2025-01-18 18:40:40 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][80/312]	eta 0:02:26 lr 0.002914	time 0.6061 (0.6313)	model_time 0.6060 (0.6095)	loss 2.6084 (3.5429)	grad_norm 1.8579 (1.4996/0.6622)	mem 24308MB
[2025-01-18 18:40:46 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][90/312]	eta 0:02:19 lr 0.002914	time 0.5767 (0.6286)	model_time 0.5763 (0.6092)	loss 4.3793 (3.5806)	grad_norm 2.8850 (1.5254/0.6634)	mem 24308MB
[2025-01-18 18:40:52 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][100/312]	eta 0:02:12 lr 0.002913	time 0.5848 (0.6249)	model_time 0.5846 (0.6074)	loss 4.3408 (3.6009)	grad_norm 2.7914 (1.5829/0.7293)	mem 24308MB
[2025-01-18 18:40:58 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][110/312]	eta 0:02:05 lr 0.002912	time 0.5887 (0.6222)	model_time 0.5885 (0.6063)	loss 3.4340 (3.5848)	grad_norm 1.6126 (1.5653/0.7029)	mem 24308MB
[2025-01-18 18:41:04 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][120/312]	eta 0:01:58 lr 0.002912	time 0.5888 (0.6192)	model_time 0.5883 (0.6045)	loss 2.3383 (3.5542)	grad_norm 0.8826 (1.5321/0.6847)	mem 24308MB
[2025-01-18 18:41:09 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][130/312]	eta 0:01:52 lr 0.002911	time 0.5800 (0.6164)	model_time 0.5798 (0.6028)	loss 4.3162 (3.5403)	grad_norm 0.9537 (1.5149/0.6642)	mem 24308MB
[2025-01-18 18:41:15 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][140/312]	eta 0:01:45 lr 0.002911	time 0.5899 (0.6149)	model_time 0.5898 (0.6022)	loss 2.6864 (3.5307)	grad_norm 1.9283 (1.5221/0.6540)	mem 24308MB
[2025-01-18 18:41:22 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][150/312]	eta 0:01:39 lr 0.002910	time 0.6703 (0.6153)	model_time 0.6701 (0.6034)	loss 4.1167 (3.5322)	grad_norm 1.4022 (1.5296/0.6525)	mem 24308MB
[2025-01-18 18:41:28 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][160/312]	eta 0:01:33 lr 0.002909	time 0.5747 (0.6143)	model_time 0.5746 (0.6031)	loss 3.7574 (3.5318)	grad_norm 1.6630 (1.5434/0.6468)	mem 24308MB
[2025-01-18 18:41:34 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][170/312]	eta 0:01:27 lr 0.002909	time 0.5773 (0.6146)	model_time 0.5772 (0.6041)	loss 4.4926 (3.5208)	grad_norm 1.2023 (1.5339/0.6318)	mem 24308MB
[2025-01-18 18:41:40 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][180/312]	eta 0:01:21 lr 0.002908	time 0.6689 (0.6150)	model_time 0.6684 (0.6050)	loss 3.5385 (3.5407)	grad_norm 0.5951 (1.5398/0.6345)	mem 24308MB
[2025-01-18 18:41:46 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][190/312]	eta 0:01:15 lr 0.002908	time 0.7046 (0.6159)	model_time 0.7044 (0.6065)	loss 2.8021 (3.5353)	grad_norm 1.2878 (1.5388/0.6282)	mem 24308MB
[2025-01-18 18:41:52 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][200/312]	eta 0:01:08 lr 0.002907	time 0.5994 (0.6147)	model_time 0.5989 (0.6057)	loss 3.7039 (3.5239)	grad_norm 1.9389 (1.5525/0.6276)	mem 24308MB
[2025-01-18 18:41:58 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][210/312]	eta 0:01:02 lr 0.002906	time 0.5981 (0.6149)	model_time 0.5979 (0.6063)	loss 3.8609 (3.5196)	grad_norm 1.1799 (1.5411/0.6194)	mem 24308MB
[2025-01-18 18:42:04 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][220/312]	eta 0:00:56 lr 0.002906	time 0.5900 (0.6136)	model_time 0.5896 (0.6054)	loss 3.4882 (3.5085)	grad_norm 1.2435 (1.5448/0.6100)	mem 24308MB
[2025-01-18 18:42:10 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][230/312]	eta 0:00:50 lr 0.002905	time 0.5742 (0.6129)	model_time 0.5740 (0.6050)	loss 3.5029 (3.5034)	grad_norm 1.1932 (1.5415/0.6025)	mem 24308MB
[2025-01-18 18:42:16 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][240/312]	eta 0:00:44 lr 0.002905	time 0.5843 (0.6119)	model_time 0.5842 (0.6043)	loss 4.0796 (3.4988)	grad_norm 3.9883 (1.5475/0.6202)	mem 24308MB
[2025-01-18 18:42:22 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][250/312]	eta 0:00:37 lr 0.002904	time 0.6011 (0.6107)	model_time 0.6009 (0.6035)	loss 3.3290 (3.5108)	grad_norm 1.8129 (1.5686/0.6342)	mem 24308MB
[2025-01-18 18:42:28 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][260/312]	eta 0:00:31 lr 0.002903	time 0.5813 (0.6102)	model_time 0.5808 (0.6032)	loss 4.1703 (3.5044)	grad_norm 2.8274 (1.5913/0.6756)	mem 24308MB
[2025-01-18 18:42:34 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][270/312]	eta 0:00:25 lr 0.002903	time 0.5785 (0.6103)	model_time 0.5784 (0.6035)	loss 3.7816 (3.5138)	grad_norm 1.1545 (1.5767/0.6689)	mem 24308MB
[2025-01-18 18:42:40 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][280/312]	eta 0:00:19 lr 0.002902	time 0.5823 (0.6105)	model_time 0.5821 (0.6039)	loss 3.8051 (3.5140)	grad_norm 1.3875 (1.5569/0.6663)	mem 24308MB
[2025-01-18 18:42:47 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][290/312]	eta 0:00:13 lr 0.002902	time 0.6537 (0.6110)	model_time 0.6536 (0.6047)	loss 4.3703 (3.5281)	grad_norm 0.7830 (1.5675/0.6812)	mem 24308MB
[2025-01-18 18:42:53 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][300/312]	eta 0:00:07 lr 0.002901	time 0.5670 (0.6109)	model_time 0.5670 (0.6047)	loss 4.1295 (3.5341)	grad_norm 1.5978 (1.5650/0.6810)	mem 24308MB
[2025-01-18 18:42:59 internimage_s_1k_224] (main.py 510): INFO Train: [105/300][310/312]	eta 0:00:01 lr 0.002900	time 0.5640 (0.6110)	model_time 0.5637 (0.6050)	loss 2.9788 (3.5210)	grad_norm 0.9711 (1.5592/0.6831)	mem 24308MB
[2025-01-18 18:42:59 internimage_s_1k_224] (main.py 519): INFO EPOCH 105 training takes 0:03:10
[2025-01-18 18:42:59 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_105.pth saving......
[2025-01-18 18:43:01 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_105.pth saved !!!
[2025-01-18 18:43:08 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.265 (7.265)	Loss 0.9137 (0.9137)	Acc@1 81.104 (81.104)	Acc@5 96.094 (96.094)	Mem 24308MB
[2025-01-18 18:43:12 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.961)	Loss 1.2476 (1.0675)	Acc@1 72.632 (77.517)	Acc@5 91.797 (94.052)	Mem 24308MB
[2025-01-18 18:43:12 internimage_s_1k_224] (main.py 575): INFO [Epoch:105] * Acc@1 77.449 Acc@5 94.092
[2025-01-18 18:43:12 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.4%
[2025-01-18 18:43:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 18:43:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 18:43:14 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.45%
[2025-01-18 18:43:21 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.303 (7.303)	Loss 0.7848 (0.7848)	Acc@1 80.591 (80.591)	Acc@5 96.094 (96.094)	Mem 24308MB
[2025-01-18 18:43:24 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.967)	Loss 1.1964 (0.9543)	Acc@1 70.508 (76.853)	Acc@5 90.771 (93.768)	Mem 24308MB
[2025-01-18 18:43:24 internimage_s_1k_224] (main.py 575): INFO [Epoch:105] * Acc@1 76.793 Acc@5 93.818
[2025-01-18 18:43:24 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 76.8%
[2025-01-18 18:43:24 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 18:43:27 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 18:43:27 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 76.79%
[2025-01-18 18:43:29 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][0/312]	eta 0:11:32 lr 0.002900	time 2.2180 (2.2180)	model_time 0.6128 (0.6128)	loss 2.8139 (2.8139)	grad_norm 1.0731 (1.0731/0.0000)	mem 24308MB
[2025-01-18 18:43:35 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][10/312]	eta 0:03:45 lr 0.002900	time 0.5887 (0.7483)	model_time 0.5885 (0.6017)	loss 3.2982 (3.5449)	grad_norm 1.0480 (1.6457/0.8751)	mem 24308MB
[2025-01-18 18:43:41 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][20/312]	eta 0:03:19 lr 0.002899	time 0.5954 (0.6829)	model_time 0.5952 (0.6060)	loss 3.4150 (3.5826)	grad_norm 1.9612 (1.6276/0.7198)	mem 24308MB
[2025-01-18 18:43:47 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][30/312]	eta 0:03:04 lr 0.002899	time 0.5722 (0.6536)	model_time 0.5717 (0.6013)	loss 3.1715 (3.5493)	grad_norm 1.7882 (1.6962/0.6832)	mem 24308MB
[2025-01-18 18:43:53 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][40/312]	eta 0:02:54 lr 0.002898	time 0.6131 (0.6407)	model_time 0.6127 (0.6011)	loss 4.1803 (3.6308)	grad_norm 1.5198 (1.6336/0.6359)	mem 24308MB
[2025-01-18 18:43:59 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][50/312]	eta 0:02:45 lr 0.002897	time 0.5810 (0.6300)	model_time 0.5808 (0.5981)	loss 3.7364 (3.6022)	grad_norm 1.5170 (1.6483/0.5926)	mem 24308MB
[2025-01-18 18:44:05 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][60/312]	eta 0:02:37 lr 0.002897	time 0.5865 (0.6234)	model_time 0.5861 (0.5967)	loss 3.5725 (3.5763)	grad_norm 1.0854 (1.5986/0.5997)	mem 24308MB
[2025-01-18 18:44:11 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][70/312]	eta 0:02:30 lr 0.002896	time 0.6688 (0.6203)	model_time 0.6687 (0.5973)	loss 2.4114 (3.5000)	grad_norm 3.0801 (1.7162/0.6789)	mem 24308MB
[2025-01-18 18:44:17 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][80/312]	eta 0:02:23 lr 0.002896	time 0.5725 (0.6191)	model_time 0.5720 (0.5989)	loss 3.8808 (3.4775)	grad_norm 1.1356 (1.6998/0.6699)	mem 24308MB
[2025-01-18 18:44:23 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][90/312]	eta 0:02:17 lr 0.002895	time 0.6290 (0.6199)	model_time 0.6286 (0.6019)	loss 3.6229 (3.4910)	grad_norm 1.1879 (1.6667/0.6444)	mem 24308MB
[2025-01-18 18:44:29 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][100/312]	eta 0:02:11 lr 0.002894	time 0.5808 (0.6199)	model_time 0.5806 (0.6037)	loss 2.5855 (3.4936)	grad_norm 0.8791 (1.6386/0.6348)	mem 24308MB
[2025-01-18 18:44:36 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][110/312]	eta 0:02:05 lr 0.002894	time 0.6538 (0.6195)	model_time 0.6534 (0.6046)	loss 4.4060 (3.4929)	grad_norm 1.8114 (1.6089/0.6196)	mem 24308MB
[2025-01-18 18:44:42 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][120/312]	eta 0:01:59 lr 0.002893	time 0.5881 (0.6200)	model_time 0.5877 (0.6063)	loss 3.4773 (3.4915)	grad_norm 3.2024 (1.6305/0.6312)	mem 24308MB
[2025-01-18 18:44:48 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][130/312]	eta 0:01:52 lr 0.002893	time 0.5790 (0.6185)	model_time 0.5788 (0.6059)	loss 3.2443 (3.4873)	grad_norm 0.8423 (1.6395/0.6336)	mem 24308MB
[2025-01-18 18:44:54 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][140/312]	eta 0:01:46 lr 0.002892	time 0.6694 (0.6185)	model_time 0.6693 (0.6067)	loss 3.1663 (3.4730)	grad_norm 3.0229 (1.6500/0.6380)	mem 24308MB
[2025-01-18 18:45:00 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][150/312]	eta 0:01:39 lr 0.002891	time 0.6055 (0.6163)	model_time 0.6053 (0.6053)	loss 3.2638 (3.4622)	grad_norm 2.0405 (1.6716/0.6922)	mem 24308MB
[2025-01-18 18:45:06 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][160/312]	eta 0:01:33 lr 0.002891	time 0.5766 (0.6153)	model_time 0.5762 (0.6050)	loss 3.4063 (3.4650)	grad_norm 1.1884 (1.6461/0.6855)	mem 24308MB
[2025-01-18 18:45:12 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][170/312]	eta 0:01:27 lr 0.002890	time 0.5834 (0.6139)	model_time 0.5832 (0.6041)	loss 4.3526 (3.4874)	grad_norm 2.6159 (1.6609/0.6847)	mem 24308MB
[2025-01-18 18:45:18 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][180/312]	eta 0:01:20 lr 0.002890	time 0.5766 (0.6124)	model_time 0.5762 (0.6032)	loss 3.8251 (3.4827)	grad_norm 1.2364 (1.6619/0.6842)	mem 24308MB
[2025-01-18 18:45:24 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][190/312]	eta 0:01:14 lr 0.002889	time 0.5833 (0.6113)	model_time 0.5831 (0.6025)	loss 4.0264 (3.4873)	grad_norm 1.7151 (1.6397/0.6803)	mem 24308MB
[2025-01-18 18:45:30 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][200/312]	eta 0:01:08 lr 0.002888	time 0.6081 (0.6118)	model_time 0.6076 (0.6035)	loss 3.2080 (3.4910)	grad_norm 0.9329 (1.6142/0.6753)	mem 24308MB
[2025-01-18 18:45:36 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][210/312]	eta 0:01:02 lr 0.002888	time 0.5767 (0.6133)	model_time 0.5763 (0.6053)	loss 4.4284 (3.4933)	grad_norm 1.7862 (1.6124/0.6721)	mem 24308MB
[2025-01-18 18:45:43 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][220/312]	eta 0:00:56 lr 0.002887	time 0.6678 (0.6147)	model_time 0.6676 (0.6071)	loss 3.2911 (3.5034)	grad_norm 1.0466 (1.6360/0.6996)	mem 24308MB
[2025-01-18 18:45:49 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][230/312]	eta 0:00:50 lr 0.002887	time 0.5801 (0.6145)	model_time 0.5800 (0.6072)	loss 3.8749 (3.5078)	grad_norm 0.7743 (1.6089/0.6984)	mem 24308MB
[2025-01-18 18:45:55 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][240/312]	eta 0:00:44 lr 0.002886	time 0.6575 (0.6150)	model_time 0.6571 (0.6080)	loss 3.4989 (3.5098)	grad_norm 1.8454 (1.6186/0.6998)	mem 24308MB
[2025-01-18 18:46:01 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][250/312]	eta 0:00:38 lr 0.002885	time 0.5783 (0.6142)	model_time 0.5778 (0.6075)	loss 3.7764 (3.5202)	grad_norm 1.3040 (1.6270/0.7068)	mem 24308MB
[2025-01-18 18:46:07 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][260/312]	eta 0:00:31 lr 0.002885	time 0.6734 (0.6139)	model_time 0.6733 (0.6074)	loss 2.9328 (3.5253)	grad_norm 1.5227 (1.6336/0.7046)	mem 24308MB
[2025-01-18 18:46:13 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][270/312]	eta 0:00:25 lr 0.002884	time 0.5964 (0.6136)	model_time 0.5962 (0.6073)	loss 3.2302 (3.5237)	grad_norm 1.0903 (1.6380/0.7042)	mem 24308MB
[2025-01-18 18:46:19 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][280/312]	eta 0:00:19 lr 0.002884	time 0.5748 (0.6128)	model_time 0.5746 (0.6067)	loss 3.7390 (3.5289)	grad_norm 0.9470 (1.6181/0.7017)	mem 24308MB
[2025-01-18 18:46:25 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][290/312]	eta 0:00:13 lr 0.002883	time 0.5779 (0.6122)	model_time 0.5778 (0.6063)	loss 4.2560 (3.5233)	grad_norm 1.7600 (1.6110/0.6953)	mem 24308MB
[2025-01-18 18:46:31 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][300/312]	eta 0:00:07 lr 0.002882	time 0.6277 (0.6115)	model_time 0.6276 (0.6058)	loss 2.9151 (3.5112)	grad_norm 2.2900 (1.6103/0.6895)	mem 24308MB
[2025-01-18 18:46:37 internimage_s_1k_224] (main.py 510): INFO Train: [106/300][310/312]	eta 0:00:01 lr 0.002882	time 0.5750 (0.6102)	model_time 0.5748 (0.6047)	loss 3.3614 (3.5155)	grad_norm 0.8374 (1.6251/0.6931)	mem 24308MB
[2025-01-18 18:46:37 internimage_s_1k_224] (main.py 519): INFO EPOCH 106 training takes 0:03:10
[2025-01-18 18:46:37 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_106.pth saving......
[2025-01-18 18:46:39 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_106.pth saved !!!
[2025-01-18 18:46:46 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.876 (6.876)	Loss 0.8727 (0.8727)	Acc@1 81.152 (81.152)	Acc@5 96.069 (96.069)	Mem 24308MB
[2025-01-18 18:46:49 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.902)	Loss 1.2544 (1.0383)	Acc@1 72.485 (77.401)	Acc@5 91.919 (94.025)	Mem 24308MB
[2025-01-18 18:46:49 internimage_s_1k_224] (main.py 575): INFO [Epoch:106] * Acc@1 77.323 Acc@5 94.006
[2025-01-18 18:46:49 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.3%
[2025-01-18 18:46:49 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.45%
[2025-01-18 18:46:57 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.011 (8.011)	Loss 0.7815 (0.7815)	Acc@1 80.737 (80.737)	Acc@5 96.143 (96.143)	Mem 24308MB
[2025-01-18 18:47:01 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.078)	Loss 1.1900 (0.9497)	Acc@1 70.630 (76.935)	Acc@5 90.918 (93.825)	Mem 24308MB
[2025-01-18 18:47:01 internimage_s_1k_224] (main.py 575): INFO [Epoch:106] * Acc@1 76.881 Acc@5 93.870
[2025-01-18 18:47:01 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 76.9%
[2025-01-18 18:47:01 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 18:47:04 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 18:47:04 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 76.88%
[2025-01-18 18:47:06 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][0/312]	eta 0:13:11 lr 0.002882	time 2.5365 (2.5365)	model_time 0.6089 (0.6089)	loss 3.5999 (3.5999)	grad_norm 2.5636 (2.5636/0.0000)	mem 24308MB
[2025-01-18 18:47:12 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][10/312]	eta 0:04:01 lr 0.002881	time 0.5806 (0.8007)	model_time 0.5804 (0.6252)	loss 2.8017 (3.4620)	grad_norm 1.8746 (1.7852/0.7232)	mem 24308MB
[2025-01-18 18:47:18 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][20/312]	eta 0:03:27 lr 0.002881	time 0.5907 (0.7114)	model_time 0.5756 (0.6186)	loss 2.9520 (3.4335)	grad_norm 1.5021 (1.8779/0.6426)	mem 24308MB
[2025-01-18 18:47:25 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][30/312]	eta 0:03:12 lr 0.002880	time 0.6715 (0.6829)	model_time 0.6711 (0.6199)	loss 2.2488 (3.3064)	grad_norm 1.1046 (1.6925/0.6339)	mem 24308MB
[2025-01-18 18:47:31 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][40/312]	eta 0:03:00 lr 0.002879	time 0.5789 (0.6651)	model_time 0.5787 (0.6174)	loss 3.1789 (3.3269)	grad_norm 1.5933 (1.6143/0.6044)	mem 24308MB
[2025-01-18 18:47:37 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][50/312]	eta 0:02:52 lr 0.002879	time 0.6875 (0.6583)	model_time 0.6871 (0.6199)	loss 3.1953 (3.3381)	grad_norm 0.6723 (1.5689/0.6095)	mem 24308MB
[2025-01-18 18:47:43 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][60/312]	eta 0:02:44 lr 0.002878	time 0.5858 (0.6513)	model_time 0.5857 (0.6191)	loss 3.7416 (3.3597)	grad_norm 0.9085 (1.5317/0.5996)	mem 24308MB
[2025-01-18 18:47:49 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][70/312]	eta 0:02:35 lr 0.002878	time 0.5802 (0.6443)	model_time 0.5801 (0.6166)	loss 3.9764 (3.3624)	grad_norm 1.7735 (1.5173/0.5681)	mem 24308MB
[2025-01-18 18:47:55 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][80/312]	eta 0:02:28 lr 0.002877	time 0.6023 (0.6391)	model_time 0.6018 (0.6148)	loss 4.4830 (3.3880)	grad_norm 1.4697 (1.4939/0.5431)	mem 24308MB
[2025-01-18 18:48:01 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][90/312]	eta 0:02:20 lr 0.002876	time 0.6917 (0.6345)	model_time 0.6916 (0.6129)	loss 4.1882 (3.4420)	grad_norm 0.9558 (1.5090/0.5478)	mem 24308MB
[2025-01-18 18:48:07 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][100/312]	eta 0:02:13 lr 0.002876	time 0.5959 (0.6298)	model_time 0.5957 (0.6102)	loss 3.7682 (3.4799)	grad_norm 1.0574 (1.4929/0.5371)	mem 24308MB
[2025-01-18 18:48:13 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][110/312]	eta 0:02:06 lr 0.002875	time 0.5874 (0.6266)	model_time 0.5872 (0.6088)	loss 3.7783 (3.4616)	grad_norm 1.1436 (1.5225/0.5840)	mem 24308MB
[2025-01-18 18:48:19 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][120/312]	eta 0:01:59 lr 0.002875	time 0.5729 (0.6241)	model_time 0.5727 (0.6077)	loss 3.6380 (3.4806)	grad_norm 1.8673 (1.5289/0.5719)	mem 24308MB
[2025-01-18 18:48:25 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][130/312]	eta 0:01:53 lr 0.002874	time 0.5780 (0.6241)	model_time 0.5779 (0.6089)	loss 3.6599 (3.4916)	grad_norm 1.0538 (1.5132/0.5628)	mem 24308MB
[2025-01-18 18:48:31 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][140/312]	eta 0:01:47 lr 0.002873	time 0.5797 (0.6232)	model_time 0.5795 (0.6091)	loss 3.5407 (3.4950)	grad_norm 1.7834 (1.5326/0.5730)	mem 24308MB
[2025-01-18 18:48:38 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][150/312]	eta 0:01:40 lr 0.002873	time 0.6754 (0.6228)	model_time 0.6752 (0.6096)	loss 3.7229 (3.5023)	grad_norm 0.7721 (1.5468/0.5893)	mem 24308MB
[2025-01-18 18:48:44 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][160/312]	eta 0:01:34 lr 0.002872	time 0.6027 (0.6215)	model_time 0.6022 (0.6091)	loss 3.8197 (3.5070)	grad_norm 2.0219 (1.5351/0.5884)	mem 24308MB
[2025-01-18 18:48:50 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][170/312]	eta 0:01:28 lr 0.002872	time 0.5847 (0.6228)	model_time 0.5845 (0.6111)	loss 3.5014 (3.5032)	grad_norm 0.8576 (1.5230/0.5822)	mem 24308MB
[2025-01-18 18:48:56 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][180/312]	eta 0:01:22 lr 0.002871	time 0.6001 (0.6236)	model_time 0.5999 (0.6126)	loss 3.5220 (3.5142)	grad_norm 0.9267 (1.5248/0.5967)	mem 24308MB
[2025-01-18 18:49:02 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][190/312]	eta 0:01:15 lr 0.002870	time 0.5852 (0.6221)	model_time 0.5850 (0.6116)	loss 3.6422 (3.5179)	grad_norm 1.9890 (1.5234/0.5970)	mem 24308MB
[2025-01-18 18:49:08 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][200/312]	eta 0:01:09 lr 0.002870	time 0.5714 (0.6214)	model_time 0.5708 (0.6114)	loss 3.5559 (3.5192)	grad_norm 2.9675 (1.5660/0.6332)	mem 24308MB
[2025-01-18 18:49:14 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][210/312]	eta 0:01:03 lr 0.002869	time 0.5900 (0.6200)	model_time 0.5899 (0.6104)	loss 3.6079 (3.5248)	grad_norm 1.1377 (1.5585/0.6297)	mem 24308MB
[2025-01-18 18:49:20 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][220/312]	eta 0:00:56 lr 0.002869	time 0.5806 (0.6188)	model_time 0.5804 (0.6096)	loss 2.3919 (3.5242)	grad_norm 1.4766 (1.5427/0.6220)	mem 24308MB
[2025-01-18 18:49:26 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][230/312]	eta 0:00:50 lr 0.002868	time 0.5969 (0.6176)	model_time 0.5964 (0.6089)	loss 3.6155 (3.5393)	grad_norm 1.1356 (1.5252/0.6157)	mem 24308MB
[2025-01-18 18:49:32 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][240/312]	eta 0:00:44 lr 0.002867	time 0.5845 (0.6164)	model_time 0.5840 (0.6080)	loss 3.7956 (3.5379)	grad_norm 1.3768 (1.5327/0.6170)	mem 24308MB
[2025-01-18 18:49:38 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][250/312]	eta 0:00:38 lr 0.002867	time 0.6576 (0.6165)	model_time 0.6574 (0.6084)	loss 3.0279 (3.5389)	grad_norm 1.7969 (1.5510/0.6307)	mem 24308MB
[2025-01-18 18:49:44 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][260/312]	eta 0:00:32 lr 0.002866	time 0.6014 (0.6159)	model_time 0.6012 (0.6082)	loss 2.6043 (3.5223)	grad_norm 1.5424 (1.5382/0.6231)	mem 24308MB
[2025-01-18 18:49:50 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][270/312]	eta 0:00:25 lr 0.002866	time 0.6558 (0.6157)	model_time 0.6556 (0.6082)	loss 3.1075 (3.5162)	grad_norm 1.1199 (1.5297/0.6182)	mem 24308MB
[2025-01-18 18:49:57 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][280/312]	eta 0:00:19 lr 0.002865	time 0.5782 (0.6156)	model_time 0.5781 (0.6084)	loss 3.4022 (3.5172)	grad_norm 1.3419 (1.5286/0.6112)	mem 24308MB
[2025-01-18 18:50:03 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][290/312]	eta 0:00:13 lr 0.002864	time 0.5822 (0.6165)	model_time 0.5818 (0.6095)	loss 3.6647 (3.5193)	grad_norm 2.3089 (1.5171/0.6093)	mem 24308MB
[2025-01-18 18:50:09 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][300/312]	eta 0:00:07 lr 0.002864	time 0.6482 (0.6164)	model_time 0.6481 (0.6096)	loss 2.1386 (3.5128)	grad_norm 1.2212 (1.5336/0.6296)	mem 24308MB
[2025-01-18 18:50:15 internimage_s_1k_224] (main.py 510): INFO Train: [107/300][310/312]	eta 0:00:01 lr 0.002863	time 0.5701 (0.6152)	model_time 0.5700 (0.6086)	loss 3.5124 (3.5087)	grad_norm 1.4308 (1.5348/0.6238)	mem 24308MB
[2025-01-18 18:50:15 internimage_s_1k_224] (main.py 519): INFO EPOCH 107 training takes 0:03:11
[2025-01-18 18:50:15 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_107.pth saving......
[2025-01-18 18:50:17 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_107.pth saved !!!
[2025-01-18 18:50:24 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.087 (7.087)	Loss 0.8893 (0.8893)	Acc@1 81.396 (81.396)	Acc@5 95.825 (95.825)	Mem 24308MB
[2025-01-18 18:50:28 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.930)	Loss 1.2021 (1.0217)	Acc@1 72.681 (77.468)	Acc@5 91.821 (93.999)	Mem 24308MB
[2025-01-18 18:50:28 internimage_s_1k_224] (main.py 575): INFO [Epoch:107] * Acc@1 77.337 Acc@5 94.026
[2025-01-18 18:50:28 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.3%
[2025-01-18 18:50:28 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.45%
[2025-01-18 18:50:36 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.058 (8.058)	Loss 0.7780 (0.7780)	Acc@1 80.835 (80.835)	Acc@5 96.143 (96.143)	Mem 24308MB
[2025-01-18 18:50:40 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.091)	Loss 1.1838 (0.9453)	Acc@1 70.703 (77.022)	Acc@5 90.991 (93.879)	Mem 24308MB
[2025-01-18 18:50:40 internimage_s_1k_224] (main.py 575): INFO [Epoch:107] * Acc@1 76.959 Acc@5 93.924
[2025-01-18 18:50:40 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 77.0%
[2025-01-18 18:50:40 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 18:50:42 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 18:50:42 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 76.96%
[2025-01-18 18:50:45 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][0/312]	eta 0:12:02 lr 0.002863	time 2.3157 (2.3157)	model_time 0.6083 (0.6083)	loss 3.7860 (3.7860)	grad_norm 0.8867 (0.8867/0.0000)	mem 24308MB
[2025-01-18 18:50:51 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][10/312]	eta 0:03:48 lr 0.002862	time 0.5918 (0.7572)	model_time 0.5917 (0.6017)	loss 3.7387 (3.4315)	grad_norm 1.2566 (1.6401/0.5506)	mem 24308MB
[2025-01-18 18:50:57 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][20/312]	eta 0:03:18 lr 0.002862	time 0.6008 (0.6806)	model_time 0.6006 (0.5990)	loss 3.2709 (3.4145)	grad_norm 0.9629 (1.5221/0.5415)	mem 24308MB
[2025-01-18 18:51:03 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][30/312]	eta 0:03:03 lr 0.002861	time 0.5934 (0.6516)	model_time 0.5932 (0.5963)	loss 3.7405 (3.3096)	grad_norm 2.6768 (1.5254/0.6229)	mem 24308MB
[2025-01-18 18:51:08 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][40/312]	eta 0:02:53 lr 0.002861	time 0.5825 (0.6380)	model_time 0.5823 (0.5961)	loss 3.4743 (3.3476)	grad_norm 1.9657 (1.5106/0.5706)	mem 24308MB
[2025-01-18 18:51:14 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][50/312]	eta 0:02:44 lr 0.002860	time 0.5782 (0.6282)	model_time 0.5777 (0.5945)	loss 3.5329 (3.4352)	grad_norm 1.2672 (1.4611/0.5419)	mem 24308MB
[2025-01-18 18:51:21 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][60/312]	eta 0:02:37 lr 0.002859	time 0.5734 (0.6263)	model_time 0.5732 (0.5980)	loss 3.2831 (3.3966)	grad_norm 2.0274 (1.4897/0.5278)	mem 24308MB
[2025-01-18 18:51:27 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][70/312]	eta 0:02:31 lr 0.002859	time 0.5919 (0.6243)	model_time 0.5917 (0.6000)	loss 2.3830 (3.3798)	grad_norm 1.4420 (1.4632/0.5073)	mem 24308MB
[2025-01-18 18:51:33 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][80/312]	eta 0:02:24 lr 0.002858	time 0.5870 (0.6218)	model_time 0.5866 (0.6004)	loss 3.8474 (3.3917)	grad_norm 1.3684 (1.4280/0.4911)	mem 24308MB
[2025-01-18 18:51:39 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][90/312]	eta 0:02:17 lr 0.002858	time 0.5806 (0.6209)	model_time 0.5802 (0.6018)	loss 3.9998 (3.3655)	grad_norm 2.4241 (1.4528/0.4980)	mem 24308MB
[2025-01-18 18:51:45 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][100/312]	eta 0:02:11 lr 0.002857	time 0.6603 (0.6215)	model_time 0.6602 (0.6043)	loss 3.9145 (3.3700)	grad_norm 1.4209 (1.4709/0.4961)	mem 24308MB
[2025-01-18 18:51:51 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][110/312]	eta 0:02:05 lr 0.002856	time 0.5782 (0.6207)	model_time 0.5778 (0.6050)	loss 3.6794 (3.4119)	grad_norm 2.3843 (1.5599/0.6164)	mem 24308MB
[2025-01-18 18:51:57 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][120/312]	eta 0:01:58 lr 0.002856	time 0.5961 (0.6189)	model_time 0.5960 (0.6044)	loss 3.6489 (3.4134)	grad_norm 1.7106 (1.5541/0.6069)	mem 24308MB
[2025-01-18 18:52:03 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][130/312]	eta 0:01:52 lr 0.002855	time 0.6308 (0.6181)	model_time 0.6307 (0.6047)	loss 3.7567 (3.4176)	grad_norm 2.6517 (1.5904/0.6539)	mem 24308MB
[2025-01-18 18:52:09 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][140/312]	eta 0:01:46 lr 0.002855	time 0.5815 (0.6163)	model_time 0.5814 (0.6039)	loss 3.9454 (3.4265)	grad_norm 1.0413 (1.5753/0.6406)	mem 24308MB
[2025-01-18 18:52:15 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][150/312]	eta 0:01:39 lr 0.002854	time 0.5831 (0.6150)	model_time 0.5827 (0.6034)	loss 3.9167 (3.4353)	grad_norm 1.1382 (1.5563/0.6346)	mem 24308MB
[2025-01-18 18:52:21 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][160/312]	eta 0:01:33 lr 0.002853	time 0.5766 (0.6131)	model_time 0.5762 (0.6021)	loss 3.6145 (3.4459)	grad_norm 3.8914 (1.5721/0.6559)	mem 24308MB
[2025-01-18 18:52:27 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][170/312]	eta 0:01:26 lr 0.002853	time 0.5755 (0.6116)	model_time 0.5752 (0.6013)	loss 3.2278 (3.4675)	grad_norm 1.1218 (1.5546/0.6461)	mem 24308MB
[2025-01-18 18:52:33 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][180/312]	eta 0:01:20 lr 0.002852	time 0.5923 (0.6118)	model_time 0.5919 (0.6020)	loss 3.5967 (3.4799)	grad_norm 1.5923 (1.5711/0.6729)	mem 24308MB
[2025-01-18 18:52:39 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][190/312]	eta 0:01:14 lr 0.002852	time 0.5855 (0.6116)	model_time 0.5854 (0.6023)	loss 3.8088 (3.4764)	grad_norm 1.5137 (1.5892/0.6739)	mem 24308MB
[2025-01-18 18:52:45 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][200/312]	eta 0:01:08 lr 0.002851	time 0.5986 (0.6115)	model_time 0.5984 (0.6027)	loss 3.8527 (3.4877)	grad_norm 2.2559 (1.6074/0.6716)	mem 24308MB
[2025-01-18 18:52:51 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][210/312]	eta 0:01:02 lr 0.002850	time 0.6498 (0.6115)	model_time 0.6496 (0.6031)	loss 2.1706 (3.4759)	grad_norm 2.9988 (1.6093/0.6702)	mem 24308MB
[2025-01-18 18:52:58 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][220/312]	eta 0:00:56 lr 0.002850	time 0.6811 (0.6132)	model_time 0.6809 (0.6052)	loss 3.2280 (3.4625)	grad_norm 0.9798 (1.6180/0.6880)	mem 24308MB
[2025-01-18 18:53:04 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][230/312]	eta 0:00:50 lr 0.002849	time 0.5852 (0.6130)	model_time 0.5850 (0.6053)	loss 4.1873 (3.4612)	grad_norm 2.7729 (1.6117/0.6870)	mem 24308MB
[2025-01-18 18:53:10 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][240/312]	eta 0:00:44 lr 0.002849	time 0.5768 (0.6127)	model_time 0.5763 (0.6052)	loss 3.0441 (3.4654)	grad_norm 0.7915 (1.5929/0.6819)	mem 24308MB
[2025-01-18 18:53:16 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][250/312]	eta 0:00:37 lr 0.002848	time 0.5703 (0.6125)	model_time 0.5701 (0.6054)	loss 3.5762 (3.4559)	grad_norm 1.7976 (1.5899/0.6787)	mem 24308MB
[2025-01-18 18:53:22 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][260/312]	eta 0:00:31 lr 0.002847	time 0.5794 (0.6119)	model_time 0.5792 (0.6050)	loss 2.3391 (3.4386)	grad_norm 1.8862 (1.6109/0.6968)	mem 24308MB
[2025-01-18 18:53:28 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][270/312]	eta 0:00:25 lr 0.002847	time 0.5732 (0.6112)	model_time 0.5730 (0.6046)	loss 2.9560 (3.4462)	grad_norm 1.7320 (1.5911/0.6936)	mem 24308MB
[2025-01-18 18:53:34 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][280/312]	eta 0:00:19 lr 0.002846	time 0.5754 (0.6103)	model_time 0.5749 (0.6039)	loss 4.2605 (3.4489)	grad_norm 2.8670 (1.6103/0.7020)	mem 24308MB
[2025-01-18 18:53:40 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][290/312]	eta 0:00:13 lr 0.002846	time 0.5962 (0.6098)	model_time 0.5958 (0.6036)	loss 3.5644 (3.4443)	grad_norm 2.0857 (1.6091/0.6981)	mem 24308MB
[2025-01-18 18:53:46 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][300/312]	eta 0:00:07 lr 0.002845	time 0.6409 (0.6096)	model_time 0.6408 (0.6035)	loss 2.5523 (3.4399)	grad_norm 1.7661 (1.6054/0.6887)	mem 24308MB
[2025-01-18 18:53:52 internimage_s_1k_224] (main.py 510): INFO Train: [108/300][310/312]	eta 0:00:01 lr 0.002844	time 0.5733 (0.6086)	model_time 0.5732 (0.6028)	loss 3.4565 (3.4471)	grad_norm 2.1217 (1.5921/0.6896)	mem 24308MB
[2025-01-18 18:53:52 internimage_s_1k_224] (main.py 519): INFO EPOCH 108 training takes 0:03:09
[2025-01-18 18:53:52 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_108.pth saving......
[2025-01-18 18:53:54 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_108.pth saved !!!
[2025-01-18 18:54:01 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.786 (6.786)	Loss 0.8995 (0.8995)	Acc@1 80.737 (80.737)	Acc@5 96.118 (96.118)	Mem 24308MB
[2025-01-18 18:54:04 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.898)	Loss 1.2228 (1.0470)	Acc@1 72.729 (77.623)	Acc@5 91.943 (94.161)	Mem 24308MB
[2025-01-18 18:54:04 internimage_s_1k_224] (main.py 575): INFO [Epoch:108] * Acc@1 77.521 Acc@5 94.206
[2025-01-18 18:54:04 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.5%
[2025-01-18 18:54:04 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 18:54:06 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 18:54:06 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.52%
[2025-01-18 18:54:13 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.646 (6.646)	Loss 0.7742 (0.7742)	Acc@1 80.908 (80.908)	Acc@5 96.289 (96.289)	Mem 24308MB
[2025-01-18 18:54:16 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.866)	Loss 1.1780 (0.9410)	Acc@1 70.801 (77.135)	Acc@5 90.991 (93.948)	Mem 24308MB
[2025-01-18 18:54:16 internimage_s_1k_224] (main.py 575): INFO [Epoch:108] * Acc@1 77.067 Acc@5 93.990
[2025-01-18 18:54:16 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 77.1%
[2025-01-18 18:54:16 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 18:54:18 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 18:54:18 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 77.07%
[2025-01-18 18:54:21 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][0/312]	eta 0:12:54 lr 0.002844	time 2.4822 (2.4822)	model_time 0.5965 (0.5965)	loss 2.7627 (2.7627)	grad_norm 1.7797 (1.7797/0.0000)	mem 24308MB
[2025-01-18 18:54:27 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][10/312]	eta 0:03:58 lr 0.002844	time 0.5763 (0.7902)	model_time 0.5762 (0.6186)	loss 2.8285 (3.3715)	grad_norm 1.0568 (1.2361/0.2429)	mem 24308MB
[2025-01-18 18:54:33 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][20/312]	eta 0:03:26 lr 0.002843	time 0.5739 (0.7075)	model_time 0.5737 (0.6174)	loss 3.0317 (3.3923)	grad_norm 1.4604 (1.2482/0.3129)	mem 24308MB
[2025-01-18 18:54:40 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][30/312]	eta 0:03:14 lr 0.002842	time 0.5936 (0.6909)	model_time 0.5934 (0.6297)	loss 2.7799 (3.4316)	grad_norm 1.0516 (1.2787/0.3687)	mem 24308MB
[2025-01-18 18:54:46 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][40/312]	eta 0:03:02 lr 0.002842	time 0.6676 (0.6723)	model_time 0.6674 (0.6260)	loss 3.4646 (3.4410)	grad_norm 2.2648 (1.3535/0.4505)	mem 24308MB
[2025-01-18 18:54:52 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][50/312]	eta 0:02:52 lr 0.002841	time 0.5772 (0.6570)	model_time 0.5771 (0.6197)	loss 4.2142 (3.4349)	grad_norm 1.3214 (1.4460/0.4814)	mem 24308MB
[2025-01-18 18:54:58 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][60/312]	eta 0:02:43 lr 0.002841	time 0.6430 (0.6492)	model_time 0.6426 (0.6179)	loss 3.1811 (3.4609)	grad_norm 1.1557 (1.4332/0.4495)	mem 24308MB
[2025-01-18 18:55:04 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][70/312]	eta 0:02:35 lr 0.002840	time 0.6019 (0.6419)	model_time 0.6014 (0.6150)	loss 3.1464 (3.4592)	grad_norm 1.1061 (1.4978/0.5889)	mem 24308MB
[2025-01-18 18:55:10 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][80/312]	eta 0:02:27 lr 0.002839	time 0.5921 (0.6363)	model_time 0.5916 (0.6126)	loss 3.9832 (3.4342)	grad_norm 2.0235 (1.6204/0.7374)	mem 24308MB
[2025-01-18 18:55:16 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][90/312]	eta 0:02:20 lr 0.002839	time 0.5816 (0.6310)	model_time 0.5814 (0.6098)	loss 4.3733 (3.4672)	grad_norm 1.4209 (1.5908/0.7077)	mem 24308MB
[2025-01-18 18:55:22 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][100/312]	eta 0:02:13 lr 0.002838	time 0.5731 (0.6275)	model_time 0.5727 (0.6084)	loss 3.3862 (3.4411)	grad_norm 1.6415 (1.5749/0.6813)	mem 24308MB
[2025-01-18 18:55:28 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][110/312]	eta 0:02:06 lr 0.002838	time 0.5834 (0.6253)	model_time 0.5833 (0.6079)	loss 3.8638 (3.4465)	grad_norm 1.8497 (1.5724/0.6646)	mem 24308MB
[2025-01-18 18:55:34 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][120/312]	eta 0:01:59 lr 0.002837	time 0.5755 (0.6236)	model_time 0.5753 (0.6076)	loss 3.1565 (3.4455)	grad_norm 0.9713 (1.5325/0.6524)	mem 24308MB
[2025-01-18 18:55:40 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][130/312]	eta 0:01:53 lr 0.002836	time 0.5911 (0.6232)	model_time 0.5907 (0.6084)	loss 3.5199 (3.4601)	grad_norm 1.2577 (1.5079/0.6383)	mem 24308MB
[2025-01-18 18:55:46 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][140/312]	eta 0:01:47 lr 0.002836	time 0.5860 (0.6231)	model_time 0.5859 (0.6093)	loss 3.1758 (3.4461)	grad_norm 1.1845 (1.5237/0.6366)	mem 24308MB
[2025-01-18 18:55:53 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][150/312]	eta 0:01:40 lr 0.002835	time 0.5813 (0.6228)	model_time 0.5808 (0.6099)	loss 4.0994 (3.4620)	grad_norm 1.0549 (1.5461/0.6478)	mem 24308MB
[2025-01-18 18:55:59 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][160/312]	eta 0:01:34 lr 0.002835	time 0.6575 (0.6225)	model_time 0.6573 (0.6103)	loss 2.3771 (3.4565)	grad_norm 2.3788 (1.5488/0.6481)	mem 24308MB
[2025-01-18 18:56:05 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][170/312]	eta 0:01:28 lr 0.002834	time 0.5853 (0.6208)	model_time 0.5851 (0.6093)	loss 3.5800 (3.4400)	grad_norm 2.0732 (1.5504/0.6498)	mem 24308MB
[2025-01-18 18:56:11 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][180/312]	eta 0:01:21 lr 0.002833	time 0.5839 (0.6192)	model_time 0.5837 (0.6083)	loss 3.5675 (3.4605)	grad_norm 1.1104 (1.5407/0.6377)	mem 24308MB
[2025-01-18 18:56:17 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][190/312]	eta 0:01:15 lr 0.002833	time 0.6282 (0.6188)	model_time 0.6280 (0.6084)	loss 2.4512 (3.4394)	grad_norm 1.3466 (1.5363/0.6268)	mem 24308MB
[2025-01-18 18:56:23 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][200/312]	eta 0:01:09 lr 0.002832	time 0.5820 (0.6177)	model_time 0.5819 (0.6078)	loss 3.9936 (3.4379)	grad_norm 1.1247 (1.5375/0.6192)	mem 24308MB
[2025-01-18 18:56:28 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][210/312]	eta 0:01:02 lr 0.002832	time 0.5749 (0.6161)	model_time 0.5748 (0.6067)	loss 3.5876 (3.4339)	grad_norm 1.2983 (1.5379/0.6106)	mem 24308MB
[2025-01-18 18:56:34 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][220/312]	eta 0:00:56 lr 0.002831	time 0.5875 (0.6151)	model_time 0.5870 (0.6062)	loss 3.7426 (3.4125)	grad_norm 2.0492 (1.5331/0.6069)	mem 24308MB
[2025-01-18 18:56:40 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][230/312]	eta 0:00:50 lr 0.002830	time 0.5924 (0.6145)	model_time 0.5922 (0.6059)	loss 3.6110 (3.4245)	grad_norm 0.9382 (1.5335/0.5977)	mem 24308MB
[2025-01-18 18:56:47 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][240/312]	eta 0:00:44 lr 0.002830	time 0.5749 (0.6144)	model_time 0.5747 (0.6061)	loss 3.6699 (3.4211)	grad_norm 2.0403 (1.5266/0.5906)	mem 24308MB
[2025-01-18 18:56:53 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][250/312]	eta 0:00:38 lr 0.002829	time 0.6642 (0.6142)	model_time 0.6640 (0.6063)	loss 3.2353 (3.4208)	grad_norm 1.2014 (1.5174/0.5888)	mem 24308MB
[2025-01-18 18:56:59 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][260/312]	eta 0:00:31 lr 0.002828	time 0.5748 (0.6151)	model_time 0.5744 (0.6074)	loss 4.2952 (3.4241)	grad_norm 1.5477 (1.5245/0.5941)	mem 24308MB
[2025-01-18 18:57:05 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][270/312]	eta 0:00:25 lr 0.002828	time 0.5776 (0.6156)	model_time 0.5772 (0.6082)	loss 3.5395 (3.4303)	grad_norm 0.8793 (1.5171/0.5877)	mem 24308MB
[2025-01-18 18:57:12 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][280/312]	eta 0:00:19 lr 0.002827	time 0.6886 (0.6159)	model_time 0.6879 (0.6088)	loss 3.7412 (3.4350)	grad_norm 2.4030 (1.5106/0.5858)	mem 24308MB
[2025-01-18 18:57:18 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][290/312]	eta 0:00:13 lr 0.002827	time 0.6297 (0.6154)	model_time 0.6295 (0.6085)	loss 3.3230 (3.4313)	grad_norm 3.6926 (1.5306/0.6129)	mem 24308MB
[2025-01-18 18:57:23 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][300/312]	eta 0:00:07 lr 0.002826	time 0.5712 (0.6146)	model_time 0.5710 (0.6078)	loss 2.9250 (3.4388)	grad_norm 1.6409 (1.5477/0.6296)	mem 24308MB
[2025-01-18 18:57:29 internimage_s_1k_224] (main.py 510): INFO Train: [109/300][310/312]	eta 0:00:01 lr 0.002825	time 0.5721 (0.6139)	model_time 0.5720 (0.6073)	loss 4.0617 (3.4443)	grad_norm 1.2516 (1.5516/0.6284)	mem 24308MB
[2025-01-18 18:57:30 internimage_s_1k_224] (main.py 519): INFO EPOCH 109 training takes 0:03:11
[2025-01-18 18:57:30 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_109.pth saving......
[2025-01-18 18:57:32 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_109.pth saved !!!
[2025-01-18 18:57:39 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.921 (6.921)	Loss 0.8970 (0.8970)	Acc@1 80.322 (80.322)	Acc@5 96.216 (96.216)	Mem 24308MB
[2025-01-18 18:57:42 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.916)	Loss 1.2565 (1.0424)	Acc@1 72.607 (77.506)	Acc@5 91.235 (94.172)	Mem 24308MB
[2025-01-18 18:57:42 internimage_s_1k_224] (main.py 575): INFO [Epoch:109] * Acc@1 77.449 Acc@5 94.214
[2025-01-18 18:57:42 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.4%
[2025-01-18 18:57:42 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.52%
[2025-01-18 18:57:50 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.052 (8.052)	Loss 0.7709 (0.7709)	Acc@1 80.933 (80.933)	Acc@5 96.338 (96.338)	Mem 24308MB
[2025-01-18 18:57:54 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.094)	Loss 1.1723 (0.9368)	Acc@1 71.094 (77.246)	Acc@5 91.138 (93.996)	Mem 24308MB
[2025-01-18 18:57:54 internimage_s_1k_224] (main.py 575): INFO [Epoch:109] * Acc@1 77.173 Acc@5 94.038
[2025-01-18 18:57:54 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 77.2%
[2025-01-18 18:57:54 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 18:57:57 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 18:57:57 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 77.17%
[2025-01-18 18:57:59 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][0/312]	eta 0:12:20 lr 0.002825	time 2.3735 (2.3735)	model_time 0.5980 (0.5980)	loss 3.7002 (3.7002)	grad_norm 1.3274 (1.3274/0.0000)	mem 24308MB
[2025-01-18 18:58:05 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][10/312]	eta 0:03:48 lr 0.002825	time 0.5749 (0.7582)	model_time 0.5747 (0.5965)	loss 3.3039 (3.5965)	grad_norm 1.3344 (1.5962/0.7310)	mem 24308MB
[2025-01-18 18:58:11 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][20/312]	eta 0:03:18 lr 0.002824	time 0.5760 (0.6782)	model_time 0.5758 (0.5934)	loss 2.6759 (3.4301)	grad_norm 1.7546 (1.5974/0.6028)	mem 24308MB
[2025-01-18 18:58:17 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][30/312]	eta 0:03:04 lr 0.002824	time 0.5894 (0.6559)	model_time 0.5888 (0.5984)	loss 3.7882 (3.3968)	grad_norm 0.9264 (1.4625/0.5703)	mem 24308MB
[2025-01-18 18:58:23 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][40/312]	eta 0:02:55 lr 0.002823	time 0.6780 (0.6439)	model_time 0.6779 (0.6003)	loss 3.7698 (3.4465)	grad_norm 1.7395 (1.4942/0.5819)	mem 24308MB
[2025-01-18 18:58:29 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][50/312]	eta 0:02:46 lr 0.002822	time 0.6737 (0.6359)	model_time 0.6735 (0.6007)	loss 3.5511 (3.5002)	grad_norm 1.5523 (1.5415/0.5612)	mem 24308MB
[2025-01-18 18:58:35 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][60/312]	eta 0:02:39 lr 0.002822	time 0.6537 (0.6322)	model_time 0.6536 (0.6027)	loss 3.5480 (3.5138)	grad_norm 2.1722 (1.6579/0.7030)	mem 24308MB
[2025-01-18 18:58:41 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][70/312]	eta 0:02:32 lr 0.002821	time 0.5866 (0.6303)	model_time 0.5864 (0.6049)	loss 2.7452 (3.5047)	grad_norm 1.0986 (1.6505/0.6934)	mem 24308MB
[2025-01-18 18:58:48 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][80/312]	eta 0:02:26 lr 0.002820	time 0.5802 (0.6310)	model_time 0.5798 (0.6087)	loss 3.5124 (3.5115)	grad_norm 1.3017 (1.6647/0.6864)	mem 24308MB
[2025-01-18 18:58:54 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][90/312]	eta 0:02:19 lr 0.002820	time 0.6745 (0.6286)	model_time 0.6743 (0.6087)	loss 3.5080 (3.5147)	grad_norm 1.7377 (1.6732/0.6647)	mem 24308MB
[2025-01-18 18:59:00 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][100/312]	eta 0:02:12 lr 0.002819	time 0.5985 (0.6260)	model_time 0.5980 (0.6081)	loss 4.1063 (3.4954)	grad_norm 0.8221 (1.6298/0.6502)	mem 24308MB
[2025-01-18 18:59:06 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][110/312]	eta 0:02:05 lr 0.002819	time 0.5739 (0.6234)	model_time 0.5738 (0.6071)	loss 3.6648 (3.4865)	grad_norm 0.8739 (1.5824/0.6436)	mem 24308MB
[2025-01-18 18:59:12 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][120/312]	eta 0:01:59 lr 0.002818	time 0.5839 (0.6217)	model_time 0.5838 (0.6067)	loss 3.5537 (3.4796)	grad_norm 1.4252 (1.5485/0.6292)	mem 24308MB
[2025-01-18 18:59:18 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][130/312]	eta 0:01:52 lr 0.002817	time 0.5824 (0.6196)	model_time 0.5822 (0.6057)	loss 3.7838 (3.4883)	grad_norm 1.1207 (1.5681/0.6320)	mem 24308MB
[2025-01-18 18:59:24 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][140/312]	eta 0:01:46 lr 0.002817	time 0.5741 (0.6173)	model_time 0.5739 (0.6044)	loss 2.5476 (3.4709)	grad_norm 1.1821 (1.5750/0.6236)	mem 24308MB
[2025-01-18 18:59:30 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][150/312]	eta 0:01:39 lr 0.002816	time 0.5890 (0.6167)	model_time 0.5889 (0.6047)	loss 3.4904 (3.4540)	grad_norm 1.2050 (1.5476/0.6133)	mem 24308MB
[2025-01-18 18:59:36 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][160/312]	eta 0:01:33 lr 0.002816	time 0.6576 (0.6160)	model_time 0.6575 (0.6047)	loss 3.9153 (3.4654)	grad_norm 2.4799 (1.5379/0.6076)	mem 24308MB
[2025-01-18 18:59:42 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][170/312]	eta 0:01:27 lr 0.002815	time 0.5796 (0.6149)	model_time 0.5792 (0.6042)	loss 4.2130 (3.4811)	grad_norm 1.1292 (1.5567/0.6106)	mem 24308MB
[2025-01-18 18:59:48 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][180/312]	eta 0:01:21 lr 0.002814	time 0.5846 (0.6146)	model_time 0.5845 (0.6044)	loss 2.9899 (3.4837)	grad_norm 1.2214 (1.5898/0.6321)	mem 24308MB
[2025-01-18 18:59:54 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][190/312]	eta 0:01:15 lr 0.002814	time 0.5792 (0.6154)	model_time 0.5791 (0.6058)	loss 3.2665 (3.4738)	grad_norm 1.1889 (1.6032/0.6422)	mem 24308MB
[2025-01-18 19:00:01 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][200/312]	eta 0:01:09 lr 0.002813	time 0.6660 (0.6178)	model_time 0.6656 (0.6086)	loss 2.6949 (3.4775)	grad_norm 1.3736 (1.6085/0.6393)	mem 24308MB
[2025-01-18 19:00:07 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][210/312]	eta 0:01:02 lr 0.002813	time 0.6741 (0.6176)	model_time 0.6740 (0.6088)	loss 4.0109 (3.4739)	grad_norm 1.7543 (1.6062/0.6323)	mem 24308MB
[2025-01-18 19:00:13 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][220/312]	eta 0:00:56 lr 0.002812	time 0.5776 (0.6170)	model_time 0.5772 (0.6086)	loss 3.0266 (3.4770)	grad_norm 0.9571 (1.5874/0.6289)	mem 24308MB
[2025-01-18 19:00:19 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][230/312]	eta 0:00:50 lr 0.002811	time 0.5873 (0.6160)	model_time 0.5871 (0.6080)	loss 4.2047 (3.4818)	grad_norm 0.7259 (1.5910/0.6433)	mem 24308MB
[2025-01-18 19:00:25 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][240/312]	eta 0:00:44 lr 0.002811	time 0.5725 (0.6152)	model_time 0.5723 (0.6075)	loss 3.6959 (3.4762)	grad_norm 1.0812 (1.6034/0.6624)	mem 24308MB
[2025-01-18 19:00:31 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][250/312]	eta 0:00:38 lr 0.002810	time 0.5772 (0.6145)	model_time 0.5767 (0.6070)	loss 3.6422 (3.4701)	grad_norm 0.9380 (1.5870/0.6585)	mem 24308MB
[2025-01-18 19:00:37 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][260/312]	eta 0:00:31 lr 0.002810	time 0.5821 (0.6133)	model_time 0.5816 (0.6062)	loss 3.3964 (3.4702)	grad_norm 2.0043 (1.5803/0.6520)	mem 24308MB
[2025-01-18 19:00:43 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][270/312]	eta 0:00:25 lr 0.002809	time 0.5855 (0.6131)	model_time 0.5850 (0.6062)	loss 3.8166 (3.4774)	grad_norm 3.0309 (1.5965/0.6633)	mem 24308MB
[2025-01-18 19:00:49 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][280/312]	eta 0:00:19 lr 0.002808	time 0.6347 (0.6126)	model_time 0.6345 (0.6059)	loss 2.5865 (3.4711)	grad_norm 2.1117 (1.6165/0.6740)	mem 24308MB
[2025-01-18 19:00:55 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][290/312]	eta 0:00:13 lr 0.002808	time 0.5740 (0.6121)	model_time 0.5739 (0.6056)	loss 3.3814 (3.4724)	grad_norm 0.8861 (1.6134/0.6681)	mem 24308MB
[2025-01-18 19:01:01 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][300/312]	eta 0:00:07 lr 0.002807	time 0.5681 (0.6120)	model_time 0.5680 (0.6058)	loss 3.6857 (3.4596)	grad_norm 0.9221 (1.5991/0.6646)	mem 24308MB
[2025-01-18 19:01:07 internimage_s_1k_224] (main.py 510): INFO Train: [110/300][310/312]	eta 0:00:01 lr 0.002806	time 0.5703 (0.6122)	model_time 0.5702 (0.6062)	loss 3.4512 (3.4541)	grad_norm 1.8176 (1.6045/0.6617)	mem 24308MB
[2025-01-18 19:01:08 internimage_s_1k_224] (main.py 519): INFO EPOCH 110 training takes 0:03:10
[2025-01-18 19:01:08 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_110.pth saving......
[2025-01-18 19:01:09 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_110.pth saved !!!
[2025-01-18 19:01:17 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.302 (7.302)	Loss 0.8848 (0.8848)	Acc@1 81.055 (81.055)	Acc@5 95.923 (95.923)	Mem 24308MB
[2025-01-18 19:01:20 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.946)	Loss 1.2414 (1.0324)	Acc@1 72.559 (77.464)	Acc@5 91.870 (94.218)	Mem 24308MB
[2025-01-18 19:01:20 internimage_s_1k_224] (main.py 575): INFO [Epoch:110] * Acc@1 77.463 Acc@5 94.260
[2025-01-18 19:01:20 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.5%
[2025-01-18 19:01:20 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.52%
[2025-01-18 19:01:28 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.173 (8.173)	Loss 0.7680 (0.7680)	Acc@1 81.079 (81.079)	Acc@5 96.387 (96.387)	Mem 24308MB
[2025-01-18 19:01:32 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.106)	Loss 1.1668 (0.9329)	Acc@1 71.338 (77.353)	Acc@5 91.260 (94.039)	Mem 24308MB
[2025-01-18 19:01:32 internimage_s_1k_224] (main.py 575): INFO [Epoch:110] * Acc@1 77.273 Acc@5 94.080
[2025-01-18 19:01:32 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 77.3%
[2025-01-18 19:01:32 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 19:01:35 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 19:01:35 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 77.27%
[2025-01-18 19:01:37 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][0/312]	eta 0:12:13 lr 0.002806	time 2.3523 (2.3523)	model_time 0.6119 (0.6119)	loss 3.7431 (3.7431)	grad_norm 1.0954 (1.0954/0.0000)	mem 24308MB
[2025-01-18 19:01:43 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][10/312]	eta 0:03:55 lr 0.002806	time 0.5740 (0.7807)	model_time 0.5736 (0.6221)	loss 3.8938 (3.1592)	grad_norm 2.1083 (1.4543/0.4376)	mem 24308MB
[2025-01-18 19:01:49 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][20/312]	eta 0:03:23 lr 0.002805	time 0.5724 (0.6966)	model_time 0.5722 (0.6134)	loss 3.7068 (3.2657)	grad_norm 1.3366 (1.4507/0.3879)	mem 24308MB
[2025-01-18 19:01:56 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][30/312]	eta 0:03:08 lr 0.002805	time 0.5921 (0.6689)	model_time 0.5919 (0.6124)	loss 3.8005 (3.2807)	grad_norm 2.2383 (1.4589/0.3860)	mem 24308MB
[2025-01-18 19:02:02 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][40/312]	eta 0:02:57 lr 0.002804	time 0.5920 (0.6520)	model_time 0.5916 (0.6092)	loss 3.2324 (3.3627)	grad_norm 2.7031 (1.5987/0.5549)	mem 24308MB
[2025-01-18 19:02:08 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][50/312]	eta 0:02:47 lr 0.002803	time 0.5735 (0.6405)	model_time 0.5733 (0.6061)	loss 3.5953 (3.3384)	grad_norm 1.0789 (1.6371/0.6291)	mem 24308MB
[2025-01-18 19:02:13 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][60/312]	eta 0:02:39 lr 0.002803	time 0.5860 (0.6334)	model_time 0.5855 (0.6045)	loss 3.7147 (3.4448)	grad_norm 1.3521 (1.5923/0.6153)	mem 24308MB
[2025-01-18 19:02:19 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][70/312]	eta 0:02:31 lr 0.002802	time 0.5940 (0.6278)	model_time 0.5939 (0.6030)	loss 4.3443 (3.4944)	grad_norm 0.7603 (1.5833/0.5918)	mem 24308MB
[2025-01-18 19:02:25 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][80/312]	eta 0:02:24 lr 0.002801	time 0.5883 (0.6245)	model_time 0.5879 (0.6026)	loss 3.7767 (3.5447)	grad_norm 1.1070 (1.5490/0.5867)	mem 24308MB
[2025-01-18 19:02:31 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][90/312]	eta 0:02:17 lr 0.002801	time 0.5852 (0.6205)	model_time 0.5851 (0.6011)	loss 3.3444 (3.5273)	grad_norm 1.2937 (1.5558/0.5753)	mem 24308MB
[2025-01-18 19:02:37 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][100/312]	eta 0:02:11 lr 0.002800	time 0.5824 (0.6191)	model_time 0.5822 (0.6015)	loss 4.1603 (3.5269)	grad_norm 1.2937 (1.5163/0.5624)	mem 24308MB
[2025-01-18 19:02:44 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][110/312]	eta 0:02:04 lr 0.002800	time 0.6043 (0.6184)	model_time 0.6038 (0.6024)	loss 3.7242 (3.5030)	grad_norm 1.0668 (1.5119/0.5733)	mem 24308MB
[2025-01-18 19:02:50 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][120/312]	eta 0:01:59 lr 0.002799	time 0.6703 (0.6198)	model_time 0.6698 (0.6050)	loss 4.2266 (3.5093)	grad_norm 1.0548 (1.5373/0.5781)	mem 24308MB
[2025-01-18 19:02:56 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][130/312]	eta 0:01:52 lr 0.002798	time 0.6834 (0.6203)	model_time 0.6833 (0.6066)	loss 3.2997 (3.5196)	grad_norm 1.5825 (1.5670/0.6277)	mem 24308MB
[2025-01-18 19:03:02 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][140/312]	eta 0:01:46 lr 0.002798	time 0.6549 (0.6191)	model_time 0.6548 (0.6062)	loss 4.1686 (3.5344)	grad_norm 1.8913 (1.6188/0.6460)	mem 24308MB
[2025-01-18 19:03:08 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][150/312]	eta 0:01:40 lr 0.002797	time 0.5716 (0.6180)	model_time 0.5711 (0.6059)	loss 3.3962 (3.5429)	grad_norm 0.9637 (1.6362/0.7063)	mem 24308MB
[2025-01-18 19:03:14 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][160/312]	eta 0:01:33 lr 0.002797	time 0.5843 (0.6168)	model_time 0.5842 (0.6054)	loss 3.3844 (3.5260)	grad_norm 1.6754 (1.6101/0.6980)	mem 24308MB
[2025-01-18 19:03:20 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][170/312]	eta 0:01:27 lr 0.002796	time 0.5893 (0.6157)	model_time 0.5891 (0.6050)	loss 3.6718 (3.5093)	grad_norm 1.2639 (1.5847/0.6877)	mem 24308MB
[2025-01-18 19:03:26 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][180/312]	eta 0:01:21 lr 0.002795	time 0.5757 (0.6149)	model_time 0.5753 (0.6048)	loss 4.4449 (3.5194)	grad_norm 1.1207 (1.5708/0.6764)	mem 24308MB
[2025-01-18 19:03:32 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][190/312]	eta 0:01:14 lr 0.002795	time 0.5942 (0.6135)	model_time 0.5938 (0.6039)	loss 2.9224 (3.5131)	grad_norm 0.7644 (1.5536/0.6755)	mem 24308MB
[2025-01-18 19:03:38 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][200/312]	eta 0:01:08 lr 0.002794	time 0.5815 (0.6124)	model_time 0.5814 (0.6032)	loss 3.6299 (3.5150)	grad_norm 1.4096 (1.5485/0.6665)	mem 24308MB
[2025-01-18 19:03:44 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][210/312]	eta 0:01:02 lr 0.002794	time 0.5834 (0.6112)	model_time 0.5832 (0.6024)	loss 4.0272 (3.5162)	grad_norm 0.8684 (1.5394/0.6599)	mem 24308MB
[2025-01-18 19:03:50 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][220/312]	eta 0:00:56 lr 0.002793	time 0.5859 (0.6111)	model_time 0.5855 (0.6027)	loss 4.4256 (3.5125)	grad_norm 1.0499 (1.5434/0.6639)	mem 24308MB
[2025-01-18 19:03:56 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][230/312]	eta 0:00:50 lr 0.002792	time 0.5971 (0.6111)	model_time 0.5970 (0.6031)	loss 3.6444 (3.5218)	grad_norm 1.3405 (1.5410/0.6616)	mem 24308MB
[2025-01-18 19:04:02 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][240/312]	eta 0:00:44 lr 0.002792	time 0.6432 (0.6119)	model_time 0.6427 (0.6042)	loss 3.5702 (3.5232)	grad_norm 2.2973 (1.5619/0.6576)	mem 24308MB
[2025-01-18 19:04:09 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][250/312]	eta 0:00:37 lr 0.002791	time 0.5823 (0.6123)	model_time 0.5819 (0.6049)	loss 3.3065 (3.5173)	grad_norm 1.2694 (1.5600/0.6552)	mem 24308MB
[2025-01-18 19:04:15 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][260/312]	eta 0:00:31 lr 0.002790	time 0.5992 (0.6127)	model_time 0.5991 (0.6056)	loss 3.6595 (3.5071)	grad_norm 1.5431 (1.5386/0.6544)	mem 24308MB
[2025-01-18 19:04:21 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][270/312]	eta 0:00:25 lr 0.002790	time 0.5892 (0.6127)	model_time 0.5890 (0.6058)	loss 4.1807 (3.5108)	grad_norm 1.2312 (1.5481/0.6584)	mem 24308MB
[2025-01-18 19:04:27 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][280/312]	eta 0:00:19 lr 0.002789	time 0.5893 (0.6124)	model_time 0.5888 (0.6057)	loss 4.0675 (3.5041)	grad_norm 3.1993 (1.5463/0.6565)	mem 24308MB
[2025-01-18 19:04:33 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][290/312]	eta 0:00:13 lr 0.002789	time 0.5732 (0.6117)	model_time 0.5728 (0.6053)	loss 3.1971 (3.5034)	grad_norm 2.3462 (1.5744/0.7195)	mem 24308MB
[2025-01-18 19:04:39 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][300/312]	eta 0:00:07 lr 0.002788	time 0.5677 (0.6108)	model_time 0.5675 (0.6046)	loss 3.0571 (3.5101)	grad_norm 1.1806 (1.5619/0.7143)	mem 24308MB
[2025-01-18 19:04:45 internimage_s_1k_224] (main.py 510): INFO Train: [111/300][310/312]	eta 0:00:01 lr 0.002787	time 0.5700 (0.6100)	model_time 0.5699 (0.6040)	loss 3.9149 (3.5010)	grad_norm 1.3804 (1.5711/0.7268)	mem 24308MB
[2025-01-18 19:04:45 internimage_s_1k_224] (main.py 519): INFO EPOCH 111 training takes 0:03:10
[2025-01-18 19:04:45 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_111.pth saving......
[2025-01-18 19:04:47 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_111.pth saved !!!
[2025-01-18 19:04:54 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.037 (7.037)	Loss 0.8795 (0.8795)	Acc@1 80.884 (80.884)	Acc@5 96.143 (96.143)	Mem 24308MB
[2025-01-18 19:04:57 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.925)	Loss 1.2177 (1.0325)	Acc@1 72.290 (77.566)	Acc@5 91.406 (94.154)	Mem 24308MB
[2025-01-18 19:04:57 internimage_s_1k_224] (main.py 575): INFO [Epoch:111] * Acc@1 77.571 Acc@5 94.216
[2025-01-18 19:04:57 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.6%
[2025-01-18 19:04:57 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 19:05:00 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 19:05:00 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.57%
[2025-01-18 19:05:07 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.026 (7.026)	Loss 0.7651 (0.7651)	Acc@1 81.152 (81.152)	Acc@5 96.411 (96.411)	Mem 24308MB
[2025-01-18 19:05:10 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.915)	Loss 1.1616 (0.9291)	Acc@1 71.484 (77.464)	Acc@5 91.357 (94.101)	Mem 24308MB
[2025-01-18 19:05:10 internimage_s_1k_224] (main.py 575): INFO [Epoch:111] * Acc@1 77.395 Acc@5 94.136
[2025-01-18 19:05:10 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 77.4%
[2025-01-18 19:05:10 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 19:05:12 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 19:05:12 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 77.40%
[2025-01-18 19:05:15 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][0/312]	eta 0:12:26 lr 0.002787	time 2.3910 (2.3910)	model_time 0.5908 (0.5908)	loss 3.9684 (3.9684)	grad_norm 3.2818 (3.2818/0.0000)	mem 24308MB
[2025-01-18 19:05:21 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][10/312]	eta 0:03:50 lr 0.002787	time 0.6693 (0.7617)	model_time 0.6691 (0.5978)	loss 4.2369 (3.7013)	grad_norm 1.2506 (1.8102/0.7284)	mem 24308MB
[2025-01-18 19:05:26 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][20/312]	eta 0:03:18 lr 0.002786	time 0.5740 (0.6789)	model_time 0.5738 (0.5929)	loss 3.9031 (3.6837)	grad_norm 1.4177 (1.7179/0.6504)	mem 24308MB
[2025-01-18 19:05:32 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][30/312]	eta 0:03:04 lr 0.002785	time 0.5718 (0.6550)	model_time 0.5716 (0.5966)	loss 3.4195 (3.6210)	grad_norm 0.9569 (1.5201/0.6293)	mem 24308MB
[2025-01-18 19:05:39 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][40/312]	eta 0:02:55 lr 0.002785	time 0.6388 (0.6460)	model_time 0.6383 (0.6018)	loss 3.4355 (3.4812)	grad_norm 1.3084 (1.5040/0.5694)	mem 24308MB
[2025-01-18 19:05:45 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][50/312]	eta 0:02:48 lr 0.002784	time 0.6885 (0.6424)	model_time 0.6880 (0.6067)	loss 4.3395 (3.4628)	grad_norm 1.2473 (1.4407/0.5391)	mem 24308MB
[2025-01-18 19:05:51 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][60/312]	eta 0:02:41 lr 0.002784	time 0.5790 (0.6393)	model_time 0.5788 (0.6095)	loss 3.4449 (3.4747)	grad_norm 1.7800 (1.4025/0.5243)	mem 24308MB
[2025-01-18 19:05:57 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][70/312]	eta 0:02:33 lr 0.002783	time 0.6681 (0.6355)	model_time 0.6679 (0.6098)	loss 3.9036 (3.4399)	grad_norm 2.6506 (1.4848/0.6056)	mem 24308MB
[2025-01-18 19:06:04 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][80/312]	eta 0:02:27 lr 0.002782	time 0.6439 (0.6342)	model_time 0.6434 (0.6116)	loss 3.4796 (3.4273)	grad_norm 0.8281 (1.4594/0.5805)	mem 24308MB
[2025-01-18 19:06:09 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][90/312]	eta 0:02:19 lr 0.002782	time 0.5791 (0.6298)	model_time 0.5787 (0.6097)	loss 3.8670 (3.4168)	grad_norm 1.0164 (1.4320/0.5631)	mem 24308MB
[2025-01-18 19:06:15 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][100/312]	eta 0:02:12 lr 0.002781	time 0.5772 (0.6270)	model_time 0.5771 (0.6088)	loss 2.3272 (3.4107)	grad_norm 2.2103 (1.4970/0.6341)	mem 24308MB
[2025-01-18 19:06:21 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][110/312]	eta 0:02:06 lr 0.002781	time 0.5931 (0.6248)	model_time 0.5930 (0.6082)	loss 3.5024 (3.4127)	grad_norm 0.8948 (1.5039/0.6423)	mem 24308MB
[2025-01-18 19:06:27 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][120/312]	eta 0:01:59 lr 0.002780	time 0.6003 (0.6215)	model_time 0.6002 (0.6063)	loss 2.2351 (3.4017)	grad_norm 1.2191 (1.5516/0.7304)	mem 24308MB
[2025-01-18 19:06:33 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][130/312]	eta 0:01:52 lr 0.002779	time 0.6698 (0.6194)	model_time 0.6694 (0.6053)	loss 2.9274 (3.4208)	grad_norm 1.5631 (1.5250/0.7140)	mem 24308MB
[2025-01-18 19:06:39 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][140/312]	eta 0:01:46 lr 0.002779	time 0.6001 (0.6176)	model_time 0.5999 (0.6043)	loss 3.0942 (3.4069)	grad_norm 1.3317 (1.5015/0.6974)	mem 24308MB
[2025-01-18 19:06:45 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][150/312]	eta 0:01:39 lr 0.002778	time 0.5908 (0.6169)	model_time 0.5903 (0.6045)	loss 4.4408 (3.4244)	grad_norm 2.4876 (1.5045/0.6850)	mem 24308MB
[2025-01-18 19:06:51 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][160/312]	eta 0:01:33 lr 0.002777	time 0.5721 (0.6166)	model_time 0.5719 (0.6049)	loss 2.8832 (3.4128)	grad_norm 2.7008 (1.5404/0.7047)	mem 24308MB
[2025-01-18 19:06:58 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][170/312]	eta 0:01:27 lr 0.002777	time 0.6578 (0.6169)	model_time 0.6576 (0.6059)	loss 3.6328 (3.4236)	grad_norm 2.4120 (1.5303/0.6965)	mem 24308MB
[2025-01-18 19:07:04 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][180/312]	eta 0:01:21 lr 0.002776	time 0.6527 (0.6197)	model_time 0.6525 (0.6093)	loss 3.8347 (3.4447)	grad_norm 1.9331 (1.5218/0.6889)	mem 24308MB
[2025-01-18 19:07:10 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][190/312]	eta 0:01:15 lr 0.002776	time 0.5948 (0.6192)	model_time 0.5943 (0.6094)	loss 3.4802 (3.4612)	grad_norm 4.9244 (1.5950/0.8192)	mem 24308MB
[2025-01-18 19:07:17 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][200/312]	eta 0:01:09 lr 0.002775	time 0.6045 (0.6189)	model_time 0.6043 (0.6095)	loss 3.6727 (3.4647)	grad_norm 1.7733 (1.6128/0.8192)	mem 24308MB
[2025-01-18 19:07:23 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][210/312]	eta 0:01:03 lr 0.002774	time 0.5813 (0.6180)	model_time 0.5809 (0.6091)	loss 3.8798 (3.4733)	grad_norm 1.0035 (1.5813/0.8127)	mem 24308MB
[2025-01-18 19:07:29 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][220/312]	eta 0:00:56 lr 0.002774	time 0.5742 (0.6170)	model_time 0.5741 (0.6085)	loss 3.7402 (3.4786)	grad_norm 1.0913 (1.5764/0.8020)	mem 24308MB
[2025-01-18 19:07:35 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][230/312]	eta 0:00:50 lr 0.002773	time 0.5780 (0.6163)	model_time 0.5779 (0.6081)	loss 4.0594 (3.4841)	grad_norm 0.9987 (1.5790/0.8062)	mem 24308MB
[2025-01-18 19:07:40 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][240/312]	eta 0:00:44 lr 0.002773	time 0.5949 (0.6152)	model_time 0.5947 (0.6073)	loss 4.0889 (3.4916)	grad_norm 2.2251 (1.5807/0.8023)	mem 24308MB
[2025-01-18 19:07:46 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][250/312]	eta 0:00:38 lr 0.002772	time 0.6880 (0.6145)	model_time 0.6879 (0.6069)	loss 3.4970 (3.4987)	grad_norm 1.0189 (1.5746/0.7921)	mem 24308MB
[2025-01-18 19:07:52 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][260/312]	eta 0:00:31 lr 0.002771	time 0.5733 (0.6135)	model_time 0.5729 (0.6061)	loss 4.2240 (3.5058)	grad_norm 1.0345 (1.5724/0.7815)	mem 24308MB
[2025-01-18 19:07:58 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][270/312]	eta 0:00:25 lr 0.002771	time 0.5774 (0.6133)	model_time 0.5773 (0.6062)	loss 3.9127 (3.5059)	grad_norm 0.8260 (1.5743/0.7821)	mem 24308MB
[2025-01-18 19:08:04 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][280/312]	eta 0:00:19 lr 0.002770	time 0.5926 (0.6132)	model_time 0.5924 (0.6064)	loss 3.6716 (3.5032)	grad_norm 1.4559 (1.5573/0.7742)	mem 24308MB
[2025-01-18 19:08:11 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][290/312]	eta 0:00:13 lr 0.002769	time 0.5923 (0.6129)	model_time 0.5919 (0.6064)	loss 3.5264 (3.5004)	grad_norm 2.2298 (1.5695/0.7798)	mem 24308MB
[2025-01-18 19:08:17 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][300/312]	eta 0:00:07 lr 0.002769	time 0.6438 (0.6138)	model_time 0.6437 (0.6074)	loss 4.4102 (3.5048)	grad_norm 2.1754 (1.5697/0.7741)	mem 24308MB
[2025-01-18 19:08:23 internimage_s_1k_224] (main.py 510): INFO Train: [112/300][310/312]	eta 0:00:01 lr 0.002768	time 0.5740 (0.6134)	model_time 0.5738 (0.6072)	loss 3.7854 (3.5166)	grad_norm 1.6254 (1.5632/0.7723)	mem 24308MB
[2025-01-18 19:08:23 internimage_s_1k_224] (main.py 519): INFO EPOCH 112 training takes 0:03:11
[2025-01-18 19:08:24 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_112.pth saving......
[2025-01-18 19:08:25 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_112.pth saved !!!
[2025-01-18 19:08:33 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.257 (7.257)	Loss 0.8702 (0.8702)	Acc@1 81.055 (81.055)	Acc@5 96.460 (96.460)	Mem 24308MB
[2025-01-18 19:08:36 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.954)	Loss 1.2403 (1.0357)	Acc@1 72.607 (77.921)	Acc@5 91.943 (94.254)	Mem 24308MB
[2025-01-18 19:08:36 internimage_s_1k_224] (main.py 575): INFO [Epoch:112] * Acc@1 77.851 Acc@5 94.324
[2025-01-18 19:08:36 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.9%
[2025-01-18 19:08:36 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 19:08:38 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 19:08:38 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.85%
[2025-01-18 19:08:45 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.123 (7.123)	Loss 0.7626 (0.7626)	Acc@1 81.274 (81.274)	Acc@5 96.460 (96.460)	Mem 24308MB
[2025-01-18 19:08:48 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.938)	Loss 1.1566 (0.9256)	Acc@1 71.655 (77.603)	Acc@5 91.577 (94.156)	Mem 24308MB
[2025-01-18 19:08:49 internimage_s_1k_224] (main.py 575): INFO [Epoch:112] * Acc@1 77.529 Acc@5 94.198
[2025-01-18 19:08:49 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 77.5%
[2025-01-18 19:08:49 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 19:08:51 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 19:08:51 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 77.53%
[2025-01-18 19:08:53 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][0/312]	eta 0:10:51 lr 0.002768	time 2.0867 (2.0867)	model_time 0.6017 (0.6017)	loss 4.0383 (4.0383)	grad_norm 1.2182 (1.2182/0.0000)	mem 24308MB
[2025-01-18 19:08:59 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][10/312]	eta 0:03:52 lr 0.002768	time 0.5791 (0.7691)	model_time 0.5790 (0.6339)	loss 3.5726 (3.3388)	grad_norm 2.3308 (1.8050/0.6644)	mem 24308MB
[2025-01-18 19:09:05 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][20/312]	eta 0:03:21 lr 0.002767	time 0.5864 (0.6898)	model_time 0.5859 (0.6188)	loss 2.5078 (3.2985)	grad_norm 1.1083 (1.7529/0.6885)	mem 24308MB
[2025-01-18 19:09:11 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][30/312]	eta 0:03:06 lr 0.002766	time 0.5816 (0.6600)	model_time 0.5814 (0.6117)	loss 2.6835 (3.2944)	grad_norm 1.4420 (1.7299/0.6661)	mem 24308MB
[2025-01-18 19:09:17 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][40/312]	eta 0:02:55 lr 0.002766	time 0.5786 (0.6451)	model_time 0.5784 (0.6086)	loss 3.2394 (3.2909)	grad_norm 2.3228 (1.6622/0.6240)	mem 24308MB
[2025-01-18 19:09:23 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][50/312]	eta 0:02:46 lr 0.002765	time 0.5823 (0.6352)	model_time 0.5821 (0.6058)	loss 2.4323 (3.3225)	grad_norm 3.4161 (1.7217/0.6950)	mem 24308MB
[2025-01-18 19:09:29 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][60/312]	eta 0:02:38 lr 0.002764	time 0.6002 (0.6284)	model_time 0.5998 (0.6037)	loss 3.8038 (3.3624)	grad_norm 1.9107 (1.7584/0.7954)	mem 24308MB
[2025-01-18 19:09:35 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][70/312]	eta 0:02:31 lr 0.002764	time 0.6265 (0.6243)	model_time 0.6260 (0.6031)	loss 3.3256 (3.3643)	grad_norm 1.3043 (1.7045/0.7640)	mem 24308MB
[2025-01-18 19:09:41 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][80/312]	eta 0:02:24 lr 0.002763	time 0.6204 (0.6233)	model_time 0.6202 (0.6046)	loss 2.7057 (3.3634)	grad_norm 1.4783 (1.6777/0.7286)	mem 24308MB
[2025-01-18 19:09:48 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][90/312]	eta 0:02:18 lr 0.002763	time 0.6709 (0.6219)	model_time 0.6708 (0.6052)	loss 3.4142 (3.3548)	grad_norm 3.5052 (1.6825/0.7361)	mem 24308MB
[2025-01-18 19:09:54 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][100/312]	eta 0:02:11 lr 0.002762	time 0.6521 (0.6214)	model_time 0.6520 (0.6063)	loss 2.8181 (3.3382)	grad_norm 1.2409 (1.7067/0.7744)	mem 24308MB
[2025-01-18 19:10:00 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][110/312]	eta 0:02:05 lr 0.002761	time 0.6631 (0.6221)	model_time 0.6629 (0.6084)	loss 4.1262 (3.3475)	grad_norm 1.5691 (1.6621/0.7595)	mem 24308MB
[2025-01-18 19:10:06 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][120/312]	eta 0:01:59 lr 0.002761	time 0.5861 (0.6214)	model_time 0.5860 (0.6088)	loss 3.2306 (3.3430)	grad_norm 1.5968 (1.6483/0.7458)	mem 24308MB
[2025-01-18 19:10:12 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][130/312]	eta 0:01:53 lr 0.002760	time 0.6845 (0.6216)	model_time 0.6844 (0.6100)	loss 4.3130 (3.3495)	grad_norm 1.5638 (1.6396/0.7330)	mem 24308MB
[2025-01-18 19:10:18 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][140/312]	eta 0:01:46 lr 0.002760	time 0.5837 (0.6202)	model_time 0.5836 (0.6094)	loss 2.2712 (3.3253)	grad_norm 1.1351 (1.6133/0.7228)	mem 24308MB
[2025-01-18 19:10:24 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][150/312]	eta 0:01:40 lr 0.002759	time 0.5776 (0.6190)	model_time 0.5774 (0.6088)	loss 2.2556 (3.3261)	grad_norm 1.2268 (1.5881/0.7077)	mem 24308MB
[2025-01-18 19:10:30 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][160/312]	eta 0:01:33 lr 0.002758	time 0.5758 (0.6176)	model_time 0.5756 (0.6080)	loss 3.4652 (3.3409)	grad_norm 1.1675 (1.5647/0.6931)	mem 24308MB
[2025-01-18 19:10:36 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][170/312]	eta 0:01:27 lr 0.002758	time 0.5757 (0.6167)	model_time 0.5752 (0.6077)	loss 2.9248 (3.3537)	grad_norm 1.1537 (1.5588/0.6935)	mem 24308MB
[2025-01-18 19:10:42 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][180/312]	eta 0:01:21 lr 0.002757	time 0.5875 (0.6151)	model_time 0.5873 (0.6066)	loss 3.5265 (3.3672)	grad_norm 1.2256 (1.5527/0.6810)	mem 24308MB
[2025-01-18 19:10:48 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][190/312]	eta 0:01:14 lr 0.002756	time 0.6171 (0.6145)	model_time 0.6170 (0.6063)	loss 4.0874 (3.3734)	grad_norm 1.1866 (1.5676/0.6799)	mem 24308MB
[2025-01-18 19:10:54 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][200/312]	eta 0:01:08 lr 0.002756	time 0.6575 (0.6140)	model_time 0.6573 (0.6062)	loss 2.2365 (3.3661)	grad_norm 0.7534 (1.5690/0.6769)	mem 24308MB
[2025-01-18 19:11:01 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][210/312]	eta 0:01:02 lr 0.002755	time 0.6987 (0.6140)	model_time 0.6983 (0.6066)	loss 3.6774 (3.3764)	grad_norm 1.6556 (1.5815/0.6751)	mem 24308MB
[2025-01-18 19:11:07 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][220/312]	eta 0:00:56 lr 0.002755	time 0.6028 (0.6138)	model_time 0.6026 (0.6067)	loss 3.9862 (3.3860)	grad_norm 1.2172 (1.5621/0.6683)	mem 24308MB
[2025-01-18 19:11:13 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][230/312]	eta 0:00:50 lr 0.002754	time 0.6603 (0.6156)	model_time 0.6598 (0.6088)	loss 3.8995 (3.3941)	grad_norm 1.7516 (1.5759/0.6645)	mem 24308MB
[2025-01-18 19:11:19 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][240/312]	eta 0:00:44 lr 0.002753	time 0.5658 (0.6158)	model_time 0.5653 (0.6092)	loss 3.6472 (3.3927)	grad_norm 2.1712 (1.5783/0.6580)	mem 24308MB
[2025-01-18 19:11:26 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][250/312]	eta 0:00:38 lr 0.002753	time 0.6429 (0.6164)	model_time 0.6427 (0.6100)	loss 2.5294 (3.3895)	grad_norm 1.8436 (1.5886/0.6709)	mem 24308MB
[2025-01-18 19:11:32 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][260/312]	eta 0:00:32 lr 0.002752	time 0.5839 (0.6155)	model_time 0.5837 (0.6094)	loss 3.2865 (3.3983)	grad_norm 2.5304 (1.5880/0.6668)	mem 24308MB
[2025-01-18 19:11:38 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][270/312]	eta 0:00:25 lr 0.002751	time 0.5666 (0.6149)	model_time 0.5664 (0.6090)	loss 3.5352 (3.4038)	grad_norm 3.3284 (1.6008/0.6738)	mem 24308MB
[2025-01-18 19:11:43 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][280/312]	eta 0:00:19 lr 0.002751	time 0.5880 (0.6140)	model_time 0.5878 (0.6083)	loss 2.6043 (3.3895)	grad_norm 0.9889 (1.5992/0.6725)	mem 24308MB
[2025-01-18 19:11:49 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][290/312]	eta 0:00:13 lr 0.002750	time 0.5819 (0.6135)	model_time 0.5814 (0.6080)	loss 3.9439 (3.3960)	grad_norm 1.7560 (1.5968/0.6629)	mem 24308MB
[2025-01-18 19:11:55 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][300/312]	eta 0:00:07 lr 0.002750	time 0.5661 (0.6125)	model_time 0.5660 (0.6071)	loss 3.9754 (3.4000)	grad_norm 2.9840 (1.6087/0.6786)	mem 24308MB
[2025-01-18 19:12:01 internimage_s_1k_224] (main.py 510): INFO Train: [113/300][310/312]	eta 0:00:01 lr 0.002749	time 0.6270 (0.6116)	model_time 0.6269 (0.6064)	loss 3.6792 (3.4044)	grad_norm 2.4230 (1.6123/0.6780)	mem 24308MB
[2025-01-18 19:12:02 internimage_s_1k_224] (main.py 519): INFO EPOCH 113 training takes 0:03:10
[2025-01-18 19:12:02 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_113.pth saving......
[2025-01-18 19:12:03 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_113.pth saved !!!
[2025-01-18 19:12:11 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.410 (7.410)	Loss 0.8612 (0.8612)	Acc@1 81.323 (81.323)	Acc@5 96.143 (96.143)	Mem 24308MB
[2025-01-18 19:12:14 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.981)	Loss 1.2062 (1.0260)	Acc@1 72.607 (77.759)	Acc@5 92.358 (94.294)	Mem 24308MB
[2025-01-18 19:12:15 internimage_s_1k_224] (main.py 575): INFO [Epoch:113] * Acc@1 77.683 Acc@5 94.334
[2025-01-18 19:12:15 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.7%
[2025-01-18 19:12:15 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.85%
[2025-01-18 19:12:23 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.125 (8.125)	Loss 0.7599 (0.7599)	Acc@1 81.323 (81.323)	Acc@5 96.509 (96.509)	Mem 24308MB
[2025-01-18 19:12:27 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.107)	Loss 1.1518 (0.9221)	Acc@1 71.680 (77.694)	Acc@5 91.772 (94.216)	Mem 24308MB
[2025-01-18 19:12:27 internimage_s_1k_224] (main.py 575): INFO [Epoch:113] * Acc@1 77.619 Acc@5 94.256
[2025-01-18 19:12:27 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 77.6%
[2025-01-18 19:12:27 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 19:12:29 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 19:12:29 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 77.62%
[2025-01-18 19:12:31 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][0/312]	eta 0:10:12 lr 0.002749	time 1.9627 (1.9627)	model_time 0.6274 (0.6274)	loss 2.8851 (2.8851)	grad_norm 2.1535 (2.1535/0.0000)	mem 24308MB
[2025-01-18 19:12:37 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][10/312]	eta 0:03:39 lr 0.002748	time 0.5788 (0.7258)	model_time 0.5787 (0.6042)	loss 3.6377 (3.5960)	grad_norm 2.1599 (1.5540/0.4358)	mem 24308MB
[2025-01-18 19:12:44 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][20/312]	eta 0:03:18 lr 0.002748	time 0.5892 (0.6790)	model_time 0.5887 (0.6151)	loss 3.3007 (3.5775)	grad_norm 1.3591 (1.3817/0.4004)	mem 24308MB
[2025-01-18 19:12:50 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][30/312]	eta 0:03:05 lr 0.002747	time 0.5923 (0.6588)	model_time 0.5921 (0.6155)	loss 3.5786 (3.5588)	grad_norm 1.8524 (1.4415/0.4612)	mem 24308MB
[2025-01-18 19:12:56 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][40/312]	eta 0:02:56 lr 0.002746	time 0.6748 (0.6507)	model_time 0.6746 (0.6178)	loss 3.6732 (3.6220)	grad_norm 2.3794 (1.5486/0.4980)	mem 24308MB
[2025-01-18 19:13:02 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][50/312]	eta 0:02:49 lr 0.002746	time 0.5730 (0.6464)	model_time 0.5728 (0.6200)	loss 3.7066 (3.5741)	grad_norm 2.2075 (1.5498/0.5364)	mem 24308MB
[2025-01-18 19:13:08 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][60/312]	eta 0:02:41 lr 0.002745	time 0.5819 (0.6401)	model_time 0.5817 (0.6180)	loss 3.6013 (3.6101)	grad_norm 0.8998 (1.5450/0.5907)	mem 24308MB
[2025-01-18 19:13:15 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][70/312]	eta 0:02:34 lr 0.002745	time 0.6856 (0.6373)	model_time 0.6852 (0.6182)	loss 3.7696 (3.5697)	grad_norm 4.2561 (1.6008/0.6780)	mem 24308MB
[2025-01-18 19:13:21 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][80/312]	eta 0:02:26 lr 0.002744	time 0.6560 (0.6324)	model_time 0.6558 (0.6156)	loss 3.7418 (3.5016)	grad_norm 2.4298 (1.6612/0.7299)	mem 24308MB
[2025-01-18 19:13:26 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][90/312]	eta 0:02:19 lr 0.002743	time 0.5761 (0.6281)	model_time 0.5760 (0.6131)	loss 4.1247 (3.5136)	grad_norm 1.5525 (1.6068/0.7083)	mem 24308MB
[2025-01-18 19:13:33 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][100/312]	eta 0:02:12 lr 0.002743	time 0.5740 (0.6261)	model_time 0.5739 (0.6125)	loss 2.7042 (3.4696)	grad_norm 0.7954 (1.5762/0.6931)	mem 24308MB
[2025-01-18 19:13:38 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][110/312]	eta 0:02:05 lr 0.002742	time 0.5705 (0.6228)	model_time 0.5703 (0.6105)	loss 2.7564 (3.4628)	grad_norm 2.1737 (1.5822/0.6898)	mem 24308MB
[2025-01-18 19:13:44 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][120/312]	eta 0:01:59 lr 0.002741	time 0.5828 (0.6206)	model_time 0.5824 (0.6092)	loss 2.2495 (3.4510)	grad_norm 1.1578 (1.5635/0.6717)	mem 24308MB
[2025-01-18 19:13:50 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][130/312]	eta 0:01:52 lr 0.002741	time 0.5784 (0.6195)	model_time 0.5782 (0.6090)	loss 3.2324 (3.4634)	grad_norm 0.6803 (1.5510/0.6645)	mem 24308MB
[2025-01-18 19:13:57 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][140/312]	eta 0:01:46 lr 0.002740	time 0.5729 (0.6192)	model_time 0.5725 (0.6094)	loss 3.8003 (3.4548)	grad_norm 1.1210 (1.5501/0.6502)	mem 24308MB
[2025-01-18 19:14:03 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][150/312]	eta 0:01:40 lr 0.002740	time 0.5870 (0.6208)	model_time 0.5865 (0.6116)	loss 2.3768 (3.4275)	grad_norm 0.8900 (1.5518/0.6402)	mem 24308MB
[2025-01-18 19:14:09 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][160/312]	eta 0:01:34 lr 0.002739	time 0.6688 (0.6216)	model_time 0.6686 (0.6130)	loss 3.5036 (3.4368)	grad_norm 1.9438 (1.5499/0.6257)	mem 24308MB
[2025-01-18 19:14:16 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][170/312]	eta 0:01:28 lr 0.002738	time 0.5988 (0.6230)	model_time 0.5984 (0.6148)	loss 3.5573 (3.4244)	grad_norm 1.1364 (1.5391/0.6253)	mem 24308MB
[2025-01-18 19:14:22 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][180/312]	eta 0:01:22 lr 0.002738	time 0.5626 (0.6222)	model_time 0.5621 (0.6144)	loss 3.6388 (3.4361)	grad_norm 2.0317 (1.5392/0.6121)	mem 24308MB
[2025-01-18 19:14:28 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][190/312]	eta 0:01:15 lr 0.002737	time 0.5738 (0.6214)	model_time 0.5734 (0.6140)	loss 3.0526 (3.4533)	grad_norm 0.9500 (1.5671/0.6483)	mem 24308MB
[2025-01-18 19:14:34 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][200/312]	eta 0:01:09 lr 0.002737	time 0.5856 (0.6198)	model_time 0.5852 (0.6128)	loss 2.8657 (3.4236)	grad_norm 2.0355 (1.6008/0.6769)	mem 24308MB
[2025-01-18 19:14:40 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][210/312]	eta 0:01:03 lr 0.002736	time 0.5929 (0.6186)	model_time 0.5927 (0.6119)	loss 3.4089 (3.4216)	grad_norm 2.0917 (1.6112/0.6722)	mem 24308MB
[2025-01-18 19:14:46 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][220/312]	eta 0:00:56 lr 0.002735	time 0.6350 (0.6183)	model_time 0.6349 (0.6119)	loss 3.5409 (3.4297)	grad_norm 1.2763 (1.5979/0.6643)	mem 24308MB
[2025-01-18 19:14:52 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][230/312]	eta 0:00:50 lr 0.002735	time 0.5842 (0.6168)	model_time 0.5841 (0.6106)	loss 3.8346 (3.4403)	grad_norm 1.4237 (1.6184/0.6890)	mem 24308MB
[2025-01-18 19:14:58 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][240/312]	eta 0:00:44 lr 0.002734	time 0.5804 (0.6161)	model_time 0.5802 (0.6102)	loss 3.6692 (3.4416)	grad_norm 0.8944 (1.6197/0.6861)	mem 24308MB
[2025-01-18 19:15:04 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][250/312]	eta 0:00:38 lr 0.002733	time 0.5850 (0.6155)	model_time 0.5848 (0.6099)	loss 3.1516 (3.4394)	grad_norm 1.7596 (1.6124/0.6839)	mem 24308MB
[2025-01-18 19:15:10 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][260/312]	eta 0:00:31 lr 0.002733	time 0.5966 (0.6153)	model_time 0.5961 (0.6098)	loss 3.7670 (3.4446)	grad_norm 1.1707 (1.6096/0.6872)	mem 24308MB
[2025-01-18 19:15:16 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][270/312]	eta 0:00:25 lr 0.002732	time 0.6660 (0.6165)	model_time 0.6658 (0.6112)	loss 3.4085 (3.4454)	grad_norm 1.0428 (1.5898/0.6828)	mem 24308MB
[2025-01-18 19:15:22 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][280/312]	eta 0:00:19 lr 0.002732	time 0.6807 (0.6163)	model_time 0.6802 (0.6112)	loss 2.9369 (3.4466)	grad_norm 3.4348 (1.5941/0.6973)	mem 24308MB
[2025-01-18 19:15:29 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][290/312]	eta 0:00:13 lr 0.002731	time 0.5875 (0.6164)	model_time 0.5871 (0.6115)	loss 3.3702 (3.4359)	grad_norm 1.0255 (1.5973/0.6905)	mem 24308MB
[2025-01-18 19:15:35 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][300/312]	eta 0:00:07 lr 0.002730	time 0.5682 (0.6163)	model_time 0.5681 (0.6115)	loss 2.7947 (3.4306)	grad_norm 2.4014 (1.6118/0.6971)	mem 24308MB
[2025-01-18 19:15:41 internimage_s_1k_224] (main.py 510): INFO Train: [114/300][310/312]	eta 0:00:01 lr 0.002730	time 0.5670 (0.6156)	model_time 0.5669 (0.6109)	loss 2.8395 (3.4354)	grad_norm 0.7895 (1.6159/0.7007)	mem 24308MB
[2025-01-18 19:15:41 internimage_s_1k_224] (main.py 519): INFO EPOCH 114 training takes 0:03:12
[2025-01-18 19:15:41 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_114.pth saving......
[2025-01-18 19:15:43 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_114.pth saved !!!
[2025-01-18 19:15:50 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.090 (7.090)	Loss 0.8938 (0.8938)	Acc@1 80.688 (80.688)	Acc@5 96.167 (96.167)	Mem 24308MB
[2025-01-18 19:15:54 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.926)	Loss 1.1986 (1.0437)	Acc@1 74.487 (77.586)	Acc@5 92.407 (94.380)	Mem 24308MB
[2025-01-18 19:15:54 internimage_s_1k_224] (main.py 575): INFO [Epoch:114] * Acc@1 77.511 Acc@5 94.406
[2025-01-18 19:15:54 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.5%
[2025-01-18 19:15:54 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.85%
[2025-01-18 19:16:02 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.124 (8.124)	Loss 0.7573 (0.7573)	Acc@1 81.494 (81.494)	Acc@5 96.606 (96.606)	Mem 24308MB
[2025-01-18 19:16:06 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.112)	Loss 1.1468 (0.9187)	Acc@1 71.777 (77.757)	Acc@5 91.797 (94.285)	Mem 24308MB
[2025-01-18 19:16:06 internimage_s_1k_224] (main.py 575): INFO [Epoch:114] * Acc@1 77.675 Acc@5 94.322
[2025-01-18 19:16:06 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 77.7%
[2025-01-18 19:16:06 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 19:16:09 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 19:16:09 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 77.68%
[2025-01-18 19:16:10 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][0/312]	eta 0:10:11 lr 0.002730	time 1.9583 (1.9583)	model_time 0.6238 (0.6238)	loss 2.6061 (2.6061)	grad_norm 0.9918 (0.9918/0.0000)	mem 24308MB
[2025-01-18 19:16:17 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][10/312]	eta 0:03:39 lr 0.002729	time 0.5932 (0.7280)	model_time 0.5931 (0.6064)	loss 2.3602 (3.0598)	grad_norm 1.6919 (1.8743/0.5416)	mem 24308MB
[2025-01-18 19:16:23 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][20/312]	eta 0:03:14 lr 0.002728	time 0.6019 (0.6659)	model_time 0.6017 (0.6020)	loss 3.1617 (3.1736)	grad_norm 1.0045 (1.6321/0.5326)	mem 24308MB
[2025-01-18 19:16:28 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][30/312]	eta 0:03:01 lr 0.002728	time 0.5854 (0.6441)	model_time 0.5853 (0.6007)	loss 3.4608 (3.2880)	grad_norm 1.7469 (1.5962/0.5186)	mem 24308MB
[2025-01-18 19:16:34 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][40/312]	eta 0:02:52 lr 0.002727	time 0.5952 (0.6324)	model_time 0.5950 (0.5995)	loss 3.6079 (3.3128)	grad_norm 2.6012 (1.7251/0.5778)	mem 24308MB
[2025-01-18 19:16:40 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][50/312]	eta 0:02:44 lr 0.002726	time 0.5836 (0.6261)	model_time 0.5834 (0.5995)	loss 2.6566 (3.2994)	grad_norm 2.8561 (1.8236/0.6423)	mem 24308MB
[2025-01-18 19:16:47 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][60/312]	eta 0:02:37 lr 0.002726	time 0.5911 (0.6234)	model_time 0.5907 (0.6012)	loss 3.6759 (3.3486)	grad_norm 1.5102 (1.7123/0.6493)	mem 24308MB
[2025-01-18 19:16:53 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][70/312]	eta 0:02:30 lr 0.002725	time 0.6575 (0.6220)	model_time 0.6571 (0.6029)	loss 2.4079 (3.3431)	grad_norm 1.8029 (1.6414/0.6370)	mem 24308MB
[2025-01-18 19:16:59 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][80/312]	eta 0:02:24 lr 0.002725	time 0.5882 (0.6211)	model_time 0.5881 (0.6043)	loss 3.5901 (3.3925)	grad_norm 1.5428 (1.5688/0.6332)	mem 24308MB
[2025-01-18 19:17:05 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][90/312]	eta 0:02:17 lr 0.002724	time 0.5966 (0.6198)	model_time 0.5964 (0.6048)	loss 2.6628 (3.3696)	grad_norm 1.0753 (1.5578/0.6277)	mem 24308MB
[2025-01-18 19:17:11 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][100/312]	eta 0:02:11 lr 0.002723	time 0.6696 (0.6225)	model_time 0.6694 (0.6090)	loss 2.6297 (3.3277)	grad_norm 1.9840 (1.5559/0.6212)	mem 24308MB
[2025-01-18 19:17:18 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][110/312]	eta 0:02:05 lr 0.002723	time 0.5774 (0.6215)	model_time 0.5770 (0.6091)	loss 4.0100 (3.3432)	grad_norm 2.3769 (1.6242/0.6573)	mem 24308MB
[2025-01-18 19:17:24 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][120/312]	eta 0:01:59 lr 0.002722	time 0.5954 (0.6204)	model_time 0.5953 (0.6090)	loss 2.5407 (3.3234)	grad_norm 1.1208 (1.6357/0.6593)	mem 24308MB
[2025-01-18 19:17:30 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][130/312]	eta 0:01:52 lr 0.002721	time 0.5803 (0.6191)	model_time 0.5801 (0.6085)	loss 3.2882 (3.3283)	grad_norm 0.7606 (1.6357/0.6711)	mem 24308MB
[2025-01-18 19:17:36 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][140/312]	eta 0:01:46 lr 0.002721	time 0.5926 (0.6175)	model_time 0.5921 (0.6077)	loss 2.0488 (3.3186)	grad_norm 2.0904 (1.6509/0.6617)	mem 24308MB
[2025-01-18 19:17:42 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][150/312]	eta 0:01:39 lr 0.002720	time 0.6794 (0.6163)	model_time 0.6792 (0.6071)	loss 3.8002 (3.3426)	grad_norm 2.3477 (1.6850/0.6727)	mem 24308MB
[2025-01-18 19:17:48 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][160/312]	eta 0:01:33 lr 0.002720	time 0.5870 (0.6149)	model_time 0.5869 (0.6062)	loss 4.3980 (3.3564)	grad_norm 1.6654 (1.6708/0.6639)	mem 24308MB
[2025-01-18 19:17:54 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][170/312]	eta 0:01:27 lr 0.002719	time 0.5747 (0.6139)	model_time 0.5745 (0.6058)	loss 2.4921 (3.3753)	grad_norm 2.2324 (1.6425/0.6623)	mem 24308MB
[2025-01-18 19:18:00 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][180/312]	eta 0:01:21 lr 0.002718	time 0.5851 (0.6138)	model_time 0.5846 (0.6060)	loss 4.1938 (3.3756)	grad_norm 1.1980 (1.6228/0.6513)	mem 24308MB
[2025-01-18 19:18:06 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][190/312]	eta 0:01:14 lr 0.002718	time 0.6004 (0.6129)	model_time 0.6003 (0.6055)	loss 3.4350 (3.3760)	grad_norm 1.2228 (1.6250/0.6607)	mem 24308MB
[2025-01-18 19:18:12 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][200/312]	eta 0:01:08 lr 0.002717	time 0.6017 (0.6130)	model_time 0.6012 (0.6060)	loss 2.3368 (3.3593)	grad_norm 0.9778 (1.6143/0.6540)	mem 24308MB
[2025-01-18 19:18:18 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][210/312]	eta 0:01:02 lr 0.002717	time 0.5896 (0.6133)	model_time 0.5892 (0.6066)	loss 3.5741 (3.3686)	grad_norm 1.6646 (1.6087/0.6499)	mem 24308MB
[2025-01-18 19:18:25 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][220/312]	eta 0:00:56 lr 0.002716	time 0.6764 (0.6159)	model_time 0.6763 (0.6095)	loss 3.0555 (3.3670)	grad_norm 1.4318 (1.6055/0.6370)	mem 24308MB
[2025-01-18 19:18:31 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][230/312]	eta 0:00:50 lr 0.002715	time 0.5816 (0.6158)	model_time 0.5814 (0.6096)	loss 3.5496 (3.3700)	grad_norm 1.1002 (1.5885/0.6298)	mem 24308MB
[2025-01-18 19:18:37 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][240/312]	eta 0:00:44 lr 0.002715	time 0.5845 (0.6155)	model_time 0.5843 (0.6096)	loss 3.9513 (3.3714)	grad_norm 1.5558 (1.6046/0.6333)	mem 24308MB
[2025-01-18 19:18:43 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][250/312]	eta 0:00:38 lr 0.002714	time 0.6326 (0.6151)	model_time 0.6325 (0.6094)	loss 2.4309 (3.3657)	grad_norm 2.3283 (1.6248/0.6545)	mem 24308MB
[2025-01-18 19:18:49 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][260/312]	eta 0:00:31 lr 0.002713	time 0.5831 (0.6143)	model_time 0.5826 (0.6088)	loss 2.4345 (3.3674)	grad_norm 1.1147 (1.6390/0.6748)	mem 24308MB
[2025-01-18 19:18:55 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][270/312]	eta 0:00:25 lr 0.002713	time 0.5874 (0.6138)	model_time 0.5873 (0.6085)	loss 3.3512 (3.3676)	grad_norm 1.1215 (1.6332/0.6704)	mem 24308MB
[2025-01-18 19:19:01 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][280/312]	eta 0:00:19 lr 0.002712	time 0.5768 (0.6133)	model_time 0.5766 (0.6081)	loss 4.2310 (3.3811)	grad_norm 1.1325 (1.6087/0.6713)	mem 24308MB
[2025-01-18 19:19:07 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][290/312]	eta 0:00:13 lr 0.002712	time 0.5819 (0.6128)	model_time 0.5818 (0.6079)	loss 3.9867 (3.3804)	grad_norm 1.9841 (1.6076/0.6696)	mem 24308MB
[2025-01-18 19:19:13 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][300/312]	eta 0:00:07 lr 0.002711	time 0.6485 (0.6121)	model_time 0.6484 (0.6073)	loss 2.4534 (3.3809)	grad_norm 0.8696 (1.6221/0.6872)	mem 24308MB
[2025-01-18 19:19:19 internimage_s_1k_224] (main.py 510): INFO Train: [115/300][310/312]	eta 0:00:01 lr 0.002710	time 0.5577 (0.6110)	model_time 0.5576 (0.6063)	loss 3.4560 (3.3882)	grad_norm 1.2354 (1.6098/0.6821)	mem 24308MB
[2025-01-18 19:19:19 internimage_s_1k_224] (main.py 519): INFO EPOCH 115 training takes 0:03:10
[2025-01-18 19:19:19 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_115.pth saving......
[2025-01-18 19:19:21 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_115.pth saved !!!
[2025-01-18 19:19:28 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.128 (7.128)	Loss 0.8982 (0.8982)	Acc@1 81.348 (81.348)	Acc@5 95.776 (95.776)	Mem 24308MB
[2025-01-18 19:19:31 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.922)	Loss 1.2223 (1.0409)	Acc@1 73.608 (77.586)	Acc@5 91.968 (94.087)	Mem 24308MB
[2025-01-18 19:19:31 internimage_s_1k_224] (main.py 575): INFO [Epoch:115] * Acc@1 77.451 Acc@5 94.108
[2025-01-18 19:19:31 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.5%
[2025-01-18 19:19:31 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.85%
[2025-01-18 19:19:39 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.039 (8.039)	Loss 0.7545 (0.7545)	Acc@1 81.567 (81.567)	Acc@5 96.582 (96.582)	Mem 24308MB
[2025-01-18 19:19:43 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.096)	Loss 1.1420 (0.9154)	Acc@1 71.851 (77.825)	Acc@5 91.797 (94.309)	Mem 24308MB
[2025-01-18 19:19:44 internimage_s_1k_224] (main.py 575): INFO [Epoch:115] * Acc@1 77.743 Acc@5 94.352
[2025-01-18 19:19:44 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 77.7%
[2025-01-18 19:19:44 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 19:19:46 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 19:19:46 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 77.74%
[2025-01-18 19:19:48 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][0/312]	eta 0:10:57 lr 0.002710	time 2.1066 (2.1066)	model_time 0.5919 (0.5919)	loss 3.6981 (3.6981)	grad_norm 2.1202 (2.1202/0.0000)	mem 24308MB
[2025-01-18 19:19:54 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][10/312]	eta 0:03:44 lr 0.002710	time 0.5952 (0.7440)	model_time 0.5951 (0.6061)	loss 3.2080 (3.3093)	grad_norm 1.8225 (1.6021/0.4442)	mem 24308MB
[2025-01-18 19:20:01 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][20/312]	eta 0:03:20 lr 0.002709	time 0.6152 (0.6866)	model_time 0.6148 (0.6141)	loss 4.1547 (3.3893)	grad_norm 2.6461 (1.7438/0.5366)	mem 24308MB
[2025-01-18 19:20:07 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][30/312]	eta 0:03:10 lr 0.002708	time 0.6880 (0.6743)	model_time 0.6877 (0.6251)	loss 3.2565 (3.3946)	grad_norm 1.3881 (1.6270/0.5548)	mem 24308MB
[2025-01-18 19:20:13 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][40/312]	eta 0:02:59 lr 0.002708	time 0.5878 (0.6614)	model_time 0.5874 (0.6241)	loss 3.6198 (3.3317)	grad_norm 2.8451 (1.5297/0.5951)	mem 24308MB
[2025-01-18 19:20:19 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][50/312]	eta 0:02:50 lr 0.002707	time 0.5875 (0.6517)	model_time 0.5873 (0.6217)	loss 2.5921 (3.3578)	grad_norm 1.0991 (1.5834/0.6917)	mem 24308MB
[2025-01-18 19:20:25 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][60/312]	eta 0:02:41 lr 0.002706	time 0.5739 (0.6427)	model_time 0.5738 (0.6175)	loss 2.9913 (3.3795)	grad_norm 1.4132 (1.5503/0.6909)	mem 24308MB
[2025-01-18 19:20:31 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][70/312]	eta 0:02:33 lr 0.002706	time 0.5820 (0.6364)	model_time 0.5815 (0.6146)	loss 3.4658 (3.4170)	grad_norm 1.6714 (1.5715/0.6745)	mem 24308MB
[2025-01-18 19:20:37 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][80/312]	eta 0:02:26 lr 0.002705	time 0.5956 (0.6308)	model_time 0.5955 (0.6117)	loss 4.0214 (3.4502)	grad_norm 0.7015 (1.6022/0.6684)	mem 24308MB
[2025-01-18 19:20:43 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][90/312]	eta 0:02:19 lr 0.002705	time 0.5895 (0.6279)	model_time 0.5890 (0.6109)	loss 3.0629 (3.4541)	grad_norm 1.8412 (1.5767/0.6504)	mem 24308MB
[2025-01-18 19:20:49 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][100/312]	eta 0:02:12 lr 0.002704	time 0.5777 (0.6251)	model_time 0.5772 (0.6097)	loss 2.3691 (3.4487)	grad_norm 1.3807 (1.6067/0.6612)	mem 24308MB
[2025-01-18 19:20:55 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][110/312]	eta 0:02:05 lr 0.002703	time 0.5893 (0.6234)	model_time 0.5891 (0.6094)	loss 3.7434 (3.4541)	grad_norm 0.8168 (1.5602/0.6518)	mem 24308MB
[2025-01-18 19:21:01 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][120/312]	eta 0:01:59 lr 0.002703	time 0.5785 (0.6221)	model_time 0.5783 (0.6092)	loss 3.0914 (3.4343)	grad_norm 1.8219 (1.5971/0.6731)	mem 24308MB
[2025-01-18 19:21:08 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][130/312]	eta 0:01:53 lr 0.002702	time 0.5973 (0.6221)	model_time 0.5969 (0.6101)	loss 3.6423 (3.4212)	grad_norm 1.1158 (1.5843/0.6688)	mem 24308MB
[2025-01-18 19:21:14 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][140/312]	eta 0:01:46 lr 0.002701	time 0.7015 (0.6220)	model_time 0.7013 (0.6109)	loss 2.7325 (3.4236)	grad_norm 0.8433 (1.5807/0.6685)	mem 24308MB
[2025-01-18 19:21:20 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][150/312]	eta 0:01:40 lr 0.002701	time 0.6657 (0.6223)	model_time 0.6652 (0.6119)	loss 3.1118 (3.4033)	grad_norm 0.9437 (1.5842/0.6750)	mem 24308MB
[2025-01-18 19:21:26 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][160/312]	eta 0:01:34 lr 0.002700	time 0.5786 (0.6210)	model_time 0.5783 (0.6112)	loss 3.7129 (3.4078)	grad_norm 2.5347 (1.6383/0.7288)	mem 24308MB
[2025-01-18 19:21:32 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][170/312]	eta 0:01:28 lr 0.002700	time 0.5781 (0.6204)	model_time 0.5777 (0.6112)	loss 3.2515 (3.4056)	grad_norm 1.1100 (1.6343/0.7239)	mem 24308MB
[2025-01-18 19:21:38 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][180/312]	eta 0:01:21 lr 0.002699	time 0.5763 (0.6188)	model_time 0.5761 (0.6101)	loss 3.6045 (3.4117)	grad_norm 2.8995 (1.6620/0.7539)	mem 24308MB
[2025-01-18 19:21:44 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][190/312]	eta 0:01:15 lr 0.002698	time 0.5789 (0.6175)	model_time 0.5784 (0.6091)	loss 4.2487 (3.4173)	grad_norm 1.8603 (1.6710/0.7543)	mem 24308MB
[2025-01-18 19:21:50 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][200/312]	eta 0:01:09 lr 0.002698	time 0.5817 (0.6161)	model_time 0.5812 (0.6082)	loss 3.6191 (3.4081)	grad_norm 1.4702 (1.6518/0.7427)	mem 24308MB
[2025-01-18 19:21:56 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][210/312]	eta 0:01:02 lr 0.002697	time 0.5827 (0.6152)	model_time 0.5822 (0.6076)	loss 2.3977 (3.4105)	grad_norm 0.8115 (1.6405/0.7348)	mem 24308MB
[2025-01-18 19:22:02 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][220/312]	eta 0:00:56 lr 0.002696	time 0.5746 (0.6143)	model_time 0.5745 (0.6071)	loss 2.4712 (3.4129)	grad_norm 2.0158 (1.6334/0.7262)	mem 24308MB
[2025-01-18 19:22:08 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][230/312]	eta 0:00:50 lr 0.002696	time 0.7033 (0.6142)	model_time 0.7029 (0.6073)	loss 2.5146 (3.4165)	grad_norm 0.9576 (1.6331/0.7243)	mem 24308MB
[2025-01-18 19:22:14 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][240/312]	eta 0:00:44 lr 0.002695	time 0.5866 (0.6131)	model_time 0.5862 (0.6064)	loss 3.7836 (3.4230)	grad_norm 1.2696 (1.6345/0.7234)	mem 24308MB
[2025-01-18 19:22:20 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][250/312]	eta 0:00:38 lr 0.002695	time 0.5781 (0.6146)	model_time 0.5779 (0.6081)	loss 3.6202 (3.4300)	grad_norm 1.3856 (1.6221/0.7158)	mem 24308MB
[2025-01-18 19:22:27 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][260/312]	eta 0:00:32 lr 0.002694	time 0.8790 (0.6159)	model_time 0.8788 (0.6097)	loss 3.2850 (3.4290)	grad_norm 1.2452 (1.6266/0.7089)	mem 24308MB
[2025-01-18 19:22:33 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][270/312]	eta 0:00:25 lr 0.002693	time 0.6598 (0.6170)	model_time 0.6596 (0.6110)	loss 3.8717 (3.4301)	grad_norm 0.7508 (1.6139/0.7037)	mem 24308MB
[2025-01-18 19:22:40 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][280/312]	eta 0:00:19 lr 0.002693	time 0.5615 (0.6172)	model_time 0.5611 (0.6114)	loss 4.3329 (3.4217)	grad_norm 1.7144 (1.6070/0.6964)	mem 24308MB
[2025-01-18 19:22:46 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][290/312]	eta 0:00:13 lr 0.002692	time 0.5834 (0.6167)	model_time 0.5833 (0.6111)	loss 3.5779 (3.4146)	grad_norm 1.5066 (1.6133/0.6997)	mem 24308MB
[2025-01-18 19:22:51 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][300/312]	eta 0:00:07 lr 0.002691	time 0.5640 (0.6158)	model_time 0.5639 (0.6103)	loss 2.7169 (3.4162)	grad_norm 1.2232 (1.6077/0.6922)	mem 24308MB
[2025-01-18 19:22:57 internimage_s_1k_224] (main.py 510): INFO Train: [116/300][310/312]	eta 0:00:01 lr 0.002691	time 0.5706 (0.6145)	model_time 0.5705 (0.6092)	loss 3.7728 (3.4205)	grad_norm 1.2460 (1.6041/0.6921)	mem 24308MB
[2025-01-18 19:22:58 internimage_s_1k_224] (main.py 519): INFO EPOCH 116 training takes 0:03:11
[2025-01-18 19:22:58 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_116.pth saving......
[2025-01-18 19:23:00 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_116.pth saved !!!
[2025-01-18 19:23:07 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.229 (7.229)	Loss 0.8477 (0.8477)	Acc@1 81.348 (81.348)	Acc@5 96.045 (96.045)	Mem 24308MB
[2025-01-18 19:23:10 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.950)	Loss 1.1932 (1.0160)	Acc@1 73.804 (77.923)	Acc@5 92.334 (94.312)	Mem 24308MB
[2025-01-18 19:23:10 internimage_s_1k_224] (main.py 575): INFO [Epoch:116] * Acc@1 77.919 Acc@5 94.334
[2025-01-18 19:23:10 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.9%
[2025-01-18 19:23:10 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 19:23:12 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 19:23:12 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.92%
[2025-01-18 19:23:20 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.103 (7.103)	Loss 0.7518 (0.7518)	Acc@1 81.592 (81.592)	Acc@5 96.655 (96.655)	Mem 24308MB
[2025-01-18 19:23:23 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.134 (0.929)	Loss 1.1373 (0.9120)	Acc@1 71.973 (77.899)	Acc@5 91.846 (94.367)	Mem 24308MB
[2025-01-18 19:23:23 internimage_s_1k_224] (main.py 575): INFO [Epoch:116] * Acc@1 77.823 Acc@5 94.402
[2025-01-18 19:23:23 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 77.8%
[2025-01-18 19:23:23 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 19:23:25 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 19:23:25 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 77.82%
[2025-01-18 19:23:27 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][0/312]	eta 0:11:55 lr 0.002691	time 2.2942 (2.2942)	model_time 0.6053 (0.6053)	loss 4.1820 (4.1820)	grad_norm 1.2132 (1.2132/0.0000)	mem 24308MB
[2025-01-18 19:23:33 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][10/312]	eta 0:03:43 lr 0.002690	time 0.5930 (0.7410)	model_time 0.5929 (0.5872)	loss 2.3140 (3.5160)	grad_norm 2.2433 (1.6955/0.6286)	mem 24308MB
[2025-01-18 19:23:39 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][20/312]	eta 0:03:17 lr 0.002689	time 0.5946 (0.6753)	model_time 0.5944 (0.5945)	loss 2.6528 (3.5797)	grad_norm 0.8445 (1.5148/0.5267)	mem 24308MB
[2025-01-18 19:23:45 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][30/312]	eta 0:03:03 lr 0.002689	time 0.6001 (0.6506)	model_time 0.6000 (0.5958)	loss 2.1683 (3.4370)	grad_norm 2.4831 (1.6802/0.6970)	mem 24308MB
[2025-01-18 19:23:51 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][40/312]	eta 0:02:53 lr 0.002688	time 0.5816 (0.6381)	model_time 0.5811 (0.5965)	loss 3.5995 (3.4424)	grad_norm 1.4172 (1.6091/0.6465)	mem 24308MB
[2025-01-18 19:23:57 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][50/312]	eta 0:02:45 lr 0.002688	time 0.5914 (0.6301)	model_time 0.5910 (0.5966)	loss 3.3085 (3.4341)	grad_norm 1.3615 (1.5133/0.6177)	mem 24308MB
[2025-01-18 19:24:04 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][60/312]	eta 0:02:38 lr 0.002687	time 0.5781 (0.6300)	model_time 0.5779 (0.6020)	loss 4.0710 (3.4081)	grad_norm 1.5557 (1.5309/0.5902)	mem 24308MB
[2025-01-18 19:24:10 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][70/312]	eta 0:02:32 lr 0.002686	time 0.5716 (0.6290)	model_time 0.5714 (0.6049)	loss 3.8415 (3.4536)	grad_norm 2.9025 (1.5223/0.5794)	mem 24308MB
[2025-01-18 19:24:16 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][80/312]	eta 0:02:26 lr 0.002686	time 0.6459 (0.6302)	model_time 0.6457 (0.6090)	loss 3.8686 (3.4410)	grad_norm 1.1938 (1.5196/0.5628)	mem 24308MB
[2025-01-18 19:24:22 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][90/312]	eta 0:02:19 lr 0.002685	time 0.5960 (0.6282)	model_time 0.5958 (0.6093)	loss 3.5190 (3.4549)	grad_norm 1.7029 (1.5703/0.6163)	mem 24308MB
[2025-01-18 19:24:28 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][100/312]	eta 0:02:12 lr 0.002684	time 0.5873 (0.6255)	model_time 0.5869 (0.6084)	loss 3.8827 (3.4805)	grad_norm 3.5658 (1.6095/0.6339)	mem 24308MB
[2025-01-18 19:24:34 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][110/312]	eta 0:02:05 lr 0.002684	time 0.5947 (0.6228)	model_time 0.5946 (0.6072)	loss 3.6345 (3.4720)	grad_norm 1.9297 (1.6300/0.6355)	mem 24308MB
[2025-01-18 19:24:41 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][120/312]	eta 0:01:59 lr 0.002683	time 0.5804 (0.6228)	model_time 0.5799 (0.6085)	loss 3.3838 (3.4621)	grad_norm 0.9131 (1.6026/0.6217)	mem 24308MB
[2025-01-18 19:24:46 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][130/312]	eta 0:01:52 lr 0.002683	time 0.6121 (0.6205)	model_time 0.6117 (0.6073)	loss 3.3885 (3.4391)	grad_norm 2.9059 (1.6307/0.6666)	mem 24308MB
[2025-01-18 19:24:52 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][140/312]	eta 0:01:46 lr 0.002682	time 0.5836 (0.6192)	model_time 0.5834 (0.6068)	loss 2.6961 (3.4412)	grad_norm 0.8965 (1.5926/0.6624)	mem 24308MB
[2025-01-18 19:24:58 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][150/312]	eta 0:01:40 lr 0.002681	time 0.5798 (0.6177)	model_time 0.5796 (0.6062)	loss 3.5773 (3.4550)	grad_norm 1.2560 (1.5943/0.6611)	mem 24308MB
[2025-01-18 19:25:04 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][160/312]	eta 0:01:33 lr 0.002681	time 0.5830 (0.6164)	model_time 0.5825 (0.6055)	loss 2.7732 (3.4686)	grad_norm 0.8134 (1.5981/0.6590)	mem 24308MB
[2025-01-18 19:25:10 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][170/312]	eta 0:01:27 lr 0.002680	time 0.5822 (0.6152)	model_time 0.5818 (0.6049)	loss 4.2116 (3.4742)	grad_norm 1.1622 (1.6175/0.6693)	mem 24308MB
[2025-01-18 19:25:17 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][180/312]	eta 0:01:21 lr 0.002679	time 0.6564 (0.6162)	model_time 0.6562 (0.6065)	loss 3.9641 (3.4581)	grad_norm 1.4498 (1.5998/0.6632)	mem 24308MB
[2025-01-18 19:25:23 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][190/312]	eta 0:01:15 lr 0.002679	time 0.5948 (0.6159)	model_time 0.5944 (0.6066)	loss 2.9454 (3.4596)	grad_norm 2.7350 (1.6074/0.6667)	mem 24308MB
[2025-01-18 19:25:29 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][200/312]	eta 0:01:09 lr 0.002678	time 0.8337 (0.6170)	model_time 0.8335 (0.6082)	loss 3.3043 (3.4511)	grad_norm 1.9352 (1.6123/0.6570)	mem 24308MB
[2025-01-18 19:25:35 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][210/312]	eta 0:01:02 lr 0.002678	time 0.5864 (0.6173)	model_time 0.5862 (0.6090)	loss 2.5713 (3.4359)	grad_norm 0.7329 (1.6196/0.6564)	mem 24308MB
[2025-01-18 19:25:42 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][220/312]	eta 0:00:56 lr 0.002677	time 0.5754 (0.6169)	model_time 0.5750 (0.6089)	loss 4.0005 (3.4489)	grad_norm 2.2215 (1.6192/0.6493)	mem 24308MB
[2025-01-18 19:25:47 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][230/312]	eta 0:00:50 lr 0.002676	time 0.5949 (0.6160)	model_time 0.5948 (0.6083)	loss 2.7053 (3.4310)	grad_norm 1.5278 (1.5996/0.6447)	mem 24308MB
[2025-01-18 19:25:53 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][240/312]	eta 0:00:44 lr 0.002676	time 0.5839 (0.6148)	model_time 0.5837 (0.6074)	loss 3.5638 (3.4309)	grad_norm 2.5312 (1.5960/0.6373)	mem 24308MB
[2025-01-18 19:25:59 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][250/312]	eta 0:00:38 lr 0.002675	time 0.6067 (0.6142)	model_time 0.6062 (0.6071)	loss 4.3018 (3.4400)	grad_norm 3.6086 (1.6055/0.6504)	mem 24308MB
[2025-01-18 19:26:05 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][260/312]	eta 0:00:31 lr 0.002674	time 0.5836 (0.6135)	model_time 0.5834 (0.6066)	loss 3.2984 (3.4485)	grad_norm 3.6301 (1.6249/0.6711)	mem 24308MB
[2025-01-18 19:26:11 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][270/312]	eta 0:00:25 lr 0.002674	time 0.5960 (0.6127)	model_time 0.5955 (0.6061)	loss 3.1709 (3.4507)	grad_norm 2.0599 (1.6471/0.6963)	mem 24308MB
[2025-01-18 19:26:17 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][280/312]	eta 0:00:19 lr 0.002673	time 0.5924 (0.6123)	model_time 0.5919 (0.6059)	loss 3.6167 (3.4433)	grad_norm 1.4132 (1.6407/0.6894)	mem 24308MB
[2025-01-18 19:26:23 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][290/312]	eta 0:00:13 lr 0.002673	time 0.5779 (0.6120)	model_time 0.5774 (0.6058)	loss 3.3705 (3.4454)	grad_norm 1.2780 (1.6322/0.6843)	mem 24308MB
[2025-01-18 19:26:29 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][300/312]	eta 0:00:07 lr 0.002672	time 0.6527 (0.6121)	model_time 0.6525 (0.6061)	loss 3.2982 (3.4433)	grad_norm 0.9273 (1.6178/0.6803)	mem 24308MB
[2025-01-18 19:26:35 internimage_s_1k_224] (main.py 510): INFO Train: [117/300][310/312]	eta 0:00:01 lr 0.002671	time 0.5664 (0.6116)	model_time 0.5663 (0.6058)	loss 3.4216 (3.4358)	grad_norm 1.4999 (1.6102/0.6765)	mem 24308MB
[2025-01-18 19:26:36 internimage_s_1k_224] (main.py 519): INFO EPOCH 117 training takes 0:03:10
[2025-01-18 19:26:36 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_117.pth saving......
[2025-01-18 19:26:38 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_117.pth saved !!!
[2025-01-18 19:26:45 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.995 (6.995)	Loss 0.9285 (0.9285)	Acc@1 80.884 (80.884)	Acc@5 95.679 (95.679)	Mem 24308MB
[2025-01-18 19:26:48 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.924)	Loss 1.2005 (1.0337)	Acc@1 73.804 (77.956)	Acc@5 91.968 (94.280)	Mem 24308MB
[2025-01-18 19:26:48 internimage_s_1k_224] (main.py 575): INFO [Epoch:117] * Acc@1 77.919 Acc@5 94.342
[2025-01-18 19:26:48 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.9%
[2025-01-18 19:26:48 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 19:26:50 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 19:26:50 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 77.92%
[2025-01-18 19:26:57 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.152 (7.152)	Loss 0.7496 (0.7496)	Acc@1 81.567 (81.567)	Acc@5 96.704 (96.704)	Mem 24308MB
[2025-01-18 19:27:00 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.931)	Loss 1.1329 (0.9089)	Acc@1 72.046 (77.970)	Acc@5 91.895 (94.396)	Mem 24308MB
[2025-01-18 19:27:01 internimage_s_1k_224] (main.py 575): INFO [Epoch:117] * Acc@1 77.883 Acc@5 94.428
[2025-01-18 19:27:01 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 77.9%
[2025-01-18 19:27:01 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 19:27:03 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 19:27:03 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 77.88%
[2025-01-18 19:27:05 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][0/312]	eta 0:11:11 lr 0.002671	time 2.1533 (2.1533)	model_time 0.5863 (0.5863)	loss 4.0433 (4.0433)	grad_norm 0.7621 (0.7621/0.0000)	mem 24308MB
[2025-01-18 19:27:11 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][10/312]	eta 0:03:51 lr 0.002671	time 0.5945 (0.7661)	model_time 0.5943 (0.6233)	loss 3.3489 (3.5463)	grad_norm 0.9310 (1.1813/0.2971)	mem 24308MB
[2025-01-18 19:27:18 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][20/312]	eta 0:03:27 lr 0.002670	time 0.5918 (0.7110)	model_time 0.5914 (0.6361)	loss 3.8159 (3.3612)	grad_norm 2.0632 (1.1857/0.3620)	mem 24308MB
[2025-01-18 19:27:24 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][30/312]	eta 0:03:11 lr 0.002669	time 0.5764 (0.6794)	model_time 0.5760 (0.6285)	loss 2.2965 (3.4295)	grad_norm 1.8492 (1.2392/0.3955)	mem 24308MB
[2025-01-18 19:27:30 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][40/312]	eta 0:02:59 lr 0.002669	time 0.5680 (0.6607)	model_time 0.5678 (0.6221)	loss 3.8886 (3.3802)	grad_norm 1.2169 (1.2596/0.3969)	mem 24308MB
[2025-01-18 19:27:36 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][50/312]	eta 0:02:49 lr 0.002668	time 0.5963 (0.6466)	model_time 0.5962 (0.6155)	loss 3.5060 (3.4248)	grad_norm 1.8293 (1.3408/0.4430)	mem 24308MB
[2025-01-18 19:27:42 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][60/312]	eta 0:02:40 lr 0.002667	time 0.5913 (0.6384)	model_time 0.5908 (0.6123)	loss 3.2967 (3.4190)	grad_norm 1.1023 (1.5764/0.8727)	mem 24308MB
[2025-01-18 19:27:48 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][70/312]	eta 0:02:33 lr 0.002667	time 0.6051 (0.6330)	model_time 0.6046 (0.6105)	loss 3.8101 (3.4373)	grad_norm 1.4048 (1.6682/0.8741)	mem 24308MB
[2025-01-18 19:27:54 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][80/312]	eta 0:02:25 lr 0.002666	time 0.5864 (0.6277)	model_time 0.5863 (0.6079)	loss 3.9424 (3.4591)	grad_norm 1.4317 (1.6577/0.8411)	mem 24308MB
[2025-01-18 19:28:00 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][90/312]	eta 0:02:18 lr 0.002666	time 0.6539 (0.6260)	model_time 0.6537 (0.6084)	loss 2.2856 (3.4355)	grad_norm 2.0686 (1.6166/0.8117)	mem 24308MB
[2025-01-18 19:28:06 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][100/312]	eta 0:02:11 lr 0.002665	time 0.5918 (0.6221)	model_time 0.5914 (0.6062)	loss 3.8280 (3.4588)	grad_norm 1.2820 (1.5869/0.7794)	mem 24308MB
[2025-01-18 19:28:12 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][110/312]	eta 0:02:05 lr 0.002664	time 0.6633 (0.6208)	model_time 0.6631 (0.6063)	loss 2.7836 (3.4355)	grad_norm 1.6519 (1.5871/0.7647)	mem 24308MB
[2025-01-18 19:28:18 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][120/312]	eta 0:01:59 lr 0.002664	time 0.6823 (0.6209)	model_time 0.6818 (0.6076)	loss 4.1602 (3.4763)	grad_norm 2.1661 (1.6240/0.7680)	mem 24308MB
[2025-01-18 19:28:24 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][130/312]	eta 0:01:52 lr 0.002663	time 0.5793 (0.6206)	model_time 0.5792 (0.6083)	loss 3.3184 (3.4511)	grad_norm 1.5703 (1.6450/0.7515)	mem 24308MB
[2025-01-18 19:28:30 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][140/312]	eta 0:01:46 lr 0.002662	time 0.6491 (0.6208)	model_time 0.6487 (0.6092)	loss 3.0457 (3.4460)	grad_norm 1.5045 (1.6311/0.7326)	mem 24308MB
[2025-01-18 19:28:36 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][150/312]	eta 0:01:40 lr 0.002662	time 0.5817 (0.6200)	model_time 0.5812 (0.6092)	loss 3.5433 (3.4647)	grad_norm 0.9099 (1.5950/0.7238)	mem 24308MB
[2025-01-18 19:28:42 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][160/312]	eta 0:01:34 lr 0.002661	time 0.5760 (0.6187)	model_time 0.5758 (0.6086)	loss 4.1540 (3.4582)	grad_norm 1.7830 (1.5751/0.7117)	mem 24308MB
[2025-01-18 19:28:48 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][170/312]	eta 0:01:27 lr 0.002660	time 0.5965 (0.6169)	model_time 0.5961 (0.6074)	loss 3.1846 (3.4693)	grad_norm 1.3294 (1.5864/0.7122)	mem 24308MB
[2025-01-18 19:28:54 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][180/312]	eta 0:01:21 lr 0.002660	time 0.5779 (0.6158)	model_time 0.5777 (0.6067)	loss 3.6722 (3.4735)	grad_norm 2.3425 (1.5688/0.7048)	mem 24308MB
[2025-01-18 19:29:00 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][190/312]	eta 0:01:14 lr 0.002659	time 0.5765 (0.6147)	model_time 0.5763 (0.6062)	loss 2.5732 (3.4709)	grad_norm 0.7470 (1.5799/0.7166)	mem 24308MB
[2025-01-18 19:29:06 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][200/312]	eta 0:01:08 lr 0.002659	time 0.5808 (0.6134)	model_time 0.5804 (0.6053)	loss 3.5902 (3.4664)	grad_norm 1.2396 (1.5984/0.7136)	mem 24308MB
[2025-01-18 19:29:12 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][210/312]	eta 0:01:02 lr 0.002658	time 0.6616 (0.6136)	model_time 0.6612 (0.6058)	loss 2.9195 (3.4550)	grad_norm 2.4395 (1.6088/0.7086)	mem 24308MB
[2025-01-18 19:29:18 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][220/312]	eta 0:00:56 lr 0.002657	time 0.5908 (0.6124)	model_time 0.5906 (0.6049)	loss 3.8207 (3.4548)	grad_norm 0.9563 (1.6394/0.7292)	mem 24308MB
[2025-01-18 19:29:24 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][230/312]	eta 0:00:50 lr 0.002657	time 0.6468 (0.6123)	model_time 0.6466 (0.6051)	loss 2.8323 (3.4446)	grad_norm 1.0246 (1.6336/0.7199)	mem 24308MB
[2025-01-18 19:29:31 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][240/312]	eta 0:00:44 lr 0.002656	time 0.6557 (0.6126)	model_time 0.6555 (0.6057)	loss 3.5670 (3.4442)	grad_norm 3.8062 (1.6322/0.7249)	mem 24308MB
[2025-01-18 19:29:37 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][250/312]	eta 0:00:38 lr 0.002655	time 0.5798 (0.6131)	model_time 0.5796 (0.6065)	loss 3.5829 (3.4448)	grad_norm 2.2512 (1.6431/0.7277)	mem 24308MB
[2025-01-18 19:29:43 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][260/312]	eta 0:00:31 lr 0.002655	time 0.5782 (0.6151)	model_time 0.5778 (0.6087)	loss 4.0278 (3.4484)	grad_norm 1.6410 (1.6390/0.7163)	mem 24308MB
[2025-01-18 19:29:50 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][270/312]	eta 0:00:25 lr 0.002654	time 0.5812 (0.6149)	model_time 0.5810 (0.6087)	loss 3.0809 (3.4431)	grad_norm 1.8048 (1.6369/0.7080)	mem 24308MB
[2025-01-18 19:29:56 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][280/312]	eta 0:00:19 lr 0.002654	time 0.5796 (0.6143)	model_time 0.5791 (0.6084)	loss 3.6579 (3.4373)	grad_norm 0.8349 (1.6291/0.7018)	mem 24308MB
[2025-01-18 19:30:01 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][290/312]	eta 0:00:13 lr 0.002653	time 0.5893 (0.6138)	model_time 0.5891 (0.6080)	loss 2.8892 (3.4347)	grad_norm 1.1657 (1.6382/0.7163)	mem 24308MB
[2025-01-18 19:30:07 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][300/312]	eta 0:00:07 lr 0.002652	time 0.5681 (0.6129)	model_time 0.5680 (0.6073)	loss 3.7683 (3.4413)	grad_norm 1.4079 (1.6391/0.7065)	mem 24308MB
[2025-01-18 19:30:13 internimage_s_1k_224] (main.py 510): INFO Train: [118/300][310/312]	eta 0:00:01 lr 0.002652	time 0.5785 (0.6120)	model_time 0.5784 (0.6065)	loss 2.1588 (3.4291)	grad_norm 1.3086 (1.6452/0.7065)	mem 24308MB
[2025-01-18 19:30:14 internimage_s_1k_224] (main.py 519): INFO EPOCH 118 training takes 0:03:10
[2025-01-18 19:30:14 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_118.pth saving......
[2025-01-18 19:30:16 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_118.pth saved !!!
[2025-01-18 19:30:23 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.118 (7.118)	Loss 0.8750 (0.8750)	Acc@1 81.641 (81.641)	Acc@5 95.752 (95.752)	Mem 24308MB
[2025-01-18 19:30:26 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.943)	Loss 1.1799 (1.0062)	Acc@1 74.121 (78.127)	Acc@5 92.847 (94.409)	Mem 24308MB
[2025-01-18 19:30:26 internimage_s_1k_224] (main.py 575): INFO [Epoch:118] * Acc@1 78.067 Acc@5 94.442
[2025-01-18 19:30:26 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.1%
[2025-01-18 19:30:26 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 19:30:28 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 19:30:28 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.07%
[2025-01-18 19:30:35 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.078 (7.078)	Loss 0.7477 (0.7477)	Acc@1 81.567 (81.567)	Acc@5 96.704 (96.704)	Mem 24308MB
[2025-01-18 19:30:39 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.929)	Loss 1.1292 (0.9061)	Acc@1 72.119 (78.061)	Acc@5 91.943 (94.427)	Mem 24308MB
[2025-01-18 19:30:39 internimage_s_1k_224] (main.py 575): INFO [Epoch:118] * Acc@1 77.959 Acc@5 94.456
[2025-01-18 19:30:39 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.0%
[2025-01-18 19:30:39 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 19:30:41 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 19:30:41 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 77.96%
[2025-01-18 19:30:43 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][0/312]	eta 0:12:55 lr 0.002652	time 2.4858 (2.4858)	model_time 0.6113 (0.6113)	loss 3.5079 (3.5079)	grad_norm 1.0951 (1.0951/0.0000)	mem 24308MB
[2025-01-18 19:30:49 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][10/312]	eta 0:03:49 lr 0.002651	time 0.5877 (0.7595)	model_time 0.5875 (0.5888)	loss 4.3767 (3.6379)	grad_norm 0.9148 (1.7057/0.9084)	mem 24308MB
[2025-01-18 19:30:55 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][20/312]	eta 0:03:20 lr 0.002650	time 0.5913 (0.6881)	model_time 0.5911 (0.5985)	loss 3.0845 (3.4944)	grad_norm 0.8010 (1.3859/0.7567)	mem 24308MB
[2025-01-18 19:31:01 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][30/312]	eta 0:03:05 lr 0.002650	time 0.6665 (0.6580)	model_time 0.6661 (0.5972)	loss 3.7697 (3.5089)	grad_norm 1.5950 (1.3645/0.6685)	mem 24308MB
[2025-01-18 19:31:07 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][40/312]	eta 0:02:55 lr 0.002649	time 0.5858 (0.6449)	model_time 0.5853 (0.5989)	loss 2.5375 (3.4584)	grad_norm 2.1402 (1.4350/0.6512)	mem 24308MB
[2025-01-18 19:31:13 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][50/312]	eta 0:02:46 lr 0.002648	time 0.5794 (0.6372)	model_time 0.5793 (0.6001)	loss 3.0758 (3.5118)	grad_norm 1.8364 (1.4474/0.6215)	mem 24308MB
[2025-01-18 19:31:19 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][60/312]	eta 0:02:39 lr 0.002648	time 0.5760 (0.6344)	model_time 0.5759 (0.6034)	loss 2.8935 (3.4837)	grad_norm 2.7203 (1.5189/0.6362)	mem 24308MB
[2025-01-18 19:31:26 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][70/312]	eta 0:02:33 lr 0.002647	time 0.5870 (0.6326)	model_time 0.5865 (0.6058)	loss 3.7879 (3.4283)	grad_norm 1.5147 (1.5192/0.6120)	mem 24308MB
[2025-01-18 19:31:32 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][80/312]	eta 0:02:26 lr 0.002646	time 0.6815 (0.6308)	model_time 0.6810 (0.6073)	loss 3.2686 (3.3928)	grad_norm 1.0143 (1.4658/0.5947)	mem 24308MB
[2025-01-18 19:31:38 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][90/312]	eta 0:02:19 lr 0.002646	time 0.6837 (0.6276)	model_time 0.6835 (0.6067)	loss 3.6330 (3.4064)	grad_norm 1.5982 (1.4479/0.5686)	mem 24308MB
[2025-01-18 19:31:44 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][100/312]	eta 0:02:12 lr 0.002645	time 0.5882 (0.6235)	model_time 0.5878 (0.6045)	loss 3.0850 (3.4001)	grad_norm 1.1598 (1.4787/0.5703)	mem 24308MB
[2025-01-18 19:31:50 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][110/312]	eta 0:02:05 lr 0.002645	time 0.5845 (0.6212)	model_time 0.5841 (0.6039)	loss 3.6040 (3.4122)	grad_norm 0.9492 (1.5107/0.6317)	mem 24308MB
[2025-01-18 19:31:56 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][120/312]	eta 0:01:58 lr 0.002644	time 0.5785 (0.6193)	model_time 0.5781 (0.6035)	loss 3.4233 (3.3939)	grad_norm 1.7868 (1.5210/0.6390)	mem 24308MB
[2025-01-18 19:32:02 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][130/312]	eta 0:01:52 lr 0.002643	time 0.5880 (0.6169)	model_time 0.5878 (0.6022)	loss 3.5394 (3.3888)	grad_norm 1.7370 (1.4925/0.6280)	mem 24308MB
[2025-01-18 19:32:08 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][140/312]	eta 0:01:46 lr 0.002643	time 0.6078 (0.6163)	model_time 0.6076 (0.6026)	loss 2.8114 (3.3975)	grad_norm 1.6508 (1.5053/0.6187)	mem 24308MB
[2025-01-18 19:32:14 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][150/312]	eta 0:01:39 lr 0.002642	time 0.5813 (0.6145)	model_time 0.5808 (0.6017)	loss 3.5059 (3.4068)	grad_norm 1.2330 (1.4896/0.6039)	mem 24308MB
[2025-01-18 19:32:20 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][160/312]	eta 0:01:33 lr 0.002641	time 0.5822 (0.6138)	model_time 0.5820 (0.6017)	loss 2.5017 (3.4208)	grad_norm 0.7955 (1.4803/0.5984)	mem 24308MB
[2025-01-18 19:32:26 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][170/312]	eta 0:01:27 lr 0.002641	time 0.6606 (0.6141)	model_time 0.6604 (0.6028)	loss 4.3104 (3.4183)	grad_norm 2.3365 (1.4669/0.5924)	mem 24308MB
[2025-01-18 19:32:32 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][180/312]	eta 0:01:21 lr 0.002640	time 0.5833 (0.6145)	model_time 0.5828 (0.6037)	loss 3.8275 (3.4287)	grad_norm 5.9978 (1.4942/0.6837)	mem 24308MB
[2025-01-18 19:32:38 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][190/312]	eta 0:01:14 lr 0.002640	time 0.6782 (0.6146)	model_time 0.6780 (0.6044)	loss 3.8150 (3.4382)	grad_norm 2.3001 (1.5655/0.8000)	mem 24308MB
[2025-01-18 19:32:44 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][200/312]	eta 0:01:08 lr 0.002639	time 0.5819 (0.6152)	model_time 0.5814 (0.6055)	loss 3.5188 (3.4456)	grad_norm 0.9414 (1.5591/0.7872)	mem 24308MB
[2025-01-18 19:32:51 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][210/312]	eta 0:01:02 lr 0.002638	time 0.6992 (0.6153)	model_time 0.6988 (0.6060)	loss 2.6446 (3.4330)	grad_norm 1.2430 (1.5513/0.7706)	mem 24308MB
[2025-01-18 19:32:56 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][220/312]	eta 0:00:56 lr 0.002638	time 0.5808 (0.6140)	model_time 0.5807 (0.6051)	loss 3.4810 (3.4434)	grad_norm 1.0803 (1.5620/0.7681)	mem 24308MB
[2025-01-18 19:33:02 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][230/312]	eta 0:00:50 lr 0.002637	time 0.5891 (0.6133)	model_time 0.5890 (0.6047)	loss 3.3330 (3.4490)	grad_norm 1.2857 (1.5809/0.7774)	mem 24308MB
[2025-01-18 19:33:08 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][240/312]	eta 0:00:44 lr 0.002636	time 0.5795 (0.6120)	model_time 0.5793 (0.6038)	loss 2.9197 (3.4453)	grad_norm 1.3390 (1.5759/0.7650)	mem 24308MB
[2025-01-18 19:33:14 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][250/312]	eta 0:00:37 lr 0.002636	time 0.5776 (0.6114)	model_time 0.5772 (0.6035)	loss 3.5873 (3.4391)	grad_norm 1.7157 (1.5697/0.7530)	mem 24308MB
[2025-01-18 19:33:20 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][260/312]	eta 0:00:31 lr 0.002635	time 0.5800 (0.6112)	model_time 0.5797 (0.6036)	loss 3.6695 (3.4459)	grad_norm 0.9406 (1.5497/0.7461)	mem 24308MB
[2025-01-18 19:33:26 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][270/312]	eta 0:00:25 lr 0.002635	time 0.5892 (0.6106)	model_time 0.5890 (0.6032)	loss 4.3185 (3.4544)	grad_norm 1.1051 (1.5387/0.7359)	mem 24308MB
[2025-01-18 19:33:32 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][280/312]	eta 0:00:19 lr 0.002634	time 0.6506 (0.6102)	model_time 0.6502 (0.6031)	loss 3.7538 (3.4486)	grad_norm 1.1527 (1.5687/0.7507)	mem 24308MB
[2025-01-18 19:33:38 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][290/312]	eta 0:00:13 lr 0.002633	time 0.6564 (0.6105)	model_time 0.6563 (0.6037)	loss 3.5905 (3.4499)	grad_norm 2.3521 (1.5609/0.7431)	mem 24308MB
[2025-01-18 19:33:45 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][300/312]	eta 0:00:07 lr 0.002633	time 0.5639 (0.6106)	model_time 0.5638 (0.6039)	loss 2.7468 (3.4505)	grad_norm 1.5670 (1.5792/0.7560)	mem 24308MB
[2025-01-18 19:33:51 internimage_s_1k_224] (main.py 510): INFO Train: [119/300][310/312]	eta 0:00:01 lr 0.002632	time 0.5687 (0.6107)	model_time 0.5687 (0.6042)	loss 3.2916 (3.4439)	grad_norm 1.9295 (1.5719/0.7394)	mem 24308MB
[2025-01-18 19:33:51 internimage_s_1k_224] (main.py 519): INFO EPOCH 119 training takes 0:03:10
[2025-01-18 19:33:51 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_119.pth saving......
[2025-01-18 19:33:53 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_119.pth saved !!!
[2025-01-18 19:34:01 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.462 (7.462)	Loss 0.8651 (0.8651)	Acc@1 81.470 (81.470)	Acc@5 96.069 (96.069)	Mem 24308MB
[2025-01-18 19:34:04 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.962)	Loss 1.2071 (0.9976)	Acc@1 73.608 (78.056)	Acc@5 91.675 (94.358)	Mem 24308MB
[2025-01-18 19:34:04 internimage_s_1k_224] (main.py 575): INFO [Epoch:119] * Acc@1 77.937 Acc@5 94.360
[2025-01-18 19:34:04 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.9%
[2025-01-18 19:34:04 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.07%
[2025-01-18 19:34:12 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.260 (8.260)	Loss 0.7460 (0.7460)	Acc@1 81.714 (81.714)	Acc@5 96.704 (96.704)	Mem 24308MB
[2025-01-18 19:34:16 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.108)	Loss 1.1252 (0.9034)	Acc@1 72.192 (78.147)	Acc@5 91.968 (94.445)	Mem 24308MB
[2025-01-18 19:34:16 internimage_s_1k_224] (main.py 575): INFO [Epoch:119] * Acc@1 78.051 Acc@5 94.474
[2025-01-18 19:34:16 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.1%
[2025-01-18 19:34:16 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 19:34:18 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 19:34:18 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 78.05%
[2025-01-18 19:34:21 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][0/312]	eta 0:12:05 lr 0.002632	time 2.3247 (2.3247)	model_time 0.5923 (0.5923)	loss 3.9870 (3.9870)	grad_norm 1.4752 (1.4752/0.0000)	mem 24308MB
[2025-01-18 19:34:27 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][10/312]	eta 0:03:52 lr 0.002631	time 0.5916 (0.7707)	model_time 0.5915 (0.6130)	loss 3.8696 (3.3993)	grad_norm 2.7544 (1.9072/0.4573)	mem 24308MB
[2025-01-18 19:34:33 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][20/312]	eta 0:03:22 lr 0.002631	time 0.6842 (0.6922)	model_time 0.6840 (0.6094)	loss 3.4446 (3.3465)	grad_norm 1.0093 (1.6760/0.5217)	mem 24308MB
[2025-01-18 19:34:39 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][30/312]	eta 0:03:05 lr 0.002630	time 0.5729 (0.6586)	model_time 0.5728 (0.6021)	loss 2.4220 (3.3179)	grad_norm 0.9381 (1.6192/0.5473)	mem 24308MB
[2025-01-18 19:34:45 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][40/312]	eta 0:02:55 lr 0.002629	time 0.5779 (0.6445)	model_time 0.5778 (0.6017)	loss 3.3148 (3.3478)	grad_norm 0.8419 (1.4812/0.5499)	mem 24308MB
[2025-01-18 19:34:51 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][50/312]	eta 0:02:46 lr 0.002629	time 0.5784 (0.6345)	model_time 0.5782 (0.6000)	loss 3.2758 (3.3374)	grad_norm 2.1343 (1.4410/0.5235)	mem 24308MB
[2025-01-18 19:34:57 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][60/312]	eta 0:02:38 lr 0.002628	time 0.6113 (0.6299)	model_time 0.6108 (0.6011)	loss 4.0105 (3.3082)	grad_norm 1.5953 (1.4717/0.4939)	mem 24308MB
[2025-01-18 19:35:03 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][70/312]	eta 0:02:31 lr 0.002627	time 0.5884 (0.6269)	model_time 0.5882 (0.6021)	loss 4.3612 (3.3396)	grad_norm 1.4686 (1.4902/0.4961)	mem 24308MB
[2025-01-18 19:35:09 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][80/312]	eta 0:02:24 lr 0.002627	time 0.6146 (0.6221)	model_time 0.6142 (0.6003)	loss 3.6720 (3.3408)	grad_norm 2.6328 (1.5366/0.5309)	mem 24308MB
[2025-01-18 19:35:15 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][90/312]	eta 0:02:17 lr 0.002626	time 0.6533 (0.6204)	model_time 0.6532 (0.6009)	loss 4.1106 (3.3565)	grad_norm 1.3287 (1.5554/0.5597)	mem 24308MB
[2025-01-18 19:35:21 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][100/312]	eta 0:02:11 lr 0.002626	time 0.5799 (0.6193)	model_time 0.5794 (0.6017)	loss 4.0253 (3.3624)	grad_norm 0.9706 (1.5143/0.5487)	mem 24308MB
[2025-01-18 19:35:27 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][110/312]	eta 0:02:05 lr 0.002625	time 0.5920 (0.6203)	model_time 0.5919 (0.6042)	loss 3.3988 (3.3644)	grad_norm 2.0370 (1.5411/0.5600)	mem 24308MB
[2025-01-18 19:35:34 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][120/312]	eta 0:01:59 lr 0.002624	time 0.6742 (0.6214)	model_time 0.6740 (0.6067)	loss 3.5772 (3.3714)	grad_norm 1.6522 (1.5572/0.5655)	mem 24308MB
[2025-01-18 19:35:40 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][130/312]	eta 0:01:52 lr 0.002624	time 0.5973 (0.6202)	model_time 0.5969 (0.6065)	loss 2.8036 (3.3700)	grad_norm 1.8283 (1.5545/0.5726)	mem 24308MB
[2025-01-18 19:35:45 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][140/312]	eta 0:01:46 lr 0.002623	time 0.5865 (0.6179)	model_time 0.5863 (0.6051)	loss 3.5345 (3.3864)	grad_norm 2.3416 (1.5840/0.5774)	mem 24308MB
[2025-01-18 19:35:51 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][150/312]	eta 0:01:39 lr 0.002622	time 0.5873 (0.6162)	model_time 0.5869 (0.6043)	loss 4.0723 (3.4030)	grad_norm 0.9395 (1.5841/0.5675)	mem 24308MB
[2025-01-18 19:35:57 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][160/312]	eta 0:01:33 lr 0.002622	time 0.5911 (0.6147)	model_time 0.5907 (0.6034)	loss 3.1809 (3.3798)	grad_norm 1.5013 (1.5611/0.5588)	mem 24308MB
[2025-01-18 19:36:03 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][170/312]	eta 0:01:27 lr 0.002621	time 0.5941 (0.6136)	model_time 0.5936 (0.6030)	loss 3.3485 (3.3886)	grad_norm 0.9215 (1.5462/0.5577)	mem 24308MB
[2025-01-18 19:36:09 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][180/312]	eta 0:01:20 lr 0.002620	time 0.5666 (0.6124)	model_time 0.5662 (0.6023)	loss 3.2482 (3.3832)	grad_norm 1.1209 (1.5630/0.5664)	mem 24308MB
[2025-01-18 19:36:15 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][190/312]	eta 0:01:14 lr 0.002620	time 0.5684 (0.6119)	model_time 0.5680 (0.6024)	loss 2.5159 (3.3830)	grad_norm 1.2868 (1.5621/0.5615)	mem 24308MB
[2025-01-18 19:36:21 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][200/312]	eta 0:01:08 lr 0.002619	time 0.5984 (0.6108)	model_time 0.5979 (0.6016)	loss 3.4737 (3.3982)	grad_norm 2.1334 (1.6287/0.6852)	mem 24308MB
[2025-01-18 19:36:27 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][210/312]	eta 0:01:02 lr 0.002619	time 0.5709 (0.6105)	model_time 0.5705 (0.6018)	loss 2.4113 (3.4122)	grad_norm 1.6533 (1.6363/0.6767)	mem 24308MB
[2025-01-18 19:36:33 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][220/312]	eta 0:00:56 lr 0.002618	time 0.5682 (0.6109)	model_time 0.5678 (0.6026)	loss 3.5817 (3.4148)	grad_norm 0.8810 (1.6124/0.6743)	mem 24308MB
[2025-01-18 19:36:39 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][230/312]	eta 0:00:50 lr 0.002617	time 0.5793 (0.6105)	model_time 0.5791 (0.6025)	loss 3.4687 (3.4176)	grad_norm 1.1447 (1.6037/0.6659)	mem 24308MB
[2025-01-18 19:36:46 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][240/312]	eta 0:00:44 lr 0.002617	time 0.6861 (0.6113)	model_time 0.6857 (0.6037)	loss 2.6927 (3.4095)	grad_norm 1.6264 (1.5991/0.6605)	mem 24308MB
[2025-01-18 19:36:52 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][250/312]	eta 0:00:37 lr 0.002616	time 0.5838 (0.6109)	model_time 0.5832 (0.6035)	loss 3.2871 (3.4197)	grad_norm 1.4677 (1.6304/0.6976)	mem 24308MB
[2025-01-18 19:36:58 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][260/312]	eta 0:00:31 lr 0.002615	time 0.5944 (0.6105)	model_time 0.5942 (0.6034)	loss 3.6687 (3.4234)	grad_norm 1.6607 (1.6207/0.6887)	mem 24308MB
[2025-01-18 19:37:04 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][270/312]	eta 0:00:25 lr 0.002615	time 0.5873 (0.6100)	model_time 0.5869 (0.6032)	loss 2.4153 (3.4208)	grad_norm 3.6007 (1.6341/0.7005)	mem 24308MB
[2025-01-18 19:37:09 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][280/312]	eta 0:00:19 lr 0.002614	time 0.5734 (0.6090)	model_time 0.5732 (0.6024)	loss 3.0256 (3.4293)	grad_norm 2.1699 (1.6496/0.7049)	mem 24308MB
[2025-01-18 19:37:15 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][290/312]	eta 0:00:13 lr 0.002613	time 0.5793 (0.6084)	model_time 0.5791 (0.6020)	loss 4.3160 (3.4303)	grad_norm 2.2116 (1.6483/0.6970)	mem 24308MB
[2025-01-18 19:37:21 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][300/312]	eta 0:00:07 lr 0.002613	time 0.5664 (0.6079)	model_time 0.5663 (0.6017)	loss 2.5306 (3.4261)	grad_norm 0.9279 (1.6395/0.6907)	mem 24308MB
[2025-01-18 19:37:27 internimage_s_1k_224] (main.py 510): INFO Train: [120/300][310/312]	eta 0:00:01 lr 0.002612	time 0.5722 (0.6072)	model_time 0.5721 (0.6012)	loss 2.3403 (3.4085)	grad_norm 2.2719 (1.6312/0.6939)	mem 24308MB
[2025-01-18 19:37:28 internimage_s_1k_224] (main.py 519): INFO EPOCH 120 training takes 0:03:09
[2025-01-18 19:37:28 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_120.pth saving......
[2025-01-18 19:37:30 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_120.pth saved !!!
[2025-01-18 19:37:38 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.892 (7.892)	Loss 0.8566 (0.8566)	Acc@1 80.786 (80.786)	Acc@5 95.972 (95.972)	Mem 24308MB
[2025-01-18 19:37:41 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.025)	Loss 1.1993 (0.9970)	Acc@1 73.169 (77.996)	Acc@5 91.870 (94.451)	Mem 24308MB
[2025-01-18 19:37:41 internimage_s_1k_224] (main.py 575): INFO [Epoch:120] * Acc@1 77.901 Acc@5 94.494
[2025-01-18 19:37:41 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.9%
[2025-01-18 19:37:41 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.07%
[2025-01-18 19:37:50 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.365 (8.365)	Loss 0.7444 (0.7444)	Acc@1 81.787 (81.787)	Acc@5 96.729 (96.729)	Mem 24308MB
[2025-01-18 19:37:53 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.113)	Loss 1.1214 (0.9007)	Acc@1 72.437 (78.249)	Acc@5 92.090 (94.491)	Mem 24308MB
[2025-01-18 19:37:54 internimage_s_1k_224] (main.py 575): INFO [Epoch:120] * Acc@1 78.151 Acc@5 94.514
[2025-01-18 19:37:54 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.2%
[2025-01-18 19:37:54 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 19:37:55 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 19:37:55 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 78.15%
[2025-01-18 19:37:58 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][0/312]	eta 0:11:45 lr 0.002612	time 2.2626 (2.2626)	model_time 0.5946 (0.5946)	loss 3.4845 (3.4845)	grad_norm 1.5730 (1.5730/0.0000)	mem 24308MB
[2025-01-18 19:38:03 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][10/312]	eta 0:03:42 lr 0.002611	time 0.5833 (0.7376)	model_time 0.5831 (0.5857)	loss 3.9063 (3.4890)	grad_norm 2.3480 (2.1219/0.7961)	mem 24308MB
[2025-01-18 19:38:10 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][20/312]	eta 0:03:18 lr 0.002611	time 0.5726 (0.6796)	model_time 0.5724 (0.5999)	loss 3.5612 (3.4115)	grad_norm 0.9672 (1.9062/0.7361)	mem 24308MB
[2025-01-18 19:38:16 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][30/312]	eta 0:03:07 lr 0.002610	time 0.5783 (0.6643)	model_time 0.5778 (0.6102)	loss 3.8132 (3.3941)	grad_norm 1.1492 (1.8334/0.6966)	mem 24308MB
[2025-01-18 19:38:22 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][40/312]	eta 0:02:57 lr 0.002610	time 0.5723 (0.6535)	model_time 0.5721 (0.6125)	loss 3.4163 (3.3899)	grad_norm 1.5186 (1.7653/0.6518)	mem 24308MB
[2025-01-18 19:38:29 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][50/312]	eta 0:02:50 lr 0.002609	time 0.6877 (0.6508)	model_time 0.6876 (0.6177)	loss 3.2184 (3.4457)	grad_norm 1.4237 (1.7972/0.6709)	mem 24308MB
[2025-01-18 19:38:35 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][60/312]	eta 0:02:42 lr 0.002608	time 0.5918 (0.6438)	model_time 0.5914 (0.6161)	loss 2.4474 (3.3982)	grad_norm 1.1474 (1.7406/0.6524)	mem 24308MB
[2025-01-18 19:38:41 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][70/312]	eta 0:02:34 lr 0.002608	time 0.5837 (0.6379)	model_time 0.5835 (0.6141)	loss 3.3050 (3.4068)	grad_norm 1.7937 (1.6883/0.6340)	mem 24308MB
[2025-01-18 19:38:47 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][80/312]	eta 0:02:26 lr 0.002607	time 0.5824 (0.6329)	model_time 0.5823 (0.6120)	loss 3.9488 (3.3875)	grad_norm 2.7738 (1.6822/0.6208)	mem 24308MB
[2025-01-18 19:38:52 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][90/312]	eta 0:02:19 lr 0.002606	time 0.5859 (0.6276)	model_time 0.5857 (0.6089)	loss 2.5772 (3.3771)	grad_norm 0.7554 (1.6551/0.6094)	mem 24308MB
[2025-01-18 19:38:58 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][100/312]	eta 0:02:12 lr 0.002606	time 0.5800 (0.6247)	model_time 0.5799 (0.6078)	loss 4.0325 (3.4005)	grad_norm 1.0052 (1.6771/0.6218)	mem 24308MB
[2025-01-18 19:39:04 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][110/312]	eta 0:02:05 lr 0.002605	time 0.6097 (0.6219)	model_time 0.6095 (0.6065)	loss 2.8188 (3.4056)	grad_norm 1.0000 (1.6727/0.6392)	mem 24308MB
[2025-01-18 19:39:11 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][120/312]	eta 0:01:59 lr 0.002604	time 0.5823 (0.6213)	model_time 0.5821 (0.6071)	loss 3.8793 (3.4151)	grad_norm 1.7395 (1.6623/0.6256)	mem 24308MB
[2025-01-18 19:39:16 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][130/312]	eta 0:01:52 lr 0.002604	time 0.5775 (0.6187)	model_time 0.5773 (0.6056)	loss 4.0036 (3.4423)	grad_norm 1.2540 (1.6388/0.6282)	mem 24308MB
[2025-01-18 19:39:22 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][140/312]	eta 0:01:46 lr 0.002603	time 0.6337 (0.6173)	model_time 0.6335 (0.6051)	loss 4.1760 (3.4382)	grad_norm 1.3449 (1.6276/0.6243)	mem 24308MB
[2025-01-18 19:39:29 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][150/312]	eta 0:01:39 lr 0.002603	time 0.6562 (0.6172)	model_time 0.6557 (0.6058)	loss 3.7756 (3.4236)	grad_norm 1.7649 (1.6113/0.6192)	mem 24308MB
[2025-01-18 19:39:35 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][160/312]	eta 0:01:33 lr 0.002602	time 0.5818 (0.6174)	model_time 0.5817 (0.6067)	loss 2.4210 (3.4263)	grad_norm 1.1521 (1.6331/0.6344)	mem 24308MB
[2025-01-18 19:39:41 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][170/312]	eta 0:01:27 lr 0.002601	time 0.5736 (0.6172)	model_time 0.5732 (0.6071)	loss 3.2438 (3.4285)	grad_norm 1.7402 (1.6410/0.6324)	mem 24308MB
[2025-01-18 19:39:47 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][180/312]	eta 0:01:21 lr 0.002601	time 0.5805 (0.6170)	model_time 0.5803 (0.6074)	loss 2.9144 (3.4275)	grad_norm 2.1039 (1.6610/0.6521)	mem 24308MB
[2025-01-18 19:39:53 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][190/312]	eta 0:01:15 lr 0.002600	time 0.5778 (0.6165)	model_time 0.5774 (0.6074)	loss 3.8690 (3.4184)	grad_norm 0.6718 (1.6780/0.6679)	mem 24308MB
[2025-01-18 19:39:59 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][200/312]	eta 0:01:08 lr 0.002599	time 0.5931 (0.6153)	model_time 0.5930 (0.6066)	loss 3.1150 (3.3986)	grad_norm 1.7489 (1.6886/0.6853)	mem 24308MB
[2025-01-18 19:40:05 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][210/312]	eta 0:01:02 lr 0.002599	time 0.5755 (0.6139)	model_time 0.5754 (0.6057)	loss 3.6195 (3.4078)	grad_norm 2.7895 (1.6840/0.6797)	mem 24308MB
[2025-01-18 19:40:11 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][220/312]	eta 0:00:56 lr 0.002598	time 0.5963 (0.6131)	model_time 0.5961 (0.6052)	loss 2.5799 (3.4039)	grad_norm 1.1503 (1.6719/0.6724)	mem 24308MB
[2025-01-18 19:40:17 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][230/312]	eta 0:00:50 lr 0.002597	time 0.5834 (0.6123)	model_time 0.5829 (0.6047)	loss 3.6491 (3.4013)	grad_norm 0.9048 (1.6654/0.6779)	mem 24308MB
[2025-01-18 19:40:23 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][240/312]	eta 0:00:44 lr 0.002597	time 0.6549 (0.6119)	model_time 0.6547 (0.6047)	loss 3.1980 (3.3994)	grad_norm 1.5649 (1.6593/0.6707)	mem 24308MB
[2025-01-18 19:40:29 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][250/312]	eta 0:00:37 lr 0.002596	time 0.5815 (0.6113)	model_time 0.5813 (0.6043)	loss 4.2258 (3.4045)	grad_norm 2.5677 (1.6632/0.6621)	mem 24308MB
[2025-01-18 19:40:35 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][260/312]	eta 0:00:31 lr 0.002596	time 0.7679 (0.6112)	model_time 0.7675 (0.6045)	loss 3.1139 (3.3923)	grad_norm 0.7436 (1.6586/0.6604)	mem 24308MB
[2025-01-18 19:40:41 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][270/312]	eta 0:00:25 lr 0.002595	time 0.6682 (0.6113)	model_time 0.6678 (0.6048)	loss 3.6947 (3.3982)	grad_norm 1.2518 (1.6402/0.6560)	mem 24308MB
[2025-01-18 19:40:47 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][280/312]	eta 0:00:19 lr 0.002594	time 0.5996 (0.6111)	model_time 0.5995 (0.6048)	loss 2.7551 (3.3920)	grad_norm inf (1.6457/0.6575)	mem 24308MB
[2025-01-18 19:40:53 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][290/312]	eta 0:00:13 lr 0.002594	time 0.5791 (0.6115)	model_time 0.5787 (0.6054)	loss 3.6134 (3.3919)	grad_norm 1.3014 (1.6484/0.6512)	mem 24308MB
[2025-01-18 19:40:59 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][300/312]	eta 0:00:07 lr 0.002593	time 0.5661 (0.6117)	model_time 0.5660 (0.6058)	loss 3.5165 (3.3896)	grad_norm 1.6838 (1.6549/0.6510)	mem 24308MB
[2025-01-18 19:41:05 internimage_s_1k_224] (main.py 510): INFO Train: [121/300][310/312]	eta 0:00:01 lr 0.002592	time 0.5725 (0.6106)	model_time 0.5724 (0.6049)	loss 3.0208 (3.3926)	grad_norm 3.2137 (1.6581/0.6488)	mem 24308MB
[2025-01-18 19:41:06 internimage_s_1k_224] (main.py 519): INFO EPOCH 121 training takes 0:03:10
[2025-01-18 19:41:06 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_121.pth saving......
[2025-01-18 19:41:08 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_121.pth saved !!!
[2025-01-18 19:41:17 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.118 (9.118)	Loss 0.9137 (0.9137)	Acc@1 80.835 (80.835)	Acc@5 95.801 (95.801)	Mem 24308MB
[2025-01-18 19:41:21 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.201)	Loss 1.2671 (1.0585)	Acc@1 72.412 (77.836)	Acc@5 92.065 (94.256)	Mem 24308MB
[2025-01-18 19:41:21 internimage_s_1k_224] (main.py 575): INFO [Epoch:121] * Acc@1 77.831 Acc@5 94.326
[2025-01-18 19:41:21 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 77.8%
[2025-01-18 19:41:21 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.07%
[2025-01-18 19:41:31 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 10.138 (10.138)	Loss 0.7428 (0.7428)	Acc@1 81.934 (81.934)	Acc@5 96.777 (96.777)	Mem 24308MB
[2025-01-18 19:41:36 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.362)	Loss 1.1175 (0.8983)	Acc@1 72.461 (78.356)	Acc@5 92.236 (94.531)	Mem 24308MB
[2025-01-18 19:41:36 internimage_s_1k_224] (main.py 575): INFO [Epoch:121] * Acc@1 78.257 Acc@5 94.558
[2025-01-18 19:41:36 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.3%
[2025-01-18 19:41:36 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 19:41:38 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 19:41:38 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 78.26%
[2025-01-18 19:41:41 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][0/312]	eta 0:11:48 lr 0.002592	time 2.2707 (2.2707)	model_time 0.6075 (0.6075)	loss 3.6826 (3.6826)	grad_norm 2.5068 (2.5068/0.0000)	mem 24308MB
[2025-01-18 19:41:47 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][10/312]	eta 0:03:45 lr 0.002592	time 0.6061 (0.7468)	model_time 0.6058 (0.5954)	loss 3.6494 (3.2152)	grad_norm 1.3367 (1.7388/0.6915)	mem 24308MB
[2025-01-18 19:41:53 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][20/312]	eta 0:03:15 lr 0.002591	time 0.5831 (0.6702)	model_time 0.5829 (0.5907)	loss 3.5052 (3.2146)	grad_norm 1.1665 (1.6575/0.6297)	mem 24308MB
[2025-01-18 19:41:58 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][30/312]	eta 0:03:02 lr 0.002590	time 0.5903 (0.6458)	model_time 0.5902 (0.5918)	loss 3.6232 (3.3125)	grad_norm 1.4091 (1.6697/0.5844)	mem 24308MB
[2025-01-18 19:42:04 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][40/312]	eta 0:02:52 lr 0.002590	time 0.5847 (0.6328)	model_time 0.5842 (0.5919)	loss 3.6498 (3.4079)	grad_norm 2.1655 (1.6798/0.5245)	mem 24308MB
[2025-01-18 19:42:10 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][50/312]	eta 0:02:44 lr 0.002589	time 0.6966 (0.6274)	model_time 0.6961 (0.5945)	loss 3.8931 (3.4247)	grad_norm 2.1047 (1.6612/0.5301)	mem 24308MB
[2025-01-18 19:42:16 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][60/312]	eta 0:02:36 lr 0.002588	time 0.5878 (0.6219)	model_time 0.5877 (0.5943)	loss 3.9706 (3.4524)	grad_norm 3.0538 (1.8209/0.7079)	mem 24308MB
[2025-01-18 19:42:22 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][70/312]	eta 0:02:29 lr 0.002588	time 0.7104 (0.6185)	model_time 0.7100 (0.5948)	loss 2.3656 (3.4546)	grad_norm 1.4679 (1.8118/0.7201)	mem 24308MB
[2025-01-18 19:42:28 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][80/312]	eta 0:02:22 lr 0.002587	time 0.5821 (0.6157)	model_time 0.5820 (0.5949)	loss 3.8732 (3.4621)	grad_norm 1.1642 (1.7644/0.7081)	mem 24308MB
[2025-01-18 19:42:35 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][90/312]	eta 0:02:16 lr 0.002587	time 0.6650 (0.6166)	model_time 0.6648 (0.5979)	loss 3.9867 (3.4883)	grad_norm 1.1479 (1.6826/0.7135)	mem 24308MB
[2025-01-18 19:42:41 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][100/312]	eta 0:02:10 lr 0.002586	time 0.5726 (0.6171)	model_time 0.5725 (0.6001)	loss 3.9669 (3.4798)	grad_norm 1.6997 (1.6522/0.6918)	mem 24308MB
[2025-01-18 19:42:47 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][110/312]	eta 0:02:04 lr 0.002585	time 0.5796 (0.6178)	model_time 0.5795 (0.6023)	loss 3.6531 (3.4726)	grad_norm 1.2252 (1.6434/0.6856)	mem 24308MB
[2025-01-18 19:42:53 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][120/312]	eta 0:01:58 lr 0.002585	time 0.6967 (0.6168)	model_time 0.6966 (0.6026)	loss 4.0517 (3.4540)	grad_norm 1.7159 (1.7034/0.7453)	mem 24308MB
[2025-01-18 19:42:59 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][130/312]	eta 0:01:52 lr 0.002584	time 0.5792 (0.6160)	model_time 0.5787 (0.6028)	loss 2.3905 (3.4523)	grad_norm 2.1726 (1.7509/0.7440)	mem 24308MB
[2025-01-18 19:43:05 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][140/312]	eta 0:01:45 lr 0.002583	time 0.5854 (0.6139)	model_time 0.5852 (0.6017)	loss 4.0803 (3.4589)	grad_norm 1.0147 (1.7149/0.7314)	mem 24308MB
[2025-01-18 19:43:11 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][150/312]	eta 0:01:39 lr 0.002583	time 0.5876 (0.6139)	model_time 0.5875 (0.6024)	loss 4.0850 (3.4748)	grad_norm 1.3241 (1.6956/0.7196)	mem 24308MB
[2025-01-18 19:43:17 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][160/312]	eta 0:01:33 lr 0.002582	time 0.5815 (0.6131)	model_time 0.5813 (0.6023)	loss 2.3854 (3.4625)	grad_norm 2.1124 (1.7047/0.7184)	mem 24308MB
[2025-01-18 19:43:23 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][170/312]	eta 0:01:26 lr 0.002581	time 0.7105 (0.6125)	model_time 0.7104 (0.6024)	loss 3.9869 (3.4670)	grad_norm 0.7756 (1.6908/0.7076)	mem 24308MB
[2025-01-18 19:43:29 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][180/312]	eta 0:01:20 lr 0.002581	time 0.6045 (0.6122)	model_time 0.6040 (0.6026)	loss 3.7276 (3.4655)	grad_norm 0.9823 (1.6838/0.7017)	mem 24308MB
[2025-01-18 19:43:35 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][190/312]	eta 0:01:14 lr 0.002580	time 0.5849 (0.6108)	model_time 0.5847 (0.6017)	loss 4.1733 (3.4631)	grad_norm 1.0052 (1.6578/0.6945)	mem 24308MB
[2025-01-18 19:43:41 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][200/312]	eta 0:01:08 lr 0.002580	time 0.5703 (0.6107)	model_time 0.5702 (0.6020)	loss 3.3459 (3.4663)	grad_norm 0.9887 (1.6563/0.6997)	mem 24308MB
[2025-01-18 19:43:47 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][210/312]	eta 0:01:02 lr 0.002579	time 0.5886 (0.6113)	model_time 0.5882 (0.6030)	loss 3.6167 (3.4727)	grad_norm 1.1167 (1.6270/0.6974)	mem 24308MB
[2025-01-18 19:43:54 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][220/312]	eta 0:00:56 lr 0.002578	time 0.5902 (0.6121)	model_time 0.5901 (0.6042)	loss 4.2271 (3.4725)	grad_norm 1.3298 (1.6278/0.7003)	mem 24308MB
[2025-01-18 19:44:00 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][230/312]	eta 0:00:50 lr 0.002578	time 0.5800 (0.6125)	model_time 0.5795 (0.6049)	loss 3.9901 (3.4650)	grad_norm 1.5508 (1.6311/0.7010)	mem 24308MB
[2025-01-18 19:44:06 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][240/312]	eta 0:00:44 lr 0.002577	time 0.5907 (0.6120)	model_time 0.5902 (0.6047)	loss 2.1090 (3.4542)	grad_norm 2.3952 (1.6442/0.7049)	mem 24308MB
[2025-01-18 19:44:12 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][250/312]	eta 0:00:37 lr 0.002576	time 0.7153 (0.6127)	model_time 0.7151 (0.6057)	loss 3.6729 (3.4484)	grad_norm 3.7846 (1.6652/0.7172)	mem 24308MB
[2025-01-18 19:44:18 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][260/312]	eta 0:00:31 lr 0.002576	time 0.5769 (0.6115)	model_time 0.5767 (0.6047)	loss 3.2047 (3.4371)	grad_norm 1.1061 (1.6768/0.7248)	mem 24308MB
[2025-01-18 19:44:24 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][270/312]	eta 0:00:25 lr 0.002575	time 0.5776 (0.6108)	model_time 0.5774 (0.6042)	loss 2.2798 (3.4314)	grad_norm 0.9455 (1.6616/0.7210)	mem 24308MB
[2025-01-18 19:44:30 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][280/312]	eta 0:00:19 lr 0.002574	time 0.5916 (0.6104)	model_time 0.5912 (0.6040)	loss 2.8260 (3.4281)	grad_norm 2.2389 (1.6600/0.7121)	mem 24308MB
[2025-01-18 19:44:36 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][290/312]	eta 0:00:13 lr 0.002574	time 0.5628 (0.6096)	model_time 0.5627 (0.6035)	loss 3.9437 (3.4297)	grad_norm 1.8224 (1.6599/0.7178)	mem 24308MB
[2025-01-18 19:44:42 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][300/312]	eta 0:00:07 lr 0.002573	time 0.5696 (0.6093)	model_time 0.5695 (0.6033)	loss 3.4211 (3.4318)	grad_norm 1.5586 (1.6457/0.7158)	mem 24308MB
[2025-01-18 19:44:48 internimage_s_1k_224] (main.py 510): INFO Train: [122/300][310/312]	eta 0:00:01 lr 0.002573	time 0.5675 (0.6081)	model_time 0.5675 (0.6024)	loss 3.7975 (3.4334)	grad_norm 0.9350 (1.6601/0.7271)	mem 24308MB
[2025-01-18 19:44:48 internimage_s_1k_224] (main.py 519): INFO EPOCH 122 training takes 0:03:09
[2025-01-18 19:44:48 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_122.pth saving......
[2025-01-18 19:44:50 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_122.pth saved !!!
[2025-01-18 19:44:57 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.355 (7.355)	Loss 0.8464 (0.8464)	Acc@1 81.885 (81.885)	Acc@5 96.313 (96.313)	Mem 24308MB
[2025-01-18 19:45:00 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.949)	Loss 1.2203 (1.0225)	Acc@1 72.729 (78.256)	Acc@5 92.188 (94.249)	Mem 24308MB
[2025-01-18 19:45:01 internimage_s_1k_224] (main.py 575): INFO [Epoch:122] * Acc@1 78.129 Acc@5 94.284
[2025-01-18 19:45:01 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.1%
[2025-01-18 19:45:01 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 19:45:03 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 19:45:03 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.13%
[2025-01-18 19:45:10 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.777 (6.777)	Loss 0.7412 (0.7412)	Acc@1 82.031 (82.031)	Acc@5 96.802 (96.802)	Mem 24308MB
[2025-01-18 19:45:13 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.933)	Loss 1.1137 (0.8958)	Acc@1 72.485 (78.438)	Acc@5 92.261 (94.576)	Mem 24308MB
[2025-01-18 19:45:13 internimage_s_1k_224] (main.py 575): INFO [Epoch:122] * Acc@1 78.341 Acc@5 94.600
[2025-01-18 19:45:13 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.3%
[2025-01-18 19:45:13 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 19:45:15 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 19:45:15 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 78.34%
[2025-01-18 19:45:18 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][0/312]	eta 0:12:27 lr 0.002572	time 2.3968 (2.3968)	model_time 0.5990 (0.5990)	loss 3.0736 (3.0736)	grad_norm 1.0189 (1.0189/0.0000)	mem 24308MB
[2025-01-18 19:45:24 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][10/312]	eta 0:03:55 lr 0.002572	time 0.6496 (0.7792)	model_time 0.6495 (0.6155)	loss 3.4128 (3.3381)	grad_norm 1.2104 (1.5287/0.3916)	mem 24308MB
[2025-01-18 19:45:30 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][20/312]	eta 0:03:25 lr 0.002571	time 0.5883 (0.7025)	model_time 0.5879 (0.6165)	loss 3.1281 (3.3942)	grad_norm 2.2408 (1.5990/0.4356)	mem 24308MB
[2025-01-18 19:45:36 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][30/312]	eta 0:03:11 lr 0.002570	time 0.5867 (0.6797)	model_time 0.5866 (0.6214)	loss 3.1830 (3.3245)	grad_norm 2.7901 (1.6488/0.4352)	mem 24308MB
[2025-01-18 19:45:42 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][40/312]	eta 0:03:00 lr 0.002570	time 0.5850 (0.6639)	model_time 0.5848 (0.6197)	loss 3.4902 (3.3015)	grad_norm 1.1635 (1.6094/0.4604)	mem 24308MB
[2025-01-18 19:45:48 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][50/312]	eta 0:02:50 lr 0.002569	time 0.6000 (0.6513)	model_time 0.5998 (0.6157)	loss 3.6849 (3.3575)	grad_norm 1.2563 (1.7372/0.6424)	mem 24308MB
[2025-01-18 19:45:54 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][60/312]	eta 0:02:42 lr 0.002569	time 0.5730 (0.6437)	model_time 0.5726 (0.6138)	loss 3.5661 (3.3876)	grad_norm 0.9275 (1.7220/0.6409)	mem 24308MB
[2025-01-18 19:46:00 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][70/312]	eta 0:02:33 lr 0.002568	time 0.5848 (0.6353)	model_time 0.5847 (0.6096)	loss 2.5775 (3.3700)	grad_norm 1.0465 (1.7440/0.6278)	mem 24308MB
[2025-01-18 19:46:06 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][80/312]	eta 0:02:26 lr 0.002567	time 0.5943 (0.6334)	model_time 0.5938 (0.6109)	loss 3.8269 (3.3583)	grad_norm 1.8239 (1.7321/0.6366)	mem 24308MB
[2025-01-18 19:46:12 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][90/312]	eta 0:02:19 lr 0.002567	time 0.5890 (0.6296)	model_time 0.5889 (0.6095)	loss 2.8116 (3.3590)	grad_norm 1.3277 (1.6879/0.6271)	mem 24308MB
[2025-01-18 19:46:18 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][100/312]	eta 0:02:12 lr 0.002566	time 0.5800 (0.6269)	model_time 0.5798 (0.6088)	loss 3.0048 (3.3795)	grad_norm 2.5192 (1.6863/0.6145)	mem 24308MB
[2025-01-18 19:46:24 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][110/312]	eta 0:02:06 lr 0.002565	time 0.5809 (0.6247)	model_time 0.5808 (0.6081)	loss 4.2889 (3.3715)	grad_norm 0.8719 (1.6878/0.6195)	mem 24308MB
[2025-01-18 19:46:30 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][120/312]	eta 0:01:59 lr 0.002565	time 0.5872 (0.6215)	model_time 0.5870 (0.6063)	loss 3.4628 (3.3723)	grad_norm 1.5013 (1.7022/0.6137)	mem 24308MB
[2025-01-18 19:46:36 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][130/312]	eta 0:01:52 lr 0.002564	time 0.5875 (0.6207)	model_time 0.5874 (0.6066)	loss 4.4102 (3.3880)	grad_norm 0.8078 (1.6943/0.6189)	mem 24308MB
[2025-01-18 19:46:43 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][140/312]	eta 0:01:46 lr 0.002563	time 0.5821 (0.6215)	model_time 0.5817 (0.6085)	loss 4.1789 (3.3979)	grad_norm 1.0640 (1.6651/0.6130)	mem 24308MB
[2025-01-18 19:46:49 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][150/312]	eta 0:01:40 lr 0.002563	time 0.5822 (0.6225)	model_time 0.5820 (0.6102)	loss 3.7960 (3.4011)	grad_norm 2.5272 (1.6705/0.6023)	mem 24308MB
[2025-01-18 19:46:56 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][160/312]	eta 0:01:34 lr 0.002562	time 0.5888 (0.6240)	model_time 0.5886 (0.6125)	loss 2.2759 (3.3912)	grad_norm 1.9928 (1.7033/0.6707)	mem 24308MB
[2025-01-18 19:47:02 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][170/312]	eta 0:01:28 lr 0.002562	time 0.5922 (0.6237)	model_time 0.5918 (0.6129)	loss 2.8819 (3.3790)	grad_norm 2.1771 (1.7227/0.7039)	mem 24308MB
[2025-01-18 19:47:08 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][180/312]	eta 0:01:22 lr 0.002561	time 0.5850 (0.6227)	model_time 0.5847 (0.6125)	loss 3.4358 (3.3773)	grad_norm 1.0060 (1.7276/0.6982)	mem 24308MB
[2025-01-18 19:47:14 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][190/312]	eta 0:01:15 lr 0.002560	time 0.5851 (0.6207)	model_time 0.5850 (0.6109)	loss 3.2609 (3.3766)	grad_norm 1.7246 (1.7384/0.6940)	mem 24308MB
[2025-01-18 19:47:20 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][200/312]	eta 0:01:09 lr 0.002560	time 0.5846 (0.6198)	model_time 0.5845 (0.6105)	loss 3.7215 (3.3802)	grad_norm 1.4185 (1.7397/0.6859)	mem 24308MB
[2025-01-18 19:47:26 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][210/312]	eta 0:01:03 lr 0.002559	time 0.5769 (0.6188)	model_time 0.5764 (0.6099)	loss 2.8232 (3.3697)	grad_norm 1.1475 (1.7286/0.6778)	mem 24308MB
[2025-01-18 19:47:32 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][220/312]	eta 0:00:56 lr 0.002558	time 0.5935 (0.6177)	model_time 0.5931 (0.6092)	loss 3.5527 (3.3642)	grad_norm 1.6398 (1.7226/0.6739)	mem 24308MB
[2025-01-18 19:47:37 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][230/312]	eta 0:00:50 lr 0.002558	time 0.5864 (0.6162)	model_time 0.5863 (0.6081)	loss 2.8572 (3.3688)	grad_norm 1.8165 (1.7334/0.6748)	mem 24308MB
[2025-01-18 19:47:43 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][240/312]	eta 0:00:44 lr 0.002557	time 0.5861 (0.6150)	model_time 0.5859 (0.6072)	loss 3.4938 (3.3684)	grad_norm 1.3246 (1.7451/0.6920)	mem 24308MB
[2025-01-18 19:47:49 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][250/312]	eta 0:00:38 lr 0.002556	time 0.5734 (0.6146)	model_time 0.5732 (0.6071)	loss 2.3639 (3.3711)	grad_norm 1.1144 (1.7687/0.7244)	mem 24308MB
[2025-01-18 19:47:55 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][260/312]	eta 0:00:31 lr 0.002556	time 0.5756 (0.6145)	model_time 0.5754 (0.6073)	loss 3.6660 (3.3761)	grad_norm 1.8411 (1.7583/0.7140)	mem 24308MB
[2025-01-18 19:48:02 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][270/312]	eta 0:00:25 lr 0.002555	time 0.5685 (0.6146)	model_time 0.5683 (0.6076)	loss 4.1679 (3.3682)	grad_norm 1.0527 (1.7469/0.7084)	mem 24308MB
[2025-01-18 19:48:08 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][280/312]	eta 0:00:19 lr 0.002555	time 0.5949 (0.6149)	model_time 0.5948 (0.6082)	loss 4.4649 (3.3709)	grad_norm 1.3401 (1.7323/0.7017)	mem 24308MB
[2025-01-18 19:48:14 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][290/312]	eta 0:00:13 lr 0.002554	time 0.5795 (0.6145)	model_time 0.5790 (0.6079)	loss 3.2725 (3.3664)	grad_norm 1.1357 (1.7217/0.6968)	mem 24308MB
[2025-01-18 19:48:20 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][300/312]	eta 0:00:07 lr 0.002553	time 0.5836 (0.6137)	model_time 0.5835 (0.6074)	loss 2.7261 (3.3680)	grad_norm 2.1943 (1.7434/0.7070)	mem 24308MB
[2025-01-18 19:48:26 internimage_s_1k_224] (main.py 510): INFO Train: [123/300][310/312]	eta 0:00:01 lr 0.002553	time 0.5693 (0.6127)	model_time 0.5692 (0.6065)	loss 3.8748 (3.3689)	grad_norm 1.1487 (1.7457/0.7114)	mem 24308MB
[2025-01-18 19:48:26 internimage_s_1k_224] (main.py 519): INFO EPOCH 123 training takes 0:03:11
[2025-01-18 19:48:26 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_123.pth saving......
[2025-01-18 19:48:28 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_123.pth saved !!!
[2025-01-18 19:48:35 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.195 (7.195)	Loss 0.8536 (0.8536)	Acc@1 81.274 (81.274)	Acc@5 96.411 (96.411)	Mem 24308MB
[2025-01-18 19:48:39 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.944)	Loss 1.2064 (1.0019)	Acc@1 73.120 (78.045)	Acc@5 92.261 (94.442)	Mem 24308MB
[2025-01-18 19:48:39 internimage_s_1k_224] (main.py 575): INFO [Epoch:123] * Acc@1 77.979 Acc@5 94.486
[2025-01-18 19:48:39 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.0%
[2025-01-18 19:48:39 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.13%
[2025-01-18 19:48:47 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.212 (8.212)	Loss 0.7394 (0.7394)	Acc@1 82.104 (82.104)	Acc@5 96.826 (96.826)	Mem 24308MB
[2025-01-18 19:48:51 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.134 (1.110)	Loss 1.1100 (0.8933)	Acc@1 72.485 (78.533)	Acc@5 92.358 (94.602)	Mem 24308MB
[2025-01-18 19:48:51 internimage_s_1k_224] (main.py 575): INFO [Epoch:123] * Acc@1 78.429 Acc@5 94.624
[2025-01-18 19:48:51 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.4%
[2025-01-18 19:48:51 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 19:48:53 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 19:48:53 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 78.43%
[2025-01-18 19:48:55 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][0/312]	eta 0:12:27 lr 0.002552	time 2.3961 (2.3961)	model_time 0.6009 (0.6009)	loss 2.5066 (2.5066)	grad_norm 1.4478 (1.4478/0.0000)	mem 24308MB
[2025-01-18 19:49:01 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][10/312]	eta 0:03:47 lr 0.002552	time 0.5845 (0.7537)	model_time 0.5841 (0.5902)	loss 4.2186 (3.3425)	grad_norm 2.1612 (1.4600/0.5741)	mem 24308MB
[2025-01-18 19:49:07 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][20/312]	eta 0:03:18 lr 0.002551	time 0.5842 (0.6796)	model_time 0.5840 (0.5938)	loss 3.4016 (3.3955)	grad_norm 2.7061 (1.5941/0.6658)	mem 24308MB
[2025-01-18 19:49:13 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][30/312]	eta 0:03:04 lr 0.002551	time 0.5787 (0.6543)	model_time 0.5785 (0.5960)	loss 3.6944 (3.3944)	grad_norm 2.4946 (1.6157/0.6544)	mem 24308MB
[2025-01-18 19:49:19 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][40/312]	eta 0:02:53 lr 0.002550	time 0.5908 (0.6386)	model_time 0.5907 (0.5945)	loss 2.6443 (3.3616)	grad_norm 1.7788 (1.7264/0.7320)	mem 24308MB
[2025-01-18 19:49:25 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][50/312]	eta 0:02:44 lr 0.002549	time 0.5962 (0.6290)	model_time 0.5961 (0.5935)	loss 3.0401 (3.4486)	grad_norm 1.9005 (1.6849/0.6887)	mem 24308MB
[2025-01-18 19:49:31 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][60/312]	eta 0:02:37 lr 0.002549	time 0.5967 (0.6267)	model_time 0.5966 (0.5969)	loss 3.5556 (3.4378)	grad_norm 1.3915 (1.6903/0.6715)	mem 24308MB
[2025-01-18 19:49:37 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][70/312]	eta 0:02:31 lr 0.002548	time 0.6657 (0.6252)	model_time 0.6656 (0.5996)	loss 2.9569 (3.4217)	grad_norm 1.0257 (1.6721/0.6574)	mem 24308MB
[2025-01-18 19:49:43 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][80/312]	eta 0:02:24 lr 0.002547	time 0.6737 (0.6227)	model_time 0.6736 (0.6002)	loss 2.2340 (3.3617)	grad_norm 0.8977 (1.6284/0.6405)	mem 24308MB
[2025-01-18 19:49:50 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][90/312]	eta 0:02:18 lr 0.002547	time 0.6557 (0.6241)	model_time 0.6552 (0.6040)	loss 3.5641 (3.3670)	grad_norm 2.7133 (1.5898/0.6400)	mem 24308MB
[2025-01-18 19:49:56 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][100/312]	eta 0:02:11 lr 0.002546	time 0.5979 (0.6218)	model_time 0.5977 (0.6037)	loss 3.9885 (3.3671)	grad_norm 1.9653 (1.5977/0.6241)	mem 24308MB
[2025-01-18 19:50:02 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][110/312]	eta 0:02:05 lr 0.002545	time 0.5921 (0.6194)	model_time 0.5919 (0.6029)	loss 4.1071 (3.3973)	grad_norm 1.6860 (1.6360/0.7286)	mem 24308MB
[2025-01-18 19:50:08 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][120/312]	eta 0:01:58 lr 0.002545	time 0.5761 (0.6173)	model_time 0.5757 (0.6021)	loss 3.7086 (3.3904)	grad_norm 1.5166 (1.6847/0.7710)	mem 24308MB
[2025-01-18 19:50:14 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][130/312]	eta 0:01:52 lr 0.002544	time 0.5688 (0.6157)	model_time 0.5683 (0.6016)	loss 3.1724 (3.3624)	grad_norm 2.7333 (1.6767/0.7608)	mem 24308MB
[2025-01-18 19:50:20 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][140/312]	eta 0:01:45 lr 0.002543	time 0.5988 (0.6145)	model_time 0.5984 (0.6014)	loss 3.2169 (3.3387)	grad_norm 1.2903 (1.6660/0.7425)	mem 24308MB
[2025-01-18 19:50:25 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][150/312]	eta 0:01:39 lr 0.002543	time 0.5937 (0.6130)	model_time 0.5935 (0.6007)	loss 3.6071 (3.3402)	grad_norm 1.1736 (1.6501/0.7270)	mem 24308MB
[2025-01-18 19:50:31 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][160/312]	eta 0:01:33 lr 0.002542	time 0.5985 (0.6121)	model_time 0.5983 (0.6006)	loss 3.4834 (3.3288)	grad_norm 1.4788 (1.6625/0.7331)	mem 24308MB
[2025-01-18 19:50:37 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][170/312]	eta 0:01:26 lr 0.002542	time 0.5673 (0.6108)	model_time 0.5669 (0.5999)	loss 3.3089 (3.3227)	grad_norm 1.8803 (1.6768/0.7358)	mem 24308MB
[2025-01-18 19:50:44 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][180/312]	eta 0:01:20 lr 0.002541	time 0.6583 (0.6115)	model_time 0.6581 (0.6011)	loss 4.1683 (3.3326)	grad_norm 1.4559 (1.6701/0.7315)	mem 24308MB
[2025-01-18 19:50:50 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][190/312]	eta 0:01:14 lr 0.002540	time 0.6904 (0.6123)	model_time 0.6902 (0.6024)	loss 3.9422 (3.3472)	grad_norm 1.7393 (1.6481/0.7214)	mem 24308MB
[2025-01-18 19:50:56 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][200/312]	eta 0:01:08 lr 0.002540	time 0.6766 (0.6127)	model_time 0.6761 (0.6033)	loss 4.2296 (3.3634)	grad_norm 1.4445 (1.6550/0.7232)	mem 24308MB
[2025-01-18 19:51:02 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][210/312]	eta 0:01:02 lr 0.002539	time 0.6741 (0.6128)	model_time 0.6736 (0.6039)	loss 3.4322 (3.3776)	grad_norm 2.3373 (1.6579/0.7139)	mem 24308MB
[2025-01-18 19:51:08 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][220/312]	eta 0:00:56 lr 0.002538	time 0.5823 (0.6127)	model_time 0.5821 (0.6041)	loss 3.9856 (3.3900)	grad_norm 2.3005 (1.6469/0.7064)	mem 24308MB
[2025-01-18 19:51:14 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][230/312]	eta 0:00:50 lr 0.002538	time 0.6576 (0.6118)	model_time 0.6570 (0.6036)	loss 3.6853 (3.3923)	grad_norm 1.0077 (1.6354/0.6995)	mem 24308MB
[2025-01-18 19:51:20 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][240/312]	eta 0:00:44 lr 0.002537	time 0.5868 (0.6113)	model_time 0.5866 (0.6034)	loss 4.3889 (3.3844)	grad_norm 1.7904 (1.6632/0.7245)	mem 24308MB
[2025-01-18 19:51:26 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][250/312]	eta 0:00:37 lr 0.002536	time 0.5952 (0.6106)	model_time 0.5950 (0.6030)	loss 2.8786 (3.3817)	grad_norm 1.0071 (1.6675/0.7410)	mem 24308MB
[2025-01-18 19:51:32 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][260/312]	eta 0:00:31 lr 0.002536	time 0.5806 (0.6099)	model_time 0.5802 (0.6026)	loss 3.0784 (3.3783)	grad_norm 1.7324 (1.6675/0.7329)	mem 24308MB
[2025-01-18 19:51:38 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][270/312]	eta 0:00:25 lr 0.002535	time 0.5816 (0.6094)	model_time 0.5814 (0.6023)	loss 3.9662 (3.3971)	grad_norm 2.1872 (1.6581/0.7257)	mem 24308MB
[2025-01-18 19:51:44 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][280/312]	eta 0:00:19 lr 0.002535	time 0.5855 (0.6091)	model_time 0.5850 (0.6023)	loss 3.1668 (3.3882)	grad_norm 1.3690 (1.6567/0.7176)	mem 24308MB
[2025-01-18 19:51:50 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][290/312]	eta 0:00:13 lr 0.002534	time 0.5705 (0.6088)	model_time 0.5700 (0.6022)	loss 4.0958 (3.3860)	grad_norm 0.6292 (1.6456/0.7112)	mem 24308MB
[2025-01-18 19:51:56 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][300/312]	eta 0:00:07 lr 0.002533	time 0.5698 (0.6082)	model_time 0.5697 (0.6018)	loss 3.6131 (3.3923)	grad_norm 1.6511 (1.6344/0.7071)	mem 24308MB
[2025-01-18 19:52:02 internimage_s_1k_224] (main.py 510): INFO Train: [124/300][310/312]	eta 0:00:01 lr 0.002533	time 0.6470 (0.6083)	model_time 0.6469 (0.6021)	loss 3.3473 (3.3889)	grad_norm 1.0046 (1.6526/0.7162)	mem 24308MB
[2025-01-18 19:52:03 internimage_s_1k_224] (main.py 519): INFO EPOCH 124 training takes 0:03:09
[2025-01-18 19:52:03 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_124.pth saving......
[2025-01-18 19:52:05 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_124.pth saved !!!
[2025-01-18 19:52:12 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.263 (7.263)	Loss 0.8880 (0.8880)	Acc@1 81.226 (81.226)	Acc@5 96.436 (96.436)	Mem 24308MB
[2025-01-18 19:52:15 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.953)	Loss 1.1864 (1.0096)	Acc@1 73.950 (78.551)	Acc@5 92.554 (94.525)	Mem 24308MB
[2025-01-18 19:52:15 internimage_s_1k_224] (main.py 575): INFO [Epoch:124] * Acc@1 78.427 Acc@5 94.578
[2025-01-18 19:52:15 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.4%
[2025-01-18 19:52:15 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 19:52:17 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 19:52:17 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.43%
[2025-01-18 19:52:24 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.273 (7.273)	Loss 0.7378 (0.7378)	Acc@1 82.202 (82.202)	Acc@5 96.826 (96.826)	Mem 24308MB
[2025-01-18 19:52:28 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.949)	Loss 1.1064 (0.8909)	Acc@1 72.754 (78.629)	Acc@5 92.407 (94.647)	Mem 24308MB
[2025-01-18 19:52:28 internimage_s_1k_224] (main.py 575): INFO [Epoch:124] * Acc@1 78.523 Acc@5 94.670
[2025-01-18 19:52:28 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.5%
[2025-01-18 19:52:28 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 19:52:30 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 19:52:30 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 78.52%
[2025-01-18 19:52:32 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][0/312]	eta 0:10:36 lr 0.002532	time 2.0385 (2.0385)	model_time 0.5887 (0.5887)	loss 3.7414 (3.7414)	grad_norm 1.9179 (1.9179/0.0000)	mem 24308MB
[2025-01-18 19:52:39 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][10/312]	eta 0:03:51 lr 0.002532	time 0.5732 (0.7667)	model_time 0.5730 (0.6346)	loss 3.6881 (3.2990)	grad_norm 1.4898 (1.5454/0.3589)	mem 24308MB
[2025-01-18 19:52:45 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][20/312]	eta 0:03:22 lr 0.002531	time 0.5912 (0.6947)	model_time 0.5910 (0.6254)	loss 3.0666 (3.1975)	grad_norm 1.6525 (1.6652/0.6346)	mem 24308MB
[2025-01-18 19:52:51 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][30/312]	eta 0:03:07 lr 0.002531	time 0.5819 (0.6634)	model_time 0.5814 (0.6163)	loss 3.5190 (3.2712)	grad_norm 1.8545 (1.7753/0.6137)	mem 24308MB
[2025-01-18 19:52:57 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][40/312]	eta 0:02:56 lr 0.002530	time 0.5740 (0.6477)	model_time 0.5738 (0.6120)	loss 2.2454 (3.3006)	grad_norm 1.0081 (1.6956/0.5936)	mem 24308MB
[2025-01-18 19:53:03 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][50/312]	eta 0:02:47 lr 0.002529	time 0.5978 (0.6383)	model_time 0.5974 (0.6095)	loss 2.6948 (3.3921)	grad_norm 0.7657 (1.6517/0.5876)	mem 24308MB
[2025-01-18 19:53:09 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][60/312]	eta 0:02:39 lr 0.002529	time 0.5761 (0.6313)	model_time 0.5760 (0.6072)	loss 3.6321 (3.3708)	grad_norm 2.4210 (1.6910/0.6410)	mem 24308MB
[2025-01-18 19:53:15 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][70/312]	eta 0:02:31 lr 0.002528	time 0.5659 (0.6266)	model_time 0.5658 (0.6058)	loss 2.8952 (3.3969)	grad_norm 1.0449 (1.6555/0.6533)	mem 24308MB
[2025-01-18 19:53:21 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][80/312]	eta 0:02:24 lr 0.002527	time 0.5731 (0.6220)	model_time 0.5729 (0.6037)	loss 3.1732 (3.4277)	grad_norm 4.1526 (1.6771/0.7506)	mem 24308MB
[2025-01-18 19:53:27 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][90/312]	eta 0:02:17 lr 0.002527	time 0.5783 (0.6191)	model_time 0.5781 (0.6028)	loss 3.5515 (3.4334)	grad_norm 1.5286 (1.7217/0.8604)	mem 24308MB
[2025-01-18 19:53:33 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][100/312]	eta 0:02:10 lr 0.002526	time 0.5933 (0.6168)	model_time 0.5929 (0.6021)	loss 2.9500 (3.4216)	grad_norm 2.5261 (1.7080/0.8404)	mem 24308MB
[2025-01-18 19:53:39 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][110/312]	eta 0:02:04 lr 0.002525	time 0.7071 (0.6156)	model_time 0.7069 (0.6021)	loss 4.1537 (3.4470)	grad_norm 1.6089 (1.7095/0.8349)	mem 24308MB
[2025-01-18 19:53:45 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][120/312]	eta 0:01:58 lr 0.002525	time 0.6792 (0.6160)	model_time 0.6787 (0.6036)	loss 2.5396 (3.4446)	grad_norm 1.5187 (1.6736/0.8153)	mem 24308MB
[2025-01-18 19:53:51 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][130/312]	eta 0:01:52 lr 0.002524	time 0.6934 (0.6167)	model_time 0.6932 (0.6053)	loss 2.9587 (3.4418)	grad_norm 1.6423 (1.7040/0.8448)	mem 24308MB
[2025-01-18 19:53:57 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][140/312]	eta 0:01:46 lr 0.002523	time 0.5726 (0.6173)	model_time 0.5724 (0.6066)	loss 3.9325 (3.4241)	grad_norm 1.2679 (1.7021/0.8272)	mem 24308MB
[2025-01-18 19:54:03 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][150/312]	eta 0:01:39 lr 0.002523	time 0.5850 (0.6163)	model_time 0.5848 (0.6063)	loss 3.9194 (3.4093)	grad_norm 1.3225 (1.6871/0.8081)	mem 24308MB
[2025-01-18 19:54:09 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][160/312]	eta 0:01:33 lr 0.002522	time 0.5740 (0.6151)	model_time 0.5738 (0.6057)	loss 3.5769 (3.4036)	grad_norm 1.3556 (1.6805/0.8041)	mem 24308MB
[2025-01-18 19:54:15 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][170/312]	eta 0:01:27 lr 0.002522	time 0.5988 (0.6140)	model_time 0.5984 (0.6051)	loss 3.2543 (3.4019)	grad_norm 1.3352 (1.6623/0.7884)	mem 24308MB
[2025-01-18 19:54:21 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][180/312]	eta 0:01:20 lr 0.002521	time 0.5891 (0.6126)	model_time 0.5886 (0.6042)	loss 4.3179 (3.4247)	grad_norm 1.0861 (1.6577/0.7822)	mem 24308MB
[2025-01-18 19:54:27 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][190/312]	eta 0:01:14 lr 0.002520	time 0.5632 (0.6112)	model_time 0.5629 (0.6032)	loss 3.1096 (3.4247)	grad_norm 0.9136 (1.6661/0.7740)	mem 24308MB
[2025-01-18 19:54:33 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][200/312]	eta 0:01:08 lr 0.002520	time 0.5753 (0.6103)	model_time 0.5752 (0.6027)	loss 2.7060 (3.4364)	grad_norm 1.0065 (1.6702/0.7613)	mem 24308MB
[2025-01-18 19:54:39 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][210/312]	eta 0:01:02 lr 0.002519	time 0.5780 (0.6097)	model_time 0.5779 (0.6024)	loss 3.1512 (3.4322)	grad_norm 2.8923 (1.6782/0.7562)	mem 24308MB
[2025-01-18 19:54:45 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][220/312]	eta 0:00:56 lr 0.002518	time 0.5834 (0.6089)	model_time 0.5827 (0.6019)	loss 3.8966 (3.4371)	grad_norm 1.0765 (1.6696/0.7550)	mem 24308MB
[2025-01-18 19:54:51 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][230/312]	eta 0:00:49 lr 0.002518	time 0.7007 (0.6084)	model_time 0.7005 (0.6017)	loss 3.5972 (3.4377)	grad_norm 2.1468 (1.6617/0.7481)	mem 24308MB
[2025-01-18 19:54:57 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][240/312]	eta 0:00:43 lr 0.002517	time 0.6745 (0.6091)	model_time 0.6744 (0.6026)	loss 3.4544 (3.4343)	grad_norm 2.0714 (1.6992/0.7888)	mem 24308MB
[2025-01-18 19:55:03 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][250/312]	eta 0:00:37 lr 0.002516	time 0.6725 (0.6094)	model_time 0.6723 (0.6032)	loss 3.9183 (3.4329)	grad_norm 1.8128 (1.7038/0.7831)	mem 24308MB
[2025-01-18 19:55:09 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][260/312]	eta 0:00:31 lr 0.002516	time 0.5747 (0.6101)	model_time 0.5742 (0.6042)	loss 3.6700 (3.4409)	grad_norm 1.4282 (1.6920/0.7756)	mem 24308MB
[2025-01-18 19:55:16 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][270/312]	eta 0:00:25 lr 0.002515	time 0.6924 (0.6101)	model_time 0.6919 (0.6044)	loss 3.3638 (3.4314)	grad_norm 1.1927 (1.6874/0.7688)	mem 24308MB
[2025-01-18 19:55:21 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][280/312]	eta 0:00:19 lr 0.002514	time 0.5789 (0.6093)	model_time 0.5787 (0.6038)	loss 3.3552 (3.4305)	grad_norm 1.3063 (1.6728/0.7620)	mem 24308MB
[2025-01-18 19:55:27 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][290/312]	eta 0:00:13 lr 0.002514	time 0.5796 (0.6091)	model_time 0.5794 (0.6037)	loss 2.5695 (3.4270)	grad_norm 2.5273 (1.6696/0.7548)	mem 24308MB
[2025-01-18 19:55:33 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][300/312]	eta 0:00:07 lr 0.002513	time 0.5683 (0.6085)	model_time 0.5683 (0.6032)	loss 3.7408 (3.4188)	grad_norm 1.6053 (1.6994/0.7888)	mem 24308MB
[2025-01-18 19:55:39 internimage_s_1k_224] (main.py 510): INFO Train: [125/300][310/312]	eta 0:00:01 lr 0.002513	time 0.5749 (0.6073)	model_time 0.5748 (0.6022)	loss 3.3059 (3.4245)	grad_norm 1.1931 (1.6939/0.7908)	mem 24308MB
[2025-01-18 19:55:40 internimage_s_1k_224] (main.py 519): INFO EPOCH 125 training takes 0:03:09
[2025-01-18 19:55:40 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_125.pth saving......
[2025-01-18 19:55:42 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_125.pth saved !!!
[2025-01-18 19:55:50 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.983 (7.983)	Loss 0.8811 (0.8811)	Acc@1 81.055 (81.055)	Acc@5 96.313 (96.313)	Mem 24308MB
[2025-01-18 19:55:53 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.033)	Loss 1.1873 (1.0213)	Acc@1 74.194 (78.112)	Acc@5 92.505 (94.538)	Mem 24308MB
[2025-01-18 19:55:53 internimage_s_1k_224] (main.py 575): INFO [Epoch:125] * Acc@1 78.069 Acc@5 94.540
[2025-01-18 19:55:53 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.1%
[2025-01-18 19:55:53 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.43%
[2025-01-18 19:56:02 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.767 (8.767)	Loss 0.7362 (0.7362)	Acc@1 82.227 (82.227)	Acc@5 96.826 (96.826)	Mem 24308MB
[2025-01-18 19:56:06 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.154)	Loss 1.1031 (0.8886)	Acc@1 72.803 (78.695)	Acc@5 92.407 (94.673)	Mem 24308MB
[2025-01-18 19:56:06 internimage_s_1k_224] (main.py 575): INFO [Epoch:125] * Acc@1 78.581 Acc@5 94.698
[2025-01-18 19:56:06 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.6%
[2025-01-18 19:56:06 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 19:56:08 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 19:56:08 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 78.58%
[2025-01-18 19:56:10 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][0/312]	eta 0:12:20 lr 0.002512	time 2.3719 (2.3719)	model_time 0.6029 (0.6029)	loss 3.0668 (3.0668)	grad_norm 1.1875 (1.1875/0.0000)	mem 24308MB
[2025-01-18 19:56:16 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][10/312]	eta 0:03:48 lr 0.002512	time 0.5994 (0.7565)	model_time 0.5993 (0.5954)	loss 4.0124 (3.5503)	grad_norm 1.2962 (1.2035/0.1585)	mem 24308MB
[2025-01-18 19:56:22 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][20/312]	eta 0:03:20 lr 0.002511	time 0.5902 (0.6872)	model_time 0.5901 (0.6026)	loss 4.0922 (3.2919)	grad_norm 2.1404 (1.5302/0.4787)	mem 24308MB
[2025-01-18 19:56:28 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][30/312]	eta 0:03:04 lr 0.002510	time 0.5898 (0.6551)	model_time 0.5896 (0.5976)	loss 3.0888 (3.2583)	grad_norm 2.5423 (1.6664/0.6363)	mem 24308MB
[2025-01-18 19:56:34 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][40/312]	eta 0:02:54 lr 0.002510	time 0.6600 (0.6424)	model_time 0.6595 (0.5989)	loss 4.1126 (3.3425)	grad_norm 1.6339 (1.6863/0.6501)	mem 24308MB
[2025-01-18 19:56:41 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][50/312]	eta 0:02:47 lr 0.002509	time 0.5723 (0.6380)	model_time 0.5719 (0.6029)	loss 4.0610 (3.3795)	grad_norm 1.3419 (1.6464/0.6274)	mem 24308MB
[2025-01-18 19:56:47 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][60/312]	eta 0:02:39 lr 0.002509	time 0.5918 (0.6331)	model_time 0.5916 (0.6037)	loss 3.0481 (3.3893)	grad_norm 0.8144 (1.6002/0.6254)	mem 24308MB
[2025-01-18 19:56:53 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][70/312]	eta 0:02:33 lr 0.002508	time 0.6764 (0.6343)	model_time 0.6759 (0.6090)	loss 4.1934 (3.4123)	grad_norm 1.7129 (1.5715/0.5950)	mem 24308MB
[2025-01-18 19:56:59 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][80/312]	eta 0:02:26 lr 0.002507	time 0.5894 (0.6314)	model_time 0.5892 (0.6092)	loss 3.5596 (3.4049)	grad_norm 2.7113 (1.5984/0.6245)	mem 24308MB
[2025-01-18 19:57:05 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][90/312]	eta 0:02:19 lr 0.002507	time 0.5751 (0.6264)	model_time 0.5750 (0.6066)	loss 3.1231 (3.4381)	grad_norm 1.1567 (1.6563/0.6792)	mem 24308MB
[2025-01-18 19:57:11 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][100/312]	eta 0:02:12 lr 0.002506	time 0.5789 (0.6241)	model_time 0.5787 (0.6062)	loss 2.3778 (3.4338)	grad_norm 1.0032 (1.6111/0.6633)	mem 24308MB
[2025-01-18 19:57:17 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][110/312]	eta 0:02:05 lr 0.002505	time 0.5828 (0.6213)	model_time 0.5826 (0.6050)	loss 3.5021 (3.4434)	grad_norm 2.0578 (1.6207/0.6605)	mem 24308MB
[2025-01-18 19:57:23 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][120/312]	eta 0:01:58 lr 0.002505	time 0.5709 (0.6182)	model_time 0.5705 (0.6032)	loss 3.6713 (3.4328)	grad_norm 1.9115 (1.6763/0.7108)	mem 24308MB
[2025-01-18 19:57:29 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][130/312]	eta 0:01:52 lr 0.002504	time 0.5758 (0.6164)	model_time 0.5753 (0.6026)	loss 3.3323 (3.4195)	grad_norm 0.8168 (1.6335/0.7022)	mem 24308MB
[2025-01-18 19:57:35 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][140/312]	eta 0:01:45 lr 0.002503	time 0.5749 (0.6151)	model_time 0.5747 (0.6022)	loss 3.7139 (3.4252)	grad_norm 1.5927 (1.6230/0.6937)	mem 24308MB
[2025-01-18 19:57:41 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][150/312]	eta 0:01:39 lr 0.002503	time 0.5796 (0.6133)	model_time 0.5792 (0.6013)	loss 3.5792 (3.4174)	grad_norm 1.1008 (1.5923/0.6853)	mem 24308MB
[2025-01-18 19:57:47 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][160/312]	eta 0:01:33 lr 0.002502	time 0.5926 (0.6122)	model_time 0.5922 (0.6009)	loss 3.1674 (3.4183)	grad_norm 2.4813 (1.6037/0.6860)	mem 24308MB
[2025-01-18 19:57:53 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][170/312]	eta 0:01:27 lr 0.002501	time 0.5757 (0.6133)	model_time 0.5753 (0.6026)	loss 3.6646 (3.4267)	grad_norm 1.2883 (1.6242/0.6887)	mem 24308MB
[2025-01-18 19:57:59 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][180/312]	eta 0:01:21 lr 0.002501	time 0.5844 (0.6140)	model_time 0.5842 (0.6039)	loss 3.5883 (3.4148)	grad_norm 2.6023 (1.6631/0.7203)	mem 24308MB
[2025-01-18 19:58:06 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][190/312]	eta 0:01:15 lr 0.002500	time 0.6758 (0.6153)	model_time 0.6754 (0.6057)	loss 3.1932 (3.4143)	grad_norm 1.8414 (1.6858/0.7355)	mem 24308MB
[2025-01-18 19:58:12 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][200/312]	eta 0:01:08 lr 0.002500	time 0.5922 (0.6150)	model_time 0.5918 (0.6058)	loss 3.7170 (3.4156)	grad_norm 1.7793 (1.6938/0.7279)	mem 24308MB
[2025-01-18 19:58:18 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][210/312]	eta 0:01:02 lr 0.002499	time 0.5754 (0.6139)	model_time 0.5752 (0.6052)	loss 4.2533 (3.4329)	grad_norm 2.1020 (1.6871/0.7189)	mem 24308MB
[2025-01-18 19:58:24 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][220/312]	eta 0:00:56 lr 0.002498	time 0.5774 (0.6144)	model_time 0.5772 (0.6060)	loss 2.3219 (3.4249)	grad_norm 1.7388 (1.6769/0.7046)	mem 24308MB
[2025-01-18 19:58:30 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][230/312]	eta 0:00:50 lr 0.002498	time 0.5842 (0.6137)	model_time 0.5841 (0.6056)	loss 2.7889 (3.4167)	grad_norm 1.4105 (1.6585/0.6988)	mem 24308MB
[2025-01-18 19:58:36 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][240/312]	eta 0:00:44 lr 0.002497	time 0.5863 (0.6125)	model_time 0.5861 (0.6047)	loss 3.8477 (3.4052)	grad_norm 1.5133 (1.6462/0.6935)	mem 24308MB
[2025-01-18 19:58:42 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][250/312]	eta 0:00:37 lr 0.002496	time 0.5926 (0.6118)	model_time 0.5921 (0.6043)	loss 4.1402 (3.4022)	grad_norm 3.1898 (1.6387/0.6944)	mem 24308MB
[2025-01-18 19:58:48 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][260/312]	eta 0:00:31 lr 0.002496	time 0.5944 (0.6113)	model_time 0.5939 (0.6041)	loss 3.6282 (3.4046)	grad_norm 1.0910 (1.6378/0.6861)	mem 24308MB
[2025-01-18 19:58:53 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][270/312]	eta 0:00:25 lr 0.002495	time 0.5855 (0.6104)	model_time 0.5853 (0.6034)	loss 3.6796 (3.4172)	grad_norm 2.3615 (1.6697/0.7360)	mem 24308MB
[2025-01-18 19:58:59 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][280/312]	eta 0:00:19 lr 0.002494	time 0.5949 (0.6095)	model_time 0.5947 (0.6028)	loss 3.8209 (3.4237)	grad_norm 0.8839 (1.6674/0.7320)	mem 24308MB
[2025-01-18 19:59:05 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][290/312]	eta 0:00:13 lr 0.002494	time 0.5812 (0.6099)	model_time 0.5807 (0.6034)	loss 3.1206 (3.4242)	grad_norm 1.3181 (1.6491/0.7277)	mem 24308MB
[2025-01-18 19:59:12 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][300/312]	eta 0:00:07 lr 0.002493	time 0.5623 (0.6100)	model_time 0.5621 (0.6037)	loss 3.7426 (3.4191)	grad_norm 1.0779 (1.6439/0.7253)	mem 24308MB
[2025-01-18 19:59:18 internimage_s_1k_224] (main.py 510): INFO Train: [126/300][310/312]	eta 0:00:01 lr 0.002492	time 0.5697 (0.6098)	model_time 0.5696 (0.6037)	loss 3.4589 (3.4227)	grad_norm 2.0888 (1.6697/0.7303)	mem 24308MB
[2025-01-18 19:59:18 internimage_s_1k_224] (main.py 519): INFO EPOCH 126 training takes 0:03:10
[2025-01-18 19:59:19 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_126.pth saving......
[2025-01-18 19:59:20 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_126.pth saved !!!
[2025-01-18 19:59:27 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.127 (7.127)	Loss 0.8883 (0.8883)	Acc@1 81.616 (81.616)	Acc@5 96.216 (96.216)	Mem 24308MB
[2025-01-18 19:59:31 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.135 (0.933)	Loss 1.1561 (1.0211)	Acc@1 75.000 (78.396)	Acc@5 93.115 (94.633)	Mem 24308MB
[2025-01-18 19:59:31 internimage_s_1k_224] (main.py 575): INFO [Epoch:126] * Acc@1 78.369 Acc@5 94.674
[2025-01-18 19:59:31 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.4%
[2025-01-18 19:59:31 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.43%
[2025-01-18 19:59:39 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.131 (8.131)	Loss 0.7345 (0.7345)	Acc@1 82.300 (82.300)	Acc@5 96.826 (96.826)	Mem 24308MB
[2025-01-18 19:59:43 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.101)	Loss 1.0995 (0.8863)	Acc@1 72.949 (78.791)	Acc@5 92.432 (94.722)	Mem 24308MB
[2025-01-18 19:59:43 internimage_s_1k_224] (main.py 575): INFO [Epoch:126] * Acc@1 78.667 Acc@5 94.744
[2025-01-18 19:59:43 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.7%
[2025-01-18 19:59:43 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 19:59:45 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 19:59:45 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 78.67%
[2025-01-18 19:59:47 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][0/312]	eta 0:11:46 lr 0.002492	time 2.2630 (2.2630)	model_time 0.5966 (0.5966)	loss 3.4909 (3.4909)	grad_norm 1.2829 (1.2829/0.0000)	mem 24308MB
[2025-01-18 19:59:53 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][10/312]	eta 0:03:48 lr 0.002492	time 0.5633 (0.7582)	model_time 0.5631 (0.6064)	loss 3.2606 (3.4088)	grad_norm 1.0294 (1.6469/0.4477)	mem 24308MB
[2025-01-18 19:59:59 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][20/312]	eta 0:03:19 lr 0.002491	time 0.6081 (0.6827)	model_time 0.6079 (0.6030)	loss 3.5244 (3.4285)	grad_norm 1.4143 (1.6404/0.3686)	mem 24308MB
[2025-01-18 20:00:06 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][30/312]	eta 0:03:05 lr 0.002490	time 0.5837 (0.6576)	model_time 0.5833 (0.6035)	loss 2.4250 (3.4084)	grad_norm 1.9460 (1.6703/0.4374)	mem 24308MB
[2025-01-18 20:00:11 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][40/312]	eta 0:02:54 lr 0.002490	time 0.5862 (0.6413)	model_time 0.5860 (0.6003)	loss 2.3235 (3.3643)	grad_norm 1.4758 (1.7008/0.4474)	mem 24308MB
[2025-01-18 20:00:17 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][50/312]	eta 0:02:45 lr 0.002489	time 0.5894 (0.6318)	model_time 0.5893 (0.5987)	loss 2.9809 (3.3898)	grad_norm 1.2795 (1.7246/0.4675)	mem 24308MB
[2025-01-18 20:00:23 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][60/312]	eta 0:02:37 lr 0.002488	time 0.5900 (0.6262)	model_time 0.5898 (0.5985)	loss 3.4963 (3.4073)	grad_norm 1.6062 (1.6522/0.4824)	mem 24308MB
[2025-01-18 20:00:29 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][70/312]	eta 0:02:30 lr 0.002488	time 0.5701 (0.6232)	model_time 0.5696 (0.5993)	loss 3.5925 (3.4186)	grad_norm 1.6691 (1.6677/0.5139)	mem 24308MB
[2025-01-18 20:00:35 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][80/312]	eta 0:02:23 lr 0.002487	time 0.5798 (0.6187)	model_time 0.5791 (0.5978)	loss 2.6315 (3.4146)	grad_norm 3.0108 (1.6928/0.5349)	mem 24308MB
[2025-01-18 20:00:41 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][90/312]	eta 0:02:16 lr 0.002486	time 0.5680 (0.6161)	model_time 0.5675 (0.5974)	loss 3.7986 (3.4111)	grad_norm 0.7331 (1.6913/0.5576)	mem 24308MB
[2025-01-18 20:00:47 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][100/312]	eta 0:02:10 lr 0.002486	time 0.5932 (0.6151)	model_time 0.5927 (0.5982)	loss 3.7195 (3.4299)	grad_norm 1.4258 (1.6552/0.5477)	mem 24308MB
[2025-01-18 20:00:54 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][110/312]	eta 0:02:04 lr 0.002485	time 0.5884 (0.6166)	model_time 0.5882 (0.6012)	loss 3.9576 (3.4320)	grad_norm 1.4980 (1.6409/0.5300)	mem 24308MB
[2025-01-18 20:01:00 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][120/312]	eta 0:01:58 lr 0.002485	time 0.6627 (0.6175)	model_time 0.6621 (0.6033)	loss 3.8901 (3.4313)	grad_norm 3.2766 (1.6903/0.5959)	mem 24308MB
[2025-01-18 20:01:06 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][130/312]	eta 0:01:52 lr 0.002484	time 0.5677 (0.6176)	model_time 0.5676 (0.6045)	loss 3.8843 (3.4324)	grad_norm 1.6843 (1.6956/0.6021)	mem 24308MB
[2025-01-18 20:01:12 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][140/312]	eta 0:01:45 lr 0.002483	time 0.5861 (0.6158)	model_time 0.5859 (0.6036)	loss 2.6634 (3.4317)	grad_norm 0.9695 (1.6999/0.6057)	mem 24308MB
[2025-01-18 20:01:18 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][150/312]	eta 0:01:39 lr 0.002483	time 0.5876 (0.6156)	model_time 0.5874 (0.6042)	loss 2.6401 (3.4259)	grad_norm 1.4805 (1.6834/0.5947)	mem 24308MB
[2025-01-18 20:01:24 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][160/312]	eta 0:01:33 lr 0.002482	time 0.5809 (0.6141)	model_time 0.5804 (0.6034)	loss 2.8124 (3.4120)	grad_norm 1.1926 (1.6518/0.5926)	mem 24308MB
[2025-01-18 20:01:30 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][170/312]	eta 0:01:26 lr 0.002481	time 0.5951 (0.6125)	model_time 0.5946 (0.6023)	loss 3.8103 (3.4069)	grad_norm 3.3140 (1.6572/0.6065)	mem 24308MB
[2025-01-18 20:01:36 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][180/312]	eta 0:01:20 lr 0.002481	time 0.5843 (0.6119)	model_time 0.5838 (0.6023)	loss 2.3810 (3.4077)	grad_norm 1.6885 (1.6478/0.6016)	mem 24308MB
[2025-01-18 20:01:42 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][190/312]	eta 0:01:14 lr 0.002480	time 0.5756 (0.6116)	model_time 0.5754 (0.6025)	loss 3.7380 (3.4264)	grad_norm 1.3986 (1.6440/0.6052)	mem 24308MB
[2025-01-18 20:01:48 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][200/312]	eta 0:01:08 lr 0.002479	time 0.5874 (0.6105)	model_time 0.5873 (0.6017)	loss 2.2831 (3.4181)	grad_norm 1.3895 (1.6650/0.6173)	mem 24308MB
[2025-01-18 20:01:54 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][210/312]	eta 0:01:02 lr 0.002479	time 0.5903 (0.6097)	model_time 0.5901 (0.6014)	loss 3.3841 (3.4172)	grad_norm 2.1068 (1.6723/0.6129)	mem 24308MB
[2025-01-18 20:02:00 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][220/312]	eta 0:00:56 lr 0.002478	time 0.5885 (0.6096)	model_time 0.5884 (0.6016)	loss 2.5090 (3.4050)	grad_norm 1.4505 (1.6692/0.6090)	mem 24308MB
[2025-01-18 20:02:06 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][230/312]	eta 0:00:50 lr 0.002477	time 0.5698 (0.6102)	model_time 0.5694 (0.6025)	loss 3.6310 (3.4116)	grad_norm 1.0127 (1.6594/0.6122)	mem 24308MB
[2025-01-18 20:02:12 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][240/312]	eta 0:00:43 lr 0.002477	time 0.5739 (0.6102)	model_time 0.5738 (0.6029)	loss 3.6544 (3.4129)	grad_norm 1.6900 (1.6623/0.6210)	mem 24308MB
[2025-01-18 20:02:18 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][250/312]	eta 0:00:37 lr 0.002476	time 0.5833 (0.6106)	model_time 0.5829 (0.6036)	loss 3.4743 (3.4212)	grad_norm 1.4883 (1.6632/0.6126)	mem 24308MB
[2025-01-18 20:02:24 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][260/312]	eta 0:00:31 lr 0.002475	time 0.5694 (0.6100)	model_time 0.5693 (0.6032)	loss 3.3226 (3.4097)	grad_norm 2.4210 (1.6529/0.6115)	mem 24308MB
[2025-01-18 20:02:31 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][270/312]	eta 0:00:25 lr 0.002475	time 0.5759 (0.6105)	model_time 0.5757 (0.6039)	loss 2.7760 (3.4040)	grad_norm 2.2778 (1.6690/0.6264)	mem 24308MB
[2025-01-18 20:02:37 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][280/312]	eta 0:00:19 lr 0.002474	time 0.5911 (0.6098)	model_time 0.5906 (0.6035)	loss 3.4953 (3.3998)	grad_norm 1.5365 (1.6708/0.6214)	mem 24308MB
[2025-01-18 20:02:42 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][290/312]	eta 0:00:13 lr 0.002474	time 0.5826 (0.6091)	model_time 0.5822 (0.6029)	loss 3.6446 (3.4017)	grad_norm 0.8758 (1.6734/0.6173)	mem 24308MB
[2025-01-18 20:02:48 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][300/312]	eta 0:00:07 lr 0.002473	time 0.5745 (0.6083)	model_time 0.5744 (0.6024)	loss 3.5159 (3.4018)	grad_norm 0.9772 (1.6610/0.6143)	mem 24308MB
[2025-01-18 20:02:54 internimage_s_1k_224] (main.py 510): INFO Train: [127/300][310/312]	eta 0:00:01 lr 0.002472	time 0.6601 (0.6077)	model_time 0.6600 (0.6019)	loss 3.4408 (3.3959)	grad_norm 2.1637 (1.6465/0.6202)	mem 24308MB
[2025-01-18 20:02:55 internimage_s_1k_224] (main.py 519): INFO EPOCH 127 training takes 0:03:09
[2025-01-18 20:02:55 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_127.pth saving......
[2025-01-18 20:02:56 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_127.pth saved !!!
[2025-01-18 20:03:04 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.183 (7.183)	Loss 0.8485 (0.8485)	Acc@1 80.933 (80.933)	Acc@5 96.484 (96.484)	Mem 24308MB
[2025-01-18 20:03:07 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.941)	Loss 1.2033 (0.9994)	Acc@1 73.853 (78.429)	Acc@5 92.261 (94.551)	Mem 24308MB
[2025-01-18 20:03:07 internimage_s_1k_224] (main.py 575): INFO [Epoch:127] * Acc@1 78.337 Acc@5 94.548
[2025-01-18 20:03:07 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.3%
[2025-01-18 20:03:07 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.43%
[2025-01-18 20:03:15 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.116 (8.116)	Loss 0.7330 (0.7330)	Acc@1 82.300 (82.300)	Acc@5 96.851 (96.851)	Mem 24308MB
[2025-01-18 20:03:19 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.102)	Loss 1.0961 (0.8841)	Acc@1 72.974 (78.835)	Acc@5 92.456 (94.755)	Mem 24308MB
[2025-01-18 20:03:19 internimage_s_1k_224] (main.py 575): INFO [Epoch:127] * Acc@1 78.715 Acc@5 94.772
[2025-01-18 20:03:19 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.7%
[2025-01-18 20:03:19 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 20:03:22 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 20:03:22 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 78.71%
[2025-01-18 20:03:24 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][0/312]	eta 0:11:11 lr 0.002472	time 2.1527 (2.1527)	model_time 0.5964 (0.5964)	loss 3.7065 (3.7065)	grad_norm 1.4317 (1.4317/0.0000)	mem 24308MB
[2025-01-18 20:03:30 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][10/312]	eta 0:03:40 lr 0.002471	time 0.5815 (0.7289)	model_time 0.5813 (0.5871)	loss 4.1922 (3.7088)	grad_norm 1.6094 (1.5884/0.4368)	mem 24308MB
[2025-01-18 20:03:36 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][20/312]	eta 0:03:15 lr 0.002471	time 0.6104 (0.6700)	model_time 0.6102 (0.5955)	loss 2.6049 (3.5800)	grad_norm 1.1137 (2.0406/1.1838)	mem 24308MB
[2025-01-18 20:03:42 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][30/312]	eta 0:03:02 lr 0.002470	time 0.6651 (0.6479)	model_time 0.6649 (0.5974)	loss 3.1366 (3.4949)	grad_norm 1.4140 (1.9798/1.0447)	mem 24308MB
[2025-01-18 20:03:48 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][40/312]	eta 0:02:54 lr 0.002470	time 0.6059 (0.6411)	model_time 0.6058 (0.6028)	loss 4.0633 (3.4416)	grad_norm 1.8366 (1.8564/0.9578)	mem 24308MB
[2025-01-18 20:03:54 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][50/312]	eta 0:02:46 lr 0.002469	time 0.7199 (0.6374)	model_time 0.7197 (0.6065)	loss 3.5573 (3.4977)	grad_norm 2.6478 (2.0564/1.2462)	mem 24308MB
[2025-01-18 20:04:00 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][60/312]	eta 0:02:39 lr 0.002468	time 0.5703 (0.6329)	model_time 0.5702 (0.6071)	loss 3.6802 (3.5096)	grad_norm 1.4257 (1.9519/1.1725)	mem 24308MB
[2025-01-18 20:04:06 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][70/312]	eta 0:02:31 lr 0.002468	time 0.5822 (0.6273)	model_time 0.5821 (0.6051)	loss 4.2388 (3.4926)	grad_norm 1.2525 (1.8444/1.1224)	mem 24308MB
[2025-01-18 20:04:12 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][80/312]	eta 0:02:25 lr 0.002467	time 0.5918 (0.6270)	model_time 0.5917 (0.6075)	loss 3.2534 (3.4657)	grad_norm 1.6861 (1.7735/1.0752)	mem 24308MB
[2025-01-18 20:04:18 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][90/312]	eta 0:02:18 lr 0.002466	time 0.5728 (0.6232)	model_time 0.5726 (0.6058)	loss 2.8088 (3.4233)	grad_norm 1.7702 (1.7730/1.0214)	mem 24308MB
[2025-01-18 20:04:24 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][100/312]	eta 0:02:11 lr 0.002466	time 0.5947 (0.6199)	model_time 0.5945 (0.6042)	loss 4.2835 (3.4140)	grad_norm 2.3977 (1.7882/0.9904)	mem 24308MB
[2025-01-18 20:04:30 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][110/312]	eta 0:02:04 lr 0.002465	time 0.5797 (0.6175)	model_time 0.5795 (0.6031)	loss 3.9144 (3.4002)	grad_norm 0.9924 (1.8053/0.9829)	mem 24308MB
[2025-01-18 20:04:36 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][120/312]	eta 0:01:58 lr 0.002464	time 0.5838 (0.6166)	model_time 0.5834 (0.6034)	loss 3.3668 (3.4021)	grad_norm 1.9277 (1.8186/0.9771)	mem 24308MB
[2025-01-18 20:04:42 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][130/312]	eta 0:01:51 lr 0.002464	time 0.5858 (0.6144)	model_time 0.5857 (0.6022)	loss 3.6655 (3.4116)	grad_norm 1.1010 (1.7958/0.9560)	mem 24308MB
[2025-01-18 20:04:48 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][140/312]	eta 0:01:45 lr 0.002463	time 0.6671 (0.6138)	model_time 0.6669 (0.6024)	loss 2.5280 (3.4195)	grad_norm 1.0400 (1.7720/0.9318)	mem 24308MB
[2025-01-18 20:04:54 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][150/312]	eta 0:01:39 lr 0.002462	time 0.6831 (0.6135)	model_time 0.6826 (0.6028)	loss 2.3138 (3.4103)	grad_norm 1.0759 (1.7459/0.9145)	mem 24308MB
[2025-01-18 20:05:00 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][160/312]	eta 0:01:33 lr 0.002462	time 0.5931 (0.6139)	model_time 0.5929 (0.6039)	loss 3.8179 (3.4281)	grad_norm 2.2275 (1.7555/0.9072)	mem 24308MB
[2025-01-18 20:05:07 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][170/312]	eta 0:01:27 lr 0.002461	time 0.6727 (0.6134)	model_time 0.6726 (0.6039)	loss 3.8251 (3.4164)	grad_norm 1.0761 (1.7433/0.8872)	mem 24308MB
[2025-01-18 20:05:13 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][180/312]	eta 0:01:21 lr 0.002460	time 0.5860 (0.6144)	model_time 0.5858 (0.6055)	loss 3.7556 (3.4180)	grad_norm 2.6001 (1.7242/0.8743)	mem 24308MB
[2025-01-18 20:05:19 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][190/312]	eta 0:01:14 lr 0.002460	time 0.5976 (0.6135)	model_time 0.5974 (0.6050)	loss 2.9873 (3.4039)	grad_norm 1.0481 (1.7168/0.8599)	mem 24308MB
[2025-01-18 20:05:25 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][200/312]	eta 0:01:08 lr 0.002459	time 0.5951 (0.6134)	model_time 0.5946 (0.6053)	loss 4.2874 (3.4021)	grad_norm 2.0427 (1.7145/0.8418)	mem 24308MB
[2025-01-18 20:05:31 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][210/312]	eta 0:01:02 lr 0.002459	time 0.5939 (0.6124)	model_time 0.5937 (0.6047)	loss 3.9759 (3.4112)	grad_norm 2.2469 (1.7036/0.8290)	mem 24308MB
[2025-01-18 20:05:37 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][220/312]	eta 0:00:56 lr 0.002458	time 0.5777 (0.6114)	model_time 0.5774 (0.6040)	loss 3.2169 (3.4111)	grad_norm 0.9223 (1.7124/0.8320)	mem 24308MB
[2025-01-18 20:05:43 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][230/312]	eta 0:00:50 lr 0.002457	time 0.6040 (0.6108)	model_time 0.6036 (0.6037)	loss 4.1297 (3.4078)	grad_norm 1.5938 (1.7105/0.8205)	mem 24308MB
[2025-01-18 20:05:49 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][240/312]	eta 0:00:43 lr 0.002457	time 0.5848 (0.6103)	model_time 0.5843 (0.6035)	loss 2.7199 (3.4086)	grad_norm 0.6111 (1.6963/0.8091)	mem 24308MB
[2025-01-18 20:05:55 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][250/312]	eta 0:00:37 lr 0.002456	time 0.5703 (0.6092)	model_time 0.5699 (0.6027)	loss 3.1783 (3.4044)	grad_norm 0.8570 (1.6788/0.7989)	mem 24308MB
[2025-01-18 20:06:01 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][260/312]	eta 0:00:31 lr 0.002455	time 0.6757 (0.6091)	model_time 0.6755 (0.6027)	loss 4.2450 (3.4025)	grad_norm 1.6955 (1.6881/0.7950)	mem 24308MB
[2025-01-18 20:06:07 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][270/312]	eta 0:00:25 lr 0.002455	time 0.6416 (0.6090)	model_time 0.6414 (0.6029)	loss 3.0538 (3.4073)	grad_norm 1.5920 (1.6915/0.7843)	mem 24308MB
[2025-01-18 20:06:13 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][280/312]	eta 0:00:19 lr 0.002454	time 0.6620 (0.6097)	model_time 0.6617 (0.6039)	loss 3.6501 (3.4036)	grad_norm 2.6102 (1.6915/0.7808)	mem 24308MB
[2025-01-18 20:06:19 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][290/312]	eta 0:00:13 lr 0.002453	time 0.6634 (0.6095)	model_time 0.6632 (0.6038)	loss 3.9122 (3.4010)	grad_norm 1.4044 (1.6941/0.7751)	mem 24308MB
[2025-01-18 20:06:25 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][300/312]	eta 0:00:07 lr 0.002453	time 0.6517 (0.6108)	model_time 0.6516 (0.6052)	loss 2.4982 (3.3964)	grad_norm 1.0171 (1.6987/0.7819)	mem 24308MB
[2025-01-18 20:06:31 internimage_s_1k_224] (main.py 510): INFO Train: [128/300][310/312]	eta 0:00:01 lr 0.002452	time 0.5667 (0.6101)	model_time 0.5666 (0.6047)	loss 3.7813 (3.3927)	grad_norm 1.6618 (1.6926/0.7838)	mem 24308MB
[2025-01-18 20:06:32 internimage_s_1k_224] (main.py 519): INFO EPOCH 128 training takes 0:03:10
[2025-01-18 20:06:32 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_128.pth saving......
[2025-01-18 20:06:34 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_128.pth saved !!!
[2025-01-18 20:06:41 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.156 (7.156)	Loss 0.8605 (0.8605)	Acc@1 81.543 (81.543)	Acc@5 96.533 (96.533)	Mem 24308MB
[2025-01-18 20:06:44 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.933)	Loss 1.1430 (0.9945)	Acc@1 74.316 (78.329)	Acc@5 92.822 (94.596)	Mem 24308MB
[2025-01-18 20:06:44 internimage_s_1k_224] (main.py 575): INFO [Epoch:128] * Acc@1 78.241 Acc@5 94.604
[2025-01-18 20:06:44 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.2%
[2025-01-18 20:06:44 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.43%
[2025-01-18 20:06:53 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.696 (8.696)	Loss 0.7317 (0.7317)	Acc@1 82.324 (82.324)	Acc@5 96.851 (96.851)	Mem 24308MB
[2025-01-18 20:06:57 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.135 (1.159)	Loss 1.0926 (0.8820)	Acc@1 73.193 (78.922)	Acc@5 92.505 (94.784)	Mem 24308MB
[2025-01-18 20:06:57 internimage_s_1k_224] (main.py 575): INFO [Epoch:128] * Acc@1 78.799 Acc@5 94.806
[2025-01-18 20:06:57 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.8%
[2025-01-18 20:06:57 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 20:06:59 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 20:06:59 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 78.80%
[2025-01-18 20:07:01 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][0/312]	eta 0:10:37 lr 0.002452	time 2.0420 (2.0420)	model_time 0.6107 (0.6107)	loss 3.7834 (3.7834)	grad_norm 1.4846 (1.4846/0.0000)	mem 24308MB
[2025-01-18 20:07:08 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][10/312]	eta 0:03:43 lr 0.002451	time 0.5998 (0.7403)	model_time 0.5996 (0.6099)	loss 3.2087 (3.4122)	grad_norm 1.2641 (1.5988/0.4970)	mem 24308MB
[2025-01-18 20:07:13 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][20/312]	eta 0:03:15 lr 0.002451	time 0.5789 (0.6698)	model_time 0.5784 (0.6012)	loss 3.9878 (3.5479)	grad_norm 1.4911 (1.7002/0.5518)	mem 24308MB
[2025-01-18 20:07:19 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][30/312]	eta 0:03:01 lr 0.002450	time 0.5974 (0.6422)	model_time 0.5972 (0.5957)	loss 4.0480 (3.5416)	grad_norm 1.4821 (1.7045/0.5361)	mem 24308MB
[2025-01-18 20:07:25 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][40/312]	eta 0:02:51 lr 0.002449	time 0.5657 (0.6309)	model_time 0.5655 (0.5956)	loss 3.9000 (3.5797)	grad_norm 1.8543 (1.6219/0.5133)	mem 24308MB
[2025-01-18 20:07:31 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][50/312]	eta 0:02:44 lr 0.002449	time 0.5912 (0.6281)	model_time 0.5911 (0.5997)	loss 3.5709 (3.5729)	grad_norm 1.6843 (1.5408/0.5007)	mem 24308MB
[2025-01-18 20:07:37 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][60/312]	eta 0:02:36 lr 0.002448	time 0.5804 (0.6214)	model_time 0.5800 (0.5976)	loss 4.0507 (3.5892)	grad_norm 1.4827 (1.6691/0.7542)	mem 24308MB
[2025-01-18 20:07:43 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][70/312]	eta 0:02:29 lr 0.002447	time 0.5674 (0.6176)	model_time 0.5673 (0.5971)	loss 3.1408 (3.5703)	grad_norm 0.7592 (1.7121/0.7751)	mem 24308MB
[2025-01-18 20:07:49 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][80/312]	eta 0:02:23 lr 0.002447	time 0.5761 (0.6175)	model_time 0.5759 (0.5994)	loss 3.5750 (3.5355)	grad_norm 1.0627 (1.6706/0.7414)	mem 24308MB
[2025-01-18 20:07:56 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][90/312]	eta 0:02:17 lr 0.002446	time 0.5778 (0.6187)	model_time 0.5774 (0.6026)	loss 3.3128 (3.5031)	grad_norm 0.7901 (1.6859/0.7568)	mem 24308MB
[2025-01-18 20:08:02 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][100/312]	eta 0:02:10 lr 0.002445	time 0.5755 (0.6177)	model_time 0.5753 (0.6031)	loss 2.4959 (3.4756)	grad_norm 1.2395 (1.6717/0.7502)	mem 24308MB
[2025-01-18 20:08:08 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][110/312]	eta 0:02:05 lr 0.002445	time 0.6466 (0.6188)	model_time 0.6462 (0.6056)	loss 3.3192 (3.4597)	grad_norm 0.9830 (1.6561/0.7295)	mem 24308MB
[2025-01-18 20:08:14 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][120/312]	eta 0:01:58 lr 0.002444	time 0.5706 (0.6186)	model_time 0.5705 (0.6064)	loss 3.4318 (3.4512)	grad_norm 0.8870 (1.6440/0.7371)	mem 24308MB
[2025-01-18 20:08:20 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][130/312]	eta 0:01:52 lr 0.002443	time 0.5712 (0.6181)	model_time 0.5708 (0.6068)	loss 2.9356 (3.4490)	grad_norm 2.1217 (1.6168/0.7229)	mem 24308MB
[2025-01-18 20:08:26 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][140/312]	eta 0:01:46 lr 0.002443	time 0.5750 (0.6163)	model_time 0.5748 (0.6058)	loss 3.2981 (3.4611)	grad_norm 1.4225 (1.6803/0.7641)	mem 24308MB
[2025-01-18 20:08:32 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][150/312]	eta 0:01:39 lr 0.002442	time 0.6102 (0.6146)	model_time 0.6100 (0.6047)	loss 2.9703 (3.4547)	grad_norm 2.8992 (1.6982/0.7523)	mem 24308MB
[2025-01-18 20:08:38 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][160/312]	eta 0:01:33 lr 0.002442	time 0.6021 (0.6138)	model_time 0.6019 (0.6046)	loss 3.4187 (3.4300)	grad_norm 1.1695 (1.6919/0.7374)	mem 24308MB
[2025-01-18 20:08:44 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][170/312]	eta 0:01:27 lr 0.002441	time 0.5811 (0.6132)	model_time 0.5809 (0.6044)	loss 4.1361 (3.4272)	grad_norm 1.0804 (1.7016/0.7295)	mem 24308MB
[2025-01-18 20:08:50 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][180/312]	eta 0:01:20 lr 0.002440	time 0.5845 (0.6121)	model_time 0.5843 (0.6039)	loss 3.1570 (3.4267)	grad_norm 2.1751 (1.6881/0.7281)	mem 24308MB
[2025-01-18 20:08:56 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][190/312]	eta 0:01:14 lr 0.002440	time 0.5627 (0.6108)	model_time 0.5625 (0.6029)	loss 2.6657 (3.4217)	grad_norm 1.5279 (1.6557/0.7242)	mem 24308MB
[2025-01-18 20:09:02 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][200/312]	eta 0:01:08 lr 0.002439	time 0.6066 (0.6116)	model_time 0.6060 (0.6041)	loss 3.8020 (3.4290)	grad_norm 2.1533 (1.6454/0.7140)	mem 24308MB
[2025-01-18 20:09:09 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][210/312]	eta 0:01:02 lr 0.002438	time 0.5769 (0.6129)	model_time 0.5767 (0.6057)	loss 3.3318 (3.4341)	grad_norm 1.2922 (1.6500/0.7281)	mem 24308MB
[2025-01-18 20:09:15 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][220/312]	eta 0:00:56 lr 0.002438	time 0.5751 (0.6119)	model_time 0.5747 (0.6051)	loss 2.6823 (3.4455)	grad_norm 1.0230 (1.6555/0.7331)	mem 24308MB
[2025-01-18 20:09:21 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][230/312]	eta 0:00:50 lr 0.002437	time 0.6690 (0.6134)	model_time 0.6688 (0.6069)	loss 4.3639 (3.4464)	grad_norm 1.3972 (1.6642/0.7369)	mem 24308MB
[2025-01-18 20:09:27 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][240/312]	eta 0:00:44 lr 0.002436	time 0.5823 (0.6133)	model_time 0.5819 (0.6070)	loss 3.3940 (3.4543)	grad_norm 1.0147 (1.6622/0.7368)	mem 24308MB
[2025-01-18 20:09:33 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][250/312]	eta 0:00:38 lr 0.002436	time 0.5923 (0.6131)	model_time 0.5921 (0.6070)	loss 3.0029 (3.4530)	grad_norm 0.9124 (1.6413/0.7312)	mem 24308MB
[2025-01-18 20:09:39 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][260/312]	eta 0:00:31 lr 0.002435	time 0.5747 (0.6121)	model_time 0.5746 (0.6063)	loss 3.5830 (3.4523)	grad_norm 1.7738 (1.6427/0.7306)	mem 24308MB
[2025-01-18 20:09:45 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][270/312]	eta 0:00:25 lr 0.002434	time 0.5708 (0.6112)	model_time 0.5706 (0.6056)	loss 3.7493 (3.4530)	grad_norm 1.6654 (1.6756/0.7977)	mem 24308MB
[2025-01-18 20:09:51 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][280/312]	eta 0:00:19 lr 0.002434	time 0.5770 (0.6108)	model_time 0.5767 (0.6054)	loss 3.6913 (3.4587)	grad_norm 0.8569 (1.6835/0.7940)	mem 24308MB
[2025-01-18 20:09:57 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][290/312]	eta 0:00:13 lr 0.002433	time 0.5872 (0.6107)	model_time 0.5871 (0.6054)	loss 3.3205 (3.4502)	grad_norm 1.9930 (1.6872/0.7956)	mem 24308MB
[2025-01-18 20:10:03 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][300/312]	eta 0:00:07 lr 0.002432	time 0.5678 (0.6100)	model_time 0.5677 (0.6049)	loss 2.8195 (3.4408)	grad_norm 1.2488 (1.6784/0.7875)	mem 24308MB
[2025-01-18 20:10:09 internimage_s_1k_224] (main.py 510): INFO Train: [129/300][310/312]	eta 0:00:01 lr 0.002432	time 0.5678 (0.6089)	model_time 0.5677 (0.6039)	loss 3.1579 (3.4339)	grad_norm 1.0156 (1.6701/0.7924)	mem 24308MB
[2025-01-18 20:10:09 internimage_s_1k_224] (main.py 519): INFO EPOCH 129 training takes 0:03:09
[2025-01-18 20:10:09 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_129.pth saving......
[2025-01-18 20:10:11 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_129.pth saved !!!
[2025-01-18 20:10:18 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.866 (6.866)	Loss 0.8700 (0.8700)	Acc@1 81.519 (81.519)	Acc@5 96.265 (96.265)	Mem 24308MB
[2025-01-18 20:10:21 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.134 (0.905)	Loss 1.1851 (1.0113)	Acc@1 73.413 (78.389)	Acc@5 92.700 (94.502)	Mem 24308MB
[2025-01-18 20:10:21 internimage_s_1k_224] (main.py 575): INFO [Epoch:129] * Acc@1 78.321 Acc@5 94.528
[2025-01-18 20:10:21 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.3%
[2025-01-18 20:10:21 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.43%
[2025-01-18 20:10:30 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.117 (8.117)	Loss 0.7305 (0.7305)	Acc@1 82.422 (82.422)	Acc@5 96.875 (96.875)	Mem 24308MB
[2025-01-18 20:10:34 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.097)	Loss 1.0891 (0.8800)	Acc@1 73.145 (78.966)	Acc@5 92.651 (94.813)	Mem 24308MB
[2025-01-18 20:10:34 internimage_s_1k_224] (main.py 575): INFO [Epoch:129] * Acc@1 78.847 Acc@5 94.834
[2025-01-18 20:10:34 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.8%
[2025-01-18 20:10:34 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 20:10:36 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 20:10:36 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 78.85%
[2025-01-18 20:10:38 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][0/312]	eta 0:12:30 lr 0.002432	time 2.4053 (2.4053)	model_time 0.6111 (0.6111)	loss 3.3450 (3.3450)	grad_norm 0.9446 (0.9446/0.0000)	mem 24308MB
[2025-01-18 20:10:44 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][10/312]	eta 0:03:55 lr 0.002431	time 0.5682 (0.7784)	model_time 0.5680 (0.6148)	loss 4.1002 (3.6035)	grad_norm 3.5223 (2.2195/1.1818)	mem 24308MB
[2025-01-18 20:10:50 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][20/312]	eta 0:03:24 lr 0.002430	time 0.6578 (0.7011)	model_time 0.6572 (0.6152)	loss 3.6788 (3.5702)	grad_norm 1.1215 (2.1148/0.9613)	mem 24308MB
[2025-01-18 20:10:56 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][30/312]	eta 0:03:09 lr 0.002430	time 0.6583 (0.6722)	model_time 0.6581 (0.6139)	loss 3.4571 (3.4615)	grad_norm 1.7654 (1.8787/0.8847)	mem 24308MB
[2025-01-18 20:11:03 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][40/312]	eta 0:03:00 lr 0.002429	time 0.6494 (0.6652)	model_time 0.6492 (0.6210)	loss 3.5739 (3.4383)	grad_norm 2.3497 (1.7808/0.8233)	mem 24308MB
[2025-01-18 20:11:09 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][50/312]	eta 0:02:50 lr 0.002428	time 0.5685 (0.6508)	model_time 0.5683 (0.6153)	loss 3.5247 (3.4043)	grad_norm 2.5907 (1.7640/0.7666)	mem 24308MB
[2025-01-18 20:11:15 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][60/312]	eta 0:02:42 lr 0.002428	time 0.5654 (0.6460)	model_time 0.5653 (0.6162)	loss 3.3042 (3.3980)	grad_norm 0.9329 (1.7994/0.8184)	mem 24308MB
[2025-01-18 20:11:21 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][70/312]	eta 0:02:34 lr 0.002427	time 0.6175 (0.6398)	model_time 0.6173 (0.6141)	loss 2.8769 (3.3677)	grad_norm 0.6252 (1.8164/0.8513)	mem 24308MB
[2025-01-18 20:11:27 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][80/312]	eta 0:02:26 lr 0.002426	time 0.5861 (0.6334)	model_time 0.5859 (0.6109)	loss 3.2549 (3.3649)	grad_norm 1.7696 (1.8235/0.8295)	mem 24308MB
[2025-01-18 20:11:33 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][90/312]	eta 0:02:20 lr 0.002426	time 0.5836 (0.6314)	model_time 0.5834 (0.6113)	loss 3.9117 (3.3688)	grad_norm 1.6909 (1.8016/0.8022)	mem 24308MB
[2025-01-18 20:11:39 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][100/312]	eta 0:02:13 lr 0.002425	time 0.6950 (0.6296)	model_time 0.6949 (0.6114)	loss 3.6349 (3.3712)	grad_norm 1.9713 (1.7652/0.7755)	mem 24308MB
[2025-01-18 20:11:45 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][110/312]	eta 0:02:06 lr 0.002425	time 0.6022 (0.6265)	model_time 0.6018 (0.6100)	loss 3.6216 (3.3872)	grad_norm 1.3953 (1.7361/0.7553)	mem 24308MB
[2025-01-18 20:11:51 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][120/312]	eta 0:01:59 lr 0.002424	time 0.6073 (0.6235)	model_time 0.6071 (0.6083)	loss 3.2262 (3.3775)	grad_norm 1.4573 (1.6961/0.7444)	mem 24308MB
[2025-01-18 20:11:57 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][130/312]	eta 0:01:53 lr 0.002423	time 0.5743 (0.6224)	model_time 0.5740 (0.6083)	loss 4.0405 (3.3553)	grad_norm 1.9991 (1.6970/0.7222)	mem 24308MB
[2025-01-18 20:12:03 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][140/312]	eta 0:01:47 lr 0.002423	time 0.5916 (0.6231)	model_time 0.5914 (0.6101)	loss 2.3864 (3.3452)	grad_norm 1.4738 (1.7099/0.7023)	mem 24308MB
[2025-01-18 20:12:09 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][150/312]	eta 0:01:40 lr 0.002422	time 0.5795 (0.6222)	model_time 0.5793 (0.6100)	loss 3.5152 (3.3518)	grad_norm 0.9400 (1.7209/0.7048)	mem 24308MB
[2025-01-18 20:12:16 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][160/312]	eta 0:01:34 lr 0.002421	time 0.6109 (0.6228)	model_time 0.6108 (0.6113)	loss 3.1392 (3.3633)	grad_norm 0.9566 (1.7370/0.7293)	mem 24308MB
[2025-01-18 20:12:22 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][170/312]	eta 0:01:28 lr 0.002421	time 0.5819 (0.6210)	model_time 0.5818 (0.6102)	loss 3.0146 (3.3748)	grad_norm 1.1243 (1.7170/0.7268)	mem 24308MB
[2025-01-18 20:12:28 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][180/312]	eta 0:01:21 lr 0.002420	time 0.6218 (0.6210)	model_time 0.6216 (0.6107)	loss 2.3009 (3.3681)	grad_norm 1.4534 (1.6901/0.7200)	mem 24308MB
[2025-01-18 20:12:34 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][190/312]	eta 0:01:15 lr 0.002419	time 0.5714 (0.6195)	model_time 0.5712 (0.6098)	loss 3.9602 (3.3738)	grad_norm 3.3789 (1.6955/0.7185)	mem 24308MB
[2025-01-18 20:12:40 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][200/312]	eta 0:01:09 lr 0.002419	time 0.6081 (0.6182)	model_time 0.6079 (0.6089)	loss 3.3035 (3.3715)	grad_norm 1.6744 (1.7049/0.7449)	mem 24308MB
[2025-01-18 20:12:46 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][210/312]	eta 0:01:02 lr 0.002418	time 0.5851 (0.6175)	model_time 0.5846 (0.6086)	loss 3.1031 (3.3672)	grad_norm 0.7051 (1.6860/0.7454)	mem 24308MB
[2025-01-18 20:12:52 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][220/312]	eta 0:00:56 lr 0.002417	time 0.6938 (0.6176)	model_time 0.6936 (0.6091)	loss 2.6733 (3.3684)	grad_norm 2.5971 (1.6753/0.7407)	mem 24308MB
[2025-01-18 20:12:58 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][230/312]	eta 0:00:50 lr 0.002417	time 0.5708 (0.6165)	model_time 0.5703 (0.6084)	loss 3.2621 (3.3619)	grad_norm 1.8028 (1.6638/0.7361)	mem 24308MB
[2025-01-18 20:13:04 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][240/312]	eta 0:00:44 lr 0.002416	time 0.5941 (0.6155)	model_time 0.5939 (0.6077)	loss 3.3064 (3.3579)	grad_norm 1.9297 (1.6757/0.7578)	mem 24308MB
[2025-01-18 20:13:10 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][250/312]	eta 0:00:38 lr 0.002415	time 0.5764 (0.6151)	model_time 0.5760 (0.6076)	loss 3.9061 (3.3588)	grad_norm 2.1439 (1.6962/0.7713)	mem 24308MB
[2025-01-18 20:13:16 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][260/312]	eta 0:00:32 lr 0.002415	time 0.5986 (0.6160)	model_time 0.5984 (0.6088)	loss 3.5290 (3.3606)	grad_norm 2.3451 (1.6998/0.7616)	mem 24308MB
[2025-01-18 20:13:23 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][270/312]	eta 0:00:25 lr 0.002414	time 0.6024 (0.6161)	model_time 0.6023 (0.6092)	loss 3.7680 (3.3514)	grad_norm 1.7008 (1.7043/0.7581)	mem 24308MB
[2025-01-18 20:13:29 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][280/312]	eta 0:00:19 lr 0.002413	time 0.5839 (0.6161)	model_time 0.5837 (0.6094)	loss 3.1996 (3.3443)	grad_norm 3.5227 (1.7240/0.7752)	mem 24308MB
[2025-01-18 20:13:35 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][290/312]	eta 0:00:13 lr 0.002413	time 0.6032 (0.6158)	model_time 0.6027 (0.6093)	loss 3.2308 (3.3411)	grad_norm 1.3461 (1.7288/0.7705)	mem 24308MB
[2025-01-18 20:13:41 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][300/312]	eta 0:00:07 lr 0.002412	time 0.5760 (0.6150)	model_time 0.5759 (0.6087)	loss 3.4005 (3.3492)	grad_norm 1.7104 (1.7180/0.7642)	mem 24308MB
[2025-01-18 20:13:47 internimage_s_1k_224] (main.py 510): INFO Train: [130/300][310/312]	eta 0:00:01 lr 0.002411	time 0.6655 (0.6142)	model_time 0.6654 (0.6081)	loss 3.7691 (3.3562)	grad_norm 1.6203 (1.6925/0.7294)	mem 24308MB
[2025-01-18 20:13:47 internimage_s_1k_224] (main.py 519): INFO EPOCH 130 training takes 0:03:11
[2025-01-18 20:13:47 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_130.pth saving......
[2025-01-18 20:13:49 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_130.pth saved !!!
[2025-01-18 20:13:56 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.925 (6.925)	Loss 0.8973 (0.8973)	Acc@1 81.494 (81.494)	Acc@5 96.313 (96.313)	Mem 24308MB
[2025-01-18 20:13:59 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.895)	Loss 1.2108 (1.0391)	Acc@1 73.462 (78.345)	Acc@5 92.554 (94.525)	Mem 24308MB
[2025-01-18 20:13:59 internimage_s_1k_224] (main.py 575): INFO [Epoch:130] * Acc@1 78.239 Acc@5 94.544
[2025-01-18 20:13:59 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.2%
[2025-01-18 20:13:59 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.43%
[2025-01-18 20:14:07 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.238 (8.238)	Loss 0.7289 (0.7289)	Acc@1 82.495 (82.495)	Acc@5 96.948 (96.948)	Mem 24308MB
[2025-01-18 20:14:12 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.136 (1.123)	Loss 1.0856 (0.8778)	Acc@1 73.096 (79.031)	Acc@5 92.725 (94.842)	Mem 24308MB
[2025-01-18 20:14:12 internimage_s_1k_224] (main.py 575): INFO [Epoch:130] * Acc@1 78.905 Acc@5 94.864
[2025-01-18 20:14:12 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 78.9%
[2025-01-18 20:14:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 20:14:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 20:14:14 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 78.90%
[2025-01-18 20:14:16 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][0/312]	eta 0:12:35 lr 0.002411	time 2.4199 (2.4199)	model_time 0.5918 (0.5918)	loss 2.6308 (2.6308)	grad_norm 1.4440 (1.4440/0.0000)	mem 24308MB
[2025-01-18 20:14:22 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][10/312]	eta 0:03:49 lr 0.002411	time 0.5882 (0.7584)	model_time 0.5880 (0.5919)	loss 3.7714 (3.2876)	grad_norm 2.1520 (1.5262/0.4962)	mem 24308MB
[2025-01-18 20:14:28 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][20/312]	eta 0:03:19 lr 0.002410	time 0.5851 (0.6841)	model_time 0.5847 (0.5967)	loss 3.4660 (3.1656)	grad_norm 1.1570 (1.6115/0.6198)	mem 24308MB
[2025-01-18 20:14:34 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][30/312]	eta 0:03:06 lr 0.002409	time 0.5986 (0.6604)	model_time 0.5984 (0.6012)	loss 4.4898 (3.3226)	grad_norm 1.5896 (1.5536/0.5637)	mem 24308MB
[2025-01-18 20:14:40 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][40/312]	eta 0:02:55 lr 0.002409	time 0.5786 (0.6436)	model_time 0.5784 (0.5987)	loss 3.8686 (3.2787)	grad_norm 0.8323 (1.5042/0.5840)	mem 24308MB
[2025-01-18 20:14:46 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][50/312]	eta 0:02:45 lr 0.002408	time 0.5840 (0.6334)	model_time 0.5838 (0.5973)	loss 3.3575 (3.3000)	grad_norm 2.3358 (1.5246/0.5875)	mem 24308MB
[2025-01-18 20:14:52 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][60/312]	eta 0:02:38 lr 0.002407	time 0.6956 (0.6298)	model_time 0.6955 (0.5995)	loss 3.8065 (3.3029)	grad_norm 3.1569 (1.5854/0.6270)	mem 24308MB
[2025-01-18 20:14:58 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][70/312]	eta 0:02:32 lr 0.002407	time 0.6128 (0.6290)	model_time 0.6123 (0.6030)	loss 2.9210 (3.2787)	grad_norm 1.4382 (1.5469/0.6012)	mem 24308MB
[2025-01-18 20:15:04 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][80/312]	eta 0:02:25 lr 0.002406	time 0.6715 (0.6271)	model_time 0.6713 (0.6043)	loss 3.5370 (3.2671)	grad_norm 1.1447 (1.5254/0.5767)	mem 24308MB
[2025-01-18 20:15:11 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][90/312]	eta 0:02:19 lr 0.002405	time 0.6709 (0.6275)	model_time 0.6704 (0.6072)	loss 4.1171 (3.2787)	grad_norm 2.9214 (1.5536/0.5904)	mem 24308MB
[2025-01-18 20:15:17 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][100/312]	eta 0:02:12 lr 0.002405	time 0.5989 (0.6247)	model_time 0.5987 (0.6063)	loss 3.6305 (3.2908)	grad_norm 1.3871 (1.5539/0.5736)	mem 24308MB
[2025-01-18 20:15:23 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][110/312]	eta 0:02:05 lr 0.002404	time 0.5882 (0.6231)	model_time 0.5880 (0.6063)	loss 3.9913 (3.3107)	grad_norm 1.0665 (1.5347/0.5649)	mem 24308MB
[2025-01-18 20:15:29 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][120/312]	eta 0:01:59 lr 0.002404	time 0.5927 (0.6224)	model_time 0.5925 (0.6069)	loss 4.0549 (3.3254)	grad_norm 1.3097 (1.5502/0.5847)	mem 24308MB
[2025-01-18 20:15:35 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][130/312]	eta 0:01:52 lr 0.002403	time 0.5813 (0.6194)	model_time 0.5811 (0.6052)	loss 3.7296 (3.3277)	grad_norm 2.6115 (1.5898/0.6087)	mem 24308MB
[2025-01-18 20:15:41 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][140/312]	eta 0:01:46 lr 0.002402	time 0.5898 (0.6179)	model_time 0.5894 (0.6046)	loss 3.4624 (3.3341)	grad_norm 1.7833 (1.6278/0.6367)	mem 24308MB
[2025-01-18 20:15:47 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][150/312]	eta 0:01:39 lr 0.002402	time 0.5939 (0.6172)	model_time 0.5937 (0.6047)	loss 3.7291 (3.3471)	grad_norm 0.8080 (1.6257/0.6235)	mem 24308MB
[2025-01-18 20:15:53 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][160/312]	eta 0:01:33 lr 0.002401	time 0.5712 (0.6161)	model_time 0.5711 (0.6044)	loss 3.3980 (3.3633)	grad_norm 1.4578 (1.6135/0.6124)	mem 24308MB
[2025-01-18 20:15:59 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][170/312]	eta 0:01:27 lr 0.002400	time 0.6029 (0.6144)	model_time 0.6028 (0.6034)	loss 3.8380 (3.3626)	grad_norm 2.1891 (1.6317/0.6196)	mem 24308MB
[2025-01-18 20:16:05 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][180/312]	eta 0:01:21 lr 0.002400	time 0.6905 (0.6139)	model_time 0.6904 (0.6035)	loss 2.8774 (3.3655)	grad_norm 0.8776 (1.6412/0.6207)	mem 24308MB
[2025-01-18 20:16:11 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][190/312]	eta 0:01:15 lr 0.002399	time 0.7022 (0.6151)	model_time 0.7017 (0.6052)	loss 3.2820 (3.3653)	grad_norm 1.9460 (1.6321/0.6159)	mem 24308MB
[2025-01-18 20:16:17 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][200/312]	eta 0:01:08 lr 0.002398	time 0.6687 (0.6148)	model_time 0.6685 (0.6054)	loss 3.2580 (3.3766)	grad_norm 2.3035 (1.6298/0.6155)	mem 24308MB
[2025-01-18 20:16:24 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][210/312]	eta 0:01:02 lr 0.002398	time 0.6849 (0.6155)	model_time 0.6845 (0.6065)	loss 2.5768 (3.3813)	grad_norm 1.2385 (1.6373/0.6085)	mem 24308MB
[2025-01-18 20:16:30 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][220/312]	eta 0:00:56 lr 0.002397	time 0.5728 (0.6150)	model_time 0.5727 (0.6064)	loss 3.8250 (3.3915)	grad_norm 2.0575 (1.6301/0.6043)	mem 24308MB
[2025-01-18 20:16:36 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][230/312]	eta 0:00:50 lr 0.002396	time 0.5778 (0.6145)	model_time 0.5776 (0.6062)	loss 2.9054 (3.4007)	grad_norm 1.8694 (1.6519/0.6705)	mem 24308MB
[2025-01-18 20:16:42 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][240/312]	eta 0:00:44 lr 0.002396	time 0.5905 (0.6141)	model_time 0.5903 (0.6061)	loss 3.9076 (3.4054)	grad_norm 1.7817 (1.6732/0.6886)	mem 24308MB
[2025-01-18 20:16:48 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][250/312]	eta 0:00:38 lr 0.002395	time 0.5875 (0.6131)	model_time 0.5873 (0.6055)	loss 2.4371 (3.4117)	grad_norm 2.3307 (1.6739/0.6899)	mem 24308MB
[2025-01-18 20:16:54 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][260/312]	eta 0:00:31 lr 0.002394	time 0.5987 (0.6126)	model_time 0.5985 (0.6052)	loss 3.6282 (3.4175)	grad_norm 1.2942 (1.6699/0.6799)	mem 24308MB
[2025-01-18 20:17:00 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][270/312]	eta 0:00:25 lr 0.002394	time 0.5895 (0.6122)	model_time 0.5891 (0.6051)	loss 2.2912 (3.4282)	grad_norm 1.8712 (1.6572/0.6723)	mem 24308MB
[2025-01-18 20:17:05 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][280/312]	eta 0:00:19 lr 0.002393	time 0.5992 (0.6116)	model_time 0.5990 (0.6047)	loss 3.7194 (3.4363)	grad_norm 0.9806 (1.6368/0.6693)	mem 24308MB
[2025-01-18 20:17:11 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][290/312]	eta 0:00:13 lr 0.002392	time 0.5884 (0.6111)	model_time 0.5880 (0.6045)	loss 3.5608 (3.4323)	grad_norm 2.3440 (1.6204/0.6690)	mem 24308MB
[2025-01-18 20:17:17 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][300/312]	eta 0:00:07 lr 0.002392	time 0.6422 (0.6103)	model_time 0.6421 (0.6039)	loss 2.3045 (3.4296)	grad_norm 0.8752 (1.6261/0.6728)	mem 24308MB
[2025-01-18 20:17:23 internimage_s_1k_224] (main.py 510): INFO Train: [131/300][310/312]	eta 0:00:01 lr 0.002391	time 0.6451 (0.6102)	model_time 0.6450 (0.6040)	loss 3.3892 (3.4308)	grad_norm 1.4220 (1.6439/0.6971)	mem 24308MB
[2025-01-18 20:17:24 internimage_s_1k_224] (main.py 519): INFO EPOCH 131 training takes 0:03:10
[2025-01-18 20:17:24 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_131.pth saving......
[2025-01-18 20:17:26 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_131.pth saved !!!
[2025-01-18 20:17:33 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.980 (6.980)	Loss 0.8819 (0.8819)	Acc@1 81.714 (81.714)	Acc@5 96.216 (96.216)	Mem 24308MB
[2025-01-18 20:17:36 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.907)	Loss 1.1841 (1.0208)	Acc@1 74.365 (78.647)	Acc@5 92.725 (94.631)	Mem 24308MB
[2025-01-18 20:17:36 internimage_s_1k_224] (main.py 575): INFO [Epoch:131] * Acc@1 78.545 Acc@5 94.630
[2025-01-18 20:17:36 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.5%
[2025-01-18 20:17:36 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 20:17:38 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 20:17:38 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.54%
[2025-01-18 20:17:45 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.922 (6.922)	Loss 0.7277 (0.7277)	Acc@1 82.617 (82.617)	Acc@5 96.973 (96.973)	Mem 24308MB
[2025-01-18 20:17:48 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.909)	Loss 1.0824 (0.8757)	Acc@1 73.267 (79.079)	Acc@5 92.627 (94.842)	Mem 24308MB
[2025-01-18 20:17:48 internimage_s_1k_224] (main.py 575): INFO [Epoch:131] * Acc@1 78.955 Acc@5 94.870
[2025-01-18 20:17:48 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.0%
[2025-01-18 20:17:48 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 20:17:50 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 20:17:50 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 78.95%
[2025-01-18 20:17:52 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][0/312]	eta 0:10:28 lr 0.002391	time 2.0138 (2.0138)	model_time 0.6008 (0.6008)	loss 2.6328 (2.6328)	grad_norm 1.0955 (1.0955/0.0000)	mem 24308MB
[2025-01-18 20:17:58 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][10/312]	eta 0:03:44 lr 0.002390	time 0.5809 (0.7443)	model_time 0.5808 (0.6155)	loss 3.2565 (3.3394)	grad_norm 1.2500 (1.6237/0.5523)	mem 24308MB
[2025-01-18 20:18:05 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][20/312]	eta 0:03:20 lr 0.002390	time 0.6036 (0.6854)	model_time 0.6031 (0.6177)	loss 3.9753 (3.3511)	grad_norm 0.9410 (1.6567/0.5029)	mem 24308MB
[2025-01-18 20:18:11 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][30/312]	eta 0:03:07 lr 0.002389	time 0.5840 (0.6660)	model_time 0.5836 (0.6201)	loss 3.5094 (3.3680)	grad_norm 1.3224 (1.5536/0.5199)	mem 24308MB
[2025-01-18 20:18:17 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][40/312]	eta 0:02:57 lr 0.002388	time 0.5847 (0.6514)	model_time 0.5843 (0.6165)	loss 2.5684 (3.3111)	grad_norm 3.1429 (1.6570/0.6265)	mem 24308MB
[2025-01-18 20:18:23 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][50/312]	eta 0:02:48 lr 0.002388	time 0.6713 (0.6419)	model_time 0.6708 (0.6138)	loss 3.5421 (3.3008)	grad_norm 2.2269 (1.6954/0.7044)	mem 24308MB
[2025-01-18 20:18:29 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][60/312]	eta 0:02:39 lr 0.002387	time 0.5867 (0.6329)	model_time 0.5865 (0.6094)	loss 3.9410 (3.2984)	grad_norm 1.1092 (1.6836/0.6796)	mem 24308MB
[2025-01-18 20:18:35 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][70/312]	eta 0:02:32 lr 0.002386	time 0.5728 (0.6281)	model_time 0.5724 (0.6079)	loss 2.8219 (3.2826)	grad_norm 1.6769 (1.6528/0.6592)	mem 24308MB
[2025-01-18 20:18:41 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][80/312]	eta 0:02:25 lr 0.002386	time 0.6786 (0.6257)	model_time 0.6782 (0.6079)	loss 2.1750 (3.2843)	grad_norm 2.3650 (1.7188/0.7622)	mem 24308MB
[2025-01-18 20:18:47 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][90/312]	eta 0:02:18 lr 0.002385	time 0.5757 (0.6221)	model_time 0.5753 (0.6062)	loss 2.7508 (3.3142)	grad_norm 2.8527 (1.7466/0.7406)	mem 24308MB
[2025-01-18 20:18:53 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][100/312]	eta 0:02:11 lr 0.002384	time 0.5947 (0.6189)	model_time 0.5945 (0.6045)	loss 3.5923 (3.3505)	grad_norm 1.3120 (1.7455/0.7184)	mem 24308MB
[2025-01-18 20:18:59 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][110/312]	eta 0:02:04 lr 0.002384	time 0.5905 (0.6181)	model_time 0.5903 (0.6050)	loss 4.0712 (3.3743)	grad_norm 0.7841 (1.7337/0.7213)	mem 24308MB
[2025-01-18 20:19:05 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][120/312]	eta 0:01:58 lr 0.002383	time 0.5778 (0.6194)	model_time 0.5774 (0.6073)	loss 2.8001 (3.3766)	grad_norm 1.3071 (1.7273/0.7050)	mem 24308MB
[2025-01-18 20:19:11 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][130/312]	eta 0:01:52 lr 0.002383	time 0.5881 (0.6192)	model_time 0.5879 (0.6080)	loss 3.5524 (3.3740)	grad_norm 2.5426 (1.7134/0.6886)	mem 24308MB
[2025-01-18 20:19:17 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][140/312]	eta 0:01:46 lr 0.002382	time 0.6480 (0.6190)	model_time 0.6479 (0.6086)	loss 3.4828 (3.3646)	grad_norm 1.0359 (1.6891/0.6763)	mem 24308MB
[2025-01-18 20:19:24 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][150/312]	eta 0:01:40 lr 0.002381	time 0.5747 (0.6194)	model_time 0.5745 (0.6096)	loss 3.5710 (3.3608)	grad_norm 2.6017 (1.7064/0.6934)	mem 24308MB
[2025-01-18 20:19:30 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][160/312]	eta 0:01:33 lr 0.002381	time 0.6885 (0.6184)	model_time 0.6884 (0.6092)	loss 3.4854 (3.3449)	grad_norm 2.0065 (1.7634/0.7289)	mem 24308MB
[2025-01-18 20:19:36 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][170/312]	eta 0:01:27 lr 0.002380	time 0.6393 (0.6179)	model_time 0.6388 (0.6093)	loss 2.4713 (3.3392)	grad_norm 0.9499 (1.7633/0.7240)	mem 24308MB
[2025-01-18 20:19:42 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][180/312]	eta 0:01:21 lr 0.002379	time 0.5791 (0.6160)	model_time 0.5789 (0.6078)	loss 2.4878 (3.3582)	grad_norm 1.6511 (1.7405/0.7197)	mem 24308MB
[2025-01-18 20:19:48 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][190/312]	eta 0:01:15 lr 0.002379	time 0.6658 (0.6148)	model_time 0.6653 (0.6070)	loss 3.3790 (3.3649)	grad_norm 1.0212 (1.7322/0.7137)	mem 24308MB
[2025-01-18 20:19:54 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][200/312]	eta 0:01:08 lr 0.002378	time 0.5911 (0.6142)	model_time 0.5910 (0.6068)	loss 3.0246 (3.3689)	grad_norm 2.0181 (1.7244/0.7030)	mem 24308MB
[2025-01-18 20:20:00 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][210/312]	eta 0:01:02 lr 0.002377	time 0.5883 (0.6138)	model_time 0.5879 (0.6067)	loss 3.4714 (3.3737)	grad_norm 1.3644 (1.7136/0.6938)	mem 24308MB
[2025-01-18 20:20:06 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][220/312]	eta 0:00:56 lr 0.002377	time 0.5964 (0.6128)	model_time 0.5960 (0.6060)	loss 2.8393 (3.3759)	grad_norm 2.4802 (1.7045/0.6867)	mem 24308MB
[2025-01-18 20:20:12 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][230/312]	eta 0:00:50 lr 0.002376	time 0.5755 (0.6121)	model_time 0.5749 (0.6056)	loss 3.5814 (3.3806)	grad_norm 2.8004 (1.6861/0.6865)	mem 24308MB
[2025-01-18 20:20:18 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][240/312]	eta 0:00:44 lr 0.002375	time 0.5806 (0.6129)	model_time 0.5802 (0.6066)	loss 2.3859 (3.3645)	grad_norm 1.1309 (1.7168/0.7238)	mem 24308MB
[2025-01-18 20:20:24 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][250/312]	eta 0:00:38 lr 0.002375	time 0.5770 (0.6129)	model_time 0.5766 (0.6069)	loss 2.2688 (3.3619)	grad_norm 1.7810 (1.7207/0.7263)	mem 24308MB
[2025-01-18 20:20:30 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][260/312]	eta 0:00:31 lr 0.002374	time 0.5743 (0.6130)	model_time 0.5741 (0.6071)	loss 4.2314 (3.3707)	grad_norm 1.1604 (1.7088/0.7193)	mem 24308MB
[2025-01-18 20:20:36 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][270/312]	eta 0:00:25 lr 0.002373	time 0.6068 (0.6135)	model_time 0.6063 (0.6079)	loss 3.3471 (3.3661)	grad_norm 1.3211 (1.7004/0.7140)	mem 24308MB
[2025-01-18 20:20:42 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][280/312]	eta 0:00:19 lr 0.002373	time 0.6335 (0.6129)	model_time 0.6333 (0.6074)	loss 2.2161 (3.3563)	grad_norm 1.3095 (1.6930/0.7079)	mem 24308MB
[2025-01-18 20:20:48 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][290/312]	eta 0:00:13 lr 0.002372	time 0.5802 (0.6126)	model_time 0.5800 (0.6073)	loss 3.6953 (3.3597)	grad_norm 3.9504 (1.7102/0.7167)	mem 24308MB
[2025-01-18 20:20:54 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][300/312]	eta 0:00:07 lr 0.002371	time 0.5696 (0.6118)	model_time 0.5695 (0.6066)	loss 4.0988 (3.3616)	grad_norm 3.6130 (1.7324/0.7400)	mem 24308MB
[2025-01-18 20:21:00 internimage_s_1k_224] (main.py 510): INFO Train: [132/300][310/312]	eta 0:00:01 lr 0.002371	time 0.5828 (0.6106)	model_time 0.5827 (0.6056)	loss 3.5520 (3.3618)	grad_norm 1.1967 (1.7347/0.7460)	mem 24308MB
[2025-01-18 20:21:01 internimage_s_1k_224] (main.py 519): INFO EPOCH 132 training takes 0:03:10
[2025-01-18 20:21:01 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_132.pth saving......
[2025-01-18 20:21:02 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_132.pth saved !!!
[2025-01-18 20:21:10 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.470 (7.470)	Loss 0.8366 (0.8366)	Acc@1 82.251 (82.251)	Acc@5 96.460 (96.460)	Mem 24308MB
[2025-01-18 20:21:13 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.984)	Loss 1.1832 (1.0030)	Acc@1 73.828 (78.505)	Acc@5 92.798 (94.573)	Mem 24308MB
[2025-01-18 20:21:13 internimage_s_1k_224] (main.py 575): INFO [Epoch:132] * Acc@1 78.521 Acc@5 94.658
[2025-01-18 20:21:13 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.5%
[2025-01-18 20:21:13 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.54%
[2025-01-18 20:21:22 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.246 (8.246)	Loss 0.7265 (0.7265)	Acc@1 82.666 (82.666)	Acc@5 96.997 (96.997)	Mem 24308MB
[2025-01-18 20:21:25 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.099)	Loss 1.0789 (0.8738)	Acc@1 73.340 (79.124)	Acc@5 92.627 (94.871)	Mem 24308MB
[2025-01-18 20:21:26 internimage_s_1k_224] (main.py 575): INFO [Epoch:132] * Acc@1 78.991 Acc@5 94.896
[2025-01-18 20:21:26 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.0%
[2025-01-18 20:21:26 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 20:21:28 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 20:21:28 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 78.99%
[2025-01-18 20:21:30 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][0/312]	eta 0:12:02 lr 0.002371	time 2.3141 (2.3141)	model_time 0.5994 (0.5994)	loss 2.1942 (2.1942)	grad_norm 1.1640 (1.1640/0.0000)	mem 24308MB
[2025-01-18 20:21:36 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][10/312]	eta 0:03:46 lr 0.002370	time 0.5935 (0.7515)	model_time 0.5934 (0.5953)	loss 3.5445 (3.0924)	grad_norm 1.2925 (1.2159/0.1895)	mem 24308MB
[2025-01-18 20:21:42 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][20/312]	eta 0:03:19 lr 0.002369	time 0.5905 (0.6824)	model_time 0.5904 (0.6004)	loss 3.8071 (3.2694)	grad_norm 1.4629 (1.5754/0.6031)	mem 24308MB
[2025-01-18 20:21:48 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][30/312]	eta 0:03:03 lr 0.002369	time 0.5723 (0.6525)	model_time 0.5718 (0.5968)	loss 3.7385 (3.1903)	grad_norm 1.8682 (1.6407/0.6380)	mem 24308MB
[2025-01-18 20:21:54 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][40/312]	eta 0:02:54 lr 0.002368	time 0.5874 (0.6411)	model_time 0.5872 (0.5990)	loss 3.8301 (3.2337)	grad_norm 1.4155 (1.5991/0.6135)	mem 24308MB
[2025-01-18 20:22:00 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][50/312]	eta 0:02:46 lr 0.002367	time 0.5860 (0.6359)	model_time 0.5856 (0.6017)	loss 2.3314 (3.2351)	grad_norm 1.1510 (1.5293/0.5841)	mem 24308MB
[2025-01-18 20:22:07 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][60/312]	eta 0:02:39 lr 0.002367	time 0.5748 (0.6345)	model_time 0.5746 (0.6058)	loss 4.1863 (3.2600)	grad_norm 3.3313 (1.5800/0.6955)	mem 24308MB
[2025-01-18 20:22:13 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][70/312]	eta 0:02:33 lr 0.002366	time 0.5783 (0.6323)	model_time 0.5779 (0.6077)	loss 3.7530 (3.3441)	grad_norm 1.1884 (1.6052/0.6802)	mem 24308MB
[2025-01-18 20:22:19 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][80/312]	eta 0:02:26 lr 0.002365	time 0.5764 (0.6318)	model_time 0.5763 (0.6101)	loss 3.4756 (3.3603)	grad_norm 1.0748 (1.5981/0.6626)	mem 24308MB
[2025-01-18 20:22:25 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][90/312]	eta 0:02:19 lr 0.002365	time 0.5924 (0.6281)	model_time 0.5920 (0.6088)	loss 3.5795 (3.3701)	grad_norm 0.7905 (1.5847/0.6617)	mem 24308MB
[2025-01-18 20:22:31 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][100/312]	eta 0:02:12 lr 0.002364	time 0.5965 (0.6256)	model_time 0.5963 (0.6081)	loss 3.3802 (3.3723)	grad_norm 1.3120 (1.5552/0.6413)	mem 24308MB
[2025-01-18 20:22:37 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][110/312]	eta 0:02:06 lr 0.002363	time 0.5746 (0.6246)	model_time 0.5742 (0.6087)	loss 2.6201 (3.3483)	grad_norm 1.8556 (1.5798/0.6403)	mem 24308MB
[2025-01-18 20:22:43 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][120/312]	eta 0:01:59 lr 0.002363	time 0.7052 (0.6224)	model_time 0.7047 (0.6077)	loss 3.8056 (3.3532)	grad_norm 1.3138 (1.6209/0.6898)	mem 24308MB
[2025-01-18 20:22:49 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][130/312]	eta 0:01:52 lr 0.002362	time 0.5752 (0.6206)	model_time 0.5747 (0.6069)	loss 3.2340 (3.3511)	grad_norm 1.6782 (1.5951/0.6915)	mem 24308MB
[2025-01-18 20:22:55 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][140/312]	eta 0:01:46 lr 0.002361	time 0.6598 (0.6195)	model_time 0.6596 (0.6068)	loss 3.8919 (3.3386)	grad_norm 1.1850 (1.5985/0.6786)	mem 24308MB
[2025-01-18 20:23:01 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][150/312]	eta 0:01:40 lr 0.002361	time 0.6126 (0.6176)	model_time 0.6122 (0.6057)	loss 2.6916 (3.3165)	grad_norm 2.0863 (1.6304/0.6778)	mem 24308MB
[2025-01-18 20:23:07 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][160/312]	eta 0:01:33 lr 0.002360	time 0.5902 (0.6165)	model_time 0.5901 (0.6053)	loss 4.2769 (3.3276)	grad_norm 2.8255 (1.6692/0.6895)	mem 24308MB
[2025-01-18 20:23:14 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][170/312]	eta 0:01:27 lr 0.002360	time 0.6928 (0.6172)	model_time 0.6926 (0.6066)	loss 3.6896 (3.3258)	grad_norm 1.0477 (1.6533/0.6776)	mem 24308MB
[2025-01-18 20:23:20 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][180/312]	eta 0:01:21 lr 0.002359	time 0.5906 (0.6188)	model_time 0.5902 (0.6088)	loss 3.1897 (3.3282)	grad_norm 2.7135 (1.6553/0.6731)	mem 24308MB
[2025-01-18 20:23:26 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][190/312]	eta 0:01:15 lr 0.002358	time 0.6000 (0.6187)	model_time 0.5999 (0.6092)	loss 3.1917 (3.3218)	grad_norm 1.5010 (1.6535/0.6773)	mem 24308MB
[2025-01-18 20:23:32 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][200/312]	eta 0:01:09 lr 0.002358	time 0.5835 (0.6183)	model_time 0.5834 (0.6093)	loss 3.4927 (3.3283)	grad_norm 2.6386 (1.6527/0.6769)	mem 24308MB
[2025-01-18 20:23:38 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][210/312]	eta 0:01:02 lr 0.002357	time 0.6667 (0.6169)	model_time 0.6666 (0.6083)	loss 4.3530 (3.3217)	grad_norm 1.2464 (1.6668/0.6840)	mem 24308MB
[2025-01-18 20:23:44 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][220/312]	eta 0:00:56 lr 0.002356	time 0.5927 (0.6161)	model_time 0.5926 (0.6079)	loss 2.9317 (3.3194)	grad_norm 1.8621 (1.6928/0.7358)	mem 24308MB
[2025-01-18 20:23:50 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][230/312]	eta 0:00:50 lr 0.002356	time 0.5810 (0.6157)	model_time 0.5806 (0.6078)	loss 3.5025 (3.3195)	grad_norm 2.1811 (1.6890/0.7239)	mem 24308MB
[2025-01-18 20:23:56 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][240/312]	eta 0:00:44 lr 0.002355	time 0.5744 (0.6144)	model_time 0.5740 (0.6068)	loss 3.6382 (3.3174)	grad_norm 1.0276 (1.6783/0.7128)	mem 24308MB
[2025-01-18 20:24:02 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][250/312]	eta 0:00:38 lr 0.002354	time 0.5994 (0.6143)	model_time 0.5992 (0.6069)	loss 3.3534 (3.3188)	grad_norm 2.1260 (1.6789/0.7025)	mem 24308MB
[2025-01-18 20:24:08 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][260/312]	eta 0:00:31 lr 0.002354	time 0.6611 (0.6141)	model_time 0.6607 (0.6071)	loss 3.4629 (3.3100)	grad_norm 1.1669 (1.6709/0.6939)	mem 24308MB
[2025-01-18 20:24:14 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][270/312]	eta 0:00:25 lr 0.002353	time 0.5870 (0.6132)	model_time 0.5866 (0.6063)	loss 3.5876 (3.3096)	grad_norm 1.2257 (1.6566/0.6886)	mem 24308MB
[2025-01-18 20:24:20 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][280/312]	eta 0:00:19 lr 0.002352	time 0.5849 (0.6129)	model_time 0.5848 (0.6062)	loss 3.6248 (3.3068)	grad_norm 1.3675 (1.6610/0.6878)	mem 24308MB
[2025-01-18 20:24:26 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][290/312]	eta 0:00:13 lr 0.002352	time 0.6598 (0.6131)	model_time 0.6596 (0.6067)	loss 3.7790 (3.3133)	grad_norm 2.4780 (1.6607/0.6837)	mem 24308MB
[2025-01-18 20:24:33 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][300/312]	eta 0:00:07 lr 0.002351	time 0.6778 (0.6138)	model_time 0.6777 (0.6076)	loss 4.1130 (3.3186)	grad_norm 1.1326 (1.6639/0.6908)	mem 24308MB
[2025-01-18 20:24:39 internimage_s_1k_224] (main.py 510): INFO Train: [133/300][310/312]	eta 0:00:01 lr 0.002350	time 0.5680 (0.6129)	model_time 0.5679 (0.6069)	loss 3.3945 (3.3144)	grad_norm 1.3044 (1.6930/0.7109)	mem 24308MB
[2025-01-18 20:24:39 internimage_s_1k_224] (main.py 519): INFO EPOCH 133 training takes 0:03:11
[2025-01-18 20:24:39 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_133.pth saving......
[2025-01-18 20:24:41 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_133.pth saved !!!
[2025-01-18 20:24:48 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.021 (7.021)	Loss 0.8637 (0.8637)	Acc@1 81.885 (81.885)	Acc@5 96.313 (96.313)	Mem 24308MB
[2025-01-18 20:24:51 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.929)	Loss 1.1386 (0.9801)	Acc@1 74.390 (78.724)	Acc@5 92.725 (94.702)	Mem 24308MB
[2025-01-18 20:24:52 internimage_s_1k_224] (main.py 575): INFO [Epoch:133] * Acc@1 78.605 Acc@5 94.708
[2025-01-18 20:24:52 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.6%
[2025-01-18 20:24:52 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 20:24:53 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 20:24:53 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.60%
[2025-01-18 20:25:01 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.170 (7.170)	Loss 0.7252 (0.7252)	Acc@1 82.812 (82.812)	Acc@5 97.021 (97.021)	Mem 24308MB
[2025-01-18 20:25:04 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.965)	Loss 1.0759 (0.8719)	Acc@1 73.511 (79.197)	Acc@5 92.651 (94.900)	Mem 24308MB
[2025-01-18 20:25:04 internimage_s_1k_224] (main.py 575): INFO [Epoch:133] * Acc@1 79.063 Acc@5 94.918
[2025-01-18 20:25:04 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.1%
[2025-01-18 20:25:04 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 20:25:06 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 20:25:06 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 79.06%
[2025-01-18 20:25:08 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][0/312]	eta 0:11:50 lr 0.002350	time 2.2765 (2.2765)	model_time 0.5989 (0.5989)	loss 4.2147 (4.2147)	grad_norm 0.9922 (0.9922/0.0000)	mem 24308MB
[2025-01-18 20:25:15 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][10/312]	eta 0:03:52 lr 0.002350	time 0.5725 (0.7686)	model_time 0.5723 (0.6158)	loss 3.5941 (3.3271)	grad_norm 1.8104 (1.3838/0.3869)	mem 24308MB
[2025-01-18 20:25:21 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][20/312]	eta 0:03:20 lr 0.002349	time 0.5800 (0.6866)	model_time 0.5798 (0.6065)	loss 4.1036 (3.2566)	grad_norm 1.6649 (1.3374/0.3222)	mem 24308MB
[2025-01-18 20:25:27 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][30/312]	eta 0:03:06 lr 0.002348	time 0.6212 (0.6596)	model_time 0.6208 (0.6052)	loss 2.1089 (3.1629)	grad_norm 4.3925 (1.5158/0.6500)	mem 24308MB
[2025-01-18 20:25:33 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][40/312]	eta 0:02:55 lr 0.002348	time 0.5741 (0.6438)	model_time 0.5740 (0.6022)	loss 3.5899 (3.2439)	grad_norm 2.1867 (1.8442/0.9931)	mem 24308MB
[2025-01-18 20:25:39 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][50/312]	eta 0:02:46 lr 0.002347	time 0.5878 (0.6352)	model_time 0.5874 (0.6017)	loss 3.5157 (3.2717)	grad_norm 2.2224 (1.8872/0.9608)	mem 24308MB
[2025-01-18 20:25:45 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][60/312]	eta 0:02:38 lr 0.002346	time 0.5721 (0.6294)	model_time 0.5717 (0.6013)	loss 2.8877 (3.2675)	grad_norm 1.2592 (1.8299/0.9049)	mem 24308MB
[2025-01-18 20:25:50 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][70/312]	eta 0:02:31 lr 0.002346	time 0.5886 (0.6245)	model_time 0.5885 (0.6003)	loss 3.3239 (3.2872)	grad_norm 2.2824 (1.7715/0.8721)	mem 24308MB
[2025-01-18 20:25:56 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][80/312]	eta 0:02:24 lr 0.002345	time 0.5939 (0.6215)	model_time 0.5935 (0.6002)	loss 3.0948 (3.2864)	grad_norm 2.8738 (1.7400/0.8515)	mem 24308MB
[2025-01-18 20:26:03 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][90/312]	eta 0:02:17 lr 0.002344	time 0.6539 (0.6200)	model_time 0.6535 (0.6010)	loss 3.4590 (3.2863)	grad_norm 2.0389 (1.7322/0.8215)	mem 24308MB
[2025-01-18 20:26:09 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][100/312]	eta 0:02:11 lr 0.002344	time 0.6679 (0.6203)	model_time 0.6677 (0.6031)	loss 3.4339 (3.3262)	grad_norm 1.6919 (1.6803/0.8019)	mem 24308MB
[2025-01-18 20:26:15 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][110/312]	eta 0:02:05 lr 0.002343	time 0.5869 (0.6200)	model_time 0.5867 (0.6044)	loss 3.2265 (3.3229)	grad_norm 1.1311 (1.6371/0.7863)	mem 24308MB
[2025-01-18 20:26:21 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][120/312]	eta 0:01:58 lr 0.002342	time 0.6755 (0.6190)	model_time 0.6751 (0.6046)	loss 1.9709 (3.3135)	grad_norm 1.3940 (1.6327/0.7596)	mem 24308MB
[2025-01-18 20:26:27 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][130/312]	eta 0:01:52 lr 0.002342	time 0.5722 (0.6197)	model_time 0.5721 (0.6064)	loss 3.6162 (3.3055)	grad_norm 3.5838 (1.6529/0.7981)	mem 24308MB
[2025-01-18 20:26:33 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][140/312]	eta 0:01:46 lr 0.002341	time 0.6021 (0.6174)	model_time 0.6017 (0.6050)	loss 3.5321 (3.3183)	grad_norm 1.7850 (1.6803/0.8258)	mem 24308MB
[2025-01-18 20:26:39 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][150/312]	eta 0:01:39 lr 0.002340	time 0.5861 (0.6163)	model_time 0.5860 (0.6047)	loss 3.4199 (3.3408)	grad_norm 1.3679 (1.6886/0.8115)	mem 24308MB
[2025-01-18 20:26:45 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][160/312]	eta 0:01:33 lr 0.002340	time 0.5845 (0.6151)	model_time 0.5841 (0.6042)	loss 3.8476 (3.3448)	grad_norm 1.3158 (1.6936/0.7989)	mem 24308MB
[2025-01-18 20:26:51 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][170/312]	eta 0:01:27 lr 0.002339	time 0.5753 (0.6135)	model_time 0.5749 (0.6032)	loss 4.2372 (3.3393)	grad_norm 1.0653 (1.6762/0.8006)	mem 24308MB
[2025-01-18 20:26:57 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][180/312]	eta 0:01:20 lr 0.002338	time 0.5850 (0.6126)	model_time 0.5846 (0.6029)	loss 3.6093 (3.3653)	grad_norm 2.0374 (1.6737/0.7944)	mem 24308MB
[2025-01-18 20:27:03 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][190/312]	eta 0:01:14 lr 0.002338	time 0.5773 (0.6123)	model_time 0.5771 (0.6031)	loss 3.6924 (3.3633)	grad_norm 2.0981 (1.6933/0.7976)	mem 24308MB
[2025-01-18 20:27:09 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][200/312]	eta 0:01:08 lr 0.002337	time 0.5728 (0.6116)	model_time 0.5726 (0.6028)	loss 3.3631 (3.3681)	grad_norm 1.3032 (1.6915/0.7873)	mem 24308MB
[2025-01-18 20:27:15 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][210/312]	eta 0:01:02 lr 0.002336	time 0.6229 (0.6110)	model_time 0.6225 (0.6026)	loss 3.8380 (3.3605)	grad_norm 0.8368 (1.6859/0.8109)	mem 24308MB
[2025-01-18 20:27:21 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][220/312]	eta 0:00:56 lr 0.002336	time 0.7159 (0.6118)	model_time 0.7154 (0.6038)	loss 2.3358 (3.3587)	grad_norm 1.1093 (1.6634/0.7999)	mem 24308MB
[2025-01-18 20:27:28 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][230/312]	eta 0:00:50 lr 0.002335	time 0.5799 (0.6125)	model_time 0.5798 (0.6048)	loss 4.2939 (3.3716)	grad_norm 1.1838 (1.6477/0.7914)	mem 24308MB
[2025-01-18 20:27:34 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][240/312]	eta 0:00:44 lr 0.002334	time 0.5748 (0.6126)	model_time 0.5746 (0.6052)	loss 3.2981 (3.3757)	grad_norm 1.5928 (1.6244/0.7846)	mem 24308MB
[2025-01-18 20:27:40 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][250/312]	eta 0:00:38 lr 0.002334	time 0.6048 (0.6131)	model_time 0.6044 (0.6060)	loss 3.2043 (3.3772)	grad_norm 1.6602 (1.6452/0.7806)	mem 24308MB
[2025-01-18 20:27:46 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][260/312]	eta 0:00:31 lr 0.002333	time 0.5811 (0.6125)	model_time 0.5809 (0.6057)	loss 3.2735 (3.3787)	grad_norm 1.2730 (1.6511/0.7698)	mem 24308MB
[2025-01-18 20:27:52 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][270/312]	eta 0:00:25 lr 0.002332	time 0.6002 (0.6124)	model_time 0.6001 (0.6058)	loss 2.8944 (3.3742)	grad_norm 1.1324 (1.6397/0.7623)	mem 24308MB
[2025-01-18 20:27:58 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][280/312]	eta 0:00:19 lr 0.002332	time 0.5720 (0.6118)	model_time 0.5716 (0.6054)	loss 3.6354 (3.3741)	grad_norm 1.2132 (1.6524/0.7629)	mem 24308MB
[2025-01-18 20:28:04 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][290/312]	eta 0:00:13 lr 0.002331	time 0.6152 (0.6112)	model_time 0.6143 (0.6050)	loss 3.5433 (3.3688)	grad_norm 1.5445 (1.6527/0.7539)	mem 24308MB
[2025-01-18 20:28:10 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][300/312]	eta 0:00:07 lr 0.002331	time 0.5690 (0.6106)	model_time 0.5689 (0.6046)	loss 2.7560 (3.3669)	grad_norm 1.0007 (1.6415/0.7480)	mem 24308MB
[2025-01-18 20:28:16 internimage_s_1k_224] (main.py 510): INFO Train: [134/300][310/312]	eta 0:00:01 lr 0.002330	time 0.5680 (0.6098)	model_time 0.5679 (0.6040)	loss 3.8159 (3.3753)	grad_norm 1.6040 (1.6379/0.7524)	mem 24308MB
[2025-01-18 20:28:16 internimage_s_1k_224] (main.py 519): INFO EPOCH 134 training takes 0:03:10
[2025-01-18 20:28:16 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_134.pth saving......
[2025-01-18 20:28:18 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_134.pth saved !!!
[2025-01-18 20:28:25 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.229 (7.229)	Loss 0.8146 (0.8146)	Acc@1 82.861 (82.861)	Acc@5 96.338 (96.338)	Mem 24308MB
[2025-01-18 20:28:29 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.972)	Loss 1.1743 (0.9716)	Acc@1 74.609 (78.811)	Acc@5 92.212 (94.718)	Mem 24308MB
[2025-01-18 20:28:29 internimage_s_1k_224] (main.py 575): INFO [Epoch:134] * Acc@1 78.723 Acc@5 94.760
[2025-01-18 20:28:29 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.7%
[2025-01-18 20:28:29 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 20:28:31 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 20:28:31 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.72%
[2025-01-18 20:28:38 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.009 (7.009)	Loss 0.7241 (0.7241)	Acc@1 82.788 (82.788)	Acc@5 97.021 (97.021)	Mem 24308MB
[2025-01-18 20:28:41 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.951)	Loss 1.0732 (0.8700)	Acc@1 73.535 (79.248)	Acc@5 92.627 (94.935)	Mem 24308MB
[2025-01-18 20:28:42 internimage_s_1k_224] (main.py 575): INFO [Epoch:134] * Acc@1 79.113 Acc@5 94.952
[2025-01-18 20:28:42 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.1%
[2025-01-18 20:28:42 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 20:28:44 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 20:28:44 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 79.11%
[2025-01-18 20:28:46 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][0/312]	eta 0:12:07 lr 0.002330	time 2.3333 (2.3333)	model_time 0.5905 (0.5905)	loss 4.0935 (4.0935)	grad_norm 1.2263 (1.2263/0.0000)	mem 24308MB
[2025-01-18 20:28:52 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][10/312]	eta 0:03:49 lr 0.002329	time 0.6030 (0.7585)	model_time 0.6028 (0.5998)	loss 2.8837 (3.2340)	grad_norm 1.5106 (1.2249/0.3384)	mem 24308MB
[2025-01-18 20:28:58 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][20/312]	eta 0:03:18 lr 0.002328	time 0.5966 (0.6798)	model_time 0.5961 (0.5965)	loss 2.7991 (3.3854)	grad_norm 1.3907 (1.3086/0.3863)	mem 24308MB
[2025-01-18 20:29:04 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][30/312]	eta 0:03:06 lr 0.002328	time 0.5827 (0.6618)	model_time 0.5825 (0.6053)	loss 2.9526 (3.3440)	grad_norm 1.2709 (1.4303/0.5786)	mem 24308MB
[2025-01-18 20:29:11 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][40/312]	eta 0:02:57 lr 0.002327	time 0.5840 (0.6535)	model_time 0.5838 (0.6106)	loss 2.6647 (3.2965)	grad_norm 1.5772 (1.7745/1.0098)	mem 24308MB
[2025-01-18 20:29:17 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][50/312]	eta 0:02:48 lr 0.002326	time 0.5846 (0.6446)	model_time 0.5845 (0.6101)	loss 4.1183 (3.3072)	grad_norm 1.2221 (1.7920/0.9417)	mem 24308MB
[2025-01-18 20:29:23 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][60/312]	eta 0:02:42 lr 0.002326	time 0.5889 (0.6439)	model_time 0.5888 (0.6150)	loss 3.8754 (3.3679)	grad_norm 1.0364 (1.6857/0.8975)	mem 24308MB
[2025-01-18 20:29:29 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][70/312]	eta 0:02:34 lr 0.002325	time 0.5738 (0.6378)	model_time 0.5733 (0.6129)	loss 3.4943 (3.3695)	grad_norm 2.2185 (1.6769/0.8701)	mem 24308MB
[2025-01-18 20:29:35 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][80/312]	eta 0:02:27 lr 0.002324	time 0.5912 (0.6348)	model_time 0.5910 (0.6127)	loss 2.6417 (3.4077)	grad_norm 0.8989 (1.6832/0.8401)	mem 24308MB
[2025-01-18 20:29:41 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][90/312]	eta 0:02:19 lr 0.002324	time 0.5788 (0.6305)	model_time 0.5784 (0.6108)	loss 2.2126 (3.3830)	grad_norm 0.8449 (1.6718/0.8016)	mem 24308MB
[2025-01-18 20:29:47 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][100/312]	eta 0:02:12 lr 0.002323	time 0.5827 (0.6262)	model_time 0.5825 (0.6084)	loss 3.1377 (3.4005)	grad_norm 2.0752 (1.6624/0.7696)	mem 24308MB
[2025-01-18 20:29:53 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][110/312]	eta 0:02:06 lr 0.002323	time 0.5902 (0.6245)	model_time 0.5897 (0.6083)	loss 3.1420 (3.3980)	grad_norm 0.9586 (1.6276/0.7495)	mem 24308MB
[2025-01-18 20:29:59 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][120/312]	eta 0:01:59 lr 0.002322	time 0.5834 (0.6226)	model_time 0.5830 (0.6077)	loss 2.8173 (3.4067)	grad_norm 0.8267 (1.6826/0.8106)	mem 24308MB
[2025-01-18 20:30:05 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][130/312]	eta 0:01:52 lr 0.002321	time 0.5912 (0.6204)	model_time 0.5907 (0.6067)	loss 4.2140 (3.3914)	grad_norm 1.7489 (1.6654/0.7872)	mem 24308MB
[2025-01-18 20:30:11 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][140/312]	eta 0:01:46 lr 0.002321	time 0.5943 (0.6187)	model_time 0.5937 (0.6059)	loss 3.4299 (3.4202)	grad_norm 1.0977 (1.6626/0.7708)	mem 24308MB
[2025-01-18 20:30:17 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][150/312]	eta 0:01:40 lr 0.002320	time 0.6473 (0.6195)	model_time 0.6472 (0.6075)	loss 2.6426 (3.3899)	grad_norm 2.1900 (1.6499/0.7547)	mem 24308MB
[2025-01-18 20:30:24 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][160/312]	eta 0:01:34 lr 0.002319	time 0.5947 (0.6198)	model_time 0.5946 (0.6085)	loss 3.6541 (3.3871)	grad_norm 0.9964 (1.6742/0.7857)	mem 24308MB
[2025-01-18 20:30:30 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][170/312]	eta 0:01:27 lr 0.002319	time 0.5828 (0.6187)	model_time 0.5823 (0.6081)	loss 2.7241 (3.3726)	grad_norm 3.4258 (1.6766/0.7789)	mem 24308MB
[2025-01-18 20:30:36 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][180/312]	eta 0:01:21 lr 0.002318	time 0.5722 (0.6190)	model_time 0.5720 (0.6089)	loss 3.5944 (3.3714)	grad_norm 1.0005 (1.7108/0.8091)	mem 24308MB
[2025-01-18 20:30:42 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][190/312]	eta 0:01:15 lr 0.002317	time 0.5747 (0.6182)	model_time 0.5743 (0.6086)	loss 2.8398 (3.3776)	grad_norm 1.0502 (1.6885/0.7967)	mem 24308MB
[2025-01-18 20:30:48 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][200/312]	eta 0:01:09 lr 0.002317	time 0.6860 (0.6178)	model_time 0.6858 (0.6087)	loss 3.4500 (3.3794)	grad_norm 2.1571 (1.6880/0.7942)	mem 24308MB
[2025-01-18 20:30:54 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][210/312]	eta 0:01:02 lr 0.002316	time 0.5932 (0.6170)	model_time 0.5930 (0.6083)	loss 3.4716 (3.3931)	grad_norm 1.3578 (1.6851/0.7880)	mem 24308MB
[2025-01-18 20:31:00 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][220/312]	eta 0:00:56 lr 0.002315	time 0.6035 (0.6157)	model_time 0.6031 (0.6074)	loss 3.5848 (3.3908)	grad_norm 1.3357 (1.6895/0.7914)	mem 24308MB
[2025-01-18 20:31:06 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][230/312]	eta 0:00:50 lr 0.002315	time 0.6366 (0.6156)	model_time 0.6365 (0.6076)	loss 3.4961 (3.3857)	grad_norm 1.3375 (1.6923/0.7864)	mem 24308MB
[2025-01-18 20:31:12 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][240/312]	eta 0:00:44 lr 0.002314	time 0.5846 (0.6149)	model_time 0.5841 (0.6072)	loss 2.7630 (3.3833)	grad_norm 2.0869 (1.7240/0.7965)	mem 24308MB
[2025-01-18 20:31:18 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][250/312]	eta 0:00:38 lr 0.002313	time 0.5734 (0.6141)	model_time 0.5730 (0.6068)	loss 3.6326 (3.3793)	grad_norm 1.7361 (1.7207/0.7849)	mem 24308MB
[2025-01-18 20:31:24 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][260/312]	eta 0:00:31 lr 0.002313	time 0.5746 (0.6133)	model_time 0.5742 (0.6062)	loss 3.6156 (3.3728)	grad_norm 1.7274 (1.7172/0.7758)	mem 24308MB
[2025-01-18 20:31:30 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][270/312]	eta 0:00:25 lr 0.002312	time 0.6748 (0.6134)	model_time 0.6746 (0.6066)	loss 3.1834 (3.3710)	grad_norm 1.5876 (1.7205/0.7681)	mem 24308MB
[2025-01-18 20:31:37 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][280/312]	eta 0:00:19 lr 0.002311	time 0.8314 (0.6145)	model_time 0.8312 (0.6079)	loss 3.7959 (3.3713)	grad_norm 1.6671 (1.7123/0.7603)	mem 24308MB
[2025-01-18 20:31:43 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][290/312]	eta 0:00:13 lr 0.002311	time 0.5772 (0.6142)	model_time 0.5767 (0.6078)	loss 4.2668 (3.3778)	grad_norm 1.1364 (1.7093/0.7594)	mem 24308MB
[2025-01-18 20:31:49 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][300/312]	eta 0:00:07 lr 0.002310	time 0.5687 (0.6139)	model_time 0.5686 (0.6077)	loss 3.4004 (3.3742)	grad_norm 0.9895 (1.6975/0.7520)	mem 24308MB
[2025-01-18 20:31:55 internimage_s_1k_224] (main.py 510): INFO Train: [135/300][310/312]	eta 0:00:01 lr 0.002309	time 0.5695 (0.6137)	model_time 0.5694 (0.6077)	loss 2.9241 (3.3730)	grad_norm 1.1521 (1.7058/0.7484)	mem 24308MB
[2025-01-18 20:31:55 internimage_s_1k_224] (main.py 519): INFO EPOCH 135 training takes 0:03:11
[2025-01-18 20:31:55 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_135.pth saving......
[2025-01-18 20:31:57 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_135.pth saved !!!
[2025-01-18 20:32:04 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.162 (7.162)	Loss 0.8617 (0.8617)	Acc@1 81.055 (81.055)	Acc@5 96.387 (96.387)	Mem 24308MB
[2025-01-18 20:32:08 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.982)	Loss 1.1233 (0.9790)	Acc@1 75.171 (78.604)	Acc@5 92.920 (94.604)	Mem 24308MB
[2025-01-18 20:32:08 internimage_s_1k_224] (main.py 575): INFO [Epoch:135] * Acc@1 78.441 Acc@5 94.592
[2025-01-18 20:32:08 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.4%
[2025-01-18 20:32:08 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.72%
[2025-01-18 20:32:16 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.252 (8.252)	Loss 0.7229 (0.7229)	Acc@1 82.959 (82.959)	Acc@5 97.046 (97.046)	Mem 24308MB
[2025-01-18 20:32:21 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.121)	Loss 1.0702 (0.8681)	Acc@1 73.657 (79.335)	Acc@5 92.725 (94.966)	Mem 24308MB
[2025-01-18 20:32:21 internimage_s_1k_224] (main.py 575): INFO [Epoch:135] * Acc@1 79.205 Acc@5 94.982
[2025-01-18 20:32:21 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.2%
[2025-01-18 20:32:21 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 20:32:23 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 20:32:23 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 79.20%
[2025-01-18 20:32:26 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][0/312]	eta 0:13:02 lr 0.002309	time 2.5081 (2.5081)	model_time 0.6230 (0.6230)	loss 3.6174 (3.6174)	grad_norm 0.7562 (0.7562/0.0000)	mem 24308MB
[2025-01-18 20:32:32 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][10/312]	eta 0:03:54 lr 0.002309	time 0.6450 (0.7765)	model_time 0.6448 (0.6049)	loss 2.4865 (3.2261)	grad_norm 1.2315 (2.6222/1.5857)	mem 24308MB
[2025-01-18 20:32:38 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][20/312]	eta 0:03:21 lr 0.002308	time 0.5943 (0.6909)	model_time 0.5942 (0.6008)	loss 2.4717 (3.3198)	grad_norm 1.8189 (2.3605/1.2551)	mem 24308MB
[2025-01-18 20:32:44 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][30/312]	eta 0:03:06 lr 0.002307	time 0.5832 (0.6616)	model_time 0.5831 (0.6005)	loss 3.7610 (3.3304)	grad_norm 1.3507 (2.1281/1.1410)	mem 24308MB
[2025-01-18 20:32:50 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][40/312]	eta 0:02:56 lr 0.002307	time 0.5803 (0.6473)	model_time 0.5801 (0.6010)	loss 3.4731 (3.3469)	grad_norm 1.2012 (1.9828/1.0508)	mem 24308MB
[2025-01-18 20:32:56 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][50/312]	eta 0:02:47 lr 0.002306	time 0.5768 (0.6391)	model_time 0.5764 (0.6019)	loss 3.3612 (3.3751)	grad_norm 1.8562 (1.9486/0.9803)	mem 24308MB
[2025-01-18 20:33:02 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][60/312]	eta 0:02:39 lr 0.002305	time 0.5985 (0.6333)	model_time 0.5983 (0.6021)	loss 4.2380 (3.3850)	grad_norm 1.8691 (1.8568/0.9443)	mem 24308MB
[2025-01-18 20:33:08 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][70/312]	eta 0:02:31 lr 0.002305	time 0.5799 (0.6278)	model_time 0.5798 (0.6009)	loss 3.8056 (3.4287)	grad_norm 1.9356 (1.8770/1.0019)	mem 24308MB
[2025-01-18 20:33:14 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][80/312]	eta 0:02:25 lr 0.002304	time 0.5943 (0.6259)	model_time 0.5939 (0.6023)	loss 3.2203 (3.4263)	grad_norm 2.2189 (1.9799/1.0528)	mem 24308MB
[2025-01-18 20:33:20 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][90/312]	eta 0:02:19 lr 0.002303	time 0.6600 (0.6271)	model_time 0.6598 (0.6060)	loss 3.2165 (3.4338)	grad_norm 0.8651 (1.9396/1.0168)	mem 24308MB
[2025-01-18 20:33:26 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][100/312]	eta 0:02:12 lr 0.002303	time 0.6012 (0.6247)	model_time 0.6010 (0.6057)	loss 3.3263 (3.4184)	grad_norm 1.5398 (1.8960/0.9791)	mem 24308MB
[2025-01-18 20:33:32 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][110/312]	eta 0:02:06 lr 0.002302	time 0.6788 (0.6239)	model_time 0.6784 (0.6066)	loss 4.2842 (3.4225)	grad_norm 3.0603 (1.8778/0.9636)	mem 24308MB
[2025-01-18 20:33:39 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][120/312]	eta 0:01:59 lr 0.002301	time 0.5725 (0.6236)	model_time 0.5724 (0.6077)	loss 2.4854 (3.4098)	grad_norm 1.5268 (1.8586/0.9409)	mem 24308MB
[2025-01-18 20:33:45 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][130/312]	eta 0:01:53 lr 0.002301	time 0.6817 (0.6220)	model_time 0.6815 (0.6073)	loss 2.0639 (3.3585)	grad_norm 0.9598 (1.8284/0.9229)	mem 24308MB
[2025-01-18 20:33:51 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][140/312]	eta 0:01:46 lr 0.002300	time 0.6061 (0.6208)	model_time 0.6059 (0.6070)	loss 3.4092 (3.3777)	grad_norm 1.5332 (1.8267/0.9043)	mem 24308MB
[2025-01-18 20:33:57 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][150/312]	eta 0:01:40 lr 0.002299	time 0.5912 (0.6189)	model_time 0.5908 (0.6060)	loss 3.5601 (3.3730)	grad_norm 0.8882 (1.7903/0.8907)	mem 24308MB
[2025-01-18 20:34:03 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][160/312]	eta 0:01:33 lr 0.002299	time 0.6062 (0.6182)	model_time 0.6057 (0.6060)	loss 3.1774 (3.3650)	grad_norm 1.5665 (1.7480/0.8795)	mem 24308MB
[2025-01-18 20:34:09 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][170/312]	eta 0:01:27 lr 0.002298	time 0.5812 (0.6171)	model_time 0.5808 (0.6056)	loss 3.6481 (3.3589)	grad_norm 1.6070 (1.7854/0.9184)	mem 24308MB
[2025-01-18 20:34:15 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][180/312]	eta 0:01:21 lr 0.002297	time 0.5784 (0.6161)	model_time 0.5782 (0.6052)	loss 2.7927 (3.3526)	grad_norm 0.8978 (1.7577/0.9057)	mem 24308MB
[2025-01-18 20:34:20 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][190/312]	eta 0:01:14 lr 0.002297	time 0.5819 (0.6146)	model_time 0.5814 (0.6043)	loss 2.9766 (3.3552)	grad_norm 2.5791 (1.7620/0.8870)	mem 24308MB
[2025-01-18 20:34:27 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][200/312]	eta 0:01:08 lr 0.002296	time 0.5855 (0.6146)	model_time 0.5850 (0.6048)	loss 3.2604 (3.3562)	grad_norm 2.2467 (1.7495/0.8703)	mem 24308MB
[2025-01-18 20:34:33 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][210/312]	eta 0:01:02 lr 0.002295	time 0.6614 (0.6162)	model_time 0.6609 (0.6068)	loss 2.3926 (3.3588)	grad_norm 3.0337 (1.7416/0.8620)	mem 24308MB
[2025-01-18 20:34:39 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][220/312]	eta 0:00:56 lr 0.002295	time 0.5845 (0.6170)	model_time 0.5843 (0.6080)	loss 3.8871 (3.3744)	grad_norm 1.5251 (1.7394/0.8518)	mem 24308MB
[2025-01-18 20:34:46 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][230/312]	eta 0:00:50 lr 0.002294	time 0.7923 (0.6173)	model_time 0.7922 (0.6087)	loss 3.1570 (3.3668)	grad_norm 1.2833 (1.7368/0.8441)	mem 24308MB
[2025-01-18 20:34:52 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][240/312]	eta 0:00:44 lr 0.002293	time 0.5744 (0.6167)	model_time 0.5740 (0.6085)	loss 3.4283 (3.3600)	grad_norm 2.6233 (1.7462/0.8353)	mem 24308MB
[2025-01-18 20:34:58 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][250/312]	eta 0:00:38 lr 0.002293	time 0.6224 (0.6159)	model_time 0.6219 (0.6080)	loss 3.0187 (3.3625)	grad_norm 1.6212 (1.7550/0.8320)	mem 24308MB
[2025-01-18 20:35:04 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][260/312]	eta 0:00:32 lr 0.002292	time 0.5989 (0.6164)	model_time 0.5987 (0.6088)	loss 3.1151 (3.3558)	grad_norm 1.2716 (1.7611/0.8363)	mem 24308MB
[2025-01-18 20:35:10 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][270/312]	eta 0:00:25 lr 0.002291	time 0.5969 (0.6153)	model_time 0.5964 (0.6080)	loss 3.5936 (3.3506)	grad_norm 1.1148 (1.7593/0.8306)	mem 24308MB
[2025-01-18 20:35:16 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][280/312]	eta 0:00:19 lr 0.002291	time 0.6837 (0.6150)	model_time 0.6836 (0.6079)	loss 3.1267 (3.3454)	grad_norm 1.7640 (1.7476/0.8214)	mem 24308MB
[2025-01-18 20:35:22 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][290/312]	eta 0:00:13 lr 0.002290	time 0.5958 (0.6147)	model_time 0.5957 (0.6078)	loss 2.6271 (3.3478)	grad_norm 2.1205 (1.7411/0.8172)	mem 24308MB
[2025-01-18 20:35:28 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][300/312]	eta 0:00:07 lr 0.002290	time 0.5608 (0.6139)	model_time 0.5607 (0.6072)	loss 3.8727 (3.3528)	grad_norm 2.2452 (1.7410/0.8081)	mem 24308MB
[2025-01-18 20:35:34 internimage_s_1k_224] (main.py 510): INFO Train: [136/300][310/312]	eta 0:00:01 lr 0.002289	time 0.5689 (0.6125)	model_time 0.5688 (0.6061)	loss 4.0556 (3.3588)	grad_norm 1.6254 (1.7097/0.7475)	mem 24308MB
[2025-01-18 20:35:34 internimage_s_1k_224] (main.py 519): INFO EPOCH 136 training takes 0:03:11
[2025-01-18 20:35:34 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_136.pth saving......
[2025-01-18 20:35:36 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_136.pth saved !!!
[2025-01-18 20:35:43 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.191 (7.191)	Loss 0.8672 (0.8672)	Acc@1 81.836 (81.836)	Acc@5 96.411 (96.411)	Mem 24308MB
[2025-01-18 20:35:47 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.964)	Loss 1.1303 (0.9807)	Acc@1 74.194 (78.733)	Acc@5 93.140 (94.795)	Mem 24308MB
[2025-01-18 20:35:47 internimage_s_1k_224] (main.py 575): INFO [Epoch:136] * Acc@1 78.645 Acc@5 94.816
[2025-01-18 20:35:47 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.6%
[2025-01-18 20:35:47 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.72%
[2025-01-18 20:35:55 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.342 (8.342)	Loss 0.7218 (0.7218)	Acc@1 82.910 (82.910)	Acc@5 97.070 (97.070)	Mem 24308MB
[2025-01-18 20:36:00 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.221)	Loss 1.0671 (0.8664)	Acc@1 73.853 (79.390)	Acc@5 92.700 (94.975)	Mem 24308MB
[2025-01-18 20:36:00 internimage_s_1k_224] (main.py 575): INFO [Epoch:136] * Acc@1 79.255 Acc@5 94.994
[2025-01-18 20:36:00 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.3%
[2025-01-18 20:36:00 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 20:36:03 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 20:36:03 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 79.25%
[2025-01-18 20:36:05 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][0/312]	eta 0:11:23 lr 0.002289	time 2.1903 (2.1903)	model_time 0.7399 (0.7399)	loss 4.0512 (4.0512)	grad_norm 1.8676 (1.8676/0.0000)	mem 24308MB
[2025-01-18 20:36:11 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][10/312]	eta 0:03:52 lr 0.002288	time 0.6527 (0.7688)	model_time 0.6523 (0.6366)	loss 2.4285 (3.2833)	grad_norm 1.5186 (1.6322/0.4261)	mem 24308MB
[2025-01-18 20:36:18 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][20/312]	eta 0:03:26 lr 0.002287	time 0.6596 (0.7074)	model_time 0.6594 (0.6380)	loss 3.7649 (3.3260)	grad_norm 2.5983 (1.7275/0.6525)	mem 24308MB
[2025-01-18 20:36:24 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][30/312]	eta 0:03:10 lr 0.002287	time 0.6032 (0.6772)	model_time 0.6026 (0.6300)	loss 3.7702 (3.3238)	grad_norm 3.4829 (1.8850/0.7313)	mem 24308MB
[2025-01-18 20:36:30 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][40/312]	eta 0:03:01 lr 0.002286	time 0.6638 (0.6661)	model_time 0.6633 (0.6304)	loss 3.8344 (3.3007)	grad_norm 2.6832 (1.8935/0.6859)	mem 24308MB
[2025-01-18 20:36:36 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][50/312]	eta 0:02:51 lr 0.002285	time 0.5890 (0.6540)	model_time 0.5885 (0.6251)	loss 3.1755 (3.3072)	grad_norm 1.5957 (2.0042/0.8456)	mem 24308MB
[2025-01-18 20:36:42 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][60/312]	eta 0:02:42 lr 0.002285	time 0.5735 (0.6443)	model_time 0.5733 (0.6202)	loss 3.5653 (3.3470)	grad_norm 1.6941 (1.9668/0.8109)	mem 24308MB
[2025-01-18 20:36:48 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][70/312]	eta 0:02:34 lr 0.002284	time 0.5795 (0.6393)	model_time 0.5790 (0.6185)	loss 2.5686 (3.3420)	grad_norm 1.7487 (1.8915/0.7924)	mem 24308MB
[2025-01-18 20:36:54 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][80/312]	eta 0:02:26 lr 0.002283	time 0.5713 (0.6330)	model_time 0.5711 (0.6147)	loss 3.5180 (3.3757)	grad_norm 0.7638 (1.8188/0.7934)	mem 24308MB
[2025-01-18 20:37:00 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][90/312]	eta 0:02:19 lr 0.002283	time 0.5974 (0.6287)	model_time 0.5972 (0.6124)	loss 3.5430 (3.3607)	grad_norm 1.3621 (1.7715/0.7717)	mem 24308MB
[2025-01-18 20:37:06 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][100/312]	eta 0:02:12 lr 0.002282	time 0.5888 (0.6271)	model_time 0.5886 (0.6124)	loss 3.4989 (3.3590)	grad_norm 1.3167 (1.7316/0.7518)	mem 24308MB
[2025-01-18 20:37:12 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][110/312]	eta 0:02:06 lr 0.002281	time 0.5795 (0.6240)	model_time 0.5793 (0.6105)	loss 3.6690 (3.3479)	grad_norm 1.4796 (1.6963/0.7401)	mem 24308MB
[2025-01-18 20:37:18 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][120/312]	eta 0:01:59 lr 0.002281	time 0.5836 (0.6212)	model_time 0.5834 (0.6089)	loss 3.0822 (3.3656)	grad_norm 1.1506 (1.6988/0.7326)	mem 24308MB
[2025-01-18 20:37:24 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][130/312]	eta 0:01:52 lr 0.002280	time 0.6710 (0.6204)	model_time 0.6709 (0.6089)	loss 3.6383 (3.3723)	grad_norm 1.6619 (1.7086/0.7268)	mem 24308MB
[2025-01-18 20:37:30 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][140/312]	eta 0:01:46 lr 0.002279	time 0.5830 (0.6207)	model_time 0.5828 (0.6101)	loss 3.4272 (3.3633)	grad_norm 1.5644 (1.6952/0.7153)	mem 24308MB
[2025-01-18 20:37:37 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][150/312]	eta 0:01:40 lr 0.002279	time 0.6940 (0.6207)	model_time 0.6939 (0.6107)	loss 3.1654 (3.3402)	grad_norm 1.4876 (1.6766/0.6989)	mem 24308MB
[2025-01-18 20:37:43 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][160/312]	eta 0:01:34 lr 0.002278	time 0.5771 (0.6205)	model_time 0.5769 (0.6112)	loss 3.7829 (3.3455)	grad_norm 2.7940 (1.6730/0.6930)	mem 24308MB
[2025-01-18 20:37:49 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][170/312]	eta 0:01:28 lr 0.002278	time 0.5943 (0.6200)	model_time 0.5939 (0.6111)	loss 4.5855 (3.3583)	grad_norm 1.6104 (1.6663/0.6955)	mem 24308MB
[2025-01-18 20:37:55 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][180/312]	eta 0:01:21 lr 0.002277	time 0.5743 (0.6183)	model_time 0.5738 (0.6099)	loss 4.0473 (3.3413)	grad_norm 1.5553 (1.6592/0.6851)	mem 24308MB
[2025-01-18 20:38:01 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][190/312]	eta 0:01:15 lr 0.002276	time 0.6021 (0.6180)	model_time 0.6019 (0.6100)	loss 2.8103 (3.3324)	grad_norm 1.5764 (1.6832/0.7198)	mem 24308MB
[2025-01-18 20:38:07 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][200/312]	eta 0:01:09 lr 0.002276	time 0.5816 (0.6166)	model_time 0.5812 (0.6090)	loss 2.4227 (3.3137)	grad_norm 1.5276 (1.6793/0.7103)	mem 24308MB
[2025-01-18 20:38:13 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][210/312]	eta 0:01:02 lr 0.002275	time 0.5785 (0.6151)	model_time 0.5781 (0.6079)	loss 3.4630 (3.3229)	grad_norm 2.1494 (1.6706/0.6981)	mem 24308MB
[2025-01-18 20:38:19 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][220/312]	eta 0:00:56 lr 0.002274	time 0.5760 (0.6150)	model_time 0.5756 (0.6081)	loss 3.0419 (3.3150)	grad_norm 1.0144 (1.6629/0.6884)	mem 24308MB
[2025-01-18 20:38:25 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][230/312]	eta 0:00:50 lr 0.002274	time 0.6022 (0.6139)	model_time 0.6017 (0.6073)	loss 2.1481 (3.3147)	grad_norm 1.1455 (1.6770/0.6905)	mem 24308MB
[2025-01-18 20:38:31 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][240/312]	eta 0:00:44 lr 0.002273	time 0.5855 (0.6130)	model_time 0.5851 (0.6066)	loss 2.7905 (3.3207)	grad_norm 1.2893 (1.6670/0.6822)	mem 24308MB
[2025-01-18 20:38:37 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][250/312]	eta 0:00:37 lr 0.002272	time 0.6866 (0.6127)	model_time 0.6862 (0.6066)	loss 2.4033 (3.3107)	grad_norm 0.9523 (1.6603/0.6732)	mem 24308MB
[2025-01-18 20:38:43 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][260/312]	eta 0:00:31 lr 0.002272	time 0.6334 (0.6134)	model_time 0.6332 (0.6075)	loss 2.9559 (3.3160)	grad_norm 0.9484 (1.6741/0.6897)	mem 24308MB
[2025-01-18 20:38:49 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][270/312]	eta 0:00:25 lr 0.002271	time 0.6854 (0.6139)	model_time 0.6849 (0.6082)	loss 3.7827 (3.3200)	grad_norm 2.2416 (1.6913/0.6998)	mem 24308MB
[2025-01-18 20:38:55 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][280/312]	eta 0:00:19 lr 0.002270	time 0.5874 (0.6136)	model_time 0.5872 (0.6080)	loss 3.7368 (3.3182)	grad_norm 3.1911 (1.7161/0.7302)	mem 24308MB
[2025-01-18 20:39:01 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][290/312]	eta 0:00:13 lr 0.002270	time 0.6205 (0.6134)	model_time 0.6201 (0.6080)	loss 3.6066 (3.3262)	grad_norm 1.2054 (1.7004/0.7257)	mem 24308MB
[2025-01-18 20:39:07 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][300/312]	eta 0:00:07 lr 0.002269	time 0.5697 (0.6127)	model_time 0.5696 (0.6075)	loss 3.4137 (3.3277)	grad_norm 1.3806 (1.6861/0.7211)	mem 24308MB
[2025-01-18 20:39:13 internimage_s_1k_224] (main.py 510): INFO Train: [137/300][310/312]	eta 0:00:01 lr 0.002268	time 0.6584 (0.6123)	model_time 0.6583 (0.6073)	loss 3.9453 (3.3259)	grad_norm 0.9288 (1.6772/0.7220)	mem 24308MB
[2025-01-18 20:39:14 internimage_s_1k_224] (main.py 519): INFO EPOCH 137 training takes 0:03:11
[2025-01-18 20:39:14 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_137.pth saving......
[2025-01-18 20:39:16 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_137.pth saved !!!
[2025-01-18 20:39:23 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.189 (7.189)	Loss 0.8374 (0.8374)	Acc@1 82.251 (82.251)	Acc@5 96.655 (96.655)	Mem 24308MB
[2025-01-18 20:39:26 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.967)	Loss 1.1841 (0.9902)	Acc@1 73.877 (78.962)	Acc@5 92.847 (94.789)	Mem 24308MB
[2025-01-18 20:39:27 internimage_s_1k_224] (main.py 575): INFO [Epoch:137] * Acc@1 78.895 Acc@5 94.840
[2025-01-18 20:39:27 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.9%
[2025-01-18 20:39:27 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 20:39:29 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 20:39:29 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.89%
[2025-01-18 20:39:36 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.585 (7.585)	Loss 0.7207 (0.7207)	Acc@1 82.935 (82.935)	Acc@5 97.119 (97.119)	Mem 24308MB
[2025-01-18 20:39:40 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.016)	Loss 1.0641 (0.8647)	Acc@1 73.877 (79.454)	Acc@5 92.773 (95.022)	Mem 24308MB
[2025-01-18 20:39:40 internimage_s_1k_224] (main.py 575): INFO [Epoch:137] * Acc@1 79.323 Acc@5 95.048
[2025-01-18 20:39:40 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.3%
[2025-01-18 20:39:40 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 20:39:42 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 20:39:42 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 79.32%
[2025-01-18 20:39:44 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][0/312]	eta 0:12:00 lr 0.002268	time 2.3108 (2.3108)	model_time 0.6127 (0.6127)	loss 3.3863 (3.3863)	grad_norm 3.7976 (3.7976/0.0000)	mem 24308MB
[2025-01-18 20:39:50 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][10/312]	eta 0:03:47 lr 0.002268	time 0.5867 (0.7525)	model_time 0.5862 (0.5977)	loss 2.8333 (3.3675)	grad_norm 1.1537 (1.6282/0.7552)	mem 24308MB
[2025-01-18 20:39:56 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][20/312]	eta 0:03:17 lr 0.002267	time 0.5953 (0.6770)	model_time 0.5951 (0.5958)	loss 3.7391 (3.4435)	grad_norm 2.3822 (1.7710/0.6635)	mem 24308MB
[2025-01-18 20:40:02 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][30/312]	eta 0:03:04 lr 0.002266	time 0.6706 (0.6556)	model_time 0.6705 (0.6005)	loss 4.0849 (3.5050)	grad_norm 2.3795 (1.9609/0.8442)	mem 24308MB
[2025-01-18 20:40:08 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][40/312]	eta 0:02:54 lr 0.002266	time 0.5808 (0.6417)	model_time 0.5803 (0.6000)	loss 3.9303 (3.5159)	grad_norm 1.0047 (1.7938/0.8052)	mem 24308MB
[2025-01-18 20:40:14 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][50/312]	eta 0:02:45 lr 0.002265	time 0.6247 (0.6335)	model_time 0.6243 (0.5998)	loss 3.6268 (3.4664)	grad_norm 3.4907 (1.7611/0.7801)	mem 24308MB
[2025-01-18 20:40:20 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][60/312]	eta 0:02:37 lr 0.002264	time 0.5889 (0.6257)	model_time 0.5888 (0.5975)	loss 3.7068 (3.4806)	grad_norm 0.6998 (1.7183/0.7674)	mem 24308MB
[2025-01-18 20:40:27 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][70/312]	eta 0:02:32 lr 0.002264	time 0.6012 (0.6290)	model_time 0.6010 (0.6047)	loss 3.4381 (3.4315)	grad_norm 1.5330 (1.6827/0.7353)	mem 24308MB
[2025-01-18 20:40:33 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][80/312]	eta 0:02:25 lr 0.002263	time 0.6963 (0.6292)	model_time 0.6959 (0.6079)	loss 2.3603 (3.3709)	grad_norm 2.1365 (1.7323/0.7946)	mem 24308MB
[2025-01-18 20:40:39 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][90/312]	eta 0:02:19 lr 0.002262	time 0.6625 (0.6280)	model_time 0.6624 (0.6090)	loss 3.6509 (3.3813)	grad_norm 1.0638 (1.6903/0.7721)	mem 24308MB
[2025-01-18 20:40:45 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][100/312]	eta 0:02:12 lr 0.002262	time 0.5861 (0.6254)	model_time 0.5859 (0.6083)	loss 3.1894 (3.3572)	grad_norm 2.4986 (1.6715/0.7533)	mem 24308MB
[2025-01-18 20:40:51 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][110/312]	eta 0:02:05 lr 0.002261	time 0.5736 (0.6224)	model_time 0.5732 (0.6068)	loss 3.4617 (3.3387)	grad_norm 3.7489 (1.6812/0.7500)	mem 24308MB
[2025-01-18 20:40:57 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][120/312]	eta 0:01:59 lr 0.002260	time 0.6717 (0.6223)	model_time 0.6716 (0.6079)	loss 4.1334 (3.3673)	grad_norm 2.2282 (1.7158/0.7762)	mem 24308MB
[2025-01-18 20:41:03 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][130/312]	eta 0:01:52 lr 0.002260	time 0.5939 (0.6198)	model_time 0.5935 (0.6065)	loss 3.8302 (3.3761)	grad_norm 1.4946 (1.7297/0.7830)	mem 24308MB
[2025-01-18 20:41:09 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][140/312]	eta 0:01:46 lr 0.002259	time 0.5861 (0.6173)	model_time 0.5860 (0.6049)	loss 3.1582 (3.3731)	grad_norm 1.4984 (1.8101/0.8647)	mem 24308MB
[2025-01-18 20:41:15 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][150/312]	eta 0:01:39 lr 0.002258	time 0.7004 (0.6173)	model_time 0.6999 (0.6056)	loss 2.7904 (3.3756)	grad_norm 1.2514 (1.8070/0.8438)	mem 24308MB
[2025-01-18 20:41:21 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][160/312]	eta 0:01:33 lr 0.002258	time 0.5747 (0.6161)	model_time 0.5745 (0.6052)	loss 3.3099 (3.3812)	grad_norm 1.0033 (1.7801/0.8282)	mem 24308MB
[2025-01-18 20:41:27 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][170/312]	eta 0:01:27 lr 0.002257	time 0.5997 (0.6153)	model_time 0.5993 (0.6049)	loss 2.4511 (3.3742)	grad_norm 3.0868 (1.7626/0.8217)	mem 24308MB
[2025-01-18 20:41:33 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][180/312]	eta 0:01:21 lr 0.002256	time 0.5733 (0.6137)	model_time 0.5731 (0.6038)	loss 3.8056 (3.3882)	grad_norm 2.2931 (1.7861/0.8488)	mem 24308MB
[2025-01-18 20:41:40 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][190/312]	eta 0:01:14 lr 0.002256	time 0.5915 (0.6143)	model_time 0.5914 (0.6050)	loss 2.7516 (3.3953)	grad_norm 1.6246 (1.7950/0.8613)	mem 24308MB
[2025-01-18 20:41:46 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][200/312]	eta 0:01:08 lr 0.002255	time 0.6671 (0.6148)	model_time 0.6666 (0.6060)	loss 4.2520 (3.4085)	grad_norm 1.2039 (1.7736/0.8472)	mem 24308MB
[2025-01-18 20:41:52 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][210/312]	eta 0:01:02 lr 0.002254	time 0.6614 (0.6155)	model_time 0.6613 (0.6071)	loss 3.3508 (3.4054)	grad_norm 1.6320 (1.7595/0.8355)	mem 24308MB
[2025-01-18 20:41:58 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][220/312]	eta 0:00:56 lr 0.002254	time 0.5954 (0.6155)	model_time 0.5950 (0.6074)	loss 4.1819 (3.4043)	grad_norm 0.9992 (1.7363/0.8250)	mem 24308MB
[2025-01-18 20:42:04 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][230/312]	eta 0:00:50 lr 0.002253	time 0.5920 (0.6147)	model_time 0.5918 (0.6070)	loss 3.2750 (3.4098)	grad_norm 1.5855 (1.7328/0.8282)	mem 24308MB
[2025-01-18 20:42:10 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][240/312]	eta 0:00:44 lr 0.002252	time 0.6024 (0.6146)	model_time 0.6019 (0.6071)	loss 3.7583 (3.4185)	grad_norm 2.0627 (1.7334/0.8148)	mem 24308MB
[2025-01-18 20:42:16 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][250/312]	eta 0:00:38 lr 0.002252	time 0.6045 (0.6140)	model_time 0.6044 (0.6068)	loss 3.8102 (3.4041)	grad_norm 2.5798 (1.7390/0.8113)	mem 24308MB
[2025-01-18 20:42:22 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][260/312]	eta 0:00:31 lr 0.002251	time 0.5723 (0.6134)	model_time 0.5719 (0.6065)	loss 2.8266 (3.4075)	grad_norm 0.8460 (1.7297/0.8079)	mem 24308MB
[2025-01-18 20:42:28 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][270/312]	eta 0:00:25 lr 0.002250	time 0.6006 (0.6132)	model_time 0.6005 (0.6065)	loss 3.7890 (3.4043)	grad_norm 1.7420 (1.7126/0.8001)	mem 24308MB
[2025-01-18 20:42:34 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][280/312]	eta 0:00:19 lr 0.002250	time 0.6016 (0.6131)	model_time 0.6014 (0.6066)	loss 3.7315 (3.4034)	grad_norm 3.1529 (1.7263/0.8056)	mem 24308MB
[2025-01-18 20:42:41 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][290/312]	eta 0:00:13 lr 0.002249	time 0.6924 (0.6128)	model_time 0.6923 (0.6066)	loss 3.4340 (3.4083)	grad_norm 1.5655 (1.7289/0.7963)	mem 24308MB
[2025-01-18 20:42:46 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][300/312]	eta 0:00:07 lr 0.002248	time 0.5679 (0.6118)	model_time 0.5678 (0.6057)	loss 3.6044 (3.4036)	grad_norm 1.8027 (1.7337/0.7928)	mem 24308MB
[2025-01-18 20:42:52 internimage_s_1k_224] (main.py 510): INFO Train: [138/300][310/312]	eta 0:00:01 lr 0.002248	time 0.6723 (0.6118)	model_time 0.6722 (0.6059)	loss 3.7540 (3.4018)	grad_norm 2.5158 (1.7594/0.7975)	mem 24308MB
[2025-01-18 20:42:53 internimage_s_1k_224] (main.py 519): INFO EPOCH 138 training takes 0:03:10
[2025-01-18 20:42:53 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_138.pth saving......
[2025-01-18 20:42:55 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_138.pth saved !!!
[2025-01-18 20:43:02 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.150 (7.150)	Loss 0.8236 (0.8236)	Acc@1 82.471 (82.471)	Acc@5 96.606 (96.606)	Mem 24308MB
[2025-01-18 20:43:06 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.996)	Loss 1.1731 (0.9812)	Acc@1 73.682 (78.944)	Acc@5 92.456 (94.740)	Mem 24308MB
[2025-01-18 20:43:06 internimage_s_1k_224] (main.py 575): INFO [Epoch:138] * Acc@1 78.903 Acc@5 94.800
[2025-01-18 20:43:06 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.9%
[2025-01-18 20:43:06 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 20:43:08 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 20:43:08 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.90%
[2025-01-18 20:43:16 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.672 (7.672)	Loss 0.7196 (0.7196)	Acc@1 83.032 (83.032)	Acc@5 97.119 (97.119)	Mem 24308MB
[2025-01-18 20:43:19 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.998)	Loss 1.0615 (0.8631)	Acc@1 73.901 (79.479)	Acc@5 92.798 (95.040)	Mem 24308MB
[2025-01-18 20:43:19 internimage_s_1k_224] (main.py 575): INFO [Epoch:138] * Acc@1 79.351 Acc@5 95.068
[2025-01-18 20:43:19 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.4%
[2025-01-18 20:43:19 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 20:43:22 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 20:43:22 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 79.35%
[2025-01-18 20:43:24 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][0/312]	eta 0:10:53 lr 0.002248	time 2.0947 (2.0947)	model_time 0.5983 (0.5983)	loss 4.0136 (4.0136)	grad_norm 3.5502 (3.5502/0.0000)	mem 24308MB
[2025-01-18 20:43:31 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][10/312]	eta 0:03:54 lr 0.002247	time 0.5830 (0.7769)	model_time 0.5828 (0.6406)	loss 3.7420 (3.3375)	grad_norm 1.3046 (2.1628/0.8589)	mem 24308MB
[2025-01-18 20:43:37 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][20/312]	eta 0:03:26 lr 0.002246	time 0.6689 (0.7057)	model_time 0.6685 (0.6342)	loss 2.7007 (3.4524)	grad_norm 1.1737 (1.8374/0.7344)	mem 24308MB
[2025-01-18 20:43:43 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][30/312]	eta 0:03:09 lr 0.002246	time 0.5812 (0.6727)	model_time 0.5810 (0.6242)	loss 3.5532 (3.3968)	grad_norm 1.5658 (1.6561/0.6697)	mem 24308MB
[2025-01-18 20:43:49 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][40/312]	eta 0:02:58 lr 0.002245	time 0.6285 (0.6571)	model_time 0.6283 (0.6203)	loss 3.3008 (3.3886)	grad_norm 1.4739 (1.7422/0.7436)	mem 24308MB
[2025-01-18 20:43:55 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][50/312]	eta 0:02:50 lr 0.002244	time 0.7311 (0.6491)	model_time 0.7309 (0.6194)	loss 3.7035 (3.3926)	grad_norm 0.9194 (1.6530/0.7065)	mem 24308MB
[2025-01-18 20:44:01 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][60/312]	eta 0:02:41 lr 0.002244	time 0.5738 (0.6401)	model_time 0.5736 (0.6153)	loss 3.5726 (3.4145)	grad_norm 2.0892 (1.6844/0.6731)	mem 24308MB
[2025-01-18 20:44:07 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][70/312]	eta 0:02:33 lr 0.002243	time 0.5844 (0.6329)	model_time 0.5840 (0.6115)	loss 3.7099 (3.4124)	grad_norm 1.2782 (1.6284/0.6467)	mem 24308MB
[2025-01-18 20:44:13 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][80/312]	eta 0:02:26 lr 0.002242	time 0.5965 (0.6294)	model_time 0.5960 (0.6106)	loss 2.8603 (3.4015)	grad_norm 1.4900 (1.5931/0.6190)	mem 24308MB
[2025-01-18 20:44:19 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][90/312]	eta 0:02:19 lr 0.002242	time 0.6820 (0.6279)	model_time 0.6816 (0.6111)	loss 3.4938 (3.4178)	grad_norm 1.2274 (1.6292/0.6075)	mem 24308MB
[2025-01-18 20:44:25 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][100/312]	eta 0:02:12 lr 0.002241	time 0.5980 (0.6239)	model_time 0.5977 (0.6087)	loss 4.2543 (3.4117)	grad_norm 1.9034 (1.6257/0.5919)	mem 24308MB
[2025-01-18 20:44:31 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][110/312]	eta 0:02:05 lr 0.002240	time 0.5889 (0.6215)	model_time 0.5884 (0.6077)	loss 3.3410 (3.4105)	grad_norm 1.7324 (1.5915/0.5818)	mem 24308MB
[2025-01-18 20:44:37 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][120/312]	eta 0:01:59 lr 0.002240	time 0.5729 (0.6210)	model_time 0.5725 (0.6083)	loss 3.6366 (3.3898)	grad_norm 1.5904 (1.6116/0.5925)	mem 24308MB
[2025-01-18 20:44:43 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][130/312]	eta 0:01:53 lr 0.002239	time 0.5837 (0.6215)	model_time 0.5836 (0.6097)	loss 2.5657 (3.3655)	grad_norm 1.9389 (1.6137/0.5766)	mem 24308MB
[2025-01-18 20:44:50 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][140/312]	eta 0:01:46 lr 0.002238	time 0.6538 (0.6210)	model_time 0.6534 (0.6101)	loss 3.2189 (3.3679)	grad_norm 1.8220 (1.6669/0.6632)	mem 24308MB
[2025-01-18 20:44:56 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][150/312]	eta 0:01:40 lr 0.002238	time 0.6696 (0.6207)	model_time 0.6694 (0.6104)	loss 2.3378 (3.3539)	grad_norm 0.9467 (1.6652/0.6505)	mem 24308MB
[2025-01-18 20:45:02 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][160/312]	eta 0:01:34 lr 0.002237	time 0.5799 (0.6189)	model_time 0.5795 (0.6092)	loss 2.5421 (3.3580)	grad_norm 1.1833 (1.6779/0.6613)	mem 24308MB
[2025-01-18 20:45:08 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][170/312]	eta 0:01:27 lr 0.002236	time 0.5877 (0.6182)	model_time 0.5872 (0.6090)	loss 3.8147 (3.3556)	grad_norm 3.3560 (1.6826/0.6685)	mem 24308MB
[2025-01-18 20:45:14 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][180/312]	eta 0:01:21 lr 0.002236	time 0.6013 (0.6181)	model_time 0.6011 (0.6095)	loss 3.5639 (3.3617)	grad_norm 1.9881 (1.7050/0.6903)	mem 24308MB
[2025-01-18 20:45:20 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][190/312]	eta 0:01:15 lr 0.002235	time 0.5900 (0.6166)	model_time 0.5896 (0.6085)	loss 3.0377 (3.3643)	grad_norm 1.5768 (1.7087/0.6846)	mem 24308MB
[2025-01-18 20:45:26 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][200/312]	eta 0:01:08 lr 0.002234	time 0.5769 (0.6159)	model_time 0.5765 (0.6081)	loss 3.5996 (3.3598)	grad_norm 2.5461 (1.7019/0.6770)	mem 24308MB
[2025-01-18 20:45:32 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][210/312]	eta 0:01:02 lr 0.002234	time 0.6707 (0.6156)	model_time 0.6705 (0.6082)	loss 3.0444 (3.3492)	grad_norm 2.1543 (1.6959/0.6719)	mem 24308MB
[2025-01-18 20:45:38 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][220/312]	eta 0:00:56 lr 0.002233	time 0.6025 (0.6145)	model_time 0.6024 (0.6074)	loss 3.5041 (3.3480)	grad_norm 0.9101 (1.6930/0.6748)	mem 24308MB
[2025-01-18 20:45:44 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][230/312]	eta 0:00:50 lr 0.002232	time 0.5743 (0.6139)	model_time 0.5738 (0.6071)	loss 3.7251 (3.3532)	grad_norm 1.2397 (1.6957/0.6747)	mem 24308MB
[2025-01-18 20:45:50 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][240/312]	eta 0:00:44 lr 0.002232	time 0.5874 (0.6139)	model_time 0.5872 (0.6073)	loss 4.0798 (3.3556)	grad_norm 1.2137 (1.7053/0.6714)	mem 24308MB
[2025-01-18 20:45:56 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][250/312]	eta 0:00:38 lr 0.002231	time 0.6572 (0.6152)	model_time 0.6568 (0.6089)	loss 3.2482 (3.3519)	grad_norm 1.9982 (1.7208/0.6858)	mem 24308MB
[2025-01-18 20:46:03 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][260/312]	eta 0:00:32 lr 0.002230	time 0.5908 (0.6157)	model_time 0.5903 (0.6096)	loss 3.7005 (3.3474)	grad_norm 2.6043 (1.7284/0.6847)	mem 24308MB
[2025-01-18 20:46:09 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][270/312]	eta 0:00:25 lr 0.002230	time 0.6546 (0.6158)	model_time 0.6545 (0.6099)	loss 2.2660 (3.3410)	grad_norm 2.4881 (1.7421/0.6983)	mem 24308MB
[2025-01-18 20:46:15 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][280/312]	eta 0:00:19 lr 0.002229	time 0.6009 (0.6151)	model_time 0.6005 (0.6094)	loss 2.9307 (3.3513)	grad_norm 0.9035 (1.7343/0.6997)	mem 24308MB
[2025-01-18 20:46:21 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][290/312]	eta 0:00:13 lr 0.002228	time 0.5893 (0.6146)	model_time 0.5892 (0.6091)	loss 3.2428 (3.3481)	grad_norm 1.9592 (1.7278/0.6944)	mem 24308MB
[2025-01-18 20:46:27 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][300/312]	eta 0:00:07 lr 0.002228	time 0.5744 (0.6143)	model_time 0.5743 (0.6090)	loss 3.2344 (3.3537)	grad_norm 1.4259 (1.7312/0.6866)	mem 24308MB
[2025-01-18 20:46:33 internimage_s_1k_224] (main.py 510): INFO Train: [139/300][310/312]	eta 0:00:01 lr 0.002227	time 0.5715 (0.6129)	model_time 0.5714 (0.6077)	loss 3.3243 (3.3525)	grad_norm 1.3239 (1.7147/0.6765)	mem 24308MB
[2025-01-18 20:46:33 internimage_s_1k_224] (main.py 519): INFO EPOCH 139 training takes 0:03:11
[2025-01-18 20:46:33 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_139.pth saving......
[2025-01-18 20:46:35 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_139.pth saved !!!
[2025-01-18 20:46:43 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.518 (7.518)	Loss 0.8592 (0.8592)	Acc@1 82.373 (82.373)	Acc@5 96.606 (96.606)	Mem 24308MB
[2025-01-18 20:46:46 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.989)	Loss 1.1468 (0.9810)	Acc@1 74.194 (78.764)	Acc@5 92.920 (94.749)	Mem 24308MB
[2025-01-18 20:46:46 internimage_s_1k_224] (main.py 575): INFO [Epoch:139] * Acc@1 78.665 Acc@5 94.796
[2025-01-18 20:46:46 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.7%
[2025-01-18 20:46:46 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.90%
[2025-01-18 20:46:55 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.421 (8.421)	Loss 0.7187 (0.7187)	Acc@1 83.081 (83.081)	Acc@5 97.095 (97.095)	Mem 24308MB
[2025-01-18 20:46:59 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.160)	Loss 1.0587 (0.8615)	Acc@1 73.901 (79.523)	Acc@5 92.822 (95.057)	Mem 24308MB
[2025-01-18 20:46:59 internimage_s_1k_224] (main.py 575): INFO [Epoch:139] * Acc@1 79.399 Acc@5 95.078
[2025-01-18 20:46:59 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.4%
[2025-01-18 20:46:59 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 20:47:02 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 20:47:02 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 79.40%
[2025-01-18 20:47:04 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][0/312]	eta 0:13:06 lr 0.002227	time 2.5210 (2.5210)	model_time 0.6039 (0.6039)	loss 2.9084 (2.9084)	grad_norm 1.2549 (1.2549/0.0000)	mem 24308MB
[2025-01-18 20:47:10 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][10/312]	eta 0:03:58 lr 0.002226	time 0.6233 (0.7893)	model_time 0.6227 (0.6147)	loss 3.3456 (3.5946)	grad_norm 1.6493 (1.3134/0.4308)	mem 24308MB
[2025-01-18 20:47:16 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][20/312]	eta 0:03:24 lr 0.002226	time 0.5956 (0.7009)	model_time 0.5954 (0.6093)	loss 2.8935 (3.5333)	grad_norm 3.7879 (1.5060/0.6326)	mem 24308MB
[2025-01-18 20:47:22 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][30/312]	eta 0:03:07 lr 0.002225	time 0.6043 (0.6664)	model_time 0.6041 (0.6043)	loss 3.4620 (3.4593)	grad_norm 1.3277 (1.6095/0.7162)	mem 24308MB
[2025-01-18 20:47:28 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][40/312]	eta 0:02:56 lr 0.002224	time 0.6447 (0.6502)	model_time 0.6442 (0.6031)	loss 3.8339 (3.5037)	grad_norm 3.8221 (1.7999/0.8881)	mem 24308MB
[2025-01-18 20:47:34 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][50/312]	eta 0:02:48 lr 0.002224	time 0.5881 (0.6439)	model_time 0.5879 (0.6060)	loss 4.0454 (3.4496)	grad_norm 1.2593 (1.7675/0.8498)	mem 24308MB
[2025-01-18 20:47:41 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][60/312]	eta 0:02:41 lr 0.002223	time 0.6835 (0.6416)	model_time 0.6830 (0.6098)	loss 3.7046 (3.4117)	grad_norm 1.7370 (1.8123/0.8405)	mem 24308MB
[2025-01-18 20:47:47 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][70/312]	eta 0:02:34 lr 0.002222	time 0.6875 (0.6388)	model_time 0.6874 (0.6114)	loss 3.1554 (3.4058)	grad_norm 2.0625 (1.9027/0.9156)	mem 24308MB
[2025-01-18 20:47:53 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][80/312]	eta 0:02:27 lr 0.002222	time 0.5735 (0.6349)	model_time 0.5731 (0.6109)	loss 3.4689 (3.4105)	grad_norm 1.4396 (1.8670/0.8856)	mem 24308MB
[2025-01-18 20:47:59 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][90/312]	eta 0:02:20 lr 0.002221	time 0.5725 (0.6312)	model_time 0.5724 (0.6098)	loss 3.7094 (3.3738)	grad_norm 2.4281 (1.8288/0.8537)	mem 24308MB
[2025-01-18 20:48:05 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][100/312]	eta 0:02:13 lr 0.002220	time 0.6603 (0.6285)	model_time 0.6599 (0.6092)	loss 3.3583 (3.3637)	grad_norm 2.0783 (1.8171/0.8312)	mem 24308MB
[2025-01-18 20:48:11 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][110/312]	eta 0:02:06 lr 0.002220	time 0.6195 (0.6266)	model_time 0.6190 (0.6089)	loss 3.7505 (3.3617)	grad_norm 2.4706 (1.8006/0.8204)	mem 24308MB
[2025-01-18 20:48:17 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][120/312]	eta 0:01:59 lr 0.002219	time 0.6059 (0.6237)	model_time 0.6057 (0.6075)	loss 2.6852 (3.3361)	grad_norm 2.3107 (1.8136/0.8220)	mem 24308MB
[2025-01-18 20:48:23 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][130/312]	eta 0:01:53 lr 0.002218	time 0.5789 (0.6225)	model_time 0.5785 (0.6075)	loss 2.9422 (3.3252)	grad_norm 2.1081 (1.7992/0.8040)	mem 24308MB
[2025-01-18 20:48:29 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][140/312]	eta 0:01:46 lr 0.002218	time 0.5873 (0.6208)	model_time 0.5868 (0.6068)	loss 3.7708 (3.3469)	grad_norm 1.6871 (1.8348/0.8700)	mem 24308MB
[2025-01-18 20:48:35 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][150/312]	eta 0:01:40 lr 0.002217	time 0.5851 (0.6192)	model_time 0.5847 (0.6060)	loss 3.8036 (3.3561)	grad_norm 1.9784 (1.8145/0.8499)	mem 24308MB
[2025-01-18 20:48:41 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][160/312]	eta 0:01:33 lr 0.002216	time 0.6763 (0.6179)	model_time 0.6761 (0.6056)	loss 4.0102 (3.3473)	grad_norm 1.2837 (1.7967/0.8300)	mem 24308MB
[2025-01-18 20:48:47 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][170/312]	eta 0:01:27 lr 0.002216	time 0.5822 (0.6180)	model_time 0.5820 (0.6063)	loss 3.6071 (3.3534)	grad_norm 2.8164 (1.7924/0.8164)	mem 24308MB
[2025-01-18 20:48:54 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][180/312]	eta 0:01:21 lr 0.002215	time 0.7985 (0.6190)	model_time 0.7981 (0.6080)	loss 4.2082 (3.3523)	grad_norm 1.8506 (1.7910/0.8045)	mem 24308MB
[2025-01-18 20:49:00 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][190/312]	eta 0:01:15 lr 0.002214	time 0.6873 (0.6195)	model_time 0.6868 (0.6091)	loss 3.0585 (3.3448)	grad_norm 1.2001 (1.7614/0.7947)	mem 24308MB
[2025-01-18 20:49:06 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][200/312]	eta 0:01:09 lr 0.002214	time 0.5742 (0.6190)	model_time 0.5740 (0.6090)	loss 2.6849 (3.3443)	grad_norm 1.2992 (1.7651/0.7915)	mem 24308MB
[2025-01-18 20:49:12 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][210/312]	eta 0:01:03 lr 0.002213	time 0.5726 (0.6180)	model_time 0.5724 (0.6085)	loss 2.4568 (3.3382)	grad_norm 0.9951 (1.7726/0.7815)	mem 24308MB
[2025-01-18 20:49:18 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][220/312]	eta 0:00:56 lr 0.002212	time 0.6642 (0.6180)	model_time 0.6637 (0.6089)	loss 2.5459 (3.3357)	grad_norm 1.3657 (1.7885/0.8090)	mem 24308MB
[2025-01-18 20:49:24 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][230/312]	eta 0:00:50 lr 0.002212	time 0.5729 (0.6175)	model_time 0.5724 (0.6088)	loss 3.5770 (3.3436)	grad_norm 1.4431 (1.7673/0.7999)	mem 24308MB
[2025-01-18 20:49:30 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][240/312]	eta 0:00:44 lr 0.002211	time 0.5787 (0.6164)	model_time 0.5783 (0.6080)	loss 3.5076 (3.3481)	grad_norm 1.0087 (1.7760/0.8099)	mem 24308MB
[2025-01-18 20:49:36 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][250/312]	eta 0:00:38 lr 0.002210	time 0.5857 (0.6158)	model_time 0.5855 (0.6077)	loss 3.1601 (3.3519)	grad_norm 1.2239 (1.7662/0.8109)	mem 24308MB
[2025-01-18 20:49:42 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][260/312]	eta 0:00:31 lr 0.002210	time 0.5823 (0.6149)	model_time 0.5822 (0.6071)	loss 2.8193 (3.3485)	grad_norm 3.1862 (1.7838/0.8104)	mem 24308MB
[2025-01-18 20:49:48 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][270/312]	eta 0:00:25 lr 0.002209	time 0.5745 (0.6142)	model_time 0.5740 (0.6067)	loss 3.2169 (3.3473)	grad_norm 3.0665 (1.7898/0.8020)	mem 24308MB
[2025-01-18 20:49:54 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][280/312]	eta 0:00:19 lr 0.002208	time 0.6614 (0.6136)	model_time 0.6612 (0.6063)	loss 3.3600 (3.3368)	grad_norm 1.2889 (1.7790/0.8009)	mem 24308MB
[2025-01-18 20:50:00 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][290/312]	eta 0:00:13 lr 0.002208	time 0.5729 (0.6132)	model_time 0.5727 (0.6062)	loss 4.1781 (3.3440)	grad_norm 0.8724 (1.7539/0.7993)	mem 24308MB
[2025-01-18 20:50:06 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][300/312]	eta 0:00:07 lr 0.002207	time 0.6500 (0.6141)	model_time 0.6498 (0.6073)	loss 3.9769 (3.3475)	grad_norm 2.5682 (1.7463/0.7945)	mem 24308MB
[2025-01-18 20:50:13 internimage_s_1k_224] (main.py 510): INFO Train: [140/300][310/312]	eta 0:00:01 lr 0.002206	time 0.6402 (0.6140)	model_time 0.6401 (0.6074)	loss 3.4824 (3.3459)	grad_norm 1.8256 (1.7636/0.7942)	mem 24308MB
[2025-01-18 20:50:13 internimage_s_1k_224] (main.py 519): INFO EPOCH 140 training takes 0:03:11
[2025-01-18 20:50:13 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_140.pth saving......
[2025-01-18 20:50:15 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_140.pth saved !!!
[2025-01-18 20:50:22 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.133 (7.133)	Loss 0.8561 (0.8561)	Acc@1 82.300 (82.300)	Acc@5 96.631 (96.631)	Mem 24308MB
[2025-01-18 20:50:26 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.968)	Loss 1.1441 (0.9896)	Acc@1 74.146 (78.944)	Acc@5 93.262 (94.824)	Mem 24308MB
[2025-01-18 20:50:26 internimage_s_1k_224] (main.py 575): INFO [Epoch:140] * Acc@1 78.833 Acc@5 94.830
[2025-01-18 20:50:26 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.8%
[2025-01-18 20:50:26 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.90%
[2025-01-18 20:50:34 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.384 (8.384)	Loss 0.7179 (0.7179)	Acc@1 83.081 (83.081)	Acc@5 97.168 (97.168)	Mem 24308MB
[2025-01-18 20:50:39 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.142)	Loss 1.0558 (0.8600)	Acc@1 74.097 (79.610)	Acc@5 92.798 (95.084)	Mem 24308MB
[2025-01-18 20:50:39 internimage_s_1k_224] (main.py 575): INFO [Epoch:140] * Acc@1 79.477 Acc@5 95.098
[2025-01-18 20:50:39 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.5%
[2025-01-18 20:50:39 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 20:50:41 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 20:50:41 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 79.48%
[2025-01-18 20:50:43 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][0/312]	eta 0:11:34 lr 0.002206	time 2.2250 (2.2250)	model_time 0.5847 (0.5847)	loss 3.6902 (3.6902)	grad_norm 1.5501 (1.5501/0.0000)	mem 24308MB
[2025-01-18 20:50:49 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][10/312]	eta 0:03:47 lr 0.002206	time 0.5825 (0.7549)	model_time 0.5823 (0.6054)	loss 4.1575 (3.5268)	grad_norm 1.2643 (1.4477/0.3611)	mem 24308MB
[2025-01-18 20:50:55 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][20/312]	eta 0:03:18 lr 0.002205	time 0.5938 (0.6801)	model_time 0.5936 (0.6016)	loss 3.0243 (3.3859)	grad_norm 2.5148 (1.6930/0.6689)	mem 24308MB
[2025-01-18 20:51:01 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][30/312]	eta 0:03:05 lr 0.002204	time 0.5802 (0.6571)	model_time 0.5801 (0.6039)	loss 3.2216 (3.2929)	grad_norm 1.5569 (1.7016/0.6366)	mem 24308MB
[2025-01-18 20:51:07 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][40/312]	eta 0:02:54 lr 0.002204	time 0.5815 (0.6430)	model_time 0.5813 (0.6026)	loss 4.2132 (3.3585)	grad_norm 1.6703 (1.7018/0.6903)	mem 24308MB
[2025-01-18 20:51:13 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][50/312]	eta 0:02:45 lr 0.002203	time 0.6135 (0.6332)	model_time 0.6020 (0.6005)	loss 3.9403 (3.4169)	grad_norm 4.4615 (1.8577/0.8396)	mem 24308MB
[2025-01-18 20:51:19 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][60/312]	eta 0:02:38 lr 0.002202	time 0.5920 (0.6292)	model_time 0.5917 (0.6017)	loss 4.0991 (3.4170)	grad_norm 1.9936 (1.9844/0.8832)	mem 24308MB
[2025-01-18 20:51:26 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][70/312]	eta 0:02:31 lr 0.002202	time 0.5823 (0.6258)	model_time 0.5822 (0.6022)	loss 3.4423 (3.4020)	grad_norm 1.2819 (1.9278/0.8405)	mem 24308MB
[2025-01-18 20:51:32 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][80/312]	eta 0:02:24 lr 0.002201	time 0.5831 (0.6231)	model_time 0.5829 (0.6024)	loss 3.4552 (3.4017)	grad_norm 1.1418 (1.8461/0.8270)	mem 24308MB
[2025-01-18 20:51:38 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][90/312]	eta 0:02:17 lr 0.002200	time 0.5779 (0.6206)	model_time 0.5777 (0.6021)	loss 4.0292 (3.4050)	grad_norm 1.3749 (1.8105/0.8095)	mem 24308MB
[2025-01-18 20:51:44 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][100/312]	eta 0:02:11 lr 0.002200	time 0.6326 (0.6204)	model_time 0.6324 (0.6037)	loss 3.7476 (3.3813)	grad_norm 1.4385 (1.7891/0.7812)	mem 24308MB
[2025-01-18 20:51:50 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][110/312]	eta 0:02:05 lr 0.002199	time 0.5808 (0.6199)	model_time 0.5807 (0.6047)	loss 3.0620 (3.3809)	grad_norm 1.9209 (1.7450/0.7634)	mem 24308MB
[2025-01-18 20:51:56 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][120/312]	eta 0:01:59 lr 0.002198	time 0.5878 (0.6220)	model_time 0.5876 (0.6080)	loss 3.3162 (3.3977)	grad_norm 2.9453 (1.8169/0.8586)	mem 24308MB
[2025-01-18 20:52:03 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][130/312]	eta 0:01:53 lr 0.002198	time 0.5792 (0.6221)	model_time 0.5790 (0.6091)	loss 3.1350 (3.4056)	grad_norm 1.2393 (1.8163/0.8617)	mem 24308MB
[2025-01-18 20:52:09 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][140/312]	eta 0:01:46 lr 0.002197	time 0.5791 (0.6210)	model_time 0.5790 (0.6090)	loss 3.7486 (3.3962)	grad_norm 1.6792 (1.8181/0.8428)	mem 24308MB
[2025-01-18 20:52:15 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][150/312]	eta 0:01:40 lr 0.002196	time 0.5804 (0.6202)	model_time 0.5802 (0.6090)	loss 3.4979 (3.3881)	grad_norm 1.9491 (1.8429/0.8508)	mem 24308MB
[2025-01-18 20:52:21 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][160/312]	eta 0:01:34 lr 0.002196	time 0.5779 (0.6195)	model_time 0.5777 (0.6090)	loss 3.1392 (3.3878)	grad_norm 1.0899 (1.8370/0.8337)	mem 24308MB
[2025-01-18 20:52:27 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][170/312]	eta 0:01:27 lr 0.002195	time 0.5731 (0.6179)	model_time 0.5729 (0.6079)	loss 3.2406 (3.3988)	grad_norm 1.0482 (1.8207/0.8172)	mem 24308MB
[2025-01-18 20:52:33 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][180/312]	eta 0:01:21 lr 0.002194	time 0.5775 (0.6171)	model_time 0.5771 (0.6076)	loss 3.9418 (3.4039)	grad_norm 2.1394 (1.8144/0.8026)	mem 24308MB
[2025-01-18 20:52:39 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][190/312]	eta 0:01:15 lr 0.002194	time 0.5843 (0.6167)	model_time 0.5842 (0.6077)	loss 3.4763 (3.4058)	grad_norm 1.4077 (1.8130/0.7909)	mem 24308MB
[2025-01-18 20:52:45 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][200/312]	eta 0:01:08 lr 0.002193	time 0.5969 (0.6159)	model_time 0.5964 (0.6073)	loss 3.8743 (3.4185)	grad_norm 1.3345 (1.7929/0.7779)	mem 24308MB
[2025-01-18 20:52:51 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][210/312]	eta 0:01:02 lr 0.002192	time 0.6645 (0.6149)	model_time 0.6643 (0.6068)	loss 2.4183 (3.4305)	grad_norm 2.9210 (1.7969/0.7657)	mem 24308MB
[2025-01-18 20:52:57 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][220/312]	eta 0:00:56 lr 0.002192	time 0.5899 (0.6160)	model_time 0.5894 (0.6082)	loss 2.9735 (3.4196)	grad_norm 0.8782 (1.7987/0.7667)	mem 24308MB
[2025-01-18 20:53:03 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][230/312]	eta 0:00:50 lr 0.002191	time 0.5789 (0.6154)	model_time 0.5784 (0.6079)	loss 3.2789 (3.4181)	grad_norm 1.9162 (1.8014/0.7692)	mem 24308MB
[2025-01-18 20:53:10 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][240/312]	eta 0:00:44 lr 0.002190	time 0.5906 (0.6159)	model_time 0.5904 (0.6087)	loss 3.5408 (3.4157)	grad_norm 1.3729 (1.7995/0.7644)	mem 24308MB
[2025-01-18 20:53:16 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][250/312]	eta 0:00:38 lr 0.002190	time 0.5717 (0.6155)	model_time 0.5716 (0.6086)	loss 3.5526 (3.4238)	grad_norm 1.8898 (1.7817/0.7564)	mem 24308MB
[2025-01-18 20:53:22 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][260/312]	eta 0:00:31 lr 0.002189	time 0.5732 (0.6146)	model_time 0.5728 (0.6080)	loss 3.1625 (3.4232)	grad_norm 1.1412 (1.7686/0.7485)	mem 24308MB
[2025-01-18 20:53:28 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][270/312]	eta 0:00:25 lr 0.002188	time 0.5773 (0.6141)	model_time 0.5768 (0.6077)	loss 3.0364 (3.4223)	grad_norm 1.3201 (1.7613/0.7453)	mem 24308MB
[2025-01-18 20:53:34 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][280/312]	eta 0:00:19 lr 0.002188	time 0.5844 (0.6140)	model_time 0.5842 (0.6078)	loss 3.4522 (3.4235)	grad_norm 1.8608 (1.7590/0.7411)	mem 24308MB
[2025-01-18 20:53:39 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][290/312]	eta 0:00:13 lr 0.002187	time 0.5790 (0.6130)	model_time 0.5788 (0.6069)	loss 3.4386 (3.4140)	grad_norm 1.2428 (1.7757/0.7484)	mem 24308MB
[2025-01-18 20:53:45 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][300/312]	eta 0:00:07 lr 0.002186	time 0.5659 (0.6125)	model_time 0.5658 (0.6067)	loss 3.3762 (3.4085)	grad_norm 1.2267 (1.7742/0.7418)	mem 24308MB
[2025-01-18 20:53:51 internimage_s_1k_224] (main.py 510): INFO Train: [141/300][310/312]	eta 0:00:01 lr 0.002186	time 0.5663 (0.6115)	model_time 0.5661 (0.6059)	loss 3.4571 (3.4127)	grad_norm 1.1878 (1.7731/0.7416)	mem 24308MB
[2025-01-18 20:53:52 internimage_s_1k_224] (main.py 519): INFO EPOCH 141 training takes 0:03:10
[2025-01-18 20:53:52 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_141.pth saving......
[2025-01-18 20:53:54 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_141.pth saved !!!
[2025-01-18 20:54:01 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 6.970 (6.970)	Loss 0.8318 (0.8318)	Acc@1 82.275 (82.275)	Acc@5 96.875 (96.875)	Mem 24308MB
[2025-01-18 20:54:04 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.930)	Loss 1.1745 (0.9921)	Acc@1 74.121 (78.960)	Acc@5 92.676 (94.720)	Mem 24308MB
[2025-01-18 20:54:04 internimage_s_1k_224] (main.py 575): INFO [Epoch:141] * Acc@1 78.879 Acc@5 94.738
[2025-01-18 20:54:04 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.9%
[2025-01-18 20:54:04 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.90%
[2025-01-18 20:54:13 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.296 (8.296)	Loss 0.7171 (0.7171)	Acc@1 83.105 (83.105)	Acc@5 97.168 (97.168)	Mem 24308MB
[2025-01-18 20:54:17 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.125)	Loss 1.0529 (0.8585)	Acc@1 74.170 (79.650)	Acc@5 92.920 (95.095)	Mem 24308MB
[2025-01-18 20:54:17 internimage_s_1k_224] (main.py 575): INFO [Epoch:141] * Acc@1 79.523 Acc@5 95.106
[2025-01-18 20:54:17 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.5%
[2025-01-18 20:54:17 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 20:54:19 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 20:54:19 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 79.52%
[2025-01-18 20:54:22 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][0/312]	eta 0:11:59 lr 0.002186	time 2.3049 (2.3049)	model_time 0.5916 (0.5916)	loss 2.5731 (2.5731)	grad_norm 0.8776 (0.8776/0.0000)	mem 24308MB
[2025-01-18 20:54:28 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][10/312]	eta 0:03:45 lr 0.002185	time 0.5684 (0.7471)	model_time 0.5682 (0.5910)	loss 3.4144 (3.2288)	grad_norm 1.5748 (1.4659/0.4283)	mem 24308MB
[2025-01-18 20:54:34 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][20/312]	eta 0:03:17 lr 0.002184	time 0.6973 (0.6764)	model_time 0.6972 (0.5945)	loss 2.8649 (3.2591)	grad_norm 1.3405 (1.7897/0.8408)	mem 24308MB
[2025-01-18 20:54:40 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][30/312]	eta 0:03:06 lr 0.002184	time 0.6612 (0.6602)	model_time 0.6610 (0.6046)	loss 3.0467 (3.3412)	grad_norm 1.3624 (1.8132/0.7748)	mem 24308MB
[2025-01-18 20:54:46 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][40/312]	eta 0:02:56 lr 0.002183	time 0.5767 (0.6485)	model_time 0.5765 (0.6063)	loss 3.6627 (3.3221)	grad_norm 1.0075 (1.8727/0.8294)	mem 24308MB
[2025-01-18 20:54:52 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][50/312]	eta 0:02:49 lr 0.002182	time 0.5917 (0.6477)	model_time 0.5915 (0.6137)	loss 3.7987 (3.4017)	grad_norm 2.1325 (1.7866/0.7973)	mem 24308MB
[2025-01-18 20:54:59 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][60/312]	eta 0:02:41 lr 0.002182	time 0.6026 (0.6424)	model_time 0.6024 (0.6140)	loss 3.9102 (3.4024)	grad_norm 0.9907 (1.6866/0.7689)	mem 24308MB
[2025-01-18 20:55:05 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][70/312]	eta 0:02:33 lr 0.002181	time 0.5770 (0.6358)	model_time 0.5768 (0.6113)	loss 3.4830 (3.3797)	grad_norm 0.7007 (1.6869/0.7900)	mem 24308MB
[2025-01-18 20:55:11 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][80/312]	eta 0:02:26 lr 0.002180	time 0.5736 (0.6314)	model_time 0.5734 (0.6099)	loss 3.6340 (3.4075)	grad_norm 0.8945 (1.6478/0.7694)	mem 24308MB
[2025-01-18 20:55:17 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][90/312]	eta 0:02:19 lr 0.002180	time 0.6257 (0.6296)	model_time 0.6255 (0.6104)	loss 3.5101 (3.3990)	grad_norm 1.7066 (1.6060/0.7413)	mem 24308MB
[2025-01-18 20:55:23 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][100/312]	eta 0:02:12 lr 0.002179	time 0.6070 (0.6254)	model_time 0.6068 (0.6080)	loss 3.7740 (3.3859)	grad_norm 1.3405 (1.6441/0.7283)	mem 24308MB
[2025-01-18 20:55:29 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][110/312]	eta 0:02:06 lr 0.002178	time 0.6637 (0.6240)	model_time 0.6635 (0.6082)	loss 2.7566 (3.3462)	grad_norm 1.9727 (1.6329/0.7040)	mem 24308MB
[2025-01-18 20:55:35 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][120/312]	eta 0:01:59 lr 0.002178	time 0.5794 (0.6215)	model_time 0.5792 (0.6070)	loss 2.7358 (3.3275)	grad_norm 2.0914 (1.6326/0.6838)	mem 24308MB
[2025-01-18 20:55:41 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][130/312]	eta 0:01:52 lr 0.002177	time 0.5892 (0.6205)	model_time 0.5887 (0.6071)	loss 3.0334 (3.3291)	grad_norm 1.9445 (1.6290/0.6770)	mem 24308MB
[2025-01-18 20:55:47 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][140/312]	eta 0:01:46 lr 0.002176	time 0.5808 (0.6183)	model_time 0.5806 (0.6058)	loss 3.3964 (3.3220)	grad_norm 1.3752 (1.6524/0.6850)	mem 24308MB
[2025-01-18 20:55:53 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][150/312]	eta 0:01:40 lr 0.002176	time 0.5784 (0.6189)	model_time 0.5782 (0.6072)	loss 3.2817 (3.3044)	grad_norm 1.5115 (1.6562/0.6882)	mem 24308MB
[2025-01-18 20:55:59 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][160/312]	eta 0:01:33 lr 0.002175	time 0.6531 (0.6184)	model_time 0.6530 (0.6074)	loss 3.5047 (3.3106)	grad_norm 1.6144 (1.6576/0.6773)	mem 24308MB
[2025-01-18 20:56:05 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][170/312]	eta 0:01:28 lr 0.002174	time 0.7156 (0.6197)	model_time 0.7152 (0.6094)	loss 2.4470 (3.3067)	grad_norm 1.0358 (1.7096/0.7182)	mem 24308MB
[2025-01-18 20:56:12 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][180/312]	eta 0:01:21 lr 0.002174	time 0.6607 (0.6194)	model_time 0.6603 (0.6096)	loss 2.3079 (3.3005)	grad_norm 0.7243 (1.7149/0.7236)	mem 24308MB
[2025-01-18 20:56:18 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][190/312]	eta 0:01:15 lr 0.002173	time 0.5824 (0.6187)	model_time 0.5819 (0.6094)	loss 3.3244 (3.3100)	grad_norm 2.8237 (1.7216/0.7238)	mem 24308MB
[2025-01-18 20:56:24 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][200/312]	eta 0:01:09 lr 0.002172	time 0.5877 (0.6179)	model_time 0.5875 (0.6091)	loss 2.5580 (3.3113)	grad_norm 1.0295 (1.7345/0.7298)	mem 24308MB
[2025-01-18 20:56:30 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][210/312]	eta 0:01:03 lr 0.002172	time 0.5879 (0.6179)	model_time 0.5878 (0.6094)	loss 3.9385 (3.3072)	grad_norm 0.9336 (1.7299/0.7196)	mem 24308MB
[2025-01-18 20:56:36 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][220/312]	eta 0:00:56 lr 0.002171	time 0.5966 (0.6165)	model_time 0.5964 (0.6084)	loss 2.7489 (3.3019)	grad_norm 1.3940 (1.7180/0.7088)	mem 24308MB
[2025-01-18 20:56:42 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][230/312]	eta 0:00:50 lr 0.002170	time 0.5844 (0.6157)	model_time 0.5839 (0.6079)	loss 3.6142 (3.2939)	grad_norm 2.9439 (1.7408/0.7268)	mem 24308MB
[2025-01-18 20:56:48 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][240/312]	eta 0:00:44 lr 0.002170	time 0.5714 (0.6149)	model_time 0.5713 (0.6074)	loss 3.5624 (3.3038)	grad_norm 1.0385 (1.7303/0.7158)	mem 24308MB
[2025-01-18 20:56:54 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][250/312]	eta 0:00:38 lr 0.002169	time 0.6133 (0.6148)	model_time 0.6129 (0.6076)	loss 2.7591 (3.3027)	grad_norm 1.4055 (1.7281/0.7085)	mem 24308MB
[2025-01-18 20:57:00 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][260/312]	eta 0:00:31 lr 0.002168	time 0.5721 (0.6136)	model_time 0.5719 (0.6067)	loss 2.6439 (3.3003)	grad_norm 2.5086 (1.7272/0.7050)	mem 24308MB
[2025-01-18 20:57:06 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][270/312]	eta 0:00:25 lr 0.002168	time 0.5682 (0.6142)	model_time 0.5676 (0.6075)	loss 3.4999 (3.3044)	grad_norm 1.9231 (1.7490/0.7063)	mem 24308MB
[2025-01-18 20:57:12 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][280/312]	eta 0:00:19 lr 0.002167	time 0.6653 (0.6144)	model_time 0.6652 (0.6080)	loss 4.2719 (3.3089)	grad_norm 1.6584 (1.7481/0.7016)	mem 24308MB
[2025-01-18 20:57:18 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][290/312]	eta 0:00:13 lr 0.002166	time 0.6771 (0.6143)	model_time 0.6769 (0.6081)	loss 3.4769 (3.3144)	grad_norm 1.9574 (1.7502/0.6965)	mem 24308MB
[2025-01-18 20:57:24 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][300/312]	eta 0:00:07 lr 0.002166	time 0.6475 (0.6147)	model_time 0.6474 (0.6087)	loss 3.7633 (3.3179)	grad_norm 2.3074 (1.7499/0.6930)	mem 24308MB
[2025-01-18 20:57:30 internimage_s_1k_224] (main.py 510): INFO Train: [142/300][310/312]	eta 0:00:01 lr 0.002165	time 0.5713 (0.6137)	model_time 0.5711 (0.6079)	loss 3.6293 (3.3229)	grad_norm 2.2952 (1.7549/0.6934)	mem 24308MB
[2025-01-18 20:57:31 internimage_s_1k_224] (main.py 519): INFO EPOCH 142 training takes 0:03:11
[2025-01-18 20:57:31 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_142.pth saving......
[2025-01-18 20:57:33 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_142.pth saved !!!
[2025-01-18 20:57:40 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.646 (7.646)	Loss 0.8425 (0.8425)	Acc@1 82.373 (82.373)	Acc@5 96.802 (96.802)	Mem 24308MB
[2025-01-18 20:57:44 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.000)	Loss 1.1635 (0.9921)	Acc@1 74.365 (78.948)	Acc@5 92.700 (94.722)	Mem 24308MB
[2025-01-18 20:57:44 internimage_s_1k_224] (main.py 575): INFO [Epoch:142] * Acc@1 78.841 Acc@5 94.726
[2025-01-18 20:57:44 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.8%
[2025-01-18 20:57:44 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 78.90%
[2025-01-18 20:57:52 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.867 (7.867)	Loss 0.7165 (0.7165)	Acc@1 83.130 (83.130)	Acc@5 97.168 (97.168)	Mem 24308MB
[2025-01-18 20:57:56 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.087)	Loss 1.0501 (0.8569)	Acc@1 74.341 (79.710)	Acc@5 93.018 (95.115)	Mem 24308MB
[2025-01-18 20:57:56 internimage_s_1k_224] (main.py 575): INFO [Epoch:142] * Acc@1 79.575 Acc@5 95.128
[2025-01-18 20:57:56 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.6%
[2025-01-18 20:57:56 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 20:57:58 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 20:57:58 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 79.57%
[2025-01-18 20:58:01 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][0/312]	eta 0:12:30 lr 0.002165	time 2.4042 (2.4042)	model_time 0.6149 (0.6149)	loss 2.9888 (2.9888)	grad_norm 1.7357 (1.7357/0.0000)	mem 24308MB
[2025-01-18 20:58:07 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][10/312]	eta 0:03:53 lr 0.002164	time 0.5755 (0.7735)	model_time 0.5753 (0.6106)	loss 4.1483 (3.4281)	grad_norm 1.3805 (1.5374/0.4828)	mem 24308MB
[2025-01-18 20:58:13 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][20/312]	eta 0:03:22 lr 0.002164	time 0.5887 (0.6938)	model_time 0.5886 (0.6082)	loss 3.2235 (3.2982)	grad_norm 1.5985 (1.8573/0.7892)	mem 24308MB
[2025-01-18 20:58:19 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][30/312]	eta 0:03:06 lr 0.002163	time 0.5719 (0.6625)	model_time 0.5717 (0.6045)	loss 3.9210 (3.3738)	grad_norm 1.0429 (1.8310/0.7468)	mem 24308MB
[2025-01-18 20:58:25 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][40/312]	eta 0:02:56 lr 0.002162	time 0.5729 (0.6471)	model_time 0.5727 (0.6031)	loss 2.2134 (3.3544)	grad_norm 1.7106 (1.7959/0.6781)	mem 24308MB
[2025-01-18 20:58:31 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][50/312]	eta 0:02:46 lr 0.002162	time 0.5989 (0.6368)	model_time 0.5987 (0.6009)	loss 3.0797 (3.3618)	grad_norm 1.2674 (1.7926/0.6587)	mem 24308MB
[2025-01-18 20:58:37 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][60/312]	eta 0:02:39 lr 0.002161	time 0.5862 (0.6312)	model_time 0.5860 (0.6011)	loss 3.0504 (3.3325)	grad_norm 1.1565 (1.8089/0.6575)	mem 24308MB
[2025-01-18 20:58:43 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][70/312]	eta 0:02:31 lr 0.002160	time 0.5895 (0.6258)	model_time 0.5894 (0.6000)	loss 4.0131 (3.3402)	grad_norm 0.6439 (1.8860/0.8224)	mem 24308MB
[2025-01-18 20:58:49 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][80/312]	eta 0:02:25 lr 0.002160	time 0.5764 (0.6255)	model_time 0.5762 (0.6028)	loss 2.4970 (3.3188)	grad_norm 3.0318 (1.9620/0.8330)	mem 24308MB
[2025-01-18 20:58:55 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][90/312]	eta 0:02:18 lr 0.002159	time 0.5875 (0.6247)	model_time 0.5874 (0.6045)	loss 3.0645 (3.3411)	grad_norm 1.9565 (1.9775/0.8234)	mem 24308MB
[2025-01-18 20:59:01 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][100/312]	eta 0:02:12 lr 0.002158	time 0.6411 (0.6243)	model_time 0.6407 (0.6060)	loss 3.3746 (3.3615)	grad_norm 1.1851 (1.9172/0.8056)	mem 24308MB
[2025-01-18 20:59:08 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][110/312]	eta 0:02:06 lr 0.002158	time 0.6732 (0.6243)	model_time 0.6730 (0.6076)	loss 3.3842 (3.3753)	grad_norm 1.9680 (1.8664/0.8007)	mem 24308MB
[2025-01-18 20:59:14 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][120/312]	eta 0:01:59 lr 0.002157	time 0.6017 (0.6217)	model_time 0.6015 (0.6063)	loss 2.5809 (3.3740)	grad_norm 1.3731 (1.8353/0.7884)	mem 24308MB
[2025-01-18 20:59:20 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][130/312]	eta 0:01:53 lr 0.002156	time 0.5926 (0.6210)	model_time 0.5924 (0.6068)	loss 3.7473 (3.3790)	grad_norm 1.6148 (1.7876/0.7806)	mem 24308MB
[2025-01-18 20:59:26 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][140/312]	eta 0:01:46 lr 0.002156	time 0.5817 (0.6191)	model_time 0.5812 (0.6059)	loss 4.0272 (3.3792)	grad_norm 2.1740 (1.7831/0.7745)	mem 24308MB
[2025-01-18 20:59:32 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][150/312]	eta 0:01:40 lr 0.002155	time 0.6004 (0.6181)	model_time 0.6002 (0.6057)	loss 3.8113 (3.3680)	grad_norm 2.4540 (1.7631/0.7656)	mem 24308MB
[2025-01-18 20:59:38 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][160/312]	eta 0:01:33 lr 0.002154	time 0.5893 (0.6166)	model_time 0.5891 (0.6050)	loss 3.8716 (3.3616)	grad_norm 1.2261 (1.7560/0.7453)	mem 24308MB
[2025-01-18 20:59:44 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][170/312]	eta 0:01:27 lr 0.002154	time 0.5855 (0.6157)	model_time 0.5850 (0.6047)	loss 3.6622 (3.3644)	grad_norm 3.2588 (1.7647/0.7421)	mem 24308MB
[2025-01-18 20:59:50 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][180/312]	eta 0:01:21 lr 0.002153	time 0.5934 (0.6154)	model_time 0.5930 (0.6050)	loss 3.4988 (3.3650)	grad_norm 1.9910 (1.7773/0.7553)	mem 24308MB
[2025-01-18 20:59:56 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][190/312]	eta 0:01:14 lr 0.002152	time 0.5987 (0.6141)	model_time 0.5985 (0.6042)	loss 2.4965 (3.3693)	grad_norm 1.5418 (1.7645/0.7455)	mem 24308MB
[2025-01-18 21:00:02 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][200/312]	eta 0:01:08 lr 0.002152	time 0.5870 (0.6146)	model_time 0.5869 (0.6052)	loss 3.4020 (3.3588)	grad_norm 1.2803 (1.7599/0.7377)	mem 24308MB
[2025-01-18 21:00:08 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][210/312]	eta 0:01:02 lr 0.002151	time 0.6694 (0.6143)	model_time 0.6690 (0.6054)	loss 3.5433 (3.3542)	grad_norm 1.0065 (1.7628/0.7338)	mem 24308MB
[2025-01-18 21:00:14 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][220/312]	eta 0:00:56 lr 0.002150	time 0.6807 (0.6150)	model_time 0.6802 (0.6064)	loss 2.3609 (3.3513)	grad_norm 1.3006 (1.7594/0.7282)	mem 24308MB
[2025-01-18 21:00:21 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][230/312]	eta 0:00:50 lr 0.002150	time 0.6631 (0.6159)	model_time 0.6627 (0.6077)	loss 3.5698 (3.3477)	grad_norm 1.7777 (1.7661/0.7299)	mem 24308MB
[2025-01-18 21:00:27 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][240/312]	eta 0:00:44 lr 0.002149	time 0.5769 (0.6155)	model_time 0.5765 (0.6076)	loss 3.0657 (3.3417)	grad_norm 1.2743 (1.7623/0.7236)	mem 24308MB
[2025-01-18 21:00:33 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][250/312]	eta 0:00:38 lr 0.002148	time 0.6881 (0.6151)	model_time 0.6879 (0.6075)	loss 2.3579 (3.3340)	grad_norm 0.9766 (1.7610/0.7234)	mem 24308MB
[2025-01-18 21:00:39 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][260/312]	eta 0:00:31 lr 0.002148	time 0.5783 (0.6146)	model_time 0.5778 (0.6072)	loss 3.5982 (3.3354)	grad_norm 1.0387 (1.7534/0.7145)	mem 24308MB
[2025-01-18 21:00:45 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][270/312]	eta 0:00:25 lr 0.002147	time 0.6186 (0.6142)	model_time 0.6181 (0.6072)	loss 2.9896 (3.3369)	grad_norm 2.8112 (1.7527/0.7103)	mem 24308MB
[2025-01-18 21:00:51 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][280/312]	eta 0:00:19 lr 0.002146	time 0.6658 (0.6139)	model_time 0.6657 (0.6071)	loss 2.1917 (3.3387)	grad_norm 1.9454 (1.7622/0.7166)	mem 24308MB
[2025-01-18 21:00:57 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][290/312]	eta 0:00:13 lr 0.002146	time 0.5720 (0.6134)	model_time 0.5715 (0.6067)	loss 3.0873 (3.3343)	grad_norm 2.4412 (1.7807/0.7283)	mem 24308MB
[2025-01-18 21:01:03 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][300/312]	eta 0:00:07 lr 0.002145	time 0.5699 (0.6129)	model_time 0.5698 (0.6065)	loss 3.7615 (3.3367)	grad_norm 2.4619 (1.7818/0.7250)	mem 24308MB
[2025-01-18 21:01:09 internimage_s_1k_224] (main.py 510): INFO Train: [143/300][310/312]	eta 0:00:01 lr 0.002144	time 0.5688 (0.6116)	model_time 0.5686 (0.6054)	loss 2.8900 (3.3317)	grad_norm 1.2775 (1.7889/0.7260)	mem 24308MB
[2025-01-18 21:01:09 internimage_s_1k_224] (main.py 519): INFO EPOCH 143 training takes 0:03:10
[2025-01-18 21:01:09 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_143.pth saving......
[2025-01-18 21:01:11 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_143.pth saved !!!
[2025-01-18 21:01:19 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.644 (7.644)	Loss 0.8383 (0.8383)	Acc@1 82.129 (82.129)	Acc@5 96.655 (96.655)	Mem 24308MB
[2025-01-18 21:01:23 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.044)	Loss 1.1138 (0.9671)	Acc@1 74.658 (79.215)	Acc@5 93.481 (94.971)	Mem 24308MB
[2025-01-18 21:01:23 internimage_s_1k_224] (main.py 575): INFO [Epoch:143] * Acc@1 79.047 Acc@5 94.982
[2025-01-18 21:01:23 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.0%
[2025-01-18 21:01:23 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 21:01:25 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 21:01:25 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 79.05%
[2025-01-18 21:01:32 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.762 (7.762)	Loss 0.7160 (0.7160)	Acc@1 83.203 (83.203)	Acc@5 97.144 (97.144)	Mem 24308MB
[2025-01-18 21:01:36 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (1.052)	Loss 1.0471 (0.8555)	Acc@1 74.487 (79.774)	Acc@5 93.091 (95.137)	Mem 24308MB
[2025-01-18 21:01:36 internimage_s_1k_224] (main.py 575): INFO [Epoch:143] * Acc@1 79.643 Acc@5 95.150
[2025-01-18 21:01:36 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.6%
[2025-01-18 21:01:36 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 21:01:39 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 21:01:39 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 79.64%
[2025-01-18 21:01:41 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][0/312]	eta 0:11:23 lr 0.002144	time 2.1914 (2.1914)	model_time 0.6085 (0.6085)	loss 3.3522 (3.3522)	grad_norm 1.7963 (1.7963/0.0000)	mem 24308MB
[2025-01-18 21:01:47 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][10/312]	eta 0:03:49 lr 0.002144	time 0.5957 (0.7602)	model_time 0.5955 (0.6160)	loss 4.2220 (3.4092)	grad_norm 1.8037 (1.8756/0.4449)	mem 24308MB
[2025-01-18 21:01:53 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][20/312]	eta 0:03:20 lr 0.002143	time 0.5820 (0.6866)	model_time 0.5815 (0.6109)	loss 3.8220 (3.4862)	grad_norm 2.3301 (1.8710/0.6327)	mem 24308MB
[2025-01-18 21:02:00 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][30/312]	eta 0:03:08 lr 0.002142	time 0.5727 (0.6694)	model_time 0.5726 (0.6180)	loss 3.2392 (3.4718)	grad_norm 1.6807 (1.8049/0.6617)	mem 24308MB
[2025-01-18 21:02:06 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][40/312]	eta 0:02:58 lr 0.002142	time 0.6749 (0.6581)	model_time 0.6747 (0.6192)	loss 3.4389 (3.4143)	grad_norm 1.6162 (1.9042/0.7033)	mem 24308MB
[2025-01-18 21:02:12 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][50/312]	eta 0:02:49 lr 0.002141	time 0.6009 (0.6460)	model_time 0.6007 (0.6146)	loss 3.1520 (3.4014)	grad_norm 1.2166 (1.8784/0.6682)	mem 24308MB
[2025-01-18 21:02:18 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][60/312]	eta 0:02:40 lr 0.002140	time 0.5842 (0.6383)	model_time 0.5840 (0.6120)	loss 3.3809 (3.3576)	grad_norm 1.3108 (1.8521/0.6596)	mem 24308MB
[2025-01-18 21:02:24 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][70/312]	eta 0:02:33 lr 0.002140	time 0.5940 (0.6335)	model_time 0.5939 (0.6109)	loss 4.0260 (3.3817)	grad_norm 1.2804 (1.7741/0.6572)	mem 24308MB
[2025-01-18 21:02:30 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][80/312]	eta 0:02:25 lr 0.002139	time 0.5910 (0.6289)	model_time 0.5908 (0.6091)	loss 4.1030 (3.3994)	grad_norm 1.2168 (1.7582/0.6268)	mem 24308MB
[2025-01-18 21:02:36 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][90/312]	eta 0:02:18 lr 0.002138	time 0.5888 (0.6244)	model_time 0.5887 (0.6067)	loss 2.6588 (3.3864)	grad_norm 3.0731 (1.8435/0.7083)	mem 24308MB
[2025-01-18 21:02:42 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][100/312]	eta 0:02:11 lr 0.002138	time 0.6047 (0.6219)	model_time 0.6045 (0.6059)	loss 3.5245 (3.3789)	grad_norm 1.2510 (1.8280/0.7007)	mem 24308MB
[2025-01-18 21:02:48 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][110/312]	eta 0:02:05 lr 0.002137	time 0.5825 (0.6199)	model_time 0.5821 (0.6053)	loss 3.6788 (3.3827)	grad_norm 0.5827 (1.8099/0.7066)	mem 24308MB
[2025-01-18 21:02:54 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][120/312]	eta 0:01:58 lr 0.002136	time 0.5869 (0.6173)	model_time 0.5867 (0.6039)	loss 4.1732 (3.3832)	grad_norm 2.2630 (1.7961/0.6938)	mem 24308MB
[2025-01-18 21:03:00 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][130/312]	eta 0:01:52 lr 0.002136	time 0.5856 (0.6178)	model_time 0.5854 (0.6053)	loss 3.0370 (3.3651)	grad_norm 1.7558 (1.7962/0.6867)	mem 24308MB
[2025-01-18 21:03:06 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][140/312]	eta 0:01:46 lr 0.002135	time 0.6611 (0.6176)	model_time 0.6609 (0.6061)	loss 2.8817 (3.3625)	grad_norm 1.7297 (1.7806/0.6818)	mem 24308MB
[2025-01-18 21:03:12 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][150/312]	eta 0:01:40 lr 0.002134	time 0.5753 (0.6179)	model_time 0.5749 (0.6071)	loss 3.8922 (3.3800)	grad_norm 1.2588 (1.8214/0.7024)	mem 24308MB
[2025-01-18 21:03:18 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][160/312]	eta 0:01:33 lr 0.002134	time 0.5772 (0.6181)	model_time 0.5768 (0.6080)	loss 3.3758 (3.3921)	grad_norm 1.0215 (1.8054/0.6920)	mem 24308MB
[2025-01-18 21:03:24 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][170/312]	eta 0:01:27 lr 0.002133	time 0.5952 (0.6168)	model_time 0.5951 (0.6072)	loss 4.0630 (3.3991)	grad_norm 2.8628 (1.8025/0.6826)	mem 24308MB
[2025-01-18 21:03:30 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][180/312]	eta 0:01:21 lr 0.002132	time 0.6685 (0.6169)	model_time 0.6679 (0.6078)	loss 3.7061 (3.3981)	grad_norm 0.9371 (1.7976/0.6715)	mem 24308MB
[2025-01-18 21:03:36 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][190/312]	eta 0:01:15 lr 0.002132	time 0.6143 (0.6158)	model_time 0.6138 (0.6072)	loss 3.4905 (3.3941)	grad_norm 1.7056 (1.8205/0.6748)	mem 24308MB
[2025-01-18 21:03:43 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][200/312]	eta 0:01:08 lr 0.002131	time 0.5832 (0.6155)	model_time 0.5830 (0.6073)	loss 3.8633 (3.3864)	grad_norm 0.7966 (1.8162/0.6780)	mem 24308MB
[2025-01-18 21:03:48 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][210/312]	eta 0:01:02 lr 0.002130	time 0.5810 (0.6140)	model_time 0.5809 (0.6062)	loss 2.5306 (3.3850)	grad_norm 1.5256 (1.8075/0.6699)	mem 24308MB
[2025-01-18 21:03:54 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][220/312]	eta 0:00:56 lr 0.002130	time 0.6072 (0.6138)	model_time 0.6071 (0.6063)	loss 3.7551 (3.3924)	grad_norm 2.6101 (1.8094/0.6720)	mem 24308MB
[2025-01-18 21:04:01 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][230/312]	eta 0:00:50 lr 0.002129	time 0.7094 (0.6135)	model_time 0.7089 (0.6063)	loss 2.3002 (3.3779)	grad_norm 1.8227 (1.8107/0.6692)	mem 24308MB
[2025-01-18 21:04:06 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][240/312]	eta 0:00:44 lr 0.002128	time 0.5980 (0.6125)	model_time 0.5975 (0.6056)	loss 2.8467 (3.3764)	grad_norm 1.1419 (1.7886/0.6666)	mem 24308MB
[2025-01-18 21:04:13 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][250/312]	eta 0:00:37 lr 0.002128	time 0.5901 (0.6126)	model_time 0.5899 (0.6060)	loss 3.3562 (3.3807)	grad_norm 1.8576 (1.7839/0.6629)	mem 24308MB
[2025-01-18 21:04:19 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][260/312]	eta 0:00:31 lr 0.002127	time 0.5995 (0.6130)	model_time 0.5994 (0.6066)	loss 3.1642 (3.3856)	grad_norm 1.0465 (1.7852/0.6684)	mem 24308MB
[2025-01-18 21:04:25 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][270/312]	eta 0:00:25 lr 0.002126	time 0.5827 (0.6134)	model_time 0.5822 (0.6072)	loss 3.3306 (3.3764)	grad_norm 1.4108 (1.7878/0.6688)	mem 24308MB
[2025-01-18 21:04:31 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][280/312]	eta 0:00:19 lr 0.002126	time 0.5714 (0.6134)	model_time 0.5713 (0.6074)	loss 3.2196 (3.3757)	grad_norm 1.2474 (1.7958/0.6695)	mem 24308MB
[2025-01-18 21:04:37 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][290/312]	eta 0:00:13 lr 0.002125	time 0.5984 (0.6132)	model_time 0.5980 (0.6074)	loss 4.2047 (3.3724)	grad_norm 1.2730 (1.7959/0.6637)	mem 24308MB
[2025-01-18 21:04:43 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][300/312]	eta 0:00:07 lr 0.002124	time 0.5682 (0.6126)	model_time 0.5681 (0.6070)	loss 3.2811 (3.3723)	grad_norm 1.5272 (1.8032/0.6659)	mem 24308MB
[2025-01-18 21:04:49 internimage_s_1k_224] (main.py 510): INFO Train: [144/300][310/312]	eta 0:00:01 lr 0.002124	time 0.5632 (0.6121)	model_time 0.5631 (0.6066)	loss 3.6546 (3.3749)	grad_norm 2.0199 (1.8119/0.6818)	mem 24308MB
[2025-01-18 21:04:50 internimage_s_1k_224] (main.py 519): INFO EPOCH 144 training takes 0:03:10
[2025-01-18 21:04:50 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_144.pth saving......
[2025-01-18 21:04:52 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_144.pth saved !!!
[2025-01-18 21:04:59 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.213 (7.213)	Loss 0.8490 (0.8490)	Acc@1 81.934 (81.934)	Acc@5 96.680 (96.680)	Mem 24308MB
[2025-01-18 21:05:02 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.952)	Loss 1.1718 (0.9868)	Acc@1 73.926 (79.026)	Acc@5 92.749 (94.906)	Mem 24308MB
[2025-01-18 21:05:02 internimage_s_1k_224] (main.py 575): INFO [Epoch:144] * Acc@1 78.905 Acc@5 94.932
[2025-01-18 21:05:02 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 78.9%
[2025-01-18 21:05:02 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 79.05%
[2025-01-18 21:05:11 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.411 (8.411)	Loss 0.7155 (0.7155)	Acc@1 83.276 (83.276)	Acc@5 97.168 (97.168)	Mem 24308MB
[2025-01-18 21:05:15 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.135 (1.140)	Loss 1.0443 (0.8540)	Acc@1 74.414 (79.827)	Acc@5 93.164 (95.173)	Mem 24308MB
[2025-01-18 21:05:15 internimage_s_1k_224] (main.py 575): INFO [Epoch:144] * Acc@1 79.704 Acc@5 95.188
[2025-01-18 21:05:15 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.7%
[2025-01-18 21:05:15 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 21:05:17 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 21:05:17 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 79.70%
[2025-01-18 21:05:20 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][0/312]	eta 0:12:04 lr 0.002124	time 2.3225 (2.3225)	model_time 0.5991 (0.5991)	loss 2.3232 (2.3232)	grad_norm 3.5706 (3.5706/0.0000)	mem 24308MB
[2025-01-18 21:05:26 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][10/312]	eta 0:03:48 lr 0.002123	time 0.5846 (0.7551)	model_time 0.5844 (0.5980)	loss 2.6362 (2.9068)	grad_norm 3.2532 (2.2410/0.8452)	mem 24308MB
[2025-01-18 21:05:32 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][20/312]	eta 0:03:18 lr 0.002122	time 0.5743 (0.6793)	model_time 0.5739 (0.5968)	loss 2.6234 (3.1852)	grad_norm 2.5230 (2.1218/0.8500)	mem 24308MB
[2025-01-18 21:05:38 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][30/312]	eta 0:03:04 lr 0.002122	time 0.5872 (0.6531)	model_time 0.5868 (0.5971)	loss 3.4453 (3.2776)	grad_norm 0.9285 (1.8728/0.8434)	mem 24308MB
[2025-01-18 21:05:44 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][40/312]	eta 0:02:54 lr 0.002121	time 0.6517 (0.6410)	model_time 0.6516 (0.5986)	loss 3.6586 (3.2858)	grad_norm 0.9053 (1.7247/0.7929)	mem 24308MB
[2025-01-18 21:05:50 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][50/312]	eta 0:02:45 lr 0.002120	time 0.5850 (0.6330)	model_time 0.5848 (0.5988)	loss 3.5555 (3.3143)	grad_norm 0.8797 (1.6312/0.7406)	mem 24308MB
[2025-01-18 21:05:56 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][60/312]	eta 0:02:38 lr 0.002120	time 0.5735 (0.6306)	model_time 0.5733 (0.6020)	loss 3.8643 (3.3641)	grad_norm 2.9300 (1.6137/0.7321)	mem 24308MB
[2025-01-18 21:06:02 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][70/312]	eta 0:02:32 lr 0.002119	time 0.5728 (0.6282)	model_time 0.5724 (0.6035)	loss 3.4522 (3.3876)	grad_norm 1.1922 (1.6784/0.7390)	mem 24308MB
[2025-01-18 21:06:08 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][80/312]	eta 0:02:25 lr 0.002118	time 0.7903 (0.6290)	model_time 0.7902 (0.6073)	loss 2.6945 (3.3835)	grad_norm 2.5431 (1.7988/0.8835)	mem 24308MB
[2025-01-18 21:06:14 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][90/312]	eta 0:02:19 lr 0.002118	time 0.5884 (0.6273)	model_time 0.5879 (0.6080)	loss 3.7397 (3.3395)	grad_norm 2.0228 (1.7733/0.8487)	mem 24308MB
[2025-01-18 21:06:21 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][100/312]	eta 0:02:12 lr 0.002117	time 0.5731 (0.6249)	model_time 0.5727 (0.6075)	loss 3.4893 (3.3375)	grad_norm 3.1410 (1.7763/0.8409)	mem 24308MB
[2025-01-18 21:06:27 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][110/312]	eta 0:02:05 lr 0.002116	time 0.5948 (0.6230)	model_time 0.5846 (0.6070)	loss 2.4343 (3.3312)	grad_norm 2.6038 (1.8311/0.8482)	mem 24308MB
[2025-01-18 21:06:33 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][120/312]	eta 0:01:59 lr 0.002116	time 0.5806 (0.6218)	model_time 0.5801 (0.6071)	loss 3.6662 (3.3207)	grad_norm 1.2494 (1.8436/0.8431)	mem 24308MB
[2025-01-18 21:06:39 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][130/312]	eta 0:01:52 lr 0.002115	time 0.5917 (0.6205)	model_time 0.5912 (0.6069)	loss 4.1778 (3.3213)	grad_norm 1.9425 (1.8175/0.8231)	mem 24308MB
[2025-01-18 21:06:45 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][140/312]	eta 0:01:46 lr 0.002114	time 0.5734 (0.6199)	model_time 0.5732 (0.6072)	loss 2.9720 (3.2864)	grad_norm 2.4448 (1.7965/0.8062)	mem 24308MB
[2025-01-18 21:06:51 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][150/312]	eta 0:01:40 lr 0.002114	time 0.6033 (0.6187)	model_time 0.6028 (0.6068)	loss 2.9569 (3.3162)	grad_norm 1.7859 (1.8250/0.8271)	mem 24308MB
[2025-01-18 21:06:57 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][160/312]	eta 0:01:33 lr 0.002113	time 0.5777 (0.6171)	model_time 0.5772 (0.6059)	loss 3.7211 (3.3308)	grad_norm 1.1453 (1.7992/0.8108)	mem 24308MB
[2025-01-18 21:07:03 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][170/312]	eta 0:01:27 lr 0.002112	time 0.5764 (0.6165)	model_time 0.5763 (0.6060)	loss 3.1536 (3.3238)	grad_norm 1.3010 (1.7891/0.7922)	mem 24308MB
[2025-01-18 21:07:09 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][180/312]	eta 0:01:21 lr 0.002112	time 0.5742 (0.6161)	model_time 0.5739 (0.6061)	loss 2.7620 (3.3249)	grad_norm 0.9039 (1.7525/0.7875)	mem 24308MB
[2025-01-18 21:07:15 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][190/312]	eta 0:01:15 lr 0.002111	time 0.6646 (0.6166)	model_time 0.6641 (0.6071)	loss 3.3332 (3.3314)	grad_norm 1.3237 (1.7426/0.7700)	mem 24308MB
[2025-01-18 21:07:22 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][200/312]	eta 0:01:09 lr 0.002110	time 0.7477 (0.6186)	model_time 0.7475 (0.6096)	loss 2.8968 (3.3268)	grad_norm 0.9983 (1.7613/0.7854)	mem 24308MB
[2025-01-18 21:07:28 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][210/312]	eta 0:01:03 lr 0.002110	time 0.5795 (0.6188)	model_time 0.5790 (0.6102)	loss 2.8952 (3.3191)	grad_norm 1.0488 (1.7662/0.7850)	mem 24308MB
[2025-01-18 21:07:34 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][220/312]	eta 0:00:56 lr 0.002109	time 0.5845 (0.6188)	model_time 0.5843 (0.6106)	loss 3.1239 (3.3184)	grad_norm 1.1920 (1.7544/0.7784)	mem 24308MB
[2025-01-18 21:07:40 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][230/312]	eta 0:00:50 lr 0.002108	time 0.5812 (0.6181)	model_time 0.5810 (0.6102)	loss 2.8513 (3.3212)	grad_norm 1.7003 (1.7463/0.7772)	mem 24308MB
[2025-01-18 21:07:46 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][240/312]	eta 0:00:44 lr 0.002108	time 0.5739 (0.6175)	model_time 0.5737 (0.6100)	loss 3.4594 (3.3258)	grad_norm 2.5891 (1.7955/0.8266)	mem 24308MB
[2025-01-18 21:07:52 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][250/312]	eta 0:00:38 lr 0.002107	time 0.5981 (0.6169)	model_time 0.5978 (0.6097)	loss 2.0760 (3.3354)	grad_norm 2.0174 (1.7947/0.8230)	mem 24308MB
[2025-01-18 21:07:58 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][260/312]	eta 0:00:32 lr 0.002106	time 0.5956 (0.6165)	model_time 0.5952 (0.6095)	loss 4.0011 (3.3267)	grad_norm 1.8367 (1.7913/0.8147)	mem 24308MB
[2025-01-18 21:08:04 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][270/312]	eta 0:00:25 lr 0.002106	time 0.5879 (0.6159)	model_time 0.5877 (0.6092)	loss 2.7063 (3.3256)	grad_norm 1.0087 (1.7758/0.8062)	mem 24308MB
[2025-01-18 21:08:10 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][280/312]	eta 0:00:19 lr 0.002105	time 0.5833 (0.6150)	model_time 0.5831 (0.6085)	loss 2.9736 (3.3222)	grad_norm 1.6589 (1.7642/0.7962)	mem 24308MB
[2025-01-18 21:08:16 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][290/312]	eta 0:00:13 lr 0.002104	time 0.5934 (0.6147)	model_time 0.5932 (0.6084)	loss 3.2664 (3.3126)	grad_norm 1.9027 (1.7647/0.7891)	mem 24308MB
[2025-01-18 21:08:22 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][300/312]	eta 0:00:07 lr 0.002104	time 0.5674 (0.6145)	model_time 0.5673 (0.6084)	loss 3.0378 (3.3004)	grad_norm 0.9325 (1.7423/0.7775)	mem 24308MB
[2025-01-18 21:08:28 internimage_s_1k_224] (main.py 510): INFO Train: [145/300][310/312]	eta 0:00:01 lr 0.002103	time 0.6481 (0.6139)	model_time 0.6480 (0.6080)	loss 2.4145 (3.3067)	grad_norm 0.9014 (1.7184/0.7673)	mem 24308MB
[2025-01-18 21:08:29 internimage_s_1k_224] (main.py 519): INFO EPOCH 145 training takes 0:03:11
[2025-01-18 21:08:29 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_145.pth saving......
[2025-01-18 21:08:31 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_145.pth saved !!!
[2025-01-18 21:08:38 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.395 (7.395)	Loss 0.8362 (0.8362)	Acc@1 82.593 (82.593)	Acc@5 96.533 (96.533)	Mem 24308MB
[2025-01-18 21:08:41 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.974)	Loss 1.1324 (0.9661)	Acc@1 74.536 (79.084)	Acc@5 92.993 (95.037)	Mem 24308MB
[2025-01-18 21:08:42 internimage_s_1k_224] (main.py 575): INFO [Epoch:145] * Acc@1 78.989 Acc@5 95.076
[2025-01-18 21:08:42 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.0%
[2025-01-18 21:08:42 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 79.05%
[2025-01-18 21:08:50 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.298 (8.298)	Loss 0.7150 (0.7150)	Acc@1 83.423 (83.423)	Acc@5 97.144 (97.144)	Mem 24308MB
[2025-01-18 21:08:54 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.127)	Loss 1.0419 (0.8525)	Acc@1 74.536 (79.898)	Acc@5 93.188 (95.188)	Mem 24308MB
[2025-01-18 21:08:54 internimage_s_1k_224] (main.py 575): INFO [Epoch:145] * Acc@1 79.774 Acc@5 95.212
[2025-01-18 21:08:54 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.8%
[2025-01-18 21:08:54 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 21:08:57 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 21:08:57 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 79.77%
[2025-01-18 21:08:59 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][0/312]	eta 0:11:41 lr 0.002103	time 2.2492 (2.2492)	model_time 0.5932 (0.5932)	loss 4.1183 (4.1183)	grad_norm 1.2176 (1.2176/0.0000)	mem 24308MB
[2025-01-18 21:09:05 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][10/312]	eta 0:03:51 lr 0.002102	time 0.6727 (0.7678)	model_time 0.6721 (0.6169)	loss 3.6199 (3.4328)	grad_norm 1.4487 (1.3214/0.2550)	mem 24308MB
[2025-01-18 21:09:11 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][20/312]	eta 0:03:22 lr 0.002102	time 0.6616 (0.6950)	model_time 0.6612 (0.6158)	loss 2.7942 (3.2418)	grad_norm 2.3678 (1.8680/0.9729)	mem 24308MB
[2025-01-18 21:09:17 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][30/312]	eta 0:03:09 lr 0.002101	time 0.5983 (0.6717)	model_time 0.5981 (0.6179)	loss 3.7294 (3.2787)	grad_norm 1.1872 (1.9294/0.9739)	mem 24308MB
[2025-01-18 21:09:23 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][40/312]	eta 0:02:58 lr 0.002100	time 0.6564 (0.6546)	model_time 0.6559 (0.6138)	loss 3.7949 (3.3161)	grad_norm 2.3242 (1.8406/0.8905)	mem 24308MB
[2025-01-18 21:09:29 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][50/312]	eta 0:02:49 lr 0.002100	time 0.5797 (0.6457)	model_time 0.5795 (0.6129)	loss 4.2202 (3.2794)	grad_norm 1.2336 (1.7586/0.8211)	mem 24308MB
[2025-01-18 21:09:36 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][60/312]	eta 0:02:41 lr 0.002099	time 0.7182 (0.6395)	model_time 0.7178 (0.6120)	loss 3.5674 (3.2996)	grad_norm 1.3785 (1.7114/0.7877)	mem 24308MB
[2025-01-18 21:09:41 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][70/312]	eta 0:02:33 lr 0.002098	time 0.6779 (0.6334)	model_time 0.6777 (0.6097)	loss 2.8949 (3.2815)	grad_norm 1.1091 (1.6721/0.7568)	mem 24308MB
[2025-01-18 21:09:47 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][80/312]	eta 0:02:25 lr 0.002098	time 0.6607 (0.6288)	model_time 0.6605 (0.6080)	loss 2.7678 (3.2652)	grad_norm 2.7679 (1.8196/0.8999)	mem 24308MB
[2025-01-18 21:09:53 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][90/312]	eta 0:02:18 lr 0.002097	time 0.5916 (0.6250)	model_time 0.5911 (0.6065)	loss 3.4433 (3.2572)	grad_norm 1.5727 (1.7969/0.8803)	mem 24308MB
[2025-01-18 21:10:00 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][100/312]	eta 0:02:12 lr 0.002096	time 0.5882 (0.6235)	model_time 0.5878 (0.6067)	loss 3.0448 (3.2390)	grad_norm 0.8773 (1.7477/0.8571)	mem 24308MB
[2025-01-18 21:10:06 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][110/312]	eta 0:02:05 lr 0.002096	time 0.5976 (0.6237)	model_time 0.5974 (0.6084)	loss 4.2131 (3.2582)	grad_norm 1.6259 (1.7516/0.8388)	mem 24308MB
[2025-01-18 21:10:12 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][120/312]	eta 0:01:59 lr 0.002095	time 0.5735 (0.6237)	model_time 0.5733 (0.6097)	loss 4.0691 (3.2852)	grad_norm 0.9948 (1.7151/0.8169)	mem 24308MB
[2025-01-18 21:10:18 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][130/312]	eta 0:01:53 lr 0.002094	time 0.6475 (0.6231)	model_time 0.6474 (0.6101)	loss 3.4198 (3.2966)	grad_norm 1.3959 (1.7371/0.8293)	mem 24308MB
[2025-01-18 21:10:24 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][140/312]	eta 0:01:47 lr 0.002094	time 0.6784 (0.6228)	model_time 0.6782 (0.6107)	loss 3.6168 (3.3001)	grad_norm 3.8520 (1.7611/0.8533)	mem 24308MB
[2025-01-18 21:10:31 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][150/312]	eta 0:01:40 lr 0.002093	time 0.6494 (0.6226)	model_time 0.6490 (0.6113)	loss 3.6925 (3.3192)	grad_norm 2.6760 (1.7924/0.8431)	mem 24308MB
[2025-01-18 21:10:37 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][160/312]	eta 0:01:34 lr 0.002092	time 0.5948 (0.6212)	model_time 0.5947 (0.6105)	loss 3.3658 (3.2991)	grad_norm 3.6104 (1.8010/0.8420)	mem 24308MB
[2025-01-18 21:10:43 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][170/312]	eta 0:01:28 lr 0.002092	time 0.5665 (0.6202)	model_time 0.5662 (0.6102)	loss 3.9479 (3.3203)	grad_norm 1.1286 (1.7896/0.8330)	mem 24308MB
[2025-01-18 21:10:49 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][180/312]	eta 0:01:21 lr 0.002091	time 0.7039 (0.6195)	model_time 0.7037 (0.6100)	loss 2.8671 (3.3136)	grad_norm 1.4640 (1.7749/0.8206)	mem 24308MB
[2025-01-18 21:10:55 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][190/312]	eta 0:01:15 lr 0.002090	time 0.6858 (0.6185)	model_time 0.6853 (0.6095)	loss 2.3847 (3.3100)	grad_norm 1.4094 (1.7828/0.8136)	mem 24308MB
[2025-01-18 21:11:01 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][200/312]	eta 0:01:09 lr 0.002090	time 0.5793 (0.6174)	model_time 0.5791 (0.6088)	loss 3.8773 (3.3027)	grad_norm 2.5923 (1.7858/0.8014)	mem 24308MB
[2025-01-18 21:11:07 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][210/312]	eta 0:01:02 lr 0.002089	time 0.5757 (0.6169)	model_time 0.5755 (0.6087)	loss 3.0670 (3.3029)	grad_norm 1.2331 (1.7919/0.7976)	mem 24308MB
[2025-01-18 21:11:13 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][220/312]	eta 0:00:56 lr 0.002088	time 0.5745 (0.6162)	model_time 0.5743 (0.6083)	loss 4.2565 (3.3083)	grad_norm 0.8804 (1.7633/0.7930)	mem 24308MB
[2025-01-18 21:11:19 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][230/312]	eta 0:00:50 lr 0.002088	time 0.5843 (0.6152)	model_time 0.5841 (0.6077)	loss 3.4704 (3.3108)	grad_norm 1.3770 (1.7618/0.7917)	mem 24308MB
[2025-01-18 21:11:25 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][240/312]	eta 0:00:44 lr 0.002087	time 0.5867 (0.6155)	model_time 0.5865 (0.6082)	loss 2.3693 (3.3052)	grad_norm 1.1285 (1.7533/0.7818)	mem 24308MB
[2025-01-18 21:11:31 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][250/312]	eta 0:00:38 lr 0.002086	time 0.5954 (0.6154)	model_time 0.5952 (0.6085)	loss 3.7316 (3.3032)	grad_norm 2.7849 (1.7426/0.7777)	mem 24308MB
[2025-01-18 21:11:37 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][260/312]	eta 0:00:32 lr 0.002086	time 0.6094 (0.6156)	model_time 0.6092 (0.6089)	loss 3.2301 (3.2971)	grad_norm 1.0415 (1.7429/0.7741)	mem 24308MB
[2025-01-18 21:11:43 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][270/312]	eta 0:00:25 lr 0.002085	time 0.5851 (0.6161)	model_time 0.5846 (0.6096)	loss 3.9100 (3.3000)	grad_norm 1.2496 (1.7331/0.7685)	mem 24308MB
[2025-01-18 21:11:50 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][280/312]	eta 0:00:19 lr 0.002084	time 0.6387 (0.6157)	model_time 0.6386 (0.6094)	loss 3.9678 (3.3039)	grad_norm 2.1653 (1.7441/0.7688)	mem 24308MB
[2025-01-18 21:11:56 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][290/312]	eta 0:00:13 lr 0.002084	time 0.5772 (0.6153)	model_time 0.5770 (0.6093)	loss 2.9724 (3.3001)	grad_norm 1.7161 (1.7544/0.7716)	mem 24308MB
[2025-01-18 21:12:01 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][300/312]	eta 0:00:07 lr 0.002083	time 0.5702 (0.6144)	model_time 0.5701 (0.6086)	loss 3.1584 (3.3026)	grad_norm 2.6804 (1.7535/0.7643)	mem 24308MB
[2025-01-18 21:12:07 internimage_s_1k_224] (main.py 510): INFO Train: [146/300][310/312]	eta 0:00:01 lr 0.002082	time 0.5699 (0.6135)	model_time 0.5698 (0.6078)	loss 3.2679 (3.2961)	grad_norm 1.4273 (1.7611/0.7663)	mem 24308MB
[2025-01-18 21:12:08 internimage_s_1k_224] (main.py 519): INFO EPOCH 146 training takes 0:03:11
[2025-01-18 21:12:08 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_146.pth saving......
[2025-01-18 21:12:10 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_146.pth saved !!!
[2025-01-18 21:12:17 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.039 (7.039)	Loss 0.8224 (0.8224)	Acc@1 82.129 (82.129)	Acc@5 96.802 (96.802)	Mem 24308MB
[2025-01-18 21:12:20 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.949)	Loss 1.1072 (0.9538)	Acc@1 74.805 (79.355)	Acc@5 93.457 (95.022)	Mem 24308MB
[2025-01-18 21:12:21 internimage_s_1k_224] (main.py 575): INFO [Epoch:146] * Acc@1 79.277 Acc@5 95.062
[2025-01-18 21:12:21 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.3%
[2025-01-18 21:12:21 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 21:12:22 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 21:12:22 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 79.28%
[2025-01-18 21:12:30 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.132 (7.132)	Loss 0.7144 (0.7144)	Acc@1 83.398 (83.398)	Acc@5 97.144 (97.144)	Mem 24308MB
[2025-01-18 21:12:33 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.967)	Loss 1.0395 (0.8511)	Acc@1 74.634 (79.941)	Acc@5 93.164 (95.210)	Mem 24308MB
[2025-01-18 21:12:33 internimage_s_1k_224] (main.py 575): INFO [Epoch:146] * Acc@1 79.822 Acc@5 95.230
[2025-01-18 21:12:33 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.8%
[2025-01-18 21:12:33 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 21:12:35 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 21:12:35 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 79.82%
[2025-01-18 21:12:38 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][0/312]	eta 0:11:15 lr 0.002082	time 2.1656 (2.1656)	model_time 0.5929 (0.5929)	loss 2.4880 (2.4880)	grad_norm 1.7547 (1.7547/0.0000)	mem 24308MB
[2025-01-18 21:12:43 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][10/312]	eta 0:03:40 lr 0.002082	time 0.5934 (0.7316)	model_time 0.5932 (0.5884)	loss 3.4548 (2.9588)	grad_norm 1.0400 (1.8819/0.7619)	mem 24308MB
[2025-01-18 21:12:49 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][20/312]	eta 0:03:15 lr 0.002081	time 0.5838 (0.6681)	model_time 0.5836 (0.5929)	loss 3.6161 (3.1476)	grad_norm 0.9297 (1.5106/0.7137)	mem 24308MB
[2025-01-18 21:12:56 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][30/312]	eta 0:03:02 lr 0.002080	time 0.6071 (0.6472)	model_time 0.6066 (0.5961)	loss 3.6251 (3.1739)	grad_norm 2.8990 (1.6263/0.6681)	mem 24308MB
[2025-01-18 21:13:02 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][40/312]	eta 0:02:55 lr 0.002080	time 0.6565 (0.6445)	model_time 0.6560 (0.6055)	loss 3.5458 (3.1795)	grad_norm 1.6263 (1.7240/0.7657)	mem 24308MB
[2025-01-18 21:13:08 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][50/312]	eta 0:02:46 lr 0.002079	time 0.5898 (0.6360)	model_time 0.5893 (0.6046)	loss 3.4410 (3.1678)	grad_norm 1.5830 (1.7412/0.7681)	mem 24308MB
[2025-01-18 21:13:14 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][60/312]	eta 0:02:39 lr 0.002078	time 0.5928 (0.6322)	model_time 0.5926 (0.6059)	loss 2.2141 (3.2201)	grad_norm 0.9165 (1.6919/0.7898)	mem 24308MB
[2025-01-18 21:13:20 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][70/312]	eta 0:02:32 lr 0.002078	time 0.5825 (0.6305)	model_time 0.5824 (0.6078)	loss 3.6246 (3.2605)	grad_norm 0.9213 (1.8238/0.9027)	mem 24308MB
[2025-01-18 21:13:26 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][80/312]	eta 0:02:25 lr 0.002077	time 0.6008 (0.6271)	model_time 0.6006 (0.6072)	loss 3.4941 (3.2867)	grad_norm 2.1308 (1.8728/0.8933)	mem 24308MB
[2025-01-18 21:13:32 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][90/312]	eta 0:02:18 lr 0.002076	time 0.5993 (0.6251)	model_time 0.5992 (0.6074)	loss 3.1485 (3.2858)	grad_norm 1.4989 (1.8469/0.8610)	mem 24308MB
[2025-01-18 21:13:38 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][100/312]	eta 0:02:12 lr 0.002076	time 0.6630 (0.6235)	model_time 0.6629 (0.6074)	loss 3.2945 (3.2860)	grad_norm 1.1626 (1.8017/0.8375)	mem 24308MB
[2025-01-18 21:13:44 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][110/312]	eta 0:02:05 lr 0.002075	time 0.5780 (0.6206)	model_time 0.5778 (0.6060)	loss 4.2337 (3.2997)	grad_norm 1.3425 (1.7665/0.8132)	mem 24308MB
[2025-01-18 21:13:50 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][120/312]	eta 0:01:58 lr 0.002074	time 0.5929 (0.6190)	model_time 0.5927 (0.6055)	loss 3.1825 (3.2836)	grad_norm 3.8787 (1.7715/0.8135)	mem 24308MB
[2025-01-18 21:13:56 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][130/312]	eta 0:01:52 lr 0.002074	time 0.5697 (0.6171)	model_time 0.5695 (0.6047)	loss 2.4725 (3.2918)	grad_norm 1.2399 (1.7535/0.8002)	mem 24308MB
[2025-01-18 21:14:02 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][140/312]	eta 0:01:45 lr 0.002073	time 0.5753 (0.6161)	model_time 0.5748 (0.6045)	loss 3.6050 (3.2975)	grad_norm 1.0991 (1.7235/0.7862)	mem 24308MB
[2025-01-18 21:14:08 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][150/312]	eta 0:01:39 lr 0.002072	time 0.7072 (0.6154)	model_time 0.7071 (0.6045)	loss 4.0821 (3.2957)	grad_norm 1.1515 (1.7332/0.7754)	mem 24308MB
[2025-01-18 21:14:14 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][160/312]	eta 0:01:33 lr 0.002072	time 0.5928 (0.6152)	model_time 0.5926 (0.6050)	loss 2.6519 (3.3039)	grad_norm 1.1179 (1.7376/0.7797)	mem 24308MB
[2025-01-18 21:14:21 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][170/312]	eta 0:01:27 lr 0.002071	time 0.6828 (0.6153)	model_time 0.6826 (0.6057)	loss 3.4483 (3.3171)	grad_norm 2.3479 (1.7640/0.7993)	mem 24308MB
[2025-01-18 21:14:27 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][180/312]	eta 0:01:21 lr 0.002070	time 0.6443 (0.6163)	model_time 0.6441 (0.6072)	loss 2.8122 (3.3009)	grad_norm 1.8151 (1.7509/0.7879)	mem 24308MB
[2025-01-18 21:14:33 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][190/312]	eta 0:01:15 lr 0.002070	time 0.5743 (0.6180)	model_time 0.5741 (0.6094)	loss 4.2083 (3.3087)	grad_norm 2.6077 (1.7573/0.7731)	mem 24308MB
[2025-01-18 21:14:39 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][200/312]	eta 0:01:09 lr 0.002069	time 0.5781 (0.6171)	model_time 0.5776 (0.6089)	loss 3.0085 (3.3068)	grad_norm 2.0598 (1.7521/0.7614)	mem 24308MB
[2025-01-18 21:14:46 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][210/312]	eta 0:01:02 lr 0.002068	time 0.6682 (0.6169)	model_time 0.6680 (0.6091)	loss 3.3600 (3.3044)	grad_norm 2.6125 (1.7579/0.7621)	mem 24308MB
[2025-01-18 21:14:52 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][220/312]	eta 0:00:56 lr 0.002068	time 0.6667 (0.6162)	model_time 0.6663 (0.6087)	loss 2.4284 (3.3059)	grad_norm 2.6691 (1.7773/0.7736)	mem 24308MB
[2025-01-18 21:14:58 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][230/312]	eta 0:00:50 lr 0.002067	time 0.5683 (0.6152)	model_time 0.5681 (0.6080)	loss 2.6727 (3.3070)	grad_norm 2.2033 (1.7799/0.7675)	mem 24308MB
[2025-01-18 21:15:04 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][240/312]	eta 0:00:44 lr 0.002066	time 0.5743 (0.6146)	model_time 0.5739 (0.6077)	loss 3.2571 (3.3034)	grad_norm 1.5329 (1.7773/0.7617)	mem 24308MB
[2025-01-18 21:15:10 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][250/312]	eta 0:00:38 lr 0.002066	time 0.5843 (0.6140)	model_time 0.5841 (0.6073)	loss 3.8927 (3.3073)	grad_norm 1.4682 (1.7608/0.7535)	mem 24308MB
[2025-01-18 21:15:16 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][260/312]	eta 0:00:31 lr 0.002065	time 0.5815 (0.6134)	model_time 0.5813 (0.6070)	loss 3.1429 (3.3074)	grad_norm 0.7725 (1.7421/0.7479)	mem 24308MB
[2025-01-18 21:15:21 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][270/312]	eta 0:00:25 lr 0.002064	time 0.6126 (0.6126)	model_time 0.6121 (0.6064)	loss 3.3824 (3.3092)	grad_norm 1.1017 (1.7407/0.7457)	mem 24308MB
[2025-01-18 21:15:28 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][280/312]	eta 0:00:19 lr 0.002064	time 0.5842 (0.6127)	model_time 0.5841 (0.6067)	loss 3.3950 (3.3211)	grad_norm 1.7195 (1.7290/0.7397)	mem 24308MB
[2025-01-18 21:15:34 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][290/312]	eta 0:00:13 lr 0.002063	time 0.6617 (0.6129)	model_time 0.6615 (0.6071)	loss 3.2809 (3.3237)	grad_norm 2.0605 (1.7537/0.7653)	mem 24308MB
[2025-01-18 21:15:40 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][300/312]	eta 0:00:07 lr 0.002062	time 0.5779 (0.6128)	model_time 0.5778 (0.6072)	loss 3.9469 (3.3236)	grad_norm 2.4984 (1.7631/0.7667)	mem 24308MB
[2025-01-18 21:15:46 internimage_s_1k_224] (main.py 510): INFO Train: [147/300][310/312]	eta 0:00:01 lr 0.002062	time 0.5721 (0.6133)	model_time 0.5719 (0.6079)	loss 3.4878 (3.3290)	grad_norm 0.9057 (1.7621/0.7621)	mem 24308MB
[2025-01-18 21:15:47 internimage_s_1k_224] (main.py 519): INFO EPOCH 147 training takes 0:03:11
[2025-01-18 21:15:47 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_147.pth saving......
[2025-01-18 21:15:49 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_147.pth saved !!!
[2025-01-18 21:15:56 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.607 (7.607)	Loss 0.8130 (0.8130)	Acc@1 82.104 (82.104)	Acc@5 96.680 (96.680)	Mem 24308MB
[2025-01-18 21:15:59 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.134 (0.985)	Loss 1.1353 (0.9544)	Acc@1 74.561 (79.270)	Acc@5 93.433 (95.057)	Mem 24308MB
[2025-01-18 21:16:00 internimage_s_1k_224] (main.py 575): INFO [Epoch:147] * Acc@1 79.137 Acc@5 95.078
[2025-01-18 21:16:00 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.1%
[2025-01-18 21:16:00 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 79.28%
[2025-01-18 21:16:08 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.337 (8.337)	Loss 0.7139 (0.7139)	Acc@1 83.374 (83.374)	Acc@5 97.192 (97.192)	Mem 24308MB
[2025-01-18 21:16:12 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.136)	Loss 1.0372 (0.8497)	Acc@1 74.683 (79.989)	Acc@5 93.286 (95.237)	Mem 24308MB
[2025-01-18 21:16:12 internimage_s_1k_224] (main.py 575): INFO [Epoch:147] * Acc@1 79.878 Acc@5 95.258
[2025-01-18 21:16:12 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 79.9%
[2025-01-18 21:16:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 21:16:15 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 21:16:15 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 79.88%
[2025-01-18 21:16:17 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][0/312]	eta 0:10:23 lr 0.002061	time 1.9992 (1.9992)	model_time 0.5875 (0.5875)	loss 3.2449 (3.2449)	grad_norm 1.3647 (1.3647/0.0000)	mem 24308MB
[2025-01-18 21:16:23 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][10/312]	eta 0:03:41 lr 0.002061	time 0.6344 (0.7350)	model_time 0.6343 (0.6064)	loss 4.1764 (3.3315)	grad_norm 1.5362 (1.3640/0.3132)	mem 24308MB
[2025-01-18 21:16:29 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][20/312]	eta 0:03:17 lr 0.002060	time 0.6013 (0.6761)	model_time 0.6011 (0.6086)	loss 4.0079 (3.5124)	grad_norm 1.6613 (1.5569/0.4973)	mem 24308MB
[2025-01-18 21:16:35 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][30/312]	eta 0:03:05 lr 0.002059	time 0.5825 (0.6584)	model_time 0.5821 (0.6125)	loss 4.0443 (3.4069)	grad_norm 1.2968 (1.5886/0.5079)	mem 24308MB
[2025-01-18 21:16:41 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][40/312]	eta 0:02:54 lr 0.002059	time 0.6391 (0.6423)	model_time 0.6390 (0.6076)	loss 2.8611 (3.3734)	grad_norm 1.1451 (1.5663/0.5028)	mem 24308MB
[2025-01-18 21:16:47 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][50/312]	eta 0:02:45 lr 0.002058	time 0.5938 (0.6332)	model_time 0.5936 (0.6052)	loss 3.7116 (3.3852)	grad_norm 1.9280 (1.6587/0.5117)	mem 24308MB
[2025-01-18 21:16:53 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][60/312]	eta 0:02:38 lr 0.002057	time 0.5840 (0.6278)	model_time 0.5838 (0.6043)	loss 3.5084 (3.3710)	grad_norm 1.4486 (1.6460/0.5064)	mem 24308MB
[2025-01-18 21:16:59 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][70/312]	eta 0:02:30 lr 0.002057	time 0.5852 (0.6231)	model_time 0.5848 (0.6029)	loss 3.5030 (3.3469)	grad_norm 1.6464 (1.6904/0.5765)	mem 24308MB
[2025-01-18 21:17:05 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][80/312]	eta 0:02:23 lr 0.002056	time 0.6253 (0.6195)	model_time 0.6249 (0.6017)	loss 4.1376 (3.3634)	grad_norm 1.1775 (1.7534/0.6228)	mem 24308MB
[2025-01-18 21:17:11 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][90/312]	eta 0:02:17 lr 0.002055	time 0.5763 (0.6190)	model_time 0.5761 (0.6032)	loss 2.2898 (3.3642)	grad_norm 3.4363 (1.8935/0.8214)	mem 24308MB
[2025-01-18 21:17:17 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][100/312]	eta 0:02:11 lr 0.002055	time 0.5800 (0.6205)	model_time 0.5798 (0.6062)	loss 3.8280 (3.3508)	grad_norm 1.0433 (1.8770/0.7968)	mem 24308MB
[2025-01-18 21:17:24 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][110/312]	eta 0:02:05 lr 0.002054	time 0.5924 (0.6198)	model_time 0.5920 (0.6068)	loss 3.5748 (3.3658)	grad_norm 1.0469 (1.8472/0.7832)	mem 24308MB
[2025-01-18 21:17:30 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][120/312]	eta 0:01:59 lr 0.002053	time 0.6463 (0.6219)	model_time 0.6461 (0.6099)	loss 2.4032 (3.3820)	grad_norm 1.0272 (1.8244/0.7760)	mem 24308MB
[2025-01-18 21:17:36 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][130/312]	eta 0:01:52 lr 0.002053	time 0.5843 (0.6197)	model_time 0.5842 (0.6085)	loss 2.1237 (3.3595)	grad_norm 1.6496 (1.8723/0.8081)	mem 24308MB
[2025-01-18 21:17:42 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][140/312]	eta 0:01:46 lr 0.002052	time 0.6039 (0.6193)	model_time 0.6033 (0.6088)	loss 3.6344 (3.3638)	grad_norm 1.2029 (1.8603/0.7877)	mem 24308MB
[2025-01-18 21:17:48 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][150/312]	eta 0:01:40 lr 0.002051	time 0.5803 (0.6196)	model_time 0.5801 (0.6098)	loss 3.3730 (3.3636)	grad_norm 2.8338 (1.8525/0.7806)	mem 24308MB
[2025-01-18 21:17:54 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][160/312]	eta 0:01:33 lr 0.002051	time 0.5754 (0.6174)	model_time 0.5750 (0.6081)	loss 3.4089 (3.3755)	grad_norm 0.9020 (1.8467/0.7698)	mem 24308MB
[2025-01-18 21:18:00 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][170/312]	eta 0:01:27 lr 0.002050	time 0.5797 (0.6164)	model_time 0.5795 (0.6077)	loss 3.2966 (3.3706)	grad_norm 2.3821 (1.8452/0.7612)	mem 24308MB
[2025-01-18 21:18:06 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][180/312]	eta 0:01:21 lr 0.002050	time 0.5966 (0.6154)	model_time 0.5964 (0.6072)	loss 3.7088 (3.3672)	grad_norm 0.9296 (1.8024/0.7625)	mem 24308MB
[2025-01-18 21:18:12 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][190/312]	eta 0:01:15 lr 0.002049	time 0.6001 (0.6148)	model_time 0.5996 (0.6070)	loss 3.9683 (3.3769)	grad_norm 0.8616 (1.7904/0.7650)	mem 24308MB
[2025-01-18 21:18:18 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][200/312]	eta 0:01:08 lr 0.002048	time 0.5996 (0.6136)	model_time 0.5994 (0.6062)	loss 2.2121 (3.3803)	grad_norm 2.3319 (1.7827/0.7515)	mem 24308MB
[2025-01-18 21:18:24 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][210/312]	eta 0:01:02 lr 0.002048	time 0.5803 (0.6132)	model_time 0.5801 (0.6061)	loss 2.5542 (3.3745)	grad_norm 2.9735 (1.7963/0.7466)	mem 24308MB
[2025-01-18 21:18:30 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][220/312]	eta 0:00:56 lr 0.002047	time 0.6890 (0.6141)	model_time 0.6886 (0.6073)	loss 2.6544 (3.3734)	grad_norm 1.3380 (1.7706/0.7399)	mem 24308MB
[2025-01-18 21:18:36 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][230/312]	eta 0:00:50 lr 0.002046	time 0.5663 (0.6137)	model_time 0.5661 (0.6071)	loss 3.7474 (3.3783)	grad_norm 1.3740 (1.7663/0.7424)	mem 24308MB
[2025-01-18 21:18:43 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][240/312]	eta 0:00:44 lr 0.002046	time 0.6482 (0.6160)	model_time 0.6480 (0.6097)	loss 3.3997 (3.3784)	grad_norm 3.0882 (1.7919/0.7586)	mem 24308MB
[2025-01-18 21:18:49 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][250/312]	eta 0:00:38 lr 0.002045	time 0.5804 (0.6158)	model_time 0.5803 (0.6098)	loss 3.5578 (3.3702)	grad_norm 1.0021 (1.7899/0.7525)	mem 24308MB
[2025-01-18 21:18:55 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][260/312]	eta 0:00:32 lr 0.002044	time 0.6330 (0.6155)	model_time 0.6325 (0.6096)	loss 2.9380 (3.3608)	grad_norm 1.6000 (1.8039/0.7626)	mem 24308MB
[2025-01-18 21:19:02 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][270/312]	eta 0:00:25 lr 0.002044	time 0.5866 (0.6156)	model_time 0.5865 (0.6099)	loss 2.3956 (3.3561)	grad_norm 1.4763 (1.7945/0.7581)	mem 24308MB
[2025-01-18 21:19:07 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][280/312]	eta 0:00:19 lr 0.002043	time 0.5922 (0.6148)	model_time 0.5917 (0.6094)	loss 2.5206 (3.3610)	grad_norm 1.6430 (1.7776/0.7521)	mem 24308MB
[2025-01-18 21:19:13 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][290/312]	eta 0:00:13 lr 0.002042	time 0.5961 (0.6142)	model_time 0.5957 (0.6090)	loss 3.4019 (3.3595)	grad_norm 1.8074 (1.7759/0.7501)	mem 24308MB
[2025-01-18 21:19:19 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][300/312]	eta 0:00:07 lr 0.002042	time 0.5702 (0.6139)	model_time 0.5701 (0.6088)	loss 2.2734 (3.3518)	grad_norm 1.8489 (1.7661/0.7417)	mem 24308MB
[2025-01-18 21:19:25 internimage_s_1k_224] (main.py 510): INFO Train: [148/300][310/312]	eta 0:00:01 lr 0.002041	time 0.5691 (0.6127)	model_time 0.5690 (0.6078)	loss 2.7918 (3.3489)	grad_norm 1.5351 (1.8001/0.7701)	mem 24308MB
[2025-01-18 21:19:26 internimage_s_1k_224] (main.py 519): INFO EPOCH 148 training takes 0:03:11
[2025-01-18 21:19:26 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_148.pth saving......
[2025-01-18 21:19:28 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_148.pth saved !!!
[2025-01-18 21:19:35 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.381 (7.381)	Loss 0.8335 (0.8335)	Acc@1 81.934 (81.934)	Acc@5 96.436 (96.436)	Mem 24308MB
[2025-01-18 21:19:38 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.969)	Loss 1.1474 (0.9637)	Acc@1 73.975 (79.503)	Acc@5 92.749 (94.880)	Mem 24308MB
[2025-01-18 21:19:39 internimage_s_1k_224] (main.py 575): INFO [Epoch:148] * Acc@1 79.343 Acc@5 94.896
[2025-01-18 21:19:39 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.3%
[2025-01-18 21:19:39 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 21:19:41 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 21:19:41 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 79.34%
[2025-01-18 21:19:48 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.250 (7.250)	Loss 0.7133 (0.7133)	Acc@1 83.423 (83.423)	Acc@5 97.168 (97.168)	Mem 24308MB
[2025-01-18 21:19:51 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.138 (0.964)	Loss 1.0351 (0.8484)	Acc@1 74.780 (80.080)	Acc@5 93.408 (95.255)	Mem 24308MB
[2025-01-18 21:19:51 internimage_s_1k_224] (main.py 575): INFO [Epoch:148] * Acc@1 79.966 Acc@5 95.284
[2025-01-18 21:19:51 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.0%
[2025-01-18 21:19:51 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 21:19:54 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 21:19:54 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 79.97%
[2025-01-18 21:19:56 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][0/312]	eta 0:11:14 lr 0.002041	time 2.1617 (2.1617)	model_time 0.5799 (0.5799)	loss 3.6911 (3.6911)	grad_norm 1.1733 (1.1733/0.0000)	mem 24308MB
[2025-01-18 21:20:02 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][10/312]	eta 0:03:42 lr 0.002040	time 0.5943 (0.7377)	model_time 0.5941 (0.5936)	loss 2.5693 (3.1524)	grad_norm 2.1277 (1.5790/0.6886)	mem 24308MB
[2025-01-18 21:20:08 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][20/312]	eta 0:03:18 lr 0.002039	time 0.5833 (0.6787)	model_time 0.5829 (0.6031)	loss 2.5500 (3.1902)	grad_norm 1.6298 (1.5104/0.5666)	mem 24308MB
[2025-01-18 21:20:14 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][30/312]	eta 0:03:07 lr 0.002039	time 0.5840 (0.6640)	model_time 0.5835 (0.6126)	loss 3.5649 (3.2155)	grad_norm 1.6850 (1.5185/0.5541)	mem 24308MB
[2025-01-18 21:20:20 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][40/312]	eta 0:02:57 lr 0.002038	time 0.6725 (0.6544)	model_time 0.6721 (0.6155)	loss 3.5988 (3.2169)	grad_norm 1.7717 (1.5152/0.4964)	mem 24308MB
[2025-01-18 21:20:27 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][50/312]	eta 0:02:49 lr 0.002037	time 0.6954 (0.6485)	model_time 0.6950 (0.6171)	loss 3.3266 (3.2193)	grad_norm 1.0914 (1.4844/0.4828)	mem 24308MB
[2025-01-18 21:20:33 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][60/312]	eta 0:02:41 lr 0.002037	time 0.5757 (0.6403)	model_time 0.5756 (0.6140)	loss 3.8093 (3.2345)	grad_norm 2.8946 (1.6039/0.6002)	mem 24308MB
[2025-01-18 21:20:39 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][70/312]	eta 0:02:33 lr 0.002036	time 0.5761 (0.6335)	model_time 0.5759 (0.6109)	loss 2.2385 (3.2104)	grad_norm 2.2523 (1.6206/0.6211)	mem 24308MB
[2025-01-18 21:20:45 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][80/312]	eta 0:02:26 lr 0.002035	time 0.5908 (0.6318)	model_time 0.5907 (0.6119)	loss 2.4517 (3.2399)	grad_norm 2.0260 (1.6517/0.6599)	mem 24308MB
[2025-01-18 21:20:51 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][90/312]	eta 0:02:19 lr 0.002035	time 0.5705 (0.6266)	model_time 0.5704 (0.6087)	loss 3.2569 (3.2630)	grad_norm 1.3943 (1.6333/0.6336)	mem 24308MB
[2025-01-18 21:20:57 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][100/312]	eta 0:02:12 lr 0.002034	time 0.5733 (0.6235)	model_time 0.5731 (0.6073)	loss 3.7716 (3.2703)	grad_norm 2.8148 (1.7204/0.7044)	mem 24308MB
[2025-01-18 21:21:03 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][110/312]	eta 0:02:05 lr 0.002033	time 0.5798 (0.6215)	model_time 0.5796 (0.6067)	loss 2.1202 (3.2671)	grad_norm 1.4279 (1.7178/0.6885)	mem 24308MB
[2025-01-18 21:21:09 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][120/312]	eta 0:01:58 lr 0.002033	time 0.5981 (0.6195)	model_time 0.5980 (0.6060)	loss 3.7495 (3.2877)	grad_norm 1.6489 (1.7126/0.6757)	mem 24308MB
[2025-01-18 21:21:14 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][130/312]	eta 0:01:52 lr 0.002032	time 0.5868 (0.6173)	model_time 0.5867 (0.6047)	loss 3.0595 (3.2723)	grad_norm 2.8228 (1.7276/0.6962)	mem 24308MB
[2025-01-18 21:21:21 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][140/312]	eta 0:01:46 lr 0.002031	time 0.5757 (0.6168)	model_time 0.5753 (0.6051)	loss 3.0700 (3.2702)	grad_norm 1.3722 (1.7445/0.7014)	mem 24308MB
[2025-01-18 21:21:27 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][150/312]	eta 0:01:40 lr 0.002031	time 0.5625 (0.6179)	model_time 0.5624 (0.6070)	loss 3.9682 (3.2960)	grad_norm 0.8000 (1.7545/0.6943)	mem 24308MB
[2025-01-18 21:21:33 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][160/312]	eta 0:01:33 lr 0.002030	time 0.6751 (0.6177)	model_time 0.6745 (0.6074)	loss 3.6117 (3.3017)	grad_norm 0.8511 (1.7580/0.6904)	mem 24308MB
[2025-01-18 21:21:39 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][170/312]	eta 0:01:27 lr 0.002029	time 0.6687 (0.6178)	model_time 0.6682 (0.6081)	loss 2.1620 (3.2866)	grad_norm 1.1604 (1.7427/0.6807)	mem 24308MB
[2025-01-18 21:21:45 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][180/312]	eta 0:01:21 lr 0.002029	time 0.5622 (0.6169)	model_time 0.5621 (0.6077)	loss 3.7456 (3.2900)	grad_norm 1.4331 (1.7206/0.6705)	mem 24308MB
[2025-01-18 21:21:51 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][190/312]	eta 0:01:15 lr 0.002028	time 0.5905 (0.6167)	model_time 0.5900 (0.6080)	loss 3.3910 (3.2949)	grad_norm 2.5375 (1.7038/0.6659)	mem 24308MB
[2025-01-18 21:21:57 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][200/312]	eta 0:01:09 lr 0.002027	time 0.5787 (0.6167)	model_time 0.5785 (0.6084)	loss 3.8759 (3.2857)	grad_norm 1.5790 (1.6971/0.6546)	mem 24308MB
[2025-01-18 21:22:03 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][210/312]	eta 0:01:02 lr 0.002027	time 0.5946 (0.6154)	model_time 0.5944 (0.6075)	loss 2.8929 (3.2850)	grad_norm 1.2526 (1.6893/0.6533)	mem 24308MB
[2025-01-18 21:22:09 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][220/312]	eta 0:00:56 lr 0.002026	time 0.5865 (0.6142)	model_time 0.5864 (0.6066)	loss 3.0291 (3.2705)	grad_norm 1.4057 (1.6881/0.6465)	mem 24308MB
[2025-01-18 21:22:15 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][230/312]	eta 0:00:50 lr 0.002025	time 0.5789 (0.6137)	model_time 0.5785 (0.6064)	loss 4.3841 (3.2796)	grad_norm 2.4187 (1.7074/0.6679)	mem 24308MB
[2025-01-18 21:22:21 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][240/312]	eta 0:00:44 lr 0.002025	time 0.5697 (0.6127)	model_time 0.5692 (0.6057)	loss 4.0771 (3.2810)	grad_norm 4.2628 (1.7397/0.7017)	mem 24308MB
[2025-01-18 21:22:27 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][250/312]	eta 0:00:37 lr 0.002024	time 0.6049 (0.6118)	model_time 0.6044 (0.6050)	loss 3.4204 (3.2737)	grad_norm 2.8856 (1.7818/0.7582)	mem 24308MB
[2025-01-18 21:22:33 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][260/312]	eta 0:00:31 lr 0.002023	time 0.5768 (0.6116)	model_time 0.5764 (0.6051)	loss 3.6052 (3.2613)	grad_norm 1.5531 (1.7711/0.7572)	mem 24308MB
[2025-01-18 21:22:39 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][270/312]	eta 0:00:25 lr 0.002023	time 0.6593 (0.6118)	model_time 0.6591 (0.6055)	loss 3.5355 (3.2593)	grad_norm 1.8067 (1.7610/0.7486)	mem 24308MB
[2025-01-18 21:22:45 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][280/312]	eta 0:00:19 lr 0.002022	time 0.5661 (0.6119)	model_time 0.5657 (0.6058)	loss 2.6768 (3.2705)	grad_norm 0.8689 (1.7480/0.7502)	mem 24308MB
[2025-01-18 21:22:52 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][290/312]	eta 0:00:13 lr 0.002021	time 0.6838 (0.6124)	model_time 0.6836 (0.6066)	loss 3.8839 (3.2848)	grad_norm 1.1266 (1.7256/0.7478)	mem 24308MB
[2025-01-18 21:22:58 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][300/312]	eta 0:00:07 lr 0.002021	time 0.5774 (0.6116)	model_time 0.5773 (0.6059)	loss 3.6976 (3.2926)	grad_norm 1.4856 (1.7142/0.7414)	mem 24308MB
[2025-01-18 21:23:04 internimage_s_1k_224] (main.py 510): INFO Train: [149/300][310/312]	eta 0:00:01 lr 0.002020	time 0.5778 (0.6111)	model_time 0.5777 (0.6056)	loss 3.7112 (3.3037)	grad_norm 1.4718 (1.7051/0.7355)	mem 24308MB
[2025-01-18 21:23:04 internimage_s_1k_224] (main.py 519): INFO EPOCH 149 training takes 0:03:10
[2025-01-18 21:23:04 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_149.pth saving......
[2025-01-18 21:23:06 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_149.pth saved !!!
[2025-01-18 21:23:13 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.212 (7.212)	Loss 0.8058 (0.8058)	Acc@1 82.446 (82.446)	Acc@5 96.777 (96.777)	Mem 24308MB
[2025-01-18 21:23:17 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.972)	Loss 1.1203 (0.9534)	Acc@1 74.609 (79.386)	Acc@5 93.335 (94.955)	Mem 24308MB
[2025-01-18 21:23:17 internimage_s_1k_224] (main.py 575): INFO [Epoch:149] * Acc@1 79.341 Acc@5 95.022
[2025-01-18 21:23:17 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.3%
[2025-01-18 21:23:17 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 79.34%
[2025-01-18 21:23:25 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.397 (8.397)	Loss 0.7130 (0.7130)	Acc@1 83.472 (83.472)	Acc@5 97.168 (97.168)	Mem 24308MB
[2025-01-18 21:23:29 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.139)	Loss 1.0329 (0.8470)	Acc@1 74.829 (80.134)	Acc@5 93.506 (95.275)	Mem 24308MB
[2025-01-18 21:23:30 internimage_s_1k_224] (main.py 575): INFO [Epoch:149] * Acc@1 80.004 Acc@5 95.304
[2025-01-18 21:23:30 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.0%
[2025-01-18 21:23:30 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 21:23:32 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 21:23:32 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.00%
[2025-01-18 21:23:34 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][0/312]	eta 0:10:33 lr 0.002020	time 2.0295 (2.0295)	model_time 0.6089 (0.6089)	loss 2.4511 (2.4511)	grad_norm 0.7114 (0.7114/0.0000)	mem 24308MB
[2025-01-18 21:23:40 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][10/312]	eta 0:03:47 lr 0.002019	time 0.6860 (0.7520)	model_time 0.6859 (0.6225)	loss 4.0109 (3.2178)	grad_norm 0.9088 (1.6805/0.6957)	mem 24308MB
[2025-01-18 21:23:46 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][20/312]	eta 0:03:17 lr 0.002019	time 0.5729 (0.6765)	model_time 0.5727 (0.6085)	loss 3.4157 (3.3184)	grad_norm 1.4864 (2.2723/1.2404)	mem 24308MB
[2025-01-18 21:23:52 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][30/312]	eta 0:03:02 lr 0.002018	time 0.5875 (0.6478)	model_time 0.5870 (0.6016)	loss 3.3859 (3.3856)	grad_norm 1.3817 (2.0331/1.1343)	mem 24308MB
[2025-01-18 21:23:58 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][40/312]	eta 0:02:53 lr 0.002017	time 0.6916 (0.6383)	model_time 0.6914 (0.6033)	loss 4.2533 (3.3892)	grad_norm 1.4080 (1.8119/1.0640)	mem 24308MB
[2025-01-18 21:24:04 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][50/312]	eta 0:02:45 lr 0.002017	time 0.6514 (0.6314)	model_time 0.6512 (0.6032)	loss 2.6264 (3.3649)	grad_norm 1.5400 (1.7033/0.9870)	mem 24308MB
[2025-01-18 21:24:10 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][60/312]	eta 0:02:37 lr 0.002016	time 0.5878 (0.6253)	model_time 0.5876 (0.6016)	loss 3.5387 (3.3800)	grad_norm 1.9871 (1.7186/0.9474)	mem 24308MB
[2025-01-18 21:24:16 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][70/312]	eta 0:02:30 lr 0.002015	time 0.6576 (0.6222)	model_time 0.6574 (0.6019)	loss 3.2995 (3.3485)	grad_norm 2.4304 (1.7334/0.9171)	mem 24308MB
[2025-01-18 21:24:22 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][80/312]	eta 0:02:24 lr 0.002015	time 0.5803 (0.6231)	model_time 0.5798 (0.6051)	loss 3.5824 (3.3278)	grad_norm 1.3103 (1.7828/0.8865)	mem 24308MB
[2025-01-18 21:24:28 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][90/312]	eta 0:02:17 lr 0.002014	time 0.5918 (0.6206)	model_time 0.5913 (0.6046)	loss 3.5819 (3.3587)	grad_norm 1.1966 (1.7156/0.8590)	mem 24308MB
[2025-01-18 21:24:35 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][100/312]	eta 0:02:11 lr 0.002013	time 0.5908 (0.6211)	model_time 0.5907 (0.6066)	loss 4.0626 (3.3383)	grad_norm 1.6485 (1.7017/0.8538)	mem 24308MB
[2025-01-18 21:24:41 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][110/312]	eta 0:02:05 lr 0.002013	time 0.5905 (0.6198)	model_time 0.5900 (0.6066)	loss 2.4197 (3.3300)	grad_norm 1.0830 (1.7001/0.8376)	mem 24308MB
[2025-01-18 21:24:47 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][120/312]	eta 0:01:58 lr 0.002012	time 0.5851 (0.6194)	model_time 0.5849 (0.6072)	loss 3.8969 (3.3193)	grad_norm 1.7574 (1.7848/0.9205)	mem 24308MB
[2025-01-18 21:24:53 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][130/312]	eta 0:01:52 lr 0.002011	time 0.6788 (0.6194)	model_time 0.6787 (0.6081)	loss 2.9939 (3.3219)	grad_norm 1.4790 (1.7893/0.8916)	mem 24308MB
[2025-01-18 21:24:59 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][140/312]	eta 0:01:46 lr 0.002011	time 0.5844 (0.6175)	model_time 0.5839 (0.6069)	loss 3.4877 (3.3450)	grad_norm 0.8956 (1.7783/0.8747)	mem 24308MB
[2025-01-18 21:25:05 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][150/312]	eta 0:01:39 lr 0.002010	time 0.5865 (0.6156)	model_time 0.5861 (0.6058)	loss 2.6179 (3.3534)	grad_norm 3.3287 (1.7901/0.8706)	mem 24308MB
[2025-01-18 21:25:11 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][160/312]	eta 0:01:33 lr 0.002009	time 0.6855 (0.6149)	model_time 0.6854 (0.6057)	loss 3.8942 (3.3634)	grad_norm 1.2045 (1.7977/0.8563)	mem 24308MB
[2025-01-18 21:25:17 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][170/312]	eta 0:01:27 lr 0.002009	time 0.5787 (0.6138)	model_time 0.5786 (0.6051)	loss 3.0979 (3.3704)	grad_norm 2.0087 (1.8074/0.8549)	mem 24308MB
[2025-01-18 21:25:23 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][180/312]	eta 0:01:20 lr 0.002008	time 0.5719 (0.6127)	model_time 0.5715 (0.6044)	loss 2.2919 (3.3561)	grad_norm 0.9511 (1.7733/0.8445)	mem 24308MB
[2025-01-18 21:25:29 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][190/312]	eta 0:01:14 lr 0.002007	time 0.5862 (0.6118)	model_time 0.5860 (0.6040)	loss 3.6831 (3.3438)	grad_norm 1.7641 (1.7708/0.8376)	mem 24308MB
[2025-01-18 21:25:35 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][200/312]	eta 0:01:08 lr 0.002007	time 0.5766 (0.6127)	model_time 0.5764 (0.6052)	loss 3.7082 (3.3478)	grad_norm 1.1412 (1.7454/0.8260)	mem 24308MB
[2025-01-18 21:25:41 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][210/312]	eta 0:01:02 lr 0.002006	time 0.6416 (0.6121)	model_time 0.6411 (0.6050)	loss 3.8655 (3.3585)	grad_norm 1.9793 (1.7377/0.8118)	mem 24308MB
[2025-01-18 21:25:47 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][220/312]	eta 0:00:56 lr 0.002005	time 0.6722 (0.6125)	model_time 0.6720 (0.6057)	loss 3.7436 (3.3622)	grad_norm 1.8339 (1.7373/0.7952)	mem 24308MB
[2025-01-18 21:25:53 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][230/312]	eta 0:00:50 lr 0.002005	time 0.5919 (0.6132)	model_time 0.5917 (0.6066)	loss 2.5686 (3.3612)	grad_norm 2.9189 (1.7831/0.8580)	mem 24308MB
[2025-01-18 21:26:00 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][240/312]	eta 0:00:44 lr 0.002004	time 0.5823 (0.6133)	model_time 0.5819 (0.6070)	loss 4.3056 (3.3688)	grad_norm 1.8515 (1.7706/0.8476)	mem 24308MB
[2025-01-18 21:26:06 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][250/312]	eta 0:00:38 lr 0.002003	time 0.6693 (0.6136)	model_time 0.6688 (0.6076)	loss 3.3557 (3.3691)	grad_norm 1.0106 (1.7558/0.8350)	mem 24308MB
[2025-01-18 21:26:12 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][260/312]	eta 0:00:31 lr 0.002003	time 0.5845 (0.6131)	model_time 0.5843 (0.6072)	loss 3.0813 (3.3551)	grad_norm 1.1727 (1.7534/0.8264)	mem 24308MB
[2025-01-18 21:26:18 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][270/312]	eta 0:00:25 lr 0.002002	time 0.5995 (0.6122)	model_time 0.5994 (0.6066)	loss 3.4056 (3.3446)	grad_norm 1.7210 (1.7414/0.8204)	mem 24308MB
[2025-01-18 21:26:24 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][280/312]	eta 0:00:19 lr 0.002001	time 0.5829 (0.6120)	model_time 0.5827 (0.6065)	loss 3.3446 (3.3469)	grad_norm 0.8306 (1.7281/0.8142)	mem 24308MB
[2025-01-18 21:26:30 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][290/312]	eta 0:00:13 lr 0.002001	time 0.5958 (0.6119)	model_time 0.5954 (0.6066)	loss 3.1746 (3.3468)	grad_norm 1.1271 (1.7073/0.8097)	mem 24308MB
[2025-01-18 21:26:36 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][300/312]	eta 0:00:07 lr 0.002000	time 0.5668 (0.6108)	model_time 0.5667 (0.6057)	loss 3.2223 (3.3448)	grad_norm 2.3027 (1.7192/0.8042)	mem 24308MB
[2025-01-18 21:26:41 internimage_s_1k_224] (main.py 510): INFO Train: [150/300][310/312]	eta 0:00:01 lr 0.001999	time 0.5698 (0.6100)	model_time 0.5698 (0.6050)	loss 3.8155 (3.3476)	grad_norm 2.1958 (1.7284/0.8031)	mem 24308MB
[2025-01-18 21:26:42 internimage_s_1k_224] (main.py 519): INFO EPOCH 150 training takes 0:03:10
[2025-01-18 21:26:42 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_150.pth saving......
[2025-01-18 21:26:44 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_150.pth saved !!!
[2025-01-18 21:26:51 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.512 (7.512)	Loss 0.8575 (0.8575)	Acc@1 82.544 (82.544)	Acc@5 96.802 (96.802)	Mem 24308MB
[2025-01-18 21:26:55 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.990)	Loss 1.1594 (0.9834)	Acc@1 74.927 (79.519)	Acc@5 92.920 (95.077)	Mem 24308MB
[2025-01-18 21:26:55 internimage_s_1k_224] (main.py 575): INFO [Epoch:150] * Acc@1 79.403 Acc@5 95.090
[2025-01-18 21:26:55 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.4%
[2025-01-18 21:26:55 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 21:26:57 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 21:26:57 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 79.40%
[2025-01-18 21:27:04 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.176 (7.176)	Loss 0.7128 (0.7128)	Acc@1 83.569 (83.569)	Acc@5 97.119 (97.119)	Mem 24308MB
[2025-01-18 21:27:07 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.940)	Loss 1.0306 (0.8458)	Acc@1 75.000 (80.194)	Acc@5 93.579 (95.304)	Mem 24308MB
[2025-01-18 21:27:08 internimage_s_1k_224] (main.py 575): INFO [Epoch:150] * Acc@1 80.054 Acc@5 95.329
[2025-01-18 21:27:08 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.1%
[2025-01-18 21:27:08 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 21:27:10 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 21:27:10 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.05%
[2025-01-18 21:27:12 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][0/312]	eta 0:10:59 lr 0.001999	time 2.1129 (2.1129)	model_time 0.5870 (0.5870)	loss 2.9171 (2.9171)	grad_norm 3.0695 (3.0695/0.0000)	mem 24308MB
[2025-01-18 21:27:18 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][10/312]	eta 0:03:50 lr 0.001999	time 0.5804 (0.7623)	model_time 0.5802 (0.6233)	loss 3.8890 (3.0661)	grad_norm 2.1145 (1.9831/0.6438)	mem 24308MB
[2025-01-18 21:27:24 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][20/312]	eta 0:03:22 lr 0.001998	time 0.6902 (0.6934)	model_time 0.6901 (0.6204)	loss 2.5168 (3.1136)	grad_norm 1.1237 (2.0548/0.6290)	mem 24308MB
[2025-01-18 21:27:30 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][30/312]	eta 0:03:09 lr 0.001997	time 0.6534 (0.6722)	model_time 0.6531 (0.6226)	loss 2.9672 (3.2335)	grad_norm 2.2343 (2.1220/0.6608)	mem 24308MB
[2025-01-18 21:27:37 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][40/312]	eta 0:02:59 lr 0.001997	time 0.5949 (0.6599)	model_time 0.5945 (0.6223)	loss 3.6613 (3.2246)	grad_norm 1.1111 (1.9325/0.6975)	mem 24308MB
[2025-01-18 21:27:43 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][50/312]	eta 0:02:51 lr 0.001996	time 0.6005 (0.6528)	model_time 0.6004 (0.6225)	loss 4.1319 (3.3013)	grad_norm 1.3460 (1.9251/0.7679)	mem 24308MB
[2025-01-18 21:27:49 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][60/312]	eta 0:02:42 lr 0.001995	time 0.5883 (0.6446)	model_time 0.5881 (0.6193)	loss 3.3440 (3.2734)	grad_norm 2.4616 (1.8378/0.7498)	mem 24308MB
[2025-01-18 21:27:55 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][70/312]	eta 0:02:34 lr 0.001995	time 0.5842 (0.6400)	model_time 0.5838 (0.6181)	loss 3.7257 (3.3024)	grad_norm 2.2019 (1.9038/0.7571)	mem 24308MB
[2025-01-18 21:28:01 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][80/312]	eta 0:02:26 lr 0.001994	time 0.5732 (0.6333)	model_time 0.5731 (0.6140)	loss 3.4318 (3.2524)	grad_norm 3.1074 (2.0195/0.9317)	mem 24308MB
[2025-01-18 21:28:07 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][90/312]	eta 0:02:19 lr 0.001993	time 0.5828 (0.6297)	model_time 0.5826 (0.6124)	loss 3.7462 (3.2572)	grad_norm 2.0931 (1.9790/0.8945)	mem 24308MB
[2025-01-18 21:28:13 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][100/312]	eta 0:02:13 lr 0.001993	time 0.5802 (0.6278)	model_time 0.5800 (0.6123)	loss 2.5363 (3.2578)	grad_norm 0.9184 (1.9004/0.8861)	mem 24308MB
[2025-01-18 21:28:19 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][110/312]	eta 0:02:06 lr 0.001992	time 0.6035 (0.6248)	model_time 0.6034 (0.6106)	loss 3.2169 (3.2773)	grad_norm 1.3589 (1.8319/0.8744)	mem 24308MB
[2025-01-18 21:28:25 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][120/312]	eta 0:01:59 lr 0.001991	time 0.5883 (0.6230)	model_time 0.5879 (0.6100)	loss 2.6831 (3.2754)	grad_norm 3.0243 (1.8396/0.8847)	mem 24308MB
[2025-01-18 21:28:31 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][130/312]	eta 0:01:53 lr 0.001991	time 0.6849 (0.6233)	model_time 0.6847 (0.6112)	loss 2.2676 (3.2930)	grad_norm 1.5836 (1.8850/0.9342)	mem 24308MB
[2025-01-18 21:28:37 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][140/312]	eta 0:01:46 lr 0.001990	time 0.5725 (0.6216)	model_time 0.5724 (0.6103)	loss 4.2448 (3.2961)	grad_norm 1.8170 (1.8469/0.9136)	mem 24308MB
[2025-01-18 21:28:44 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][150/312]	eta 0:01:40 lr 0.001989	time 0.5878 (0.6225)	model_time 0.5877 (0.6120)	loss 4.2202 (3.3075)	grad_norm 0.7557 (1.8275/0.9027)	mem 24308MB
[2025-01-18 21:28:50 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][160/312]	eta 0:01:34 lr 0.001989	time 0.5733 (0.6237)	model_time 0.5728 (0.6138)	loss 3.5681 (3.3208)	grad_norm 1.7886 (1.8212/0.8814)	mem 24308MB
[2025-01-18 21:28:56 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][170/312]	eta 0:01:28 lr 0.001988	time 0.5806 (0.6231)	model_time 0.5801 (0.6137)	loss 3.2422 (3.3219)	grad_norm 0.9142 (1.7932/0.8686)	mem 24308MB
[2025-01-18 21:29:02 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][180/312]	eta 0:01:22 lr 0.001987	time 0.5736 (0.6223)	model_time 0.5730 (0.6134)	loss 3.4680 (3.3321)	grad_norm 1.1504 (1.7768/0.8496)	mem 24308MB
[2025-01-18 21:29:08 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][190/312]	eta 0:01:15 lr 0.001987	time 0.5844 (0.6217)	model_time 0.5840 (0.6133)	loss 3.5439 (3.3192)	grad_norm 1.8333 (1.8245/0.8806)	mem 24308MB
[2025-01-18 21:29:14 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][200/312]	eta 0:01:09 lr 0.001986	time 0.5833 (0.6200)	model_time 0.5832 (0.6120)	loss 2.3652 (3.3207)	grad_norm 1.0502 (1.7888/0.8737)	mem 24308MB
[2025-01-18 21:29:20 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][210/312]	eta 0:01:03 lr 0.001985	time 0.7345 (0.6195)	model_time 0.7343 (0.6118)	loss 3.2950 (3.3144)	grad_norm 1.6987 (1.7909/0.8601)	mem 24308MB
[2025-01-18 21:29:26 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][220/312]	eta 0:00:56 lr 0.001985	time 0.6744 (0.6190)	model_time 0.6742 (0.6117)	loss 2.9307 (3.3255)	grad_norm 1.6541 (1.7959/0.8560)	mem 24308MB
[2025-01-18 21:29:32 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][230/312]	eta 0:00:50 lr 0.001984	time 0.5818 (0.6177)	model_time 0.5813 (0.6107)	loss 3.6339 (3.3257)	grad_norm 2.9382 (1.8073/0.8528)	mem 24308MB
[2025-01-18 21:29:38 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][240/312]	eta 0:00:44 lr 0.001983	time 0.5843 (0.6173)	model_time 0.5841 (0.6106)	loss 3.7778 (3.3279)	grad_norm 1.1565 (1.8443/0.9115)	mem 24308MB
[2025-01-18 21:29:45 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][250/312]	eta 0:00:38 lr 0.001983	time 0.6487 (0.6174)	model_time 0.6482 (0.6109)	loss 3.4091 (3.3316)	grad_norm 1.9184 (1.8452/0.9060)	mem 24308MB
[2025-01-18 21:29:51 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][260/312]	eta 0:00:32 lr 0.001982	time 0.5902 (0.6169)	model_time 0.5901 (0.6106)	loss 3.9460 (3.3270)	grad_norm 1.0802 (1.8359/0.8944)	mem 24308MB
[2025-01-18 21:29:57 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][270/312]	eta 0:00:25 lr 0.001981	time 0.5840 (0.6166)	model_time 0.5835 (0.6106)	loss 3.5121 (3.3275)	grad_norm 1.9031 (1.8314/0.8871)	mem 24308MB
[2025-01-18 21:30:03 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][280/312]	eta 0:00:19 lr 0.001981	time 0.7016 (0.6172)	model_time 0.7015 (0.6114)	loss 4.4355 (3.3287)	grad_norm 2.2246 (1.8228/0.8765)	mem 24308MB
[2025-01-18 21:30:09 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][290/312]	eta 0:00:13 lr 0.001980	time 0.5832 (0.6173)	model_time 0.5830 (0.6116)	loss 3.6293 (3.3314)	grad_norm 1.7976 (1.8122/0.8668)	mem 24308MB
[2025-01-18 21:30:15 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][300/312]	eta 0:00:07 lr 0.001979	time 0.5676 (0.6169)	model_time 0.5675 (0.6114)	loss 4.0254 (3.3351)	grad_norm 2.0730 (1.7929/0.8568)	mem 24308MB
[2025-01-18 21:30:21 internimage_s_1k_224] (main.py 510): INFO Train: [151/300][310/312]	eta 0:00:01 lr 0.001979	time 0.5658 (0.6165)	model_time 0.5657 (0.6112)	loss 3.0401 (3.3378)	grad_norm 1.1272 (1.7860/0.8535)	mem 24308MB
[2025-01-18 21:30:22 internimage_s_1k_224] (main.py 519): INFO EPOCH 151 training takes 0:03:12
[2025-01-18 21:30:22 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_151.pth saving......
[2025-01-18 21:30:24 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_151.pth saved !!!
[2025-01-18 21:30:31 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.437 (7.437)	Loss 0.8304 (0.8304)	Acc@1 83.130 (83.130)	Acc@5 96.484 (96.484)	Mem 24308MB
[2025-01-18 21:30:35 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.983)	Loss 1.1019 (0.9612)	Acc@1 75.806 (79.654)	Acc@5 93.628 (95.053)	Mem 24308MB
[2025-01-18 21:30:35 internimage_s_1k_224] (main.py 575): INFO [Epoch:151] * Acc@1 79.531 Acc@5 95.074
[2025-01-18 21:30:35 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.5%
[2025-01-18 21:30:35 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 21:30:37 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 21:30:37 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 79.53%
[2025-01-18 21:30:44 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.215 (7.215)	Loss 0.7127 (0.7127)	Acc@1 83.545 (83.545)	Acc@5 97.192 (97.192)	Mem 24308MB
[2025-01-18 21:30:47 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.977)	Loss 1.0286 (0.8447)	Acc@1 75.049 (80.247)	Acc@5 93.604 (95.317)	Mem 24308MB
[2025-01-18 21:30:47 internimage_s_1k_224] (main.py 575): INFO [Epoch:151] * Acc@1 80.110 Acc@5 95.345
[2025-01-18 21:30:47 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.1%
[2025-01-18 21:30:47 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 21:30:50 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 21:30:50 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.11%
[2025-01-18 21:30:52 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][0/312]	eta 0:10:52 lr 0.001979	time 2.0915 (2.0915)	model_time 0.6036 (0.6036)	loss 3.7520 (3.7520)	grad_norm 0.9937 (0.9937/0.0000)	mem 24308MB
[2025-01-18 21:30:58 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][10/312]	eta 0:03:39 lr 0.001978	time 0.5905 (0.7284)	model_time 0.5900 (0.5928)	loss 3.3010 (3.4737)	grad_norm 1.4996 (1.3907/0.4200)	mem 24308MB
[2025-01-18 21:31:04 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][20/312]	eta 0:03:14 lr 0.001977	time 0.7192 (0.6669)	model_time 0.7190 (0.5957)	loss 3.8614 (3.4069)	grad_norm 1.7104 (1.4557/0.4091)	mem 24308MB
[2025-01-18 21:31:10 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][30/312]	eta 0:03:01 lr 0.001977	time 0.5868 (0.6433)	model_time 0.5867 (0.5950)	loss 3.1217 (3.3305)	grad_norm 2.5617 (1.4643/0.4074)	mem 24308MB
[2025-01-18 21:31:16 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][40/312]	eta 0:02:52 lr 0.001976	time 0.5830 (0.6327)	model_time 0.5826 (0.5961)	loss 3.4742 (3.3063)	grad_norm 2.3763 (1.7629/0.7056)	mem 24308MB
[2025-01-18 21:31:22 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][50/312]	eta 0:02:44 lr 0.001975	time 0.6523 (0.6267)	model_time 0.6519 (0.5971)	loss 3.7505 (3.3685)	grad_norm 2.5568 (1.7590/0.7085)	mem 24308MB
[2025-01-18 21:31:28 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][60/312]	eta 0:02:37 lr 0.001975	time 0.5815 (0.6239)	model_time 0.5813 (0.5991)	loss 3.1798 (3.3707)	grad_norm 1.4605 (1.7071/0.6820)	mem 24308MB
[2025-01-18 21:31:34 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][70/312]	eta 0:02:30 lr 0.001974	time 0.5757 (0.6218)	model_time 0.5755 (0.6004)	loss 4.0000 (3.3673)	grad_norm 1.3166 (1.6719/0.6500)	mem 24308MB
[2025-01-18 21:31:40 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][80/312]	eta 0:02:24 lr 0.001973	time 0.6602 (0.6216)	model_time 0.6598 (0.6029)	loss 3.0739 (3.3513)	grad_norm 1.8255 (1.6663/0.6251)	mem 24308MB
[2025-01-18 21:31:46 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][90/312]	eta 0:02:17 lr 0.001973	time 0.5740 (0.6213)	model_time 0.5735 (0.6046)	loss 2.3260 (3.3170)	grad_norm 1.5115 (1.6428/0.6019)	mem 24308MB
[2025-01-18 21:31:52 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][100/312]	eta 0:02:11 lr 0.001972	time 0.5774 (0.6204)	model_time 0.5649 (0.6052)	loss 2.4071 (3.3335)	grad_norm 1.5170 (1.6025/0.5886)	mem 24308MB
[2025-01-18 21:31:59 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][110/312]	eta 0:02:05 lr 0.001971	time 0.5722 (0.6196)	model_time 0.5717 (0.6057)	loss 3.3869 (3.3396)	grad_norm 1.3828 (1.7140/0.7618)	mem 24308MB
[2025-01-18 21:32:05 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][120/312]	eta 0:01:58 lr 0.001971	time 0.5811 (0.6183)	model_time 0.5806 (0.6055)	loss 3.6108 (3.3468)	grad_norm 2.0952 (1.7462/0.7680)	mem 24308MB
[2025-01-18 21:32:10 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][130/312]	eta 0:01:52 lr 0.001970	time 0.5835 (0.6158)	model_time 0.5831 (0.6040)	loss 3.6908 (3.3364)	grad_norm 0.9827 (1.7162/0.7514)	mem 24308MB
[2025-01-18 21:32:16 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][140/312]	eta 0:01:45 lr 0.001969	time 0.5822 (0.6144)	model_time 0.5821 (0.6033)	loss 3.1650 (3.3273)	grad_norm 2.2124 (1.7509/0.7699)	mem 24308MB
[2025-01-18 21:32:22 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][150/312]	eta 0:01:39 lr 0.001969	time 0.5736 (0.6140)	model_time 0.5734 (0.6037)	loss 3.3781 (3.3096)	grad_norm 1.0171 (1.7443/0.7595)	mem 24308MB
[2025-01-18 21:32:28 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][160/312]	eta 0:01:33 lr 0.001968	time 0.5870 (0.6129)	model_time 0.5869 (0.6032)	loss 3.7463 (3.3156)	grad_norm 2.3348 (1.7345/0.7497)	mem 24308MB
[2025-01-18 21:32:34 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][170/312]	eta 0:01:26 lr 0.001967	time 0.5945 (0.6120)	model_time 0.5940 (0.6028)	loss 3.9539 (3.3184)	grad_norm 1.4914 (1.7710/0.8410)	mem 24308MB
[2025-01-18 21:32:41 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][180/312]	eta 0:01:20 lr 0.001967	time 0.6724 (0.6122)	model_time 0.6723 (0.6036)	loss 3.4692 (3.3230)	grad_norm 0.9347 (1.7632/0.8335)	mem 24308MB
[2025-01-18 21:32:47 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][190/312]	eta 0:01:14 lr 0.001966	time 0.5753 (0.6123)	model_time 0.5749 (0.6040)	loss 3.3484 (3.3251)	grad_norm 5.7182 (1.8160/0.9080)	mem 24308MB
[2025-01-18 21:32:53 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][200/312]	eta 0:01:08 lr 0.001965	time 0.6712 (0.6125)	model_time 0.6710 (0.6047)	loss 3.7270 (3.3280)	grad_norm 0.9884 (1.8186/0.8918)	mem 24308MB
[2025-01-18 21:32:59 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][210/312]	eta 0:01:02 lr 0.001965	time 0.5756 (0.6127)	model_time 0.5755 (0.6052)	loss 3.5439 (3.3219)	grad_norm 1.0946 (1.8031/0.8817)	mem 24308MB
[2025-01-18 21:33:05 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][220/312]	eta 0:00:56 lr 0.001964	time 0.5810 (0.6122)	model_time 0.5808 (0.6051)	loss 2.6618 (3.3256)	grad_norm 1.7314 (1.7859/0.8691)	mem 24308MB
[2025-01-18 21:33:11 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][230/312]	eta 0:00:50 lr 0.001963	time 0.5717 (0.6126)	model_time 0.5712 (0.6057)	loss 2.8519 (3.3187)	grad_norm 1.7147 (1.7812/0.8562)	mem 24308MB
[2025-01-18 21:33:17 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][240/312]	eta 0:00:44 lr 0.001963	time 0.5807 (0.6122)	model_time 0.5805 (0.6056)	loss 3.4124 (3.3225)	grad_norm 1.0582 (1.7798/0.8449)	mem 24308MB
[2025-01-18 21:33:23 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][250/312]	eta 0:00:37 lr 0.001962	time 0.5869 (0.6114)	model_time 0.5868 (0.6051)	loss 3.0035 (3.3275)	grad_norm 0.9141 (1.7544/0.8383)	mem 24308MB
[2025-01-18 21:33:29 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][260/312]	eta 0:00:31 lr 0.001961	time 0.5988 (0.6109)	model_time 0.5986 (0.6048)	loss 3.8673 (3.3171)	grad_norm 2.8911 (1.7720/0.8531)	mem 24308MB
[2025-01-18 21:33:35 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][270/312]	eta 0:00:25 lr 0.001961	time 0.5857 (0.6107)	model_time 0.5855 (0.6048)	loss 3.6436 (3.3252)	grad_norm 1.6716 (1.7715/0.8502)	mem 24308MB
[2025-01-18 21:33:41 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][280/312]	eta 0:00:19 lr 0.001960	time 0.5766 (0.6102)	model_time 0.5761 (0.6044)	loss 2.8177 (3.3271)	grad_norm 1.7128 (1.7857/0.8494)	mem 24308MB
[2025-01-18 21:33:47 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][290/312]	eta 0:00:13 lr 0.001959	time 0.6010 (0.6098)	model_time 0.6008 (0.6043)	loss 3.4517 (3.3316)	grad_norm 1.4694 (1.8059/0.8623)	mem 24308MB
[2025-01-18 21:33:53 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][300/312]	eta 0:00:07 lr 0.001959	time 0.5676 (0.6097)	model_time 0.5675 (0.6044)	loss 2.7821 (3.3325)	grad_norm 3.5781 (1.8122/0.8629)	mem 24308MB
[2025-01-18 21:33:59 internimage_s_1k_224] (main.py 510): INFO Train: [152/300][310/312]	eta 0:00:01 lr 0.001958	time 0.5724 (0.6097)	model_time 0.5723 (0.6045)	loss 2.5740 (3.3255)	grad_norm 1.4328 (1.8237/0.8624)	mem 24308MB
[2025-01-18 21:34:00 internimage_s_1k_224] (main.py 519): INFO EPOCH 152 training takes 0:03:10
[2025-01-18 21:34:00 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_152.pth saving......
[2025-01-18 21:34:02 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_152.pth saved !!!
[2025-01-18 21:34:09 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.338 (7.338)	Loss 0.8480 (0.8480)	Acc@1 82.349 (82.349)	Acc@5 96.558 (96.558)	Mem 24308MB
[2025-01-18 21:34:13 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.983)	Loss 1.1357 (0.9565)	Acc@1 74.023 (79.512)	Acc@5 93.213 (95.037)	Mem 24308MB
[2025-01-18 21:34:13 internimage_s_1k_224] (main.py 575): INFO [Epoch:152] * Acc@1 79.437 Acc@5 95.046
[2025-01-18 21:34:13 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.4%
[2025-01-18 21:34:13 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 79.53%
[2025-01-18 21:34:21 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.396 (8.396)	Loss 0.7127 (0.7127)	Acc@1 83.496 (83.496)	Acc@5 97.217 (97.217)	Mem 24308MB
[2025-01-18 21:34:26 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.158)	Loss 1.0266 (0.8436)	Acc@1 75.049 (80.273)	Acc@5 93.604 (95.339)	Mem 24308MB
[2025-01-18 21:34:26 internimage_s_1k_224] (main.py 575): INFO [Epoch:152] * Acc@1 80.140 Acc@5 95.371
[2025-01-18 21:34:26 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.1%
[2025-01-18 21:34:26 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 21:34:28 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 21:34:28 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.14%
[2025-01-18 21:34:31 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][0/312]	eta 0:14:56 lr 0.001958	time 2.8733 (2.8733)	model_time 0.6151 (0.6151)	loss 3.1432 (3.1432)	grad_norm 1.3128 (1.3128/0.0000)	mem 24308MB
[2025-01-18 21:34:37 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][10/312]	eta 0:04:07 lr 0.001957	time 0.5922 (0.8185)	model_time 0.5917 (0.6128)	loss 3.4305 (3.4125)	grad_norm 2.4938 (1.9223/0.6330)	mem 24308MB
[2025-01-18 21:34:43 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][20/312]	eta 0:03:31 lr 0.001956	time 0.6017 (0.7239)	model_time 0.6016 (0.6161)	loss 2.7180 (3.4671)	grad_norm 1.1015 (1.6385/0.7149)	mem 24308MB
[2025-01-18 21:34:49 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][30/312]	eta 0:03:13 lr 0.001956	time 0.5851 (0.6861)	model_time 0.5849 (0.6129)	loss 2.3987 (3.4306)	grad_norm 1.6026 (1.6730/0.7496)	mem 24308MB
[2025-01-18 21:34:55 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][40/312]	eta 0:03:02 lr 0.001955	time 0.6759 (0.6694)	model_time 0.6755 (0.6140)	loss 3.1349 (3.4298)	grad_norm 1.3986 (1.6495/0.6710)	mem 24308MB
[2025-01-18 21:35:01 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][50/312]	eta 0:02:51 lr 0.001954	time 0.6003 (0.6564)	model_time 0.5999 (0.6118)	loss 2.8863 (3.4204)	grad_norm 3.3391 (1.7391/0.7213)	mem 24308MB
[2025-01-18 21:35:07 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][60/312]	eta 0:02:42 lr 0.001954	time 0.5753 (0.6453)	model_time 0.5752 (0.6079)	loss 3.9182 (3.4543)	grad_norm 1.1440 (1.7636/0.7173)	mem 24308MB
[2025-01-18 21:35:13 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][70/312]	eta 0:02:34 lr 0.001953	time 0.6103 (0.6388)	model_time 0.6101 (0.6067)	loss 3.6905 (3.4182)	grad_norm 3.8963 (1.8794/0.8282)	mem 24308MB
[2025-01-18 21:35:19 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][80/312]	eta 0:02:27 lr 0.001952	time 0.5748 (0.6344)	model_time 0.5746 (0.6061)	loss 2.4701 (3.3824)	grad_norm 1.6369 (1.8689/0.8348)	mem 24308MB
[2025-01-18 21:35:25 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][90/312]	eta 0:02:19 lr 0.001952	time 0.5734 (0.6303)	model_time 0.5732 (0.6051)	loss 3.9906 (3.3871)	grad_norm 1.3420 (1.7951/0.8207)	mem 24308MB
[2025-01-18 21:35:31 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][100/312]	eta 0:02:12 lr 0.001951	time 0.5829 (0.6268)	model_time 0.5828 (0.6041)	loss 3.1896 (3.3658)	grad_norm 0.9735 (1.7472/0.8034)	mem 24308MB
[2025-01-18 21:35:37 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][110/312]	eta 0:02:06 lr 0.001951	time 0.5812 (0.6257)	model_time 0.5810 (0.6050)	loss 3.7598 (3.3601)	grad_norm 1.0443 (1.7034/0.7854)	mem 24308MB
[2025-01-18 21:35:44 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][120/312]	eta 0:02:00 lr 0.001950	time 0.6741 (0.6262)	model_time 0.6740 (0.6071)	loss 3.3507 (3.3631)	grad_norm 1.7856 (1.7231/0.7812)	mem 24308MB
[2025-01-18 21:35:50 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][130/312]	eta 0:01:53 lr 0.001949	time 0.5720 (0.6252)	model_time 0.5718 (0.6076)	loss 3.8804 (3.3650)	grad_norm 2.1563 (1.7279/0.7560)	mem 24308MB
[2025-01-18 21:35:56 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][140/312]	eta 0:01:47 lr 0.001949	time 0.5682 (0.6244)	model_time 0.5678 (0.6080)	loss 3.7126 (3.3726)	grad_norm 1.4073 (1.7279/0.7375)	mem 24308MB
[2025-01-18 21:36:02 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][150/312]	eta 0:01:40 lr 0.001948	time 0.6820 (0.6232)	model_time 0.6818 (0.6079)	loss 3.8911 (3.3631)	grad_norm 2.7153 (1.7324/0.7293)	mem 24308MB
[2025-01-18 21:36:08 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][160/312]	eta 0:01:34 lr 0.001947	time 0.5798 (0.6224)	model_time 0.5793 (0.6080)	loss 3.8832 (3.3582)	grad_norm 3.1758 (1.7577/0.7540)	mem 24308MB
[2025-01-18 21:36:14 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][170/312]	eta 0:01:28 lr 0.001947	time 0.5781 (0.6215)	model_time 0.5776 (0.6079)	loss 3.4225 (3.3621)	grad_norm 1.6712 (1.7569/0.7380)	mem 24308MB
[2025-01-18 21:36:20 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][180/312]	eta 0:01:21 lr 0.001946	time 0.5818 (0.6196)	model_time 0.5817 (0.6068)	loss 3.3647 (3.3633)	grad_norm 1.3696 (1.7998/0.7705)	mem 24308MB
[2025-01-18 21:36:26 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][190/312]	eta 0:01:15 lr 0.001945	time 0.5922 (0.6181)	model_time 0.5917 (0.6059)	loss 3.6237 (3.3468)	grad_norm 1.5311 (1.8257/0.7967)	mem 24308MB
[2025-01-18 21:36:32 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][200/312]	eta 0:01:09 lr 0.001945	time 0.5877 (0.6174)	model_time 0.5872 (0.6058)	loss 4.0344 (3.3506)	grad_norm 2.0280 (1.8369/0.7971)	mem 24308MB
[2025-01-18 21:36:38 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][210/312]	eta 0:01:02 lr 0.001944	time 0.5917 (0.6167)	model_time 0.5915 (0.6057)	loss 3.1493 (3.3496)	grad_norm 0.9696 (1.8200/0.7849)	mem 24308MB
[2025-01-18 21:36:44 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][220/312]	eta 0:00:56 lr 0.001943	time 0.5791 (0.6158)	model_time 0.5789 (0.6052)	loss 3.0679 (3.3422)	grad_norm 1.8585 (1.8029/0.7759)	mem 24308MB
[2025-01-18 21:36:50 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][230/312]	eta 0:00:50 lr 0.001943	time 0.5799 (0.6153)	model_time 0.5797 (0.6052)	loss 3.1713 (3.3380)	grad_norm 0.9965 (1.7973/0.7672)	mem 24308MB
[2025-01-18 21:36:56 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][240/312]	eta 0:00:44 lr 0.001942	time 0.6516 (0.6160)	model_time 0.6512 (0.6062)	loss 2.9260 (3.3285)	grad_norm 1.3554 (1.8061/0.7697)	mem 24308MB
[2025-01-18 21:37:02 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][250/312]	eta 0:00:38 lr 0.001941	time 0.5848 (0.6162)	model_time 0.5846 (0.6068)	loss 3.2667 (3.3270)	grad_norm 1.3225 (1.8201/0.7853)	mem 24308MB
[2025-01-18 21:37:09 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][260/312]	eta 0:00:32 lr 0.001941	time 0.5716 (0.6159)	model_time 0.5714 (0.6068)	loss 2.5000 (3.3299)	grad_norm 1.8244 (1.8194/0.7795)	mem 24308MB
[2025-01-18 21:37:15 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][270/312]	eta 0:00:25 lr 0.001940	time 0.7072 (0.6158)	model_time 0.7070 (0.6071)	loss 3.8684 (3.3350)	grad_norm 3.0327 (1.8230/0.7736)	mem 24308MB
[2025-01-18 21:37:21 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][280/312]	eta 0:00:19 lr 0.001939	time 0.6809 (0.6157)	model_time 0.6805 (0.6073)	loss 3.7668 (3.3430)	grad_norm 1.3265 (1.8124/0.7694)	mem 24308MB
[2025-01-18 21:37:27 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][290/312]	eta 0:00:13 lr 0.001939	time 0.6229 (0.6154)	model_time 0.6227 (0.6073)	loss 4.1786 (3.3408)	grad_norm 1.6819 (1.8015/0.7609)	mem 24308MB
[2025-01-18 21:37:33 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][300/312]	eta 0:00:07 lr 0.001938	time 0.5652 (0.6146)	model_time 0.5651 (0.6067)	loss 4.0175 (3.3443)	grad_norm 0.7389 (1.7939/0.7535)	mem 24308MB
[2025-01-18 21:37:39 internimage_s_1k_224] (main.py 510): INFO Train: [153/300][310/312]	eta 0:00:01 lr 0.001937	time 0.5613 (0.6132)	model_time 0.5612 (0.6056)	loss 4.3026 (3.3488)	grad_norm 0.9601 (1.7684/0.7531)	mem 24308MB
[2025-01-18 21:37:39 internimage_s_1k_224] (main.py 519): INFO EPOCH 153 training takes 0:03:11
[2025-01-18 21:37:39 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_153.pth saving......
[2025-01-18 21:37:41 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_153.pth saved !!!
[2025-01-18 21:37:48 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.466 (7.466)	Loss 0.8088 (0.8088)	Acc@1 82.275 (82.275)	Acc@5 96.533 (96.533)	Mem 24308MB
[2025-01-18 21:37:52 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.001)	Loss 1.0991 (0.9367)	Acc@1 74.902 (79.499)	Acc@5 93.750 (95.150)	Mem 24308MB
[2025-01-18 21:37:52 internimage_s_1k_224] (main.py 575): INFO [Epoch:153] * Acc@1 79.425 Acc@5 95.170
[2025-01-18 21:37:52 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.4%
[2025-01-18 21:37:52 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 79.53%
[2025-01-18 21:38:00 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.351 (8.351)	Loss 0.7127 (0.7127)	Acc@1 83.545 (83.545)	Acc@5 97.192 (97.192)	Mem 24308MB
[2025-01-18 21:38:05 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.142)	Loss 1.0246 (0.8424)	Acc@1 75.195 (80.333)	Acc@5 93.628 (95.359)	Mem 24308MB
[2025-01-18 21:38:05 internimage_s_1k_224] (main.py 575): INFO [Epoch:153] * Acc@1 80.208 Acc@5 95.391
[2025-01-18 21:38:05 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.2%
[2025-01-18 21:38:05 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 21:38:07 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 21:38:07 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.21%
[2025-01-18 21:38:09 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][0/312]	eta 0:11:32 lr 0.001937	time 2.2210 (2.2210)	model_time 0.6227 (0.6227)	loss 3.4248 (3.4248)	grad_norm 2.6632 (2.6632/0.0000)	mem 24308MB
[2025-01-18 21:38:15 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][10/312]	eta 0:03:48 lr 0.001936	time 0.5792 (0.7554)	model_time 0.5790 (0.6098)	loss 4.3073 (3.2842)	grad_norm 2.4728 (1.7385/0.5459)	mem 24308MB
[2025-01-18 21:38:21 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][20/312]	eta 0:03:19 lr 0.001936	time 0.5951 (0.6836)	model_time 0.5949 (0.6072)	loss 4.1621 (3.2901)	grad_norm 1.2783 (1.6445/0.5147)	mem 24308MB
[2025-01-18 21:38:27 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][30/312]	eta 0:03:04 lr 0.001935	time 0.6693 (0.6554)	model_time 0.6692 (0.6035)	loss 2.5659 (3.2336)	grad_norm 2.0994 (1.9102/0.9922)	mem 24308MB
[2025-01-18 21:38:33 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][40/312]	eta 0:02:55 lr 0.001934	time 0.5893 (0.6441)	model_time 0.5891 (0.6048)	loss 2.5983 (3.2402)	grad_norm 1.4782 (1.9540/0.9754)	mem 24308MB
[2025-01-18 21:38:39 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][50/312]	eta 0:02:46 lr 0.001934	time 0.5720 (0.6373)	model_time 0.5716 (0.6056)	loss 2.3332 (3.1616)	grad_norm 1.8617 (1.8427/0.9189)	mem 24308MB
[2025-01-18 21:38:46 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][60/312]	eta 0:02:40 lr 0.001933	time 0.5639 (0.6358)	model_time 0.5638 (0.6093)	loss 3.4279 (3.1857)	grad_norm 1.9218 (1.8117/0.8628)	mem 24308MB
[2025-01-18 21:38:52 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][70/312]	eta 0:02:33 lr 0.001932	time 0.7460 (0.6342)	model_time 0.7457 (0.6114)	loss 3.9068 (3.1933)	grad_norm 3.0438 (1.8466/0.8473)	mem 24308MB
[2025-01-18 21:38:58 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][80/312]	eta 0:02:26 lr 0.001932	time 0.5736 (0.6313)	model_time 0.5734 (0.6113)	loss 3.1411 (3.2192)	grad_norm 1.7129 (1.8332/0.8283)	mem 24308MB
[2025-01-18 21:39:04 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][90/312]	eta 0:02:19 lr 0.001931	time 0.6565 (0.6301)	model_time 0.6561 (0.6122)	loss 4.0684 (3.2217)	grad_norm 1.1010 (1.7898/0.8020)	mem 24308MB
[2025-01-18 21:39:10 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][100/312]	eta 0:02:13 lr 0.001930	time 0.6048 (0.6274)	model_time 0.6044 (0.6113)	loss 3.2674 (3.2109)	grad_norm 1.3930 (1.7609/0.7818)	mem 24308MB
[2025-01-18 21:39:16 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][110/312]	eta 0:02:06 lr 0.001930	time 0.5917 (0.6245)	model_time 0.5913 (0.6098)	loss 4.0243 (3.2429)	grad_norm 1.8099 (1.7255/0.7638)	mem 24308MB
[2025-01-18 21:39:22 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][120/312]	eta 0:01:59 lr 0.001929	time 0.5942 (0.6215)	model_time 0.5940 (0.6080)	loss 3.4462 (3.2500)	grad_norm 3.5514 (1.7436/0.7833)	mem 24308MB
[2025-01-18 21:39:28 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][130/312]	eta 0:01:52 lr 0.001928	time 0.5842 (0.6195)	model_time 0.5841 (0.6070)	loss 2.7713 (3.2339)	grad_norm 1.2061 (1.7622/0.7865)	mem 24308MB
[2025-01-18 21:39:34 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][140/312]	eta 0:01:46 lr 0.001928	time 0.5738 (0.6185)	model_time 0.5734 (0.6068)	loss 4.1325 (3.2514)	grad_norm 1.2426 (1.7419/0.7709)	mem 24308MB
[2025-01-18 21:39:40 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][150/312]	eta 0:01:39 lr 0.001927	time 0.6706 (0.6173)	model_time 0.6705 (0.6063)	loss 3.0485 (3.2254)	grad_norm 0.7836 (1.7300/0.7608)	mem 24308MB
[2025-01-18 21:39:46 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][160/312]	eta 0:01:33 lr 0.001926	time 0.5936 (0.6160)	model_time 0.5934 (0.6057)	loss 3.2136 (3.2317)	grad_norm 1.3363 (1.7105/0.7436)	mem 24308MB
[2025-01-18 21:39:52 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][170/312]	eta 0:01:27 lr 0.001926	time 0.6785 (0.6164)	model_time 0.6780 (0.6067)	loss 2.4110 (3.2500)	grad_norm 2.5620 (1.7219/0.7313)	mem 24308MB
[2025-01-18 21:39:59 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][180/312]	eta 0:01:21 lr 0.001925	time 0.5917 (0.6163)	model_time 0.5916 (0.6072)	loss 3.0056 (3.2529)	grad_norm 3.5032 (1.7686/0.7670)	mem 24308MB
[2025-01-18 21:40:05 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][190/312]	eta 0:01:15 lr 0.001924	time 0.5768 (0.6164)	model_time 0.5764 (0.6077)	loss 4.2451 (3.2748)	grad_norm 1.6508 (1.7654/0.7542)	mem 24308MB
[2025-01-18 21:40:11 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][200/312]	eta 0:01:09 lr 0.001924	time 0.5769 (0.6165)	model_time 0.5765 (0.6082)	loss 3.3681 (3.2876)	grad_norm 2.2774 (1.8099/0.8214)	mem 24308MB
[2025-01-18 21:40:17 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][210/312]	eta 0:01:02 lr 0.001923	time 0.6762 (0.6164)	model_time 0.6761 (0.6085)	loss 3.6489 (3.2829)	grad_norm 1.0110 (1.8189/0.8237)	mem 24308MB
[2025-01-18 21:40:23 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][220/312]	eta 0:00:56 lr 0.001922	time 0.5952 (0.6163)	model_time 0.5951 (0.6087)	loss 4.2504 (3.2801)	grad_norm 1.0393 (1.7975/0.8148)	mem 24308MB
[2025-01-18 21:40:29 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][230/312]	eta 0:00:50 lr 0.001922	time 0.5841 (0.6153)	model_time 0.5837 (0.6081)	loss 2.6844 (3.2820)	grad_norm 3.1267 (1.7970/0.8201)	mem 24308MB
[2025-01-18 21:40:35 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][240/312]	eta 0:00:44 lr 0.001921	time 0.5687 (0.6142)	model_time 0.5683 (0.6072)	loss 3.9473 (3.3031)	grad_norm 1.4187 (1.7724/0.8129)	mem 24308MB
[2025-01-18 21:40:41 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][250/312]	eta 0:00:38 lr 0.001920	time 0.5819 (0.6137)	model_time 0.5815 (0.6070)	loss 2.7408 (3.2958)	grad_norm 1.5378 (1.7757/0.8122)	mem 24308MB
[2025-01-18 21:40:47 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][260/312]	eta 0:00:31 lr 0.001920	time 0.5864 (0.6136)	model_time 0.5859 (0.6071)	loss 3.5133 (3.2896)	grad_norm 1.8592 (1.7954/0.8174)	mem 24308MB
[2025-01-18 21:40:53 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][270/312]	eta 0:00:25 lr 0.001919	time 0.5955 (0.6126)	model_time 0.5953 (0.6064)	loss 3.1028 (3.2793)	grad_norm 1.8196 (1.7950/0.8142)	mem 24308MB
[2025-01-18 21:40:59 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][280/312]	eta 0:00:19 lr 0.001918	time 0.5989 (0.6124)	model_time 0.5988 (0.6063)	loss 2.3767 (3.2762)	grad_norm 1.2233 (1.8016/0.8141)	mem 24308MB
[2025-01-18 21:41:05 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][290/312]	eta 0:00:13 lr 0.001918	time 0.5821 (0.6121)	model_time 0.5819 (0.6063)	loss 3.0148 (3.2846)	grad_norm 1.4108 (1.8139/0.8170)	mem 24308MB
[2025-01-18 21:41:11 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][300/312]	eta 0:00:07 lr 0.001917	time 0.5585 (0.6123)	model_time 0.5584 (0.6066)	loss 2.2382 (3.2813)	grad_norm 1.4272 (1.8175/0.8130)	mem 24308MB
[2025-01-18 21:41:17 internimage_s_1k_224] (main.py 510): INFO Train: [154/300][310/312]	eta 0:00:01 lr 0.001917	time 0.5727 (0.6116)	model_time 0.5727 (0.6061)	loss 3.2500 (3.2817)	grad_norm 1.8030 (1.8206/0.8113)	mem 24308MB
[2025-01-18 21:41:18 internimage_s_1k_224] (main.py 519): INFO EPOCH 154 training takes 0:03:10
[2025-01-18 21:41:18 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_154.pth saving......
[2025-01-18 21:41:20 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_154.pth saved !!!
[2025-01-18 21:41:27 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.640 (7.640)	Loss 0.7769 (0.7769)	Acc@1 83.081 (83.081)	Acc@5 96.899 (96.899)	Mem 24308MB
[2025-01-18 21:41:31 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.991)	Loss 1.1027 (0.9233)	Acc@1 74.829 (79.778)	Acc@5 93.652 (95.286)	Mem 24308MB
[2025-01-18 21:41:31 internimage_s_1k_224] (main.py 575): INFO [Epoch:154] * Acc@1 79.617 Acc@5 95.302
[2025-01-18 21:41:31 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.6%
[2025-01-18 21:41:31 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 21:41:33 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 21:41:33 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 79.62%
[2025-01-18 21:41:40 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.162 (7.162)	Loss 0.7124 (0.7124)	Acc@1 83.594 (83.594)	Acc@5 97.266 (97.266)	Mem 24308MB
[2025-01-18 21:41:43 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.980)	Loss 1.0224 (0.8413)	Acc@1 75.195 (80.356)	Acc@5 93.652 (95.375)	Mem 24308MB
[2025-01-18 21:41:44 internimage_s_1k_224] (main.py 575): INFO [Epoch:154] * Acc@1 80.230 Acc@5 95.403
[2025-01-18 21:41:44 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.2%
[2025-01-18 21:41:44 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 21:41:46 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 21:41:46 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.23%
[2025-01-18 21:41:48 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][0/312]	eta 0:11:45 lr 0.001916	time 2.2620 (2.2620)	model_time 0.6017 (0.6017)	loss 3.3763 (3.3763)	grad_norm 1.0298 (1.0298/0.0000)	mem 24308MB
[2025-01-18 21:41:54 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][10/312]	eta 0:03:53 lr 0.001916	time 0.5692 (0.7742)	model_time 0.5690 (0.6230)	loss 3.3904 (3.4640)	grad_norm 1.1384 (1.4548/0.3686)	mem 24308MB
[2025-01-18 21:42:00 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][20/312]	eta 0:03:23 lr 0.001915	time 0.5881 (0.6967)	model_time 0.5880 (0.6173)	loss 2.9689 (3.4551)	grad_norm 1.2632 (1.5655/0.4605)	mem 24308MB
[2025-01-18 21:42:07 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][30/312]	eta 0:03:09 lr 0.001914	time 0.5787 (0.6734)	model_time 0.5782 (0.6196)	loss 3.0109 (3.4246)	grad_norm 1.0233 (1.4633/0.4350)	mem 24308MB
[2025-01-18 21:42:13 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][40/312]	eta 0:02:57 lr 0.001914	time 0.6363 (0.6544)	model_time 0.6359 (0.6135)	loss 3.6433 (3.4783)	grad_norm 1.3411 (1.5706/0.4924)	mem 24308MB
[2025-01-18 21:42:18 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][50/312]	eta 0:02:47 lr 0.001913	time 0.5945 (0.6402)	model_time 0.5943 (0.6073)	loss 3.7219 (3.4209)	grad_norm 1.8971 (1.6474/0.5579)	mem 24308MB
[2025-01-18 21:42:24 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][60/312]	eta 0:02:39 lr 0.001912	time 0.7152 (0.6346)	model_time 0.7151 (0.6071)	loss 4.0146 (3.4234)	grad_norm 1.1067 (1.6819/0.6241)	mem 24308MB
[2025-01-18 21:42:30 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][70/312]	eta 0:02:32 lr 0.001912	time 0.5825 (0.6296)	model_time 0.5823 (0.6059)	loss 3.4518 (3.3830)	grad_norm 2.0686 (1.6812/0.6610)	mem 24308MB
[2025-01-18 21:42:36 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][80/312]	eta 0:02:25 lr 0.001911	time 0.7134 (0.6262)	model_time 0.7133 (0.6053)	loss 4.1631 (3.4284)	grad_norm 1.6651 (1.6754/0.6434)	mem 24308MB
[2025-01-18 21:42:42 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][90/312]	eta 0:02:18 lr 0.001910	time 0.5870 (0.6226)	model_time 0.5868 (0.6040)	loss 2.9945 (3.4201)	grad_norm 3.4227 (1.7684/0.6989)	mem 24308MB
[2025-01-18 21:42:49 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][100/312]	eta 0:02:11 lr 0.001910	time 0.5724 (0.6215)	model_time 0.5720 (0.6047)	loss 3.7205 (3.4086)	grad_norm 1.9403 (1.8144/0.7464)	mem 24308MB
[2025-01-18 21:42:55 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][110/312]	eta 0:02:05 lr 0.001909	time 0.5805 (0.6230)	model_time 0.5801 (0.6077)	loss 1.8985 (3.3760)	grad_norm 1.3847 (1.7660/0.7350)	mem 24308MB
[2025-01-18 21:43:01 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][120/312]	eta 0:01:59 lr 0.001908	time 0.6749 (0.6223)	model_time 0.6747 (0.6082)	loss 3.6597 (3.3861)	grad_norm 2.8039 (1.7796/0.7337)	mem 24308MB
[2025-01-18 21:43:07 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][130/312]	eta 0:01:53 lr 0.001908	time 0.5707 (0.6221)	model_time 0.5703 (0.6091)	loss 2.9622 (3.3763)	grad_norm 3.0481 (1.7742/0.7304)	mem 24308MB
[2025-01-18 21:43:13 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][140/312]	eta 0:01:46 lr 0.001907	time 0.5879 (0.6204)	model_time 0.5875 (0.6082)	loss 3.3040 (3.3723)	grad_norm 1.4141 (1.7804/0.7379)	mem 24308MB
[2025-01-18 21:43:19 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][150/312]	eta 0:01:40 lr 0.001906	time 0.5880 (0.6207)	model_time 0.5878 (0.6092)	loss 2.9206 (3.3736)	grad_norm 2.0217 (1.7712/0.7262)	mem 24308MB
[2025-01-18 21:43:25 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][160/312]	eta 0:01:34 lr 0.001906	time 0.5913 (0.6190)	model_time 0.5911 (0.6083)	loss 2.7548 (3.3564)	grad_norm 5.0136 (1.8137/0.7712)	mem 24308MB
[2025-01-18 21:43:31 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][170/312]	eta 0:01:27 lr 0.001905	time 0.5887 (0.6170)	model_time 0.5883 (0.6069)	loss 3.3970 (3.3459)	grad_norm 1.0542 (1.8160/0.7808)	mem 24308MB
[2025-01-18 21:43:37 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][180/312]	eta 0:01:21 lr 0.001904	time 0.5840 (0.6157)	model_time 0.5839 (0.6061)	loss 2.4471 (3.3351)	grad_norm 1.7014 (1.8199/0.7882)	mem 24308MB
[2025-01-18 21:43:43 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][190/312]	eta 0:01:15 lr 0.001904	time 0.5773 (0.6151)	model_time 0.5769 (0.6060)	loss 2.9446 (3.3227)	grad_norm 1.6835 (1.8262/0.7982)	mem 24308MB
[2025-01-18 21:43:49 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][200/312]	eta 0:01:08 lr 0.001903	time 0.6904 (0.6144)	model_time 0.6903 (0.6057)	loss 3.6097 (3.3347)	grad_norm 1.6324 (1.8180/0.7923)	mem 24308MB
[2025-01-18 21:43:55 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][210/312]	eta 0:01:02 lr 0.001902	time 0.5792 (0.6133)	model_time 0.5790 (0.6050)	loss 3.7549 (3.3262)	grad_norm 1.2041 (1.8038/0.7809)	mem 24308MB
[2025-01-18 21:44:01 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][220/312]	eta 0:00:56 lr 0.001902	time 0.5779 (0.6128)	model_time 0.5777 (0.6049)	loss 2.8237 (3.3191)	grad_norm 0.8556 (1.7875/0.7722)	mem 24308MB
[2025-01-18 21:44:07 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][230/312]	eta 0:00:50 lr 0.001901	time 0.5762 (0.6132)	model_time 0.5758 (0.6056)	loss 3.3224 (3.3219)	grad_norm 3.8984 (1.8129/0.7853)	mem 24308MB
[2025-01-18 21:44:13 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][240/312]	eta 0:00:44 lr 0.001900	time 0.6792 (0.6128)	model_time 0.6787 (0.6055)	loss 3.3466 (3.3159)	grad_norm 2.2346 (1.8404/0.8042)	mem 24308MB
[2025-01-18 21:44:19 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][250/312]	eta 0:00:37 lr 0.001900	time 0.6670 (0.6124)	model_time 0.6669 (0.6053)	loss 3.4869 (3.3165)	grad_norm 0.9617 (1.8352/0.7958)	mem 24308MB
[2025-01-18 21:44:26 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][260/312]	eta 0:00:31 lr 0.001899	time 0.5831 (0.6123)	model_time 0.5829 (0.6055)	loss 3.1305 (3.3197)	grad_norm 1.1528 (1.8192/0.7899)	mem 24308MB
[2025-01-18 21:44:32 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][270/312]	eta 0:00:25 lr 0.001898	time 0.5780 (0.6123)	model_time 0.5775 (0.6058)	loss 3.3544 (3.3241)	grad_norm 1.4155 (1.8163/0.7790)	mem 24308MB
[2025-01-18 21:44:38 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][280/312]	eta 0:00:19 lr 0.001898	time 0.5710 (0.6120)	model_time 0.5709 (0.6057)	loss 4.1109 (3.3183)	grad_norm 1.9451 (1.8437/0.7989)	mem 24308MB
[2025-01-18 21:44:44 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][290/312]	eta 0:00:13 lr 0.001897	time 0.5796 (0.6114)	model_time 0.5791 (0.6052)	loss 3.8571 (3.3247)	grad_norm 1.4048 (1.8482/0.8000)	mem 24308MB
[2025-01-18 21:44:50 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][300/312]	eta 0:00:07 lr 0.001896	time 0.5691 (0.6106)	model_time 0.5690 (0.6047)	loss 3.0876 (3.3150)	grad_norm 3.1602 (1.8643/0.8059)	mem 24308MB
[2025-01-18 21:44:55 internimage_s_1k_224] (main.py 510): INFO Train: [155/300][310/312]	eta 0:00:01 lr 0.001896	time 0.5766 (0.6098)	model_time 0.5765 (0.6040)	loss 3.7981 (3.3057)	grad_norm 1.1430 (1.8593/0.8098)	mem 24308MB
[2025-01-18 21:44:56 internimage_s_1k_224] (main.py 519): INFO EPOCH 155 training takes 0:03:10
[2025-01-18 21:44:56 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_155.pth saving......
[2025-01-18 21:44:58 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_155.pth saved !!!
[2025-01-18 21:45:05 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.310 (7.310)	Loss 0.8223 (0.8223)	Acc@1 82.837 (82.837)	Acc@5 96.436 (96.436)	Mem 24308MB
[2025-01-18 21:45:09 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.996)	Loss 1.1221 (0.9488)	Acc@1 74.170 (79.712)	Acc@5 93.042 (95.031)	Mem 24308MB
[2025-01-18 21:45:09 internimage_s_1k_224] (main.py 575): INFO [Epoch:155] * Acc@1 79.649 Acc@5 95.106
[2025-01-18 21:45:09 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.6%
[2025-01-18 21:45:09 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 21:45:11 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 21:45:11 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 79.65%
[2025-01-18 21:45:18 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.270 (7.270)	Loss 0.7122 (0.7122)	Acc@1 83.569 (83.569)	Acc@5 97.241 (97.241)	Mem 24308MB
[2025-01-18 21:45:22 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.976)	Loss 1.0203 (0.8403)	Acc@1 75.220 (80.384)	Acc@5 93.701 (95.399)	Mem 24308MB
[2025-01-18 21:45:22 internimage_s_1k_224] (main.py 575): INFO [Epoch:155] * Acc@1 80.264 Acc@5 95.427
[2025-01-18 21:45:22 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.3%
[2025-01-18 21:45:22 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 21:45:24 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 21:45:24 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.26%
[2025-01-18 21:45:26 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][0/312]	eta 0:12:09 lr 0.001896	time 2.3373 (2.3373)	model_time 0.6113 (0.6113)	loss 3.4950 (3.4950)	grad_norm 1.1787 (1.1787/0.0000)	mem 24308MB
[2025-01-18 21:45:32 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][10/312]	eta 0:03:46 lr 0.001895	time 0.5947 (0.7486)	model_time 0.5946 (0.5914)	loss 3.9591 (3.5396)	grad_norm 2.4346 (1.4188/0.7076)	mem 24308MB
[2025-01-18 21:45:38 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][20/312]	eta 0:03:19 lr 0.001894	time 0.6006 (0.6827)	model_time 0.6005 (0.6002)	loss 2.7527 (3.3739)	grad_norm 3.5006 (1.6429/0.7919)	mem 24308MB
[2025-01-18 21:45:44 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][30/312]	eta 0:03:06 lr 0.001894	time 0.6711 (0.6596)	model_time 0.6706 (0.6035)	loss 3.2788 (3.2673)	grad_norm 2.3096 (1.6567/0.6980)	mem 24308MB
[2025-01-18 21:45:51 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][40/312]	eta 0:02:56 lr 0.001893	time 0.7168 (0.6503)	model_time 0.7166 (0.6079)	loss 2.9768 (3.2330)	grad_norm 2.4511 (1.6505/0.6313)	mem 24308MB
[2025-01-18 21:45:57 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][50/312]	eta 0:02:47 lr 0.001892	time 0.5807 (0.6393)	model_time 0.5806 (0.6050)	loss 3.9069 (3.2283)	grad_norm 1.1995 (1.6254/0.6119)	mem 24308MB
[2025-01-18 21:46:03 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][60/312]	eta 0:02:40 lr 0.001892	time 0.5904 (0.6366)	model_time 0.5902 (0.6079)	loss 3.4412 (3.2349)	grad_norm 0.9141 (1.5498/0.5947)	mem 24308MB
[2025-01-18 21:46:09 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][70/312]	eta 0:02:32 lr 0.001891	time 0.6133 (0.6315)	model_time 0.6131 (0.6068)	loss 3.1761 (3.2513)	grad_norm 3.0887 (1.6527/0.6642)	mem 24308MB
[2025-01-18 21:46:15 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][80/312]	eta 0:02:26 lr 0.001890	time 0.6401 (0.6296)	model_time 0.6399 (0.6079)	loss 2.8124 (3.2691)	grad_norm 2.7305 (1.6692/0.6861)	mem 24308MB
[2025-01-18 21:46:21 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][90/312]	eta 0:02:19 lr 0.001890	time 0.6222 (0.6270)	model_time 0.6220 (0.6077)	loss 3.9446 (3.2930)	grad_norm 1.0892 (1.6318/0.6762)	mem 24308MB
[2025-01-18 21:46:27 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][100/312]	eta 0:02:12 lr 0.001889	time 0.5951 (0.6235)	model_time 0.5946 (0.6060)	loss 3.0875 (3.2797)	grad_norm 1.1969 (1.6257/0.6545)	mem 24308MB
[2025-01-18 21:46:33 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][110/312]	eta 0:02:05 lr 0.001888	time 0.5782 (0.6210)	model_time 0.5778 (0.6051)	loss 2.6112 (3.2781)	grad_norm 3.5983 (1.7253/0.7880)	mem 24308MB
[2025-01-18 21:46:39 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][120/312]	eta 0:01:59 lr 0.001888	time 0.6993 (0.6206)	model_time 0.6989 (0.6059)	loss 3.3848 (3.2611)	grad_norm 2.1553 (1.7349/0.7641)	mem 24308MB
[2025-01-18 21:46:45 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][130/312]	eta 0:01:52 lr 0.001887	time 0.5967 (0.6182)	model_time 0.5965 (0.6047)	loss 3.4984 (3.2685)	grad_norm 1.6260 (1.7227/0.7455)	mem 24308MB
[2025-01-18 21:46:51 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][140/312]	eta 0:01:46 lr 0.001886	time 0.5924 (0.6174)	model_time 0.5922 (0.6048)	loss 3.6488 (3.2846)	grad_norm 0.8011 (1.7054/0.7360)	mem 24308MB
[2025-01-18 21:46:57 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][150/312]	eta 0:01:39 lr 0.001886	time 0.6687 (0.6169)	model_time 0.6686 (0.6051)	loss 2.4731 (3.2830)	grad_norm 1.0821 (1.6831/0.7195)	mem 24308MB
[2025-01-18 21:47:03 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][160/312]	eta 0:01:33 lr 0.001885	time 0.6691 (0.6171)	model_time 0.6689 (0.6060)	loss 3.8614 (3.2730)	grad_norm 1.6778 (1.6800/0.7256)	mem 24308MB
[2025-01-18 21:47:09 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][170/312]	eta 0:01:27 lr 0.001884	time 0.5916 (0.6171)	model_time 0.5914 (0.6067)	loss 2.5049 (3.2563)	grad_norm 2.2421 (1.6667/0.7112)	mem 24308MB
[2025-01-18 21:47:16 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][180/312]	eta 0:01:21 lr 0.001884	time 0.5867 (0.6180)	model_time 0.5865 (0.6081)	loss 2.8654 (3.2502)	grad_norm 1.2664 (1.6602/0.7010)	mem 24308MB
[2025-01-18 21:47:22 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][190/312]	eta 0:01:15 lr 0.001883	time 0.5835 (0.6172)	model_time 0.5831 (0.6078)	loss 2.8848 (3.2561)	grad_norm 1.2501 (1.6685/0.6909)	mem 24308MB
[2025-01-18 21:47:28 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][200/312]	eta 0:01:09 lr 0.001882	time 0.5896 (0.6180)	model_time 0.5892 (0.6091)	loss 3.9023 (3.2550)	grad_norm 1.4778 (1.6951/0.7085)	mem 24308MB
[2025-01-18 21:47:34 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][210/312]	eta 0:01:02 lr 0.001882	time 0.5804 (0.6175)	model_time 0.5803 (0.6090)	loss 3.8764 (3.2729)	grad_norm 1.3594 (1.6962/0.7081)	mem 24308MB
[2025-01-18 21:47:40 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][220/312]	eta 0:00:56 lr 0.001881	time 0.5700 (0.6161)	model_time 0.5695 (0.6079)	loss 3.8204 (3.2836)	grad_norm 1.9553 (1.7037/0.7170)	mem 24308MB
[2025-01-18 21:47:46 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][230/312]	eta 0:00:50 lr 0.001880	time 0.5739 (0.6154)	model_time 0.5737 (0.6075)	loss 3.6102 (3.2905)	grad_norm 2.9101 (1.7178/0.7394)	mem 24308MB
[2025-01-18 21:47:52 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][240/312]	eta 0:00:44 lr 0.001880	time 0.6593 (0.6151)	model_time 0.6592 (0.6075)	loss 3.4950 (3.3034)	grad_norm 1.3417 (1.7306/0.7474)	mem 24308MB
[2025-01-18 21:47:58 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][250/312]	eta 0:00:38 lr 0.001879	time 0.5940 (0.6139)	model_time 0.5935 (0.6067)	loss 3.9521 (3.3121)	grad_norm 1.6417 (1.7091/0.7429)	mem 24308MB
[2025-01-18 21:48:04 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][260/312]	eta 0:00:31 lr 0.001878	time 0.5783 (0.6138)	model_time 0.5781 (0.6068)	loss 3.6355 (3.3093)	grad_norm 0.8709 (1.6886/0.7385)	mem 24308MB
[2025-01-18 21:48:10 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][270/312]	eta 0:00:25 lr 0.001878	time 0.6770 (0.6138)	model_time 0.6765 (0.6071)	loss 3.4461 (3.3170)	grad_norm 2.0892 (1.6747/0.7317)	mem 24308MB
[2025-01-18 21:48:16 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][280/312]	eta 0:00:19 lr 0.001877	time 0.6505 (0.6137)	model_time 0.6501 (0.6071)	loss 2.5028 (3.2999)	grad_norm 2.0060 (1.6795/0.7281)	mem 24308MB
[2025-01-18 21:48:23 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][290/312]	eta 0:00:13 lr 0.001876	time 0.6026 (0.6137)	model_time 0.6025 (0.6074)	loss 2.9533 (3.3023)	grad_norm 3.0905 (1.6973/0.7312)	mem 24308MB
[2025-01-18 21:48:29 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][300/312]	eta 0:00:07 lr 0.001876	time 0.5746 (0.6134)	model_time 0.5745 (0.6073)	loss 2.7505 (3.3022)	grad_norm 1.1936 (1.7016/0.7337)	mem 24308MB
[2025-01-18 21:48:34 internimage_s_1k_224] (main.py 510): INFO Train: [156/300][310/312]	eta 0:00:01 lr 0.001875	time 0.5692 (0.6126)	model_time 0.5691 (0.6067)	loss 3.7661 (3.3122)	grad_norm 1.9139 (1.7117/0.7253)	mem 24308MB
[2025-01-18 21:48:35 internimage_s_1k_224] (main.py 519): INFO EPOCH 156 training takes 0:03:11
[2025-01-18 21:48:35 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_156.pth saving......
[2025-01-18 21:48:37 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_156.pth saved !!!
[2025-01-18 21:48:44 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.471 (7.471)	Loss 0.8115 (0.8115)	Acc@1 82.690 (82.690)	Acc@5 96.777 (96.777)	Mem 24308MB
[2025-01-18 21:48:48 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.996)	Loss 1.0789 (0.9307)	Acc@1 75.317 (79.947)	Acc@5 93.750 (95.275)	Mem 24308MB
[2025-01-18 21:48:48 internimage_s_1k_224] (main.py 575): INFO [Epoch:156] * Acc@1 79.812 Acc@5 95.276
[2025-01-18 21:48:48 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.8%
[2025-01-18 21:48:48 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 21:48:50 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 21:48:50 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 79.81%
[2025-01-18 21:48:57 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.237 (7.237)	Loss 0.7120 (0.7120)	Acc@1 83.569 (83.569)	Acc@5 97.266 (97.266)	Mem 24308MB
[2025-01-18 21:49:01 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.990)	Loss 1.0182 (0.8392)	Acc@1 75.366 (80.440)	Acc@5 93.701 (95.417)	Mem 24308MB
[2025-01-18 21:49:01 internimage_s_1k_224] (main.py 575): INFO [Epoch:156] * Acc@1 80.320 Acc@5 95.445
[2025-01-18 21:49:01 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.3%
[2025-01-18 21:49:01 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 21:49:03 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 21:49:03 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.32%
[2025-01-18 21:49:06 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][0/312]	eta 0:12:19 lr 0.001875	time 2.3706 (2.3706)	model_time 0.5984 (0.5984)	loss 3.7612 (3.7612)	grad_norm 1.4858 (1.4858/0.0000)	mem 24308MB
[2025-01-18 21:49:12 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][10/312]	eta 0:03:55 lr 0.001874	time 0.5928 (0.7815)	model_time 0.5926 (0.6201)	loss 3.5088 (3.1999)	grad_norm 1.7233 (1.7331/0.3792)	mem 24308MB
[2025-01-18 21:49:18 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][20/312]	eta 0:03:23 lr 0.001874	time 0.5848 (0.6975)	model_time 0.5847 (0.6128)	loss 3.8819 (3.1479)	grad_norm 1.4477 (1.7625/0.5053)	mem 24308MB
[2025-01-18 21:49:24 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][30/312]	eta 0:03:06 lr 0.001873	time 0.5815 (0.6624)	model_time 0.5813 (0.6049)	loss 3.6096 (3.3085)	grad_norm 2.0389 (1.8058/0.6081)	mem 24308MB
[2025-01-18 21:49:30 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][40/312]	eta 0:02:55 lr 0.001872	time 0.5805 (0.6469)	model_time 0.5801 (0.6034)	loss 3.0401 (3.2903)	grad_norm 1.5265 (1.9604/0.7072)	mem 24308MB
[2025-01-18 21:49:36 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][50/312]	eta 0:02:47 lr 0.001872	time 0.5871 (0.6383)	model_time 0.5870 (0.6032)	loss 3.3671 (3.2801)	grad_norm 1.5469 (1.9716/0.7075)	mem 24308MB
[2025-01-18 21:49:42 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][60/312]	eta 0:02:39 lr 0.001871	time 0.5878 (0.6343)	model_time 0.5877 (0.6049)	loss 3.4515 (3.2591)	grad_norm 1.4320 (1.9019/0.6774)	mem 24308MB
[2025-01-18 21:49:48 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][70/312]	eta 0:02:32 lr 0.001870	time 0.5927 (0.6297)	model_time 0.5926 (0.6044)	loss 3.2728 (3.2799)	grad_norm 1.8291 (1.9134/0.7294)	mem 24308MB
[2025-01-18 21:49:54 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][80/312]	eta 0:02:25 lr 0.001870	time 0.5877 (0.6261)	model_time 0.5875 (0.6039)	loss 3.6352 (3.2783)	grad_norm 1.0609 (1.9253/0.7437)	mem 24308MB
[2025-01-18 21:50:00 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][90/312]	eta 0:02:18 lr 0.001869	time 0.6702 (0.6260)	model_time 0.6700 (0.6062)	loss 3.1788 (3.2540)	grad_norm 1.2469 (1.9066/0.7325)	mem 24308MB
[2025-01-18 21:50:06 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][100/312]	eta 0:02:12 lr 0.001868	time 0.6202 (0.6254)	model_time 0.6197 (0.6075)	loss 2.8502 (3.2556)	grad_norm 1.4846 (1.8928/0.7189)	mem 24308MB
[2025-01-18 21:50:13 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][110/312]	eta 0:02:06 lr 0.001868	time 0.6564 (0.6272)	model_time 0.6560 (0.6109)	loss 3.0742 (3.2726)	grad_norm 4.1894 (1.8892/0.7286)	mem 24308MB
[2025-01-18 21:50:19 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][120/312]	eta 0:02:00 lr 0.001867	time 0.5942 (0.6254)	model_time 0.5940 (0.6104)	loss 3.2600 (3.2734)	grad_norm 2.1626 (1.9261/0.7761)	mem 24308MB
[2025-01-18 21:50:25 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][130/312]	eta 0:01:53 lr 0.001866	time 0.5917 (0.6250)	model_time 0.5916 (0.6112)	loss 3.4222 (3.2919)	grad_norm 2.1631 (1.9121/0.7653)	mem 24308MB
[2025-01-18 21:50:31 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][140/312]	eta 0:01:47 lr 0.001866	time 0.5831 (0.6232)	model_time 0.5830 (0.6103)	loss 3.5948 (3.2691)	grad_norm 1.3714 (1.8762/0.7682)	mem 24308MB
[2025-01-18 21:50:37 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][150/312]	eta 0:01:40 lr 0.001865	time 0.5710 (0.6207)	model_time 0.5708 (0.6087)	loss 3.2113 (3.2676)	grad_norm 2.5643 (1.8767/0.7558)	mem 24308MB
[2025-01-18 21:50:43 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][160/312]	eta 0:01:34 lr 0.001864	time 0.5738 (0.6192)	model_time 0.5734 (0.6079)	loss 2.5895 (3.2681)	grad_norm 3.6119 (1.8624/0.7636)	mem 24308MB
[2025-01-18 21:50:49 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][170/312]	eta 0:01:27 lr 0.001864	time 0.5891 (0.6182)	model_time 0.5887 (0.6075)	loss 3.5111 (3.2648)	grad_norm 1.2677 (1.8682/0.7553)	mem 24308MB
[2025-01-18 21:50:55 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][180/312]	eta 0:01:21 lr 0.001863	time 0.5890 (0.6178)	model_time 0.5887 (0.6077)	loss 3.8366 (3.2701)	grad_norm 1.2856 (1.8592/0.7510)	mem 24308MB
[2025-01-18 21:51:01 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][190/312]	eta 0:01:15 lr 0.001862	time 0.6066 (0.6170)	model_time 0.6062 (0.6074)	loss 3.4912 (3.2768)	grad_norm 1.2421 (1.8697/0.7822)	mem 24308MB
[2025-01-18 21:51:07 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][200/312]	eta 0:01:09 lr 0.001862	time 0.6600 (0.6163)	model_time 0.6598 (0.6071)	loss 3.8973 (3.2795)	grad_norm 1.3290 (1.8701/0.7985)	mem 24308MB
[2025-01-18 21:51:13 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][210/312]	eta 0:01:02 lr 0.001861	time 0.6639 (0.6175)	model_time 0.6637 (0.6087)	loss 3.4518 (3.2941)	grad_norm 1.9051 (1.8574/0.7889)	mem 24308MB
[2025-01-18 21:51:20 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][220/312]	eta 0:00:56 lr 0.001860	time 0.5823 (0.6173)	model_time 0.5818 (0.6090)	loss 4.1994 (3.2928)	grad_norm 0.8477 (1.8310/0.7821)	mem 24308MB
[2025-01-18 21:51:26 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][230/312]	eta 0:00:50 lr 0.001860	time 0.6648 (0.6178)	model_time 0.6646 (0.6097)	loss 3.4338 (3.3029)	grad_norm 0.6698 (1.8350/0.7858)	mem 24308MB
[2025-01-18 21:51:32 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][240/312]	eta 0:00:44 lr 0.001859	time 0.5694 (0.6167)	model_time 0.5690 (0.6090)	loss 3.8700 (3.3088)	grad_norm 2.4696 (1.8305/0.7784)	mem 24308MB
[2025-01-18 21:51:38 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][250/312]	eta 0:00:38 lr 0.001858	time 0.6765 (0.6166)	model_time 0.6763 (0.6092)	loss 3.5617 (3.3055)	grad_norm 1.6621 (1.8294/0.7679)	mem 24308MB
[2025-01-18 21:51:44 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][260/312]	eta 0:00:32 lr 0.001858	time 0.5887 (0.6168)	model_time 0.5885 (0.6097)	loss 3.8609 (3.2956)	grad_norm 2.0326 (1.8288/0.7609)	mem 24308MB
[2025-01-18 21:51:50 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][270/312]	eta 0:00:25 lr 0.001857	time 0.5680 (0.6159)	model_time 0.5676 (0.6090)	loss 3.8676 (3.2908)	grad_norm 3.6337 (1.8463/0.7906)	mem 24308MB
[2025-01-18 21:51:56 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][280/312]	eta 0:00:19 lr 0.001856	time 0.6730 (0.6154)	model_time 0.6729 (0.6088)	loss 4.1534 (3.2958)	grad_norm 1.0211 (1.8392/0.7822)	mem 24308MB
[2025-01-18 21:52:02 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][290/312]	eta 0:00:13 lr 0.001856	time 0.5809 (0.6147)	model_time 0.5808 (0.6083)	loss 3.2433 (3.3035)	grad_norm 2.5762 (1.8337/0.7741)	mem 24308MB
[2025-01-18 21:52:08 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][300/312]	eta 0:00:07 lr 0.001855	time 0.6325 (0.6141)	model_time 0.6323 (0.6078)	loss 2.2435 (3.2966)	grad_norm 3.7688 (1.8252/0.7756)	mem 24308MB
[2025-01-18 21:52:14 internimage_s_1k_224] (main.py 510): INFO Train: [157/300][310/312]	eta 0:00:01 lr 0.001854	time 0.5686 (0.6133)	model_time 0.5685 (0.6072)	loss 2.5678 (3.2960)	grad_norm 3.4565 (1.8779/0.8419)	mem 24308MB
[2025-01-18 21:52:14 internimage_s_1k_224] (main.py 519): INFO EPOCH 157 training takes 0:03:11
[2025-01-18 21:52:14 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_157.pth saving......
[2025-01-18 21:52:16 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_157.pth saved !!!
[2025-01-18 21:52:24 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.728 (7.728)	Loss 0.7995 (0.7995)	Acc@1 82.593 (82.593)	Acc@5 96.948 (96.948)	Mem 24308MB
[2025-01-18 21:52:27 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.015)	Loss 1.1092 (0.9337)	Acc@1 74.414 (79.670)	Acc@5 93.555 (95.277)	Mem 24308MB
[2025-01-18 21:52:28 internimage_s_1k_224] (main.py 575): INFO [Epoch:157] * Acc@1 79.527 Acc@5 95.294
[2025-01-18 21:52:28 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.5%
[2025-01-18 21:52:28 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 79.81%
[2025-01-18 21:52:36 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.771 (8.771)	Loss 0.7118 (0.7118)	Acc@1 83.643 (83.643)	Acc@5 97.266 (97.266)	Mem 24308MB
[2025-01-18 21:52:41 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.194)	Loss 1.0161 (0.8382)	Acc@1 75.513 (80.500)	Acc@5 93.774 (95.470)	Mem 24308MB
[2025-01-18 21:52:41 internimage_s_1k_224] (main.py 575): INFO [Epoch:157] * Acc@1 80.378 Acc@5 95.493
[2025-01-18 21:52:41 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.4%
[2025-01-18 21:52:41 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 21:52:43 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 21:52:43 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.38%
[2025-01-18 21:52:45 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][0/312]	eta 0:12:11 lr 0.001854	time 2.3442 (2.3442)	model_time 0.5934 (0.5934)	loss 4.0585 (4.0585)	grad_norm 3.5179 (3.5179/0.0000)	mem 24308MB
[2025-01-18 21:52:51 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][10/312]	eta 0:03:49 lr 0.001854	time 0.5812 (0.7615)	model_time 0.5810 (0.6020)	loss 3.0312 (3.4524)	grad_norm 1.1650 (2.0250/0.9890)	mem 24308MB
[2025-01-18 21:52:58 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][20/312]	eta 0:03:23 lr 0.001853	time 0.5810 (0.6963)	model_time 0.5808 (0.6126)	loss 2.9257 (3.2085)	grad_norm 1.4882 (1.7983/0.7755)	mem 24308MB
[2025-01-18 21:53:04 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][30/312]	eta 0:03:09 lr 0.001852	time 0.5944 (0.6729)	model_time 0.5942 (0.6161)	loss 2.9437 (3.1808)	grad_norm 2.3792 (1.7767/0.6999)	mem 24308MB
[2025-01-18 21:53:10 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][40/312]	eta 0:03:00 lr 0.001852	time 0.6817 (0.6618)	model_time 0.6814 (0.6187)	loss 2.6298 (3.1984)	grad_norm 2.2560 (1.8697/0.6798)	mem 24308MB
[2025-01-18 21:53:16 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][50/312]	eta 0:02:49 lr 0.001851	time 0.5910 (0.6484)	model_time 0.5908 (0.6137)	loss 3.3870 (3.2509)	grad_norm 1.5941 (1.7750/0.6524)	mem 24308MB
[2025-01-18 21:53:22 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][60/312]	eta 0:02:41 lr 0.001850	time 0.7061 (0.6427)	model_time 0.7059 (0.6136)	loss 3.7655 (3.2833)	grad_norm 3.6054 (1.7745/0.6814)	mem 24308MB
[2025-01-18 21:53:28 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][70/312]	eta 0:02:34 lr 0.001850	time 0.5982 (0.6379)	model_time 0.5977 (0.6129)	loss 3.7268 (3.2816)	grad_norm 0.9278 (1.8036/0.6968)	mem 24308MB
[2025-01-18 21:53:34 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][80/312]	eta 0:02:26 lr 0.001849	time 0.5947 (0.6318)	model_time 0.5945 (0.6098)	loss 2.2363 (3.2991)	grad_norm 1.1106 (1.7812/0.6674)	mem 24308MB
[2025-01-18 21:53:40 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][90/312]	eta 0:02:19 lr 0.001848	time 0.5808 (0.6282)	model_time 0.5806 (0.6086)	loss 3.3821 (3.3207)	grad_norm 2.4589 (1.7750/0.6779)	mem 24308MB
[2025-01-18 21:53:46 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][100/312]	eta 0:02:12 lr 0.001848	time 0.5735 (0.6253)	model_time 0.5733 (0.6076)	loss 3.8026 (3.3570)	grad_norm 1.6033 (1.7844/0.6632)	mem 24308MB
[2025-01-18 21:53:52 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][110/312]	eta 0:02:05 lr 0.001847	time 0.5697 (0.6237)	model_time 0.5692 (0.6076)	loss 2.7808 (3.3472)	grad_norm 1.6542 (1.7771/0.6468)	mem 24308MB
[2025-01-18 21:53:58 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][120/312]	eta 0:01:59 lr 0.001846	time 0.6012 (0.6221)	model_time 0.6010 (0.6072)	loss 3.8186 (3.3319)	grad_norm 1.1054 (1.7769/0.6363)	mem 24308MB
[2025-01-18 21:54:04 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][130/312]	eta 0:01:52 lr 0.001846	time 0.5912 (0.6208)	model_time 0.5907 (0.6070)	loss 3.4181 (3.3235)	grad_norm 1.3054 (1.7420/0.6269)	mem 24308MB
[2025-01-18 21:54:11 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][140/312]	eta 0:01:46 lr 0.001845	time 0.5810 (0.6207)	model_time 0.5808 (0.6079)	loss 2.6819 (3.3117)	grad_norm 4.4919 (1.8093/0.7155)	mem 24308MB
[2025-01-18 21:54:17 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][150/312]	eta 0:01:40 lr 0.001844	time 0.6657 (0.6231)	model_time 0.6652 (0.6111)	loss 2.0770 (3.3088)	grad_norm 2.1087 (1.8012/0.7066)	mem 24308MB
[2025-01-18 21:54:23 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][160/312]	eta 0:01:34 lr 0.001844	time 0.6724 (0.6232)	model_time 0.6720 (0.6119)	loss 3.3188 (3.3199)	grad_norm 0.8648 (1.8050/0.6988)	mem 24308MB
[2025-01-18 21:54:29 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][170/312]	eta 0:01:28 lr 0.001843	time 0.5835 (0.6219)	model_time 0.5833 (0.6113)	loss 3.5043 (3.3154)	grad_norm 1.6013 (1.8482/0.7646)	mem 24308MB
[2025-01-18 21:54:36 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][180/312]	eta 0:01:22 lr 0.001842	time 0.8533 (0.6231)	model_time 0.8529 (0.6131)	loss 3.7139 (3.3081)	grad_norm 1.1081 (1.8373/0.7563)	mem 24308MB
[2025-01-18 21:54:42 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][190/312]	eta 0:01:16 lr 0.001842	time 0.5939 (0.6238)	model_time 0.5938 (0.6143)	loss 3.3620 (3.2970)	grad_norm 3.1544 (1.8341/0.7805)	mem 24308MB
[2025-01-18 21:54:48 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][200/312]	eta 0:01:09 lr 0.001841	time 0.5871 (0.6220)	model_time 0.5869 (0.6129)	loss 3.6819 (3.2933)	grad_norm 1.5479 (1.8384/0.7886)	mem 24308MB
[2025-01-18 21:54:54 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][210/312]	eta 0:01:03 lr 0.001840	time 0.5847 (0.6204)	model_time 0.5842 (0.6117)	loss 3.0409 (3.2952)	grad_norm 1.2687 (1.8212/0.7772)	mem 24308MB
[2025-01-18 21:55:00 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][220/312]	eta 0:00:57 lr 0.001840	time 0.5786 (0.6196)	model_time 0.5785 (0.6113)	loss 3.4914 (3.3021)	grad_norm 3.7227 (1.8724/0.8600)	mem 24308MB
[2025-01-18 21:55:06 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][230/312]	eta 0:00:50 lr 0.001839	time 0.7226 (0.6195)	model_time 0.7222 (0.6115)	loss 2.6222 (3.2946)	grad_norm 1.4358 (1.8859/0.8647)	mem 24308MB
[2025-01-18 21:55:12 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][240/312]	eta 0:00:44 lr 0.001838	time 0.5742 (0.6190)	model_time 0.5741 (0.6114)	loss 2.6633 (3.2842)	grad_norm 1.0655 (1.8824/0.8574)	mem 24308MB
[2025-01-18 21:55:18 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][250/312]	eta 0:00:38 lr 0.001838	time 0.5727 (0.6185)	model_time 0.5725 (0.6111)	loss 2.2598 (3.2836)	grad_norm 0.8485 (1.8686/0.8523)	mem 24308MB
[2025-01-18 21:55:24 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][260/312]	eta 0:00:32 lr 0.001837	time 0.5839 (0.6177)	model_time 0.5835 (0.6106)	loss 3.1350 (3.2853)	grad_norm 1.5449 (1.8852/0.8628)	mem 24308MB
[2025-01-18 21:55:31 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][270/312]	eta 0:00:25 lr 0.001836	time 0.6594 (0.6182)	model_time 0.6590 (0.6114)	loss 4.0664 (3.2759)	grad_norm 1.2793 (1.8750/0.8494)	mem 24308MB
[2025-01-18 21:55:37 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][280/312]	eta 0:00:19 lr 0.001836	time 0.5856 (0.6186)	model_time 0.5855 (0.6120)	loss 3.7008 (3.2817)	grad_norm 1.9680 (1.8695/0.8441)	mem 24308MB
[2025-01-18 21:55:43 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][290/312]	eta 0:00:13 lr 0.001835	time 0.5828 (0.6185)	model_time 0.5823 (0.6121)	loss 2.7094 (3.2781)	grad_norm 3.1928 (1.8643/0.8374)	mem 24308MB
[2025-01-18 21:55:49 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][300/312]	eta 0:00:07 lr 0.001834	time 0.5691 (0.6181)	model_time 0.5690 (0.6120)	loss 3.4163 (3.2864)	grad_norm 0.8951 (1.8526/0.8241)	mem 24308MB
[2025-01-18 21:55:55 internimage_s_1k_224] (main.py 510): INFO Train: [158/300][310/312]	eta 0:00:01 lr 0.001834	time 0.5796 (0.6175)	model_time 0.5795 (0.6115)	loss 2.9159 (3.2799)	grad_norm 2.2757 (1.8485/0.8154)	mem 24308MB
[2025-01-18 21:55:56 internimage_s_1k_224] (main.py 519): INFO EPOCH 158 training takes 0:03:12
[2025-01-18 21:55:56 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_158.pth saving......
[2025-01-18 21:55:58 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_158.pth saved !!!
[2025-01-18 21:56:05 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.439 (7.439)	Loss 0.8265 (0.8265)	Acc@1 83.105 (83.105)	Acc@5 96.558 (96.558)	Mem 24308MB
[2025-01-18 21:56:09 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.139 (0.996)	Loss 1.1113 (0.9583)	Acc@1 75.293 (79.785)	Acc@5 93.335 (95.104)	Mem 24308MB
[2025-01-18 21:56:09 internimage_s_1k_224] (main.py 575): INFO [Epoch:158] * Acc@1 79.629 Acc@5 95.138
[2025-01-18 21:56:09 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.6%
[2025-01-18 21:56:09 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 79.81%
[2025-01-18 21:56:18 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.472 (8.472)	Loss 0.7114 (0.7114)	Acc@1 83.667 (83.667)	Acc@5 97.266 (97.266)	Mem 24308MB
[2025-01-18 21:56:22 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.165)	Loss 1.0143 (0.8372)	Acc@1 75.586 (80.555)	Acc@5 93.799 (95.477)	Mem 24308MB
[2025-01-18 21:56:22 internimage_s_1k_224] (main.py 575): INFO [Epoch:158] * Acc@1 80.434 Acc@5 95.503
[2025-01-18 21:56:22 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.4%
[2025-01-18 21:56:22 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 21:56:24 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 21:56:24 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.43%
[2025-01-18 21:56:27 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][0/312]	eta 0:11:20 lr 0.001834	time 2.1808 (2.1808)	model_time 0.6157 (0.6157)	loss 4.1747 (4.1747)	grad_norm 3.1821 (3.1821/0.0000)	mem 24308MB
[2025-01-18 21:56:32 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][10/312]	eta 0:03:41 lr 0.001833	time 0.5852 (0.7341)	model_time 0.5850 (0.5915)	loss 2.4172 (3.3033)	grad_norm 1.8029 (2.2357/1.0135)	mem 24308MB
[2025-01-18 21:56:39 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][20/312]	eta 0:03:16 lr 0.001832	time 0.6110 (0.6722)	model_time 0.6104 (0.5973)	loss 3.0080 (3.2582)	grad_norm 0.8619 (2.0228/0.9050)	mem 24308MB
[2025-01-18 21:56:44 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][30/312]	eta 0:03:02 lr 0.001832	time 0.5806 (0.6463)	model_time 0.5804 (0.5955)	loss 2.3647 (3.2337)	grad_norm 1.3877 (2.1050/0.9009)	mem 24308MB
[2025-01-18 21:56:50 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][40/312]	eta 0:02:52 lr 0.001831	time 0.5842 (0.6357)	model_time 0.5838 (0.5972)	loss 3.5098 (3.2755)	grad_norm 1.0945 (2.1246/0.9055)	mem 24308MB
[2025-01-18 21:56:57 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][50/312]	eta 0:02:45 lr 0.001830	time 0.6052 (0.6305)	model_time 0.6051 (0.5994)	loss 4.0380 (3.2734)	grad_norm 2.2532 (2.0055/0.8781)	mem 24308MB
[2025-01-18 21:57:03 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][60/312]	eta 0:02:37 lr 0.001830	time 0.6633 (0.6258)	model_time 0.6631 (0.5997)	loss 2.7783 (3.2461)	grad_norm 1.5745 (1.9588/0.8432)	mem 24308MB
[2025-01-18 21:57:09 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][70/312]	eta 0:02:30 lr 0.001829	time 0.6066 (0.6225)	model_time 0.6065 (0.6001)	loss 2.4598 (3.2472)	grad_norm 1.5035 (1.8850/0.8097)	mem 24308MB
[2025-01-18 21:57:15 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][80/312]	eta 0:02:24 lr 0.001828	time 0.5952 (0.6236)	model_time 0.5950 (0.6039)	loss 3.5611 (3.2786)	grad_norm 2.3274 (1.8235/0.7859)	mem 24308MB
[2025-01-18 21:57:21 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][90/312]	eta 0:02:18 lr 0.001828	time 0.6490 (0.6233)	model_time 0.6489 (0.6057)	loss 3.3089 (3.2718)	grad_norm 4.6566 (1.8296/0.8068)	mem 24308MB
[2025-01-18 21:57:27 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][100/312]	eta 0:02:12 lr 0.001827	time 0.5803 (0.6237)	model_time 0.5799 (0.6079)	loss 3.0462 (3.2490)	grad_norm 2.1855 (1.8716/0.8538)	mem 24308MB
[2025-01-18 21:57:34 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][110/312]	eta 0:02:05 lr 0.001826	time 0.5963 (0.6226)	model_time 0.5962 (0.6081)	loss 3.7122 (3.2367)	grad_norm 0.8478 (1.8363/0.8326)	mem 24308MB
[2025-01-18 21:57:40 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][120/312]	eta 0:01:59 lr 0.001826	time 0.6928 (0.6239)	model_time 0.6923 (0.6105)	loss 2.6763 (3.2367)	grad_norm 2.2355 (1.8043/0.8217)	mem 24308MB
[2025-01-18 21:57:46 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][130/312]	eta 0:01:53 lr 0.001825	time 0.5826 (0.6210)	model_time 0.5824 (0.6087)	loss 4.0019 (3.2586)	grad_norm 2.3631 (1.7960/0.8057)	mem 24308MB
[2025-01-18 21:57:52 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][140/312]	eta 0:01:46 lr 0.001824	time 0.5812 (0.6193)	model_time 0.5807 (0.6078)	loss 3.3402 (3.2542)	grad_norm 2.7946 (1.8075/0.8094)	mem 24308MB
[2025-01-18 21:57:58 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][150/312]	eta 0:01:40 lr 0.001824	time 0.6037 (0.6173)	model_time 0.6032 (0.6065)	loss 2.8886 (3.2460)	grad_norm 0.9329 (1.8035/0.7990)	mem 24308MB
[2025-01-18 21:58:04 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][160/312]	eta 0:01:33 lr 0.001823	time 0.5766 (0.6160)	model_time 0.5764 (0.6059)	loss 4.2523 (3.2632)	grad_norm 0.8152 (1.7858/0.7878)	mem 24308MB
[2025-01-18 21:58:10 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][170/312]	eta 0:01:27 lr 0.001822	time 0.5896 (0.6149)	model_time 0.5894 (0.6054)	loss 3.6746 (3.2490)	grad_norm 1.5317 (1.7542/0.7779)	mem 24308MB
[2025-01-18 21:58:16 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][180/312]	eta 0:01:21 lr 0.001822	time 0.6636 (0.6149)	model_time 0.6632 (0.6058)	loss 2.2373 (3.2548)	grad_norm 0.9504 (1.7218/0.7709)	mem 24308MB
[2025-01-18 21:58:22 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][190/312]	eta 0:01:14 lr 0.001821	time 0.6652 (0.6143)	model_time 0.6647 (0.6057)	loss 3.3426 (3.2573)	grad_norm 1.6937 (1.7057/0.7567)	mem 24308MB
[2025-01-18 21:58:28 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][200/312]	eta 0:01:08 lr 0.001820	time 0.6706 (0.6149)	model_time 0.6701 (0.6067)	loss 3.6380 (3.2619)	grad_norm 3.2153 (1.7284/0.7650)	mem 24308MB
[2025-01-18 21:58:34 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][210/312]	eta 0:01:02 lr 0.001820	time 0.6565 (0.6151)	model_time 0.6563 (0.6073)	loss 3.3556 (3.2719)	grad_norm 2.3744 (1.7687/0.8108)	mem 24308MB
[2025-01-18 21:58:40 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][220/312]	eta 0:00:56 lr 0.001819	time 0.5888 (0.6146)	model_time 0.5887 (0.6072)	loss 2.9439 (3.2741)	grad_norm 3.1769 (1.7948/0.8200)	mem 24308MB
[2025-01-18 21:58:46 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][230/312]	eta 0:00:50 lr 0.001818	time 0.6094 (0.6143)	model_time 0.6092 (0.6071)	loss 3.1702 (3.2733)	grad_norm 0.9834 (1.7933/0.8259)	mem 24308MB
[2025-01-18 21:58:52 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][240/312]	eta 0:00:44 lr 0.001818	time 0.5904 (0.6138)	model_time 0.5900 (0.6070)	loss 3.4112 (3.2725)	grad_norm 1.2327 (1.7922/0.8155)	mem 24308MB
[2025-01-18 21:58:58 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][250/312]	eta 0:00:38 lr 0.001817	time 0.5911 (0.6135)	model_time 0.5909 (0.6069)	loss 3.3696 (3.2592)	grad_norm 1.2202 (1.8064/0.8240)	mem 24308MB
[2025-01-18 21:59:04 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][260/312]	eta 0:00:31 lr 0.001816	time 0.5777 (0.6128)	model_time 0.5776 (0.6065)	loss 3.2715 (3.2658)	grad_norm 1.7651 (1.8059/0.8164)	mem 24308MB
[2025-01-18 21:59:10 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][270/312]	eta 0:00:25 lr 0.001816	time 0.5920 (0.6120)	model_time 0.5916 (0.6058)	loss 3.2935 (3.2723)	grad_norm 2.6982 (1.7926/0.8143)	mem 24308MB
[2025-01-18 21:59:16 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][280/312]	eta 0:00:19 lr 0.001815	time 0.5884 (0.6114)	model_time 0.5879 (0.6054)	loss 3.4153 (3.2721)	grad_norm 1.6257 (1.7762/0.8081)	mem 24308MB
[2025-01-18 21:59:22 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][290/312]	eta 0:00:13 lr 0.001814	time 0.5867 (0.6110)	model_time 0.5861 (0.6052)	loss 3.5519 (3.2758)	grad_norm 1.4585 (1.7701/0.7996)	mem 24308MB
[2025-01-18 21:59:28 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][300/312]	eta 0:00:07 lr 0.001814	time 0.5679 (0.6106)	model_time 0.5678 (0.6050)	loss 2.4523 (3.2768)	grad_norm 3.9366 (1.7883/0.8153)	mem 24308MB
[2025-01-18 21:59:34 internimage_s_1k_224] (main.py 510): INFO Train: [159/300][310/312]	eta 0:00:01 lr 0.001813	time 0.6457 (0.6104)	model_time 0.6456 (0.6050)	loss 4.0939 (3.2852)	grad_norm 1.1498 (1.7797/0.8024)	mem 24308MB
[2025-01-18 21:59:35 internimage_s_1k_224] (main.py 519): INFO EPOCH 159 training takes 0:03:10
[2025-01-18 21:59:35 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_159.pth saving......
[2025-01-18 21:59:37 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_159.pth saved !!!
[2025-01-18 21:59:44 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.576 (7.576)	Loss 0.7983 (0.7983)	Acc@1 82.031 (82.031)	Acc@5 96.802 (96.802)	Mem 24308MB
[2025-01-18 21:59:48 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.000)	Loss 1.1040 (0.9322)	Acc@1 74.438 (79.574)	Acc@5 93.384 (95.226)	Mem 24308MB
[2025-01-18 21:59:48 internimage_s_1k_224] (main.py 575): INFO [Epoch:159] * Acc@1 79.459 Acc@5 95.240
[2025-01-18 21:59:48 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.5%
[2025-01-18 21:59:48 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 79.81%
[2025-01-18 21:59:56 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.475 (8.475)	Loss 0.7110 (0.7110)	Acc@1 83.740 (83.740)	Acc@5 97.290 (97.290)	Mem 24308MB
[2025-01-18 22:00:01 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.161)	Loss 1.0126 (0.8362)	Acc@1 75.659 (80.589)	Acc@5 93.872 (95.492)	Mem 24308MB
[2025-01-18 22:00:01 internimage_s_1k_224] (main.py 575): INFO [Epoch:159] * Acc@1 80.466 Acc@5 95.517
[2025-01-18 22:00:01 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.5%
[2025-01-18 22:00:01 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 22:00:03 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 22:00:03 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.47%
[2025-01-18 22:00:05 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][0/312]	eta 0:12:04 lr 0.001813	time 2.3207 (2.3207)	model_time 0.5945 (0.5945)	loss 2.7408 (2.7408)	grad_norm 2.0773 (2.0773/0.0000)	mem 24308MB
[2025-01-18 22:00:11 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][10/312]	eta 0:03:54 lr 0.001812	time 0.6046 (0.7750)	model_time 0.6044 (0.6178)	loss 4.0944 (3.4824)	grad_norm 1.5691 (1.7031/0.3951)	mem 24308MB
[2025-01-18 22:00:18 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][20/312]	eta 0:03:24 lr 0.001812	time 0.5656 (0.7019)	model_time 0.5655 (0.6193)	loss 4.1641 (3.5701)	grad_norm 3.0606 (1.8624/0.6661)	mem 24308MB
[2025-01-18 22:00:24 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][30/312]	eta 0:03:09 lr 0.001811	time 0.6134 (0.6727)	model_time 0.6132 (0.6167)	loss 3.2281 (3.5271)	grad_norm 1.4030 (1.7053/0.6099)	mem 24308MB
[2025-01-18 22:00:30 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][40/312]	eta 0:02:58 lr 0.001810	time 0.6378 (0.6562)	model_time 0.6376 (0.6138)	loss 3.6072 (3.4294)	grad_norm 1.3570 (1.5608/0.6000)	mem 24308MB
[2025-01-18 22:00:36 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][50/312]	eta 0:02:48 lr 0.001810	time 0.5877 (0.6447)	model_time 0.5875 (0.6105)	loss 3.3226 (3.3587)	grad_norm 1.1887 (1.5668/0.5892)	mem 24308MB
[2025-01-18 22:00:42 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][60/312]	eta 0:02:40 lr 0.001809	time 0.5876 (0.6380)	model_time 0.5874 (0.6094)	loss 3.0594 (3.3955)	grad_norm 1.1671 (1.5320/0.5559)	mem 24308MB
[2025-01-18 22:00:48 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][70/312]	eta 0:02:33 lr 0.001808	time 0.7024 (0.6340)	model_time 0.7022 (0.6094)	loss 2.8895 (3.3904)	grad_norm 1.6320 (1.6003/0.6151)	mem 24308MB
[2025-01-18 22:00:54 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][80/312]	eta 0:02:25 lr 0.001808	time 0.5835 (0.6284)	model_time 0.5834 (0.6067)	loss 2.5009 (3.3389)	grad_norm 1.0859 (1.5596/0.5943)	mem 24308MB
[2025-01-18 22:01:00 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][90/312]	eta 0:02:18 lr 0.001807	time 0.6015 (0.6253)	model_time 0.6014 (0.6059)	loss 2.9859 (3.3160)	grad_norm 1.4356 (1.5741/0.5822)	mem 24308MB
[2025-01-18 22:01:06 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][100/312]	eta 0:02:12 lr 0.001806	time 0.5662 (0.6230)	model_time 0.5660 (0.6056)	loss 2.1176 (3.2944)	grad_norm 1.6616 (1.6031/0.6062)	mem 24308MB
[2025-01-18 22:01:12 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][110/312]	eta 0:02:05 lr 0.001806	time 0.5744 (0.6215)	model_time 0.5739 (0.6056)	loss 2.8140 (3.3004)	grad_norm 1.5632 (1.5859/0.5888)	mem 24308MB
[2025-01-18 22:01:18 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][120/312]	eta 0:01:59 lr 0.001805	time 0.5663 (0.6209)	model_time 0.5661 (0.6063)	loss 2.2104 (3.2647)	grad_norm 1.1394 (1.6123/0.6044)	mem 24308MB
[2025-01-18 22:01:24 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][130/312]	eta 0:01:52 lr 0.001804	time 0.5764 (0.6199)	model_time 0.5762 (0.6064)	loss 3.5183 (3.2684)	grad_norm 1.6353 (1.6536/0.6396)	mem 24308MB
[2025-01-18 22:01:30 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][140/312]	eta 0:01:46 lr 0.001804	time 0.6170 (0.6199)	model_time 0.6166 (0.6074)	loss 3.5966 (3.2756)	grad_norm 2.2277 (1.6777/0.6489)	mem 24308MB
[2025-01-18 22:01:37 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][150/312]	eta 0:01:40 lr 0.001803	time 0.5744 (0.6196)	model_time 0.5742 (0.6078)	loss 2.7634 (3.2882)	grad_norm 1.0390 (1.6827/0.6560)	mem 24308MB
[2025-01-18 22:01:43 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][160/312]	eta 0:01:34 lr 0.001802	time 0.5803 (0.6189)	model_time 0.5801 (0.6078)	loss 3.9516 (3.2809)	grad_norm 1.9023 (1.6812/0.6456)	mem 24308MB
[2025-01-18 22:01:49 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][170/312]	eta 0:01:27 lr 0.001802	time 0.6699 (0.6181)	model_time 0.6697 (0.6076)	loss 2.5454 (3.2772)	grad_norm 3.0159 (1.7187/0.6921)	mem 24308MB
[2025-01-18 22:01:55 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][180/312]	eta 0:01:21 lr 0.001801	time 0.5784 (0.6174)	model_time 0.5779 (0.6075)	loss 2.0203 (3.2768)	grad_norm 0.8900 (1.7524/0.7366)	mem 24308MB
[2025-01-18 22:02:01 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][190/312]	eta 0:01:15 lr 0.001800	time 0.5866 (0.6167)	model_time 0.5861 (0.6073)	loss 3.2984 (3.2549)	grad_norm 2.1317 (1.7741/0.7325)	mem 24308MB
[2025-01-18 22:02:07 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][200/312]	eta 0:01:08 lr 0.001800	time 0.6014 (0.6155)	model_time 0.6013 (0.6066)	loss 3.2519 (3.2593)	grad_norm 2.2318 (1.7805/0.7345)	mem 24308MB
[2025-01-18 22:02:13 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][210/312]	eta 0:01:02 lr 0.001799	time 0.6447 (0.6148)	model_time 0.6445 (0.6062)	loss 3.8555 (3.2457)	grad_norm 1.5657 (1.7593/0.7310)	mem 24308MB
[2025-01-18 22:02:19 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][220/312]	eta 0:00:56 lr 0.001798	time 0.5932 (0.6141)	model_time 0.5930 (0.6059)	loss 3.7032 (3.2454)	grad_norm 2.3957 (1.7660/0.7297)	mem 24308MB
[2025-01-18 22:02:25 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][230/312]	eta 0:00:50 lr 0.001798	time 0.5920 (0.6139)	model_time 0.5915 (0.6061)	loss 2.2133 (3.2439)	grad_norm 3.1495 (1.8085/0.7720)	mem 24308MB
[2025-01-18 22:02:31 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][240/312]	eta 0:00:44 lr 0.001797	time 0.8421 (0.6147)	model_time 0.8419 (0.6072)	loss 4.0199 (3.2509)	grad_norm 2.4399 (1.8336/0.7796)	mem 24308MB
[2025-01-18 22:02:37 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][250/312]	eta 0:00:38 lr 0.001797	time 0.5846 (0.6145)	model_time 0.5841 (0.6073)	loss 2.6855 (3.2491)	grad_norm 1.8931 (1.8217/0.7745)	mem 24308MB
[2025-01-18 22:02:43 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][260/312]	eta 0:00:31 lr 0.001796	time 0.6826 (0.6149)	model_time 0.6824 (0.6079)	loss 3.3608 (3.2441)	grad_norm 1.6338 (1.8061/0.7663)	mem 24308MB
[2025-01-18 22:02:50 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][270/312]	eta 0:00:25 lr 0.001795	time 0.6059 (0.6148)	model_time 0.6053 (0.6080)	loss 3.5274 (3.2516)	grad_norm 3.0641 (1.8248/0.7908)	mem 24308MB
[2025-01-18 22:02:56 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][280/312]	eta 0:00:19 lr 0.001795	time 0.5715 (0.6150)	model_time 0.5710 (0.6085)	loss 3.4376 (3.2462)	grad_norm 3.2255 (1.8246/0.7951)	mem 24308MB
[2025-01-18 22:03:02 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][290/312]	eta 0:00:13 lr 0.001794	time 0.6801 (0.6148)	model_time 0.6799 (0.6085)	loss 3.6470 (3.2527)	grad_norm 2.1519 (1.8216/0.7956)	mem 24308MB
[2025-01-18 22:03:08 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][300/312]	eta 0:00:07 lr 0.001793	time 0.5678 (0.6148)	model_time 0.5677 (0.6087)	loss 2.6828 (3.2533)	grad_norm 2.6610 (1.8254/0.7936)	mem 24308MB
[2025-01-18 22:03:14 internimage_s_1k_224] (main.py 510): INFO Train: [160/300][310/312]	eta 0:00:01 lr 0.001793	time 0.5594 (0.6138)	model_time 0.5592 (0.6079)	loss 3.0371 (3.2520)	grad_norm 1.3376 (1.8169/0.7958)	mem 24308MB
[2025-01-18 22:03:14 internimage_s_1k_224] (main.py 519): INFO EPOCH 160 training takes 0:03:11
[2025-01-18 22:03:14 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_160.pth saving......
[2025-01-18 22:03:16 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_160.pth saved !!!
[2025-01-18 22:03:24 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.593 (7.593)	Loss 0.8191 (0.8191)	Acc@1 82.935 (82.935)	Acc@5 96.729 (96.729)	Mem 24308MB
[2025-01-18 22:03:28 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.038)	Loss 1.0794 (0.9287)	Acc@1 75.342 (79.885)	Acc@5 93.823 (95.290)	Mem 24308MB
[2025-01-18 22:03:28 internimage_s_1k_224] (main.py 575): INFO [Epoch:160] * Acc@1 79.720 Acc@5 95.298
[2025-01-18 22:03:28 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.7%
[2025-01-18 22:03:28 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 79.81%
[2025-01-18 22:03:36 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.515 (8.515)	Loss 0.7107 (0.7107)	Acc@1 83.789 (83.789)	Acc@5 97.339 (97.339)	Mem 24308MB
[2025-01-18 22:03:41 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.160)	Loss 1.0109 (0.8352)	Acc@1 75.659 (80.597)	Acc@5 93.921 (95.517)	Mem 24308MB
[2025-01-18 22:03:41 internimage_s_1k_224] (main.py 575): INFO [Epoch:160] * Acc@1 80.482 Acc@5 95.539
[2025-01-18 22:03:41 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.5%
[2025-01-18 22:03:41 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 22:03:43 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 22:03:43 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.48%
[2025-01-18 22:03:45 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][0/312]	eta 0:12:03 lr 0.001792	time 2.3182 (2.3182)	model_time 0.6073 (0.6073)	loss 2.7470 (2.7470)	grad_norm 0.7801 (0.7801/0.0000)	mem 24308MB
[2025-01-18 22:03:51 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][10/312]	eta 0:03:49 lr 0.001792	time 0.5921 (0.7615)	model_time 0.5920 (0.6057)	loss 3.6182 (3.1890)	grad_norm 3.3211 (1.5929/0.7702)	mem 24308MB
[2025-01-18 22:03:57 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][20/312]	eta 0:03:19 lr 0.001791	time 0.5820 (0.6846)	model_time 0.5818 (0.6028)	loss 2.9445 (3.2378)	grad_norm 1.6415 (1.8161/0.8365)	mem 24308MB
[2025-01-18 22:04:04 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][30/312]	eta 0:03:08 lr 0.001790	time 0.6300 (0.6698)	model_time 0.6295 (0.6142)	loss 2.9565 (3.2337)	grad_norm 1.4660 (1.7255/0.7590)	mem 24308MB
[2025-01-18 22:04:10 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][40/312]	eta 0:02:58 lr 0.001790	time 0.5883 (0.6577)	model_time 0.5881 (0.6156)	loss 3.5988 (3.2808)	grad_norm 2.0098 (1.6627/0.6984)	mem 24308MB
[2025-01-18 22:04:16 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][50/312]	eta 0:02:49 lr 0.001789	time 0.5927 (0.6482)	model_time 0.5926 (0.6142)	loss 3.0348 (3.2681)	grad_norm 2.6425 (1.7078/0.6947)	mem 24308MB
[2025-01-18 22:04:22 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][60/312]	eta 0:02:42 lr 0.001788	time 0.6573 (0.6437)	model_time 0.6571 (0.6153)	loss 3.2939 (3.2916)	grad_norm 1.5738 (1.7462/0.6748)	mem 24308MB
[2025-01-18 22:04:28 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][70/312]	eta 0:02:34 lr 0.001788	time 0.5916 (0.6404)	model_time 0.5911 (0.6159)	loss 2.3289 (3.2657)	grad_norm 1.6396 (1.7439/0.6449)	mem 24308MB
[2025-01-18 22:04:34 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][80/312]	eta 0:02:28 lr 0.001787	time 0.6691 (0.6380)	model_time 0.6689 (0.6165)	loss 2.7600 (3.2378)	grad_norm 1.9892 (1.7847/0.6746)	mem 24308MB
[2025-01-18 22:04:40 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][90/312]	eta 0:02:20 lr 0.001786	time 0.5911 (0.6330)	model_time 0.5909 (0.6138)	loss 3.4719 (3.2406)	grad_norm 1.4430 (1.7974/0.6613)	mem 24308MB
[2025-01-18 22:04:46 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][100/312]	eta 0:02:13 lr 0.001786	time 0.5861 (0.6302)	model_time 0.5860 (0.6129)	loss 2.9889 (3.2665)	grad_norm 1.0199 (1.7462/0.6545)	mem 24308MB
[2025-01-18 22:04:53 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][110/312]	eta 0:02:06 lr 0.001785	time 0.5799 (0.6285)	model_time 0.5792 (0.6128)	loss 3.4874 (3.2782)	grad_norm 3.3047 (1.7435/0.6638)	mem 24308MB
[2025-01-18 22:04:58 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][120/312]	eta 0:02:00 lr 0.001785	time 0.5826 (0.6254)	model_time 0.5822 (0.6109)	loss 2.6962 (3.2828)	grad_norm 2.6051 (1.7470/0.6684)	mem 24308MB
[2025-01-18 22:05:04 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][130/312]	eta 0:01:53 lr 0.001784	time 0.5859 (0.6238)	model_time 0.5857 (0.6104)	loss 3.9032 (3.2665)	grad_norm 2.0160 (1.7881/0.6909)	mem 24308MB
[2025-01-18 22:05:11 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][140/312]	eta 0:01:47 lr 0.001783	time 0.6217 (0.6228)	model_time 0.6215 (0.6103)	loss 3.7621 (3.2717)	grad_norm 0.9853 (1.8076/0.6932)	mem 24308MB
[2025-01-18 22:05:17 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][150/312]	eta 0:01:40 lr 0.001783	time 0.5912 (0.6218)	model_time 0.5910 (0.6101)	loss 2.3056 (3.2733)	grad_norm 1.0887 (1.7852/0.6809)	mem 24308MB
[2025-01-18 22:05:23 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][160/312]	eta 0:01:34 lr 0.001782	time 0.5712 (0.6225)	model_time 0.5709 (0.6115)	loss 3.3558 (3.2731)	grad_norm 4.2006 (1.7825/0.6942)	mem 24308MB
[2025-01-18 22:05:29 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][170/312]	eta 0:01:28 lr 0.001781	time 0.5926 (0.6216)	model_time 0.5921 (0.6112)	loss 3.7700 (3.2915)	grad_norm 1.8919 (1.8134/0.7555)	mem 24308MB
[2025-01-18 22:05:35 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][180/312]	eta 0:01:21 lr 0.001781	time 0.6812 (0.6210)	model_time 0.6809 (0.6112)	loss 3.8436 (3.3031)	grad_norm 2.0256 (1.8156/0.7414)	mem 24308MB
[2025-01-18 22:05:41 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][190/312]	eta 0:01:15 lr 0.001780	time 0.5663 (0.6212)	model_time 0.5658 (0.6119)	loss 3.8208 (3.3126)	grad_norm 1.3410 (1.7984/0.7311)	mem 24308MB
[2025-01-18 22:05:48 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][200/312]	eta 0:01:09 lr 0.001779	time 0.6428 (0.6219)	model_time 0.6426 (0.6131)	loss 3.6839 (3.3198)	grad_norm 1.3264 (1.7901/0.7186)	mem 24308MB
[2025-01-18 22:05:54 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][210/312]	eta 0:01:03 lr 0.001779	time 0.5801 (0.6210)	model_time 0.5799 (0.6125)	loss 2.4334 (3.3261)	grad_norm 2.5491 (1.7959/0.7061)	mem 24308MB
[2025-01-18 22:06:00 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][220/312]	eta 0:00:57 lr 0.001778	time 0.5982 (0.6200)	model_time 0.5977 (0.6119)	loss 3.8267 (3.3362)	grad_norm 2.5641 (1.8316/0.7468)	mem 24308MB
[2025-01-18 22:06:06 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][230/312]	eta 0:00:50 lr 0.001777	time 0.5829 (0.6204)	model_time 0.5825 (0.6126)	loss 3.4764 (3.3428)	grad_norm 0.8258 (1.8271/0.7374)	mem 24308MB
[2025-01-18 22:06:12 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][240/312]	eta 0:00:44 lr 0.001777	time 0.5823 (0.6192)	model_time 0.5818 (0.6117)	loss 2.9031 (3.3443)	grad_norm 0.9878 (1.8088/0.7321)	mem 24308MB
[2025-01-18 22:06:18 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][250/312]	eta 0:00:38 lr 0.001776	time 0.5793 (0.6186)	model_time 0.5791 (0.6114)	loss 2.3414 (3.3401)	grad_norm 0.9908 (1.8023/0.7271)	mem 24308MB
[2025-01-18 22:06:24 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][260/312]	eta 0:00:32 lr 0.001775	time 0.5775 (0.6178)	model_time 0.5773 (0.6108)	loss 4.1232 (3.3321)	grad_norm 1.2217 (1.7888/0.7212)	mem 24308MB
[2025-01-18 22:06:30 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][270/312]	eta 0:00:25 lr 0.001775	time 0.6437 (0.6182)	model_time 0.6435 (0.6115)	loss 3.6148 (3.3333)	grad_norm 1.7023 (1.7755/0.7160)	mem 24308MB
[2025-01-18 22:06:36 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][280/312]	eta 0:00:19 lr 0.001774	time 0.5847 (0.6180)	model_time 0.5845 (0.6116)	loss 3.4079 (3.3325)	grad_norm 1.7146 (1.8189/0.7900)	mem 24308MB
[2025-01-18 22:06:42 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][290/312]	eta 0:00:13 lr 0.001773	time 0.6556 (0.6171)	model_time 0.6555 (0.6109)	loss 3.1545 (3.3254)	grad_norm 2.0495 (1.8290/0.7901)	mem 24308MB
[2025-01-18 22:06:48 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][300/312]	eta 0:00:07 lr 0.001773	time 0.5663 (0.6167)	model_time 0.5662 (0.6106)	loss 2.7777 (3.3214)	grad_norm 1.8454 (1.8156/0.7833)	mem 24308MB
[2025-01-18 22:06:54 internimage_s_1k_224] (main.py 510): INFO Train: [161/300][310/312]	eta 0:00:01 lr 0.001772	time 0.5769 (0.6164)	model_time 0.5768 (0.6105)	loss 3.9448 (3.3287)	grad_norm 1.1266 (1.8093/0.7778)	mem 24308MB
[2025-01-18 22:06:55 internimage_s_1k_224] (main.py 519): INFO EPOCH 161 training takes 0:03:12
[2025-01-18 22:06:55 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_161.pth saving......
[2025-01-18 22:06:57 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_161.pth saved !!!
[2025-01-18 22:07:04 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.432 (7.432)	Loss 0.8168 (0.8168)	Acc@1 83.301 (83.301)	Acc@5 96.826 (96.826)	Mem 24308MB
[2025-01-18 22:07:08 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.001)	Loss 1.1087 (0.9521)	Acc@1 74.927 (79.805)	Acc@5 93.774 (95.179)	Mem 24308MB
[2025-01-18 22:07:08 internimage_s_1k_224] (main.py 575): INFO [Epoch:161] * Acc@1 79.734 Acc@5 95.208
[2025-01-18 22:07:08 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.7%
[2025-01-18 22:07:08 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 79.81%
[2025-01-18 22:07:17 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.720 (8.720)	Loss 0.7104 (0.7104)	Acc@1 83.862 (83.862)	Acc@5 97.363 (97.363)	Mem 24308MB
[2025-01-18 22:07:21 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.181)	Loss 1.0093 (0.8343)	Acc@1 75.757 (80.651)	Acc@5 93.921 (95.550)	Mem 24308MB
[2025-01-18 22:07:21 internimage_s_1k_224] (main.py 575): INFO [Epoch:161] * Acc@1 80.538 Acc@5 95.573
[2025-01-18 22:07:21 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.5%
[2025-01-18 22:07:21 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 22:07:23 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 22:07:23 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.54%
[2025-01-18 22:07:26 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][0/312]	eta 0:11:29 lr 0.001772	time 2.2098 (2.2098)	model_time 0.5808 (0.5808)	loss 3.5013 (3.5013)	grad_norm 1.8683 (1.8683/0.0000)	mem 24308MB
[2025-01-18 22:07:32 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][10/312]	eta 0:03:51 lr 0.001771	time 0.5771 (0.7681)	model_time 0.5768 (0.6196)	loss 3.2984 (3.4643)	grad_norm 1.5586 (1.7772/0.5233)	mem 24308MB
[2025-01-18 22:07:38 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][20/312]	eta 0:03:22 lr 0.001771	time 0.5857 (0.6949)	model_time 0.5855 (0.6170)	loss 2.7116 (3.3427)	grad_norm 1.4628 (1.7565/0.4831)	mem 24308MB
[2025-01-18 22:07:44 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][30/312]	eta 0:03:06 lr 0.001770	time 0.5841 (0.6629)	model_time 0.5836 (0.6100)	loss 3.4250 (3.3828)	grad_norm 2.0909 (1.9833/1.0031)	mem 24308MB
[2025-01-18 22:07:50 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][40/312]	eta 0:02:56 lr 0.001769	time 0.6091 (0.6493)	model_time 0.6089 (0.6092)	loss 3.9841 (3.3585)	grad_norm 0.7885 (1.9757/0.9677)	mem 24308MB
[2025-01-18 22:07:56 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][50/312]	eta 0:02:47 lr 0.001769	time 0.5875 (0.6388)	model_time 0.5873 (0.6065)	loss 2.7130 (3.3215)	grad_norm 1.6554 (1.9393/0.9178)	mem 24308MB
[2025-01-18 22:08:02 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][60/312]	eta 0:02:39 lr 0.001768	time 0.6770 (0.6329)	model_time 0.6768 (0.6058)	loss 4.0280 (3.2713)	grad_norm 1.8626 (1.8831/0.8727)	mem 24308MB
[2025-01-18 22:08:08 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][70/312]	eta 0:02:32 lr 0.001767	time 0.5953 (0.6283)	model_time 0.5951 (0.6050)	loss 3.4457 (3.2540)	grad_norm 1.3508 (1.8649/0.8325)	mem 24308MB
[2025-01-18 22:08:14 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][80/312]	eta 0:02:25 lr 0.001767	time 0.5678 (0.6270)	model_time 0.5677 (0.6065)	loss 2.8169 (3.2252)	grad_norm 2.5892 (1.8539/0.7973)	mem 24308MB
[2025-01-18 22:08:20 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][90/312]	eta 0:02:18 lr 0.001766	time 0.5891 (0.6241)	model_time 0.5886 (0.6058)	loss 2.9888 (3.1994)	grad_norm 1.7956 (1.8680/0.8094)	mem 24308MB
[2025-01-18 22:08:26 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][100/312]	eta 0:02:11 lr 0.001765	time 0.6000 (0.6224)	model_time 0.5998 (0.6060)	loss 3.4831 (3.2231)	grad_norm 1.9721 (1.8906/0.7933)	mem 24308MB
[2025-01-18 22:08:32 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][110/312]	eta 0:02:05 lr 0.001765	time 0.5784 (0.6205)	model_time 0.5782 (0.6055)	loss 2.7576 (3.1817)	grad_norm 0.8557 (1.8473/0.7845)	mem 24308MB
[2025-01-18 22:08:39 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][120/312]	eta 0:01:59 lr 0.001764	time 0.5832 (0.6201)	model_time 0.5828 (0.6063)	loss 3.7746 (3.2032)	grad_norm 1.4992 (1.8422/0.7765)	mem 24308MB
[2025-01-18 22:08:45 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][130/312]	eta 0:01:53 lr 0.001763	time 0.7453 (0.6211)	model_time 0.7451 (0.6083)	loss 3.5198 (3.2182)	grad_norm 1.4225 (1.8584/0.7886)	mem 24308MB
[2025-01-18 22:08:51 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][140/312]	eta 0:01:46 lr 0.001763	time 0.5822 (0.6195)	model_time 0.5820 (0.6076)	loss 3.9730 (3.2210)	grad_norm 3.3614 (1.8420/0.7971)	mem 24308MB
[2025-01-18 22:08:57 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][150/312]	eta 0:01:40 lr 0.001762	time 0.5754 (0.6180)	model_time 0.5753 (0.6069)	loss 3.9869 (3.2465)	grad_norm 1.7828 (1.8653/0.8232)	mem 24308MB
[2025-01-18 22:09:03 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][160/312]	eta 0:01:33 lr 0.001761	time 0.5970 (0.6176)	model_time 0.5966 (0.6072)	loss 2.9387 (3.2598)	grad_norm 1.9256 (1.8734/0.8078)	mem 24308MB
[2025-01-18 22:09:09 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][170/312]	eta 0:01:27 lr 0.001761	time 0.5988 (0.6163)	model_time 0.5986 (0.6064)	loss 3.7120 (3.2692)	grad_norm 1.8900 (1.9036/0.8063)	mem 24308MB
[2025-01-18 22:09:15 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][180/312]	eta 0:01:21 lr 0.001760	time 0.5791 (0.6152)	model_time 0.5786 (0.6058)	loss 3.9544 (3.2842)	grad_norm 1.5103 (1.8740/0.7979)	mem 24308MB
[2025-01-18 22:09:21 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][190/312]	eta 0:01:14 lr 0.001759	time 0.5801 (0.6145)	model_time 0.5799 (0.6057)	loss 3.3513 (3.2856)	grad_norm 1.6744 (1.8456/0.7923)	mem 24308MB
[2025-01-18 22:09:27 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][200/312]	eta 0:01:08 lr 0.001759	time 0.5992 (0.6138)	model_time 0.5988 (0.6054)	loss 4.0248 (3.2941)	grad_norm 1.7969 (1.8412/0.7795)	mem 24308MB
[2025-01-18 22:09:33 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][210/312]	eta 0:01:02 lr 0.001758	time 0.6454 (0.6142)	model_time 0.6453 (0.6061)	loss 3.7281 (3.2813)	grad_norm 1.6689 (1.8690/0.7920)	mem 24308MB
[2025-01-18 22:09:39 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][220/312]	eta 0:00:56 lr 0.001757	time 0.5800 (0.6140)	model_time 0.5796 (0.6063)	loss 3.2797 (3.2664)	grad_norm 2.9384 (1.8802/0.7918)	mem 24308MB
[2025-01-18 22:09:45 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][230/312]	eta 0:00:50 lr 0.001757	time 0.5786 (0.6136)	model_time 0.5780 (0.6061)	loss 2.7493 (3.2608)	grad_norm 2.4545 (1.8629/0.7844)	mem 24308MB
[2025-01-18 22:09:51 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][240/312]	eta 0:00:44 lr 0.001756	time 0.5991 (0.6138)	model_time 0.5989 (0.6067)	loss 2.8256 (3.2457)	grad_norm 2.0436 (1.8566/0.7734)	mem 24308MB
[2025-01-18 22:09:58 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][250/312]	eta 0:00:38 lr 0.001755	time 0.5937 (0.6139)	model_time 0.5936 (0.6070)	loss 3.1571 (3.2424)	grad_norm 1.3292 (1.8831/0.8074)	mem 24308MB
[2025-01-18 22:10:04 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][260/312]	eta 0:00:31 lr 0.001755	time 0.5851 (0.6140)	model_time 0.5850 (0.6074)	loss 3.6452 (3.2420)	grad_norm 2.2779 (1.8895/0.7991)	mem 24308MB
[2025-01-18 22:10:10 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][270/312]	eta 0:00:25 lr 0.001754	time 0.5876 (0.6135)	model_time 0.5874 (0.6071)	loss 3.5368 (3.2449)	grad_norm 1.7517 (1.9047/0.8000)	mem 24308MB
[2025-01-18 22:10:16 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][280/312]	eta 0:00:19 lr 0.001753	time 0.5778 (0.6132)	model_time 0.5773 (0.6070)	loss 4.0125 (3.2416)	grad_norm 2.2111 (1.9050/0.7881)	mem 24308MB
[2025-01-18 22:10:22 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][290/312]	eta 0:00:13 lr 0.001753	time 0.5736 (0.6125)	model_time 0.5735 (0.6065)	loss 3.3123 (3.2507)	grad_norm 1.5505 (1.9027/0.7833)	mem 24308MB
[2025-01-18 22:10:28 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][300/312]	eta 0:00:07 lr 0.001752	time 0.5621 (0.6119)	model_time 0.5621 (0.6061)	loss 3.4832 (3.2545)	grad_norm 1.8702 (1.9086/0.7777)	mem 24308MB
[2025-01-18 22:10:33 internimage_s_1k_224] (main.py 510): INFO Train: [162/300][310/312]	eta 0:00:01 lr 0.001751	time 0.5673 (0.6106)	model_time 0.5672 (0.6050)	loss 3.6948 (3.2629)	grad_norm 2.0174 (1.9198/0.7832)	mem 24308MB
[2025-01-18 22:10:34 internimage_s_1k_224] (main.py 519): INFO EPOCH 162 training takes 0:03:10
[2025-01-18 22:10:34 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_162.pth saving......
[2025-01-18 22:10:36 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_162.pth saved !!!
[2025-01-18 22:10:43 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.454 (7.454)	Loss 0.8450 (0.8450)	Acc@1 82.739 (82.739)	Acc@5 96.826 (96.826)	Mem 24308MB
[2025-01-18 22:10:47 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.138 (0.993)	Loss 1.1063 (0.9681)	Acc@1 76.001 (80.129)	Acc@5 93.872 (95.253)	Mem 24308MB
[2025-01-18 22:10:47 internimage_s_1k_224] (main.py 575): INFO [Epoch:162] * Acc@1 79.986 Acc@5 95.294
[2025-01-18 22:10:47 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.0%
[2025-01-18 22:10:47 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 22:10:49 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 22:10:49 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 79.99%
[2025-01-18 22:10:57 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.524 (7.524)	Loss 0.7102 (0.7102)	Acc@1 83.862 (83.862)	Acc@5 97.388 (97.388)	Mem 24308MB
[2025-01-18 22:11:00 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.991)	Loss 1.0074 (0.8334)	Acc@1 75.757 (80.657)	Acc@5 93.945 (95.572)	Mem 24308MB
[2025-01-18 22:11:00 internimage_s_1k_224] (main.py 575): INFO [Epoch:162] * Acc@1 80.548 Acc@5 95.599
[2025-01-18 22:11:00 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.5%
[2025-01-18 22:11:00 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 22:11:02 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 22:11:02 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.55%
[2025-01-18 22:11:04 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][0/312]	eta 0:10:32 lr 0.001751	time 2.0288 (2.0288)	model_time 0.6070 (0.6070)	loss 2.9675 (2.9675)	grad_norm 1.0447 (1.0447/0.0000)	mem 24308MB
[2025-01-18 22:11:10 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][10/312]	eta 0:03:41 lr 0.001751	time 0.5807 (0.7341)	model_time 0.5805 (0.6046)	loss 3.5058 (3.5843)	grad_norm 3.3351 (1.8007/0.7509)	mem 24308MB
[2025-01-18 22:11:16 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][20/312]	eta 0:03:16 lr 0.001750	time 0.5858 (0.6728)	model_time 0.5853 (0.6048)	loss 4.0447 (3.5021)	grad_norm 1.1243 (1.7073/0.7163)	mem 24308MB
[2025-01-18 22:11:22 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][30/312]	eta 0:03:04 lr 0.001749	time 0.7298 (0.6525)	model_time 0.7296 (0.6063)	loss 3.5968 (3.4712)	grad_norm 1.5854 (1.6475/0.6199)	mem 24308MB
[2025-01-18 22:11:29 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][40/312]	eta 0:02:54 lr 0.001749	time 0.6472 (0.6409)	model_time 0.6467 (0.6059)	loss 3.3939 (3.4573)	grad_norm 2.9863 (1.7628/0.6877)	mem 24308MB
[2025-01-18 22:11:35 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][50/312]	eta 0:02:47 lr 0.001748	time 0.5739 (0.6374)	model_time 0.5735 (0.6092)	loss 3.4353 (3.4296)	grad_norm 2.2155 (1.8258/0.7084)	mem 24308MB
[2025-01-18 22:11:41 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][60/312]	eta 0:02:39 lr 0.001747	time 0.5659 (0.6341)	model_time 0.5657 (0.6104)	loss 3.5977 (3.4345)	grad_norm 2.8512 (1.8591/0.6980)	mem 24308MB
[2025-01-18 22:11:47 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][70/312]	eta 0:02:32 lr 0.001747	time 0.6649 (0.6315)	model_time 0.6648 (0.6111)	loss 2.8025 (3.4387)	grad_norm 1.3713 (1.9157/0.8566)	mem 24308MB
[2025-01-18 22:11:53 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][80/312]	eta 0:02:25 lr 0.001746	time 0.5852 (0.6266)	model_time 0.5850 (0.6087)	loss 2.9120 (3.4102)	grad_norm 1.4288 (1.8778/0.8289)	mem 24308MB
[2025-01-18 22:11:59 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][90/312]	eta 0:02:18 lr 0.001745	time 0.5925 (0.6239)	model_time 0.5923 (0.6079)	loss 2.6689 (3.3925)	grad_norm 2.8450 (1.8339/0.8121)	mem 24308MB
[2025-01-18 22:12:05 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][100/312]	eta 0:02:11 lr 0.001745	time 0.5915 (0.6212)	model_time 0.5910 (0.6067)	loss 3.1965 (3.3850)	grad_norm 1.5709 (1.9030/0.8958)	mem 24308MB
[2025-01-18 22:12:11 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][110/312]	eta 0:02:04 lr 0.001744	time 0.6857 (0.6188)	model_time 0.6855 (0.6056)	loss 2.1427 (3.3597)	grad_norm 1.6425 (1.9133/0.8675)	mem 24308MB
[2025-01-18 22:12:17 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][120/312]	eta 0:01:58 lr 0.001743	time 0.6861 (0.6168)	model_time 0.6859 (0.6046)	loss 3.7668 (3.3733)	grad_norm 1.6503 (1.9042/0.8537)	mem 24308MB
[2025-01-18 22:12:23 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][130/312]	eta 0:01:52 lr 0.001743	time 0.7029 (0.6163)	model_time 0.7024 (0.6050)	loss 2.6760 (3.3416)	grad_norm 1.7385 (1.8991/0.8347)	mem 24308MB
[2025-01-18 22:12:29 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][140/312]	eta 0:01:45 lr 0.001742	time 0.6749 (0.6148)	model_time 0.6747 (0.6043)	loss 4.2222 (3.3285)	grad_norm 1.3415 (1.8660/0.8163)	mem 24308MB
[2025-01-18 22:12:35 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][150/312]	eta 0:01:39 lr 0.001741	time 0.6795 (0.6144)	model_time 0.6791 (0.6045)	loss 2.8166 (3.3270)	grad_norm 1.5535 (1.8380/0.7984)	mem 24308MB
[2025-01-18 22:12:41 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][160/312]	eta 0:01:33 lr 0.001741	time 0.6695 (0.6137)	model_time 0.6690 (0.6045)	loss 3.5784 (3.3214)	grad_norm 3.1319 (1.8639/0.7979)	mem 24308MB
[2025-01-18 22:12:47 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][170/312]	eta 0:01:27 lr 0.001740	time 0.5803 (0.6142)	model_time 0.5801 (0.6054)	loss 3.4424 (3.3150)	grad_norm 2.0589 (1.8792/0.8046)	mem 24308MB
[2025-01-18 22:12:53 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][180/312]	eta 0:01:20 lr 0.001739	time 0.5747 (0.6134)	model_time 0.5743 (0.6051)	loss 3.5455 (3.3223)	grad_norm 1.3593 (1.8849/0.8143)	mem 24308MB
[2025-01-18 22:12:59 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][190/312]	eta 0:01:14 lr 0.001739	time 0.6552 (0.6134)	model_time 0.6550 (0.6055)	loss 3.6863 (3.3272)	grad_norm 1.1178 (1.8715/0.8062)	mem 24308MB
[2025-01-18 22:13:05 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][200/312]	eta 0:01:08 lr 0.001738	time 0.5746 (0.6129)	model_time 0.5742 (0.6054)	loss 3.4251 (3.3222)	grad_norm 1.6453 (1.8505/0.7949)	mem 24308MB
[2025-01-18 22:13:11 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][210/312]	eta 0:01:02 lr 0.001737	time 0.5771 (0.6124)	model_time 0.5766 (0.6052)	loss 3.2408 (3.3235)	grad_norm 2.4545 (1.8653/0.8031)	mem 24308MB
[2025-01-18 22:13:17 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][220/312]	eta 0:00:56 lr 0.001737	time 0.5906 (0.6115)	model_time 0.5905 (0.6046)	loss 2.2264 (3.3115)	grad_norm 1.8273 (1.8547/0.7875)	mem 24308MB
[2025-01-18 22:13:23 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][230/312]	eta 0:00:50 lr 0.001736	time 0.6774 (0.6112)	model_time 0.6772 (0.6047)	loss 2.6371 (3.3109)	grad_norm 2.6363 (1.8427/0.7769)	mem 24308MB
[2025-01-18 22:13:30 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][240/312]	eta 0:00:43 lr 0.001735	time 0.6688 (0.6109)	model_time 0.6687 (0.6046)	loss 3.7993 (3.3187)	grad_norm 1.0759 (1.8244/0.7689)	mem 24308MB
[2025-01-18 22:13:35 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][250/312]	eta 0:00:37 lr 0.001735	time 0.6609 (0.6102)	model_time 0.6608 (0.6041)	loss 3.4551 (3.3161)	grad_norm 3.0210 (1.8189/0.7619)	mem 24308MB
[2025-01-18 22:13:42 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][260/312]	eta 0:00:31 lr 0.001734	time 0.6505 (0.6102)	model_time 0.6501 (0.6043)	loss 3.9306 (3.3183)	grad_norm 1.8828 (1.8206/0.7650)	mem 24308MB
[2025-01-18 22:13:48 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][270/312]	eta 0:00:25 lr 0.001734	time 0.6643 (0.6106)	model_time 0.6641 (0.6050)	loss 3.4965 (3.3150)	grad_norm 1.5246 (1.8366/0.7850)	mem 24308MB
[2025-01-18 22:13:54 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][280/312]	eta 0:00:19 lr 0.001733	time 0.5895 (0.6101)	model_time 0.5889 (0.6047)	loss 2.3501 (3.2964)	grad_norm 2.1592 (1.8387/0.7812)	mem 24308MB
[2025-01-18 22:14:00 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][290/312]	eta 0:00:13 lr 0.001732	time 0.5811 (0.6105)	model_time 0.5809 (0.6052)	loss 2.6104 (3.2929)	grad_norm 1.7844 (1.8209/0.7760)	mem 24308MB
[2025-01-18 22:14:06 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][300/312]	eta 0:00:07 lr 0.001732	time 0.5684 (0.6104)	model_time 0.5683 (0.6053)	loss 3.6949 (3.2975)	grad_norm 2.4330 (1.8155/0.7683)	mem 24308MB
[2025-01-18 22:14:12 internimage_s_1k_224] (main.py 510): INFO Train: [163/300][310/312]	eta 0:00:01 lr 0.001731	time 0.5669 (0.6101)	model_time 0.5668 (0.6051)	loss 3.3482 (3.3015)	grad_norm 1.8468 (1.8231/0.7784)	mem 24308MB
[2025-01-18 22:14:13 internimage_s_1k_224] (main.py 519): INFO EPOCH 163 training takes 0:03:10
[2025-01-18 22:14:13 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_163.pth saving......
[2025-01-18 22:14:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_163.pth saved !!!
[2025-01-18 22:14:22 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.497 (7.497)	Loss 0.8161 (0.8161)	Acc@1 83.594 (83.594)	Acc@5 96.802 (96.802)	Mem 24308MB
[2025-01-18 22:14:26 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.143 (1.004)	Loss 1.0984 (0.9583)	Acc@1 75.635 (80.178)	Acc@5 94.019 (95.366)	Mem 24308MB
[2025-01-18 22:14:26 internimage_s_1k_224] (main.py 575): INFO [Epoch:163] * Acc@1 80.072 Acc@5 95.361
[2025-01-18 22:14:26 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.1%
[2025-01-18 22:14:26 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 22:14:28 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 22:14:28 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.07%
[2025-01-18 22:14:35 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.351 (7.351)	Loss 0.7098 (0.7098)	Acc@1 83.911 (83.911)	Acc@5 97.412 (97.412)	Mem 24308MB
[2025-01-18 22:14:39 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.134 (1.019)	Loss 1.0052 (0.8324)	Acc@1 75.830 (80.702)	Acc@5 94.019 (95.590)	Mem 24308MB
[2025-01-18 22:14:39 internimage_s_1k_224] (main.py 575): INFO [Epoch:163] * Acc@1 80.594 Acc@5 95.615
[2025-01-18 22:14:39 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.6%
[2025-01-18 22:14:39 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 22:14:41 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 22:14:41 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.59%
[2025-01-18 22:14:43 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][0/312]	eta 0:10:03 lr 0.001731	time 1.9340 (1.9340)	model_time 0.6040 (0.6040)	loss 3.6566 (3.6566)	grad_norm 1.4811 (1.4811/0.0000)	mem 24308MB
[2025-01-18 22:14:49 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][10/312]	eta 0:03:43 lr 0.001730	time 0.6243 (0.7392)	model_time 0.6241 (0.6180)	loss 2.6327 (3.1031)	grad_norm 2.7058 (2.4728/1.0112)	mem 24308MB
[2025-01-18 22:14:55 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][20/312]	eta 0:03:17 lr 0.001729	time 0.5996 (0.6747)	model_time 0.5992 (0.6110)	loss 2.1152 (3.2054)	grad_norm 1.6589 (2.1481/0.9069)	mem 24308MB
[2025-01-18 22:15:01 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][30/312]	eta 0:03:03 lr 0.001729	time 0.5677 (0.6494)	model_time 0.5672 (0.6061)	loss 3.3937 (3.2451)	grad_norm 1.4653 (1.8831/0.8827)	mem 24308MB
[2025-01-18 22:15:07 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][40/312]	eta 0:02:52 lr 0.001728	time 0.5747 (0.6347)	model_time 0.5746 (0.6018)	loss 3.2796 (3.1775)	grad_norm 1.4700 (1.7712/0.8045)	mem 24308MB
[2025-01-18 22:15:13 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][50/312]	eta 0:02:44 lr 0.001727	time 0.5736 (0.6290)	model_time 0.5734 (0.6026)	loss 3.7709 (3.1374)	grad_norm 1.4061 (1.7144/0.7733)	mem 24308MB
[2025-01-18 22:15:19 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][60/312]	eta 0:02:36 lr 0.001727	time 0.5822 (0.6222)	model_time 0.5820 (0.6000)	loss 3.3042 (3.1193)	grad_norm 2.0655 (1.6623/0.7362)	mem 24308MB
[2025-01-18 22:15:25 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][70/312]	eta 0:02:30 lr 0.001726	time 0.5708 (0.6205)	model_time 0.5704 (0.6014)	loss 4.0555 (3.0958)	grad_norm 1.4413 (1.7565/0.8269)	mem 24308MB
[2025-01-18 22:15:31 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][80/312]	eta 0:02:23 lr 0.001725	time 0.6584 (0.6180)	model_time 0.6579 (0.6012)	loss 2.7605 (3.0772)	grad_norm 1.2993 (1.8275/0.9433)	mem 24308MB
[2025-01-18 22:15:37 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][90/312]	eta 0:02:16 lr 0.001725	time 0.6883 (0.6169)	model_time 0.6881 (0.6019)	loss 3.2627 (3.0893)	grad_norm 1.3623 (1.8277/0.9188)	mem 24308MB
[2025-01-18 22:15:44 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][100/312]	eta 0:02:11 lr 0.001724	time 0.5920 (0.6195)	model_time 0.5916 (0.6059)	loss 3.6012 (3.1221)	grad_norm 1.6067 (1.8494/0.9000)	mem 24308MB
[2025-01-18 22:15:50 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][110/312]	eta 0:02:04 lr 0.001724	time 0.6010 (0.6181)	model_time 0.6008 (0.6057)	loss 3.4245 (3.1295)	grad_norm 1.1946 (1.8394/0.8728)	mem 24308MB
[2025-01-18 22:15:56 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][120/312]	eta 0:01:58 lr 0.001723	time 0.5841 (0.6176)	model_time 0.5837 (0.6062)	loss 3.8047 (3.1373)	grad_norm 0.9415 (1.8402/0.8585)	mem 24308MB
[2025-01-18 22:16:02 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][130/312]	eta 0:01:52 lr 0.001722	time 0.6306 (0.6183)	model_time 0.6305 (0.6077)	loss 3.0527 (3.1675)	grad_norm 1.0606 (1.8279/0.8532)	mem 24308MB
[2025-01-18 22:16:08 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][140/312]	eta 0:01:46 lr 0.001722	time 0.6103 (0.6181)	model_time 0.6101 (0.6083)	loss 3.3719 (3.1569)	grad_norm 2.2648 (1.8249/0.8460)	mem 24308MB
[2025-01-18 22:16:14 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][150/312]	eta 0:01:39 lr 0.001721	time 0.5841 (0.6168)	model_time 0.5839 (0.6076)	loss 1.9971 (3.1463)	grad_norm 1.9715 (1.8095/0.8265)	mem 24308MB
[2025-01-18 22:16:20 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][160/312]	eta 0:01:33 lr 0.001720	time 0.5764 (0.6149)	model_time 0.5761 (0.6063)	loss 2.7823 (3.1523)	grad_norm 2.0371 (1.7859/0.8102)	mem 24308MB
[2025-01-18 22:16:26 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][170/312]	eta 0:01:27 lr 0.001720	time 0.5754 (0.6141)	model_time 0.5753 (0.6059)	loss 3.2556 (3.1602)	grad_norm 1.0395 (1.7605/0.8003)	mem 24308MB
[2025-01-18 22:16:32 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][180/312]	eta 0:01:20 lr 0.001719	time 0.5805 (0.6133)	model_time 0.5800 (0.6055)	loss 3.8301 (3.1760)	grad_norm 0.9401 (1.7442/0.7974)	mem 24308MB
[2025-01-18 22:16:38 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][190/312]	eta 0:01:14 lr 0.001718	time 0.5898 (0.6129)	model_time 0.5896 (0.6056)	loss 3.5874 (3.1894)	grad_norm 4.6462 (1.7815/0.8185)	mem 24308MB
[2025-01-18 22:16:45 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][200/312]	eta 0:01:08 lr 0.001718	time 0.6509 (0.6132)	model_time 0.6505 (0.6062)	loss 3.9227 (3.1955)	grad_norm 3.5454 (1.8299/0.8587)	mem 24308MB
[2025-01-18 22:16:50 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][210/312]	eta 0:01:02 lr 0.001717	time 0.5949 (0.6123)	model_time 0.5945 (0.6056)	loss 3.2691 (3.1882)	grad_norm 2.0837 (1.8422/0.8691)	mem 24308MB
[2025-01-18 22:16:57 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][220/312]	eta 0:00:56 lr 0.001716	time 0.6589 (0.6138)	model_time 0.6587 (0.6074)	loss 3.5962 (3.2038)	grad_norm 1.2440 (1.8433/0.8557)	mem 24308MB
[2025-01-18 22:17:03 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][230/312]	eta 0:00:50 lr 0.001716	time 0.5846 (0.6133)	model_time 0.5844 (0.6071)	loss 3.2625 (3.2041)	grad_norm 1.6063 (1.8341/0.8430)	mem 24308MB
[2025-01-18 22:17:09 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][240/312]	eta 0:00:44 lr 0.001715	time 0.5768 (0.6136)	model_time 0.5766 (0.6077)	loss 3.2059 (3.2029)	grad_norm 2.1708 (1.8209/0.8316)	mem 24308MB
[2025-01-18 22:17:15 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][250/312]	eta 0:00:38 lr 0.001714	time 0.5887 (0.6132)	model_time 0.5885 (0.6075)	loss 3.5625 (3.2165)	grad_norm 1.8523 (1.8443/0.8453)	mem 24308MB
[2025-01-18 22:17:21 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][260/312]	eta 0:00:31 lr 0.001714	time 0.5646 (0.6130)	model_time 0.5641 (0.6075)	loss 2.7642 (3.2232)	grad_norm 3.2966 (1.8727/0.8534)	mem 24308MB
[2025-01-18 22:17:27 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][270/312]	eta 0:00:25 lr 0.001713	time 0.5767 (0.6120)	model_time 0.5766 (0.6067)	loss 3.5605 (3.2231)	grad_norm 1.9469 (1.8705/0.8439)	mem 24308MB
[2025-01-18 22:17:33 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][280/312]	eta 0:00:19 lr 0.001712	time 0.5765 (0.6115)	model_time 0.5761 (0.6064)	loss 3.3302 (3.2277)	grad_norm 2.5987 (1.8711/0.8342)	mem 24308MB
[2025-01-18 22:17:39 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][290/312]	eta 0:00:13 lr 0.001712	time 0.5853 (0.6109)	model_time 0.5851 (0.6060)	loss 2.9925 (3.2274)	grad_norm 0.9370 (1.8880/0.8402)	mem 24308MB
[2025-01-18 22:17:45 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][300/312]	eta 0:00:07 lr 0.001711	time 0.5673 (0.6104)	model_time 0.5672 (0.6056)	loss 2.9321 (3.2342)	grad_norm 1.0537 (1.8938/0.8385)	mem 24308MB
[2025-01-18 22:17:51 internimage_s_1k_224] (main.py 510): INFO Train: [164/300][310/312]	eta 0:00:01 lr 0.001710	time 0.5669 (0.6095)	model_time 0.5668 (0.6049)	loss 2.5805 (3.2274)	grad_norm 2.0131 (1.8637/0.8132)	mem 24308MB
[2025-01-18 22:17:51 internimage_s_1k_224] (main.py 519): INFO EPOCH 164 training takes 0:03:10
[2025-01-18 22:17:51 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_164.pth saving......
[2025-01-18 22:17:53 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_164.pth saved !!!
[2025-01-18 22:18:01 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.590 (7.590)	Loss 0.7832 (0.7832)	Acc@1 83.032 (83.032)	Acc@5 96.680 (96.680)	Mem 24308MB
[2025-01-18 22:18:04 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.000)	Loss 1.0699 (0.9252)	Acc@1 76.245 (80.116)	Acc@5 93.774 (95.366)	Mem 24308MB
[2025-01-18 22:18:05 internimage_s_1k_224] (main.py 575): INFO [Epoch:164] * Acc@1 79.958 Acc@5 95.369
[2025-01-18 22:18:05 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.0%
[2025-01-18 22:18:05 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.07%
[2025-01-18 22:18:13 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.411 (8.411)	Loss 0.7094 (0.7094)	Acc@1 83.813 (83.813)	Acc@5 97.412 (97.412)	Mem 24308MB
[2025-01-18 22:18:17 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (1.163)	Loss 1.0030 (0.8314)	Acc@1 75.977 (80.746)	Acc@5 93.945 (95.581)	Mem 24308MB
[2025-01-18 22:18:18 internimage_s_1k_224] (main.py 575): INFO [Epoch:164] * Acc@1 80.642 Acc@5 95.609
[2025-01-18 22:18:18 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.6%
[2025-01-18 22:18:18 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 22:18:20 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 22:18:20 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.64%
[2025-01-18 22:18:22 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][0/312]	eta 0:10:25 lr 0.001710	time 2.0060 (2.0060)	model_time 0.5987 (0.5987)	loss 2.6931 (2.6931)	grad_norm 2.3947 (2.3947/0.0000)	mem 24308MB
[2025-01-18 22:18:28 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][10/312]	eta 0:03:45 lr 0.001710	time 0.5947 (0.7482)	model_time 0.5945 (0.6200)	loss 2.0974 (2.9450)	grad_norm 1.8650 (2.1628/0.5160)	mem 24308MB
[2025-01-18 22:18:34 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][20/312]	eta 0:03:17 lr 0.001709	time 0.5919 (0.6753)	model_time 0.5917 (0.6075)	loss 3.3479 (3.1797)	grad_norm 2.1176 (2.0060/0.5806)	mem 24308MB
[2025-01-18 22:18:40 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][30/312]	eta 0:03:06 lr 0.001708	time 0.6264 (0.6627)	model_time 0.6259 (0.6166)	loss 3.5584 (3.1884)	grad_norm 1.7577 (1.9216/0.5819)	mem 24308MB
[2025-01-18 22:18:46 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][40/312]	eta 0:02:55 lr 0.001708	time 0.5814 (0.6469)	model_time 0.5809 (0.6120)	loss 2.9021 (3.2222)	grad_norm 1.1923 (1.9214/0.6202)	mem 24308MB
[2025-01-18 22:18:52 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][50/312]	eta 0:02:48 lr 0.001707	time 0.5858 (0.6417)	model_time 0.5856 (0.6136)	loss 4.2235 (3.2881)	grad_norm 2.1214 (1.9122/0.6799)	mem 24308MB
[2025-01-18 22:18:58 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][60/312]	eta 0:02:40 lr 0.001706	time 0.5798 (0.6357)	model_time 0.5797 (0.6121)	loss 2.9979 (3.3133)	grad_norm 1.4657 (1.9367/0.6663)	mem 24308MB
[2025-01-18 22:19:05 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][70/312]	eta 0:02:32 lr 0.001706	time 0.5943 (0.6321)	model_time 0.5938 (0.6118)	loss 2.6956 (3.2637)	grad_norm 1.4637 (2.0040/0.7110)	mem 24308MB
[2025-01-18 22:19:11 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][80/312]	eta 0:02:25 lr 0.001705	time 0.5824 (0.6279)	model_time 0.5822 (0.6100)	loss 2.2409 (3.2832)	grad_norm 2.6397 (2.0210/0.7083)	mem 24308MB
[2025-01-18 22:19:17 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][90/312]	eta 0:02:18 lr 0.001704	time 0.6296 (0.6252)	model_time 0.6295 (0.6092)	loss 2.4143 (3.2484)	grad_norm 1.8879 (1.9709/0.7034)	mem 24308MB
[2025-01-18 22:19:23 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][100/312]	eta 0:02:11 lr 0.001704	time 0.5811 (0.6223)	model_time 0.5806 (0.6080)	loss 3.6734 (3.2555)	grad_norm 1.2052 (1.9377/0.6836)	mem 24308MB
[2025-01-18 22:19:29 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][110/312]	eta 0:02:05 lr 0.001703	time 0.5883 (0.6211)	model_time 0.5878 (0.6080)	loss 4.0231 (3.2572)	grad_norm 1.7544 (1.9509/0.7152)	mem 24308MB
[2025-01-18 22:19:35 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][120/312]	eta 0:01:58 lr 0.001702	time 0.5930 (0.6193)	model_time 0.5928 (0.6073)	loss 3.5827 (3.2673)	grad_norm 2.0325 (1.9817/0.7365)	mem 24308MB
[2025-01-18 22:19:41 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][130/312]	eta 0:01:52 lr 0.001702	time 0.5876 (0.6184)	model_time 0.5875 (0.6072)	loss 4.1467 (3.2881)	grad_norm 1.7602 (1.9890/0.7248)	mem 24308MB
[2025-01-18 22:19:47 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][140/312]	eta 0:01:46 lr 0.001701	time 0.5756 (0.6184)	model_time 0.5751 (0.6080)	loss 3.1480 (3.2971)	grad_norm 2.9011 (1.9987/0.7331)	mem 24308MB
[2025-01-18 22:19:54 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][150/312]	eta 0:01:40 lr 0.001700	time 0.6512 (0.6218)	model_time 0.6510 (0.6120)	loss 3.7193 (3.2769)	grad_norm 1.9100 (1.9884/0.7216)	mem 24308MB
[2025-01-18 22:20:00 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][160/312]	eta 0:01:34 lr 0.001700	time 0.6780 (0.6205)	model_time 0.6779 (0.6114)	loss 3.8451 (3.2981)	grad_norm 1.8710 (1.9745/0.7140)	mem 24308MB
[2025-01-18 22:20:06 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][170/312]	eta 0:01:28 lr 0.001699	time 0.6566 (0.6202)	model_time 0.6564 (0.6115)	loss 3.2548 (3.2899)	grad_norm 0.9955 (1.9623/0.7139)	mem 24308MB
[2025-01-18 22:20:12 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][180/312]	eta 0:01:21 lr 0.001698	time 0.5830 (0.6197)	model_time 0.5825 (0.6115)	loss 2.6063 (3.2779)	grad_norm 2.5477 (1.9478/0.7254)	mem 24308MB
[2025-01-18 22:20:18 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][190/312]	eta 0:01:15 lr 0.001698	time 0.5903 (0.6198)	model_time 0.5899 (0.6119)	loss 2.5591 (3.2846)	grad_norm 1.6636 (1.9637/0.7255)	mem 24308MB
[2025-01-18 22:20:24 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][200/312]	eta 0:01:09 lr 0.001697	time 0.5896 (0.6186)	model_time 0.5892 (0.6111)	loss 3.5578 (3.2834)	grad_norm 2.9054 (1.9758/0.7232)	mem 24308MB
[2025-01-18 22:20:30 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][210/312]	eta 0:01:02 lr 0.001696	time 0.5838 (0.6176)	model_time 0.5833 (0.6104)	loss 2.8722 (3.2784)	grad_norm 1.5903 (1.9637/0.7134)	mem 24308MB
[2025-01-18 22:20:36 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][220/312]	eta 0:00:56 lr 0.001696	time 0.5833 (0.6166)	model_time 0.5832 (0.6098)	loss 3.2921 (3.2660)	grad_norm 1.0895 (1.9486/0.7106)	mem 24308MB
[2025-01-18 22:20:42 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][230/312]	eta 0:00:50 lr 0.001695	time 0.5966 (0.6165)	model_time 0.5961 (0.6100)	loss 3.4988 (3.2692)	grad_norm 1.3650 (1.9206/0.7122)	mem 24308MB
[2025-01-18 22:20:48 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][240/312]	eta 0:00:44 lr 0.001695	time 0.6335 (0.6159)	model_time 0.6331 (0.6096)	loss 2.5129 (3.2649)	grad_norm 1.2548 (1.9163/0.7272)	mem 24308MB
[2025-01-18 22:20:54 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][250/312]	eta 0:00:38 lr 0.001694	time 0.5854 (0.6152)	model_time 0.5852 (0.6092)	loss 2.9300 (3.2544)	grad_norm 1.4655 (1.9199/0.7206)	mem 24308MB
[2025-01-18 22:21:00 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][260/312]	eta 0:00:31 lr 0.001693	time 0.5769 (0.6147)	model_time 0.5765 (0.6089)	loss 3.4698 (3.2600)	grad_norm 1.4091 (1.9330/0.7271)	mem 24308MB
[2025-01-18 22:21:07 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][270/312]	eta 0:00:25 lr 0.001693	time 0.6537 (0.6159)	model_time 0.6532 (0.6102)	loss 3.6753 (3.2620)	grad_norm 1.0761 (1.9328/0.7247)	mem 24308MB
[2025-01-18 22:21:13 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][280/312]	eta 0:00:19 lr 0.001692	time 0.6911 (0.6157)	model_time 0.6910 (0.6103)	loss 2.7830 (3.2620)	grad_norm 2.2774 (1.9210/0.7191)	mem 24308MB
[2025-01-18 22:21:19 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][290/312]	eta 0:00:13 lr 0.001691	time 0.6581 (0.6157)	model_time 0.6580 (0.6105)	loss 2.8189 (3.2505)	grad_norm 1.5997 (1.9129/0.7174)	mem 24308MB
[2025-01-18 22:21:25 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][300/312]	eta 0:00:07 lr 0.001691	time 0.6361 (0.6152)	model_time 0.6361 (0.6101)	loss 2.9160 (3.2500)	grad_norm 1.1965 (1.9165/0.7165)	mem 24308MB
[2025-01-18 22:21:31 internimage_s_1k_224] (main.py 510): INFO Train: [165/300][310/312]	eta 0:00:01 lr 0.001690	time 0.5647 (0.6144)	model_time 0.5646 (0.6095)	loss 3.6646 (3.2518)	grad_norm 3.0766 (1.9115/0.7271)	mem 24308MB
[2025-01-18 22:21:31 internimage_s_1k_224] (main.py 519): INFO EPOCH 165 training takes 0:03:11
[2025-01-18 22:21:31 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_165.pth saving......
[2025-01-18 22:21:33 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_165.pth saved !!!
[2025-01-18 22:21:41 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.240 (7.240)	Loss 0.7931 (0.7931)	Acc@1 83.496 (83.496)	Acc@5 96.655 (96.655)	Mem 24308MB
[2025-01-18 22:21:44 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.977)	Loss 1.0687 (0.9214)	Acc@1 76.270 (80.131)	Acc@5 93.823 (95.406)	Mem 24308MB
[2025-01-18 22:21:44 internimage_s_1k_224] (main.py 575): INFO [Epoch:165] * Acc@1 80.028 Acc@5 95.423
[2025-01-18 22:21:44 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.0%
[2025-01-18 22:21:44 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.07%
[2025-01-18 22:21:53 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.712 (8.712)	Loss 0.7091 (0.7091)	Acc@1 83.887 (83.887)	Acc@5 97.412 (97.412)	Mem 24308MB
[2025-01-18 22:21:57 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.173)	Loss 1.0011 (0.8305)	Acc@1 76.025 (80.784)	Acc@5 94.067 (95.621)	Mem 24308MB
[2025-01-18 22:21:57 internimage_s_1k_224] (main.py 575): INFO [Epoch:165] * Acc@1 80.684 Acc@5 95.645
[2025-01-18 22:21:57 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.7%
[2025-01-18 22:21:57 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 22:21:59 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 22:21:59 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.68%
[2025-01-18 22:22:02 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][0/312]	eta 0:11:16 lr 0.001690	time 2.1694 (2.1694)	model_time 0.5796 (0.5796)	loss 3.0698 (3.0698)	grad_norm 3.4061 (3.4061/0.0000)	mem 24308MB
[2025-01-18 22:22:08 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][10/312]	eta 0:03:44 lr 0.001689	time 0.5805 (0.7421)	model_time 0.5803 (0.5973)	loss 3.5414 (3.2020)	grad_norm 1.0165 (1.8027/0.9111)	mem 24308MB
[2025-01-18 22:22:14 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][20/312]	eta 0:03:16 lr 0.001688	time 0.5986 (0.6746)	model_time 0.5984 (0.5986)	loss 3.3659 (3.2568)	grad_norm 0.9603 (1.5728/0.7811)	mem 24308MB
[2025-01-18 22:22:20 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][30/312]	eta 0:03:03 lr 0.001688	time 0.5812 (0.6510)	model_time 0.5808 (0.5994)	loss 4.3727 (3.2799)	grad_norm 1.4734 (1.6160/0.7116)	mem 24308MB
[2025-01-18 22:22:26 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][40/312]	eta 0:02:54 lr 0.001687	time 0.5650 (0.6410)	model_time 0.5646 (0.6019)	loss 3.2926 (3.2391)	grad_norm 1.2488 (1.7409/0.9203)	mem 24308MB
[2025-01-18 22:22:32 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][50/312]	eta 0:02:46 lr 0.001687	time 0.6446 (0.6350)	model_time 0.6444 (0.6035)	loss 3.4252 (3.2364)	grad_norm 2.5849 (1.7357/0.8888)	mem 24308MB
[2025-01-18 22:22:38 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][60/312]	eta 0:02:38 lr 0.001686	time 0.5826 (0.6294)	model_time 0.5824 (0.6030)	loss 2.8833 (3.2108)	grad_norm 1.0163 (1.8030/0.8637)	mem 24308MB
[2025-01-18 22:22:44 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][70/312]	eta 0:02:31 lr 0.001685	time 0.6055 (0.6267)	model_time 0.6051 (0.6040)	loss 2.9711 (3.2097)	grad_norm 1.2469 (1.7849/0.8209)	mem 24308MB
[2025-01-18 22:22:50 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][80/312]	eta 0:02:25 lr 0.001685	time 0.6715 (0.6256)	model_time 0.6711 (0.6057)	loss 3.2040 (3.2147)	grad_norm 1.8099 (1.7583/0.7924)	mem 24308MB
[2025-01-18 22:22:56 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][90/312]	eta 0:02:18 lr 0.001684	time 0.5829 (0.6230)	model_time 0.5825 (0.6052)	loss 2.5692 (3.1979)	grad_norm 1.2619 (1.7518/0.7675)	mem 24308MB
[2025-01-18 22:23:02 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][100/312]	eta 0:02:11 lr 0.001683	time 0.6711 (0.6224)	model_time 0.6707 (0.6063)	loss 4.1619 (3.2483)	grad_norm 1.0038 (1.7902/0.7826)	mem 24308MB
[2025-01-18 22:23:08 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][110/312]	eta 0:02:05 lr 0.001683	time 0.5679 (0.6208)	model_time 0.5674 (0.6061)	loss 2.8808 (3.2452)	grad_norm 1.8997 (1.8177/0.7710)	mem 24308MB
[2025-01-18 22:23:14 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][120/312]	eta 0:01:58 lr 0.001682	time 0.6524 (0.6194)	model_time 0.6522 (0.6058)	loss 4.0017 (3.2605)	grad_norm 1.7119 (1.8234/0.7442)	mem 24308MB
[2025-01-18 22:23:20 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][130/312]	eta 0:01:52 lr 0.001681	time 0.5846 (0.6168)	model_time 0.5842 (0.6043)	loss 2.6882 (3.2503)	grad_norm 1.5802 (1.8231/0.7284)	mem 24308MB
[2025-01-18 22:23:26 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][140/312]	eta 0:01:45 lr 0.001681	time 0.5823 (0.6155)	model_time 0.5822 (0.6039)	loss 3.5072 (3.2693)	grad_norm 1.1416 (1.8481/0.7595)	mem 24308MB
[2025-01-18 22:23:32 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][150/312]	eta 0:01:39 lr 0.001680	time 0.5780 (0.6149)	model_time 0.5778 (0.6041)	loss 3.1133 (3.2687)	grad_norm 1.5124 (1.8387/0.7468)	mem 24308MB
[2025-01-18 22:23:38 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][160/312]	eta 0:01:33 lr 0.001679	time 0.5934 (0.6139)	model_time 0.5933 (0.6037)	loss 3.1783 (3.2631)	grad_norm 3.6457 (1.8589/0.7786)	mem 24308MB
[2025-01-18 22:23:44 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][170/312]	eta 0:01:27 lr 0.001679	time 0.5666 (0.6135)	model_time 0.5665 (0.6038)	loss 3.3797 (3.2739)	grad_norm 1.6674 (1.8361/0.7670)	mem 24308MB
[2025-01-18 22:23:50 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][180/312]	eta 0:01:20 lr 0.001678	time 0.5719 (0.6134)	model_time 0.5715 (0.6042)	loss 3.5115 (3.2739)	grad_norm 0.7526 (1.8350/0.7656)	mem 24308MB
[2025-01-18 22:23:57 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][190/312]	eta 0:01:14 lr 0.001677	time 0.5908 (0.6131)	model_time 0.5907 (0.6044)	loss 3.0960 (3.2725)	grad_norm 1.7823 (1.8340/0.7495)	mem 24308MB
[2025-01-18 22:24:03 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][200/312]	eta 0:01:08 lr 0.001677	time 0.7844 (0.6143)	model_time 0.7842 (0.6060)	loss 3.2724 (3.2695)	grad_norm 5.0674 (1.9225/0.9029)	mem 24308MB
[2025-01-18 22:24:09 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][210/312]	eta 0:01:02 lr 0.001676	time 0.5775 (0.6145)	model_time 0.5774 (0.6066)	loss 3.9448 (3.2727)	grad_norm 1.2733 (1.9256/0.8969)	mem 24308MB
[2025-01-18 22:24:15 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][220/312]	eta 0:00:56 lr 0.001675	time 0.5901 (0.6138)	model_time 0.5899 (0.6062)	loss 2.8241 (3.2700)	grad_norm 1.7845 (1.9064/0.8856)	mem 24308MB
[2025-01-18 22:24:21 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][230/312]	eta 0:00:50 lr 0.001675	time 0.6789 (0.6141)	model_time 0.6785 (0.6068)	loss 3.3547 (3.2685)	grad_norm 0.8733 (1.9018/0.8747)	mem 24308MB
[2025-01-18 22:24:27 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][240/312]	eta 0:00:44 lr 0.001674	time 0.6613 (0.6140)	model_time 0.6611 (0.6070)	loss 3.1627 (3.2614)	grad_norm 1.2746 (1.8831/0.8648)	mem 24308MB
[2025-01-18 22:24:33 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][250/312]	eta 0:00:37 lr 0.001673	time 0.5791 (0.6128)	model_time 0.5790 (0.6061)	loss 4.0663 (3.2722)	grad_norm 3.4593 (1.8746/0.8607)	mem 24308MB
[2025-01-18 22:24:39 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][260/312]	eta 0:00:31 lr 0.001673	time 0.5812 (0.6125)	model_time 0.5808 (0.6060)	loss 3.5027 (3.2575)	grad_norm 1.2671 (1.8857/0.8679)	mem 24308MB
[2025-01-18 22:24:45 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][270/312]	eta 0:00:25 lr 0.001672	time 0.6043 (0.6119)	model_time 0.6041 (0.6056)	loss 4.0058 (3.2618)	grad_norm 1.5202 (1.8833/0.8542)	mem 24308MB
[2025-01-18 22:24:51 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][280/312]	eta 0:00:19 lr 0.001671	time 0.5923 (0.6117)	model_time 0.5918 (0.6057)	loss 4.0347 (3.2530)	grad_norm 1.4736 (1.8826/0.8445)	mem 24308MB
[2025-01-18 22:24:57 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][290/312]	eta 0:00:13 lr 0.001671	time 0.5828 (0.6118)	model_time 0.5824 (0.6059)	loss 3.3427 (3.2579)	grad_norm 1.5903 (1.8729/0.8359)	mem 24308MB
[2025-01-18 22:25:03 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][300/312]	eta 0:00:07 lr 0.001670	time 0.5677 (0.6114)	model_time 0.5676 (0.6057)	loss 3.8722 (3.2577)	grad_norm 2.4259 (1.8618/0.8249)	mem 24308MB
[2025-01-18 22:25:09 internimage_s_1k_224] (main.py 510): INFO Train: [166/300][310/312]	eta 0:00:01 lr 0.001670	time 0.5660 (0.6105)	model_time 0.5659 (0.6050)	loss 3.2206 (3.2568)	grad_norm 1.7494 (1.8879/0.8572)	mem 24308MB
[2025-01-18 22:25:10 internimage_s_1k_224] (main.py 519): INFO EPOCH 166 training takes 0:03:10
[2025-01-18 22:25:10 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_166.pth saving......
[2025-01-18 22:25:12 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_166.pth saved !!!
[2025-01-18 22:25:19 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.676 (7.676)	Loss 0.8070 (0.8070)	Acc@1 82.983 (82.983)	Acc@5 97.046 (97.046)	Mem 24308MB
[2025-01-18 22:25:23 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.035)	Loss 1.1436 (0.9508)	Acc@1 75.000 (79.952)	Acc@5 93.433 (95.284)	Mem 24308MB
[2025-01-18 22:25:23 internimage_s_1k_224] (main.py 575): INFO [Epoch:166] * Acc@1 79.846 Acc@5 95.302
[2025-01-18 22:25:23 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 79.8%
[2025-01-18 22:25:23 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.07%
[2025-01-18 22:25:32 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.860 (8.860)	Loss 0.7089 (0.7089)	Acc@1 83.960 (83.960)	Acc@5 97.388 (97.388)	Mem 24308MB
[2025-01-18 22:25:36 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.138 (1.201)	Loss 0.9991 (0.8295)	Acc@1 76.074 (80.831)	Acc@5 94.043 (95.621)	Mem 24308MB
[2025-01-18 22:25:37 internimage_s_1k_224] (main.py 575): INFO [Epoch:166] * Acc@1 80.732 Acc@5 95.643
[2025-01-18 22:25:37 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.7%
[2025-01-18 22:25:37 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 22:25:39 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 22:25:39 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.73%
[2025-01-18 22:25:41 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][0/312]	eta 0:11:22 lr 0.001669	time 2.1864 (2.1864)	model_time 0.5991 (0.5991)	loss 3.2468 (3.2468)	grad_norm 2.4528 (2.4528/0.0000)	mem 24308MB
[2025-01-18 22:25:47 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][10/312]	eta 0:03:52 lr 0.001669	time 0.5816 (0.7706)	model_time 0.5814 (0.6259)	loss 2.8499 (3.3567)	grad_norm 1.8471 (2.0912/0.7346)	mem 24308MB
[2025-01-18 22:25:54 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][20/312]	eta 0:03:22 lr 0.001668	time 0.6002 (0.6935)	model_time 0.5997 (0.6176)	loss 4.2756 (3.4473)	grad_norm 2.1480 (1.9354/0.7625)	mem 24308MB
[2025-01-18 22:26:00 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][30/312]	eta 0:03:07 lr 0.001667	time 0.6031 (0.6653)	model_time 0.6027 (0.6137)	loss 3.5288 (3.4896)	grad_norm 2.4600 (1.9482/0.7275)	mem 24308MB
[2025-01-18 22:26:06 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][40/312]	eta 0:02:57 lr 0.001667	time 0.5883 (0.6537)	model_time 0.5881 (0.6146)	loss 2.7547 (3.4528)	grad_norm 2.0411 (1.9261/0.7536)	mem 24308MB
[2025-01-18 22:26:12 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][50/312]	eta 0:02:49 lr 0.001666	time 0.6600 (0.6469)	model_time 0.6598 (0.6154)	loss 3.5250 (3.4407)	grad_norm 1.4791 (1.8482/0.7301)	mem 24308MB
[2025-01-18 22:26:18 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][60/312]	eta 0:02:40 lr 0.001665	time 0.5854 (0.6380)	model_time 0.5849 (0.6116)	loss 3.4535 (3.4230)	grad_norm 1.1920 (1.8526/0.7720)	mem 24308MB
[2025-01-18 22:26:24 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][70/312]	eta 0:02:33 lr 0.001665	time 0.6095 (0.6326)	model_time 0.6093 (0.6099)	loss 3.8230 (3.4114)	grad_norm 5.1977 (1.9250/0.8996)	mem 24308MB
[2025-01-18 22:26:30 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][80/312]	eta 0:02:25 lr 0.001664	time 0.5794 (0.6279)	model_time 0.5789 (0.6079)	loss 2.3390 (3.3725)	grad_norm 1.1439 (1.8988/0.8777)	mem 24308MB
[2025-01-18 22:26:36 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][90/312]	eta 0:02:18 lr 0.001663	time 0.5741 (0.6247)	model_time 0.5739 (0.6069)	loss 2.2176 (3.3493)	grad_norm 1.3547 (1.8534/0.8604)	mem 24308MB
[2025-01-18 22:26:42 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][100/312]	eta 0:02:11 lr 0.001663	time 0.5857 (0.6226)	model_time 0.5852 (0.6065)	loss 3.8525 (3.3383)	grad_norm 1.4735 (1.8374/0.8349)	mem 24308MB
[2025-01-18 22:26:48 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][110/312]	eta 0:02:05 lr 0.001662	time 0.6228 (0.6209)	model_time 0.6224 (0.6062)	loss 3.7758 (3.3346)	grad_norm 1.7341 (1.8294/0.8156)	mem 24308MB
[2025-01-18 22:26:54 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][120/312]	eta 0:01:58 lr 0.001662	time 0.6822 (0.6193)	model_time 0.6820 (0.6057)	loss 3.1152 (3.3398)	grad_norm 2.1194 (1.8142/0.7900)	mem 24308MB
[2025-01-18 22:27:00 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][130/312]	eta 0:01:52 lr 0.001661	time 0.5936 (0.6188)	model_time 0.5934 (0.6063)	loss 3.3597 (3.3455)	grad_norm 4.2695 (1.8273/0.7996)	mem 24308MB
[2025-01-18 22:27:06 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][140/312]	eta 0:01:46 lr 0.001660	time 0.5701 (0.6194)	model_time 0.5699 (0.6078)	loss 3.8600 (3.3437)	grad_norm 1.8562 (1.8437/0.8041)	mem 24308MB
[2025-01-18 22:27:12 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][150/312]	eta 0:01:40 lr 0.001660	time 0.5907 (0.6184)	model_time 0.5905 (0.6076)	loss 2.4529 (3.3499)	grad_norm 2.4524 (1.8815/0.8253)	mem 24308MB
[2025-01-18 22:27:18 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][160/312]	eta 0:01:33 lr 0.001659	time 0.5930 (0.6182)	model_time 0.5928 (0.6079)	loss 2.9682 (3.3345)	grad_norm 1.1773 (1.8882/0.8501)	mem 24308MB
[2025-01-18 22:27:25 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][170/312]	eta 0:01:27 lr 0.001658	time 0.5980 (0.6177)	model_time 0.5978 (0.6080)	loss 2.8321 (3.3270)	grad_norm 1.7500 (1.8708/0.8350)	mem 24308MB
[2025-01-18 22:27:31 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][180/312]	eta 0:01:21 lr 0.001658	time 0.6013 (0.6167)	model_time 0.6009 (0.6075)	loss 3.3772 (3.3294)	grad_norm 2.1480 (1.8990/0.8458)	mem 24308MB
[2025-01-18 22:27:36 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][190/312]	eta 0:01:15 lr 0.001657	time 0.5930 (0.6152)	model_time 0.5928 (0.6065)	loss 3.2960 (3.3212)	grad_norm 1.8593 (1.8960/0.8354)	mem 24308MB
[2025-01-18 22:27:43 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][200/312]	eta 0:01:08 lr 0.001656	time 0.5691 (0.6150)	model_time 0.5689 (0.6067)	loss 3.4401 (3.3213)	grad_norm 2.4795 (1.8885/0.8203)	mem 24308MB
[2025-01-18 22:27:49 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][210/312]	eta 0:01:02 lr 0.001656	time 0.6200 (0.6144)	model_time 0.6199 (0.6065)	loss 2.3732 (3.3210)	grad_norm 1.5665 (1.8987/0.8328)	mem 24308MB
[2025-01-18 22:27:55 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][220/312]	eta 0:00:56 lr 0.001655	time 0.5998 (0.6140)	model_time 0.5994 (0.6065)	loss 3.3794 (3.3191)	grad_norm 1.6388 (1.8813/0.8221)	mem 24308MB
[2025-01-18 22:28:01 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][230/312]	eta 0:00:50 lr 0.001654	time 0.6032 (0.6139)	model_time 0.6030 (0.6066)	loss 3.5169 (3.3228)	grad_norm 2.3420 (1.8696/0.8153)	mem 24308MB
[2025-01-18 22:28:07 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][240/312]	eta 0:00:44 lr 0.001654	time 0.6636 (0.6134)	model_time 0.6631 (0.6064)	loss 3.9789 (3.3048)	grad_norm 2.0781 (1.8616/0.8060)	mem 24308MB
[2025-01-18 22:28:13 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][250/312]	eta 0:00:38 lr 0.001653	time 0.5905 (0.6134)	model_time 0.5901 (0.6067)	loss 3.5848 (3.2905)	grad_norm 2.0757 (1.8488/0.7974)	mem 24308MB
[2025-01-18 22:28:19 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][260/312]	eta 0:00:31 lr 0.001652	time 0.5808 (0.6141)	model_time 0.5807 (0.6076)	loss 3.2934 (3.2910)	grad_norm 2.9406 (1.8839/0.8335)	mem 24308MB
[2025-01-18 22:28:25 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][270/312]	eta 0:00:25 lr 0.001652	time 0.5752 (0.6138)	model_time 0.5750 (0.6075)	loss 2.8499 (3.2922)	grad_norm 1.4968 (1.8791/0.8259)	mem 24308MB
[2025-01-18 22:28:32 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][280/312]	eta 0:00:19 lr 0.001651	time 0.6709 (0.6142)	model_time 0.6704 (0.6082)	loss 3.5416 (3.3010)	grad_norm 1.7163 (1.8727/0.8210)	mem 24308MB
[2025-01-18 22:28:38 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][290/312]	eta 0:00:13 lr 0.001650	time 0.5840 (0.6138)	model_time 0.5837 (0.6079)	loss 3.8149 (3.3038)	grad_norm 3.7013 (1.8979/0.8281)	mem 24308MB
[2025-01-18 22:28:43 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][300/312]	eta 0:00:07 lr 0.001650	time 0.5731 (0.6129)	model_time 0.5730 (0.6072)	loss 3.5076 (3.2995)	grad_norm 3.7841 (1.9245/0.8403)	mem 24308MB
[2025-01-18 22:28:49 internimage_s_1k_224] (main.py 510): INFO Train: [167/300][310/312]	eta 0:00:01 lr 0.001649	time 0.5664 (0.6115)	model_time 0.5663 (0.6060)	loss 3.8699 (3.3037)	grad_norm 1.0863 (1.9020/0.8367)	mem 24308MB
[2025-01-18 22:28:50 internimage_s_1k_224] (main.py 519): INFO EPOCH 167 training takes 0:03:10
[2025-01-18 22:28:50 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_167.pth saving......
[2025-01-18 22:28:52 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_167.pth saved !!!
[2025-01-18 22:28:59 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.506 (7.506)	Loss 0.8210 (0.8210)	Acc@1 83.276 (83.276)	Acc@5 96.851 (96.851)	Mem 24308MB
[2025-01-18 22:29:03 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (1.003)	Loss 1.0709 (0.9296)	Acc@1 76.196 (80.227)	Acc@5 93.896 (95.430)	Mem 24308MB
[2025-01-18 22:29:03 internimage_s_1k_224] (main.py 575): INFO [Epoch:167] * Acc@1 80.122 Acc@5 95.429
[2025-01-18 22:29:03 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.1%
[2025-01-18 22:29:03 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 22:29:05 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 22:29:05 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.12%
[2025-01-18 22:29:13 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.602 (7.602)	Loss 0.7085 (0.7085)	Acc@1 83.984 (83.984)	Acc@5 97.339 (97.339)	Mem 24308MB
[2025-01-18 22:29:16 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.006)	Loss 0.9973 (0.8287)	Acc@1 76.099 (80.833)	Acc@5 94.067 (95.637)	Mem 24308MB
[2025-01-18 22:29:16 internimage_s_1k_224] (main.py 575): INFO [Epoch:167] * Acc@1 80.732 Acc@5 95.669
[2025-01-18 22:29:16 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.7%
[2025-01-18 22:29:16 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.73%
[2025-01-18 22:29:19 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][0/312]	eta 0:15:14 lr 0.001649	time 2.9301 (2.9301)	model_time 1.4288 (1.4288)	loss 3.1185 (3.1185)	grad_norm 2.3320 (2.3320/0.0000)	mem 24308MB
[2025-01-18 22:29:25 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][10/312]	eta 0:04:10 lr 0.001648	time 0.5994 (0.8289)	model_time 0.5989 (0.6921)	loss 2.6077 (3.2365)	grad_norm 1.3316 (1.6221/0.5266)	mem 24308MB
[2025-01-18 22:29:31 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][20/312]	eta 0:03:29 lr 0.001648	time 0.5943 (0.7176)	model_time 0.5938 (0.6457)	loss 3.3180 (3.2001)	grad_norm 1.3165 (1.5619/0.5188)	mem 24308MB
[2025-01-18 22:29:37 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][30/312]	eta 0:03:12 lr 0.001647	time 0.5885 (0.6823)	model_time 0.5881 (0.6335)	loss 3.4977 (3.2133)	grad_norm 1.6239 (1.6166/0.5076)	mem 24308MB
[2025-01-18 22:29:43 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][40/312]	eta 0:03:00 lr 0.001646	time 0.6707 (0.6640)	model_time 0.6705 (0.6271)	loss 3.6538 (3.2134)	grad_norm 1.8279 (1.7517/0.5701)	mem 24308MB
[2025-01-18 22:29:49 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][50/312]	eta 0:02:51 lr 0.001646	time 0.6834 (0.6537)	model_time 0.6832 (0.6239)	loss 3.5277 (3.2501)	grad_norm 2.4001 (1.7473/0.5763)	mem 24308MB
[2025-01-18 22:29:56 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][60/312]	eta 0:02:43 lr 0.001645	time 0.6583 (0.6485)	model_time 0.6579 (0.6235)	loss 3.8765 (3.2547)	grad_norm 1.2034 (1.6901/0.5703)	mem 24308MB
[2025-01-18 22:30:02 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][70/312]	eta 0:02:35 lr 0.001644	time 0.5912 (0.6431)	model_time 0.5910 (0.6215)	loss 2.9743 (3.2148)	grad_norm 1.2119 (1.7191/0.5941)	mem 24308MB
[2025-01-18 22:30:08 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][80/312]	eta 0:02:27 lr 0.001644	time 0.5803 (0.6378)	model_time 0.5801 (0.6189)	loss 3.9691 (3.2156)	grad_norm 2.1821 (1.7080/0.5979)	mem 24308MB
[2025-01-18 22:30:14 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][90/312]	eta 0:02:21 lr 0.001643	time 0.6602 (0.6360)	model_time 0.6601 (0.6191)	loss 2.6363 (3.2046)	grad_norm 1.1533 (1.6939/0.5836)	mem 24308MB
[2025-01-18 22:30:20 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][100/312]	eta 0:02:14 lr 0.001642	time 0.5881 (0.6338)	model_time 0.5879 (0.6186)	loss 2.2029 (3.2124)	grad_norm 1.7694 (1.6866/0.5676)	mem 24308MB
[2025-01-18 22:30:26 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][110/312]	eta 0:02:07 lr 0.001642	time 0.5766 (0.6300)	model_time 0.5764 (0.6162)	loss 3.5598 (3.2123)	grad_norm 3.8334 (1.7764/0.6954)	mem 24308MB
[2025-01-18 22:30:32 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][120/312]	eta 0:02:00 lr 0.001641	time 0.5904 (0.6281)	model_time 0.5903 (0.6154)	loss 2.6797 (3.2178)	grad_norm 2.2931 (1.7861/0.6927)	mem 24308MB
[2025-01-18 22:30:38 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][130/312]	eta 0:01:54 lr 0.001641	time 0.5874 (0.6265)	model_time 0.5869 (0.6147)	loss 3.3008 (3.2392)	grad_norm 1.8644 (1.8207/0.7050)	mem 24308MB
[2025-01-18 22:30:44 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][140/312]	eta 0:01:47 lr 0.001640	time 0.5798 (0.6243)	model_time 0.5793 (0.6133)	loss 3.2782 (3.2540)	grad_norm 2.7177 (1.8041/0.6928)	mem 24308MB
[2025-01-18 22:30:50 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][150/312]	eta 0:01:40 lr 0.001639	time 0.5830 (0.6231)	model_time 0.5825 (0.6128)	loss 3.3582 (3.2606)	grad_norm 2.1487 (1.7707/0.6879)	mem 24308MB
[2025-01-18 22:30:56 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][160/312]	eta 0:01:34 lr 0.001639	time 0.6561 (0.6224)	model_time 0.6558 (0.6127)	loss 3.5886 (3.2775)	grad_norm 0.9248 (1.7828/0.7064)	mem 24308MB
[2025-01-18 22:31:02 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][170/312]	eta 0:01:28 lr 0.001638	time 0.5724 (0.6208)	model_time 0.5722 (0.6117)	loss 2.9265 (3.2906)	grad_norm 1.8253 (1.7896/0.6961)	mem 24308MB
[2025-01-18 22:31:09 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][180/312]	eta 0:01:22 lr 0.001637	time 0.5750 (0.6215)	model_time 0.5748 (0.6129)	loss 2.8183 (3.2794)	grad_norm 1.5185 (1.7725/0.6854)	mem 24308MB
[2025-01-18 22:31:15 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][190/312]	eta 0:01:15 lr 0.001637	time 0.5745 (0.6212)	model_time 0.5743 (0.6130)	loss 3.6472 (3.2750)	grad_norm 1.1805 (1.7792/0.6851)	mem 24308MB
[2025-01-18 22:31:21 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][200/312]	eta 0:01:09 lr 0.001636	time 0.6863 (0.6202)	model_time 0.6861 (0.6124)	loss 3.2624 (3.2835)	grad_norm 2.8894 (1.7974/0.7040)	mem 24308MB
[2025-01-18 22:31:27 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][210/312]	eta 0:01:03 lr 0.001635	time 0.5799 (0.6195)	model_time 0.5797 (0.6121)	loss 2.8446 (3.2713)	grad_norm 0.8425 (1.8184/0.7179)	mem 24308MB
[2025-01-18 22:31:33 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][220/312]	eta 0:00:56 lr 0.001635	time 0.5949 (0.6192)	model_time 0.5947 (0.6121)	loss 3.1259 (3.2702)	grad_norm 0.7907 (1.8099/0.7127)	mem 24308MB
[2025-01-18 22:31:39 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][230/312]	eta 0:00:50 lr 0.001634	time 0.5835 (0.6188)	model_time 0.5833 (0.6119)	loss 3.0090 (3.2662)	grad_norm 1.3396 (1.8474/0.7650)	mem 24308MB
[2025-01-18 22:31:45 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][240/312]	eta 0:00:44 lr 0.001633	time 0.5839 (0.6179)	model_time 0.5834 (0.6113)	loss 2.8242 (3.2578)	grad_norm 1.1042 (1.8486/0.7623)	mem 24308MB
[2025-01-18 22:31:51 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][250/312]	eta 0:00:38 lr 0.001633	time 0.6769 (0.6174)	model_time 0.6767 (0.6111)	loss 2.1249 (3.2445)	grad_norm 1.8685 (1.8589/0.7579)	mem 24308MB
[2025-01-18 22:31:57 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][260/312]	eta 0:00:32 lr 0.001632	time 0.5869 (0.6167)	model_time 0.5865 (0.6106)	loss 2.9864 (3.2328)	grad_norm 1.7547 (1.8649/0.7579)	mem 24308MB
[2025-01-18 22:32:03 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][270/312]	eta 0:00:25 lr 0.001631	time 0.5835 (0.6165)	model_time 0.5834 (0.6106)	loss 2.7635 (3.2341)	grad_norm 2.2281 (1.8591/0.7520)	mem 24308MB
[2025-01-18 22:32:09 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][280/312]	eta 0:00:19 lr 0.001631	time 0.5759 (0.6159)	model_time 0.5757 (0.6102)	loss 3.7125 (3.2442)	grad_norm 2.9802 (1.8747/0.7647)	mem 24308MB
[2025-01-18 22:32:15 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][290/312]	eta 0:00:13 lr 0.001630	time 0.5926 (0.6154)	model_time 0.5924 (0.6099)	loss 3.0244 (3.2425)	grad_norm 3.0126 (1.8688/0.7648)	mem 24308MB
[2025-01-18 22:32:21 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][300/312]	eta 0:00:07 lr 0.001629	time 0.6385 (0.6157)	model_time 0.6384 (0.6104)	loss 3.8323 (3.2456)	grad_norm 1.1302 (1.8789/0.7790)	mem 24308MB
[2025-01-18 22:32:28 internimage_s_1k_224] (main.py 510): INFO Train: [168/300][310/312]	eta 0:00:01 lr 0.001629	time 0.5806 (0.6153)	model_time 0.5805 (0.6102)	loss 2.8828 (3.2472)	grad_norm 1.2139 (1.8728/0.7802)	mem 24308MB
[2025-01-18 22:32:28 internimage_s_1k_224] (main.py 519): INFO EPOCH 168 training takes 0:03:11
[2025-01-18 22:32:28 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_168.pth saving......
[2025-01-18 22:32:30 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_168.pth saved !!!
[2025-01-18 22:32:37 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.328 (7.328)	Loss 0.7953 (0.7953)	Acc@1 82.935 (82.935)	Acc@5 96.729 (96.729)	Mem 24308MB
[2025-01-18 22:32:41 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.985)	Loss 1.0927 (0.9143)	Acc@1 75.537 (80.318)	Acc@5 93.750 (95.386)	Mem 24308MB
[2025-01-18 22:32:41 internimage_s_1k_224] (main.py 575): INFO [Epoch:168] * Acc@1 80.232 Acc@5 95.413
[2025-01-18 22:32:41 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.2%
[2025-01-18 22:32:41 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 22:32:43 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 22:32:43 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.23%
[2025-01-18 22:32:50 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.403 (7.403)	Loss 0.7081 (0.7081)	Acc@1 84.009 (84.009)	Acc@5 97.363 (97.363)	Mem 24308MB
[2025-01-18 22:32:54 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.987)	Loss 0.9953 (0.8278)	Acc@1 76.074 (80.859)	Acc@5 94.141 (95.657)	Mem 24308MB
[2025-01-18 22:32:54 internimage_s_1k_224] (main.py 575): INFO [Epoch:168] * Acc@1 80.764 Acc@5 95.691
[2025-01-18 22:32:54 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.8%
[2025-01-18 22:32:54 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 22:32:56 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 22:32:56 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.76%
[2025-01-18 22:32:59 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][0/312]	eta 0:11:24 lr 0.001629	time 2.1935 (2.1935)	model_time 0.5909 (0.5909)	loss 3.4715 (3.4715)	grad_norm 1.3657 (1.3657/0.0000)	mem 24308MB
[2025-01-18 22:33:05 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][10/312]	eta 0:03:45 lr 0.001628	time 0.6531 (0.7455)	model_time 0.6529 (0.5995)	loss 2.8263 (3.0236)	grad_norm 2.1141 (1.4782/0.4605)	mem 24308MB
[2025-01-18 22:33:11 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][20/312]	eta 0:03:20 lr 0.001627	time 0.6364 (0.6872)	model_time 0.6359 (0.6106)	loss 3.4042 (3.0986)	grad_norm 1.8511 (2.1237/1.1872)	mem 24308MB
[2025-01-18 22:33:17 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][30/312]	eta 0:03:07 lr 0.001627	time 0.6741 (0.6635)	model_time 0.6739 (0.6115)	loss 3.5569 (3.2418)	grad_norm 1.5692 (2.3291/1.2592)	mem 24308MB
[2025-01-18 22:33:23 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][40/312]	eta 0:02:56 lr 0.001626	time 0.5843 (0.6474)	model_time 0.5841 (0.6080)	loss 3.0798 (3.2200)	grad_norm 3.3605 (2.2148/1.1590)	mem 24308MB
[2025-01-18 22:33:29 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][50/312]	eta 0:02:46 lr 0.001625	time 0.5872 (0.6357)	model_time 0.5869 (0.6040)	loss 3.9685 (3.1585)	grad_norm 3.2111 (2.1871/1.1300)	mem 24308MB
[2025-01-18 22:33:35 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][60/312]	eta 0:02:39 lr 0.001625	time 0.5838 (0.6318)	model_time 0.5833 (0.6052)	loss 3.2244 (3.1439)	grad_norm 2.4507 (2.2120/1.1187)	mem 24308MB
[2025-01-18 22:33:41 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][70/312]	eta 0:02:32 lr 0.001624	time 0.5752 (0.6281)	model_time 0.5750 (0.6052)	loss 3.0461 (3.1764)	grad_norm 1.3383 (2.1456/1.0806)	mem 24308MB
[2025-01-18 22:33:47 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][80/312]	eta 0:02:25 lr 0.001623	time 0.5742 (0.6260)	model_time 0.5737 (0.6059)	loss 4.2006 (3.1825)	grad_norm 2.4510 (2.1286/1.0287)	mem 24308MB
[2025-01-18 22:33:53 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][90/312]	eta 0:02:18 lr 0.001623	time 0.6801 (0.6233)	model_time 0.6797 (0.6054)	loss 3.5707 (3.1644)	grad_norm 3.8771 (2.2053/1.0490)	mem 24308MB
[2025-01-18 22:33:59 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][100/312]	eta 0:02:11 lr 0.001622	time 0.6004 (0.6216)	model_time 0.6000 (0.6054)	loss 3.4247 (3.1719)	grad_norm 2.5602 (2.2326/1.0142)	mem 24308MB
[2025-01-18 22:34:05 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][110/312]	eta 0:02:05 lr 0.001621	time 0.6686 (0.6226)	model_time 0.6682 (0.6078)	loss 2.9938 (3.1682)	grad_norm 2.6264 (2.1974/0.9971)	mem 24308MB
[2025-01-18 22:34:12 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][120/312]	eta 0:01:59 lr 0.001621	time 0.5788 (0.6212)	model_time 0.5784 (0.6076)	loss 2.6416 (3.1507)	grad_norm 1.8196 (2.1652/0.9698)	mem 24308MB
[2025-01-18 22:34:18 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][130/312]	eta 0:01:52 lr 0.001620	time 0.6591 (0.6199)	model_time 0.6586 (0.6073)	loss 3.3920 (3.1696)	grad_norm 1.3318 (2.1120/0.9547)	mem 24308MB
[2025-01-18 22:34:24 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][140/312]	eta 0:01:46 lr 0.001620	time 0.5855 (0.6202)	model_time 0.5853 (0.6085)	loss 2.6584 (3.1755)	grad_norm 2.0144 (2.0631/0.9410)	mem 24308MB
[2025-01-18 22:34:30 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][150/312]	eta 0:01:40 lr 0.001619	time 0.6684 (0.6191)	model_time 0.6680 (0.6082)	loss 3.5027 (3.1790)	grad_norm 1.4822 (2.0250/0.9249)	mem 24308MB
[2025-01-18 22:34:36 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][160/312]	eta 0:01:34 lr 0.001618	time 0.5846 (0.6187)	model_time 0.5844 (0.6084)	loss 2.2142 (3.1876)	grad_norm 1.6171 (1.9994/0.9109)	mem 24308MB
[2025-01-18 22:34:42 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][170/312]	eta 0:01:27 lr 0.001618	time 0.6079 (0.6175)	model_time 0.6077 (0.6078)	loss 2.5579 (3.1688)	grad_norm 1.2485 (1.9626/0.8992)	mem 24308MB
[2025-01-18 22:34:48 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][180/312]	eta 0:01:21 lr 0.001617	time 0.5755 (0.6175)	model_time 0.5751 (0.6083)	loss 3.0972 (3.1514)	grad_norm 3.7359 (1.9448/0.8972)	mem 24308MB
[2025-01-18 22:34:54 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][190/312]	eta 0:01:15 lr 0.001616	time 0.5856 (0.6168)	model_time 0.5851 (0.6081)	loss 2.7396 (3.1564)	grad_norm 3.4976 (1.9560/0.8868)	mem 24308MB
[2025-01-18 22:35:00 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][200/312]	eta 0:01:08 lr 0.001616	time 0.5893 (0.6159)	model_time 0.5889 (0.6076)	loss 3.3185 (3.1618)	grad_norm 1.0296 (1.9508/0.8841)	mem 24308MB
[2025-01-18 22:35:06 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][210/312]	eta 0:01:02 lr 0.001615	time 0.6609 (0.6158)	model_time 0.6607 (0.6078)	loss 3.5073 (3.1688)	grad_norm 1.8126 (1.9382/0.8692)	mem 24308MB
[2025-01-18 22:35:12 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][220/312]	eta 0:00:56 lr 0.001614	time 0.5917 (0.6148)	model_time 0.5915 (0.6072)	loss 3.9160 (3.1805)	grad_norm 4.3814 (1.9642/0.9051)	mem 24308MB
[2025-01-18 22:35:19 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][230/312]	eta 0:00:50 lr 0.001614	time 0.5962 (0.6153)	model_time 0.5958 (0.6080)	loss 3.5689 (3.1731)	grad_norm 2.0789 (1.9659/0.8981)	mem 24308MB
[2025-01-18 22:35:25 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][240/312]	eta 0:00:44 lr 0.001613	time 0.5947 (0.6151)	model_time 0.5943 (0.6081)	loss 3.2624 (3.1712)	grad_norm 1.4123 (1.9661/0.8879)	mem 24308MB
[2025-01-18 22:35:31 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][250/312]	eta 0:00:38 lr 0.001612	time 0.5956 (0.6143)	model_time 0.5952 (0.6076)	loss 3.7295 (3.1715)	grad_norm 1.4168 (1.9490/0.8790)	mem 24308MB
[2025-01-18 22:35:37 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][260/312]	eta 0:00:31 lr 0.001612	time 0.5819 (0.6143)	model_time 0.5818 (0.6078)	loss 2.6529 (3.1770)	grad_norm 0.8254 (1.9303/0.8722)	mem 24308MB
[2025-01-18 22:35:43 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][270/312]	eta 0:00:25 lr 0.001611	time 0.5818 (0.6138)	model_time 0.5813 (0.6076)	loss 2.2516 (3.1804)	grad_norm 2.7242 (1.9298/0.8660)	mem 24308MB
[2025-01-18 22:35:49 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][280/312]	eta 0:00:19 lr 0.001610	time 0.5985 (0.6140)	model_time 0.5984 (0.6079)	loss 2.6189 (3.1857)	grad_norm 0.9585 (1.9116/0.8582)	mem 24308MB
[2025-01-18 22:35:55 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][290/312]	eta 0:00:13 lr 0.001610	time 0.5898 (0.6132)	model_time 0.5897 (0.6073)	loss 3.5316 (3.1910)	grad_norm 1.4686 (1.8979/0.8495)	mem 24308MB
[2025-01-18 22:36:01 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][300/312]	eta 0:00:07 lr 0.001609	time 0.5618 (0.6127)	model_time 0.5617 (0.6071)	loss 2.6869 (3.1969)	grad_norm 2.0948 (1.9237/0.8862)	mem 24308MB
[2025-01-18 22:36:07 internimage_s_1k_224] (main.py 510): INFO Train: [169/300][310/312]	eta 0:00:01 lr 0.001608	time 0.5683 (0.6119)	model_time 0.5682 (0.6064)	loss 3.1148 (3.2029)	grad_norm 1.5878 (1.9469/0.9032)	mem 24308MB
[2025-01-18 22:36:07 internimage_s_1k_224] (main.py 519): INFO EPOCH 169 training takes 0:03:10
[2025-01-18 22:36:07 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_169.pth saving......
[2025-01-18 22:36:09 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_169.pth saved !!!
[2025-01-18 22:36:17 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.797 (7.797)	Loss 0.7809 (0.7809)	Acc@1 82.764 (82.764)	Acc@5 96.973 (96.973)	Mem 24308MB
[2025-01-18 22:36:21 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.138 (1.057)	Loss 1.0538 (0.9007)	Acc@1 75.293 (80.136)	Acc@5 93.774 (95.426)	Mem 24308MB
[2025-01-18 22:36:21 internimage_s_1k_224] (main.py 575): INFO [Epoch:169] * Acc@1 80.012 Acc@5 95.445
[2025-01-18 22:36:21 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.0%
[2025-01-18 22:36:21 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.23%
[2025-01-18 22:36:30 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.205 (9.205)	Loss 0.7079 (0.7079)	Acc@1 83.984 (83.984)	Acc@5 97.388 (97.388)	Mem 24308MB
[2025-01-18 22:36:35 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.256)	Loss 0.9934 (0.8269)	Acc@1 76.123 (80.922)	Acc@5 94.141 (95.665)	Mem 24308MB
[2025-01-18 22:36:35 internimage_s_1k_224] (main.py 575): INFO [Epoch:169] * Acc@1 80.822 Acc@5 95.703
[2025-01-18 22:36:35 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.8%
[2025-01-18 22:36:35 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 22:36:37 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 22:36:37 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.82%
[2025-01-18 22:36:40 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][0/312]	eta 0:13:20 lr 0.001608	time 2.5655 (2.5655)	model_time 0.6024 (0.6024)	loss 2.2732 (2.2732)	grad_norm 0.9427 (0.9427/0.0000)	mem 24308MB
[2025-01-18 22:36:46 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][10/312]	eta 0:03:57 lr 0.001608	time 0.5764 (0.7879)	model_time 0.5760 (0.6092)	loss 3.0550 (3.1011)	grad_norm 1.0844 (1.2396/0.3712)	mem 24308MB
[2025-01-18 22:36:52 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][20/312]	eta 0:03:25 lr 0.001607	time 0.5749 (0.7033)	model_time 0.5748 (0.6095)	loss 3.4750 (3.2538)	grad_norm 1.8822 (2.3399/1.7323)	mem 24308MB
[2025-01-18 22:36:58 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][30/312]	eta 0:03:10 lr 0.001606	time 0.6298 (0.6766)	model_time 0.6293 (0.6130)	loss 2.3688 (3.1919)	grad_norm 1.2781 (2.3075/1.5462)	mem 24308MB
[2025-01-18 22:37:05 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][40/312]	eta 0:03:00 lr 0.001606	time 0.5776 (0.6642)	model_time 0.5774 (0.6160)	loss 3.6954 (3.1981)	grad_norm 1.3745 (2.0640/1.4146)	mem 24308MB
[2025-01-18 22:37:11 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][50/312]	eta 0:02:51 lr 0.001605	time 0.5924 (0.6536)	model_time 0.5922 (0.6148)	loss 2.0800 (3.1944)	grad_norm 3.2377 (1.9358/1.3378)	mem 24308MB
[2025-01-18 22:37:17 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][60/312]	eta 0:02:42 lr 0.001604	time 0.5948 (0.6456)	model_time 0.5946 (0.6131)	loss 3.2645 (3.1990)	grad_norm 1.6161 (1.8413/1.2522)	mem 24308MB
[2025-01-18 22:37:23 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][70/312]	eta 0:02:35 lr 0.001604	time 0.6635 (0.6444)	model_time 0.6633 (0.6164)	loss 3.1370 (3.1950)	grad_norm 1.3677 (1.8067/1.1743)	mem 24308MB
[2025-01-18 22:37:29 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][80/312]	eta 0:02:28 lr 0.001603	time 0.5909 (0.6399)	model_time 0.5905 (0.6153)	loss 3.6530 (3.2351)	grad_norm 2.1041 (1.7913/1.1164)	mem 24308MB
[2025-01-18 22:37:35 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][90/312]	eta 0:02:21 lr 0.001602	time 0.5776 (0.6364)	model_time 0.5774 (0.6145)	loss 3.3984 (3.2193)	grad_norm 1.2884 (1.8033/1.1080)	mem 24308MB
[2025-01-18 22:37:41 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][100/312]	eta 0:02:14 lr 0.001602	time 0.5916 (0.6323)	model_time 0.5913 (0.6126)	loss 4.0869 (3.2309)	grad_norm 1.9998 (1.8249/1.0694)	mem 24308MB
[2025-01-18 22:37:47 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][110/312]	eta 0:02:07 lr 0.001601	time 0.5868 (0.6304)	model_time 0.5867 (0.6124)	loss 2.9547 (3.2308)	grad_norm 1.7993 (1.8785/1.0504)	mem 24308MB
[2025-01-18 22:37:53 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][120/312]	eta 0:02:00 lr 0.001601	time 0.5808 (0.6279)	model_time 0.5803 (0.6113)	loss 4.0342 (3.2551)	grad_norm 1.8807 (1.8314/1.0232)	mem 24308MB
[2025-01-18 22:37:59 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][130/312]	eta 0:01:53 lr 0.001600	time 0.5863 (0.6253)	model_time 0.5861 (0.6099)	loss 4.1568 (3.2435)	grad_norm 3.3302 (1.8960/1.0455)	mem 24308MB
[2025-01-18 22:38:05 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][140/312]	eta 0:01:47 lr 0.001599	time 0.5950 (0.6250)	model_time 0.5948 (0.6107)	loss 3.4264 (3.2214)	grad_norm 0.9307 (1.8723/1.0251)	mem 24308MB
[2025-01-18 22:38:11 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][150/312]	eta 0:01:40 lr 0.001599	time 0.5831 (0.6232)	model_time 0.5829 (0.6099)	loss 3.3971 (3.2288)	grad_norm 3.0677 (1.8447/1.0068)	mem 24308MB
[2025-01-18 22:38:18 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][160/312]	eta 0:01:34 lr 0.001598	time 0.6729 (0.6225)	model_time 0.6727 (0.6100)	loss 2.9262 (3.2205)	grad_norm 2.1337 (1.8266/0.9872)	mem 24308MB
[2025-01-18 22:38:24 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][170/312]	eta 0:01:28 lr 0.001597	time 0.5757 (0.6217)	model_time 0.5755 (0.6099)	loss 2.1952 (3.2043)	grad_norm 3.2844 (1.8568/0.9748)	mem 24308MB
[2025-01-18 22:38:30 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][180/312]	eta 0:01:21 lr 0.001597	time 0.5733 (0.6207)	model_time 0.5728 (0.6095)	loss 3.6408 (3.2055)	grad_norm 1.0631 (1.8956/1.0000)	mem 24308MB
[2025-01-18 22:38:36 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][190/312]	eta 0:01:15 lr 0.001596	time 0.6773 (0.6210)	model_time 0.6769 (0.6103)	loss 3.2298 (3.2117)	grad_norm 2.2434 (1.8934/0.9827)	mem 24308MB
[2025-01-18 22:38:42 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][200/312]	eta 0:01:09 lr 0.001595	time 0.5890 (0.6205)	model_time 0.5713 (0.6103)	loss 2.1380 (3.2059)	grad_norm 1.3052 (1.8823/0.9655)	mem 24308MB
[2025-01-18 22:38:48 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][210/312]	eta 0:01:03 lr 0.001595	time 0.5831 (0.6205)	model_time 0.5826 (0.6107)	loss 2.0817 (3.2043)	grad_norm 1.2387 (1.8589/0.9543)	mem 24308MB
[2025-01-18 22:38:54 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][220/312]	eta 0:00:56 lr 0.001594	time 0.5871 (0.6192)	model_time 0.5869 (0.6099)	loss 3.4539 (3.2020)	grad_norm 1.9573 (1.8664/0.9490)	mem 24308MB
[2025-01-18 22:39:00 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][230/312]	eta 0:00:50 lr 0.001593	time 0.6901 (0.6187)	model_time 0.6897 (0.6097)	loss 3.8100 (3.1906)	grad_norm 3.8936 (1.8974/0.9615)	mem 24308MB
[2025-01-18 22:39:06 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][240/312]	eta 0:00:44 lr 0.001593	time 0.6627 (0.6177)	model_time 0.6623 (0.6092)	loss 3.7743 (3.1988)	grad_norm 2.4275 (1.9162/0.9648)	mem 24308MB
[2025-01-18 22:39:12 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][250/312]	eta 0:00:38 lr 0.001592	time 0.5731 (0.6168)	model_time 0.5726 (0.6085)	loss 2.3255 (3.1949)	grad_norm 2.0419 (1.9243/0.9536)	mem 24308MB
[2025-01-18 22:39:18 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][260/312]	eta 0:00:32 lr 0.001591	time 0.5740 (0.6163)	model_time 0.5738 (0.6084)	loss 2.7366 (3.1964)	grad_norm 1.7056 (1.9233/0.9415)	mem 24308MB
[2025-01-18 22:39:24 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][270/312]	eta 0:00:25 lr 0.001591	time 0.6369 (0.6164)	model_time 0.6368 (0.6087)	loss 3.1472 (3.1938)	grad_norm 2.7673 (1.9188/0.9321)	mem 24308MB
[2025-01-18 22:39:31 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][280/312]	eta 0:00:19 lr 0.001590	time 0.6728 (0.6163)	model_time 0.6726 (0.6089)	loss 2.1516 (3.1869)	grad_norm 1.3965 (1.8984/0.9239)	mem 24308MB
[2025-01-18 22:39:37 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][290/312]	eta 0:00:13 lr 0.001590	time 0.6660 (0.6166)	model_time 0.6658 (0.6095)	loss 3.4144 (3.1877)	grad_norm 1.1870 (1.8849/0.9116)	mem 24308MB
[2025-01-18 22:39:43 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][300/312]	eta 0:00:07 lr 0.001589	time 0.5603 (0.6160)	model_time 0.5602 (0.6090)	loss 3.4401 (3.1892)	grad_norm 1.8656 (1.9086/0.9268)	mem 24308MB
[2025-01-18 22:39:49 internimage_s_1k_224] (main.py 510): INFO Train: [170/300][310/312]	eta 0:00:01 lr 0.001588	time 0.5609 (0.6153)	model_time 0.5608 (0.6086)	loss 3.2214 (3.1897)	grad_norm 2.3344 (1.9445/0.9306)	mem 24308MB
[2025-01-18 22:39:49 internimage_s_1k_224] (main.py 519): INFO EPOCH 170 training takes 0:03:11
[2025-01-18 22:39:49 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_170.pth saving......
[2025-01-18 22:39:51 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_170.pth saved !!!
[2025-01-18 22:39:59 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.887 (7.887)	Loss 0.8079 (0.8079)	Acc@1 83.154 (83.154)	Acc@5 96.802 (96.802)	Mem 24308MB
[2025-01-18 22:40:03 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.034)	Loss 1.0887 (0.9391)	Acc@1 76.074 (80.320)	Acc@5 93.921 (95.415)	Mem 24308MB
[2025-01-18 22:40:03 internimage_s_1k_224] (main.py 575): INFO [Epoch:170] * Acc@1 80.228 Acc@5 95.445
[2025-01-18 22:40:03 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.2%
[2025-01-18 22:40:03 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.23%
[2025-01-18 22:40:11 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.668 (8.668)	Loss 0.7075 (0.7075)	Acc@1 84.009 (84.009)	Acc@5 97.437 (97.437)	Mem 24308MB
[2025-01-18 22:40:16 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.182)	Loss 0.9915 (0.8261)	Acc@1 76.099 (80.939)	Acc@5 94.141 (95.685)	Mem 24308MB
[2025-01-18 22:40:16 internimage_s_1k_224] (main.py 575): INFO [Epoch:170] * Acc@1 80.840 Acc@5 95.723
[2025-01-18 22:40:16 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.8%
[2025-01-18 22:40:16 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 22:40:18 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 22:40:18 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.84%
[2025-01-18 22:40:21 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][0/312]	eta 0:11:36 lr 0.001588	time 2.2315 (2.2315)	model_time 0.5939 (0.5939)	loss 3.3541 (3.3541)	grad_norm 2.6515 (2.6515/0.0000)	mem 24308MB
[2025-01-18 22:40:27 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][10/312]	eta 0:03:46 lr 0.001587	time 0.5728 (0.7509)	model_time 0.5726 (0.6004)	loss 3.6465 (3.4004)	grad_norm 1.8041 (2.3135/0.6596)	mem 24308MB
[2025-01-18 22:40:33 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][20/312]	eta 0:03:18 lr 0.001587	time 0.5891 (0.6813)	model_time 0.5889 (0.6023)	loss 3.5357 (3.3511)	grad_norm 2.6047 (2.3522/0.6974)	mem 24308MB
[2025-01-18 22:40:39 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][30/312]	eta 0:03:04 lr 0.001586	time 0.5880 (0.6525)	model_time 0.5879 (0.5989)	loss 2.4875 (3.2263)	grad_norm 3.1136 (2.4543/0.7843)	mem 24308MB
[2025-01-18 22:40:45 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][40/312]	eta 0:02:54 lr 0.001585	time 0.5795 (0.6416)	model_time 0.5793 (0.6011)	loss 3.1175 (3.1950)	grad_norm 1.1257 (2.3178/0.8921)	mem 24308MB
[2025-01-18 22:40:51 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][50/312]	eta 0:02:46 lr 0.001585	time 0.6787 (0.6342)	model_time 0.6782 (0.6015)	loss 2.7508 (3.2068)	grad_norm 0.9027 (2.0832/0.9364)	mem 24308MB
[2025-01-18 22:40:57 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][60/312]	eta 0:02:38 lr 0.001584	time 0.5882 (0.6277)	model_time 0.5878 (0.6003)	loss 3.3697 (3.2100)	grad_norm 1.3346 (1.9469/0.9163)	mem 24308MB
[2025-01-18 22:41:03 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][70/312]	eta 0:02:31 lr 0.001584	time 0.5864 (0.6248)	model_time 0.5862 (0.6012)	loss 3.2541 (3.2097)	grad_norm 1.2654 (1.8903/0.8758)	mem 24308MB
[2025-01-18 22:41:09 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][80/312]	eta 0:02:24 lr 0.001583	time 0.5732 (0.6228)	model_time 0.5728 (0.6021)	loss 3.1623 (3.2081)	grad_norm 1.1646 (1.8979/0.8397)	mem 24308MB
[2025-01-18 22:41:15 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][90/312]	eta 0:02:18 lr 0.001582	time 0.5938 (0.6216)	model_time 0.5934 (0.6031)	loss 3.9709 (3.2045)	grad_norm 1.8266 (1.9217/0.8687)	mem 24308MB
[2025-01-18 22:41:21 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][100/312]	eta 0:02:11 lr 0.001582	time 0.5722 (0.6219)	model_time 0.5720 (0.6052)	loss 3.4572 (3.2153)	grad_norm 2.0160 (1.9704/0.8936)	mem 24308MB
[2025-01-18 22:41:27 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][110/312]	eta 0:02:05 lr 0.001581	time 0.5960 (0.6206)	model_time 0.5956 (0.6053)	loss 3.9465 (3.1848)	grad_norm 2.3766 (1.9432/0.8669)	mem 24308MB
[2025-01-18 22:41:33 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][120/312]	eta 0:01:59 lr 0.001580	time 0.6110 (0.6202)	model_time 0.6109 (0.6062)	loss 2.9712 (3.1902)	grad_norm 1.3390 (2.0303/0.9201)	mem 24308MB
[2025-01-18 22:41:40 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][130/312]	eta 0:01:52 lr 0.001580	time 0.5718 (0.6197)	model_time 0.5716 (0.6067)	loss 2.8534 (3.1766)	grad_norm 1.3013 (2.0193/0.8958)	mem 24308MB
[2025-01-18 22:41:46 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][140/312]	eta 0:01:46 lr 0.001579	time 0.5824 (0.6199)	model_time 0.5820 (0.6078)	loss 4.0768 (3.1974)	grad_norm 1.8191 (1.9826/0.8878)	mem 24308MB
[2025-01-18 22:41:52 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][150/312]	eta 0:01:40 lr 0.001578	time 0.5751 (0.6179)	model_time 0.5747 (0.6066)	loss 3.3074 (3.2004)	grad_norm 1.9222 (1.9739/0.8703)	mem 24308MB
[2025-01-18 22:41:58 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][160/312]	eta 0:01:33 lr 0.001578	time 0.6548 (0.6168)	model_time 0.6543 (0.6062)	loss 3.4289 (3.2077)	grad_norm 1.1675 (1.9714/0.8643)	mem 24308MB
[2025-01-18 22:42:04 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][170/312]	eta 0:01:27 lr 0.001577	time 0.5971 (0.6153)	model_time 0.5966 (0.6052)	loss 3.8034 (3.2178)	grad_norm 1.5323 (1.9583/0.8505)	mem 24308MB
[2025-01-18 22:42:10 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][180/312]	eta 0:01:21 lr 0.001576	time 0.5841 (0.6143)	model_time 0.5839 (0.6047)	loss 3.5857 (3.2312)	grad_norm 1.9808 (1.9440/0.8356)	mem 24308MB
[2025-01-18 22:42:16 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][190/312]	eta 0:01:14 lr 0.001576	time 0.5871 (0.6139)	model_time 0.5867 (0.6049)	loss 2.5036 (3.2176)	grad_norm 1.9197 (1.9228/0.8222)	mem 24308MB
[2025-01-18 22:42:22 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][200/312]	eta 0:01:08 lr 0.001575	time 0.5904 (0.6134)	model_time 0.5902 (0.6048)	loss 3.6937 (3.2241)	grad_norm 1.0581 (1.9251/0.8282)	mem 24308MB
[2025-01-18 22:42:28 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][210/312]	eta 0:01:02 lr 0.001574	time 0.5901 (0.6137)	model_time 0.5896 (0.6054)	loss 3.3490 (3.2181)	grad_norm 3.0595 (1.9362/0.8357)	mem 24308MB
[2025-01-18 22:42:34 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][220/312]	eta 0:00:56 lr 0.001574	time 0.5733 (0.6143)	model_time 0.5728 (0.6064)	loss 2.9525 (3.2185)	grad_norm 1.3429 (1.9173/0.8250)	mem 24308MB
[2025-01-18 22:42:40 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][230/312]	eta 0:00:50 lr 0.001573	time 0.5833 (0.6141)	model_time 0.5832 (0.6065)	loss 2.3769 (3.2161)	grad_norm 1.9721 (1.9003/0.8170)	mem 24308MB
[2025-01-18 22:42:46 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][240/312]	eta 0:00:44 lr 0.001573	time 0.6680 (0.6139)	model_time 0.6676 (0.6066)	loss 3.4240 (3.2305)	grad_norm 1.0206 (1.8807/0.8093)	mem 24308MB
[2025-01-18 22:42:52 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][250/312]	eta 0:00:38 lr 0.001572	time 0.6649 (0.6136)	model_time 0.6645 (0.6066)	loss 3.8499 (3.2329)	grad_norm 1.2691 (1.8653/0.7996)	mem 24308MB
[2025-01-18 22:42:59 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][260/312]	eta 0:00:31 lr 0.001571	time 0.5714 (0.6136)	model_time 0.5712 (0.6068)	loss 3.2246 (3.2330)	grad_norm 1.9914 (1.8701/0.7981)	mem 24308MB
[2025-01-18 22:43:04 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][270/312]	eta 0:00:25 lr 0.001571	time 0.6049 (0.6127)	model_time 0.6047 (0.6062)	loss 3.3552 (3.2258)	grad_norm 1.1596 (1.9057/0.8767)	mem 24308MB
[2025-01-18 22:43:10 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][280/312]	eta 0:00:19 lr 0.001570	time 0.6610 (0.6122)	model_time 0.6606 (0.6059)	loss 3.1775 (3.2207)	grad_norm 2.2314 (1.9071/0.8694)	mem 24308MB
[2025-01-18 22:43:16 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][290/312]	eta 0:00:13 lr 0.001569	time 0.5819 (0.6116)	model_time 0.5817 (0.6055)	loss 3.4022 (3.2103)	grad_norm 1.1750 (1.9093/0.8592)	mem 24308MB
[2025-01-18 22:43:22 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][300/312]	eta 0:00:07 lr 0.001569	time 0.5683 (0.6108)	model_time 0.5682 (0.6049)	loss 3.3780 (3.2133)	grad_norm 4.7487 (1.9095/0.8715)	mem 24308MB
[2025-01-18 22:43:28 internimage_s_1k_224] (main.py 510): INFO Train: [171/300][310/312]	eta 0:00:01 lr 0.001568	time 0.5681 (0.6101)	model_time 0.5680 (0.6044)	loss 2.9025 (3.2052)	grad_norm 3.3877 (1.9307/0.9472)	mem 24308MB
[2025-01-18 22:43:29 internimage_s_1k_224] (main.py 519): INFO EPOCH 171 training takes 0:03:10
[2025-01-18 22:43:29 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_171.pth saving......
[2025-01-18 22:43:31 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_171.pth saved !!!
[2025-01-18 22:43:38 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.688 (7.688)	Loss 0.7736 (0.7736)	Acc@1 83.081 (83.081)	Acc@5 96.875 (96.875)	Mem 24308MB
[2025-01-18 22:43:42 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.994)	Loss 1.0857 (0.9190)	Acc@1 75.781 (80.376)	Acc@5 93.896 (95.521)	Mem 24308MB
[2025-01-18 22:43:42 internimage_s_1k_224] (main.py 575): INFO [Epoch:171] * Acc@1 80.280 Acc@5 95.553
[2025-01-18 22:43:42 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.3%
[2025-01-18 22:43:42 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 22:43:44 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 22:43:44 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.28%
[2025-01-18 22:43:51 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.447 (7.447)	Loss 0.7072 (0.7072)	Acc@1 84.131 (84.131)	Acc@5 97.485 (97.485)	Mem 24308MB
[2025-01-18 22:43:55 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.993)	Loss 0.9898 (0.8254)	Acc@1 76.172 (80.990)	Acc@5 94.189 (95.714)	Mem 24308MB
[2025-01-18 22:43:55 internimage_s_1k_224] (main.py 575): INFO [Epoch:171] * Acc@1 80.882 Acc@5 95.747
[2025-01-18 22:43:55 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.9%
[2025-01-18 22:43:55 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 22:43:57 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 22:43:57 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.88%
[2025-01-18 22:43:59 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][0/312]	eta 0:11:44 lr 0.001568	time 2.2590 (2.2590)	model_time 0.6002 (0.6002)	loss 3.4922 (3.4922)	grad_norm 1.1793 (1.1793/0.0000)	mem 24308MB
[2025-01-18 22:44:05 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][10/312]	eta 0:03:49 lr 0.001567	time 0.6466 (0.7613)	model_time 0.6464 (0.6102)	loss 3.5722 (3.0850)	grad_norm 2.6203 (1.7709/0.4664)	mem 24308MB
[2025-01-18 22:44:12 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][20/312]	eta 0:03:20 lr 0.001567	time 0.6004 (0.6883)	model_time 0.6000 (0.6090)	loss 3.5393 (3.1639)	grad_norm 0.9744 (1.7597/0.6382)	mem 24308MB
[2025-01-18 22:44:18 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][30/312]	eta 0:03:08 lr 0.001566	time 0.5859 (0.6694)	model_time 0.5857 (0.6155)	loss 2.6649 (3.1615)	grad_norm 0.9287 (1.8839/0.7143)	mem 24308MB
[2025-01-18 22:44:24 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][40/312]	eta 0:02:58 lr 0.001565	time 0.5844 (0.6548)	model_time 0.5839 (0.6140)	loss 3.5384 (3.2140)	grad_norm 1.6430 (1.8452/0.7115)	mem 24308MB
[2025-01-18 22:44:30 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][50/312]	eta 0:02:48 lr 0.001565	time 0.5957 (0.6437)	model_time 0.5952 (0.6108)	loss 2.8827 (3.2035)	grad_norm 3.8467 (2.0373/0.8769)	mem 24308MB
[2025-01-18 22:44:36 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][60/312]	eta 0:02:40 lr 0.001564	time 0.6084 (0.6387)	model_time 0.6082 (0.6111)	loss 3.4016 (3.2005)	grad_norm 1.0490 (2.0430/0.8664)	mem 24308MB
[2025-01-18 22:44:42 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][70/312]	eta 0:02:33 lr 0.001563	time 0.6542 (0.6353)	model_time 0.6541 (0.6116)	loss 2.8681 (3.1841)	grad_norm 1.2841 (1.9598/0.8641)	mem 24308MB
[2025-01-18 22:44:48 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][80/312]	eta 0:02:26 lr 0.001563	time 0.5956 (0.6295)	model_time 0.5951 (0.6083)	loss 3.0696 (3.2063)	grad_norm 1.7199 (1.9384/0.8227)	mem 24308MB
[2025-01-18 22:44:54 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][90/312]	eta 0:02:18 lr 0.001562	time 0.5786 (0.6257)	model_time 0.5782 (0.6068)	loss 3.4912 (3.1958)	grad_norm 1.3904 (1.8876/0.7967)	mem 24308MB
[2025-01-18 22:45:00 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][100/312]	eta 0:02:12 lr 0.001561	time 0.5830 (0.6247)	model_time 0.5828 (0.6077)	loss 2.0151 (3.1913)	grad_norm 2.1203 (1.8306/0.7813)	mem 24308MB
[2025-01-18 22:45:06 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][110/312]	eta 0:02:05 lr 0.001561	time 0.5931 (0.6212)	model_time 0.5927 (0.6057)	loss 2.8865 (3.1787)	grad_norm 2.2851 (1.8354/0.7577)	mem 24308MB
[2025-01-18 22:45:12 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][120/312]	eta 0:01:59 lr 0.001560	time 0.5723 (0.6201)	model_time 0.5721 (0.6058)	loss 3.2626 (3.1884)	grad_norm 2.8243 (1.8767/0.7747)	mem 24308MB
[2025-01-18 22:45:18 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][130/312]	eta 0:01:52 lr 0.001559	time 0.5988 (0.6191)	model_time 0.5986 (0.6059)	loss 3.2139 (3.1759)	grad_norm 1.4570 (1.8819/0.7772)	mem 24308MB
[2025-01-18 22:45:24 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][140/312]	eta 0:01:46 lr 0.001559	time 0.5953 (0.6196)	model_time 0.5951 (0.6072)	loss 3.9524 (3.1923)	grad_norm 0.9799 (1.8565/0.7754)	mem 24308MB
[2025-01-18 22:45:31 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][150/312]	eta 0:01:40 lr 0.001558	time 0.6999 (0.6192)	model_time 0.6997 (0.6076)	loss 3.7637 (3.1879)	grad_norm 1.1121 (1.8570/0.7744)	mem 24308MB
[2025-01-18 22:45:37 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][160/312]	eta 0:01:34 lr 0.001558	time 0.5745 (0.6193)	model_time 0.5741 (0.6084)	loss 2.2256 (3.2084)	grad_norm 1.6345 (1.8655/0.7650)	mem 24308MB
[2025-01-18 22:45:43 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][170/312]	eta 0:01:27 lr 0.001557	time 0.5841 (0.6184)	model_time 0.5839 (0.6082)	loss 3.1435 (3.2166)	grad_norm 3.1964 (1.8643/0.7578)	mem 24308MB
[2025-01-18 22:45:49 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][180/312]	eta 0:01:21 lr 0.001556	time 0.5882 (0.6181)	model_time 0.5880 (0.6084)	loss 3.9286 (3.2238)	grad_norm 4.1982 (1.9090/0.8091)	mem 24308MB
[2025-01-18 22:45:55 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][190/312]	eta 0:01:15 lr 0.001556	time 0.5813 (0.6177)	model_time 0.5811 (0.6085)	loss 3.8795 (3.2294)	grad_norm 2.0733 (1.9173/0.8017)	mem 24308MB
[2025-01-18 22:46:01 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][200/312]	eta 0:01:09 lr 0.001555	time 0.5854 (0.6164)	model_time 0.5849 (0.6077)	loss 3.0750 (3.2224)	grad_norm 2.7222 (1.9444/0.8459)	mem 24308MB
[2025-01-18 22:46:07 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][210/312]	eta 0:01:02 lr 0.001554	time 0.5807 (0.6156)	model_time 0.5802 (0.6073)	loss 3.6731 (3.2281)	grad_norm 1.1000 (1.9242/0.8425)	mem 24308MB
[2025-01-18 22:46:13 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][220/312]	eta 0:00:56 lr 0.001554	time 0.5896 (0.6155)	model_time 0.5894 (0.6075)	loss 3.0748 (3.2339)	grad_norm 1.4615 (1.9038/0.8311)	mem 24308MB
[2025-01-18 22:46:19 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][230/312]	eta 0:00:50 lr 0.001553	time 0.5812 (0.6144)	model_time 0.5808 (0.6067)	loss 3.3617 (3.2385)	grad_norm 2.4437 (1.9095/0.8238)	mem 24308MB
[2025-01-18 22:46:25 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][240/312]	eta 0:00:44 lr 0.001552	time 0.5940 (0.6138)	model_time 0.5939 (0.6064)	loss 3.3949 (3.2373)	grad_norm 1.5061 (1.9108/0.8174)	mem 24308MB
[2025-01-18 22:46:31 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][250/312]	eta 0:00:38 lr 0.001552	time 0.6702 (0.6138)	model_time 0.6700 (0.6067)	loss 2.1913 (3.2268)	grad_norm 2.5062 (1.8962/0.8105)	mem 24308MB
[2025-01-18 22:46:37 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][260/312]	eta 0:00:31 lr 0.001551	time 0.6747 (0.6137)	model_time 0.6745 (0.6069)	loss 3.4576 (3.2262)	grad_norm 3.8751 (1.9346/0.8318)	mem 24308MB
[2025-01-18 22:46:43 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][270/312]	eta 0:00:25 lr 0.001550	time 0.6723 (0.6139)	model_time 0.6719 (0.6073)	loss 3.3945 (3.2266)	grad_norm 2.7251 (1.9585/0.8673)	mem 24308MB
[2025-01-18 22:46:50 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][280/312]	eta 0:00:19 lr 0.001550	time 0.6006 (0.6139)	model_time 0.6002 (0.6075)	loss 2.8210 (3.2359)	grad_norm 2.8758 (1.9862/0.8862)	mem 24308MB
[2025-01-18 22:46:56 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][290/312]	eta 0:00:13 lr 0.001549	time 0.5889 (0.6135)	model_time 0.5887 (0.6073)	loss 2.8664 (3.2399)	grad_norm 1.2792 (1.9778/0.8760)	mem 24308MB
[2025-01-18 22:47:02 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][300/312]	eta 0:00:07 lr 0.001548	time 0.5693 (0.6134)	model_time 0.5692 (0.6074)	loss 3.7405 (3.2391)	grad_norm 0.9745 (1.9582/0.8711)	mem 24308MB
[2025-01-18 22:47:08 internimage_s_1k_224] (main.py 510): INFO Train: [172/300][310/312]	eta 0:00:01 lr 0.001548	time 0.5692 (0.6127)	model_time 0.5691 (0.6070)	loss 4.0421 (3.2302)	grad_norm 0.8433 (1.9647/0.8836)	mem 24308MB
[2025-01-18 22:47:08 internimage_s_1k_224] (main.py 519): INFO EPOCH 172 training takes 0:03:11
[2025-01-18 22:47:08 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_172.pth saving......
[2025-01-18 22:47:10 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_172.pth saved !!!
[2025-01-18 22:47:18 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.558 (7.558)	Loss 0.8183 (0.8183)	Acc@1 83.032 (83.032)	Acc@5 96.802 (96.802)	Mem 24308MB
[2025-01-18 22:47:21 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.994)	Loss 1.0762 (0.9281)	Acc@1 76.099 (80.409)	Acc@5 94.067 (95.468)	Mem 24308MB
[2025-01-18 22:47:21 internimage_s_1k_224] (main.py 575): INFO [Epoch:172] * Acc@1 80.304 Acc@5 95.503
[2025-01-18 22:47:21 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.3%
[2025-01-18 22:47:21 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 22:47:23 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 22:47:23 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.30%
[2025-01-18 22:47:30 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.263 (7.263)	Loss 0.7072 (0.7072)	Acc@1 84.058 (84.058)	Acc@5 97.485 (97.485)	Mem 24308MB
[2025-01-18 22:47:34 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.997)	Loss 0.9880 (0.8248)	Acc@1 76.245 (80.997)	Acc@5 94.165 (95.725)	Mem 24308MB
[2025-01-18 22:47:34 internimage_s_1k_224] (main.py 575): INFO [Epoch:172] * Acc@1 80.888 Acc@5 95.761
[2025-01-18 22:47:34 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.9%
[2025-01-18 22:47:34 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 22:47:37 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 22:47:37 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.89%
[2025-01-18 22:47:39 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][0/312]	eta 0:11:02 lr 0.001548	time 2.1235 (2.1235)	model_time 0.6407 (0.6407)	loss 3.8370 (3.8370)	grad_norm 3.1751 (3.1751/0.0000)	mem 24308MB
[2025-01-18 22:47:45 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][10/312]	eta 0:03:41 lr 0.001547	time 0.5855 (0.7326)	model_time 0.5854 (0.5975)	loss 3.4985 (3.1290)	grad_norm 1.9820 (1.5796/0.6070)	mem 24308MB
[2025-01-18 22:47:51 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][20/312]	eta 0:03:15 lr 0.001546	time 0.6022 (0.6704)	model_time 0.6017 (0.5994)	loss 2.2847 (3.1175)	grad_norm 2.6461 (1.7128/0.6263)	mem 24308MB
[2025-01-18 22:47:57 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][30/312]	eta 0:03:03 lr 0.001546	time 0.6052 (0.6518)	model_time 0.6050 (0.6036)	loss 3.4572 (3.1153)	grad_norm 1.9832 (1.7931/0.6463)	mem 24308MB
[2025-01-18 22:48:03 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][40/312]	eta 0:02:53 lr 0.001545	time 0.5776 (0.6364)	model_time 0.5775 (0.5995)	loss 3.7845 (3.1392)	grad_norm 1.5971 (1.7612/0.6531)	mem 24308MB
[2025-01-18 22:48:09 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][50/312]	eta 0:02:44 lr 0.001544	time 0.6771 (0.6294)	model_time 0.6770 (0.5997)	loss 3.8999 (3.1677)	grad_norm 1.2617 (1.7791/0.6635)	mem 24308MB
[2025-01-18 22:48:15 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][60/312]	eta 0:02:37 lr 0.001544	time 0.5828 (0.6256)	model_time 0.5826 (0.6006)	loss 2.7278 (3.2102)	grad_norm 2.4245 (1.9292/1.0158)	mem 24308MB
[2025-01-18 22:48:21 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][70/312]	eta 0:02:30 lr 0.001543	time 0.6652 (0.6237)	model_time 0.6650 (0.6022)	loss 3.2637 (3.1869)	grad_norm 4.2186 (2.0252/1.0453)	mem 24308MB
[2025-01-18 22:48:27 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][80/312]	eta 0:02:24 lr 0.001543	time 0.5730 (0.6237)	model_time 0.5726 (0.6049)	loss 4.0640 (3.2061)	grad_norm 4.5884 (2.0807/1.0547)	mem 24308MB
[2025-01-18 22:48:33 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][90/312]	eta 0:02:18 lr 0.001542	time 0.6608 (0.6237)	model_time 0.6607 (0.6069)	loss 3.2940 (3.2169)	grad_norm 1.7759 (2.0500/1.0075)	mem 24308MB
[2025-01-18 22:48:39 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][100/312]	eta 0:02:11 lr 0.001541	time 0.5820 (0.6214)	model_time 0.5815 (0.6063)	loss 3.4985 (3.2207)	grad_norm 0.9283 (1.9864/0.9862)	mem 24308MB
[2025-01-18 22:48:46 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][110/312]	eta 0:02:05 lr 0.001541	time 0.5922 (0.6206)	model_time 0.5921 (0.6068)	loss 3.5203 (3.2338)	grad_norm 1.8906 (1.9953/0.9648)	mem 24308MB
[2025-01-18 22:48:52 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][120/312]	eta 0:01:59 lr 0.001540	time 0.5912 (0.6206)	model_time 0.5907 (0.6078)	loss 2.1615 (3.2287)	grad_norm 2.0374 (1.9781/0.9319)	mem 24308MB
[2025-01-18 22:48:58 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][130/312]	eta 0:01:52 lr 0.001539	time 0.5747 (0.6193)	model_time 0.5743 (0.6075)	loss 3.1818 (3.2022)	grad_norm 1.9424 (1.9532/0.9078)	mem 24308MB
[2025-01-18 22:49:04 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][140/312]	eta 0:01:46 lr 0.001539	time 0.5835 (0.6177)	model_time 0.5831 (0.6067)	loss 3.7354 (3.2155)	grad_norm 1.2757 (1.9941/0.9538)	mem 24308MB
[2025-01-18 22:49:10 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][150/312]	eta 0:01:39 lr 0.001538	time 0.6046 (0.6167)	model_time 0.6044 (0.6064)	loss 2.8941 (3.1916)	grad_norm 1.1671 (1.9862/0.9564)	mem 24308MB
[2025-01-18 22:49:16 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][160/312]	eta 0:01:33 lr 0.001537	time 0.5764 (0.6149)	model_time 0.5759 (0.6052)	loss 3.3867 (3.1848)	grad_norm 1.6440 (1.9580/0.9379)	mem 24308MB
[2025-01-18 22:49:22 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][170/312]	eta 0:01:27 lr 0.001537	time 0.6767 (0.6143)	model_time 0.6762 (0.6052)	loss 3.3121 (3.1836)	grad_norm 0.7828 (1.9287/0.9301)	mem 24308MB
[2025-01-18 22:49:28 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][180/312]	eta 0:01:21 lr 0.001536	time 0.6512 (0.6139)	model_time 0.6507 (0.6052)	loss 3.4856 (3.1897)	grad_norm 1.9050 (1.9192/0.9135)	mem 24308MB
[2025-01-18 22:49:34 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][190/312]	eta 0:01:15 lr 0.001535	time 0.6607 (0.6149)	model_time 0.6606 (0.6066)	loss 2.7027 (3.1822)	grad_norm 1.3560 (1.9170/0.9124)	mem 24308MB
[2025-01-18 22:49:40 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][200/312]	eta 0:01:08 lr 0.001535	time 0.5728 (0.6148)	model_time 0.5723 (0.6069)	loss 3.9442 (3.1900)	grad_norm 2.5133 (1.9198/0.9048)	mem 24308MB
[2025-01-18 22:49:46 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][210/312]	eta 0:01:02 lr 0.001534	time 0.6257 (0.6150)	model_time 0.6256 (0.6075)	loss 3.7788 (3.1937)	grad_norm 1.6057 (1.9454/0.9183)	mem 24308MB
[2025-01-18 22:49:53 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][220/312]	eta 0:00:56 lr 0.001534	time 0.5739 (0.6148)	model_time 0.5734 (0.6076)	loss 3.8445 (3.1988)	grad_norm 3.3226 (1.9410/0.9103)	mem 24308MB
[2025-01-18 22:49:59 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][230/312]	eta 0:00:50 lr 0.001533	time 0.5841 (0.6149)	model_time 0.5840 (0.6080)	loss 4.2090 (3.2047)	grad_norm 1.9646 (1.9417/0.9074)	mem 24308MB
[2025-01-18 22:50:05 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][240/312]	eta 0:00:44 lr 0.001532	time 0.5750 (0.6143)	model_time 0.5746 (0.6077)	loss 3.9275 (3.2032)	grad_norm 1.0730 (1.9559/0.9123)	mem 24308MB
[2025-01-18 22:50:11 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][250/312]	eta 0:00:38 lr 0.001532	time 0.5930 (0.6141)	model_time 0.5929 (0.6077)	loss 3.5190 (3.2030)	grad_norm 1.4756 (1.9461/0.9001)	mem 24308MB
[2025-01-18 22:50:17 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][260/312]	eta 0:00:31 lr 0.001531	time 0.5817 (0.6134)	model_time 0.5815 (0.6072)	loss 3.5345 (3.2102)	grad_norm 2.4881 (1.9588/0.8905)	mem 24308MB
[2025-01-18 22:50:23 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][270/312]	eta 0:00:25 lr 0.001530	time 0.6174 (0.6129)	model_time 0.6018 (0.6069)	loss 2.5960 (3.2094)	grad_norm 2.3501 (1.9569/0.8809)	mem 24308MB
[2025-01-18 22:50:29 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][280/312]	eta 0:00:19 lr 0.001530	time 0.5740 (0.6124)	model_time 0.5738 (0.6065)	loss 3.4323 (3.2117)	grad_norm 2.0214 (1.9464/0.8815)	mem 24308MB
[2025-01-18 22:50:35 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][290/312]	eta 0:00:13 lr 0.001529	time 0.5849 (0.6117)	model_time 0.5847 (0.6060)	loss 4.0952 (3.2214)	grad_norm 2.0262 (1.9388/0.8746)	mem 24308MB
[2025-01-18 22:50:41 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][300/312]	eta 0:00:07 lr 0.001528	time 0.5673 (0.6111)	model_time 0.5672 (0.6056)	loss 2.8395 (3.2205)	grad_norm 1.4434 (1.9288/0.8678)	mem 24308MB
[2025-01-18 22:50:47 internimage_s_1k_224] (main.py 510): INFO Train: [173/300][310/312]	eta 0:00:01 lr 0.001528	time 0.5688 (0.6106)	model_time 0.5687 (0.6053)	loss 2.4702 (3.2194)	grad_norm 1.7217 (1.9555/0.8742)	mem 24308MB
[2025-01-18 22:50:47 internimage_s_1k_224] (main.py 519): INFO EPOCH 173 training takes 0:03:10
[2025-01-18 22:50:47 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_173.pth saving......
[2025-01-18 22:50:49 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_173.pth saved !!!
[2025-01-18 22:50:57 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.536 (7.536)	Loss 0.8251 (0.8251)	Acc@1 83.301 (83.301)	Acc@5 96.924 (96.924)	Mem 24308MB
[2025-01-18 22:51:00 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.993)	Loss 1.0589 (0.9181)	Acc@1 76.538 (80.462)	Acc@5 94.385 (95.452)	Mem 24308MB
[2025-01-18 22:51:00 internimage_s_1k_224] (main.py 575): INFO [Epoch:173] * Acc@1 80.364 Acc@5 95.513
[2025-01-18 22:51:00 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.4%
[2025-01-18 22:51:00 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 22:51:02 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 22:51:02 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.36%
[2025-01-18 22:51:10 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.492 (7.492)	Loss 0.7072 (0.7072)	Acc@1 84.058 (84.058)	Acc@5 97.510 (97.510)	Mem 24308MB
[2025-01-18 22:51:13 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.986)	Loss 0.9863 (0.8241)	Acc@1 76.294 (81.032)	Acc@5 94.141 (95.752)	Mem 24308MB
[2025-01-18 22:51:13 internimage_s_1k_224] (main.py 575): INFO [Epoch:173] * Acc@1 80.924 Acc@5 95.787
[2025-01-18 22:51:13 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 80.9%
[2025-01-18 22:51:13 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 22:51:15 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 22:51:15 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.92%
[2025-01-18 22:51:17 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][0/312]	eta 0:10:35 lr 0.001528	time 2.0356 (2.0356)	model_time 0.6121 (0.6121)	loss 2.8363 (2.8363)	grad_norm 3.6846 (3.6846/0.0000)	mem 24308MB
[2025-01-18 22:51:24 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][10/312]	eta 0:03:45 lr 0.001527	time 0.5808 (0.7460)	model_time 0.5806 (0.6163)	loss 3.3407 (3.2262)	grad_norm 2.9057 (2.3137/0.9295)	mem 24308MB
[2025-01-18 22:51:30 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][20/312]	eta 0:03:19 lr 0.001526	time 0.5923 (0.6849)	model_time 0.5922 (0.6168)	loss 2.3634 (3.2148)	grad_norm 1.3290 (1.9837/0.8660)	mem 24308MB
[2025-01-18 22:51:36 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][30/312]	eta 0:03:06 lr 0.001526	time 0.6752 (0.6624)	model_time 0.6748 (0.6162)	loss 2.1326 (3.1921)	grad_norm 1.1763 (2.1285/1.0777)	mem 24308MB
[2025-01-18 22:51:42 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][40/312]	eta 0:02:56 lr 0.001525	time 0.6357 (0.6491)	model_time 0.6355 (0.6141)	loss 2.7612 (3.2165)	grad_norm 1.7486 (2.2984/1.2031)	mem 24308MB
[2025-01-18 22:51:48 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][50/312]	eta 0:02:47 lr 0.001524	time 0.5846 (0.6392)	model_time 0.5844 (0.6110)	loss 3.5692 (3.2054)	grad_norm 1.8760 (2.2118/1.1182)	mem 24308MB
[2025-01-18 22:51:54 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][60/312]	eta 0:02:40 lr 0.001524	time 0.5729 (0.6351)	model_time 0.5727 (0.6114)	loss 3.2925 (3.1682)	grad_norm 0.9382 (2.1515/1.0760)	mem 24308MB
[2025-01-18 22:52:00 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][70/312]	eta 0:02:32 lr 0.001523	time 0.5937 (0.6298)	model_time 0.5935 (0.6094)	loss 3.2489 (3.1311)	grad_norm 0.7509 (2.0814/1.0392)	mem 24308MB
[2025-01-18 22:52:06 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][80/312]	eta 0:02:25 lr 0.001522	time 0.5879 (0.6258)	model_time 0.5875 (0.6079)	loss 2.0207 (3.1146)	grad_norm 2.5144 (2.1305/1.0614)	mem 24308MB
[2025-01-18 22:52:12 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][90/312]	eta 0:02:18 lr 0.001522	time 0.5946 (0.6228)	model_time 0.5942 (0.6068)	loss 3.6655 (3.1348)	grad_norm 1.0376 (2.1772/1.0815)	mem 24308MB
[2025-01-18 22:52:18 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][100/312]	eta 0:02:11 lr 0.001521	time 0.5965 (0.6194)	model_time 0.5963 (0.6049)	loss 3.9024 (3.1696)	grad_norm 1.8695 (2.1142/1.0551)	mem 24308MB
[2025-01-18 22:52:24 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][110/312]	eta 0:02:04 lr 0.001521	time 0.5837 (0.6181)	model_time 0.5832 (0.6049)	loss 3.5182 (3.1767)	grad_norm 2.2191 (2.1105/1.0346)	mem 24308MB
[2025-01-18 22:52:30 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][120/312]	eta 0:01:58 lr 0.001520	time 0.5750 (0.6195)	model_time 0.5749 (0.6074)	loss 2.0161 (3.1386)	grad_norm 0.7425 (2.0670/1.0117)	mem 24308MB
[2025-01-18 22:52:37 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][130/312]	eta 0:01:52 lr 0.001519	time 0.5877 (0.6197)	model_time 0.5876 (0.6085)	loss 3.0932 (3.1413)	grad_norm 1.7350 (2.0435/0.9909)	mem 24308MB
[2025-01-18 22:52:43 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][140/312]	eta 0:01:46 lr 0.001519	time 0.6488 (0.6203)	model_time 0.6483 (0.6099)	loss 3.7218 (3.1404)	grad_norm 1.0472 (2.0048/0.9684)	mem 24308MB
[2025-01-18 22:52:49 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][150/312]	eta 0:01:40 lr 0.001518	time 0.5779 (0.6189)	model_time 0.5775 (0.6091)	loss 2.9111 (3.1562)	grad_norm 1.4028 (1.9754/0.9460)	mem 24308MB
[2025-01-18 22:52:55 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][160/312]	eta 0:01:34 lr 0.001517	time 0.5937 (0.6186)	model_time 0.5935 (0.6094)	loss 2.6720 (3.1392)	grad_norm 1.3606 (1.9383/0.9294)	mem 24308MB
[2025-01-18 22:53:01 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][170/312]	eta 0:01:27 lr 0.001517	time 0.5957 (0.6183)	model_time 0.5952 (0.6096)	loss 2.4364 (3.1419)	grad_norm 1.6405 (1.9179/0.9090)	mem 24308MB
[2025-01-18 22:53:07 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][180/312]	eta 0:01:21 lr 0.001516	time 0.5769 (0.6180)	model_time 0.5768 (0.6098)	loss 3.1199 (3.1412)	grad_norm 3.6465 (1.9405/0.9141)	mem 24308MB
[2025-01-18 22:53:13 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][190/312]	eta 0:01:15 lr 0.001515	time 0.5825 (0.6165)	model_time 0.5823 (0.6087)	loss 3.8115 (3.1611)	grad_norm 1.7113 (1.9658/0.9156)	mem 24308MB
[2025-01-18 22:53:19 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][200/312]	eta 0:01:09 lr 0.001515	time 0.6077 (0.6161)	model_time 0.6076 (0.6087)	loss 3.4806 (3.1548)	grad_norm 2.3653 (1.9480/0.8990)	mem 24308MB
[2025-01-18 22:53:25 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][210/312]	eta 0:01:02 lr 0.001514	time 0.5834 (0.6154)	model_time 0.5829 (0.6083)	loss 2.8588 (3.1607)	grad_norm 1.4864 (1.9294/0.8856)	mem 24308MB
[2025-01-18 22:53:31 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][220/312]	eta 0:00:56 lr 0.001513	time 0.5926 (0.6144)	model_time 0.5922 (0.6076)	loss 3.5930 (3.1658)	grad_norm 5.2245 (1.9689/0.9321)	mem 24308MB
[2025-01-18 22:53:37 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][230/312]	eta 0:00:50 lr 0.001513	time 0.7155 (0.6140)	model_time 0.7151 (0.6074)	loss 1.8713 (3.1662)	grad_norm 2.5931 (1.9593/0.9208)	mem 24308MB
[2025-01-18 22:53:43 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][240/312]	eta 0:00:44 lr 0.001512	time 0.5776 (0.6135)	model_time 0.5774 (0.6073)	loss 2.8893 (3.1693)	grad_norm 1.1529 (1.9395/0.9116)	mem 24308MB
[2025-01-18 22:53:50 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][250/312]	eta 0:00:38 lr 0.001512	time 0.5915 (0.6143)	model_time 0.5914 (0.6083)	loss 3.1219 (3.1632)	grad_norm 0.9776 (1.9156/0.9074)	mem 24308MB
[2025-01-18 22:53:56 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][260/312]	eta 0:00:31 lr 0.001511	time 0.5905 (0.6143)	model_time 0.5903 (0.6085)	loss 3.4596 (3.1654)	grad_norm 2.4602 (1.9157/0.8999)	mem 24308MB
[2025-01-18 22:54:02 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][270/312]	eta 0:00:25 lr 0.001510	time 0.5779 (0.6141)	model_time 0.5778 (0.6085)	loss 3.3816 (3.1687)	grad_norm 0.9608 (1.9301/0.9059)	mem 24308MB
[2025-01-18 22:54:08 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][280/312]	eta 0:00:19 lr 0.001510	time 0.5780 (0.6144)	model_time 0.5776 (0.6090)	loss 2.9628 (3.1768)	grad_norm 2.1222 (1.9207/0.8933)	mem 24308MB
[2025-01-18 22:54:14 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][290/312]	eta 0:00:13 lr 0.001509	time 0.5815 (0.6143)	model_time 0.5814 (0.6091)	loss 2.3664 (3.1826)	grad_norm 2.9512 (1.9282/0.8865)	mem 24308MB
[2025-01-18 22:54:20 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][300/312]	eta 0:00:07 lr 0.001508	time 0.5738 (0.6141)	model_time 0.5737 (0.6090)	loss 2.8035 (3.1848)	grad_norm 1.5661 (1.9199/0.8770)	mem 24308MB
[2025-01-18 22:54:26 internimage_s_1k_224] (main.py 510): INFO Train: [174/300][310/312]	eta 0:00:01 lr 0.001508	time 0.5761 (0.6127)	model_time 0.5760 (0.6078)	loss 3.1403 (3.1944)	grad_norm 2.5360 (1.9193/0.8801)	mem 24308MB
[2025-01-18 22:54:27 internimage_s_1k_224] (main.py 519): INFO EPOCH 174 training takes 0:03:11
[2025-01-18 22:54:27 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_174.pth saving......
[2025-01-18 22:54:28 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_174.pth saved !!!
[2025-01-18 22:54:36 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.446 (7.446)	Loss 0.8184 (0.8184)	Acc@1 84.033 (84.033)	Acc@5 96.924 (96.924)	Mem 24308MB
[2025-01-18 22:54:39 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.984)	Loss 1.0935 (0.9305)	Acc@1 76.465 (80.495)	Acc@5 94.019 (95.559)	Mem 24308MB
[2025-01-18 22:54:39 internimage_s_1k_224] (main.py 575): INFO [Epoch:174] * Acc@1 80.422 Acc@5 95.593
[2025-01-18 22:54:39 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.4%
[2025-01-18 22:54:39 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 22:54:41 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 22:54:41 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.42%
[2025-01-18 22:54:49 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.464 (7.464)	Loss 0.7075 (0.7075)	Acc@1 84.106 (84.106)	Acc@5 97.461 (97.461)	Mem 24308MB
[2025-01-18 22:54:52 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.997)	Loss 0.9847 (0.8235)	Acc@1 76.343 (81.090)	Acc@5 94.214 (95.774)	Mem 24308MB
[2025-01-18 22:54:53 internimage_s_1k_224] (main.py 575): INFO [Epoch:174] * Acc@1 80.974 Acc@5 95.807
[2025-01-18 22:54:53 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.0%
[2025-01-18 22:54:53 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 22:54:55 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 22:54:55 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 80.97%
[2025-01-18 22:54:57 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][0/312]	eta 0:10:17 lr 0.001508	time 1.9799 (1.9799)	model_time 0.5940 (0.5940)	loss 3.9072 (3.9072)	grad_norm 1.8127 (1.8127/0.0000)	mem 24308MB
[2025-01-18 22:55:03 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][10/312]	eta 0:03:41 lr 0.001507	time 0.6228 (0.7340)	model_time 0.6227 (0.6077)	loss 2.4813 (3.0614)	grad_norm 2.5959 (2.3968/0.8593)	mem 24308MB
[2025-01-18 22:55:09 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][20/312]	eta 0:03:16 lr 0.001506	time 0.5849 (0.6719)	model_time 0.5844 (0.6056)	loss 3.2247 (3.1712)	grad_norm 1.0085 (2.0623/0.8367)	mem 24308MB
[2025-01-18 22:55:15 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][30/312]	eta 0:03:02 lr 0.001506	time 0.5737 (0.6456)	model_time 0.5736 (0.6006)	loss 4.0398 (3.2465)	grad_norm 3.4162 (2.0766/0.8935)	mem 24308MB
[2025-01-18 22:55:21 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][40/312]	eta 0:02:52 lr 0.001505	time 0.5884 (0.6355)	model_time 0.5879 (0.6014)	loss 2.9286 (3.1938)	grad_norm 1.7894 (1.9993/0.8228)	mem 24308MB
[2025-01-18 22:55:27 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][50/312]	eta 0:02:45 lr 0.001504	time 0.5750 (0.6327)	model_time 0.5748 (0.6052)	loss 3.8250 (3.1622)	grad_norm 1.6385 (1.9318/0.7929)	mem 24308MB
[2025-01-18 22:55:33 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][60/312]	eta 0:02:38 lr 0.001504	time 0.7020 (0.6299)	model_time 0.7016 (0.6068)	loss 3.0034 (3.1678)	grad_norm 1.4924 (1.9870/0.8867)	mem 24308MB
[2025-01-18 22:55:39 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][70/312]	eta 0:02:31 lr 0.001503	time 0.5877 (0.6268)	model_time 0.5873 (0.6069)	loss 3.3503 (3.1494)	grad_norm 1.6171 (2.0239/0.8558)	mem 24308MB
[2025-01-18 22:55:46 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][80/312]	eta 0:02:24 lr 0.001502	time 0.5874 (0.6241)	model_time 0.5873 (0.6067)	loss 2.4578 (3.1755)	grad_norm 1.7304 (1.9628/0.8338)	mem 24308MB
[2025-01-18 22:55:52 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][90/312]	eta 0:02:18 lr 0.001502	time 0.5774 (0.6225)	model_time 0.5772 (0.6070)	loss 2.6382 (3.1726)	grad_norm 2.2624 (1.9807/0.8166)	mem 24308MB
[2025-01-18 22:55:58 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][100/312]	eta 0:02:11 lr 0.001501	time 0.5812 (0.6215)	model_time 0.5807 (0.6074)	loss 3.8346 (3.1435)	grad_norm 0.9114 (2.0194/0.8694)	mem 24308MB
[2025-01-18 22:56:04 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][110/312]	eta 0:02:05 lr 0.001500	time 0.5799 (0.6199)	model_time 0.5794 (0.6071)	loss 3.3312 (3.1218)	grad_norm 2.4996 (2.0398/0.9068)	mem 24308MB
[2025-01-18 22:56:10 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][120/312]	eta 0:01:58 lr 0.001500	time 0.5902 (0.6173)	model_time 0.5896 (0.6055)	loss 2.7651 (3.1321)	grad_norm 1.0115 (2.0798/0.9286)	mem 24308MB
[2025-01-18 22:56:16 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][130/312]	eta 0:01:52 lr 0.001499	time 0.5783 (0.6169)	model_time 0.5781 (0.6059)	loss 3.6069 (3.1289)	grad_norm 2.4546 (2.0757/0.9172)	mem 24308MB
[2025-01-18 22:56:22 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][140/312]	eta 0:01:45 lr 0.001499	time 0.5862 (0.6161)	model_time 0.5860 (0.6059)	loss 2.6080 (3.1206)	grad_norm 2.4512 (2.0689/0.9039)	mem 24308MB
[2025-01-18 22:56:28 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][150/312]	eta 0:01:39 lr 0.001498	time 0.5746 (0.6146)	model_time 0.5744 (0.6051)	loss 4.0016 (3.1260)	grad_norm 1.1065 (2.0640/0.8894)	mem 24308MB
[2025-01-18 22:56:34 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][160/312]	eta 0:01:33 lr 0.001497	time 0.5915 (0.6136)	model_time 0.5914 (0.6046)	loss 3.3023 (3.1259)	grad_norm 3.5256 (2.0875/0.8918)	mem 24308MB
[2025-01-18 22:56:40 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][170/312]	eta 0:01:27 lr 0.001497	time 0.6771 (0.6143)	model_time 0.6769 (0.6059)	loss 3.1475 (3.1143)	grad_norm 3.0144 (2.1051/0.9142)	mem 24308MB
[2025-01-18 22:56:46 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][180/312]	eta 0:01:21 lr 0.001496	time 0.6918 (0.6141)	model_time 0.6917 (0.6061)	loss 3.8365 (3.1266)	grad_norm 2.5247 (2.1273/0.9215)	mem 24308MB
[2025-01-18 22:56:52 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][190/312]	eta 0:01:14 lr 0.001495	time 0.5914 (0.6144)	model_time 0.5909 (0.6068)	loss 3.1792 (3.1328)	grad_norm 1.6333 (2.0833/0.9175)	mem 24308MB
[2025-01-18 22:56:58 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][200/312]	eta 0:01:08 lr 0.001495	time 0.6752 (0.6137)	model_time 0.6751 (0.6065)	loss 3.4710 (3.1375)	grad_norm 0.9757 (2.0426/0.9146)	mem 24308MB
[2025-01-18 22:57:04 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][210/312]	eta 0:01:02 lr 0.001494	time 0.5819 (0.6138)	model_time 0.5817 (0.6069)	loss 3.2433 (3.1384)	grad_norm 1.3153 (2.0350/0.9043)	mem 24308MB
[2025-01-18 22:57:11 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][220/312]	eta 0:00:56 lr 0.001493	time 0.5851 (0.6135)	model_time 0.5847 (0.6069)	loss 3.9491 (3.1416)	grad_norm 3.4923 (2.0245/0.9019)	mem 24308MB
[2025-01-18 22:57:17 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][230/312]	eta 0:00:50 lr 0.001493	time 0.6205 (0.6137)	model_time 0.6200 (0.6074)	loss 3.9083 (3.1453)	grad_norm 1.8932 (2.0338/0.9009)	mem 24308MB
[2025-01-18 22:57:23 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][240/312]	eta 0:00:44 lr 0.001492	time 0.5877 (0.6127)	model_time 0.5875 (0.6066)	loss 2.1561 (3.1396)	grad_norm 2.7713 (2.0111/0.8966)	mem 24308MB
[2025-01-18 22:57:29 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][250/312]	eta 0:00:37 lr 0.001492	time 0.5771 (0.6125)	model_time 0.5767 (0.6066)	loss 3.5596 (3.1562)	grad_norm 1.1095 (2.0109/0.8928)	mem 24308MB
[2025-01-18 22:57:35 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][260/312]	eta 0:00:31 lr 0.001491	time 0.5897 (0.6120)	model_time 0.5893 (0.6063)	loss 3.9983 (3.1492)	grad_norm 1.7171 (1.9976/0.8827)	mem 24308MB
[2025-01-18 22:57:41 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][270/312]	eta 0:00:25 lr 0.001490	time 0.5840 (0.6112)	model_time 0.5838 (0.6057)	loss 3.3545 (3.1594)	grad_norm 1.6865 (2.0068/0.8972)	mem 24308MB
[2025-01-18 22:57:47 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][280/312]	eta 0:00:19 lr 0.001490	time 0.5901 (0.6106)	model_time 0.5897 (0.6053)	loss 3.7214 (3.1693)	grad_norm 2.3937 (2.0314/0.9148)	mem 24308MB
[2025-01-18 22:57:53 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][290/312]	eta 0:00:13 lr 0.001489	time 0.6713 (0.6109)	model_time 0.6712 (0.6058)	loss 3.4191 (3.1680)	grad_norm 2.9707 (2.0314/0.9094)	mem 24308MB
[2025-01-18 22:57:59 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][300/312]	eta 0:00:07 lr 0.001488	time 0.5687 (0.6103)	model_time 0.5686 (0.6054)	loss 3.4567 (3.1809)	grad_norm 1.1327 (2.0168/0.9011)	mem 24308MB
[2025-01-18 22:58:05 internimage_s_1k_224] (main.py 510): INFO Train: [175/300][310/312]	eta 0:00:01 lr 0.001488	time 0.5605 (0.6106)	model_time 0.5604 (0.6058)	loss 2.7806 (3.1795)	grad_norm 1.8327 (1.9935/0.8921)	mem 24308MB
[2025-01-18 22:58:06 internimage_s_1k_224] (main.py 519): INFO EPOCH 175 training takes 0:03:10
[2025-01-18 22:58:06 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_175.pth saving......
[2025-01-18 22:58:07 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_175.pth saved !!!
[2025-01-18 22:58:15 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.819 (7.819)	Loss 0.8109 (0.8109)	Acc@1 82.983 (82.983)	Acc@5 96.924 (96.924)	Mem 24308MB
[2025-01-18 22:58:19 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.024)	Loss 1.0717 (0.9250)	Acc@1 77.271 (80.635)	Acc@5 93.921 (95.526)	Mem 24308MB
[2025-01-18 22:58:19 internimage_s_1k_224] (main.py 575): INFO [Epoch:175] * Acc@1 80.516 Acc@5 95.601
[2025-01-18 22:58:19 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.5%
[2025-01-18 22:58:19 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 22:58:21 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 22:58:21 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.52%
[2025-01-18 22:58:28 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.606 (7.606)	Loss 0.7077 (0.7077)	Acc@1 84.204 (84.204)	Acc@5 97.437 (97.437)	Mem 24308MB
[2025-01-18 22:58:32 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.991)	Loss 0.9830 (0.8228)	Acc@1 76.416 (81.152)	Acc@5 94.189 (95.774)	Mem 24308MB
[2025-01-18 22:58:32 internimage_s_1k_224] (main.py 575): INFO [Epoch:175] * Acc@1 81.028 Acc@5 95.805
[2025-01-18 22:58:32 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.0%
[2025-01-18 22:58:32 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 22:58:34 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 22:58:34 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.03%
[2025-01-18 22:58:37 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][0/312]	eta 0:13:00 lr 0.001488	time 2.5027 (2.5027)	model_time 0.6006 (0.6006)	loss 3.8398 (3.8398)	grad_norm 4.0099 (4.0099/0.0000)	mem 24308MB
[2025-01-18 22:58:43 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][10/312]	eta 0:03:51 lr 0.001487	time 0.5790 (0.7663)	model_time 0.5788 (0.5931)	loss 3.8569 (3.1354)	grad_norm 3.4938 (3.1097/0.7753)	mem 24308MB
[2025-01-18 22:58:49 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][20/312]	eta 0:03:24 lr 0.001486	time 0.6065 (0.7010)	model_time 0.6061 (0.6101)	loss 3.3995 (3.1589)	grad_norm 1.7163 (2.5579/1.0078)	mem 24308MB
[2025-01-18 22:58:55 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][30/312]	eta 0:03:09 lr 0.001486	time 0.6831 (0.6725)	model_time 0.6825 (0.6108)	loss 3.1211 (3.2078)	grad_norm 2.4492 (2.3353/0.9549)	mem 24308MB
[2025-01-18 22:59:01 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][40/312]	eta 0:02:58 lr 0.001485	time 0.5782 (0.6553)	model_time 0.5780 (0.6082)	loss 3.1807 (3.1582)	grad_norm 1.4502 (2.2760/0.9010)	mem 24308MB
[2025-01-18 22:59:07 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][50/312]	eta 0:02:48 lr 0.001484	time 0.5844 (0.6427)	model_time 0.5839 (0.6048)	loss 3.4822 (3.1664)	grad_norm 1.3777 (2.2297/0.8930)	mem 24308MB
[2025-01-18 22:59:13 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][60/312]	eta 0:02:40 lr 0.001484	time 0.5917 (0.6383)	model_time 0.5915 (0.6066)	loss 3.6537 (3.1237)	grad_norm 1.8909 (2.1980/0.8568)	mem 24308MB
[2025-01-18 22:59:19 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][70/312]	eta 0:02:33 lr 0.001483	time 0.5860 (0.6331)	model_time 0.5856 (0.6058)	loss 3.3992 (3.1201)	grad_norm 0.8365 (2.0847/0.8670)	mem 24308MB
[2025-01-18 22:59:25 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][80/312]	eta 0:02:25 lr 0.001482	time 0.5926 (0.6278)	model_time 0.5925 (0.6038)	loss 3.2618 (3.1179)	grad_norm 1.9411 (2.0803/0.8592)	mem 24308MB
[2025-01-18 22:59:31 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][90/312]	eta 0:02:18 lr 0.001482	time 0.5727 (0.6250)	model_time 0.5726 (0.6036)	loss 3.0538 (3.1115)	grad_norm 0.8825 (2.0013/0.8516)	mem 24308MB
[2025-01-18 22:59:38 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][100/312]	eta 0:02:12 lr 0.001481	time 0.6525 (0.6243)	model_time 0.6520 (0.6050)	loss 2.3772 (3.1080)	grad_norm 4.1750 (1.9889/0.8593)	mem 24308MB
[2025-01-18 22:59:44 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][110/312]	eta 0:02:05 lr 0.001481	time 0.5719 (0.6220)	model_time 0.5717 (0.6044)	loss 3.5498 (3.1277)	grad_norm 2.3760 (2.0374/0.8718)	mem 24308MB
[2025-01-18 22:59:50 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][120/312]	eta 0:01:59 lr 0.001480	time 0.5765 (0.6232)	model_time 0.5763 (0.6070)	loss 4.1304 (3.1408)	grad_norm 2.1133 (2.0402/0.8394)	mem 24308MB
[2025-01-18 22:59:56 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][130/312]	eta 0:01:53 lr 0.001479	time 0.5961 (0.6211)	model_time 0.5960 (0.6061)	loss 3.0954 (3.1299)	grad_norm 1.4811 (2.0480/0.8398)	mem 24308MB
[2025-01-18 23:00:02 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][140/312]	eta 0:01:46 lr 0.001479	time 0.6765 (0.6217)	model_time 0.6763 (0.6077)	loss 3.6931 (3.1385)	grad_norm 1.2074 (2.0104/0.8239)	mem 24308MB
[2025-01-18 23:00:08 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][150/312]	eta 0:01:40 lr 0.001478	time 0.5732 (0.6204)	model_time 0.5730 (0.6073)	loss 2.9577 (3.1463)	grad_norm 1.6457 (2.0388/0.8591)	mem 24308MB
[2025-01-18 23:00:14 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][160/312]	eta 0:01:34 lr 0.001477	time 0.5766 (0.6204)	model_time 0.5764 (0.6081)	loss 3.0598 (3.1617)	grad_norm 1.3870 (2.0110/0.8446)	mem 24308MB
[2025-01-18 23:00:20 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][170/312]	eta 0:01:27 lr 0.001477	time 0.6098 (0.6184)	model_time 0.6094 (0.6069)	loss 2.9766 (3.1589)	grad_norm 1.5332 (1.9749/0.8388)	mem 24308MB
[2025-01-18 23:00:26 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][180/312]	eta 0:01:21 lr 0.001476	time 0.7200 (0.6180)	model_time 0.7198 (0.6071)	loss 3.0481 (3.1640)	grad_norm 1.5739 (1.9875/0.8274)	mem 24308MB
[2025-01-18 23:00:32 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][190/312]	eta 0:01:15 lr 0.001475	time 0.5862 (0.6170)	model_time 0.5860 (0.6065)	loss 4.1652 (3.1640)	grad_norm 2.1498 (2.0106/0.8363)	mem 24308MB
[2025-01-18 23:00:38 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][200/312]	eta 0:01:08 lr 0.001475	time 0.5854 (0.6156)	model_time 0.5852 (0.6056)	loss 3.1021 (3.1627)	grad_norm 3.0556 (2.0245/0.8458)	mem 24308MB
[2025-01-18 23:00:44 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][210/312]	eta 0:01:02 lr 0.001474	time 0.5869 (0.6147)	model_time 0.5867 (0.6051)	loss 3.3091 (3.1686)	grad_norm 1.4492 (2.0319/0.8539)	mem 24308MB
[2025-01-18 23:00:50 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][220/312]	eta 0:00:56 lr 0.001473	time 0.6782 (0.6149)	model_time 0.6776 (0.6056)	loss 2.8928 (3.1751)	grad_norm 2.9994 (2.0449/0.8582)	mem 24308MB
[2025-01-18 23:00:56 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][230/312]	eta 0:00:50 lr 0.001473	time 0.5983 (0.6144)	model_time 0.5982 (0.6055)	loss 2.7689 (3.1763)	grad_norm 3.2432 (2.0640/0.8675)	mem 24308MB
[2025-01-18 23:01:03 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][240/312]	eta 0:00:44 lr 0.001472	time 0.6919 (0.6147)	model_time 0.6918 (0.6062)	loss 2.8207 (3.1740)	grad_norm 1.6416 (2.0418/0.8607)	mem 24308MB
[2025-01-18 23:01:09 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][250/312]	eta 0:00:38 lr 0.001472	time 0.5880 (0.6141)	model_time 0.5878 (0.6060)	loss 2.4121 (3.1720)	grad_norm 2.6678 (2.0480/0.8495)	mem 24308MB
[2025-01-18 23:01:15 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][260/312]	eta 0:00:31 lr 0.001471	time 0.6611 (0.6151)	model_time 0.6610 (0.6072)	loss 3.6061 (3.1737)	grad_norm 1.1078 (2.0249/0.8440)	mem 24308MB
[2025-01-18 23:01:21 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][270/312]	eta 0:00:25 lr 0.001470	time 0.5742 (0.6148)	model_time 0.5740 (0.6072)	loss 3.5568 (3.1775)	grad_norm 2.1297 (2.0164/0.8324)	mem 24308MB
[2025-01-18 23:01:27 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][280/312]	eta 0:00:19 lr 0.001470	time 0.6750 (0.6150)	model_time 0.6746 (0.6076)	loss 2.6389 (3.1783)	grad_norm 2.4507 (2.0162/0.8291)	mem 24308MB
[2025-01-18 23:01:33 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][290/312]	eta 0:00:13 lr 0.001469	time 0.6061 (0.6142)	model_time 0.6059 (0.6071)	loss 3.8448 (3.1865)	grad_norm 1.0101 (1.9949/0.8244)	mem 24308MB
[2025-01-18 23:01:39 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][300/312]	eta 0:00:07 lr 0.001468	time 0.5691 (0.6134)	model_time 0.5690 (0.6065)	loss 2.8940 (3.1862)	grad_norm 1.6265 (1.9779/0.8198)	mem 24308MB
[2025-01-18 23:01:45 internimage_s_1k_224] (main.py 510): INFO Train: [176/300][310/312]	eta 0:00:01 lr 0.001468	time 0.5674 (0.6126)	model_time 0.5673 (0.6060)	loss 3.0065 (3.1920)	grad_norm 2.3007 (1.9576/0.7985)	mem 24308MB
[2025-01-18 23:01:46 internimage_s_1k_224] (main.py 519): INFO EPOCH 176 training takes 0:03:11
[2025-01-18 23:01:46 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_176.pth saving......
[2025-01-18 23:01:47 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_176.pth saved !!!
[2025-01-18 23:01:55 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.520 (7.520)	Loss 0.7927 (0.7927)	Acc@1 83.936 (83.936)	Acc@5 97.241 (97.241)	Mem 24308MB
[2025-01-18 23:01:59 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.003)	Loss 1.0661 (0.9200)	Acc@1 77.124 (80.733)	Acc@5 93.701 (95.597)	Mem 24308MB
[2025-01-18 23:01:59 internimage_s_1k_224] (main.py 575): INFO [Epoch:176] * Acc@1 80.630 Acc@5 95.609
[2025-01-18 23:01:59 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.6%
[2025-01-18 23:01:59 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 23:02:01 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 23:02:01 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.63%
[2025-01-18 23:02:08 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.699 (7.699)	Loss 0.7080 (0.7080)	Acc@1 84.229 (84.229)	Acc@5 97.534 (97.534)	Mem 24308MB
[2025-01-18 23:02:12 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.016)	Loss 0.9814 (0.8221)	Acc@1 76.440 (81.208)	Acc@5 94.189 (95.807)	Mem 24308MB
[2025-01-18 23:02:12 internimage_s_1k_224] (main.py 575): INFO [Epoch:176] * Acc@1 81.080 Acc@5 95.837
[2025-01-18 23:02:12 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.1%
[2025-01-18 23:02:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 23:02:15 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 23:02:15 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.08%
[2025-01-18 23:02:17 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][0/312]	eta 0:10:48 lr 0.001468	time 2.0784 (2.0784)	model_time 0.5918 (0.5918)	loss 3.2304 (3.2304)	grad_norm 0.8108 (0.8108/0.0000)	mem 24308MB
[2025-01-18 23:02:23 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][10/312]	eta 0:03:38 lr 0.001467	time 0.5793 (0.7222)	model_time 0.5792 (0.5869)	loss 2.9601 (3.2158)	grad_norm 2.4615 (1.4553/0.4645)	mem 24308MB
[2025-01-18 23:02:28 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][20/312]	eta 0:03:12 lr 0.001466	time 0.6165 (0.6605)	model_time 0.6161 (0.5894)	loss 2.5829 (3.1031)	grad_norm 2.0458 (1.6130/0.5580)	mem 24308MB
[2025-01-18 23:02:35 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][30/312]	eta 0:03:03 lr 0.001466	time 0.6734 (0.6499)	model_time 0.6732 (0.6016)	loss 3.0066 (3.1903)	grad_norm 0.9337 (1.6379/0.5675)	mem 24308MB
[2025-01-18 23:02:41 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][40/312]	eta 0:02:54 lr 0.001465	time 0.5760 (0.6417)	model_time 0.5756 (0.6047)	loss 2.7413 (3.1224)	grad_norm 2.1329 (1.5763/0.5788)	mem 24308MB
[2025-01-18 23:02:47 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][50/312]	eta 0:02:46 lr 0.001464	time 0.6994 (0.6366)	model_time 0.6992 (0.6067)	loss 3.9821 (3.1536)	grad_norm 1.3067 (1.6160/0.5927)	mem 24308MB
[2025-01-18 23:02:53 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][60/312]	eta 0:02:39 lr 0.001464	time 0.6049 (0.6317)	model_time 0.6047 (0.6067)	loss 3.3604 (3.1410)	grad_norm 1.4903 (1.5865/0.5505)	mem 24308MB
[2025-01-18 23:02:59 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][70/312]	eta 0:02:32 lr 0.001463	time 0.6135 (0.6298)	model_time 0.6131 (0.6083)	loss 2.6210 (3.1416)	grad_norm 3.1824 (1.6011/0.5617)	mem 24308MB
[2025-01-18 23:03:05 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][80/312]	eta 0:02:25 lr 0.001462	time 0.5890 (0.6283)	model_time 0.5888 (0.6094)	loss 3.6589 (3.1570)	grad_norm 2.3469 (1.6591/0.6138)	mem 24308MB
[2025-01-18 23:03:12 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][90/312]	eta 0:02:19 lr 0.001462	time 0.6004 (0.6271)	model_time 0.6000 (0.6102)	loss 2.9126 (3.1630)	grad_norm 1.2217 (1.6334/0.5967)	mem 24308MB
[2025-01-18 23:03:18 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][100/312]	eta 0:02:12 lr 0.001461	time 0.5763 (0.6247)	model_time 0.5761 (0.6095)	loss 3.2900 (3.1549)	grad_norm 2.3656 (1.6293/0.5954)	mem 24308MB
[2025-01-18 23:03:24 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][110/312]	eta 0:02:05 lr 0.001461	time 0.5802 (0.6220)	model_time 0.5797 (0.6081)	loss 3.2651 (3.1762)	grad_norm 2.5546 (1.6944/0.7158)	mem 24308MB
[2025-01-18 23:03:30 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][120/312]	eta 0:01:59 lr 0.001460	time 0.5816 (0.6210)	model_time 0.5814 (0.6082)	loss 3.2587 (3.1796)	grad_norm 1.1560 (1.7112/0.7357)	mem 24308MB
[2025-01-18 23:03:36 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][130/312]	eta 0:01:52 lr 0.001459	time 0.5949 (0.6190)	model_time 0.5945 (0.6072)	loss 3.0900 (3.1843)	grad_norm 1.0250 (1.7093/0.7253)	mem 24308MB
[2025-01-18 23:03:42 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][140/312]	eta 0:01:46 lr 0.001459	time 0.5835 (0.6167)	model_time 0.5830 (0.6057)	loss 3.3405 (3.1907)	grad_norm 3.4218 (1.7363/0.7500)	mem 24308MB
[2025-01-18 23:03:48 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][150/312]	eta 0:01:39 lr 0.001458	time 0.5950 (0.6165)	model_time 0.5949 (0.6062)	loss 4.3347 (3.2087)	grad_norm 1.7744 (1.7945/0.8127)	mem 24308MB
[2025-01-18 23:03:54 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][160/312]	eta 0:01:33 lr 0.001457	time 0.5795 (0.6165)	model_time 0.5786 (0.6067)	loss 2.7463 (3.1997)	grad_norm 0.9657 (1.8080/0.8123)	mem 24308MB
[2025-01-18 23:04:00 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][170/312]	eta 0:01:27 lr 0.001457	time 0.6769 (0.6169)	model_time 0.6765 (0.6077)	loss 3.1457 (3.2017)	grad_norm 2.6097 (1.8053/0.8055)	mem 24308MB
[2025-01-18 23:04:06 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][180/312]	eta 0:01:21 lr 0.001456	time 0.5966 (0.6165)	model_time 0.5965 (0.6078)	loss 2.9020 (3.1906)	grad_norm 1.9040 (1.8112/0.7967)	mem 24308MB
[2025-01-18 23:04:12 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][190/312]	eta 0:01:15 lr 0.001455	time 0.5942 (0.6162)	model_time 0.5940 (0.6079)	loss 3.9552 (3.2027)	grad_norm 1.5697 (1.7967/0.7816)	mem 24308MB
[2025-01-18 23:04:19 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][200/312]	eta 0:01:09 lr 0.001455	time 0.5785 (0.6164)	model_time 0.5783 (0.6086)	loss 3.0969 (3.2126)	grad_norm 3.3599 (1.8725/0.9020)	mem 24308MB
[2025-01-18 23:04:25 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][210/312]	eta 0:01:02 lr 0.001454	time 0.5782 (0.6158)	model_time 0.5780 (0.6083)	loss 3.3371 (3.2076)	grad_norm 2.3040 (1.8990/0.9195)	mem 24308MB
[2025-01-18 23:04:31 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][220/312]	eta 0:00:56 lr 0.001454	time 0.6155 (0.6152)	model_time 0.6154 (0.6080)	loss 3.3413 (3.2090)	grad_norm 3.3660 (1.9132/0.9114)	mem 24308MB
[2025-01-18 23:04:36 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][230/312]	eta 0:00:50 lr 0.001453	time 0.5884 (0.6139)	model_time 0.5883 (0.6070)	loss 3.8140 (3.2092)	grad_norm 0.9245 (1.9123/0.9020)	mem 24308MB
[2025-01-18 23:04:43 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][240/312]	eta 0:00:44 lr 0.001452	time 0.5808 (0.6140)	model_time 0.5803 (0.6074)	loss 3.2058 (3.2033)	grad_norm 1.4853 (1.8903/0.8964)	mem 24308MB
[2025-01-18 23:04:48 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][250/312]	eta 0:00:38 lr 0.001452	time 0.5941 (0.6130)	model_time 0.5939 (0.6066)	loss 3.8979 (3.2066)	grad_norm 2.2960 (1.8810/0.8858)	mem 24308MB
[2025-01-18 23:04:54 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][260/312]	eta 0:00:31 lr 0.001451	time 0.6302 (0.6123)	model_time 0.6297 (0.6062)	loss 4.2206 (3.2173)	grad_norm 2.5580 (1.8890/0.8824)	mem 24308MB
[2025-01-18 23:05:01 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][270/312]	eta 0:00:25 lr 0.001450	time 0.5756 (0.6124)	model_time 0.5755 (0.6065)	loss 2.1815 (3.2196)	grad_norm 1.1508 (1.8840/0.8697)	mem 24308MB
[2025-01-18 23:05:07 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][280/312]	eta 0:00:19 lr 0.001450	time 0.5855 (0.6132)	model_time 0.5850 (0.6074)	loss 3.4470 (3.2106)	grad_norm 2.4265 (1.8950/0.8615)	mem 24308MB
[2025-01-18 23:05:13 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][290/312]	eta 0:00:13 lr 0.001449	time 0.6246 (0.6133)	model_time 0.6242 (0.6078)	loss 3.4820 (3.2168)	grad_norm 1.2901 (1.8947/0.8520)	mem 24308MB
[2025-01-18 23:05:19 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][300/312]	eta 0:00:07 lr 0.001448	time 0.5604 (0.6136)	model_time 0.5603 (0.6082)	loss 3.0983 (3.2216)	grad_norm 1.3738 (1.8851/0.8425)	mem 24308MB
[2025-01-18 23:05:25 internimage_s_1k_224] (main.py 510): INFO Train: [177/300][310/312]	eta 0:00:01 lr 0.001448	time 0.5699 (0.6127)	model_time 0.5697 (0.6075)	loss 2.7341 (3.2226)	grad_norm 5.6491 (1.9043/0.8689)	mem 24308MB
[2025-01-18 23:05:26 internimage_s_1k_224] (main.py 519): INFO EPOCH 177 training takes 0:03:11
[2025-01-18 23:05:26 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_177.pth saving......
[2025-01-18 23:05:28 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_177.pth saved !!!
[2025-01-18 23:05:35 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.602 (7.602)	Loss 0.7843 (0.7843)	Acc@1 83.472 (83.472)	Acc@5 97.070 (97.070)	Mem 24308MB
[2025-01-18 23:05:39 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.004)	Loss 1.0656 (0.9159)	Acc@1 76.099 (80.449)	Acc@5 94.092 (95.492)	Mem 24308MB
[2025-01-18 23:05:39 internimage_s_1k_224] (main.py 575): INFO [Epoch:177] * Acc@1 80.402 Acc@5 95.545
[2025-01-18 23:05:39 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.4%
[2025-01-18 23:05:39 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.63%
[2025-01-18 23:05:48 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.739 (8.739)	Loss 0.7080 (0.7080)	Acc@1 84.180 (84.180)	Acc@5 97.559 (97.559)	Mem 24308MB
[2025-01-18 23:05:52 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.190)	Loss 0.9799 (0.8214)	Acc@1 76.465 (81.241)	Acc@5 94.263 (95.836)	Mem 24308MB
[2025-01-18 23:05:52 internimage_s_1k_224] (main.py 575): INFO [Epoch:177] * Acc@1 81.114 Acc@5 95.863
[2025-01-18 23:05:52 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.1%
[2025-01-18 23:05:52 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 23:05:55 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 23:05:55 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.11%
[2025-01-18 23:05:57 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][0/312]	eta 0:12:26 lr 0.001448	time 2.3920 (2.3920)	model_time 0.6069 (0.6069)	loss 3.2256 (3.2256)	grad_norm 4.2111 (4.2111/0.0000)	mem 24308MB
[2025-01-18 23:06:03 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][10/312]	eta 0:03:56 lr 0.001447	time 0.5950 (0.7815)	model_time 0.5949 (0.6189)	loss 3.3315 (2.9930)	grad_norm 1.3226 (2.3855/1.1416)	mem 24308MB
[2025-01-18 23:06:10 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][20/312]	eta 0:03:24 lr 0.001446	time 0.5828 (0.7014)	model_time 0.5826 (0.6161)	loss 3.8556 (3.1710)	grad_norm 3.0284 (2.4517/0.9699)	mem 24308MB
[2025-01-18 23:06:15 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][30/312]	eta 0:03:07 lr 0.001446	time 0.6085 (0.6663)	model_time 0.6084 (0.6084)	loss 2.8577 (3.2295)	grad_norm 1.1293 (2.2699/0.9653)	mem 24308MB
[2025-01-18 23:06:21 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][40/312]	eta 0:02:56 lr 0.001445	time 0.6701 (0.6492)	model_time 0.6696 (0.6053)	loss 2.5806 (3.1531)	grad_norm 1.3936 (2.1025/0.9580)	mem 24308MB
[2025-01-18 23:06:27 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][50/312]	eta 0:02:47 lr 0.001445	time 0.5961 (0.6408)	model_time 0.5956 (0.6055)	loss 3.3913 (3.2038)	grad_norm 1.5829 (2.0379/0.8773)	mem 24308MB
[2025-01-18 23:06:33 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][60/312]	eta 0:02:39 lr 0.001444	time 0.5795 (0.6319)	model_time 0.5793 (0.6023)	loss 2.9594 (3.2048)	grad_norm 1.2447 (1.9067/0.8632)	mem 24308MB
[2025-01-18 23:06:39 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][70/312]	eta 0:02:31 lr 0.001443	time 0.5782 (0.6258)	model_time 0.5777 (0.6003)	loss 3.3259 (3.2245)	grad_norm 3.3390 (1.9590/0.9104)	mem 24308MB
[2025-01-18 23:06:45 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][80/312]	eta 0:02:24 lr 0.001443	time 0.5824 (0.6244)	model_time 0.5822 (0.6020)	loss 3.0433 (3.2229)	grad_norm 5.8710 (2.0861/1.0262)	mem 24308MB
[2025-01-18 23:06:52 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][90/312]	eta 0:02:19 lr 0.001442	time 0.6055 (0.6263)	model_time 0.6053 (0.6063)	loss 3.5546 (3.2448)	grad_norm 2.1657 (2.1607/1.0333)	mem 24308MB
[2025-01-18 23:06:58 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][100/312]	eta 0:02:12 lr 0.001441	time 0.6827 (0.6242)	model_time 0.6823 (0.6062)	loss 3.9069 (3.2411)	grad_norm 1.5795 (2.1995/1.0448)	mem 24308MB
[2025-01-18 23:07:04 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][110/312]	eta 0:02:05 lr 0.001441	time 0.5848 (0.6230)	model_time 0.5844 (0.6065)	loss 2.6018 (3.2241)	grad_norm 3.1670 (2.2332/1.0420)	mem 24308MB
[2025-01-18 23:07:10 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][120/312]	eta 0:01:59 lr 0.001440	time 0.6647 (0.6222)	model_time 0.6645 (0.6071)	loss 3.3558 (3.1945)	grad_norm 1.0532 (2.1806/1.0241)	mem 24308MB
[2025-01-18 23:07:16 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][130/312]	eta 0:01:53 lr 0.001439	time 0.6629 (0.6231)	model_time 0.6627 (0.6092)	loss 3.4624 (3.1950)	grad_norm 1.7134 (2.1285/1.0102)	mem 24308MB
[2025-01-18 23:07:23 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][140/312]	eta 0:01:47 lr 0.001439	time 0.6679 (0.6228)	model_time 0.6675 (0.6098)	loss 3.4212 (3.1859)	grad_norm 2.2930 (2.0897/0.9890)	mem 24308MB
[2025-01-18 23:07:28 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][150/312]	eta 0:01:40 lr 0.001438	time 0.5772 (0.6204)	model_time 0.5771 (0.6082)	loss 3.7443 (3.1789)	grad_norm 1.5119 (2.0810/0.9776)	mem 24308MB
[2025-01-18 23:07:34 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][160/312]	eta 0:01:34 lr 0.001438	time 0.6509 (0.6187)	model_time 0.6507 (0.6072)	loss 3.8998 (3.1971)	grad_norm 1.4295 (2.0525/0.9606)	mem 24308MB
[2025-01-18 23:07:41 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][170/312]	eta 0:01:27 lr 0.001437	time 0.5821 (0.6183)	model_time 0.5819 (0.6075)	loss 2.2513 (3.1931)	grad_norm 2.1903 (2.0463/0.9524)	mem 24308MB
[2025-01-18 23:07:46 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][180/312]	eta 0:01:21 lr 0.001436	time 0.5938 (0.6169)	model_time 0.5937 (0.6066)	loss 2.4173 (3.1809)	grad_norm 2.1081 (2.0326/0.9368)	mem 24308MB
[2025-01-18 23:07:52 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][190/312]	eta 0:01:15 lr 0.001436	time 0.5752 (0.6155)	model_time 0.5748 (0.6057)	loss 3.5307 (3.1819)	grad_norm 1.7768 (2.0278/0.9293)	mem 24308MB
[2025-01-18 23:07:58 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][200/312]	eta 0:01:08 lr 0.001435	time 0.6739 (0.6149)	model_time 0.6734 (0.6056)	loss 3.1673 (3.1731)	grad_norm 2.3057 (2.0162/0.9188)	mem 24308MB
[2025-01-18 23:08:05 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][210/312]	eta 0:01:02 lr 0.001434	time 0.6581 (0.6150)	model_time 0.6576 (0.6062)	loss 3.8514 (3.1741)	grad_norm 3.0511 (2.0250/0.9097)	mem 24308MB
[2025-01-18 23:08:11 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][220/312]	eta 0:00:56 lr 0.001434	time 0.5893 (0.6142)	model_time 0.5888 (0.6058)	loss 1.8556 (3.1746)	grad_norm 1.8734 (2.0269/0.9069)	mem 24308MB
[2025-01-18 23:08:17 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][230/312]	eta 0:00:50 lr 0.001433	time 0.5881 (0.6146)	model_time 0.5876 (0.6065)	loss 3.3859 (3.1727)	grad_norm 1.2584 (2.0633/0.9364)	mem 24308MB
[2025-01-18 23:08:23 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][240/312]	eta 0:00:44 lr 0.001432	time 0.6880 (0.6142)	model_time 0.6876 (0.6064)	loss 3.2939 (3.1742)	grad_norm 1.8397 (2.0602/0.9233)	mem 24308MB
[2025-01-18 23:08:29 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][250/312]	eta 0:00:38 lr 0.001432	time 0.7645 (0.6145)	model_time 0.7644 (0.6071)	loss 3.4959 (3.1723)	grad_norm 1.2548 (2.0522/0.9091)	mem 24308MB
[2025-01-18 23:08:35 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][260/312]	eta 0:00:31 lr 0.001431	time 0.6667 (0.6140)	model_time 0.6665 (0.6068)	loss 2.5984 (3.1671)	grad_norm 2.7405 (2.0507/0.8974)	mem 24308MB
[2025-01-18 23:08:41 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][270/312]	eta 0:00:25 lr 0.001431	time 0.5781 (0.6129)	model_time 0.5775 (0.6060)	loss 3.3795 (3.1719)	grad_norm 1.8581 (2.0679/0.9233)	mem 24308MB
[2025-01-18 23:08:47 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][280/312]	eta 0:00:19 lr 0.001430	time 0.5741 (0.6120)	model_time 0.5740 (0.6053)	loss 3.1896 (3.1719)	grad_norm 2.4431 (2.0693/0.9124)	mem 24308MB
[2025-01-18 23:08:53 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][290/312]	eta 0:00:13 lr 0.001429	time 0.6026 (0.6118)	model_time 0.6021 (0.6053)	loss 2.7688 (3.1580)	grad_norm 1.5655 (2.0728/0.9022)	mem 24308MB
[2025-01-18 23:08:59 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][300/312]	eta 0:00:07 lr 0.001429	time 0.5705 (0.6112)	model_time 0.5704 (0.6048)	loss 3.5736 (3.1587)	grad_norm 1.2890 (2.0455/0.8901)	mem 24308MB
[2025-01-18 23:09:05 internimage_s_1k_224] (main.py 510): INFO Train: [178/300][310/312]	eta 0:00:01 lr 0.001428	time 0.5683 (0.6100)	model_time 0.5681 (0.6039)	loss 1.8993 (3.1527)	grad_norm 2.9657 (2.0303/0.8759)	mem 24308MB
[2025-01-18 23:09:05 internimage_s_1k_224] (main.py 519): INFO EPOCH 178 training takes 0:03:10
[2025-01-18 23:09:05 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_178.pth saving......
[2025-01-18 23:09:07 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_178.pth saved !!!
[2025-01-18 23:09:15 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.674 (7.674)	Loss 0.7825 (0.7825)	Acc@1 83.691 (83.691)	Acc@5 97.095 (97.095)	Mem 24308MB
[2025-01-18 23:09:18 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.007)	Loss 1.0516 (0.9007)	Acc@1 76.514 (80.919)	Acc@5 94.043 (95.599)	Mem 24308MB
[2025-01-18 23:09:18 internimage_s_1k_224] (main.py 575): INFO [Epoch:178] * Acc@1 80.728 Acc@5 95.605
[2025-01-18 23:09:18 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.7%
[2025-01-18 23:09:18 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 23:09:20 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 23:09:20 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.73%
[2025-01-18 23:09:28 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.484 (7.484)	Loss 0.7080 (0.7080)	Acc@1 84.155 (84.155)	Acc@5 97.583 (97.583)	Mem 24308MB
[2025-01-18 23:09:31 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (0.995)	Loss 0.9787 (0.8208)	Acc@1 76.440 (81.248)	Acc@5 94.336 (95.856)	Mem 24308MB
[2025-01-18 23:09:31 internimage_s_1k_224] (main.py 575): INFO [Epoch:178] * Acc@1 81.132 Acc@5 95.883
[2025-01-18 23:09:31 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.1%
[2025-01-18 23:09:31 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 23:09:34 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 23:09:34 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.13%
[2025-01-18 23:09:36 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][0/312]	eta 0:13:36 lr 0.001428	time 2.6169 (2.6169)	model_time 0.6200 (0.6200)	loss 3.1409 (3.1409)	grad_norm 1.8346 (1.8346/0.0000)	mem 24308MB
[2025-01-18 23:09:42 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][10/312]	eta 0:03:57 lr 0.001427	time 0.5921 (0.7861)	model_time 0.5919 (0.6042)	loss 3.4128 (3.1915)	grad_norm 2.6938 (1.8371/0.8384)	mem 24308MB
[2025-01-18 23:09:49 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][20/312]	eta 0:03:29 lr 0.001427	time 0.6639 (0.7191)	model_time 0.6638 (0.6237)	loss 3.3686 (3.2581)	grad_norm 2.3815 (1.9724/0.6935)	mem 24308MB
[2025-01-18 23:09:55 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][30/312]	eta 0:03:12 lr 0.001426	time 0.6138 (0.6822)	model_time 0.6135 (0.6174)	loss 3.1510 (3.1895)	grad_norm 1.8248 (1.9027/0.7065)	mem 24308MB
[2025-01-18 23:10:01 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][40/312]	eta 0:03:01 lr 0.001425	time 0.5804 (0.6690)	model_time 0.5803 (0.6199)	loss 3.2544 (3.1616)	grad_norm 1.2444 (1.8877/0.6716)	mem 24308MB
[2025-01-18 23:10:07 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][50/312]	eta 0:02:52 lr 0.001425	time 0.6650 (0.6601)	model_time 0.6649 (0.6205)	loss 3.7321 (3.1968)	grad_norm 3.0433 (1.9541/0.6816)	mem 24308MB
[2025-01-18 23:10:13 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][60/312]	eta 0:02:44 lr 0.001424	time 0.6953 (0.6528)	model_time 0.6951 (0.6197)	loss 3.5521 (3.1327)	grad_norm 1.0953 (1.8719/0.6710)	mem 24308MB
[2025-01-18 23:10:20 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][70/312]	eta 0:02:36 lr 0.001423	time 0.6141 (0.6460)	model_time 0.6138 (0.6175)	loss 3.2335 (3.1512)	grad_norm 1.8578 (1.9588/0.7457)	mem 24308MB
[2025-01-18 23:10:25 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][80/312]	eta 0:02:28 lr 0.001423	time 0.5861 (0.6388)	model_time 0.5859 (0.6138)	loss 3.3245 (3.1749)	grad_norm 3.2009 (1.9838/0.7581)	mem 24308MB
[2025-01-18 23:10:31 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][90/312]	eta 0:02:20 lr 0.001422	time 0.6067 (0.6339)	model_time 0.6065 (0.6115)	loss 3.6388 (3.1748)	grad_norm 2.5220 (2.0684/0.8059)	mem 24308MB
[2025-01-18 23:10:37 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][100/312]	eta 0:02:13 lr 0.001422	time 0.6957 (0.6316)	model_time 0.6956 (0.6115)	loss 2.7626 (3.1823)	grad_norm 2.7584 (2.0647/0.8269)	mem 24308MB
[2025-01-18 23:10:43 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][110/312]	eta 0:02:06 lr 0.001421	time 0.5718 (0.6276)	model_time 0.5716 (0.6092)	loss 2.3711 (3.1946)	grad_norm 1.0938 (2.0091/0.8158)	mem 24308MB
[2025-01-18 23:10:49 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][120/312]	eta 0:01:59 lr 0.001420	time 0.6053 (0.6247)	model_time 0.6048 (0.6078)	loss 2.9437 (3.2025)	grad_norm 1.8747 (2.0064/0.8124)	mem 24308MB
[2025-01-18 23:10:55 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][130/312]	eta 0:01:53 lr 0.001420	time 0.6662 (0.6232)	model_time 0.6660 (0.6076)	loss 3.0925 (3.2278)	grad_norm 2.6013 (2.0209/0.8053)	mem 24308MB
[2025-01-18 23:11:01 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][140/312]	eta 0:01:47 lr 0.001419	time 0.5762 (0.6225)	model_time 0.5760 (0.6080)	loss 2.5958 (3.2257)	grad_norm 2.0578 (1.9967/0.7862)	mem 24308MB
[2025-01-18 23:11:08 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][150/312]	eta 0:01:40 lr 0.001418	time 0.6693 (0.6220)	model_time 0.6691 (0.6084)	loss 2.7007 (3.2232)	grad_norm 1.2969 (1.9586/0.7765)	mem 24308MB
[2025-01-18 23:11:14 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][160/312]	eta 0:01:34 lr 0.001418	time 0.5930 (0.6215)	model_time 0.5929 (0.6087)	loss 3.1989 (3.2197)	grad_norm 1.5363 (1.9175/0.7706)	mem 24308MB
[2025-01-18 23:11:20 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][170/312]	eta 0:01:28 lr 0.001417	time 0.5901 (0.6210)	model_time 0.5900 (0.6089)	loss 3.5161 (3.2249)	grad_norm 1.0856 (1.8965/0.7588)	mem 24308MB
[2025-01-18 23:11:26 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][180/312]	eta 0:01:21 lr 0.001416	time 0.5809 (0.6208)	model_time 0.5807 (0.6094)	loss 2.9311 (3.2090)	grad_norm 1.1831 (1.8869/0.7540)	mem 24308MB
[2025-01-18 23:11:32 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][190/312]	eta 0:01:15 lr 0.001416	time 0.6694 (0.6211)	model_time 0.6692 (0.6103)	loss 2.3011 (3.2109)	grad_norm 1.3622 (1.8890/0.7416)	mem 24308MB
[2025-01-18 23:11:38 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][200/312]	eta 0:01:09 lr 0.001415	time 0.5716 (0.6198)	model_time 0.5714 (0.6095)	loss 2.2747 (3.2099)	grad_norm 1.3447 (1.8876/0.7495)	mem 24308MB
[2025-01-18 23:11:44 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][210/312]	eta 0:01:03 lr 0.001415	time 0.6152 (0.6185)	model_time 0.6151 (0.6087)	loss 3.5321 (3.2185)	grad_norm 1.4699 (1.8887/0.7452)	mem 24308MB
[2025-01-18 23:11:50 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][220/312]	eta 0:00:56 lr 0.001414	time 0.6947 (0.6186)	model_time 0.6943 (0.6092)	loss 2.2018 (3.2213)	grad_norm 1.4221 (1.8974/0.7397)	mem 24308MB
[2025-01-18 23:11:56 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][230/312]	eta 0:00:50 lr 0.001413	time 0.5783 (0.6171)	model_time 0.5779 (0.6081)	loss 2.8943 (3.2071)	grad_norm 1.4572 (1.8807/0.7317)	mem 24308MB
[2025-01-18 23:12:02 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][240/312]	eta 0:00:44 lr 0.001413	time 0.5933 (0.6160)	model_time 0.5931 (0.6073)	loss 3.1468 (3.2083)	grad_norm 1.1160 (1.8800/0.7479)	mem 24308MB
[2025-01-18 23:12:08 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][250/312]	eta 0:00:38 lr 0.001412	time 0.5848 (0.6152)	model_time 0.5846 (0.6068)	loss 2.9630 (3.2030)	grad_norm 3.4921 (1.8988/0.7600)	mem 24308MB
[2025-01-18 23:12:14 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][260/312]	eta 0:00:32 lr 0.001411	time 0.5818 (0.6157)	model_time 0.5813 (0.6077)	loss 3.1409 (3.2043)	grad_norm 3.0536 (1.9321/0.7925)	mem 24308MB
[2025-01-18 23:12:20 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][270/312]	eta 0:00:25 lr 0.001411	time 0.5793 (0.6156)	model_time 0.5788 (0.6079)	loss 2.1475 (3.2008)	grad_norm 3.5995 (1.9610/0.8108)	mem 24308MB
[2025-01-18 23:12:27 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][280/312]	eta 0:00:19 lr 0.001410	time 0.6575 (0.6154)	model_time 0.6570 (0.6080)	loss 3.3943 (3.1933)	grad_norm 1.9978 (1.9635/0.8045)	mem 24308MB
[2025-01-18 23:12:33 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][290/312]	eta 0:00:13 lr 0.001410	time 0.6095 (0.6156)	model_time 0.6093 (0.6084)	loss 2.8919 (3.1902)	grad_norm 1.4234 (1.9576/0.7974)	mem 24308MB
[2025-01-18 23:12:39 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][300/312]	eta 0:00:07 lr 0.001409	time 0.5680 (0.6153)	model_time 0.5679 (0.6083)	loss 3.4373 (3.1829)	grad_norm 1.8424 (1.9512/0.7952)	mem 24308MB
[2025-01-18 23:12:45 internimage_s_1k_224] (main.py 510): INFO Train: [179/300][310/312]	eta 0:00:01 lr 0.001408	time 0.5711 (0.6147)	model_time 0.5710 (0.6079)	loss 3.8656 (3.1828)	grad_norm 2.7248 (1.9656/0.7866)	mem 24308MB
[2025-01-18 23:12:45 internimage_s_1k_224] (main.py 519): INFO EPOCH 179 training takes 0:03:11
[2025-01-18 23:12:45 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_179.pth saving......
[2025-01-18 23:12:47 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_179.pth saved !!!
[2025-01-18 23:12:55 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.608 (7.608)	Loss 0.7666 (0.7666)	Acc@1 83.496 (83.496)	Acc@5 97.119 (97.119)	Mem 24308MB
[2025-01-18 23:12:58 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.015)	Loss 1.0578 (0.8949)	Acc@1 76.318 (80.766)	Acc@5 93.945 (95.657)	Mem 24308MB
[2025-01-18 23:12:58 internimage_s_1k_224] (main.py 575): INFO [Epoch:179] * Acc@1 80.646 Acc@5 95.705
[2025-01-18 23:12:58 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.6%
[2025-01-18 23:12:59 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.73%
[2025-01-18 23:13:07 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.584 (8.584)	Loss 0.7080 (0.7080)	Acc@1 84.204 (84.204)	Acc@5 97.583 (97.583)	Mem 24308MB
[2025-01-18 23:13:11 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.173)	Loss 0.9775 (0.8201)	Acc@1 76.416 (81.266)	Acc@5 94.312 (95.883)	Mem 24308MB
[2025-01-18 23:13:12 internimage_s_1k_224] (main.py 575): INFO [Epoch:179] * Acc@1 81.162 Acc@5 95.911
[2025-01-18 23:13:12 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.2%
[2025-01-18 23:13:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 23:13:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 23:13:14 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.16%
[2025-01-18 23:13:16 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][0/312]	eta 0:11:17 lr 0.001408	time 2.1701 (2.1701)	model_time 0.6032 (0.6032)	loss 3.5779 (3.5779)	grad_norm 1.7173 (1.7173/0.0000)	mem 24308MB
[2025-01-18 23:13:22 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][10/312]	eta 0:03:43 lr 0.001408	time 0.5825 (0.7413)	model_time 0.5823 (0.5986)	loss 2.7423 (3.2426)	grad_norm 1.8136 (2.2667/0.7871)	mem 24308MB
[2025-01-18 23:13:28 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][20/312]	eta 0:03:16 lr 0.001407	time 0.6983 (0.6734)	model_time 0.6981 (0.5985)	loss 3.2413 (3.1577)	grad_norm 1.7963 (2.2940/0.8540)	mem 24308MB
[2025-01-18 23:13:34 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][30/312]	eta 0:03:04 lr 0.001406	time 0.5912 (0.6525)	model_time 0.5911 (0.6017)	loss 3.3459 (3.2610)	grad_norm 0.9997 (2.2565/0.8814)	mem 24308MB
[2025-01-18 23:13:40 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][40/312]	eta 0:02:53 lr 0.001406	time 0.6041 (0.6377)	model_time 0.6039 (0.5992)	loss 3.0248 (3.2023)	grad_norm 3.2124 (2.2026/0.8766)	mem 24308MB
[2025-01-18 23:13:46 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][50/312]	eta 0:02:44 lr 0.001405	time 0.5730 (0.6278)	model_time 0.5726 (0.5967)	loss 3.8387 (3.1712)	grad_norm 2.3479 (2.2291/0.9459)	mem 24308MB
[2025-01-18 23:13:52 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][60/312]	eta 0:02:37 lr 0.001404	time 0.6949 (0.6245)	model_time 0.6947 (0.5985)	loss 2.6451 (3.1886)	grad_norm 3.8201 (2.2916/0.9627)	mem 24308MB
[2025-01-18 23:13:58 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][70/312]	eta 0:02:31 lr 0.001404	time 0.5844 (0.6256)	model_time 0.5843 (0.6032)	loss 2.6469 (3.1577)	grad_norm 1.3029 (2.1875/0.9458)	mem 24308MB
[2025-01-18 23:14:04 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][80/312]	eta 0:02:24 lr 0.001403	time 0.5767 (0.6231)	model_time 0.5762 (0.6034)	loss 4.1137 (3.2046)	grad_norm 1.7554 (2.0976/0.9234)	mem 24308MB
[2025-01-18 23:14:11 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][90/312]	eta 0:02:18 lr 0.001402	time 0.6573 (0.6242)	model_time 0.6568 (0.6066)	loss 3.1449 (3.2196)	grad_norm 1.7488 (2.0442/0.8894)	mem 24308MB
[2025-01-18 23:14:17 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][100/312]	eta 0:02:12 lr 0.001402	time 0.5904 (0.6253)	model_time 0.5899 (0.6094)	loss 2.9415 (3.1905)	grad_norm 1.2182 (1.9539/0.8919)	mem 24308MB
[2025-01-18 23:14:23 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][110/312]	eta 0:02:05 lr 0.001401	time 0.6412 (0.6237)	model_time 0.6407 (0.6092)	loss 2.6669 (3.1969)	grad_norm 1.1768 (1.9838/0.9329)	mem 24308MB
[2025-01-18 23:14:29 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][120/312]	eta 0:01:59 lr 0.001401	time 0.5856 (0.6219)	model_time 0.5854 (0.6086)	loss 2.4448 (3.2049)	grad_norm 1.3269 (1.9817/0.9314)	mem 24308MB
[2025-01-18 23:14:35 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][130/312]	eta 0:01:53 lr 0.001400	time 0.5721 (0.6210)	model_time 0.5720 (0.6087)	loss 2.9449 (3.1937)	grad_norm 2.2394 (1.9591/0.9092)	mem 24308MB
[2025-01-18 23:14:41 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][140/312]	eta 0:01:46 lr 0.001399	time 0.5841 (0.6192)	model_time 0.5839 (0.6077)	loss 2.9416 (3.1963)	grad_norm 1.2583 (1.9455/0.8975)	mem 24308MB
[2025-01-18 23:14:47 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][150/312]	eta 0:01:40 lr 0.001399	time 0.5765 (0.6189)	model_time 0.5761 (0.6082)	loss 3.4174 (3.1981)	grad_norm 1.6253 (1.9195/0.8868)	mem 24308MB
[2025-01-18 23:14:53 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][160/312]	eta 0:01:33 lr 0.001398	time 0.6023 (0.6175)	model_time 0.6018 (0.6074)	loss 3.2908 (3.2254)	grad_norm 0.8007 (1.8890/0.8708)	mem 24308MB
[2025-01-18 23:14:59 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][170/312]	eta 0:01:27 lr 0.001397	time 0.5780 (0.6156)	model_time 0.5776 (0.6061)	loss 3.3444 (3.2348)	grad_norm 1.3391 (1.9152/0.9096)	mem 24308MB
[2025-01-18 23:15:05 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][180/312]	eta 0:01:21 lr 0.001397	time 0.5891 (0.6147)	model_time 0.5887 (0.6057)	loss 2.4217 (3.2351)	grad_norm 1.8555 (1.9196/0.8973)	mem 24308MB
[2025-01-18 23:15:11 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][190/312]	eta 0:01:15 lr 0.001396	time 0.5971 (0.6151)	model_time 0.5969 (0.6065)	loss 3.1939 (3.2240)	grad_norm 1.5566 (1.9563/0.9362)	mem 24308MB
[2025-01-18 23:15:18 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][200/312]	eta 0:01:08 lr 0.001396	time 0.5908 (0.6153)	model_time 0.5907 (0.6072)	loss 3.6527 (3.2366)	grad_norm 1.2809 (1.9335/0.9225)	mem 24308MB
[2025-01-18 23:15:24 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][210/312]	eta 0:01:02 lr 0.001395	time 0.5967 (0.6152)	model_time 0.5965 (0.6074)	loss 3.3415 (3.2359)	grad_norm 1.5792 (1.9501/0.9493)	mem 24308MB
[2025-01-18 23:15:30 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][220/312]	eta 0:00:56 lr 0.001394	time 0.5922 (0.6150)	model_time 0.5920 (0.6075)	loss 3.7304 (3.2458)	grad_norm 2.4703 (1.9849/0.9666)	mem 24308MB
[2025-01-18 23:15:36 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][230/312]	eta 0:00:50 lr 0.001394	time 0.6030 (0.6149)	model_time 0.6028 (0.6077)	loss 3.7336 (3.2517)	grad_norm 1.7516 (1.9920/0.9567)	mem 24308MB
[2025-01-18 23:15:42 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][240/312]	eta 0:00:44 lr 0.001393	time 0.5824 (0.6149)	model_time 0.5820 (0.6080)	loss 2.6238 (3.2503)	grad_norm 2.0628 (2.0016/0.9529)	mem 24308MB
[2025-01-18 23:15:48 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][250/312]	eta 0:00:38 lr 0.001392	time 0.5863 (0.6146)	model_time 0.5861 (0.6079)	loss 3.0712 (3.2515)	grad_norm 1.6516 (1.9791/0.9422)	mem 24308MB
[2025-01-18 23:15:54 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][260/312]	eta 0:00:31 lr 0.001392	time 0.5950 (0.6134)	model_time 0.5944 (0.6070)	loss 3.5956 (3.2530)	grad_norm 0.9651 (1.9720/0.9359)	mem 24308MB
[2025-01-18 23:16:00 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][270/312]	eta 0:00:25 lr 0.001391	time 0.5801 (0.6132)	model_time 0.5796 (0.6070)	loss 2.8568 (3.2460)	grad_norm 3.2782 (1.9947/0.9477)	mem 24308MB
[2025-01-18 23:16:06 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][280/312]	eta 0:00:19 lr 0.001390	time 0.5917 (0.6127)	model_time 0.5915 (0.6067)	loss 2.9450 (3.2412)	grad_norm 1.3433 (1.9803/0.9380)	mem 24308MB
[2025-01-18 23:16:12 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][290/312]	eta 0:00:13 lr 0.001390	time 0.5727 (0.6118)	model_time 0.5725 (0.6061)	loss 2.2752 (3.2449)	grad_norm 1.8827 (1.9601/0.9308)	mem 24308MB
[2025-01-18 23:16:18 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][300/312]	eta 0:00:07 lr 0.001389	time 0.5680 (0.6109)	model_time 0.5679 (0.6053)	loss 2.8644 (3.2361)	grad_norm 1.8920 (1.9698/0.9313)	mem 24308MB
[2025-01-18 23:16:24 internimage_s_1k_224] (main.py 510): INFO Train: [180/300][310/312]	eta 0:00:01 lr 0.001389	time 0.6491 (0.6107)	model_time 0.6490 (0.6052)	loss 2.9886 (3.2337)	grad_norm 1.4215 (1.9595/0.9303)	mem 24308MB
[2025-01-18 23:16:24 internimage_s_1k_224] (main.py 519): INFO EPOCH 180 training takes 0:03:10
[2025-01-18 23:16:25 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_180.pth saving......
[2025-01-18 23:16:26 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_180.pth saved !!!
[2025-01-18 23:16:34 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.631 (7.631)	Loss 0.7971 (0.7971)	Acc@1 83.496 (83.496)	Acc@5 96.924 (96.924)	Mem 24308MB
[2025-01-18 23:16:38 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.012)	Loss 1.0770 (0.9240)	Acc@1 75.928 (80.686)	Acc@5 94.458 (95.563)	Mem 24308MB
[2025-01-18 23:16:38 internimage_s_1k_224] (main.py 575): INFO [Epoch:180] * Acc@1 80.624 Acc@5 95.607
[2025-01-18 23:16:38 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.6%
[2025-01-18 23:16:38 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.73%
[2025-01-18 23:16:46 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.498 (8.498)	Loss 0.7080 (0.7080)	Acc@1 84.204 (84.204)	Acc@5 97.583 (97.583)	Mem 24308MB
[2025-01-18 23:16:50 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.136 (1.158)	Loss 0.9760 (0.8193)	Acc@1 76.514 (81.317)	Acc@5 94.360 (95.894)	Mem 24308MB
[2025-01-18 23:16:51 internimage_s_1k_224] (main.py 575): INFO [Epoch:180] * Acc@1 81.204 Acc@5 95.919
[2025-01-18 23:16:51 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.2%
[2025-01-18 23:16:51 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 23:16:53 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 23:16:53 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.20%
[2025-01-18 23:16:56 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][0/312]	eta 0:12:11 lr 0.001388	time 2.3443 (2.3443)	model_time 0.6090 (0.6090)	loss 3.6398 (3.6398)	grad_norm 3.1996 (3.1996/0.0000)	mem 24308MB
[2025-01-18 23:17:02 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][10/312]	eta 0:03:53 lr 0.001388	time 0.5951 (0.7726)	model_time 0.5950 (0.6145)	loss 3.1406 (3.2463)	grad_norm 2.7929 (2.0578/0.7950)	mem 24308MB
[2025-01-18 23:17:08 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][20/312]	eta 0:03:23 lr 0.001387	time 0.5971 (0.6966)	model_time 0.5969 (0.6137)	loss 3.1869 (3.2528)	grad_norm 1.2360 (1.7654/0.7731)	mem 24308MB
[2025-01-18 23:17:14 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][30/312]	eta 0:03:08 lr 0.001387	time 0.6107 (0.6679)	model_time 0.6103 (0.6116)	loss 3.2552 (3.2289)	grad_norm 1.0825 (1.7139/0.6806)	mem 24308MB
[2025-01-18 23:17:20 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][40/312]	eta 0:02:57 lr 0.001386	time 0.5978 (0.6541)	model_time 0.5976 (0.6114)	loss 3.8641 (3.2409)	grad_norm 1.9064 (1.7238/0.6189)	mem 24308MB
[2025-01-18 23:17:26 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][50/312]	eta 0:02:49 lr 0.001385	time 0.6768 (0.6457)	model_time 0.6767 (0.6113)	loss 2.5985 (3.2293)	grad_norm 4.0410 (1.9287/0.8643)	mem 24308MB
[2025-01-18 23:17:32 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][60/312]	eta 0:02:40 lr 0.001385	time 0.5763 (0.6388)	model_time 0.5759 (0.6100)	loss 1.8458 (3.1884)	grad_norm 1.1278 (1.9417/0.8265)	mem 24308MB
[2025-01-18 23:17:38 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][70/312]	eta 0:02:33 lr 0.001384	time 0.5862 (0.6330)	model_time 0.5858 (0.6082)	loss 3.0548 (3.1774)	grad_norm 3.3548 (1.9473/0.7983)	mem 24308MB
[2025-01-18 23:17:44 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][80/312]	eta 0:02:26 lr 0.001383	time 0.5744 (0.6302)	model_time 0.5743 (0.6085)	loss 3.2214 (3.1933)	grad_norm 1.0497 (1.9544/0.8041)	mem 24308MB
[2025-01-18 23:17:50 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][90/312]	eta 0:02:18 lr 0.001383	time 0.5801 (0.6254)	model_time 0.5799 (0.6059)	loss 2.6265 (3.1958)	grad_norm 2.3701 (2.0006/0.8225)	mem 24308MB
[2025-01-18 23:17:56 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][100/312]	eta 0:02:11 lr 0.001382	time 0.5949 (0.6219)	model_time 0.5948 (0.6044)	loss 2.7183 (3.1606)	grad_norm 0.9841 (1.9870/0.8096)	mem 24308MB
[2025-01-18 23:18:02 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][110/312]	eta 0:02:05 lr 0.001382	time 0.5810 (0.6199)	model_time 0.5806 (0.6039)	loss 3.4287 (3.1634)	grad_norm 2.3046 (1.9934/0.8017)	mem 24308MB
[2025-01-18 23:18:08 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][120/312]	eta 0:01:59 lr 0.001381	time 0.6833 (0.6201)	model_time 0.6831 (0.6054)	loss 2.5025 (3.1643)	grad_norm 0.8540 (1.9865/0.8123)	mem 24308MB
[2025-01-18 23:18:15 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][130/312]	eta 0:01:52 lr 0.001380	time 0.6817 (0.6208)	model_time 0.6815 (0.6072)	loss 2.1042 (3.1730)	grad_norm 1.8041 (1.9370/0.8176)	mem 24308MB
[2025-01-18 23:18:21 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][140/312]	eta 0:01:46 lr 0.001380	time 0.5730 (0.6203)	model_time 0.5725 (0.6076)	loss 3.8071 (3.1717)	grad_norm 1.1903 (1.9247/0.8103)	mem 24308MB
[2025-01-18 23:18:27 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][150/312]	eta 0:01:40 lr 0.001379	time 0.5852 (0.6199)	model_time 0.5850 (0.6081)	loss 2.9925 (3.1798)	grad_norm 1.8486 (1.9534/0.8187)	mem 24308MB
[2025-01-18 23:18:33 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][160/312]	eta 0:01:34 lr 0.001378	time 0.5866 (0.6194)	model_time 0.5864 (0.6083)	loss 3.4577 (3.1744)	grad_norm 1.9287 (1.9664/0.8099)	mem 24308MB
[2025-01-18 23:18:39 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][170/312]	eta 0:01:27 lr 0.001378	time 0.5740 (0.6183)	model_time 0.5736 (0.6078)	loss 3.0401 (3.1690)	grad_norm 1.6085 (1.9465/0.8054)	mem 24308MB
[2025-01-18 23:18:45 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][180/312]	eta 0:01:21 lr 0.001377	time 0.6151 (0.6181)	model_time 0.6146 (0.6081)	loss 3.4155 (3.1829)	grad_norm 2.0033 (1.9326/0.8008)	mem 24308MB
[2025-01-18 23:18:51 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][190/312]	eta 0:01:15 lr 0.001377	time 0.5922 (0.6168)	model_time 0.5917 (0.6073)	loss 2.9902 (3.1830)	grad_norm 1.4382 (1.9442/0.7984)	mem 24308MB
[2025-01-18 23:18:57 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][200/312]	eta 0:01:08 lr 0.001376	time 0.6933 (0.6160)	model_time 0.6932 (0.6070)	loss 3.6024 (3.1865)	grad_norm 1.9978 (1.9533/0.7884)	mem 24308MB
[2025-01-18 23:19:03 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][210/312]	eta 0:01:02 lr 0.001375	time 0.5790 (0.6155)	model_time 0.5786 (0.6069)	loss 2.1916 (3.1967)	grad_norm 1.8179 (1.9743/0.8060)	mem 24308MB
[2025-01-18 23:19:09 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][220/312]	eta 0:00:56 lr 0.001375	time 0.5863 (0.6144)	model_time 0.5861 (0.6061)	loss 3.3362 (3.1964)	grad_norm 2.1422 (1.9714/0.7969)	mem 24308MB
[2025-01-18 23:19:15 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][230/312]	eta 0:00:50 lr 0.001374	time 0.5931 (0.6137)	model_time 0.5925 (0.6058)	loss 3.1828 (3.1921)	grad_norm 2.1462 (1.9838/0.7948)	mem 24308MB
[2025-01-18 23:19:21 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][240/312]	eta 0:00:44 lr 0.001373	time 0.6697 (0.6134)	model_time 0.6694 (0.6058)	loss 2.9471 (3.1888)	grad_norm 2.1500 (1.9924/0.7871)	mem 24308MB
[2025-01-18 23:19:27 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][250/312]	eta 0:00:38 lr 0.001373	time 0.5745 (0.6136)	model_time 0.5744 (0.6063)	loss 3.2326 (3.1908)	grad_norm 1.7469 (1.9959/0.7860)	mem 24308MB
[2025-01-18 23:19:33 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][260/312]	eta 0:00:31 lr 0.001372	time 0.5915 (0.6136)	model_time 0.5913 (0.6066)	loss 3.5543 (3.1920)	grad_norm 1.7161 (1.9764/0.7849)	mem 24308MB
[2025-01-18 23:19:40 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][270/312]	eta 0:00:25 lr 0.001371	time 0.5911 (0.6137)	model_time 0.5909 (0.6069)	loss 3.6844 (3.1911)	grad_norm 2.7057 (1.9671/0.7795)	mem 24308MB
[2025-01-18 23:19:46 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][280/312]	eta 0:00:19 lr 0.001371	time 0.6025 (0.6137)	model_time 0.6023 (0.6072)	loss 2.9901 (3.1900)	grad_norm 1.1860 (1.9755/0.7757)	mem 24308MB
[2025-01-18 23:19:52 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][290/312]	eta 0:00:13 lr 0.001370	time 0.5739 (0.6136)	model_time 0.5737 (0.6073)	loss 4.2266 (3.1860)	grad_norm 3.3823 (1.9980/0.7889)	mem 24308MB
[2025-01-18 23:19:58 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][300/312]	eta 0:00:07 lr 0.001370	time 0.6556 (0.6135)	model_time 0.6555 (0.6073)	loss 3.9030 (3.1886)	grad_norm 2.0446 (1.9943/0.7848)	mem 24308MB
[2025-01-18 23:20:04 internimage_s_1k_224] (main.py 510): INFO Train: [181/300][310/312]	eta 0:00:01 lr 0.001369	time 0.5675 (0.6122)	model_time 0.5674 (0.6063)	loss 3.2801 (3.1908)	grad_norm 3.6300 (2.0104/0.8237)	mem 24308MB
[2025-01-18 23:20:04 internimage_s_1k_224] (main.py 519): INFO EPOCH 181 training takes 0:03:10
[2025-01-18 23:20:04 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_181.pth saving......
[2025-01-18 23:20:06 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_181.pth saved !!!
[2025-01-18 23:20:14 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.844 (7.844)	Loss 0.8109 (0.8109)	Acc@1 83.472 (83.472)	Acc@5 96.680 (96.680)	Mem 24308MB
[2025-01-18 23:20:17 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.025)	Loss 1.0614 (0.9134)	Acc@1 76.416 (80.904)	Acc@5 94.141 (95.528)	Mem 24308MB
[2025-01-18 23:20:17 internimage_s_1k_224] (main.py 575): INFO [Epoch:181] * Acc@1 80.770 Acc@5 95.561
[2025-01-18 23:20:17 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.8%
[2025-01-18 23:20:17 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 23:20:19 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 23:20:19 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.77%
[2025-01-18 23:20:27 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.748 (7.748)	Loss 0.7081 (0.7081)	Acc@1 84.277 (84.277)	Acc@5 97.534 (97.534)	Mem 24308MB
[2025-01-18 23:20:30 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.015)	Loss 0.9747 (0.8188)	Acc@1 76.636 (81.365)	Acc@5 94.434 (95.910)	Mem 24308MB
[2025-01-18 23:20:31 internimage_s_1k_224] (main.py 575): INFO [Epoch:181] * Acc@1 81.248 Acc@5 95.933
[2025-01-18 23:20:31 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.2%
[2025-01-18 23:20:31 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 23:20:33 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 23:20:33 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.25%
[2025-01-18 23:20:35 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][0/312]	eta 0:11:27 lr 0.001369	time 2.2030 (2.2030)	model_time 0.5953 (0.5953)	loss 3.6387 (3.6387)	grad_norm 2.7936 (2.7936/0.0000)	mem 24308MB
[2025-01-18 23:20:41 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][10/312]	eta 0:03:48 lr 0.001368	time 0.5890 (0.7562)	model_time 0.5888 (0.6098)	loss 3.2019 (3.2754)	grad_norm 0.9987 (1.5783/0.5909)	mem 24308MB
[2025-01-18 23:20:47 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][20/312]	eta 0:03:18 lr 0.001368	time 0.5843 (0.6800)	model_time 0.5838 (0.6024)	loss 2.5331 (3.1441)	grad_norm 1.8295 (1.7605/0.7633)	mem 24308MB
[2025-01-18 23:20:53 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][30/312]	eta 0:03:03 lr 0.001367	time 0.5805 (0.6512)	model_time 0.5804 (0.5985)	loss 2.3398 (3.1024)	grad_norm 2.5442 (1.8902/0.7512)	mem 24308MB
[2025-01-18 23:20:59 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][40/312]	eta 0:02:53 lr 0.001366	time 0.5733 (0.6378)	model_time 0.5731 (0.5979)	loss 3.8386 (3.1666)	grad_norm 2.0492 (1.8956/0.7204)	mem 24308MB
[2025-01-18 23:21:06 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][50/312]	eta 0:02:46 lr 0.001366	time 0.5739 (0.6362)	model_time 0.5737 (0.6041)	loss 3.6001 (3.2044)	grad_norm 2.3197 (1.8398/0.7058)	mem 24308MB
[2025-01-18 23:21:12 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][60/312]	eta 0:02:41 lr 0.001365	time 0.6163 (0.6397)	model_time 0.6161 (0.6128)	loss 3.5553 (3.2498)	grad_norm 1.0904 (1.7965/0.6868)	mem 24308MB
[2025-01-18 23:21:18 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][70/312]	eta 0:02:33 lr 0.001364	time 0.6529 (0.6359)	model_time 0.6524 (0.6127)	loss 3.0598 (3.2311)	grad_norm 1.6290 (1.7862/0.6882)	mem 24308MB
[2025-01-18 23:21:25 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][80/312]	eta 0:02:27 lr 0.001364	time 0.6978 (0.6355)	model_time 0.6976 (0.6151)	loss 3.2194 (3.2266)	grad_norm 1.8089 (1.9183/0.8209)	mem 24308MB
[2025-01-18 23:21:31 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][90/312]	eta 0:02:20 lr 0.001363	time 0.6018 (0.6320)	model_time 0.6013 (0.6139)	loss 2.8998 (3.2009)	grad_norm 1.0231 (1.9575/0.8557)	mem 24308MB
[2025-01-18 23:21:37 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][100/312]	eta 0:02:13 lr 0.001363	time 0.5983 (0.6302)	model_time 0.5978 (0.6137)	loss 3.4855 (3.2072)	grad_norm 1.2707 (1.9440/0.8370)	mem 24308MB
[2025-01-18 23:21:43 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][110/312]	eta 0:02:07 lr 0.001362	time 0.6708 (0.6294)	model_time 0.6707 (0.6144)	loss 3.0653 (3.1846)	grad_norm 2.5753 (2.0097/0.8940)	mem 24308MB
[2025-01-18 23:21:49 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][120/312]	eta 0:02:00 lr 0.001361	time 0.5822 (0.6262)	model_time 0.5820 (0.6124)	loss 3.5079 (3.1974)	grad_norm 2.9694 (2.0109/0.8867)	mem 24308MB
[2025-01-18 23:21:55 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][130/312]	eta 0:01:53 lr 0.001361	time 0.6771 (0.6244)	model_time 0.6766 (0.6117)	loss 2.5914 (3.1988)	grad_norm 1.9879 (1.9992/0.8742)	mem 24308MB
[2025-01-18 23:22:01 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][140/312]	eta 0:01:47 lr 0.001360	time 0.5751 (0.6227)	model_time 0.5745 (0.6108)	loss 3.4296 (3.2047)	grad_norm 1.9352 (1.9982/0.8633)	mem 24308MB
[2025-01-18 23:22:07 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][150/312]	eta 0:01:40 lr 0.001359	time 0.5783 (0.6203)	model_time 0.5779 (0.6091)	loss 3.4841 (3.1924)	grad_norm 2.6941 (2.0376/0.8751)	mem 24308MB
[2025-01-18 23:22:13 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][160/312]	eta 0:01:34 lr 0.001359	time 0.6673 (0.6191)	model_time 0.6668 (0.6087)	loss 3.4458 (3.1929)	grad_norm 1.8378 (2.0343/0.8623)	mem 24308MB
[2025-01-18 23:22:19 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][170/312]	eta 0:01:27 lr 0.001358	time 0.5730 (0.6187)	model_time 0.5725 (0.6089)	loss 3.2402 (3.1819)	grad_norm 4.7437 (2.0565/0.9027)	mem 24308MB
[2025-01-18 23:22:25 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][180/312]	eta 0:01:21 lr 0.001358	time 0.5787 (0.6186)	model_time 0.5785 (0.6093)	loss 3.9035 (3.1841)	grad_norm 3.8603 (2.0867/0.9261)	mem 24308MB
[2025-01-18 23:22:31 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][190/312]	eta 0:01:15 lr 0.001357	time 0.6542 (0.6194)	model_time 0.6540 (0.6105)	loss 3.4035 (3.1863)	grad_norm 1.5495 (2.0696/0.9174)	mem 24308MB
[2025-01-18 23:22:37 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][200/312]	eta 0:01:09 lr 0.001356	time 0.6929 (0.6188)	model_time 0.6925 (0.6104)	loss 3.3636 (3.1938)	grad_norm 0.9592 (2.0779/0.9235)	mem 24308MB
[2025-01-18 23:22:44 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][210/312]	eta 0:01:03 lr 0.001356	time 0.5818 (0.6189)	model_time 0.5814 (0.6108)	loss 3.3100 (3.1888)	grad_norm 0.8825 (2.0608/0.9232)	mem 24308MB
[2025-01-18 23:22:50 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][220/312]	eta 0:00:56 lr 0.001355	time 0.5751 (0.6183)	model_time 0.5747 (0.6106)	loss 2.2747 (3.1815)	grad_norm 2.1887 (2.0361/0.9171)	mem 24308MB
[2025-01-18 23:22:56 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][230/312]	eta 0:00:50 lr 0.001354	time 0.6687 (0.6181)	model_time 0.6686 (0.6107)	loss 3.3346 (3.1894)	grad_norm 1.6165 (2.0561/0.9267)	mem 24308MB
[2025-01-18 23:23:02 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][240/312]	eta 0:00:44 lr 0.001354	time 0.5708 (0.6171)	model_time 0.5706 (0.6100)	loss 1.9883 (3.1778)	grad_norm 1.7498 (2.0506/0.9200)	mem 24308MB
[2025-01-18 23:23:08 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][250/312]	eta 0:00:38 lr 0.001353	time 0.5761 (0.6159)	model_time 0.5757 (0.6091)	loss 2.7395 (3.1739)	grad_norm 1.8606 (2.0436/0.9123)	mem 24308MB
[2025-01-18 23:23:14 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][260/312]	eta 0:00:32 lr 0.001353	time 0.5708 (0.6158)	model_time 0.5707 (0.6092)	loss 3.2238 (3.1707)	grad_norm 0.8279 (2.0439/0.9129)	mem 24308MB
[2025-01-18 23:23:20 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][270/312]	eta 0:00:25 lr 0.001352	time 0.5838 (0.6148)	model_time 0.5833 (0.6084)	loss 3.4449 (3.1795)	grad_norm 1.4989 (2.0369/0.9074)	mem 24308MB
[2025-01-18 23:23:26 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][280/312]	eta 0:00:19 lr 0.001351	time 0.6894 (0.6142)	model_time 0.6890 (0.6079)	loss 3.2101 (3.1869)	grad_norm 3.0838 (2.0329/0.9038)	mem 24308MB
[2025-01-18 23:23:32 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][290/312]	eta 0:00:13 lr 0.001351	time 0.5894 (0.6139)	model_time 0.5890 (0.6078)	loss 2.1227 (3.1781)	grad_norm 1.3414 (2.0429/0.9126)	mem 24308MB
[2025-01-18 23:23:38 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][300/312]	eta 0:00:07 lr 0.001350	time 0.6454 (0.6145)	model_time 0.6453 (0.6086)	loss 2.9173 (3.1755)	grad_norm 1.5908 (2.0220/0.9118)	mem 24308MB
[2025-01-18 23:23:44 internimage_s_1k_224] (main.py 510): INFO Train: [182/300][310/312]	eta 0:00:01 lr 0.001349	time 0.5693 (0.6142)	model_time 0.5692 (0.6085)	loss 3.3126 (3.1766)	grad_norm 4.1215 (2.0558/0.9365)	mem 24308MB
[2025-01-18 23:23:45 internimage_s_1k_224] (main.py 519): INFO EPOCH 182 training takes 0:03:11
[2025-01-18 23:23:45 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_182.pth saving......
[2025-01-18 23:23:47 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_182.pth saved !!!
[2025-01-18 23:23:54 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.463 (7.463)	Loss 0.7918 (0.7918)	Acc@1 83.521 (83.521)	Acc@5 97.021 (97.021)	Mem 24308MB
[2025-01-18 23:23:57 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.983)	Loss 1.0552 (0.9164)	Acc@1 76.025 (80.560)	Acc@5 94.556 (95.672)	Mem 24308MB
[2025-01-18 23:23:58 internimage_s_1k_224] (main.py 575): INFO [Epoch:182] * Acc@1 80.456 Acc@5 95.665
[2025-01-18 23:23:58 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.5%
[2025-01-18 23:23:58 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.77%
[2025-01-18 23:24:06 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.700 (8.700)	Loss 0.7081 (0.7081)	Acc@1 84.375 (84.375)	Acc@5 97.534 (97.534)	Mem 24308MB
[2025-01-18 23:24:10 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.169)	Loss 0.9733 (0.8181)	Acc@1 76.587 (81.423)	Acc@5 94.409 (95.925)	Mem 24308MB
[2025-01-18 23:24:11 internimage_s_1k_224] (main.py 575): INFO [Epoch:182] * Acc@1 81.298 Acc@5 95.949
[2025-01-18 23:24:11 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.3%
[2025-01-18 23:24:11 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 23:24:13 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 23:24:13 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.30%
[2025-01-18 23:24:15 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][0/312]	eta 0:12:02 lr 0.001349	time 2.3161 (2.3161)	model_time 0.6004 (0.6004)	loss 2.5601 (2.5601)	grad_norm 6.3619 (6.3619/0.0000)	mem 24308MB
[2025-01-18 23:24:21 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][10/312]	eta 0:03:47 lr 0.001349	time 0.5741 (0.7531)	model_time 0.5736 (0.5958)	loss 3.0555 (3.1885)	grad_norm 2.9538 (2.8173/1.3737)	mem 24308MB
[2025-01-18 23:24:27 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][20/312]	eta 0:03:21 lr 0.001348	time 0.5730 (0.6902)	model_time 0.5728 (0.6076)	loss 2.4410 (3.0684)	grad_norm 1.4647 (2.5285/1.0922)	mem 24308MB
[2025-01-18 23:24:33 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][30/312]	eta 0:03:07 lr 0.001347	time 0.6021 (0.6642)	model_time 0.6020 (0.6082)	loss 3.4864 (3.2116)	grad_norm 1.9099 (2.2492/1.0093)	mem 24308MB
[2025-01-18 23:24:40 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][40/312]	eta 0:02:56 lr 0.001347	time 0.5829 (0.6500)	model_time 0.5827 (0.6075)	loss 2.0422 (3.1008)	grad_norm 1.8968 (2.0916/0.9401)	mem 24308MB
[2025-01-18 23:24:45 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][50/312]	eta 0:02:47 lr 0.001346	time 0.5806 (0.6375)	model_time 0.5805 (0.6033)	loss 3.4576 (3.1374)	grad_norm 1.6433 (1.9905/0.8949)	mem 24308MB
[2025-01-18 23:24:52 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][60/312]	eta 0:02:39 lr 0.001346	time 0.7086 (0.6334)	model_time 0.7084 (0.6047)	loss 3.3681 (3.1603)	grad_norm 3.1881 (1.9402/0.8708)	mem 24308MB
[2025-01-18 23:24:58 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][70/312]	eta 0:02:32 lr 0.001345	time 0.5937 (0.6296)	model_time 0.5936 (0.6049)	loss 3.6916 (3.1607)	grad_norm 2.2134 (1.9752/0.8640)	mem 24308MB
[2025-01-18 23:25:04 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][80/312]	eta 0:02:24 lr 0.001344	time 0.5917 (0.6247)	model_time 0.5915 (0.6030)	loss 2.7585 (3.1357)	grad_norm 3.4862 (2.0338/0.8887)	mem 24308MB
[2025-01-18 23:25:09 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][90/312]	eta 0:02:17 lr 0.001344	time 0.6374 (0.6209)	model_time 0.6370 (0.6015)	loss 3.7719 (3.1139)	grad_norm 1.4171 (2.0016/0.8642)	mem 24308MB
[2025-01-18 23:25:16 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][100/312]	eta 0:02:11 lr 0.001343	time 0.5958 (0.6199)	model_time 0.5953 (0.6023)	loss 3.5292 (3.1138)	grad_norm 1.0981 (1.9612/0.8425)	mem 24308MB
[2025-01-18 23:25:22 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][110/312]	eta 0:02:05 lr 0.001342	time 0.6839 (0.6213)	model_time 0.6834 (0.6052)	loss 2.2368 (3.1323)	grad_norm 1.6135 (1.9802/0.8520)	mem 24308MB
[2025-01-18 23:25:28 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][120/312]	eta 0:01:59 lr 0.001342	time 0.6811 (0.6221)	model_time 0.6809 (0.6073)	loss 3.3703 (3.1291)	grad_norm 2.3643 (2.0189/0.8728)	mem 24308MB
[2025-01-18 23:25:34 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][130/312]	eta 0:01:53 lr 0.001341	time 0.6017 (0.6211)	model_time 0.6015 (0.6074)	loss 2.0379 (3.1103)	grad_norm 2.3576 (2.0778/0.8870)	mem 24308MB
[2025-01-18 23:25:41 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][140/312]	eta 0:01:46 lr 0.001341	time 0.5859 (0.6213)	model_time 0.5858 (0.6086)	loss 2.4625 (3.1043)	grad_norm 2.8721 (2.1002/0.8998)	mem 24308MB
[2025-01-18 23:25:47 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][150/312]	eta 0:01:40 lr 0.001340	time 0.6824 (0.6204)	model_time 0.6822 (0.6085)	loss 3.1399 (3.0887)	grad_norm 1.1901 (2.0983/0.8847)	mem 24308MB
[2025-01-18 23:25:53 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][160/312]	eta 0:01:34 lr 0.001339	time 0.5828 (0.6197)	model_time 0.5823 (0.6085)	loss 3.6820 (3.0938)	grad_norm 1.7863 (2.0813/0.8658)	mem 24308MB
[2025-01-18 23:25:59 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][170/312]	eta 0:01:27 lr 0.001339	time 0.5776 (0.6189)	model_time 0.5771 (0.6083)	loss 2.6642 (3.0982)	grad_norm 4.3872 (2.1328/0.8998)	mem 24308MB
[2025-01-18 23:26:05 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][180/312]	eta 0:01:21 lr 0.001338	time 0.5729 (0.6178)	model_time 0.5725 (0.6078)	loss 3.5217 (3.1051)	grad_norm 2.3500 (2.1553/0.8966)	mem 24308MB
[2025-01-18 23:26:11 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][190/312]	eta 0:01:15 lr 0.001337	time 0.5980 (0.6172)	model_time 0.5978 (0.6077)	loss 3.6331 (3.1093)	grad_norm 1.7464 (2.1314/0.8915)	mem 24308MB
[2025-01-18 23:26:17 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][200/312]	eta 0:01:08 lr 0.001337	time 0.5892 (0.6159)	model_time 0.5891 (0.6069)	loss 2.2255 (3.0976)	grad_norm 1.3980 (2.0913/0.8894)	mem 24308MB
[2025-01-18 23:26:23 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][210/312]	eta 0:01:02 lr 0.001336	time 0.6111 (0.6149)	model_time 0.6107 (0.6063)	loss 3.1406 (3.1097)	grad_norm 2.1116 (2.0694/0.8800)	mem 24308MB
[2025-01-18 23:26:29 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][220/312]	eta 0:00:56 lr 0.001336	time 0.5827 (0.6145)	model_time 0.5825 (0.6062)	loss 2.3785 (3.1211)	grad_norm 1.9262 (2.0784/0.8767)	mem 24308MB
[2025-01-18 23:26:35 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][230/312]	eta 0:00:50 lr 0.001335	time 0.5881 (0.6154)	model_time 0.5877 (0.6074)	loss 3.0962 (3.1360)	grad_norm 1.0285 (2.0638/0.8690)	mem 24308MB
[2025-01-18 23:26:41 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][240/312]	eta 0:00:44 lr 0.001334	time 0.5765 (0.6152)	model_time 0.5764 (0.6076)	loss 3.8073 (3.1340)	grad_norm 2.7386 (2.0666/0.8604)	mem 24308MB
[2025-01-18 23:26:47 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][250/312]	eta 0:00:38 lr 0.001334	time 0.6837 (0.6154)	model_time 0.6833 (0.6081)	loss 2.1677 (3.1325)	grad_norm 2.9403 (2.0639/0.8510)	mem 24308MB
[2025-01-18 23:26:54 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][260/312]	eta 0:00:32 lr 0.001333	time 0.5769 (0.6166)	model_time 0.5767 (0.6096)	loss 1.9726 (3.1245)	grad_norm 1.1427 (2.0403/0.8460)	mem 24308MB
[2025-01-18 23:27:00 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][270/312]	eta 0:00:25 lr 0.001332	time 0.6664 (0.6162)	model_time 0.6660 (0.6094)	loss 2.9749 (3.1262)	grad_norm 1.5548 (2.0353/0.8381)	mem 24308MB
[2025-01-18 23:27:06 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][280/312]	eta 0:00:19 lr 0.001332	time 0.5792 (0.6162)	model_time 0.5790 (0.6096)	loss 2.6079 (3.1239)	grad_norm 0.9875 (2.0241/0.8361)	mem 24308MB
[2025-01-18 23:27:12 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][290/312]	eta 0:00:13 lr 0.001331	time 0.5727 (0.6162)	model_time 0.5723 (0.6099)	loss 3.4509 (3.1312)	grad_norm 1.3750 (2.0158/0.8308)	mem 24308MB
[2025-01-18 23:27:18 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][300/312]	eta 0:00:07 lr 0.001331	time 0.5624 (0.6154)	model_time 0.5620 (0.6093)	loss 2.3369 (3.1220)	grad_norm 1.2151 (2.0104/0.8319)	mem 24308MB
[2025-01-18 23:27:24 internimage_s_1k_224] (main.py 510): INFO Train: [183/300][310/312]	eta 0:00:01 lr 0.001330	time 0.6504 (0.6147)	model_time 0.6503 (0.6087)	loss 3.2900 (3.1225)	grad_norm 2.1736 (1.9854/0.7942)	mem 24308MB
[2025-01-18 23:27:25 internimage_s_1k_224] (main.py 519): INFO EPOCH 183 training takes 0:03:11
[2025-01-18 23:27:25 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_183.pth saving......
[2025-01-18 23:27:27 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_183.pth saved !!!
[2025-01-18 23:27:34 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.559 (7.559)	Loss 0.7911 (0.7911)	Acc@1 83.569 (83.569)	Acc@5 96.948 (96.948)	Mem 24308MB
[2025-01-18 23:27:37 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (0.985)	Loss 1.0351 (0.9056)	Acc@1 77.222 (80.924)	Acc@5 94.653 (95.625)	Mem 24308MB
[2025-01-18 23:27:38 internimage_s_1k_224] (main.py 575): INFO [Epoch:183] * Acc@1 80.802 Acc@5 95.655
[2025-01-18 23:27:38 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.8%
[2025-01-18 23:27:38 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 23:27:40 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 23:27:40 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.80%
[2025-01-18 23:27:47 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.426 (7.426)	Loss 0.7079 (0.7079)	Acc@1 84.399 (84.399)	Acc@5 97.534 (97.534)	Mem 24308MB
[2025-01-18 23:27:50 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.983)	Loss 0.9717 (0.8173)	Acc@1 76.587 (81.443)	Acc@5 94.434 (95.936)	Mem 24308MB
[2025-01-18 23:27:51 internimage_s_1k_224] (main.py 575): INFO [Epoch:183] * Acc@1 81.314 Acc@5 95.961
[2025-01-18 23:27:51 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.3%
[2025-01-18 23:27:51 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 23:27:53 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 23:27:53 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.31%
[2025-01-18 23:27:55 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][0/312]	eta 0:12:07 lr 0.001330	time 2.3318 (2.3318)	model_time 0.6073 (0.6073)	loss 3.7599 (3.7599)	grad_norm 2.4516 (2.4516/0.0000)	mem 24308MB
[2025-01-18 23:28:01 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][10/312]	eta 0:03:47 lr 0.001329	time 0.5899 (0.7535)	model_time 0.5897 (0.5964)	loss 3.2429 (3.3488)	grad_norm 1.7340 (2.2894/0.9804)	mem 24308MB
[2025-01-18 23:28:07 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][20/312]	eta 0:03:17 lr 0.001329	time 0.6260 (0.6762)	model_time 0.6255 (0.5937)	loss 3.2555 (3.1124)	grad_norm 1.2621 (1.8483/0.9495)	mem 24308MB
[2025-01-18 23:28:13 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][30/312]	eta 0:03:04 lr 0.001328	time 0.6335 (0.6534)	model_time 0.6332 (0.5974)	loss 2.7196 (3.1444)	grad_norm 3.0661 (1.8915/0.8795)	mem 24308MB
[2025-01-18 23:28:20 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][40/312]	eta 0:02:56 lr 0.001327	time 0.5951 (0.6481)	model_time 0.5950 (0.6057)	loss 3.7678 (3.1527)	grad_norm 2.0000 (2.0301/1.0254)	mem 24308MB
[2025-01-18 23:28:26 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][50/312]	eta 0:02:47 lr 0.001327	time 0.5930 (0.6391)	model_time 0.5928 (0.6050)	loss 3.0145 (3.1448)	grad_norm 1.2875 (2.1453/1.0323)	mem 24308MB
[2025-01-18 23:28:32 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][60/312]	eta 0:02:39 lr 0.001326	time 0.5759 (0.6334)	model_time 0.5757 (0.6048)	loss 2.0677 (3.0849)	grad_norm 2.5612 (2.1515/1.0004)	mem 24308MB
[2025-01-18 23:28:38 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][70/312]	eta 0:02:33 lr 0.001325	time 0.6447 (0.6331)	model_time 0.6443 (0.6085)	loss 4.0005 (3.0824)	grad_norm 1.1612 (2.0200/0.9837)	mem 24308MB
[2025-01-18 23:28:44 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][80/312]	eta 0:02:26 lr 0.001325	time 0.5869 (0.6294)	model_time 0.5865 (0.6078)	loss 2.2356 (3.0670)	grad_norm 2.0012 (1.9656/0.9403)	mem 24308MB
[2025-01-18 23:28:50 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][90/312]	eta 0:02:20 lr 0.001324	time 0.5899 (0.6309)	model_time 0.5898 (0.6116)	loss 2.6968 (3.0689)	grad_norm 2.1411 (1.9905/0.9404)	mem 24308MB
[2025-01-18 23:28:56 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][100/312]	eta 0:02:12 lr 0.001324	time 0.5895 (0.6273)	model_time 0.5893 (0.6098)	loss 3.5241 (3.0738)	grad_norm 1.2511 (1.9658/0.9016)	mem 24308MB
[2025-01-18 23:29:02 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][110/312]	eta 0:02:06 lr 0.001323	time 0.6800 (0.6250)	model_time 0.6796 (0.6092)	loss 2.4795 (3.0998)	grad_norm 1.6601 (1.9324/0.8772)	mem 24308MB
[2025-01-18 23:29:08 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][120/312]	eta 0:01:59 lr 0.001322	time 0.5971 (0.6232)	model_time 0.5967 (0.6086)	loss 3.2972 (3.0955)	grad_norm 1.4538 (1.9318/0.8813)	mem 24308MB
[2025-01-18 23:29:14 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][130/312]	eta 0:01:53 lr 0.001322	time 0.5719 (0.6211)	model_time 0.5718 (0.6075)	loss 3.5476 (3.1037)	grad_norm 1.0236 (1.9253/0.8648)	mem 24308MB
[2025-01-18 23:29:20 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][140/312]	eta 0:01:46 lr 0.001321	time 0.5822 (0.6189)	model_time 0.5820 (0.6063)	loss 1.9105 (3.0955)	grad_norm 3.8144 (1.9627/0.8931)	mem 24308MB
[2025-01-18 23:29:26 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][150/312]	eta 0:01:40 lr 0.001320	time 0.5993 (0.6176)	model_time 0.5988 (0.6058)	loss 2.5564 (3.1013)	grad_norm 3.3117 (2.0398/0.9957)	mem 24308MB
[2025-01-18 23:29:33 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][160/312]	eta 0:01:34 lr 0.001320	time 0.6735 (0.6189)	model_time 0.6730 (0.6079)	loss 3.2432 (3.1060)	grad_norm 1.8606 (2.0125/0.9789)	mem 24308MB
[2025-01-18 23:29:39 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][170/312]	eta 0:01:27 lr 0.001319	time 0.6503 (0.6189)	model_time 0.6502 (0.6085)	loss 3.4312 (3.1052)	grad_norm 1.2188 (1.9792/0.9637)	mem 24308MB
[2025-01-18 23:29:45 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][180/312]	eta 0:01:21 lr 0.001319	time 0.5741 (0.6184)	model_time 0.5736 (0.6085)	loss 3.4380 (3.1254)	grad_norm 1.7086 (1.9598/0.9482)	mem 24308MB
[2025-01-18 23:29:51 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][190/312]	eta 0:01:15 lr 0.001318	time 0.6582 (0.6193)	model_time 0.6580 (0.6099)	loss 3.9112 (3.1303)	grad_norm 1.6207 (1.9485/0.9303)	mem 24308MB
[2025-01-18 23:29:57 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][200/312]	eta 0:01:09 lr 0.001317	time 0.5845 (0.6180)	model_time 0.5841 (0.6090)	loss 2.9093 (3.1425)	grad_norm 3.0971 (1.9321/0.9196)	mem 24308MB
[2025-01-18 23:30:04 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][210/312]	eta 0:01:03 lr 0.001317	time 0.6595 (0.6190)	model_time 0.6593 (0.6104)	loss 3.5909 (3.1516)	grad_norm 3.0000 (1.9426/0.9236)	mem 24308MB
[2025-01-18 23:30:10 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][220/312]	eta 0:00:56 lr 0.001316	time 0.5738 (0.6185)	model_time 0.5736 (0.6102)	loss 3.3406 (3.1540)	grad_norm 2.9525 (1.9650/0.9228)	mem 24308MB
[2025-01-18 23:30:16 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][230/312]	eta 0:00:50 lr 0.001316	time 0.6729 (0.6175)	model_time 0.6728 (0.6095)	loss 2.8111 (3.1657)	grad_norm 1.7889 (1.9960/0.9380)	mem 24308MB
[2025-01-18 23:30:22 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][240/312]	eta 0:00:44 lr 0.001315	time 0.6072 (0.6169)	model_time 0.6068 (0.6092)	loss 2.2380 (3.1620)	grad_norm 2.1084 (2.0143/0.9383)	mem 24308MB
[2025-01-18 23:30:28 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][250/312]	eta 0:00:38 lr 0.001314	time 0.5815 (0.6162)	model_time 0.5810 (0.6088)	loss 3.8165 (3.1625)	grad_norm 2.7204 (2.0346/0.9546)	mem 24308MB
[2025-01-18 23:30:34 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][260/312]	eta 0:00:31 lr 0.001314	time 0.5860 (0.6151)	model_time 0.5859 (0.6080)	loss 3.4109 (3.1653)	grad_norm 2.0765 (2.0414/0.9438)	mem 24308MB
[2025-01-18 23:30:40 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][270/312]	eta 0:00:25 lr 0.001313	time 0.5931 (0.6145)	model_time 0.5926 (0.6077)	loss 3.6101 (3.1681)	grad_norm 2.9813 (2.0603/0.9500)	mem 24308MB
[2025-01-18 23:30:46 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][280/312]	eta 0:00:19 lr 0.001312	time 0.6028 (0.6153)	model_time 0.6026 (0.6086)	loss 3.4224 (3.1758)	grad_norm 2.8232 (2.0542/0.9414)	mem 24308MB
[2025-01-18 23:30:52 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][290/312]	eta 0:00:13 lr 0.001312	time 0.5801 (0.6150)	model_time 0.5797 (0.6086)	loss 3.8344 (3.1821)	grad_norm 2.4286 (2.0453/0.9323)	mem 24308MB
[2025-01-18 23:30:58 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][300/312]	eta 0:00:07 lr 0.001311	time 0.5691 (0.6145)	model_time 0.5690 (0.6083)	loss 3.1087 (3.1782)	grad_norm 0.9577 (2.0291/0.9243)	mem 24308MB
[2025-01-18 23:31:04 internimage_s_1k_224] (main.py 510): INFO Train: [184/300][310/312]	eta 0:00:01 lr 0.001311	time 0.5680 (0.6141)	model_time 0.5678 (0.6081)	loss 3.1134 (3.1698)	grad_norm 1.4372 (2.0010/0.9128)	mem 24308MB
[2025-01-18 23:31:05 internimage_s_1k_224] (main.py 519): INFO EPOCH 184 training takes 0:03:11
[2025-01-18 23:31:05 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_184.pth saving......
[2025-01-18 23:31:06 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_184.pth saved !!!
[2025-01-18 23:31:14 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.806 (7.806)	Loss 0.8021 (0.8021)	Acc@1 83.936 (83.936)	Acc@5 96.973 (96.973)	Mem 24308MB
[2025-01-18 23:31:18 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.009)	Loss 1.0577 (0.9092)	Acc@1 76.343 (80.824)	Acc@5 94.116 (95.670)	Mem 24308MB
[2025-01-18 23:31:18 internimage_s_1k_224] (main.py 575): INFO [Epoch:184] * Acc@1 80.710 Acc@5 95.705
[2025-01-18 23:31:18 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.7%
[2025-01-18 23:31:18 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.80%
[2025-01-18 23:31:26 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.590 (8.590)	Loss 0.7077 (0.7077)	Acc@1 84.399 (84.399)	Acc@5 97.510 (97.510)	Mem 24308MB
[2025-01-18 23:31:31 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.172)	Loss 0.9702 (0.8166)	Acc@1 76.636 (81.501)	Acc@5 94.482 (95.932)	Mem 24308MB
[2025-01-18 23:31:31 internimage_s_1k_224] (main.py 575): INFO [Epoch:184] * Acc@1 81.370 Acc@5 95.967
[2025-01-18 23:31:31 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.4%
[2025-01-18 23:31:31 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 23:31:33 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 23:31:33 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.37%
[2025-01-18 23:31:35 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][0/312]	eta 0:11:38 lr 0.001310	time 2.2396 (2.2396)	model_time 0.6006 (0.6006)	loss 2.5116 (2.5116)	grad_norm 1.6565 (1.6565/0.0000)	mem 24308MB
[2025-01-18 23:31:42 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][10/312]	eta 0:03:48 lr 0.001310	time 0.6140 (0.7576)	model_time 0.6138 (0.6084)	loss 3.0890 (3.2244)	grad_norm 4.2182 (3.2281/1.6561)	mem 24308MB
[2025-01-18 23:31:48 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][20/312]	eta 0:03:22 lr 0.001309	time 0.5962 (0.6938)	model_time 0.5960 (0.6154)	loss 3.6182 (3.0821)	grad_norm 1.0355 (2.5541/1.4663)	mem 24308MB
[2025-01-18 23:31:54 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][30/312]	eta 0:03:07 lr 0.001309	time 0.5925 (0.6662)	model_time 0.5923 (0.6130)	loss 3.3939 (3.1501)	grad_norm 0.9833 (2.5055/1.3290)	mem 24308MB
[2025-01-18 23:32:00 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][40/312]	eta 0:02:56 lr 0.001308	time 0.5959 (0.6489)	model_time 0.5954 (0.6086)	loss 3.0849 (3.1242)	grad_norm 1.3067 (2.3733/1.2343)	mem 24308MB
[2025-01-18 23:32:06 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][50/312]	eta 0:02:47 lr 0.001307	time 0.5937 (0.6408)	model_time 0.5935 (0.6084)	loss 3.0345 (3.1617)	grad_norm 3.2077 (2.2735/1.1807)	mem 24308MB
[2025-01-18 23:32:12 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][60/312]	eta 0:02:39 lr 0.001307	time 0.6037 (0.6348)	model_time 0.6036 (0.6076)	loss 2.0101 (3.1534)	grad_norm 1.6188 (2.1386/1.1422)	mem 24308MB
[2025-01-18 23:32:18 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][70/312]	eta 0:02:32 lr 0.001306	time 0.5917 (0.6285)	model_time 0.5912 (0.6050)	loss 3.3429 (3.1776)	grad_norm 1.1375 (2.0654/1.0935)	mem 24308MB
[2025-01-18 23:32:24 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][80/312]	eta 0:02:24 lr 0.001305	time 0.5837 (0.6245)	model_time 0.5835 (0.6039)	loss 3.3300 (3.1979)	grad_norm 2.9003 (2.0857/1.0910)	mem 24308MB
[2025-01-18 23:32:30 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][90/312]	eta 0:02:19 lr 0.001305	time 0.6917 (0.6277)	model_time 0.6915 (0.6093)	loss 3.3391 (3.1750)	grad_norm 0.9431 (2.1462/1.1201)	mem 24308MB
[2025-01-18 23:32:37 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][100/312]	eta 0:02:13 lr 0.001304	time 0.6886 (0.6276)	model_time 0.6884 (0.6110)	loss 3.5365 (3.1668)	grad_norm 1.0268 (2.0889/1.0868)	mem 24308MB
[2025-01-18 23:32:43 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][110/312]	eta 0:02:06 lr 0.001304	time 0.5967 (0.6250)	model_time 0.5965 (0.6099)	loss 3.7666 (3.1504)	grad_norm 1.9457 (2.0585/1.0731)	mem 24308MB
[2025-01-18 23:32:49 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][120/312]	eta 0:02:00 lr 0.001303	time 0.7165 (0.6251)	model_time 0.7160 (0.6112)	loss 3.7246 (3.1407)	grad_norm 1.0463 (2.0439/1.0428)	mem 24308MB
[2025-01-18 23:32:55 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][130/312]	eta 0:01:53 lr 0.001302	time 0.5884 (0.6230)	model_time 0.5882 (0.6102)	loss 3.3475 (3.1586)	grad_norm 1.0206 (2.0428/1.0293)	mem 24308MB
[2025-01-18 23:33:01 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][140/312]	eta 0:01:47 lr 0.001302	time 0.5969 (0.6227)	model_time 0.5967 (0.6107)	loss 3.1635 (3.1451)	grad_norm 1.9583 (2.0207/1.0082)	mem 24308MB
[2025-01-18 23:33:07 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][150/312]	eta 0:01:40 lr 0.001301	time 0.5932 (0.6219)	model_time 0.5930 (0.6107)	loss 3.4659 (3.1242)	grad_norm 1.0432 (2.0217/0.9853)	mem 24308MB
[2025-01-18 23:33:13 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][160/312]	eta 0:01:34 lr 0.001301	time 0.5929 (0.6207)	model_time 0.5927 (0.6102)	loss 3.2490 (3.1037)	grad_norm 1.0544 (2.0401/0.9900)	mem 24308MB
[2025-01-18 23:33:19 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][170/312]	eta 0:01:28 lr 0.001300	time 0.5791 (0.6201)	model_time 0.5789 (0.6102)	loss 2.7521 (3.1163)	grad_norm 2.4891 (2.1099/1.0328)	mem 24308MB
[2025-01-18 23:33:25 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][180/312]	eta 0:01:21 lr 0.001299	time 0.5848 (0.6190)	model_time 0.5846 (0.6096)	loss 2.3903 (3.1142)	grad_norm 3.2637 (2.1378/1.0417)	mem 24308MB
[2025-01-18 23:33:31 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][190/312]	eta 0:01:15 lr 0.001299	time 0.5911 (0.6172)	model_time 0.5906 (0.6083)	loss 3.2972 (3.1097)	grad_norm 1.6552 (2.1208/1.0250)	mem 24308MB
[2025-01-18 23:33:37 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][200/312]	eta 0:01:09 lr 0.001298	time 0.5861 (0.6171)	model_time 0.5860 (0.6086)	loss 3.0613 (3.1120)	grad_norm 1.9846 (2.1000/1.0087)	mem 24308MB
[2025-01-18 23:33:44 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][210/312]	eta 0:01:03 lr 0.001297	time 0.6667 (0.6189)	model_time 0.6665 (0.6108)	loss 2.1128 (3.1066)	grad_norm 3.1188 (2.1035/1.0024)	mem 24308MB
[2025-01-18 23:33:50 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][220/312]	eta 0:00:56 lr 0.001297	time 0.5754 (0.6192)	model_time 0.5752 (0.6114)	loss 2.1610 (3.1059)	grad_norm 3.1740 (2.1191/1.0010)	mem 24308MB
[2025-01-18 23:33:56 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][230/312]	eta 0:00:50 lr 0.001296	time 0.5931 (0.6188)	model_time 0.5929 (0.6113)	loss 2.6077 (3.1178)	grad_norm 1.4713 (2.0991/0.9856)	mem 24308MB
[2025-01-18 23:34:02 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][240/312]	eta 0:00:44 lr 0.001296	time 0.8625 (0.6192)	model_time 0.8623 (0.6120)	loss 3.5977 (3.1212)	grad_norm 1.5071 (2.0673/0.9799)	mem 24308MB
[2025-01-18 23:34:08 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][250/312]	eta 0:00:38 lr 0.001295	time 0.6026 (0.6186)	model_time 0.6024 (0.6117)	loss 2.2399 (3.1237)	grad_norm 1.5400 (2.0439/0.9691)	mem 24308MB
[2025-01-18 23:34:15 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][260/312]	eta 0:00:32 lr 0.001294	time 0.5689 (0.6182)	model_time 0.5687 (0.6115)	loss 3.0794 (3.1204)	grad_norm 1.9149 (2.0227/0.9590)	mem 24308MB
[2025-01-18 23:34:21 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][270/312]	eta 0:00:25 lr 0.001294	time 0.5965 (0.6182)	model_time 0.5964 (0.6118)	loss 3.1514 (3.1178)	grad_norm 1.6659 (2.0140/0.9458)	mem 24308MB
[2025-01-18 23:34:27 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][280/312]	eta 0:00:19 lr 0.001293	time 0.5750 (0.6179)	model_time 0.5748 (0.6117)	loss 3.6666 (3.1132)	grad_norm 4.6234 (2.0205/0.9479)	mem 24308MB
[2025-01-18 23:34:33 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][290/312]	eta 0:00:13 lr 0.001292	time 0.5713 (0.6174)	model_time 0.5712 (0.6114)	loss 2.9300 (3.1155)	grad_norm 1.1053 (2.0019/0.9447)	mem 24308MB
[2025-01-18 23:34:39 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][300/312]	eta 0:00:07 lr 0.001292	time 0.5665 (0.6166)	model_time 0.5664 (0.6108)	loss 3.0442 (3.1157)	grad_norm 1.6624 (1.9996/0.9430)	mem 24308MB
[2025-01-18 23:34:45 internimage_s_1k_224] (main.py 510): INFO Train: [185/300][310/312]	eta 0:00:01 lr 0.001291	time 0.5684 (0.6152)	model_time 0.5683 (0.6096)	loss 3.6801 (3.1182)	grad_norm 3.6691 (1.9870/0.9004)	mem 24308MB
[2025-01-18 23:34:45 internimage_s_1k_224] (main.py 519): INFO EPOCH 185 training takes 0:03:11
[2025-01-18 23:34:45 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_185.pth saving......
[2025-01-18 23:34:47 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_185.pth saved !!!
[2025-01-18 23:34:55 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.723 (7.723)	Loss 0.7535 (0.7535)	Acc@1 83.643 (83.643)	Acc@5 97.095 (97.095)	Mem 24308MB
[2025-01-18 23:34:58 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.013)	Loss 1.0324 (0.8851)	Acc@1 77.124 (81.024)	Acc@5 94.263 (95.657)	Mem 24308MB
[2025-01-18 23:34:58 internimage_s_1k_224] (main.py 575): INFO [Epoch:185] * Acc@1 80.936 Acc@5 95.707
[2025-01-18 23:34:58 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.9%
[2025-01-18 23:34:58 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 23:35:00 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 23:35:00 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.94%
[2025-01-18 23:35:08 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.653 (7.653)	Loss 0.7075 (0.7075)	Acc@1 84.448 (84.448)	Acc@5 97.559 (97.559)	Mem 24308MB
[2025-01-18 23:35:11 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.014)	Loss 0.9684 (0.8158)	Acc@1 76.782 (81.543)	Acc@5 94.434 (95.934)	Mem 24308MB
[2025-01-18 23:35:12 internimage_s_1k_224] (main.py 575): INFO [Epoch:185] * Acc@1 81.412 Acc@5 95.969
[2025-01-18 23:35:12 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.4%
[2025-01-18 23:35:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 23:35:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 23:35:14 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.41%
[2025-01-18 23:35:16 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][0/312]	eta 0:11:40 lr 0.001291	time 2.2462 (2.2462)	model_time 0.6184 (0.6184)	loss 3.7976 (3.7976)	grad_norm 1.2683 (1.2683/0.0000)	mem 24308MB
[2025-01-18 23:35:22 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][10/312]	eta 0:03:46 lr 0.001290	time 0.5920 (0.7512)	model_time 0.5919 (0.6029)	loss 3.5476 (3.3664)	grad_norm 1.7156 (1.6929/0.6281)	mem 24308MB
[2025-01-18 23:35:29 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][20/312]	eta 0:03:22 lr 0.001290	time 0.5892 (0.6926)	model_time 0.5890 (0.6147)	loss 3.3069 (3.4175)	grad_norm 2.2242 (1.6486/0.5586)	mem 24308MB
[2025-01-18 23:35:35 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][30/312]	eta 0:03:08 lr 0.001289	time 0.5732 (0.6690)	model_time 0.5727 (0.6161)	loss 3.3918 (3.3865)	grad_norm 1.6746 (1.7360/0.5990)	mem 24308MB
[2025-01-18 23:35:41 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][40/312]	eta 0:02:58 lr 0.001289	time 0.5954 (0.6552)	model_time 0.5949 (0.6151)	loss 3.4809 (3.3693)	grad_norm 1.7668 (1.6788/0.5469)	mem 24308MB
[2025-01-18 23:35:47 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][50/312]	eta 0:02:49 lr 0.001288	time 0.5870 (0.6480)	model_time 0.5869 (0.6157)	loss 3.6293 (3.3251)	grad_norm 2.1799 (1.8059/0.6878)	mem 24308MB
[2025-01-18 23:35:53 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][60/312]	eta 0:02:41 lr 0.001287	time 0.5801 (0.6408)	model_time 0.5799 (0.6137)	loss 3.5405 (3.2665)	grad_norm 3.5214 (1.9116/0.7422)	mem 24308MB
[2025-01-18 23:35:59 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][70/312]	eta 0:02:34 lr 0.001287	time 0.6206 (0.6367)	model_time 0.6202 (0.6134)	loss 3.4761 (3.2948)	grad_norm 2.0974 (1.9842/0.8012)	mem 24308MB
[2025-01-18 23:36:05 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][80/312]	eta 0:02:26 lr 0.001286	time 0.5849 (0.6327)	model_time 0.5844 (0.6123)	loss 3.5835 (3.2886)	grad_norm 3.1132 (1.9758/0.8021)	mem 24308MB
[2025-01-18 23:36:11 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][90/312]	eta 0:02:19 lr 0.001286	time 0.5804 (0.6287)	model_time 0.5802 (0.6104)	loss 1.9687 (3.2590)	grad_norm 2.6113 (1.9901/0.7909)	mem 24308MB
[2025-01-18 23:36:17 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][100/312]	eta 0:02:12 lr 0.001285	time 0.5721 (0.6265)	model_time 0.5719 (0.6101)	loss 3.5639 (3.2629)	grad_norm 1.7256 (1.9421/0.7874)	mem 24308MB
[2025-01-18 23:36:23 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][110/312]	eta 0:02:06 lr 0.001284	time 0.5753 (0.6240)	model_time 0.5749 (0.6090)	loss 3.6631 (3.2472)	grad_norm 1.4695 (1.9656/0.8084)	mem 24308MB
[2025-01-18 23:36:29 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][120/312]	eta 0:01:59 lr 0.001284	time 0.5742 (0.6210)	model_time 0.5741 (0.6072)	loss 2.6712 (3.1981)	grad_norm 1.2269 (1.9744/0.7896)	mem 24308MB
[2025-01-18 23:36:35 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][130/312]	eta 0:01:52 lr 0.001283	time 0.5809 (0.6189)	model_time 0.5807 (0.6061)	loss 2.4504 (3.1967)	grad_norm 1.5112 (1.9424/0.7770)	mem 24308MB
[2025-01-18 23:36:41 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][140/312]	eta 0:01:46 lr 0.001282	time 0.6775 (0.6203)	model_time 0.6771 (0.6083)	loss 3.0598 (3.1785)	grad_norm 3.4384 (1.9517/0.7785)	mem 24308MB
[2025-01-18 23:36:48 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][150/312]	eta 0:01:40 lr 0.001282	time 0.5867 (0.6199)	model_time 0.5862 (0.6087)	loss 3.8664 (3.1764)	grad_norm 1.5105 (1.9619/0.7906)	mem 24308MB
[2025-01-18 23:36:54 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][160/312]	eta 0:01:34 lr 0.001281	time 0.5777 (0.6200)	model_time 0.5772 (0.6095)	loss 3.2195 (3.1798)	grad_norm 1.2825 (2.0509/0.9405)	mem 24308MB
[2025-01-18 23:37:00 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][170/312]	eta 0:01:28 lr 0.001281	time 0.5776 (0.6197)	model_time 0.5771 (0.6098)	loss 3.8527 (3.1913)	grad_norm 1.3255 (2.0511/0.9377)	mem 24308MB
[2025-01-18 23:37:06 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][180/312]	eta 0:01:21 lr 0.001280	time 0.5848 (0.6195)	model_time 0.5846 (0.6102)	loss 3.0078 (3.1801)	grad_norm 1.6514 (2.0382/0.9310)	mem 24308MB
[2025-01-18 23:37:12 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][190/312]	eta 0:01:15 lr 0.001279	time 0.6619 (0.6194)	model_time 0.6614 (0.6105)	loss 3.0138 (3.1759)	grad_norm 1.2279 (2.0239/0.9226)	mem 24308MB
[2025-01-18 23:37:19 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][200/312]	eta 0:01:09 lr 0.001279	time 0.5804 (0.6196)	model_time 0.5799 (0.6111)	loss 3.3338 (3.1758)	grad_norm 1.8215 (2.0370/0.9110)	mem 24308MB
[2025-01-18 23:37:24 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][210/312]	eta 0:01:03 lr 0.001278	time 0.5781 (0.6183)	model_time 0.5779 (0.6102)	loss 2.8778 (3.1783)	grad_norm 1.9804 (2.0397/0.8982)	mem 24308MB
[2025-01-18 23:37:31 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][220/312]	eta 0:00:56 lr 0.001278	time 0.5868 (0.6180)	model_time 0.5866 (0.6103)	loss 3.1250 (3.1710)	grad_norm 1.8489 (2.0417/0.8858)	mem 24308MB
[2025-01-18 23:37:37 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][230/312]	eta 0:00:50 lr 0.001277	time 0.5791 (0.6173)	model_time 0.5787 (0.6098)	loss 2.7356 (3.1712)	grad_norm 3.9676 (2.0685/0.9098)	mem 24308MB
[2025-01-18 23:37:42 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][240/312]	eta 0:00:44 lr 0.001276	time 0.5843 (0.6160)	model_time 0.5841 (0.6089)	loss 3.4597 (3.1750)	grad_norm 1.7937 (2.1051/0.9498)	mem 24308MB
[2025-01-18 23:37:48 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][250/312]	eta 0:00:38 lr 0.001276	time 0.5626 (0.6150)	model_time 0.5624 (0.6081)	loss 3.2225 (3.1799)	grad_norm 1.0354 (2.0981/0.9421)	mem 24308MB
[2025-01-18 23:37:54 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][260/312]	eta 0:00:31 lr 0.001275	time 0.5841 (0.6146)	model_time 0.5837 (0.6080)	loss 3.4097 (3.1618)	grad_norm 1.4799 (2.1157/0.9366)	mem 24308MB
[2025-01-18 23:38:01 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][270/312]	eta 0:00:25 lr 0.001274	time 0.6725 (0.6153)	model_time 0.6720 (0.6089)	loss 3.1430 (3.1683)	grad_norm 1.1516 (2.0942/0.9330)	mem 24308MB
[2025-01-18 23:38:07 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][280/312]	eta 0:00:19 lr 0.001274	time 0.5820 (0.6153)	model_time 0.5816 (0.6092)	loss 3.7384 (3.1680)	grad_norm 3.0189 (2.1030/0.9389)	mem 24308MB
[2025-01-18 23:38:13 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][290/312]	eta 0:00:13 lr 0.001273	time 0.5938 (0.6148)	model_time 0.5936 (0.6088)	loss 3.0210 (3.1747)	grad_norm 1.8112 (2.1133/0.9373)	mem 24308MB
[2025-01-18 23:38:19 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][300/312]	eta 0:00:07 lr 0.001273	time 0.6458 (0.6146)	model_time 0.6457 (0.6088)	loss 2.7916 (3.1725)	grad_norm 1.4185 (2.1146/0.9287)	mem 24308MB
[2025-01-18 23:38:25 internimage_s_1k_224] (main.py 510): INFO Train: [186/300][310/312]	eta 0:00:01 lr 0.001272	time 0.5744 (0.6135)	model_time 0.5743 (0.6079)	loss 2.9258 (3.1720)	grad_norm 1.6547 (2.1189/0.9273)	mem 24308MB
[2025-01-18 23:38:25 internimage_s_1k_224] (main.py 519): INFO EPOCH 186 training takes 0:03:11
[2025-01-18 23:38:25 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_186.pth saving......
[2025-01-18 23:38:27 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_186.pth saved !!!
[2025-01-18 23:38:41 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 13.112 (13.112)	Loss 0.7745 (0.7745)	Acc@1 84.131 (84.131)	Acc@5 97.217 (97.217)	Mem 24308MB
[2025-01-18 23:38:47 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (1.771)	Loss 1.0468 (0.8926)	Acc@1 76.636 (81.106)	Acc@5 93.994 (95.708)	Mem 24308MB
[2025-01-18 23:38:47 internimage_s_1k_224] (main.py 575): INFO [Epoch:186] * Acc@1 80.990 Acc@5 95.719
[2025-01-18 23:38:47 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.0%
[2025-01-18 23:38:47 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 23:38:49 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 23:38:49 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 80.99%
[2025-01-18 23:39:02 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 13.329 (13.329)	Loss 0.7076 (0.7076)	Acc@1 84.521 (84.521)	Acc@5 97.559 (97.559)	Mem 24308MB
[2025-01-18 23:39:09 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.832)	Loss 0.9668 (0.8150)	Acc@1 76.953 (81.612)	Acc@5 94.434 (95.949)	Mem 24308MB
[2025-01-18 23:39:09 internimage_s_1k_224] (main.py 575): INFO [Epoch:186] * Acc@1 81.478 Acc@5 95.989
[2025-01-18 23:39:09 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.5%
[2025-01-18 23:39:09 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 23:39:11 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 23:39:11 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.48%
[2025-01-18 23:39:13 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][0/312]	eta 0:10:50 lr 0.001272	time 2.0854 (2.0854)	model_time 0.5942 (0.5942)	loss 3.0118 (3.0118)	grad_norm 1.7590 (1.7590/0.0000)	mem 24308MB
[2025-01-18 23:39:19 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][10/312]	eta 0:03:42 lr 0.001271	time 0.5856 (0.7380)	model_time 0.5855 (0.6021)	loss 2.1666 (3.0159)	grad_norm 1.2651 (2.0691/0.4937)	mem 24308MB
[2025-01-18 23:39:25 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][20/312]	eta 0:03:15 lr 0.001271	time 0.6723 (0.6710)	model_time 0.6721 (0.5996)	loss 3.2095 (3.0868)	grad_norm 2.9268 (2.2764/0.8248)	mem 24308MB
[2025-01-18 23:39:32 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][30/312]	eta 0:03:03 lr 0.001270	time 0.5818 (0.6513)	model_time 0.5814 (0.6028)	loss 2.8304 (3.0383)	grad_norm 1.1510 (2.1174/0.7801)	mem 24308MB
[2025-01-18 23:39:38 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][40/312]	eta 0:02:54 lr 0.001269	time 0.6084 (0.6403)	model_time 0.6081 (0.6036)	loss 3.1837 (3.0773)	grad_norm 3.1577 (2.0664/0.7761)	mem 24308MB
[2025-01-18 23:39:44 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][50/312]	eta 0:02:45 lr 0.001269	time 0.5744 (0.6306)	model_time 0.5739 (0.6009)	loss 2.4878 (3.0288)	grad_norm 1.8107 (2.0780/0.7633)	mem 24308MB
[2025-01-18 23:39:49 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][60/312]	eta 0:02:37 lr 0.001268	time 0.5922 (0.6248)	model_time 0.5920 (0.6000)	loss 2.3377 (3.0296)	grad_norm 1.0006 (1.9867/0.7546)	mem 24308MB
[2025-01-18 23:39:56 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][70/312]	eta 0:02:31 lr 0.001268	time 0.8681 (0.6261)	model_time 0.8679 (0.6047)	loss 2.1388 (3.0434)	grad_norm 0.7623 (1.8893/0.7544)	mem 24308MB
[2025-01-18 23:40:02 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][80/312]	eta 0:02:25 lr 0.001267	time 0.6833 (0.6278)	model_time 0.6828 (0.6090)	loss 2.8647 (3.0336)	grad_norm 4.1903 (1.9474/0.8095)	mem 24308MB
[2025-01-18 23:40:08 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][90/312]	eta 0:02:18 lr 0.001266	time 0.5850 (0.6247)	model_time 0.5848 (0.6079)	loss 3.5870 (3.0972)	grad_norm 2.5945 (1.8948/0.7924)	mem 24308MB
[2025-01-18 23:40:14 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][100/312]	eta 0:02:12 lr 0.001266	time 0.5721 (0.6229)	model_time 0.5719 (0.6077)	loss 3.4708 (3.1159)	grad_norm 3.7860 (1.9364/0.7999)	mem 24308MB
[2025-01-18 23:40:20 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][110/312]	eta 0:02:05 lr 0.001265	time 0.6153 (0.6226)	model_time 0.6151 (0.6087)	loss 2.8542 (3.1012)	grad_norm 1.5850 (1.9409/0.8070)	mem 24308MB
[2025-01-18 23:40:26 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][120/312]	eta 0:01:59 lr 0.001264	time 0.6663 (0.6208)	model_time 0.6661 (0.6081)	loss 2.8217 (3.1231)	grad_norm 3.0996 (2.0085/0.8662)	mem 24308MB
[2025-01-18 23:40:32 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][130/312]	eta 0:01:52 lr 0.001264	time 0.5855 (0.6189)	model_time 0.5854 (0.6071)	loss 3.0569 (3.1434)	grad_norm 1.7172 (1.9689/0.8574)	mem 24308MB
[2025-01-18 23:40:38 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][140/312]	eta 0:01:46 lr 0.001263	time 0.5827 (0.6166)	model_time 0.5821 (0.6056)	loss 2.9396 (3.1369)	grad_norm 1.5397 (1.9439/0.8347)	mem 24308MB
[2025-01-18 23:40:44 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][150/312]	eta 0:01:39 lr 0.001263	time 0.5825 (0.6152)	model_time 0.5824 (0.6050)	loss 3.6428 (3.1496)	grad_norm 1.1916 (1.9254/0.8200)	mem 24308MB
[2025-01-18 23:40:50 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][160/312]	eta 0:01:33 lr 0.001262	time 0.6011 (0.6147)	model_time 0.6007 (0.6051)	loss 3.8900 (3.1547)	grad_norm 1.3158 (1.9611/0.8924)	mem 24308MB
[2025-01-18 23:40:56 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][170/312]	eta 0:01:27 lr 0.001261	time 0.5909 (0.6129)	model_time 0.5904 (0.6038)	loss 2.3313 (3.1537)	grad_norm 2.2872 (1.9859/0.9013)	mem 24308MB
[2025-01-18 23:41:02 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][180/312]	eta 0:01:20 lr 0.001261	time 0.5647 (0.6116)	model_time 0.5645 (0.6030)	loss 3.4437 (3.1438)	grad_norm 1.6290 (1.9869/0.9093)	mem 24308MB
[2025-01-18 23:41:08 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][190/312]	eta 0:01:14 lr 0.001260	time 0.6706 (0.6119)	model_time 0.6701 (0.6037)	loss 3.0586 (3.1416)	grad_norm 3.2290 (1.9895/0.8961)	mem 24308MB
[2025-01-18 23:41:14 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][200/312]	eta 0:01:08 lr 0.001260	time 0.5995 (0.6125)	model_time 0.5990 (0.6047)	loss 2.9298 (3.1393)	grad_norm 1.5443 (1.9932/0.8830)	mem 24308MB
[2025-01-18 23:41:21 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][210/312]	eta 0:01:02 lr 0.001259	time 0.5869 (0.6127)	model_time 0.5868 (0.6053)	loss 3.3271 (3.1225)	grad_norm 1.0705 (1.9857/0.8708)	mem 24308MB
[2025-01-18 23:41:27 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][220/312]	eta 0:00:56 lr 0.001258	time 0.6604 (0.6128)	model_time 0.6600 (0.6056)	loss 2.6144 (3.1181)	grad_norm 1.4399 (1.9731/0.8600)	mem 24308MB
[2025-01-18 23:41:33 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][230/312]	eta 0:00:50 lr 0.001258	time 0.5909 (0.6130)	model_time 0.5905 (0.6061)	loss 3.5384 (3.1197)	grad_norm 2.9558 (1.9781/0.8538)	mem 24308MB
[2025-01-18 23:41:39 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][240/312]	eta 0:00:44 lr 0.001257	time 0.5922 (0.6133)	model_time 0.5920 (0.6067)	loss 3.3311 (3.1190)	grad_norm 1.9564 (1.9908/0.8535)	mem 24308MB
[2025-01-18 23:41:45 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][250/312]	eta 0:00:38 lr 0.001257	time 0.6705 (0.6136)	model_time 0.6703 (0.6073)	loss 3.3957 (3.1160)	grad_norm 1.8502 (1.9882/0.8489)	mem 24308MB
[2025-01-18 23:41:51 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][260/312]	eta 0:00:31 lr 0.001256	time 0.5851 (0.6124)	model_time 0.5849 (0.6063)	loss 3.6064 (3.1126)	grad_norm 1.4750 (1.9879/0.8427)	mem 24308MB
[2025-01-18 23:41:57 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][270/312]	eta 0:00:25 lr 0.001255	time 0.5794 (0.6121)	model_time 0.5792 (0.6062)	loss 2.2691 (3.1188)	grad_norm 2.5115 (2.0207/0.8573)	mem 24308MB
[2025-01-18 23:42:03 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][280/312]	eta 0:00:19 lr 0.001255	time 0.5907 (0.6118)	model_time 0.5906 (0.6061)	loss 2.7963 (3.1031)	grad_norm 1.7563 (2.0342/0.8584)	mem 24308MB
[2025-01-18 23:42:09 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][290/312]	eta 0:00:13 lr 0.001254	time 0.5685 (0.6112)	model_time 0.5683 (0.6057)	loss 3.6599 (3.1038)	grad_norm 2.6629 (2.0522/0.8890)	mem 24308MB
[2025-01-18 23:42:15 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][300/312]	eta 0:00:07 lr 0.001253	time 0.6380 (0.6106)	model_time 0.6379 (0.6052)	loss 3.0500 (3.1046)	grad_norm 4.4120 (2.0723/0.8965)	mem 24308MB
[2025-01-18 23:42:21 internimage_s_1k_224] (main.py 510): INFO Train: [187/300][310/312]	eta 0:00:01 lr 0.001253	time 0.5719 (0.6096)	model_time 0.5718 (0.6044)	loss 3.2589 (3.1027)	grad_norm 1.9891 (2.0604/0.8973)	mem 24308MB
[2025-01-18 23:42:22 internimage_s_1k_224] (main.py 519): INFO EPOCH 187 training takes 0:03:10
[2025-01-18 23:42:22 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_187.pth saving......
[2025-01-18 23:42:23 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_187.pth saved !!!
[2025-01-18 23:42:37 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 13.181 (13.181)	Loss 0.7817 (0.7817)	Acc@1 83.984 (83.984)	Acc@5 96.899 (96.899)	Mem 24308MB
[2025-01-18 23:42:43 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.813)	Loss 1.0367 (0.8899)	Acc@1 77.295 (81.148)	Acc@5 94.385 (95.801)	Mem 24308MB
[2025-01-18 23:42:44 internimage_s_1k_224] (main.py 575): INFO [Epoch:187] * Acc@1 81.040 Acc@5 95.821
[2025-01-18 23:42:44 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.0%
[2025-01-18 23:42:44 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 23:42:46 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 23:42:46 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.04%
[2025-01-18 23:42:58 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 12.728 (12.728)	Loss 0.7077 (0.7077)	Acc@1 84.473 (84.473)	Acc@5 97.607 (97.607)	Mem 24308MB
[2025-01-18 23:43:05 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.793)	Loss 0.9654 (0.8143)	Acc@1 76.929 (81.652)	Acc@5 94.507 (95.965)	Mem 24308MB
[2025-01-18 23:43:06 internimage_s_1k_224] (main.py 575): INFO [Epoch:187] * Acc@1 81.518 Acc@5 96.003
[2025-01-18 23:43:06 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.5%
[2025-01-18 23:43:06 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 23:43:08 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 23:43:08 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.52%
[2025-01-18 23:43:10 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][0/312]	eta 0:11:54 lr 0.001253	time 2.2912 (2.2912)	model_time 0.6037 (0.6037)	loss 3.0315 (3.0315)	grad_norm 1.7134 (1.7134/0.0000)	mem 24308MB
[2025-01-18 23:43:16 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][10/312]	eta 0:03:53 lr 0.001252	time 0.5705 (0.7717)	model_time 0.5703 (0.6180)	loss 3.0372 (3.1237)	grad_norm 0.8464 (1.4383/0.3904)	mem 24308MB
[2025-01-18 23:43:22 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][20/312]	eta 0:03:24 lr 0.001251	time 0.5837 (0.7001)	model_time 0.5836 (0.6195)	loss 2.9715 (3.2557)	grad_norm 1.9207 (1.8253/0.7497)	mem 24308MB
[2025-01-18 23:43:29 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][30/312]	eta 0:03:09 lr 0.001251	time 0.6512 (0.6719)	model_time 0.6507 (0.6172)	loss 3.4088 (3.2228)	grad_norm 1.2288 (1.8677/0.6551)	mem 24308MB
[2025-01-18 23:43:35 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][40/312]	eta 0:02:58 lr 0.001250	time 0.5653 (0.6566)	model_time 0.5651 (0.6151)	loss 3.5300 (3.1931)	grad_norm 1.7346 (1.8998/0.6310)	mem 24308MB
[2025-01-18 23:43:41 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][50/312]	eta 0:02:48 lr 0.001250	time 0.5769 (0.6444)	model_time 0.5763 (0.6109)	loss 3.1733 (3.2001)	grad_norm 1.9519 (1.8356/0.6005)	mem 24308MB
[2025-01-18 23:43:47 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][60/312]	eta 0:02:41 lr 0.001249	time 0.6834 (0.6416)	model_time 0.6830 (0.6136)	loss 3.4676 (3.2120)	grad_norm 3.3149 (1.8429/0.6256)	mem 24308MB
[2025-01-18 23:43:53 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][70/312]	eta 0:02:33 lr 0.001248	time 0.5904 (0.6343)	model_time 0.5903 (0.6102)	loss 3.3698 (3.1895)	grad_norm 4.4554 (1.8759/0.6612)	mem 24308MB
[2025-01-18 23:43:59 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][80/312]	eta 0:02:25 lr 0.001248	time 0.5818 (0.6293)	model_time 0.5814 (0.6081)	loss 2.6367 (3.1676)	grad_norm 2.3470 (1.9620/0.8577)	mem 24308MB
[2025-01-18 23:44:05 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][90/312]	eta 0:02:19 lr 0.001247	time 0.5812 (0.6275)	model_time 0.5810 (0.6087)	loss 3.2063 (3.1697)	grad_norm 2.0455 (1.9994/0.8300)	mem 24308MB
[2025-01-18 23:44:11 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][100/312]	eta 0:02:12 lr 0.001247	time 0.5813 (0.6237)	model_time 0.5809 (0.6067)	loss 3.6013 (3.1766)	grad_norm 1.0143 (2.0216/0.8437)	mem 24308MB
[2025-01-18 23:44:17 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][110/312]	eta 0:02:05 lr 0.001246	time 0.6738 (0.6212)	model_time 0.6736 (0.6056)	loss 2.8841 (3.1778)	grad_norm 1.2744 (2.0398/0.8337)	mem 24308MB
[2025-01-18 23:44:23 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][120/312]	eta 0:01:58 lr 0.001245	time 0.5826 (0.6190)	model_time 0.5822 (0.6047)	loss 3.4139 (3.1715)	grad_norm 0.9930 (2.1006/0.8931)	mem 24308MB
[2025-01-18 23:44:29 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][130/312]	eta 0:01:52 lr 0.001245	time 0.5754 (0.6192)	model_time 0.5749 (0.6059)	loss 2.4511 (3.1780)	grad_norm 1.6974 (2.1232/0.9016)	mem 24308MB
[2025-01-18 23:44:35 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][140/312]	eta 0:01:46 lr 0.001244	time 0.6617 (0.6199)	model_time 0.6615 (0.6076)	loss 3.2374 (3.1911)	grad_norm 1.8369 (2.0973/0.8827)	mem 24308MB
[2025-01-18 23:44:41 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][150/312]	eta 0:01:40 lr 0.001244	time 0.6612 (0.6196)	model_time 0.6607 (0.6081)	loss 3.3448 (3.1962)	grad_norm 2.2953 (2.0755/0.8672)	mem 24308MB
[2025-01-18 23:44:47 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][160/312]	eta 0:01:34 lr 0.001243	time 0.6553 (0.6191)	model_time 0.6549 (0.6083)	loss 3.4787 (3.1800)	grad_norm 3.9278 (2.1030/0.8711)	mem 24308MB
[2025-01-18 23:44:53 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][170/312]	eta 0:01:27 lr 0.001242	time 0.6120 (0.6187)	model_time 0.6118 (0.6084)	loss 3.3337 (3.1801)	grad_norm 2.4968 (2.1099/0.8687)	mem 24308MB
[2025-01-18 23:45:00 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][180/312]	eta 0:01:21 lr 0.001242	time 0.6748 (0.6185)	model_time 0.6746 (0.6087)	loss 2.3309 (3.1657)	grad_norm 2.5810 (2.1052/0.8577)	mem 24308MB
[2025-01-18 23:45:06 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][190/312]	eta 0:01:15 lr 0.001241	time 0.5923 (0.6173)	model_time 0.5919 (0.6080)	loss 2.9807 (3.1610)	grad_norm 1.5594 (2.1230/0.8692)	mem 24308MB
[2025-01-18 23:45:12 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][200/312]	eta 0:01:09 lr 0.001240	time 0.5749 (0.6163)	model_time 0.5747 (0.6075)	loss 2.9225 (3.1585)	grad_norm 4.5476 (2.1458/0.8811)	mem 24308MB
[2025-01-18 23:45:18 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][210/312]	eta 0:01:02 lr 0.001240	time 0.5709 (0.6165)	model_time 0.5707 (0.6081)	loss 3.7720 (3.1682)	grad_norm 1.0759 (2.1499/0.8858)	mem 24308MB
[2025-01-18 23:45:24 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][220/312]	eta 0:00:56 lr 0.001239	time 0.5886 (0.6151)	model_time 0.5881 (0.6070)	loss 2.8998 (3.1705)	grad_norm 4.5982 (2.1486/0.9011)	mem 24308MB
[2025-01-18 23:45:30 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][230/312]	eta 0:00:50 lr 0.001239	time 0.5969 (0.6140)	model_time 0.5964 (0.6063)	loss 3.0526 (3.1746)	grad_norm 1.4947 (2.1460/0.8983)	mem 24308MB
[2025-01-18 23:45:36 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][240/312]	eta 0:00:44 lr 0.001238	time 0.5778 (0.6139)	model_time 0.5776 (0.6064)	loss 2.9321 (3.1663)	grad_norm 2.2492 (2.1305/0.8937)	mem 24308MB
[2025-01-18 23:45:42 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][250/312]	eta 0:00:38 lr 0.001237	time 0.5840 (0.6143)	model_time 0.5835 (0.6071)	loss 2.4685 (3.1600)	grad_norm 1.6930 (2.1262/0.8855)	mem 24308MB
[2025-01-18 23:45:48 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][260/312]	eta 0:00:31 lr 0.001237	time 0.5749 (0.6143)	model_time 0.5745 (0.6074)	loss 2.6909 (3.1503)	grad_norm 1.1901 (2.1114/0.8771)	mem 24308MB
[2025-01-18 23:45:54 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][270/312]	eta 0:00:25 lr 0.001236	time 0.6598 (0.6145)	model_time 0.6596 (0.6078)	loss 3.2827 (3.1575)	grad_norm 1.7973 (2.0903/0.8693)	mem 24308MB
[2025-01-18 23:46:00 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][280/312]	eta 0:00:19 lr 0.001236	time 0.5935 (0.6142)	model_time 0.5933 (0.6078)	loss 3.1277 (3.1565)	grad_norm 1.7709 (2.0769/0.8586)	mem 24308MB
[2025-01-18 23:46:06 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][290/312]	eta 0:00:13 lr 0.001235	time 0.6925 (0.6143)	model_time 0.6921 (0.6081)	loss 3.2506 (3.1498)	grad_norm 2.8653 (2.0676/0.8532)	mem 24308MB
[2025-01-18 23:46:12 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][300/312]	eta 0:00:07 lr 0.001234	time 0.5656 (0.6137)	model_time 0.5655 (0.6076)	loss 3.5198 (3.1609)	grad_norm 2.2863 (2.0827/0.8548)	mem 24308MB
[2025-01-18 23:46:18 internimage_s_1k_224] (main.py 510): INFO Train: [188/300][310/312]	eta 0:00:01 lr 0.001234	time 0.5738 (0.6131)	model_time 0.5737 (0.6073)	loss 3.5924 (3.1698)	grad_norm 1.6460 (2.1202/0.8599)	mem 24308MB
[2025-01-18 23:46:19 internimage_s_1k_224] (main.py 519): INFO EPOCH 188 training takes 0:03:11
[2025-01-18 23:46:19 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_188.pth saving......
[2025-01-18 23:46:21 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_188.pth saved !!!
[2025-01-18 23:46:29 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.587 (7.587)	Loss 0.7820 (0.7820)	Acc@1 83.838 (83.838)	Acc@5 96.997 (96.997)	Mem 24308MB
[2025-01-18 23:46:32 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (0.999)	Loss 1.0422 (0.9028)	Acc@1 76.636 (80.981)	Acc@5 94.434 (95.803)	Mem 24308MB
[2025-01-18 23:46:32 internimage_s_1k_224] (main.py 575): INFO [Epoch:188] * Acc@1 80.908 Acc@5 95.795
[2025-01-18 23:46:32 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 80.9%
[2025-01-18 23:46:32 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.04%
[2025-01-18 23:46:41 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.009 (9.009)	Loss 0.7076 (0.7076)	Acc@1 84.497 (84.497)	Acc@5 97.607 (97.607)	Mem 24308MB
[2025-01-18 23:46:45 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.198)	Loss 0.9641 (0.8136)	Acc@1 77.051 (81.705)	Acc@5 94.531 (95.978)	Mem 24308MB
[2025-01-18 23:46:46 internimage_s_1k_224] (main.py 575): INFO [Epoch:188] * Acc@1 81.574 Acc@5 96.011
[2025-01-18 23:46:46 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.6%
[2025-01-18 23:46:46 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 23:46:48 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 23:46:48 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.57%
[2025-01-18 23:46:50 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][0/312]	eta 0:09:37 lr 0.001234	time 1.8502 (1.8502)	model_time 0.6068 (0.6068)	loss 2.9869 (2.9869)	grad_norm 1.1960 (1.1960/0.0000)	mem 24308MB
[2025-01-18 23:46:56 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][10/312]	eta 0:03:35 lr 0.001233	time 0.5957 (0.7131)	model_time 0.5955 (0.5997)	loss 3.2536 (3.0046)	grad_norm 1.6516 (1.4365/0.3708)	mem 24308MB
[2025-01-18 23:47:02 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][20/312]	eta 0:03:14 lr 0.001232	time 0.6974 (0.6651)	model_time 0.6970 (0.6054)	loss 3.4025 (3.1466)	grad_norm 2.5177 (1.7273/0.6171)	mem 24308MB
[2025-01-18 23:47:08 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][30/312]	eta 0:03:00 lr 0.001232	time 0.5900 (0.6408)	model_time 0.5898 (0.6003)	loss 2.2978 (3.0706)	grad_norm 1.4232 (1.7192/0.5818)	mem 24308MB
[2025-01-18 23:47:14 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][40/312]	eta 0:02:51 lr 0.001231	time 0.5722 (0.6294)	model_time 0.5718 (0.5986)	loss 3.7235 (3.0776)	grad_norm 1.2176 (1.9568/0.9263)	mem 24308MB
[2025-01-18 23:47:20 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][50/312]	eta 0:02:43 lr 0.001231	time 0.5823 (0.6250)	model_time 0.5822 (0.6002)	loss 2.6611 (3.0922)	grad_norm 4.4125 (2.2138/1.0718)	mem 24308MB
[2025-01-18 23:47:26 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][60/312]	eta 0:02:36 lr 0.001230	time 0.5983 (0.6227)	model_time 0.5979 (0.6020)	loss 3.5868 (3.0927)	grad_norm 1.3258 (2.2349/1.0714)	mem 24308MB
[2025-01-18 23:47:32 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][70/312]	eta 0:02:30 lr 0.001229	time 0.6680 (0.6226)	model_time 0.6675 (0.6047)	loss 3.5080 (3.1030)	grad_norm 1.2988 (2.1426/1.0322)	mem 24308MB
[2025-01-18 23:47:38 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][80/312]	eta 0:02:24 lr 0.001229	time 0.5798 (0.6220)	model_time 0.5796 (0.6062)	loss 2.5860 (3.1130)	grad_norm 1.2304 (2.0867/0.9887)	mem 24308MB
[2025-01-18 23:47:44 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][90/312]	eta 0:02:18 lr 0.001228	time 0.6635 (0.6217)	model_time 0.6633 (0.6076)	loss 2.2375 (3.0930)	grad_norm 3.4809 (2.1036/0.9656)	mem 24308MB
[2025-01-18 23:47:50 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][100/312]	eta 0:02:11 lr 0.001228	time 0.5857 (0.6202)	model_time 0.5855 (0.6075)	loss 3.9506 (3.1059)	grad_norm 1.7404 (2.0891/0.9356)	mem 24308MB
[2025-01-18 23:47:56 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][110/312]	eta 0:02:04 lr 0.001227	time 0.5815 (0.6184)	model_time 0.5813 (0.6068)	loss 3.0601 (3.1303)	grad_norm 1.4909 (2.0564/0.9085)	mem 24308MB
[2025-01-18 23:48:03 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][120/312]	eta 0:01:58 lr 0.001226	time 0.5941 (0.6185)	model_time 0.5937 (0.6079)	loss 3.4167 (3.1297)	grad_norm 1.7973 (2.0341/0.8840)	mem 24308MB
[2025-01-18 23:48:09 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][130/312]	eta 0:01:52 lr 0.001226	time 0.5825 (0.6167)	model_time 0.5824 (0.6068)	loss 2.3720 (3.1143)	grad_norm 1.5154 (1.9773/0.8738)	mem 24308MB
[2025-01-18 23:48:15 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][140/312]	eta 0:01:45 lr 0.001225	time 0.5753 (0.6155)	model_time 0.5752 (0.6062)	loss 3.8523 (3.1144)	grad_norm 1.4079 (1.9567/0.8567)	mem 24308MB
[2025-01-18 23:48:20 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][150/312]	eta 0:01:39 lr 0.001225	time 0.5776 (0.6142)	model_time 0.5774 (0.6055)	loss 3.5498 (3.1300)	grad_norm 1.6921 (1.9831/0.8515)	mem 24308MB
[2025-01-18 23:48:26 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][160/312]	eta 0:01:33 lr 0.001224	time 0.5868 (0.6124)	model_time 0.5866 (0.6042)	loss 3.4534 (3.1398)	grad_norm 1.2334 (1.9891/0.8471)	mem 24308MB
[2025-01-18 23:48:33 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][170/312]	eta 0:01:26 lr 0.001223	time 0.6535 (0.6126)	model_time 0.6534 (0.6048)	loss 2.6005 (3.1313)	grad_norm 1.8183 (1.9756/0.8314)	mem 24308MB
[2025-01-18 23:48:39 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][180/312]	eta 0:01:20 lr 0.001223	time 0.5813 (0.6122)	model_time 0.5809 (0.6049)	loss 2.2311 (3.1193)	grad_norm 2.6783 (1.9542/0.8204)	mem 24308MB
[2025-01-18 23:48:45 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][190/312]	eta 0:01:14 lr 0.001222	time 0.6539 (0.6128)	model_time 0.6538 (0.6059)	loss 3.1826 (3.1326)	grad_norm 2.5703 (1.9455/0.8047)	mem 24308MB
[2025-01-18 23:48:51 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][200/312]	eta 0:01:08 lr 0.001221	time 0.5819 (0.6124)	model_time 0.5815 (0.6057)	loss 3.0327 (3.1334)	grad_norm 3.5722 (2.0153/0.8591)	mem 24308MB
[2025-01-18 23:48:57 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][210/312]	eta 0:01:02 lr 0.001221	time 0.6605 (0.6125)	model_time 0.6603 (0.6061)	loss 3.0501 (3.1381)	grad_norm 1.9080 (2.0464/0.8757)	mem 24308MB
[2025-01-18 23:49:03 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][220/312]	eta 0:00:56 lr 0.001220	time 0.5933 (0.6117)	model_time 0.5931 (0.6056)	loss 3.4015 (3.1294)	grad_norm 1.7529 (2.0343/0.8650)	mem 24308MB
[2025-01-18 23:49:09 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][230/312]	eta 0:00:50 lr 0.001220	time 0.5885 (0.6116)	model_time 0.5880 (0.6058)	loss 3.2694 (3.1364)	grad_norm 2.1026 (2.0157/0.8564)	mem 24308MB
[2025-01-18 23:49:15 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][240/312]	eta 0:00:43 lr 0.001219	time 0.5733 (0.6110)	model_time 0.5731 (0.6054)	loss 3.7134 (3.1437)	grad_norm 2.1890 (1.9989/0.8459)	mem 24308MB
[2025-01-18 23:49:21 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][250/312]	eta 0:00:37 lr 0.001218	time 0.6106 (0.6105)	model_time 0.6102 (0.6052)	loss 3.2870 (3.1501)	grad_norm 1.6722 (1.9983/0.8368)	mem 24308MB
[2025-01-18 23:49:27 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][260/312]	eta 0:00:31 lr 0.001218	time 0.5765 (0.6099)	model_time 0.5763 (0.6047)	loss 2.2781 (3.1515)	grad_norm 1.2371 (1.9715/0.8323)	mem 24308MB
[2025-01-18 23:49:33 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][270/312]	eta 0:00:25 lr 0.001217	time 0.5775 (0.6093)	model_time 0.5773 (0.6043)	loss 2.8872 (3.1540)	grad_norm 0.9909 (1.9560/0.8228)	mem 24308MB
[2025-01-18 23:49:39 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][280/312]	eta 0:00:19 lr 0.001217	time 0.5862 (0.6085)	model_time 0.5860 (0.6037)	loss 3.1861 (3.1506)	grad_norm 1.5701 (1.9395/0.8143)	mem 24308MB
[2025-01-18 23:49:45 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][290/312]	eta 0:00:13 lr 0.001216	time 0.6762 (0.6083)	model_time 0.6760 (0.6036)	loss 2.7941 (3.1427)	grad_norm 3.4423 (1.9509/0.8219)	mem 24308MB
[2025-01-18 23:49:51 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][300/312]	eta 0:00:07 lr 0.001215	time 0.5674 (0.6081)	model_time 0.5673 (0.6036)	loss 2.5813 (3.1470)	grad_norm 2.5791 (1.9769/0.8314)	mem 24308MB
[2025-01-18 23:49:57 internimage_s_1k_224] (main.py 510): INFO Train: [189/300][310/312]	eta 0:00:01 lr 0.001215	time 0.6515 (0.6080)	model_time 0.6515 (0.6036)	loss 3.3236 (3.1407)	grad_norm 1.7953 (1.9959/0.8283)	mem 24308MB
[2025-01-18 23:49:57 internimage_s_1k_224] (main.py 519): INFO EPOCH 189 training takes 0:03:09
[2025-01-18 23:49:57 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_189.pth saving......
[2025-01-18 23:49:59 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_189.pth saved !!!
[2025-01-18 23:50:07 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.548 (7.548)	Loss 0.7636 (0.7636)	Acc@1 83.667 (83.667)	Acc@5 97.070 (97.070)	Mem 24308MB
[2025-01-18 23:50:10 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.003)	Loss 1.0438 (0.8880)	Acc@1 76.904 (81.126)	Acc@5 94.238 (95.696)	Mem 24308MB
[2025-01-18 23:50:10 internimage_s_1k_224] (main.py 575): INFO [Epoch:189] * Acc@1 80.956 Acc@5 95.685
[2025-01-18 23:50:10 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.0%
[2025-01-18 23:50:10 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.04%
[2025-01-18 23:50:19 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.813 (8.813)	Loss 0.7074 (0.7074)	Acc@1 84.595 (84.595)	Acc@5 97.607 (97.607)	Mem 24308MB
[2025-01-18 23:50:23 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.136 (1.176)	Loss 0.9628 (0.8130)	Acc@1 77.124 (81.738)	Acc@5 94.580 (96.009)	Mem 24308MB
[2025-01-18 23:50:24 internimage_s_1k_224] (main.py 575): INFO [Epoch:189] * Acc@1 81.604 Acc@5 96.041
[2025-01-18 23:50:24 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.6%
[2025-01-18 23:50:24 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 23:50:26 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 23:50:26 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.60%
[2025-01-18 23:50:28 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][0/312]	eta 0:13:06 lr 0.001215	time 2.5203 (2.5203)	model_time 0.6133 (0.6133)	loss 3.5370 (3.5370)	grad_norm 1.6974 (1.6974/0.0000)	mem 24308MB
[2025-01-18 23:50:34 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][10/312]	eta 0:03:54 lr 0.001214	time 0.5764 (0.7777)	model_time 0.5763 (0.6041)	loss 3.5123 (3.0268)	grad_norm 2.3297 (1.7710/0.4148)	mem 24308MB
[2025-01-18 23:50:40 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][20/312]	eta 0:03:25 lr 0.001213	time 0.5916 (0.7053)	model_time 0.5911 (0.6141)	loss 3.5759 (2.9693)	grad_norm 1.9307 (1.9762/0.5466)	mem 24308MB
[2025-01-18 23:50:46 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][30/312]	eta 0:03:08 lr 0.001213	time 0.5818 (0.6693)	model_time 0.5817 (0.6074)	loss 2.7936 (3.0423)	grad_norm 2.7408 (2.1496/0.7503)	mem 24308MB
[2025-01-18 23:50:52 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][40/312]	eta 0:02:58 lr 0.001212	time 0.5863 (0.6558)	model_time 0.5861 (0.6088)	loss 3.6830 (3.0824)	grad_norm 2.9186 (2.1289/0.7226)	mem 24308MB
[2025-01-18 23:50:58 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][50/312]	eta 0:02:49 lr 0.001212	time 0.6487 (0.6458)	model_time 0.6485 (0.6080)	loss 3.4772 (3.0975)	grad_norm 1.0775 (2.0390/0.7151)	mem 24308MB
[2025-01-18 23:51:04 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][60/312]	eta 0:02:40 lr 0.001211	time 0.5876 (0.6369)	model_time 0.5871 (0.6052)	loss 3.4463 (3.1073)	grad_norm 4.2397 (2.0465/0.7454)	mem 24308MB
[2025-01-18 23:51:10 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][70/312]	eta 0:02:32 lr 0.001210	time 0.5786 (0.6312)	model_time 0.5784 (0.6039)	loss 3.1177 (3.1305)	grad_norm 2.8537 (2.0712/0.7996)	mem 24308MB
[2025-01-18 23:51:16 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][80/312]	eta 0:02:25 lr 0.001210	time 0.5757 (0.6264)	model_time 0.5755 (0.6024)	loss 2.3183 (3.1440)	grad_norm 1.9072 (2.1287/0.8753)	mem 24308MB
[2025-01-18 23:51:22 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][90/312]	eta 0:02:18 lr 0.001209	time 0.5872 (0.6222)	model_time 0.5870 (0.6009)	loss 2.8393 (3.1511)	grad_norm 1.5085 (2.1254/0.8825)	mem 24308MB
[2025-01-18 23:51:28 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][100/312]	eta 0:02:11 lr 0.001209	time 0.6507 (0.6208)	model_time 0.6505 (0.6015)	loss 3.8914 (3.1716)	grad_norm 2.4535 (2.0907/0.8720)	mem 24308MB
[2025-01-18 23:51:34 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][110/312]	eta 0:02:05 lr 0.001208	time 0.6697 (0.6203)	model_time 0.6695 (0.6027)	loss 3.1183 (3.1788)	grad_norm 2.4163 (2.0733/0.8577)	mem 24308MB
[2025-01-18 23:51:40 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][120/312]	eta 0:01:58 lr 0.001207	time 0.6832 (0.6194)	model_time 0.6830 (0.6032)	loss 2.5826 (3.1755)	grad_norm 1.5263 (2.1225/0.8999)	mem 24308MB
[2025-01-18 23:51:46 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][130/312]	eta 0:01:52 lr 0.001207	time 0.5861 (0.6178)	model_time 0.5859 (0.6029)	loss 2.9949 (3.1664)	grad_norm 2.4629 (2.1025/0.8877)	mem 24308MB
[2025-01-18 23:51:53 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][140/312]	eta 0:01:46 lr 0.001206	time 0.5837 (0.6192)	model_time 0.5836 (0.6053)	loss 3.3236 (3.1694)	grad_norm 2.1019 (2.1054/0.8729)	mem 24308MB
[2025-01-18 23:51:59 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][150/312]	eta 0:01:40 lr 0.001206	time 0.5873 (0.6179)	model_time 0.5868 (0.6049)	loss 3.1145 (3.1637)	grad_norm 1.1102 (2.1116/0.8885)	mem 24308MB
[2025-01-18 23:52:05 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][160/312]	eta 0:01:33 lr 0.001205	time 0.5933 (0.6173)	model_time 0.5928 (0.6050)	loss 3.0668 (3.1575)	grad_norm 1.1300 (2.0655/0.8808)	mem 24308MB
[2025-01-18 23:52:11 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][170/312]	eta 0:01:27 lr 0.001204	time 0.6766 (0.6173)	model_time 0.6765 (0.6057)	loss 3.1579 (3.1596)	grad_norm 3.1797 (2.0877/0.9011)	mem 24308MB
[2025-01-18 23:52:17 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][180/312]	eta 0:01:21 lr 0.001204	time 0.5829 (0.6158)	model_time 0.5828 (0.6049)	loss 3.3193 (3.1381)	grad_norm 2.7139 (2.1424/0.9751)	mem 24308MB
[2025-01-18 23:52:23 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][190/312]	eta 0:01:15 lr 0.001203	time 0.5878 (0.6151)	model_time 0.5872 (0.6047)	loss 2.9262 (3.1314)	grad_norm 1.0920 (2.1422/0.9685)	mem 24308MB
[2025-01-18 23:52:29 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][200/312]	eta 0:01:08 lr 0.001203	time 0.5762 (0.6143)	model_time 0.5757 (0.6044)	loss 3.7703 (3.1290)	grad_norm 1.4315 (2.1250/0.9529)	mem 24308MB
[2025-01-18 23:52:35 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][210/312]	eta 0:01:02 lr 0.001202	time 0.5876 (0.6129)	model_time 0.5875 (0.6034)	loss 3.4622 (3.1358)	grad_norm 2.6766 (2.1080/0.9406)	mem 24308MB
[2025-01-18 23:52:41 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][220/312]	eta 0:00:56 lr 0.001201	time 0.6752 (0.6126)	model_time 0.6747 (0.6036)	loss 3.4626 (3.1398)	grad_norm 1.1371 (2.0897/0.9287)	mem 24308MB
[2025-01-18 23:52:47 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][230/312]	eta 0:00:50 lr 0.001201	time 0.5785 (0.6123)	model_time 0.5781 (0.6036)	loss 2.9602 (3.1393)	grad_norm 1.3691 (2.0727/0.9173)	mem 24308MB
[2025-01-18 23:52:53 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][240/312]	eta 0:00:44 lr 0.001200	time 0.6670 (0.6127)	model_time 0.6669 (0.6044)	loss 2.3248 (3.1545)	grad_norm 3.2527 (2.0931/0.9323)	mem 24308MB
[2025-01-18 23:52:59 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][250/312]	eta 0:00:37 lr 0.001200	time 0.6028 (0.6127)	model_time 0.6026 (0.6047)	loss 3.4080 (3.1644)	grad_norm 0.9675 (2.1049/0.9285)	mem 24308MB
[2025-01-18 23:53:06 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][260/312]	eta 0:00:31 lr 0.001199	time 0.6627 (0.6134)	model_time 0.6622 (0.6057)	loss 2.2774 (3.1554)	grad_norm 2.9539 (2.0907/0.9203)	mem 24308MB
[2025-01-18 23:53:12 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][270/312]	eta 0:00:25 lr 0.001198	time 0.5793 (0.6129)	model_time 0.5791 (0.6054)	loss 3.4549 (3.1509)	grad_norm 1.4744 (2.0773/0.9224)	mem 24308MB
[2025-01-18 23:53:18 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][280/312]	eta 0:00:19 lr 0.001198	time 0.5850 (0.6124)	model_time 0.5848 (0.6052)	loss 2.7502 (3.1618)	grad_norm 5.3453 (2.0976/0.9494)	mem 24308MB
[2025-01-18 23:53:24 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][290/312]	eta 0:00:13 lr 0.001197	time 0.5967 (0.6122)	model_time 0.5962 (0.6052)	loss 3.4041 (3.1595)	grad_norm 3.0040 (2.1148/0.9640)	mem 24308MB
[2025-01-18 23:53:30 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][300/312]	eta 0:00:07 lr 0.001196	time 0.5674 (0.6113)	model_time 0.5673 (0.6046)	loss 3.2775 (3.1590)	grad_norm 2.9824 (2.1160/0.9634)	mem 24308MB
[2025-01-18 23:53:35 internimage_s_1k_224] (main.py 510): INFO Train: [190/300][310/312]	eta 0:00:01 lr 0.001196	time 0.5757 (0.6104)	model_time 0.5756 (0.6039)	loss 3.6748 (3.1594)	grad_norm 1.4704 (2.0991/0.9715)	mem 24308MB
[2025-01-18 23:53:36 internimage_s_1k_224] (main.py 519): INFO EPOCH 190 training takes 0:03:10
[2025-01-18 23:53:36 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_190.pth saving......
[2025-01-18 23:53:38 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_190.pth saved !!!
[2025-01-18 23:53:53 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.554 (15.554)	Loss 0.7833 (0.7833)	Acc@1 84.009 (84.009)	Acc@5 96.997 (96.997)	Mem 24308MB
[2025-01-18 23:53:58 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.842)	Loss 1.0442 (0.8967)	Acc@1 76.392 (81.281)	Acc@5 94.434 (95.794)	Mem 24308MB
[2025-01-18 23:53:58 internimage_s_1k_224] (main.py 575): INFO [Epoch:190] * Acc@1 81.134 Acc@5 95.793
[2025-01-18 23:53:58 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.1%
[2025-01-18 23:53:58 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 23:54:00 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 23:54:00 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.13%
[2025-01-18 23:54:08 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.546 (7.546)	Loss 0.7072 (0.7072)	Acc@1 84.619 (84.619)	Acc@5 97.607 (97.607)	Mem 24308MB
[2025-01-18 23:54:11 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.008)	Loss 0.9614 (0.8122)	Acc@1 77.246 (81.769)	Acc@5 94.580 (96.009)	Mem 24308MB
[2025-01-18 23:54:12 internimage_s_1k_224] (main.py 575): INFO [Epoch:190] * Acc@1 81.632 Acc@5 96.043
[2025-01-18 23:54:12 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.6%
[2025-01-18 23:54:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 23:54:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 23:54:14 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.63%
[2025-01-18 23:54:16 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][0/312]	eta 0:10:37 lr 0.001196	time 2.0441 (2.0441)	model_time 0.6003 (0.6003)	loss 2.9631 (2.9631)	grad_norm 1.9853 (1.9853/0.0000)	mem 24308MB
[2025-01-18 23:54:22 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][10/312]	eta 0:03:41 lr 0.001195	time 0.6068 (0.7326)	model_time 0.6066 (0.6010)	loss 3.3288 (3.2486)	grad_norm 2.3464 (2.2054/0.5168)	mem 24308MB
[2025-01-18 23:54:28 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][20/312]	eta 0:03:14 lr 0.001195	time 0.5717 (0.6648)	model_time 0.5715 (0.5957)	loss 3.2144 (3.0592)	grad_norm 1.7932 (2.4189/0.9064)	mem 24308MB
[2025-01-18 23:54:34 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][30/312]	eta 0:03:02 lr 0.001194	time 0.6748 (0.6469)	model_time 0.6747 (0.5999)	loss 3.9111 (3.1504)	grad_norm 1.3467 (2.2810/0.8782)	mem 24308MB
[2025-01-18 23:54:40 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][40/312]	eta 0:02:54 lr 0.001193	time 0.7094 (0.6404)	model_time 0.7092 (0.6049)	loss 3.8329 (3.2118)	grad_norm 2.4249 (2.1316/0.8398)	mem 24308MB
[2025-01-18 23:54:46 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][50/312]	eta 0:02:46 lr 0.001193	time 0.5743 (0.6347)	model_time 0.5739 (0.6060)	loss 3.5849 (3.1526)	grad_norm 2.2335 (2.0823/0.7843)	mem 24308MB
[2025-01-18 23:54:52 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][60/312]	eta 0:02:38 lr 0.001192	time 0.5762 (0.6305)	model_time 0.5757 (0.6064)	loss 2.5891 (3.1219)	grad_norm 1.5300 (2.0322/0.7490)	mem 24308MB
[2025-01-18 23:54:58 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][70/312]	eta 0:02:32 lr 0.001192	time 0.6767 (0.6296)	model_time 0.6765 (0.6089)	loss 3.0491 (3.0902)	grad_norm 1.2680 (2.1297/0.9992)	mem 24308MB
[2025-01-18 23:55:04 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][80/312]	eta 0:02:25 lr 0.001191	time 0.6106 (0.6264)	model_time 0.6102 (0.6082)	loss 3.8610 (3.0955)	grad_norm 2.2441 (2.1794/1.0047)	mem 24308MB
[2025-01-18 23:55:10 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][90/312]	eta 0:02:18 lr 0.001190	time 0.5899 (0.6234)	model_time 0.5897 (0.6072)	loss 3.6202 (3.0944)	grad_norm 1.6119 (2.0898/0.9960)	mem 24308MB
[2025-01-18 23:55:16 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][100/312]	eta 0:02:11 lr 0.001190	time 0.5933 (0.6213)	model_time 0.5929 (0.6066)	loss 2.9903 (3.0547)	grad_norm 2.7306 (2.0608/0.9612)	mem 24308MB
[2025-01-18 23:55:22 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][110/312]	eta 0:02:05 lr 0.001189	time 0.5777 (0.6189)	model_time 0.5775 (0.6055)	loss 3.2914 (3.0496)	grad_norm 2.1622 (2.1164/0.9875)	mem 24308MB
[2025-01-18 23:55:28 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][120/312]	eta 0:01:58 lr 0.001189	time 0.5987 (0.6172)	model_time 0.5986 (0.6049)	loss 2.9930 (3.0585)	grad_norm 1.4709 (2.1445/0.9843)	mem 24308MB
[2025-01-18 23:55:34 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][130/312]	eta 0:01:52 lr 0.001188	time 0.5718 (0.6155)	model_time 0.5713 (0.6041)	loss 2.3865 (3.0628)	grad_norm 2.8302 (2.1855/0.9806)	mem 24308MB
[2025-01-18 23:55:40 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][140/312]	eta 0:01:45 lr 0.001187	time 0.5835 (0.6135)	model_time 0.5833 (0.6029)	loss 2.6897 (3.0565)	grad_norm 1.0732 (2.1586/0.9691)	mem 24308MB
[2025-01-18 23:55:46 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][150/312]	eta 0:01:39 lr 0.001187	time 0.6645 (0.6135)	model_time 0.6644 (0.6036)	loss 4.0449 (3.0630)	grad_norm 1.8031 (2.1521/0.9622)	mem 24308MB
[2025-01-18 23:55:53 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][160/312]	eta 0:01:33 lr 0.001186	time 0.6630 (0.6149)	model_time 0.6628 (0.6055)	loss 3.3439 (3.0759)	grad_norm 3.0835 (2.1401/0.9433)	mem 24308MB
[2025-01-18 23:55:59 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][170/312]	eta 0:01:27 lr 0.001186	time 0.5855 (0.6148)	model_time 0.5851 (0.6060)	loss 2.1381 (3.0710)	grad_norm 2.6107 (2.1136/0.9283)	mem 24308MB
[2025-01-18 23:56:05 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][180/312]	eta 0:01:21 lr 0.001185	time 0.5890 (0.6140)	model_time 0.5888 (0.6057)	loss 2.7402 (3.0690)	grad_norm 1.4309 (2.1048/0.9148)	mem 24308MB
[2025-01-18 23:56:11 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][190/312]	eta 0:01:14 lr 0.001184	time 0.5809 (0.6139)	model_time 0.5804 (0.6060)	loss 3.3131 (3.0659)	grad_norm 1.8588 (2.0865/0.9064)	mem 24308MB
[2025-01-18 23:56:17 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][200/312]	eta 0:01:08 lr 0.001184	time 0.5932 (0.6142)	model_time 0.5930 (0.6066)	loss 3.0162 (3.0610)	grad_norm 1.9071 (2.0743/0.8903)	mem 24308MB
[2025-01-18 23:56:23 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][210/312]	eta 0:01:02 lr 0.001183	time 0.5989 (0.6136)	model_time 0.5987 (0.6063)	loss 3.3865 (3.0699)	grad_norm 1.6099 (2.0747/0.8976)	mem 24308MB
[2025-01-18 23:56:29 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][220/312]	eta 0:00:56 lr 0.001182	time 0.6121 (0.6132)	model_time 0.6119 (0.6063)	loss 2.3946 (3.0841)	grad_norm 2.7802 (2.0737/0.8847)	mem 24308MB
[2025-01-18 23:56:35 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][230/312]	eta 0:00:50 lr 0.001182	time 0.5811 (0.6123)	model_time 0.5807 (0.6056)	loss 2.9906 (3.0851)	grad_norm 1.1976 (2.0622/0.8799)	mem 24308MB
[2025-01-18 23:56:41 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][240/312]	eta 0:00:44 lr 0.001181	time 0.5748 (0.6114)	model_time 0.5746 (0.6050)	loss 2.0403 (3.0875)	grad_norm 1.2295 (2.0459/0.8751)	mem 24308MB
[2025-01-18 23:56:47 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][250/312]	eta 0:00:37 lr 0.001181	time 0.5856 (0.6108)	model_time 0.5855 (0.6046)	loss 3.1000 (3.0840)	grad_norm 3.0312 (2.0848/0.8957)	mem 24308MB
[2025-01-18 23:56:53 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][260/312]	eta 0:00:31 lr 0.001180	time 0.5914 (0.6098)	model_time 0.5913 (0.6039)	loss 2.0566 (3.0766)	grad_norm 1.1996 (2.0720/0.8909)	mem 24308MB
[2025-01-18 23:56:59 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][270/312]	eta 0:00:25 lr 0.001179	time 0.5818 (0.6094)	model_time 0.5814 (0.6037)	loss 2.1296 (3.0850)	grad_norm 1.2580 (2.0864/0.9204)	mem 24308MB
[2025-01-18 23:57:05 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][280/312]	eta 0:00:19 lr 0.001179	time 0.6736 (0.6096)	model_time 0.6732 (0.6040)	loss 3.5021 (3.0906)	grad_norm 1.8504 (2.1063/0.9347)	mem 24308MB
[2025-01-18 23:57:11 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][290/312]	eta 0:00:13 lr 0.001178	time 0.5840 (0.6097)	model_time 0.5836 (0.6043)	loss 2.8762 (3.0875)	grad_norm 3.1040 (2.1108/0.9400)	mem 24308MB
[2025-01-18 23:57:17 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][300/312]	eta 0:00:07 lr 0.001178	time 0.5831 (0.6097)	model_time 0.5830 (0.6046)	loss 3.8797 (3.0905)	grad_norm 1.6359 (2.1208/0.9371)	mem 24308MB
[2025-01-18 23:57:23 internimage_s_1k_224] (main.py 510): INFO Train: [191/300][310/312]	eta 0:00:01 lr 0.001177	time 0.5705 (0.6093)	model_time 0.5704 (0.6043)	loss 3.8983 (3.0971)	grad_norm 0.9823 (2.0926/0.9432)	mem 24308MB
[2025-01-18 23:57:24 internimage_s_1k_224] (main.py 519): INFO EPOCH 191 training takes 0:03:10
[2025-01-18 23:57:24 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_191.pth saving......
[2025-01-18 23:57:26 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_191.pth saved !!!
[2025-01-18 23:57:34 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.830 (7.830)	Loss 0.7779 (0.7779)	Acc@1 83.838 (83.838)	Acc@5 97.388 (97.388)	Mem 24308MB
[2025-01-18 23:57:37 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.016)	Loss 1.0676 (0.8902)	Acc@1 76.245 (81.334)	Acc@5 94.189 (95.752)	Mem 24308MB
[2025-01-18 23:57:37 internimage_s_1k_224] (main.py 575): INFO [Epoch:191] * Acc@1 81.142 Acc@5 95.747
[2025-01-18 23:57:37 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.1%
[2025-01-18 23:57:37 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-18 23:57:39 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-18 23:57:39 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.14%
[2025-01-18 23:57:47 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.785 (7.785)	Loss 0.7072 (0.7072)	Acc@1 84.644 (84.644)	Acc@5 97.607 (97.607)	Mem 24308MB
[2025-01-18 23:57:52 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.141)	Loss 0.9600 (0.8116)	Acc@1 77.197 (81.785)	Acc@5 94.556 (96.009)	Mem 24308MB
[2025-01-18 23:57:52 internimage_s_1k_224] (main.py 575): INFO [Epoch:191] * Acc@1 81.660 Acc@5 96.047
[2025-01-18 23:57:52 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.7%
[2025-01-18 23:57:52 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-18 23:57:54 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-18 23:57:54 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.66%
[2025-01-18 23:57:56 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][0/312]	eta 0:10:26 lr 0.001177	time 2.0093 (2.0093)	model_time 0.6161 (0.6161)	loss 2.3296 (2.3296)	grad_norm 1.4348 (1.4348/0.0000)	mem 24308MB
[2025-01-18 23:58:02 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][10/312]	eta 0:03:42 lr 0.001176	time 0.5836 (0.7381)	model_time 0.5834 (0.6111)	loss 3.4261 (2.8257)	grad_norm 1.6891 (2.1054/0.6706)	mem 24308MB
[2025-01-18 23:58:08 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][20/312]	eta 0:03:19 lr 0.001176	time 0.5840 (0.6818)	model_time 0.5838 (0.6151)	loss 2.4340 (2.9413)	grad_norm 1.0477 (2.1118/0.6529)	mem 24308MB
[2025-01-18 23:58:14 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][30/312]	eta 0:03:05 lr 0.001175	time 0.5823 (0.6565)	model_time 0.5818 (0.6112)	loss 2.3167 (2.9284)	grad_norm 1.0025 (2.0173/0.6206)	mem 24308MB
[2025-01-18 23:58:20 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][40/312]	eta 0:02:54 lr 0.001175	time 0.5957 (0.6427)	model_time 0.5954 (0.6083)	loss 3.2150 (3.0258)	grad_norm 2.5332 (2.0034/0.5922)	mem 24308MB
[2025-01-18 23:58:26 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][50/312]	eta 0:02:46 lr 0.001174	time 0.5841 (0.6341)	model_time 0.5839 (0.6064)	loss 3.2861 (3.0305)	grad_norm 3.0746 (2.0621/0.6855)	mem 24308MB
[2025-01-18 23:58:32 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][60/312]	eta 0:02:38 lr 0.001173	time 0.5861 (0.6284)	model_time 0.5859 (0.6052)	loss 3.8293 (3.0645)	grad_norm 1.6132 (2.0951/0.6873)	mem 24308MB
[2025-01-18 23:58:38 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][70/312]	eta 0:02:30 lr 0.001173	time 0.5838 (0.6229)	model_time 0.5837 (0.6029)	loss 3.0318 (3.0916)	grad_norm 1.4895 (2.0167/0.6813)	mem 24308MB
[2025-01-18 23:58:44 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][80/312]	eta 0:02:23 lr 0.001172	time 0.6006 (0.6200)	model_time 0.6002 (0.6024)	loss 3.3371 (3.0778)	grad_norm 2.1419 (1.9824/0.6636)	mem 24308MB
[2025-01-18 23:58:50 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][90/312]	eta 0:02:17 lr 0.001172	time 0.5873 (0.6191)	model_time 0.5868 (0.6034)	loss 3.8624 (3.1012)	grad_norm 1.1877 (1.9470/0.6576)	mem 24308MB
[2025-01-18 23:58:57 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][100/312]	eta 0:02:11 lr 0.001171	time 0.6600 (0.6193)	model_time 0.6595 (0.6051)	loss 2.3273 (3.1203)	grad_norm 1.2330 (1.9171/0.6534)	mem 24308MB
[2025-01-18 23:59:03 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][110/312]	eta 0:02:04 lr 0.001170	time 0.6803 (0.6185)	model_time 0.6801 (0.6055)	loss 3.6686 (3.1158)	grad_norm 2.3368 (1.9146/0.6373)	mem 24308MB
[2025-01-18 23:59:09 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][120/312]	eta 0:01:58 lr 0.001170	time 0.5813 (0.6182)	model_time 0.5811 (0.6063)	loss 3.0468 (3.1089)	grad_norm 1.4740 (1.9421/0.6559)	mem 24308MB
[2025-01-18 23:59:15 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][130/312]	eta 0:01:52 lr 0.001169	time 0.5761 (0.6169)	model_time 0.5759 (0.6059)	loss 3.5497 (3.1152)	grad_norm 1.9126 (1.9335/0.6406)	mem 24308MB
[2025-01-18 23:59:21 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][140/312]	eta 0:01:46 lr 0.001169	time 0.6656 (0.6167)	model_time 0.6652 (0.6065)	loss 3.2081 (3.1224)	grad_norm 0.9109 (1.9108/0.6386)	mem 24308MB
[2025-01-18 23:59:27 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][150/312]	eta 0:01:39 lr 0.001168	time 0.6062 (0.6156)	model_time 0.6058 (0.6060)	loss 3.6464 (3.1437)	grad_norm 3.2235 (1.9285/0.6388)	mem 24308MB
[2025-01-18 23:59:33 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][160/312]	eta 0:01:33 lr 0.001167	time 0.5679 (0.6141)	model_time 0.5675 (0.6051)	loss 2.9996 (3.1504)	grad_norm 1.1548 (1.9362/0.6405)	mem 24308MB
[2025-01-18 23:59:39 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][170/312]	eta 0:01:27 lr 0.001167	time 0.5823 (0.6130)	model_time 0.5822 (0.6045)	loss 3.6854 (3.1377)	grad_norm 1.3347 (1.9623/0.6948)	mem 24308MB
[2025-01-18 23:59:45 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][180/312]	eta 0:01:20 lr 0.001166	time 0.5826 (0.6124)	model_time 0.5821 (0.6043)	loss 3.1175 (3.1456)	grad_norm 5.6578 (1.9948/0.7582)	mem 24308MB
[2025-01-18 23:59:51 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][190/312]	eta 0:01:14 lr 0.001166	time 0.5816 (0.6109)	model_time 0.5811 (0.6032)	loss 3.5493 (3.1523)	grad_norm 1.9708 (2.0038/0.7646)	mem 24308MB
[2025-01-18 23:59:57 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][200/312]	eta 0:01:08 lr 0.001165	time 0.5776 (0.6104)	model_time 0.5774 (0.6030)	loss 3.3967 (3.1462)	grad_norm 4.0624 (2.0553/0.8194)	mem 24308MB
[2025-01-19 00:00:03 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][210/312]	eta 0:01:02 lr 0.001164	time 0.5933 (0.6112)	model_time 0.5931 (0.6042)	loss 2.2874 (3.1506)	grad_norm 2.9417 (2.0923/0.8683)	mem 24308MB
[2025-01-19 00:00:09 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][220/312]	eta 0:00:56 lr 0.001164	time 0.6634 (0.6115)	model_time 0.6629 (0.6048)	loss 3.7203 (3.1544)	grad_norm 1.0185 (2.0945/0.8673)	mem 24308MB
[2025-01-19 00:00:15 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][230/312]	eta 0:00:50 lr 0.001163	time 0.5747 (0.6121)	model_time 0.5746 (0.6056)	loss 3.2352 (3.1543)	grad_norm 1.3657 (2.0919/0.8581)	mem 24308MB
[2025-01-19 00:00:22 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][240/312]	eta 0:00:44 lr 0.001163	time 0.5815 (0.6123)	model_time 0.5810 (0.6062)	loss 3.4176 (3.1558)	grad_norm 2.1088 (2.0781/0.8471)	mem 24308MB
[2025-01-19 00:00:28 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][250/312]	eta 0:00:37 lr 0.001162	time 0.5804 (0.6123)	model_time 0.5803 (0.6064)	loss 3.9622 (3.1625)	grad_norm 1.1767 (2.0907/0.8649)	mem 24308MB
[2025-01-19 00:00:34 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][260/312]	eta 0:00:31 lr 0.001161	time 0.5860 (0.6121)	model_time 0.5855 (0.6063)	loss 3.2649 (3.1619)	grad_norm 3.7071 (2.1201/0.8928)	mem 24308MB
[2025-01-19 00:00:40 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][270/312]	eta 0:00:25 lr 0.001161	time 0.5856 (0.6117)	model_time 0.5854 (0.6061)	loss 3.4622 (3.1562)	grad_norm 1.8961 (2.1294/0.8881)	mem 24308MB
[2025-01-19 00:00:46 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][280/312]	eta 0:00:19 lr 0.001160	time 0.5888 (0.6111)	model_time 0.5883 (0.6058)	loss 3.7704 (3.1549)	grad_norm 0.8044 (2.1229/0.8920)	mem 24308MB
[2025-01-19 00:00:52 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][290/312]	eta 0:00:13 lr 0.001160	time 0.5750 (0.6107)	model_time 0.5748 (0.6055)	loss 2.2623 (3.1491)	grad_norm 1.7009 (2.1227/0.8829)	mem 24308MB
[2025-01-19 00:00:58 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][300/312]	eta 0:00:07 lr 0.001159	time 0.5680 (0.6100)	model_time 0.5679 (0.6050)	loss 3.2027 (3.1477)	grad_norm 1.2163 (2.1102/0.8745)	mem 24308MB
[2025-01-19 00:01:03 internimage_s_1k_224] (main.py 510): INFO Train: [192/300][310/312]	eta 0:00:01 lr 0.001158	time 0.5736 (0.6089)	model_time 0.5735 (0.6040)	loss 3.3656 (3.1586)	grad_norm 2.1999 (2.1089/0.8749)	mem 24308MB
[2025-01-19 00:01:04 internimage_s_1k_224] (main.py 519): INFO EPOCH 192 training takes 0:03:09
[2025-01-19 00:01:04 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_192.pth saving......
[2025-01-19 00:01:06 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_192.pth saved !!!
[2025-01-19 00:01:14 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.716 (7.716)	Loss 0.7775 (0.7775)	Acc@1 83.813 (83.813)	Acc@5 97.046 (97.046)	Mem 24308MB
[2025-01-19 00:01:17 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.134 (1.043)	Loss 1.0305 (0.8821)	Acc@1 77.246 (81.308)	Acc@5 94.507 (95.821)	Mem 24308MB
[2025-01-19 00:01:18 internimage_s_1k_224] (main.py 575): INFO [Epoch:192] * Acc@1 81.226 Acc@5 95.851
[2025-01-19 00:01:18 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.2%
[2025-01-19 00:01:18 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:01:19 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:01:20 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.23%
[2025-01-19 00:01:28 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.043 (8.043)	Loss 0.7071 (0.7071)	Acc@1 84.692 (84.692)	Acc@5 97.632 (97.632)	Mem 24308MB
[2025-01-19 00:01:31 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.062)	Loss 0.9589 (0.8110)	Acc@1 77.173 (81.825)	Acc@5 94.629 (96.029)	Mem 24308MB
[2025-01-19 00:01:31 internimage_s_1k_224] (main.py 575): INFO [Epoch:192] * Acc@1 81.702 Acc@5 96.069
[2025-01-19 00:01:31 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.7%
[2025-01-19 00:01:31 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:01:34 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:01:34 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.70%
[2025-01-19 00:01:36 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][0/312]	eta 0:11:28 lr 0.001158	time 2.2077 (2.2077)	model_time 0.6078 (0.6078)	loss 2.5140 (2.5140)	grad_norm 1.4586 (1.4586/0.0000)	mem 24308MB
[2025-01-19 00:01:42 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][10/312]	eta 0:03:51 lr 0.001158	time 0.7692 (0.7667)	model_time 0.7691 (0.6210)	loss 2.5351 (2.9885)	grad_norm 2.2437 (2.1709/0.9754)	mem 24308MB
[2025-01-19 00:01:48 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][20/312]	eta 0:03:20 lr 0.001157	time 0.5794 (0.6875)	model_time 0.5792 (0.6110)	loss 2.5292 (3.1063)	grad_norm 1.7170 (1.9852/0.8543)	mem 24308MB
[2025-01-19 00:01:54 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][30/312]	eta 0:03:08 lr 0.001156	time 0.5806 (0.6697)	model_time 0.5804 (0.6178)	loss 3.5474 (3.1000)	grad_norm 1.5175 (1.9168/0.7769)	mem 24308MB
[2025-01-19 00:02:00 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][40/312]	eta 0:02:58 lr 0.001156	time 0.6919 (0.6579)	model_time 0.6913 (0.6185)	loss 2.4863 (3.1106)	grad_norm 0.7724 (1.8011/0.7233)	mem 24308MB
[2025-01-19 00:02:07 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][50/312]	eta 0:02:50 lr 0.001155	time 0.6649 (0.6509)	model_time 0.6647 (0.6192)	loss 3.6466 (3.1086)	grad_norm 1.8630 (1.8521/0.6730)	mem 24308MB
[2025-01-19 00:02:13 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][60/312]	eta 0:02:42 lr 0.001155	time 0.5889 (0.6449)	model_time 0.5884 (0.6183)	loss 2.6558 (3.0808)	grad_norm 2.1911 (1.7947/0.6482)	mem 24308MB
[2025-01-19 00:02:19 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][70/312]	eta 0:02:34 lr 0.001154	time 0.6480 (0.6384)	model_time 0.6478 (0.6155)	loss 2.6214 (3.0621)	grad_norm 2.4866 (1.8003/0.6260)	mem 24308MB
[2025-01-19 00:02:25 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][80/312]	eta 0:02:27 lr 0.001153	time 0.5866 (0.6342)	model_time 0.5864 (0.6141)	loss 3.2978 (3.1003)	grad_norm 3.2488 (1.8077/0.6547)	mem 24308MB
[2025-01-19 00:02:31 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][90/312]	eta 0:02:19 lr 0.001153	time 0.5958 (0.6302)	model_time 0.5956 (0.6122)	loss 3.4316 (3.0981)	grad_norm 1.3452 (1.8239/0.6855)	mem 24308MB
[2025-01-19 00:02:37 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][100/312]	eta 0:02:12 lr 0.001152	time 0.5812 (0.6267)	model_time 0.5807 (0.6105)	loss 3.2490 (3.0901)	grad_norm 1.7933 (1.8784/0.7716)	mem 24308MB
[2025-01-19 00:02:43 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][110/312]	eta 0:02:06 lr 0.001152	time 0.5873 (0.6242)	model_time 0.5871 (0.6094)	loss 3.4805 (3.0809)	grad_norm 2.9438 (1.9163/0.7741)	mem 24308MB
[2025-01-19 00:02:49 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][120/312]	eta 0:01:59 lr 0.001151	time 0.5787 (0.6211)	model_time 0.5784 (0.6075)	loss 2.4181 (3.0717)	grad_norm 1.1756 (1.9361/0.7964)	mem 24308MB
[2025-01-19 00:02:55 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][130/312]	eta 0:01:52 lr 0.001150	time 0.6711 (0.6197)	model_time 0.6710 (0.6071)	loss 4.1157 (3.0854)	grad_norm 3.1934 (2.0409/0.9960)	mem 24308MB
[2025-01-19 00:03:01 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][140/312]	eta 0:01:46 lr 0.001150	time 0.5858 (0.6191)	model_time 0.5856 (0.6074)	loss 3.1081 (3.0952)	grad_norm 0.9223 (2.0841/1.0021)	mem 24308MB
[2025-01-19 00:03:07 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][150/312]	eta 0:01:40 lr 0.001149	time 0.5914 (0.6191)	model_time 0.5912 (0.6081)	loss 3.5205 (3.0980)	grad_norm 2.4317 (2.0824/1.0018)	mem 24308MB
[2025-01-19 00:03:13 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][160/312]	eta 0:01:34 lr 0.001149	time 0.5792 (0.6188)	model_time 0.5791 (0.6085)	loss 3.2338 (3.0810)	grad_norm 1.4706 (2.0631/0.9839)	mem 24308MB
[2025-01-19 00:03:19 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][170/312]	eta 0:01:27 lr 0.001148	time 0.6707 (0.6192)	model_time 0.6702 (0.6095)	loss 3.8726 (3.0875)	grad_norm 1.3363 (2.0525/0.9765)	mem 24308MB
[2025-01-19 00:03:26 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][180/312]	eta 0:01:21 lr 0.001147	time 0.5793 (0.6196)	model_time 0.5792 (0.6104)	loss 2.5127 (3.0871)	grad_norm 0.9514 (2.0290/0.9656)	mem 24308MB
[2025-01-19 00:03:32 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][190/312]	eta 0:01:15 lr 0.001147	time 0.6643 (0.6187)	model_time 0.6638 (0.6099)	loss 3.6708 (3.0940)	grad_norm 3.4739 (2.0705/0.9713)	mem 24308MB
[2025-01-19 00:03:38 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][200/312]	eta 0:01:09 lr 0.001146	time 0.5635 (0.6180)	model_time 0.5631 (0.6097)	loss 3.2127 (3.0795)	grad_norm 1.5003 (2.0790/0.9570)	mem 24308MB
[2025-01-19 00:03:44 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][210/312]	eta 0:01:02 lr 0.001146	time 0.5753 (0.6169)	model_time 0.5751 (0.6090)	loss 2.9007 (3.0758)	grad_norm 1.1274 (2.0407/0.9512)	mem 24308MB
[2025-01-19 00:03:50 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][220/312]	eta 0:00:56 lr 0.001145	time 0.5875 (0.6162)	model_time 0.5871 (0.6086)	loss 2.2763 (3.0895)	grad_norm 1.7931 (2.0295/0.9379)	mem 24308MB
[2025-01-19 00:03:56 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][230/312]	eta 0:00:50 lr 0.001145	time 0.5846 (0.6156)	model_time 0.5842 (0.6083)	loss 3.7359 (3.0926)	grad_norm 1.4785 (2.0390/0.9325)	mem 24308MB
[2025-01-19 00:04:02 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][240/312]	eta 0:00:44 lr 0.001144	time 0.5955 (0.6144)	model_time 0.5951 (0.6074)	loss 2.2114 (3.0884)	grad_norm 3.0862 (2.0624/0.9319)	mem 24308MB
[2025-01-19 00:04:08 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][250/312]	eta 0:00:38 lr 0.001143	time 0.6647 (0.6144)	model_time 0.6644 (0.6077)	loss 3.3043 (3.0922)	grad_norm 2.1326 (2.0867/0.9442)	mem 24308MB
[2025-01-19 00:04:14 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][260/312]	eta 0:00:31 lr 0.001143	time 0.5836 (0.6146)	model_time 0.5832 (0.6081)	loss 3.1919 (3.0880)	grad_norm 2.4562 (2.0756/0.9366)	mem 24308MB
[2025-01-19 00:04:20 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][270/312]	eta 0:00:25 lr 0.001142	time 0.5938 (0.6143)	model_time 0.5936 (0.6081)	loss 2.1585 (3.0871)	grad_norm 2.0445 (2.0697/0.9320)	mem 24308MB
[2025-01-19 00:04:26 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][280/312]	eta 0:00:19 lr 0.001142	time 0.6824 (0.6146)	model_time 0.6822 (0.6085)	loss 3.7768 (3.0853)	grad_norm 3.5083 (2.0788/0.9281)	mem 24308MB
[2025-01-19 00:04:32 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][290/312]	eta 0:00:13 lr 0.001141	time 0.6638 (0.6150)	model_time 0.6634 (0.6092)	loss 2.3618 (3.0809)	grad_norm 1.4425 (2.0717/0.9213)	mem 24308MB
[2025-01-19 00:04:38 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][300/312]	eta 0:00:07 lr 0.001140	time 0.5713 (0.6144)	model_time 0.5712 (0.6088)	loss 2.8131 (3.0926)	grad_norm 1.7117 (2.0752/0.9135)	mem 24308MB
[2025-01-19 00:04:44 internimage_s_1k_224] (main.py 510): INFO Train: [193/300][310/312]	eta 0:00:01 lr 0.001140	time 0.5655 (0.6136)	model_time 0.5654 (0.6081)	loss 3.7661 (3.0966)	grad_norm 1.1770 (2.0676/0.9096)	mem 24308MB
[2025-01-19 00:04:45 internimage_s_1k_224] (main.py 519): INFO EPOCH 193 training takes 0:03:11
[2025-01-19 00:04:45 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_193.pth saving......
[2025-01-19 00:04:47 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_193.pth saved !!!
[2025-01-19 00:04:55 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.841 (7.841)	Loss 0.7863 (0.7863)	Acc@1 83.838 (83.838)	Acc@5 96.948 (96.948)	Mem 24308MB
[2025-01-19 00:04:58 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.027)	Loss 1.0531 (0.9084)	Acc@1 77.271 (81.279)	Acc@5 94.385 (95.774)	Mem 24308MB
[2025-01-19 00:04:58 internimage_s_1k_224] (main.py 575): INFO [Epoch:193] * Acc@1 81.144 Acc@5 95.807
[2025-01-19 00:04:58 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.1%
[2025-01-19 00:04:58 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.23%
[2025-01-19 00:05:07 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.847 (8.847)	Loss 0.7070 (0.7070)	Acc@1 84.741 (84.741)	Acc@5 97.656 (97.656)	Mem 24308MB
[2025-01-19 00:05:12 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (1.195)	Loss 0.9575 (0.8103)	Acc@1 77.295 (81.876)	Acc@5 94.702 (96.054)	Mem 24308MB
[2025-01-19 00:05:12 internimage_s_1k_224] (main.py 575): INFO [Epoch:193] * Acc@1 81.750 Acc@5 96.093
[2025-01-19 00:05:12 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.7%
[2025-01-19 00:05:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:05:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:05:14 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.75%
[2025-01-19 00:05:16 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][0/312]	eta 0:11:05 lr 0.001140	time 2.1324 (2.1324)	model_time 0.5921 (0.5921)	loss 3.5183 (3.5183)	grad_norm 1.4121 (1.4121/0.0000)	mem 24308MB
[2025-01-19 00:05:22 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][10/312]	eta 0:03:45 lr 0.001139	time 0.5861 (0.7482)	model_time 0.5860 (0.6079)	loss 3.1071 (3.2598)	grad_norm 1.6767 (2.0095/0.6469)	mem 24308MB
[2025-01-19 00:05:28 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][20/312]	eta 0:03:17 lr 0.001138	time 0.5869 (0.6765)	model_time 0.5864 (0.6028)	loss 3.0566 (3.3086)	grad_norm 2.3439 (2.1060/0.6687)	mem 24308MB
[2025-01-19 00:05:34 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][30/312]	eta 0:03:03 lr 0.001138	time 0.5991 (0.6521)	model_time 0.5989 (0.6021)	loss 3.7085 (3.2752)	grad_norm 2.1924 (2.1309/0.6644)	mem 24308MB
[2025-01-19 00:05:40 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][40/312]	eta 0:02:53 lr 0.001137	time 0.5848 (0.6390)	model_time 0.5844 (0.6010)	loss 2.1204 (3.1677)	grad_norm 2.5160 (2.0083/0.6661)	mem 24308MB
[2025-01-19 00:05:46 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][50/312]	eta 0:02:44 lr 0.001137	time 0.5877 (0.6297)	model_time 0.5873 (0.5992)	loss 3.3249 (3.1350)	grad_norm 2.2973 (2.0059/0.6436)	mem 24308MB
[2025-01-19 00:05:52 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][60/312]	eta 0:02:37 lr 0.001136	time 0.6594 (0.6241)	model_time 0.6593 (0.5984)	loss 3.4790 (3.1953)	grad_norm 4.3682 (2.1009/0.7607)	mem 24308MB
[2025-01-19 00:05:58 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][70/312]	eta 0:02:30 lr 0.001135	time 0.6018 (0.6234)	model_time 0.6016 (0.6013)	loss 2.2276 (3.2006)	grad_norm 1.5572 (2.1804/0.8254)	mem 24308MB
[2025-01-19 00:06:04 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][80/312]	eta 0:02:24 lr 0.001135	time 0.6621 (0.6223)	model_time 0.6617 (0.6029)	loss 3.7190 (3.1877)	grad_norm 1.2674 (2.1652/0.8027)	mem 24308MB
[2025-01-19 00:06:11 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][90/312]	eta 0:02:18 lr 0.001134	time 0.5762 (0.6227)	model_time 0.5761 (0.6054)	loss 3.5317 (3.1908)	grad_norm 1.3754 (2.1453/0.7929)	mem 24308MB
[2025-01-19 00:06:17 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][100/312]	eta 0:02:11 lr 0.001134	time 0.5862 (0.6225)	model_time 0.5860 (0.6069)	loss 2.5192 (3.1679)	grad_norm 1.7048 (2.2009/0.8371)	mem 24308MB
[2025-01-19 00:06:23 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][110/312]	eta 0:02:05 lr 0.001133	time 0.5972 (0.6206)	model_time 0.5968 (0.6064)	loss 2.7206 (3.1799)	grad_norm 1.0411 (2.2199/0.8439)	mem 24308MB
[2025-01-19 00:06:29 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][120/312]	eta 0:01:58 lr 0.001132	time 0.6085 (0.6190)	model_time 0.6083 (0.6059)	loss 3.4212 (3.1900)	grad_norm 2.1105 (2.2053/0.8285)	mem 24308MB
[2025-01-19 00:06:35 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][130/312]	eta 0:01:52 lr 0.001132	time 0.5773 (0.6187)	model_time 0.5769 (0.6066)	loss 3.3354 (3.1922)	grad_norm 4.8126 (2.2272/0.8488)	mem 24308MB
[2025-01-19 00:06:41 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][140/312]	eta 0:01:46 lr 0.001131	time 0.5868 (0.6173)	model_time 0.5866 (0.6060)	loss 3.3188 (3.1835)	grad_norm 2.1415 (2.2766/0.8631)	mem 24308MB
[2025-01-19 00:06:47 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][150/312]	eta 0:01:39 lr 0.001131	time 0.6038 (0.6160)	model_time 0.6033 (0.6055)	loss 3.1468 (3.1829)	grad_norm 0.8394 (2.2230/0.8704)	mem 24308MB
[2025-01-19 00:06:53 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][160/312]	eta 0:01:33 lr 0.001130	time 0.5863 (0.6149)	model_time 0.5859 (0.6050)	loss 3.6849 (3.1885)	grad_norm 2.5259 (2.2309/0.8665)	mem 24308MB
[2025-01-19 00:06:59 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][170/312]	eta 0:01:27 lr 0.001130	time 0.5871 (0.6135)	model_time 0.5869 (0.6041)	loss 2.6772 (3.1829)	grad_norm 1.2346 (2.1795/0.8689)	mem 24308MB
[2025-01-19 00:07:05 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][180/312]	eta 0:01:20 lr 0.001129	time 0.6503 (0.6125)	model_time 0.6499 (0.6036)	loss 3.7268 (3.1694)	grad_norm 1.6585 (2.1480/0.8639)	mem 24308MB
[2025-01-19 00:07:11 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][190/312]	eta 0:01:14 lr 0.001128	time 0.5881 (0.6131)	model_time 0.5877 (0.6047)	loss 2.7596 (3.1681)	grad_norm 1.7739 (2.1221/0.8525)	mem 24308MB
[2025-01-19 00:07:17 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][200/312]	eta 0:01:08 lr 0.001128	time 0.6771 (0.6129)	model_time 0.6767 (0.6049)	loss 3.0135 (3.1620)	grad_norm 1.9964 (2.1538/0.8707)	mem 24308MB
[2025-01-19 00:07:23 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][210/312]	eta 0:01:02 lr 0.001127	time 0.6044 (0.6133)	model_time 0.6040 (0.6056)	loss 3.6505 (3.1713)	grad_norm 2.0646 (2.1664/0.8880)	mem 24308MB
[2025-01-19 00:07:30 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][220/312]	eta 0:00:56 lr 0.001127	time 0.5800 (0.6135)	model_time 0.5795 (0.6062)	loss 3.2867 (3.1763)	grad_norm 1.6358 (2.1495/0.8805)	mem 24308MB
[2025-01-19 00:07:36 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][230/312]	eta 0:00:50 lr 0.001126	time 0.5953 (0.6134)	model_time 0.5948 (0.6063)	loss 3.2192 (3.1863)	grad_norm 2.0549 (2.1607/0.8791)	mem 24308MB
[2025-01-19 00:07:42 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][240/312]	eta 0:00:44 lr 0.001125	time 0.6208 (0.6126)	model_time 0.6204 (0.6058)	loss 2.4242 (3.1719)	grad_norm 0.9728 (2.1323/0.8754)	mem 24308MB
[2025-01-19 00:07:48 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][250/312]	eta 0:00:37 lr 0.001125	time 0.5856 (0.6128)	model_time 0.5855 (0.6063)	loss 3.7482 (3.1682)	grad_norm 4.2269 (2.1605/0.9068)	mem 24308MB
[2025-01-19 00:07:54 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][260/312]	eta 0:00:31 lr 0.001124	time 0.6308 (0.6120)	model_time 0.6303 (0.6057)	loss 3.4876 (3.1671)	grad_norm 1.4412 (2.1601/0.9185)	mem 24308MB
[2025-01-19 00:08:00 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][270/312]	eta 0:00:25 lr 0.001124	time 0.6267 (0.6118)	model_time 0.6265 (0.6058)	loss 3.4790 (3.1657)	grad_norm 1.8121 (2.1596/0.9121)	mem 24308MB
[2025-01-19 00:08:06 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][280/312]	eta 0:00:19 lr 0.001123	time 0.5841 (0.6110)	model_time 0.5837 (0.6052)	loss 3.0471 (3.1689)	grad_norm 1.8497 (2.1770/0.9109)	mem 24308MB
[2025-01-19 00:08:12 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][290/312]	eta 0:00:13 lr 0.001122	time 0.5672 (0.6106)	model_time 0.5670 (0.6049)	loss 2.7098 (3.1649)	grad_norm 1.1438 (2.1695/0.9119)	mem 24308MB
[2025-01-19 00:08:17 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][300/312]	eta 0:00:07 lr 0.001122	time 0.5685 (0.6097)	model_time 0.5684 (0.6043)	loss 3.6574 (3.1681)	grad_norm 3.6375 (2.1710/0.9118)	mem 24308MB
[2025-01-19 00:08:23 internimage_s_1k_224] (main.py 510): INFO Train: [194/300][310/312]	eta 0:00:01 lr 0.001121	time 0.5817 (0.6096)	model_time 0.5816 (0.6042)	loss 3.6511 (3.1762)	grad_norm 2.9886 (2.2014/0.9705)	mem 24308MB
[2025-01-19 00:08:24 internimage_s_1k_224] (main.py 519): INFO EPOCH 194 training takes 0:03:10
[2025-01-19 00:08:24 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_194.pth saving......
[2025-01-19 00:08:26 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_194.pth saved !!!
[2025-01-19 00:08:34 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.695 (7.695)	Loss 0.7592 (0.7592)	Acc@1 84.082 (84.082)	Acc@5 97.412 (97.412)	Mem 24308MB
[2025-01-19 00:08:37 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.024)	Loss 1.0420 (0.8876)	Acc@1 77.026 (81.272)	Acc@5 94.189 (95.830)	Mem 24308MB
[2025-01-19 00:08:37 internimage_s_1k_224] (main.py 575): INFO [Epoch:194] * Acc@1 81.122 Acc@5 95.819
[2025-01-19 00:08:37 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.1%
[2025-01-19 00:08:37 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.23%
[2025-01-19 00:08:46 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.891 (8.891)	Loss 0.7069 (0.7069)	Acc@1 84.790 (84.790)	Acc@5 97.632 (97.632)	Mem 24308MB
[2025-01-19 00:08:51 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.193)	Loss 0.9562 (0.8097)	Acc@1 77.271 (81.880)	Acc@5 94.702 (96.056)	Mem 24308MB
[2025-01-19 00:08:51 internimage_s_1k_224] (main.py 575): INFO [Epoch:194] * Acc@1 81.750 Acc@5 96.095
[2025-01-19 00:08:51 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.7%
[2025-01-19 00:08:51 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.75%
[2025-01-19 00:08:54 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][0/312]	eta 0:14:27 lr 0.001121	time 2.7789 (2.7789)	model_time 1.1776 (1.1776)	loss 2.4665 (2.4665)	grad_norm 2.6016 (2.6016/0.0000)	mem 24308MB
[2025-01-19 00:09:00 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][10/312]	eta 0:04:05 lr 0.001121	time 0.6721 (0.8119)	model_time 0.6719 (0.6659)	loss 2.0171 (3.1256)	grad_norm 3.3692 (2.5414/0.8832)	mem 24308MB
[2025-01-19 00:09:06 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][20/312]	eta 0:03:31 lr 0.001120	time 0.7064 (0.7231)	model_time 0.7060 (0.6464)	loss 3.0923 (3.0002)	grad_norm 1.9878 (2.2700/0.7828)	mem 24308MB
[2025-01-19 00:09:12 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][30/312]	eta 0:03:14 lr 0.001119	time 0.5761 (0.6908)	model_time 0.5760 (0.6387)	loss 3.3125 (2.9927)	grad_norm 1.1889 (2.1294/0.8539)	mem 24308MB
[2025-01-19 00:09:18 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][40/312]	eta 0:03:01 lr 0.001119	time 0.5842 (0.6691)	model_time 0.5841 (0.6296)	loss 3.1742 (2.9995)	grad_norm 3.4895 (2.2604/0.9420)	mem 24308MB
[2025-01-19 00:09:24 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][50/312]	eta 0:02:51 lr 0.001118	time 0.5880 (0.6537)	model_time 0.5878 (0.6219)	loss 3.4505 (3.0265)	grad_norm 3.5015 (2.3581/0.9901)	mem 24308MB
[2025-01-19 00:09:30 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][60/312]	eta 0:02:42 lr 0.001118	time 0.5825 (0.6458)	model_time 0.5824 (0.6192)	loss 3.2990 (3.0190)	grad_norm 1.0658 (2.3086/0.9547)	mem 24308MB
[2025-01-19 00:09:36 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][70/312]	eta 0:02:34 lr 0.001117	time 0.5715 (0.6395)	model_time 0.5714 (0.6166)	loss 3.5294 (3.0424)	grad_norm 2.1422 (2.2563/0.9109)	mem 24308MB
[2025-01-19 00:09:42 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][80/312]	eta 0:02:27 lr 0.001116	time 0.6807 (0.6346)	model_time 0.6805 (0.6144)	loss 2.6910 (3.0543)	grad_norm 2.1184 (2.2229/0.9085)	mem 24308MB
[2025-01-19 00:09:48 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][90/312]	eta 0:02:19 lr 0.001116	time 0.7009 (0.6305)	model_time 0.7004 (0.6126)	loss 3.3548 (3.0755)	grad_norm 1.8665 (2.1607/0.8903)	mem 24308MB
[2025-01-19 00:09:54 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][100/312]	eta 0:02:12 lr 0.001115	time 0.5774 (0.6262)	model_time 0.5773 (0.6100)	loss 2.8182 (3.0500)	grad_norm 1.8169 (2.1189/0.8696)	mem 24308MB
[2025-01-19 00:10:00 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][110/312]	eta 0:02:05 lr 0.001115	time 0.5918 (0.6233)	model_time 0.5917 (0.6085)	loss 3.3022 (3.0654)	grad_norm 1.8275 (2.0998/0.8819)	mem 24308MB
[2025-01-19 00:10:07 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][120/312]	eta 0:02:00 lr 0.001114	time 0.6730 (0.6267)	model_time 0.6729 (0.6131)	loss 2.4795 (3.0616)	grad_norm 0.9838 (2.0786/0.8801)	mem 24308MB
[2025-01-19 00:10:13 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][130/312]	eta 0:01:53 lr 0.001113	time 0.6667 (0.6251)	model_time 0.6666 (0.6125)	loss 2.8599 (3.0666)	grad_norm 4.2449 (2.1753/0.9762)	mem 24308MB
[2025-01-19 00:10:19 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][140/312]	eta 0:01:47 lr 0.001113	time 0.5640 (0.6257)	model_time 0.5636 (0.6140)	loss 2.6988 (3.0846)	grad_norm 1.8564 (2.2016/0.9971)	mem 24308MB
[2025-01-19 00:10:25 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][150/312]	eta 0:01:41 lr 0.001112	time 0.6835 (0.6254)	model_time 0.6833 (0.6145)	loss 3.1964 (3.0933)	grad_norm 1.2816 (2.1726/0.9897)	mem 24308MB
[2025-01-19 00:10:31 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][160/312]	eta 0:01:34 lr 0.001112	time 0.6058 (0.6243)	model_time 0.6056 (0.6140)	loss 2.5671 (3.0914)	grad_norm 1.8715 (2.1367/0.9742)	mem 24308MB
[2025-01-19 00:10:37 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][170/312]	eta 0:01:28 lr 0.001111	time 0.5849 (0.6231)	model_time 0.5844 (0.6133)	loss 2.5794 (3.0819)	grad_norm 2.1561 (2.1108/0.9548)	mem 24308MB
[2025-01-19 00:10:43 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][180/312]	eta 0:01:22 lr 0.001110	time 0.5810 (0.6219)	model_time 0.5808 (0.6127)	loss 3.0135 (3.0854)	grad_norm 1.0459 (2.0760/0.9452)	mem 24308MB
[2025-01-19 00:10:49 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][190/312]	eta 0:01:15 lr 0.001110	time 0.5813 (0.6206)	model_time 0.5809 (0.6119)	loss 2.8250 (3.0838)	grad_norm 1.3781 (2.0731/0.9323)	mem 24308MB
[2025-01-19 00:10:55 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][200/312]	eta 0:01:09 lr 0.001109	time 0.6742 (0.6197)	model_time 0.6740 (0.6113)	loss 3.3348 (3.1058)	grad_norm 1.2940 (2.0505/0.9177)	mem 24308MB
[2025-01-19 00:11:01 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][210/312]	eta 0:01:03 lr 0.001109	time 0.6094 (0.6182)	model_time 0.6092 (0.6103)	loss 3.5053 (3.0980)	grad_norm 1.2022 (2.0577/0.9105)	mem 24308MB
[2025-01-19 00:11:07 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][220/312]	eta 0:00:56 lr 0.001108	time 0.5700 (0.6172)	model_time 0.5696 (0.6096)	loss 3.9753 (3.1039)	grad_norm 2.2389 (2.0787/0.9295)	mem 24308MB
[2025-01-19 00:11:13 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][230/312]	eta 0:00:50 lr 0.001108	time 0.5870 (0.6162)	model_time 0.5866 (0.6089)	loss 2.0807 (3.0981)	grad_norm 3.0991 (2.0798/0.9197)	mem 24308MB
[2025-01-19 00:11:19 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][240/312]	eta 0:00:44 lr 0.001107	time 0.5656 (0.6170)	model_time 0.5654 (0.6100)	loss 3.6818 (3.0968)	grad_norm 2.3839 (2.0959/0.9195)	mem 24308MB
[2025-01-19 00:11:26 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][250/312]	eta 0:00:38 lr 0.001106	time 0.5919 (0.6164)	model_time 0.5915 (0.6096)	loss 2.6068 (3.0932)	grad_norm 2.7651 (2.0948/0.9071)	mem 24308MB
[2025-01-19 00:11:32 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][260/312]	eta 0:00:32 lr 0.001106	time 0.6503 (0.6167)	model_time 0.6501 (0.6102)	loss 2.7566 (3.0916)	grad_norm 1.3960 (2.0904/0.9034)	mem 24308MB
[2025-01-19 00:11:38 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][270/312]	eta 0:00:25 lr 0.001105	time 0.5926 (0.6170)	model_time 0.5921 (0.6107)	loss 2.4015 (3.0945)	grad_norm 3.8796 (2.0976/0.9063)	mem 24308MB
[2025-01-19 00:11:44 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][280/312]	eta 0:00:19 lr 0.001105	time 0.5733 (0.6168)	model_time 0.5731 (0.6107)	loss 3.2525 (3.1026)	grad_norm 1.2835 (2.1027/0.9062)	mem 24308MB
[2025-01-19 00:11:50 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][290/312]	eta 0:00:13 lr 0.001104	time 0.5801 (0.6162)	model_time 0.5799 (0.6103)	loss 3.7665 (3.1018)	grad_norm 1.2728 (2.0878/0.8980)	mem 24308MB
[2025-01-19 00:11:56 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][300/312]	eta 0:00:07 lr 0.001103	time 0.5665 (0.6154)	model_time 0.5664 (0.6097)	loss 3.4126 (3.1007)	grad_norm 2.0121 (2.0824/0.8901)	mem 24308MB
[2025-01-19 00:12:02 internimage_s_1k_224] (main.py 510): INFO Train: [195/300][310/312]	eta 0:00:01 lr 0.001103	time 0.5689 (0.6145)	model_time 0.5689 (0.6090)	loss 3.3730 (3.0991)	grad_norm 1.2290 (2.0696/0.8811)	mem 24308MB
[2025-01-19 00:12:02 internimage_s_1k_224] (main.py 519): INFO EPOCH 195 training takes 0:03:11
[2025-01-19 00:12:02 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_195.pth saving......
[2025-01-19 00:12:04 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_195.pth saved !!!
[2025-01-19 00:12:12 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.913 (7.913)	Loss 0.7524 (0.7524)	Acc@1 84.229 (84.229)	Acc@5 97.266 (97.266)	Mem 24308MB
[2025-01-19 00:12:16 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.040)	Loss 1.0214 (0.8737)	Acc@1 77.295 (81.516)	Acc@5 94.678 (95.914)	Mem 24308MB
[2025-01-19 00:12:16 internimage_s_1k_224] (main.py 575): INFO [Epoch:195] * Acc@1 81.426 Acc@5 95.927
[2025-01-19 00:12:16 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.4%
[2025-01-19 00:12:16 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:12:18 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:12:18 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.43%
[2025-01-19 00:12:26 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.299 (8.299)	Loss 0.7067 (0.7067)	Acc@1 84.790 (84.790)	Acc@5 97.656 (97.656)	Mem 24308MB
[2025-01-19 00:12:30 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.075)	Loss 0.9550 (0.8091)	Acc@1 77.344 (81.905)	Acc@5 94.727 (96.074)	Mem 24308MB
[2025-01-19 00:12:30 internimage_s_1k_224] (main.py 575): INFO [Epoch:195] * Acc@1 81.776 Acc@5 96.111
[2025-01-19 00:12:30 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.8%
[2025-01-19 00:12:30 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:12:32 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:12:32 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.78%
[2025-01-19 00:12:34 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][0/312]	eta 0:10:42 lr 0.001103	time 2.0601 (2.0601)	model_time 0.5934 (0.5934)	loss 2.5584 (2.5584)	grad_norm 1.8364 (1.8364/0.0000)	mem 24308MB
[2025-01-19 00:12:40 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][10/312]	eta 0:03:40 lr 0.001102	time 0.5849 (0.7285)	model_time 0.5848 (0.5948)	loss 3.4634 (3.0756)	grad_norm 3.1213 (2.1574/0.5531)	mem 24308MB
[2025-01-19 00:12:46 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][20/312]	eta 0:03:15 lr 0.001101	time 0.6032 (0.6689)	model_time 0.6027 (0.5986)	loss 2.2658 (2.8733)	grad_norm 2.3946 (2.0260/0.7021)	mem 24308MB
[2025-01-19 00:12:52 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][30/312]	eta 0:03:03 lr 0.001101	time 0.7074 (0.6497)	model_time 0.7072 (0.6020)	loss 3.3218 (2.9935)	grad_norm 2.3640 (1.8991/0.6627)	mem 24308MB
[2025-01-19 00:12:58 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][40/312]	eta 0:02:52 lr 0.001100	time 0.5771 (0.6350)	model_time 0.5769 (0.5984)	loss 2.7714 (2.9606)	grad_norm 1.8000 (1.9456/0.7095)	mem 24308MB
[2025-01-19 00:13:05 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][50/312]	eta 0:02:45 lr 0.001100	time 0.5774 (0.6333)	model_time 0.5769 (0.6038)	loss 2.5654 (2.9527)	grad_norm 1.9170 (1.9041/0.6930)	mem 24308MB
[2025-01-19 00:13:11 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][60/312]	eta 0:02:38 lr 0.001099	time 0.6720 (0.6295)	model_time 0.6718 (0.6048)	loss 2.1182 (2.9826)	grad_norm 1.8639 (1.8948/0.6763)	mem 24308MB
[2025-01-19 00:13:17 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][70/312]	eta 0:02:32 lr 0.001099	time 0.6948 (0.6310)	model_time 0.6947 (0.6097)	loss 3.2464 (3.0185)	grad_norm 1.6629 (1.9439/0.6942)	mem 24308MB
[2025-01-19 00:13:23 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][80/312]	eta 0:02:26 lr 0.001098	time 0.6727 (0.6293)	model_time 0.6725 (0.6106)	loss 2.9445 (3.0526)	grad_norm 2.1411 (2.0423/0.8501)	mem 24308MB
[2025-01-19 00:13:29 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][90/312]	eta 0:02:19 lr 0.001097	time 0.5734 (0.6280)	model_time 0.5732 (0.6113)	loss 3.1618 (3.0666)	grad_norm 1.7185 (2.0330/0.8307)	mem 24308MB
[2025-01-19 00:13:35 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][100/312]	eta 0:02:12 lr 0.001097	time 0.5897 (0.6254)	model_time 0.5896 (0.6103)	loss 2.7590 (3.0753)	grad_norm 2.1961 (2.0321/0.8291)	mem 24308MB
[2025-01-19 00:13:41 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][110/312]	eta 0:02:06 lr 0.001096	time 0.6916 (0.6238)	model_time 0.6911 (0.6100)	loss 3.1221 (3.0939)	grad_norm 0.9558 (2.0020/0.8175)	mem 24308MB
[2025-01-19 00:13:47 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][120/312]	eta 0:01:59 lr 0.001096	time 0.5807 (0.6217)	model_time 0.5806 (0.6090)	loss 3.7285 (3.1058)	grad_norm 0.9041 (2.0999/1.0270)	mem 24308MB
[2025-01-19 00:13:53 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][130/312]	eta 0:01:52 lr 0.001095	time 0.5865 (0.6195)	model_time 0.5863 (0.6077)	loss 3.2045 (3.0967)	grad_norm 2.9417 (2.1364/1.0228)	mem 24308MB
[2025-01-19 00:13:59 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][140/312]	eta 0:01:46 lr 0.001094	time 0.5799 (0.6180)	model_time 0.5798 (0.6071)	loss 3.5035 (3.0825)	grad_norm 1.8703 (2.1843/1.0335)	mem 24308MB
[2025-01-19 00:14:05 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][150/312]	eta 0:01:39 lr 0.001094	time 0.5960 (0.6167)	model_time 0.5958 (0.6065)	loss 3.4993 (3.0855)	grad_norm 1.6886 (2.1470/1.0118)	mem 24308MB
[2025-01-19 00:14:11 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][160/312]	eta 0:01:33 lr 0.001093	time 0.5661 (0.6151)	model_time 0.5656 (0.6056)	loss 3.5188 (3.0999)	grad_norm 1.1834 (2.1343/0.9862)	mem 24308MB
[2025-01-19 00:14:18 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][170/312]	eta 0:01:27 lr 0.001093	time 0.5971 (0.6158)	model_time 0.5970 (0.6067)	loss 2.9307 (3.0971)	grad_norm 1.9678 (2.1318/0.9677)	mem 24308MB
[2025-01-19 00:14:24 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][180/312]	eta 0:01:21 lr 0.001092	time 0.6885 (0.6153)	model_time 0.6883 (0.6067)	loss 2.5788 (3.0885)	grad_norm 1.8024 (2.1336/0.9580)	mem 24308MB
[2025-01-19 00:14:30 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][190/312]	eta 0:01:15 lr 0.001092	time 0.5657 (0.6160)	model_time 0.5655 (0.6079)	loss 3.2665 (3.0914)	grad_norm 5.0432 (2.1832/1.0197)	mem 24308MB
[2025-01-19 00:14:36 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][200/312]	eta 0:01:08 lr 0.001091	time 0.5923 (0.6160)	model_time 0.5918 (0.6082)	loss 2.3905 (3.0892)	grad_norm 1.1299 (2.1922/1.0161)	mem 24308MB
[2025-01-19 00:14:42 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][210/312]	eta 0:01:02 lr 0.001090	time 0.5773 (0.6159)	model_time 0.5769 (0.6085)	loss 2.8375 (3.0850)	grad_norm 2.5507 (2.2187/1.0126)	mem 24308MB
[2025-01-19 00:14:48 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][220/312]	eta 0:00:56 lr 0.001090	time 0.5816 (0.6153)	model_time 0.5815 (0.6082)	loss 3.2113 (3.0867)	grad_norm 1.1712 (2.2114/1.0001)	mem 24308MB
[2025-01-19 00:14:54 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][230/312]	eta 0:00:50 lr 0.001089	time 0.6546 (0.6147)	model_time 0.6541 (0.6079)	loss 3.4227 (3.0932)	grad_norm 1.0481 (2.1701/0.9988)	mem 24308MB
[2025-01-19 00:15:00 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][240/312]	eta 0:00:44 lr 0.001089	time 0.5652 (0.6141)	model_time 0.5647 (0.6076)	loss 3.2933 (3.0879)	grad_norm 1.3811 (2.1565/0.9847)	mem 24308MB
[2025-01-19 00:15:06 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][250/312]	eta 0:00:38 lr 0.001088	time 0.5796 (0.6133)	model_time 0.5792 (0.6070)	loss 3.3682 (3.0765)	grad_norm 3.1699 (2.1531/0.9715)	mem 24308MB
[2025-01-19 00:15:12 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][260/312]	eta 0:00:31 lr 0.001087	time 0.5865 (0.6127)	model_time 0.5863 (0.6066)	loss 2.7579 (3.0754)	grad_norm 1.7321 (2.1370/0.9609)	mem 24308MB
[2025-01-19 00:15:18 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][270/312]	eta 0:00:25 lr 0.001087	time 0.5821 (0.6124)	model_time 0.5816 (0.6065)	loss 3.1104 (3.0725)	grad_norm 1.3146 (2.1323/0.9580)	mem 24308MB
[2025-01-19 00:15:24 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][280/312]	eta 0:00:19 lr 0.001086	time 0.5802 (0.6118)	model_time 0.5798 (0.6062)	loss 2.9149 (3.0746)	grad_norm 3.0744 (2.1351/0.9470)	mem 24308MB
[2025-01-19 00:15:30 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][290/312]	eta 0:00:13 lr 0.001086	time 0.6795 (0.6117)	model_time 0.6793 (0.6062)	loss 2.8815 (3.0771)	grad_norm 0.8873 (2.1295/0.9387)	mem 24308MB
[2025-01-19 00:15:36 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][300/312]	eta 0:00:07 lr 0.001085	time 0.5659 (0.6112)	model_time 0.5658 (0.6059)	loss 3.8575 (3.0779)	grad_norm 4.2619 (2.1205/0.9383)	mem 24308MB
[2025-01-19 00:15:42 internimage_s_1k_224] (main.py 510): INFO Train: [196/300][310/312]	eta 0:00:01 lr 0.001084	time 0.5665 (0.6110)	model_time 0.5665 (0.6059)	loss 2.1241 (3.0757)	grad_norm 2.8843 (2.1149/0.9435)	mem 24308MB
[2025-01-19 00:15:43 internimage_s_1k_224] (main.py 519): INFO EPOCH 196 training takes 0:03:10
[2025-01-19 00:15:43 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_196.pth saving......
[2025-01-19 00:15:45 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_196.pth saved !!!
[2025-01-19 00:15:53 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.993 (7.993)	Loss 0.7582 (0.7582)	Acc@1 84.326 (84.326)	Acc@5 97.314 (97.314)	Mem 24308MB
[2025-01-19 00:15:56 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.044)	Loss 0.9931 (0.8724)	Acc@1 78.247 (81.530)	Acc@5 94.897 (95.967)	Mem 24308MB
[2025-01-19 00:15:56 internimage_s_1k_224] (main.py 575): INFO [Epoch:196] * Acc@1 81.434 Acc@5 96.003
[2025-01-19 00:15:56 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.4%
[2025-01-19 00:15:56 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:15:58 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:15:59 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.43%
[2025-01-19 00:16:06 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.832 (7.832)	Loss 0.7064 (0.7064)	Acc@1 84.741 (84.741)	Acc@5 97.632 (97.632)	Mem 24308MB
[2025-01-19 00:16:10 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.011)	Loss 0.9536 (0.8083)	Acc@1 77.368 (81.938)	Acc@5 94.751 (96.074)	Mem 24308MB
[2025-01-19 00:16:10 internimage_s_1k_224] (main.py 575): INFO [Epoch:196] * Acc@1 81.808 Acc@5 96.113
[2025-01-19 00:16:10 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.8%
[2025-01-19 00:16:10 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:16:12 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:16:12 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.81%
[2025-01-19 00:16:14 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][0/312]	eta 0:10:37 lr 0.001084	time 2.0443 (2.0443)	model_time 0.5948 (0.5948)	loss 3.2284 (3.2284)	grad_norm 1.4557 (1.4557/0.0000)	mem 24308MB
[2025-01-19 00:16:20 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][10/312]	eta 0:03:46 lr 0.001084	time 0.6641 (0.7511)	model_time 0.6639 (0.6190)	loss 3.6055 (3.0178)	grad_norm 2.5148 (1.7993/0.6081)	mem 24308MB
[2025-01-19 00:16:27 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][20/312]	eta 0:03:23 lr 0.001083	time 0.5929 (0.6973)	model_time 0.5927 (0.6279)	loss 2.5417 (3.1117)	grad_norm 2.1389 (1.7307/0.5677)	mem 24308MB
[2025-01-19 00:16:33 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][30/312]	eta 0:03:07 lr 0.001083	time 0.6028 (0.6652)	model_time 0.6026 (0.6181)	loss 2.1285 (3.0126)	grad_norm 1.7454 (1.7681/0.5721)	mem 24308MB
[2025-01-19 00:16:39 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][40/312]	eta 0:02:56 lr 0.001082	time 0.5839 (0.6503)	model_time 0.5838 (0.6146)	loss 2.1380 (2.9885)	grad_norm 1.1533 (1.7458/0.5708)	mem 24308MB
[2025-01-19 00:16:45 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][50/312]	eta 0:02:47 lr 0.001081	time 0.5817 (0.6408)	model_time 0.5815 (0.6120)	loss 2.7577 (2.9896)	grad_norm 2.0142 (1.7365/0.5529)	mem 24308MB
[2025-01-19 00:16:51 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][60/312]	eta 0:02:39 lr 0.001081	time 0.5723 (0.6335)	model_time 0.5721 (0.6094)	loss 3.1156 (3.0133)	grad_norm 2.0749 (1.8439/0.6745)	mem 24308MB
[2025-01-19 00:16:57 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][70/312]	eta 0:02:32 lr 0.001080	time 0.5826 (0.6287)	model_time 0.5821 (0.6080)	loss 3.2015 (3.0377)	grad_norm 5.2428 (2.0494/0.9546)	mem 24308MB
[2025-01-19 00:17:03 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][80/312]	eta 0:02:25 lr 0.001080	time 0.6039 (0.6257)	model_time 0.6037 (0.6074)	loss 2.3908 (3.0608)	grad_norm 1.8110 (2.0922/0.9750)	mem 24308MB
[2025-01-19 00:17:09 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][90/312]	eta 0:02:18 lr 0.001079	time 0.5762 (0.6222)	model_time 0.5756 (0.6059)	loss 3.7249 (3.0427)	grad_norm 1.2642 (2.0093/0.9536)	mem 24308MB
[2025-01-19 00:17:15 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][100/312]	eta 0:02:11 lr 0.001078	time 0.5748 (0.6210)	model_time 0.5744 (0.6063)	loss 3.3041 (3.0419)	grad_norm 1.4663 (2.0100/0.9258)	mem 24308MB
[2025-01-19 00:17:21 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][110/312]	eta 0:02:05 lr 0.001078	time 0.6013 (0.6193)	model_time 0.6011 (0.6059)	loss 3.1519 (3.0404)	grad_norm 1.9283 (2.0201/0.9117)	mem 24308MB
[2025-01-19 00:17:27 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][120/312]	eta 0:01:58 lr 0.001077	time 0.5815 (0.6191)	model_time 0.5811 (0.6067)	loss 2.0188 (3.0391)	grad_norm 1.3190 (2.0994/0.9465)	mem 24308MB
[2025-01-19 00:17:33 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][130/312]	eta 0:01:52 lr 0.001077	time 0.5757 (0.6192)	model_time 0.5756 (0.6078)	loss 2.2369 (3.0391)	grad_norm 4.5546 (2.1703/0.9631)	mem 24308MB
[2025-01-19 00:17:39 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][140/312]	eta 0:01:46 lr 0.001076	time 0.5871 (0.6196)	model_time 0.5867 (0.6089)	loss 3.3315 (3.0380)	grad_norm 2.9223 (2.1654/0.9531)	mem 24308MB
[2025-01-19 00:17:45 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][150/312]	eta 0:01:40 lr 0.001076	time 0.5733 (0.6182)	model_time 0.5731 (0.6082)	loss 3.9030 (3.0482)	grad_norm 2.0932 (2.1453/0.9325)	mem 24308MB
[2025-01-19 00:17:51 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][160/312]	eta 0:01:33 lr 0.001075	time 0.5950 (0.6169)	model_time 0.5948 (0.6075)	loss 2.9537 (3.0530)	grad_norm 1.7304 (2.1236/0.9178)	mem 24308MB
[2025-01-19 00:17:58 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][170/312]	eta 0:01:27 lr 0.001074	time 0.5921 (0.6167)	model_time 0.5916 (0.6079)	loss 3.3042 (3.0522)	grad_norm 2.4683 (2.0917/0.9096)	mem 24308MB
[2025-01-19 00:18:04 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][180/312]	eta 0:01:21 lr 0.001074	time 0.6742 (0.6156)	model_time 0.6740 (0.6072)	loss 2.0375 (3.0475)	grad_norm 2.2439 (2.1323/0.9564)	mem 24308MB
[2025-01-19 00:18:10 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][190/312]	eta 0:01:14 lr 0.001073	time 0.5756 (0.6146)	model_time 0.5751 (0.6067)	loss 3.6109 (3.0568)	grad_norm 4.4172 (2.1578/0.9716)	mem 24308MB
[2025-01-19 00:18:16 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][200/312]	eta 0:01:08 lr 0.001073	time 0.5726 (0.6141)	model_time 0.5722 (0.6065)	loss 3.4851 (3.0702)	grad_norm 2.4182 (2.1740/0.9636)	mem 24308MB
[2025-01-19 00:18:22 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][210/312]	eta 0:01:02 lr 0.001072	time 0.5821 (0.6133)	model_time 0.5820 (0.6061)	loss 3.6416 (3.0637)	grad_norm 3.6353 (2.1995/0.9796)	mem 24308MB
[2025-01-19 00:18:28 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][220/312]	eta 0:00:56 lr 0.001071	time 0.7056 (0.6136)	model_time 0.7052 (0.6066)	loss 3.2517 (3.0707)	grad_norm 1.1579 (2.1872/0.9739)	mem 24308MB
[2025-01-19 00:18:34 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][230/312]	eta 0:00:50 lr 0.001071	time 0.5931 (0.6131)	model_time 0.5930 (0.6065)	loss 3.1284 (3.0769)	grad_norm 1.6781 (2.1820/0.9581)	mem 24308MB
[2025-01-19 00:18:40 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][240/312]	eta 0:00:44 lr 0.001070	time 0.5818 (0.6139)	model_time 0.5816 (0.6075)	loss 2.1320 (3.0787)	grad_norm 1.5789 (2.1540/0.9503)	mem 24308MB
[2025-01-19 00:18:46 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][250/312]	eta 0:00:38 lr 0.001070	time 0.5894 (0.6137)	model_time 0.5890 (0.6075)	loss 2.8544 (3.0824)	grad_norm 1.3694 (2.1404/0.9392)	mem 24308MB
[2025-01-19 00:18:52 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][260/312]	eta 0:00:31 lr 0.001069	time 0.5878 (0.6144)	model_time 0.5873 (0.6084)	loss 3.4470 (3.0783)	grad_norm 1.3963 (2.1480/0.9409)	mem 24308MB
[2025-01-19 00:18:59 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][270/312]	eta 0:00:25 lr 0.001069	time 0.5812 (0.6142)	model_time 0.5810 (0.6084)	loss 3.4057 (3.0866)	grad_norm 3.2132 (2.1858/0.9688)	mem 24308MB
[2025-01-19 00:19:05 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][280/312]	eta 0:00:19 lr 0.001068	time 0.5810 (0.6136)	model_time 0.5809 (0.6080)	loss 3.1797 (3.0920)	grad_norm 1.2483 (2.1829/0.9651)	mem 24308MB
[2025-01-19 00:19:11 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][290/312]	eta 0:00:13 lr 0.001067	time 0.6564 (0.6139)	model_time 0.6563 (0.6085)	loss 2.0071 (3.0951)	grad_norm 1.9245 (2.1636/0.9570)	mem 24308MB
[2025-01-19 00:19:17 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][300/312]	eta 0:00:07 lr 0.001067	time 0.6522 (0.6130)	model_time 0.6521 (0.6078)	loss 2.3114 (3.0916)	grad_norm 1.2977 (2.1648/0.9547)	mem 24308MB
[2025-01-19 00:19:22 internimage_s_1k_224] (main.py 510): INFO Train: [197/300][310/312]	eta 0:00:01 lr 0.001066	time 0.5691 (0.6119)	model_time 0.5690 (0.6069)	loss 2.2066 (3.0808)	grad_norm 1.6281 (2.1542/0.9541)	mem 24308MB
[2025-01-19 00:19:23 internimage_s_1k_224] (main.py 519): INFO EPOCH 197 training takes 0:03:10
[2025-01-19 00:19:23 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_197.pth saving......
[2025-01-19 00:19:25 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_197.pth saved !!!
[2025-01-19 00:19:33 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.780 (7.780)	Loss 0.7415 (0.7415)	Acc@1 84.473 (84.473)	Acc@5 97.241 (97.241)	Mem 24308MB
[2025-01-19 00:19:36 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.021)	Loss 0.9938 (0.8665)	Acc@1 77.661 (81.552)	Acc@5 94.849 (95.892)	Mem 24308MB
[2025-01-19 00:19:36 internimage_s_1k_224] (main.py 575): INFO [Epoch:197] * Acc@1 81.430 Acc@5 95.893
[2025-01-19 00:19:36 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.4%
[2025-01-19 00:19:36 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.43%
[2025-01-19 00:19:53 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.324 (16.324)	Loss 0.7064 (0.7064)	Acc@1 84.717 (84.717)	Acc@5 97.632 (97.632)	Mem 24308MB
[2025-01-19 00:20:02 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (2.303)	Loss 0.9523 (0.8076)	Acc@1 77.441 (81.951)	Acc@5 94.800 (96.089)	Mem 24308MB
[2025-01-19 00:20:02 internimage_s_1k_224] (main.py 575): INFO [Epoch:197] * Acc@1 81.828 Acc@5 96.129
[2025-01-19 00:20:02 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.8%
[2025-01-19 00:20:02 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:20:04 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:20:04 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.83%
[2025-01-19 00:20:06 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][0/312]	eta 0:11:39 lr 0.001066	time 2.2426 (2.2426)	model_time 0.5977 (0.5977)	loss 3.3455 (3.3455)	grad_norm 1.8121 (1.8121/0.0000)	mem 24308MB
[2025-01-19 00:20:12 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][10/312]	eta 0:03:46 lr 0.001066	time 0.5893 (0.7489)	model_time 0.5891 (0.5989)	loss 3.6964 (3.3275)	grad_norm 2.2658 (1.9658/0.6855)	mem 24308MB
[2025-01-19 00:20:18 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][20/312]	eta 0:03:16 lr 0.001065	time 0.5875 (0.6731)	model_time 0.5873 (0.5944)	loss 3.2886 (3.0890)	grad_norm 1.7506 (2.3318/1.1503)	mem 24308MB
[2025-01-19 00:20:24 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][30/312]	eta 0:03:04 lr 0.001064	time 0.5867 (0.6556)	model_time 0.5723 (0.6017)	loss 2.7056 (3.1430)	grad_norm 1.5474 (2.1808/1.1589)	mem 24308MB
[2025-01-19 00:20:30 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][40/312]	eta 0:02:54 lr 0.001064	time 0.5898 (0.6433)	model_time 0.5896 (0.6024)	loss 2.4007 (3.0980)	grad_norm 2.1370 (2.0590/1.0392)	mem 24308MB
[2025-01-19 00:20:37 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][50/312]	eta 0:02:48 lr 0.001063	time 0.5808 (0.6422)	model_time 0.5806 (0.6093)	loss 1.9832 (3.1074)	grad_norm 1.3811 (2.0209/0.9705)	mem 24308MB
[2025-01-19 00:20:43 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][60/312]	eta 0:02:40 lr 0.001063	time 0.6123 (0.6379)	model_time 0.6119 (0.6103)	loss 3.4454 (3.0572)	grad_norm 3.1235 (2.1299/1.0431)	mem 24308MB
[2025-01-19 00:20:49 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][70/312]	eta 0:02:34 lr 0.001062	time 0.5889 (0.6364)	model_time 0.5887 (0.6127)	loss 2.2718 (3.0335)	grad_norm 1.1514 (2.1173/0.9951)	mem 24308MB
[2025-01-19 00:20:55 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][80/312]	eta 0:02:26 lr 0.001061	time 0.5861 (0.6313)	model_time 0.5859 (0.6104)	loss 2.2879 (3.0278)	grad_norm 2.1023 (2.1191/0.9692)	mem 24308MB
[2025-01-19 00:21:01 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][90/312]	eta 0:02:19 lr 0.001061	time 0.5802 (0.6286)	model_time 0.5800 (0.6100)	loss 3.5570 (3.0461)	grad_norm 1.5362 (2.0659/0.9427)	mem 24308MB
[2025-01-19 00:21:07 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][100/312]	eta 0:02:12 lr 0.001060	time 0.6087 (0.6253)	model_time 0.6085 (0.6085)	loss 2.8758 (3.0421)	grad_norm 1.7505 (2.0672/0.9115)	mem 24308MB
[2025-01-19 00:21:13 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][110/312]	eta 0:02:05 lr 0.001060	time 0.5841 (0.6231)	model_time 0.5839 (0.6078)	loss 3.8219 (3.0546)	grad_norm 1.6806 (2.0406/0.8850)	mem 24308MB
[2025-01-19 00:21:19 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][120/312]	eta 0:01:59 lr 0.001059	time 0.5814 (0.6212)	model_time 0.5812 (0.6072)	loss 3.3837 (3.0732)	grad_norm 2.7276 (2.0535/0.8803)	mem 24308MB
[2025-01-19 00:21:25 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][130/312]	eta 0:01:52 lr 0.001059	time 0.5791 (0.6195)	model_time 0.5786 (0.6065)	loss 3.3844 (3.0668)	grad_norm 2.8076 (2.0795/0.8982)	mem 24308MB
[2025-01-19 00:21:31 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][140/312]	eta 0:01:46 lr 0.001058	time 0.6135 (0.6176)	model_time 0.6037 (0.6054)	loss 3.6967 (3.0880)	grad_norm 2.0876 (2.0432/0.8833)	mem 24308MB
[2025-01-19 00:21:37 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][150/312]	eta 0:01:39 lr 0.001057	time 0.5805 (0.6167)	model_time 0.5803 (0.6053)	loss 2.7745 (3.1069)	grad_norm 2.4419 (2.0668/0.8868)	mem 24308MB
[2025-01-19 00:21:43 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][160/312]	eta 0:01:33 lr 0.001057	time 0.5865 (0.6162)	model_time 0.5863 (0.6055)	loss 3.5965 (3.1204)	grad_norm 1.2628 (2.1092/0.9439)	mem 24308MB
[2025-01-19 00:21:50 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][170/312]	eta 0:01:27 lr 0.001056	time 0.5795 (0.6191)	model_time 0.5794 (0.6090)	loss 2.2482 (3.1273)	grad_norm 3.3444 (2.1878/0.9860)	mem 24308MB
[2025-01-19 00:21:56 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][180/312]	eta 0:01:21 lr 0.001056	time 0.6153 (0.6193)	model_time 0.6151 (0.6097)	loss 3.5666 (3.1261)	grad_norm 1.7825 (2.1662/0.9702)	mem 24308MB
[2025-01-19 00:22:02 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][190/312]	eta 0:01:15 lr 0.001055	time 0.5824 (0.6197)	model_time 0.5819 (0.6105)	loss 3.2619 (3.1258)	grad_norm 4.0861 (2.1931/0.9763)	mem 24308MB
[2025-01-19 00:22:08 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][200/312]	eta 0:01:09 lr 0.001055	time 0.6482 (0.6187)	model_time 0.6480 (0.6100)	loss 2.4688 (3.1185)	grad_norm 1.6979 (2.2061/0.9761)	mem 24308MB
[2025-01-19 00:22:15 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][210/312]	eta 0:01:03 lr 0.001054	time 0.5842 (0.6187)	model_time 0.5840 (0.6104)	loss 3.2862 (3.1070)	grad_norm 1.4437 (2.2440/1.0109)	mem 24308MB
[2025-01-19 00:22:21 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][220/312]	eta 0:00:56 lr 0.001053	time 0.5804 (0.6176)	model_time 0.5802 (0.6096)	loss 2.7774 (3.1064)	grad_norm 1.2902 (2.2104/1.0045)	mem 24308MB
[2025-01-19 00:22:27 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][230/312]	eta 0:00:50 lr 0.001053	time 0.5985 (0.6167)	model_time 0.5983 (0.6091)	loss 2.3222 (3.1113)	grad_norm 1.8378 (2.2070/0.9941)	mem 24308MB
[2025-01-19 00:22:33 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][240/312]	eta 0:00:44 lr 0.001052	time 0.5917 (0.6164)	model_time 0.5925 (0.6091)	loss 3.5238 (3.1139)	grad_norm 3.0991 (2.2049/0.9846)	mem 24308MB
[2025-01-19 00:22:39 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][250/312]	eta 0:00:38 lr 0.001052	time 0.5920 (0.6156)	model_time 0.5918 (0.6086)	loss 3.7051 (3.1099)	grad_norm 1.5498 (2.2068/0.9887)	mem 24308MB
[2025-01-19 00:22:45 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][260/312]	eta 0:00:31 lr 0.001051	time 0.5787 (0.6147)	model_time 0.5786 (0.6079)	loss 2.6051 (3.1134)	grad_norm 2.3300 (2.2363/0.9903)	mem 24308MB
[2025-01-19 00:22:51 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][270/312]	eta 0:00:25 lr 0.001050	time 0.6052 (0.6143)	model_time 0.6050 (0.6077)	loss 3.6100 (3.1107)	grad_norm 2.4675 (2.2563/0.9878)	mem 24308MB
[2025-01-19 00:22:57 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][280/312]	eta 0:00:19 lr 0.001050	time 0.5723 (0.6143)	model_time 0.5719 (0.6079)	loss 3.0297 (3.1136)	grad_norm 1.3585 (2.2421/0.9795)	mem 24308MB
[2025-01-19 00:23:03 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][290/312]	eta 0:00:13 lr 0.001049	time 0.5747 (0.6143)	model_time 0.5746 (0.6082)	loss 3.2837 (3.1111)	grad_norm 3.4028 (2.2311/0.9726)	mem 24308MB
[2025-01-19 00:23:09 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][300/312]	eta 0:00:07 lr 0.001049	time 0.5725 (0.6143)	model_time 0.5724 (0.6083)	loss 1.9681 (3.1107)	grad_norm 2.6555 (2.2351/0.9649)	mem 24308MB
[2025-01-19 00:23:15 internimage_s_1k_224] (main.py 510): INFO Train: [198/300][310/312]	eta 0:00:01 lr 0.001048	time 0.6586 (0.6138)	model_time 0.6585 (0.6080)	loss 3.6069 (3.1091)	grad_norm 5.4905 (2.2528/0.9870)	mem 24308MB
[2025-01-19 00:23:16 internimage_s_1k_224] (main.py 519): INFO EPOCH 198 training takes 0:03:11
[2025-01-19 00:23:16 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_198.pth saving......
[2025-01-19 00:23:17 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_198.pth saved !!!
[2025-01-19 00:23:25 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.900 (7.900)	Loss 0.7650 (0.7650)	Acc@1 84.326 (84.326)	Acc@5 97.510 (97.510)	Mem 24308MB
[2025-01-19 00:23:29 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.025)	Loss 1.0131 (0.8741)	Acc@1 77.441 (81.634)	Acc@5 95.044 (95.918)	Mem 24308MB
[2025-01-19 00:23:29 internimage_s_1k_224] (main.py 575): INFO [Epoch:198] * Acc@1 81.502 Acc@5 95.953
[2025-01-19 00:23:29 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.5%
[2025-01-19 00:23:29 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:23:31 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:23:31 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.50%
[2025-01-19 00:23:39 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.009 (8.009)	Loss 0.7062 (0.7062)	Acc@1 84.790 (84.790)	Acc@5 97.632 (97.632)	Mem 24308MB
[2025-01-19 00:23:42 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.054)	Loss 0.9512 (0.8070)	Acc@1 77.466 (81.987)	Acc@5 94.824 (96.118)	Mem 24308MB
[2025-01-19 00:23:43 internimage_s_1k_224] (main.py 575): INFO [Epoch:198] * Acc@1 81.858 Acc@5 96.151
[2025-01-19 00:23:43 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.9%
[2025-01-19 00:23:43 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:23:45 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:23:45 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.86%
[2025-01-19 00:23:48 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][0/312]	eta 0:12:56 lr 0.001048	time 2.4895 (2.4895)	model_time 0.5943 (0.5943)	loss 3.2747 (3.2747)	grad_norm 2.9712 (2.9712/0.0000)	mem 24308MB
[2025-01-19 00:23:54 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][10/312]	eta 0:03:53 lr 0.001047	time 0.6557 (0.7717)	model_time 0.6555 (0.5992)	loss 1.9041 (2.8725)	grad_norm 2.4257 (2.4716/0.5305)	mem 24308MB
[2025-01-19 00:24:00 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][20/312]	eta 0:03:23 lr 0.001047	time 0.5883 (0.6963)	model_time 0.5882 (0.6057)	loss 3.1953 (2.8693)	grad_norm 1.5547 (2.1151/0.6554)	mem 24308MB
[2025-01-19 00:24:06 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][30/312]	eta 0:03:07 lr 0.001046	time 0.5975 (0.6637)	model_time 0.5973 (0.6023)	loss 2.9926 (2.9230)	grad_norm 3.1419 (2.0109/0.6359)	mem 24308MB
[2025-01-19 00:24:12 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][40/312]	eta 0:02:56 lr 0.001046	time 0.5793 (0.6493)	model_time 0.5791 (0.6028)	loss 2.1342 (2.9526)	grad_norm 1.0134 (1.8895/0.6086)	mem 24308MB
[2025-01-19 00:24:18 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][50/312]	eta 0:02:47 lr 0.001045	time 0.5960 (0.6404)	model_time 0.5959 (0.6029)	loss 2.4914 (2.9672)	grad_norm 1.2682 (1.8696/0.5880)	mem 24308MB
[2025-01-19 00:24:24 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][60/312]	eta 0:02:39 lr 0.001045	time 0.5817 (0.6331)	model_time 0.5815 (0.6017)	loss 3.9172 (2.9856)	grad_norm 1.4216 (1.9229/0.6066)	mem 24308MB
[2025-01-19 00:24:30 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][70/312]	eta 0:02:31 lr 0.001044	time 0.5879 (0.6268)	model_time 0.5876 (0.5997)	loss 3.6782 (2.9968)	grad_norm 1.5945 (1.9876/0.8114)	mem 24308MB
[2025-01-19 00:24:36 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][80/312]	eta 0:02:25 lr 0.001043	time 0.5739 (0.6257)	model_time 0.5737 (0.6020)	loss 3.1285 (3.0212)	grad_norm 1.6761 (1.9855/0.7879)	mem 24308MB
[2025-01-19 00:24:42 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][90/312]	eta 0:02:18 lr 0.001043	time 0.5960 (0.6235)	model_time 0.5958 (0.6023)	loss 3.3236 (3.0549)	grad_norm 1.2259 (2.0112/0.7798)	mem 24308MB
[2025-01-19 00:24:48 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][100/312]	eta 0:02:12 lr 0.001042	time 0.6647 (0.6241)	model_time 0.6642 (0.6050)	loss 3.5328 (3.0697)	grad_norm 2.5255 (2.0667/0.8025)	mem 24308MB
[2025-01-19 00:24:54 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][110/312]	eta 0:02:05 lr 0.001042	time 0.5732 (0.6220)	model_time 0.5728 (0.6046)	loss 2.7210 (3.0752)	grad_norm 2.5449 (2.0895/0.8019)	mem 24308MB
[2025-01-19 00:25:00 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][120/312]	eta 0:01:59 lr 0.001041	time 0.6851 (0.6216)	model_time 0.6850 (0.6056)	loss 3.5462 (3.0640)	grad_norm 1.0028 (2.0437/0.7965)	mem 24308MB
[2025-01-19 00:25:06 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][130/312]	eta 0:01:52 lr 0.001040	time 0.5932 (0.6206)	model_time 0.5931 (0.6058)	loss 2.9360 (3.0583)	grad_norm 1.4473 (2.0063/0.7847)	mem 24308MB
[2025-01-19 00:25:13 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][140/312]	eta 0:01:46 lr 0.001040	time 0.6869 (0.6212)	model_time 0.6868 (0.6074)	loss 3.0101 (3.0589)	grad_norm 2.6090 (1.9755/0.7751)	mem 24308MB
[2025-01-19 00:25:19 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][150/312]	eta 0:01:40 lr 0.001039	time 0.5959 (0.6197)	model_time 0.5957 (0.6068)	loss 1.8730 (3.0526)	grad_norm 5.1808 (2.0158/0.8155)	mem 24308MB
[2025-01-19 00:25:25 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][160/312]	eta 0:01:34 lr 0.001039	time 0.5865 (0.6186)	model_time 0.5863 (0.6064)	loss 3.4029 (3.0642)	grad_norm 1.2685 (2.0158/0.8118)	mem 24308MB
[2025-01-19 00:25:31 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][170/312]	eta 0:01:27 lr 0.001038	time 0.5755 (0.6178)	model_time 0.5753 (0.6063)	loss 3.1607 (3.0521)	grad_norm 1.9606 (2.0033/0.8002)	mem 24308MB
[2025-01-19 00:25:37 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][180/312]	eta 0:01:21 lr 0.001038	time 0.6009 (0.6168)	model_time 0.6005 (0.6060)	loss 3.0973 (3.0545)	grad_norm 3.4108 (1.9964/0.7969)	mem 24308MB
[2025-01-19 00:25:43 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][190/312]	eta 0:01:15 lr 0.001037	time 0.5955 (0.6155)	model_time 0.5950 (0.6052)	loss 3.0262 (3.0426)	grad_norm 2.9436 (2.0214/0.8177)	mem 24308MB
[2025-01-19 00:25:49 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][200/312]	eta 0:01:08 lr 0.001036	time 0.5813 (0.6151)	model_time 0.5811 (0.6052)	loss 3.1328 (3.0466)	grad_norm 2.2994 (2.0087/0.8117)	mem 24308MB
[2025-01-19 00:25:55 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][210/312]	eta 0:01:02 lr 0.001036	time 0.5746 (0.6148)	model_time 0.5741 (0.6054)	loss 2.5171 (3.0517)	grad_norm 4.4461 (2.0133/0.8350)	mem 24308MB
[2025-01-19 00:26:01 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][220/312]	eta 0:00:56 lr 0.001035	time 0.5875 (0.6145)	model_time 0.5871 (0.6055)	loss 3.6403 (3.0509)	grad_norm 1.2595 (2.0142/0.8236)	mem 24308MB
[2025-01-19 00:26:07 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][230/312]	eta 0:00:50 lr 0.001035	time 0.5796 (0.6145)	model_time 0.5795 (0.6059)	loss 3.1635 (3.0504)	grad_norm 3.0985 (2.0094/0.8192)	mem 24308MB
[2025-01-19 00:26:13 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][240/312]	eta 0:00:44 lr 0.001034	time 0.5740 (0.6150)	model_time 0.5738 (0.6068)	loss 3.5802 (3.0528)	grad_norm 3.4018 (2.0464/0.8301)	mem 24308MB
[2025-01-19 00:26:19 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][250/312]	eta 0:00:38 lr 0.001034	time 0.5734 (0.6149)	model_time 0.5729 (0.6069)	loss 3.4421 (3.0608)	grad_norm 1.9584 (2.0726/0.8482)	mem 24308MB
[2025-01-19 00:26:26 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][260/312]	eta 0:00:32 lr 0.001033	time 0.7354 (0.6161)	model_time 0.7349 (0.6084)	loss 3.5071 (3.0585)	grad_norm 1.1435 (2.0439/0.8454)	mem 24308MB
[2025-01-19 00:26:32 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][270/312]	eta 0:00:25 lr 0.001032	time 0.5897 (0.6155)	model_time 0.5892 (0.6081)	loss 3.8808 (3.0601)	grad_norm 2.9328 (2.0360/0.8368)	mem 24308MB
[2025-01-19 00:26:38 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][280/312]	eta 0:00:19 lr 0.001032	time 0.5849 (0.6148)	model_time 0.5847 (0.6076)	loss 3.9719 (3.0688)	grad_norm 3.3866 (2.0881/0.9085)	mem 24308MB
[2025-01-19 00:26:44 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][290/312]	eta 0:00:13 lr 0.001031	time 0.5798 (0.6144)	model_time 0.5796 (0.6075)	loss 2.8751 (3.0546)	grad_norm 2.5187 (2.1292/0.9595)	mem 24308MB
[2025-01-19 00:26:50 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][300/312]	eta 0:00:07 lr 0.001031	time 0.6550 (0.6137)	model_time 0.6549 (0.6070)	loss 3.1975 (3.0585)	grad_norm 1.0785 (2.1252/0.9506)	mem 24308MB
[2025-01-19 00:26:55 internimage_s_1k_224] (main.py 510): INFO Train: [199/300][310/312]	eta 0:00:01 lr 0.001030	time 0.5671 (0.6122)	model_time 0.5670 (0.6057)	loss 3.0260 (3.0592)	grad_norm 1.4009 (2.0999/0.9491)	mem 24308MB
[2025-01-19 00:26:56 internimage_s_1k_224] (main.py 519): INFO EPOCH 199 training takes 0:03:10
[2025-01-19 00:26:56 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_199.pth saving......
[2025-01-19 00:26:58 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_199.pth saved !!!
[2025-01-19 00:27:06 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.909 (7.909)	Loss 0.7479 (0.7479)	Acc@1 84.351 (84.351)	Acc@5 97.217 (97.217)	Mem 24308MB
[2025-01-19 00:27:09 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.024)	Loss 0.9942 (0.8488)	Acc@1 77.563 (81.696)	Acc@5 94.775 (95.958)	Mem 24308MB
[2025-01-19 00:27:09 internimage_s_1k_224] (main.py 575): INFO [Epoch:199] * Acc@1 81.598 Acc@5 95.983
[2025-01-19 00:27:09 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.6%
[2025-01-19 00:27:09 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:27:11 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:27:11 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.60%
[2025-01-19 00:27:19 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.890 (7.890)	Loss 0.7063 (0.7063)	Acc@1 84.839 (84.839)	Acc@5 97.632 (97.632)	Mem 24308MB
[2025-01-19 00:27:22 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.025)	Loss 0.9500 (0.8064)	Acc@1 77.539 (82.027)	Acc@5 94.873 (96.134)	Mem 24308MB
[2025-01-19 00:27:23 internimage_s_1k_224] (main.py 575): INFO [Epoch:199] * Acc@1 81.896 Acc@5 96.163
[2025-01-19 00:27:23 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 81.9%
[2025-01-19 00:27:23 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:27:25 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:27:25 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.90%
[2025-01-19 00:27:27 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][0/312]	eta 0:12:12 lr 0.001030	time 2.3479 (2.3479)	model_time 0.5908 (0.5908)	loss 3.6228 (3.6228)	grad_norm 1.5329 (1.5329/0.0000)	mem 24308MB
[2025-01-19 00:27:33 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][10/312]	eta 0:03:52 lr 0.001029	time 0.5775 (0.7703)	model_time 0.5773 (0.6103)	loss 1.8424 (2.9520)	grad_norm 2.1655 (2.3156/0.9571)	mem 24308MB
[2025-01-19 00:27:40 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][20/312]	eta 0:03:22 lr 0.001029	time 0.5890 (0.6922)	model_time 0.5885 (0.6082)	loss 3.3160 (2.9724)	grad_norm 2.1889 (2.0668/0.8167)	mem 24308MB
[2025-01-19 00:27:46 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][30/312]	eta 0:03:08 lr 0.001028	time 0.6643 (0.6694)	model_time 0.6639 (0.6124)	loss 3.9125 (2.9738)	grad_norm 1.4145 (1.9177/0.7327)	mem 24308MB
[2025-01-19 00:27:52 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][40/312]	eta 0:02:59 lr 0.001028	time 0.5899 (0.6590)	model_time 0.5894 (0.6158)	loss 3.4404 (3.0256)	grad_norm 1.7593 (2.0688/0.8516)	mem 24308MB
[2025-01-19 00:27:58 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][50/312]	eta 0:02:50 lr 0.001027	time 0.6663 (0.6490)	model_time 0.6662 (0.6142)	loss 3.6412 (3.0791)	grad_norm 1.5159 (2.0262/0.8019)	mem 24308MB
[2025-01-19 00:28:04 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][60/312]	eta 0:02:41 lr 0.001027	time 0.5835 (0.6412)	model_time 0.5830 (0.6120)	loss 2.4037 (3.0877)	grad_norm 2.8037 (2.0290/0.7802)	mem 24308MB
[2025-01-19 00:28:10 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][70/312]	eta 0:02:34 lr 0.001026	time 0.5835 (0.6366)	model_time 0.5834 (0.6115)	loss 3.1000 (3.0936)	grad_norm 2.4015 (2.0170/0.7401)	mem 24308MB
[2025-01-19 00:28:16 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][80/312]	eta 0:02:26 lr 0.001025	time 0.5788 (0.6319)	model_time 0.5786 (0.6098)	loss 3.3521 (3.0779)	grad_norm 4.2776 (2.0853/0.8035)	mem 24308MB
[2025-01-19 00:28:22 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][90/312]	eta 0:02:19 lr 0.001025	time 0.6778 (0.6288)	model_time 0.6774 (0.6091)	loss 2.1733 (3.0619)	grad_norm 1.2504 (2.2035/1.0170)	mem 24308MB
[2025-01-19 00:28:28 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][100/312]	eta 0:02:12 lr 0.001024	time 0.5851 (0.6257)	model_time 0.5847 (0.6079)	loss 3.4062 (3.0676)	grad_norm 1.4286 (2.1614/0.9825)	mem 24308MB
[2025-01-19 00:28:34 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][110/312]	eta 0:02:05 lr 0.001024	time 0.5970 (0.6235)	model_time 0.5969 (0.6073)	loss 2.6990 (3.0778)	grad_norm 1.1408 (2.1030/0.9635)	mem 24308MB
[2025-01-19 00:28:40 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][120/312]	eta 0:01:59 lr 0.001023	time 0.5853 (0.6211)	model_time 0.5852 (0.6062)	loss 2.8564 (3.0380)	grad_norm 2.9069 (2.1463/0.9583)	mem 24308MB
[2025-01-19 00:28:46 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][130/312]	eta 0:01:52 lr 0.001023	time 0.6727 (0.6202)	model_time 0.6725 (0.6064)	loss 3.0458 (3.0432)	grad_norm 2.8590 (2.1868/0.9629)	mem 24308MB
[2025-01-19 00:28:52 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][140/312]	eta 0:01:46 lr 0.001022	time 0.6744 (0.6195)	model_time 0.6742 (0.6066)	loss 3.3696 (3.0652)	grad_norm 2.3346 (2.1996/0.9442)	mem 24308MB
[2025-01-19 00:28:58 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][150/312]	eta 0:01:40 lr 0.001021	time 0.5922 (0.6186)	model_time 0.5921 (0.6066)	loss 2.6054 (3.0704)	grad_norm 2.1789 (2.2091/0.9212)	mem 24308MB
[2025-01-19 00:29:05 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][160/312]	eta 0:01:34 lr 0.001021	time 0.5932 (0.6197)	model_time 0.5928 (0.6084)	loss 3.0630 (3.0606)	grad_norm 3.9544 (2.2107/0.9191)	mem 24308MB
[2025-01-19 00:29:11 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][170/312]	eta 0:01:27 lr 0.001020	time 0.6708 (0.6190)	model_time 0.6706 (0.6083)	loss 2.4558 (3.0620)	grad_norm 0.9792 (2.1738/0.9189)	mem 24308MB
[2025-01-19 00:29:17 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][180/312]	eta 0:01:21 lr 0.001020	time 0.5753 (0.6189)	model_time 0.5748 (0.6088)	loss 1.9742 (3.0665)	grad_norm 0.7344 (2.1570/0.9125)	mem 24308MB
[2025-01-19 00:29:23 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][190/312]	eta 0:01:15 lr 0.001019	time 0.5908 (0.6186)	model_time 0.5907 (0.6090)	loss 2.6070 (3.0578)	grad_norm 2.8105 (2.1403/0.9017)	mem 24308MB
[2025-01-19 00:29:29 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][200/312]	eta 0:01:09 lr 0.001019	time 0.5875 (0.6180)	model_time 0.5873 (0.6088)	loss 3.7823 (3.0565)	grad_norm 1.8734 (2.1342/0.8870)	mem 24308MB
[2025-01-19 00:29:35 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][210/312]	eta 0:01:02 lr 0.001018	time 0.5923 (0.6172)	model_time 0.5921 (0.6084)	loss 2.9518 (3.0663)	grad_norm 4.9373 (2.1803/0.9222)	mem 24308MB
[2025-01-19 00:29:41 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][220/312]	eta 0:00:56 lr 0.001017	time 0.5908 (0.6166)	model_time 0.5904 (0.6082)	loss 2.0592 (3.0605)	grad_norm 2.9125 (2.2621/1.0491)	mem 24308MB
[2025-01-19 00:29:47 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][230/312]	eta 0:00:50 lr 0.001017	time 0.5916 (0.6159)	model_time 0.5915 (0.6078)	loss 3.5033 (3.0547)	grad_norm 1.3284 (2.2791/1.0457)	mem 24308MB
[2025-01-19 00:29:53 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][240/312]	eta 0:00:44 lr 0.001016	time 0.6160 (0.6152)	model_time 0.6158 (0.6074)	loss 3.4841 (3.0605)	grad_norm 1.2946 (2.2526/1.0360)	mem 24308MB
[2025-01-19 00:29:59 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][250/312]	eta 0:00:38 lr 0.001016	time 0.5884 (0.6148)	model_time 0.5880 (0.6074)	loss 3.2532 (3.0538)	grad_norm 1.0885 (2.2359/1.0238)	mem 24308MB
[2025-01-19 00:30:05 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][260/312]	eta 0:00:31 lr 0.001015	time 0.5927 (0.6146)	model_time 0.5926 (0.6074)	loss 3.8821 (3.0646)	grad_norm 1.9916 (2.2313/1.0153)	mem 24308MB
[2025-01-19 00:30:11 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][270/312]	eta 0:00:25 lr 0.001015	time 0.6051 (0.6140)	model_time 0.6049 (0.6071)	loss 3.2231 (3.0749)	grad_norm 3.4072 (2.2645/1.0485)	mem 24308MB
[2025-01-19 00:30:18 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][280/312]	eta 0:00:19 lr 0.001014	time 0.5774 (0.6149)	model_time 0.5772 (0.6083)	loss 3.1157 (3.0710)	grad_norm 1.6777 (2.2881/1.0492)	mem 24308MB
[2025-01-19 00:30:24 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][290/312]	eta 0:00:13 lr 0.001013	time 0.6685 (0.6148)	model_time 0.6683 (0.6083)	loss 3.5763 (3.0797)	grad_norm 2.3370 (2.2765/1.0399)	mem 24308MB
[2025-01-19 00:30:30 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][300/312]	eta 0:00:07 lr 0.001013	time 0.5719 (0.6145)	model_time 0.5718 (0.6082)	loss 3.3911 (3.0852)	grad_norm 1.4619 (2.2913/1.0513)	mem 24308MB
[2025-01-19 00:30:36 internimage_s_1k_224] (main.py 510): INFO Train: [200/300][310/312]	eta 0:00:01 lr 0.001012	time 0.5687 (0.6137)	model_time 0.5686 (0.6076)	loss 3.7482 (3.0837)	grad_norm 1.7663 (2.2818/1.0432)	mem 24308MB
[2025-01-19 00:30:37 internimage_s_1k_224] (main.py 519): INFO EPOCH 200 training takes 0:03:11
[2025-01-19 00:30:37 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_200.pth saving......
[2025-01-19 00:30:38 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_200.pth saved !!!
[2025-01-19 00:30:46 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.744 (7.744)	Loss 0.7387 (0.7387)	Acc@1 84.180 (84.180)	Acc@5 97.510 (97.510)	Mem 24308MB
[2025-01-19 00:30:50 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.021)	Loss 1.0415 (0.8627)	Acc@1 76.953 (81.652)	Acc@5 94.482 (95.958)	Mem 24308MB
[2025-01-19 00:30:50 internimage_s_1k_224] (main.py 575): INFO [Epoch:200] * Acc@1 81.528 Acc@5 96.005
[2025-01-19 00:30:50 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.5%
[2025-01-19 00:30:50 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.60%
[2025-01-19 00:30:58 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.714 (8.714)	Loss 0.7063 (0.7063)	Acc@1 84.888 (84.888)	Acc@5 97.632 (97.632)	Mem 24308MB
[2025-01-19 00:31:03 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.180)	Loss 0.9489 (0.8058)	Acc@1 77.612 (82.093)	Acc@5 94.873 (96.149)	Mem 24308MB
[2025-01-19 00:31:03 internimage_s_1k_224] (main.py 575): INFO [Epoch:200] * Acc@1 81.952 Acc@5 96.177
[2025-01-19 00:31:03 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.0%
[2025-01-19 00:31:03 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:31:05 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:31:05 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.95%
[2025-01-19 00:31:08 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][0/312]	eta 0:12:36 lr 0.001012	time 2.4261 (2.4261)	model_time 0.6040 (0.6040)	loss 3.1120 (3.1120)	grad_norm 1.5021 (1.5021/0.0000)	mem 24308MB
[2025-01-19 00:31:14 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][10/312]	eta 0:03:54 lr 0.001012	time 0.5957 (0.7769)	model_time 0.5955 (0.6111)	loss 3.2056 (3.0170)	grad_norm 1.5182 (1.8116/0.4784)	mem 24308MB
[2025-01-19 00:31:20 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][20/312]	eta 0:03:22 lr 0.001011	time 0.6170 (0.6920)	model_time 0.6168 (0.6050)	loss 3.6337 (3.0937)	grad_norm 1.0052 (1.8078/0.6007)	mem 24308MB
[2025-01-19 00:31:26 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][30/312]	eta 0:03:07 lr 0.001010	time 0.5993 (0.6661)	model_time 0.5992 (0.6071)	loss 2.5788 (3.0590)	grad_norm 2.4427 (1.9037/0.6710)	mem 24308MB
[2025-01-19 00:31:32 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][40/312]	eta 0:02:57 lr 0.001010	time 0.5849 (0.6516)	model_time 0.5848 (0.6068)	loss 2.8835 (3.0115)	grad_norm 2.4634 (2.0202/0.6519)	mem 24308MB
[2025-01-19 00:31:38 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][50/312]	eta 0:02:47 lr 0.001009	time 0.5763 (0.6392)	model_time 0.5762 (0.6032)	loss 2.7639 (3.0066)	grad_norm 1.8513 (1.9454/0.6322)	mem 24308MB
[2025-01-19 00:31:44 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][60/312]	eta 0:02:39 lr 0.001009	time 0.6699 (0.6348)	model_time 0.6697 (0.6046)	loss 3.0932 (3.0229)	grad_norm 2.3512 (1.9501/0.6875)	mem 24308MB
[2025-01-19 00:31:50 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][70/312]	eta 0:02:32 lr 0.001008	time 0.6891 (0.6309)	model_time 0.6886 (0.6049)	loss 3.4134 (3.0588)	grad_norm 1.8098 (1.8885/0.6850)	mem 24308MB
[2025-01-19 00:31:56 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][80/312]	eta 0:02:25 lr 0.001008	time 0.6448 (0.6272)	model_time 0.6446 (0.6044)	loss 1.9381 (3.0588)	grad_norm 1.4622 (1.8861/0.6751)	mem 24308MB
[2025-01-19 00:32:02 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][90/312]	eta 0:02:19 lr 0.001007	time 0.5759 (0.6272)	model_time 0.5754 (0.6068)	loss 2.1183 (3.0503)	grad_norm 2.7899 (1.9245/0.6568)	mem 24308MB
[2025-01-19 00:32:09 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][100/312]	eta 0:02:12 lr 0.001006	time 0.6618 (0.6265)	model_time 0.6613 (0.6081)	loss 3.4379 (3.0698)	grad_norm 1.4144 (1.9790/0.6837)	mem 24308MB
[2025-01-19 00:32:15 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][110/312]	eta 0:02:06 lr 0.001006	time 0.5985 (0.6244)	model_time 0.5981 (0.6076)	loss 3.6519 (3.0850)	grad_norm 3.0268 (2.0519/0.7567)	mem 24308MB
[2025-01-19 00:32:21 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][120/312]	eta 0:01:59 lr 0.001005	time 0.5837 (0.6241)	model_time 0.5835 (0.6087)	loss 2.6051 (3.0740)	grad_norm 3.0071 (2.0412/0.7446)	mem 24308MB
[2025-01-19 00:32:27 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][130/312]	eta 0:01:53 lr 0.001005	time 0.6067 (0.6234)	model_time 0.6064 (0.6092)	loss 2.4515 (3.0662)	grad_norm 3.5867 (2.0882/0.7554)	mem 24308MB
[2025-01-19 00:32:33 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][140/312]	eta 0:01:46 lr 0.001004	time 0.5930 (0.6214)	model_time 0.5929 (0.6082)	loss 3.5332 (3.0552)	grad_norm 3.2344 (2.1392/0.7957)	mem 24308MB
[2025-01-19 00:32:39 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][150/312]	eta 0:01:40 lr 0.001004	time 0.6022 (0.6202)	model_time 0.6020 (0.6078)	loss 3.7867 (3.0822)	grad_norm 5.0063 (2.1351/0.8351)	mem 24308MB
[2025-01-19 00:32:45 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][160/312]	eta 0:01:34 lr 0.001003	time 0.5948 (0.6195)	model_time 0.5944 (0.6078)	loss 3.6986 (3.0924)	grad_norm 2.3000 (2.1148/0.8203)	mem 24308MB
[2025-01-19 00:32:51 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][170/312]	eta 0:01:27 lr 0.001002	time 0.5961 (0.6182)	model_time 0.5956 (0.6072)	loss 3.2055 (3.0932)	grad_norm 1.6025 (2.0835/0.8083)	mem 24308MB
[2025-01-19 00:32:57 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][180/312]	eta 0:01:21 lr 0.001002	time 0.6940 (0.6174)	model_time 0.6936 (0.6070)	loss 3.7898 (3.0981)	grad_norm 2.1023 (2.0955/0.8170)	mem 24308MB
[2025-01-19 00:33:03 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][190/312]	eta 0:01:15 lr 0.001001	time 0.8650 (0.6182)	model_time 0.8645 (0.6083)	loss 3.1709 (3.1101)	grad_norm 5.1424 (2.1304/0.8453)	mem 24308MB
[2025-01-19 00:33:09 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][200/312]	eta 0:01:09 lr 0.001001	time 0.5963 (0.6176)	model_time 0.5961 (0.6082)	loss 2.6162 (3.1124)	grad_norm 3.3376 (2.1972/0.9739)	mem 24308MB
[2025-01-19 00:33:16 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][210/312]	eta 0:01:03 lr 0.001000	time 0.5903 (0.6184)	model_time 0.5899 (0.6094)	loss 3.3278 (3.1079)	grad_norm 2.5553 (2.2140/0.9721)	mem 24308MB
[2025-01-19 00:33:22 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][220/312]	eta 0:00:56 lr 0.001000	time 0.6656 (0.6179)	model_time 0.6652 (0.6093)	loss 2.9053 (3.1101)	grad_norm 1.3881 (2.1981/0.9614)	mem 24308MB
[2025-01-19 00:33:28 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][230/312]	eta 0:00:50 lr 0.000999	time 0.5907 (0.6176)	model_time 0.5902 (0.6093)	loss 3.2708 (3.1076)	grad_norm 1.9526 (2.1946/0.9509)	mem 24308MB
[2025-01-19 00:33:34 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][240/312]	eta 0:00:44 lr 0.000998	time 0.5808 (0.6169)	model_time 0.5804 (0.6089)	loss 3.2789 (3.1093)	grad_norm 1.2538 (2.1776/0.9398)	mem 24308MB
[2025-01-19 00:33:40 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][250/312]	eta 0:00:38 lr 0.000998	time 0.6587 (0.6165)	model_time 0.6585 (0.6088)	loss 3.7412 (3.1047)	grad_norm 1.3659 (2.1536/0.9317)	mem 24308MB
[2025-01-19 00:33:46 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][260/312]	eta 0:00:32 lr 0.000997	time 0.5923 (0.6156)	model_time 0.5919 (0.6083)	loss 2.4576 (3.1094)	grad_norm 1.2563 (2.1455/0.9252)	mem 24308MB
[2025-01-19 00:33:52 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][270/312]	eta 0:00:25 lr 0.000997	time 0.5818 (0.6153)	model_time 0.5816 (0.6082)	loss 3.2582 (3.1166)	grad_norm 1.5662 (2.1293/0.9253)	mem 24308MB
[2025-01-19 00:33:58 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][280/312]	eta 0:00:19 lr 0.000996	time 0.5863 (0.6150)	model_time 0.5861 (0.6081)	loss 3.2379 (3.1149)	grad_norm 1.8805 (2.1244/0.9187)	mem 24308MB
[2025-01-19 00:34:04 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][290/312]	eta 0:00:13 lr 0.000996	time 0.5842 (0.6141)	model_time 0.5838 (0.6074)	loss 3.4866 (3.1121)	grad_norm 2.3275 (2.1090/0.9127)	mem 24308MB
[2025-01-19 00:34:10 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][300/312]	eta 0:00:07 lr 0.000995	time 0.5713 (0.6133)	model_time 0.5712 (0.6068)	loss 3.1706 (3.1174)	grad_norm 1.4565 (2.1087/0.9050)	mem 24308MB
[2025-01-19 00:34:16 internimage_s_1k_224] (main.py 510): INFO Train: [201/300][310/312]	eta 0:00:01 lr 0.000994	time 0.6748 (0.6129)	model_time 0.6747 (0.6066)	loss 3.0070 (3.1093)	grad_norm 2.7735 (2.1192/0.9047)	mem 24308MB
[2025-01-19 00:34:16 internimage_s_1k_224] (main.py 519): INFO EPOCH 201 training takes 0:03:11
[2025-01-19 00:34:16 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_201.pth saving......
[2025-01-19 00:34:18 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_201.pth saved !!!
[2025-01-19 00:34:26 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.973 (7.973)	Loss 0.7669 (0.7669)	Acc@1 84.131 (84.131)	Acc@5 97.290 (97.290)	Mem 24308MB
[2025-01-19 00:34:30 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.135 (1.049)	Loss 1.0030 (0.8684)	Acc@1 77.319 (81.774)	Acc@5 94.702 (95.981)	Mem 24308MB
[2025-01-19 00:34:30 internimage_s_1k_224] (main.py 575): INFO [Epoch:201] * Acc@1 81.598 Acc@5 96.003
[2025-01-19 00:34:30 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.6%
[2025-01-19 00:34:30 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.60%
[2025-01-19 00:34:39 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.742 (8.742)	Loss 0.7061 (0.7061)	Acc@1 84.863 (84.863)	Acc@5 97.656 (97.656)	Mem 24308MB
[2025-01-19 00:34:43 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (1.194)	Loss 0.9477 (0.8052)	Acc@1 77.661 (82.109)	Acc@5 94.946 (96.178)	Mem 24308MB
[2025-01-19 00:34:43 internimage_s_1k_224] (main.py 575): INFO [Epoch:201] * Acc@1 81.970 Acc@5 96.207
[2025-01-19 00:34:43 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.0%
[2025-01-19 00:34:43 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:34:46 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:34:46 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 81.97%
[2025-01-19 00:34:48 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][0/312]	eta 0:11:39 lr 0.000994	time 2.2410 (2.2410)	model_time 0.5930 (0.5930)	loss 3.6446 (3.6446)	grad_norm 1.5732 (1.5732/0.0000)	mem 24308MB
[2025-01-19 00:34:54 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][10/312]	eta 0:03:49 lr 0.000994	time 0.5746 (0.7590)	model_time 0.5744 (0.6089)	loss 3.4378 (3.1568)	grad_norm 2.8266 (2.8479/1.2019)	mem 24308MB
[2025-01-19 00:35:01 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][20/312]	eta 0:03:24 lr 0.000993	time 0.5801 (0.6997)	model_time 0.5799 (0.6210)	loss 2.9907 (3.1446)	grad_norm 2.5737 (2.4508/1.0636)	mem 24308MB
[2025-01-19 00:35:07 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][30/312]	eta 0:03:08 lr 0.000993	time 0.6806 (0.6692)	model_time 0.6804 (0.6157)	loss 3.0545 (3.1079)	grad_norm 2.7435 (2.2663/0.9526)	mem 24308MB
[2025-01-19 00:35:13 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][40/312]	eta 0:02:58 lr 0.000992	time 0.5956 (0.6550)	model_time 0.5952 (0.6144)	loss 2.0442 (3.0620)	grad_norm 3.0558 (2.1714/0.9081)	mem 24308MB
[2025-01-19 00:35:19 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][50/312]	eta 0:02:49 lr 0.000991	time 0.5947 (0.6480)	model_time 0.5945 (0.6154)	loss 3.0177 (3.0678)	grad_norm 1.9557 (2.2022/0.9067)	mem 24308MB
[2025-01-19 00:35:25 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][60/312]	eta 0:02:41 lr 0.000991	time 0.6746 (0.6412)	model_time 0.6742 (0.6138)	loss 3.3181 (3.0916)	grad_norm 2.1393 (2.1939/0.8736)	mem 24308MB
[2025-01-19 00:35:31 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][70/312]	eta 0:02:33 lr 0.000990	time 0.5917 (0.6340)	model_time 0.5912 (0.6104)	loss 3.1325 (3.1324)	grad_norm 1.6486 (2.1607/0.8567)	mem 24308MB
[2025-01-19 00:35:37 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][80/312]	eta 0:02:26 lr 0.000990	time 0.6481 (0.6317)	model_time 0.6479 (0.6109)	loss 3.6559 (3.1443)	grad_norm 0.8083 (2.0973/0.8384)	mem 24308MB
[2025-01-19 00:35:43 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][90/312]	eta 0:02:19 lr 0.000989	time 0.6885 (0.6277)	model_time 0.6881 (0.6092)	loss 2.7545 (3.1219)	grad_norm 1.3980 (2.0872/0.8301)	mem 24308MB
[2025-01-19 00:35:49 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][100/312]	eta 0:02:12 lr 0.000989	time 0.5818 (0.6241)	model_time 0.5813 (0.6074)	loss 3.4196 (3.1415)	grad_norm 2.5196 (2.1150/0.8197)	mem 24308MB
[2025-01-19 00:35:55 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][110/312]	eta 0:02:05 lr 0.000988	time 0.5856 (0.6215)	model_time 0.5852 (0.6063)	loss 3.6284 (3.1357)	grad_norm 1.5050 (2.1071/0.7969)	mem 24308MB
[2025-01-19 00:36:01 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][120/312]	eta 0:01:59 lr 0.000987	time 0.5757 (0.6203)	model_time 0.5755 (0.6063)	loss 2.8619 (3.1167)	grad_norm 2.6088 (2.0715/0.7840)	mem 24308MB
[2025-01-19 00:36:07 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][130/312]	eta 0:01:52 lr 0.000987	time 0.6899 (0.6204)	model_time 0.6898 (0.6074)	loss 3.4429 (3.0987)	grad_norm 1.4101 (2.0826/0.7743)	mem 24308MB
[2025-01-19 00:36:14 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][140/312]	eta 0:01:46 lr 0.000986	time 0.6701 (0.6217)	model_time 0.6699 (0.6096)	loss 2.9627 (3.0802)	grad_norm 1.4938 (2.1175/0.8265)	mem 24308MB
[2025-01-19 00:36:19 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][150/312]	eta 0:01:40 lr 0.000986	time 0.5735 (0.6198)	model_time 0.5733 (0.6085)	loss 2.9633 (3.0836)	grad_norm 2.0470 (2.1176/0.8162)	mem 24308MB
[2025-01-19 00:36:26 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][160/312]	eta 0:01:34 lr 0.000985	time 0.5879 (0.6195)	model_time 0.5874 (0.6089)	loss 3.3206 (3.0873)	grad_norm 4.6826 (2.1147/0.8417)	mem 24308MB
[2025-01-19 00:36:32 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][170/312]	eta 0:01:27 lr 0.000985	time 0.5890 (0.6193)	model_time 0.5886 (0.6093)	loss 3.5074 (3.0832)	grad_norm 1.3800 (2.1213/0.8436)	mem 24308MB
[2025-01-19 00:36:38 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][180/312]	eta 0:01:21 lr 0.000984	time 0.6548 (0.6183)	model_time 0.6542 (0.6088)	loss 3.2501 (3.0836)	grad_norm 2.2881 (2.1300/0.8352)	mem 24308MB
[2025-01-19 00:36:44 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][190/312]	eta 0:01:15 lr 0.000984	time 0.5960 (0.6173)	model_time 0.5956 (0.6083)	loss 3.1172 (3.0867)	grad_norm 2.1587 (2.1078/0.8246)	mem 24308MB
[2025-01-19 00:36:50 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][200/312]	eta 0:01:09 lr 0.000983	time 0.6870 (0.6169)	model_time 0.6865 (0.6083)	loss 3.4386 (3.0929)	grad_norm 2.5108 (2.1081/0.8135)	mem 24308MB
[2025-01-19 00:36:56 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][210/312]	eta 0:01:02 lr 0.000982	time 0.5754 (0.6154)	model_time 0.5752 (0.6071)	loss 3.6079 (3.0925)	grad_norm 2.6560 (2.1517/0.8468)	mem 24308MB
[2025-01-19 00:37:02 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][220/312]	eta 0:00:56 lr 0.000982	time 0.5840 (0.6148)	model_time 0.5835 (0.6069)	loss 3.0490 (3.0907)	grad_norm 3.3401 (2.1652/0.8537)	mem 24308MB
[2025-01-19 00:37:08 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][230/312]	eta 0:00:50 lr 0.000981	time 0.5783 (0.6143)	model_time 0.5779 (0.6068)	loss 3.6413 (3.0903)	grad_norm 1.6504 (2.1496/0.8450)	mem 24308MB
[2025-01-19 00:37:14 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][240/312]	eta 0:00:44 lr 0.000981	time 0.5723 (0.6141)	model_time 0.5721 (0.6069)	loss 3.1189 (3.0944)	grad_norm 2.1636 (2.1593/0.8543)	mem 24308MB
[2025-01-19 00:37:20 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][250/312]	eta 0:00:38 lr 0.000980	time 0.6855 (0.6143)	model_time 0.6851 (0.6074)	loss 3.4653 (3.0989)	grad_norm 2.6232 (2.1913/0.8929)	mem 24308MB
[2025-01-19 00:37:26 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][260/312]	eta 0:00:31 lr 0.000980	time 0.6476 (0.6152)	model_time 0.6474 (0.6085)	loss 2.9485 (3.0978)	grad_norm 1.4922 (2.1860/0.8875)	mem 24308MB
[2025-01-19 00:37:32 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][270/312]	eta 0:00:25 lr 0.000979	time 0.6192 (0.6146)	model_time 0.6187 (0.6082)	loss 3.4151 (3.0912)	grad_norm 2.8697 (2.1886/0.9073)	mem 24308MB
[2025-01-19 00:37:39 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][280/312]	eta 0:00:19 lr 0.000978	time 0.5918 (0.6148)	model_time 0.5916 (0.6085)	loss 3.6129 (3.0915)	grad_norm 1.1273 (2.1702/0.9019)	mem 24308MB
[2025-01-19 00:37:45 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][290/312]	eta 0:00:13 lr 0.000978	time 0.5943 (0.6150)	model_time 0.5942 (0.6090)	loss 3.6802 (3.0914)	grad_norm 2.4891 (2.1694/0.8950)	mem 24308MB
[2025-01-19 00:37:51 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][300/312]	eta 0:00:07 lr 0.000977	time 0.5692 (0.6140)	model_time 0.5691 (0.6082)	loss 3.4826 (3.0956)	grad_norm 4.6644 (2.1884/0.8973)	mem 24308MB
[2025-01-19 00:37:57 internimage_s_1k_224] (main.py 510): INFO Train: [202/300][310/312]	eta 0:00:01 lr 0.000977	time 0.5701 (0.6133)	model_time 0.5700 (0.6076)	loss 3.1749 (3.1018)	grad_norm 3.2034 (2.1619/0.8697)	mem 24308MB
[2025-01-19 00:37:57 internimage_s_1k_224] (main.py 519): INFO EPOCH 202 training takes 0:03:11
[2025-01-19 00:37:57 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_202.pth saving......
[2025-01-19 00:37:59 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_202.pth saved !!!
[2025-01-19 00:38:07 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.698 (7.698)	Loss 0.7591 (0.7591)	Acc@1 83.984 (83.984)	Acc@5 97.217 (97.217)	Mem 24308MB
[2025-01-19 00:38:10 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.030)	Loss 0.9952 (0.8665)	Acc@1 77.930 (81.887)	Acc@5 94.727 (95.994)	Mem 24308MB
[2025-01-19 00:38:11 internimage_s_1k_224] (main.py 575): INFO [Epoch:202] * Acc@1 81.684 Acc@5 95.993
[2025-01-19 00:38:11 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.7%
[2025-01-19 00:38:11 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:38:13 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:38:13 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.68%
[2025-01-19 00:38:20 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.796 (7.796)	Loss 0.7059 (0.7059)	Acc@1 84.912 (84.912)	Acc@5 97.632 (97.632)	Mem 24308MB
[2025-01-19 00:38:24 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.018)	Loss 0.9465 (0.8046)	Acc@1 77.734 (82.138)	Acc@5 94.922 (96.171)	Mem 24308MB
[2025-01-19 00:38:24 internimage_s_1k_224] (main.py 575): INFO [Epoch:202] * Acc@1 82.000 Acc@5 96.203
[2025-01-19 00:38:24 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.0%
[2025-01-19 00:38:24 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:38:26 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:38:26 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.00%
[2025-01-19 00:38:28 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][0/312]	eta 0:11:33 lr 0.000977	time 2.2216 (2.2216)	model_time 0.6033 (0.6033)	loss 3.5044 (3.5044)	grad_norm 2.6309 (2.6309/0.0000)	mem 24308MB
[2025-01-19 00:38:35 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][10/312]	eta 0:03:47 lr 0.000976	time 0.6515 (0.7528)	model_time 0.6513 (0.6054)	loss 2.4626 (3.1919)	grad_norm 1.1956 (2.0994/0.5361)	mem 24308MB
[2025-01-19 00:38:40 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][20/312]	eta 0:03:17 lr 0.000975	time 0.5744 (0.6774)	model_time 0.5742 (0.6001)	loss 1.9521 (3.0550)	grad_norm 1.9527 (2.2945/0.8025)	mem 24308MB
[2025-01-19 00:38:47 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][30/312]	eta 0:03:04 lr 0.000975	time 0.5733 (0.6545)	model_time 0.5726 (0.6020)	loss 2.4199 (3.0551)	grad_norm 1.6767 (2.0848/0.7556)	mem 24308MB
[2025-01-19 00:38:52 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][40/312]	eta 0:02:54 lr 0.000974	time 0.6572 (0.6401)	model_time 0.6570 (0.5999)	loss 3.2403 (3.1039)	grad_norm 1.5571 (2.1751/0.8566)	mem 24308MB
[2025-01-19 00:38:59 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][50/312]	eta 0:02:46 lr 0.000974	time 0.5726 (0.6349)	model_time 0.5724 (0.6025)	loss 2.5160 (3.0801)	grad_norm 2.2674 (2.1885/0.8652)	mem 24308MB
[2025-01-19 00:39:05 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][60/312]	eta 0:02:39 lr 0.000973	time 0.5971 (0.6329)	model_time 0.5969 (0.6058)	loss 1.9819 (3.0858)	grad_norm 1.4803 (2.2004/0.9479)	mem 24308MB
[2025-01-19 00:39:11 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][70/312]	eta 0:02:33 lr 0.000973	time 0.5754 (0.6339)	model_time 0.5750 (0.6106)	loss 2.7189 (3.0683)	grad_norm 2.2470 (2.1585/0.9132)	mem 24308MB
[2025-01-19 00:39:17 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][80/312]	eta 0:02:26 lr 0.000972	time 0.5828 (0.6297)	model_time 0.5823 (0.6092)	loss 3.2006 (3.0648)	grad_norm 1.7204 (2.1347/0.8791)	mem 24308MB
[2025-01-19 00:39:23 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][90/312]	eta 0:02:19 lr 0.000972	time 0.6571 (0.6291)	model_time 0.6570 (0.6108)	loss 2.0789 (3.0786)	grad_norm 1.4718 (2.1031/0.8550)	mem 24308MB
[2025-01-19 00:39:30 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][100/312]	eta 0:02:12 lr 0.000971	time 0.6668 (0.6271)	model_time 0.6666 (0.6106)	loss 2.0965 (3.0648)	grad_norm 1.8112 (2.1679/0.9322)	mem 24308MB
[2025-01-19 00:39:36 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][110/312]	eta 0:02:06 lr 0.000970	time 0.6735 (0.6246)	model_time 0.6731 (0.6095)	loss 3.6572 (3.0764)	grad_norm 2.9221 (2.2494/1.0024)	mem 24308MB
[2025-01-19 00:39:42 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][120/312]	eta 0:01:59 lr 0.000970	time 0.5842 (0.6226)	model_time 0.5838 (0.6087)	loss 3.1092 (3.0881)	grad_norm 2.1630 (2.2071/0.9782)	mem 24308MB
[2025-01-19 00:39:48 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][130/312]	eta 0:01:52 lr 0.000969	time 0.5894 (0.6206)	model_time 0.5892 (0.6077)	loss 3.2187 (3.0780)	grad_norm 1.4266 (2.1733/0.9623)	mem 24308MB
[2025-01-19 00:39:54 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][140/312]	eta 0:01:46 lr 0.000969	time 0.5906 (0.6192)	model_time 0.5904 (0.6072)	loss 3.4416 (3.0865)	grad_norm 3.1954 (2.1553/0.9456)	mem 24308MB
[2025-01-19 00:40:00 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][150/312]	eta 0:01:40 lr 0.000968	time 0.6008 (0.6178)	model_time 0.6004 (0.6067)	loss 3.4288 (3.0741)	grad_norm 2.4802 (2.2343/1.0030)	mem 24308MB
[2025-01-19 00:40:05 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][160/312]	eta 0:01:33 lr 0.000968	time 0.5969 (0.6159)	model_time 0.5967 (0.6054)	loss 3.8356 (3.0774)	grad_norm 2.9546 (2.3071/1.0677)	mem 24308MB
[2025-01-19 00:40:12 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][170/312]	eta 0:01:27 lr 0.000967	time 0.5865 (0.6156)	model_time 0.5861 (0.6057)	loss 3.4167 (3.0911)	grad_norm 3.5702 (2.2886/1.0528)	mem 24308MB
[2025-01-19 00:40:18 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][180/312]	eta 0:01:21 lr 0.000966	time 0.5747 (0.6151)	model_time 0.5745 (0.6057)	loss 2.5714 (3.0878)	grad_norm 2.9002 (2.2445/1.0485)	mem 24308MB
[2025-01-19 00:40:24 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][190/312]	eta 0:01:15 lr 0.000966	time 0.5805 (0.6159)	model_time 0.5803 (0.6069)	loss 2.8460 (3.0858)	grad_norm 1.3129 (2.2135/1.0350)	mem 24308MB
[2025-01-19 00:40:30 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][200/312]	eta 0:01:08 lr 0.000965	time 0.5750 (0.6154)	model_time 0.5748 (0.6069)	loss 3.3402 (3.0854)	grad_norm 3.3086 (2.2140/1.0211)	mem 24308MB
[2025-01-19 00:40:36 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][210/312]	eta 0:01:02 lr 0.000965	time 0.6641 (0.6158)	model_time 0.6639 (0.6077)	loss 2.7943 (3.0899)	grad_norm 1.6457 (2.2691/1.0580)	mem 24308MB
[2025-01-19 00:40:42 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][220/312]	eta 0:00:56 lr 0.000964	time 0.5782 (0.6154)	model_time 0.5780 (0.6077)	loss 3.1374 (3.0819)	grad_norm 1.9092 (2.2638/1.0443)	mem 24308MB
[2025-01-19 00:40:48 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][230/312]	eta 0:00:50 lr 0.000964	time 0.5991 (0.6149)	model_time 0.5989 (0.6074)	loss 3.1892 (3.0775)	grad_norm 1.5689 (2.2319/1.0349)	mem 24308MB
[2025-01-19 00:40:54 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][240/312]	eta 0:00:44 lr 0.000963	time 0.5768 (0.6145)	model_time 0.5766 (0.6074)	loss 2.2928 (3.0785)	grad_norm 2.1342 (2.2357/1.0211)	mem 24308MB
[2025-01-19 00:41:00 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][250/312]	eta 0:00:38 lr 0.000963	time 0.5794 (0.6139)	model_time 0.5792 (0.6070)	loss 3.0771 (3.0762)	grad_norm 2.6848 (2.2434/1.0174)	mem 24308MB
[2025-01-19 00:41:06 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][260/312]	eta 0:00:31 lr 0.000962	time 0.6053 (0.6134)	model_time 0.6049 (0.6068)	loss 1.9966 (3.0698)	grad_norm 2.9970 (2.2570/1.0076)	mem 24308MB
[2025-01-19 00:41:12 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][270/312]	eta 0:00:25 lr 0.000961	time 0.5886 (0.6129)	model_time 0.5883 (0.6065)	loss 2.5757 (3.0676)	grad_norm 1.5983 (2.2454/0.9976)	mem 24308MB
[2025-01-19 00:41:18 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][280/312]	eta 0:00:19 lr 0.000961	time 0.6066 (0.6121)	model_time 0.6062 (0.6060)	loss 3.2520 (3.0686)	grad_norm 2.3606 (2.2370/0.9843)	mem 24308MB
[2025-01-19 00:41:24 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][290/312]	eta 0:00:13 lr 0.000960	time 0.5867 (0.6120)	model_time 0.5865 (0.6060)	loss 3.1387 (3.0623)	grad_norm 2.8017 (2.2492/0.9792)	mem 24308MB
[2025-01-19 00:41:30 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][300/312]	eta 0:00:07 lr 0.000960	time 0.5801 (0.6119)	model_time 0.5800 (0.6061)	loss 3.1448 (3.0666)	grad_norm 1.4737 (2.2543/0.9795)	mem 24308MB
[2025-01-19 00:41:37 internimage_s_1k_224] (main.py 510): INFO Train: [203/300][310/312]	eta 0:00:01 lr 0.000959	time 0.5635 (0.6119)	model_time 0.5634 (0.6063)	loss 3.4277 (3.0652)	grad_norm 1.4174 (2.2409/0.9838)	mem 24308MB
[2025-01-19 00:41:37 internimage_s_1k_224] (main.py 519): INFO EPOCH 203 training takes 0:03:10
[2025-01-19 00:41:37 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_203.pth saving......
[2025-01-19 00:41:39 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_203.pth saved !!!
[2025-01-19 00:41:55 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.397 (16.397)	Loss 0.7644 (0.7644)	Acc@1 84.009 (84.009)	Acc@5 97.412 (97.412)	Mem 24308MB
[2025-01-19 00:42:02 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (2.109)	Loss 0.9834 (0.8581)	Acc@1 78.076 (81.916)	Acc@5 94.873 (96.098)	Mem 24308MB
[2025-01-19 00:42:02 internimage_s_1k_224] (main.py 575): INFO [Epoch:203] * Acc@1 81.680 Acc@5 96.095
[2025-01-19 00:42:02 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.7%
[2025-01-19 00:42:02 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.68%
[2025-01-19 00:42:20 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 17.591 (17.591)	Loss 0.7058 (0.7058)	Acc@1 84.863 (84.863)	Acc@5 97.632 (97.632)	Mem 24308MB
[2025-01-19 00:42:26 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (2.160)	Loss 0.9451 (0.8039)	Acc@1 77.808 (82.164)	Acc@5 94.922 (96.189)	Mem 24308MB
[2025-01-19 00:42:26 internimage_s_1k_224] (main.py 575): INFO [Epoch:203] * Acc@1 82.030 Acc@5 96.217
[2025-01-19 00:42:26 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.0%
[2025-01-19 00:42:26 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:42:29 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:42:29 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.03%
[2025-01-19 00:42:31 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][0/312]	eta 0:09:54 lr 0.000959	time 1.9042 (1.9042)	model_time 0.6081 (0.6081)	loss 2.5412 (2.5412)	grad_norm 1.0076 (1.0076/0.0000)	mem 24308MB
[2025-01-19 00:42:37 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][10/312]	eta 0:03:40 lr 0.000959	time 0.6736 (0.7309)	model_time 0.6734 (0.6128)	loss 3.5918 (3.0631)	grad_norm 2.1367 (1.9601/0.6283)	mem 24308MB
[2025-01-19 00:42:43 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][20/312]	eta 0:03:16 lr 0.000958	time 0.6015 (0.6733)	model_time 0.6010 (0.6112)	loss 3.3730 (3.2642)	grad_norm 1.1683 (1.8940/0.5244)	mem 24308MB
[2025-01-19 00:42:49 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][30/312]	eta 0:03:04 lr 0.000957	time 0.6227 (0.6538)	model_time 0.6225 (0.6117)	loss 3.0578 (3.2259)	grad_norm 1.8770 (1.8262/0.5258)	mem 24308MB
[2025-01-19 00:42:55 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][40/312]	eta 0:02:54 lr 0.000957	time 0.5815 (0.6418)	model_time 0.5813 (0.6098)	loss 3.3999 (3.1601)	grad_norm 1.5795 (1.9738/0.6394)	mem 24308MB
[2025-01-19 00:43:01 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][50/312]	eta 0:02:46 lr 0.000956	time 0.5893 (0.6350)	model_time 0.5888 (0.6093)	loss 1.9295 (3.1336)	grad_norm 4.6876 (2.1868/0.9534)	mem 24308MB
[2025-01-19 00:43:07 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][60/312]	eta 0:02:38 lr 0.000956	time 0.5751 (0.6293)	model_time 0.5746 (0.6077)	loss 2.2455 (3.1122)	grad_norm 1.5935 (2.1998/0.9834)	mem 24308MB
[2025-01-19 00:43:13 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][70/312]	eta 0:02:31 lr 0.000955	time 0.5984 (0.6244)	model_time 0.5979 (0.6058)	loss 3.4439 (3.1145)	grad_norm 1.4410 (2.1673/0.9509)	mem 24308MB
[2025-01-19 00:43:19 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][80/312]	eta 0:02:24 lr 0.000955	time 0.5939 (0.6217)	model_time 0.5935 (0.6053)	loss 3.7392 (3.1027)	grad_norm 1.9135 (2.1328/0.9113)	mem 24308MB
[2025-01-19 00:43:25 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][90/312]	eta 0:02:17 lr 0.000954	time 0.5722 (0.6180)	model_time 0.5720 (0.6034)	loss 3.3911 (3.1177)	grad_norm 5.5241 (2.2044/1.0404)	mem 24308MB
[2025-01-19 00:43:31 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][100/312]	eta 0:02:10 lr 0.000953	time 0.6778 (0.6174)	model_time 0.6777 (0.6042)	loss 3.2989 (3.1005)	grad_norm 1.9889 (2.1853/1.0093)	mem 24308MB
[2025-01-19 00:43:37 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][110/312]	eta 0:02:04 lr 0.000953	time 0.5858 (0.6163)	model_time 0.5856 (0.6043)	loss 3.1791 (3.1137)	grad_norm 1.6073 (2.1762/0.9849)	mem 24308MB
[2025-01-19 00:43:43 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][120/312]	eta 0:01:58 lr 0.000952	time 0.6669 (0.6177)	model_time 0.6664 (0.6066)	loss 2.8104 (3.1042)	grad_norm 1.9864 (2.2134/1.0236)	mem 24308MB
[2025-01-19 00:43:50 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][130/312]	eta 0:01:52 lr 0.000952	time 0.6789 (0.6173)	model_time 0.6784 (0.6070)	loss 2.2011 (3.0976)	grad_norm 2.1963 (2.2853/1.0769)	mem 24308MB
[2025-01-19 00:43:56 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][140/312]	eta 0:01:46 lr 0.000951	time 0.5718 (0.6165)	model_time 0.5717 (0.6069)	loss 3.2640 (3.1116)	grad_norm 1.7209 (2.3033/1.0633)	mem 24308MB
[2025-01-19 00:44:02 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][150/312]	eta 0:01:39 lr 0.000951	time 0.5739 (0.6165)	model_time 0.5734 (0.6075)	loss 2.2089 (3.1134)	grad_norm 2.1176 (2.3034/1.0418)	mem 24308MB
[2025-01-19 00:44:08 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][160/312]	eta 0:01:33 lr 0.000950	time 0.5861 (0.6171)	model_time 0.5859 (0.6087)	loss 2.8304 (3.1060)	grad_norm 1.7753 (2.3382/1.0691)	mem 24308MB
[2025-01-19 00:44:14 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][170/312]	eta 0:01:27 lr 0.000950	time 0.5950 (0.6153)	model_time 0.5945 (0.6074)	loss 2.1318 (3.1105)	grad_norm 3.0582 (2.3315/1.0521)	mem 24308MB
[2025-01-19 00:44:20 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][180/312]	eta 0:01:21 lr 0.000949	time 0.6563 (0.6154)	model_time 0.6558 (0.6079)	loss 3.2222 (3.1018)	grad_norm 1.4416 (2.3344/1.0403)	mem 24308MB
[2025-01-19 00:44:26 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][190/312]	eta 0:01:14 lr 0.000948	time 0.5846 (0.6144)	model_time 0.5844 (0.6072)	loss 3.0941 (3.0983)	grad_norm 1.9091 (2.3207/1.0241)	mem 24308MB
[2025-01-19 00:44:32 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][200/312]	eta 0:01:08 lr 0.000948	time 0.5815 (0.6138)	model_time 0.5811 (0.6069)	loss 3.5533 (3.1068)	grad_norm 1.0559 (2.3017/1.0106)	mem 24308MB
[2025-01-19 00:44:38 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][210/312]	eta 0:01:02 lr 0.000947	time 0.5790 (0.6127)	model_time 0.5785 (0.6062)	loss 2.2495 (3.0945)	grad_norm 2.3602 (2.2881/0.9962)	mem 24308MB
[2025-01-19 00:44:44 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][220/312]	eta 0:00:56 lr 0.000947	time 0.6606 (0.6123)	model_time 0.6601 (0.6061)	loss 2.5231 (3.1029)	grad_norm 1.3087 (2.2708/0.9979)	mem 24308MB
[2025-01-19 00:44:50 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][230/312]	eta 0:00:50 lr 0.000946	time 0.5770 (0.6123)	model_time 0.5768 (0.6063)	loss 3.5140 (3.1092)	grad_norm 5.3815 (2.2670/1.0097)	mem 24308MB
[2025-01-19 00:44:56 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][240/312]	eta 0:00:44 lr 0.000946	time 0.6675 (0.6129)	model_time 0.6673 (0.6072)	loss 3.2349 (3.1055)	grad_norm 1.4889 (2.2909/1.0366)	mem 24308MB
[2025-01-19 00:45:03 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][250/312]	eta 0:00:38 lr 0.000945	time 0.6628 (0.6131)	model_time 0.6624 (0.6076)	loss 2.8828 (3.1145)	grad_norm 1.5847 (2.2851/1.0231)	mem 24308MB
[2025-01-19 00:45:09 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][260/312]	eta 0:00:31 lr 0.000945	time 0.5843 (0.6125)	model_time 0.5841 (0.6071)	loss 2.9261 (3.1159)	grad_norm 1.3732 (2.2592/1.0150)	mem 24308MB
[2025-01-19 00:45:15 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][270/312]	eta 0:00:25 lr 0.000944	time 0.5873 (0.6125)	model_time 0.5868 (0.6074)	loss 3.5309 (3.1145)	grad_norm 1.0841 (2.2584/1.0177)	mem 24308MB
[2025-01-19 00:45:21 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][280/312]	eta 0:00:19 lr 0.000943	time 0.5896 (0.6131)	model_time 0.5894 (0.6081)	loss 2.8962 (3.1104)	grad_norm 2.9956 (2.2562/1.0081)	mem 24308MB
[2025-01-19 00:45:27 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][290/312]	eta 0:00:13 lr 0.000943	time 0.6163 (0.6125)	model_time 0.6161 (0.6076)	loss 2.7916 (3.1066)	grad_norm 3.8672 (2.2492/1.0028)	mem 24308MB
[2025-01-19 00:45:33 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][300/312]	eta 0:00:07 lr 0.000942	time 0.5685 (0.6122)	model_time 0.5684 (0.6075)	loss 2.7235 (3.0997)	grad_norm 2.2047 (2.2597/0.9924)	mem 24308MB
[2025-01-19 00:45:39 internimage_s_1k_224] (main.py 510): INFO Train: [204/300][310/312]	eta 0:00:01 lr 0.000942	time 0.5686 (0.6112)	model_time 0.5685 (0.6067)	loss 3.8053 (3.1014)	grad_norm 1.9294 (2.2665/1.0035)	mem 24308MB
[2025-01-19 00:45:39 internimage_s_1k_224] (main.py 519): INFO EPOCH 204 training takes 0:03:10
[2025-01-19 00:45:39 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_204.pth saving......
[2025-01-19 00:45:41 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_204.pth saved !!!
[2025-01-19 00:45:49 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.786 (7.786)	Loss 0.7667 (0.7667)	Acc@1 84.180 (84.180)	Acc@5 97.119 (97.119)	Mem 24308MB
[2025-01-19 00:45:52 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.014)	Loss 1.0166 (0.8637)	Acc@1 77.539 (81.823)	Acc@5 94.604 (95.910)	Mem 24308MB
[2025-01-19 00:45:53 internimage_s_1k_224] (main.py 575): INFO [Epoch:204] * Acc@1 81.722 Acc@5 95.979
[2025-01-19 00:45:53 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.7%
[2025-01-19 00:45:53 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:45:54 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:45:54 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.72%
[2025-01-19 00:46:02 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.848 (7.848)	Loss 0.7058 (0.7058)	Acc@1 84.863 (84.863)	Acc@5 97.632 (97.632)	Mem 24308MB
[2025-01-19 00:46:06 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.032)	Loss 0.9437 (0.8033)	Acc@1 77.832 (82.204)	Acc@5 94.946 (96.200)	Mem 24308MB
[2025-01-19 00:46:06 internimage_s_1k_224] (main.py 575): INFO [Epoch:204] * Acc@1 82.074 Acc@5 96.229
[2025-01-19 00:46:06 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.1%
[2025-01-19 00:46:06 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:46:08 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:46:08 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.07%
[2025-01-19 00:46:11 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][0/312]	eta 0:12:04 lr 0.000942	time 2.3224 (2.3224)	model_time 0.5985 (0.5985)	loss 3.1900 (3.1900)	grad_norm 2.4215 (2.4215/0.0000)	mem 24308MB
[2025-01-19 00:46:17 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][10/312]	eta 0:03:49 lr 0.000941	time 0.7372 (0.7611)	model_time 0.7370 (0.6041)	loss 2.1775 (3.0050)	grad_norm 2.2777 (2.2099/0.6867)	mem 24308MB
[2025-01-19 00:46:23 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][20/312]	eta 0:03:19 lr 0.000941	time 0.5712 (0.6838)	model_time 0.5708 (0.6014)	loss 3.2094 (3.0596)	grad_norm 1.5614 (2.1190/0.7638)	mem 24308MB
[2025-01-19 00:46:29 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][30/312]	eta 0:03:05 lr 0.000940	time 0.6006 (0.6562)	model_time 0.6004 (0.6002)	loss 3.1335 (3.0970)	grad_norm 3.7097 (2.1718/0.7705)	mem 24308MB
[2025-01-19 00:46:35 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][40/312]	eta 0:02:55 lr 0.000939	time 0.5780 (0.6456)	model_time 0.5778 (0.6033)	loss 2.5339 (3.0858)	grad_norm 1.5880 (2.0578/0.7426)	mem 24308MB
[2025-01-19 00:46:41 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][50/312]	eta 0:02:48 lr 0.000939	time 0.6344 (0.6413)	model_time 0.6339 (0.6072)	loss 1.6888 (3.1129)	grad_norm 2.2288 (2.0547/0.7253)	mem 24308MB
[2025-01-19 00:46:47 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][60/312]	eta 0:02:40 lr 0.000938	time 0.5729 (0.6362)	model_time 0.5725 (0.6076)	loss 2.7930 (3.1092)	grad_norm 3.1244 (2.0689/0.7456)	mem 24308MB
[2025-01-19 00:46:53 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][70/312]	eta 0:02:33 lr 0.000938	time 0.5842 (0.6325)	model_time 0.5840 (0.6079)	loss 3.2478 (3.0986)	grad_norm 3.2594 (2.2760/1.1254)	mem 24308MB
[2025-01-19 00:47:00 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][80/312]	eta 0:02:26 lr 0.000937	time 0.5724 (0.6318)	model_time 0.5722 (0.6102)	loss 3.7107 (3.0685)	grad_norm 1.2445 (2.3476/1.1691)	mem 24308MB
[2025-01-19 00:47:06 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][90/312]	eta 0:02:19 lr 0.000937	time 0.5712 (0.6292)	model_time 0.5711 (0.6100)	loss 2.6290 (3.0690)	grad_norm 2.1836 (2.3966/1.1761)	mem 24308MB
[2025-01-19 00:47:12 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][100/312]	eta 0:02:12 lr 0.000936	time 0.5863 (0.6259)	model_time 0.5858 (0.6085)	loss 2.8825 (3.0625)	grad_norm 1.3669 (2.4350/1.1988)	mem 24308MB
[2025-01-19 00:47:18 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][110/312]	eta 0:02:06 lr 0.000935	time 0.5817 (0.6247)	model_time 0.5812 (0.6088)	loss 3.0206 (3.0662)	grad_norm 1.3072 (2.3815/1.1819)	mem 24308MB
[2025-01-19 00:47:24 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][120/312]	eta 0:01:59 lr 0.000935	time 0.6122 (0.6232)	model_time 0.6121 (0.6086)	loss 2.5196 (3.0583)	grad_norm 2.7698 (2.3543/1.1508)	mem 24308MB
[2025-01-19 00:47:30 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][130/312]	eta 0:01:53 lr 0.000934	time 0.6829 (0.6213)	model_time 0.6827 (0.6078)	loss 3.1924 (3.0570)	grad_norm 1.1084 (2.3197/1.1183)	mem 24308MB
[2025-01-19 00:47:36 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][140/312]	eta 0:01:46 lr 0.000934	time 0.5734 (0.6189)	model_time 0.5730 (0.6063)	loss 3.5290 (3.0604)	grad_norm 2.4364 (2.3454/1.1010)	mem 24308MB
[2025-01-19 00:47:42 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][150/312]	eta 0:01:40 lr 0.000933	time 0.5788 (0.6174)	model_time 0.5786 (0.6056)	loss 2.0735 (3.0639)	grad_norm 1.8108 (2.2925/1.0883)	mem 24308MB
[2025-01-19 00:47:48 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][160/312]	eta 0:01:33 lr 0.000933	time 0.5967 (0.6170)	model_time 0.5965 (0.6059)	loss 2.8174 (3.0425)	grad_norm 1.7892 (2.2454/1.0726)	mem 24308MB
[2025-01-19 00:47:54 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][170/312]	eta 0:01:27 lr 0.000932	time 0.6730 (0.6177)	model_time 0.6725 (0.6072)	loss 3.3724 (3.0352)	grad_norm 2.7097 (2.2311/1.0545)	mem 24308MB
[2025-01-19 00:48:00 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][180/312]	eta 0:01:21 lr 0.000932	time 0.5952 (0.6174)	model_time 0.5951 (0.6075)	loss 2.7417 (3.0338)	grad_norm 0.9792 (2.2015/1.0372)	mem 24308MB
[2025-01-19 00:48:06 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][190/312]	eta 0:01:15 lr 0.000931	time 0.5851 (0.6171)	model_time 0.5846 (0.6076)	loss 3.3147 (3.0421)	grad_norm 1.4237 (2.1908/1.0303)	mem 24308MB
[2025-01-19 00:48:12 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][200/312]	eta 0:01:09 lr 0.000930	time 0.5870 (0.6173)	model_time 0.5866 (0.6083)	loss 2.7119 (3.0314)	grad_norm 3.0463 (2.2051/1.0239)	mem 24308MB
[2025-01-19 00:48:18 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][210/312]	eta 0:01:02 lr 0.000930	time 0.5829 (0.6165)	model_time 0.5827 (0.6079)	loss 3.7155 (3.0332)	grad_norm 3.4367 (2.2297/1.0325)	mem 24308MB
[2025-01-19 00:48:24 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][220/312]	eta 0:00:56 lr 0.000929	time 0.6197 (0.6160)	model_time 0.6193 (0.6077)	loss 3.7997 (3.0431)	grad_norm 1.2672 (2.2786/1.0985)	mem 24308MB
[2025-01-19 00:48:31 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][230/312]	eta 0:00:50 lr 0.000929	time 0.5755 (0.6155)	model_time 0.5753 (0.6076)	loss 2.6389 (3.0363)	grad_norm 2.7435 (2.3040/1.1077)	mem 24308MB
[2025-01-19 00:48:37 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][240/312]	eta 0:00:44 lr 0.000928	time 0.6988 (0.6149)	model_time 0.6986 (0.6073)	loss 1.9682 (3.0340)	grad_norm 3.3465 (2.2989/1.0963)	mem 24308MB
[2025-01-19 00:48:42 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][250/312]	eta 0:00:38 lr 0.000928	time 0.5782 (0.6137)	model_time 0.5777 (0.6064)	loss 2.5083 (3.0363)	grad_norm 3.2614 (2.3284/1.1073)	mem 24308MB
[2025-01-19 00:48:48 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][260/312]	eta 0:00:31 lr 0.000927	time 0.5863 (0.6132)	model_time 0.5859 (0.6061)	loss 2.7339 (3.0393)	grad_norm 1.8401 (2.3329/1.0990)	mem 24308MB
[2025-01-19 00:48:54 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][270/312]	eta 0:00:25 lr 0.000927	time 0.5950 (0.6128)	model_time 0.5948 (0.6060)	loss 3.2957 (3.0412)	grad_norm 1.8167 (2.3149/1.0892)	mem 24308MB
[2025-01-19 00:49:00 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][280/312]	eta 0:00:19 lr 0.000926	time 0.5860 (0.6123)	model_time 0.5858 (0.6057)	loss 2.9286 (3.0384)	grad_norm 2.1800 (2.3400/1.0870)	mem 24308MB
[2025-01-19 00:49:07 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][290/312]	eta 0:00:13 lr 0.000926	time 0.5989 (0.6128)	model_time 0.5984 (0.6065)	loss 3.2429 (3.0433)	grad_norm 1.5788 (2.3424/1.0829)	mem 24308MB
[2025-01-19 00:49:13 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][300/312]	eta 0:00:07 lr 0.000925	time 0.5638 (0.6133)	model_time 0.5637 (0.6072)	loss 3.4206 (3.0404)	grad_norm 1.2923 (2.3437/1.0745)	mem 24308MB
[2025-01-19 00:49:19 internimage_s_1k_224] (main.py 510): INFO Train: [205/300][310/312]	eta 0:00:01 lr 0.000924	time 0.6512 (0.6130)	model_time 0.6511 (0.6070)	loss 3.3773 (3.0364)	grad_norm 2.0397 (2.3397/1.0789)	mem 24308MB
[2025-01-19 00:49:20 internimage_s_1k_224] (main.py 519): INFO EPOCH 205 training takes 0:03:11
[2025-01-19 00:49:20 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_205.pth saving......
[2025-01-19 00:49:21 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_205.pth saved !!!
[2025-01-19 00:49:29 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.619 (7.619)	Loss 0.7896 (0.7896)	Acc@1 84.204 (84.204)	Acc@5 97.339 (97.339)	Mem 24308MB
[2025-01-19 00:49:33 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.005)	Loss 1.0049 (0.8762)	Acc@1 77.563 (81.965)	Acc@5 95.215 (96.089)	Mem 24308MB
[2025-01-19 00:49:33 internimage_s_1k_224] (main.py 575): INFO [Epoch:205] * Acc@1 81.790 Acc@5 96.073
[2025-01-19 00:49:33 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.8%
[2025-01-19 00:49:33 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 00:49:35 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 00:49:35 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.79%
[2025-01-19 00:49:42 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.515 (7.515)	Loss 0.7058 (0.7058)	Acc@1 84.863 (84.863)	Acc@5 97.705 (97.705)	Mem 24308MB
[2025-01-19 00:49:46 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.006)	Loss 0.9427 (0.8028)	Acc@1 77.856 (82.231)	Acc@5 94.971 (96.225)	Mem 24308MB
[2025-01-19 00:49:46 internimage_s_1k_224] (main.py 575): INFO [Epoch:205] * Acc@1 82.096 Acc@5 96.251
[2025-01-19 00:49:46 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.1%
[2025-01-19 00:49:46 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:49:48 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:49:48 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.10%
[2025-01-19 00:49:51 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][0/312]	eta 0:13:10 lr 0.000924	time 2.5344 (2.5344)	model_time 0.6125 (0.6125)	loss 2.8145 (2.8145)	grad_norm 2.7505 (2.7505/0.0000)	mem 24308MB
[2025-01-19 00:49:57 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][10/312]	eta 0:04:02 lr 0.000924	time 0.6468 (0.8025)	model_time 0.6466 (0.6275)	loss 2.3040 (2.9432)	grad_norm 3.0715 (2.7405/0.6858)	mem 24308MB
[2025-01-19 00:50:03 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][20/312]	eta 0:03:27 lr 0.000923	time 0.5759 (0.7091)	model_time 0.5755 (0.6172)	loss 3.3710 (3.0579)	grad_norm 1.4277 (2.5021/0.8355)	mem 24308MB
[2025-01-19 00:50:09 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][30/312]	eta 0:03:10 lr 0.000923	time 0.5887 (0.6744)	model_time 0.5886 (0.6121)	loss 2.6205 (3.1191)	grad_norm 2.0489 (2.2585/0.8046)	mem 24308MB
[2025-01-19 00:50:15 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][40/312]	eta 0:02:59 lr 0.000922	time 0.5892 (0.6610)	model_time 0.5890 (0.6138)	loss 3.7315 (3.1340)	grad_norm 1.7670 (2.1234/0.7799)	mem 24308MB
[2025-01-19 00:50:21 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][50/312]	eta 0:02:50 lr 0.000922	time 0.6218 (0.6496)	model_time 0.6217 (0.6116)	loss 2.5159 (3.0924)	grad_norm 2.0691 (2.0331/0.7392)	mem 24308MB
[2025-01-19 00:50:27 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][60/312]	eta 0:02:41 lr 0.000921	time 0.5936 (0.6394)	model_time 0.5931 (0.6076)	loss 3.3455 (3.1121)	grad_norm 3.7383 (2.0742/0.7586)	mem 24308MB
[2025-01-19 00:50:33 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][70/312]	eta 0:02:33 lr 0.000920	time 0.5733 (0.6340)	model_time 0.5729 (0.6066)	loss 2.8104 (3.1007)	grad_norm 1.1141 (2.0886/0.7831)	mem 24308MB
[2025-01-19 00:50:39 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][80/312]	eta 0:02:26 lr 0.000920	time 0.5727 (0.6301)	model_time 0.5725 (0.6061)	loss 2.7883 (3.0943)	grad_norm 1.5939 (2.0533/0.7743)	mem 24308MB
[2025-01-19 00:50:45 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][90/312]	eta 0:02:19 lr 0.000919	time 0.5979 (0.6282)	model_time 0.5977 (0.6068)	loss 2.1773 (3.0803)	grad_norm 2.3192 (2.0139/0.7640)	mem 24308MB
[2025-01-19 00:50:52 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][100/312]	eta 0:02:13 lr 0.000919	time 0.5888 (0.6283)	model_time 0.5883 (0.6089)	loss 3.1592 (3.0817)	grad_norm 2.2179 (2.0579/0.7997)	mem 24308MB
[2025-01-19 00:50:58 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][110/312]	eta 0:02:07 lr 0.000918	time 0.5821 (0.6288)	model_time 0.5816 (0.6111)	loss 3.6932 (3.0870)	grad_norm 2.7432 (2.2065/0.9788)	mem 24308MB
[2025-01-19 00:51:04 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][120/312]	eta 0:02:00 lr 0.000918	time 0.5935 (0.6274)	model_time 0.5931 (0.6112)	loss 2.7898 (3.0731)	grad_norm 2.9419 (2.1897/0.9561)	mem 24308MB
[2025-01-19 00:51:11 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][130/312]	eta 0:01:54 lr 0.000917	time 0.6777 (0.6284)	model_time 0.6776 (0.6134)	loss 3.1688 (3.0704)	grad_norm 1.8164 (2.2129/0.9515)	mem 24308MB
[2025-01-19 00:51:17 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][140/312]	eta 0:01:47 lr 0.000917	time 0.6089 (0.6265)	model_time 0.6087 (0.6126)	loss 3.3421 (3.0786)	grad_norm 1.5257 (2.1885/0.9429)	mem 24308MB
[2025-01-19 00:51:23 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][150/312]	eta 0:01:41 lr 0.000916	time 0.6038 (0.6252)	model_time 0.6036 (0.6122)	loss 3.3605 (3.0856)	grad_norm 3.3202 (2.1994/0.9344)	mem 24308MB
[2025-01-19 00:51:29 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][160/312]	eta 0:01:34 lr 0.000915	time 0.6698 (0.6240)	model_time 0.6696 (0.6118)	loss 3.5177 (3.0682)	grad_norm 2.3010 (2.1933/0.9315)	mem 24308MB
[2025-01-19 00:51:35 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][170/312]	eta 0:01:28 lr 0.000915	time 0.5917 (0.6229)	model_time 0.5915 (0.6113)	loss 3.0489 (3.0617)	grad_norm 1.9331 (2.1936/0.9144)	mem 24308MB
[2025-01-19 00:51:41 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][180/312]	eta 0:01:21 lr 0.000914	time 0.5741 (0.6209)	model_time 0.5736 (0.6099)	loss 3.2169 (3.0629)	grad_norm 2.3829 (2.1910/0.9044)	mem 24308MB
[2025-01-19 00:51:47 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][190/312]	eta 0:01:15 lr 0.000914	time 0.5846 (0.6198)	model_time 0.5845 (0.6094)	loss 2.9671 (3.0661)	grad_norm 3.5509 (2.1981/0.9218)	mem 24308MB
[2025-01-19 00:51:53 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][200/312]	eta 0:01:09 lr 0.000913	time 0.5892 (0.6185)	model_time 0.5888 (0.6086)	loss 2.9374 (3.0755)	grad_norm 1.6245 (2.2075/0.9221)	mem 24308MB
[2025-01-19 00:51:59 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][210/312]	eta 0:01:03 lr 0.000913	time 0.5783 (0.6179)	model_time 0.5781 (0.6084)	loss 3.5442 (3.0799)	grad_norm 2.8442 (2.1923/0.9116)	mem 24308MB
[2025-01-19 00:52:05 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][220/312]	eta 0:00:56 lr 0.000912	time 0.5905 (0.6184)	model_time 0.5900 (0.6094)	loss 3.2020 (3.0790)	grad_norm 2.0390 (2.1901/0.9002)	mem 24308MB
[2025-01-19 00:52:11 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][230/312]	eta 0:00:50 lr 0.000912	time 0.5876 (0.6188)	model_time 0.5872 (0.6102)	loss 3.3447 (3.0755)	grad_norm 3.4829 (2.2337/0.9261)	mem 24308MB
[2025-01-19 00:52:17 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][240/312]	eta 0:00:44 lr 0.000911	time 0.6990 (0.6185)	model_time 0.6989 (0.6101)	loss 2.4164 (3.0674)	grad_norm 3.3555 (2.2538/0.9457)	mem 24308MB
[2025-01-19 00:52:24 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][250/312]	eta 0:00:38 lr 0.000910	time 0.5934 (0.6186)	model_time 0.5932 (0.6106)	loss 3.0278 (3.0704)	grad_norm 1.2014 (2.2616/0.9710)	mem 24308MB
[2025-01-19 00:52:30 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][260/312]	eta 0:00:32 lr 0.000910	time 0.5904 (0.6185)	model_time 0.5900 (0.6108)	loss 1.9535 (3.0555)	grad_norm 1.0953 (2.2392/0.9614)	mem 24308MB
[2025-01-19 00:52:36 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][270/312]	eta 0:00:25 lr 0.000909	time 0.5849 (0.6179)	model_time 0.5845 (0.6105)	loss 3.3146 (3.0583)	grad_norm 2.9642 (2.2327/0.9507)	mem 24308MB
[2025-01-19 00:52:42 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][280/312]	eta 0:00:19 lr 0.000909	time 0.6927 (0.6176)	model_time 0.6925 (0.6104)	loss 2.8571 (3.0541)	grad_norm 5.8157 (2.2406/0.9751)	mem 24308MB
[2025-01-19 00:52:48 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][290/312]	eta 0:00:13 lr 0.000908	time 0.5878 (0.6168)	model_time 0.5876 (0.6098)	loss 3.2641 (3.0536)	grad_norm 2.2165 (2.2744/0.9918)	mem 24308MB
[2025-01-19 00:52:54 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][300/312]	eta 0:00:07 lr 0.000908	time 0.5697 (0.6161)	model_time 0.5696 (0.6093)	loss 3.6055 (3.0505)	grad_norm 2.4520 (2.2997/1.0077)	mem 24308MB
[2025-01-19 00:53:00 internimage_s_1k_224] (main.py 510): INFO Train: [206/300][310/312]	eta 0:00:01 lr 0.000907	time 0.5685 (0.6151)	model_time 0.5684 (0.6086)	loss 2.8604 (3.0568)	grad_norm 1.6926 (2.2577/1.0106)	mem 24308MB
[2025-01-19 00:53:00 internimage_s_1k_224] (main.py 519): INFO EPOCH 206 training takes 0:03:11
[2025-01-19 00:53:00 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_206.pth saving......
[2025-01-19 00:53:02 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_206.pth saved !!!
[2025-01-19 00:53:10 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.838 (7.838)	Loss 0.7767 (0.7767)	Acc@1 84.302 (84.302)	Acc@5 97.168 (97.168)	Mem 24308MB
[2025-01-19 00:53:13 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.042)	Loss 0.9910 (0.8758)	Acc@1 78.052 (81.889)	Acc@5 94.946 (96.045)	Mem 24308MB
[2025-01-19 00:53:14 internimage_s_1k_224] (main.py 575): INFO [Epoch:206] * Acc@1 81.754 Acc@5 96.037
[2025-01-19 00:53:14 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.8%
[2025-01-19 00:53:14 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.79%
[2025-01-19 00:53:22 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.818 (8.818)	Loss 0.7059 (0.7059)	Acc@1 84.888 (84.888)	Acc@5 97.705 (97.705)	Mem 24308MB
[2025-01-19 00:53:27 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.199)	Loss 0.9415 (0.8023)	Acc@1 77.905 (82.262)	Acc@5 95.044 (96.247)	Mem 24308MB
[2025-01-19 00:53:27 internimage_s_1k_224] (main.py 575): INFO [Epoch:206] * Acc@1 82.130 Acc@5 96.271
[2025-01-19 00:53:27 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.1%
[2025-01-19 00:53:27 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:53:30 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:53:30 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.13%
[2025-01-19 00:53:32 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][0/312]	eta 0:14:37 lr 0.000907	time 2.8117 (2.8117)	model_time 0.5899 (0.5899)	loss 2.6925 (2.6925)	grad_norm 1.2195 (1.2195/0.0000)	mem 24308MB
[2025-01-19 00:53:38 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][10/312]	eta 0:04:03 lr 0.000907	time 0.6069 (0.8050)	model_time 0.6068 (0.6027)	loss 3.1129 (2.8914)	grad_norm 2.7349 (1.8375/1.1094)	mem 24308MB
[2025-01-19 00:53:44 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][20/312]	eta 0:03:25 lr 0.000906	time 0.5806 (0.7049)	model_time 0.5801 (0.5988)	loss 3.4504 (3.1020)	grad_norm 4.1443 (2.2612/1.4057)	mem 24308MB
[2025-01-19 00:53:51 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][30/312]	eta 0:03:13 lr 0.000905	time 0.5783 (0.6858)	model_time 0.5782 (0.6138)	loss 3.6840 (3.1932)	grad_norm 2.5485 (2.2851/1.2496)	mem 24308MB
[2025-01-19 00:53:57 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][40/312]	eta 0:03:03 lr 0.000905	time 0.6203 (0.6749)	model_time 0.6201 (0.6204)	loss 2.9687 (3.1224)	grad_norm 2.6857 (2.2466/1.1687)	mem 24308MB
[2025-01-19 00:54:03 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][50/312]	eta 0:02:52 lr 0.000904	time 0.5869 (0.6592)	model_time 0.5865 (0.6153)	loss 3.5424 (3.0845)	grad_norm 1.4300 (2.2394/1.1431)	mem 24308MB
[2025-01-19 00:54:09 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][60/312]	eta 0:02:44 lr 0.000904	time 0.6999 (0.6536)	model_time 0.6996 (0.6168)	loss 2.8614 (3.0702)	grad_norm 1.4803 (2.1239/1.0892)	mem 24308MB
[2025-01-19 00:54:16 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][70/312]	eta 0:02:36 lr 0.000903	time 0.6856 (0.6465)	model_time 0.6854 (0.6148)	loss 2.3347 (3.0543)	grad_norm 1.4561 (2.0806/1.0327)	mem 24308MB
[2025-01-19 00:54:22 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][80/312]	eta 0:02:28 lr 0.000903	time 0.5813 (0.6415)	model_time 0.5811 (0.6137)	loss 2.0287 (3.0055)	grad_norm 2.6319 (2.0818/0.9862)	mem 24308MB
[2025-01-19 00:54:28 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][90/312]	eta 0:02:21 lr 0.000902	time 0.5992 (0.6375)	model_time 0.5990 (0.6128)	loss 3.4579 (3.0208)	grad_norm 1.8308 (2.0759/0.9808)	mem 24308MB
[2025-01-19 00:54:34 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][100/312]	eta 0:02:14 lr 0.000902	time 0.5819 (0.6341)	model_time 0.5817 (0.6118)	loss 3.3253 (3.0279)	grad_norm 2.3734 (2.0841/0.9388)	mem 24308MB
[2025-01-19 00:54:40 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][110/312]	eta 0:02:07 lr 0.000901	time 0.5754 (0.6301)	model_time 0.5752 (0.6098)	loss 2.0788 (3.0163)	grad_norm 2.9351 (2.0601/0.9193)	mem 24308MB
[2025-01-19 00:54:46 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][120/312]	eta 0:02:00 lr 0.000900	time 0.5891 (0.6283)	model_time 0.5887 (0.6096)	loss 3.2630 (3.0275)	grad_norm 1.0261 (2.0818/0.9410)	mem 24308MB
[2025-01-19 00:54:52 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][130/312]	eta 0:01:54 lr 0.000900	time 0.5838 (0.6264)	model_time 0.5836 (0.6091)	loss 3.3761 (3.0344)	grad_norm 3.8296 (2.1966/1.0147)	mem 24308MB
[2025-01-19 00:54:58 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][140/312]	eta 0:01:47 lr 0.000899	time 0.5860 (0.6252)	model_time 0.5855 (0.6091)	loss 3.1818 (3.0289)	grad_norm 1.5359 (2.2350/1.0656)	mem 24308MB
[2025-01-19 00:55:04 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][150/312]	eta 0:01:41 lr 0.000899	time 0.6674 (0.6252)	model_time 0.6672 (0.6102)	loss 3.0874 (3.0277)	grad_norm 1.6941 (2.2372/1.0579)	mem 24308MB
[2025-01-19 00:55:10 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][160/312]	eta 0:01:35 lr 0.000898	time 0.5986 (0.6250)	model_time 0.5985 (0.6109)	loss 3.5935 (3.0476)	grad_norm 1.6680 (2.2403/1.0457)	mem 24308MB
[2025-01-19 00:55:16 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][170/312]	eta 0:01:28 lr 0.000898	time 0.6641 (0.6236)	model_time 0.6639 (0.6103)	loss 2.1836 (3.0455)	grad_norm 1.8365 (2.2411/1.0328)	mem 24308MB
[2025-01-19 00:55:22 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][180/312]	eta 0:01:22 lr 0.000897	time 0.6571 (0.6226)	model_time 0.6567 (0.6099)	loss 2.2976 (3.0387)	grad_norm 1.2357 (2.2008/1.0203)	mem 24308MB
[2025-01-19 00:55:28 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][190/312]	eta 0:01:15 lr 0.000897	time 0.5870 (0.6216)	model_time 0.5865 (0.6096)	loss 2.5362 (3.0340)	grad_norm 2.3945 (2.1751/1.0050)	mem 24308MB
[2025-01-19 00:55:35 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][200/312]	eta 0:01:09 lr 0.000896	time 0.5731 (0.6214)	model_time 0.5730 (0.6099)	loss 3.2768 (3.0365)	grad_norm 3.5286 (2.2025/1.0059)	mem 24308MB
[2025-01-19 00:55:41 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][210/312]	eta 0:01:03 lr 0.000896	time 0.5766 (0.6205)	model_time 0.5761 (0.6096)	loss 3.8106 (3.0411)	grad_norm 3.1983 (2.2072/1.0059)	mem 24308MB
[2025-01-19 00:55:47 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][220/312]	eta 0:00:56 lr 0.000895	time 0.5807 (0.6194)	model_time 0.5805 (0.6090)	loss 2.6523 (3.0282)	grad_norm 2.0797 (2.2091/1.0085)	mem 24308MB
[2025-01-19 00:55:53 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][230/312]	eta 0:00:50 lr 0.000894	time 0.6148 (0.6188)	model_time 0.6146 (0.6088)	loss 3.2169 (3.0243)	grad_norm 3.1361 (2.2408/1.0073)	mem 24308MB
[2025-01-19 00:55:59 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][240/312]	eta 0:00:44 lr 0.000894	time 0.5860 (0.6183)	model_time 0.5858 (0.6088)	loss 3.4415 (3.0220)	grad_norm 1.7883 (2.2390/1.0039)	mem 24308MB
[2025-01-19 00:56:05 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][250/312]	eta 0:00:38 lr 0.000893	time 0.5859 (0.6176)	model_time 0.5858 (0.6084)	loss 3.2554 (3.0182)	grad_norm 2.6689 (2.2155/0.9937)	mem 24308MB
[2025-01-19 00:56:11 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][260/312]	eta 0:00:32 lr 0.000893	time 0.5881 (0.6170)	model_time 0.5877 (0.6081)	loss 3.6868 (3.0199)	grad_norm 1.1960 (2.2321/1.0441)	mem 24308MB
[2025-01-19 00:56:17 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][270/312]	eta 0:00:25 lr 0.000892	time 0.5782 (0.6167)	model_time 0.5780 (0.6082)	loss 2.7279 (3.0199)	grad_norm 2.2103 (2.2375/1.0383)	mem 24308MB
[2025-01-19 00:56:23 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][280/312]	eta 0:00:19 lr 0.000892	time 0.6539 (0.6179)	model_time 0.6537 (0.6096)	loss 3.4827 (3.0306)	grad_norm 2.4792 (2.2373/1.0248)	mem 24308MB
[2025-01-19 00:56:29 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][290/312]	eta 0:00:13 lr 0.000891	time 0.5847 (0.6173)	model_time 0.5845 (0.6093)	loss 3.5819 (3.0356)	grad_norm 1.4515 (2.2244/1.0197)	mem 24308MB
[2025-01-19 00:56:35 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][300/312]	eta 0:00:07 lr 0.000891	time 0.5753 (0.6167)	model_time 0.5752 (0.6089)	loss 3.2953 (3.0344)	grad_norm 1.3292 (2.2025/1.0130)	mem 24308MB
[2025-01-19 00:56:41 internimage_s_1k_224] (main.py 510): INFO Train: [207/300][310/312]	eta 0:00:01 lr 0.000890	time 0.5711 (0.6156)	model_time 0.5710 (0.6081)	loss 3.5771 (3.0384)	grad_norm 2.2374 (2.1960/0.9994)	mem 24308MB
[2025-01-19 00:56:42 internimage_s_1k_224] (main.py 519): INFO EPOCH 207 training takes 0:03:12
[2025-01-19 00:56:42 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_207.pth saving......
[2025-01-19 00:56:43 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_207.pth saved !!!
[2025-01-19 00:56:52 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.411 (8.411)	Loss 0.7538 (0.7538)	Acc@1 84.351 (84.351)	Acc@5 96.997 (96.997)	Mem 24308MB
[2025-01-19 00:56:56 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.125)	Loss 0.9999 (0.8634)	Acc@1 77.759 (81.878)	Acc@5 94.751 (95.954)	Mem 24308MB
[2025-01-19 00:56:56 internimage_s_1k_224] (main.py 575): INFO [Epoch:207] * Acc@1 81.724 Acc@5 95.965
[2025-01-19 00:56:56 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.7%
[2025-01-19 00:56:56 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.79%
[2025-01-19 00:57:05 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.254 (9.254)	Loss 0.7060 (0.7060)	Acc@1 84.888 (84.888)	Acc@5 97.729 (97.729)	Mem 24308MB
[2025-01-19 00:57:10 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.259)	Loss 0.9403 (0.8018)	Acc@1 77.954 (82.264)	Acc@5 95.044 (96.276)	Mem 24308MB
[2025-01-19 00:57:10 internimage_s_1k_224] (main.py 575): INFO [Epoch:207] * Acc@1 82.136 Acc@5 96.299
[2025-01-19 00:57:10 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.1%
[2025-01-19 00:57:10 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 00:57:13 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 00:57:13 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.14%
[2025-01-19 00:57:15 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][0/312]	eta 0:12:58 lr 0.000890	time 2.4968 (2.4968)	model_time 0.5922 (0.5922)	loss 2.9084 (2.9084)	grad_norm 1.9487 (1.9487/0.0000)	mem 24308MB
[2025-01-19 00:57:21 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][10/312]	eta 0:03:58 lr 0.000889	time 0.6525 (0.7900)	model_time 0.6524 (0.6166)	loss 2.7600 (3.1160)	grad_norm 2.2749 (3.5568/1.4590)	mem 24308MB
[2025-01-19 00:57:27 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][20/312]	eta 0:03:24 lr 0.000889	time 0.6083 (0.7004)	model_time 0.6082 (0.6094)	loss 3.3675 (3.0628)	grad_norm 1.7074 (3.1612/1.3116)	mem 24308MB
[2025-01-19 00:57:34 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][30/312]	eta 0:03:09 lr 0.000888	time 0.5839 (0.6735)	model_time 0.5837 (0.6117)	loss 2.4864 (3.0728)	grad_norm 1.9029 (2.7559/1.2661)	mem 24308MB
[2025-01-19 00:57:39 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][40/312]	eta 0:02:57 lr 0.000888	time 0.5873 (0.6537)	model_time 0.5869 (0.6069)	loss 2.9062 (3.1103)	grad_norm 1.0195 (2.5657/1.1983)	mem 24308MB
[2025-01-19 00:57:46 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][50/312]	eta 0:02:48 lr 0.000887	time 0.5769 (0.6442)	model_time 0.5764 (0.6065)	loss 3.5967 (3.0687)	grad_norm 3.8816 (2.5028/1.1822)	mem 24308MB
[2025-01-19 00:57:52 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][60/312]	eta 0:02:40 lr 0.000887	time 0.5823 (0.6379)	model_time 0.5819 (0.6063)	loss 2.6345 (3.0875)	grad_norm 2.1143 (2.4769/1.1116)	mem 24308MB
[2025-01-19 00:57:58 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][70/312]	eta 0:02:33 lr 0.000886	time 0.5987 (0.6342)	model_time 0.5985 (0.6070)	loss 3.1035 (3.0604)	grad_norm 1.9275 (2.4269/1.0411)	mem 24308MB
[2025-01-19 00:58:04 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][80/312]	eta 0:02:26 lr 0.000886	time 0.5902 (0.6302)	model_time 0.5898 (0.6063)	loss 3.4517 (3.0713)	grad_norm 3.9399 (2.4847/1.0966)	mem 24308MB
[2025-01-19 00:58:10 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][90/312]	eta 0:02:20 lr 0.000885	time 0.6562 (0.6330)	model_time 0.6561 (0.6117)	loss 3.7381 (3.0763)	grad_norm 2.2290 (2.4493/1.0668)	mem 24308MB
[2025-01-19 00:58:16 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][100/312]	eta 0:02:13 lr 0.000885	time 0.7085 (0.6300)	model_time 0.7084 (0.6108)	loss 3.4714 (3.0798)	grad_norm 3.8913 (2.4863/1.0734)	mem 24308MB
[2025-01-19 00:58:22 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][110/312]	eta 0:02:07 lr 0.000884	time 0.5773 (0.6287)	model_time 0.5769 (0.6112)	loss 3.5852 (3.0704)	grad_norm 2.4203 (2.5142/1.0717)	mem 24308MB
[2025-01-19 00:58:29 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][120/312]	eta 0:02:00 lr 0.000883	time 0.5908 (0.6269)	model_time 0.5907 (0.6108)	loss 3.2279 (3.0466)	grad_norm 1.6506 (2.4957/1.0779)	mem 24308MB
[2025-01-19 00:58:35 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][130/312]	eta 0:01:53 lr 0.000883	time 0.6752 (0.6257)	model_time 0.6750 (0.6108)	loss 3.0966 (3.0591)	grad_norm 1.5220 (2.4213/1.0735)	mem 24308MB
[2025-01-19 00:58:41 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][140/312]	eta 0:01:47 lr 0.000882	time 0.5915 (0.6238)	model_time 0.5913 (0.6100)	loss 1.9676 (3.0412)	grad_norm 1.4525 (2.3986/1.0627)	mem 24308MB
[2025-01-19 00:58:47 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][150/312]	eta 0:01:40 lr 0.000882	time 0.5833 (0.6225)	model_time 0.5828 (0.6095)	loss 3.8287 (3.0442)	grad_norm 1.3910 (2.3831/1.0610)	mem 24308MB
[2025-01-19 00:58:53 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][160/312]	eta 0:01:34 lr 0.000881	time 0.5831 (0.6210)	model_time 0.5826 (0.6088)	loss 2.7471 (3.0413)	grad_norm 1.4195 (2.3495/1.0462)	mem 24308MB
[2025-01-19 00:58:59 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][170/312]	eta 0:01:27 lr 0.000881	time 0.5744 (0.6190)	model_time 0.5743 (0.6075)	loss 3.7401 (3.0521)	grad_norm 0.8913 (2.3098/1.0346)	mem 24308MB
[2025-01-19 00:59:05 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][180/312]	eta 0:01:21 lr 0.000880	time 0.6961 (0.6184)	model_time 0.6960 (0.6075)	loss 3.1564 (3.0418)	grad_norm 2.3647 (2.3187/1.0213)	mem 24308MB
[2025-01-19 00:59:11 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][190/312]	eta 0:01:15 lr 0.000880	time 0.5911 (0.6178)	model_time 0.5909 (0.6074)	loss 3.5579 (3.0504)	grad_norm 1.9381 (2.2859/1.0103)	mem 24308MB
[2025-01-19 00:59:17 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][200/312]	eta 0:01:09 lr 0.000879	time 0.5746 (0.6174)	model_time 0.5741 (0.6075)	loss 2.5890 (3.0474)	grad_norm 1.5613 (2.2840/1.0003)	mem 24308MB
[2025-01-19 00:59:23 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][210/312]	eta 0:01:03 lr 0.000879	time 0.6500 (0.6183)	model_time 0.6498 (0.6089)	loss 3.3326 (3.0523)	grad_norm 4.5758 (2.2974/1.0040)	mem 24308MB
[2025-01-19 00:59:29 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][220/312]	eta 0:00:56 lr 0.000878	time 0.7055 (0.6179)	model_time 0.7054 (0.6089)	loss 3.1852 (3.0587)	grad_norm 2.7667 (2.3159/1.0417)	mem 24308MB
[2025-01-19 00:59:35 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][230/312]	eta 0:00:50 lr 0.000877	time 0.5952 (0.6181)	model_time 0.5948 (0.6094)	loss 2.2195 (3.0501)	grad_norm 1.9250 (2.3277/1.0355)	mem 24308MB
[2025-01-19 00:59:42 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][240/312]	eta 0:00:44 lr 0.000877	time 0.6034 (0.6175)	model_time 0.6032 (0.6092)	loss 3.2420 (3.0446)	grad_norm 3.0147 (2.3160/1.0219)	mem 24308MB
[2025-01-19 00:59:48 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][250/312]	eta 0:00:38 lr 0.000876	time 0.6620 (0.6175)	model_time 0.6618 (0.6095)	loss 3.3272 (3.0412)	grad_norm 1.4041 (2.3164/1.0283)	mem 24308MB
[2025-01-19 00:59:54 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][260/312]	eta 0:00:32 lr 0.000876	time 0.5741 (0.6168)	model_time 0.5736 (0.6091)	loss 3.3667 (3.0454)	grad_norm 1.3732 (2.3249/1.0427)	mem 24308MB
[2025-01-19 01:00:00 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][270/312]	eta 0:00:25 lr 0.000875	time 0.5731 (0.6163)	model_time 0.5729 (0.6088)	loss 3.2894 (3.0460)	grad_norm 1.8734 (2.3255/1.0435)	mem 24308MB
[2025-01-19 01:00:06 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][280/312]	eta 0:00:19 lr 0.000875	time 0.5878 (0.6158)	model_time 0.5876 (0.6086)	loss 3.3559 (3.0519)	grad_norm 2.4839 (2.3077/1.0328)	mem 24308MB
[2025-01-19 01:00:12 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][290/312]	eta 0:00:13 lr 0.000874	time 0.5741 (0.6150)	model_time 0.5737 (0.6080)	loss 3.2868 (3.0610)	grad_norm 2.1284 (2.3024/1.0200)	mem 24308MB
[2025-01-19 01:00:18 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][300/312]	eta 0:00:07 lr 0.000874	time 0.5722 (0.6143)	model_time 0.5721 (0.6075)	loss 3.5266 (3.0646)	grad_norm 1.8142 (2.3057/1.0126)	mem 24308MB
[2025-01-19 01:00:24 internimage_s_1k_224] (main.py 510): INFO Train: [208/300][310/312]	eta 0:00:01 lr 0.000873	time 0.5709 (0.6138)	model_time 0.5708 (0.6073)	loss 3.1648 (3.0739)	grad_norm 2.0135 (2.2658/0.9612)	mem 24308MB
[2025-01-19 01:00:24 internimage_s_1k_224] (main.py 519): INFO EPOCH 208 training takes 0:03:11
[2025-01-19 01:00:24 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_208.pth saving......
[2025-01-19 01:00:26 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_208.pth saved !!!
[2025-01-19 01:00:35 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.534 (8.534)	Loss 0.7509 (0.7509)	Acc@1 84.692 (84.692)	Acc@5 97.217 (97.217)	Mem 24308MB
[2025-01-19 01:00:38 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.108)	Loss 0.9792 (0.8556)	Acc@1 77.979 (81.934)	Acc@5 95.459 (96.147)	Mem 24308MB
[2025-01-19 01:00:39 internimage_s_1k_224] (main.py 575): INFO [Epoch:208] * Acc@1 81.786 Acc@5 96.149
[2025-01-19 01:00:39 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 81.8%
[2025-01-19 01:00:39 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.79%
[2025-01-19 01:00:48 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.633 (9.633)	Loss 0.7061 (0.7061)	Acc@1 84.961 (84.961)	Acc@5 97.729 (97.729)	Mem 24308MB
[2025-01-19 01:00:53 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.288)	Loss 0.9392 (0.8013)	Acc@1 78.027 (82.291)	Acc@5 95.068 (96.289)	Mem 24308MB
[2025-01-19 01:00:53 internimage_s_1k_224] (main.py 575): INFO [Epoch:208] * Acc@1 82.158 Acc@5 96.309
[2025-01-19 01:00:53 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.2%
[2025-01-19 01:00:53 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:00:55 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:00:55 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.16%
[2025-01-19 01:00:57 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][0/312]	eta 0:11:30 lr 0.000873	time 2.2144 (2.2144)	model_time 0.5986 (0.5986)	loss 3.6474 (3.6474)	grad_norm 1.1895 (1.1895/0.0000)	mem 24308MB
[2025-01-19 01:01:04 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][10/312]	eta 0:03:49 lr 0.000872	time 0.6950 (0.7593)	model_time 0.6948 (0.6122)	loss 2.9403 (2.8696)	grad_norm 1.9326 (1.8199/0.4856)	mem 24308MB
[2025-01-19 01:01:10 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][20/312]	eta 0:03:26 lr 0.000872	time 0.6564 (0.7059)	model_time 0.6563 (0.6287)	loss 2.1197 (3.0393)	grad_norm 2.1337 (1.8001/0.5182)	mem 24308MB
[2025-01-19 01:01:16 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][30/312]	eta 0:03:09 lr 0.000871	time 0.6289 (0.6705)	model_time 0.6287 (0.6180)	loss 3.2760 (2.9870)	grad_norm 2.2788 (1.8831/0.5281)	mem 24308MB
[2025-01-19 01:01:22 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][40/312]	eta 0:03:00 lr 0.000871	time 0.6018 (0.6639)	model_time 0.6017 (0.6242)	loss 2.1036 (3.0138)	grad_norm 2.0073 (2.0283/0.7699)	mem 24308MB
[2025-01-19 01:01:29 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][50/312]	eta 0:02:51 lr 0.000870	time 0.5929 (0.6528)	model_time 0.5928 (0.6207)	loss 2.2858 (3.0403)	grad_norm 1.3706 (2.1590/0.8729)	mem 24308MB
[2025-01-19 01:01:35 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][60/312]	eta 0:02:42 lr 0.000870	time 0.5804 (0.6447)	model_time 0.5800 (0.6178)	loss 3.5114 (3.0765)	grad_norm 1.5738 (2.2574/1.0472)	mem 24308MB
[2025-01-19 01:01:41 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][70/312]	eta 0:02:34 lr 0.000869	time 0.6668 (0.6396)	model_time 0.6664 (0.6165)	loss 2.9586 (3.0812)	grad_norm 2.2623 (2.1717/1.0075)	mem 24308MB
[2025-01-19 01:01:47 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][80/312]	eta 0:02:27 lr 0.000869	time 0.5910 (0.6356)	model_time 0.5909 (0.6153)	loss 1.9710 (3.0633)	grad_norm 2.3093 (2.1694/0.9839)	mem 24308MB
[2025-01-19 01:01:53 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][90/312]	eta 0:02:20 lr 0.000868	time 0.5733 (0.6316)	model_time 0.5731 (0.6135)	loss 2.3742 (3.0569)	grad_norm 1.5726 (2.1418/0.9534)	mem 24308MB
[2025-01-19 01:01:59 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][100/312]	eta 0:02:12 lr 0.000868	time 0.5947 (0.6273)	model_time 0.5943 (0.6109)	loss 3.6621 (3.0320)	grad_norm 2.7636 (2.1258/0.9315)	mem 24308MB
[2025-01-19 01:02:05 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][110/312]	eta 0:02:06 lr 0.000867	time 0.5900 (0.6252)	model_time 0.5896 (0.6102)	loss 2.7836 (3.0369)	grad_norm 1.5248 (2.1541/0.9107)	mem 24308MB
[2025-01-19 01:02:11 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][120/312]	eta 0:01:59 lr 0.000867	time 0.5776 (0.6245)	model_time 0.5775 (0.6108)	loss 1.9350 (3.0211)	grad_norm 1.7679 (2.1314/0.8875)	mem 24308MB
[2025-01-19 01:02:17 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][130/312]	eta 0:01:53 lr 0.000866	time 0.6539 (0.6239)	model_time 0.6538 (0.6112)	loss 2.0317 (3.0028)	grad_norm 2.6476 (2.1274/0.8598)	mem 24308MB
[2025-01-19 01:02:23 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][140/312]	eta 0:01:47 lr 0.000865	time 0.6968 (0.6237)	model_time 0.6963 (0.6118)	loss 3.5069 (3.0137)	grad_norm 2.3892 (2.2331/1.0707)	mem 24308MB
[2025-01-19 01:02:29 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][150/312]	eta 0:01:40 lr 0.000865	time 0.5816 (0.6224)	model_time 0.5814 (0.6113)	loss 3.1958 (3.0172)	grad_norm 1.1043 (2.2331/1.0719)	mem 24308MB
[2025-01-19 01:02:36 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][160/312]	eta 0:01:34 lr 0.000864	time 0.7007 (0.6241)	model_time 0.7002 (0.6137)	loss 3.6816 (3.0008)	grad_norm 3.8421 (2.2515/1.0830)	mem 24308MB
[2025-01-19 01:02:42 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][170/312]	eta 0:01:28 lr 0.000864	time 0.5880 (0.6230)	model_time 0.5876 (0.6131)	loss 3.2872 (3.0100)	grad_norm 2.9058 (2.2735/1.0738)	mem 24308MB
[2025-01-19 01:02:48 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][180/312]	eta 0:01:22 lr 0.000863	time 0.6021 (0.6229)	model_time 0.6020 (0.6136)	loss 2.7004 (3.0098)	grad_norm 3.5966 (2.3012/1.0826)	mem 24308MB
[2025-01-19 01:02:54 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][190/312]	eta 0:01:15 lr 0.000863	time 0.6020 (0.6216)	model_time 0.6018 (0.6128)	loss 2.9104 (3.0135)	grad_norm 3.0762 (2.3144/1.0794)	mem 24308MB
[2025-01-19 01:03:00 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][200/312]	eta 0:01:09 lr 0.000862	time 0.5981 (0.6222)	model_time 0.5874 (0.6137)	loss 2.2641 (3.0163)	grad_norm 1.5411 (2.3030/1.0713)	mem 24308MB
[2025-01-19 01:03:06 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][210/312]	eta 0:01:03 lr 0.000862	time 0.5999 (0.6210)	model_time 0.5997 (0.6129)	loss 3.3268 (3.0316)	grad_norm 2.8746 (2.3413/1.0785)	mem 24308MB
[2025-01-19 01:03:12 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][220/312]	eta 0:00:56 lr 0.000861	time 0.5747 (0.6195)	model_time 0.5743 (0.6118)	loss 3.3813 (3.0372)	grad_norm 2.9640 (2.3422/1.0690)	mem 24308MB
[2025-01-19 01:03:18 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][230/312]	eta 0:00:50 lr 0.000861	time 0.6108 (0.6187)	model_time 0.6106 (0.6113)	loss 3.6434 (3.0483)	grad_norm 2.2615 (2.3473/1.0580)	mem 24308MB
[2025-01-19 01:03:24 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][240/312]	eta 0:00:44 lr 0.000860	time 0.5750 (0.6182)	model_time 0.5746 (0.6110)	loss 2.7464 (3.0497)	grad_norm 2.3173 (2.3297/1.0505)	mem 24308MB
[2025-01-19 01:03:30 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][250/312]	eta 0:00:38 lr 0.000860	time 0.5899 (0.6178)	model_time 0.5897 (0.6110)	loss 3.4652 (3.0517)	grad_norm 1.8563 (2.3063/1.0385)	mem 24308MB
[2025-01-19 01:03:36 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][260/312]	eta 0:00:32 lr 0.000859	time 0.5917 (0.6174)	model_time 0.5912 (0.6108)	loss 3.3734 (3.0589)	grad_norm 3.1544 (2.2829/1.0327)	mem 24308MB
[2025-01-19 01:03:43 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][270/312]	eta 0:00:25 lr 0.000858	time 0.5874 (0.6177)	model_time 0.5870 (0.6113)	loss 3.1864 (3.0534)	grad_norm 3.6269 (2.2650/1.0284)	mem 24308MB
[2025-01-19 01:03:49 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][280/312]	eta 0:00:19 lr 0.000858	time 0.6556 (0.6180)	model_time 0.6551 (0.6118)	loss 2.7816 (3.0587)	grad_norm 4.5798 (2.3038/1.0598)	mem 24308MB
[2025-01-19 01:03:55 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][290/312]	eta 0:00:13 lr 0.000857	time 0.5738 (0.6173)	model_time 0.5736 (0.6114)	loss 2.1195 (3.0599)	grad_norm 1.8284 (2.3402/1.0804)	mem 24308MB
[2025-01-19 01:04:01 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][300/312]	eta 0:00:07 lr 0.000857	time 0.6446 (0.6169)	model_time 0.6445 (0.6112)	loss 3.4179 (3.0655)	grad_norm 1.9619 (2.3667/1.1141)	mem 24308MB
[2025-01-19 01:04:07 internimage_s_1k_224] (main.py 510): INFO Train: [209/300][310/312]	eta 0:00:01 lr 0.000856	time 0.5686 (0.6158)	model_time 0.5685 (0.6102)	loss 3.4064 (3.0687)	grad_norm 2.9163 (2.3844/1.1329)	mem 24308MB
[2025-01-19 01:04:07 internimage_s_1k_224] (main.py 519): INFO EPOCH 209 training takes 0:03:12
[2025-01-19 01:04:07 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_209.pth saving......
[2025-01-19 01:04:09 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_209.pth saved !!!
[2025-01-19 01:04:21 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 12.288 (12.288)	Loss 0.7586 (0.7586)	Acc@1 84.253 (84.253)	Acc@5 97.241 (97.241)	Mem 24308MB
[2025-01-19 01:04:26 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.135 (1.507)	Loss 0.9730 (0.8434)	Acc@1 77.856 (82.124)	Acc@5 94.873 (96.127)	Mem 24308MB
[2025-01-19 01:04:26 internimage_s_1k_224] (main.py 575): INFO [Epoch:209] * Acc@1 81.984 Acc@5 96.135
[2025-01-19 01:04:26 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.0%
[2025-01-19 01:04:26 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 01:04:28 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 01:04:28 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.98%
[2025-01-19 01:04:36 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.963 (7.963)	Loss 0.7063 (0.7063)	Acc@1 84.912 (84.912)	Acc@5 97.729 (97.729)	Mem 24308MB
[2025-01-19 01:04:40 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.068)	Loss 0.9381 (0.8008)	Acc@1 78.101 (82.320)	Acc@5 95.190 (96.309)	Mem 24308MB
[2025-01-19 01:04:40 internimage_s_1k_224] (main.py 575): INFO [Epoch:209] * Acc@1 82.186 Acc@5 96.325
[2025-01-19 01:04:40 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.2%
[2025-01-19 01:04:40 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:04:42 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:04:42 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.19%
[2025-01-19 01:04:45 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][0/312]	eta 0:12:07 lr 0.000856	time 2.3319 (2.3319)	model_time 0.6095 (0.6095)	loss 3.6828 (3.6828)	grad_norm 2.0269 (2.0269/0.0000)	mem 24308MB
[2025-01-19 01:04:51 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][10/312]	eta 0:03:51 lr 0.000856	time 0.5796 (0.7657)	model_time 0.5795 (0.6088)	loss 2.9196 (3.1592)	grad_norm 2.6520 (2.1873/0.5806)	mem 24308MB
[2025-01-19 01:04:57 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][20/312]	eta 0:03:21 lr 0.000855	time 0.6003 (0.6886)	model_time 0.5998 (0.6062)	loss 3.1012 (3.2538)	grad_norm 1.7039 (2.4087/0.9988)	mem 24308MB
[2025-01-19 01:05:03 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][30/312]	eta 0:03:05 lr 0.000855	time 0.6036 (0.6586)	model_time 0.6034 (0.6027)	loss 3.0947 (3.1390)	grad_norm 2.1728 (2.2824/0.9898)	mem 24308MB
[2025-01-19 01:05:09 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][40/312]	eta 0:02:55 lr 0.000854	time 0.5866 (0.6448)	model_time 0.5865 (0.6025)	loss 3.2425 (3.1457)	grad_norm 2.4372 (2.1892/0.9266)	mem 24308MB
[2025-01-19 01:05:15 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][50/312]	eta 0:02:47 lr 0.000853	time 0.6110 (0.6388)	model_time 0.6106 (0.6046)	loss 3.0555 (3.1276)	grad_norm 1.9304 (2.3060/0.9708)	mem 24308MB
[2025-01-19 01:05:21 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][60/312]	eta 0:02:39 lr 0.000853	time 0.5878 (0.6334)	model_time 0.5876 (0.6049)	loss 3.3697 (3.1032)	grad_norm 1.4948 (2.3461/0.9343)	mem 24308MB
[2025-01-19 01:05:27 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][70/312]	eta 0:02:32 lr 0.000852	time 0.5837 (0.6316)	model_time 0.5835 (0.6070)	loss 2.3831 (3.0859)	grad_norm 1.8910 (2.3292/0.9597)	mem 24308MB
[2025-01-19 01:05:33 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][80/312]	eta 0:02:26 lr 0.000852	time 0.5781 (0.6312)	model_time 0.5777 (0.6096)	loss 3.4425 (3.0600)	grad_norm 2.6358 (2.3923/1.0085)	mem 24308MB
[2025-01-19 01:05:40 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][90/312]	eta 0:02:19 lr 0.000851	time 0.5917 (0.6294)	model_time 0.5913 (0.6100)	loss 3.1933 (3.0739)	grad_norm 2.5949 (2.3878/0.9637)	mem 24308MB
[2025-01-19 01:05:46 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][100/312]	eta 0:02:12 lr 0.000851	time 0.5885 (0.6273)	model_time 0.5883 (0.6099)	loss 3.2791 (3.0600)	grad_norm 2.0076 (2.3854/1.0018)	mem 24308MB
[2025-01-19 01:05:52 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][110/312]	eta 0:02:06 lr 0.000850	time 0.5841 (0.6266)	model_time 0.5836 (0.6107)	loss 3.3766 (3.0445)	grad_norm 3.2329 (2.3272/0.9950)	mem 24308MB
[2025-01-19 01:05:58 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][120/312]	eta 0:01:59 lr 0.000850	time 0.5810 (0.6239)	model_time 0.5808 (0.6093)	loss 3.6787 (3.0419)	grad_norm 1.3823 (2.3107/0.9653)	mem 24308MB
[2025-01-19 01:06:04 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][130/312]	eta 0:01:53 lr 0.000849	time 0.6697 (0.6232)	model_time 0.6695 (0.6097)	loss 2.4275 (3.0258)	grad_norm 3.8010 (2.3101/0.9407)	mem 24308MB
[2025-01-19 01:06:10 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][140/312]	eta 0:01:46 lr 0.000849	time 0.5745 (0.6213)	model_time 0.5743 (0.6087)	loss 3.3967 (3.0110)	grad_norm 1.8953 (2.3457/0.9578)	mem 24308MB
[2025-01-19 01:06:16 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][150/312]	eta 0:01:40 lr 0.000848	time 0.6010 (0.6195)	model_time 0.6007 (0.6077)	loss 3.8343 (3.0246)	grad_norm 1.7158 (2.3202/0.9612)	mem 24308MB
[2025-01-19 01:06:22 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][160/312]	eta 0:01:34 lr 0.000848	time 0.5868 (0.6187)	model_time 0.5864 (0.6076)	loss 2.8682 (3.0223)	grad_norm 2.8705 (2.3392/0.9562)	mem 24308MB
[2025-01-19 01:06:28 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][170/312]	eta 0:01:27 lr 0.000847	time 0.6567 (0.6186)	model_time 0.6562 (0.6082)	loss 3.8806 (3.0241)	grad_norm 1.6680 (2.3150/0.9419)	mem 24308MB
[2025-01-19 01:06:34 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][180/312]	eta 0:01:21 lr 0.000847	time 0.5841 (0.6183)	model_time 0.5839 (0.6085)	loss 3.2281 (3.0176)	grad_norm 3.0712 (2.3374/0.9664)	mem 24308MB
[2025-01-19 01:06:41 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][190/312]	eta 0:01:15 lr 0.000846	time 0.5783 (0.6193)	model_time 0.5771 (0.6099)	loss 2.7554 (3.0156)	grad_norm 1.9889 (2.3180/0.9571)	mem 24308MB
[2025-01-19 01:06:47 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][200/312]	eta 0:01:09 lr 0.000845	time 0.5748 (0.6202)	model_time 0.5747 (0.6113)	loss 3.3547 (3.0173)	grad_norm 2.9818 (2.3223/0.9457)	mem 24308MB
[2025-01-19 01:06:53 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][210/312]	eta 0:01:03 lr 0.000845	time 0.5722 (0.6197)	model_time 0.5718 (0.6112)	loss 2.8894 (3.0204)	grad_norm 2.1441 (2.3005/0.9444)	mem 24308MB
[2025-01-19 01:06:59 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][220/312]	eta 0:00:56 lr 0.000844	time 0.5960 (0.6190)	model_time 0.5958 (0.6109)	loss 2.4566 (3.0095)	grad_norm 2.2902 (2.2910/0.9303)	mem 24308MB
[2025-01-19 01:07:05 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][230/312]	eta 0:00:50 lr 0.000844	time 0.5810 (0.6188)	model_time 0.5809 (0.6109)	loss 2.8015 (3.0113)	grad_norm 1.0480 (2.2860/0.9356)	mem 24308MB
[2025-01-19 01:07:11 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][240/312]	eta 0:00:44 lr 0.000843	time 0.6052 (0.6182)	model_time 0.6048 (0.6107)	loss 2.5399 (3.0180)	grad_norm 1.9842 (2.2885/0.9264)	mem 24308MB
[2025-01-19 01:07:18 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][250/312]	eta 0:00:38 lr 0.000843	time 0.8405 (0.6184)	model_time 0.8400 (0.6112)	loss 3.4331 (3.0249)	grad_norm 3.9159 (2.3262/0.9618)	mem 24308MB
[2025-01-19 01:07:24 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][260/312]	eta 0:00:32 lr 0.000842	time 0.5759 (0.6179)	model_time 0.5756 (0.6109)	loss 3.3881 (3.0054)	grad_norm 2.4044 (2.3426/0.9711)	mem 24308MB
[2025-01-19 01:07:29 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][270/312]	eta 0:00:25 lr 0.000842	time 0.5777 (0.6167)	model_time 0.5775 (0.6100)	loss 2.9641 (3.0167)	grad_norm 2.1918 (2.3252/0.9711)	mem 24308MB
[2025-01-19 01:07:35 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][280/312]	eta 0:00:19 lr 0.000841	time 0.5817 (0.6162)	model_time 0.5815 (0.6097)	loss 3.0702 (3.0223)	grad_norm 3.9801 (2.3355/0.9821)	mem 24308MB
[2025-01-19 01:07:42 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][290/312]	eta 0:00:13 lr 0.000841	time 0.5763 (0.6161)	model_time 0.5762 (0.6098)	loss 2.1441 (3.0211)	grad_norm 6.0372 (2.3697/1.0362)	mem 24308MB
[2025-01-19 01:07:48 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][300/312]	eta 0:00:07 lr 0.000840	time 0.5689 (0.6158)	model_time 0.5688 (0.6097)	loss 3.0527 (3.0156)	grad_norm 2.1822 (2.3829/1.0310)	mem 24308MB
[2025-01-19 01:07:54 internimage_s_1k_224] (main.py 510): INFO Train: [210/300][310/312]	eta 0:00:01 lr 0.000840	time 0.6460 (0.6155)	model_time 0.6459 (0.6096)	loss 2.0173 (3.0096)	grad_norm 2.4125 (2.3787/1.0350)	mem 24308MB
[2025-01-19 01:07:54 internimage_s_1k_224] (main.py 519): INFO EPOCH 210 training takes 0:03:11
[2025-01-19 01:07:54 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_210.pth saving......
[2025-01-19 01:07:56 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_210.pth saved !!!
[2025-01-19 01:08:04 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.614 (7.614)	Loss 0.7680 (0.7680)	Acc@1 84.302 (84.302)	Acc@5 97.607 (97.607)	Mem 24308MB
[2025-01-19 01:08:08 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.021)	Loss 1.0057 (0.8569)	Acc@1 77.344 (82.082)	Acc@5 94.849 (96.078)	Mem 24308MB
[2025-01-19 01:08:08 internimage_s_1k_224] (main.py 575): INFO [Epoch:210] * Acc@1 81.966 Acc@5 96.125
[2025-01-19 01:08:08 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.0%
[2025-01-19 01:08:08 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 81.98%
[2025-01-19 01:08:19 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 11.746 (11.746)	Loss 0.7063 (0.7063)	Acc@1 85.010 (85.010)	Acc@5 97.729 (97.729)	Mem 24308MB
[2025-01-19 01:08:29 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.895)	Loss 0.9370 (0.8001)	Acc@1 78.125 (82.335)	Acc@5 95.215 (96.313)	Mem 24308MB
[2025-01-19 01:08:29 internimage_s_1k_224] (main.py 575): INFO [Epoch:210] * Acc@1 82.202 Acc@5 96.333
[2025-01-19 01:08:29 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.2%
[2025-01-19 01:08:29 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:08:31 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:08:31 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.20%
[2025-01-19 01:08:33 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][0/312]	eta 0:11:24 lr 0.000839	time 2.1926 (2.1926)	model_time 0.6045 (0.6045)	loss 2.5824 (2.5824)	grad_norm 1.4225 (1.4225/0.0000)	mem 24308MB
[2025-01-19 01:08:40 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][10/312]	eta 0:03:51 lr 0.000839	time 0.5949 (0.7660)	model_time 0.5947 (0.6214)	loss 3.6484 (2.9073)	grad_norm 2.6522 (2.1593/0.9267)	mem 24308MB
[2025-01-19 01:08:46 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][20/312]	eta 0:03:20 lr 0.000838	time 0.5864 (0.6872)	model_time 0.5859 (0.6105)	loss 3.4502 (3.0145)	grad_norm 1.9722 (2.1303/0.8357)	mem 24308MB
[2025-01-19 01:08:52 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][30/312]	eta 0:03:07 lr 0.000838	time 0.5768 (0.6636)	model_time 0.5762 (0.6115)	loss 2.4344 (3.0151)	grad_norm 1.8643 (2.0196/0.7253)	mem 24308MB
[2025-01-19 01:08:58 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][40/312]	eta 0:02:57 lr 0.000837	time 0.5914 (0.6513)	model_time 0.5909 (0.6118)	loss 3.2037 (3.0233)	grad_norm 2.1640 (2.0667/0.7377)	mem 24308MB
[2025-01-19 01:09:04 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][50/312]	eta 0:02:47 lr 0.000837	time 0.6058 (0.6408)	model_time 0.6056 (0.6090)	loss 3.3335 (3.0597)	grad_norm 1.8144 (2.2097/0.9143)	mem 24308MB
[2025-01-19 01:09:10 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][60/312]	eta 0:02:40 lr 0.000836	time 0.5797 (0.6350)	model_time 0.5793 (0.6083)	loss 2.5900 (3.0342)	grad_norm 1.7182 (2.2477/0.9309)	mem 24308MB
[2025-01-19 01:09:16 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][70/312]	eta 0:02:32 lr 0.000836	time 0.6153 (0.6307)	model_time 0.6149 (0.6077)	loss 4.0196 (3.0410)	grad_norm 1.7588 (2.1940/0.8974)	mem 24308MB
[2025-01-19 01:09:22 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][80/312]	eta 0:02:25 lr 0.000835	time 0.5900 (0.6257)	model_time 0.5782 (0.6053)	loss 3.7378 (3.0675)	grad_norm 0.8446 (2.1073/0.8813)	mem 24308MB
[2025-01-19 01:09:28 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][90/312]	eta 0:02:18 lr 0.000835	time 0.5905 (0.6231)	model_time 0.5901 (0.6049)	loss 3.2276 (3.0728)	grad_norm 2.0899 (2.0524/0.8531)	mem 24308MB
[2025-01-19 01:09:34 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][100/312]	eta 0:02:11 lr 0.000834	time 0.7434 (0.6219)	model_time 0.7432 (0.6055)	loss 1.9432 (3.0666)	grad_norm 1.4117 (2.0542/0.8254)	mem 24308MB
[2025-01-19 01:09:40 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][110/312]	eta 0:02:05 lr 0.000834	time 0.5808 (0.6215)	model_time 0.5804 (0.6065)	loss 3.5222 (3.0802)	grad_norm 1.4207 (2.0226/0.8097)	mem 24308MB
[2025-01-19 01:09:46 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][120/312]	eta 0:01:59 lr 0.000833	time 0.6703 (0.6213)	model_time 0.6702 (0.6075)	loss 3.1801 (3.0722)	grad_norm 2.6423 (2.0132/0.8094)	mem 24308MB
[2025-01-19 01:09:53 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][130/312]	eta 0:01:53 lr 0.000833	time 0.5843 (0.6211)	model_time 0.5841 (0.6084)	loss 2.7657 (3.0619)	grad_norm 2.2658 (1.9680/0.8003)	mem 24308MB
[2025-01-19 01:09:59 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][140/312]	eta 0:01:46 lr 0.000832	time 0.5851 (0.6206)	model_time 0.5847 (0.6086)	loss 3.5283 (3.0519)	grad_norm 1.4736 (1.9106/0.7995)	mem 24308MB
[2025-01-19 01:10:05 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][150/312]	eta 0:01:40 lr 0.000831	time 0.5843 (0.6203)	model_time 0.5839 (0.6091)	loss 2.6096 (3.0333)	grad_norm 1.5978 (1.8958/0.7818)	mem 24308MB
[2025-01-19 01:10:11 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][160/312]	eta 0:01:34 lr 0.000831	time 0.5792 (0.6199)	model_time 0.5790 (0.6094)	loss 3.2576 (3.0474)	grad_norm 1.1230 (1.9194/0.7914)	mem 24308MB
[2025-01-19 01:10:17 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][170/312]	eta 0:01:27 lr 0.000830	time 0.5762 (0.6193)	model_time 0.5760 (0.6094)	loss 3.1078 (3.0417)	grad_norm 6.5469 (2.0073/0.9471)	mem 24308MB
[2025-01-19 01:10:23 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][180/312]	eta 0:01:21 lr 0.000830	time 0.5717 (0.6185)	model_time 0.5715 (0.6091)	loss 2.9424 (3.0444)	grad_norm 3.2343 (2.0993/1.0793)	mem 24308MB
[2025-01-19 01:10:29 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][190/312]	eta 0:01:15 lr 0.000829	time 0.6097 (0.6176)	model_time 0.6095 (0.6087)	loss 3.3183 (3.0331)	grad_norm 1.6503 (2.1124/1.0673)	mem 24308MB
[2025-01-19 01:10:35 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][200/312]	eta 0:01:09 lr 0.000829	time 0.5844 (0.6165)	model_time 0.5842 (0.6080)	loss 2.3061 (3.0338)	grad_norm 2.1860 (2.1083/1.0492)	mem 24308MB
[2025-01-19 01:10:41 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][210/312]	eta 0:01:02 lr 0.000828	time 0.5911 (0.6158)	model_time 0.5910 (0.6077)	loss 3.5634 (3.0324)	grad_norm 2.6582 (2.1216/1.0372)	mem 24308MB
[2025-01-19 01:10:47 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][220/312]	eta 0:00:56 lr 0.000828	time 0.6781 (0.6154)	model_time 0.6778 (0.6076)	loss 3.4600 (3.0377)	grad_norm 2.5361 (2.1322/1.0487)	mem 24308MB
[2025-01-19 01:10:53 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][230/312]	eta 0:00:50 lr 0.000827	time 0.5781 (0.6152)	model_time 0.5777 (0.6077)	loss 3.3513 (3.0352)	grad_norm 1.5800 (2.1351/1.0526)	mem 24308MB
[2025-01-19 01:10:59 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][240/312]	eta 0:00:44 lr 0.000827	time 0.6309 (0.6153)	model_time 0.6307 (0.6081)	loss 3.2331 (3.0341)	grad_norm 4.0649 (2.1407/1.0541)	mem 24308MB
[2025-01-19 01:11:06 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][250/312]	eta 0:00:38 lr 0.000826	time 0.6985 (0.6160)	model_time 0.6983 (0.6090)	loss 3.9499 (3.0441)	grad_norm 4.4058 (2.1787/1.0670)	mem 24308MB
[2025-01-19 01:11:12 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][260/312]	eta 0:00:32 lr 0.000826	time 0.5767 (0.6155)	model_time 0.5765 (0.6088)	loss 2.9070 (3.0439)	grad_norm 1.5434 (2.1923/1.0738)	mem 24308MB
[2025-01-19 01:11:18 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][270/312]	eta 0:00:25 lr 0.000825	time 0.5873 (0.6154)	model_time 0.5871 (0.6089)	loss 2.3102 (3.0474)	grad_norm 1.2667 (2.1662/1.0664)	mem 24308MB
[2025-01-19 01:11:24 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][280/312]	eta 0:00:19 lr 0.000825	time 0.5995 (0.6151)	model_time 0.5991 (0.6089)	loss 3.0883 (3.0546)	grad_norm 2.9952 (2.2203/1.1282)	mem 24308MB
[2025-01-19 01:11:30 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][290/312]	eta 0:00:13 lr 0.000824	time 0.5723 (0.6146)	model_time 0.5721 (0.6086)	loss 2.4992 (3.0480)	grad_norm 4.2877 (2.2528/1.1347)	mem 24308MB
[2025-01-19 01:11:36 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][300/312]	eta 0:00:07 lr 0.000824	time 0.5805 (0.6139)	model_time 0.5803 (0.6081)	loss 2.5677 (3.0531)	grad_norm 2.1819 (2.2473/1.1251)	mem 24308MB
[2025-01-19 01:11:42 internimage_s_1k_224] (main.py 510): INFO Train: [211/300][310/312]	eta 0:00:01 lr 0.000823	time 0.5697 (0.6128)	model_time 0.5696 (0.6072)	loss 2.8733 (3.0551)	grad_norm 2.0135 (2.2468/1.1136)	mem 24308MB
[2025-01-19 01:11:42 internimage_s_1k_224] (main.py 519): INFO EPOCH 211 training takes 0:03:11
[2025-01-19 01:11:42 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_211.pth saving......
[2025-01-19 01:11:44 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_211.pth saved !!!
[2025-01-19 01:11:53 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.586 (8.586)	Loss 0.7555 (0.7555)	Acc@1 84.424 (84.424)	Acc@5 97.241 (97.241)	Mem 24308MB
[2025-01-19 01:11:57 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.138 (1.190)	Loss 0.9739 (0.8513)	Acc@1 78.052 (82.213)	Acc@5 95.117 (96.149)	Mem 24308MB
[2025-01-19 01:11:58 internimage_s_1k_224] (main.py 575): INFO [Epoch:211] * Acc@1 82.068 Acc@5 96.159
[2025-01-19 01:11:58 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.1%
[2025-01-19 01:11:58 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 01:11:59 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 01:12:00 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.07%
[2025-01-19 01:12:09 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.318 (9.318)	Loss 0.7063 (0.7063)	Acc@1 84.985 (84.985)	Acc@5 97.729 (97.729)	Mem 24308MB
[2025-01-19 01:12:13 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.268)	Loss 0.9360 (0.7995)	Acc@1 78.198 (82.366)	Acc@5 95.239 (96.322)	Mem 24308MB
[2025-01-19 01:12:14 internimage_s_1k_224] (main.py 575): INFO [Epoch:211] * Acc@1 82.232 Acc@5 96.343
[2025-01-19 01:12:14 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.2%
[2025-01-19 01:12:14 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:12:16 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:12:16 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.23%
[2025-01-19 01:12:18 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][0/312]	eta 0:11:26 lr 0.000823	time 2.2002 (2.2002)	model_time 0.5956 (0.5956)	loss 3.5671 (3.5671)	grad_norm 1.9572 (1.9572/0.0000)	mem 24308MB
[2025-01-19 01:12:24 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][10/312]	eta 0:03:46 lr 0.000822	time 0.6114 (0.7497)	model_time 0.6113 (0.6035)	loss 3.1193 (3.0659)	grad_norm 1.5927 (1.4560/0.4482)	mem 24308MB
[2025-01-19 01:12:30 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][20/312]	eta 0:03:18 lr 0.000822	time 0.5953 (0.6805)	model_time 0.5951 (0.6037)	loss 3.5553 (3.1407)	grad_norm 4.2084 (1.9920/0.8776)	mem 24308MB
[2025-01-19 01:12:37 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][30/312]	eta 0:03:05 lr 0.000821	time 0.5984 (0.6580)	model_time 0.5980 (0.6059)	loss 2.7713 (3.1101)	grad_norm 2.0064 (2.4459/1.1149)	mem 24308MB
[2025-01-19 01:12:43 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][40/312]	eta 0:02:56 lr 0.000821	time 0.6791 (0.6492)	model_time 0.6790 (0.6097)	loss 2.1866 (3.0555)	grad_norm 1.0550 (2.4610/1.1449)	mem 24308MB
[2025-01-19 01:12:49 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][50/312]	eta 0:02:48 lr 0.000820	time 0.5837 (0.6412)	model_time 0.5835 (0.6094)	loss 3.1704 (3.0585)	grad_norm 1.6380 (2.3617/1.0605)	mem 24308MB
[2025-01-19 01:12:55 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][60/312]	eta 0:02:40 lr 0.000820	time 0.5807 (0.6386)	model_time 0.5806 (0.6119)	loss 2.3673 (3.0732)	grad_norm 4.5118 (2.3584/1.0275)	mem 24308MB
[2025-01-19 01:13:01 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][70/312]	eta 0:02:33 lr 0.000819	time 0.6058 (0.6350)	model_time 0.6057 (0.6121)	loss 2.1154 (3.0542)	grad_norm 1.4878 (2.3312/0.9968)	mem 24308MB
[2025-01-19 01:13:07 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][80/312]	eta 0:02:26 lr 0.000819	time 0.5739 (0.6327)	model_time 0.5738 (0.6125)	loss 3.0204 (3.0201)	grad_norm 1.2945 (2.2804/0.9695)	mem 24308MB
[2025-01-19 01:13:14 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][90/312]	eta 0:02:20 lr 0.000818	time 0.6445 (0.6313)	model_time 0.6443 (0.6133)	loss 2.9760 (3.0416)	grad_norm 1.4041 (2.3251/0.9959)	mem 24308MB
[2025-01-19 01:13:20 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][100/312]	eta 0:02:13 lr 0.000818	time 0.5873 (0.6285)	model_time 0.5869 (0.6123)	loss 3.4936 (3.0618)	grad_norm 1.3850 (2.3042/1.0109)	mem 24308MB
[2025-01-19 01:13:26 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][110/312]	eta 0:02:06 lr 0.000817	time 0.7637 (0.6269)	model_time 0.7635 (0.6121)	loss 3.1227 (3.0500)	grad_norm 1.7372 (2.2976/0.9920)	mem 24308MB
[2025-01-19 01:13:32 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][120/312]	eta 0:02:00 lr 0.000817	time 0.7121 (0.6256)	model_time 0.7119 (0.6120)	loss 2.2013 (3.0437)	grad_norm 3.5241 (2.3093/0.9736)	mem 24308MB
[2025-01-19 01:13:38 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][130/312]	eta 0:01:53 lr 0.000816	time 0.5936 (0.6235)	model_time 0.5930 (0.6109)	loss 3.3365 (3.0346)	grad_norm 3.2909 (2.4227/1.0555)	mem 24308MB
[2025-01-19 01:13:44 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][140/312]	eta 0:01:47 lr 0.000815	time 0.5956 (0.6222)	model_time 0.5954 (0.6104)	loss 2.5422 (3.0286)	grad_norm 3.1013 (2.4335/1.0417)	mem 24308MB
[2025-01-19 01:13:50 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][150/312]	eta 0:01:40 lr 0.000815	time 0.6099 (0.6211)	model_time 0.6095 (0.6101)	loss 2.7583 (3.0195)	grad_norm 1.2497 (2.4501/1.0612)	mem 24308MB
[2025-01-19 01:13:56 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][160/312]	eta 0:01:34 lr 0.000814	time 0.6916 (0.6212)	model_time 0.6912 (0.6108)	loss 2.7492 (3.0293)	grad_norm 2.2659 (2.4350/1.0422)	mem 24308MB
[2025-01-19 01:14:02 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][170/312]	eta 0:01:28 lr 0.000814	time 0.5893 (0.6202)	model_time 0.5889 (0.6104)	loss 2.1714 (3.0105)	grad_norm 2.0802 (2.4475/1.0501)	mem 24308MB
[2025-01-19 01:14:09 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][180/312]	eta 0:01:21 lr 0.000813	time 0.6855 (0.6211)	model_time 0.6853 (0.6119)	loss 2.9277 (3.0011)	grad_norm 3.6799 (2.4580/1.0600)	mem 24308MB
[2025-01-19 01:14:15 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][190/312]	eta 0:01:15 lr 0.000813	time 0.5730 (0.6207)	model_time 0.5728 (0.6119)	loss 2.5661 (3.0033)	grad_norm 3.6724 (2.5175/1.0883)	mem 24308MB
[2025-01-19 01:14:21 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][200/312]	eta 0:01:09 lr 0.000812	time 0.5889 (0.6195)	model_time 0.5885 (0.6112)	loss 3.5459 (3.0123)	grad_norm 1.4430 (2.4772/1.0834)	mem 24308MB
[2025-01-19 01:14:27 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][210/312]	eta 0:01:03 lr 0.000812	time 0.5804 (0.6187)	model_time 0.5800 (0.6107)	loss 2.9667 (3.0171)	grad_norm 1.5921 (2.4508/1.0684)	mem 24308MB
[2025-01-19 01:14:33 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][220/312]	eta 0:00:56 lr 0.000811	time 0.6211 (0.6185)	model_time 0.6207 (0.6109)	loss 3.2857 (3.0283)	grad_norm 1.9991 (2.4319/1.0509)	mem 24308MB
[2025-01-19 01:14:39 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][230/312]	eta 0:00:50 lr 0.000811	time 0.6823 (0.6177)	model_time 0.6821 (0.6104)	loss 2.1468 (3.0292)	grad_norm 1.3842 (2.4109/1.0434)	mem 24308MB
[2025-01-19 01:14:45 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][240/312]	eta 0:00:44 lr 0.000810	time 0.5859 (0.6172)	model_time 0.5856 (0.6102)	loss 1.8712 (3.0231)	grad_norm 2.1155 (2.4168/1.0421)	mem 24308MB
[2025-01-19 01:14:51 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][250/312]	eta 0:00:38 lr 0.000810	time 0.5855 (0.6169)	model_time 0.5853 (0.6101)	loss 3.3348 (3.0305)	grad_norm 1.9324 (2.4494/1.0562)	mem 24308MB
[2025-01-19 01:14:57 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][260/312]	eta 0:00:32 lr 0.000809	time 0.5754 (0.6162)	model_time 0.5750 (0.6096)	loss 2.5717 (3.0316)	grad_norm 3.1153 (2.4381/1.0526)	mem 24308MB
[2025-01-19 01:15:03 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][270/312]	eta 0:00:25 lr 0.000809	time 0.5862 (0.6157)	model_time 0.5860 (0.6095)	loss 3.0515 (3.0321)	grad_norm 1.9396 (2.4178/1.0418)	mem 24308MB
[2025-01-19 01:15:09 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][280/312]	eta 0:00:19 lr 0.000808	time 0.5738 (0.6152)	model_time 0.5737 (0.6092)	loss 2.4789 (3.0249)	grad_norm 0.9667 (2.3950/1.0391)	mem 24308MB
[2025-01-19 01:15:15 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][290/312]	eta 0:00:13 lr 0.000808	time 0.5734 (0.6151)	model_time 0.5732 (0.6092)	loss 2.8701 (3.0340)	grad_norm 3.3692 (2.4030/1.0346)	mem 24308MB
[2025-01-19 01:15:21 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][300/312]	eta 0:00:07 lr 0.000807	time 0.5745 (0.6155)	model_time 0.5744 (0.6098)	loss 2.9201 (3.0285)	grad_norm 2.2194 (2.4070/1.0286)	mem 24308MB
[2025-01-19 01:15:27 internimage_s_1k_224] (main.py 510): INFO Train: [212/300][310/312]	eta 0:00:01 lr 0.000807	time 0.6522 (0.6151)	model_time 0.6521 (0.6096)	loss 3.3482 (3.0183)	grad_norm 2.1922 (2.4419/1.0219)	mem 24308MB
[2025-01-19 01:15:28 internimage_s_1k_224] (main.py 519): INFO EPOCH 212 training takes 0:03:11
[2025-01-19 01:15:28 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_212.pth saving......
[2025-01-19 01:15:30 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_212.pth saved !!!
[2025-01-19 01:15:38 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.011 (8.011)	Loss 0.7197 (0.7197)	Acc@1 85.107 (85.107)	Acc@5 97.339 (97.339)	Mem 24308MB
[2025-01-19 01:15:42 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.062)	Loss 0.9439 (0.8243)	Acc@1 78.345 (82.211)	Acc@5 94.775 (96.160)	Mem 24308MB
[2025-01-19 01:15:42 internimage_s_1k_224] (main.py 575): INFO [Epoch:212] * Acc@1 82.080 Acc@5 96.175
[2025-01-19 01:15:42 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.1%
[2025-01-19 01:15:42 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 01:15:44 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 01:15:44 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.08%
[2025-01-19 01:15:52 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.829 (7.829)	Loss 0.7063 (0.7063)	Acc@1 85.034 (85.034)	Acc@5 97.729 (97.729)	Mem 24308MB
[2025-01-19 01:15:55 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (1.035)	Loss 0.9349 (0.7988)	Acc@1 78.223 (82.413)	Acc@5 95.312 (96.338)	Mem 24308MB
[2025-01-19 01:15:55 internimage_s_1k_224] (main.py 575): INFO [Epoch:212] * Acc@1 82.280 Acc@5 96.361
[2025-01-19 01:15:55 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.3%
[2025-01-19 01:15:55 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:15:58 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:15:58 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.28%
[2025-01-19 01:16:00 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][0/312]	eta 0:11:32 lr 0.000806	time 2.2208 (2.2208)	model_time 0.6038 (0.6038)	loss 3.7554 (3.7554)	grad_norm 1.9270 (1.9270/0.0000)	mem 24308MB
[2025-01-19 01:16:06 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][10/312]	eta 0:03:44 lr 0.000806	time 0.5789 (0.7430)	model_time 0.5787 (0.5956)	loss 3.1244 (3.1388)	grad_norm 1.6707 (1.8844/0.4918)	mem 24308MB
[2025-01-19 01:16:12 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][20/312]	eta 0:03:16 lr 0.000805	time 0.5923 (0.6730)	model_time 0.5921 (0.5957)	loss 2.8145 (2.9455)	grad_norm 1.9440 (1.9580/0.5629)	mem 24308MB
[2025-01-19 01:16:18 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][30/312]	eta 0:03:05 lr 0.000805	time 0.6351 (0.6568)	model_time 0.6349 (0.6043)	loss 2.2895 (2.9794)	grad_norm 2.1979 (2.0307/0.5410)	mem 24308MB
[2025-01-19 01:16:24 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][40/312]	eta 0:02:54 lr 0.000804	time 0.5829 (0.6425)	model_time 0.5827 (0.6027)	loss 2.1524 (2.9263)	grad_norm 3.2431 (2.1263/0.6072)	mem 24308MB
[2025-01-19 01:16:30 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][50/312]	eta 0:02:47 lr 0.000804	time 0.5978 (0.6387)	model_time 0.5977 (0.6067)	loss 3.5941 (2.9611)	grad_norm 2.7183 (2.1507/0.6301)	mem 24308MB
[2025-01-19 01:16:37 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][60/312]	eta 0:02:39 lr 0.000803	time 0.6056 (0.6333)	model_time 0.6054 (0.6064)	loss 3.6534 (2.9907)	grad_norm 1.4125 (2.1710/0.6614)	mem 24308MB
[2025-01-19 01:16:43 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][70/312]	eta 0:02:32 lr 0.000803	time 0.6182 (0.6290)	model_time 0.6179 (0.6059)	loss 2.8482 (3.0210)	grad_norm 3.2687 (2.1739/0.6537)	mem 24308MB
[2025-01-19 01:16:49 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][80/312]	eta 0:02:25 lr 0.000802	time 0.5804 (0.6253)	model_time 0.5802 (0.6051)	loss 2.6558 (3.0128)	grad_norm 1.5787 (2.2591/0.8223)	mem 24308MB
[2025-01-19 01:16:55 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][90/312]	eta 0:02:18 lr 0.000802	time 0.5813 (0.6231)	model_time 0.5812 (0.6050)	loss 3.2681 (3.0198)	grad_norm 1.9939 (2.2105/0.8170)	mem 24308MB
[2025-01-19 01:17:01 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][100/312]	eta 0:02:11 lr 0.000801	time 0.6148 (0.6215)	model_time 0.6143 (0.6052)	loss 3.2224 (3.0201)	grad_norm 5.2654 (2.2229/0.8596)	mem 24308MB
[2025-01-19 01:17:07 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][110/312]	eta 0:02:05 lr 0.000801	time 0.6705 (0.6222)	model_time 0.6703 (0.6073)	loss 3.1237 (3.0286)	grad_norm 1.9803 (2.2630/0.8748)	mem 24308MB
[2025-01-19 01:17:13 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][120/312]	eta 0:01:59 lr 0.000800	time 0.6733 (0.6226)	model_time 0.6731 (0.6089)	loss 3.3382 (3.0271)	grad_norm 2.1680 (2.2638/0.8475)	mem 24308MB
[2025-01-19 01:17:19 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][130/312]	eta 0:01:52 lr 0.000800	time 0.5865 (0.6204)	model_time 0.5863 (0.6078)	loss 3.2314 (3.0350)	grad_norm 1.5083 (2.2521/0.8625)	mem 24308MB
[2025-01-19 01:17:25 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][140/312]	eta 0:01:46 lr 0.000799	time 0.5787 (0.6193)	model_time 0.5785 (0.6075)	loss 3.1393 (3.0221)	grad_norm 2.0709 (2.2425/0.8389)	mem 24308MB
[2025-01-19 01:17:31 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][150/312]	eta 0:01:40 lr 0.000799	time 0.5919 (0.6196)	model_time 0.5917 (0.6085)	loss 2.8986 (3.0073)	grad_norm 1.4706 (2.2359/0.8462)	mem 24308MB
[2025-01-19 01:17:37 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][160/312]	eta 0:01:33 lr 0.000798	time 0.5841 (0.6181)	model_time 0.5837 (0.6077)	loss 2.7874 (3.0101)	grad_norm 1.6531 (2.2546/0.8619)	mem 24308MB
[2025-01-19 01:17:43 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][170/312]	eta 0:01:27 lr 0.000798	time 0.5982 (0.6173)	model_time 0.5980 (0.6075)	loss 3.4030 (2.9930)	grad_norm 1.3116 (2.2484/0.8569)	mem 24308MB
[2025-01-19 01:17:49 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][180/312]	eta 0:01:21 lr 0.000797	time 0.5843 (0.6160)	model_time 0.5838 (0.6067)	loss 3.2529 (2.9908)	grad_norm 1.1320 (2.2277/0.8478)	mem 24308MB
[2025-01-19 01:17:55 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][190/312]	eta 0:01:15 lr 0.000796	time 0.5895 (0.6155)	model_time 0.5894 (0.6067)	loss 2.9079 (2.9927)	grad_norm 3.0236 (2.2241/0.8509)	mem 24308MB
[2025-01-19 01:18:02 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][200/312]	eta 0:01:08 lr 0.000796	time 0.6026 (0.6150)	model_time 0.6024 (0.6066)	loss 3.3935 (3.0005)	grad_norm 1.1032 (2.2211/0.8471)	mem 24308MB
[2025-01-19 01:18:08 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][210/312]	eta 0:01:02 lr 0.000795	time 0.5673 (0.6145)	model_time 0.5672 (0.6064)	loss 3.3020 (3.0003)	grad_norm 1.8971 (2.2115/0.8391)	mem 24308MB
[2025-01-19 01:18:14 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][220/312]	eta 0:00:56 lr 0.000795	time 0.5767 (0.6146)	model_time 0.5763 (0.6069)	loss 3.3056 (3.0105)	grad_norm 2.6266 (2.1968/0.8314)	mem 24308MB
[2025-01-19 01:18:20 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][230/312]	eta 0:00:50 lr 0.000794	time 0.5822 (0.6154)	model_time 0.5817 (0.6080)	loss 3.5618 (3.0105)	grad_norm 1.4511 (2.2061/0.8501)	mem 24308MB
[2025-01-19 01:18:26 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][240/312]	eta 0:00:44 lr 0.000794	time 0.5847 (0.6160)	model_time 0.5845 (0.6089)	loss 3.2855 (3.0042)	grad_norm 5.9664 (2.2569/0.9388)	mem 24308MB
[2025-01-19 01:18:32 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][250/312]	eta 0:00:38 lr 0.000793	time 0.5824 (0.6151)	model_time 0.5820 (0.6083)	loss 3.0721 (3.0126)	grad_norm 3.5066 (2.2838/0.9448)	mem 24308MB
[2025-01-19 01:18:39 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][260/312]	eta 0:00:31 lr 0.000793	time 0.6307 (0.6153)	model_time 0.6305 (0.6088)	loss 3.5917 (3.0182)	grad_norm 4.5155 (2.2950/0.9778)	mem 24308MB
[2025-01-19 01:18:45 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][270/312]	eta 0:00:25 lr 0.000792	time 0.6707 (0.6152)	model_time 0.6703 (0.6089)	loss 3.4913 (3.0200)	grad_norm 3.4296 (2.3268/0.9979)	mem 24308MB
[2025-01-19 01:18:51 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][280/312]	eta 0:00:19 lr 0.000792	time 0.5727 (0.6146)	model_time 0.5725 (0.6085)	loss 3.3371 (3.0222)	grad_norm 4.0609 (2.3368/0.9958)	mem 24308MB
[2025-01-19 01:18:57 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][290/312]	eta 0:00:13 lr 0.000791	time 0.5964 (0.6142)	model_time 0.5960 (0.6083)	loss 3.1928 (3.0195)	grad_norm 1.4532 (2.3340/0.9953)	mem 24308MB
[2025-01-19 01:19:02 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][300/312]	eta 0:00:07 lr 0.000791	time 0.5693 (0.6132)	model_time 0.5692 (0.6075)	loss 2.5553 (3.0131)	grad_norm 2.0960 (2.3358/0.9899)	mem 24308MB
[2025-01-19 01:19:08 internimage_s_1k_224] (main.py 510): INFO Train: [213/300][310/312]	eta 0:00:01 lr 0.000790	time 0.5725 (0.6124)	model_time 0.5724 (0.6068)	loss 3.6031 (3.0180)	grad_norm 1.9201 (2.3376/0.9929)	mem 24308MB
[2025-01-19 01:19:09 internimage_s_1k_224] (main.py 519): INFO EPOCH 213 training takes 0:03:11
[2025-01-19 01:19:09 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_213.pth saving......
[2025-01-19 01:19:11 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_213.pth saved !!!
[2025-01-19 01:19:19 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.972 (7.972)	Loss 0.7719 (0.7719)	Acc@1 84.644 (84.644)	Acc@5 97.339 (97.339)	Mem 24308MB
[2025-01-19 01:19:22 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.046)	Loss 0.9770 (0.8600)	Acc@1 78.442 (82.342)	Acc@5 95.044 (96.178)	Mem 24308MB
[2025-01-19 01:19:23 internimage_s_1k_224] (main.py 575): INFO [Epoch:213] * Acc@1 82.208 Acc@5 96.195
[2025-01-19 01:19:23 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.2%
[2025-01-19 01:19:23 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 01:19:24 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 01:19:24 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.21%
[2025-01-19 01:19:32 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.746 (7.746)	Loss 0.7063 (0.7063)	Acc@1 85.083 (85.083)	Acc@5 97.729 (97.729)	Mem 24308MB
[2025-01-19 01:19:36 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.044)	Loss 0.9337 (0.7982)	Acc@1 78.198 (82.455)	Acc@5 95.312 (96.349)	Mem 24308MB
[2025-01-19 01:19:36 internimage_s_1k_224] (main.py 575): INFO [Epoch:213] * Acc@1 82.312 Acc@5 96.371
[2025-01-19 01:19:36 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.3%
[2025-01-19 01:19:36 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:19:38 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:19:38 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.31%
[2025-01-19 01:19:41 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][0/312]	eta 0:13:49 lr 0.000790	time 2.6586 (2.6586)	model_time 0.6398 (0.6398)	loss 3.3628 (3.3628)	grad_norm 1.9404 (1.9404/0.0000)	mem 24308MB
[2025-01-19 01:19:47 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][10/312]	eta 0:04:02 lr 0.000790	time 0.6493 (0.8023)	model_time 0.6491 (0.6185)	loss 3.1407 (2.9997)	grad_norm 2.6816 (1.9139/0.3682)	mem 24308MB
[2025-01-19 01:19:53 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][20/312]	eta 0:03:26 lr 0.000789	time 0.5952 (0.7070)	model_time 0.5947 (0.6105)	loss 2.5206 (3.0038)	grad_norm 3.8600 (2.4630/0.9206)	mem 24308MB
[2025-01-19 01:19:59 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][30/312]	eta 0:03:10 lr 0.000789	time 0.5948 (0.6755)	model_time 0.5943 (0.6100)	loss 2.9144 (3.0048)	grad_norm 1.5043 (2.3650/0.8703)	mem 24308MB
[2025-01-19 01:20:06 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][40/312]	eta 0:03:01 lr 0.000788	time 0.6566 (0.6669)	model_time 0.6564 (0.6173)	loss 3.5427 (3.0288)	grad_norm 1.8081 (2.3619/0.8606)	mem 24308MB
[2025-01-19 01:20:12 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][50/312]	eta 0:02:52 lr 0.000788	time 0.5813 (0.6573)	model_time 0.5808 (0.6174)	loss 3.5149 (3.0264)	grad_norm 3.7567 (2.4539/0.8882)	mem 24308MB
[2025-01-19 01:20:18 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][60/312]	eta 0:02:43 lr 0.000787	time 0.5866 (0.6490)	model_time 0.5864 (0.6155)	loss 2.3553 (3.0749)	grad_norm 2.7068 (2.4042/0.8657)	mem 24308MB
[2025-01-19 01:20:24 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][70/312]	eta 0:02:35 lr 0.000786	time 0.5876 (0.6439)	model_time 0.5870 (0.6151)	loss 3.0106 (3.0991)	grad_norm 1.1682 (2.3587/0.8569)	mem 24308MB
[2025-01-19 01:20:30 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][80/312]	eta 0:02:28 lr 0.000786	time 0.5770 (0.6401)	model_time 0.5769 (0.6148)	loss 3.5676 (3.1172)	grad_norm 1.6292 (2.3514/0.8554)	mem 24308MB
[2025-01-19 01:20:36 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][90/312]	eta 0:02:21 lr 0.000785	time 0.5979 (0.6354)	model_time 0.5976 (0.6129)	loss 3.2823 (3.1452)	grad_norm 1.2588 (2.4265/0.9619)	mem 24308MB
[2025-01-19 01:20:42 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][100/312]	eta 0:02:13 lr 0.000785	time 0.6566 (0.6318)	model_time 0.6564 (0.6115)	loss 3.2013 (3.1280)	grad_norm 2.4567 (2.4606/0.9515)	mem 24308MB
[2025-01-19 01:20:48 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][110/312]	eta 0:02:06 lr 0.000784	time 0.5852 (0.6283)	model_time 0.5850 (0.6098)	loss 3.2117 (3.1132)	grad_norm 1.9553 (2.4388/0.9901)	mem 24308MB
[2025-01-19 01:20:54 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][120/312]	eta 0:02:00 lr 0.000784	time 0.5916 (0.6268)	model_time 0.5912 (0.6098)	loss 3.5717 (3.1046)	grad_norm 4.8374 (2.4615/1.0124)	mem 24308MB
[2025-01-19 01:21:00 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][130/312]	eta 0:01:53 lr 0.000783	time 0.5744 (0.6261)	model_time 0.5742 (0.6103)	loss 3.3001 (3.0800)	grad_norm 3.5525 (2.4556/0.9959)	mem 24308MB
[2025-01-19 01:21:07 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][140/312]	eta 0:01:47 lr 0.000783	time 0.5765 (0.6251)	model_time 0.5764 (0.6105)	loss 3.6739 (3.0574)	grad_norm 2.2282 (2.4390/0.9698)	mem 24308MB
[2025-01-19 01:21:13 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][150/312]	eta 0:01:41 lr 0.000782	time 0.5791 (0.6239)	model_time 0.5789 (0.6102)	loss 2.7163 (3.0621)	grad_norm 1.1789 (2.4567/0.9830)	mem 24308MB
[2025-01-19 01:21:19 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][160/312]	eta 0:01:35 lr 0.000782	time 0.6572 (0.6254)	model_time 0.6567 (0.6125)	loss 2.9348 (3.0746)	grad_norm 4.7954 (2.4530/0.9884)	mem 24308MB
[2025-01-19 01:21:25 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][170/312]	eta 0:01:28 lr 0.000781	time 0.5717 (0.6243)	model_time 0.5712 (0.6122)	loss 3.2828 (3.0726)	grad_norm 1.2243 (2.4121/0.9847)	mem 24308MB
[2025-01-19 01:21:31 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][180/312]	eta 0:01:22 lr 0.000781	time 0.5748 (0.6233)	model_time 0.5746 (0.6118)	loss 3.4224 (3.0786)	grad_norm 0.8836 (2.3740/1.0042)	mem 24308MB
[2025-01-19 01:21:37 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][190/312]	eta 0:01:15 lr 0.000780	time 0.5920 (0.6221)	model_time 0.5915 (0.6112)	loss 3.3548 (3.0693)	grad_norm 2.5826 (2.3932/0.9940)	mem 24308MB
[2025-01-19 01:21:44 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][200/312]	eta 0:01:09 lr 0.000780	time 0.5858 (0.6225)	model_time 0.5856 (0.6121)	loss 2.0655 (3.0679)	grad_norm 1.7565 (2.3635/0.9945)	mem 24308MB
[2025-01-19 01:21:50 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][210/312]	eta 0:01:03 lr 0.000779	time 0.6291 (0.6216)	model_time 0.6289 (0.6117)	loss 2.8558 (3.0640)	grad_norm 1.3872 (2.3461/0.9901)	mem 24308MB
[2025-01-19 01:21:56 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][220/312]	eta 0:00:57 lr 0.000779	time 0.5849 (0.6205)	model_time 0.5847 (0.6110)	loss 3.0854 (3.0671)	grad_norm 1.0763 (2.3853/1.0564)	mem 24308MB
[2025-01-19 01:22:02 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][230/312]	eta 0:00:50 lr 0.000778	time 0.5783 (0.6195)	model_time 0.5778 (0.6104)	loss 2.5144 (3.0591)	grad_norm 4.5504 (2.4183/1.0644)	mem 24308MB
[2025-01-19 01:22:08 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][240/312]	eta 0:00:44 lr 0.000778	time 0.5772 (0.6186)	model_time 0.5770 (0.6099)	loss 2.2534 (3.0556)	grad_norm 3.9672 (2.4281/1.0855)	mem 24308MB
[2025-01-19 01:22:14 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][250/312]	eta 0:00:38 lr 0.000777	time 0.6720 (0.6180)	model_time 0.6718 (0.6096)	loss 2.0216 (3.0578)	grad_norm 1.4994 (2.4093/1.0717)	mem 24308MB
[2025-01-19 01:22:20 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][260/312]	eta 0:00:32 lr 0.000777	time 0.5785 (0.6180)	model_time 0.5781 (0.6099)	loss 3.1960 (3.0502)	grad_norm 2.1789 (2.4071/1.0626)	mem 24308MB
[2025-01-19 01:22:26 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][270/312]	eta 0:00:25 lr 0.000776	time 0.6205 (0.6176)	model_time 0.6200 (0.6098)	loss 3.4466 (3.0489)	grad_norm 3.2694 (2.3957/1.0558)	mem 24308MB
[2025-01-19 01:22:32 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][280/312]	eta 0:00:19 lr 0.000776	time 0.6554 (0.6185)	model_time 0.6549 (0.6109)	loss 2.4201 (3.0490)	grad_norm 2.1612 (2.3926/1.0404)	mem 24308MB
[2025-01-19 01:22:38 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][290/312]	eta 0:00:13 lr 0.000775	time 0.6599 (0.6186)	model_time 0.6597 (0.6113)	loss 2.8885 (3.0481)	grad_norm 2.3240 (2.3804/1.0295)	mem 24308MB
[2025-01-19 01:22:44 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][300/312]	eta 0:00:07 lr 0.000775	time 0.5796 (0.6179)	model_time 0.5795 (0.6108)	loss 3.1440 (3.0544)	grad_norm 2.9382 (2.3646/1.0228)	mem 24308MB
[2025-01-19 01:22:50 internimage_s_1k_224] (main.py 510): INFO Train: [214/300][310/312]	eta 0:00:01 lr 0.000774	time 0.6452 (0.6170)	model_time 0.6451 (0.6102)	loss 2.7878 (3.0532)	grad_norm 3.9968 (2.4012/1.0640)	mem 24308MB
[2025-01-19 01:22:51 internimage_s_1k_224] (main.py 519): INFO EPOCH 214 training takes 0:03:12
[2025-01-19 01:22:51 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_214.pth saving......
[2025-01-19 01:22:53 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_214.pth saved !!!
[2025-01-19 01:23:01 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.907 (7.907)	Loss 0.7395 (0.7395)	Acc@1 83.984 (83.984)	Acc@5 97.437 (97.437)	Mem 24308MB
[2025-01-19 01:23:04 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.044)	Loss 0.9624 (0.8455)	Acc@1 78.198 (82.091)	Acc@5 95.239 (96.214)	Mem 24308MB
[2025-01-19 01:23:05 internimage_s_1k_224] (main.py 575): INFO [Epoch:214] * Acc@1 81.988 Acc@5 96.201
[2025-01-19 01:23:05 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.0%
[2025-01-19 01:23:05 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.21%
[2025-01-19 01:23:14 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.063 (9.063)	Loss 0.7063 (0.7063)	Acc@1 85.083 (85.083)	Acc@5 97.705 (97.705)	Mem 24308MB
[2025-01-19 01:23:18 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.224)	Loss 0.9328 (0.7977)	Acc@1 78.223 (82.504)	Acc@5 95.337 (96.356)	Mem 24308MB
[2025-01-19 01:23:18 internimage_s_1k_224] (main.py 575): INFO [Epoch:214] * Acc@1 82.360 Acc@5 96.377
[2025-01-19 01:23:18 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.4%
[2025-01-19 01:23:18 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:23:21 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:23:21 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.36%
[2025-01-19 01:23:23 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][0/312]	eta 0:10:54 lr 0.000774	time 2.0962 (2.0962)	model_time 0.6020 (0.6020)	loss 2.5156 (2.5156)	grad_norm 1.7065 (1.7065/0.0000)	mem 24308MB
[2025-01-19 01:23:29 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][10/312]	eta 0:03:46 lr 0.000773	time 0.6032 (0.7490)	model_time 0.6031 (0.6129)	loss 3.1429 (2.7863)	grad_norm 3.1498 (1.7248/0.6088)	mem 24308MB
[2025-01-19 01:23:35 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][20/312]	eta 0:03:16 lr 0.000773	time 0.5906 (0.6742)	model_time 0.5904 (0.6027)	loss 3.9024 (2.9792)	grad_norm 3.5005 (1.9200/0.6796)	mem 24308MB
[2025-01-19 01:23:41 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][30/312]	eta 0:03:03 lr 0.000772	time 0.6191 (0.6491)	model_time 0.6189 (0.6006)	loss 2.4301 (2.8618)	grad_norm 2.0253 (2.0520/0.9598)	mem 24308MB
[2025-01-19 01:23:47 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][40/312]	eta 0:02:53 lr 0.000772	time 0.5692 (0.6363)	model_time 0.5689 (0.5996)	loss 2.4458 (2.8829)	grad_norm 2.9354 (2.4198/1.3234)	mem 24308MB
[2025-01-19 01:23:53 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][50/312]	eta 0:02:45 lr 0.000771	time 0.5759 (0.6312)	model_time 0.5757 (0.6016)	loss 2.3309 (2.9345)	grad_norm 2.1389 (2.3426/1.2142)	mem 24308MB
[2025-01-19 01:23:59 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][60/312]	eta 0:02:37 lr 0.000771	time 0.6040 (0.6261)	model_time 0.6038 (0.6012)	loss 2.1447 (2.9360)	grad_norm 3.5886 (2.2630/1.1627)	mem 24308MB
[2025-01-19 01:24:05 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][70/312]	eta 0:02:30 lr 0.000770	time 0.5795 (0.6235)	model_time 0.5794 (0.6021)	loss 2.5253 (2.9514)	grad_norm 6.1091 (2.2987/1.2205)	mem 24308MB
[2025-01-19 01:24:11 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][80/312]	eta 0:02:24 lr 0.000770	time 0.5895 (0.6231)	model_time 0.5894 (0.6043)	loss 3.7320 (2.9483)	grad_norm 1.5752 (2.3616/1.2493)	mem 24308MB
[2025-01-19 01:24:17 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][90/312]	eta 0:02:18 lr 0.000769	time 0.6219 (0.6234)	model_time 0.6217 (0.6066)	loss 2.8355 (2.9676)	grad_norm 1.6205 (2.4351/1.2471)	mem 24308MB
[2025-01-19 01:24:24 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][100/312]	eta 0:02:12 lr 0.000769	time 0.5744 (0.6240)	model_time 0.5742 (0.6088)	loss 3.5475 (2.9846)	grad_norm 2.5887 (2.5143/1.2458)	mem 24308MB
[2025-01-19 01:24:30 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][110/312]	eta 0:02:05 lr 0.000768	time 0.5951 (0.6217)	model_time 0.5946 (0.6079)	loss 3.0999 (3.0036)	grad_norm 2.1500 (2.5336/1.2282)	mem 24308MB
[2025-01-19 01:24:36 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][120/312]	eta 0:01:59 lr 0.000768	time 0.5811 (0.6215)	model_time 0.5809 (0.6088)	loss 2.3694 (2.9755)	grad_norm 1.8410 (2.5307/1.2022)	mem 24308MB
[2025-01-19 01:24:42 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][130/312]	eta 0:01:52 lr 0.000767	time 0.5735 (0.6198)	model_time 0.5733 (0.6081)	loss 3.1854 (2.9824)	grad_norm 1.9110 (2.5157/1.1923)	mem 24308MB
[2025-01-19 01:24:48 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][140/312]	eta 0:01:46 lr 0.000767	time 0.6830 (0.6182)	model_time 0.6828 (0.6072)	loss 2.9896 (2.9874)	grad_norm 2.6539 (2.4709/1.1703)	mem 24308MB
[2025-01-19 01:24:54 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][150/312]	eta 0:01:39 lr 0.000766	time 0.5935 (0.6169)	model_time 0.5933 (0.6066)	loss 3.3774 (2.9845)	grad_norm 2.0305 (2.4669/1.1410)	mem 24308MB
[2025-01-19 01:25:00 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][160/312]	eta 0:01:33 lr 0.000766	time 0.5872 (0.6155)	model_time 0.5870 (0.6059)	loss 3.2063 (2.9822)	grad_norm 2.1749 (2.4397/1.1206)	mem 24308MB
[2025-01-19 01:25:06 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][170/312]	eta 0:01:27 lr 0.000765	time 0.5852 (0.6145)	model_time 0.5850 (0.6054)	loss 3.5289 (2.9661)	grad_norm 2.4313 (2.4924/1.1609)	mem 24308MB
[2025-01-19 01:25:12 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][180/312]	eta 0:01:21 lr 0.000765	time 0.5783 (0.6140)	model_time 0.5781 (0.6053)	loss 2.6695 (2.9640)	grad_norm 4.1795 (2.5098/1.1649)	mem 24308MB
[2025-01-19 01:25:18 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][190/312]	eta 0:01:14 lr 0.000764	time 0.5724 (0.6137)	model_time 0.5722 (0.6055)	loss 2.7529 (2.9623)	grad_norm 3.2970 (2.5389/1.1564)	mem 24308MB
[2025-01-19 01:25:24 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][200/312]	eta 0:01:08 lr 0.000764	time 0.5785 (0.6133)	model_time 0.5783 (0.6055)	loss 3.7118 (2.9712)	grad_norm 1.4210 (2.5418/1.1560)	mem 24308MB
[2025-01-19 01:25:30 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][210/312]	eta 0:01:02 lr 0.000763	time 0.8165 (0.6148)	model_time 0.8164 (0.6073)	loss 3.4816 (2.9843)	grad_norm 1.9782 (2.5044/1.1465)	mem 24308MB
[2025-01-19 01:25:36 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][220/312]	eta 0:00:56 lr 0.000763	time 0.5638 (0.6149)	model_time 0.5637 (0.6077)	loss 2.9975 (2.9816)	grad_norm 2.6212 (2.4805/1.1295)	mem 24308MB
[2025-01-19 01:25:42 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][230/312]	eta 0:00:50 lr 0.000762	time 0.7144 (0.6142)	model_time 0.7142 (0.6073)	loss 3.2132 (2.9788)	grad_norm 3.4656 (2.4783/1.1102)	mem 24308MB
[2025-01-19 01:25:49 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][240/312]	eta 0:00:44 lr 0.000762	time 0.5805 (0.6147)	model_time 0.5803 (0.6081)	loss 2.1131 (2.9698)	grad_norm 2.2110 (2.4574/1.1005)	mem 24308MB
[2025-01-19 01:25:55 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][250/312]	eta 0:00:38 lr 0.000761	time 0.5702 (0.6146)	model_time 0.5697 (0.6083)	loss 3.4985 (2.9737)	grad_norm 1.9612 (2.4413/1.0898)	mem 24308MB
[2025-01-19 01:26:01 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][260/312]	eta 0:00:31 lr 0.000761	time 0.5982 (0.6137)	model_time 0.5980 (0.6077)	loss 2.8584 (2.9735)	grad_norm 1.7402 (2.4414/1.1053)	mem 24308MB
[2025-01-19 01:26:07 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][270/312]	eta 0:00:25 lr 0.000760	time 0.5792 (0.6134)	model_time 0.5788 (0.6075)	loss 2.0188 (2.9807)	grad_norm 1.1815 (2.4569/1.1109)	mem 24308MB
[2025-01-19 01:26:13 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][280/312]	eta 0:00:19 lr 0.000760	time 0.5803 (0.6129)	model_time 0.5801 (0.6072)	loss 3.2011 (2.9859)	grad_norm 3.3430 (2.4486/1.1058)	mem 24308MB
[2025-01-19 01:26:19 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][290/312]	eta 0:00:13 lr 0.000759	time 0.5893 (0.6122)	model_time 0.5891 (0.6067)	loss 3.0337 (2.9861)	grad_norm 2.0605 (2.4345/1.0935)	mem 24308MB
[2025-01-19 01:26:25 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][300/312]	eta 0:00:07 lr 0.000759	time 0.5703 (0.6120)	model_time 0.5702 (0.6066)	loss 2.2736 (2.9789)	grad_norm 2.3316 (2.4109/1.0879)	mem 24308MB
[2025-01-19 01:26:31 internimage_s_1k_224] (main.py 510): INFO Train: [215/300][310/312]	eta 0:00:01 lr 0.000758	time 0.5726 (0.6113)	model_time 0.5725 (0.6061)	loss 3.0993 (2.9834)	grad_norm 1.5580 (2.4096/1.0840)	mem 24308MB
[2025-01-19 01:26:31 internimage_s_1k_224] (main.py 519): INFO EPOCH 215 training takes 0:03:10
[2025-01-19 01:26:31 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_215.pth saving......
[2025-01-19 01:26:33 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_215.pth saved !!!
[2025-01-19 01:26:41 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.911 (7.911)	Loss 0.7433 (0.7433)	Acc@1 84.937 (84.937)	Acc@5 97.192 (97.192)	Mem 24308MB
[2025-01-19 01:26:45 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.037)	Loss 0.9412 (0.8417)	Acc@1 78.711 (82.282)	Acc@5 95.508 (96.171)	Mem 24308MB
[2025-01-19 01:26:45 internimage_s_1k_224] (main.py 575): INFO [Epoch:215] * Acc@1 82.162 Acc@5 96.185
[2025-01-19 01:26:45 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.2%
[2025-01-19 01:26:45 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.21%
[2025-01-19 01:26:54 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.117 (9.117)	Loss 0.7061 (0.7061)	Acc@1 85.181 (85.181)	Acc@5 97.729 (97.729)	Mem 24308MB
[2025-01-19 01:26:58 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.227)	Loss 0.9315 (0.7971)	Acc@1 78.271 (82.540)	Acc@5 95.386 (96.367)	Mem 24308MB
[2025-01-19 01:26:58 internimage_s_1k_224] (main.py 575): INFO [Epoch:215] * Acc@1 82.392 Acc@5 96.385
[2025-01-19 01:26:58 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.4%
[2025-01-19 01:26:59 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:27:01 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:27:01 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.39%
[2025-01-19 01:27:03 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][0/312]	eta 0:11:03 lr 0.000758	time 2.1259 (2.1259)	model_time 0.5896 (0.5896)	loss 3.5584 (3.5584)	grad_norm 1.5841 (1.5841/0.0000)	mem 24308MB
[2025-01-19 01:27:09 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][10/312]	eta 0:03:45 lr 0.000757	time 0.5813 (0.7457)	model_time 0.5811 (0.6057)	loss 3.2753 (2.9094)	grad_norm 3.5870 (2.0239/0.7395)	mem 24308MB
[2025-01-19 01:27:15 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][20/312]	eta 0:03:18 lr 0.000757	time 0.6706 (0.6811)	model_time 0.6704 (0.6076)	loss 2.7268 (3.0223)	grad_norm 2.2902 (2.1070/0.7040)	mem 24308MB
[2025-01-19 01:27:21 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][30/312]	eta 0:03:08 lr 0.000756	time 0.5880 (0.6684)	model_time 0.5878 (0.6185)	loss 2.6096 (2.9759)	grad_norm 1.6902 (2.3392/0.9951)	mem 24308MB
[2025-01-19 01:27:27 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][40/312]	eta 0:02:57 lr 0.000756	time 0.6721 (0.6516)	model_time 0.6717 (0.6138)	loss 3.1659 (2.9770)	grad_norm 3.3301 (2.5555/1.1520)	mem 24308MB
[2025-01-19 01:27:33 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][50/312]	eta 0:02:48 lr 0.000755	time 0.6820 (0.6420)	model_time 0.6816 (0.6115)	loss 3.3406 (3.0012)	grad_norm 3.9209 (2.6341/1.1684)	mem 24308MB
[2025-01-19 01:27:40 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][60/312]	eta 0:02:40 lr 0.000755	time 0.5896 (0.6372)	model_time 0.5892 (0.6117)	loss 2.4530 (2.9664)	grad_norm 2.5071 (2.5975/1.1367)	mem 24308MB
[2025-01-19 01:27:45 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][70/312]	eta 0:02:32 lr 0.000754	time 0.6069 (0.6299)	model_time 0.6067 (0.6078)	loss 2.1800 (2.9762)	grad_norm 1.8066 (2.7285/1.2269)	mem 24308MB
[2025-01-19 01:27:51 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][80/312]	eta 0:02:25 lr 0.000754	time 0.5884 (0.6271)	model_time 0.5882 (0.6078)	loss 3.3386 (2.9848)	grad_norm 3.6025 (2.7427/1.2121)	mem 24308MB
[2025-01-19 01:27:58 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][90/312]	eta 0:02:18 lr 0.000753	time 0.5643 (0.6252)	model_time 0.5642 (0.6080)	loss 3.5676 (2.9688)	grad_norm 2.0253 (2.7191/1.1644)	mem 24308MB
[2025-01-19 01:28:04 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][100/312]	eta 0:02:11 lr 0.000753	time 0.5933 (0.6222)	model_time 0.5929 (0.6067)	loss 3.0470 (2.9556)	grad_norm 1.4662 (2.6176/1.1538)	mem 24308MB
[2025-01-19 01:28:10 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][110/312]	eta 0:02:05 lr 0.000752	time 0.6713 (0.6207)	model_time 0.6711 (0.6065)	loss 3.5078 (2.9811)	grad_norm 3.7577 (2.5580/1.1378)	mem 24308MB
[2025-01-19 01:28:16 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][120/312]	eta 0:01:58 lr 0.000752	time 0.6760 (0.6191)	model_time 0.6755 (0.6061)	loss 3.2421 (2.9691)	grad_norm 1.9665 (2.6967/1.2547)	mem 24308MB
[2025-01-19 01:28:22 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][130/312]	eta 0:01:52 lr 0.000751	time 0.5826 (0.6180)	model_time 0.5822 (0.6059)	loss 2.9266 (2.9729)	grad_norm 2.6914 (2.6630/1.2414)	mem 24308MB
[2025-01-19 01:28:28 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][140/312]	eta 0:01:46 lr 0.000751	time 0.7163 (0.6174)	model_time 0.7158 (0.6061)	loss 2.0380 (2.9546)	grad_norm 1.8192 (2.5708/1.2436)	mem 24308MB
[2025-01-19 01:28:34 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][150/312]	eta 0:01:40 lr 0.000750	time 0.5788 (0.6176)	model_time 0.5784 (0.6071)	loss 2.6974 (2.9652)	grad_norm 1.0597 (2.4898/1.2404)	mem 24308MB
[2025-01-19 01:28:40 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][160/312]	eta 0:01:33 lr 0.000750	time 0.6045 (0.6164)	model_time 0.6040 (0.6065)	loss 2.1102 (2.9498)	grad_norm 1.6391 (2.4569/1.2160)	mem 24308MB
[2025-01-19 01:28:46 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][170/312]	eta 0:01:27 lr 0.000749	time 0.6840 (0.6167)	model_time 0.6835 (0.6074)	loss 2.9411 (2.9578)	grad_norm 4.0072 (2.4500/1.2048)	mem 24308MB
[2025-01-19 01:28:52 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][180/312]	eta 0:01:21 lr 0.000749	time 0.6518 (0.6167)	model_time 0.6516 (0.6078)	loss 2.9534 (2.9710)	grad_norm 1.5493 (2.4244/1.1849)	mem 24308MB
[2025-01-19 01:28:58 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][190/312]	eta 0:01:15 lr 0.000748	time 0.5939 (0.6151)	model_time 0.5934 (0.6067)	loss 3.0342 (2.9748)	grad_norm 1.9041 (2.3974/1.1630)	mem 24308MB
[2025-01-19 01:29:04 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][200/312]	eta 0:01:08 lr 0.000748	time 0.5788 (0.6150)	model_time 0.5783 (0.6069)	loss 2.3851 (2.9842)	grad_norm 1.9519 (2.3947/1.1490)	mem 24308MB
[2025-01-19 01:29:10 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][210/312]	eta 0:01:02 lr 0.000747	time 0.5634 (0.6144)	model_time 0.5630 (0.6067)	loss 3.6409 (2.9780)	grad_norm 1.5033 (2.3721/1.1324)	mem 24308MB
[2025-01-19 01:29:16 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][220/312]	eta 0:00:56 lr 0.000747	time 0.5760 (0.6135)	model_time 0.5758 (0.6062)	loss 2.2458 (2.9787)	grad_norm 2.7501 (2.3784/1.1190)	mem 24308MB
[2025-01-19 01:29:22 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][230/312]	eta 0:00:50 lr 0.000746	time 0.5774 (0.6132)	model_time 0.5770 (0.6062)	loss 2.9000 (2.9831)	grad_norm 3.5393 (2.4044/1.1152)	mem 24308MB
[2025-01-19 01:29:28 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][240/312]	eta 0:00:44 lr 0.000746	time 0.6734 (0.6131)	model_time 0.6729 (0.6063)	loss 3.3645 (2.9817)	grad_norm 0.7738 (2.4381/1.1622)	mem 24308MB
[2025-01-19 01:29:35 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][250/312]	eta 0:00:38 lr 0.000745	time 0.7352 (0.6131)	model_time 0.7351 (0.6066)	loss 3.4036 (2.9870)	grad_norm 3.4010 (2.4491/1.1485)	mem 24308MB
[2025-01-19 01:29:41 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][260/312]	eta 0:00:31 lr 0.000745	time 0.5876 (0.6126)	model_time 0.5874 (0.6064)	loss 3.3420 (2.9845)	grad_norm 1.7211 (2.4680/1.1553)	mem 24308MB
[2025-01-19 01:29:47 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][270/312]	eta 0:00:25 lr 0.000744	time 0.6637 (0.6138)	model_time 0.6633 (0.6078)	loss 2.2025 (2.9912)	grad_norm 2.7193 (2.4471/1.1437)	mem 24308MB
[2025-01-19 01:29:53 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][280/312]	eta 0:00:19 lr 0.000744	time 0.5981 (0.6132)	model_time 0.5977 (0.6073)	loss 3.5067 (2.9988)	grad_norm 2.2275 (2.4422/1.1397)	mem 24308MB
[2025-01-19 01:29:59 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][290/312]	eta 0:00:13 lr 0.000743	time 0.8873 (0.6137)	model_time 0.8871 (0.6081)	loss 3.0529 (3.0024)	grad_norm 3.1466 (2.4428/1.1325)	mem 24308MB
[2025-01-19 01:30:05 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][300/312]	eta 0:00:07 lr 0.000743	time 0.5633 (0.6132)	model_time 0.5631 (0.6078)	loss 3.0163 (2.9993)	grad_norm 1.6446 (2.4603/1.1486)	mem 24308MB
[2025-01-19 01:30:11 internimage_s_1k_224] (main.py 510): INFO Train: [216/300][310/312]	eta 0:00:01 lr 0.000742	time 0.5658 (0.6122)	model_time 0.5657 (0.6069)	loss 3.0564 (3.0060)	grad_norm 1.7969 (2.4890/1.1594)	mem 24308MB
[2025-01-19 01:30:12 internimage_s_1k_224] (main.py 519): INFO EPOCH 216 training takes 0:03:10
[2025-01-19 01:30:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_216.pth saving......
[2025-01-19 01:30:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_216.pth saved !!!
[2025-01-19 01:30:26 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 12.573 (12.573)	Loss 0.7502 (0.7502)	Acc@1 85.010 (85.010)	Acc@5 97.681 (97.681)	Mem 24308MB
[2025-01-19 01:30:34 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.819)	Loss 0.9758 (0.8536)	Acc@1 79.028 (82.473)	Acc@5 95.459 (96.313)	Mem 24308MB
[2025-01-19 01:30:34 internimage_s_1k_224] (main.py 575): INFO [Epoch:216] * Acc@1 82.418 Acc@5 96.329
[2025-01-19 01:30:34 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.4%
[2025-01-19 01:30:34 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 01:30:36 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 01:30:36 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.42%
[2025-01-19 01:30:51 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.991 (14.991)	Loss 0.7059 (0.7059)	Acc@1 85.181 (85.181)	Acc@5 97.729 (97.729)	Mem 24308MB
[2025-01-19 01:30:59 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (2.127)	Loss 0.9303 (0.7965)	Acc@1 78.345 (82.593)	Acc@5 95.410 (96.378)	Mem 24308MB
[2025-01-19 01:30:59 internimage_s_1k_224] (main.py 575): INFO [Epoch:216] * Acc@1 82.450 Acc@5 96.395
[2025-01-19 01:30:59 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.4%
[2025-01-19 01:30:59 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:31:01 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:31:01 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.45%
[2025-01-19 01:31:03 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][0/312]	eta 0:10:46 lr 0.000742	time 2.0715 (2.0715)	model_time 0.5989 (0.5989)	loss 3.4315 (3.4315)	grad_norm 3.3105 (3.3105/0.0000)	mem 24308MB
[2025-01-19 01:31:09 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][10/312]	eta 0:03:42 lr 0.000741	time 0.5702 (0.7352)	model_time 0.5696 (0.6010)	loss 3.6508 (3.0493)	grad_norm 1.4065 (1.9551/0.6126)	mem 24308MB
[2025-01-19 01:31:15 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][20/312]	eta 0:03:15 lr 0.000741	time 0.5831 (0.6709)	model_time 0.5829 (0.6004)	loss 2.4288 (2.8978)	grad_norm 3.2887 (2.0441/0.7682)	mem 24308MB
[2025-01-19 01:31:21 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][30/312]	eta 0:03:02 lr 0.000740	time 0.5676 (0.6478)	model_time 0.5671 (0.6000)	loss 3.7478 (2.9650)	grad_norm 3.5680 (2.0661/0.7470)	mem 24308MB
[2025-01-19 01:31:27 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][40/312]	eta 0:02:52 lr 0.000740	time 0.5889 (0.6360)	model_time 0.5879 (0.5997)	loss 3.6850 (2.9330)	grad_norm 1.8930 (2.2108/0.8665)	mem 24308MB
[2025-01-19 01:31:34 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][50/312]	eta 0:02:45 lr 0.000739	time 0.5925 (0.6319)	model_time 0.5923 (0.6026)	loss 3.1100 (2.9661)	grad_norm 1.6604 (2.1905/0.8341)	mem 24308MB
[2025-01-19 01:31:40 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][60/312]	eta 0:02:39 lr 0.000739	time 0.5752 (0.6316)	model_time 0.5747 (0.6071)	loss 3.0878 (2.9695)	grad_norm 2.1206 (2.2596/0.8642)	mem 24308MB
[2025-01-19 01:31:46 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][70/312]	eta 0:02:31 lr 0.000738	time 0.5875 (0.6274)	model_time 0.5873 (0.6063)	loss 3.4607 (2.9461)	grad_norm 3.8961 (2.2449/0.8347)	mem 24308MB
[2025-01-19 01:31:52 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][80/312]	eta 0:02:26 lr 0.000738	time 0.6640 (0.6298)	model_time 0.6638 (0.6113)	loss 2.3330 (2.9367)	grad_norm 1.2388 (2.2852/0.8600)	mem 24308MB
[2025-01-19 01:31:58 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][90/312]	eta 0:02:18 lr 0.000737	time 0.5698 (0.6258)	model_time 0.5696 (0.6093)	loss 2.2309 (2.9397)	grad_norm 1.9026 (2.2996/0.8573)	mem 24308MB
[2025-01-19 01:32:04 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][100/312]	eta 0:02:12 lr 0.000737	time 0.6703 (0.6243)	model_time 0.6698 (0.6094)	loss 3.3329 (2.9755)	grad_norm 4.2412 (2.2866/0.8867)	mem 24308MB
[2025-01-19 01:32:10 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][110/312]	eta 0:02:05 lr 0.000736	time 0.6620 (0.6226)	model_time 0.6617 (0.6090)	loss 4.0242 (2.9927)	grad_norm 5.0387 (2.3592/0.9273)	mem 24308MB
[2025-01-19 01:32:16 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][120/312]	eta 0:01:59 lr 0.000736	time 0.5696 (0.6205)	model_time 0.5694 (0.6079)	loss 2.8484 (2.9923)	grad_norm 3.2782 (2.3647/0.9436)	mem 24308MB
[2025-01-19 01:32:23 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][130/312]	eta 0:01:52 lr 0.000735	time 0.6820 (0.6196)	model_time 0.6815 (0.6080)	loss 3.6646 (2.9925)	grad_norm 1.0476 (2.3455/0.9390)	mem 24308MB
[2025-01-19 01:32:28 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][140/312]	eta 0:01:46 lr 0.000735	time 0.5758 (0.6176)	model_time 0.5756 (0.6068)	loss 2.5719 (2.9876)	grad_norm 1.9349 (2.3104/0.9180)	mem 24308MB
[2025-01-19 01:32:34 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][150/312]	eta 0:01:39 lr 0.000734	time 0.5813 (0.6165)	model_time 0.5811 (0.6064)	loss 2.5590 (2.9653)	grad_norm 3.3458 (2.2930/0.9032)	mem 24308MB
[2025-01-19 01:32:40 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][160/312]	eta 0:01:33 lr 0.000734	time 0.5749 (0.6156)	model_time 0.5747 (0.6060)	loss 2.1775 (2.9610)	grad_norm 2.7136 (2.2939/0.9030)	mem 24308MB
[2025-01-19 01:32:47 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][170/312]	eta 0:01:27 lr 0.000733	time 0.6320 (0.6150)	model_time 0.6315 (0.6060)	loss 3.1216 (2.9572)	grad_norm 1.8087 (2.2875/0.8950)	mem 24308MB
[2025-01-19 01:32:53 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][180/312]	eta 0:01:21 lr 0.000733	time 0.5805 (0.6151)	model_time 0.5804 (0.6066)	loss 2.7076 (2.9653)	grad_norm 1.4991 (2.2718/0.8900)	mem 24308MB
[2025-01-19 01:32:59 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][190/312]	eta 0:01:14 lr 0.000732	time 0.5878 (0.6142)	model_time 0.5874 (0.6062)	loss 1.8504 (2.9734)	grad_norm 2.0683 (2.2677/0.8880)	mem 24308MB
[2025-01-19 01:33:05 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][200/312]	eta 0:01:08 lr 0.000732	time 0.5893 (0.6157)	model_time 0.5892 (0.6080)	loss 3.0653 (2.9806)	grad_norm 1.8825 (2.2458/0.8864)	mem 24308MB
[2025-01-19 01:33:11 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][210/312]	eta 0:01:02 lr 0.000731	time 0.5833 (0.6149)	model_time 0.5832 (0.6076)	loss 3.3284 (2.9809)	grad_norm 4.0415 (2.2419/0.8887)	mem 24308MB
[2025-01-19 01:33:17 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][220/312]	eta 0:00:56 lr 0.000731	time 0.6602 (0.6148)	model_time 0.6598 (0.6078)	loss 3.6601 (2.9808)	grad_norm 2.1949 (2.2423/0.8799)	mem 24308MB
[2025-01-19 01:33:23 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][230/312]	eta 0:00:50 lr 0.000730	time 0.5797 (0.6144)	model_time 0.5795 (0.6076)	loss 3.3378 (2.9718)	grad_norm 3.6312 (2.2331/0.8725)	mem 24308MB
[2025-01-19 01:33:29 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][240/312]	eta 0:00:44 lr 0.000730	time 0.5808 (0.6140)	model_time 0.5805 (0.6075)	loss 2.9952 (2.9743)	grad_norm 1.8210 (2.2461/0.8886)	mem 24308MB
[2025-01-19 01:33:35 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][250/312]	eta 0:00:38 lr 0.000729	time 0.6903 (0.6133)	model_time 0.6898 (0.6071)	loss 3.3252 (2.9739)	grad_norm 1.1450 (2.2403/0.8916)	mem 24308MB
[2025-01-19 01:33:41 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][260/312]	eta 0:00:31 lr 0.000729	time 0.5851 (0.6127)	model_time 0.5846 (0.6067)	loss 2.8239 (2.9766)	grad_norm 3.9424 (2.2397/0.8970)	mem 24308MB
[2025-01-19 01:33:47 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][270/312]	eta 0:00:25 lr 0.000728	time 0.5756 (0.6119)	model_time 0.5754 (0.6061)	loss 1.9646 (2.9750)	grad_norm 3.0004 (2.2479/0.8917)	mem 24308MB
[2025-01-19 01:33:53 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][280/312]	eta 0:00:19 lr 0.000728	time 0.5797 (0.6116)	model_time 0.5796 (0.6060)	loss 3.2221 (2.9807)	grad_norm 2.0289 (2.2500/0.8966)	mem 24308MB
[2025-01-19 01:33:59 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][290/312]	eta 0:00:13 lr 0.000727	time 0.5981 (0.6117)	model_time 0.5976 (0.6062)	loss 2.9655 (2.9735)	grad_norm 1.6443 (2.2466/0.8873)	mem 24308MB
[2025-01-19 01:34:05 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][300/312]	eta 0:00:07 lr 0.000727	time 0.5656 (0.6112)	model_time 0.5655 (0.6059)	loss 3.2821 (2.9771)	grad_norm 1.6526 (2.2486/0.8964)	mem 24308MB
[2025-01-19 01:34:11 internimage_s_1k_224] (main.py 510): INFO Train: [217/300][310/312]	eta 0:00:01 lr 0.000726	time 0.5690 (0.6111)	model_time 0.5689 (0.6060)	loss 3.5228 (2.9784)	grad_norm 2.8328 (2.2685/0.9078)	mem 24308MB
[2025-01-19 01:34:12 internimage_s_1k_224] (main.py 519): INFO EPOCH 217 training takes 0:03:10
[2025-01-19 01:34:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_217.pth saving......
[2025-01-19 01:34:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_217.pth saved !!!
[2025-01-19 01:34:22 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.778 (7.778)	Loss 0.7463 (0.7463)	Acc@1 84.668 (84.668)	Acc@5 97.339 (97.339)	Mem 24308MB
[2025-01-19 01:34:26 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.047)	Loss 0.9749 (0.8388)	Acc@1 78.442 (82.369)	Acc@5 95.166 (96.260)	Mem 24308MB
[2025-01-19 01:34:26 internimage_s_1k_224] (main.py 575): INFO [Epoch:217] * Acc@1 82.214 Acc@5 96.283
[2025-01-19 01:34:26 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.2%
[2025-01-19 01:34:26 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.42%
[2025-01-19 01:34:35 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.102 (9.102)	Loss 0.7056 (0.7056)	Acc@1 85.181 (85.181)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 01:34:39 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.230)	Loss 0.9291 (0.7958)	Acc@1 78.369 (82.608)	Acc@5 95.435 (96.398)	Mem 24308MB
[2025-01-19 01:34:39 internimage_s_1k_224] (main.py 575): INFO [Epoch:217] * Acc@1 82.472 Acc@5 96.419
[2025-01-19 01:34:39 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.5%
[2025-01-19 01:34:39 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:34:42 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:34:42 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.47%
[2025-01-19 01:34:44 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][0/312]	eta 0:10:00 lr 0.000726	time 1.9255 (1.9255)	model_time 0.5929 (0.5929)	loss 2.6522 (2.6522)	grad_norm 1.0394 (1.0394/0.0000)	mem 24308MB
[2025-01-19 01:34:50 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][10/312]	eta 0:03:45 lr 0.000726	time 0.6541 (0.7482)	model_time 0.6539 (0.6267)	loss 3.0869 (2.9008)	grad_norm 1.8341 (2.1853/1.0958)	mem 24308MB
[2025-01-19 01:34:56 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][20/312]	eta 0:03:17 lr 0.000725	time 0.5816 (0.6777)	model_time 0.5815 (0.6139)	loss 3.0549 (3.0453)	grad_norm 3.8368 (2.2960/0.9112)	mem 24308MB
[2025-01-19 01:35:02 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][30/312]	eta 0:03:05 lr 0.000725	time 0.6182 (0.6571)	model_time 0.6178 (0.6137)	loss 2.0696 (2.9424)	grad_norm 1.3448 (2.3097/0.8721)	mem 24308MB
[2025-01-19 01:35:08 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][40/312]	eta 0:02:55 lr 0.000724	time 0.6016 (0.6449)	model_time 0.6015 (0.6121)	loss 2.5959 (2.9252)	grad_norm 3.0986 (2.3528/0.9003)	mem 24308MB
[2025-01-19 01:35:14 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][50/312]	eta 0:02:47 lr 0.000724	time 0.5956 (0.6377)	model_time 0.5954 (0.6112)	loss 2.3173 (2.9259)	grad_norm 1.5515 (2.3671/0.9140)	mem 24308MB
[2025-01-19 01:35:20 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][60/312]	eta 0:02:38 lr 0.000723	time 0.5786 (0.6307)	model_time 0.5782 (0.6085)	loss 2.1683 (2.9268)	grad_norm 2.4089 (2.3943/0.8906)	mem 24308MB
[2025-01-19 01:35:26 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][70/312]	eta 0:02:31 lr 0.000723	time 0.5821 (0.6273)	model_time 0.5819 (0.6082)	loss 3.3081 (2.9212)	grad_norm 5.6679 (2.4397/0.9746)	mem 24308MB
[2025-01-19 01:35:32 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][80/312]	eta 0:02:24 lr 0.000722	time 0.5846 (0.6240)	model_time 0.5841 (0.6072)	loss 3.1584 (2.9403)	grad_norm 6.3379 (2.6256/1.2375)	mem 24308MB
[2025-01-19 01:35:38 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][90/312]	eta 0:02:17 lr 0.000722	time 0.5837 (0.6216)	model_time 0.5835 (0.6066)	loss 2.5531 (2.9681)	grad_norm 2.1929 (2.6262/1.2132)	mem 24308MB
[2025-01-19 01:35:44 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][100/312]	eta 0:02:11 lr 0.000721	time 0.6029 (0.6197)	model_time 0.6025 (0.6062)	loss 2.3595 (2.9813)	grad_norm 1.4087 (2.5990/1.2356)	mem 24308MB
[2025-01-19 01:35:50 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][110/312]	eta 0:02:05 lr 0.000721	time 0.6612 (0.6195)	model_time 0.6608 (0.6071)	loss 3.3749 (2.9664)	grad_norm 1.6143 (2.5557/1.2180)	mem 24308MB
[2025-01-19 01:35:56 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][120/312]	eta 0:01:58 lr 0.000720	time 0.5705 (0.6187)	model_time 0.5701 (0.6073)	loss 2.9964 (2.9955)	grad_norm 1.6442 (2.4984/1.1948)	mem 24308MB
[2025-01-19 01:36:03 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][130/312]	eta 0:01:52 lr 0.000720	time 0.5808 (0.6209)	model_time 0.5806 (0.6103)	loss 3.1546 (2.9874)	grad_norm 1.1787 (2.5083/1.1983)	mem 24308MB
[2025-01-19 01:36:09 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][140/312]	eta 0:01:46 lr 0.000719	time 0.5867 (0.6212)	model_time 0.5865 (0.6114)	loss 2.0667 (2.9789)	grad_norm 3.4939 (2.5329/1.1839)	mem 24308MB
[2025-01-19 01:36:15 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][150/312]	eta 0:01:40 lr 0.000719	time 0.6073 (0.6201)	model_time 0.6068 (0.6109)	loss 3.5031 (2.9802)	grad_norm 1.8196 (2.5251/1.1827)	mem 24308MB
[2025-01-19 01:36:21 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][160/312]	eta 0:01:34 lr 0.000718	time 0.5915 (0.6190)	model_time 0.5913 (0.6103)	loss 3.4764 (3.0066)	grad_norm 2.0232 (2.4918/1.1562)	mem 24308MB
[2025-01-19 01:36:27 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][170/312]	eta 0:01:27 lr 0.000718	time 0.5836 (0.6182)	model_time 0.5834 (0.6100)	loss 2.7777 (3.0176)	grad_norm 2.4759 (2.4633/1.1520)	mem 24308MB
[2025-01-19 01:36:33 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][180/312]	eta 0:01:21 lr 0.000717	time 0.5849 (0.6164)	model_time 0.5844 (0.6087)	loss 3.5110 (3.0271)	grad_norm 3.4715 (2.4958/1.1618)	mem 24308MB
[2025-01-19 01:36:39 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][190/312]	eta 0:01:15 lr 0.000717	time 0.5770 (0.6160)	model_time 0.5765 (0.6086)	loss 2.8947 (3.0201)	grad_norm 1.4287 (2.5199/1.1755)	mem 24308MB
[2025-01-19 01:36:45 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][200/312]	eta 0:01:08 lr 0.000716	time 0.5889 (0.6149)	model_time 0.5885 (0.6079)	loss 2.9823 (3.0207)	grad_norm 2.5933 (2.5015/1.1749)	mem 24308MB
[2025-01-19 01:36:51 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][210/312]	eta 0:01:02 lr 0.000716	time 0.5864 (0.6141)	model_time 0.5862 (0.6074)	loss 2.8583 (3.0238)	grad_norm 1.9595 (2.4715/1.1659)	mem 24308MB
[2025-01-19 01:36:57 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][220/312]	eta 0:00:56 lr 0.000715	time 0.5944 (0.6137)	model_time 0.5940 (0.6073)	loss 2.3593 (3.0287)	grad_norm 3.6421 (2.4543/1.1529)	mem 24308MB
[2025-01-19 01:37:03 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][230/312]	eta 0:00:50 lr 0.000715	time 0.6686 (0.6132)	model_time 0.6684 (0.6071)	loss 2.4865 (3.0274)	grad_norm 1.6284 (2.4411/1.1404)	mem 24308MB
[2025-01-19 01:37:09 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][240/312]	eta 0:00:44 lr 0.000714	time 0.5739 (0.6131)	model_time 0.5737 (0.6071)	loss 2.8168 (3.0304)	grad_norm 4.8554 (2.4348/1.1379)	mem 24308MB
[2025-01-19 01:37:16 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][250/312]	eta 0:00:38 lr 0.000714	time 0.5864 (0.6138)	model_time 0.5860 (0.6081)	loss 3.0653 (3.0300)	grad_norm 1.5132 (2.4388/1.1361)	mem 24308MB
[2025-01-19 01:37:22 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][260/312]	eta 0:00:31 lr 0.000713	time 0.5851 (0.6136)	model_time 0.5847 (0.6081)	loss 3.0535 (3.0344)	grad_norm 2.3416 (2.4055/1.1285)	mem 24308MB
[2025-01-19 01:37:28 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][270/312]	eta 0:00:25 lr 0.000713	time 0.5883 (0.6133)	model_time 0.5881 (0.6080)	loss 3.3828 (3.0309)	grad_norm 1.7556 (2.3764/1.1212)	mem 24308MB
[2025-01-19 01:37:34 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][280/312]	eta 0:00:19 lr 0.000712	time 0.6714 (0.6131)	model_time 0.6709 (0.6079)	loss 3.3590 (3.0262)	grad_norm 2.7908 (2.3753/1.1157)	mem 24308MB
[2025-01-19 01:37:40 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][290/312]	eta 0:00:13 lr 0.000712	time 0.5889 (0.6128)	model_time 0.5887 (0.6078)	loss 2.6796 (3.0291)	grad_norm 2.2748 (2.3693/1.1120)	mem 24308MB
[2025-01-19 01:37:46 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][300/312]	eta 0:00:07 lr 0.000711	time 0.5671 (0.6118)	model_time 0.5670 (0.6070)	loss 3.1844 (3.0362)	grad_norm 2.3148 (2.3915/1.1110)	mem 24308MB
[2025-01-19 01:37:52 internimage_s_1k_224] (main.py 510): INFO Train: [218/300][310/312]	eta 0:00:01 lr 0.000711	time 0.5641 (0.6110)	model_time 0.5639 (0.6063)	loss 3.7731 (3.0363)	grad_norm 1.1603 (2.3828/1.0992)	mem 24308MB
[2025-01-19 01:37:52 internimage_s_1k_224] (main.py 519): INFO EPOCH 218 training takes 0:03:10
[2025-01-19 01:37:52 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_218.pth saving......
[2025-01-19 01:37:54 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_218.pth saved !!!
[2025-01-19 01:38:02 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.010 (8.010)	Loss 0.7373 (0.7373)	Acc@1 84.448 (84.448)	Acc@5 97.314 (97.314)	Mem 24308MB
[2025-01-19 01:38:06 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.048)	Loss 0.9740 (0.8372)	Acc@1 78.394 (82.362)	Acc@5 95.215 (96.236)	Mem 24308MB
[2025-01-19 01:38:06 internimage_s_1k_224] (main.py 575): INFO [Epoch:218] * Acc@1 82.244 Acc@5 96.233
[2025-01-19 01:38:06 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.2%
[2025-01-19 01:38:06 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.42%
[2025-01-19 01:38:15 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.887 (8.887)	Loss 0.7054 (0.7054)	Acc@1 85.205 (85.205)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 01:38:19 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.201)	Loss 0.9280 (0.7951)	Acc@1 78.369 (82.648)	Acc@5 95.532 (96.420)	Mem 24308MB
[2025-01-19 01:38:19 internimage_s_1k_224] (main.py 575): INFO [Epoch:218] * Acc@1 82.510 Acc@5 96.443
[2025-01-19 01:38:19 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.5%
[2025-01-19 01:38:19 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:38:21 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:38:21 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.51%
[2025-01-19 01:38:23 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][0/312]	eta 0:11:44 lr 0.000711	time 2.2593 (2.2593)	model_time 0.6132 (0.6132)	loss 3.2651 (3.2651)	grad_norm 2.4896 (2.4896/0.0000)	mem 24308MB
[2025-01-19 01:38:29 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][10/312]	eta 0:03:46 lr 0.000710	time 0.5933 (0.7499)	model_time 0.5932 (0.5999)	loss 2.9171 (3.0852)	grad_norm 4.2880 (2.5123/0.8622)	mem 24308MB
[2025-01-19 01:38:35 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][20/312]	eta 0:03:17 lr 0.000710	time 0.5978 (0.6774)	model_time 0.5976 (0.5987)	loss 2.7619 (3.1486)	grad_norm 3.4845 (2.4762/0.8498)	mem 24308MB
[2025-01-19 01:38:42 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][30/312]	eta 0:03:05 lr 0.000709	time 0.5807 (0.6565)	model_time 0.5806 (0.6031)	loss 2.7758 (3.1084)	grad_norm 1.8122 (2.6626/1.0588)	mem 24308MB
[2025-01-19 01:38:48 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][40/312]	eta 0:02:55 lr 0.000709	time 0.7104 (0.6466)	model_time 0.7103 (0.6062)	loss 3.0176 (3.1037)	grad_norm 1.3960 (2.5242/0.9847)	mem 24308MB
[2025-01-19 01:38:54 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][50/312]	eta 0:02:46 lr 0.000708	time 0.5854 (0.6345)	model_time 0.5852 (0.6018)	loss 2.6665 (3.1148)	grad_norm 2.3480 (2.4425/0.9360)	mem 24308MB
[2025-01-19 01:39:00 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][60/312]	eta 0:02:39 lr 0.000708	time 0.6672 (0.6342)	model_time 0.6668 (0.6069)	loss 2.0259 (3.0880)	grad_norm 2.7945 (2.2790/0.9596)	mem 24308MB
[2025-01-19 01:39:06 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][70/312]	eta 0:02:32 lr 0.000707	time 0.5841 (0.6306)	model_time 0.5837 (0.6070)	loss 2.9751 (3.0735)	grad_norm 1.9927 (2.2112/0.9218)	mem 24308MB
[2025-01-19 01:39:12 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][80/312]	eta 0:02:25 lr 0.000707	time 0.5787 (0.6267)	model_time 0.5785 (0.6060)	loss 2.7554 (3.0783)	grad_norm 1.4569 (2.2593/0.9631)	mem 24308MB
[2025-01-19 01:39:18 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][90/312]	eta 0:02:19 lr 0.000706	time 0.6522 (0.6270)	model_time 0.6518 (0.6085)	loss 2.8604 (3.0694)	grad_norm 1.4902 (2.2228/0.9333)	mem 24308MB
[2025-01-19 01:39:24 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][100/312]	eta 0:02:12 lr 0.000706	time 0.5985 (0.6240)	model_time 0.5983 (0.6073)	loss 3.3300 (3.0657)	grad_norm 1.4065 (2.2359/0.9397)	mem 24308MB
[2025-01-19 01:39:30 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][110/312]	eta 0:02:05 lr 0.000705	time 0.5718 (0.6209)	model_time 0.5716 (0.6057)	loss 3.1764 (3.0915)	grad_norm 2.0309 (2.1978/0.9296)	mem 24308MB
[2025-01-19 01:39:36 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][120/312]	eta 0:01:59 lr 0.000705	time 0.6794 (0.6201)	model_time 0.6792 (0.6061)	loss 3.3821 (3.0902)	grad_norm 2.0379 (2.1889/0.9228)	mem 24308MB
[2025-01-19 01:39:42 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][130/312]	eta 0:01:52 lr 0.000704	time 0.5805 (0.6185)	model_time 0.5803 (0.6056)	loss 3.3053 (3.0675)	grad_norm 1.3476 (2.1842/0.9291)	mem 24308MB
[2025-01-19 01:39:48 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][140/312]	eta 0:01:46 lr 0.000704	time 0.5990 (0.6170)	model_time 0.5988 (0.6049)	loss 3.4474 (3.0782)	grad_norm 1.1824 (2.1963/0.9426)	mem 24308MB
[2025-01-19 01:39:54 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][150/312]	eta 0:01:39 lr 0.000703	time 0.5717 (0.6158)	model_time 0.5715 (0.6044)	loss 2.2479 (3.0731)	grad_norm 1.3046 (2.2957/1.0868)	mem 24308MB
[2025-01-19 01:40:00 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][160/312]	eta 0:01:33 lr 0.000703	time 0.5667 (0.6153)	model_time 0.5666 (0.6045)	loss 3.0557 (3.0699)	grad_norm 2.4835 (2.2940/1.0837)	mem 24308MB
[2025-01-19 01:40:06 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][170/312]	eta 0:01:27 lr 0.000702	time 0.5832 (0.6145)	model_time 0.5828 (0.6044)	loss 3.4555 (3.0545)	grad_norm 4.0923 (2.3137/1.0955)	mem 24308MB
[2025-01-19 01:40:13 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][180/312]	eta 0:01:21 lr 0.000702	time 0.6666 (0.6161)	model_time 0.6661 (0.6065)	loss 3.5110 (3.0491)	grad_norm 1.9173 (2.2949/1.0770)	mem 24308MB
[2025-01-19 01:40:19 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][190/312]	eta 0:01:15 lr 0.000701	time 0.5803 (0.6165)	model_time 0.5800 (0.6074)	loss 2.6083 (3.0364)	grad_norm 1.3808 (2.3176/1.0934)	mem 24308MB
[2025-01-19 01:40:25 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][200/312]	eta 0:01:08 lr 0.000701	time 0.5832 (0.6157)	model_time 0.5830 (0.6071)	loss 3.4901 (3.0486)	grad_norm 2.0695 (2.3058/1.1075)	mem 24308MB
[2025-01-19 01:40:31 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][210/312]	eta 0:01:02 lr 0.000700	time 0.6522 (0.6164)	model_time 0.6520 (0.6081)	loss 2.7913 (3.0441)	grad_norm 1.9296 (2.2932/1.0880)	mem 24308MB
[2025-01-19 01:40:37 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][220/312]	eta 0:00:56 lr 0.000700	time 0.5890 (0.6151)	model_time 0.5888 (0.6072)	loss 3.2886 (3.0503)	grad_norm 2.6291 (2.3151/1.0832)	mem 24308MB
[2025-01-19 01:40:43 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][230/312]	eta 0:00:50 lr 0.000699	time 0.5880 (0.6143)	model_time 0.5878 (0.6067)	loss 3.5955 (3.0524)	grad_norm 1.1568 (2.2956/1.0697)	mem 24308MB
[2025-01-19 01:40:49 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][240/312]	eta 0:00:44 lr 0.000699	time 0.6722 (0.6141)	model_time 0.6718 (0.6068)	loss 3.7332 (3.0628)	grad_norm 1.8111 (2.2746/1.0586)	mem 24308MB
[2025-01-19 01:40:55 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][250/312]	eta 0:00:38 lr 0.000698	time 0.5866 (0.6135)	model_time 0.5864 (0.6065)	loss 3.1312 (3.0515)	grad_norm 1.5227 (2.2602/1.0423)	mem 24308MB
[2025-01-19 01:41:01 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][260/312]	eta 0:00:31 lr 0.000698	time 0.5964 (0.6130)	model_time 0.5963 (0.6062)	loss 3.3589 (3.0500)	grad_norm 3.0436 (2.2663/1.0338)	mem 24308MB
[2025-01-19 01:41:07 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][270/312]	eta 0:00:25 lr 0.000697	time 0.6509 (0.6126)	model_time 0.6504 (0.6060)	loss 2.5711 (3.0506)	grad_norm 2.9792 (2.2766/1.0296)	mem 24308MB
[2025-01-19 01:41:13 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][280/312]	eta 0:00:19 lr 0.000697	time 0.6631 (0.6122)	model_time 0.6626 (0.6058)	loss 2.9707 (3.0448)	grad_norm 2.1881 (2.2811/1.0243)	mem 24308MB
[2025-01-19 01:41:19 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][290/312]	eta 0:00:13 lr 0.000696	time 0.5823 (0.6119)	model_time 0.5818 (0.6058)	loss 3.4629 (3.0449)	grad_norm 1.7869 (2.2666/1.0128)	mem 24308MB
[2025-01-19 01:41:25 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][300/312]	eta 0:00:07 lr 0.000696	time 0.5723 (0.6120)	model_time 0.5722 (0.6061)	loss 2.2849 (3.0479)	grad_norm 2.5710 (2.2675/1.0041)	mem 24308MB
[2025-01-19 01:41:32 internimage_s_1k_224] (main.py 510): INFO Train: [219/300][310/312]	eta 0:00:01 lr 0.000695	time 0.5641 (0.6120)	model_time 0.5640 (0.6063)	loss 3.3106 (3.0410)	grad_norm 1.8347 (2.2596/0.9948)	mem 24308MB
[2025-01-19 01:41:32 internimage_s_1k_224] (main.py 519): INFO EPOCH 219 training takes 0:03:10
[2025-01-19 01:41:32 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_219.pth saving......
[2025-01-19 01:41:34 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_219.pth saved !!!
[2025-01-19 01:41:42 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.946 (7.946)	Loss 0.7442 (0.7442)	Acc@1 84.375 (84.375)	Acc@5 97.485 (97.485)	Mem 24308MB
[2025-01-19 01:41:46 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.069)	Loss 0.9748 (0.8455)	Acc@1 78.394 (82.477)	Acc@5 95.532 (96.373)	Mem 24308MB
[2025-01-19 01:41:46 internimage_s_1k_224] (main.py 575): INFO [Epoch:219] * Acc@1 82.308 Acc@5 96.381
[2025-01-19 01:41:46 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.3%
[2025-01-19 01:41:46 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.42%
[2025-01-19 01:41:55 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.207 (9.207)	Loss 0.7054 (0.7054)	Acc@1 85.181 (85.181)	Acc@5 97.803 (97.803)	Mem 24308MB
[2025-01-19 01:42:00 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.243)	Loss 0.9268 (0.7945)	Acc@1 78.394 (82.682)	Acc@5 95.557 (96.416)	Mem 24308MB
[2025-01-19 01:42:00 internimage_s_1k_224] (main.py 575): INFO [Epoch:219] * Acc@1 82.550 Acc@5 96.437
[2025-01-19 01:42:00 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.5%
[2025-01-19 01:42:00 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:42:02 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:42:02 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.55%
[2025-01-19 01:42:04 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][0/312]	eta 0:12:01 lr 0.000695	time 2.3111 (2.3111)	model_time 0.5946 (0.5946)	loss 3.0950 (3.0950)	grad_norm 1.1003 (1.1003/0.0000)	mem 24308MB
[2025-01-19 01:42:10 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][10/312]	eta 0:03:49 lr 0.000695	time 0.6478 (0.7596)	model_time 0.6476 (0.6033)	loss 3.3952 (3.1694)	grad_norm 2.9789 (1.9888/0.6060)	mem 24308MB
[2025-01-19 01:42:16 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][20/312]	eta 0:03:19 lr 0.000694	time 0.6013 (0.6817)	model_time 0.6012 (0.5996)	loss 3.5114 (3.1885)	grad_norm 3.0568 (2.2075/0.6869)	mem 24308MB
[2025-01-19 01:42:22 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][30/312]	eta 0:03:04 lr 0.000694	time 0.5761 (0.6534)	model_time 0.5759 (0.5978)	loss 3.6145 (3.1606)	grad_norm 1.8452 (2.0463/0.6476)	mem 24308MB
[2025-01-19 01:42:28 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][40/312]	eta 0:02:54 lr 0.000693	time 0.5809 (0.6401)	model_time 0.5805 (0.5979)	loss 2.0958 (3.0335)	grad_norm 5.8181 (2.0996/0.8660)	mem 24308MB
[2025-01-19 01:42:34 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][50/312]	eta 0:02:45 lr 0.000693	time 0.5973 (0.6332)	model_time 0.5971 (0.5992)	loss 3.0064 (3.0065)	grad_norm 2.4499 (2.1417/0.8058)	mem 24308MB
[2025-01-19 01:42:40 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][60/312]	eta 0:02:38 lr 0.000692	time 0.6285 (0.6287)	model_time 0.6283 (0.6002)	loss 3.3049 (2.9730)	grad_norm 1.1387 (2.1807/0.8515)	mem 24308MB
[2025-01-19 01:42:46 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][70/312]	eta 0:02:31 lr 0.000692	time 0.5835 (0.6251)	model_time 0.5831 (0.6006)	loss 2.0944 (2.9568)	grad_norm 2.3247 (2.2215/0.8847)	mem 24308MB
[2025-01-19 01:42:52 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][80/312]	eta 0:02:24 lr 0.000691	time 0.5815 (0.6215)	model_time 0.5813 (0.5999)	loss 3.0042 (3.0041)	grad_norm 2.6341 (2.2138/0.8718)	mem 24308MB
[2025-01-19 01:42:58 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][90/312]	eta 0:02:17 lr 0.000691	time 0.6654 (0.6208)	model_time 0.6652 (0.6016)	loss 3.4248 (3.0173)	grad_norm 3.0784 (2.2266/0.8721)	mem 24308MB
[2025-01-19 01:43:04 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][100/312]	eta 0:02:11 lr 0.000690	time 0.5801 (0.6198)	model_time 0.5800 (0.6025)	loss 3.2089 (3.0042)	grad_norm 0.8785 (2.2251/0.8779)	mem 24308MB
[2025-01-19 01:43:11 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][110/312]	eta 0:02:05 lr 0.000690	time 0.5779 (0.6210)	model_time 0.5774 (0.6051)	loss 3.5197 (3.0043)	grad_norm 5.0676 (2.2097/0.8944)	mem 24308MB
[2025-01-19 01:43:17 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][120/312]	eta 0:01:59 lr 0.000689	time 0.5800 (0.6213)	model_time 0.5798 (0.6067)	loss 2.3559 (2.9889)	grad_norm 1.7765 (2.2811/0.9903)	mem 24308MB
[2025-01-19 01:43:23 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][130/312]	eta 0:01:52 lr 0.000689	time 0.5770 (0.6191)	model_time 0.5767 (0.6056)	loss 2.5982 (2.9841)	grad_norm 2.3518 (2.2909/0.9794)	mem 24308MB
[2025-01-19 01:43:29 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][140/312]	eta 0:01:46 lr 0.000688	time 0.5789 (0.6187)	model_time 0.5784 (0.6062)	loss 3.2562 (2.9737)	grad_norm 2.9948 (2.2683/0.9680)	mem 24308MB
[2025-01-19 01:43:35 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][150/312]	eta 0:01:39 lr 0.000688	time 0.5736 (0.6169)	model_time 0.5733 (0.6052)	loss 1.6191 (2.9654)	grad_norm 2.3045 (2.3261/1.0181)	mem 24308MB
[2025-01-19 01:43:41 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][160/312]	eta 0:01:33 lr 0.000687	time 0.5854 (0.6157)	model_time 0.5850 (0.6047)	loss 3.3100 (2.9633)	grad_norm 1.7236 (2.3748/1.0386)	mem 24308MB
[2025-01-19 01:43:47 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][170/312]	eta 0:01:27 lr 0.000687	time 0.5676 (0.6151)	model_time 0.5674 (0.6047)	loss 2.4915 (2.9628)	grad_norm 1.6735 (2.4312/1.1075)	mem 24308MB
[2025-01-19 01:43:53 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][180/312]	eta 0:01:21 lr 0.000686	time 0.5913 (0.6149)	model_time 0.5912 (0.6050)	loss 2.6705 (2.9650)	grad_norm 2.1440 (2.4247/1.0881)	mem 24308MB
[2025-01-19 01:43:59 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][190/312]	eta 0:01:14 lr 0.000686	time 0.5793 (0.6136)	model_time 0.5788 (0.6042)	loss 3.5165 (2.9768)	grad_norm 2.7642 (2.4005/1.0740)	mem 24308MB
[2025-01-19 01:44:05 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][200/312]	eta 0:01:08 lr 0.000685	time 0.5822 (0.6132)	model_time 0.5818 (0.6042)	loss 3.0460 (2.9739)	grad_norm 1.6326 (2.4020/1.0624)	mem 24308MB
[2025-01-19 01:44:11 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][210/312]	eta 0:01:02 lr 0.000685	time 0.5825 (0.6129)	model_time 0.5824 (0.6044)	loss 2.6345 (2.9697)	grad_norm 1.0712 (2.3656/1.0558)	mem 24308MB
[2025-01-19 01:44:17 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][220/312]	eta 0:00:56 lr 0.000684	time 0.5808 (0.6131)	model_time 0.5804 (0.6049)	loss 3.1228 (2.9671)	grad_norm 3.7077 (2.3628/1.0439)	mem 24308MB
[2025-01-19 01:44:23 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][230/312]	eta 0:00:50 lr 0.000684	time 0.5718 (0.6130)	model_time 0.5714 (0.6052)	loss 3.0166 (2.9691)	grad_norm 2.4982 (2.3682/1.0405)	mem 24308MB
[2025-01-19 01:44:30 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][240/312]	eta 0:00:44 lr 0.000683	time 0.6587 (0.6134)	model_time 0.6585 (0.6059)	loss 2.8158 (2.9558)	grad_norm 3.1084 (2.3586/1.0260)	mem 24308MB
[2025-01-19 01:44:36 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][250/312]	eta 0:00:37 lr 0.000683	time 0.5771 (0.6127)	model_time 0.5769 (0.6055)	loss 3.0821 (2.9648)	grad_norm 6.0092 (2.4083/1.0714)	mem 24308MB
[2025-01-19 01:44:42 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][260/312]	eta 0:00:31 lr 0.000682	time 0.5970 (0.6136)	model_time 0.5966 (0.6066)	loss 2.4658 (2.9654)	grad_norm 2.4123 (2.4086/1.0571)	mem 24308MB
[2025-01-19 01:44:48 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][270/312]	eta 0:00:25 lr 0.000682	time 0.5776 (0.6130)	model_time 0.5771 (0.6063)	loss 3.0077 (2.9572)	grad_norm 1.7928 (2.4242/1.0894)	mem 24308MB
[2025-01-19 01:44:54 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][280/312]	eta 0:00:19 lr 0.000681	time 0.6618 (0.6127)	model_time 0.6616 (0.6062)	loss 2.7764 (2.9631)	grad_norm 4.3968 (2.4305/1.0827)	mem 24308MB
[2025-01-19 01:45:00 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][290/312]	eta 0:00:13 lr 0.000681	time 0.6725 (0.6123)	model_time 0.6723 (0.6060)	loss 3.3208 (2.9698)	grad_norm 1.5254 (2.4319/1.0790)	mem 24308MB
[2025-01-19 01:45:06 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][300/312]	eta 0:00:07 lr 0.000680	time 0.6727 (0.6117)	model_time 0.6726 (0.6057)	loss 3.3031 (2.9765)	grad_norm 2.3358 (2.4306/1.0654)	mem 24308MB
[2025-01-19 01:45:12 internimage_s_1k_224] (main.py 510): INFO Train: [220/300][310/312]	eta 0:00:01 lr 0.000680	time 0.5709 (0.6105)	model_time 0.5708 (0.6046)	loss 2.5005 (2.9731)	grad_norm 3.0475 (2.4593/1.0756)	mem 24308MB
[2025-01-19 01:45:12 internimage_s_1k_224] (main.py 519): INFO EPOCH 220 training takes 0:03:10
[2025-01-19 01:45:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_220.pth saving......
[2025-01-19 01:45:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_220.pth saved !!!
[2025-01-19 01:45:22 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.805 (7.805)	Loss 0.7713 (0.7713)	Acc@1 84.717 (84.717)	Acc@5 97.485 (97.485)	Mem 24308MB
[2025-01-19 01:45:26 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.045)	Loss 0.9977 (0.8640)	Acc@1 78.442 (82.444)	Acc@5 95.117 (96.276)	Mem 24308MB
[2025-01-19 01:45:26 internimage_s_1k_224] (main.py 575): INFO [Epoch:220] * Acc@1 82.332 Acc@5 96.303
[2025-01-19 01:45:26 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.3%
[2025-01-19 01:45:26 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.42%
[2025-01-19 01:45:35 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.032 (9.032)	Loss 0.7053 (0.7053)	Acc@1 85.156 (85.156)	Acc@5 97.778 (97.778)	Mem 24308MB
[2025-01-19 01:45:39 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.220)	Loss 0.9258 (0.7939)	Acc@1 78.418 (82.699)	Acc@5 95.605 (96.449)	Mem 24308MB
[2025-01-19 01:45:39 internimage_s_1k_224] (main.py 575): INFO [Epoch:220] * Acc@1 82.570 Acc@5 96.467
[2025-01-19 01:45:39 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.6%
[2025-01-19 01:45:39 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:45:41 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:45:41 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.57%
[2025-01-19 01:45:44 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][0/312]	eta 0:11:50 lr 0.000680	time 2.2758 (2.2758)	model_time 0.6129 (0.6129)	loss 2.2674 (2.2674)	grad_norm 2.5378 (2.5378/0.0000)	mem 24308MB
[2025-01-19 01:45:50 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][10/312]	eta 0:03:50 lr 0.000679	time 0.6604 (0.7629)	model_time 0.6602 (0.6114)	loss 2.9686 (3.0669)	grad_norm 4.0058 (3.5941/1.1253)	mem 24308MB
[2025-01-19 01:45:56 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][20/312]	eta 0:03:20 lr 0.000679	time 0.5857 (0.6859)	model_time 0.5856 (0.6063)	loss 3.1558 (3.0816)	grad_norm 2.3195 (3.0867/1.0980)	mem 24308MB
[2025-01-19 01:46:02 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][30/312]	eta 0:03:06 lr 0.000678	time 0.6653 (0.6630)	model_time 0.6651 (0.6090)	loss 2.6674 (3.0352)	grad_norm 2.2658 (2.7765/1.0534)	mem 24308MB
[2025-01-19 01:46:08 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][40/312]	eta 0:02:58 lr 0.000678	time 0.5773 (0.6556)	model_time 0.5771 (0.6146)	loss 3.8972 (3.0379)	grad_norm 2.6602 (2.6437/1.0168)	mem 24308MB
[2025-01-19 01:46:15 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][50/312]	eta 0:02:50 lr 0.000677	time 0.5953 (0.6502)	model_time 0.5948 (0.6172)	loss 2.7836 (3.0332)	grad_norm 2.2067 (2.4770/0.9937)	mem 24308MB
[2025-01-19 01:46:20 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][60/312]	eta 0:02:41 lr 0.000677	time 0.5721 (0.6411)	model_time 0.5719 (0.6135)	loss 3.1343 (3.0349)	grad_norm 1.7953 (2.3806/0.9592)	mem 24308MB
[2025-01-19 01:46:27 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][70/312]	eta 0:02:34 lr 0.000676	time 0.5866 (0.6369)	model_time 0.5862 (0.6131)	loss 2.9104 (3.0141)	grad_norm 1.9794 (2.4357/0.9812)	mem 24308MB
[2025-01-19 01:46:33 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][80/312]	eta 0:02:26 lr 0.000676	time 0.6123 (0.6323)	model_time 0.6120 (0.6114)	loss 3.1845 (3.0185)	grad_norm 1.4490 (2.4043/0.9410)	mem 24308MB
[2025-01-19 01:46:38 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][90/312]	eta 0:02:19 lr 0.000675	time 0.5907 (0.6271)	model_time 0.5902 (0.6084)	loss 3.4279 (2.9752)	grad_norm 3.6178 (2.4428/0.9564)	mem 24308MB
[2025-01-19 01:46:44 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][100/312]	eta 0:02:12 lr 0.000675	time 0.6101 (0.6246)	model_time 0.6095 (0.6077)	loss 3.1604 (2.9974)	grad_norm 2.3273 (2.4371/0.9418)	mem 24308MB
[2025-01-19 01:46:51 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][110/312]	eta 0:02:06 lr 0.000674	time 0.5918 (0.6240)	model_time 0.5916 (0.6086)	loss 3.4934 (3.0256)	grad_norm 1.8245 (2.4064/0.9249)	mem 24308MB
[2025-01-19 01:46:57 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][120/312]	eta 0:01:59 lr 0.000674	time 0.5810 (0.6215)	model_time 0.5808 (0.6073)	loss 3.3048 (3.0075)	grad_norm 1.2744 (2.3998/0.9018)	mem 24308MB
[2025-01-19 01:47:03 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][130/312]	eta 0:01:52 lr 0.000673	time 0.5861 (0.6204)	model_time 0.5858 (0.6073)	loss 1.8776 (2.9923)	grad_norm 2.4721 (2.3924/0.9031)	mem 24308MB
[2025-01-19 01:47:09 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][140/312]	eta 0:01:46 lr 0.000673	time 0.5836 (0.6195)	model_time 0.5834 (0.6073)	loss 3.3594 (2.9816)	grad_norm 1.8396 (2.3799/0.9095)	mem 24308MB
[2025-01-19 01:47:15 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][150/312]	eta 0:01:40 lr 0.000672	time 0.5725 (0.6187)	model_time 0.5723 (0.6073)	loss 3.9081 (2.9819)	grad_norm 2.0066 (2.3900/0.9065)	mem 24308MB
[2025-01-19 01:47:21 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][160/312]	eta 0:01:34 lr 0.000672	time 0.6428 (0.6203)	model_time 0.6423 (0.6096)	loss 3.5086 (2.9814)	grad_norm 3.3850 (2.3810/0.8891)	mem 24308MB
[2025-01-19 01:47:28 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][170/312]	eta 0:01:28 lr 0.000671	time 0.5910 (0.6214)	model_time 0.5909 (0.6113)	loss 3.0293 (2.9751)	grad_norm 3.3409 (2.3995/0.8956)	mem 24308MB
[2025-01-19 01:47:34 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][180/312]	eta 0:01:21 lr 0.000671	time 0.6575 (0.6198)	model_time 0.6571 (0.6102)	loss 1.9545 (2.9719)	grad_norm 3.5159 (2.4093/0.8849)	mem 24308MB
[2025-01-19 01:47:40 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][190/312]	eta 0:01:15 lr 0.000671	time 0.5823 (0.6204)	model_time 0.5822 (0.6113)	loss 2.6707 (2.9657)	grad_norm 2.2795 (2.3983/0.8874)	mem 24308MB
[2025-01-19 01:47:46 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][200/312]	eta 0:01:09 lr 0.000670	time 0.5789 (0.6191)	model_time 0.5785 (0.6104)	loss 2.8453 (2.9653)	grad_norm 2.6008 (2.4128/0.9019)	mem 24308MB
[2025-01-19 01:47:52 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][210/312]	eta 0:01:02 lr 0.000670	time 0.5863 (0.6175)	model_time 0.5861 (0.6092)	loss 3.1966 (2.9714)	grad_norm 1.0830 (2.3866/0.9037)	mem 24308MB
[2025-01-19 01:47:58 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][220/312]	eta 0:00:56 lr 0.000669	time 0.5787 (0.6167)	model_time 0.5782 (0.6088)	loss 3.0301 (2.9765)	grad_norm 4.8575 (2.3889/0.9121)	mem 24308MB
[2025-01-19 01:48:04 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][230/312]	eta 0:00:50 lr 0.000669	time 0.6713 (0.6160)	model_time 0.6711 (0.6084)	loss 2.6930 (2.9834)	grad_norm 3.2646 (2.4026/0.9342)	mem 24308MB
[2025-01-19 01:48:10 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][240/312]	eta 0:00:44 lr 0.000668	time 0.6082 (0.6153)	model_time 0.6078 (0.6080)	loss 3.1219 (2.9799)	grad_norm 3.0005 (2.4284/0.9795)	mem 24308MB
[2025-01-19 01:48:16 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][250/312]	eta 0:00:38 lr 0.000668	time 0.5838 (0.6147)	model_time 0.5833 (0.6076)	loss 2.9306 (2.9793)	grad_norm 1.1720 (2.4048/0.9708)	mem 24308MB
[2025-01-19 01:48:22 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][260/312]	eta 0:00:31 lr 0.000667	time 0.5839 (0.6146)	model_time 0.5837 (0.6078)	loss 3.2703 (2.9800)	grad_norm 2.8558 (2.4193/0.9867)	mem 24308MB
[2025-01-19 01:48:28 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][270/312]	eta 0:00:25 lr 0.000667	time 0.5923 (0.6139)	model_time 0.5919 (0.6074)	loss 3.4653 (2.9872)	grad_norm 3.0252 (2.4466/1.0062)	mem 24308MB
[2025-01-19 01:48:34 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][280/312]	eta 0:00:19 lr 0.000666	time 0.6841 (0.6143)	model_time 0.6836 (0.6080)	loss 3.4057 (2.9855)	grad_norm 1.3916 (2.4473/1.0043)	mem 24308MB
[2025-01-19 01:48:40 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][290/312]	eta 0:00:13 lr 0.000666	time 0.6529 (0.6148)	model_time 0.6525 (0.6086)	loss 2.8859 (2.9758)	grad_norm 3.4039 (2.4551/0.9944)	mem 24308MB
[2025-01-19 01:48:46 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][300/312]	eta 0:00:07 lr 0.000665	time 0.6463 (0.6140)	model_time 0.6462 (0.6081)	loss 3.8486 (2.9772)	grad_norm 3.6740 (2.4631/0.9973)	mem 24308MB
[2025-01-19 01:48:52 internimage_s_1k_224] (main.py 510): INFO Train: [221/300][310/312]	eta 0:00:01 lr 0.000665	time 0.6768 (0.6138)	model_time 0.6767 (0.6080)	loss 2.4333 (2.9732)	grad_norm 1.4029 (2.4016/0.9613)	mem 24308MB
[2025-01-19 01:48:53 internimage_s_1k_224] (main.py 519): INFO EPOCH 221 training takes 0:03:11
[2025-01-19 01:48:53 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_221.pth saving......
[2025-01-19 01:48:55 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_221.pth saved !!!
[2025-01-19 01:49:03 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.894 (7.894)	Loss 0.7548 (0.7548)	Acc@1 84.790 (84.790)	Acc@5 97.485 (97.485)	Mem 24308MB
[2025-01-19 01:49:06 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.137 (1.071)	Loss 0.9653 (0.8505)	Acc@1 78.711 (82.471)	Acc@5 95.312 (96.309)	Mem 24308MB
[2025-01-19 01:49:07 internimage_s_1k_224] (main.py 575): INFO [Epoch:221] * Acc@1 82.314 Acc@5 96.353
[2025-01-19 01:49:07 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.3%
[2025-01-19 01:49:07 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.42%
[2025-01-19 01:49:16 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.123 (9.123)	Loss 0.7052 (0.7052)	Acc@1 85.205 (85.205)	Acc@5 97.803 (97.803)	Mem 24308MB
[2025-01-19 01:49:20 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.233)	Loss 0.9247 (0.7933)	Acc@1 78.467 (82.726)	Acc@5 95.654 (96.467)	Mem 24308MB
[2025-01-19 01:49:20 internimage_s_1k_224] (main.py 575): INFO [Epoch:221] * Acc@1 82.598 Acc@5 96.489
[2025-01-19 01:49:20 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.6%
[2025-01-19 01:49:20 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:49:23 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:49:23 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.60%
[2025-01-19 01:49:25 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][0/312]	eta 0:10:16 lr 0.000665	time 1.9755 (1.9755)	model_time 0.6579 (0.6579)	loss 2.9384 (2.9384)	grad_norm 1.2799 (1.2799/0.0000)	mem 24308MB
[2025-01-19 01:49:31 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][10/312]	eta 0:03:36 lr 0.000664	time 0.6109 (0.7176)	model_time 0.6107 (0.5975)	loss 2.1694 (3.0508)	grad_norm 2.2932 (1.8277/0.4525)	mem 24308MB
[2025-01-19 01:49:37 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][20/312]	eta 0:03:12 lr 0.000664	time 0.5943 (0.6580)	model_time 0.5942 (0.5950)	loss 2.6311 (2.9592)	grad_norm 2.2181 (2.0127/0.6201)	mem 24308MB
[2025-01-19 01:49:43 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][30/312]	eta 0:03:00 lr 0.000663	time 0.5899 (0.6404)	model_time 0.5897 (0.5976)	loss 3.7007 (3.0345)	grad_norm 1.6616 (2.0059/0.6370)	mem 24308MB
[2025-01-19 01:49:49 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][40/312]	eta 0:02:51 lr 0.000663	time 0.5857 (0.6313)	model_time 0.5853 (0.5988)	loss 2.8636 (3.0099)	grad_norm 1.8100 (2.2236/0.8753)	mem 24308MB
[2025-01-19 01:49:55 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][50/312]	eta 0:02:43 lr 0.000662	time 0.5908 (0.6254)	model_time 0.5906 (0.5992)	loss 3.0560 (2.9747)	grad_norm 1.5751 (2.1551/0.8310)	mem 24308MB
[2025-01-19 01:50:01 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][60/312]	eta 0:02:36 lr 0.000662	time 0.6501 (0.6230)	model_time 0.6498 (0.6010)	loss 3.1075 (3.0017)	grad_norm 1.6907 (2.2703/0.9661)	mem 24308MB
[2025-01-19 01:50:07 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][70/312]	eta 0:02:30 lr 0.000661	time 0.5990 (0.6202)	model_time 0.5988 (0.6012)	loss 3.2663 (2.9918)	grad_norm 2.3356 (2.3506/1.0210)	mem 24308MB
[2025-01-19 01:50:13 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][80/312]	eta 0:02:23 lr 0.000661	time 0.6689 (0.6187)	model_time 0.6687 (0.6020)	loss 3.3061 (2.9966)	grad_norm 2.8252 (2.3627/1.0193)	mem 24308MB
[2025-01-19 01:50:19 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][90/312]	eta 0:02:17 lr 0.000660	time 0.7103 (0.6187)	model_time 0.7102 (0.6038)	loss 3.3064 (2.9937)	grad_norm 1.6597 (2.4309/1.0356)	mem 24308MB
[2025-01-19 01:50:25 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][100/312]	eta 0:02:11 lr 0.000660	time 0.5775 (0.6200)	model_time 0.5774 (0.6065)	loss 3.0962 (3.0006)	grad_norm 1.2845 (2.4511/1.0180)	mem 24308MB
[2025-01-19 01:50:31 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][110/312]	eta 0:02:04 lr 0.000659	time 0.5924 (0.6178)	model_time 0.5922 (0.6055)	loss 3.1388 (2.9963)	grad_norm 2.5012 (2.4375/1.0055)	mem 24308MB
[2025-01-19 01:50:38 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][120/312]	eta 0:01:58 lr 0.000659	time 0.6770 (0.6192)	model_time 0.6768 (0.6079)	loss 3.1216 (3.0006)	grad_norm 1.9955 (2.4511/1.0148)	mem 24308MB
[2025-01-19 01:50:44 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][130/312]	eta 0:01:52 lr 0.000658	time 0.5819 (0.6170)	model_time 0.5817 (0.6065)	loss 3.2711 (3.0006)	grad_norm 4.2182 (2.4359/1.0093)	mem 24308MB
[2025-01-19 01:50:50 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][140/312]	eta 0:01:45 lr 0.000658	time 0.5730 (0.6151)	model_time 0.5724 (0.6053)	loss 2.9304 (2.9849)	grad_norm 3.3643 (2.5574/1.1340)	mem 24308MB
[2025-01-19 01:50:56 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][150/312]	eta 0:01:39 lr 0.000657	time 0.5891 (0.6141)	model_time 0.5889 (0.6050)	loss 2.9640 (2.9811)	grad_norm 1.2838 (2.6045/1.1670)	mem 24308MB
[2025-01-19 01:51:02 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][160/312]	eta 0:01:33 lr 0.000657	time 0.5782 (0.6136)	model_time 0.5777 (0.6051)	loss 3.0357 (2.9897)	grad_norm 1.4544 (2.6167/1.1783)	mem 24308MB
[2025-01-19 01:51:08 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][170/312]	eta 0:01:27 lr 0.000656	time 0.5768 (0.6128)	model_time 0.5766 (0.6047)	loss 3.2532 (3.0013)	grad_norm 1.3922 (2.5616/1.1691)	mem 24308MB
[2025-01-19 01:51:14 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][180/312]	eta 0:01:20 lr 0.000656	time 0.6498 (0.6120)	model_time 0.6496 (0.6043)	loss 3.1633 (3.0060)	grad_norm 3.3648 (2.5305/1.1552)	mem 24308MB
[2025-01-19 01:51:20 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][190/312]	eta 0:01:14 lr 0.000655	time 0.5969 (0.6120)	model_time 0.5967 (0.6048)	loss 2.1049 (3.0081)	grad_norm 1.8584 (2.5360/1.1520)	mem 24308MB
[2025-01-19 01:51:26 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][200/312]	eta 0:01:08 lr 0.000655	time 0.6685 (0.6116)	model_time 0.6683 (0.6047)	loss 2.6095 (3.0085)	grad_norm 2.4564 (2.5334/1.1450)	mem 24308MB
[2025-01-19 01:51:32 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][210/312]	eta 0:01:02 lr 0.000654	time 0.6899 (0.6121)	model_time 0.6897 (0.6054)	loss 1.9365 (2.9992)	grad_norm 2.5101 (2.5260/1.1305)	mem 24308MB
[2025-01-19 01:51:38 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][220/312]	eta 0:00:56 lr 0.000654	time 0.5923 (0.6133)	model_time 0.5922 (0.6070)	loss 3.0497 (3.0015)	grad_norm 1.3431 (2.5070/1.1212)	mem 24308MB
[2025-01-19 01:51:44 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][230/312]	eta 0:00:50 lr 0.000653	time 0.5969 (0.6122)	model_time 0.5965 (0.6061)	loss 2.8319 (2.9936)	grad_norm 1.2651 (2.4694/1.1153)	mem 24308MB
[2025-01-19 01:51:51 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][240/312]	eta 0:00:44 lr 0.000653	time 0.6561 (0.6132)	model_time 0.6557 (0.6073)	loss 3.1140 (2.9866)	grad_norm 1.8385 (2.4286/1.1106)	mem 24308MB
[2025-01-19 01:51:57 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][250/312]	eta 0:00:37 lr 0.000653	time 0.5887 (0.6124)	model_time 0.5886 (0.6068)	loss 3.2734 (2.9858)	grad_norm 1.3802 (2.4258/1.1019)	mem 24308MB
[2025-01-19 01:52:02 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][260/312]	eta 0:00:31 lr 0.000652	time 0.6118 (0.6117)	model_time 0.6114 (0.6062)	loss 3.6495 (2.9882)	grad_norm 1.6487 (2.4222/1.0944)	mem 24308MB
[2025-01-19 01:52:08 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][270/312]	eta 0:00:25 lr 0.000652	time 0.6341 (0.6112)	model_time 0.6337 (0.6060)	loss 2.7201 (2.9878)	grad_norm 2.0745 (2.4125/1.0846)	mem 24308MB
[2025-01-19 01:52:14 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][280/312]	eta 0:00:19 lr 0.000651	time 0.5674 (0.6109)	model_time 0.5670 (0.6059)	loss 2.2889 (2.9921)	grad_norm 1.9729 (2.3855/1.0776)	mem 24308MB
[2025-01-19 01:52:20 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][290/312]	eta 0:00:13 lr 0.000651	time 0.5760 (0.6106)	model_time 0.5759 (0.6057)	loss 1.8460 (2.9912)	grad_norm 1.6285 (2.3728/1.0665)	mem 24308MB
[2025-01-19 01:52:26 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][300/312]	eta 0:00:07 lr 0.000650	time 0.5691 (0.6097)	model_time 0.5690 (0.6049)	loss 2.5992 (2.9846)	grad_norm 1.9275 (2.3688/1.0585)	mem 24308MB
[2025-01-19 01:52:32 internimage_s_1k_224] (main.py 510): INFO Train: [222/300][310/312]	eta 0:00:01 lr 0.000650	time 0.6940 (0.6098)	model_time 0.6939 (0.6052)	loss 3.3262 (2.9791)	grad_norm 4.0041 (2.3819/1.0630)	mem 24308MB
[2025-01-19 01:52:33 internimage_s_1k_224] (main.py 519): INFO EPOCH 222 training takes 0:03:10
[2025-01-19 01:52:33 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_222.pth saving......
[2025-01-19 01:52:35 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_222.pth saved !!!
[2025-01-19 01:52:48 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 13.376 (13.376)	Loss 0.7332 (0.7332)	Acc@1 84.595 (84.595)	Acc@5 97.510 (97.510)	Mem 24308MB
[2025-01-19 01:52:56 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.862)	Loss 0.9288 (0.8155)	Acc@1 78.589 (82.537)	Acc@5 95.532 (96.351)	Mem 24308MB
[2025-01-19 01:52:56 internimage_s_1k_224] (main.py 575): INFO [Epoch:222] * Acc@1 82.408 Acc@5 96.371
[2025-01-19 01:52:56 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.4%
[2025-01-19 01:52:56 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.42%
[2025-01-19 01:53:12 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.140 (16.140)	Loss 0.7052 (0.7052)	Acc@1 85.254 (85.254)	Acc@5 97.778 (97.778)	Mem 24308MB
[2025-01-19 01:53:21 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (2.279)	Loss 0.9235 (0.7928)	Acc@1 78.442 (82.755)	Acc@5 95.679 (96.467)	Mem 24308MB
[2025-01-19 01:53:21 internimage_s_1k_224] (main.py 575): INFO [Epoch:222] * Acc@1 82.632 Acc@5 96.491
[2025-01-19 01:53:21 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.6%
[2025-01-19 01:53:21 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:53:23 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:53:23 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.63%
[2025-01-19 01:53:25 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][0/312]	eta 0:11:09 lr 0.000650	time 2.1461 (2.1461)	model_time 0.6001 (0.6001)	loss 2.7557 (2.7557)	grad_norm 2.3557 (2.3557/0.0000)	mem 24308MB
[2025-01-19 01:53:31 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][10/312]	eta 0:03:46 lr 0.000649	time 0.6099 (0.7484)	model_time 0.6098 (0.6075)	loss 2.5477 (2.7951)	grad_norm 3.4140 (3.3150/1.2820)	mem 24308MB
[2025-01-19 01:53:37 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][20/312]	eta 0:03:19 lr 0.000649	time 0.5870 (0.6838)	model_time 0.5868 (0.6099)	loss 3.1977 (2.9237)	grad_norm 2.8190 (3.0954/1.0861)	mem 24308MB
[2025-01-19 01:53:44 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][30/312]	eta 0:03:08 lr 0.000648	time 0.5931 (0.6692)	model_time 0.5929 (0.6190)	loss 2.7750 (2.8896)	grad_norm 1.8391 (3.0481/1.2501)	mem 24308MB
[2025-01-19 01:53:50 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][40/312]	eta 0:02:56 lr 0.000648	time 0.5822 (0.6504)	model_time 0.5818 (0.6123)	loss 3.1406 (2.9291)	grad_norm 2.0369 (3.0649/1.2524)	mem 24308MB
[2025-01-19 01:53:56 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][50/312]	eta 0:02:48 lr 0.000647	time 0.5817 (0.6427)	model_time 0.5815 (0.6120)	loss 2.8870 (2.8882)	grad_norm 1.8203 (2.9317/1.2599)	mem 24308MB
[2025-01-19 01:54:02 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][60/312]	eta 0:02:40 lr 0.000647	time 0.5940 (0.6353)	model_time 0.5938 (0.6096)	loss 2.8639 (2.9013)	grad_norm 2.4445 (2.7821/1.2148)	mem 24308MB
[2025-01-19 01:54:08 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][70/312]	eta 0:02:32 lr 0.000646	time 0.5913 (0.6289)	model_time 0.5911 (0.6067)	loss 2.3146 (2.8960)	grad_norm 1.9134 (2.6400/1.1886)	mem 24308MB
[2025-01-19 01:54:14 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][80/312]	eta 0:02:25 lr 0.000646	time 0.5848 (0.6250)	model_time 0.5844 (0.6056)	loss 2.8288 (2.8931)	grad_norm 2.6063 (2.5456/1.1624)	mem 24308MB
[2025-01-19 01:54:20 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][90/312]	eta 0:02:18 lr 0.000645	time 0.5705 (0.6236)	model_time 0.5704 (0.6062)	loss 3.6106 (2.9134)	grad_norm 1.2615 (2.5616/1.1551)	mem 24308MB
[2025-01-19 01:54:26 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][100/312]	eta 0:02:11 lr 0.000645	time 0.5763 (0.6210)	model_time 0.5759 (0.6053)	loss 3.2762 (2.9041)	grad_norm 3.7640 (2.6318/1.1552)	mem 24308MB
[2025-01-19 01:54:32 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][110/312]	eta 0:02:04 lr 0.000644	time 0.5883 (0.6188)	model_time 0.5881 (0.6045)	loss 2.6643 (2.9206)	grad_norm 2.2223 (2.6941/1.1600)	mem 24308MB
[2025-01-19 01:54:38 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][120/312]	eta 0:01:58 lr 0.000644	time 0.6690 (0.6194)	model_time 0.6685 (0.6063)	loss 2.9034 (2.9231)	grad_norm 2.6329 (2.7281/1.1759)	mem 24308MB
[2025-01-19 01:54:44 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][130/312]	eta 0:01:52 lr 0.000643	time 0.5776 (0.6182)	model_time 0.5774 (0.6061)	loss 3.6740 (2.9358)	grad_norm 3.2036 (2.6951/1.1485)	mem 24308MB
[2025-01-19 01:54:50 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][140/312]	eta 0:01:46 lr 0.000643	time 0.5820 (0.6178)	model_time 0.5818 (0.6065)	loss 3.2386 (2.9428)	grad_norm 1.8892 (2.6253/1.1397)	mem 24308MB
[2025-01-19 01:54:57 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][150/312]	eta 0:01:40 lr 0.000642	time 0.5717 (0.6207)	model_time 0.5715 (0.6101)	loss 2.7856 (2.9328)	grad_norm 1.8036 (2.5592/1.1315)	mem 24308MB
[2025-01-19 01:55:03 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][160/312]	eta 0:01:34 lr 0.000642	time 0.5954 (0.6203)	model_time 0.5950 (0.6103)	loss 3.7041 (2.9579)	grad_norm 4.3810 (2.5361/1.1206)	mem 24308MB
[2025-01-19 01:55:09 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][170/312]	eta 0:01:28 lr 0.000641	time 0.5901 (0.6207)	model_time 0.5897 (0.6113)	loss 2.4229 (2.9647)	grad_norm 2.1223 (2.5425/1.1098)	mem 24308MB
[2025-01-19 01:55:15 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][180/312]	eta 0:01:21 lr 0.000641	time 0.5833 (0.6189)	model_time 0.5832 (0.6100)	loss 2.0621 (2.9651)	grad_norm 2.0528 (2.5036/1.0942)	mem 24308MB
[2025-01-19 01:55:21 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][190/312]	eta 0:01:15 lr 0.000640	time 0.6058 (0.6177)	model_time 0.6056 (0.6092)	loss 3.2413 (2.9837)	grad_norm 4.5643 (2.5128/1.0839)	mem 24308MB
[2025-01-19 01:55:27 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][200/312]	eta 0:01:09 lr 0.000640	time 0.5819 (0.6170)	model_time 0.5818 (0.6089)	loss 3.2963 (2.9751)	grad_norm 1.7789 (2.4873/1.0713)	mem 24308MB
[2025-01-19 01:55:33 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][210/312]	eta 0:01:02 lr 0.000640	time 0.5714 (0.6174)	model_time 0.5713 (0.6097)	loss 3.1518 (2.9628)	grad_norm 2.2036 (2.4731/1.0552)	mem 24308MB
[2025-01-19 01:55:39 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][220/312]	eta 0:00:56 lr 0.000639	time 0.5928 (0.6162)	model_time 0.5927 (0.6089)	loss 2.3649 (2.9652)	grad_norm 2.1433 (2.4846/1.0530)	mem 24308MB
[2025-01-19 01:55:45 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][230/312]	eta 0:00:50 lr 0.000639	time 0.5943 (0.6150)	model_time 0.5939 (0.6080)	loss 2.8769 (2.9710)	grad_norm 3.0735 (2.4730/1.0423)	mem 24308MB
[2025-01-19 01:55:51 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][240/312]	eta 0:00:44 lr 0.000638	time 0.5800 (0.6148)	model_time 0.5796 (0.6080)	loss 2.9995 (2.9632)	grad_norm 4.2341 (2.4949/1.0398)	mem 24308MB
[2025-01-19 01:55:57 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][250/312]	eta 0:00:38 lr 0.000638	time 0.5847 (0.6142)	model_time 0.5843 (0.6077)	loss 1.9010 (2.9618)	grad_norm 3.3981 (2.5328/1.0613)	mem 24308MB
[2025-01-19 01:56:04 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][260/312]	eta 0:00:31 lr 0.000637	time 0.5798 (0.6147)	model_time 0.5796 (0.6084)	loss 2.4831 (2.9602)	grad_norm 3.9267 (2.5589/1.0698)	mem 24308MB
[2025-01-19 01:56:10 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][270/312]	eta 0:00:25 lr 0.000637	time 0.5771 (0.6153)	model_time 0.5766 (0.6093)	loss 3.0048 (2.9675)	grad_norm 3.0274 (2.5858/1.1017)	mem 24308MB
[2025-01-19 01:56:16 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][280/312]	eta 0:00:19 lr 0.000636	time 0.5865 (0.6146)	model_time 0.5861 (0.6087)	loss 3.2841 (2.9624)	grad_norm 5.9311 (2.6190/1.1368)	mem 24308MB
[2025-01-19 01:56:22 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][290/312]	eta 0:00:13 lr 0.000636	time 0.6668 (0.6149)	model_time 0.6667 (0.6092)	loss 3.1127 (2.9659)	grad_norm 1.5157 (2.6356/1.1567)	mem 24308MB
[2025-01-19 01:56:28 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][300/312]	eta 0:00:07 lr 0.000635	time 0.5680 (0.6140)	model_time 0.5679 (0.6085)	loss 2.3787 (2.9469)	grad_norm 3.2108 (2.6406/1.1471)	mem 24308MB
[2025-01-19 01:56:34 internimage_s_1k_224] (main.py 510): INFO Train: [223/300][310/312]	eta 0:00:01 lr 0.000635	time 0.5692 (0.6128)	model_time 0.5691 (0.6075)	loss 3.3135 (2.9480)	grad_norm 1.2063 (2.6104/1.1201)	mem 24308MB
[2025-01-19 01:56:34 internimage_s_1k_224] (main.py 519): INFO EPOCH 223 training takes 0:03:11
[2025-01-19 01:56:34 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_223.pth saving......
[2025-01-19 01:56:36 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_223.pth saved !!!
[2025-01-19 01:56:44 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.764 (7.764)	Loss 0.7487 (0.7487)	Acc@1 84.912 (84.912)	Acc@5 97.388 (97.388)	Mem 24308MB
[2025-01-19 01:56:48 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.023)	Loss 0.9679 (0.8421)	Acc@1 78.687 (82.664)	Acc@5 95.264 (96.367)	Mem 24308MB
[2025-01-19 01:56:48 internimage_s_1k_224] (main.py 575): INFO [Epoch:223] * Acc@1 82.482 Acc@5 96.381
[2025-01-19 01:56:48 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.5%
[2025-01-19 01:56:48 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 01:56:50 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 01:56:50 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.48%
[2025-01-19 01:56:57 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.696 (7.696)	Loss 0.7051 (0.7051)	Acc@1 85.278 (85.278)	Acc@5 97.778 (97.778)	Mem 24308MB
[2025-01-19 01:57:01 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.038)	Loss 0.9222 (0.7922)	Acc@1 78.516 (82.788)	Acc@5 95.679 (96.489)	Mem 24308MB
[2025-01-19 01:57:01 internimage_s_1k_224] (main.py 575): INFO [Epoch:223] * Acc@1 82.666 Acc@5 96.515
[2025-01-19 01:57:01 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.7%
[2025-01-19 01:57:01 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 01:57:03 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 01:57:03 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.67%
[2025-01-19 01:57:06 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][0/312]	eta 0:11:55 lr 0.000635	time 2.2937 (2.2937)	model_time 0.6071 (0.6071)	loss 3.3025 (3.3025)	grad_norm 1.2104 (1.2104/0.0000)	mem 24308MB
[2025-01-19 01:57:12 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][10/312]	eta 0:03:47 lr 0.000634	time 0.5851 (0.7536)	model_time 0.5849 (0.6000)	loss 3.4181 (2.9788)	grad_norm 1.7198 (1.5835/0.4428)	mem 24308MB
[2025-01-19 01:57:18 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][20/312]	eta 0:03:21 lr 0.000634	time 0.5826 (0.6889)	model_time 0.5825 (0.6083)	loss 3.2257 (2.9858)	grad_norm 1.2633 (1.6302/0.4714)	mem 24308MB
[2025-01-19 01:57:24 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][30/312]	eta 0:03:06 lr 0.000633	time 0.5873 (0.6606)	model_time 0.5872 (0.6058)	loss 2.5739 (2.9649)	grad_norm 3.0690 (1.7842/0.5983)	mem 24308MB
[2025-01-19 01:57:30 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][40/312]	eta 0:02:54 lr 0.000633	time 0.5888 (0.6430)	model_time 0.5883 (0.6015)	loss 3.6518 (2.9861)	grad_norm 2.0815 (1.9669/0.7262)	mem 24308MB
[2025-01-19 01:57:36 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][50/312]	eta 0:02:47 lr 0.000632	time 0.6436 (0.6393)	model_time 0.6434 (0.6059)	loss 3.2532 (3.0124)	grad_norm 2.7557 (1.9840/0.6884)	mem 24308MB
[2025-01-19 01:57:42 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][60/312]	eta 0:02:39 lr 0.000632	time 0.5649 (0.6333)	model_time 0.5647 (0.6053)	loss 3.0560 (2.9805)	grad_norm 5.2308 (2.2688/0.9854)	mem 24308MB
[2025-01-19 01:57:48 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][70/312]	eta 0:02:33 lr 0.000631	time 0.6564 (0.6340)	model_time 0.6560 (0.6098)	loss 2.1786 (2.9833)	grad_norm 3.7572 (2.3424/1.0437)	mem 24308MB
[2025-01-19 01:57:55 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][80/312]	eta 0:02:26 lr 0.000631	time 0.6755 (0.6333)	model_time 0.6751 (0.6121)	loss 2.6184 (2.9606)	grad_norm 3.8645 (2.3763/1.0114)	mem 24308MB
[2025-01-19 01:58:01 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][90/312]	eta 0:02:20 lr 0.000630	time 0.6639 (0.6315)	model_time 0.6634 (0.6126)	loss 2.1783 (2.9533)	grad_norm 3.1624 (2.4260/1.0231)	mem 24308MB
[2025-01-19 01:58:07 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][100/312]	eta 0:02:13 lr 0.000630	time 0.6806 (0.6297)	model_time 0.6805 (0.6127)	loss 2.1895 (2.9324)	grad_norm 3.1559 (2.4053/0.9975)	mem 24308MB
[2025-01-19 01:58:13 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][110/312]	eta 0:02:06 lr 0.000629	time 0.5828 (0.6262)	model_time 0.5824 (0.6106)	loss 3.2684 (2.9353)	grad_norm 1.1672 (2.4194/1.0106)	mem 24308MB
[2025-01-19 01:58:19 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][120/312]	eta 0:01:59 lr 0.000629	time 0.5916 (0.6239)	model_time 0.5914 (0.6096)	loss 3.0588 (2.9151)	grad_norm 1.5859 (2.3653/0.9917)	mem 24308MB
[2025-01-19 01:58:25 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][130/312]	eta 0:01:53 lr 0.000629	time 0.5736 (0.6216)	model_time 0.5731 (0.6084)	loss 3.3464 (2.9287)	grad_norm 1.9792 (2.3309/0.9768)	mem 24308MB
[2025-01-19 01:58:31 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][140/312]	eta 0:01:46 lr 0.000628	time 0.5862 (0.6209)	model_time 0.5860 (0.6086)	loss 3.0997 (2.9211)	grad_norm 2.6215 (2.3189/0.9658)	mem 24308MB
[2025-01-19 01:58:37 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][150/312]	eta 0:01:40 lr 0.000628	time 0.5706 (0.6193)	model_time 0.5704 (0.6077)	loss 2.4303 (2.9059)	grad_norm 2.5767 (2.3046/0.9477)	mem 24308MB
[2025-01-19 01:58:43 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][160/312]	eta 0:01:33 lr 0.000627	time 0.5845 (0.6174)	model_time 0.5841 (0.6066)	loss 3.0930 (2.9171)	grad_norm 3.6267 (2.3497/0.9640)	mem 24308MB
[2025-01-19 01:58:49 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][170/312]	eta 0:01:27 lr 0.000627	time 0.6600 (0.6165)	model_time 0.6598 (0.6062)	loss 2.1472 (2.9151)	grad_norm 3.5041 (2.3564/0.9589)	mem 24308MB
[2025-01-19 01:58:55 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][180/312]	eta 0:01:21 lr 0.000626	time 0.5874 (0.6172)	model_time 0.5869 (0.6075)	loss 3.2987 (2.9210)	grad_norm 2.9363 (2.3671/0.9581)	mem 24308MB
[2025-01-19 01:59:01 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][190/312]	eta 0:01:15 lr 0.000626	time 0.6740 (0.6176)	model_time 0.6736 (0.6084)	loss 3.3972 (2.9383)	grad_norm 2.4542 (2.3454/0.9454)	mem 24308MB
[2025-01-19 01:59:08 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][200/312]	eta 0:01:09 lr 0.000625	time 0.6748 (0.6181)	model_time 0.6746 (0.6094)	loss 2.9989 (2.9405)	grad_norm 1.4879 (2.3509/0.9499)	mem 24308MB
[2025-01-19 01:59:14 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][210/312]	eta 0:01:03 lr 0.000625	time 0.6089 (0.6177)	model_time 0.6087 (0.6093)	loss 2.8172 (2.9250)	grad_norm 3.2356 (2.3247/0.9429)	mem 24308MB
[2025-01-19 01:59:20 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][220/312]	eta 0:00:56 lr 0.000624	time 0.6617 (0.6172)	model_time 0.6613 (0.6091)	loss 2.0650 (2.9254)	grad_norm 2.3481 (2.3425/0.9556)	mem 24308MB
[2025-01-19 01:59:26 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][230/312]	eta 0:00:50 lr 0.000624	time 0.5732 (0.6168)	model_time 0.5730 (0.6091)	loss 2.4681 (2.9319)	grad_norm 1.2508 (2.3408/0.9548)	mem 24308MB
[2025-01-19 01:59:32 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][240/312]	eta 0:00:44 lr 0.000623	time 0.5805 (0.6160)	model_time 0.5800 (0.6086)	loss 2.2465 (2.9354)	grad_norm 2.6326 (2.3722/0.9729)	mem 24308MB
[2025-01-19 01:59:38 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][250/312]	eta 0:00:38 lr 0.000623	time 0.5776 (0.6155)	model_time 0.5771 (0.6084)	loss 2.2012 (2.9270)	grad_norm 2.5130 (2.3945/0.9728)	mem 24308MB
[2025-01-19 01:59:44 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][260/312]	eta 0:00:32 lr 0.000622	time 0.6662 (0.6158)	model_time 0.6660 (0.6089)	loss 3.7478 (2.9341)	grad_norm 1.4465 (2.3832/0.9710)	mem 24308MB
[2025-01-19 01:59:50 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][270/312]	eta 0:00:25 lr 0.000622	time 0.5920 (0.6153)	model_time 0.5918 (0.6086)	loss 3.2591 (2.9416)	grad_norm 2.0832 (2.3570/0.9645)	mem 24308MB
[2025-01-19 01:59:56 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][280/312]	eta 0:00:19 lr 0.000621	time 0.5869 (0.6145)	model_time 0.5865 (0.6081)	loss 2.8595 (2.9393)	grad_norm 1.1589 (2.3391/0.9621)	mem 24308MB
[2025-01-19 02:00:02 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][290/312]	eta 0:00:13 lr 0.000621	time 0.6677 (0.6141)	model_time 0.6675 (0.6079)	loss 3.1443 (2.9340)	grad_norm 1.1741 (2.3357/0.9735)	mem 24308MB
[2025-01-19 02:00:08 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][300/312]	eta 0:00:07 lr 0.000620	time 0.5674 (0.6136)	model_time 0.5673 (0.6076)	loss 3.1041 (2.9387)	grad_norm 4.7540 (2.3528/0.9818)	mem 24308MB
[2025-01-19 02:00:14 internimage_s_1k_224] (main.py 510): INFO Train: [224/300][310/312]	eta 0:00:01 lr 0.000620	time 0.5670 (0.6132)	model_time 0.5669 (0.6074)	loss 2.4509 (2.9424)	grad_norm 2.8500 (2.4084/0.9947)	mem 24308MB
[2025-01-19 02:00:15 internimage_s_1k_224] (main.py 519): INFO EPOCH 224 training takes 0:03:11
[2025-01-19 02:00:15 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_224.pth saving......
[2025-01-19 02:00:16 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_224.pth saved !!!
[2025-01-19 02:00:24 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.860 (7.860)	Loss 0.7198 (0.7198)	Acc@1 85.010 (85.010)	Acc@5 97.681 (97.681)	Mem 24308MB
[2025-01-19 02:00:28 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.040)	Loss 0.9443 (0.8174)	Acc@1 78.149 (82.646)	Acc@5 95.435 (96.404)	Mem 24308MB
[2025-01-19 02:00:28 internimage_s_1k_224] (main.py 575): INFO [Epoch:224] * Acc@1 82.556 Acc@5 96.437
[2025-01-19 02:00:28 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.6%
[2025-01-19 02:00:28 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 02:00:30 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 02:00:30 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.56%
[2025-01-19 02:00:38 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.871 (7.871)	Loss 0.7049 (0.7049)	Acc@1 85.352 (85.352)	Acc@5 97.778 (97.778)	Mem 24308MB
[2025-01-19 02:00:42 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.043)	Loss 0.9210 (0.7916)	Acc@1 78.564 (82.830)	Acc@5 95.654 (96.491)	Mem 24308MB
[2025-01-19 02:00:42 internimage_s_1k_224] (main.py 575): INFO [Epoch:224] * Acc@1 82.700 Acc@5 96.515
[2025-01-19 02:00:42 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.7%
[2025-01-19 02:00:42 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:00:44 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:00:44 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.70%
[2025-01-19 02:00:46 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][0/312]	eta 0:11:46 lr 0.000620	time 2.2638 (2.2638)	model_time 0.5850 (0.5850)	loss 2.8084 (2.8084)	grad_norm 1.8461 (1.8461/0.0000)	mem 24308MB
[2025-01-19 02:00:53 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][10/312]	eta 0:03:56 lr 0.000619	time 0.6675 (0.7824)	model_time 0.6674 (0.6296)	loss 3.1950 (2.9506)	grad_norm 1.6714 (2.2025/0.7517)	mem 24308MB
[2025-01-19 02:00:59 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][20/312]	eta 0:03:23 lr 0.000619	time 0.5967 (0.6973)	model_time 0.5965 (0.6171)	loss 3.5551 (2.9249)	grad_norm 1.1631 (2.0994/0.7187)	mem 24308MB
[2025-01-19 02:01:05 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][30/312]	eta 0:03:10 lr 0.000619	time 0.6013 (0.6764)	model_time 0.6011 (0.6219)	loss 3.4036 (2.8790)	grad_norm 1.8229 (2.0822/0.7605)	mem 24308MB
[2025-01-19 02:01:11 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][40/312]	eta 0:02:59 lr 0.000618	time 0.5937 (0.6602)	model_time 0.5935 (0.6189)	loss 3.1725 (2.9409)	grad_norm 4.5986 (2.0280/0.8310)	mem 24308MB
[2025-01-19 02:01:17 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][50/312]	eta 0:02:50 lr 0.000618	time 0.5666 (0.6490)	model_time 0.5664 (0.6158)	loss 1.7681 (2.9001)	grad_norm 1.6566 (2.1417/0.9860)	mem 24308MB
[2025-01-19 02:01:23 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][60/312]	eta 0:02:41 lr 0.000617	time 0.5775 (0.6410)	model_time 0.5773 (0.6131)	loss 2.9628 (2.8797)	grad_norm 3.1665 (2.3348/1.1287)	mem 24308MB
[2025-01-19 02:01:29 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][70/312]	eta 0:02:33 lr 0.000617	time 0.5819 (0.6360)	model_time 0.5815 (0.6120)	loss 3.0072 (2.9040)	grad_norm 2.7358 (2.3616/1.1248)	mem 24308MB
[2025-01-19 02:01:35 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][80/312]	eta 0:02:26 lr 0.000616	time 0.5974 (0.6318)	model_time 0.5970 (0.6108)	loss 2.1166 (2.8845)	grad_norm 1.5472 (2.3214/1.0812)	mem 24308MB
[2025-01-19 02:01:41 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][90/312]	eta 0:02:19 lr 0.000616	time 0.5957 (0.6269)	model_time 0.5955 (0.6081)	loss 3.4307 (2.9066)	grad_norm 3.2001 (2.2966/1.0551)	mem 24308MB
[2025-01-19 02:01:47 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][100/312]	eta 0:02:12 lr 0.000615	time 0.6018 (0.6236)	model_time 0.6014 (0.6066)	loss 2.6674 (2.9340)	grad_norm 4.8853 (2.4014/1.1284)	mem 24308MB
[2025-01-19 02:01:53 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][110/312]	eta 0:02:05 lr 0.000615	time 0.7014 (0.6236)	model_time 0.7012 (0.6081)	loss 2.2926 (2.9253)	grad_norm 1.5913 (2.3629/1.0931)	mem 24308MB
[2025-01-19 02:02:00 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][120/312]	eta 0:01:59 lr 0.000614	time 0.5702 (0.6229)	model_time 0.5697 (0.6087)	loss 2.8394 (2.9241)	grad_norm 1.6416 (2.3362/1.0587)	mem 24308MB
[2025-01-19 02:02:06 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][130/312]	eta 0:01:53 lr 0.000614	time 0.6911 (0.6238)	model_time 0.6908 (0.6106)	loss 3.3616 (2.9327)	grad_norm 1.8904 (2.3406/1.0600)	mem 24308MB
[2025-01-19 02:02:12 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][140/312]	eta 0:01:47 lr 0.000613	time 0.5895 (0.6226)	model_time 0.5893 (0.6103)	loss 3.1955 (2.9451)	grad_norm 3.2679 (2.3507/1.0497)	mem 24308MB
[2025-01-19 02:02:18 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][150/312]	eta 0:01:40 lr 0.000613	time 0.5790 (0.6211)	model_time 0.5785 (0.6096)	loss 2.2451 (2.9594)	grad_norm 1.5293 (2.3272/1.0232)	mem 24308MB
[2025-01-19 02:02:24 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][160/312]	eta 0:01:34 lr 0.000612	time 0.5862 (0.6206)	model_time 0.5860 (0.6098)	loss 2.2306 (2.9601)	grad_norm 2.3604 (2.3437/1.0076)	mem 24308MB
[2025-01-19 02:02:30 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][170/312]	eta 0:01:28 lr 0.000612	time 0.6067 (0.6201)	model_time 0.6065 (0.6099)	loss 3.6161 (2.9570)	grad_norm 1.9639 (2.3414/0.9926)	mem 24308MB
[2025-01-19 02:02:36 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][180/312]	eta 0:01:21 lr 0.000611	time 0.5932 (0.6191)	model_time 0.5930 (0.6095)	loss 3.0617 (2.9712)	grad_norm 1.5602 (2.3229/0.9734)	mem 24308MB
[2025-01-19 02:02:42 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][190/312]	eta 0:01:15 lr 0.000611	time 0.6196 (0.6186)	model_time 0.6191 (0.6094)	loss 2.9705 (2.9815)	grad_norm 2.7494 (2.3615/1.0072)	mem 24308MB
[2025-01-19 02:02:48 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][200/312]	eta 0:01:09 lr 0.000611	time 0.5944 (0.6175)	model_time 0.5942 (0.6088)	loss 3.2606 (2.9783)	grad_norm 1.2281 (2.3677/1.0086)	mem 24308MB
[2025-01-19 02:02:54 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][210/312]	eta 0:01:02 lr 0.000610	time 0.5797 (0.6161)	model_time 0.5793 (0.6078)	loss 2.9789 (2.9853)	grad_norm 2.2767 (2.3746/1.0093)	mem 24308MB
[2025-01-19 02:03:00 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][220/312]	eta 0:00:56 lr 0.000610	time 0.5963 (0.6152)	model_time 0.5958 (0.6072)	loss 3.0774 (2.9912)	grad_norm 1.2542 (2.3746/0.9973)	mem 24308MB
[2025-01-19 02:03:06 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][230/312]	eta 0:00:50 lr 0.000609	time 0.6720 (0.6160)	model_time 0.6718 (0.6083)	loss 3.0393 (2.9865)	grad_norm 1.7175 (2.3696/0.9848)	mem 24308MB
[2025-01-19 02:03:12 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][240/312]	eta 0:00:44 lr 0.000609	time 0.6695 (0.6153)	model_time 0.6693 (0.6080)	loss 2.6863 (2.9846)	grad_norm 1.3092 (2.3532/0.9815)	mem 24308MB
[2025-01-19 02:03:19 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][250/312]	eta 0:00:38 lr 0.000608	time 0.5868 (0.6159)	model_time 0.5867 (0.6088)	loss 3.2380 (2.9882)	grad_norm 1.1420 (2.3570/0.9862)	mem 24308MB
[2025-01-19 02:03:25 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][260/312]	eta 0:00:32 lr 0.000608	time 0.6000 (0.6156)	model_time 0.5998 (0.6088)	loss 2.7848 (2.9926)	grad_norm 2.0993 (2.3519/0.9730)	mem 24308MB
[2025-01-19 02:03:31 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][270/312]	eta 0:00:25 lr 0.000607	time 0.6195 (0.6155)	model_time 0.6193 (0.6089)	loss 2.9687 (2.9878)	grad_norm 2.4964 (2.3459/0.9683)	mem 24308MB
[2025-01-19 02:03:37 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][280/312]	eta 0:00:19 lr 0.000607	time 0.6048 (0.6155)	model_time 0.6046 (0.6091)	loss 3.2239 (2.9903)	grad_norm 3.3876 (2.3349/0.9716)	mem 24308MB
[2025-01-19 02:03:43 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][290/312]	eta 0:00:13 lr 0.000606	time 0.5748 (0.6155)	model_time 0.5747 (0.6093)	loss 3.5027 (2.9859)	grad_norm 1.1487 (2.3220/0.9693)	mem 24308MB
[2025-01-19 02:03:49 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][300/312]	eta 0:00:07 lr 0.000606	time 0.5809 (0.6152)	model_time 0.5809 (0.6092)	loss 3.0327 (2.9818)	grad_norm 2.1400 (2.3134/0.9613)	mem 24308MB
[2025-01-19 02:03:55 internimage_s_1k_224] (main.py 510): INFO Train: [225/300][310/312]	eta 0:00:01 lr 0.000605	time 0.5731 (0.6140)	model_time 0.5731 (0.6082)	loss 2.2006 (2.9820)	grad_norm 1.3181 (2.3293/0.9794)	mem 24308MB
[2025-01-19 02:03:56 internimage_s_1k_224] (main.py 519): INFO EPOCH 225 training takes 0:03:11
[2025-01-19 02:03:56 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_225.pth saving......
[2025-01-19 02:03:58 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_225.pth saved !!!
[2025-01-19 02:04:05 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.762 (7.762)	Loss 0.7357 (0.7357)	Acc@1 85.303 (85.303)	Acc@5 97.778 (97.778)	Mem 24308MB
[2025-01-19 02:04:09 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.041)	Loss 0.9505 (0.8401)	Acc@1 79.272 (82.702)	Acc@5 95.605 (96.473)	Mem 24308MB
[2025-01-19 02:04:09 internimage_s_1k_224] (main.py 575): INFO [Epoch:225] * Acc@1 82.544 Acc@5 96.483
[2025-01-19 02:04:09 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.5%
[2025-01-19 02:04:09 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.56%
[2025-01-19 02:04:18 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.043 (9.043)	Loss 0.7047 (0.7047)	Acc@1 85.376 (85.376)	Acc@5 97.778 (97.778)	Mem 24308MB
[2025-01-19 02:04:23 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (1.216)	Loss 0.9197 (0.7909)	Acc@1 78.589 (82.855)	Acc@5 95.654 (96.495)	Mem 24308MB
[2025-01-19 02:04:23 internimage_s_1k_224] (main.py 575): INFO [Epoch:225] * Acc@1 82.726 Acc@5 96.521
[2025-01-19 02:04:23 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.7%
[2025-01-19 02:04:23 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:04:25 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:04:25 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.73%
[2025-01-19 02:04:27 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][0/312]	eta 0:10:57 lr 0.000605	time 2.1077 (2.1077)	model_time 0.6050 (0.6050)	loss 3.0991 (3.0991)	grad_norm 2.7412 (2.7412/0.0000)	mem 24308MB
[2025-01-19 02:04:33 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][10/312]	eta 0:03:42 lr 0.000605	time 0.6552 (0.7364)	model_time 0.6551 (0.5996)	loss 2.8884 (3.0903)	grad_norm 2.3235 (2.7065/1.0152)	mem 24308MB
[2025-01-19 02:04:39 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][20/312]	eta 0:03:14 lr 0.000604	time 0.5799 (0.6656)	model_time 0.5796 (0.5937)	loss 3.3881 (3.1358)	grad_norm 2.7213 (2.6173/1.1623)	mem 24308MB
[2025-01-19 02:04:45 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][30/312]	eta 0:03:02 lr 0.000604	time 0.5870 (0.6460)	model_time 0.5868 (0.5972)	loss 1.7573 (3.1494)	grad_norm 4.6978 (3.1393/1.5642)	mem 24308MB
[2025-01-19 02:04:51 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][40/312]	eta 0:02:53 lr 0.000603	time 0.5881 (0.6375)	model_time 0.5879 (0.6005)	loss 2.1648 (3.0478)	grad_norm 1.7532 (3.0047/1.5398)	mem 24308MB
[2025-01-19 02:04:57 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][50/312]	eta 0:02:45 lr 0.000603	time 0.6562 (0.6321)	model_time 0.6558 (0.6023)	loss 2.0310 (3.0616)	grad_norm 3.9384 (2.9378/1.4839)	mem 24308MB
[2025-01-19 02:05:04 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][60/312]	eta 0:02:38 lr 0.000603	time 0.5771 (0.6309)	model_time 0.5769 (0.6060)	loss 2.9339 (3.0639)	grad_norm 2.7771 (2.9109/1.3682)	mem 24308MB
[2025-01-19 02:05:10 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][70/312]	eta 0:02:31 lr 0.000602	time 0.5745 (0.6276)	model_time 0.5744 (0.6062)	loss 2.2044 (3.0356)	grad_norm 2.3281 (2.9592/1.4791)	mem 24308MB
[2025-01-19 02:05:16 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][80/312]	eta 0:02:24 lr 0.000602	time 0.5764 (0.6245)	model_time 0.5763 (0.6057)	loss 3.0192 (3.0331)	grad_norm 1.6516 (2.8647/1.4271)	mem 24308MB
[2025-01-19 02:05:22 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][90/312]	eta 0:02:18 lr 0.000601	time 0.6096 (0.6234)	model_time 0.6094 (0.6065)	loss 2.2878 (3.0463)	grad_norm 1.7978 (2.8004/1.3808)	mem 24308MB
[2025-01-19 02:05:28 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][100/312]	eta 0:02:11 lr 0.000601	time 0.5798 (0.6207)	model_time 0.5796 (0.6055)	loss 3.2343 (3.0477)	grad_norm 2.3154 (2.7419/1.3374)	mem 24308MB
[2025-01-19 02:05:34 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][110/312]	eta 0:02:05 lr 0.000600	time 0.5851 (0.6196)	model_time 0.5849 (0.6057)	loss 3.2198 (3.0282)	grad_norm 1.3872 (2.7008/1.2988)	mem 24308MB
[2025-01-19 02:05:40 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][120/312]	eta 0:01:58 lr 0.000600	time 0.5728 (0.6186)	model_time 0.5726 (0.6059)	loss 2.8822 (3.0153)	grad_norm 5.0765 (2.7105/1.3061)	mem 24308MB
[2025-01-19 02:05:46 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][130/312]	eta 0:01:52 lr 0.000599	time 0.6026 (0.6167)	model_time 0.6024 (0.6047)	loss 2.2708 (3.0124)	grad_norm 1.5217 (2.7567/1.3278)	mem 24308MB
[2025-01-19 02:05:52 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][140/312]	eta 0:01:45 lr 0.000599	time 0.5747 (0.6156)	model_time 0.5745 (0.6045)	loss 3.3753 (3.0093)	grad_norm 4.5961 (2.7498/1.3097)	mem 24308MB
[2025-01-19 02:05:58 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][150/312]	eta 0:01:39 lr 0.000598	time 0.6204 (0.6149)	model_time 0.6199 (0.6045)	loss 3.0803 (3.0115)	grad_norm 5.2099 (2.7691/1.3270)	mem 24308MB
[2025-01-19 02:06:04 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][160/312]	eta 0:01:33 lr 0.000598	time 0.5800 (0.6151)	model_time 0.5797 (0.6053)	loss 3.3342 (3.0186)	grad_norm 3.3345 (2.8088/1.3319)	mem 24308MB
[2025-01-19 02:06:10 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][170/312]	eta 0:01:27 lr 0.000597	time 0.6862 (0.6152)	model_time 0.6860 (0.6060)	loss 2.1949 (3.0220)	grad_norm 3.2054 (2.7971/1.3118)	mem 24308MB
[2025-01-19 02:06:17 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][180/312]	eta 0:01:21 lr 0.000597	time 0.6618 (0.6164)	model_time 0.6617 (0.6076)	loss 3.4298 (3.0264)	grad_norm 1.8185 (2.7486/1.2955)	mem 24308MB
[2025-01-19 02:06:23 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][190/312]	eta 0:01:15 lr 0.000597	time 0.5716 (0.6165)	model_time 0.5714 (0.6082)	loss 3.0368 (3.0294)	grad_norm 2.8056 (2.7212/1.2705)	mem 24308MB
[2025-01-19 02:06:29 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][200/312]	eta 0:01:08 lr 0.000596	time 0.6079 (0.6158)	model_time 0.6077 (0.6078)	loss 1.9633 (3.0288)	grad_norm 1.9150 (2.6748/1.2564)	mem 24308MB
[2025-01-19 02:06:35 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][210/312]	eta 0:01:02 lr 0.000596	time 0.5900 (0.6164)	model_time 0.5898 (0.6088)	loss 3.1464 (3.0276)	grad_norm 1.2868 (2.6484/1.2437)	mem 24308MB
[2025-01-19 02:06:41 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][220/312]	eta 0:00:56 lr 0.000595	time 0.5940 (0.6155)	model_time 0.5939 (0.6082)	loss 3.1965 (3.0333)	grad_norm 2.5621 (2.6256/1.2271)	mem 24308MB
[2025-01-19 02:06:47 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][230/312]	eta 0:00:50 lr 0.000595	time 0.5764 (0.6149)	model_time 0.5759 (0.6079)	loss 2.5968 (3.0270)	grad_norm 4.2723 (2.6585/1.2459)	mem 24308MB
[2025-01-19 02:06:53 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][240/312]	eta 0:00:44 lr 0.000594	time 0.5716 (0.6144)	model_time 0.5715 (0.6077)	loss 2.2540 (3.0160)	grad_norm 1.4604 (2.6515/1.2312)	mem 24308MB
[2025-01-19 02:06:59 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][250/312]	eta 0:00:38 lr 0.000594	time 0.5901 (0.6134)	model_time 0.5900 (0.6069)	loss 3.4195 (3.0129)	grad_norm 1.9175 (2.6190/1.2223)	mem 24308MB
[2025-01-19 02:07:05 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][260/312]	eta 0:00:31 lr 0.000593	time 0.5902 (0.6132)	model_time 0.5901 (0.6069)	loss 3.4137 (3.0075)	grad_norm 1.5637 (2.5840/1.2162)	mem 24308MB
[2025-01-19 02:07:11 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][270/312]	eta 0:00:25 lr 0.000593	time 0.5769 (0.6127)	model_time 0.5764 (0.6066)	loss 3.7821 (3.0042)	grad_norm 2.0620 (2.5767/1.2016)	mem 24308MB
[2025-01-19 02:07:17 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][280/312]	eta 0:00:19 lr 0.000592	time 0.5875 (0.6128)	model_time 0.5873 (0.6070)	loss 1.9628 (2.9901)	grad_norm 2.9232 (2.5915/1.1992)	mem 24308MB
[2025-01-19 02:07:24 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][290/312]	eta 0:00:13 lr 0.000592	time 0.6650 (0.6127)	model_time 0.6643 (0.6071)	loss 2.1790 (2.9783)	grad_norm 1.7505 (2.6053/1.2202)	mem 24308MB
[2025-01-19 02:07:30 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][300/312]	eta 0:00:07 lr 0.000591	time 0.6527 (0.6135)	model_time 0.6526 (0.6080)	loss 2.6060 (2.9789)	grad_norm 2.3609 (2.5976/1.2096)	mem 24308MB
[2025-01-19 02:07:36 internimage_s_1k_224] (main.py 510): INFO Train: [226/300][310/312]	eta 0:00:01 lr 0.000591	time 0.5697 (0.6138)	model_time 0.5696 (0.6084)	loss 3.1746 (2.9748)	grad_norm 1.4184 (2.5701/1.2061)	mem 24308MB
[2025-01-19 02:07:37 internimage_s_1k_224] (main.py 519): INFO EPOCH 226 training takes 0:03:11
[2025-01-19 02:07:37 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_226.pth saving......
[2025-01-19 02:07:39 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_226.pth saved !!!
[2025-01-19 02:07:46 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.729 (7.729)	Loss 0.7228 (0.7228)	Acc@1 85.132 (85.132)	Acc@5 97.363 (97.363)	Mem 24308MB
[2025-01-19 02:07:50 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.037)	Loss 0.9563 (0.8162)	Acc@1 78.027 (82.677)	Acc@5 95.068 (96.347)	Mem 24308MB
[2025-01-19 02:07:50 internimage_s_1k_224] (main.py 575): INFO [Epoch:226] * Acc@1 82.568 Acc@5 96.345
[2025-01-19 02:07:50 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.6%
[2025-01-19 02:07:50 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 02:07:52 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 02:07:52 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.57%
[2025-01-19 02:08:00 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.846 (7.846)	Loss 0.7046 (0.7046)	Acc@1 85.352 (85.352)	Acc@5 97.778 (97.778)	Mem 24308MB
[2025-01-19 02:08:04 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.033)	Loss 0.9185 (0.7903)	Acc@1 78.564 (82.870)	Acc@5 95.654 (96.500)	Mem 24308MB
[2025-01-19 02:08:04 internimage_s_1k_224] (main.py 575): INFO [Epoch:226] * Acc@1 82.752 Acc@5 96.527
[2025-01-19 02:08:04 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.8%
[2025-01-19 02:08:04 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:08:06 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:08:06 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.75%
[2025-01-19 02:08:08 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][0/312]	eta 0:10:40 lr 0.000591	time 2.0530 (2.0530)	model_time 0.6065 (0.6065)	loss 3.1955 (3.1955)	grad_norm 2.5040 (2.5040/0.0000)	mem 24308MB
[2025-01-19 02:08:14 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][10/312]	eta 0:03:40 lr 0.000590	time 0.5875 (0.7295)	model_time 0.5873 (0.5977)	loss 2.9521 (3.0342)	grad_norm 1.6784 (2.2627/0.7094)	mem 24308MB
[2025-01-19 02:08:20 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][20/312]	eta 0:03:16 lr 0.000590	time 0.6025 (0.6745)	model_time 0.6020 (0.6053)	loss 2.7921 (2.8932)	grad_norm 4.3548 (2.4508/1.0265)	mem 24308MB
[2025-01-19 02:08:26 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][30/312]	eta 0:03:03 lr 0.000590	time 0.6015 (0.6505)	model_time 0.6010 (0.6035)	loss 3.0532 (2.9627)	grad_norm 2.2895 (3.3043/2.0699)	mem 24308MB
[2025-01-19 02:08:32 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][40/312]	eta 0:02:54 lr 0.000589	time 0.6133 (0.6399)	model_time 0.6131 (0.6043)	loss 3.4421 (2.9916)	grad_norm 2.1068 (3.1354/1.8441)	mem 24308MB
[2025-01-19 02:08:38 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][50/312]	eta 0:02:46 lr 0.000589	time 0.6720 (0.6337)	model_time 0.6718 (0.6050)	loss 2.2199 (2.9793)	grad_norm 3.1107 (3.1672/1.7866)	mem 24308MB
[2025-01-19 02:08:44 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][60/312]	eta 0:02:38 lr 0.000588	time 0.6493 (0.6278)	model_time 0.6492 (0.6038)	loss 2.8721 (2.9329)	grad_norm 4.4586 (3.0540/1.6926)	mem 24308MB
[2025-01-19 02:08:50 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][70/312]	eta 0:02:31 lr 0.000588	time 0.5797 (0.6240)	model_time 0.5796 (0.6033)	loss 2.7389 (2.9488)	grad_norm 1.8604 (3.0115/1.6035)	mem 24308MB
[2025-01-19 02:08:56 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][80/312]	eta 0:02:23 lr 0.000587	time 0.5772 (0.6197)	model_time 0.5771 (0.6015)	loss 1.9050 (2.9424)	grad_norm 1.3711 (3.0126/1.5603)	mem 24308MB
[2025-01-19 02:09:02 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][90/312]	eta 0:02:17 lr 0.000587	time 0.6427 (0.6203)	model_time 0.6426 (0.6040)	loss 3.1237 (2.9768)	grad_norm 2.3137 (3.0034/1.5154)	mem 24308MB
[2025-01-19 02:09:09 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][100/312]	eta 0:02:11 lr 0.000586	time 0.5823 (0.6192)	model_time 0.5822 (0.6046)	loss 2.6942 (2.9597)	grad_norm 1.2077 (2.8966/1.4793)	mem 24308MB
[2025-01-19 02:09:15 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][110/312]	eta 0:02:05 lr 0.000586	time 0.6643 (0.6192)	model_time 0.6641 (0.6058)	loss 2.6948 (2.9438)	grad_norm 1.4079 (2.7959/1.4553)	mem 24308MB
[2025-01-19 02:09:21 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][120/312]	eta 0:01:58 lr 0.000585	time 0.5914 (0.6191)	model_time 0.5913 (0.6068)	loss 3.4092 (2.9569)	grad_norm 1.6229 (2.6893/1.4411)	mem 24308MB
[2025-01-19 02:09:27 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][130/312]	eta 0:01:52 lr 0.000585	time 0.6650 (0.6178)	model_time 0.6648 (0.6064)	loss 3.1814 (2.9777)	grad_norm 1.6500 (2.6800/1.4415)	mem 24308MB
[2025-01-19 02:09:33 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][140/312]	eta 0:01:46 lr 0.000584	time 0.5717 (0.6170)	model_time 0.5712 (0.6064)	loss 2.9403 (2.9959)	grad_norm 4.9781 (2.7162/1.4215)	mem 24308MB
[2025-01-19 02:09:39 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][150/312]	eta 0:01:39 lr 0.000584	time 0.5921 (0.6155)	model_time 0.5919 (0.6056)	loss 3.2830 (2.9999)	grad_norm 2.2864 (2.7362/1.4017)	mem 24308MB
[2025-01-19 02:09:45 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][160/312]	eta 0:01:33 lr 0.000584	time 0.5791 (0.6147)	model_time 0.5790 (0.6054)	loss 2.9031 (2.9964)	grad_norm 1.9585 (2.7803/1.3980)	mem 24308MB
[2025-01-19 02:09:51 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][170/312]	eta 0:01:27 lr 0.000583	time 0.5975 (0.6136)	model_time 0.5971 (0.6048)	loss 2.9896 (2.9874)	grad_norm 2.0084 (2.7429/1.3681)	mem 24308MB
[2025-01-19 02:09:57 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][180/312]	eta 0:01:20 lr 0.000583	time 0.5973 (0.6128)	model_time 0.5969 (0.6044)	loss 2.0193 (2.9793)	grad_norm 1.3645 (2.6968/1.3569)	mem 24308MB
[2025-01-19 02:10:03 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][190/312]	eta 0:01:14 lr 0.000582	time 0.5856 (0.6125)	model_time 0.5855 (0.6045)	loss 3.3227 (2.9857)	grad_norm 3.0137 (2.6908/1.3356)	mem 24308MB
[2025-01-19 02:10:09 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][200/312]	eta 0:01:08 lr 0.000582	time 0.5856 (0.6112)	model_time 0.5854 (0.6037)	loss 2.8007 (2.9877)	grad_norm 1.5932 (2.6533/1.3310)	mem 24308MB
[2025-01-19 02:10:15 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][210/312]	eta 0:01:02 lr 0.000581	time 0.6660 (0.6119)	model_time 0.6659 (0.6047)	loss 3.7178 (2.9862)	grad_norm 2.3579 (2.6737/1.3217)	mem 24308MB
[2025-01-19 02:10:21 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][220/312]	eta 0:00:56 lr 0.000581	time 0.5720 (0.6117)	model_time 0.5716 (0.6048)	loss 2.9136 (2.9962)	grad_norm 1.6335 (2.6541/1.3046)	mem 24308MB
[2025-01-19 02:10:27 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][230/312]	eta 0:00:50 lr 0.000580	time 0.5733 (0.6117)	model_time 0.5728 (0.6051)	loss 3.3399 (2.9993)	grad_norm 4.9873 (2.6594/1.2939)	mem 24308MB
[2025-01-19 02:10:34 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][240/312]	eta 0:00:44 lr 0.000580	time 0.6746 (0.6123)	model_time 0.6745 (0.6059)	loss 2.9207 (2.9897)	grad_norm 3.5058 (2.6709/1.2885)	mem 24308MB
[2025-01-19 02:10:40 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][250/312]	eta 0:00:37 lr 0.000579	time 0.6651 (0.6121)	model_time 0.6646 (0.6060)	loss 2.5478 (2.9779)	grad_norm 1.1430 (2.6344/1.2795)	mem 24308MB
[2025-01-19 02:10:46 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][260/312]	eta 0:00:31 lr 0.000579	time 0.5942 (0.6122)	model_time 0.5941 (0.6063)	loss 3.2416 (2.9739)	grad_norm 1.1863 (2.5987/1.2745)	mem 24308MB
[2025-01-19 02:10:52 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][270/312]	eta 0:00:25 lr 0.000579	time 0.6076 (0.6117)	model_time 0.6074 (0.6060)	loss 2.4873 (2.9663)	grad_norm 1.7556 (2.5740/1.2611)	mem 24308MB
[2025-01-19 02:10:58 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][280/312]	eta 0:00:19 lr 0.000578	time 0.5862 (0.6113)	model_time 0.5861 (0.6058)	loss 2.8212 (2.9635)	grad_norm 1.5355 (2.5601/1.2488)	mem 24308MB
[2025-01-19 02:11:04 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][290/312]	eta 0:00:13 lr 0.000578	time 0.5822 (0.6108)	model_time 0.5820 (0.6055)	loss 3.1116 (2.9651)	grad_norm 1.6059 (2.5656/1.2441)	mem 24308MB
[2025-01-19 02:11:10 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][300/312]	eta 0:00:07 lr 0.000577	time 0.5685 (0.6102)	model_time 0.5684 (0.6050)	loss 2.9457 (2.9689)	grad_norm 2.7317 (2.5555/1.2353)	mem 24308MB
[2025-01-19 02:11:16 internimage_s_1k_224] (main.py 510): INFO Train: [227/300][310/312]	eta 0:00:01 lr 0.000577	time 0.5696 (0.6095)	model_time 0.5695 (0.6045)	loss 2.2198 (2.9666)	grad_norm 2.9137 (2.5588/1.2347)	mem 24308MB
[2025-01-19 02:11:16 internimage_s_1k_224] (main.py 519): INFO EPOCH 227 training takes 0:03:10
[2025-01-19 02:11:16 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_227.pth saving......
[2025-01-19 02:11:18 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_227.pth saved !!!
[2025-01-19 02:11:26 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.142 (8.142)	Loss 0.7367 (0.7367)	Acc@1 85.156 (85.156)	Acc@5 97.534 (97.534)	Mem 24308MB
[2025-01-19 02:11:30 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.070)	Loss 0.9312 (0.8218)	Acc@1 79.443 (82.793)	Acc@5 95.410 (96.409)	Mem 24308MB
[2025-01-19 02:11:30 internimage_s_1k_224] (main.py 575): INFO [Epoch:227] * Acc@1 82.660 Acc@5 96.423
[2025-01-19 02:11:30 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.7%
[2025-01-19 02:11:30 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 02:11:32 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 02:11:32 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.66%
[2025-01-19 02:11:40 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.158 (8.158)	Loss 0.7045 (0.7045)	Acc@1 85.352 (85.352)	Acc@5 97.778 (97.778)	Mem 24308MB
[2025-01-19 02:11:44 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.066)	Loss 0.9174 (0.7898)	Acc@1 78.662 (82.906)	Acc@5 95.703 (96.522)	Mem 24308MB
[2025-01-19 02:11:44 internimage_s_1k_224] (main.py 575): INFO [Epoch:227] * Acc@1 82.790 Acc@5 96.543
[2025-01-19 02:11:44 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.8%
[2025-01-19 02:11:44 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:11:46 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:11:46 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.79%
[2025-01-19 02:11:48 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][0/312]	eta 0:11:03 lr 0.000577	time 2.1276 (2.1276)	model_time 0.6037 (0.6037)	loss 2.8833 (2.8833)	grad_norm 1.6952 (1.6952/0.0000)	mem 24308MB
[2025-01-19 02:11:54 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][10/312]	eta 0:03:41 lr 0.000576	time 0.5913 (0.7325)	model_time 0.5912 (0.5937)	loss 2.6251 (2.7398)	grad_norm 3.7701 (3.0114/1.3679)	mem 24308MB
[2025-01-19 02:12:01 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][20/312]	eta 0:03:20 lr 0.000576	time 0.5862 (0.6852)	model_time 0.5861 (0.6123)	loss 2.5543 (2.8903)	grad_norm 4.3940 (2.8819/1.1763)	mem 24308MB
[2025-01-19 02:12:07 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][30/312]	eta 0:03:06 lr 0.000575	time 0.6824 (0.6618)	model_time 0.6724 (0.6119)	loss 2.4207 (2.9242)	grad_norm 1.3020 (2.6334/1.0816)	mem 24308MB
[2025-01-19 02:12:13 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][40/312]	eta 0:02:56 lr 0.000575	time 0.5863 (0.6494)	model_time 0.5858 (0.6116)	loss 2.5792 (2.9427)	grad_norm 1.8726 (2.5542/1.0178)	mem 24308MB
[2025-01-19 02:12:19 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][50/312]	eta 0:02:48 lr 0.000574	time 0.6315 (0.6440)	model_time 0.6314 (0.6136)	loss 3.0477 (2.9721)	grad_norm 2.8734 (2.4993/0.9626)	mem 24308MB
[2025-01-19 02:12:25 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][60/312]	eta 0:02:40 lr 0.000574	time 0.5825 (0.6387)	model_time 0.5823 (0.6132)	loss 1.9807 (2.9290)	grad_norm 2.9952 (2.6886/1.1281)	mem 24308MB
[2025-01-19 02:12:31 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][70/312]	eta 0:02:34 lr 0.000573	time 0.5828 (0.6390)	model_time 0.5826 (0.6170)	loss 3.1190 (2.9271)	grad_norm 2.7715 (2.5907/1.1022)	mem 24308MB
[2025-01-19 02:12:37 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][80/312]	eta 0:02:26 lr 0.000573	time 0.5868 (0.6335)	model_time 0.5866 (0.6143)	loss 3.1985 (2.9243)	grad_norm 2.3854 (2.5607/1.0879)	mem 24308MB
[2025-01-19 02:12:43 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][90/312]	eta 0:02:19 lr 0.000573	time 0.5831 (0.6305)	model_time 0.5829 (0.6133)	loss 2.9265 (2.9195)	grad_norm 2.4330 (2.4948/1.0568)	mem 24308MB
[2025-01-19 02:12:50 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][100/312]	eta 0:02:13 lr 0.000572	time 0.5893 (0.6276)	model_time 0.5892 (0.6121)	loss 2.7969 (2.9365)	grad_norm 1.3655 (2.5142/1.0671)	mem 24308MB
[2025-01-19 02:12:56 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][110/312]	eta 0:02:06 lr 0.000572	time 0.5880 (0.6254)	model_time 0.5875 (0.6112)	loss 2.9764 (2.9595)	grad_norm 1.5417 (2.4424/1.0580)	mem 24308MB
[2025-01-19 02:13:02 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][120/312]	eta 0:01:59 lr 0.000571	time 0.5850 (0.6233)	model_time 0.5848 (0.6103)	loss 2.2308 (2.9495)	grad_norm 4.2137 (2.4404/1.0574)	mem 24308MB
[2025-01-19 02:13:07 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][130/312]	eta 0:01:53 lr 0.000571	time 0.5936 (0.6210)	model_time 0.5933 (0.6089)	loss 3.1759 (2.9515)	grad_norm 1.4266 (2.3997/1.0498)	mem 24308MB
[2025-01-19 02:13:14 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][140/312]	eta 0:01:46 lr 0.000570	time 0.6897 (0.6211)	model_time 0.6895 (0.6098)	loss 3.3908 (2.9653)	grad_norm 1.5094 (2.3570/1.0382)	mem 24308MB
[2025-01-19 02:13:20 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][150/312]	eta 0:01:40 lr 0.000570	time 0.6979 (0.6205)	model_time 0.6977 (0.6100)	loss 3.0376 (2.9491)	grad_norm 1.6359 (2.3301/1.0173)	mem 24308MB
[2025-01-19 02:13:26 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][160/312]	eta 0:01:34 lr 0.000569	time 0.5725 (0.6196)	model_time 0.5721 (0.6097)	loss 2.7392 (2.9410)	grad_norm 1.3165 (2.2947/1.0004)	mem 24308MB
[2025-01-19 02:13:32 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][170/312]	eta 0:01:28 lr 0.000569	time 0.5903 (0.6199)	model_time 0.5902 (0.6106)	loss 3.0803 (2.9444)	grad_norm 1.8131 (2.2806/0.9793)	mem 24308MB
[2025-01-19 02:13:38 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][180/312]	eta 0:01:21 lr 0.000568	time 0.5959 (0.6193)	model_time 0.5954 (0.6105)	loss 3.2369 (2.9543)	grad_norm 2.9696 (2.3015/0.9943)	mem 24308MB
[2025-01-19 02:13:45 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][190/312]	eta 0:01:15 lr 0.000568	time 0.6437 (0.6198)	model_time 0.6435 (0.6114)	loss 3.1721 (2.9318)	grad_norm 2.0007 (2.4567/1.2461)	mem 24308MB
[2025-01-19 02:13:50 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][200/312]	eta 0:01:09 lr 0.000568	time 0.5805 (0.6188)	model_time 0.5803 (0.6108)	loss 2.7330 (2.9205)	grad_norm 2.6960 (2.4746/1.2463)	mem 24308MB
[2025-01-19 02:13:57 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][210/312]	eta 0:01:03 lr 0.000567	time 0.5728 (0.6181)	model_time 0.5724 (0.6105)	loss 3.4396 (2.9163)	grad_norm 3.8393 (2.4581/1.2341)	mem 24308MB
[2025-01-19 02:14:02 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][220/312]	eta 0:00:56 lr 0.000567	time 0.5811 (0.6171)	model_time 0.5809 (0.6098)	loss 3.5742 (2.9119)	grad_norm 3.1870 (2.4864/1.2470)	mem 24308MB
[2025-01-19 02:14:09 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][230/312]	eta 0:00:50 lr 0.000566	time 0.5805 (0.6167)	model_time 0.5803 (0.6097)	loss 2.8209 (2.9143)	grad_norm 1.5864 (2.4721/1.2341)	mem 24308MB
[2025-01-19 02:14:15 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][240/312]	eta 0:00:44 lr 0.000566	time 0.6022 (0.6160)	model_time 0.6021 (0.6092)	loss 2.8392 (2.9082)	grad_norm 1.4163 (2.4519/1.2191)	mem 24308MB
[2025-01-19 02:14:20 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][250/312]	eta 0:00:38 lr 0.000565	time 0.5794 (0.6147)	model_time 0.5792 (0.6082)	loss 2.3292 (2.9132)	grad_norm 2.5409 (2.4791/1.2355)	mem 24308MB
[2025-01-19 02:14:27 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][260/312]	eta 0:00:31 lr 0.000565	time 0.6534 (0.6149)	model_time 0.6533 (0.6087)	loss 2.6698 (2.9197)	grad_norm 2.3806 (2.4700/1.2181)	mem 24308MB
[2025-01-19 02:14:33 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][270/312]	eta 0:00:25 lr 0.000564	time 0.5931 (0.6147)	model_time 0.5927 (0.6087)	loss 3.1634 (2.9222)	grad_norm 2.7221 (2.5010/1.2309)	mem 24308MB
[2025-01-19 02:14:39 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][280/312]	eta 0:00:19 lr 0.000564	time 0.5829 (0.6145)	model_time 0.5827 (0.6087)	loss 3.2434 (2.9290)	grad_norm 3.2976 (2.5279/1.2347)	mem 24308MB
[2025-01-19 02:14:45 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][290/312]	eta 0:00:13 lr 0.000564	time 0.6553 (0.6147)	model_time 0.6552 (0.6090)	loss 3.2868 (2.9155)	grad_norm 2.9096 (2.5305/1.2320)	mem 24308MB
[2025-01-19 02:14:51 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][300/312]	eta 0:00:07 lr 0.000563	time 0.6053 (0.6141)	model_time 0.6052 (0.6086)	loss 3.0285 (2.9192)	grad_norm 1.2329 (2.5113/1.2235)	mem 24308MB
[2025-01-19 02:14:57 internimage_s_1k_224] (main.py 510): INFO Train: [228/300][310/312]	eta 0:00:01 lr 0.000563	time 0.5721 (0.6137)	model_time 0.5720 (0.6085)	loss 3.2273 (2.9315)	grad_norm 1.0696 (2.4946/1.2079)	mem 24308MB
[2025-01-19 02:14:58 internimage_s_1k_224] (main.py 519): INFO EPOCH 228 training takes 0:03:11
[2025-01-19 02:14:58 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_228.pth saving......
[2025-01-19 02:14:59 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_228.pth saved !!!
[2025-01-19 02:15:13 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 13.277 (13.277)	Loss 0.7432 (0.7432)	Acc@1 85.205 (85.205)	Acc@5 97.583 (97.583)	Mem 24308MB
[2025-01-19 02:15:20 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.902)	Loss 0.9619 (0.8367)	Acc@1 78.662 (82.799)	Acc@5 95.312 (96.447)	Mem 24308MB
[2025-01-19 02:15:21 internimage_s_1k_224] (main.py 575): INFO [Epoch:228] * Acc@1 82.618 Acc@5 96.435
[2025-01-19 02:15:21 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.6%
[2025-01-19 02:15:21 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.66%
[2025-01-19 02:15:37 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.688 (16.688)	Loss 0.7044 (0.7044)	Acc@1 85.425 (85.425)	Acc@5 97.803 (97.803)	Mem 24308MB
[2025-01-19 02:15:46 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (2.341)	Loss 0.9162 (0.7892)	Acc@1 78.662 (82.899)	Acc@5 95.776 (96.538)	Mem 24308MB
[2025-01-19 02:15:47 internimage_s_1k_224] (main.py 575): INFO [Epoch:228] * Acc@1 82.790 Acc@5 96.557
[2025-01-19 02:15:47 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.8%
[2025-01-19 02:15:47 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.79%
[2025-01-19 02:15:50 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][0/312]	eta 0:17:59 lr 0.000563	time 3.4603 (3.4603)	model_time 1.5224 (1.5224)	loss 2.8433 (2.8433)	grad_norm 2.5946 (2.5946/0.0000)	mem 24308MB
[2025-01-19 02:15:56 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][10/312]	eta 0:04:21 lr 0.000562	time 0.6675 (0.8666)	model_time 0.6674 (0.6900)	loss 3.1042 (3.1773)	grad_norm 2.6281 (2.6821/1.0321)	mem 24308MB
[2025-01-19 02:16:02 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][20/312]	eta 0:03:38 lr 0.000562	time 0.6722 (0.7470)	model_time 0.6718 (0.6544)	loss 2.9756 (3.0727)	grad_norm 1.3222 (2.6866/1.0775)	mem 24308MB
[2025-01-19 02:16:08 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][30/312]	eta 0:03:17 lr 0.000561	time 0.5728 (0.6987)	model_time 0.5725 (0.6358)	loss 3.1403 (3.0610)	grad_norm 2.8945 (2.6541/1.0324)	mem 24308MB
[2025-01-19 02:16:14 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][40/312]	eta 0:03:03 lr 0.000561	time 0.5885 (0.6743)	model_time 0.5884 (0.6267)	loss 3.4122 (3.0365)	grad_norm 2.5560 (2.7241/1.1232)	mem 24308MB
[2025-01-19 02:16:20 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][50/312]	eta 0:02:52 lr 0.000560	time 0.5939 (0.6595)	model_time 0.5934 (0.6211)	loss 3.1116 (3.0291)	grad_norm 3.9184 (2.7925/1.1287)	mem 24308MB
[2025-01-19 02:16:26 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][60/312]	eta 0:02:43 lr 0.000560	time 0.5856 (0.6498)	model_time 0.5855 (0.6177)	loss 2.9462 (2.9976)	grad_norm 4.6924 (2.9170/1.1664)	mem 24308MB
[2025-01-19 02:16:32 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][70/312]	eta 0:02:35 lr 0.000559	time 0.6174 (0.6443)	model_time 0.6172 (0.6167)	loss 2.5818 (2.9524)	grad_norm 2.3830 (2.9595/1.1792)	mem 24308MB
[2025-01-19 02:16:38 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][80/312]	eta 0:02:28 lr 0.000559	time 0.5885 (0.6387)	model_time 0.5884 (0.6144)	loss 3.0587 (2.9448)	grad_norm 2.0473 (2.8295/1.1672)	mem 24308MB
[2025-01-19 02:16:44 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][90/312]	eta 0:02:21 lr 0.000558	time 0.5802 (0.6353)	model_time 0.5800 (0.6136)	loss 2.0606 (2.9264)	grad_norm 1.9323 (2.7724/1.1294)	mem 24308MB
[2025-01-19 02:16:51 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][100/312]	eta 0:02:14 lr 0.000558	time 0.5998 (0.6343)	model_time 0.5994 (0.6147)	loss 2.6956 (2.9333)	grad_norm 2.0712 (2.7797/1.1117)	mem 24308MB
[2025-01-19 02:16:57 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][110/312]	eta 0:02:07 lr 0.000558	time 0.5795 (0.6321)	model_time 0.5794 (0.6143)	loss 2.7683 (2.9243)	grad_norm 2.0841 (2.8036/1.1339)	mem 24308MB
[2025-01-19 02:17:03 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][120/312]	eta 0:02:01 lr 0.000557	time 0.5722 (0.6308)	model_time 0.5720 (0.6145)	loss 2.6191 (2.9232)	grad_norm 2.4113 (2.7434/1.1080)	mem 24308MB
[2025-01-19 02:17:09 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][130/312]	eta 0:01:54 lr 0.000557	time 0.5741 (0.6277)	model_time 0.5737 (0.6125)	loss 1.8603 (2.9178)	grad_norm 4.3410 (2.7315/1.0897)	mem 24308MB
[2025-01-19 02:17:15 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][140/312]	eta 0:01:47 lr 0.000556	time 0.7039 (0.6267)	model_time 0.7037 (0.6126)	loss 1.9762 (2.9184)	grad_norm 1.4780 (2.6872/1.0780)	mem 24308MB
[2025-01-19 02:17:21 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][150/312]	eta 0:01:41 lr 0.000556	time 0.5760 (0.6250)	model_time 0.5755 (0.6118)	loss 2.1420 (2.9172)	grad_norm 3.3072 (2.6774/1.0634)	mem 24308MB
[2025-01-19 02:17:27 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][160/312]	eta 0:01:34 lr 0.000555	time 0.5767 (0.6230)	model_time 0.5765 (0.6106)	loss 3.2891 (2.9222)	grad_norm 4.3041 (2.7116/1.0780)	mem 24308MB
[2025-01-19 02:17:33 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][170/312]	eta 0:01:28 lr 0.000555	time 0.7094 (0.6218)	model_time 0.7092 (0.6101)	loss 3.4935 (2.9293)	grad_norm 3.0397 (2.7462/1.0887)	mem 24308MB
[2025-01-19 02:17:39 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][180/312]	eta 0:01:21 lr 0.000554	time 0.5965 (0.6199)	model_time 0.5961 (0.6089)	loss 3.6262 (2.9414)	grad_norm 3.1981 (2.7546/1.0839)	mem 24308MB
[2025-01-19 02:17:45 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][190/312]	eta 0:01:15 lr 0.000554	time 0.6007 (0.6199)	model_time 0.6002 (0.6094)	loss 2.9414 (2.9416)	grad_norm 1.4002 (2.7301/1.0778)	mem 24308MB
[2025-01-19 02:17:51 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][200/312]	eta 0:01:09 lr 0.000554	time 0.5812 (0.6188)	model_time 0.5808 (0.6088)	loss 2.9725 (2.9274)	grad_norm 4.2646 (2.6977/1.0774)	mem 24308MB
[2025-01-19 02:17:57 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][210/312]	eta 0:01:03 lr 0.000553	time 0.6624 (0.6186)	model_time 0.6622 (0.6090)	loss 2.7973 (2.9303)	grad_norm 1.6588 (2.7079/1.0631)	mem 24308MB
[2025-01-19 02:18:03 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][220/312]	eta 0:00:56 lr 0.000553	time 0.5866 (0.6189)	model_time 0.5862 (0.6098)	loss 2.6499 (2.9304)	grad_norm 1.7880 (2.7231/1.0940)	mem 24308MB
[2025-01-19 02:18:09 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][230/312]	eta 0:00:50 lr 0.000552	time 0.5807 (0.6186)	model_time 0.5805 (0.6099)	loss 3.3623 (2.9371)	grad_norm 1.8575 (2.6867/1.0861)	mem 24308MB
[2025-01-19 02:18:16 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][240/312]	eta 0:00:44 lr 0.000552	time 0.6799 (0.6186)	model_time 0.6798 (0.6102)	loss 2.7947 (2.9411)	grad_norm 1.8416 (2.6695/1.0800)	mem 24308MB
[2025-01-19 02:18:21 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][250/312]	eta 0:00:38 lr 0.000551	time 0.5727 (0.6172)	model_time 0.5725 (0.6092)	loss 3.7562 (2.9526)	grad_norm 1.1850 (2.6532/1.0760)	mem 24308MB
[2025-01-19 02:18:28 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][260/312]	eta 0:00:32 lr 0.000551	time 0.6332 (0.6169)	model_time 0.6327 (0.6091)	loss 2.6350 (2.9581)	grad_norm 3.3028 (2.6579/1.0759)	mem 24308MB
[2025-01-19 02:18:34 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][270/312]	eta 0:00:25 lr 0.000550	time 0.5872 (0.6168)	model_time 0.5871 (0.6093)	loss 3.0280 (2.9522)	grad_norm 1.2408 (2.6899/1.1208)	mem 24308MB
[2025-01-19 02:18:40 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][280/312]	eta 0:00:19 lr 0.000550	time 0.5760 (0.6162)	model_time 0.5755 (0.6089)	loss 3.8755 (2.9545)	grad_norm 2.4269 (2.7082/1.1333)	mem 24308MB
[2025-01-19 02:18:46 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][290/312]	eta 0:00:13 lr 0.000550	time 0.5980 (0.6154)	model_time 0.5975 (0.6083)	loss 3.0143 (2.9538)	grad_norm 1.1250 (2.6903/1.1312)	mem 24308MB
[2025-01-19 02:18:52 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][300/312]	eta 0:00:07 lr 0.000549	time 0.5683 (0.6147)	model_time 0.5682 (0.6079)	loss 3.3932 (2.9580)	grad_norm 2.0219 (2.6881/1.1441)	mem 24308MB
[2025-01-19 02:18:57 internimage_s_1k_224] (main.py 510): INFO Train: [229/300][310/312]	eta 0:00:01 lr 0.000549	time 0.5712 (0.6139)	model_time 0.5711 (0.6073)	loss 3.2129 (2.9668)	grad_norm 3.3602 (2.6781/1.1423)	mem 24308MB
[2025-01-19 02:18:58 internimage_s_1k_224] (main.py 519): INFO EPOCH 229 training takes 0:03:11
[2025-01-19 02:18:58 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_229.pth saving......
[2025-01-19 02:19:00 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_229.pth saved !!!
[2025-01-19 02:19:08 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.674 (7.674)	Loss 0.7557 (0.7557)	Acc@1 85.083 (85.083)	Acc@5 97.388 (97.388)	Mem 24308MB
[2025-01-19 02:19:11 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.043)	Loss 0.9776 (0.8386)	Acc@1 78.027 (82.888)	Acc@5 95.288 (96.400)	Mem 24308MB
[2025-01-19 02:19:12 internimage_s_1k_224] (main.py 575): INFO [Epoch:229] * Acc@1 82.742 Acc@5 96.403
[2025-01-19 02:19:12 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.7%
[2025-01-19 02:19:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 02:19:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 02:19:14 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.74%
[2025-01-19 02:19:21 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.685 (7.685)	Loss 0.7043 (0.7043)	Acc@1 85.474 (85.474)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 02:19:25 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.028)	Loss 0.9151 (0.7885)	Acc@1 78.687 (82.921)	Acc@5 95.801 (96.549)	Mem 24308MB
[2025-01-19 02:19:25 internimage_s_1k_224] (main.py 575): INFO [Epoch:229] * Acc@1 82.808 Acc@5 96.571
[2025-01-19 02:19:25 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.8%
[2025-01-19 02:19:25 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:19:28 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:19:28 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.81%
[2025-01-19 02:19:30 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][0/312]	eta 0:11:39 lr 0.000549	time 2.2413 (2.2413)	model_time 0.6129 (0.6129)	loss 2.2878 (2.2878)	grad_norm 1.6114 (1.6114/0.0000)	mem 24308MB
[2025-01-19 02:19:36 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][10/312]	eta 0:03:45 lr 0.000548	time 0.5891 (0.7478)	model_time 0.5889 (0.5995)	loss 3.2991 (2.9352)	grad_norm 1.5140 (2.1691/0.8103)	mem 24308MB
[2025-01-19 02:19:42 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][20/312]	eta 0:03:19 lr 0.000548	time 0.6681 (0.6831)	model_time 0.6676 (0.6052)	loss 2.0292 (2.9595)	grad_norm 5.0212 (2.7740/1.2605)	mem 24308MB
[2025-01-19 02:19:48 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][30/312]	eta 0:03:07 lr 0.000547	time 0.5793 (0.6641)	model_time 0.5791 (0.6113)	loss 2.4046 (2.8470)	grad_norm 5.1725 (2.9647/1.3229)	mem 24308MB
[2025-01-19 02:19:54 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][40/312]	eta 0:02:57 lr 0.000547	time 0.5885 (0.6513)	model_time 0.5881 (0.6112)	loss 1.9655 (2.8558)	grad_norm 2.4249 (2.9511/1.2912)	mem 24308MB
[2025-01-19 02:20:01 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][50/312]	eta 0:02:48 lr 0.000546	time 0.6157 (0.6437)	model_time 0.6155 (0.6115)	loss 3.4302 (2.8796)	grad_norm 3.3321 (2.9876/1.2972)	mem 24308MB
[2025-01-19 02:20:06 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][60/312]	eta 0:02:40 lr 0.000546	time 0.6193 (0.6354)	model_time 0.6191 (0.6083)	loss 2.5112 (2.8656)	grad_norm 1.1156 (2.9603/1.2718)	mem 24308MB
[2025-01-19 02:20:12 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][70/312]	eta 0:02:32 lr 0.000545	time 0.5731 (0.6305)	model_time 0.5727 (0.6072)	loss 3.1605 (2.8793)	grad_norm 1.5631 (2.9389/1.2007)	mem 24308MB
[2025-01-19 02:20:19 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][80/312]	eta 0:02:25 lr 0.000545	time 0.5828 (0.6275)	model_time 0.5826 (0.6071)	loss 2.6356 (2.8887)	grad_norm 3.6227 (2.9120/1.1497)	mem 24308MB
[2025-01-19 02:20:25 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][90/312]	eta 0:02:18 lr 0.000545	time 0.5851 (0.6247)	model_time 0.5850 (0.6064)	loss 3.0515 (2.9042)	grad_norm 2.1670 (2.8293/1.1412)	mem 24308MB
[2025-01-19 02:20:30 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][100/312]	eta 0:02:11 lr 0.000544	time 0.5762 (0.6212)	model_time 0.5758 (0.6047)	loss 2.2818 (2.8986)	grad_norm 2.5358 (2.7063/1.1537)	mem 24308MB
[2025-01-19 02:20:36 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][110/312]	eta 0:02:04 lr 0.000544	time 0.5733 (0.6187)	model_time 0.5731 (0.6037)	loss 3.2176 (2.9027)	grad_norm 2.4930 (2.6732/1.1262)	mem 24308MB
[2025-01-19 02:20:43 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][120/312]	eta 0:01:58 lr 0.000543	time 0.6724 (0.6185)	model_time 0.6722 (0.6047)	loss 3.9206 (2.9000)	grad_norm 6.4977 (2.7199/1.2014)	mem 24308MB
[2025-01-19 02:20:48 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][130/312]	eta 0:01:52 lr 0.000543	time 0.5940 (0.6167)	model_time 0.5934 (0.6039)	loss 2.5297 (2.8755)	grad_norm 1.4957 (2.7241/1.2133)	mem 24308MB
[2025-01-19 02:20:55 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][140/312]	eta 0:01:46 lr 0.000542	time 0.6781 (0.6169)	model_time 0.6779 (0.6049)	loss 2.6814 (2.8741)	grad_norm 1.1369 (2.7009/1.1933)	mem 24308MB
[2025-01-19 02:21:01 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][150/312]	eta 0:01:40 lr 0.000542	time 0.6512 (0.6176)	model_time 0.6510 (0.6064)	loss 3.0631 (2.8630)	grad_norm 2.2238 (2.6428/1.1798)	mem 24308MB
[2025-01-19 02:21:07 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][160/312]	eta 0:01:33 lr 0.000541	time 0.6082 (0.6167)	model_time 0.6077 (0.6062)	loss 3.1345 (2.8672)	grad_norm 1.9808 (2.6644/1.1836)	mem 24308MB
[2025-01-19 02:21:13 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][170/312]	eta 0:01:27 lr 0.000541	time 0.5738 (0.6166)	model_time 0.5734 (0.6067)	loss 2.9020 (2.8653)	grad_norm 3.6274 (2.6575/1.1619)	mem 24308MB
[2025-01-19 02:21:19 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][180/312]	eta 0:01:21 lr 0.000541	time 0.5862 (0.6158)	model_time 0.5860 (0.6064)	loss 3.0050 (2.8689)	grad_norm 1.5552 (2.6663/1.1755)	mem 24308MB
[2025-01-19 02:21:25 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][190/312]	eta 0:01:15 lr 0.000540	time 0.5816 (0.6153)	model_time 0.5814 (0.6064)	loss 3.0692 (2.8799)	grad_norm 1.8208 (2.6448/1.1638)	mem 24308MB
[2025-01-19 02:21:31 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][200/312]	eta 0:01:08 lr 0.000540	time 0.6720 (0.6150)	model_time 0.6715 (0.6066)	loss 3.0526 (2.8776)	grad_norm 2.3192 (2.6316/1.1531)	mem 24308MB
[2025-01-19 02:21:37 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][210/312]	eta 0:01:02 lr 0.000539	time 0.5775 (0.6146)	model_time 0.5773 (0.6065)	loss 3.2503 (2.8870)	grad_norm 3.3463 (2.6494/1.1612)	mem 24308MB
[2025-01-19 02:21:43 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][220/312]	eta 0:00:56 lr 0.000539	time 0.5826 (0.6133)	model_time 0.5824 (0.6054)	loss 2.2388 (2.8921)	grad_norm 2.3527 (2.6329/1.1448)	mem 24308MB
[2025-01-19 02:21:49 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][230/312]	eta 0:00:50 lr 0.000538	time 0.5972 (0.6128)	model_time 0.5968 (0.6053)	loss 3.2244 (2.9046)	grad_norm 1.1887 (2.6207/1.1317)	mem 24308MB
[2025-01-19 02:21:55 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][240/312]	eta 0:00:44 lr 0.000538	time 0.6866 (0.6128)	model_time 0.6861 (0.6056)	loss 3.6124 (2.9108)	grad_norm 1.3226 (2.6167/1.1295)	mem 24308MB
[2025-01-19 02:22:01 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][250/312]	eta 0:00:37 lr 0.000538	time 0.5735 (0.6124)	model_time 0.5733 (0.6055)	loss 3.1122 (2.9136)	grad_norm 1.9342 (2.6260/1.1300)	mem 24308MB
[2025-01-19 02:22:08 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][260/312]	eta 0:00:31 lr 0.000537	time 0.6791 (0.6126)	model_time 0.6789 (0.6060)	loss 2.8741 (2.9189)	grad_norm 1.6082 (2.6205/1.1214)	mem 24308MB
[2025-01-19 02:22:14 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][270/312]	eta 0:00:25 lr 0.000537	time 0.6609 (0.6137)	model_time 0.6605 (0.6073)	loss 3.0646 (2.9184)	grad_norm 1.8034 (2.6504/1.1554)	mem 24308MB
[2025-01-19 02:22:20 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][280/312]	eta 0:00:19 lr 0.000536	time 0.5735 (0.6133)	model_time 0.5730 (0.6071)	loss 3.5541 (2.9181)	grad_norm 2.3385 (2.6170/1.1526)	mem 24308MB
[2025-01-19 02:22:26 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][290/312]	eta 0:00:13 lr 0.000536	time 0.5936 (0.6133)	model_time 0.5935 (0.6073)	loss 3.3220 (2.9194)	grad_norm 1.5793 (2.5979/1.1451)	mem 24308MB
[2025-01-19 02:22:32 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][300/312]	eta 0:00:07 lr 0.000535	time 0.5701 (0.6126)	model_time 0.5700 (0.6068)	loss 3.3762 (2.9140)	grad_norm 4.5351 (2.6297/1.1794)	mem 24308MB
[2025-01-19 02:22:38 internimage_s_1k_224] (main.py 510): INFO Train: [230/300][310/312]	eta 0:00:01 lr 0.000535	time 0.6453 (0.6116)	model_time 0.6452 (0.6059)	loss 2.7970 (2.9178)	grad_norm 2.2444 (2.6628/1.1964)	mem 24308MB
[2025-01-19 02:22:39 internimage_s_1k_224] (main.py 519): INFO EPOCH 230 training takes 0:03:10
[2025-01-19 02:22:39 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_230.pth saving......
[2025-01-19 02:22:40 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_230.pth saved !!!
[2025-01-19 02:22:48 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.889 (7.889)	Loss 0.7408 (0.7408)	Acc@1 84.937 (84.937)	Acc@5 97.241 (97.241)	Mem 24308MB
[2025-01-19 02:22:52 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.025)	Loss 0.9649 (0.8359)	Acc@1 79.077 (82.815)	Acc@5 95.459 (96.402)	Mem 24308MB
[2025-01-19 02:22:52 internimage_s_1k_224] (main.py 575): INFO [Epoch:230] * Acc@1 82.706 Acc@5 96.435
[2025-01-19 02:22:52 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.7%
[2025-01-19 02:22:52 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.74%
[2025-01-19 02:23:01 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.919 (8.919)	Loss 0.7041 (0.7041)	Acc@1 85.474 (85.474)	Acc@5 97.803 (97.803)	Mem 24308MB
[2025-01-19 02:23:05 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.207)	Loss 0.9140 (0.7879)	Acc@1 78.760 (82.959)	Acc@5 95.776 (96.562)	Mem 24308MB
[2025-01-19 02:23:06 internimage_s_1k_224] (main.py 575): INFO [Epoch:230] * Acc@1 82.849 Acc@5 96.585
[2025-01-19 02:23:06 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.8%
[2025-01-19 02:23:06 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:23:08 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:23:08 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.85%
[2025-01-19 02:23:10 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][0/312]	eta 0:11:27 lr 0.000535	time 2.2049 (2.2049)	model_time 0.6202 (0.6202)	loss 3.1094 (3.1094)	grad_norm 1.6427 (1.6427/0.0000)	mem 24308MB
[2025-01-19 02:23:16 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][10/312]	eta 0:03:46 lr 0.000534	time 0.6821 (0.7515)	model_time 0.6819 (0.6069)	loss 3.4993 (3.0000)	grad_norm 3.3432 (2.2720/0.9525)	mem 24308MB
[2025-01-19 02:23:22 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][20/312]	eta 0:03:17 lr 0.000534	time 0.6067 (0.6776)	model_time 0.6066 (0.6018)	loss 2.9906 (3.0323)	grad_norm 1.5544 (2.1963/0.9070)	mem 24308MB
[2025-01-19 02:23:28 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][30/312]	eta 0:03:03 lr 0.000533	time 0.5888 (0.6490)	model_time 0.5883 (0.5975)	loss 2.8787 (3.0213)	grad_norm 1.7097 (2.1686/0.9077)	mem 24308MB
[2025-01-19 02:23:34 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][40/312]	eta 0:02:53 lr 0.000533	time 0.5903 (0.6373)	model_time 0.5898 (0.5983)	loss 3.2319 (3.0532)	grad_norm 2.1056 (2.1432/0.8274)	mem 24308MB
[2025-01-19 02:23:40 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][50/312]	eta 0:02:45 lr 0.000533	time 0.6958 (0.6315)	model_time 0.6954 (0.6001)	loss 2.9712 (3.0244)	grad_norm 3.9666 (2.1779/0.8121)	mem 24308MB
[2025-01-19 02:23:46 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][60/312]	eta 0:02:38 lr 0.000532	time 0.6826 (0.6293)	model_time 0.6822 (0.6030)	loss 3.2127 (2.9985)	grad_norm 2.1368 (2.1293/0.7841)	mem 24308MB
[2025-01-19 02:23:52 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][70/312]	eta 0:02:31 lr 0.000532	time 0.5773 (0.6274)	model_time 0.5769 (0.6047)	loss 2.7499 (2.9508)	grad_norm 3.2918 (2.0915/0.7663)	mem 24308MB
[2025-01-19 02:23:59 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][80/312]	eta 0:02:25 lr 0.000531	time 0.6907 (0.6276)	model_time 0.6906 (0.6077)	loss 2.1272 (2.9326)	grad_norm 1.8131 (2.1697/0.9348)	mem 24308MB
[2025-01-19 02:24:05 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][90/312]	eta 0:02:18 lr 0.000531	time 0.5991 (0.6259)	model_time 0.5990 (0.6081)	loss 3.2625 (2.9292)	grad_norm 1.1323 (2.2469/0.9581)	mem 24308MB
[2025-01-19 02:24:11 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][100/312]	eta 0:02:12 lr 0.000530	time 0.5905 (0.6236)	model_time 0.5904 (0.6075)	loss 2.7236 (2.9100)	grad_norm 4.1028 (2.2478/0.9926)	mem 24308MB
[2025-01-19 02:24:17 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][110/312]	eta 0:02:05 lr 0.000530	time 0.5747 (0.6205)	model_time 0.5743 (0.6059)	loss 3.3669 (2.9062)	grad_norm 1.6457 (2.2705/0.9676)	mem 24308MB
[2025-01-19 02:24:23 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][120/312]	eta 0:01:58 lr 0.000530	time 0.5721 (0.6190)	model_time 0.5717 (0.6056)	loss 2.9463 (2.8847)	grad_norm 3.1615 (2.2666/0.9428)	mem 24308MB
[2025-01-19 02:24:29 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][130/312]	eta 0:01:52 lr 0.000529	time 0.5816 (0.6180)	model_time 0.5814 (0.6055)	loss 2.8590 (2.8950)	grad_norm 7.6273 (2.4202/1.1950)	mem 24308MB
[2025-01-19 02:24:35 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][140/312]	eta 0:01:46 lr 0.000529	time 0.5852 (0.6172)	model_time 0.5847 (0.6056)	loss 3.3230 (2.9083)	grad_norm 1.9000 (2.4396/1.2133)	mem 24308MB
[2025-01-19 02:24:41 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][150/312]	eta 0:01:39 lr 0.000528	time 0.5751 (0.6152)	model_time 0.5747 (0.6043)	loss 2.8232 (2.9168)	grad_norm 2.6011 (2.4574/1.2093)	mem 24308MB
[2025-01-19 02:24:47 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][160/312]	eta 0:01:33 lr 0.000528	time 0.6607 (0.6137)	model_time 0.6606 (0.6035)	loss 3.3209 (2.9302)	grad_norm 2.5089 (2.4323/1.1806)	mem 24308MB
[2025-01-19 02:24:53 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][170/312]	eta 0:01:27 lr 0.000527	time 0.5818 (0.6130)	model_time 0.5817 (0.6034)	loss 2.4589 (2.9311)	grad_norm 1.8804 (2.4382/1.1667)	mem 24308MB
[2025-01-19 02:24:59 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][180/312]	eta 0:01:20 lr 0.000527	time 0.5875 (0.6129)	model_time 0.5873 (0.6038)	loss 3.2426 (2.9213)	grad_norm 2.6531 (2.4373/1.1518)	mem 24308MB
[2025-01-19 02:25:05 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][190/312]	eta 0:01:14 lr 0.000526	time 0.5881 (0.6138)	model_time 0.5877 (0.6052)	loss 3.2769 (2.9322)	grad_norm 2.7252 (2.4149/1.1312)	mem 24308MB
[2025-01-19 02:25:11 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][200/312]	eta 0:01:08 lr 0.000526	time 0.7254 (0.6153)	model_time 0.7252 (0.6070)	loss 2.5571 (2.9362)	grad_norm 1.1145 (2.4162/1.1403)	mem 24308MB
[2025-01-19 02:25:18 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][210/312]	eta 0:01:02 lr 0.000526	time 0.5716 (0.6152)	model_time 0.5714 (0.6073)	loss 3.3605 (2.9497)	grad_norm 1.5071 (2.4261/1.1387)	mem 24308MB
[2025-01-19 02:25:24 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][220/312]	eta 0:00:56 lr 0.000525	time 0.5882 (0.6147)	model_time 0.5877 (0.6071)	loss 3.6000 (2.9566)	grad_norm 2.5269 (2.4146/1.1230)	mem 24308MB
[2025-01-19 02:25:30 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][230/312]	eta 0:00:50 lr 0.000525	time 0.5775 (0.6142)	model_time 0.5771 (0.6069)	loss 3.0339 (2.9572)	grad_norm 1.4882 (2.4073/1.1107)	mem 24308MB
[2025-01-19 02:25:36 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][240/312]	eta 0:00:44 lr 0.000524	time 0.5724 (0.6136)	model_time 0.5722 (0.6066)	loss 3.1632 (2.9586)	grad_norm 1.5911 (2.4107/1.0973)	mem 24308MB
[2025-01-19 02:25:42 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][250/312]	eta 0:00:38 lr 0.000524	time 0.6007 (0.6133)	model_time 0.6005 (0.6066)	loss 3.6964 (2.9549)	grad_norm 1.3915 (2.3906/1.0829)	mem 24308MB
[2025-01-19 02:25:48 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][260/312]	eta 0:00:31 lr 0.000523	time 0.5983 (0.6130)	model_time 0.5981 (0.6065)	loss 3.1651 (2.9480)	grad_norm 7.0196 (2.4007/1.1115)	mem 24308MB
[2025-01-19 02:25:54 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][270/312]	eta 0:00:25 lr 0.000523	time 0.5745 (0.6123)	model_time 0.5744 (0.6060)	loss 2.5404 (2.9480)	grad_norm 4.0383 (2.4290/1.1136)	mem 24308MB
[2025-01-19 02:26:00 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][280/312]	eta 0:00:19 lr 0.000523	time 0.5795 (0.6116)	model_time 0.5791 (0.6056)	loss 2.8611 (2.9502)	grad_norm 1.5246 (2.4411/1.1131)	mem 24308MB
[2025-01-19 02:26:06 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][290/312]	eta 0:00:13 lr 0.000522	time 0.5806 (0.6110)	model_time 0.5805 (0.6051)	loss 2.5319 (2.9466)	grad_norm 1.8100 (2.4198/1.1046)	mem 24308MB
[2025-01-19 02:26:12 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][300/312]	eta 0:00:07 lr 0.000522	time 0.6529 (0.6116)	model_time 0.6528 (0.6059)	loss 3.5509 (2.9406)	grad_norm 1.8263 (2.4316/1.0970)	mem 24308MB
[2025-01-19 02:26:18 internimage_s_1k_224] (main.py 510): INFO Train: [231/300][310/312]	eta 0:00:01 lr 0.000521	time 0.9152 (0.6117)	model_time 0.9151 (0.6062)	loss 3.1537 (2.9378)	grad_norm 1.4406 (2.4115/1.0958)	mem 24308MB
[2025-01-19 02:26:19 internimage_s_1k_224] (main.py 519): INFO EPOCH 231 training takes 0:03:10
[2025-01-19 02:26:19 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_231.pth saving......
[2025-01-19 02:26:20 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_231.pth saved !!!
[2025-01-19 02:26:28 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.895 (7.895)	Loss 0.7391 (0.7391)	Acc@1 85.156 (85.156)	Acc@5 97.266 (97.266)	Mem 24308MB
[2025-01-19 02:26:32 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.022)	Loss 0.9597 (0.8246)	Acc@1 79.053 (82.937)	Acc@5 95.264 (96.493)	Mem 24308MB
[2025-01-19 02:26:32 internimage_s_1k_224] (main.py 575): INFO [Epoch:231] * Acc@1 82.794 Acc@5 96.513
[2025-01-19 02:26:32 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.8%
[2025-01-19 02:26:32 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 02:26:34 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 02:26:34 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.79%
[2025-01-19 02:26:42 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.826 (7.826)	Loss 0.7038 (0.7038)	Acc@1 85.498 (85.498)	Acc@5 97.803 (97.803)	Mem 24308MB
[2025-01-19 02:26:45 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.016)	Loss 0.9128 (0.7871)	Acc@1 78.735 (82.979)	Acc@5 95.776 (96.558)	Mem 24308MB
[2025-01-19 02:26:45 internimage_s_1k_224] (main.py 575): INFO [Epoch:231] * Acc@1 82.867 Acc@5 96.581
[2025-01-19 02:26:45 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.9%
[2025-01-19 02:26:45 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:26:47 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:26:47 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.87%
[2025-01-19 02:26:50 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][0/312]	eta 0:12:39 lr 0.000521	time 2.4349 (2.4349)	model_time 0.5961 (0.5961)	loss 2.9827 (2.9827)	grad_norm 1.6952 (1.6952/0.0000)	mem 24308MB
[2025-01-19 02:26:56 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][10/312]	eta 0:04:01 lr 0.000521	time 0.6619 (0.7989)	model_time 0.6617 (0.6314)	loss 2.0885 (3.1149)	grad_norm 3.2324 (2.2940/0.7156)	mem 24308MB
[2025-01-19 02:27:02 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][20/312]	eta 0:03:27 lr 0.000520	time 0.5725 (0.7106)	model_time 0.5723 (0.6227)	loss 3.0732 (2.9269)	grad_norm 1.2413 (2.1949/0.8508)	mem 24308MB
[2025-01-19 02:27:08 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][30/312]	eta 0:03:10 lr 0.000520	time 0.6620 (0.6767)	model_time 0.6618 (0.6171)	loss 2.4431 (2.9208)	grad_norm 1.8143 (2.2524/0.9008)	mem 24308MB
[2025-01-19 02:27:14 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][40/312]	eta 0:02:58 lr 0.000519	time 0.6018 (0.6575)	model_time 0.6014 (0.6123)	loss 2.2897 (2.8594)	grad_norm 4.0879 (2.4404/1.0006)	mem 24308MB
[2025-01-19 02:27:20 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][50/312]	eta 0:02:49 lr 0.000519	time 0.5831 (0.6458)	model_time 0.5829 (0.6094)	loss 3.1381 (2.8613)	grad_norm 1.8172 (2.4588/0.9208)	mem 24308MB
[2025-01-19 02:27:26 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][60/312]	eta 0:02:41 lr 0.000519	time 0.6585 (0.6392)	model_time 0.6581 (0.6086)	loss 3.6965 (2.8585)	grad_norm 1.6742 (2.5324/1.0488)	mem 24308MB
[2025-01-19 02:27:32 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][70/312]	eta 0:02:33 lr 0.000518	time 0.5849 (0.6330)	model_time 0.5844 (0.6067)	loss 3.0990 (2.8822)	grad_norm 2.0744 (2.6374/1.1315)	mem 24308MB
[2025-01-19 02:27:38 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][80/312]	eta 0:02:25 lr 0.000518	time 0.5755 (0.6277)	model_time 0.5751 (0.6046)	loss 2.6922 (2.8918)	grad_norm 4.3387 (2.7042/1.1511)	mem 24308MB
[2025-01-19 02:27:44 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][90/312]	eta 0:02:18 lr 0.000517	time 0.6127 (0.6240)	model_time 0.6123 (0.6034)	loss 2.3691 (2.9086)	grad_norm 3.2202 (2.6771/1.1739)	mem 24308MB
[2025-01-19 02:27:50 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][100/312]	eta 0:02:11 lr 0.000517	time 0.6487 (0.6223)	model_time 0.6483 (0.6037)	loss 2.9674 (2.8941)	grad_norm 2.7199 (2.6413/1.1375)	mem 24308MB
[2025-01-19 02:27:56 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][110/312]	eta 0:02:05 lr 0.000516	time 0.5748 (0.6212)	model_time 0.5744 (0.6043)	loss 2.4894 (2.8833)	grad_norm 4.2117 (2.6597/1.1507)	mem 24308MB
[2025-01-19 02:28:03 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][120/312]	eta 0:01:59 lr 0.000516	time 0.6680 (0.6214)	model_time 0.6679 (0.6059)	loss 3.2085 (2.8906)	grad_norm 2.2027 (2.7192/1.1927)	mem 24308MB
[2025-01-19 02:28:09 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][130/312]	eta 0:01:53 lr 0.000516	time 0.6842 (0.6216)	model_time 0.6838 (0.6072)	loss 2.4096 (2.8628)	grad_norm 4.8911 (2.8363/1.2602)	mem 24308MB
[2025-01-19 02:28:15 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][140/312]	eta 0:01:46 lr 0.000515	time 0.5797 (0.6211)	model_time 0.5795 (0.6076)	loss 3.2531 (2.8659)	grad_norm 1.6366 (2.8438/1.2581)	mem 24308MB
[2025-01-19 02:28:21 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][150/312]	eta 0:01:40 lr 0.000515	time 0.6633 (0.6209)	model_time 0.6629 (0.6083)	loss 3.2847 (2.8519)	grad_norm 1.5533 (2.8028/1.2464)	mem 24308MB
[2025-01-19 02:28:27 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][160/312]	eta 0:01:34 lr 0.000514	time 0.6096 (0.6196)	model_time 0.6095 (0.6078)	loss 2.2080 (2.8589)	grad_norm 1.8766 (2.7634/1.2342)	mem 24308MB
[2025-01-19 02:28:33 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][170/312]	eta 0:01:27 lr 0.000514	time 0.5748 (0.6183)	model_time 0.5743 (0.6071)	loss 2.2053 (2.8638)	grad_norm 2.1973 (2.6994/1.2282)	mem 24308MB
[2025-01-19 02:28:39 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][180/312]	eta 0:01:21 lr 0.000513	time 0.6781 (0.6173)	model_time 0.6780 (0.6067)	loss 2.4178 (2.8497)	grad_norm 1.3581 (2.6487/1.2188)	mem 24308MB
[2025-01-19 02:28:45 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][190/312]	eta 0:01:15 lr 0.000513	time 0.5870 (0.6165)	model_time 0.5869 (0.6065)	loss 3.2001 (2.8494)	grad_norm 1.2488 (2.6383/1.2035)	mem 24308MB
[2025-01-19 02:28:51 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][200/312]	eta 0:01:08 lr 0.000512	time 0.6212 (0.6154)	model_time 0.6208 (0.6059)	loss 3.0889 (2.8496)	grad_norm 2.3114 (2.6479/1.1891)	mem 24308MB
[2025-01-19 02:28:57 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][210/312]	eta 0:01:02 lr 0.000512	time 0.6075 (0.6142)	model_time 0.6073 (0.6051)	loss 3.2512 (2.8543)	grad_norm 1.5444 (2.6601/1.1862)	mem 24308MB
[2025-01-19 02:29:03 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][220/312]	eta 0:00:56 lr 0.000512	time 0.6743 (0.6137)	model_time 0.6738 (0.6050)	loss 2.7022 (2.8491)	grad_norm 4.2276 (2.6548/1.2054)	mem 24308MB
[2025-01-19 02:29:09 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][230/312]	eta 0:00:50 lr 0.000511	time 0.5964 (0.6136)	model_time 0.5959 (0.6053)	loss 1.9911 (2.8473)	grad_norm 2.5231 (2.6719/1.2093)	mem 24308MB
[2025-01-19 02:29:16 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][240/312]	eta 0:00:44 lr 0.000511	time 0.6618 (0.6147)	model_time 0.6616 (0.6067)	loss 3.1157 (2.8501)	grad_norm 3.5915 (2.6525/1.1966)	mem 24308MB
[2025-01-19 02:29:22 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][250/312]	eta 0:00:38 lr 0.000510	time 0.5765 (0.6145)	model_time 0.5761 (0.6067)	loss 3.1567 (2.8578)	grad_norm 5.6771 (2.7028/1.2570)	mem 24308MB
[2025-01-19 02:29:28 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][260/312]	eta 0:00:31 lr 0.000510	time 0.5844 (0.6147)	model_time 0.5840 (0.6072)	loss 3.1600 (2.8691)	grad_norm 4.0363 (2.7107/1.2479)	mem 24308MB
[2025-01-19 02:29:34 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][270/312]	eta 0:00:25 lr 0.000509	time 0.6582 (0.6145)	model_time 0.6578 (0.6073)	loss 3.7115 (2.8743)	grad_norm 2.8658 (2.6856/1.2367)	mem 24308MB
[2025-01-19 02:29:40 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][280/312]	eta 0:00:19 lr 0.000509	time 0.5762 (0.6143)	model_time 0.5757 (0.6073)	loss 3.1943 (2.8819)	grad_norm 2.4472 (2.6688/1.2218)	mem 24308MB
[2025-01-19 02:29:46 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][290/312]	eta 0:00:13 lr 0.000509	time 0.5849 (0.6136)	model_time 0.5847 (0.6068)	loss 3.1051 (2.8743)	grad_norm 4.2022 (2.6689/1.2164)	mem 24308MB
[2025-01-19 02:29:52 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][300/312]	eta 0:00:07 lr 0.000508	time 0.5694 (0.6128)	model_time 0.5693 (0.6063)	loss 2.5931 (2.8764)	grad_norm 2.1589 (2.6611/1.2132)	mem 24308MB
[2025-01-19 02:29:58 internimage_s_1k_224] (main.py 510): INFO Train: [232/300][310/312]	eta 0:00:01 lr 0.000508	time 0.5695 (0.6122)	model_time 0.5694 (0.6059)	loss 3.3564 (2.8711)	grad_norm 1.9291 (2.6519/1.2129)	mem 24308MB
[2025-01-19 02:29:58 internimage_s_1k_224] (main.py 519): INFO EPOCH 232 training takes 0:03:10
[2025-01-19 02:29:58 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_232.pth saving......
[2025-01-19 02:30:00 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_232.pth saved !!!
[2025-01-19 02:30:08 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.063 (8.063)	Loss 0.7388 (0.7388)	Acc@1 85.571 (85.571)	Acc@5 97.388 (97.388)	Mem 24308MB
[2025-01-19 02:30:12 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.039)	Loss 0.9412 (0.8276)	Acc@1 79.126 (82.875)	Acc@5 95.361 (96.418)	Mem 24308MB
[2025-01-19 02:30:12 internimage_s_1k_224] (main.py 575): INFO [Epoch:232] * Acc@1 82.724 Acc@5 96.435
[2025-01-19 02:30:12 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.7%
[2025-01-19 02:30:12 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.79%
[2025-01-19 02:30:21 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.919 (8.919)	Loss 0.7036 (0.7036)	Acc@1 85.474 (85.474)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 02:30:25 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.206)	Loss 0.9117 (0.7864)	Acc@1 78.760 (82.992)	Acc@5 95.801 (96.571)	Mem 24308MB
[2025-01-19 02:30:25 internimage_s_1k_224] (main.py 575): INFO [Epoch:232] * Acc@1 82.883 Acc@5 96.593
[2025-01-19 02:30:25 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.9%
[2025-01-19 02:30:25 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:30:28 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:30:28 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.88%
[2025-01-19 02:30:30 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][0/312]	eta 0:12:46 lr 0.000508	time 2.4556 (2.4556)	model_time 0.6300 (0.6300)	loss 3.2561 (3.2561)	grad_norm 2.7464 (2.7464/0.0000)	mem 24308MB
[2025-01-19 02:30:36 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][10/312]	eta 0:03:48 lr 0.000507	time 0.5768 (0.7554)	model_time 0.5766 (0.5890)	loss 3.3341 (3.1680)	grad_norm 2.4482 (2.8870/0.8004)	mem 24308MB
[2025-01-19 02:30:42 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][20/312]	eta 0:03:17 lr 0.000507	time 0.5762 (0.6763)	model_time 0.5758 (0.5890)	loss 3.8360 (3.0810)	grad_norm 2.4638 (2.4579/0.8461)	mem 24308MB
[2025-01-19 02:30:48 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][30/312]	eta 0:03:04 lr 0.000506	time 0.5821 (0.6533)	model_time 0.5817 (0.5940)	loss 2.3690 (3.0263)	grad_norm 5.5145 (2.8347/1.2622)	mem 24308MB
[2025-01-19 02:30:55 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][40/312]	eta 0:02:55 lr 0.000506	time 0.5871 (0.6463)	model_time 0.5869 (0.6014)	loss 1.9625 (3.0157)	grad_norm 4.1149 (2.9154/1.2308)	mem 24308MB
[2025-01-19 02:31:01 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][50/312]	eta 0:02:48 lr 0.000506	time 0.6710 (0.6419)	model_time 0.6708 (0.6057)	loss 1.9651 (3.0052)	grad_norm 4.1221 (2.9068/1.1905)	mem 24308MB
[2025-01-19 02:31:07 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][60/312]	eta 0:02:40 lr 0.000505	time 0.5797 (0.6370)	model_time 0.5795 (0.6067)	loss 3.2903 (2.9956)	grad_norm 1.6483 (2.8442/1.1610)	mem 24308MB
[2025-01-19 02:31:13 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][70/312]	eta 0:02:33 lr 0.000505	time 0.5986 (0.6345)	model_time 0.5982 (0.6084)	loss 3.5370 (2.9795)	grad_norm 2.9637 (2.7055/1.1478)	mem 24308MB
[2025-01-19 02:31:19 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][80/312]	eta 0:02:26 lr 0.000504	time 0.6878 (0.6335)	model_time 0.6877 (0.6106)	loss 2.9674 (2.9525)	grad_norm 2.7989 (2.8008/1.1641)	mem 24308MB
[2025-01-19 02:31:25 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][90/312]	eta 0:02:19 lr 0.000504	time 0.6455 (0.6302)	model_time 0.6453 (0.6098)	loss 1.9697 (2.9219)	grad_norm 1.4351 (2.7699/1.1467)	mem 24308MB
[2025-01-19 02:31:31 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][100/312]	eta 0:02:12 lr 0.000503	time 0.5728 (0.6272)	model_time 0.5724 (0.6086)	loss 3.0852 (2.9281)	grad_norm 1.5949 (2.7471/1.1245)	mem 24308MB
[2025-01-19 02:31:37 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][110/312]	eta 0:02:06 lr 0.000503	time 0.5790 (0.6243)	model_time 0.5786 (0.6073)	loss 2.3445 (2.9138)	grad_norm 1.3231 (2.6584/1.1198)	mem 24308MB
[2025-01-19 02:31:43 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][120/312]	eta 0:01:59 lr 0.000503	time 0.5868 (0.6227)	model_time 0.5864 (0.6071)	loss 2.5617 (2.9191)	grad_norm 1.4672 (2.6087/1.1125)	mem 24308MB
[2025-01-19 02:31:49 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][130/312]	eta 0:01:52 lr 0.000502	time 0.5748 (0.6202)	model_time 0.5746 (0.6058)	loss 2.8003 (2.9144)	grad_norm 3.4851 (2.6227/1.1051)	mem 24308MB
[2025-01-19 02:31:55 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][140/312]	eta 0:01:46 lr 0.000502	time 0.5765 (0.6184)	model_time 0.5763 (0.6050)	loss 2.9924 (2.9183)	grad_norm 2.5569 (2.6564/1.1269)	mem 24308MB
[2025-01-19 02:32:01 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][150/312]	eta 0:01:39 lr 0.000501	time 0.5711 (0.6170)	model_time 0.5707 (0.6045)	loss 3.0272 (2.9257)	grad_norm 2.2461 (2.6172/1.1108)	mem 24308MB
[2025-01-19 02:32:07 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][160/312]	eta 0:01:33 lr 0.000501	time 0.5948 (0.6175)	model_time 0.5943 (0.6056)	loss 2.6961 (2.9207)	grad_norm 1.5858 (2.5785/1.1060)	mem 24308MB
[2025-01-19 02:32:14 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][170/312]	eta 0:01:27 lr 0.000500	time 0.6303 (0.6178)	model_time 0.6302 (0.6067)	loss 3.0954 (2.9218)	grad_norm 1.3906 (2.6044/1.1353)	mem 24308MB
[2025-01-19 02:32:20 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][180/312]	eta 0:01:21 lr 0.000500	time 0.5782 (0.6189)	model_time 0.5777 (0.6083)	loss 3.8058 (2.9220)	grad_norm 2.3567 (2.6009/1.1345)	mem 24308MB
[2025-01-19 02:32:26 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][190/312]	eta 0:01:15 lr 0.000500	time 0.5758 (0.6195)	model_time 0.5756 (0.6094)	loss 2.7126 (2.9357)	grad_norm 2.7221 (2.5921/1.1281)	mem 24308MB
[2025-01-19 02:32:32 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][200/312]	eta 0:01:09 lr 0.000499	time 0.6741 (0.6187)	model_time 0.6738 (0.6091)	loss 3.4605 (2.9534)	grad_norm 1.2936 (2.5793/1.1141)	mem 24308MB
[2025-01-19 02:32:39 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][210/312]	eta 0:01:03 lr 0.000499	time 0.5883 (0.6190)	model_time 0.5882 (0.6099)	loss 2.0990 (2.9385)	grad_norm 1.5679 (2.5611/1.1028)	mem 24308MB
[2025-01-19 02:32:45 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][220/312]	eta 0:00:56 lr 0.000498	time 0.5733 (0.6184)	model_time 0.5729 (0.6097)	loss 3.4442 (2.9489)	grad_norm 1.7161 (2.5437/1.0880)	mem 24308MB
[2025-01-19 02:32:51 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][230/312]	eta 0:00:50 lr 0.000498	time 0.5945 (0.6176)	model_time 0.5944 (0.6092)	loss 3.2727 (2.9438)	grad_norm 5.3634 (2.5973/1.1785)	mem 24308MB
[2025-01-19 02:32:57 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][240/312]	eta 0:00:44 lr 0.000497	time 0.6110 (0.6171)	model_time 0.6109 (0.6090)	loss 2.9084 (2.9446)	grad_norm 2.8288 (2.5977/1.1953)	mem 24308MB
[2025-01-19 02:33:03 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][250/312]	eta 0:00:38 lr 0.000497	time 0.5754 (0.6160)	model_time 0.5753 (0.6082)	loss 2.2118 (2.9472)	grad_norm 2.2398 (2.6240/1.2077)	mem 24308MB
[2025-01-19 02:33:09 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][260/312]	eta 0:00:31 lr 0.000497	time 0.5840 (0.6150)	model_time 0.5836 (0.6075)	loss 3.5945 (2.9486)	grad_norm 2.4527 (2.6575/1.2087)	mem 24308MB
[2025-01-19 02:33:15 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][270/312]	eta 0:00:25 lr 0.000496	time 0.5790 (0.6144)	model_time 0.5786 (0.6072)	loss 3.1526 (2.9470)	grad_norm 3.1414 (2.7063/1.2542)	mem 24308MB
[2025-01-19 02:33:21 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][280/312]	eta 0:00:19 lr 0.000496	time 0.5749 (0.6142)	model_time 0.5744 (0.6073)	loss 3.7017 (2.9507)	grad_norm 4.7735 (2.7065/1.2643)	mem 24308MB
[2025-01-19 02:33:27 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][290/312]	eta 0:00:13 lr 0.000495	time 0.6640 (0.6145)	model_time 0.6635 (0.6078)	loss 3.1072 (2.9600)	grad_norm 1.8544 (2.6953/1.2509)	mem 24308MB
[2025-01-19 02:33:33 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][300/312]	eta 0:00:07 lr 0.000495	time 0.6586 (0.6148)	model_time 0.6585 (0.6083)	loss 3.4859 (2.9638)	grad_norm 3.3504 (2.6791/1.2446)	mem 24308MB
[2025-01-19 02:33:39 internimage_s_1k_224] (main.py 510): INFO Train: [233/300][310/312]	eta 0:00:01 lr 0.000494	time 0.5698 (0.6145)	model_time 0.5697 (0.6082)	loss 3.2914 (2.9659)	grad_norm 1.3676 (2.6445/1.2466)	mem 24308MB
[2025-01-19 02:33:40 internimage_s_1k_224] (main.py 519): INFO EPOCH 233 training takes 0:03:11
[2025-01-19 02:33:40 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_233.pth saving......
[2025-01-19 02:33:42 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_233.pth saved !!!
[2025-01-19 02:33:50 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.989 (7.989)	Loss 0.7258 (0.7258)	Acc@1 84.937 (84.937)	Acc@5 97.559 (97.559)	Mem 24308MB
[2025-01-19 02:33:53 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.039)	Loss 0.9300 (0.8116)	Acc@1 78.760 (82.950)	Acc@5 95.435 (96.513)	Mem 24308MB
[2025-01-19 02:33:53 internimage_s_1k_224] (main.py 575): INFO [Epoch:233] * Acc@1 82.808 Acc@5 96.519
[2025-01-19 02:33:53 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.8%
[2025-01-19 02:33:53 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 02:33:55 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 02:33:55 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.81%
[2025-01-19 02:34:03 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.088 (8.088)	Loss 0.7035 (0.7035)	Acc@1 85.498 (85.498)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 02:34:07 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.138 (1.066)	Loss 0.9106 (0.7858)	Acc@1 78.735 (83.034)	Acc@5 95.874 (96.573)	Mem 24308MB
[2025-01-19 02:34:07 internimage_s_1k_224] (main.py 575): INFO [Epoch:233] * Acc@1 82.933 Acc@5 96.597
[2025-01-19 02:34:07 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 82.9%
[2025-01-19 02:34:07 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:34:09 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:34:09 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.93%
[2025-01-19 02:34:12 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][0/312]	eta 0:10:56 lr 0.000494	time 2.1037 (2.1037)	model_time 0.5959 (0.5959)	loss 2.4351 (2.4351)	grad_norm 1.5540 (1.5540/0.0000)	mem 24308MB
[2025-01-19 02:34:18 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][10/312]	eta 0:03:45 lr 0.000494	time 0.5735 (0.7457)	model_time 0.5733 (0.6083)	loss 3.5794 (2.7529)	grad_norm 1.4953 (1.6854/0.3247)	mem 24308MB
[2025-01-19 02:34:24 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][20/312]	eta 0:03:19 lr 0.000494	time 0.5907 (0.6824)	model_time 0.5905 (0.6103)	loss 3.0166 (2.8108)	grad_norm 2.5547 (1.9188/0.6041)	mem 24308MB
[2025-01-19 02:34:30 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][30/312]	eta 0:03:04 lr 0.000493	time 0.5970 (0.6560)	model_time 0.5968 (0.6070)	loss 3.4312 (2.9174)	grad_norm 1.4290 (2.0259/0.7679)	mem 24308MB
[2025-01-19 02:34:36 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][40/312]	eta 0:02:54 lr 0.000493	time 0.6781 (0.6420)	model_time 0.6779 (0.6049)	loss 2.7027 (2.8995)	grad_norm 1.6325 (2.2066/0.9611)	mem 24308MB
[2025-01-19 02:34:42 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][50/312]	eta 0:02:46 lr 0.000492	time 0.6203 (0.6354)	model_time 0.6198 (0.6055)	loss 1.9363 (2.8482)	grad_norm 1.6734 (2.3468/1.1044)	mem 24308MB
[2025-01-19 02:34:48 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][60/312]	eta 0:02:38 lr 0.000492	time 0.5764 (0.6287)	model_time 0.5762 (0.6037)	loss 3.4867 (2.9185)	grad_norm 2.8979 (2.3723/1.0502)	mem 24308MB
[2025-01-19 02:34:54 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][70/312]	eta 0:02:30 lr 0.000491	time 0.6258 (0.6239)	model_time 0.6256 (0.6023)	loss 3.3058 (2.9310)	grad_norm 2.6948 (2.3805/1.0311)	mem 24308MB
[2025-01-19 02:35:00 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][80/312]	eta 0:02:24 lr 0.000491	time 0.6924 (0.6212)	model_time 0.6919 (0.6022)	loss 2.2259 (2.9281)	grad_norm 3.0781 (2.3663/1.0395)	mem 24308MB
[2025-01-19 02:35:06 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][90/312]	eta 0:02:17 lr 0.000491	time 0.5865 (0.6208)	model_time 0.5860 (0.6038)	loss 3.3762 (2.9557)	grad_norm 1.9512 (2.3159/1.0029)	mem 24308MB
[2025-01-19 02:35:12 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][100/312]	eta 0:02:11 lr 0.000490	time 0.6941 (0.6220)	model_time 0.6939 (0.6067)	loss 2.7891 (2.9320)	grad_norm 2.1695 (2.3600/1.0228)	mem 24308MB
[2025-01-19 02:35:19 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][110/312]	eta 0:02:06 lr 0.000490	time 0.7614 (0.6245)	model_time 0.7610 (0.6105)	loss 2.9627 (2.9319)	grad_norm 2.5537 (2.3169/1.0009)	mem 24308MB
[2025-01-19 02:35:25 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][120/312]	eta 0:01:59 lr 0.000489	time 0.6815 (0.6242)	model_time 0.6814 (0.6114)	loss 3.3696 (2.9399)	grad_norm 1.5464 (2.3517/1.0272)	mem 24308MB
[2025-01-19 02:35:31 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][130/312]	eta 0:01:53 lr 0.000489	time 0.5720 (0.6229)	model_time 0.5719 (0.6110)	loss 3.0650 (2.9561)	grad_norm 4.4340 (2.3795/1.0387)	mem 24308MB
[2025-01-19 02:35:37 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][140/312]	eta 0:01:47 lr 0.000488	time 0.6955 (0.6227)	model_time 0.6954 (0.6116)	loss 2.8192 (2.9468)	grad_norm 3.1306 (2.3635/1.0219)	mem 24308MB
[2025-01-19 02:35:43 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][150/312]	eta 0:01:40 lr 0.000488	time 0.6032 (0.6209)	model_time 0.6031 (0.6105)	loss 3.0610 (2.9452)	grad_norm 2.4326 (2.3598/0.9979)	mem 24308MB
[2025-01-19 02:35:49 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][160/312]	eta 0:01:34 lr 0.000488	time 0.5831 (0.6191)	model_time 0.5827 (0.6094)	loss 3.4222 (2.9452)	grad_norm 3.2390 (2.3750/0.9909)	mem 24308MB
[2025-01-19 02:35:56 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][170/312]	eta 0:01:28 lr 0.000487	time 0.5816 (0.6204)	model_time 0.5815 (0.6111)	loss 3.3845 (2.9470)	grad_norm 3.0063 (2.4309/1.0129)	mem 24308MB
[2025-01-19 02:36:01 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][180/312]	eta 0:01:21 lr 0.000487	time 0.5882 (0.6188)	model_time 0.5880 (0.6101)	loss 3.0456 (2.9358)	grad_norm 1.0546 (2.4341/1.0251)	mem 24308MB
[2025-01-19 02:36:07 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][190/312]	eta 0:01:15 lr 0.000486	time 0.5714 (0.6173)	model_time 0.5709 (0.6090)	loss 2.9293 (2.9517)	grad_norm 2.2649 (2.4367/1.0270)	mem 24308MB
[2025-01-19 02:36:13 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][200/312]	eta 0:01:09 lr 0.000486	time 0.7034 (0.6165)	model_time 0.7033 (0.6086)	loss 2.1862 (2.9553)	grad_norm 2.0598 (2.4517/1.0321)	mem 24308MB
[2025-01-19 02:36:19 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][210/312]	eta 0:01:02 lr 0.000486	time 0.6776 (0.6163)	model_time 0.6774 (0.6087)	loss 3.1231 (2.9567)	grad_norm 1.6696 (2.4229/1.0223)	mem 24308MB
[2025-01-19 02:36:26 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][220/312]	eta 0:00:56 lr 0.000485	time 0.6911 (0.6167)	model_time 0.6907 (0.6095)	loss 2.9072 (2.9593)	grad_norm 4.6659 (2.4684/1.0643)	mem 24308MB
[2025-01-19 02:36:32 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][230/312]	eta 0:00:50 lr 0.000485	time 0.5929 (0.6165)	model_time 0.5927 (0.6096)	loss 3.1486 (2.9556)	grad_norm 4.7935 (2.5147/1.0916)	mem 24308MB
[2025-01-19 02:36:38 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][240/312]	eta 0:00:44 lr 0.000484	time 0.6648 (0.6168)	model_time 0.6644 (0.6101)	loss 2.3784 (2.9528)	grad_norm 3.6319 (2.5270/1.0971)	mem 24308MB
[2025-01-19 02:36:44 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][250/312]	eta 0:00:38 lr 0.000484	time 0.5766 (0.6164)	model_time 0.5761 (0.6100)	loss 3.1093 (2.9548)	grad_norm 3.8130 (2.5179/1.0847)	mem 24308MB
[2025-01-19 02:36:50 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][260/312]	eta 0:00:32 lr 0.000483	time 0.5645 (0.6166)	model_time 0.5643 (0.6104)	loss 3.3502 (2.9571)	grad_norm 3.1062 (2.5256/1.0839)	mem 24308MB
[2025-01-19 02:36:56 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][270/312]	eta 0:00:25 lr 0.000483	time 0.5990 (0.6162)	model_time 0.5988 (0.6103)	loss 2.0428 (2.9616)	grad_norm 3.0370 (2.5182/1.0788)	mem 24308MB
[2025-01-19 02:37:02 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][280/312]	eta 0:00:19 lr 0.000483	time 0.5823 (0.6153)	model_time 0.5819 (0.6095)	loss 3.3907 (2.9624)	grad_norm 4.0109 (2.5205/1.0806)	mem 24308MB
[2025-01-19 02:37:08 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][290/312]	eta 0:00:13 lr 0.000482	time 0.5763 (0.6152)	model_time 0.5758 (0.6096)	loss 2.7456 (2.9567)	grad_norm 1.8924 (2.4965/1.0769)	mem 24308MB
[2025-01-19 02:37:14 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][300/312]	eta 0:00:07 lr 0.000482	time 0.5708 (0.6145)	model_time 0.5707 (0.6091)	loss 2.9677 (2.9548)	grad_norm 1.7369 (2.4910/1.0770)	mem 24308MB
[2025-01-19 02:37:20 internimage_s_1k_224] (main.py 510): INFO Train: [234/300][310/312]	eta 0:00:01 lr 0.000481	time 0.5695 (0.6130)	model_time 0.5694 (0.6078)	loss 3.3040 (2.9488)	grad_norm 1.2140 (2.5361/1.0920)	mem 24308MB
[2025-01-19 02:37:21 internimage_s_1k_224] (main.py 519): INFO EPOCH 234 training takes 0:03:11
[2025-01-19 02:37:21 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_234.pth saving......
[2025-01-19 02:37:23 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_234.pth saved !!!
[2025-01-19 02:37:33 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 10.677 (10.677)	Loss 0.7341 (0.7341)	Acc@1 85.571 (85.571)	Acc@5 97.314 (97.314)	Mem 24308MB
[2025-01-19 02:37:40 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.138 (1.589)	Loss 0.9393 (0.8225)	Acc@1 79.810 (83.125)	Acc@5 95.532 (96.549)	Mem 24308MB
[2025-01-19 02:37:40 internimage_s_1k_224] (main.py 575): INFO [Epoch:234] * Acc@1 82.957 Acc@5 96.549
[2025-01-19 02:37:40 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.0%
[2025-01-19 02:37:40 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 02:37:42 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 02:37:42 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 82.96%
[2025-01-19 02:37:57 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.643 (14.643)	Loss 0.7033 (0.7033)	Acc@1 85.522 (85.522)	Acc@5 97.852 (97.852)	Mem 24308MB
[2025-01-19 02:38:05 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (2.049)	Loss 0.9096 (0.7852)	Acc@1 78.760 (83.057)	Acc@5 95.850 (96.582)	Mem 24308MB
[2025-01-19 02:38:05 internimage_s_1k_224] (main.py 575): INFO [Epoch:234] * Acc@1 82.961 Acc@5 96.601
[2025-01-19 02:38:05 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.0%
[2025-01-19 02:38:05 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:38:07 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:38:07 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.96%
[2025-01-19 02:38:10 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][0/312]	eta 0:12:08 lr 0.000481	time 2.3343 (2.3343)	model_time 0.6215 (0.6215)	loss 3.0939 (3.0939)	grad_norm 2.8924 (2.8924/0.0000)	mem 24308MB
[2025-01-19 02:38:16 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][10/312]	eta 0:03:47 lr 0.000481	time 0.5917 (0.7529)	model_time 0.5916 (0.5969)	loss 2.8837 (2.7848)	grad_norm 2.2054 (2.6672/0.6207)	mem 24308MB
[2025-01-19 02:38:22 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][20/312]	eta 0:03:21 lr 0.000480	time 0.5981 (0.6909)	model_time 0.5976 (0.6090)	loss 3.4284 (2.8221)	grad_norm 1.5582 (2.8188/0.8889)	mem 24308MB
[2025-01-19 02:38:28 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][30/312]	eta 0:03:08 lr 0.000480	time 0.5833 (0.6688)	model_time 0.5831 (0.6132)	loss 3.4817 (2.8730)	grad_norm 2.0330 (2.8641/1.0278)	mem 24308MB
[2025-01-19 02:38:34 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][40/312]	eta 0:02:58 lr 0.000480	time 0.6641 (0.6574)	model_time 0.6639 (0.6153)	loss 3.2499 (2.9007)	grad_norm 1.7078 (2.7564/0.9650)	mem 24308MB
[2025-01-19 02:38:41 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][50/312]	eta 0:02:51 lr 0.000479	time 0.6549 (0.6535)	model_time 0.6547 (0.6196)	loss 3.2059 (2.9115)	grad_norm 1.7360 (2.6698/0.9091)	mem 24308MB
[2025-01-19 02:38:47 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][60/312]	eta 0:02:42 lr 0.000479	time 0.5753 (0.6466)	model_time 0.5749 (0.6181)	loss 3.1196 (2.9060)	grad_norm 2.0367 (2.6946/0.9446)	mem 24308MB
[2025-01-19 02:38:53 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][70/312]	eta 0:02:35 lr 0.000478	time 0.5865 (0.6407)	model_time 0.5861 (0.6162)	loss 3.1271 (2.9055)	grad_norm 2.7151 (2.6904/0.9442)	mem 24308MB
[2025-01-19 02:38:59 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][80/312]	eta 0:02:27 lr 0.000478	time 0.5842 (0.6357)	model_time 0.5837 (0.6142)	loss 2.4387 (2.9148)	grad_norm 2.7059 (2.6283/0.9219)	mem 24308MB
[2025-01-19 02:39:05 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][90/312]	eta 0:02:20 lr 0.000477	time 0.5890 (0.6316)	model_time 0.5888 (0.6124)	loss 2.9193 (2.8966)	grad_norm 1.6243 (2.6384/0.9279)	mem 24308MB
[2025-01-19 02:39:11 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][100/312]	eta 0:02:13 lr 0.000477	time 0.5725 (0.6297)	model_time 0.5720 (0.6124)	loss 3.3781 (2.9168)	grad_norm 0.9868 (2.5822/0.9184)	mem 24308MB
[2025-01-19 02:39:17 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][110/312]	eta 0:02:06 lr 0.000477	time 0.5820 (0.6264)	model_time 0.5818 (0.6106)	loss 3.6065 (2.9198)	grad_norm 1.8100 (2.4884/0.9322)	mem 24308MB
[2025-01-19 02:39:23 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][120/312]	eta 0:01:59 lr 0.000476	time 0.5917 (0.6230)	model_time 0.5912 (0.6085)	loss 2.5058 (2.9274)	grad_norm 1.4345 (2.4461/0.9178)	mem 24308MB
[2025-01-19 02:39:29 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][130/312]	eta 0:01:52 lr 0.000476	time 0.5867 (0.6203)	model_time 0.5866 (0.6069)	loss 3.0159 (2.9237)	grad_norm 2.0296 (2.4697/0.9985)	mem 24308MB
[2025-01-19 02:39:35 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][140/312]	eta 0:01:46 lr 0.000475	time 0.5915 (0.6193)	model_time 0.5913 (0.6068)	loss 3.6277 (2.9352)	grad_norm 2.3169 (2.4520/0.9838)	mem 24308MB
[2025-01-19 02:39:41 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][150/312]	eta 0:01:40 lr 0.000475	time 0.5745 (0.6191)	model_time 0.5743 (0.6074)	loss 2.9200 (2.9201)	grad_norm 0.9195 (2.4346/0.9750)	mem 24308MB
[2025-01-19 02:39:47 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][160/312]	eta 0:01:34 lr 0.000475	time 0.6682 (0.6197)	model_time 0.6677 (0.6087)	loss 3.1455 (2.9243)	grad_norm 1.2578 (2.4520/1.0150)	mem 24308MB
[2025-01-19 02:39:53 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][170/312]	eta 0:01:28 lr 0.000474	time 0.5911 (0.6206)	model_time 0.5910 (0.6103)	loss 3.2576 (2.9364)	grad_norm 2.7450 (2.4700/1.0104)	mem 24308MB
[2025-01-19 02:40:00 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][180/312]	eta 0:01:22 lr 0.000474	time 0.6653 (0.6220)	model_time 0.6648 (0.6121)	loss 2.5756 (2.9241)	grad_norm 2.0115 (2.4707/0.9955)	mem 24308MB
[2025-01-19 02:40:06 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][190/312]	eta 0:01:15 lr 0.000473	time 0.5778 (0.6219)	model_time 0.5777 (0.6126)	loss 2.8350 (2.9291)	grad_norm 4.2290 (2.4746/0.9935)	mem 24308MB
[2025-01-19 02:40:12 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][200/312]	eta 0:01:09 lr 0.000473	time 0.5760 (0.6215)	model_time 0.5756 (0.6126)	loss 3.0821 (2.9252)	grad_norm 3.2718 (2.5226/1.0822)	mem 24308MB
[2025-01-19 02:40:18 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][210/312]	eta 0:01:03 lr 0.000473	time 0.5724 (0.6205)	model_time 0.5723 (0.6120)	loss 3.3325 (2.9290)	grad_norm 2.3298 (2.5435/1.0884)	mem 24308MB
[2025-01-19 02:40:24 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][220/312]	eta 0:00:57 lr 0.000472	time 0.5818 (0.6199)	model_time 0.5814 (0.6117)	loss 2.8376 (2.9297)	grad_norm 1.2250 (2.5283/1.0804)	mem 24308MB
[2025-01-19 02:40:30 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][230/312]	eta 0:00:50 lr 0.000472	time 0.5855 (0.6187)	model_time 0.5850 (0.6109)	loss 3.3321 (2.9255)	grad_norm 3.4797 (2.5325/1.0823)	mem 24308MB
[2025-01-19 02:40:36 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][240/312]	eta 0:00:44 lr 0.000471	time 0.6082 (0.6176)	model_time 0.6078 (0.6101)	loss 2.7334 (2.9150)	grad_norm 4.4528 (2.5655/1.1114)	mem 24308MB
[2025-01-19 02:40:42 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][250/312]	eta 0:00:38 lr 0.000471	time 0.5940 (0.6166)	model_time 0.5939 (0.6094)	loss 3.2312 (2.9213)	grad_norm 3.6203 (2.5897/1.1385)	mem 24308MB
[2025-01-19 02:40:48 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][260/312]	eta 0:00:32 lr 0.000470	time 0.5948 (0.6161)	model_time 0.5946 (0.6092)	loss 1.8252 (2.9178)	grad_norm 4.5235 (2.6163/1.1357)	mem 24308MB
[2025-01-19 02:40:54 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][270/312]	eta 0:00:25 lr 0.000470	time 0.5921 (0.6165)	model_time 0.5916 (0.6099)	loss 3.1259 (2.9200)	grad_norm 7.6174 (2.6626/1.2093)	mem 24308MB
[2025-01-19 02:41:01 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][280/312]	eta 0:00:19 lr 0.000470	time 0.6510 (0.6174)	model_time 0.6505 (0.6109)	loss 2.4637 (2.9091)	grad_norm 3.8044 (2.6986/1.2301)	mem 24308MB
[2025-01-19 02:41:07 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][290/312]	eta 0:00:13 lr 0.000469	time 0.5897 (0.6170)	model_time 0.5892 (0.6108)	loss 2.6955 (2.9184)	grad_norm 1.7422 (2.6914/1.2230)	mem 24308MB
[2025-01-19 02:41:13 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][300/312]	eta 0:00:07 lr 0.000469	time 0.6539 (0.6175)	model_time 0.6538 (0.6114)	loss 3.1846 (2.9140)	grad_norm 1.4657 (2.7092/1.2250)	mem 24308MB
[2025-01-19 02:41:19 internimage_s_1k_224] (main.py 510): INFO Train: [235/300][310/312]	eta 0:00:01 lr 0.000468	time 0.5647 (0.6169)	model_time 0.5646 (0.6111)	loss 3.0879 (2.9184)	grad_norm 2.6419 (2.7163/1.2420)	mem 24308MB
[2025-01-19 02:41:20 internimage_s_1k_224] (main.py 519): INFO EPOCH 235 training takes 0:03:12
[2025-01-19 02:41:20 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_235.pth saving......
[2025-01-19 02:41:22 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_235.pth saved !!!
[2025-01-19 02:41:30 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.800 (7.800)	Loss 0.7197 (0.7197)	Acc@1 85.962 (85.962)	Acc@5 97.485 (97.485)	Mem 24308MB
[2025-01-19 02:41:33 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.033)	Loss 0.9335 (0.8130)	Acc@1 79.321 (83.267)	Acc@5 95.776 (96.549)	Mem 24308MB
[2025-01-19 02:41:33 internimage_s_1k_224] (main.py 575): INFO [Epoch:235] * Acc@1 83.081 Acc@5 96.541
[2025-01-19 02:41:33 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.1%
[2025-01-19 02:41:33 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 02:41:35 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 02:41:35 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.08%
[2025-01-19 02:41:43 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.077 (8.077)	Loss 0.7033 (0.7033)	Acc@1 85.425 (85.425)	Acc@5 97.852 (97.852)	Mem 24308MB
[2025-01-19 02:41:47 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.069)	Loss 0.9085 (0.7846)	Acc@1 78.857 (83.059)	Acc@5 95.850 (96.578)	Mem 24308MB
[2025-01-19 02:41:47 internimage_s_1k_224] (main.py 575): INFO [Epoch:235] * Acc@1 82.957 Acc@5 96.601
[2025-01-19 02:41:47 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.0%
[2025-01-19 02:41:47 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 82.96%
[2025-01-19 02:41:50 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][0/312]	eta 0:15:31 lr 0.000468	time 2.9871 (2.9871)	model_time 1.1263 (1.1263)	loss 3.0268 (3.0268)	grad_norm 1.9024 (1.9024/0.0000)	mem 24308MB
[2025-01-19 02:41:56 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][10/312]	eta 0:04:09 lr 0.000468	time 0.6828 (0.8265)	model_time 0.6824 (0.6570)	loss 2.4097 (2.7716)	grad_norm 2.4254 (1.9016/0.6293)	mem 24308MB
[2025-01-19 02:42:02 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][20/312]	eta 0:03:28 lr 0.000467	time 0.5875 (0.7150)	model_time 0.5869 (0.6247)	loss 2.8989 (2.8679)	grad_norm 1.4316 (2.2004/1.3432)	mem 24308MB
[2025-01-19 02:42:08 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][30/312]	eta 0:03:12 lr 0.000467	time 0.5789 (0.6840)	model_time 0.5787 (0.6227)	loss 3.3591 (2.8161)	grad_norm 4.2997 (2.2614/1.2550)	mem 24308MB
[2025-01-19 02:42:14 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][40/312]	eta 0:02:59 lr 0.000467	time 0.5944 (0.6615)	model_time 0.5939 (0.6151)	loss 2.7613 (2.8516)	grad_norm 5.4340 (2.3265/1.3053)	mem 24308MB
[2025-01-19 02:42:20 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][50/312]	eta 0:02:49 lr 0.000466	time 0.5929 (0.6478)	model_time 0.5927 (0.6104)	loss 2.8269 (2.8567)	grad_norm 3.7691 (2.6308/1.4608)	mem 24308MB
[2025-01-19 02:42:26 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][60/312]	eta 0:02:41 lr 0.000466	time 0.5804 (0.6412)	model_time 0.5802 (0.6099)	loss 3.3342 (2.8877)	grad_norm 1.8139 (2.6528/1.4262)	mem 24308MB
[2025-01-19 02:42:32 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][70/312]	eta 0:02:33 lr 0.000465	time 0.5839 (0.6363)	model_time 0.5835 (0.6093)	loss 2.6443 (2.8427)	grad_norm 1.6468 (2.6567/1.3601)	mem 24308MB
[2025-01-19 02:42:39 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][80/312]	eta 0:02:27 lr 0.000465	time 0.5994 (0.6364)	model_time 0.5989 (0.6128)	loss 2.0756 (2.8314)	grad_norm 3.4477 (2.6369/1.2945)	mem 24308MB
[2025-01-19 02:42:45 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][90/312]	eta 0:02:20 lr 0.000465	time 0.5845 (0.6346)	model_time 0.5839 (0.6135)	loss 3.3379 (2.8380)	grad_norm 1.1031 (2.5889/1.2624)	mem 24308MB
[2025-01-19 02:42:51 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][100/312]	eta 0:02:14 lr 0.000464	time 0.6794 (0.6333)	model_time 0.6792 (0.6143)	loss 3.1940 (2.8622)	grad_norm 1.3934 (2.5295/1.2279)	mem 24308MB
[2025-01-19 02:42:57 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][110/312]	eta 0:02:07 lr 0.000464	time 0.6730 (0.6312)	model_time 0.6728 (0.6138)	loss 3.2213 (2.8726)	grad_norm 2.2795 (2.4934/1.2044)	mem 24308MB
[2025-01-19 02:43:03 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][120/312]	eta 0:02:00 lr 0.000463	time 0.5879 (0.6284)	model_time 0.5874 (0.6124)	loss 2.1338 (2.8657)	grad_norm 3.7234 (2.5803/1.2654)	mem 24308MB
[2025-01-19 02:43:09 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][130/312]	eta 0:01:53 lr 0.000463	time 0.5848 (0.6250)	model_time 0.5847 (0.6102)	loss 3.3249 (2.8801)	grad_norm 3.9431 (2.6588/1.3207)	mem 24308MB
[2025-01-19 02:43:15 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][140/312]	eta 0:01:47 lr 0.000463	time 0.5900 (0.6230)	model_time 0.5895 (0.6092)	loss 2.6440 (2.8713)	grad_norm 4.6104 (2.6700/1.3053)	mem 24308MB
[2025-01-19 02:43:21 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][150/312]	eta 0:01:40 lr 0.000462	time 0.7040 (0.6219)	model_time 0.7039 (0.6090)	loss 3.0636 (2.8745)	grad_norm 1.6325 (2.7244/1.3650)	mem 24308MB
[2025-01-19 02:43:27 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][160/312]	eta 0:01:34 lr 0.000462	time 0.5913 (0.6204)	model_time 0.5911 (0.6083)	loss 2.0350 (2.8752)	grad_norm 1.8530 (2.7565/1.3484)	mem 24308MB
[2025-01-19 02:43:33 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][170/312]	eta 0:01:27 lr 0.000461	time 0.5892 (0.6186)	model_time 0.5890 (0.6071)	loss 2.6035 (2.8852)	grad_norm 3.0065 (2.7334/1.3285)	mem 24308MB
[2025-01-19 02:43:39 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][180/312]	eta 0:01:21 lr 0.000461	time 0.5740 (0.6178)	model_time 0.5738 (0.6070)	loss 2.1875 (2.8798)	grad_norm 2.5118 (2.7079/1.3107)	mem 24308MB
[2025-01-19 02:43:45 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][190/312]	eta 0:01:15 lr 0.000460	time 0.5801 (0.6179)	model_time 0.5796 (0.6076)	loss 2.9303 (2.8847)	grad_norm 2.1071 (2.7659/1.3760)	mem 24308MB
[2025-01-19 02:43:51 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][200/312]	eta 0:01:09 lr 0.000460	time 0.5767 (0.6178)	model_time 0.5763 (0.6081)	loss 3.1386 (2.8784)	grad_norm 2.3488 (2.7596/1.3620)	mem 24308MB
[2025-01-19 02:43:58 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][210/312]	eta 0:01:03 lr 0.000460	time 0.5895 (0.6185)	model_time 0.5894 (0.6092)	loss 2.9612 (2.8936)	grad_norm 2.0817 (2.7400/1.3422)	mem 24308MB
[2025-01-19 02:44:04 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][220/312]	eta 0:00:56 lr 0.000459	time 0.5805 (0.6188)	model_time 0.5803 (0.6099)	loss 2.1540 (2.8904)	grad_norm 2.8877 (2.6982/1.3303)	mem 24308MB
[2025-01-19 02:44:10 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][230/312]	eta 0:00:50 lr 0.000459	time 0.6586 (0.6189)	model_time 0.6585 (0.6104)	loss 3.1572 (2.8950)	grad_norm 3.7935 (2.6847/1.3209)	mem 24308MB
[2025-01-19 02:44:16 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][240/312]	eta 0:00:44 lr 0.000458	time 0.5740 (0.6187)	model_time 0.5738 (0.6105)	loss 2.5122 (2.8884)	grad_norm 1.4410 (2.6674/1.3160)	mem 24308MB
[2025-01-19 02:44:22 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][250/312]	eta 0:00:38 lr 0.000458	time 0.5885 (0.6176)	model_time 0.5881 (0.6097)	loss 2.4060 (2.8871)	grad_norm 1.5301 (2.6476/1.3050)	mem 24308MB
[2025-01-19 02:44:28 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][260/312]	eta 0:00:32 lr 0.000458	time 0.6024 (0.6168)	model_time 0.6020 (0.6092)	loss 3.2119 (2.8826)	grad_norm 4.2993 (2.6626/1.2906)	mem 24308MB
[2025-01-19 02:44:34 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][270/312]	eta 0:00:25 lr 0.000457	time 0.5782 (0.6164)	model_time 0.5777 (0.6091)	loss 3.6184 (2.8830)	grad_norm 1.7737 (2.6321/1.2800)	mem 24308MB
[2025-01-19 02:44:40 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][280/312]	eta 0:00:19 lr 0.000457	time 0.5850 (0.6161)	model_time 0.5848 (0.6090)	loss 3.3090 (2.8886)	grad_norm 1.6729 (2.6158/1.2689)	mem 24308MB
[2025-01-19 02:44:46 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][290/312]	eta 0:00:13 lr 0.000456	time 0.5789 (0.6151)	model_time 0.5784 (0.6083)	loss 2.5849 (2.8895)	grad_norm 2.4892 (2.6142/1.2596)	mem 24308MB
[2025-01-19 02:44:52 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][300/312]	eta 0:00:07 lr 0.000456	time 0.5699 (0.6144)	model_time 0.5698 (0.6077)	loss 2.3963 (2.8868)	grad_norm 2.9566 (2.6185/1.2574)	mem 24308MB
[2025-01-19 02:44:58 internimage_s_1k_224] (main.py 510): INFO Train: [236/300][310/312]	eta 0:00:01 lr 0.000456	time 0.5686 (0.6135)	model_time 0.5685 (0.6070)	loss 3.4788 (2.8891)	grad_norm 3.4189 (2.6332/1.2558)	mem 24308MB
[2025-01-19 02:44:59 internimage_s_1k_224] (main.py 519): INFO EPOCH 236 training takes 0:03:11
[2025-01-19 02:44:59 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_236.pth saving......
[2025-01-19 02:45:00 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_236.pth saved !!!
[2025-01-19 02:45:08 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.986 (7.986)	Loss 0.7374 (0.7374)	Acc@1 85.596 (85.596)	Acc@5 97.778 (97.778)	Mem 24308MB
[2025-01-19 02:45:12 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.046)	Loss 0.9417 (0.8257)	Acc@1 79.126 (83.216)	Acc@5 95.532 (96.458)	Mem 24308MB
[2025-01-19 02:45:12 internimage_s_1k_224] (main.py 575): INFO [Epoch:236] * Acc@1 83.087 Acc@5 96.493
[2025-01-19 02:45:12 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.1%
[2025-01-19 02:45:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 02:45:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 02:45:14 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.09%
[2025-01-19 02:45:22 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.822 (7.822)	Loss 0.7031 (0.7031)	Acc@1 85.498 (85.498)	Acc@5 97.852 (97.852)	Mem 24308MB
[2025-01-19 02:45:25 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.034)	Loss 0.9075 (0.7841)	Acc@1 78.833 (83.110)	Acc@5 95.850 (96.586)	Mem 24308MB
[2025-01-19 02:45:26 internimage_s_1k_224] (main.py 575): INFO [Epoch:236] * Acc@1 83.007 Acc@5 96.609
[2025-01-19 02:45:26 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.0%
[2025-01-19 02:45:26 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:45:28 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:45:28 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.01%
[2025-01-19 02:45:30 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][0/312]	eta 0:10:38 lr 0.000455	time 2.0449 (2.0449)	model_time 0.6060 (0.6060)	loss 2.2215 (2.2215)	grad_norm 1.5667 (1.5667/0.0000)	mem 24308MB
[2025-01-19 02:45:36 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][10/312]	eta 0:03:49 lr 0.000455	time 0.5755 (0.7600)	model_time 0.5754 (0.6289)	loss 2.5269 (2.6264)	grad_norm 1.1418 (2.3369/1.6963)	mem 24308MB
[2025-01-19 02:45:43 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][20/312]	eta 0:03:21 lr 0.000455	time 0.5854 (0.6905)	model_time 0.5852 (0.6216)	loss 2.8461 (2.7785)	grad_norm 2.6531 (2.2334/1.3058)	mem 24308MB
[2025-01-19 02:45:49 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][30/312]	eta 0:03:08 lr 0.000454	time 0.5986 (0.6687)	model_time 0.5984 (0.6220)	loss 3.3023 (2.8077)	grad_norm 1.5589 (2.1932/1.1528)	mem 24308MB
[2025-01-19 02:45:55 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][40/312]	eta 0:02:59 lr 0.000454	time 0.6885 (0.6591)	model_time 0.6883 (0.6237)	loss 2.7213 (2.8181)	grad_norm 1.7970 (2.1298/1.0359)	mem 24308MB
[2025-01-19 02:46:01 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][50/312]	eta 0:02:50 lr 0.000453	time 0.5744 (0.6508)	model_time 0.5742 (0.6221)	loss 2.8033 (2.8803)	grad_norm 5.3929 (2.2789/1.1439)	mem 24308MB
[2025-01-19 02:46:07 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][60/312]	eta 0:02:41 lr 0.000453	time 0.5934 (0.6422)	model_time 0.5932 (0.6181)	loss 2.4298 (2.8776)	grad_norm 0.9965 (2.3717/1.1652)	mem 24308MB
[2025-01-19 02:46:13 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][70/312]	eta 0:02:34 lr 0.000453	time 0.5762 (0.6383)	model_time 0.5761 (0.6176)	loss 3.2945 (2.8795)	grad_norm 3.7226 (2.4174/1.1466)	mem 24308MB
[2025-01-19 02:46:19 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][80/312]	eta 0:02:27 lr 0.000452	time 0.5973 (0.6344)	model_time 0.5968 (0.6161)	loss 2.9877 (2.8966)	grad_norm 1.6754 (2.4076/1.0973)	mem 24308MB
[2025-01-19 02:46:25 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][90/312]	eta 0:02:20 lr 0.000452	time 0.5795 (0.6311)	model_time 0.5791 (0.6148)	loss 3.5045 (2.9033)	grad_norm 1.3464 (2.3921/1.0572)	mem 24308MB
[2025-01-19 02:46:31 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][100/312]	eta 0:02:12 lr 0.000451	time 0.5880 (0.6270)	model_time 0.5878 (0.6123)	loss 2.5225 (2.8872)	grad_norm 1.6248 (2.3936/1.0492)	mem 24308MB
[2025-01-19 02:46:37 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][110/312]	eta 0:02:05 lr 0.000451	time 0.6044 (0.6238)	model_time 0.6039 (0.6103)	loss 3.3324 (2.8922)	grad_norm 1.9613 (2.4207/1.0446)	mem 24308MB
[2025-01-19 02:46:43 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][120/312]	eta 0:01:59 lr 0.000451	time 0.5896 (0.6231)	model_time 0.5891 (0.6106)	loss 2.9432 (2.8986)	grad_norm 1.4256 (2.4664/1.1277)	mem 24308MB
[2025-01-19 02:46:50 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][130/312]	eta 0:01:53 lr 0.000450	time 0.5926 (0.6221)	model_time 0.5922 (0.6106)	loss 2.7429 (2.8999)	grad_norm 1.7013 (2.5709/1.1992)	mem 24308MB
[2025-01-19 02:46:56 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][140/312]	eta 0:01:46 lr 0.000450	time 0.5800 (0.6220)	model_time 0.5798 (0.6112)	loss 2.9596 (2.9088)	grad_norm 3.4031 (2.6344/1.2440)	mem 24308MB
[2025-01-19 02:47:02 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][150/312]	eta 0:01:40 lr 0.000449	time 0.5730 (0.6220)	model_time 0.5726 (0.6119)	loss 3.2060 (2.9100)	grad_norm 1.9911 (2.6182/1.2109)	mem 24308MB
[2025-01-19 02:47:08 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][160/312]	eta 0:01:34 lr 0.000449	time 0.5736 (0.6237)	model_time 0.5734 (0.6142)	loss 2.5904 (2.9054)	grad_norm 1.4635 (2.5885/1.1940)	mem 24308MB
[2025-01-19 02:47:14 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][170/312]	eta 0:01:28 lr 0.000449	time 0.5732 (0.6222)	model_time 0.5730 (0.6132)	loss 2.9786 (2.9129)	grad_norm 1.3554 (2.5746/1.2081)	mem 24308MB
[2025-01-19 02:47:20 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][180/312]	eta 0:01:21 lr 0.000448	time 0.5878 (0.6202)	model_time 0.5876 (0.6118)	loss 3.0271 (2.9272)	grad_norm 3.2416 (2.5778/1.1934)	mem 24308MB
[2025-01-19 02:47:26 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][190/312]	eta 0:01:15 lr 0.000448	time 0.5992 (0.6192)	model_time 0.5987 (0.6112)	loss 3.1558 (2.9278)	grad_norm 2.5907 (2.5755/1.1837)	mem 24308MB
[2025-01-19 02:47:32 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][200/312]	eta 0:01:09 lr 0.000447	time 0.6933 (0.6184)	model_time 0.6928 (0.6107)	loss 2.9512 (2.9220)	grad_norm 1.2509 (2.5468/1.1764)	mem 24308MB
[2025-01-19 02:47:38 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][210/312]	eta 0:01:02 lr 0.000447	time 0.5827 (0.6174)	model_time 0.5823 (0.6101)	loss 3.0567 (2.9200)	grad_norm 3.8334 (2.5514/1.1654)	mem 24308MB
[2025-01-19 02:47:44 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][220/312]	eta 0:00:56 lr 0.000447	time 0.5910 (0.6161)	model_time 0.5907 (0.6091)	loss 3.1924 (2.9220)	grad_norm 1.3439 (2.5443/1.1542)	mem 24308MB
[2025-01-19 02:47:50 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][230/312]	eta 0:00:50 lr 0.000446	time 0.5860 (0.6149)	model_time 0.5858 (0.6082)	loss 1.9733 (2.9068)	grad_norm 1.8380 (2.5345/1.1379)	mem 24308MB
[2025-01-19 02:47:56 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][240/312]	eta 0:00:44 lr 0.000446	time 0.6007 (0.6145)	model_time 0.6003 (0.6080)	loss 2.7513 (2.9153)	grad_norm 4.6410 (2.5403/1.1401)	mem 24308MB
[2025-01-19 02:48:02 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][250/312]	eta 0:00:38 lr 0.000445	time 0.5973 (0.6146)	model_time 0.5969 (0.6084)	loss 3.4824 (2.9163)	grad_norm 4.0903 (2.5518/1.1409)	mem 24308MB
[2025-01-19 02:48:09 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][260/312]	eta 0:00:31 lr 0.000445	time 0.5869 (0.6150)	model_time 0.5867 (0.6090)	loss 2.8084 (2.9167)	grad_norm 4.0125 (2.5815/1.1580)	mem 24308MB
[2025-01-19 02:48:15 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][270/312]	eta 0:00:25 lr 0.000445	time 0.6537 (0.6149)	model_time 0.6535 (0.6091)	loss 2.9785 (2.9053)	grad_norm 1.5360 (2.5692/1.1528)	mem 24308MB
[2025-01-19 02:48:21 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][280/312]	eta 0:00:19 lr 0.000444	time 0.6393 (0.6152)	model_time 0.6391 (0.6096)	loss 3.3114 (2.8972)	grad_norm 2.8841 (2.5599/1.1391)	mem 24308MB
[2025-01-19 02:48:27 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][290/312]	eta 0:00:13 lr 0.000444	time 0.6342 (0.6152)	model_time 0.6340 (0.6098)	loss 3.1290 (2.8938)	grad_norm 1.7327 (2.5594/1.1396)	mem 24308MB
[2025-01-19 02:48:33 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][300/312]	eta 0:00:07 lr 0.000443	time 0.5809 (0.6141)	model_time 0.5808 (0.6088)	loss 2.3560 (2.8906)	grad_norm 3.1051 (2.5779/1.1505)	mem 24308MB
[2025-01-19 02:48:39 internimage_s_1k_224] (main.py 510): INFO Train: [237/300][310/312]	eta 0:00:01 lr 0.000443	time 0.5691 (0.6130)	model_time 0.5690 (0.6079)	loss 2.3664 (2.8907)	grad_norm 5.6748 (2.6087/1.1323)	mem 24308MB
[2025-01-19 02:48:39 internimage_s_1k_224] (main.py 519): INFO EPOCH 237 training takes 0:03:11
[2025-01-19 02:48:39 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_237.pth saving......
[2025-01-19 02:48:41 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_237.pth saved !!!
[2025-01-19 02:48:49 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.248 (8.248)	Loss 0.7473 (0.7473)	Acc@1 85.132 (85.132)	Acc@5 97.510 (97.510)	Mem 24308MB
[2025-01-19 02:48:53 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.059)	Loss 0.9383 (0.8211)	Acc@1 79.297 (83.003)	Acc@5 95.435 (96.484)	Mem 24308MB
[2025-01-19 02:48:53 internimage_s_1k_224] (main.py 575): INFO [Epoch:237] * Acc@1 82.865 Acc@5 96.491
[2025-01-19 02:48:53 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 82.9%
[2025-01-19 02:48:53 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.09%
[2025-01-19 02:49:02 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.015 (9.015)	Loss 0.7030 (0.7030)	Acc@1 85.498 (85.498)	Acc@5 97.852 (97.852)	Mem 24308MB
[2025-01-19 02:49:06 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.216)	Loss 0.9065 (0.7835)	Acc@1 78.906 (83.168)	Acc@5 95.825 (96.582)	Mem 24308MB
[2025-01-19 02:49:07 internimage_s_1k_224] (main.py 575): INFO [Epoch:237] * Acc@1 83.061 Acc@5 96.609
[2025-01-19 02:49:07 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.1%
[2025-01-19 02:49:07 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:49:09 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:49:09 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.06%
[2025-01-19 02:49:11 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][0/312]	eta 0:10:58 lr 0.000443	time 2.1119 (2.1119)	model_time 0.5959 (0.5959)	loss 2.8982 (2.8982)	grad_norm 1.6926 (1.6926/0.0000)	mem 24308MB
[2025-01-19 02:49:17 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][10/312]	eta 0:03:43 lr 0.000442	time 0.6618 (0.7411)	model_time 0.6616 (0.6029)	loss 2.7798 (2.9200)	grad_norm 2.1140 (3.2500/1.3830)	mem 24308MB
[2025-01-19 02:49:23 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][20/312]	eta 0:03:17 lr 0.000442	time 0.5853 (0.6764)	model_time 0.5848 (0.6039)	loss 3.4113 (2.9654)	grad_norm 1.6954 (2.6118/1.3221)	mem 24308MB
[2025-01-19 02:49:29 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][30/312]	eta 0:03:02 lr 0.000442	time 0.5848 (0.6483)	model_time 0.5846 (0.5990)	loss 3.0025 (2.9261)	grad_norm 3.7699 (2.7362/1.4467)	mem 24308MB
[2025-01-19 02:49:35 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][40/312]	eta 0:02:52 lr 0.000441	time 0.5828 (0.6347)	model_time 0.5826 (0.5974)	loss 2.0598 (2.9304)	grad_norm 1.5658 (2.8624/1.3782)	mem 24308MB
[2025-01-19 02:49:41 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][50/312]	eta 0:02:44 lr 0.000441	time 0.5852 (0.6292)	model_time 0.5741 (0.5990)	loss 3.2172 (2.9180)	grad_norm 4.2113 (2.8957/1.3748)	mem 24308MB
[2025-01-19 02:49:47 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][60/312]	eta 0:02:38 lr 0.000440	time 0.7131 (0.6294)	model_time 0.7129 (0.6041)	loss 2.0574 (2.9135)	grad_norm 1.8007 (2.7261/1.3309)	mem 24308MB
[2025-01-19 02:49:54 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][70/312]	eta 0:02:32 lr 0.000440	time 0.5846 (0.6309)	model_time 0.5844 (0.6090)	loss 3.4926 (2.9537)	grad_norm 6.0728 (2.7207/1.3357)	mem 24308MB
[2025-01-19 02:50:00 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][80/312]	eta 0:02:25 lr 0.000440	time 0.5946 (0.6291)	model_time 0.5944 (0.6099)	loss 3.1445 (2.9614)	grad_norm 2.8937 (2.7440/1.3055)	mem 24308MB
[2025-01-19 02:50:06 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][90/312]	eta 0:02:19 lr 0.000439	time 0.6614 (0.6278)	model_time 0.6609 (0.6107)	loss 3.1684 (2.9443)	grad_norm 2.9838 (2.7600/1.2999)	mem 24308MB
[2025-01-19 02:50:12 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][100/312]	eta 0:02:13 lr 0.000439	time 0.5943 (0.6275)	model_time 0.5941 (0.6121)	loss 3.4680 (2.9748)	grad_norm 2.7587 (2.6916/1.2721)	mem 24308MB
[2025-01-19 02:50:18 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][110/312]	eta 0:02:06 lr 0.000438	time 0.5972 (0.6241)	model_time 0.5971 (0.6100)	loss 2.8067 (2.9760)	grad_norm 2.4529 (2.6381/1.2390)	mem 24308MB
[2025-01-19 02:50:24 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][120/312]	eta 0:01:59 lr 0.000438	time 0.5915 (0.6225)	model_time 0.5913 (0.6096)	loss 2.6528 (2.9665)	grad_norm 2.0207 (2.6105/1.2059)	mem 24308MB
[2025-01-19 02:50:30 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][130/312]	eta 0:01:52 lr 0.000438	time 0.5797 (0.6204)	model_time 0.5795 (0.6084)	loss 2.1146 (2.9701)	grad_norm 2.9984 (2.5908/1.1744)	mem 24308MB
[2025-01-19 02:50:36 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][140/312]	eta 0:01:46 lr 0.000437	time 0.5973 (0.6194)	model_time 0.5971 (0.6082)	loss 2.7267 (2.9773)	grad_norm 6.2357 (2.6264/1.2100)	mem 24308MB
[2025-01-19 02:50:42 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][150/312]	eta 0:01:39 lr 0.000437	time 0.5847 (0.6172)	model_time 0.5845 (0.6068)	loss 2.3401 (2.9643)	grad_norm 1.6868 (2.6997/1.2553)	mem 24308MB
[2025-01-19 02:50:48 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][160/312]	eta 0:01:33 lr 0.000436	time 0.5643 (0.6154)	model_time 0.5641 (0.6056)	loss 3.0436 (2.9497)	grad_norm 2.7331 (2.6853/1.2334)	mem 24308MB
[2025-01-19 02:50:54 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][170/312]	eta 0:01:27 lr 0.000436	time 0.6620 (0.6150)	model_time 0.6618 (0.6057)	loss 2.8966 (2.9478)	grad_norm 3.0682 (2.6539/1.2131)	mem 24308MB
[2025-01-19 02:51:00 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][180/312]	eta 0:01:21 lr 0.000436	time 0.6909 (0.6156)	model_time 0.6907 (0.6068)	loss 3.0865 (2.9355)	grad_norm 3.3151 (2.6402/1.1941)	mem 24308MB
[2025-01-19 02:51:06 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][190/312]	eta 0:01:15 lr 0.000435	time 0.5854 (0.6156)	model_time 0.5852 (0.6073)	loss 3.3289 (2.9263)	grad_norm 2.1682 (2.6174/1.1721)	mem 24308MB
[2025-01-19 02:51:13 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][200/312]	eta 0:01:08 lr 0.000435	time 0.5960 (0.6156)	model_time 0.5958 (0.6076)	loss 2.9247 (2.9273)	grad_norm 1.4330 (2.5851/1.1534)	mem 24308MB
[2025-01-19 02:51:19 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][210/312]	eta 0:01:02 lr 0.000434	time 0.6836 (0.6164)	model_time 0.6834 (0.6088)	loss 3.1603 (2.9313)	grad_norm 3.3884 (2.6061/1.1510)	mem 24308MB
[2025-01-19 02:51:25 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][220/312]	eta 0:00:56 lr 0.000434	time 0.5754 (0.6178)	model_time 0.5752 (0.6106)	loss 2.5115 (2.9358)	grad_norm 3.2628 (2.6140/1.1368)	mem 24308MB
[2025-01-19 02:51:31 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][230/312]	eta 0:00:50 lr 0.000434	time 0.5997 (0.6165)	model_time 0.5992 (0.6095)	loss 2.8188 (2.9360)	grad_norm 1.2476 (2.5768/1.1320)	mem 24308MB
[2025-01-19 02:51:37 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][240/312]	eta 0:00:44 lr 0.000433	time 0.5874 (0.6159)	model_time 0.5873 (0.6092)	loss 3.1167 (2.9319)	grad_norm 2.0055 (2.5671/1.1362)	mem 24308MB
[2025-01-19 02:51:43 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][250/312]	eta 0:00:38 lr 0.000433	time 0.5971 (0.6152)	model_time 0.5965 (0.6087)	loss 3.3729 (2.9259)	grad_norm 1.5718 (2.5732/1.1356)	mem 24308MB
[2025-01-19 02:51:49 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][260/312]	eta 0:00:31 lr 0.000432	time 0.5764 (0.6149)	model_time 0.5762 (0.6087)	loss 2.9878 (2.9228)	grad_norm 1.5819 (2.5819/1.1329)	mem 24308MB
[2025-01-19 02:51:55 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][270/312]	eta 0:00:25 lr 0.000432	time 0.5896 (0.6137)	model_time 0.5894 (0.6077)	loss 3.4546 (2.9247)	grad_norm 3.5015 (2.5887/1.1337)	mem 24308MB
[2025-01-19 02:52:01 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][280/312]	eta 0:00:19 lr 0.000432	time 0.5820 (0.6127)	model_time 0.5816 (0.6069)	loss 2.5482 (2.9255)	grad_norm 3.6825 (2.5955/1.1294)	mem 24308MB
[2025-01-19 02:52:07 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][290/312]	eta 0:00:13 lr 0.000431	time 0.5799 (0.6121)	model_time 0.5797 (0.6065)	loss 2.0245 (2.9136)	grad_norm 0.9840 (2.5869/1.1220)	mem 24308MB
[2025-01-19 02:52:13 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][300/312]	eta 0:00:07 lr 0.000431	time 0.6566 (0.6119)	model_time 0.6565 (0.6065)	loss 2.4261 (2.9107)	grad_norm 2.2940 (2.6024/1.1195)	mem 24308MB
[2025-01-19 02:52:19 internimage_s_1k_224] (main.py 510): INFO Train: [238/300][310/312]	eta 0:00:01 lr 0.000431	time 0.5717 (0.6113)	model_time 0.5716 (0.6061)	loss 2.0521 (2.9121)	grad_norm 2.8453 (2.5752/1.0889)	mem 24308MB
[2025-01-19 02:52:20 internimage_s_1k_224] (main.py 519): INFO EPOCH 238 training takes 0:03:10
[2025-01-19 02:52:20 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_238.pth saving......
[2025-01-19 02:52:21 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_238.pth saved !!!
[2025-01-19 02:52:29 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.779 (7.779)	Loss 0.7175 (0.7175)	Acc@1 85.547 (85.547)	Acc@5 97.607 (97.607)	Mem 24308MB
[2025-01-19 02:52:33 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.041)	Loss 0.9369 (0.8173)	Acc@1 79.419 (83.239)	Acc@5 95.776 (96.560)	Mem 24308MB
[2025-01-19 02:52:33 internimage_s_1k_224] (main.py 575): INFO [Epoch:238] * Acc@1 83.077 Acc@5 96.557
[2025-01-19 02:52:33 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.1%
[2025-01-19 02:52:33 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.09%
[2025-01-19 02:52:42 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.921 (8.921)	Loss 0.7027 (0.7027)	Acc@1 85.522 (85.522)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 02:52:47 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.136 (1.221)	Loss 0.9055 (0.7830)	Acc@1 78.979 (83.190)	Acc@5 95.825 (96.600)	Mem 24308MB
[2025-01-19 02:52:47 internimage_s_1k_224] (main.py 575): INFO [Epoch:238] * Acc@1 83.085 Acc@5 96.629
[2025-01-19 02:52:47 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.1%
[2025-01-19 02:52:47 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:52:49 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:52:49 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.09%
[2025-01-19 02:52:51 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][0/312]	eta 0:11:48 lr 0.000430	time 2.2712 (2.2712)	model_time 0.6047 (0.6047)	loss 3.0824 (3.0824)	grad_norm 5.5596 (5.5596/0.0000)	mem 24308MB
[2025-01-19 02:52:57 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][10/312]	eta 0:03:50 lr 0.000430	time 0.5819 (0.7621)	model_time 0.5817 (0.6103)	loss 3.0020 (2.8985)	grad_norm 1.4726 (2.8673/1.2020)	mem 24308MB
[2025-01-19 02:53:04 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][20/312]	eta 0:03:23 lr 0.000430	time 0.7111 (0.6962)	model_time 0.7106 (0.6166)	loss 3.1856 (2.9072)	grad_norm 3.8343 (3.0488/1.2313)	mem 24308MB
[2025-01-19 02:53:10 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][30/312]	eta 0:03:09 lr 0.000429	time 0.5888 (0.6724)	model_time 0.5886 (0.6184)	loss 3.3998 (2.9096)	grad_norm 2.7760 (3.3655/1.4601)	mem 24308MB
[2025-01-19 02:53:16 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][40/312]	eta 0:02:57 lr 0.000429	time 0.5785 (0.6513)	model_time 0.5783 (0.6103)	loss 2.8853 (2.9917)	grad_norm 3.1962 (3.3221/1.3921)	mem 24308MB
[2025-01-19 02:53:22 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][50/312]	eta 0:02:49 lr 0.000428	time 0.9493 (0.6457)	model_time 0.9491 (0.6127)	loss 3.1885 (2.9283)	grad_norm 3.1764 (3.2707/1.3256)	mem 24308MB
[2025-01-19 02:53:28 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][60/312]	eta 0:02:40 lr 0.000428	time 0.6057 (0.6374)	model_time 0.6055 (0.6097)	loss 2.6786 (2.8682)	grad_norm 3.7450 (3.1741/1.3097)	mem 24308MB
[2025-01-19 02:53:34 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][70/312]	eta 0:02:33 lr 0.000428	time 0.6049 (0.6347)	model_time 0.6047 (0.6109)	loss 3.3398 (2.9189)	grad_norm 3.4822 (3.1962/1.2591)	mem 24308MB
[2025-01-19 02:53:40 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][80/312]	eta 0:02:25 lr 0.000427	time 0.5964 (0.6289)	model_time 0.5962 (0.6080)	loss 1.9200 (2.9200)	grad_norm 2.0833 (3.2048/1.2377)	mem 24308MB
[2025-01-19 02:53:46 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][90/312]	eta 0:02:18 lr 0.000427	time 0.5909 (0.6245)	model_time 0.5907 (0.6058)	loss 3.0767 (2.9367)	grad_norm 6.3802 (3.2052/1.2701)	mem 24308MB
[2025-01-19 02:53:52 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][100/312]	eta 0:02:12 lr 0.000426	time 0.5749 (0.6226)	model_time 0.5747 (0.6058)	loss 2.9600 (2.9372)	grad_norm 3.2040 (3.1619/1.2447)	mem 24308MB
[2025-01-19 02:53:58 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][110/312]	eta 0:02:05 lr 0.000426	time 0.5860 (0.6214)	model_time 0.5858 (0.6061)	loss 3.1609 (2.9435)	grad_norm 1.5376 (3.1529/1.2411)	mem 24308MB
[2025-01-19 02:54:04 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][120/312]	eta 0:01:59 lr 0.000426	time 0.6125 (0.6221)	model_time 0.6123 (0.6079)	loss 3.5927 (2.9489)	grad_norm 1.2710 (3.1079/1.2514)	mem 24308MB
[2025-01-19 02:54:10 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][130/312]	eta 0:01:53 lr 0.000425	time 0.5802 (0.6214)	model_time 0.5800 (0.6084)	loss 2.6159 (2.9494)	grad_norm 1.7661 (3.0297/1.2440)	mem 24308MB
[2025-01-19 02:54:17 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][140/312]	eta 0:01:46 lr 0.000425	time 0.5851 (0.6209)	model_time 0.5846 (0.6087)	loss 3.0862 (2.9429)	grad_norm 2.3154 (2.9810/1.2208)	mem 24308MB
[2025-01-19 02:54:23 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][150/312]	eta 0:01:40 lr 0.000424	time 0.5794 (0.6212)	model_time 0.5791 (0.6099)	loss 3.3469 (2.9455)	grad_norm 1.1237 (2.9068/1.2204)	mem 24308MB
[2025-01-19 02:54:29 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][160/312]	eta 0:01:34 lr 0.000424	time 0.5704 (0.6201)	model_time 0.5702 (0.6094)	loss 2.9702 (2.9528)	grad_norm 2.6754 (2.8689/1.2086)	mem 24308MB
[2025-01-19 02:54:35 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][170/312]	eta 0:01:27 lr 0.000424	time 0.6787 (0.6188)	model_time 0.6785 (0.6087)	loss 3.0472 (2.9678)	grad_norm 2.3690 (2.8347/1.1879)	mem 24308MB
[2025-01-19 02:54:41 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][180/312]	eta 0:01:21 lr 0.000423	time 0.5839 (0.6175)	model_time 0.5837 (0.6080)	loss 3.1773 (2.9668)	grad_norm 4.6063 (2.8117/1.1839)	mem 24308MB
[2025-01-19 02:54:47 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][190/312]	eta 0:01:15 lr 0.000423	time 0.5903 (0.6185)	model_time 0.5901 (0.6095)	loss 3.3758 (2.9619)	grad_norm 4.2457 (2.8022/1.1651)	mem 24308MB
[2025-01-19 02:54:53 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][200/312]	eta 0:01:09 lr 0.000423	time 0.5668 (0.6168)	model_time 0.5666 (0.6081)	loss 2.9629 (2.9537)	grad_norm 1.6731 (2.8756/1.2650)	mem 24308MB
[2025-01-19 02:54:59 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][210/312]	eta 0:01:02 lr 0.000422	time 0.5842 (0.6154)	model_time 0.5840 (0.6071)	loss 3.6549 (2.9483)	grad_norm 2.8835 (2.9261/1.3290)	mem 24308MB
[2025-01-19 02:55:05 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][220/312]	eta 0:00:56 lr 0.000422	time 0.5754 (0.6142)	model_time 0.5752 (0.6063)	loss 3.3487 (2.9500)	grad_norm 3.5936 (2.9128/1.3184)	mem 24308MB
[2025-01-19 02:55:11 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][230/312]	eta 0:00:50 lr 0.000421	time 0.5860 (0.6141)	model_time 0.5858 (0.6065)	loss 3.0311 (2.9529)	grad_norm 2.1277 (2.8795/1.3039)	mem 24308MB
[2025-01-19 02:55:17 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][240/312]	eta 0:00:44 lr 0.000421	time 0.5746 (0.6143)	model_time 0.5745 (0.6070)	loss 3.1851 (2.9591)	grad_norm 1.3815 (2.8435/1.2938)	mem 24308MB
[2025-01-19 02:55:23 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][250/312]	eta 0:00:38 lr 0.000421	time 0.6851 (0.6148)	model_time 0.6846 (0.6078)	loss 3.2831 (2.9577)	grad_norm 1.1514 (2.8380/1.2844)	mem 24308MB
[2025-01-19 02:55:30 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][260/312]	eta 0:00:31 lr 0.000420	time 0.5820 (0.6152)	model_time 0.5819 (0.6084)	loss 2.8842 (2.9490)	grad_norm 3.6219 (2.8772/1.3198)	mem 24308MB
[2025-01-19 02:55:36 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][270/312]	eta 0:00:25 lr 0.000420	time 0.5826 (0.6154)	model_time 0.5824 (0.6089)	loss 3.5342 (2.9459)	grad_norm 4.1438 (2.8954/1.3174)	mem 24308MB
[2025-01-19 02:55:42 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][280/312]	eta 0:00:19 lr 0.000419	time 0.5857 (0.6148)	model_time 0.5856 (0.6085)	loss 3.2272 (2.9450)	grad_norm 2.1295 (2.8923/1.3099)	mem 24308MB
[2025-01-19 02:55:48 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][290/312]	eta 0:00:13 lr 0.000419	time 0.6712 (0.6143)	model_time 0.6711 (0.6082)	loss 3.3038 (2.9499)	grad_norm 2.9901 (2.8792/1.3027)	mem 24308MB
[2025-01-19 02:55:54 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][300/312]	eta 0:00:07 lr 0.000419	time 0.6882 (0.6136)	model_time 0.6881 (0.6077)	loss 3.6044 (2.9497)	grad_norm 2.7157 (2.8667/1.2973)	mem 24308MB
[2025-01-19 02:56:00 internimage_s_1k_224] (main.py 510): INFO Train: [239/300][310/312]	eta 0:00:01 lr 0.000418	time 0.5693 (0.6131)	model_time 0.5692 (0.6074)	loss 2.2363 (2.9437)	grad_norm 5.4202 (2.8905/1.3151)	mem 24308MB
[2025-01-19 02:56:00 internimage_s_1k_224] (main.py 519): INFO EPOCH 239 training takes 0:03:11
[2025-01-19 02:56:00 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_239.pth saving......
[2025-01-19 02:56:02 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_239.pth saved !!!
[2025-01-19 02:56:10 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.055 (8.055)	Loss 0.7175 (0.7175)	Acc@1 85.596 (85.596)	Acc@5 97.534 (97.534)	Mem 24308MB
[2025-01-19 02:56:13 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.032)	Loss 0.9400 (0.8098)	Acc@1 79.150 (83.205)	Acc@5 95.654 (96.547)	Mem 24308MB
[2025-01-19 02:56:14 internimage_s_1k_224] (main.py 575): INFO [Epoch:239] * Acc@1 83.049 Acc@5 96.543
[2025-01-19 02:56:14 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.0%
[2025-01-19 02:56:14 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.09%
[2025-01-19 02:56:22 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.794 (8.794)	Loss 0.7024 (0.7024)	Acc@1 85.474 (85.474)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 02:56:27 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.183)	Loss 0.9044 (0.7824)	Acc@1 78.979 (83.232)	Acc@5 95.850 (96.609)	Mem 24308MB
[2025-01-19 02:56:27 internimage_s_1k_224] (main.py 575): INFO [Epoch:239] * Acc@1 83.133 Acc@5 96.637
[2025-01-19 02:56:27 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.1%
[2025-01-19 02:56:27 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 02:56:29 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 02:56:29 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.13%
[2025-01-19 02:56:31 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][0/312]	eta 0:12:14 lr 0.000418	time 2.3549 (2.3549)	model_time 0.6165 (0.6165)	loss 2.5067 (2.5067)	grad_norm 2.9280 (2.9280/0.0000)	mem 24308MB
[2025-01-19 02:56:37 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][10/312]	eta 0:03:47 lr 0.000418	time 0.5944 (0.7519)	model_time 0.5942 (0.5935)	loss 2.6011 (2.9997)	grad_norm 3.0804 (2.3337/0.6823)	mem 24308MB
[2025-01-19 02:56:43 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][20/312]	eta 0:03:17 lr 0.000417	time 0.5956 (0.6773)	model_time 0.5949 (0.5942)	loss 3.4307 (2.9409)	grad_norm 1.7002 (2.2933/0.6638)	mem 24308MB
[2025-01-19 02:56:49 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][30/312]	eta 0:03:04 lr 0.000417	time 0.6892 (0.6544)	model_time 0.6887 (0.5980)	loss 1.9972 (2.9525)	grad_norm 2.1295 (2.2688/0.6503)	mem 24308MB
[2025-01-19 02:56:55 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][40/312]	eta 0:02:55 lr 0.000417	time 0.5675 (0.6436)	model_time 0.5673 (0.6009)	loss 2.8461 (2.9402)	grad_norm 2.2665 (2.2204/0.6308)	mem 24308MB
[2025-01-19 02:57:01 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][50/312]	eta 0:02:47 lr 0.000416	time 0.6623 (0.6385)	model_time 0.6622 (0.6041)	loss 2.4626 (2.9407)	grad_norm 1.6511 (2.2112/0.6963)	mem 24308MB
[2025-01-19 02:57:08 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][60/312]	eta 0:02:39 lr 0.000416	time 0.5835 (0.6348)	model_time 0.5833 (0.6059)	loss 2.9507 (2.9452)	grad_norm 1.8501 (2.4113/0.8658)	mem 24308MB
[2025-01-19 02:57:14 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][70/312]	eta 0:02:32 lr 0.000415	time 0.5794 (0.6310)	model_time 0.5793 (0.6062)	loss 3.0557 (2.9269)	grad_norm 4.0830 (2.6302/1.1371)	mem 24308MB
[2025-01-19 02:57:20 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][80/312]	eta 0:02:25 lr 0.000415	time 0.6071 (0.6292)	model_time 0.6069 (0.6073)	loss 2.0501 (2.9215)	grad_norm 4.3444 (2.7362/1.2343)	mem 24308MB
[2025-01-19 02:57:26 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][90/312]	eta 0:02:18 lr 0.000415	time 0.5806 (0.6255)	model_time 0.5804 (0.6060)	loss 3.0689 (2.9143)	grad_norm 1.8377 (2.6850/1.2203)	mem 24308MB
[2025-01-19 02:57:32 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][100/312]	eta 0:02:11 lr 0.000414	time 0.6928 (0.6226)	model_time 0.6923 (0.6050)	loss 1.8957 (2.9054)	grad_norm 2.1688 (2.6427/1.1791)	mem 24308MB
[2025-01-19 02:57:38 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][110/312]	eta 0:02:05 lr 0.000414	time 0.6140 (0.6204)	model_time 0.6137 (0.6044)	loss 1.9227 (2.9035)	grad_norm 2.4869 (2.6203/1.1580)	mem 24308MB
[2025-01-19 02:57:44 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][120/312]	eta 0:01:58 lr 0.000413	time 0.6872 (0.6192)	model_time 0.6870 (0.6044)	loss 2.7473 (2.9070)	grad_norm 2.7041 (2.6466/1.1782)	mem 24308MB
[2025-01-19 02:57:50 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][130/312]	eta 0:01:52 lr 0.000413	time 0.5822 (0.6167)	model_time 0.5817 (0.6030)	loss 3.0424 (2.9015)	grad_norm 3.0169 (2.6322/1.1707)	mem 24308MB
[2025-01-19 02:57:56 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][140/312]	eta 0:01:45 lr 0.000413	time 0.5644 (0.6155)	model_time 0.5639 (0.6028)	loss 2.9027 (2.9016)	grad_norm 1.8899 (2.6010/1.1536)	mem 24308MB
[2025-01-19 02:58:02 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][150/312]	eta 0:01:39 lr 0.000412	time 0.6811 (0.6148)	model_time 0.6809 (0.6029)	loss 3.0202 (2.9086)	grad_norm 2.7823 (2.6095/1.1404)	mem 24308MB
[2025-01-19 02:58:08 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][160/312]	eta 0:01:33 lr 0.000412	time 0.5862 (0.6136)	model_time 0.5857 (0.6024)	loss 3.4515 (2.9042)	grad_norm 2.0835 (2.5787/1.1207)	mem 24308MB
[2025-01-19 02:58:14 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][170/312]	eta 0:01:27 lr 0.000412	time 0.6632 (0.6138)	model_time 0.6631 (0.6033)	loss 2.9899 (2.9093)	grad_norm 3.7025 (2.5680/1.1084)	mem 24308MB
[2025-01-19 02:58:20 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][180/312]	eta 0:01:21 lr 0.000411	time 0.5783 (0.6147)	model_time 0.5778 (0.6047)	loss 2.7136 (2.9099)	grad_norm 2.5100 (2.6279/1.1363)	mem 24308MB
[2025-01-19 02:58:26 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][190/312]	eta 0:01:14 lr 0.000411	time 0.5687 (0.6143)	model_time 0.5682 (0.6048)	loss 2.9567 (2.9046)	grad_norm 4.2630 (2.6325/1.1257)	mem 24308MB
[2025-01-19 02:58:33 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][200/312]	eta 0:01:08 lr 0.000410	time 0.7075 (0.6157)	model_time 0.7072 (0.6066)	loss 2.4567 (2.8930)	grad_norm 1.6788 (2.6050/1.1085)	mem 24308MB
[2025-01-19 02:58:39 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][210/312]	eta 0:01:02 lr 0.000410	time 0.5820 (0.6146)	model_time 0.5818 (0.6059)	loss 3.0150 (2.9002)	grad_norm 1.4428 (2.5758/1.0975)	mem 24308MB
[2025-01-19 02:58:44 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][220/312]	eta 0:00:56 lr 0.000410	time 0.5867 (0.6134)	model_time 0.5865 (0.6052)	loss 2.6855 (2.8981)	grad_norm 2.7276 (2.5820/1.0918)	mem 24308MB
[2025-01-19 02:58:50 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][230/312]	eta 0:00:50 lr 0.000409	time 0.5727 (0.6130)	model_time 0.5726 (0.6051)	loss 3.1529 (2.9035)	grad_norm 3.4322 (2.5950/1.1045)	mem 24308MB
[2025-01-19 02:58:56 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][240/312]	eta 0:00:44 lr 0.000409	time 0.5956 (0.6124)	model_time 0.5954 (0.6048)	loss 3.1949 (2.9053)	grad_norm 1.7907 (2.5809/1.0965)	mem 24308MB
[2025-01-19 02:59:02 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][250/312]	eta 0:00:37 lr 0.000408	time 0.5873 (0.6116)	model_time 0.5869 (0.6043)	loss 3.4027 (2.9053)	grad_norm 1.6260 (2.5837/1.0974)	mem 24308MB
[2025-01-19 02:59:08 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][260/312]	eta 0:00:31 lr 0.000408	time 0.5621 (0.6112)	model_time 0.5620 (0.6041)	loss 3.2495 (2.9052)	grad_norm 3.0804 (2.6131/1.1207)	mem 24308MB
[2025-01-19 02:59:14 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][270/312]	eta 0:00:25 lr 0.000408	time 0.6649 (0.6108)	model_time 0.6647 (0.6040)	loss 3.3257 (2.9020)	grad_norm 4.7407 (2.6393/1.1649)	mem 24308MB
[2025-01-19 02:59:20 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][280/312]	eta 0:00:19 lr 0.000407	time 0.5786 (0.6102)	model_time 0.5782 (0.6036)	loss 3.5333 (2.8985)	grad_norm 5.4734 (2.6843/1.2039)	mem 24308MB
[2025-01-19 02:59:26 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][290/312]	eta 0:00:13 lr 0.000407	time 0.5697 (0.6104)	model_time 0.5692 (0.6041)	loss 3.0341 (2.8996)	grad_norm 1.3225 (2.6734/1.1918)	mem 24308MB
[2025-01-19 02:59:33 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][300/312]	eta 0:00:07 lr 0.000407	time 0.6399 (0.6112)	model_time 0.6398 (0.6051)	loss 3.0116 (2.9015)	grad_norm 2.2450 (2.6630/1.1869)	mem 24308MB
[2025-01-19 02:59:39 internimage_s_1k_224] (main.py 510): INFO Train: [240/300][310/312]	eta 0:00:01 lr 0.000406	time 0.6760 (0.6107)	model_time 0.6759 (0.6048)	loss 2.7984 (2.9023)	grad_norm 1.7096 (2.6455/1.1916)	mem 24308MB
[2025-01-19 02:59:39 internimage_s_1k_224] (main.py 519): INFO EPOCH 240 training takes 0:03:10
[2025-01-19 02:59:39 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_240.pth saving......
[2025-01-19 02:59:41 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_240.pth saved !!!
[2025-01-19 02:59:51 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 10.026 (10.026)	Loss 0.7209 (0.7209)	Acc@1 85.718 (85.718)	Acc@5 97.583 (97.583)	Mem 24308MB
[2025-01-19 02:59:58 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.550)	Loss 0.8890 (0.7958)	Acc@1 79.883 (83.330)	Acc@5 95.776 (96.604)	Mem 24308MB
[2025-01-19 02:59:58 internimage_s_1k_224] (main.py 575): INFO [Epoch:240] * Acc@1 83.177 Acc@5 96.591
[2025-01-19 02:59:58 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.2%
[2025-01-19 02:59:58 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 03:00:00 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 03:00:00 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.18%
[2025-01-19 03:00:15 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.727 (14.727)	Loss 0.7021 (0.7021)	Acc@1 85.474 (85.474)	Acc@5 97.803 (97.803)	Mem 24308MB
[2025-01-19 03:00:24 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (2.131)	Loss 0.9032 (0.7818)	Acc@1 79.004 (83.250)	Acc@5 95.825 (96.620)	Mem 24308MB
[2025-01-19 03:00:24 internimage_s_1k_224] (main.py 575): INFO [Epoch:240] * Acc@1 83.153 Acc@5 96.649
[2025-01-19 03:00:24 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.2%
[2025-01-19 03:00:24 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:00:26 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:00:26 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.15%
[2025-01-19 03:00:28 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][0/312]	eta 0:10:47 lr 0.000406	time 2.0767 (2.0767)	model_time 0.5963 (0.5963)	loss 1.9180 (1.9180)	grad_norm 2.1511 (2.1511/0.0000)	mem 24308MB
[2025-01-19 03:00:35 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][10/312]	eta 0:03:50 lr 0.000406	time 0.5820 (0.7634)	model_time 0.5816 (0.6285)	loss 2.8892 (2.9356)	grad_norm 2.8496 (2.3550/0.7059)	mem 24308MB
[2025-01-19 03:00:41 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][20/312]	eta 0:03:20 lr 0.000405	time 0.5840 (0.6883)	model_time 0.5838 (0.6174)	loss 2.8640 (2.7925)	grad_norm 2.0706 (2.4712/0.9891)	mem 24308MB
[2025-01-19 03:00:47 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][30/312]	eta 0:03:05 lr 0.000405	time 0.6115 (0.6571)	model_time 0.6109 (0.6090)	loss 3.4403 (2.8943)	grad_norm 1.6893 (2.5053/1.0246)	mem 24308MB
[2025-01-19 03:00:53 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][40/312]	eta 0:02:55 lr 0.000405	time 0.5838 (0.6443)	model_time 0.5837 (0.6078)	loss 2.8954 (2.9403)	grad_norm 1.7972 (2.7290/1.3747)	mem 24308MB
[2025-01-19 03:00:59 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][50/312]	eta 0:02:46 lr 0.000404	time 0.5801 (0.6337)	model_time 0.5797 (0.6042)	loss 3.5168 (2.8918)	grad_norm 3.3325 (2.6800/1.3234)	mem 24308MB
[2025-01-19 03:01:05 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][60/312]	eta 0:02:38 lr 0.000404	time 0.5694 (0.6278)	model_time 0.5689 (0.6030)	loss 2.8731 (2.8980)	grad_norm 3.4233 (2.6299/1.2435)	mem 24308MB
[2025-01-19 03:01:11 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][70/312]	eta 0:02:30 lr 0.000403	time 0.5793 (0.6230)	model_time 0.5792 (0.6016)	loss 2.8477 (2.8883)	grad_norm 1.4183 (2.5041/1.2014)	mem 24308MB
[2025-01-19 03:01:17 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][80/312]	eta 0:02:23 lr 0.000403	time 0.5819 (0.6198)	model_time 0.5814 (0.6010)	loss 3.2511 (2.8962)	grad_norm 2.6332 (2.4759/1.1439)	mem 24308MB
[2025-01-19 03:01:23 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][90/312]	eta 0:02:17 lr 0.000403	time 0.6870 (0.6183)	model_time 0.6868 (0.6015)	loss 2.0692 (2.8965)	grad_norm 1.4536 (2.4729/1.1002)	mem 24308MB
[2025-01-19 03:01:29 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][100/312]	eta 0:02:11 lr 0.000402	time 0.7735 (0.6185)	model_time 0.7733 (0.6034)	loss 2.4779 (2.8991)	grad_norm 4.0973 (2.4980/1.0724)	mem 24308MB
[2025-01-19 03:01:35 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][110/312]	eta 0:02:05 lr 0.000402	time 0.6565 (0.6225)	model_time 0.6563 (0.6087)	loss 2.9960 (2.9098)	grad_norm 3.7717 (2.5948/1.1366)	mem 24308MB
[2025-01-19 03:01:41 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][120/312]	eta 0:01:59 lr 0.000401	time 0.5838 (0.6210)	model_time 0.5833 (0.6083)	loss 3.0531 (2.9205)	grad_norm 1.9976 (2.6753/1.1541)	mem 24308MB
[2025-01-19 03:01:48 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][130/312]	eta 0:01:52 lr 0.000401	time 0.5893 (0.6206)	model_time 0.5891 (0.6088)	loss 3.2799 (2.9213)	grad_norm 1.6098 (2.6781/1.1227)	mem 24308MB
[2025-01-19 03:01:54 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][140/312]	eta 0:01:46 lr 0.000401	time 0.5702 (0.6202)	model_time 0.5698 (0.6093)	loss 2.8141 (2.9234)	grad_norm 2.3020 (2.6031/1.1210)	mem 24308MB
[2025-01-19 03:02:00 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][150/312]	eta 0:01:40 lr 0.000400	time 0.5820 (0.6183)	model_time 0.5815 (0.6080)	loss 2.2564 (2.9245)	grad_norm 3.4094 (2.5811/1.0970)	mem 24308MB
[2025-01-19 03:02:06 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][160/312]	eta 0:01:33 lr 0.000400	time 0.5876 (0.6175)	model_time 0.5873 (0.6078)	loss 2.1471 (2.9110)	grad_norm 2.0103 (2.5801/1.0929)	mem 24308MB
[2025-01-19 03:02:12 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][170/312]	eta 0:01:27 lr 0.000400	time 0.5638 (0.6168)	model_time 0.5636 (0.6077)	loss 3.0502 (2.8981)	grad_norm 5.7153 (2.5988/1.1066)	mem 24308MB
[2025-01-19 03:02:18 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][180/312]	eta 0:01:21 lr 0.000399	time 0.5811 (0.6159)	model_time 0.5809 (0.6073)	loss 3.1314 (2.9028)	grad_norm 2.0654 (2.6276/1.1177)	mem 24308MB
[2025-01-19 03:02:24 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][190/312]	eta 0:01:14 lr 0.000399	time 0.5793 (0.6147)	model_time 0.5791 (0.6065)	loss 2.3604 (2.8921)	grad_norm 6.0346 (2.6444/1.1349)	mem 24308MB
[2025-01-19 03:02:30 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][200/312]	eta 0:01:08 lr 0.000398	time 0.5883 (0.6136)	model_time 0.5882 (0.6058)	loss 3.1293 (2.8860)	grad_norm 1.6876 (2.6308/1.1257)	mem 24308MB
[2025-01-19 03:02:36 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][210/312]	eta 0:01:02 lr 0.000398	time 0.6701 (0.6130)	model_time 0.6699 (0.6056)	loss 3.4452 (2.8943)	grad_norm 1.5174 (2.6036/1.1088)	mem 24308MB
[2025-01-19 03:02:42 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][220/312]	eta 0:00:56 lr 0.000398	time 0.7013 (0.6133)	model_time 0.7008 (0.6061)	loss 3.1958 (2.8955)	grad_norm 3.1828 (2.6114/1.1225)	mem 24308MB
[2025-01-19 03:02:48 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][230/312]	eta 0:00:50 lr 0.000397	time 0.5767 (0.6135)	model_time 0.5763 (0.6067)	loss 3.4529 (2.9055)	grad_norm 1.8060 (2.6199/1.1255)	mem 24308MB
[2025-01-19 03:02:54 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][240/312]	eta 0:00:44 lr 0.000397	time 0.5729 (0.6132)	model_time 0.5723 (0.6066)	loss 3.5517 (2.9053)	grad_norm 1.4383 (2.5872/1.1297)	mem 24308MB
[2025-01-19 03:03:00 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][250/312]	eta 0:00:38 lr 0.000396	time 0.5839 (0.6134)	model_time 0.5835 (0.6071)	loss 3.6866 (2.9079)	grad_norm 1.7398 (2.6060/1.1271)	mem 24308MB
[2025-01-19 03:03:06 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][260/312]	eta 0:00:31 lr 0.000396	time 0.5966 (0.6129)	model_time 0.5964 (0.6068)	loss 3.7306 (2.9117)	grad_norm 1.3143 (2.5785/1.1250)	mem 24308MB
[2025-01-19 03:03:12 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][270/312]	eta 0:00:25 lr 0.000396	time 0.6126 (0.6121)	model_time 0.6122 (0.6062)	loss 3.0218 (2.9121)	grad_norm 1.7444 (2.5707/1.1115)	mem 24308MB
[2025-01-19 03:03:18 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][280/312]	eta 0:00:19 lr 0.000395	time 0.5715 (0.6117)	model_time 0.5713 (0.6060)	loss 2.9884 (2.9141)	grad_norm 2.5423 (2.5805/1.1161)	mem 24308MB
[2025-01-19 03:03:24 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][290/312]	eta 0:00:13 lr 0.000395	time 0.5746 (0.6117)	model_time 0.5745 (0.6062)	loss 2.3182 (2.9074)	grad_norm 3.5318 (2.6208/1.1330)	mem 24308MB
[2025-01-19 03:03:30 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][300/312]	eta 0:00:07 lr 0.000395	time 0.5675 (0.6109)	model_time 0.5674 (0.6056)	loss 2.6144 (2.9037)	grad_norm 1.7350 (2.6493/1.1586)	mem 24308MB
[2025-01-19 03:03:36 internimage_s_1k_224] (main.py 510): INFO Train: [241/300][310/312]	eta 0:00:01 lr 0.000394	time 0.5747 (0.6101)	model_time 0.5746 (0.6049)	loss 2.9168 (2.9044)	grad_norm 2.9554 (2.6615/1.1650)	mem 24308MB
[2025-01-19 03:03:37 internimage_s_1k_224] (main.py 519): INFO EPOCH 241 training takes 0:03:10
[2025-01-19 03:03:37 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_241.pth saving......
[2025-01-19 03:03:38 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_241.pth saved !!!
[2025-01-19 03:03:46 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.004 (8.004)	Loss 0.7185 (0.7185)	Acc@1 85.498 (85.498)	Acc@5 97.510 (97.510)	Mem 24308MB
[2025-01-19 03:03:50 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.052)	Loss 0.9084 (0.7960)	Acc@1 79.614 (83.378)	Acc@5 95.654 (96.606)	Mem 24308MB
[2025-01-19 03:03:50 internimage_s_1k_224] (main.py 575): INFO [Epoch:241] * Acc@1 83.267 Acc@5 96.607
[2025-01-19 03:03:50 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.3%
[2025-01-19 03:03:50 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 03:03:52 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 03:03:52 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.27%
[2025-01-19 03:04:01 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.420 (8.420)	Loss 0.7021 (0.7021)	Acc@1 85.474 (85.474)	Acc@5 97.778 (97.778)	Mem 24308MB
[2025-01-19 03:04:04 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.087)	Loss 0.9021 (0.7813)	Acc@1 79.053 (83.272)	Acc@5 95.850 (96.626)	Mem 24308MB
[2025-01-19 03:04:04 internimage_s_1k_224] (main.py 575): INFO [Epoch:241] * Acc@1 83.171 Acc@5 96.655
[2025-01-19 03:04:04 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.2%
[2025-01-19 03:04:04 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:04:07 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:04:07 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.17%
[2025-01-19 03:04:09 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][0/312]	eta 0:11:47 lr 0.000394	time 2.2686 (2.2686)	model_time 0.6116 (0.6116)	loss 2.2447 (2.2447)	grad_norm 1.9953 (1.9953/0.0000)	mem 24308MB
[2025-01-19 03:04:15 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][10/312]	eta 0:03:48 lr 0.000394	time 0.5780 (0.7559)	model_time 0.5776 (0.6049)	loss 3.2559 (3.0670)	grad_norm 4.2727 (2.6516/0.7895)	mem 24308MB
[2025-01-19 03:04:21 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][20/312]	eta 0:03:19 lr 0.000393	time 0.5982 (0.6840)	model_time 0.5980 (0.6048)	loss 2.6510 (2.9737)	grad_norm 4.4268 (2.5331/0.8379)	mem 24308MB
[2025-01-19 03:04:27 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][30/312]	eta 0:03:05 lr 0.000393	time 0.5798 (0.6590)	model_time 0.5793 (0.6052)	loss 3.3919 (2.9558)	grad_norm 2.2447 (2.3762/0.7658)	mem 24308MB
[2025-01-19 03:04:33 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][40/312]	eta 0:02:57 lr 0.000393	time 0.6662 (0.6520)	model_time 0.6658 (0.6112)	loss 1.8662 (2.9282)	grad_norm 2.8345 (2.3219/0.7108)	mem 24308MB
[2025-01-19 03:04:39 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][50/312]	eta 0:02:48 lr 0.000392	time 0.5854 (0.6424)	model_time 0.5848 (0.6095)	loss 2.7461 (2.8995)	grad_norm 3.9789 (2.4046/0.7572)	mem 24308MB
[2025-01-19 03:04:46 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][60/312]	eta 0:02:41 lr 0.000392	time 0.7138 (0.6408)	model_time 0.7133 (0.6133)	loss 3.0393 (2.9018)	grad_norm 2.6587 (2.4013/0.7314)	mem 24308MB
[2025-01-19 03:04:52 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][70/312]	eta 0:02:34 lr 0.000391	time 0.5770 (0.6372)	model_time 0.5766 (0.6135)	loss 2.7396 (2.8993)	grad_norm 0.9204 (2.3405/0.7376)	mem 24308MB
[2025-01-19 03:04:58 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][80/312]	eta 0:02:26 lr 0.000391	time 0.5929 (0.6315)	model_time 0.5927 (0.6107)	loss 3.3373 (2.9143)	grad_norm 2.6675 (2.3547/0.7047)	mem 24308MB
[2025-01-19 03:05:04 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][90/312]	eta 0:02:19 lr 0.000391	time 0.6941 (0.6291)	model_time 0.6937 (0.6105)	loss 3.3260 (2.9344)	grad_norm 1.7201 (2.4402/0.7856)	mem 24308MB
[2025-01-19 03:05:10 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][100/312]	eta 0:02:12 lr 0.000390	time 0.6764 (0.6267)	model_time 0.6760 (0.6099)	loss 3.2737 (2.9305)	grad_norm 5.0981 (2.5153/0.8783)	mem 24308MB
[2025-01-19 03:05:16 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][110/312]	eta 0:02:05 lr 0.000390	time 0.6010 (0.6235)	model_time 0.6009 (0.6082)	loss 3.3725 (2.9365)	grad_norm 2.1312 (2.6291/1.0177)	mem 24308MB
[2025-01-19 03:05:22 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][120/312]	eta 0:01:59 lr 0.000390	time 0.5826 (0.6212)	model_time 0.5825 (0.6072)	loss 3.0579 (2.9382)	grad_norm 2.4395 (2.6041/0.9970)	mem 24308MB
[2025-01-19 03:05:28 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][130/312]	eta 0:01:52 lr 0.000389	time 0.5653 (0.6193)	model_time 0.5652 (0.6062)	loss 3.6791 (2.9469)	grad_norm 3.0123 (2.5712/0.9852)	mem 24308MB
[2025-01-19 03:05:34 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][140/312]	eta 0:01:46 lr 0.000389	time 0.6052 (0.6178)	model_time 0.6046 (0.6057)	loss 3.1792 (2.9544)	grad_norm 2.6721 (2.5926/0.9843)	mem 24308MB
[2025-01-19 03:05:40 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][150/312]	eta 0:01:40 lr 0.000388	time 0.5836 (0.6175)	model_time 0.5832 (0.6062)	loss 3.2035 (2.9486)	grad_norm 2.6378 (2.5531/0.9714)	mem 24308MB
[2025-01-19 03:05:46 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][160/312]	eta 0:01:33 lr 0.000388	time 0.6676 (0.6178)	model_time 0.6671 (0.6072)	loss 3.7618 (2.9556)	grad_norm 2.1053 (2.5539/0.9629)	mem 24308MB
[2025-01-19 03:05:52 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][170/312]	eta 0:01:27 lr 0.000388	time 0.5894 (0.6170)	model_time 0.5890 (0.6069)	loss 3.1950 (2.9661)	grad_norm 2.8702 (2.5647/0.9526)	mem 24308MB
[2025-01-19 03:05:58 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][180/312]	eta 0:01:21 lr 0.000387	time 0.7231 (0.6175)	model_time 0.7230 (0.6080)	loss 3.0715 (2.9643)	grad_norm 3.0563 (2.5783/0.9715)	mem 24308MB
[2025-01-19 03:06:04 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][190/312]	eta 0:01:15 lr 0.000387	time 0.6097 (0.6172)	model_time 0.6092 (0.6081)	loss 3.5364 (2.9577)	grad_norm 3.8574 (2.5868/0.9628)	mem 24308MB
[2025-01-19 03:06:10 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][200/312]	eta 0:01:08 lr 0.000387	time 0.6186 (0.6159)	model_time 0.6182 (0.6073)	loss 3.3732 (2.9601)	grad_norm 3.4905 (2.6906/1.1123)	mem 24308MB
[2025-01-19 03:06:17 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][210/312]	eta 0:01:02 lr 0.000386	time 0.9258 (0.6161)	model_time 0.9254 (0.6079)	loss 2.6436 (2.9583)	grad_norm 2.0313 (2.6768/1.0946)	mem 24308MB
[2025-01-19 03:06:23 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][220/312]	eta 0:00:56 lr 0.000386	time 0.7836 (0.6161)	model_time 0.7833 (0.6082)	loss 2.8663 (2.9581)	grad_norm 2.4003 (2.6695/1.0921)	mem 24308MB
[2025-01-19 03:06:29 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][230/312]	eta 0:00:50 lr 0.000385	time 0.6215 (0.6154)	model_time 0.6211 (0.6079)	loss 3.0091 (2.9564)	grad_norm 3.2454 (2.6766/1.0908)	mem 24308MB
[2025-01-19 03:06:35 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][240/312]	eta 0:00:44 lr 0.000385	time 0.5881 (0.6145)	model_time 0.5879 (0.6073)	loss 2.7374 (2.9597)	grad_norm 3.8527 (2.6951/1.1228)	mem 24308MB
[2025-01-19 03:06:41 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][250/312]	eta 0:00:38 lr 0.000385	time 0.5790 (0.6138)	model_time 0.5789 (0.6068)	loss 2.7424 (2.9542)	grad_norm 3.5052 (2.7342/1.1892)	mem 24308MB
[2025-01-19 03:06:47 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][260/312]	eta 0:00:31 lr 0.000384	time 0.5843 (0.6134)	model_time 0.5841 (0.6067)	loss 3.2100 (2.9578)	grad_norm 1.9172 (2.7813/1.2701)	mem 24308MB
[2025-01-19 03:06:53 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][270/312]	eta 0:00:25 lr 0.000384	time 0.5813 (0.6131)	model_time 0.5809 (0.6066)	loss 2.8735 (2.9553)	grad_norm 1.8399 (2.7571/1.2562)	mem 24308MB
[2025-01-19 03:06:59 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][280/312]	eta 0:00:19 lr 0.000384	time 0.6537 (0.6137)	model_time 0.6533 (0.6074)	loss 3.0249 (2.9536)	grad_norm 0.8441 (2.7353/1.2534)	mem 24308MB
[2025-01-19 03:07:05 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][290/312]	eta 0:00:13 lr 0.000383	time 0.5780 (0.6138)	model_time 0.5776 (0.6077)	loss 2.7208 (2.9498)	grad_norm 1.8712 (2.7014/1.2459)	mem 24308MB
[2025-01-19 03:07:11 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][300/312]	eta 0:00:07 lr 0.000383	time 0.5688 (0.6133)	model_time 0.5686 (0.6074)	loss 1.9083 (2.9495)	grad_norm 2.2417 (2.6746/1.2381)	mem 24308MB
[2025-01-19 03:07:17 internimage_s_1k_224] (main.py 510): INFO Train: [242/300][310/312]	eta 0:00:01 lr 0.000382	time 0.5694 (0.6132)	model_time 0.5693 (0.6075)	loss 3.0738 (2.9428)	grad_norm 3.9095 (2.6682/1.2423)	mem 24308MB
[2025-01-19 03:07:18 internimage_s_1k_224] (main.py 519): INFO EPOCH 242 training takes 0:03:11
[2025-01-19 03:07:18 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_242.pth saving......
[2025-01-19 03:07:20 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_242.pth saved !!!
[2025-01-19 03:07:28 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.088 (8.088)	Loss 0.7261 (0.7261)	Acc@1 85.645 (85.645)	Acc@5 97.534 (97.534)	Mem 24308MB
[2025-01-19 03:07:31 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.063)	Loss 0.9296 (0.8128)	Acc@1 79.419 (83.323)	Acc@5 95.972 (96.635)	Mem 24308MB
[2025-01-19 03:07:32 internimage_s_1k_224] (main.py 575): INFO [Epoch:242] * Acc@1 83.199 Acc@5 96.653
[2025-01-19 03:07:32 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.2%
[2025-01-19 03:07:32 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.27%
[2025-01-19 03:07:41 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.293 (9.293)	Loss 0.7019 (0.7019)	Acc@1 85.449 (85.449)	Acc@5 97.803 (97.803)	Mem 24308MB
[2025-01-19 03:07:45 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.237)	Loss 0.9009 (0.7807)	Acc@1 79.102 (83.303)	Acc@5 95.874 (96.653)	Mem 24308MB
[2025-01-19 03:07:45 internimage_s_1k_224] (main.py 575): INFO [Epoch:242] * Acc@1 83.203 Acc@5 96.679
[2025-01-19 03:07:45 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.2%
[2025-01-19 03:07:45 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:07:47 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:07:47 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.20%
[2025-01-19 03:07:50 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][0/312]	eta 0:11:12 lr 0.000382	time 2.1564 (2.1564)	model_time 0.6168 (0.6168)	loss 2.0221 (2.0221)	grad_norm 2.1517 (2.1517/0.0000)	mem 24308MB
[2025-01-19 03:07:56 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][10/312]	eta 0:03:41 lr 0.000382	time 0.5826 (0.7338)	model_time 0.5824 (0.5935)	loss 3.0760 (2.8560)	grad_norm 2.1765 (3.2604/1.4768)	mem 24308MB
[2025-01-19 03:08:02 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][20/312]	eta 0:03:16 lr 0.000382	time 0.5885 (0.6714)	model_time 0.5883 (0.5977)	loss 3.3662 (2.8976)	grad_norm 1.5822 (3.1908/1.2977)	mem 24308MB
[2025-01-19 03:08:08 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][30/312]	eta 0:03:04 lr 0.000381	time 0.5740 (0.6554)	model_time 0.5736 (0.6054)	loss 2.5864 (2.8446)	grad_norm 4.1921 (2.9566/1.1901)	mem 24308MB
[2025-01-19 03:08:14 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][40/312]	eta 0:02:54 lr 0.000381	time 0.5707 (0.6416)	model_time 0.5705 (0.6037)	loss 3.0776 (2.8814)	grad_norm 1.9627 (2.7543/1.1226)	mem 24308MB
[2025-01-19 03:08:20 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][50/312]	eta 0:02:45 lr 0.000381	time 0.5881 (0.6319)	model_time 0.5880 (0.6013)	loss 3.2457 (2.8854)	grad_norm 2.1314 (2.6007/1.0711)	mem 24308MB
[2025-01-19 03:08:26 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][60/312]	eta 0:02:38 lr 0.000380	time 0.6966 (0.6273)	model_time 0.6961 (0.6017)	loss 2.8792 (2.8846)	grad_norm 1.5318 (2.5789/1.0360)	mem 24308MB
[2025-01-19 03:08:32 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][70/312]	eta 0:02:30 lr 0.000380	time 0.5814 (0.6239)	model_time 0.5813 (0.6018)	loss 1.8831 (2.8519)	grad_norm 2.1316 (2.6633/1.0368)	mem 24308MB
[2025-01-19 03:08:38 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][80/312]	eta 0:02:24 lr 0.000379	time 0.6492 (0.6220)	model_time 0.6491 (0.6026)	loss 2.8377 (2.8575)	grad_norm 2.1433 (2.6188/1.0427)	mem 24308MB
[2025-01-19 03:08:44 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][90/312]	eta 0:02:18 lr 0.000379	time 0.6589 (0.6247)	model_time 0.6587 (0.6074)	loss 3.0588 (2.8604)	grad_norm 3.5467 (2.7840/1.2592)	mem 24308MB
[2025-01-19 03:08:50 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][100/312]	eta 0:02:12 lr 0.000379	time 0.6218 (0.6231)	model_time 0.6216 (0.6075)	loss 3.0663 (2.8602)	grad_norm 6.0556 (2.8975/1.3052)	mem 24308MB
[2025-01-19 03:08:57 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][110/312]	eta 0:02:05 lr 0.000378	time 0.6715 (0.6233)	model_time 0.6710 (0.6091)	loss 2.1744 (2.8516)	grad_norm 3.3703 (2.9047/1.3011)	mem 24308MB
[2025-01-19 03:09:03 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][120/312]	eta 0:02:00 lr 0.000378	time 0.5811 (0.6252)	model_time 0.5809 (0.6121)	loss 2.9759 (2.8431)	grad_norm 3.1189 (2.8907/1.2598)	mem 24308MB
[2025-01-19 03:09:09 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][130/312]	eta 0:01:53 lr 0.000378	time 0.5707 (0.6223)	model_time 0.5705 (0.6102)	loss 2.6613 (2.8469)	grad_norm 3.1566 (2.9052/1.2538)	mem 24308MB
[2025-01-19 03:09:15 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][140/312]	eta 0:01:46 lr 0.000377	time 0.6022 (0.6200)	model_time 0.5866 (0.6086)	loss 2.5157 (2.8513)	grad_norm 2.8221 (2.9308/1.2516)	mem 24308MB
[2025-01-19 03:09:21 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][150/312]	eta 0:01:40 lr 0.000377	time 0.5895 (0.6205)	model_time 0.5893 (0.6098)	loss 2.3470 (2.8381)	grad_norm 2.5626 (2.8722/1.2419)	mem 24308MB
[2025-01-19 03:09:27 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][160/312]	eta 0:01:34 lr 0.000376	time 0.5825 (0.6195)	model_time 0.5821 (0.6094)	loss 2.9411 (2.8422)	grad_norm 5.6400 (2.8190/1.2585)	mem 24308MB
[2025-01-19 03:09:33 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][170/312]	eta 0:01:27 lr 0.000376	time 0.5829 (0.6175)	model_time 0.5824 (0.6081)	loss 2.9372 (2.8346)	grad_norm 1.7977 (2.8100/1.2592)	mem 24308MB
[2025-01-19 03:09:39 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][180/312]	eta 0:01:21 lr 0.000376	time 0.6185 (0.6166)	model_time 0.6184 (0.6076)	loss 2.6748 (2.8278)	grad_norm 3.1277 (2.7853/1.2351)	mem 24308MB
[2025-01-19 03:09:45 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][190/312]	eta 0:01:15 lr 0.000375	time 0.6656 (0.6159)	model_time 0.6654 (0.6074)	loss 2.0237 (2.8238)	grad_norm 1.3501 (2.7520/1.2155)	mem 24308MB
[2025-01-19 03:09:51 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][200/312]	eta 0:01:08 lr 0.000375	time 0.6639 (0.6156)	model_time 0.6635 (0.6074)	loss 2.0912 (2.8209)	grad_norm 1.8716 (2.7061/1.2081)	mem 24308MB
[2025-01-19 03:09:58 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][210/312]	eta 0:01:02 lr 0.000375	time 0.6670 (0.6163)	model_time 0.6669 (0.6085)	loss 3.1702 (2.8209)	grad_norm 3.2101 (2.7118/1.2076)	mem 24308MB
[2025-01-19 03:10:04 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][220/312]	eta 0:00:56 lr 0.000374	time 0.5848 (0.6165)	model_time 0.5844 (0.6090)	loss 3.4317 (2.8244)	grad_norm 1.3715 (2.7121/1.1946)	mem 24308MB
[2025-01-19 03:10:10 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][230/312]	eta 0:00:50 lr 0.000374	time 0.6749 (0.6169)	model_time 0.6745 (0.6098)	loss 2.6335 (2.8222)	grad_norm 6.0041 (2.7513/1.2159)	mem 24308MB
[2025-01-19 03:10:16 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][240/312]	eta 0:00:44 lr 0.000373	time 0.5726 (0.6172)	model_time 0.5721 (0.6103)	loss 2.6806 (2.8178)	grad_norm 2.3777 (2.7723/1.2329)	mem 24308MB
[2025-01-19 03:10:22 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][250/312]	eta 0:00:38 lr 0.000373	time 0.5768 (0.6159)	model_time 0.5763 (0.6093)	loss 2.8415 (2.8166)	grad_norm 1.6001 (2.7768/1.2375)	mem 24308MB
[2025-01-19 03:10:28 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][260/312]	eta 0:00:31 lr 0.000373	time 0.5907 (0.6148)	model_time 0.5903 (0.6084)	loss 2.8356 (2.8260)	grad_norm 1.3671 (2.7927/1.2491)	mem 24308MB
[2025-01-19 03:10:34 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][270/312]	eta 0:00:25 lr 0.000372	time 0.5929 (0.6143)	model_time 0.5927 (0.6082)	loss 2.9781 (2.8346)	grad_norm 1.8105 (2.7620/1.2437)	mem 24308MB
[2025-01-19 03:10:40 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][280/312]	eta 0:00:19 lr 0.000372	time 0.5974 (0.6139)	model_time 0.5970 (0.6079)	loss 3.0732 (2.8377)	grad_norm 7.5322 (2.7812/1.2652)	mem 24308MB
[2025-01-19 03:10:46 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][290/312]	eta 0:00:13 lr 0.000372	time 0.5742 (0.6129)	model_time 0.5740 (0.6072)	loss 2.9409 (2.8412)	grad_norm 2.2503 (2.8226/1.3033)	mem 24308MB
[2025-01-19 03:10:52 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][300/312]	eta 0:00:07 lr 0.000371	time 0.5679 (0.6120)	model_time 0.5678 (0.6065)	loss 3.5797 (2.8476)	grad_norm 4.3861 (2.8611/1.3287)	mem 24308MB
[2025-01-19 03:10:58 internimage_s_1k_224] (main.py 510): INFO Train: [243/300][310/312]	eta 0:00:01 lr 0.000371	time 0.5690 (0.6111)	model_time 0.5689 (0.6057)	loss 3.1864 (2.8547)	grad_norm 2.3036 (2.8334/1.3044)	mem 24308MB
[2025-01-19 03:10:58 internimage_s_1k_224] (main.py 519): INFO EPOCH 243 training takes 0:03:10
[2025-01-19 03:10:58 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_243.pth saving......
[2025-01-19 03:11:00 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_243.pth saved !!!
[2025-01-19 03:11:08 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.721 (7.721)	Loss 0.7192 (0.7192)	Acc@1 86.035 (86.035)	Acc@5 97.583 (97.583)	Mem 24308MB
[2025-01-19 03:11:11 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.026)	Loss 0.9219 (0.8158)	Acc@1 79.736 (83.239)	Acc@5 95.776 (96.624)	Mem 24308MB
[2025-01-19 03:11:12 internimage_s_1k_224] (main.py 575): INFO [Epoch:243] * Acc@1 83.165 Acc@5 96.659
[2025-01-19 03:11:12 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.2%
[2025-01-19 03:11:12 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.27%
[2025-01-19 03:11:20 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.900 (8.900)	Loss 0.7018 (0.7018)	Acc@1 85.425 (85.425)	Acc@5 97.803 (97.803)	Mem 24308MB
[2025-01-19 03:11:25 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.221)	Loss 0.8998 (0.7802)	Acc@1 79.126 (83.296)	Acc@5 95.898 (96.662)	Mem 24308MB
[2025-01-19 03:11:25 internimage_s_1k_224] (main.py 575): INFO [Epoch:243] * Acc@1 83.205 Acc@5 96.685
[2025-01-19 03:11:25 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.2%
[2025-01-19 03:11:25 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:11:27 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:11:27 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.21%
[2025-01-19 03:11:30 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][0/312]	eta 0:11:36 lr 0.000371	time 2.2328 (2.2328)	model_time 0.5833 (0.5833)	loss 3.3455 (3.3455)	grad_norm 1.5844 (1.5844/0.0000)	mem 24308MB
[2025-01-19 03:11:36 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][10/312]	eta 0:03:50 lr 0.000370	time 0.5663 (0.7618)	model_time 0.5662 (0.6115)	loss 2.8422 (2.9895)	grad_norm 2.8298 (2.1132/0.5099)	mem 24308MB
[2025-01-19 03:11:42 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][20/312]	eta 0:03:21 lr 0.000370	time 0.5904 (0.6887)	model_time 0.5903 (0.6098)	loss 2.9610 (2.9460)	grad_norm 3.1630 (2.3323/0.6327)	mem 24308MB
[2025-01-19 03:11:48 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][30/312]	eta 0:03:08 lr 0.000370	time 0.5789 (0.6692)	model_time 0.5785 (0.6155)	loss 2.3603 (2.8393)	grad_norm 4.9153 (2.6615/0.9104)	mem 24308MB
[2025-01-19 03:11:54 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][40/312]	eta 0:02:59 lr 0.000369	time 0.6588 (0.6584)	model_time 0.6587 (0.6178)	loss 3.0973 (2.8524)	grad_norm 1.8111 (2.5671/0.9136)	mem 24308MB
[2025-01-19 03:12:00 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][50/312]	eta 0:02:50 lr 0.000369	time 0.5834 (0.6498)	model_time 0.5832 (0.6171)	loss 3.4909 (2.8572)	grad_norm 2.0476 (2.5730/0.8948)	mem 24308MB
[2025-01-19 03:12:06 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][60/312]	eta 0:02:41 lr 0.000369	time 0.5779 (0.6391)	model_time 0.5774 (0.6118)	loss 3.1476 (2.8646)	grad_norm 2.1270 (2.5298/0.8577)	mem 24308MB
[2025-01-19 03:12:12 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][70/312]	eta 0:02:33 lr 0.000368	time 0.5851 (0.6328)	model_time 0.5850 (0.6092)	loss 3.0804 (2.8716)	grad_norm 4.0367 (2.6913/1.1170)	mem 24308MB
[2025-01-19 03:12:18 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][80/312]	eta 0:02:26 lr 0.000368	time 0.5749 (0.6314)	model_time 0.5744 (0.6107)	loss 2.2956 (2.8511)	grad_norm 1.6598 (2.6511/1.1056)	mem 24308MB
[2025-01-19 03:12:24 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][90/312]	eta 0:02:19 lr 0.000368	time 0.5898 (0.6277)	model_time 0.5896 (0.6093)	loss 3.0663 (2.8503)	grad_norm 3.0623 (2.6126/1.0651)	mem 24308MB
[2025-01-19 03:12:30 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][100/312]	eta 0:02:12 lr 0.000367	time 0.5723 (0.6242)	model_time 0.5718 (0.6075)	loss 3.5982 (2.8674)	grad_norm 1.2612 (2.5388/1.0563)	mem 24308MB
[2025-01-19 03:12:36 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][110/312]	eta 0:02:05 lr 0.000367	time 0.6215 (0.6220)	model_time 0.6211 (0.6068)	loss 3.1331 (2.8693)	grad_norm 2.1487 (2.5161/1.0454)	mem 24308MB
[2025-01-19 03:12:42 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][120/312]	eta 0:01:59 lr 0.000366	time 0.6694 (0.6208)	model_time 0.6692 (0.6068)	loss 3.7822 (2.8605)	grad_norm 2.6905 (2.5554/1.0302)	mem 24308MB
[2025-01-19 03:12:49 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][130/312]	eta 0:01:53 lr 0.000366	time 0.5695 (0.6221)	model_time 0.5691 (0.6091)	loss 2.2853 (2.8683)	grad_norm 1.8176 (2.5739/1.0288)	mem 24308MB
[2025-01-19 03:12:55 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][140/312]	eta 0:01:46 lr 0.000366	time 0.5727 (0.6212)	model_time 0.5725 (0.6091)	loss 3.2304 (2.8713)	grad_norm 2.7297 (2.5562/1.0033)	mem 24308MB
[2025-01-19 03:13:01 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][150/312]	eta 0:01:40 lr 0.000365	time 0.6194 (0.6215)	model_time 0.6192 (0.6102)	loss 3.3576 (2.8743)	grad_norm 2.8440 (2.5215/0.9931)	mem 24308MB
[2025-01-19 03:13:07 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][160/312]	eta 0:01:34 lr 0.000365	time 0.7005 (0.6208)	model_time 0.7003 (0.6102)	loss 3.0378 (2.8725)	grad_norm 2.9418 (2.4819/0.9830)	mem 24308MB
[2025-01-19 03:13:14 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][170/312]	eta 0:01:28 lr 0.000365	time 0.5638 (0.6213)	model_time 0.5633 (0.6113)	loss 2.5849 (2.8672)	grad_norm 1.4244 (2.5204/1.0059)	mem 24308MB
[2025-01-19 03:13:20 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][180/312]	eta 0:01:21 lr 0.000364	time 0.5881 (0.6198)	model_time 0.5879 (0.6103)	loss 3.2728 (2.8683)	grad_norm 4.4639 (2.5639/1.0549)	mem 24308MB
[2025-01-19 03:13:25 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][190/312]	eta 0:01:15 lr 0.000364	time 0.5705 (0.6183)	model_time 0.5700 (0.6093)	loss 2.1125 (2.8639)	grad_norm 3.5881 (2.6302/1.0954)	mem 24308MB
[2025-01-19 03:13:32 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][200/312]	eta 0:01:09 lr 0.000363	time 0.5688 (0.6178)	model_time 0.5683 (0.6092)	loss 3.3785 (2.8634)	grad_norm 3.0331 (2.6030/1.0821)	mem 24308MB
[2025-01-19 03:13:38 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][210/312]	eta 0:01:02 lr 0.000363	time 0.5963 (0.6169)	model_time 0.5958 (0.6087)	loss 3.1376 (2.8622)	grad_norm 1.9512 (2.5726/1.0752)	mem 24308MB
[2025-01-19 03:13:43 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][220/312]	eta 0:00:56 lr 0.000363	time 0.5914 (0.6156)	model_time 0.5913 (0.6078)	loss 2.9172 (2.8653)	grad_norm 2.1484 (2.5506/1.0675)	mem 24308MB
[2025-01-19 03:13:49 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][230/312]	eta 0:00:50 lr 0.000362	time 0.5654 (0.6148)	model_time 0.5651 (0.6073)	loss 2.2645 (2.8607)	grad_norm 2.5861 (2.5663/1.1051)	mem 24308MB
[2025-01-19 03:13:55 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][240/312]	eta 0:00:44 lr 0.000362	time 0.5843 (0.6140)	model_time 0.5838 (0.6068)	loss 3.3319 (2.8588)	grad_norm 2.7884 (2.5649/1.0960)	mem 24308MB
[2025-01-19 03:14:01 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][250/312]	eta 0:00:38 lr 0.000362	time 0.6054 (0.6141)	model_time 0.6050 (0.6072)	loss 2.8363 (2.8585)	grad_norm 1.0735 (2.5531/1.0981)	mem 24308MB
[2025-01-19 03:14:08 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][260/312]	eta 0:00:31 lr 0.000361	time 0.5726 (0.6141)	model_time 0.5725 (0.6073)	loss 3.5285 (2.8514)	grad_norm 3.2650 (2.5451/1.0954)	mem 24308MB
[2025-01-19 03:14:14 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][270/312]	eta 0:00:25 lr 0.000361	time 0.5865 (0.6150)	model_time 0.5863 (0.6085)	loss 3.3133 (2.8585)	grad_norm 1.9117 (2.5278/1.0867)	mem 24308MB
[2025-01-19 03:14:20 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][280/312]	eta 0:00:19 lr 0.000361	time 0.5814 (0.6145)	model_time 0.5809 (0.6082)	loss 3.0608 (2.8674)	grad_norm 1.7316 (2.4978/1.0839)	mem 24308MB
[2025-01-19 03:14:26 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][290/312]	eta 0:00:13 lr 0.000360	time 0.5796 (0.6147)	model_time 0.5795 (0.6086)	loss 2.5807 (2.8641)	grad_norm 1.4692 (2.4880/1.0831)	mem 24308MB
[2025-01-19 03:14:32 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][300/312]	eta 0:00:07 lr 0.000360	time 0.5696 (0.6141)	model_time 0.5695 (0.6082)	loss 2.8567 (2.8640)	grad_norm 1.5293 (2.4734/1.0754)	mem 24308MB
[2025-01-19 03:14:38 internimage_s_1k_224] (main.py 510): INFO Train: [244/300][310/312]	eta 0:00:01 lr 0.000360	time 0.5741 (0.6127)	model_time 0.5740 (0.6070)	loss 2.9740 (2.8658)	grad_norm 2.1071 (2.4993/1.1004)	mem 24308MB
[2025-01-19 03:14:38 internimage_s_1k_224] (main.py 519): INFO EPOCH 244 training takes 0:03:11
[2025-01-19 03:14:38 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_244.pth saving......
[2025-01-19 03:14:40 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_244.pth saved !!!
[2025-01-19 03:14:48 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.928 (7.928)	Loss 0.7073 (0.7073)	Acc@1 85.620 (85.620)	Acc@5 97.705 (97.705)	Mem 24308MB
[2025-01-19 03:14:52 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.043)	Loss 0.8967 (0.7897)	Acc@1 79.565 (83.405)	Acc@5 95.947 (96.662)	Mem 24308MB
[2025-01-19 03:14:52 internimage_s_1k_224] (main.py 575): INFO [Epoch:244] * Acc@1 83.279 Acc@5 96.649
[2025-01-19 03:14:52 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.3%
[2025-01-19 03:14:52 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 03:14:54 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 03:14:54 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.28%
[2025-01-19 03:15:02 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.768 (7.768)	Loss 0.7015 (0.7015)	Acc@1 85.400 (85.400)	Acc@5 97.803 (97.803)	Mem 24308MB
[2025-01-19 03:15:05 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.030)	Loss 0.8987 (0.7797)	Acc@1 79.102 (83.323)	Acc@5 95.923 (96.673)	Mem 24308MB
[2025-01-19 03:15:05 internimage_s_1k_224] (main.py 575): INFO [Epoch:244] * Acc@1 83.231 Acc@5 96.699
[2025-01-19 03:15:05 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.2%
[2025-01-19 03:15:05 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:15:08 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:15:08 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.23%
[2025-01-19 03:15:10 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][0/312]	eta 0:10:11 lr 0.000359	time 1.9613 (1.9613)	model_time 0.5999 (0.5999)	loss 2.6541 (2.6541)	grad_norm 1.5150 (1.5150/0.0000)	mem 24308MB
[2025-01-19 03:15:16 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][10/312]	eta 0:03:43 lr 0.000359	time 0.5793 (0.7398)	model_time 0.5790 (0.6158)	loss 3.0504 (3.0163)	grad_norm 3.4187 (2.5673/0.8475)	mem 24308MB
[2025-01-19 03:15:22 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][20/312]	eta 0:03:16 lr 0.000359	time 0.5869 (0.6737)	model_time 0.5865 (0.6085)	loss 2.6115 (2.8664)	grad_norm 1.7741 (2.4176/0.7333)	mem 24308MB
[2025-01-19 03:15:28 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][30/312]	eta 0:03:01 lr 0.000358	time 0.5829 (0.6447)	model_time 0.5827 (0.6005)	loss 3.4367 (2.8115)	grad_norm 2.8117 (2.4753/0.8572)	mem 24308MB
[2025-01-19 03:15:34 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][40/312]	eta 0:02:51 lr 0.000358	time 0.5768 (0.6321)	model_time 0.5766 (0.5985)	loss 1.9591 (2.8248)	grad_norm 4.1740 (2.4946/0.8694)	mem 24308MB
[2025-01-19 03:15:39 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][50/312]	eta 0:02:43 lr 0.000358	time 0.5794 (0.6250)	model_time 0.5792 (0.5980)	loss 1.8840 (2.8377)	grad_norm 1.6681 (2.4692/0.8124)	mem 24308MB
[2025-01-19 03:15:46 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][60/312]	eta 0:02:37 lr 0.000357	time 0.6573 (0.6250)	model_time 0.6571 (0.6023)	loss 3.6334 (2.8492)	grad_norm 2.9448 (2.4448/0.7590)	mem 24308MB
[2025-01-19 03:15:52 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][70/312]	eta 0:02:30 lr 0.000357	time 0.6781 (0.6224)	model_time 0.6779 (0.6029)	loss 2.8788 (2.8670)	grad_norm 1.4347 (2.4386/0.7729)	mem 24308MB
[2025-01-19 03:15:58 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][80/312]	eta 0:02:24 lr 0.000357	time 0.5924 (0.6233)	model_time 0.5919 (0.6062)	loss 2.5798 (2.8554)	grad_norm 2.9217 (2.4334/0.7959)	mem 24308MB
[2025-01-19 03:16:04 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][90/312]	eta 0:02:17 lr 0.000356	time 0.5756 (0.6210)	model_time 0.5754 (0.6057)	loss 1.8854 (2.8345)	grad_norm 2.8016 (2.4867/0.9602)	mem 24308MB
[2025-01-19 03:16:11 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][100/312]	eta 0:02:12 lr 0.000356	time 0.5818 (0.6264)	model_time 0.5816 (0.6126)	loss 3.6565 (2.8920)	grad_norm 4.2922 (2.4982/0.9461)	mem 24308MB
[2025-01-19 03:16:17 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][110/312]	eta 0:02:06 lr 0.000355	time 0.6067 (0.6245)	model_time 0.6065 (0.6119)	loss 3.0635 (2.8903)	grad_norm 1.9061 (2.4527/0.9264)	mem 24308MB
[2025-01-19 03:16:23 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][120/312]	eta 0:01:59 lr 0.000355	time 0.5849 (0.6218)	model_time 0.5848 (0.6102)	loss 2.9224 (2.8807)	grad_norm 3.6998 (2.4488/0.9396)	mem 24308MB
[2025-01-19 03:16:29 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][130/312]	eta 0:01:53 lr 0.000355	time 0.6521 (0.6210)	model_time 0.6519 (0.6103)	loss 2.8470 (2.8716)	grad_norm 2.6087 (2.4641/0.9302)	mem 24308MB
[2025-01-19 03:16:35 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][140/312]	eta 0:01:46 lr 0.000354	time 0.6899 (0.6200)	model_time 0.6897 (0.6100)	loss 3.2549 (2.8823)	grad_norm 2.3970 (2.4462/0.9151)	mem 24308MB
[2025-01-19 03:16:41 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][150/312]	eta 0:01:40 lr 0.000354	time 0.5905 (0.6177)	model_time 0.5901 (0.6083)	loss 3.3523 (2.8880)	grad_norm 2.9572 (2.4599/0.9181)	mem 24308MB
[2025-01-19 03:16:47 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][160/312]	eta 0:01:33 lr 0.000354	time 0.5768 (0.6164)	model_time 0.5763 (0.6076)	loss 2.3696 (2.8835)	grad_norm 3.8475 (2.4481/0.9235)	mem 24308MB
[2025-01-19 03:16:53 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][170/312]	eta 0:01:27 lr 0.000353	time 0.5769 (0.6151)	model_time 0.5768 (0.6068)	loss 2.1699 (2.8789)	grad_norm 2.3910 (2.4452/0.9216)	mem 24308MB
[2025-01-19 03:16:59 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][180/312]	eta 0:01:21 lr 0.000353	time 0.6624 (0.6156)	model_time 0.6622 (0.6077)	loss 3.2741 (2.8833)	grad_norm 2.0655 (2.4272/0.9081)	mem 24308MB
[2025-01-19 03:17:05 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][190/312]	eta 0:01:15 lr 0.000353	time 0.6628 (0.6149)	model_time 0.6624 (0.6074)	loss 3.5398 (2.8844)	grad_norm 2.7914 (2.5232/1.1034)	mem 24308MB
[2025-01-19 03:17:11 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][200/312]	eta 0:01:08 lr 0.000352	time 0.6676 (0.6160)	model_time 0.6671 (0.6088)	loss 2.0675 (2.8820)	grad_norm 1.7364 (2.5742/1.1846)	mem 24308MB
[2025-01-19 03:17:17 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][210/312]	eta 0:01:02 lr 0.000352	time 0.5831 (0.6149)	model_time 0.5829 (0.6081)	loss 1.8550 (2.8698)	grad_norm 2.0783 (2.5867/1.1962)	mem 24308MB
[2025-01-19 03:17:23 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][220/312]	eta 0:00:56 lr 0.000352	time 0.5895 (0.6150)	model_time 0.5893 (0.6084)	loss 3.1488 (2.8699)	grad_norm 2.3834 (2.5750/1.1847)	mem 24308MB
[2025-01-19 03:17:30 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][230/312]	eta 0:00:50 lr 0.000351	time 0.5863 (0.6153)	model_time 0.5858 (0.6091)	loss 3.1590 (2.8674)	grad_norm 2.1099 (2.5718/1.1740)	mem 24308MB
[2025-01-19 03:17:36 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][240/312]	eta 0:00:44 lr 0.000351	time 0.5921 (0.6144)	model_time 0.5917 (0.6083)	loss 3.1099 (2.8771)	grad_norm 1.5643 (2.5759/1.1579)	mem 24308MB
[2025-01-19 03:17:42 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][250/312]	eta 0:00:38 lr 0.000350	time 0.5723 (0.6140)	model_time 0.5721 (0.6082)	loss 3.1219 (2.8851)	grad_norm 2.5642 (2.5835/1.1415)	mem 24308MB
[2025-01-19 03:17:48 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][260/312]	eta 0:00:31 lr 0.000350	time 0.8795 (0.6147)	model_time 0.8790 (0.6091)	loss 3.2247 (2.8802)	grad_norm 1.8214 (2.5756/1.1290)	mem 24308MB
[2025-01-19 03:17:54 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][270/312]	eta 0:00:25 lr 0.000350	time 0.5837 (0.6137)	model_time 0.5835 (0.6083)	loss 2.0286 (2.8764)	grad_norm 3.9305 (2.5893/1.1361)	mem 24308MB
[2025-01-19 03:18:00 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][280/312]	eta 0:00:19 lr 0.000349	time 0.5720 (0.6130)	model_time 0.5715 (0.6078)	loss 2.7956 (2.8771)	grad_norm 4.6389 (2.6267/1.1467)	mem 24308MB
[2025-01-19 03:18:06 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][290/312]	eta 0:00:13 lr 0.000349	time 0.5712 (0.6126)	model_time 0.5708 (0.6075)	loss 3.1582 (2.8756)	grad_norm 3.4582 (2.6304/1.1611)	mem 24308MB
[2025-01-19 03:18:12 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][300/312]	eta 0:00:07 lr 0.000349	time 0.5680 (0.6124)	model_time 0.5679 (0.6075)	loss 2.9702 (2.8689)	grad_norm 2.5326 (2.6217/1.1520)	mem 24308MB
[2025-01-19 03:18:18 internimage_s_1k_224] (main.py 510): INFO Train: [245/300][310/312]	eta 0:00:01 lr 0.000348	time 0.6509 (0.6120)	model_time 0.6509 (0.6072)	loss 3.2398 (2.8672)	grad_norm 3.1925 (2.6089/1.1515)	mem 24308MB
[2025-01-19 03:18:18 internimage_s_1k_224] (main.py 519): INFO EPOCH 245 training takes 0:03:10
[2025-01-19 03:18:19 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_245.pth saving......
[2025-01-19 03:18:20 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_245.pth saved !!!
[2025-01-19 03:18:28 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.821 (7.821)	Loss 0.7185 (0.7185)	Acc@1 85.498 (85.498)	Acc@5 97.656 (97.656)	Mem 24308MB
[2025-01-19 03:18:32 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.033)	Loss 0.9188 (0.8033)	Acc@1 79.272 (83.307)	Acc@5 95.679 (96.662)	Mem 24308MB
[2025-01-19 03:18:32 internimage_s_1k_224] (main.py 575): INFO [Epoch:245] * Acc@1 83.179 Acc@5 96.675
[2025-01-19 03:18:32 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.2%
[2025-01-19 03:18:32 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.28%
[2025-01-19 03:18:41 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.076 (9.076)	Loss 0.7014 (0.7014)	Acc@1 85.425 (85.425)	Acc@5 97.803 (97.803)	Mem 24308MB
[2025-01-19 03:18:45 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (1.211)	Loss 0.8976 (0.7792)	Acc@1 79.175 (83.345)	Acc@5 95.972 (96.675)	Mem 24308MB
[2025-01-19 03:18:45 internimage_s_1k_224] (main.py 575): INFO [Epoch:245] * Acc@1 83.251 Acc@5 96.699
[2025-01-19 03:18:45 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.3%
[2025-01-19 03:18:45 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:18:48 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:18:48 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.25%
[2025-01-19 03:18:50 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][0/312]	eta 0:11:11 lr 0.000348	time 2.1521 (2.1521)	model_time 0.5869 (0.5869)	loss 2.9629 (2.9629)	grad_norm 1.4311 (1.4311/0.0000)	mem 24308MB
[2025-01-19 03:18:56 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][10/312]	eta 0:03:52 lr 0.000348	time 0.5848 (0.7713)	model_time 0.5846 (0.6287)	loss 2.1866 (2.8259)	grad_norm 2.5448 (3.6236/2.4211)	mem 24308MB
[2025-01-19 03:19:02 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][20/312]	eta 0:03:19 lr 0.000348	time 0.5819 (0.6830)	model_time 0.5814 (0.6081)	loss 3.4992 (2.9033)	grad_norm 1.4566 (3.4043/1.9331)	mem 24308MB
[2025-01-19 03:19:08 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][30/312]	eta 0:03:09 lr 0.000347	time 0.8499 (0.6710)	model_time 0.8497 (0.6202)	loss 2.3325 (2.8827)	grad_norm 2.6826 (3.3391/1.7110)	mem 24308MB
[2025-01-19 03:19:14 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][40/312]	eta 0:02:58 lr 0.000347	time 0.5759 (0.6544)	model_time 0.5754 (0.6159)	loss 3.2280 (2.8825)	grad_norm 1.6707 (3.0570/1.5929)	mem 24308MB
[2025-01-19 03:19:21 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][50/312]	eta 0:02:48 lr 0.000346	time 0.6733 (0.6441)	model_time 0.6728 (0.6130)	loss 3.3043 (2.8961)	grad_norm 3.9532 (3.0792/1.5039)	mem 24308MB
[2025-01-19 03:19:26 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][60/312]	eta 0:02:40 lr 0.000346	time 0.6061 (0.6364)	model_time 0.6059 (0.6103)	loss 3.4377 (2.9101)	grad_norm 2.1971 (3.0642/1.4385)	mem 24308MB
[2025-01-19 03:19:33 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][70/312]	eta 0:02:33 lr 0.000346	time 0.6788 (0.6341)	model_time 0.6783 (0.6117)	loss 3.4355 (2.9177)	grad_norm 1.4537 (2.9600/1.4266)	mem 24308MB
[2025-01-19 03:19:39 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][80/312]	eta 0:02:25 lr 0.000345	time 0.5890 (0.6282)	model_time 0.5888 (0.6085)	loss 2.0466 (2.9177)	grad_norm 1.3355 (2.8423/1.3869)	mem 24308MB
[2025-01-19 03:19:45 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][90/312]	eta 0:02:18 lr 0.000345	time 0.5757 (0.6249)	model_time 0.5755 (0.6073)	loss 3.2146 (2.9298)	grad_norm 4.6658 (2.7968/1.3487)	mem 24308MB
[2025-01-19 03:19:51 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][100/312]	eta 0:02:12 lr 0.000345	time 0.6918 (0.6234)	model_time 0.6916 (0.6076)	loss 2.6577 (2.9073)	grad_norm 3.7574 (2.7700/1.2997)	mem 24308MB
[2025-01-19 03:19:57 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][110/312]	eta 0:02:05 lr 0.000344	time 0.6734 (0.6216)	model_time 0.6732 (0.6071)	loss 3.1985 (2.9186)	grad_norm 2.0197 (2.7620/1.2510)	mem 24308MB
[2025-01-19 03:20:03 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][120/312]	eta 0:01:59 lr 0.000344	time 0.5815 (0.6202)	model_time 0.5813 (0.6069)	loss 2.6867 (2.9165)	grad_norm 2.9971 (2.7625/1.2197)	mem 24308MB
[2025-01-19 03:20:09 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][130/312]	eta 0:01:52 lr 0.000344	time 0.5718 (0.6204)	model_time 0.5716 (0.6080)	loss 2.9052 (2.9116)	grad_norm 4.1563 (2.8174/1.2264)	mem 24308MB
[2025-01-19 03:20:15 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][140/312]	eta 0:01:46 lr 0.000343	time 0.5966 (0.6187)	model_time 0.5961 (0.6072)	loss 2.6701 (2.9164)	grad_norm 1.6219 (2.8542/1.2416)	mem 24308MB
[2025-01-19 03:20:21 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][150/312]	eta 0:01:40 lr 0.000343	time 0.5932 (0.6176)	model_time 0.5927 (0.6069)	loss 2.2179 (2.9104)	grad_norm 2.3500 (2.8460/1.2290)	mem 24308MB
[2025-01-19 03:20:27 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][160/312]	eta 0:01:33 lr 0.000343	time 0.5812 (0.6175)	model_time 0.5810 (0.6074)	loss 2.1898 (2.9071)	grad_norm 4.1662 (2.8443/1.2242)	mem 24308MB
[2025-01-19 03:20:33 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][170/312]	eta 0:01:27 lr 0.000342	time 0.5934 (0.6158)	model_time 0.5932 (0.6062)	loss 2.9917 (2.9087)	grad_norm 3.2636 (2.8205/1.2021)	mem 24308MB
[2025-01-19 03:20:39 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][180/312]	eta 0:01:21 lr 0.000342	time 0.5707 (0.6150)	model_time 0.5706 (0.6060)	loss 3.5100 (2.9018)	grad_norm 3.0051 (2.8462/1.1895)	mem 24308MB
[2025-01-19 03:20:45 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][190/312]	eta 0:01:14 lr 0.000341	time 0.5829 (0.6140)	model_time 0.5827 (0.6054)	loss 3.0045 (2.9005)	grad_norm 3.7887 (2.8424/1.1834)	mem 24308MB
[2025-01-19 03:20:51 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][200/312]	eta 0:01:08 lr 0.000341	time 0.5816 (0.6143)	model_time 0.5811 (0.6062)	loss 3.5206 (2.8976)	grad_norm 1.7609 (2.8356/1.1664)	mem 24308MB
[2025-01-19 03:20:57 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][210/312]	eta 0:01:02 lr 0.000341	time 0.6761 (0.6135)	model_time 0.6759 (0.6057)	loss 2.5266 (2.8928)	grad_norm 2.1367 (2.8023/1.1553)	mem 24308MB
[2025-01-19 03:21:03 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][220/312]	eta 0:00:56 lr 0.000340	time 0.5925 (0.6130)	model_time 0.5923 (0.6056)	loss 3.2983 (2.8897)	grad_norm 3.2675 (2.8145/1.1462)	mem 24308MB
[2025-01-19 03:21:09 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][230/312]	eta 0:00:50 lr 0.000340	time 0.6544 (0.6127)	model_time 0.6540 (0.6056)	loss 3.1118 (2.8785)	grad_norm 2.1368 (2.8535/1.2346)	mem 24308MB
[2025-01-19 03:21:15 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][240/312]	eta 0:00:44 lr 0.000340	time 0.5799 (0.6132)	model_time 0.5795 (0.6063)	loss 2.2924 (2.8769)	grad_norm 1.7870 (2.8372/1.2301)	mem 24308MB
[2025-01-19 03:21:22 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][250/312]	eta 0:00:38 lr 0.000339	time 0.6610 (0.6132)	model_time 0.6607 (0.6066)	loss 2.9099 (2.8748)	grad_norm 2.9557 (2.8380/1.2286)	mem 24308MB
[2025-01-19 03:21:28 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][260/312]	eta 0:00:31 lr 0.000339	time 0.5708 (0.6129)	model_time 0.5704 (0.6065)	loss 3.5912 (2.8810)	grad_norm 3.1523 (2.8205/1.2190)	mem 24308MB
[2025-01-19 03:21:34 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][270/312]	eta 0:00:25 lr 0.000339	time 0.5787 (0.6127)	model_time 0.5786 (0.6065)	loss 3.1493 (2.8800)	grad_norm 3.8157 (2.8152/1.2120)	mem 24308MB
[2025-01-19 03:21:40 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][280/312]	eta 0:00:19 lr 0.000338	time 0.6037 (0.6130)	model_time 0.6033 (0.6071)	loss 3.1632 (2.8805)	grad_norm 2.7357 (2.8103/1.2008)	mem 24308MB
[2025-01-19 03:21:46 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][290/312]	eta 0:00:13 lr 0.000338	time 0.5880 (0.6121)	model_time 0.5876 (0.6064)	loss 2.7502 (2.8791)	grad_norm 2.6425 (2.8301/1.2103)	mem 24308MB
[2025-01-19 03:21:52 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][300/312]	eta 0:00:07 lr 0.000338	time 0.5655 (0.6117)	model_time 0.5654 (0.6061)	loss 2.9044 (2.8819)	grad_norm 2.8768 (2.8992/1.2786)	mem 24308MB
[2025-01-19 03:21:58 internimage_s_1k_224] (main.py 510): INFO Train: [246/300][310/312]	eta 0:00:01 lr 0.000337	time 0.5622 (0.6108)	model_time 0.5621 (0.6054)	loss 3.5926 (2.8804)	grad_norm 1.5291 (2.8616/1.2151)	mem 24308MB
[2025-01-19 03:21:58 internimage_s_1k_224] (main.py 519): INFO EPOCH 246 training takes 0:03:10
[2025-01-19 03:21:58 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_246.pth saving......
[2025-01-19 03:22:00 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_246.pth saved !!!
[2025-01-19 03:22:08 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.780 (7.780)	Loss 0.7146 (0.7146)	Acc@1 85.522 (85.522)	Acc@5 97.729 (97.729)	Mem 24308MB
[2025-01-19 03:22:12 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.071)	Loss 0.8961 (0.7883)	Acc@1 80.005 (83.503)	Acc@5 95.630 (96.711)	Mem 24308MB
[2025-01-19 03:22:12 internimage_s_1k_224] (main.py 575): INFO [Epoch:246] * Acc@1 83.355 Acc@5 96.717
[2025-01-19 03:22:12 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.4%
[2025-01-19 03:22:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 03:22:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 03:22:14 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.36%
[2025-01-19 03:22:30 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.143 (16.143)	Loss 0.7012 (0.7012)	Acc@1 85.400 (85.400)	Acc@5 97.803 (97.803)	Mem 24308MB
[2025-01-19 03:22:37 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (2.087)	Loss 0.8963 (0.7786)	Acc@1 79.224 (83.363)	Acc@5 95.996 (96.691)	Mem 24308MB
[2025-01-19 03:22:37 internimage_s_1k_224] (main.py 575): INFO [Epoch:246] * Acc@1 83.267 Acc@5 96.719
[2025-01-19 03:22:37 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.3%
[2025-01-19 03:22:37 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:22:39 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:22:39 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.27%
[2025-01-19 03:22:42 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][0/312]	eta 0:10:54 lr 0.000337	time 2.0993 (2.0993)	model_time 0.5927 (0.5927)	loss 3.1891 (3.1891)	grad_norm 3.5595 (3.5595/0.0000)	mem 24308MB
[2025-01-19 03:22:48 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][10/312]	eta 0:03:43 lr 0.000337	time 0.6111 (0.7394)	model_time 0.6109 (0.6022)	loss 3.1897 (2.9168)	grad_norm 3.0315 (2.7756/0.9538)	mem 24308MB
[2025-01-19 03:22:54 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][20/312]	eta 0:03:17 lr 0.000337	time 0.5773 (0.6753)	model_time 0.5769 (0.6032)	loss 2.8004 (2.9323)	grad_norm 2.4071 (2.6660/0.9454)	mem 24308MB
[2025-01-19 03:23:00 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][30/312]	eta 0:03:04 lr 0.000336	time 0.6595 (0.6533)	model_time 0.6591 (0.6043)	loss 2.8210 (2.9708)	grad_norm 1.5943 (2.6559/0.9817)	mem 24308MB
[2025-01-19 03:23:06 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][40/312]	eta 0:02:55 lr 0.000336	time 0.6443 (0.6439)	model_time 0.6456 (0.6068)	loss 2.6049 (2.9684)	grad_norm 6.1828 (2.7675/1.1016)	mem 24308MB
[2025-01-19 03:23:12 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][50/312]	eta 0:02:46 lr 0.000335	time 0.5747 (0.6373)	model_time 0.5745 (0.6074)	loss 2.9609 (2.9660)	grad_norm 2.2163 (2.7890/1.2406)	mem 24308MB
[2025-01-19 03:23:18 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][60/312]	eta 0:02:40 lr 0.000335	time 0.6764 (0.6355)	model_time 0.6762 (0.6104)	loss 2.8140 (2.9432)	grad_norm 4.6738 (2.7880/1.2170)	mem 24308MB
[2025-01-19 03:23:24 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][70/312]	eta 0:02:32 lr 0.000335	time 0.5646 (0.6299)	model_time 0.5645 (0.6083)	loss 2.8064 (2.8800)	grad_norm 2.9463 (2.7869/1.2031)	mem 24308MB
[2025-01-19 03:23:30 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][80/312]	eta 0:02:25 lr 0.000334	time 0.5807 (0.6277)	model_time 0.5805 (0.6087)	loss 3.5928 (2.8905)	grad_norm 3.4733 (2.7925/1.1876)	mem 24308MB
[2025-01-19 03:23:36 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][90/312]	eta 0:02:19 lr 0.000334	time 0.6776 (0.6268)	model_time 0.6771 (0.6098)	loss 2.9930 (2.9002)	grad_norm 2.7026 (2.7394/1.1572)	mem 24308MB
[2025-01-19 03:23:42 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][100/312]	eta 0:02:12 lr 0.000334	time 0.5850 (0.6227)	model_time 0.5848 (0.6074)	loss 2.6279 (2.9046)	grad_norm 5.6886 (2.7482/1.1763)	mem 24308MB
[2025-01-19 03:23:48 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][110/312]	eta 0:02:05 lr 0.000333	time 0.5787 (0.6209)	model_time 0.5783 (0.6069)	loss 3.0741 (2.9120)	grad_norm 5.1817 (2.9744/1.4810)	mem 24308MB
[2025-01-19 03:23:54 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][120/312]	eta 0:01:58 lr 0.000333	time 0.5884 (0.6189)	model_time 0.5880 (0.6061)	loss 2.9744 (2.9143)	grad_norm 1.1816 (2.9835/1.4888)	mem 24308MB
[2025-01-19 03:24:00 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][130/312]	eta 0:01:52 lr 0.000333	time 0.5766 (0.6172)	model_time 0.5761 (0.6053)	loss 2.7694 (2.9141)	grad_norm 2.7868 (2.9723/1.4513)	mem 24308MB
[2025-01-19 03:24:06 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][140/312]	eta 0:01:45 lr 0.000332	time 0.5831 (0.6158)	model_time 0.5830 (0.6048)	loss 3.0637 (2.9152)	grad_norm 2.8707 (2.9426/1.4125)	mem 24308MB
[2025-01-19 03:24:12 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][150/312]	eta 0:01:39 lr 0.000332	time 0.6615 (0.6148)	model_time 0.6611 (0.6044)	loss 3.2197 (2.9236)	grad_norm 2.1401 (2.9179/1.3785)	mem 24308MB
[2025-01-19 03:24:18 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][160/312]	eta 0:01:33 lr 0.000332	time 0.6557 (0.6153)	model_time 0.6556 (0.6055)	loss 2.9735 (2.9139)	grad_norm 2.5999 (2.9430/1.3680)	mem 24308MB
[2025-01-19 03:24:24 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][170/312]	eta 0:01:27 lr 0.000331	time 0.5818 (0.6146)	model_time 0.5813 (0.6054)	loss 3.1101 (2.9253)	grad_norm 2.9204 (2.9103/1.3524)	mem 24308MB
[2025-01-19 03:24:31 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][180/312]	eta 0:01:21 lr 0.000331	time 0.5973 (0.6145)	model_time 0.5971 (0.6058)	loss 3.1682 (2.9288)	grad_norm 1.7713 (2.8587/1.3358)	mem 24308MB
[2025-01-19 03:24:37 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][190/312]	eta 0:01:14 lr 0.000331	time 0.5868 (0.6142)	model_time 0.5867 (0.6059)	loss 3.3018 (2.9253)	grad_norm 1.7546 (2.8068/1.3255)	mem 24308MB
[2025-01-19 03:24:43 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][200/312]	eta 0:01:08 lr 0.000330	time 0.6702 (0.6152)	model_time 0.6701 (0.6073)	loss 3.4175 (2.9232)	grad_norm 1.1616 (2.7683/1.3084)	mem 24308MB
[2025-01-19 03:24:49 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][210/312]	eta 0:01:02 lr 0.000330	time 0.7036 (0.6158)	model_time 0.7034 (0.6082)	loss 2.7160 (2.9175)	grad_norm 4.4590 (2.8078/1.3062)	mem 24308MB
[2025-01-19 03:24:55 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][220/312]	eta 0:00:56 lr 0.000330	time 0.5717 (0.6144)	model_time 0.5716 (0.6072)	loss 3.1023 (2.9155)	grad_norm 3.4505 (2.8292/1.2971)	mem 24308MB
[2025-01-19 03:25:01 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][230/312]	eta 0:00:50 lr 0.000329	time 0.5807 (0.6135)	model_time 0.5802 (0.6066)	loss 2.3730 (2.9067)	grad_norm 2.4707 (2.8037/1.2876)	mem 24308MB
[2025-01-19 03:25:07 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][240/312]	eta 0:00:44 lr 0.000329	time 0.5784 (0.6134)	model_time 0.5779 (0.6068)	loss 3.1445 (2.9061)	grad_norm 3.0939 (2.8062/1.2880)	mem 24308MB
[2025-01-19 03:25:13 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][250/312]	eta 0:00:37 lr 0.000329	time 0.5826 (0.6129)	model_time 0.5822 (0.6065)	loss 2.7352 (2.9037)	grad_norm 1.3919 (2.7998/1.2866)	mem 24308MB
[2025-01-19 03:25:19 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][260/312]	eta 0:00:31 lr 0.000328	time 0.5747 (0.6127)	model_time 0.5745 (0.6066)	loss 3.1803 (2.9079)	grad_norm 4.7551 (2.8479/1.2979)	mem 24308MB
[2025-01-19 03:25:25 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][270/312]	eta 0:00:25 lr 0.000328	time 0.6686 (0.6122)	model_time 0.6681 (0.6063)	loss 3.0692 (2.9066)	grad_norm 3.4567 (2.8617/1.3117)	mem 24308MB
[2025-01-19 03:25:31 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][280/312]	eta 0:00:19 lr 0.000327	time 0.5864 (0.6119)	model_time 0.5859 (0.6061)	loss 3.0292 (2.9100)	grad_norm 1.5772 (2.8520/1.3167)	mem 24308MB
[2025-01-19 03:25:38 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][290/312]	eta 0:00:13 lr 0.000327	time 0.6708 (0.6122)	model_time 0.6706 (0.6066)	loss 3.3899 (2.9177)	grad_norm 2.6927 (2.8423/1.3018)	mem 24308MB
[2025-01-19 03:25:43 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][300/312]	eta 0:00:07 lr 0.000327	time 0.5702 (0.6114)	model_time 0.5701 (0.6060)	loss 1.9187 (2.9126)	grad_norm 2.8539 (2.8853/1.3455)	mem 24308MB
[2025-01-19 03:25:50 internimage_s_1k_224] (main.py 510): INFO Train: [247/300][310/312]	eta 0:00:01 lr 0.000326	time 0.5718 (0.6116)	model_time 0.5716 (0.6064)	loss 2.6411 (2.9109)	grad_norm 1.9585 (2.9245/1.3780)	mem 24308MB
[2025-01-19 03:25:50 internimage_s_1k_224] (main.py 519): INFO EPOCH 247 training takes 0:03:10
[2025-01-19 03:25:50 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_247.pth saving......
[2025-01-19 03:25:52 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_247.pth saved !!!
[2025-01-19 03:26:00 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.792 (7.792)	Loss 0.7377 (0.7377)	Acc@1 85.425 (85.425)	Acc@5 97.534 (97.534)	Mem 24308MB
[2025-01-19 03:26:04 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.052)	Loss 0.9126 (0.8076)	Acc@1 79.712 (83.361)	Acc@5 95.776 (96.629)	Mem 24308MB
[2025-01-19 03:26:04 internimage_s_1k_224] (main.py 575): INFO [Epoch:247] * Acc@1 83.205 Acc@5 96.623
[2025-01-19 03:26:04 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.2%
[2025-01-19 03:26:04 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.36%
[2025-01-19 03:26:13 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.089 (9.089)	Loss 0.7010 (0.7010)	Acc@1 85.449 (85.449)	Acc@5 97.803 (97.803)	Mem 24308MB
[2025-01-19 03:26:17 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.216)	Loss 0.8952 (0.7781)	Acc@1 79.297 (83.418)	Acc@5 95.972 (96.684)	Mem 24308MB
[2025-01-19 03:26:17 internimage_s_1k_224] (main.py 575): INFO [Epoch:247] * Acc@1 83.317 Acc@5 96.711
[2025-01-19 03:26:17 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.3%
[2025-01-19 03:26:17 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:26:20 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:26:20 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.32%
[2025-01-19 03:26:22 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][0/312]	eta 0:11:22 lr 0.000326	time 2.1869 (2.1869)	model_time 0.6015 (0.6015)	loss 2.5960 (2.5960)	grad_norm 3.8619 (3.8619/0.0000)	mem 24308MB
[2025-01-19 03:26:28 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][10/312]	eta 0:03:46 lr 0.000326	time 0.6058 (0.7512)	model_time 0.6057 (0.6067)	loss 2.8347 (2.9385)	grad_norm 2.8405 (3.3964/1.3332)	mem 24308MB
[2025-01-19 03:26:34 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][20/312]	eta 0:03:20 lr 0.000326	time 0.5850 (0.6874)	model_time 0.5848 (0.6116)	loss 3.2869 (2.9744)	grad_norm 4.5265 (3.5307/1.5857)	mem 24308MB
[2025-01-19 03:26:40 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][30/312]	eta 0:03:04 lr 0.000325	time 0.5969 (0.6549)	model_time 0.5967 (0.6035)	loss 2.2388 (2.9809)	grad_norm 1.9192 (3.3335/1.4003)	mem 24308MB
[2025-01-19 03:26:46 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][40/312]	eta 0:02:54 lr 0.000325	time 0.5956 (0.6412)	model_time 0.5954 (0.6022)	loss 2.1596 (2.9912)	grad_norm 2.8611 (3.0623/1.3437)	mem 24308MB
[2025-01-19 03:26:52 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][50/312]	eta 0:02:46 lr 0.000325	time 0.5740 (0.6343)	model_time 0.5738 (0.6029)	loss 3.3034 (2.9895)	grad_norm 3.2673 (2.9859/1.3127)	mem 24308MB
[2025-01-19 03:26:58 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][60/312]	eta 0:02:38 lr 0.000324	time 0.6136 (0.6289)	model_time 0.6131 (0.6025)	loss 2.1231 (2.9200)	grad_norm 2.0550 (2.9162/1.2600)	mem 24308MB
[2025-01-19 03:27:04 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][70/312]	eta 0:02:30 lr 0.000324	time 0.5892 (0.6229)	model_time 0.5891 (0.6002)	loss 2.9701 (2.8810)	grad_norm 2.8675 (2.8469/1.2108)	mem 24308MB
[2025-01-19 03:27:10 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][80/312]	eta 0:02:23 lr 0.000324	time 0.5962 (0.6203)	model_time 0.5961 (0.6004)	loss 2.8094 (2.8850)	grad_norm 3.0316 (2.9274/1.2315)	mem 24308MB
[2025-01-19 03:27:16 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][90/312]	eta 0:02:17 lr 0.000323	time 0.6536 (0.6204)	model_time 0.6534 (0.6026)	loss 2.3667 (2.8761)	grad_norm 1.9184 (2.8661/1.2147)	mem 24308MB
[2025-01-19 03:27:22 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][100/312]	eta 0:02:11 lr 0.000323	time 0.5823 (0.6200)	model_time 0.5819 (0.6039)	loss 2.4988 (2.8866)	grad_norm 2.8132 (2.8165/1.1900)	mem 24308MB
[2025-01-19 03:27:28 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][110/312]	eta 0:02:05 lr 0.000323	time 0.5672 (0.6190)	model_time 0.5670 (0.6043)	loss 2.6676 (2.8782)	grad_norm 2.6501 (2.7849/1.1639)	mem 24308MB
[2025-01-19 03:27:35 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][120/312]	eta 0:01:59 lr 0.000322	time 0.6019 (0.6217)	model_time 0.6017 (0.6082)	loss 1.8022 (2.8656)	grad_norm 2.9092 (2.7698/1.1294)	mem 24308MB
[2025-01-19 03:27:41 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][130/312]	eta 0:01:52 lr 0.000322	time 0.5808 (0.6205)	model_time 0.5806 (0.6080)	loss 3.5114 (2.8731)	grad_norm 3.7556 (2.8217/1.1379)	mem 24308MB
[2025-01-19 03:27:47 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][140/312]	eta 0:01:46 lr 0.000322	time 0.6829 (0.6201)	model_time 0.6827 (0.6085)	loss 2.5365 (2.8714)	grad_norm 1.5914 (2.8482/1.1298)	mem 24308MB
[2025-01-19 03:27:53 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][150/312]	eta 0:01:40 lr 0.000321	time 0.5853 (0.6181)	model_time 0.5852 (0.6072)	loss 2.8353 (2.8687)	grad_norm 3.8589 (2.8270/1.1131)	mem 24308MB
[2025-01-19 03:27:59 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][160/312]	eta 0:01:33 lr 0.000321	time 0.5816 (0.6168)	model_time 0.5814 (0.6066)	loss 2.2767 (2.8452)	grad_norm 2.1808 (2.8093/1.1279)	mem 24308MB
[2025-01-19 03:28:05 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][170/312]	eta 0:01:27 lr 0.000321	time 0.5915 (0.6167)	model_time 0.5914 (0.6070)	loss 2.3739 (2.8502)	grad_norm 1.2151 (2.8134/1.1346)	mem 24308MB
[2025-01-19 03:28:11 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][180/312]	eta 0:01:21 lr 0.000320	time 0.5697 (0.6170)	model_time 0.5695 (0.6078)	loss 2.9464 (2.8474)	grad_norm 4.5403 (2.8604/1.1709)	mem 24308MB
[2025-01-19 03:28:17 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][190/312]	eta 0:01:15 lr 0.000320	time 0.5878 (0.6158)	model_time 0.5873 (0.6072)	loss 3.0507 (2.8506)	grad_norm 1.5860 (2.8460/1.1675)	mem 24308MB
[2025-01-19 03:28:23 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][200/312]	eta 0:01:08 lr 0.000320	time 0.5790 (0.6151)	model_time 0.5788 (0.6068)	loss 2.9164 (2.8445)	grad_norm 2.9924 (2.8056/1.1565)	mem 24308MB
[2025-01-19 03:28:29 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][210/312]	eta 0:01:02 lr 0.000319	time 0.6820 (0.6150)	model_time 0.6819 (0.6071)	loss 2.9076 (2.8521)	grad_norm 5.0372 (2.7986/1.1544)	mem 24308MB
[2025-01-19 03:28:36 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][220/312]	eta 0:00:56 lr 0.000319	time 0.5914 (0.6153)	model_time 0.5912 (0.6077)	loss 2.8154 (2.8515)	grad_norm 2.6434 (2.7945/1.1380)	mem 24308MB
[2025-01-19 03:28:42 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][230/312]	eta 0:00:50 lr 0.000319	time 0.6381 (0.6148)	model_time 0.6376 (0.6076)	loss 3.1552 (2.8510)	grad_norm 1.8387 (2.7854/1.1216)	mem 24308MB
[2025-01-19 03:28:48 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][240/312]	eta 0:00:44 lr 0.000318	time 0.5789 (0.6148)	model_time 0.5787 (0.6079)	loss 2.3838 (2.8556)	grad_norm 3.2643 (2.7693/1.1063)	mem 24308MB
[2025-01-19 03:28:54 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][250/312]	eta 0:00:38 lr 0.000318	time 0.5872 (0.6144)	model_time 0.5871 (0.6076)	loss 2.1377 (2.8508)	grad_norm 4.7659 (2.7865/1.1402)	mem 24308MB
[2025-01-19 03:29:00 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][260/312]	eta 0:00:31 lr 0.000317	time 0.6592 (0.6144)	model_time 0.6587 (0.6079)	loss 2.1805 (2.8508)	grad_norm 2.4182 (2.7870/1.1255)	mem 24308MB
[2025-01-19 03:29:06 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][270/312]	eta 0:00:25 lr 0.000317	time 0.5641 (0.6136)	model_time 0.5639 (0.6074)	loss 3.1452 (2.8464)	grad_norm 1.9599 (2.7653/1.1173)	mem 24308MB
[2025-01-19 03:29:12 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][280/312]	eta 0:00:19 lr 0.000317	time 0.5999 (0.6132)	model_time 0.5998 (0.6072)	loss 3.0405 (2.8399)	grad_norm 2.2197 (2.7387/1.1128)	mem 24308MB
[2025-01-19 03:29:18 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][290/312]	eta 0:00:13 lr 0.000316	time 0.5877 (0.6132)	model_time 0.5875 (0.6073)	loss 2.9931 (2.8429)	grad_norm 1.6544 (2.7252/1.1321)	mem 24308MB
[2025-01-19 03:29:24 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][300/312]	eta 0:00:07 lr 0.000316	time 0.5671 (0.6122)	model_time 0.5670 (0.6065)	loss 3.3053 (2.8451)	grad_norm 2.3743 (2.7310/1.1229)	mem 24308MB
[2025-01-19 03:29:30 internimage_s_1k_224] (main.py 510): INFO Train: [248/300][310/312]	eta 0:00:01 lr 0.000316	time 0.5700 (0.6113)	model_time 0.5699 (0.6058)	loss 2.3674 (2.8405)	grad_norm 3.4092 (2.7249/1.1100)	mem 24308MB
[2025-01-19 03:29:30 internimage_s_1k_224] (main.py 519): INFO EPOCH 248 training takes 0:03:10
[2025-01-19 03:29:30 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_248.pth saving......
[2025-01-19 03:29:32 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_248.pth saved !!!
[2025-01-19 03:29:40 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.089 (8.089)	Loss 0.7349 (0.7349)	Acc@1 85.620 (85.620)	Acc@5 97.461 (97.461)	Mem 24308MB
[2025-01-19 03:29:44 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.053)	Loss 0.8944 (0.8053)	Acc@1 80.151 (83.498)	Acc@5 95.898 (96.702)	Mem 24308MB
[2025-01-19 03:29:44 internimage_s_1k_224] (main.py 575): INFO [Epoch:248] * Acc@1 83.361 Acc@5 96.709
[2025-01-19 03:29:44 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.4%
[2025-01-19 03:29:44 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 03:29:46 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 03:29:46 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.36%
[2025-01-19 03:29:54 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.893 (7.893)	Loss 0.7008 (0.7008)	Acc@1 85.498 (85.498)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 03:29:58 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.059)	Loss 0.8941 (0.7775)	Acc@1 79.321 (83.447)	Acc@5 95.996 (96.704)	Mem 24308MB
[2025-01-19 03:29:58 internimage_s_1k_224] (main.py 575): INFO [Epoch:248] * Acc@1 83.347 Acc@5 96.729
[2025-01-19 03:29:58 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.3%
[2025-01-19 03:29:58 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:30:00 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:30:00 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.35%
[2025-01-19 03:30:02 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][0/312]	eta 0:10:13 lr 0.000316	time 1.9656 (1.9656)	model_time 0.6011 (0.6011)	loss 1.7169 (1.7169)	grad_norm 2.3935 (2.3935/0.0000)	mem 24308MB
[2025-01-19 03:30:08 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][10/312]	eta 0:03:37 lr 0.000315	time 0.5818 (0.7195)	model_time 0.5816 (0.5952)	loss 2.3418 (2.4816)	grad_norm 2.9727 (2.9532/0.9385)	mem 24308MB
[2025-01-19 03:30:14 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][20/312]	eta 0:03:19 lr 0.000315	time 0.6690 (0.6818)	model_time 0.6689 (0.6165)	loss 2.0495 (2.6114)	grad_norm 1.7623 (2.5628/1.0914)	mem 24308MB
[2025-01-19 03:30:20 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][30/312]	eta 0:03:05 lr 0.000315	time 0.5693 (0.6581)	model_time 0.5691 (0.6139)	loss 3.5133 (2.6518)	grad_norm 1.8869 (2.6102/0.9991)	mem 24308MB
[2025-01-19 03:30:27 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][40/312]	eta 0:02:56 lr 0.000314	time 0.6608 (0.6477)	model_time 0.6606 (0.6142)	loss 2.8601 (2.6622)	grad_norm 1.5015 (2.5846/0.9795)	mem 24308MB
[2025-01-19 03:30:33 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][50/312]	eta 0:02:48 lr 0.000314	time 0.6038 (0.6430)	model_time 0.6036 (0.6160)	loss 3.2178 (2.6652)	grad_norm 2.8289 (2.5804/0.9618)	mem 24308MB
[2025-01-19 03:30:39 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][60/312]	eta 0:02:40 lr 0.000314	time 0.5729 (0.6361)	model_time 0.5727 (0.6133)	loss 2.3028 (2.6921)	grad_norm 2.4204 (2.6592/1.0650)	mem 24308MB
[2025-01-19 03:30:45 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][70/312]	eta 0:02:33 lr 0.000313	time 0.5888 (0.6323)	model_time 0.5887 (0.6126)	loss 3.1734 (2.7281)	grad_norm 2.9288 (2.7646/1.2016)	mem 24308MB
[2025-01-19 03:30:51 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][80/312]	eta 0:02:25 lr 0.000313	time 0.5866 (0.6277)	model_time 0.5865 (0.6104)	loss 1.7762 (2.7588)	grad_norm 2.3910 (2.7318/1.1695)	mem 24308MB
[2025-01-19 03:30:57 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][90/312]	eta 0:02:18 lr 0.000313	time 0.5737 (0.6239)	model_time 0.5735 (0.6085)	loss 1.8191 (2.7897)	grad_norm 2.2861 (2.6364/1.1465)	mem 24308MB
[2025-01-19 03:31:03 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][100/312]	eta 0:02:12 lr 0.000312	time 0.5847 (0.6228)	model_time 0.5846 (0.6089)	loss 3.7236 (2.7783)	grad_norm 4.5153 (2.6029/1.1529)	mem 24308MB
[2025-01-19 03:31:09 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][110/312]	eta 0:02:05 lr 0.000312	time 0.5792 (0.6194)	model_time 0.5790 (0.6067)	loss 2.9790 (2.8046)	grad_norm 2.2862 (2.5918/1.1291)	mem 24308MB
[2025-01-19 03:31:15 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][120/312]	eta 0:01:58 lr 0.000312	time 0.5794 (0.6191)	model_time 0.5790 (0.6074)	loss 2.3576 (2.8052)	grad_norm 3.1510 (2.6611/1.1688)	mem 24308MB
[2025-01-19 03:31:21 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][130/312]	eta 0:01:52 lr 0.000311	time 0.5865 (0.6177)	model_time 0.5864 (0.6068)	loss 2.4262 (2.8052)	grad_norm 1.7148 (2.6797/1.1746)	mem 24308MB
[2025-01-19 03:31:27 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][140/312]	eta 0:01:46 lr 0.000311	time 0.7490 (0.6180)	model_time 0.7489 (0.6080)	loss 3.2041 (2.7948)	grad_norm 2.7274 (2.7269/1.2311)	mem 24308MB
[2025-01-19 03:31:33 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][150/312]	eta 0:01:40 lr 0.000311	time 0.5789 (0.6175)	model_time 0.5785 (0.6081)	loss 2.1261 (2.7988)	grad_norm 1.9232 (2.7605/1.2782)	mem 24308MB
[2025-01-19 03:31:39 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][160/312]	eta 0:01:33 lr 0.000310	time 0.5937 (0.6171)	model_time 0.5935 (0.6083)	loss 3.7240 (2.8036)	grad_norm 1.4094 (2.7043/1.2654)	mem 24308MB
[2025-01-19 03:31:46 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][170/312]	eta 0:01:27 lr 0.000310	time 0.6546 (0.6190)	model_time 0.6544 (0.6107)	loss 2.9252 (2.8129)	grad_norm 1.6457 (2.6655/1.2459)	mem 24308MB
[2025-01-19 03:31:52 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][180/312]	eta 0:01:21 lr 0.000310	time 0.5830 (0.6183)	model_time 0.5826 (0.6104)	loss 3.5383 (2.8259)	grad_norm 2.6806 (2.6489/1.2175)	mem 24308MB
[2025-01-19 03:31:58 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][190/312]	eta 0:01:15 lr 0.000309	time 0.5864 (0.6180)	model_time 0.5862 (0.6105)	loss 2.5251 (2.8228)	grad_norm 1.5147 (2.6398/1.2114)	mem 24308MB
[2025-01-19 03:32:04 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][200/312]	eta 0:01:09 lr 0.000309	time 0.5835 (0.6173)	model_time 0.5831 (0.6101)	loss 2.6651 (2.8216)	grad_norm 4.0346 (2.6797/1.2979)	mem 24308MB
[2025-01-19 03:32:10 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][210/312]	eta 0:01:02 lr 0.000309	time 0.5730 (0.6163)	model_time 0.5729 (0.6094)	loss 2.1831 (2.8124)	grad_norm 1.4351 (2.6635/1.2901)	mem 24308MB
[2025-01-19 03:32:16 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][220/312]	eta 0:00:56 lr 0.000308	time 0.5954 (0.6157)	model_time 0.5952 (0.6092)	loss 1.8579 (2.8130)	grad_norm 1.6546 (2.6432/1.2718)	mem 24308MB
[2025-01-19 03:32:22 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][230/312]	eta 0:00:50 lr 0.000308	time 0.5745 (0.6149)	model_time 0.5743 (0.6087)	loss 3.3408 (2.8244)	grad_norm 3.2343 (2.6410/1.2547)	mem 24308MB
[2025-01-19 03:32:28 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][240/312]	eta 0:00:44 lr 0.000308	time 0.5719 (0.6141)	model_time 0.5718 (0.6080)	loss 3.3216 (2.8352)	grad_norm 4.4518 (2.6676/1.2494)	mem 24308MB
[2025-01-19 03:32:34 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][250/312]	eta 0:00:38 lr 0.000307	time 0.5949 (0.6133)	model_time 0.5945 (0.6075)	loss 3.5494 (2.8340)	grad_norm 1.6125 (2.6983/1.2719)	mem 24308MB
[2025-01-19 03:32:40 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][260/312]	eta 0:00:31 lr 0.000307	time 0.5887 (0.6130)	model_time 0.5885 (0.6074)	loss 1.9787 (2.8401)	grad_norm 1.6745 (2.7248/1.2779)	mem 24308MB
[2025-01-19 03:32:46 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][270/312]	eta 0:00:25 lr 0.000307	time 0.5774 (0.6129)	model_time 0.5773 (0.6075)	loss 3.2009 (2.8416)	grad_norm 1.5718 (2.7103/1.2645)	mem 24308MB
[2025-01-19 03:32:52 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][280/312]	eta 0:00:19 lr 0.000306	time 0.5742 (0.6124)	model_time 0.5740 (0.6071)	loss 3.0598 (2.8386)	grad_norm 1.1783 (2.7146/1.2603)	mem 24308MB
[2025-01-19 03:32:59 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][290/312]	eta 0:00:13 lr 0.000306	time 0.6982 (0.6133)	model_time 0.6978 (0.6082)	loss 2.9736 (2.8437)	grad_norm 3.2706 (2.7142/1.2500)	mem 24308MB
[2025-01-19 03:33:04 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][300/312]	eta 0:00:07 lr 0.000306	time 0.5698 (0.6125)	model_time 0.5697 (0.6076)	loss 2.8699 (2.8446)	grad_norm 2.2228 (2.7024/1.2400)	mem 24308MB
[2025-01-19 03:33:10 internimage_s_1k_224] (main.py 510): INFO Train: [249/300][310/312]	eta 0:00:01 lr 0.000305	time 0.5705 (0.6120)	model_time 0.5704 (0.6073)	loss 3.1422 (2.8414)	grad_norm 4.1955 (2.7045/1.2413)	mem 24308MB
[2025-01-19 03:33:11 internimage_s_1k_224] (main.py 519): INFO EPOCH 249 training takes 0:03:10
[2025-01-19 03:33:11 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_249.pth saving......
[2025-01-19 03:33:13 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_249.pth saved !!!
[2025-01-19 03:33:21 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.031 (8.031)	Loss 0.7059 (0.7059)	Acc@1 85.596 (85.596)	Acc@5 97.754 (97.754)	Mem 24308MB
[2025-01-19 03:33:25 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.063)	Loss 0.8970 (0.7829)	Acc@1 79.395 (83.587)	Acc@5 95.825 (96.662)	Mem 24308MB
[2025-01-19 03:33:25 internimage_s_1k_224] (main.py 575): INFO [Epoch:249] * Acc@1 83.423 Acc@5 96.657
[2025-01-19 03:33:25 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.4%
[2025-01-19 03:33:25 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 03:33:27 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 03:33:27 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.42%
[2025-01-19 03:33:35 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.993 (7.993)	Loss 0.7006 (0.7006)	Acc@1 85.522 (85.522)	Acc@5 97.803 (97.803)	Mem 24308MB
[2025-01-19 03:33:38 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.049)	Loss 0.8928 (0.7769)	Acc@1 79.272 (83.476)	Acc@5 95.996 (96.695)	Mem 24308MB
[2025-01-19 03:33:38 internimage_s_1k_224] (main.py 575): INFO [Epoch:249] * Acc@1 83.363 Acc@5 96.723
[2025-01-19 03:33:38 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.4%
[2025-01-19 03:33:38 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:33:41 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:33:41 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.36%
[2025-01-19 03:33:43 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][0/312]	eta 0:10:23 lr 0.000305	time 1.9977 (1.9977)	model_time 0.5953 (0.5953)	loss 2.4896 (2.4896)	grad_norm 4.6063 (4.6063/0.0000)	mem 24308MB
[2025-01-19 03:33:49 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][10/312]	eta 0:03:42 lr 0.000305	time 0.5955 (0.7383)	model_time 0.5953 (0.6106)	loss 2.7917 (2.7050)	grad_norm 3.0665 (4.0852/1.9326)	mem 24308MB
[2025-01-19 03:33:55 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][20/312]	eta 0:03:16 lr 0.000305	time 0.5884 (0.6730)	model_time 0.5882 (0.6059)	loss 1.7767 (2.7450)	grad_norm 2.0687 (3.2792/1.7282)	mem 24308MB
[2025-01-19 03:34:01 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][30/312]	eta 0:03:04 lr 0.000304	time 0.5878 (0.6536)	model_time 0.5874 (0.6081)	loss 2.9595 (2.7478)	grad_norm 2.2608 (3.0601/1.5269)	mem 24308MB
[2025-01-19 03:34:07 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][40/312]	eta 0:02:54 lr 0.000304	time 0.5904 (0.6406)	model_time 0.5902 (0.6061)	loss 1.9907 (2.8172)	grad_norm 1.4667 (2.9372/1.3985)	mem 24308MB
[2025-01-19 03:34:13 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][50/312]	eta 0:02:45 lr 0.000304	time 0.5861 (0.6327)	model_time 0.5859 (0.6049)	loss 2.2377 (2.8220)	grad_norm 1.0515 (3.0064/1.3823)	mem 24308MB
[2025-01-19 03:34:19 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][60/312]	eta 0:02:37 lr 0.000303	time 0.5798 (0.6266)	model_time 0.5796 (0.6033)	loss 2.9457 (2.8643)	grad_norm 3.5338 (2.9202/1.3087)	mem 24308MB
[2025-01-19 03:34:25 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][70/312]	eta 0:02:30 lr 0.000303	time 0.6002 (0.6226)	model_time 0.6000 (0.6025)	loss 1.7746 (2.8506)	grad_norm 5.8400 (2.9681/1.3465)	mem 24308MB
[2025-01-19 03:34:31 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][80/312]	eta 0:02:24 lr 0.000303	time 0.7267 (0.6231)	model_time 0.7263 (0.6054)	loss 1.8728 (2.8323)	grad_norm 6.7784 (2.9473/1.3734)	mem 24308MB
[2025-01-19 03:34:37 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][90/312]	eta 0:02:17 lr 0.000302	time 0.5826 (0.6215)	model_time 0.5824 (0.6057)	loss 2.8594 (2.8330)	grad_norm 2.2258 (2.8748/1.3598)	mem 24308MB
[2025-01-19 03:34:43 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][100/312]	eta 0:02:11 lr 0.000302	time 0.5799 (0.6213)	model_time 0.5798 (0.6071)	loss 2.8651 (2.8549)	grad_norm 4.6440 (2.8472/1.3411)	mem 24308MB
[2025-01-19 03:34:49 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][110/312]	eta 0:02:05 lr 0.000302	time 0.6748 (0.6205)	model_time 0.6744 (0.6076)	loss 2.3042 (2.8567)	grad_norm 2.2809 (2.7946/1.3022)	mem 24308MB
[2025-01-19 03:34:56 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][120/312]	eta 0:01:58 lr 0.000301	time 0.5743 (0.6195)	model_time 0.5741 (0.6076)	loss 2.9699 (2.8476)	grad_norm 3.9176 (2.7816/1.2725)	mem 24308MB
[2025-01-19 03:35:02 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][130/312]	eta 0:01:52 lr 0.000301	time 0.6113 (0.6184)	model_time 0.6112 (0.6074)	loss 3.2113 (2.8611)	grad_norm 5.0781 (2.7833/1.2669)	mem 24308MB
[2025-01-19 03:35:08 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][140/312]	eta 0:01:46 lr 0.000301	time 0.6397 (0.6169)	model_time 0.6396 (0.6067)	loss 3.3003 (2.8663)	grad_norm 3.6196 (2.9390/1.4470)	mem 24308MB
[2025-01-19 03:35:13 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][150/312]	eta 0:01:39 lr 0.000300	time 0.5758 (0.6154)	model_time 0.5756 (0.6058)	loss 3.0447 (2.8585)	grad_norm 1.0869 (2.8957/1.4410)	mem 24308MB
[2025-01-19 03:35:20 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][160/312]	eta 0:01:33 lr 0.000300	time 0.6028 (0.6148)	model_time 0.6024 (0.6057)	loss 2.6729 (2.8699)	grad_norm 3.0524 (2.8593/1.4180)	mem 24308MB
[2025-01-19 03:35:25 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][170/312]	eta 0:01:27 lr 0.000300	time 0.5909 (0.6134)	model_time 0.5908 (0.6048)	loss 3.1476 (2.8748)	grad_norm 1.5562 (2.8276/1.3967)	mem 24308MB
[2025-01-19 03:35:31 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][180/312]	eta 0:01:20 lr 0.000299	time 0.6151 (0.6127)	model_time 0.6149 (0.6045)	loss 2.8704 (2.8763)	grad_norm 1.6628 (2.8315/1.3772)	mem 24308MB
[2025-01-19 03:35:37 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][190/312]	eta 0:01:14 lr 0.000299	time 0.5863 (0.6118)	model_time 0.5862 (0.6041)	loss 2.9858 (2.8776)	grad_norm 3.0786 (2.8070/1.3554)	mem 24308MB
[2025-01-19 03:35:44 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][200/312]	eta 0:01:08 lr 0.000299	time 0.7085 (0.6126)	model_time 0.7081 (0.6053)	loss 2.2889 (2.8741)	grad_norm 1.7550 (2.7961/1.3433)	mem 24308MB
[2025-01-19 03:35:50 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][210/312]	eta 0:01:02 lr 0.000298	time 0.5743 (0.6123)	model_time 0.5741 (0.6053)	loss 2.7036 (2.8576)	grad_norm 1.4979 (2.7643/1.3245)	mem 24308MB
[2025-01-19 03:35:56 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][220/312]	eta 0:00:56 lr 0.000298	time 0.6006 (0.6129)	model_time 0.6001 (0.6061)	loss 2.9210 (2.8652)	grad_norm 3.0687 (2.7588/1.3131)	mem 24308MB
[2025-01-19 03:36:02 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][230/312]	eta 0:00:50 lr 0.000298	time 0.6619 (0.6135)	model_time 0.6618 (0.6071)	loss 2.6622 (2.8714)	grad_norm 1.4234 (2.7240/1.2994)	mem 24308MB
[2025-01-19 03:36:08 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][240/312]	eta 0:00:44 lr 0.000297	time 0.5989 (0.6134)	model_time 0.5985 (0.6072)	loss 3.5817 (2.8698)	grad_norm 1.3377 (2.7103/1.2916)	mem 24308MB
[2025-01-19 03:36:15 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][250/312]	eta 0:00:38 lr 0.000297	time 0.5807 (0.6135)	model_time 0.5806 (0.6075)	loss 2.7432 (2.8571)	grad_norm 4.3974 (2.6993/1.2814)	mem 24308MB
[2025-01-19 03:36:21 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][260/312]	eta 0:00:31 lr 0.000297	time 0.5955 (0.6128)	model_time 0.5951 (0.6071)	loss 2.4571 (2.8580)	grad_norm 1.7065 (2.7171/1.2978)	mem 24308MB
[2025-01-19 03:36:26 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][270/312]	eta 0:00:25 lr 0.000296	time 0.6385 (0.6122)	model_time 0.6384 (0.6067)	loss 3.1701 (2.8547)	grad_norm 4.8373 (2.7579/1.3209)	mem 24308MB
[2025-01-19 03:36:33 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][280/312]	eta 0:00:19 lr 0.000296	time 0.6038 (0.6120)	model_time 0.6033 (0.6066)	loss 2.9001 (2.8456)	grad_norm 2.0401 (2.7583/1.3097)	mem 24308MB
[2025-01-19 03:36:38 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][290/312]	eta 0:00:13 lr 0.000296	time 0.5809 (0.6113)	model_time 0.5807 (0.6061)	loss 2.3763 (2.8447)	grad_norm 4.4112 (2.7734/1.3286)	mem 24308MB
[2025-01-19 03:36:44 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][300/312]	eta 0:00:07 lr 0.000295	time 0.5709 (0.6105)	model_time 0.5708 (0.6055)	loss 2.8559 (2.8492)	grad_norm 2.0838 (2.7700/1.3099)	mem 24308MB
[2025-01-19 03:36:50 internimage_s_1k_224] (main.py 510): INFO Train: [250/300][310/312]	eta 0:00:01 lr 0.000295	time 0.5686 (0.6098)	model_time 0.5685 (0.6049)	loss 3.0141 (2.8480)	grad_norm 1.3743 (2.7239/1.2484)	mem 24308MB
[2025-01-19 03:36:51 internimage_s_1k_224] (main.py 519): INFO EPOCH 250 training takes 0:03:10
[2025-01-19 03:36:51 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_250.pth saving......
[2025-01-19 03:36:52 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_250.pth saved !!!
[2025-01-19 03:37:01 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.123 (8.123)	Loss 0.7117 (0.7117)	Acc@1 85.669 (85.669)	Acc@5 97.656 (97.656)	Mem 24308MB
[2025-01-19 03:37:04 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.058)	Loss 0.9060 (0.7960)	Acc@1 79.370 (83.494)	Acc@5 95.752 (96.709)	Mem 24308MB
[2025-01-19 03:37:04 internimage_s_1k_224] (main.py 575): INFO [Epoch:250] * Acc@1 83.341 Acc@5 96.719
[2025-01-19 03:37:04 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.3%
[2025-01-19 03:37:04 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.42%
[2025-01-19 03:37:13 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.955 (8.955)	Loss 0.7005 (0.7005)	Acc@1 85.522 (85.522)	Acc@5 97.803 (97.803)	Mem 24308MB
[2025-01-19 03:37:18 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.226)	Loss 0.8918 (0.7764)	Acc@1 79.346 (83.498)	Acc@5 95.996 (96.700)	Mem 24308MB
[2025-01-19 03:37:18 internimage_s_1k_224] (main.py 575): INFO [Epoch:250] * Acc@1 83.377 Acc@5 96.725
[2025-01-19 03:37:18 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.4%
[2025-01-19 03:37:18 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:37:20 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:37:20 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.38%
[2025-01-19 03:37:23 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][0/312]	eta 0:13:20 lr 0.000295	time 2.5668 (2.5668)	model_time 0.6253 (0.6253)	loss 3.4142 (3.4142)	grad_norm 1.4740 (1.4740/0.0000)	mem 24308MB
[2025-01-19 03:37:29 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][10/312]	eta 0:03:57 lr 0.000295	time 0.5736 (0.7853)	model_time 0.5732 (0.6085)	loss 3.0972 (3.1000)	grad_norm 4.8351 (3.7026/2.1219)	mem 24308MB
[2025-01-19 03:37:35 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][20/312]	eta 0:03:28 lr 0.000294	time 0.5964 (0.7130)	model_time 0.5962 (0.6203)	loss 2.7505 (2.9709)	grad_norm 2.3923 (3.4658/1.7672)	mem 24308MB
[2025-01-19 03:37:41 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][30/312]	eta 0:03:13 lr 0.000294	time 0.6992 (0.6852)	model_time 0.6991 (0.6223)	loss 3.1202 (2.8854)	grad_norm 3.1074 (3.2916/1.5950)	mem 24308MB
[2025-01-19 03:37:48 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][40/312]	eta 0:03:02 lr 0.000294	time 0.6637 (0.6714)	model_time 0.6635 (0.6238)	loss 2.3851 (2.8348)	grad_norm 1.8981 (3.1561/1.4473)	mem 24308MB
[2025-01-19 03:37:54 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][50/312]	eta 0:02:52 lr 0.000293	time 0.5912 (0.6578)	model_time 0.5910 (0.6194)	loss 2.1575 (2.8361)	grad_norm 1.4780 (2.9659/1.3835)	mem 24308MB
[2025-01-19 03:38:00 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][60/312]	eta 0:02:43 lr 0.000293	time 0.5995 (0.6503)	model_time 0.5993 (0.6181)	loss 3.0400 (2.8586)	grad_norm 2.7120 (2.9349/1.3155)	mem 24308MB
[2025-01-19 03:38:06 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][70/312]	eta 0:02:35 lr 0.000293	time 0.6590 (0.6425)	model_time 0.6588 (0.6148)	loss 3.1900 (2.8740)	grad_norm 2.3049 (2.8070/1.2733)	mem 24308MB
[2025-01-19 03:38:12 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][80/312]	eta 0:02:27 lr 0.000292	time 0.5906 (0.6369)	model_time 0.5902 (0.6126)	loss 1.9502 (2.8508)	grad_norm 2.6216 (2.7694/1.2204)	mem 24308MB
[2025-01-19 03:38:18 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][90/312]	eta 0:02:20 lr 0.000292	time 0.5818 (0.6330)	model_time 0.5814 (0.6114)	loss 2.8603 (2.8370)	grad_norm 1.5944 (2.7115/1.1920)	mem 24308MB
[2025-01-19 03:38:24 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][100/312]	eta 0:02:13 lr 0.000292	time 0.5971 (0.6294)	model_time 0.5966 (0.6098)	loss 3.0550 (2.8453)	grad_norm 1.8454 (2.6497/1.1684)	mem 24308MB
[2025-01-19 03:38:30 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][110/312]	eta 0:02:06 lr 0.000291	time 0.6001 (0.6265)	model_time 0.5999 (0.6087)	loss 2.8708 (2.8375)	grad_norm 3.3472 (2.6403/1.1468)	mem 24308MB
[2025-01-19 03:38:36 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][120/312]	eta 0:01:59 lr 0.000291	time 0.5879 (0.6245)	model_time 0.5875 (0.6081)	loss 2.3412 (2.7994)	grad_norm 1.9305 (2.6964/1.1779)	mem 24308MB
[2025-01-19 03:38:42 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][130/312]	eta 0:01:53 lr 0.000291	time 0.6029 (0.6240)	model_time 0.6028 (0.6089)	loss 2.9405 (2.7980)	grad_norm 2.5469 (2.7310/1.1866)	mem 24308MB
[2025-01-19 03:38:48 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][140/312]	eta 0:01:47 lr 0.000290	time 0.6792 (0.6255)	model_time 0.6790 (0.6113)	loss 3.5262 (2.8070)	grad_norm 3.8698 (2.7678/1.1675)	mem 24308MB
[2025-01-19 03:38:54 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][150/312]	eta 0:01:41 lr 0.000290	time 0.6765 (0.6238)	model_time 0.6760 (0.6106)	loss 2.6514 (2.8020)	grad_norm 1.6971 (2.7835/1.1632)	mem 24308MB
[2025-01-19 03:39:01 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][160/312]	eta 0:01:34 lr 0.000290	time 0.5730 (0.6241)	model_time 0.5725 (0.6117)	loss 2.9527 (2.8013)	grad_norm 3.9966 (2.8594/1.1941)	mem 24308MB
[2025-01-19 03:39:07 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][170/312]	eta 0:01:28 lr 0.000289	time 0.6622 (0.6235)	model_time 0.6620 (0.6117)	loss 3.1489 (2.8064)	grad_norm 3.5165 (2.8932/1.2098)	mem 24308MB
[2025-01-19 03:39:13 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][180/312]	eta 0:01:22 lr 0.000289	time 0.5747 (0.6229)	model_time 0.5745 (0.6118)	loss 2.7993 (2.8040)	grad_norm 1.8261 (2.8560/1.1927)	mem 24308MB
[2025-01-19 03:39:19 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][190/312]	eta 0:01:15 lr 0.000289	time 0.5796 (0.6211)	model_time 0.5794 (0.6105)	loss 2.7771 (2.8016)	grad_norm 1.0615 (2.8054/1.1911)	mem 24308MB
[2025-01-19 03:39:25 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][200/312]	eta 0:01:09 lr 0.000289	time 0.6030 (0.6202)	model_time 0.6026 (0.6101)	loss 3.0014 (2.8104)	grad_norm 2.2848 (2.7858/1.1776)	mem 24308MB
[2025-01-19 03:39:31 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][210/312]	eta 0:01:03 lr 0.000288	time 0.5905 (0.6190)	model_time 0.5904 (0.6094)	loss 2.4335 (2.8072)	grad_norm 1.5508 (2.7399/1.1755)	mem 24308MB
[2025-01-19 03:39:37 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][220/312]	eta 0:00:56 lr 0.000288	time 0.5834 (0.6179)	model_time 0.5829 (0.6087)	loss 2.8000 (2.8157)	grad_norm 1.9116 (2.7110/1.1695)	mem 24308MB
[2025-01-19 03:39:43 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][230/312]	eta 0:00:50 lr 0.000288	time 0.5906 (0.6170)	model_time 0.5904 (0.6082)	loss 2.6119 (2.8158)	grad_norm 1.6364 (2.6685/1.1652)	mem 24308MB
[2025-01-19 03:39:49 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][240/312]	eta 0:00:44 lr 0.000287	time 0.5783 (0.6163)	model_time 0.5779 (0.6078)	loss 3.1732 (2.8184)	grad_norm 2.8574 (2.6613/1.1644)	mem 24308MB
[2025-01-19 03:39:55 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][250/312]	eta 0:00:38 lr 0.000287	time 0.5815 (0.6163)	model_time 0.5812 (0.6082)	loss 2.9012 (2.8172)	grad_norm 1.9023 (2.6658/1.1647)	mem 24308MB
[2025-01-19 03:40:01 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][260/312]	eta 0:00:32 lr 0.000287	time 0.6645 (0.6164)	model_time 0.6641 (0.6086)	loss 3.4071 (2.8185)	grad_norm 4.5045 (2.7234/1.2290)	mem 24308MB
[2025-01-19 03:40:07 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][270/312]	eta 0:00:25 lr 0.000286	time 0.6600 (0.6163)	model_time 0.6598 (0.6088)	loss 2.9924 (2.8264)	grad_norm 1.3661 (2.7138/1.2254)	mem 24308MB
[2025-01-19 03:40:14 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][280/312]	eta 0:00:19 lr 0.000286	time 0.5978 (0.6166)	model_time 0.5974 (0.6093)	loss 3.4753 (2.8358)	grad_norm 4.4978 (2.6901/1.2244)	mem 24308MB
[2025-01-19 03:40:20 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][290/312]	eta 0:00:13 lr 0.000286	time 0.5818 (0.6160)	model_time 0.5814 (0.6089)	loss 3.1349 (2.8333)	grad_norm 2.2298 (2.6811/1.2156)	mem 24308MB
[2025-01-19 03:40:26 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][300/312]	eta 0:00:07 lr 0.000285	time 0.5702 (0.6162)	model_time 0.5701 (0.6094)	loss 3.1311 (2.8294)	grad_norm 1.7827 (2.6818/1.2260)	mem 24308MB
[2025-01-19 03:40:31 internimage_s_1k_224] (main.py 510): INFO Train: [251/300][310/312]	eta 0:00:01 lr 0.000285	time 0.5684 (0.6148)	model_time 0.5683 (0.6081)	loss 1.9315 (2.8326)	grad_norm 3.1338 (2.7068/1.3003)	mem 24308MB
[2025-01-19 03:40:32 internimage_s_1k_224] (main.py 519): INFO EPOCH 251 training takes 0:03:11
[2025-01-19 03:40:32 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_251.pth saving......
[2025-01-19 03:40:34 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_251.pth saved !!!
[2025-01-19 03:40:42 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.344 (8.344)	Loss 0.7245 (0.7245)	Acc@1 85.278 (85.278)	Acc@5 97.754 (97.754)	Mem 24308MB
[2025-01-19 03:40:46 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.073)	Loss 0.9204 (0.8015)	Acc@1 79.810 (83.521)	Acc@5 95.630 (96.686)	Mem 24308MB
[2025-01-19 03:40:46 internimage_s_1k_224] (main.py 575): INFO [Epoch:251] * Acc@1 83.371 Acc@5 96.683
[2025-01-19 03:40:46 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.4%
[2025-01-19 03:40:46 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.42%
[2025-01-19 03:40:55 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.026 (9.026)	Loss 0.7003 (0.7003)	Acc@1 85.498 (85.498)	Acc@5 97.778 (97.778)	Mem 24308MB
[2025-01-19 03:40:59 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.228)	Loss 0.8908 (0.7758)	Acc@1 79.419 (83.514)	Acc@5 95.996 (96.702)	Mem 24308MB
[2025-01-19 03:40:59 internimage_s_1k_224] (main.py 575): INFO [Epoch:251] * Acc@1 83.393 Acc@5 96.727
[2025-01-19 03:40:59 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.4%
[2025-01-19 03:41:00 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:41:02 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:41:02 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.39%
[2025-01-19 03:41:04 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][0/312]	eta 0:12:01 lr 0.000285	time 2.3113 (2.3113)	model_time 0.6051 (0.6051)	loss 2.4114 (2.4114)	grad_norm 2.5928 (2.5928/0.0000)	mem 24308MB
[2025-01-19 03:41:10 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][10/312]	eta 0:03:49 lr 0.000285	time 0.5827 (0.7609)	model_time 0.5825 (0.6053)	loss 3.1737 (2.8617)	grad_norm 1.2502 (3.4525/1.8479)	mem 24308MB
[2025-01-19 03:41:16 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][20/312]	eta 0:03:19 lr 0.000284	time 0.6086 (0.6842)	model_time 0.6084 (0.6026)	loss 2.1867 (2.7998)	grad_norm 1.6857 (3.4517/1.5835)	mem 24308MB
[2025-01-19 03:41:22 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][30/312]	eta 0:03:05 lr 0.000284	time 0.5734 (0.6562)	model_time 0.5733 (0.6008)	loss 3.0473 (2.8602)	grad_norm 1.2850 (3.0681/1.4758)	mem 24308MB
[2025-01-19 03:41:28 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][40/312]	eta 0:02:54 lr 0.000284	time 0.5852 (0.6409)	model_time 0.5848 (0.5990)	loss 3.1830 (2.8852)	grad_norm 2.5445 (2.9721/1.3338)	mem 24308MB
[2025-01-19 03:41:34 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][50/312]	eta 0:02:45 lr 0.000283	time 0.6188 (0.6331)	model_time 0.6184 (0.5993)	loss 2.9447 (2.8533)	grad_norm 2.8814 (2.8586/1.2956)	mem 24308MB
[2025-01-19 03:41:40 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][60/312]	eta 0:02:38 lr 0.000283	time 0.6243 (0.6290)	model_time 0.6241 (0.6007)	loss 2.7615 (2.8789)	grad_norm 2.7101 (2.7830/1.2251)	mem 24308MB
[2025-01-19 03:41:46 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][70/312]	eta 0:02:31 lr 0.000283	time 0.5850 (0.6251)	model_time 0.5845 (0.6007)	loss 3.1189 (2.8608)	grad_norm 4.8868 (2.8461/1.2456)	mem 24308MB
[2025-01-19 03:41:52 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][80/312]	eta 0:02:24 lr 0.000282	time 0.5932 (0.6245)	model_time 0.5927 (0.6030)	loss 2.8898 (2.8783)	grad_norm 1.0398 (2.9429/1.3462)	mem 24308MB
[2025-01-19 03:41:59 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][90/312]	eta 0:02:18 lr 0.000282	time 0.5966 (0.6252)	model_time 0.5964 (0.6061)	loss 2.3227 (2.8678)	grad_norm 1.7291 (2.9826/1.3638)	mem 24308MB
[2025-01-19 03:42:05 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][100/312]	eta 0:02:12 lr 0.000282	time 0.5867 (0.6234)	model_time 0.5863 (0.6062)	loss 3.5655 (2.8726)	grad_norm 1.9010 (2.9234/1.3559)	mem 24308MB
[2025-01-19 03:42:11 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][110/312]	eta 0:02:06 lr 0.000281	time 0.5725 (0.6245)	model_time 0.5720 (0.6087)	loss 3.2030 (2.8764)	grad_norm 1.8732 (2.8551/1.3411)	mem 24308MB
[2025-01-19 03:42:17 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][120/312]	eta 0:01:59 lr 0.000281	time 0.5848 (0.6220)	model_time 0.5842 (0.6075)	loss 2.7757 (2.8703)	grad_norm 2.7712 (2.7862/1.3146)	mem 24308MB
[2025-01-19 03:42:23 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][130/312]	eta 0:01:52 lr 0.000281	time 0.5852 (0.6206)	model_time 0.5851 (0.6072)	loss 2.3777 (2.8767)	grad_norm 1.6448 (2.7726/1.2862)	mem 24308MB
[2025-01-19 03:42:29 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][140/312]	eta 0:01:46 lr 0.000280	time 0.6027 (0.6200)	model_time 0.6022 (0.6075)	loss 3.3660 (2.8801)	grad_norm 1.5377 (2.7208/1.2648)	mem 24308MB
[2025-01-19 03:42:35 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][150/312]	eta 0:01:40 lr 0.000280	time 0.5774 (0.6182)	model_time 0.5769 (0.6066)	loss 1.6557 (2.8688)	grad_norm 3.0592 (2.7287/1.2346)	mem 24308MB
[2025-01-19 03:42:41 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][160/312]	eta 0:01:33 lr 0.000280	time 0.5793 (0.6167)	model_time 0.5788 (0.6058)	loss 2.2004 (2.8588)	grad_norm 6.3516 (2.7847/1.2448)	mem 24308MB
[2025-01-19 03:42:47 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][170/312]	eta 0:01:27 lr 0.000279	time 0.5891 (0.6153)	model_time 0.5889 (0.6049)	loss 2.9659 (2.8491)	grad_norm 2.6140 (2.8187/1.2383)	mem 24308MB
[2025-01-19 03:42:53 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][180/312]	eta 0:01:21 lr 0.000279	time 0.7214 (0.6156)	model_time 0.7213 (0.6058)	loss 3.0486 (2.8327)	grad_norm 2.0504 (2.8142/1.2375)	mem 24308MB
[2025-01-19 03:43:00 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][190/312]	eta 0:01:15 lr 0.000279	time 0.6279 (0.6160)	model_time 0.6277 (0.6067)	loss 1.8957 (2.8381)	grad_norm 2.1755 (2.7847/1.2180)	mem 24308MB
[2025-01-19 03:43:06 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][200/312]	eta 0:01:08 lr 0.000279	time 0.5727 (0.6159)	model_time 0.5725 (0.6070)	loss 3.1079 (2.8352)	grad_norm 2.6865 (2.7862/1.2040)	mem 24308MB
[2025-01-19 03:43:12 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][210/312]	eta 0:01:02 lr 0.000278	time 0.6024 (0.6171)	model_time 0.6022 (0.6086)	loss 3.0754 (2.8373)	grad_norm 2.5216 (2.7721/1.1961)	mem 24308MB
[2025-01-19 03:43:18 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][220/312]	eta 0:00:56 lr 0.000278	time 0.5777 (0.6164)	model_time 0.5775 (0.6083)	loss 3.1549 (2.8392)	grad_norm 2.7651 (2.7739/1.1938)	mem 24308MB
[2025-01-19 03:43:24 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][230/312]	eta 0:00:50 lr 0.000278	time 0.5980 (0.6162)	model_time 0.5975 (0.6084)	loss 2.1461 (2.8364)	grad_norm 1.7967 (2.7531/1.1960)	mem 24308MB
[2025-01-19 03:43:30 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][240/312]	eta 0:00:44 lr 0.000277	time 0.6062 (0.6154)	model_time 0.6056 (0.6080)	loss 2.9813 (2.8409)	grad_norm 4.7097 (2.7528/1.1886)	mem 24308MB
[2025-01-19 03:43:36 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][250/312]	eta 0:00:38 lr 0.000277	time 0.5952 (0.6151)	model_time 0.5950 (0.6079)	loss 2.1471 (2.8431)	grad_norm 3.5890 (2.7577/1.1783)	mem 24308MB
[2025-01-19 03:43:42 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][260/312]	eta 0:00:31 lr 0.000277	time 0.6518 (0.6152)	model_time 0.6517 (0.6083)	loss 2.5424 (2.8400)	grad_norm 3.6825 (2.7341/1.1666)	mem 24308MB
[2025-01-19 03:43:48 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][270/312]	eta 0:00:25 lr 0.000276	time 0.5904 (0.6141)	model_time 0.5902 (0.6074)	loss 3.0341 (2.8308)	grad_norm 3.1587 (2.7197/1.1539)	mem 24308MB
[2025-01-19 03:43:54 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][280/312]	eta 0:00:19 lr 0.000276	time 0.5799 (0.6137)	model_time 0.5794 (0.6072)	loss 2.9230 (2.8385)	grad_norm 5.0290 (2.7298/1.1661)	mem 24308MB
[2025-01-19 03:44:00 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][290/312]	eta 0:00:13 lr 0.000276	time 0.6211 (0.6131)	model_time 0.6208 (0.6069)	loss 2.3709 (2.8403)	grad_norm 3.5619 (2.7371/1.1618)	mem 24308MB
[2025-01-19 03:44:06 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][300/312]	eta 0:00:07 lr 0.000275	time 0.6373 (0.6125)	model_time 0.6372 (0.6064)	loss 3.2578 (2.8507)	grad_norm 3.1610 (2.7432/1.1622)	mem 24308MB
[2025-01-19 03:44:12 internimage_s_1k_224] (main.py 510): INFO Train: [252/300][310/312]	eta 0:00:01 lr 0.000275	time 0.6420 (0.6120)	model_time 0.6419 (0.6061)	loss 3.1746 (2.8452)	grad_norm 2.4886 (2.7036/1.1150)	mem 24308MB
[2025-01-19 03:44:13 internimage_s_1k_224] (main.py 519): INFO EPOCH 252 training takes 0:03:10
[2025-01-19 03:44:13 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_252.pth saving......
[2025-01-19 03:44:15 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_252.pth saved !!!
[2025-01-19 03:44:22 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.767 (7.767)	Loss 0.7087 (0.7087)	Acc@1 85.425 (85.425)	Acc@5 97.510 (97.510)	Mem 24308MB
[2025-01-19 03:44:26 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.052)	Loss 0.9008 (0.7885)	Acc@1 79.980 (83.536)	Acc@5 95.898 (96.686)	Mem 24308MB
[2025-01-19 03:44:26 internimage_s_1k_224] (main.py 575): INFO [Epoch:252] * Acc@1 83.399 Acc@5 96.683
[2025-01-19 03:44:26 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.4%
[2025-01-19 03:44:26 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.42%
[2025-01-19 03:44:44 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 18.054 (18.054)	Loss 0.6999 (0.6999)	Acc@1 85.522 (85.522)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 03:44:53 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (2.398)	Loss 0.8899 (0.7753)	Acc@1 79.468 (83.543)	Acc@5 96.094 (96.715)	Mem 24308MB
[2025-01-19 03:44:53 internimage_s_1k_224] (main.py 575): INFO [Epoch:252] * Acc@1 83.417 Acc@5 96.739
[2025-01-19 03:44:53 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.4%
[2025-01-19 03:44:53 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:44:55 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:44:55 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.42%
[2025-01-19 03:44:57 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][0/312]	eta 0:11:40 lr 0.000275	time 2.2456 (2.2456)	model_time 0.6063 (0.6063)	loss 3.1606 (3.1606)	grad_norm 2.0226 (2.0226/0.0000)	mem 24308MB
[2025-01-19 03:45:04 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][10/312]	eta 0:03:49 lr 0.000275	time 0.6618 (0.7586)	model_time 0.6616 (0.6094)	loss 2.5434 (2.6934)	grad_norm 1.3121 (2.3901/0.8784)	mem 24308MB
[2025-01-19 03:45:10 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][20/312]	eta 0:03:24 lr 0.000274	time 0.6779 (0.6991)	model_time 0.6774 (0.6207)	loss 2.5306 (2.8022)	grad_norm 1.4185 (2.3353/0.7526)	mem 24308MB
[2025-01-19 03:45:16 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][30/312]	eta 0:03:09 lr 0.000274	time 0.6927 (0.6703)	model_time 0.6925 (0.6171)	loss 2.2593 (2.7567)	grad_norm 2.0764 (2.3459/0.6990)	mem 24308MB
[2025-01-19 03:45:22 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][40/312]	eta 0:02:59 lr 0.000274	time 0.6607 (0.6599)	model_time 0.6605 (0.6197)	loss 2.5281 (2.6761)	grad_norm 1.7295 (2.2548/0.8029)	mem 24308MB
[2025-01-19 03:45:28 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][50/312]	eta 0:02:49 lr 0.000273	time 0.6067 (0.6469)	model_time 0.6066 (0.6145)	loss 3.2788 (2.7361)	grad_norm 3.4098 (2.3580/0.8453)	mem 24308MB
[2025-01-19 03:45:34 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][60/312]	eta 0:02:41 lr 0.000273	time 0.5857 (0.6404)	model_time 0.5856 (0.6132)	loss 2.6741 (2.7523)	grad_norm 2.5766 (2.7604/1.4659)	mem 24308MB
[2025-01-19 03:45:40 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][70/312]	eta 0:02:33 lr 0.000273	time 0.5754 (0.6352)	model_time 0.5752 (0.6118)	loss 2.9215 (2.7833)	grad_norm 7.8088 (2.9852/1.6782)	mem 24308MB
[2025-01-19 03:45:46 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][80/312]	eta 0:02:26 lr 0.000273	time 0.6828 (0.6313)	model_time 0.6822 (0.6107)	loss 3.1652 (2.7890)	grad_norm 2.1121 (3.0634/1.6471)	mem 24308MB
[2025-01-19 03:45:52 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][90/312]	eta 0:02:19 lr 0.000272	time 0.5738 (0.6276)	model_time 0.5734 (0.6092)	loss 2.9324 (2.7989)	grad_norm 1.7481 (2.9378/1.6017)	mem 24308MB
[2025-01-19 03:45:58 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][100/312]	eta 0:02:12 lr 0.000272	time 0.5879 (0.6248)	model_time 0.5874 (0.6082)	loss 2.9140 (2.7951)	grad_norm 1.4451 (2.8479/1.5475)	mem 24308MB
[2025-01-19 03:46:04 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][110/312]	eta 0:02:05 lr 0.000272	time 0.5781 (0.6224)	model_time 0.5779 (0.6073)	loss 2.8189 (2.8164)	grad_norm 1.9956 (2.8206/1.4998)	mem 24308MB
[2025-01-19 03:46:11 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][120/312]	eta 0:01:59 lr 0.000271	time 0.7224 (0.6236)	model_time 0.7223 (0.6097)	loss 2.6913 (2.8086)	grad_norm 5.3689 (2.7876/1.4780)	mem 24308MB
[2025-01-19 03:46:17 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][130/312]	eta 0:01:53 lr 0.000271	time 0.6636 (0.6236)	model_time 0.6634 (0.6107)	loss 2.9844 (2.8231)	grad_norm 1.7305 (2.8447/1.5023)	mem 24308MB
[2025-01-19 03:46:23 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][140/312]	eta 0:01:47 lr 0.000271	time 0.6748 (0.6239)	model_time 0.6746 (0.6119)	loss 2.7676 (2.8176)	grad_norm 4.3619 (2.9172/1.5161)	mem 24308MB
[2025-01-19 03:46:29 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][150/312]	eta 0:01:40 lr 0.000270	time 0.5946 (0.6220)	model_time 0.5944 (0.6108)	loss 2.0956 (2.8084)	grad_norm 1.5799 (2.8679/1.4923)	mem 24308MB
[2025-01-19 03:46:35 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][160/312]	eta 0:01:34 lr 0.000270	time 0.6689 (0.6223)	model_time 0.6685 (0.6117)	loss 2.9140 (2.8078)	grad_norm 1.3480 (2.8115/1.4724)	mem 24308MB
[2025-01-19 03:46:41 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][170/312]	eta 0:01:28 lr 0.000270	time 0.5901 (0.6206)	model_time 0.5899 (0.6107)	loss 3.4160 (2.8010)	grad_norm 3.2323 (2.7839/1.4439)	mem 24308MB
[2025-01-19 03:46:47 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][180/312]	eta 0:01:21 lr 0.000269	time 0.5799 (0.6197)	model_time 0.5795 (0.6103)	loss 3.4456 (2.7883)	grad_norm 3.1762 (2.7833/1.4192)	mem 24308MB
[2025-01-19 03:46:53 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][190/312]	eta 0:01:15 lr 0.000269	time 0.5841 (0.6188)	model_time 0.5840 (0.6099)	loss 2.9237 (2.7932)	grad_norm 2.1514 (2.7639/1.3999)	mem 24308MB
[2025-01-19 03:46:59 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][200/312]	eta 0:01:09 lr 0.000269	time 0.6897 (0.6180)	model_time 0.6895 (0.6095)	loss 3.3490 (2.8013)	grad_norm 2.0863 (2.7568/1.3823)	mem 24308MB
[2025-01-19 03:47:05 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][210/312]	eta 0:01:02 lr 0.000268	time 0.6792 (0.6169)	model_time 0.6789 (0.6088)	loss 2.6984 (2.7928)	grad_norm 4.0742 (2.7438/1.3746)	mem 24308MB
[2025-01-19 03:47:11 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][220/312]	eta 0:00:56 lr 0.000268	time 0.5903 (0.6159)	model_time 0.5901 (0.6082)	loss 2.6819 (2.7932)	grad_norm 2.8661 (2.7268/1.3638)	mem 24308MB
[2025-01-19 03:47:17 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][230/312]	eta 0:00:50 lr 0.000268	time 0.5992 (0.6154)	model_time 0.5991 (0.6079)	loss 3.4928 (2.7991)	grad_norm 1.9098 (2.7416/1.3603)	mem 24308MB
[2025-01-19 03:47:24 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][240/312]	eta 0:00:44 lr 0.000268	time 0.7084 (0.6161)	model_time 0.7081 (0.6090)	loss 1.8795 (2.8011)	grad_norm 3.8401 (2.7722/1.3705)	mem 24308MB
[2025-01-19 03:47:30 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][250/312]	eta 0:00:38 lr 0.000267	time 0.5917 (0.6158)	model_time 0.5913 (0.6089)	loss 3.3132 (2.8045)	grad_norm 3.5512 (2.7700/1.3589)	mem 24308MB
[2025-01-19 03:47:36 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][260/312]	eta 0:00:32 lr 0.000267	time 0.6327 (0.6167)	model_time 0.6323 (0.6101)	loss 3.6036 (2.8116)	grad_norm 2.8200 (2.7659/1.3481)	mem 24308MB
[2025-01-19 03:47:42 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][270/312]	eta 0:00:25 lr 0.000267	time 0.6032 (0.6161)	model_time 0.6031 (0.6097)	loss 2.9549 (2.8134)	grad_norm 5.7743 (2.8209/1.3842)	mem 24308MB
[2025-01-19 03:47:48 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][280/312]	eta 0:00:19 lr 0.000266	time 0.5804 (0.6158)	model_time 0.5799 (0.6096)	loss 2.8726 (2.8176)	grad_norm 5.1401 (2.8346/1.3735)	mem 24308MB
[2025-01-19 03:47:54 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][290/312]	eta 0:00:13 lr 0.000266	time 0.5774 (0.6153)	model_time 0.5773 (0.6094)	loss 3.0973 (2.8276)	grad_norm 1.9190 (2.8329/1.3610)	mem 24308MB
[2025-01-19 03:48:00 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][300/312]	eta 0:00:07 lr 0.000266	time 0.6325 (0.6147)	model_time 0.6324 (0.6089)	loss 1.9773 (2.8321)	grad_norm 3.1526 (2.8684/1.3904)	mem 24308MB
[2025-01-19 03:48:06 internimage_s_1k_224] (main.py 510): INFO Train: [253/300][310/312]	eta 0:00:01 lr 0.000265	time 0.5702 (0.6138)	model_time 0.5701 (0.6082)	loss 2.7408 (2.8392)	grad_norm 2.6854 (2.8936/1.3984)	mem 24308MB
[2025-01-19 03:48:07 internimage_s_1k_224] (main.py 519): INFO EPOCH 253 training takes 0:03:11
[2025-01-19 03:48:07 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_253.pth saving......
[2025-01-19 03:48:09 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_253.pth saved !!!
[2025-01-19 03:48:16 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.586 (7.586)	Loss 0.7143 (0.7143)	Acc@1 85.645 (85.645)	Acc@5 97.607 (97.607)	Mem 24308MB
[2025-01-19 03:48:20 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.134 (1.016)	Loss 0.9051 (0.7959)	Acc@1 79.639 (83.576)	Acc@5 95.776 (96.682)	Mem 24308MB
[2025-01-19 03:48:20 internimage_s_1k_224] (main.py 575): INFO [Epoch:253] * Acc@1 83.395 Acc@5 96.685
[2025-01-19 03:48:20 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.4%
[2025-01-19 03:48:20 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.42%
[2025-01-19 03:48:29 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.206 (9.206)	Loss 0.6998 (0.6998)	Acc@1 85.547 (85.547)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 03:48:34 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.246)	Loss 0.8891 (0.7748)	Acc@1 79.419 (83.556)	Acc@5 96.143 (96.724)	Mem 24308MB
[2025-01-19 03:48:34 internimage_s_1k_224] (main.py 575): INFO [Epoch:253] * Acc@1 83.431 Acc@5 96.741
[2025-01-19 03:48:34 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.4%
[2025-01-19 03:48:34 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:48:36 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:48:36 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.43%
[2025-01-19 03:48:39 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][0/312]	eta 0:11:47 lr 0.000265	time 2.2687 (2.2687)	model_time 0.6187 (0.6187)	loss 3.3471 (3.3471)	grad_norm 1.3097 (1.3097/0.0000)	mem 24308MB
[2025-01-19 03:48:44 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][10/312]	eta 0:03:43 lr 0.000265	time 0.5878 (0.7395)	model_time 0.5876 (0.5893)	loss 2.2789 (2.9298)	grad_norm 2.3151 (2.1903/0.4995)	mem 24308MB
[2025-01-19 03:48:50 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][20/312]	eta 0:03:17 lr 0.000265	time 0.6704 (0.6771)	model_time 0.6699 (0.5982)	loss 3.2709 (2.8574)	grad_norm 2.8468 (2.1170/0.4987)	mem 24308MB
[2025-01-19 03:48:56 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][30/312]	eta 0:03:03 lr 0.000264	time 0.5837 (0.6499)	model_time 0.5836 (0.5964)	loss 3.1676 (2.8547)	grad_norm 2.9064 (2.2907/0.7307)	mem 24308MB
[2025-01-19 03:49:03 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][40/312]	eta 0:02:55 lr 0.000264	time 0.6838 (0.6442)	model_time 0.6833 (0.6036)	loss 3.0853 (2.8570)	grad_norm 3.2128 (2.5284/0.9699)	mem 24308MB
[2025-01-19 03:49:09 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][50/312]	eta 0:02:48 lr 0.000264	time 0.8594 (0.6429)	model_time 0.8592 (0.6102)	loss 2.8936 (2.8113)	grad_norm 2.3001 (2.6973/1.0746)	mem 24308MB
[2025-01-19 03:49:15 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][60/312]	eta 0:02:40 lr 0.000263	time 0.6979 (0.6381)	model_time 0.6978 (0.6107)	loss 3.4121 (2.8281)	grad_norm 2.4411 (2.7354/1.1419)	mem 24308MB
[2025-01-19 03:49:21 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][70/312]	eta 0:02:34 lr 0.000263	time 0.5866 (0.6368)	model_time 0.5861 (0.6132)	loss 3.4046 (2.8257)	grad_norm 3.2144 (2.7313/1.1809)	mem 24308MB
[2025-01-19 03:49:27 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][80/312]	eta 0:02:26 lr 0.000263	time 0.5813 (0.6325)	model_time 0.5812 (0.6118)	loss 2.9224 (2.8362)	grad_norm 1.5128 (2.7557/1.2702)	mem 24308MB
[2025-01-19 03:49:34 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][90/312]	eta 0:02:19 lr 0.000263	time 0.5857 (0.6299)	model_time 0.5851 (0.6114)	loss 3.1985 (2.8333)	grad_norm 1.7219 (2.8623/1.3753)	mem 24308MB
[2025-01-19 03:49:40 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][100/312]	eta 0:02:13 lr 0.000262	time 0.5763 (0.6285)	model_time 0.5761 (0.6118)	loss 2.9688 (2.8359)	grad_norm 1.3318 (2.8624/1.3409)	mem 24308MB
[2025-01-19 03:49:46 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][110/312]	eta 0:02:06 lr 0.000262	time 0.6695 (0.6263)	model_time 0.6691 (0.6111)	loss 3.0615 (2.8452)	grad_norm 4.1305 (2.9080/1.3344)	mem 24308MB
[2025-01-19 03:49:52 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][120/312]	eta 0:01:59 lr 0.000262	time 0.5901 (0.6243)	model_time 0.5900 (0.6103)	loss 2.4437 (2.8612)	grad_norm 2.9656 (2.8885/1.3070)	mem 24308MB
[2025-01-19 03:49:58 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][130/312]	eta 0:01:53 lr 0.000261	time 0.5917 (0.6219)	model_time 0.5915 (0.6090)	loss 2.5666 (2.8713)	grad_norm 1.2314 (2.8657/1.2938)	mem 24308MB
[2025-01-19 03:50:04 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][140/312]	eta 0:01:46 lr 0.000261	time 0.5883 (0.6201)	model_time 0.5881 (0.6079)	loss 2.2451 (2.8585)	grad_norm 2.2866 (2.8036/1.2787)	mem 24308MB
[2025-01-19 03:50:10 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][150/312]	eta 0:01:40 lr 0.000261	time 0.5973 (0.6189)	model_time 0.5845 (0.6074)	loss 2.7953 (2.8580)	grad_norm 1.7630 (2.7463/1.2651)	mem 24308MB
[2025-01-19 03:50:16 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][160/312]	eta 0:01:33 lr 0.000260	time 0.6713 (0.6182)	model_time 0.6711 (0.6074)	loss 2.0494 (2.8410)	grad_norm 3.4435 (2.7487/1.2668)	mem 24308MB
[2025-01-19 03:50:22 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][170/312]	eta 0:01:27 lr 0.000260	time 0.6671 (0.6185)	model_time 0.6669 (0.6084)	loss 3.2706 (2.8484)	grad_norm 2.1051 (2.7510/1.2475)	mem 24308MB
[2025-01-19 03:50:28 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][180/312]	eta 0:01:21 lr 0.000260	time 0.7026 (0.6182)	model_time 0.7021 (0.6086)	loss 3.3687 (2.8582)	grad_norm 2.5404 (2.7651/1.2793)	mem 24308MB
[2025-01-19 03:50:34 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][190/312]	eta 0:01:15 lr 0.000260	time 0.6403 (0.6177)	model_time 0.6401 (0.6085)	loss 2.8042 (2.8595)	grad_norm 1.7295 (2.7703/1.2655)	mem 24308MB
[2025-01-19 03:50:40 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][200/312]	eta 0:01:09 lr 0.000259	time 0.5908 (0.6169)	model_time 0.5905 (0.6082)	loss 2.4947 (2.8642)	grad_norm 1.5538 (2.7626/1.2445)	mem 24308MB
[2025-01-19 03:50:46 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][210/312]	eta 0:01:02 lr 0.000259	time 0.5785 (0.6163)	model_time 0.5780 (0.6080)	loss 3.1305 (2.8695)	grad_norm 1.8123 (2.7316/1.2303)	mem 24308MB
[2025-01-19 03:50:52 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][220/312]	eta 0:00:56 lr 0.000259	time 0.5936 (0.6163)	model_time 0.5934 (0.6084)	loss 3.0175 (2.8670)	grad_norm 1.7258 (2.7433/1.2266)	mem 24308MB
[2025-01-19 03:50:59 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][230/312]	eta 0:00:50 lr 0.000258	time 0.6743 (0.6159)	model_time 0.6741 (0.6083)	loss 3.0179 (2.8658)	grad_norm 6.3639 (2.7979/1.2531)	mem 24308MB
[2025-01-19 03:51:05 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][240/312]	eta 0:00:44 lr 0.000258	time 0.6251 (0.6157)	model_time 0.6246 (0.6084)	loss 3.0130 (2.8673)	grad_norm 2.4856 (2.8078/1.2584)	mem 24308MB
[2025-01-19 03:51:11 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][250/312]	eta 0:00:38 lr 0.000258	time 0.5846 (0.6145)	model_time 0.5844 (0.6075)	loss 2.3055 (2.8636)	grad_norm 3.6581 (2.8135/1.2636)	mem 24308MB
[2025-01-19 03:51:16 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][260/312]	eta 0:00:31 lr 0.000257	time 0.5807 (0.6138)	model_time 0.5802 (0.6070)	loss 3.0460 (2.8591)	grad_norm 3.6931 (2.8022/1.2485)	mem 24308MB
[2025-01-19 03:51:22 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][270/312]	eta 0:00:25 lr 0.000257	time 0.5810 (0.6133)	model_time 0.5807 (0.6067)	loss 3.1134 (2.8670)	grad_norm 1.8318 (2.7817/1.2364)	mem 24308MB
[2025-01-19 03:51:28 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][280/312]	eta 0:00:19 lr 0.000257	time 0.5763 (0.6129)	model_time 0.5758 (0.6066)	loss 3.1689 (2.8612)	grad_norm 1.4475 (2.7604/1.2433)	mem 24308MB
[2025-01-19 03:51:35 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][290/312]	eta 0:00:13 lr 0.000256	time 0.6692 (0.6136)	model_time 0.6687 (0.6075)	loss 1.6576 (2.8504)	grad_norm 2.3202 (2.7551/1.2357)	mem 24308MB
[2025-01-19 03:51:41 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][300/312]	eta 0:00:07 lr 0.000256	time 0.5689 (0.6131)	model_time 0.5688 (0.6072)	loss 2.7395 (2.8479)	grad_norm 3.5227 (2.7502/1.2255)	mem 24308MB
[2025-01-19 03:51:47 internimage_s_1k_224] (main.py 510): INFO Train: [254/300][310/312]	eta 0:00:01 lr 0.000256	time 0.5681 (0.6125)	model_time 0.5680 (0.6067)	loss 2.1074 (2.8399)	grad_norm 2.6132 (2.7595/1.2294)	mem 24308MB
[2025-01-19 03:51:47 internimage_s_1k_224] (main.py 519): INFO EPOCH 254 training takes 0:03:11
[2025-01-19 03:51:47 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_254.pth saving......
[2025-01-19 03:51:49 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_254.pth saved !!!
[2025-01-19 03:51:57 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.794 (7.794)	Loss 0.7002 (0.7002)	Acc@1 85.522 (85.522)	Acc@5 97.559 (97.559)	Mem 24308MB
[2025-01-19 03:52:01 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.034)	Loss 0.8910 (0.7781)	Acc@1 80.127 (83.669)	Acc@5 95.972 (96.711)	Mem 24308MB
[2025-01-19 03:52:01 internimage_s_1k_224] (main.py 575): INFO [Epoch:254] * Acc@1 83.503 Acc@5 96.731
[2025-01-19 03:52:01 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.5%
[2025-01-19 03:52:01 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 03:52:03 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 03:52:03 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.50%
[2025-01-19 03:52:11 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.245 (8.245)	Loss 0.6996 (0.6996)	Acc@1 85.571 (85.571)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 03:52:15 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.081)	Loss 0.8881 (0.7743)	Acc@1 79.419 (83.589)	Acc@5 96.167 (96.722)	Mem 24308MB
[2025-01-19 03:52:15 internimage_s_1k_224] (main.py 575): INFO [Epoch:254] * Acc@1 83.465 Acc@5 96.737
[2025-01-19 03:52:15 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.5%
[2025-01-19 03:52:15 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:52:17 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:52:17 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.47%
[2025-01-19 03:52:20 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][0/312]	eta 0:12:06 lr 0.000256	time 2.3300 (2.3300)	model_time 0.6071 (0.6071)	loss 3.2920 (3.2920)	grad_norm 3.1138 (3.1138/0.0000)	mem 24308MB
[2025-01-19 03:52:26 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][10/312]	eta 0:03:50 lr 0.000256	time 0.5987 (0.7622)	model_time 0.5986 (0.6053)	loss 3.3463 (2.9703)	grad_norm 3.5697 (3.2589/1.4163)	mem 24308MB
[2025-01-19 03:52:32 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][20/312]	eta 0:03:20 lr 0.000255	time 0.5867 (0.6862)	model_time 0.5865 (0.6039)	loss 3.0361 (2.8599)	grad_norm 1.5506 (3.1072/1.4977)	mem 24308MB
[2025-01-19 03:52:38 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][30/312]	eta 0:03:07 lr 0.000255	time 0.5759 (0.6649)	model_time 0.5755 (0.6090)	loss 2.5055 (2.8294)	grad_norm 1.5950 (2.9221/1.4347)	mem 24308MB
[2025-01-19 03:52:44 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][40/312]	eta 0:02:56 lr 0.000255	time 0.6800 (0.6506)	model_time 0.6799 (0.6083)	loss 3.0874 (2.8239)	grad_norm 1.4665 (2.9338/1.3250)	mem 24308MB
[2025-01-19 03:52:50 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][50/312]	eta 0:02:48 lr 0.000254	time 0.6031 (0.6416)	model_time 0.6029 (0.6075)	loss 3.1866 (2.7981)	grad_norm 2.2039 (2.9401/1.2346)	mem 24308MB
[2025-01-19 03:52:56 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][60/312]	eta 0:02:39 lr 0.000254	time 0.5830 (0.6336)	model_time 0.5829 (0.6048)	loss 3.0360 (2.8087)	grad_norm 1.7380 (2.8105/1.2115)	mem 24308MB
[2025-01-19 03:53:02 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][70/312]	eta 0:02:32 lr 0.000254	time 0.6002 (0.6285)	model_time 0.6000 (0.6038)	loss 2.6004 (2.8333)	grad_norm 1.9085 (2.7465/1.1729)	mem 24308MB
[2025-01-19 03:53:08 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][80/312]	eta 0:02:25 lr 0.000253	time 0.6474 (0.6255)	model_time 0.6469 (0.6036)	loss 2.0071 (2.8054)	grad_norm 1.6855 (2.6579/1.1415)	mem 24308MB
[2025-01-19 03:53:14 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][90/312]	eta 0:02:18 lr 0.000253	time 0.5832 (0.6232)	model_time 0.5831 (0.6037)	loss 3.2571 (2.8154)	grad_norm 2.5477 (2.5923/1.1096)	mem 24308MB
[2025-01-19 03:53:20 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][100/312]	eta 0:02:12 lr 0.000253	time 0.7123 (0.6239)	model_time 0.7122 (0.6063)	loss 2.8754 (2.8018)	grad_norm 3.5261 (2.5935/1.1230)	mem 24308MB
[2025-01-19 03:53:26 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][110/312]	eta 0:02:05 lr 0.000253	time 0.5743 (0.6217)	model_time 0.5739 (0.6056)	loss 2.5927 (2.7959)	grad_norm 1.5569 (2.5654/1.1015)	mem 24308MB
[2025-01-19 03:53:32 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][120/312]	eta 0:01:59 lr 0.000252	time 0.7039 (0.6214)	model_time 0.7036 (0.6066)	loss 3.0854 (2.7910)	grad_norm 2.5788 (2.5591/1.0780)	mem 24308MB
[2025-01-19 03:53:39 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][130/312]	eta 0:01:52 lr 0.000252	time 0.5884 (0.6206)	model_time 0.5880 (0.6069)	loss 3.2792 (2.8040)	grad_norm 1.3857 (2.5874/1.0712)	mem 24308MB
[2025-01-19 03:53:45 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][140/312]	eta 0:01:46 lr 0.000252	time 0.5917 (0.6200)	model_time 0.5915 (0.6072)	loss 2.8646 (2.7918)	grad_norm 3.0732 (2.5832/1.0581)	mem 24308MB
[2025-01-19 03:53:51 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][150/312]	eta 0:01:40 lr 0.000251	time 0.5815 (0.6193)	model_time 0.5811 (0.6073)	loss 3.1807 (2.7940)	grad_norm 4.3350 (2.6391/1.1056)	mem 24308MB
[2025-01-19 03:53:57 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][160/312]	eta 0:01:33 lr 0.000251	time 0.5770 (0.6178)	model_time 0.5768 (0.6066)	loss 2.0567 (2.7902)	grad_norm 2.3965 (2.6965/1.1340)	mem 24308MB
[2025-01-19 03:54:03 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][170/312]	eta 0:01:27 lr 0.000251	time 0.5952 (0.6176)	model_time 0.5950 (0.6069)	loss 2.4032 (2.7815)	grad_norm 1.6210 (2.7345/1.1482)	mem 24308MB
[2025-01-19 03:54:09 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][180/312]	eta 0:01:21 lr 0.000250	time 0.5822 (0.6159)	model_time 0.5821 (0.6059)	loss 2.6652 (2.7907)	grad_norm 2.7825 (2.7034/1.1340)	mem 24308MB
[2025-01-19 03:54:15 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][190/312]	eta 0:01:15 lr 0.000250	time 0.6059 (0.6153)	model_time 0.6054 (0.6058)	loss 2.8190 (2.7916)	grad_norm 2.3308 (2.7270/1.1374)	mem 24308MB
[2025-01-19 03:54:21 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][200/312]	eta 0:01:08 lr 0.000250	time 0.6435 (0.6149)	model_time 0.6433 (0.6058)	loss 2.9515 (2.7906)	grad_norm 2.1102 (2.7129/1.1202)	mem 24308MB
[2025-01-19 03:54:27 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][210/312]	eta 0:01:02 lr 0.000250	time 0.6943 (0.6149)	model_time 0.6941 (0.6062)	loss 2.0152 (2.7776)	grad_norm 1.5616 (2.7349/1.1176)	mem 24308MB
[2025-01-19 03:54:33 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][220/312]	eta 0:00:56 lr 0.000249	time 0.5754 (0.6149)	model_time 0.5752 (0.6066)	loss 2.6346 (2.7746)	grad_norm 1.6519 (2.7385/1.1028)	mem 24308MB
[2025-01-19 03:54:39 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][230/312]	eta 0:00:50 lr 0.000249	time 0.5821 (0.6149)	model_time 0.5819 (0.6070)	loss 3.1637 (2.7767)	grad_norm 2.8625 (2.7547/1.1078)	mem 24308MB
[2025-01-19 03:54:45 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][240/312]	eta 0:00:44 lr 0.000249	time 0.5813 (0.6143)	model_time 0.5809 (0.6067)	loss 2.6118 (2.7783)	grad_norm 3.5962 (2.7595/1.1082)	mem 24308MB
[2025-01-19 03:54:52 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][250/312]	eta 0:00:38 lr 0.000248	time 0.5798 (0.6152)	model_time 0.5796 (0.6078)	loss 2.7208 (2.7965)	grad_norm 2.9730 (2.7646/1.0943)	mem 24308MB
[2025-01-19 03:54:58 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][260/312]	eta 0:00:31 lr 0.000248	time 0.5843 (0.6145)	model_time 0.5838 (0.6074)	loss 3.1933 (2.7973)	grad_norm 5.9250 (2.7913/1.1464)	mem 24308MB
[2025-01-19 03:55:04 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][270/312]	eta 0:00:25 lr 0.000248	time 0.5808 (0.6151)	model_time 0.5804 (0.6083)	loss 3.3018 (2.7985)	grad_norm 1.8391 (2.7828/1.1386)	mem 24308MB
[2025-01-19 03:55:10 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][280/312]	eta 0:00:19 lr 0.000247	time 0.5749 (0.6146)	model_time 0.5748 (0.6079)	loss 2.4356 (2.7922)	grad_norm 1.4579 (2.7685/1.1319)	mem 24308MB
[2025-01-19 03:55:16 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][290/312]	eta 0:00:13 lr 0.000247	time 0.5913 (0.6142)	model_time 0.5911 (0.6078)	loss 3.1021 (2.7963)	grad_norm 2.2077 (2.7563/1.1257)	mem 24308MB
[2025-01-19 03:55:22 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][300/312]	eta 0:00:07 lr 0.000247	time 0.5758 (0.6134)	model_time 0.5757 (0.6072)	loss 2.3205 (2.7977)	grad_norm 1.3924 (2.7532/1.1312)	mem 24308MB
[2025-01-19 03:55:28 internimage_s_1k_224] (main.py 510): INFO Train: [255/300][310/312]	eta 0:00:01 lr 0.000247	time 0.5693 (0.6123)	model_time 0.5692 (0.6063)	loss 3.2732 (2.7938)	grad_norm 1.5302 (2.7134/1.1059)	mem 24308MB
[2025-01-19 03:55:28 internimage_s_1k_224] (main.py 519): INFO EPOCH 255 training takes 0:03:10
[2025-01-19 03:55:28 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_255.pth saving......
[2025-01-19 03:55:30 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_255.pth saved !!!
[2025-01-19 03:55:38 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.773 (7.773)	Loss 0.7080 (0.7080)	Acc@1 85.498 (85.498)	Acc@5 97.729 (97.729)	Mem 24308MB
[2025-01-19 03:55:42 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.036)	Loss 0.9075 (0.7941)	Acc@1 79.614 (83.492)	Acc@5 95.972 (96.800)	Mem 24308MB
[2025-01-19 03:55:42 internimage_s_1k_224] (main.py 575): INFO [Epoch:255] * Acc@1 83.295 Acc@5 96.789
[2025-01-19 03:55:42 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.3%
[2025-01-19 03:55:42 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.50%
[2025-01-19 03:55:51 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.826 (8.826)	Loss 0.6991 (0.6991)	Acc@1 85.596 (85.596)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 03:55:55 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.202)	Loss 0.8871 (0.7737)	Acc@1 79.443 (83.600)	Acc@5 96.240 (96.729)	Mem 24308MB
[2025-01-19 03:55:55 internimage_s_1k_224] (main.py 575): INFO [Epoch:255] * Acc@1 83.473 Acc@5 96.747
[2025-01-19 03:55:55 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.5%
[2025-01-19 03:55:55 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:55:57 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:55:57 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.47%
[2025-01-19 03:56:00 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][0/312]	eta 0:12:19 lr 0.000246	time 2.3686 (2.3686)	model_time 0.6060 (0.6060)	loss 2.9538 (2.9538)	grad_norm 1.8265 (1.8265/0.0000)	mem 24308MB
[2025-01-19 03:56:06 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][10/312]	eta 0:03:47 lr 0.000246	time 0.5893 (0.7549)	model_time 0.5889 (0.5943)	loss 3.0579 (2.7773)	grad_norm 2.6111 (3.1210/0.9382)	mem 24308MB
[2025-01-19 03:56:12 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][20/312]	eta 0:03:18 lr 0.000246	time 0.5780 (0.6781)	model_time 0.5778 (0.5939)	loss 2.6665 (2.7564)	grad_norm 1.1984 (3.0633/1.0326)	mem 24308MB
[2025-01-19 03:56:18 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][30/312]	eta 0:03:06 lr 0.000246	time 0.5845 (0.6597)	model_time 0.5844 (0.6025)	loss 2.8512 (2.8112)	grad_norm 2.5827 (3.0829/1.0199)	mem 24308MB
[2025-01-19 03:56:24 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][40/312]	eta 0:02:56 lr 0.000245	time 0.6834 (0.6503)	model_time 0.6829 (0.6069)	loss 1.9001 (2.7802)	grad_norm 2.0399 (3.0197/1.1006)	mem 24308MB
[2025-01-19 03:56:30 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][50/312]	eta 0:02:47 lr 0.000245	time 0.6759 (0.6401)	model_time 0.6758 (0.6052)	loss 1.5931 (2.7776)	grad_norm 2.8355 (2.9546/1.0313)	mem 24308MB
[2025-01-19 03:56:36 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][60/312]	eta 0:02:40 lr 0.000245	time 0.6708 (0.6371)	model_time 0.6707 (0.6079)	loss 3.2988 (2.8062)	grad_norm 1.5068 (2.9525/1.0290)	mem 24308MB
[2025-01-19 03:56:42 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][70/312]	eta 0:02:32 lr 0.000244	time 0.6714 (0.6320)	model_time 0.6709 (0.6068)	loss 3.0731 (2.8180)	grad_norm 3.5898 (2.9030/1.0245)	mem 24308MB
[2025-01-19 03:56:48 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][80/312]	eta 0:02:26 lr 0.000244	time 0.5915 (0.6293)	model_time 0.5913 (0.6072)	loss 3.2657 (2.8438)	grad_norm 3.5909 (2.9120/1.0086)	mem 24308MB
[2025-01-19 03:56:54 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][90/312]	eta 0:02:19 lr 0.000244	time 0.6717 (0.6271)	model_time 0.6715 (0.6074)	loss 2.8486 (2.8442)	grad_norm 3.6532 (2.8752/1.0033)	mem 24308MB
[2025-01-19 03:57:01 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][100/312]	eta 0:02:12 lr 0.000244	time 0.5728 (0.6254)	model_time 0.5724 (0.6076)	loss 2.5164 (2.8591)	grad_norm 1.9136 (2.9181/1.0950)	mem 24308MB
[2025-01-19 03:57:06 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][110/312]	eta 0:02:05 lr 0.000243	time 0.5864 (0.6225)	model_time 0.5858 (0.6063)	loss 2.6208 (2.8561)	grad_norm 2.1153 (2.8329/1.0857)	mem 24308MB
[2025-01-19 03:57:12 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][120/312]	eta 0:01:59 lr 0.000243	time 0.5860 (0.6201)	model_time 0.5856 (0.6052)	loss 3.1796 (2.8531)	grad_norm 3.6447 (2.8286/1.0710)	mem 24308MB
[2025-01-19 03:57:18 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][130/312]	eta 0:01:52 lr 0.000243	time 0.5758 (0.6181)	model_time 0.5753 (0.6043)	loss 2.8165 (2.8590)	grad_norm 2.5775 (2.8122/1.0445)	mem 24308MB
[2025-01-19 03:57:24 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][140/312]	eta 0:01:46 lr 0.000242	time 0.6377 (0.6172)	model_time 0.6375 (0.6044)	loss 3.0197 (2.8525)	grad_norm 2.3572 (2.7997/1.0323)	mem 24308MB
[2025-01-19 03:57:31 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][150/312]	eta 0:01:40 lr 0.000242	time 0.6067 (0.6177)	model_time 0.6066 (0.6057)	loss 3.1561 (2.8629)	grad_norm 2.4414 (2.8512/1.0457)	mem 24308MB
[2025-01-19 03:57:37 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][160/312]	eta 0:01:33 lr 0.000242	time 0.5833 (0.6170)	model_time 0.5831 (0.6057)	loss 2.4455 (2.8481)	grad_norm 3.6073 (2.8288/1.0307)	mem 24308MB
[2025-01-19 03:57:43 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][170/312]	eta 0:01:27 lr 0.000241	time 0.5909 (0.6157)	model_time 0.5905 (0.6050)	loss 3.4378 (2.8421)	grad_norm 1.4683 (2.8052/1.0247)	mem 24308MB
[2025-01-19 03:57:49 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][180/312]	eta 0:01:21 lr 0.000241	time 0.6783 (0.6170)	model_time 0.6778 (0.6069)	loss 3.2296 (2.8474)	grad_norm 6.3105 (2.8632/1.1100)	mem 24308MB
[2025-01-19 03:57:55 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][190/312]	eta 0:01:15 lr 0.000241	time 0.5792 (0.6159)	model_time 0.5788 (0.6063)	loss 2.9026 (2.8336)	grad_norm 1.6163 (2.8811/1.1483)	mem 24308MB
[2025-01-19 03:58:01 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][200/312]	eta 0:01:08 lr 0.000241	time 0.5959 (0.6159)	model_time 0.5957 (0.6068)	loss 3.0701 (2.8303)	grad_norm 1.9300 (2.8560/1.1430)	mem 24308MB
[2025-01-19 03:58:07 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][210/312]	eta 0:01:02 lr 0.000240	time 0.6596 (0.6157)	model_time 0.6595 (0.6070)	loss 2.6881 (2.8292)	grad_norm 5.1692 (2.8691/1.1338)	mem 24308MB
[2025-01-19 03:58:13 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][220/312]	eta 0:00:56 lr 0.000240	time 0.5739 (0.6153)	model_time 0.5737 (0.6070)	loss 2.2192 (2.8363)	grad_norm 1.1043 (2.8583/1.1300)	mem 24308MB
[2025-01-19 03:58:19 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][230/312]	eta 0:00:50 lr 0.000240	time 0.5711 (0.6145)	model_time 0.5709 (0.6065)	loss 3.0795 (2.8163)	grad_norm 2.3701 (2.8350/1.1187)	mem 24308MB
[2025-01-19 03:58:25 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][240/312]	eta 0:00:44 lr 0.000239	time 0.5910 (0.6137)	model_time 0.5909 (0.6060)	loss 2.8991 (2.8248)	grad_norm 1.4943 (2.7969/1.1163)	mem 24308MB
[2025-01-19 03:58:31 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][250/312]	eta 0:00:38 lr 0.000239	time 0.5929 (0.6131)	model_time 0.5925 (0.6057)	loss 2.7245 (2.8221)	grad_norm 3.1883 (2.8135/1.1218)	mem 24308MB
[2025-01-19 03:58:37 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][260/312]	eta 0:00:31 lr 0.000239	time 0.5900 (0.6123)	model_time 0.5898 (0.6052)	loss 2.6634 (2.8236)	grad_norm 1.3116 (2.8180/1.1213)	mem 24308MB
[2025-01-19 03:58:44 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][270/312]	eta 0:00:25 lr 0.000239	time 0.6096 (0.6134)	model_time 0.6091 (0.6065)	loss 2.8362 (2.8198)	grad_norm 2.7816 (2.8158/1.1145)	mem 24308MB
[2025-01-19 03:58:50 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][280/312]	eta 0:00:19 lr 0.000238	time 0.5979 (0.6138)	model_time 0.5975 (0.6071)	loss 2.0972 (2.8154)	grad_norm 2.4818 (2.7941/1.1100)	mem 24308MB
[2025-01-19 03:58:56 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][290/312]	eta 0:00:13 lr 0.000238	time 0.6024 (0.6133)	model_time 0.6020 (0.6069)	loss 2.6723 (2.8204)	grad_norm 2.0751 (2.7845/1.0998)	mem 24308MB
[2025-01-19 03:59:02 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][300/312]	eta 0:00:07 lr 0.000238	time 0.5702 (0.6136)	model_time 0.5701 (0.6073)	loss 3.0741 (2.8111)	grad_norm 2.2036 (2.7841/1.1050)	mem 24308MB
[2025-01-19 03:59:08 internimage_s_1k_224] (main.py 510): INFO Train: [256/300][310/312]	eta 0:00:01 lr 0.000237	time 0.5851 (0.6128)	model_time 0.5850 (0.6068)	loss 2.4156 (2.8002)	grad_norm 1.5133 (2.7569/1.0995)	mem 24308MB
[2025-01-19 03:59:09 internimage_s_1k_224] (main.py 519): INFO EPOCH 256 training takes 0:03:11
[2025-01-19 03:59:09 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_256.pth saving......
[2025-01-19 03:59:10 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_256.pth saved !!!
[2025-01-19 03:59:18 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.954 (7.954)	Loss 0.7151 (0.7151)	Acc@1 85.425 (85.425)	Acc@5 97.705 (97.705)	Mem 24308MB
[2025-01-19 03:59:22 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.042)	Loss 0.9021 (0.7861)	Acc@1 80.029 (83.849)	Acc@5 95.898 (96.820)	Mem 24308MB
[2025-01-19 03:59:22 internimage_s_1k_224] (main.py 575): INFO [Epoch:256] * Acc@1 83.647 Acc@5 96.835
[2025-01-19 03:59:22 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.6%
[2025-01-19 03:59:22 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 03:59:24 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 03:59:24 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.65%
[2025-01-19 03:59:32 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.052 (8.052)	Loss 0.6989 (0.6989)	Acc@1 85.596 (85.596)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 03:59:36 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.057)	Loss 0.8862 (0.7732)	Acc@1 79.517 (83.629)	Acc@5 96.265 (96.722)	Mem 24308MB
[2025-01-19 03:59:36 internimage_s_1k_224] (main.py 575): INFO [Epoch:256] * Acc@1 83.493 Acc@5 96.743
[2025-01-19 03:59:36 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.5%
[2025-01-19 03:59:36 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 03:59:38 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 03:59:38 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.49%
[2025-01-19 03:59:40 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][0/312]	eta 0:10:41 lr 0.000237	time 2.0549 (2.0549)	model_time 0.5990 (0.5990)	loss 3.0047 (3.0047)	grad_norm 4.6028 (4.6028/0.0000)	mem 24308MB
[2025-01-19 03:59:46 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][10/312]	eta 0:03:44 lr 0.000237	time 0.5863 (0.7443)	model_time 0.5862 (0.6115)	loss 2.5486 (2.7492)	grad_norm 2.4575 (3.3915/1.2463)	mem 24308MB
[2025-01-19 03:59:52 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][20/312]	eta 0:03:16 lr 0.000237	time 0.5835 (0.6745)	model_time 0.5833 (0.6048)	loss 3.1696 (2.8074)	grad_norm 2.3486 (3.4050/1.2147)	mem 24308MB
[2025-01-19 03:59:59 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][30/312]	eta 0:03:05 lr 0.000237	time 0.6074 (0.6565)	model_time 0.6072 (0.6092)	loss 3.0943 (2.8228)	grad_norm 1.3248 (3.0696/1.2364)	mem 24308MB
[2025-01-19 04:00:04 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][40/312]	eta 0:02:54 lr 0.000236	time 0.5953 (0.6419)	model_time 0.5951 (0.6060)	loss 2.9387 (2.8186)	grad_norm 1.5103 (3.0599/1.2157)	mem 24308MB
[2025-01-19 04:00:10 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][50/312]	eta 0:02:45 lr 0.000236	time 0.5945 (0.6333)	model_time 0.5941 (0.6044)	loss 3.0939 (2.8299)	grad_norm 5.4229 (3.1352/1.2011)	mem 24308MB
[2025-01-19 04:00:16 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][60/312]	eta 0:02:38 lr 0.000236	time 0.6141 (0.6274)	model_time 0.6139 (0.6032)	loss 3.0651 (2.8251)	grad_norm 1.8514 (2.9874/1.2075)	mem 24308MB
[2025-01-19 04:00:22 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][70/312]	eta 0:02:30 lr 0.000235	time 0.5941 (0.6231)	model_time 0.5939 (0.6023)	loss 3.0548 (2.8386)	grad_norm 4.4707 (3.0040/1.2096)	mem 24308MB
[2025-01-19 04:00:29 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][80/312]	eta 0:02:24 lr 0.000235	time 0.7877 (0.6247)	model_time 0.7875 (0.6063)	loss 2.4290 (2.8497)	grad_norm 4.2545 (3.0712/1.2351)	mem 24308MB
[2025-01-19 04:00:35 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][90/312]	eta 0:02:18 lr 0.000235	time 0.5755 (0.6222)	model_time 0.5754 (0.6058)	loss 3.0619 (2.8338)	grad_norm 2.9704 (3.0813/1.1884)	mem 24308MB
[2025-01-19 04:00:41 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][100/312]	eta 0:02:11 lr 0.000234	time 0.6600 (0.6207)	model_time 0.6596 (0.6059)	loss 3.4162 (2.8347)	grad_norm 3.4684 (3.1170/1.1934)	mem 24308MB
[2025-01-19 04:00:47 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][110/312]	eta 0:02:05 lr 0.000234	time 0.5915 (0.6212)	model_time 0.5913 (0.6078)	loss 3.2969 (2.8276)	grad_norm 1.8381 (3.0263/1.1807)	mem 24308MB
[2025-01-19 04:00:53 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][120/312]	eta 0:01:58 lr 0.000234	time 0.5905 (0.6194)	model_time 0.5899 (0.6070)	loss 2.6971 (2.8437)	grad_norm 1.9913 (3.0228/1.2143)	mem 24308MB
[2025-01-19 04:00:59 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][130/312]	eta 0:01:52 lr 0.000234	time 0.5934 (0.6189)	model_time 0.5930 (0.6074)	loss 2.6385 (2.8360)	grad_norm 3.3150 (3.0332/1.1923)	mem 24308MB
[2025-01-19 04:01:05 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][140/312]	eta 0:01:46 lr 0.000233	time 0.5792 (0.6178)	model_time 0.5791 (0.6071)	loss 3.5057 (2.8429)	grad_norm 3.5806 (3.0237/1.1797)	mem 24308MB
[2025-01-19 04:01:11 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][150/312]	eta 0:01:40 lr 0.000233	time 0.5860 (0.6175)	model_time 0.5859 (0.6075)	loss 2.5894 (2.8577)	grad_norm 1.5720 (2.9535/1.1748)	mem 24308MB
[2025-01-19 04:01:17 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][160/312]	eta 0:01:33 lr 0.000233	time 0.6034 (0.6164)	model_time 0.6030 (0.6070)	loss 3.3338 (2.8538)	grad_norm 1.4270 (2.8893/1.1735)	mem 24308MB
[2025-01-19 04:01:23 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][170/312]	eta 0:01:27 lr 0.000232	time 0.5902 (0.6155)	model_time 0.5901 (0.6066)	loss 2.8479 (2.8402)	grad_norm 3.9850 (2.8752/1.1588)	mem 24308MB
[2025-01-19 04:01:29 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][180/312]	eta 0:01:21 lr 0.000232	time 0.5743 (0.6148)	model_time 0.5741 (0.6064)	loss 2.5016 (2.8277)	grad_norm 1.6478 (2.8374/1.1545)	mem 24308MB
[2025-01-19 04:01:35 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][190/312]	eta 0:01:14 lr 0.000232	time 0.5881 (0.6139)	model_time 0.5879 (0.6059)	loss 2.8955 (2.8204)	grad_norm 3.1984 (2.8099/1.1438)	mem 24308MB
[2025-01-19 04:01:42 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][200/312]	eta 0:01:08 lr 0.000232	time 0.6860 (0.6147)	model_time 0.6858 (0.6071)	loss 2.1322 (2.8179)	grad_norm 1.5977 (2.8263/1.1552)	mem 24308MB
[2025-01-19 04:01:48 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][210/312]	eta 0:01:02 lr 0.000231	time 0.5888 (0.6148)	model_time 0.5886 (0.6075)	loss 2.8962 (2.8318)	grad_norm 1.5663 (2.8112/1.1402)	mem 24308MB
[2025-01-19 04:01:54 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][220/312]	eta 0:00:56 lr 0.000231	time 0.6682 (0.6145)	model_time 0.6677 (0.6075)	loss 2.8594 (2.8261)	grad_norm 2.5258 (2.7849/1.1306)	mem 24308MB
[2025-01-19 04:02:00 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][230/312]	eta 0:00:50 lr 0.000231	time 0.5866 (0.6149)	model_time 0.5864 (0.6082)	loss 1.7893 (2.8307)	grad_norm 4.1448 (2.8068/1.1532)	mem 24308MB
[2025-01-19 04:02:06 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][240/312]	eta 0:00:44 lr 0.000230	time 0.5876 (0.6140)	model_time 0.5872 (0.6076)	loss 2.6976 (2.8264)	grad_norm 1.6512 (2.7989/1.1521)	mem 24308MB
[2025-01-19 04:02:12 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][250/312]	eta 0:00:38 lr 0.000230	time 0.5818 (0.6138)	model_time 0.5814 (0.6076)	loss 2.9528 (2.8223)	grad_norm 2.4564 (2.7934/1.1546)	mem 24308MB
[2025-01-19 04:02:18 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][260/312]	eta 0:00:31 lr 0.000230	time 0.5724 (0.6133)	model_time 0.5723 (0.6073)	loss 3.1719 (2.8220)	grad_norm 3.0131 (2.7751/1.1570)	mem 24308MB
[2025-01-19 04:02:24 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][270/312]	eta 0:00:25 lr 0.000230	time 0.5980 (0.6128)	model_time 0.5978 (0.6071)	loss 3.0521 (2.8174)	grad_norm 1.0488 (2.7753/1.1503)	mem 24308MB
[2025-01-19 04:02:30 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][280/312]	eta 0:00:19 lr 0.000229	time 0.6007 (0.6125)	model_time 0.6003 (0.6070)	loss 2.8178 (2.8164)	grad_norm 1.8336 (2.7563/1.1474)	mem 24308MB
[2025-01-19 04:02:36 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][290/312]	eta 0:00:13 lr 0.000229	time 0.5796 (0.6119)	model_time 0.5791 (0.6065)	loss 2.7545 (2.8208)	grad_norm 4.4553 (2.7315/1.1473)	mem 24308MB
[2025-01-19 04:02:42 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][300/312]	eta 0:00:07 lr 0.000229	time 0.6441 (0.6112)	model_time 0.6440 (0.6060)	loss 2.4610 (2.8130)	grad_norm 3.8979 (2.7380/1.1437)	mem 24308MB
[2025-01-19 04:02:48 internimage_s_1k_224] (main.py 510): INFO Train: [257/300][310/312]	eta 0:00:01 lr 0.000228	time 0.5735 (0.6101)	model_time 0.5734 (0.6051)	loss 2.1917 (2.8128)	grad_norm 2.9173 (2.7222/1.1335)	mem 24308MB
[2025-01-19 04:02:49 internimage_s_1k_224] (main.py 519): INFO EPOCH 257 training takes 0:03:10
[2025-01-19 04:02:49 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_257.pth saving......
[2025-01-19 04:02:50 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_257.pth saved !!!
[2025-01-19 04:02:58 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.918 (7.918)	Loss 0.6989 (0.6989)	Acc@1 86.060 (86.060)	Acc@5 97.754 (97.754)	Mem 24308MB
[2025-01-19 04:03:02 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.054)	Loss 0.8872 (0.7814)	Acc@1 79.956 (83.751)	Acc@5 95.874 (96.764)	Mem 24308MB
[2025-01-19 04:03:02 internimage_s_1k_224] (main.py 575): INFO [Epoch:257] * Acc@1 83.605 Acc@5 96.775
[2025-01-19 04:03:02 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.6%
[2025-01-19 04:03:02 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.65%
[2025-01-19 04:03:11 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.172 (9.172)	Loss 0.6985 (0.6985)	Acc@1 85.645 (85.645)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 04:03:16 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.247)	Loss 0.8852 (0.7727)	Acc@1 79.541 (83.654)	Acc@5 96.338 (96.735)	Mem 24308MB
[2025-01-19 04:03:16 internimage_s_1k_224] (main.py 575): INFO [Epoch:257] * Acc@1 83.519 Acc@5 96.757
[2025-01-19 04:03:16 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.5%
[2025-01-19 04:03:16 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:03:18 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:03:18 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.52%
[2025-01-19 04:03:21 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][0/312]	eta 0:13:41 lr 0.000228	time 2.6332 (2.6332)	model_time 0.5964 (0.5964)	loss 2.9158 (2.9158)	grad_norm 1.9133 (1.9133/0.0000)	mem 24308MB
[2025-01-19 04:03:27 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][10/312]	eta 0:04:02 lr 0.000228	time 0.6691 (0.8041)	model_time 0.6690 (0.6187)	loss 3.0642 (2.7262)	grad_norm 5.5737 (2.8941/0.9626)	mem 24308MB
[2025-01-19 04:03:33 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][20/312]	eta 0:03:28 lr 0.000228	time 0.7034 (0.7151)	model_time 0.7029 (0.6178)	loss 3.2034 (2.8681)	grad_norm 2.2426 (3.1920/1.2660)	mem 24308MB
[2025-01-19 04:03:40 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][30/312]	eta 0:03:13 lr 0.000228	time 0.5862 (0.6879)	model_time 0.5857 (0.6219)	loss 3.2702 (2.8694)	grad_norm 2.2474 (3.1428/1.4801)	mem 24308MB
[2025-01-19 04:03:46 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][40/312]	eta 0:03:02 lr 0.000227	time 0.6023 (0.6726)	model_time 0.6022 (0.6226)	loss 2.7461 (2.8876)	grad_norm 5.8525 (3.3158/1.5966)	mem 24308MB
[2025-01-19 04:03:52 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][50/312]	eta 0:02:52 lr 0.000227	time 0.5820 (0.6575)	model_time 0.5815 (0.6172)	loss 1.7142 (2.8212)	grad_norm 2.9476 (3.5035/1.5436)	mem 24308MB
[2025-01-19 04:03:58 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][60/312]	eta 0:02:44 lr 0.000227	time 0.5805 (0.6516)	model_time 0.5803 (0.6178)	loss 2.6801 (2.8258)	grad_norm 2.9251 (3.4232/1.5644)	mem 24308MB
[2025-01-19 04:04:04 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][70/312]	eta 0:02:35 lr 0.000226	time 0.5888 (0.6430)	model_time 0.5886 (0.6139)	loss 3.1921 (2.8481)	grad_norm 2.7602 (3.3565/1.5162)	mem 24308MB
[2025-01-19 04:04:10 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][80/312]	eta 0:02:28 lr 0.000226	time 0.6681 (0.6394)	model_time 0.6679 (0.6139)	loss 2.5215 (2.8300)	grad_norm 8.8762 (3.4525/1.6196)	mem 24308MB
[2025-01-19 04:04:16 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][90/312]	eta 0:02:21 lr 0.000226	time 0.5943 (0.6353)	model_time 0.5941 (0.6126)	loss 3.2243 (2.8435)	grad_norm 2.7546 (3.5322/1.6233)	mem 24308MB
[2025-01-19 04:04:22 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][100/312]	eta 0:02:13 lr 0.000226	time 0.5778 (0.6320)	model_time 0.5776 (0.6115)	loss 3.2731 (2.8351)	grad_norm 4.7311 (3.4938/1.5953)	mem 24308MB
[2025-01-19 04:04:28 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][110/312]	eta 0:02:07 lr 0.000225	time 0.5840 (0.6292)	model_time 0.5839 (0.6105)	loss 3.6830 (2.8370)	grad_norm 5.8757 (3.5193/1.6207)	mem 24308MB
[2025-01-19 04:04:34 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][120/312]	eta 0:02:00 lr 0.000225	time 0.5776 (0.6261)	model_time 0.5775 (0.6089)	loss 3.4352 (2.8502)	grad_norm 3.6732 (3.6005/1.7036)	mem 24308MB
[2025-01-19 04:04:40 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][130/312]	eta 0:01:53 lr 0.000225	time 0.5747 (0.6246)	model_time 0.5745 (0.6087)	loss 3.0394 (2.8365)	grad_norm 4.0042 (3.5480/1.6709)	mem 24308MB
[2025-01-19 04:04:47 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][140/312]	eta 0:01:47 lr 0.000225	time 0.7066 (0.6254)	model_time 0.7064 (0.6106)	loss 2.9272 (2.8304)	grad_norm 1.6581 (3.4730/1.6420)	mem 24308MB
[2025-01-19 04:04:53 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][150/312]	eta 0:01:41 lr 0.000224	time 0.6950 (0.6249)	model_time 0.6949 (0.6110)	loss 2.2511 (2.8369)	grad_norm 2.3808 (3.4040/1.6226)	mem 24308MB
[2025-01-19 04:04:59 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][160/312]	eta 0:01:34 lr 0.000224	time 0.6006 (0.6248)	model_time 0.6004 (0.6118)	loss 3.3762 (2.8547)	grad_norm 4.6040 (3.3752/1.5906)	mem 24308MB
[2025-01-19 04:05:05 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][170/312]	eta 0:01:28 lr 0.000224	time 0.5811 (0.6232)	model_time 0.5807 (0.6109)	loss 2.3802 (2.8459)	grad_norm 2.8545 (3.3276/1.5724)	mem 24308MB
[2025-01-19 04:05:11 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][180/312]	eta 0:01:22 lr 0.000223	time 0.5814 (0.6226)	model_time 0.5810 (0.6110)	loss 2.6088 (2.8476)	grad_norm 3.0120 (3.3296/1.5393)	mem 24308MB
[2025-01-19 04:05:17 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][190/312]	eta 0:01:15 lr 0.000223	time 0.5782 (0.6214)	model_time 0.5780 (0.6104)	loss 2.5841 (2.8463)	grad_norm 1.7473 (3.3127/1.5102)	mem 24308MB
[2025-01-19 04:05:23 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][200/312]	eta 0:01:09 lr 0.000223	time 0.6815 (0.6210)	model_time 0.6811 (0.6106)	loss 3.3385 (2.8484)	grad_norm 1.6246 (3.2786/1.4959)	mem 24308MB
[2025-01-19 04:05:29 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][210/312]	eta 0:01:03 lr 0.000223	time 0.5687 (0.6198)	model_time 0.5685 (0.6098)	loss 1.9383 (2.8348)	grad_norm 2.0245 (3.2433/1.4880)	mem 24308MB
[2025-01-19 04:05:35 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][220/312]	eta 0:00:56 lr 0.000222	time 0.7935 (0.6193)	model_time 0.7931 (0.6098)	loss 3.0767 (2.8274)	grad_norm 4.3760 (3.2331/1.4731)	mem 24308MB
[2025-01-19 04:05:41 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][230/312]	eta 0:00:50 lr 0.000222	time 0.6128 (0.6181)	model_time 0.6127 (0.6089)	loss 3.1262 (2.8239)	grad_norm 2.7168 (3.2050/1.4759)	mem 24308MB
[2025-01-19 04:05:47 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][240/312]	eta 0:00:44 lr 0.000222	time 0.5789 (0.6174)	model_time 0.5785 (0.6085)	loss 2.5774 (2.8193)	grad_norm 3.6262 (3.1785/1.4661)	mem 24308MB
[2025-01-19 04:05:53 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][250/312]	eta 0:00:38 lr 0.000221	time 0.5790 (0.6166)	model_time 0.5789 (0.6081)	loss 3.1988 (2.8273)	grad_norm 2.8123 (3.1564/1.4525)	mem 24308MB
[2025-01-19 04:05:59 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][260/312]	eta 0:00:32 lr 0.000221	time 0.6832 (0.6169)	model_time 0.6827 (0.6087)	loss 1.8124 (2.8257)	grad_norm 2.6336 (3.1381/1.4491)	mem 24308MB
[2025-01-19 04:06:06 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][270/312]	eta 0:00:25 lr 0.000221	time 0.7058 (0.6166)	model_time 0.7054 (0.6087)	loss 2.7325 (2.8142)	grad_norm 1.3844 (3.1146/1.4340)	mem 24308MB
[2025-01-19 04:06:12 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][280/312]	eta 0:00:19 lr 0.000221	time 0.5938 (0.6171)	model_time 0.5933 (0.6094)	loss 2.5871 (2.8113)	grad_norm 2.2498 (3.1123/1.4246)	mem 24308MB
[2025-01-19 04:06:18 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][290/312]	eta 0:00:13 lr 0.000220	time 0.5783 (0.6164)	model_time 0.5782 (0.6090)	loss 1.7413 (2.8104)	grad_norm 1.6901 (3.0916/1.4138)	mem 24308MB
[2025-01-19 04:06:24 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][300/312]	eta 0:00:07 lr 0.000220	time 0.5683 (0.6155)	model_time 0.5682 (0.6084)	loss 2.8936 (2.8095)	grad_norm 3.5663 (3.0740/1.4040)	mem 24308MB
[2025-01-19 04:06:30 internimage_s_1k_224] (main.py 510): INFO Train: [258/300][310/312]	eta 0:00:01 lr 0.000220	time 0.5685 (0.6149)	model_time 0.5684 (0.6080)	loss 2.4411 (2.8096)	grad_norm 1.7526 (3.0902/1.4279)	mem 24308MB
[2025-01-19 04:06:30 internimage_s_1k_224] (main.py 519): INFO EPOCH 258 training takes 0:03:11
[2025-01-19 04:06:30 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_258.pth saving......
[2025-01-19 04:06:32 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_258.pth saved !!!
[2025-01-19 04:06:40 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.981 (7.981)	Loss 0.7240 (0.7240)	Acc@1 85.864 (85.864)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 04:06:44 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.055)	Loss 0.9103 (0.7914)	Acc@1 80.176 (83.873)	Acc@5 95.386 (96.782)	Mem 24308MB
[2025-01-19 04:06:44 internimage_s_1k_224] (main.py 575): INFO [Epoch:258] * Acc@1 83.713 Acc@5 96.793
[2025-01-19 04:06:44 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.7%
[2025-01-19 04:06:44 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 04:06:46 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 04:06:46 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.71%
[2025-01-19 04:07:02 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 16.455 (16.455)	Loss 0.6982 (0.6982)	Acc@1 85.669 (85.669)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 04:07:10 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (2.162)	Loss 0.8844 (0.7721)	Acc@1 79.565 (83.665)	Acc@5 96.338 (96.746)	Mem 24308MB
[2025-01-19 04:07:10 internimage_s_1k_224] (main.py 575): INFO [Epoch:258] * Acc@1 83.529 Acc@5 96.763
[2025-01-19 04:07:10 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.5%
[2025-01-19 04:07:10 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:07:12 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:07:12 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.53%
[2025-01-19 04:07:14 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][0/312]	eta 0:11:53 lr 0.000220	time 2.2870 (2.2870)	model_time 0.5907 (0.5907)	loss 3.0372 (3.0372)	grad_norm 2.6709 (2.6709/0.0000)	mem 24308MB
[2025-01-19 04:07:20 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][10/312]	eta 0:03:47 lr 0.000219	time 0.5846 (0.7536)	model_time 0.5844 (0.5990)	loss 2.5563 (2.8103)	grad_norm 3.0992 (2.2117/0.6014)	mem 24308MB
[2025-01-19 04:07:27 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][20/312]	eta 0:03:20 lr 0.000219	time 0.5933 (0.6856)	model_time 0.5931 (0.6046)	loss 3.1184 (2.8454)	grad_norm 2.1819 (2.2110/0.6066)	mem 24308MB
[2025-01-19 04:07:33 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][30/312]	eta 0:03:06 lr 0.000219	time 0.7176 (0.6598)	model_time 0.7174 (0.6048)	loss 3.3213 (2.8348)	grad_norm 2.6883 (2.5182/1.0024)	mem 24308MB
[2025-01-19 04:07:39 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][40/312]	eta 0:02:55 lr 0.000219	time 0.5925 (0.6443)	model_time 0.5923 (0.6024)	loss 3.0398 (2.8392)	grad_norm 3.6895 (2.6457/1.0810)	mem 24308MB
[2025-01-19 04:07:45 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][50/312]	eta 0:02:46 lr 0.000218	time 0.5993 (0.6368)	model_time 0.5991 (0.6030)	loss 2.8722 (2.8330)	grad_norm 1.8232 (2.8198/1.2523)	mem 24308MB
[2025-01-19 04:07:51 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][60/312]	eta 0:02:39 lr 0.000218	time 0.6624 (0.6322)	model_time 0.6622 (0.6039)	loss 3.1368 (2.8636)	grad_norm 1.3173 (2.7988/1.2128)	mem 24308MB
[2025-01-19 04:07:57 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][70/312]	eta 0:02:33 lr 0.000218	time 0.5785 (0.6350)	model_time 0.5784 (0.6106)	loss 2.7955 (2.8197)	grad_norm 2.5622 (2.7994/1.1593)	mem 24308MB
[2025-01-19 04:08:03 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][80/312]	eta 0:02:26 lr 0.000218	time 0.5907 (0.6318)	model_time 0.5905 (0.6104)	loss 2.8596 (2.8529)	grad_norm 2.9769 (2.7234/1.1381)	mem 24308MB
[2025-01-19 04:08:10 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][90/312]	eta 0:02:20 lr 0.000217	time 0.6969 (0.6327)	model_time 0.6965 (0.6136)	loss 2.3988 (2.8515)	grad_norm 2.4870 (2.7157/1.1090)	mem 24308MB
[2025-01-19 04:08:16 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][100/312]	eta 0:02:13 lr 0.000217	time 0.6541 (0.6290)	model_time 0.6539 (0.6118)	loss 3.2311 (2.8568)	grad_norm 4.4822 (2.7129/1.1065)	mem 24308MB
[2025-01-19 04:08:22 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][110/312]	eta 0:02:06 lr 0.000217	time 0.6773 (0.6272)	model_time 0.6768 (0.6115)	loss 3.3483 (2.8704)	grad_norm 1.6331 (2.7289/1.1277)	mem 24308MB
[2025-01-19 04:08:28 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][120/312]	eta 0:02:00 lr 0.000216	time 0.5720 (0.6267)	model_time 0.5715 (0.6123)	loss 2.9389 (2.8658)	grad_norm 1.9550 (2.7226/1.1160)	mem 24308MB
[2025-01-19 04:08:34 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][130/312]	eta 0:01:53 lr 0.000216	time 0.6111 (0.6243)	model_time 0.6109 (0.6110)	loss 2.0483 (2.8699)	grad_norm 2.7555 (2.6967/1.0870)	mem 24308MB
[2025-01-19 04:08:40 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][140/312]	eta 0:01:47 lr 0.000216	time 0.5932 (0.6231)	model_time 0.5927 (0.6107)	loss 3.0730 (2.8748)	grad_norm 1.6043 (2.6932/1.0753)	mem 24308MB
[2025-01-19 04:08:46 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][150/312]	eta 0:01:40 lr 0.000216	time 0.5889 (0.6210)	model_time 0.5888 (0.6094)	loss 3.2926 (2.8806)	grad_norm 2.1059 (2.6749/1.0717)	mem 24308MB
[2025-01-19 04:08:52 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][160/312]	eta 0:01:34 lr 0.000215	time 0.7017 (0.6201)	model_time 0.7012 (0.6092)	loss 3.4795 (2.8865)	grad_norm 5.0953 (2.6891/1.0805)	mem 24308MB
[2025-01-19 04:08:58 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][170/312]	eta 0:01:27 lr 0.000215	time 0.5848 (0.6185)	model_time 0.5847 (0.6082)	loss 2.8125 (2.8846)	grad_norm 1.7626 (2.7813/1.3050)	mem 24308MB
[2025-01-19 04:09:04 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][180/312]	eta 0:01:21 lr 0.000215	time 0.5995 (0.6171)	model_time 0.5845 (0.6073)	loss 3.0106 (2.8823)	grad_norm 4.0426 (2.7542/1.2962)	mem 24308MB
[2025-01-19 04:09:10 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][190/312]	eta 0:01:15 lr 0.000214	time 0.5739 (0.6182)	model_time 0.5737 (0.6089)	loss 3.2047 (2.8877)	grad_norm 2.5508 (2.7478/1.2766)	mem 24308MB
[2025-01-19 04:09:16 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][200/312]	eta 0:01:09 lr 0.000214	time 0.5757 (0.6183)	model_time 0.5756 (0.6094)	loss 3.3264 (2.8900)	grad_norm 1.7863 (2.7560/1.2781)	mem 24308MB
[2025-01-19 04:09:23 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][210/312]	eta 0:01:03 lr 0.000214	time 0.5757 (0.6186)	model_time 0.5755 (0.6101)	loss 2.9653 (2.8964)	grad_norm 3.4161 (2.7872/1.2903)	mem 24308MB
[2025-01-19 04:09:29 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][220/312]	eta 0:00:56 lr 0.000214	time 0.5750 (0.6179)	model_time 0.5746 (0.6098)	loss 3.0674 (2.8818)	grad_norm 4.1837 (2.8250/1.2998)	mem 24308MB
[2025-01-19 04:09:35 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][230/312]	eta 0:00:50 lr 0.000213	time 0.6038 (0.6170)	model_time 0.6033 (0.6092)	loss 3.4610 (2.8821)	grad_norm 4.3456 (2.8484/1.3121)	mem 24308MB
[2025-01-19 04:09:41 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][240/312]	eta 0:00:44 lr 0.000213	time 0.5728 (0.6169)	model_time 0.5726 (0.6094)	loss 2.6126 (2.8804)	grad_norm 3.2692 (2.8871/1.3505)	mem 24308MB
[2025-01-19 04:09:47 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][250/312]	eta 0:00:38 lr 0.000213	time 0.6872 (0.6161)	model_time 0.6866 (0.6089)	loss 2.0890 (2.8686)	grad_norm 2.0802 (2.9042/1.3567)	mem 24308MB
[2025-01-19 04:09:53 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][260/312]	eta 0:00:32 lr 0.000213	time 0.5833 (0.6160)	model_time 0.5832 (0.6091)	loss 3.0156 (2.8712)	grad_norm 3.1311 (2.9333/1.3567)	mem 24308MB
[2025-01-19 04:09:59 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][270/312]	eta 0:00:25 lr 0.000212	time 0.5909 (0.6151)	model_time 0.5906 (0.6084)	loss 2.4711 (2.8765)	grad_norm 1.3780 (2.9500/1.3595)	mem 24308MB
[2025-01-19 04:10:05 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][280/312]	eta 0:00:19 lr 0.000212	time 0.5774 (0.6145)	model_time 0.5770 (0.6080)	loss 2.2774 (2.8676)	grad_norm 1.5564 (2.9286/1.3460)	mem 24308MB
[2025-01-19 04:10:11 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][290/312]	eta 0:00:13 lr 0.000212	time 0.5833 (0.6139)	model_time 0.5831 (0.6077)	loss 3.2457 (2.8632)	grad_norm 3.4729 (2.9234/1.3277)	mem 24308MB
[2025-01-19 04:10:17 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][300/312]	eta 0:00:07 lr 0.000212	time 0.5710 (0.6134)	model_time 0.5709 (0.6073)	loss 2.8565 (2.8591)	grad_norm 2.7575 (2.9147/1.3244)	mem 24308MB
[2025-01-19 04:10:23 internimage_s_1k_224] (main.py 510): INFO Train: [259/300][310/312]	eta 0:00:01 lr 0.000211	time 0.5716 (0.6134)	model_time 0.5715 (0.6075)	loss 2.6904 (2.8552)	grad_norm 4.1532 (2.9446/1.3366)	mem 24308MB
[2025-01-19 04:10:23 internimage_s_1k_224] (main.py 519): INFO EPOCH 259 training takes 0:03:11
[2025-01-19 04:10:23 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_259.pth saving......
[2025-01-19 04:10:25 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_259.pth saved !!!
[2025-01-19 04:10:33 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.132 (8.132)	Loss 0.6976 (0.6976)	Acc@1 86.230 (86.230)	Acc@5 97.632 (97.632)	Mem 24308MB
[2025-01-19 04:10:37 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.057)	Loss 0.9077 (0.7880)	Acc@1 79.956 (83.862)	Acc@5 95.776 (96.775)	Mem 24308MB
[2025-01-19 04:10:37 internimage_s_1k_224] (main.py 575): INFO [Epoch:259] * Acc@1 83.681 Acc@5 96.769
[2025-01-19 04:10:37 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.7%
[2025-01-19 04:10:37 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.71%
[2025-01-19 04:10:46 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.994 (8.994)	Loss 0.6979 (0.6979)	Acc@1 85.645 (85.645)	Acc@5 97.852 (97.852)	Mem 24308MB
[2025-01-19 04:10:51 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.215)	Loss 0.8837 (0.7717)	Acc@1 79.614 (83.687)	Acc@5 96.338 (96.760)	Mem 24308MB
[2025-01-19 04:10:51 internimage_s_1k_224] (main.py 575): INFO [Epoch:259] * Acc@1 83.549 Acc@5 96.777
[2025-01-19 04:10:51 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.5%
[2025-01-19 04:10:51 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:10:53 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:10:53 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.55%
[2025-01-19 04:10:56 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][0/312]	eta 0:12:18 lr 0.000211	time 2.3656 (2.3656)	model_time 0.5985 (0.5985)	loss 3.0040 (3.0040)	grad_norm 2.6005 (2.6005/0.0000)	mem 24308MB
[2025-01-19 04:11:02 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][10/312]	eta 0:03:52 lr 0.000211	time 0.6663 (0.7708)	model_time 0.6662 (0.6099)	loss 1.8707 (2.8368)	grad_norm 2.8018 (2.0456/0.4859)	mem 24308MB
[2025-01-19 04:11:08 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][20/312]	eta 0:03:24 lr 0.000211	time 0.6116 (0.6997)	model_time 0.6112 (0.6153)	loss 2.6097 (2.8551)	grad_norm 1.9916 (2.0935/0.4996)	mem 24308MB
[2025-01-19 04:11:14 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][30/312]	eta 0:03:08 lr 0.000210	time 0.5960 (0.6667)	model_time 0.5959 (0.6094)	loss 2.9835 (2.8519)	grad_norm 1.6334 (2.1587/0.6033)	mem 24308MB
[2025-01-19 04:11:20 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][40/312]	eta 0:02:56 lr 0.000210	time 0.5796 (0.6501)	model_time 0.5794 (0.6066)	loss 2.5403 (2.8748)	grad_norm 1.4963 (2.3480/0.7858)	mem 24308MB
[2025-01-19 04:11:26 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][50/312]	eta 0:02:49 lr 0.000210	time 0.5866 (0.6476)	model_time 0.5864 (0.6126)	loss 3.1222 (2.8423)	grad_norm 2.3941 (2.3488/0.7452)	mem 24308MB
[2025-01-19 04:11:32 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][60/312]	eta 0:02:41 lr 0.000210	time 0.5727 (0.6402)	model_time 0.5722 (0.6109)	loss 1.6124 (2.8445)	grad_norm 2.3641 (2.4834/0.8782)	mem 24308MB
[2025-01-19 04:11:38 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][70/312]	eta 0:02:33 lr 0.000209	time 0.5742 (0.6358)	model_time 0.5741 (0.6106)	loss 3.0846 (2.8483)	grad_norm 3.3813 (2.5347/0.8997)	mem 24308MB
[2025-01-19 04:11:44 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][80/312]	eta 0:02:26 lr 0.000209	time 0.5949 (0.6301)	model_time 0.5944 (0.6080)	loss 2.5502 (2.8070)	grad_norm 3.2611 (2.5504/0.8954)	mem 24308MB
[2025-01-19 04:11:50 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][90/312]	eta 0:02:19 lr 0.000209	time 0.5724 (0.6264)	model_time 0.5722 (0.6066)	loss 3.3243 (2.8077)	grad_norm 4.0040 (2.6411/1.0037)	mem 24308MB
[2025-01-19 04:11:56 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][100/312]	eta 0:02:12 lr 0.000208	time 0.6050 (0.6248)	model_time 0.6049 (0.6070)	loss 1.9816 (2.7979)	grad_norm 3.3734 (2.6410/1.0084)	mem 24308MB
[2025-01-19 04:12:02 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][110/312]	eta 0:02:05 lr 0.000208	time 0.5869 (0.6221)	model_time 0.5865 (0.6058)	loss 2.7465 (2.7837)	grad_norm 3.1684 (2.6626/0.9879)	mem 24308MB
[2025-01-19 04:12:09 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][120/312]	eta 0:01:59 lr 0.000208	time 0.7032 (0.6228)	model_time 0.7031 (0.6078)	loss 3.4036 (2.7952)	grad_norm 1.1777 (2.6075/0.9919)	mem 24308MB
[2025-01-19 04:12:15 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][130/312]	eta 0:01:53 lr 0.000208	time 0.6666 (0.6220)	model_time 0.6665 (0.6081)	loss 2.7019 (2.7870)	grad_norm 1.4040 (2.6105/0.9779)	mem 24308MB
[2025-01-19 04:12:21 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][140/312]	eta 0:01:46 lr 0.000207	time 0.5780 (0.6218)	model_time 0.5779 (0.6089)	loss 2.4008 (2.7937)	grad_norm 1.3541 (2.5926/0.9601)	mem 24308MB
[2025-01-19 04:12:27 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][150/312]	eta 0:01:40 lr 0.000207	time 0.5798 (0.6201)	model_time 0.5796 (0.6080)	loss 2.5993 (2.7929)	grad_norm 3.4272 (2.6073/0.9685)	mem 24308MB
[2025-01-19 04:12:33 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][160/312]	eta 0:01:34 lr 0.000207	time 0.5960 (0.6187)	model_time 0.5956 (0.6073)	loss 3.0226 (2.7875)	grad_norm 3.6520 (2.6621/1.0150)	mem 24308MB
[2025-01-19 04:12:39 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][170/312]	eta 0:01:27 lr 0.000207	time 0.5746 (0.6196)	model_time 0.5741 (0.6089)	loss 2.3932 (2.7907)	grad_norm 3.9999 (2.6625/1.0166)	mem 24308MB
[2025-01-19 04:12:45 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][180/312]	eta 0:01:21 lr 0.000206	time 0.5817 (0.6184)	model_time 0.5815 (0.6082)	loss 2.6714 (2.7877)	grad_norm 1.9992 (2.6387/1.0017)	mem 24308MB
[2025-01-19 04:12:51 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][190/312]	eta 0:01:15 lr 0.000206	time 0.5864 (0.6180)	model_time 0.5863 (0.6084)	loss 3.7126 (2.7931)	grad_norm 5.6454 (2.6622/1.0538)	mem 24308MB
[2025-01-19 04:12:57 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][200/312]	eta 0:01:09 lr 0.000206	time 0.5857 (0.6164)	model_time 0.5853 (0.6072)	loss 1.9707 (2.7847)	grad_norm 6.9609 (2.6879/1.0970)	mem 24308MB
[2025-01-19 04:13:03 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][210/312]	eta 0:01:02 lr 0.000206	time 0.5728 (0.6151)	model_time 0.5726 (0.6063)	loss 2.6534 (2.7824)	grad_norm 2.2125 (2.7267/1.1388)	mem 24308MB
[2025-01-19 04:13:09 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][220/312]	eta 0:00:56 lr 0.000205	time 0.5849 (0.6149)	model_time 0.5844 (0.6065)	loss 3.0270 (2.7881)	grad_norm 1.4850 (2.7230/1.1345)	mem 24308MB
[2025-01-19 04:13:15 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][230/312]	eta 0:00:50 lr 0.000205	time 0.6242 (0.6138)	model_time 0.6241 (0.6057)	loss 2.9418 (2.7863)	grad_norm 2.1618 (2.7549/1.1457)	mem 24308MB
[2025-01-19 04:13:21 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][240/312]	eta 0:00:44 lr 0.000205	time 0.7113 (0.6138)	model_time 0.7108 (0.6061)	loss 3.0472 (2.7892)	grad_norm 2.4621 (2.8139/1.2297)	mem 24308MB
[2025-01-19 04:13:27 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][250/312]	eta 0:00:38 lr 0.000204	time 0.6304 (0.6139)	model_time 0.6299 (0.6064)	loss 2.9737 (2.7917)	grad_norm 4.8384 (2.8629/1.2600)	mem 24308MB
[2025-01-19 04:13:33 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][260/312]	eta 0:00:31 lr 0.000204	time 0.5870 (0.6140)	model_time 0.5866 (0.6067)	loss 3.0384 (2.7945)	grad_norm 3.6219 (2.8588/1.2486)	mem 24308MB
[2025-01-19 04:13:40 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][270/312]	eta 0:00:25 lr 0.000204	time 0.5938 (0.6140)	model_time 0.5936 (0.6070)	loss 1.7000 (2.7861)	grad_norm 3.2132 (2.8740/1.2542)	mem 24308MB
[2025-01-19 04:13:46 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][280/312]	eta 0:00:19 lr 0.000204	time 0.5994 (0.6134)	model_time 0.5993 (0.6067)	loss 2.7699 (2.7838)	grad_norm 1.4926 (2.8479/1.2451)	mem 24308MB
[2025-01-19 04:13:52 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][290/312]	eta 0:00:13 lr 0.000203	time 0.5741 (0.6142)	model_time 0.5736 (0.6077)	loss 2.3000 (2.7755)	grad_norm 1.4088 (2.8402/1.2348)	mem 24308MB
[2025-01-19 04:13:58 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][300/312]	eta 0:00:07 lr 0.000203	time 0.5686 (0.6133)	model_time 0.5685 (0.6070)	loss 2.7207 (2.7751)	grad_norm 2.1447 (2.8326/1.2304)	mem 24308MB
[2025-01-19 04:14:04 internimage_s_1k_224] (main.py 510): INFO Train: [260/300][310/312]	eta 0:00:01 lr 0.000203	time 0.5726 (0.6128)	model_time 0.5725 (0.6067)	loss 2.8940 (2.7770)	grad_norm 3.0592 (2.8562/1.2281)	mem 24308MB
[2025-01-19 04:14:04 internimage_s_1k_224] (main.py 519): INFO EPOCH 260 training takes 0:03:11
[2025-01-19 04:14:04 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_260.pth saving......
[2025-01-19 04:14:06 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_260.pth saved !!!
[2025-01-19 04:14:14 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.953 (7.953)	Loss 0.7141 (0.7141)	Acc@1 85.889 (85.889)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 04:14:18 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.052)	Loss 0.8924 (0.7875)	Acc@1 80.103 (83.769)	Acc@5 95.752 (96.777)	Mem 24308MB
[2025-01-19 04:14:18 internimage_s_1k_224] (main.py 575): INFO [Epoch:260] * Acc@1 83.613 Acc@5 96.793
[2025-01-19 04:14:18 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.6%
[2025-01-19 04:14:18 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.71%
[2025-01-19 04:14:27 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.218 (9.218)	Loss 0.6975 (0.6975)	Acc@1 85.669 (85.669)	Acc@5 97.803 (97.803)	Mem 24308MB
[2025-01-19 04:14:32 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.142 (1.251)	Loss 0.8829 (0.7712)	Acc@1 79.639 (83.696)	Acc@5 96.338 (96.766)	Mem 24308MB
[2025-01-19 04:14:32 internimage_s_1k_224] (main.py 575): INFO [Epoch:260] * Acc@1 83.557 Acc@5 96.785
[2025-01-19 04:14:32 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.6%
[2025-01-19 04:14:32 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:14:34 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:14:34 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.56%
[2025-01-19 04:14:36 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][0/312]	eta 0:10:10 lr 0.000203	time 1.9580 (1.9580)	model_time 0.6198 (0.6198)	loss 3.1343 (3.1343)	grad_norm 1.9248 (1.9248/0.0000)	mem 24308MB
[2025-01-19 04:14:42 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][10/312]	eta 0:03:36 lr 0.000203	time 0.5896 (0.7177)	model_time 0.5895 (0.5957)	loss 2.0418 (2.7494)	grad_norm 1.7622 (2.1305/0.9064)	mem 24308MB
[2025-01-19 04:14:48 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][20/312]	eta 0:03:13 lr 0.000202	time 0.6740 (0.6627)	model_time 0.6738 (0.5987)	loss 2.9170 (2.9108)	grad_norm 2.7511 (2.6004/1.3145)	mem 24308MB
[2025-01-19 04:14:54 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][30/312]	eta 0:03:01 lr 0.000202	time 0.6203 (0.6431)	model_time 0.6199 (0.5996)	loss 3.1807 (2.9035)	grad_norm 1.7740 (2.7325/1.3246)	mem 24308MB
[2025-01-19 04:15:00 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][40/312]	eta 0:02:51 lr 0.000202	time 0.6026 (0.6303)	model_time 0.6022 (0.5974)	loss 2.2719 (2.8800)	grad_norm 3.4217 (2.7652/1.1801)	mem 24308MB
[2025-01-19 04:15:06 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][50/312]	eta 0:02:44 lr 0.000202	time 0.5744 (0.6275)	model_time 0.5740 (0.6009)	loss 3.0282 (2.8524)	grad_norm 3.7099 (2.9116/1.3344)	mem 24308MB
[2025-01-19 04:15:12 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][60/312]	eta 0:02:37 lr 0.000201	time 0.5737 (0.6237)	model_time 0.5735 (0.6014)	loss 3.1079 (2.8204)	grad_norm 1.7229 (2.8046/1.2950)	mem 24308MB
[2025-01-19 04:15:19 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][70/312]	eta 0:02:31 lr 0.000201	time 0.7056 (0.6242)	model_time 0.7051 (0.6049)	loss 3.1122 (2.7833)	grad_norm 1.8365 (2.7472/1.2624)	mem 24308MB
[2025-01-19 04:15:25 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][80/312]	eta 0:02:24 lr 0.000201	time 0.5994 (0.6211)	model_time 0.5992 (0.6042)	loss 3.2264 (2.7805)	grad_norm 9.7732 (2.8768/1.4697)	mem 24308MB
[2025-01-19 04:15:30 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][90/312]	eta 0:02:17 lr 0.000200	time 0.5729 (0.6180)	model_time 0.5727 (0.6029)	loss 3.0010 (2.8002)	grad_norm 2.6979 (2.8761/1.4221)	mem 24308MB
[2025-01-19 04:15:37 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][100/312]	eta 0:02:11 lr 0.000200	time 0.5993 (0.6194)	model_time 0.5991 (0.6058)	loss 2.5887 (2.7972)	grad_norm 2.2301 (2.8301/1.3920)	mem 24308MB
[2025-01-19 04:15:43 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][110/312]	eta 0:02:04 lr 0.000200	time 0.6843 (0.6182)	model_time 0.6841 (0.6058)	loss 2.0279 (2.7808)	grad_norm 3.9194 (2.8250/1.3740)	mem 24308MB
[2025-01-19 04:15:49 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][120/312]	eta 0:01:58 lr 0.000200	time 0.5917 (0.6161)	model_time 0.5912 (0.6047)	loss 2.4447 (2.7724)	grad_norm 3.1929 (2.8709/1.3689)	mem 24308MB
[2025-01-19 04:15:55 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][130/312]	eta 0:01:51 lr 0.000199	time 0.5872 (0.6141)	model_time 0.5870 (0.6036)	loss 3.0473 (2.7853)	grad_norm 4.9652 (2.9063/1.3654)	mem 24308MB
[2025-01-19 04:16:01 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][140/312]	eta 0:01:45 lr 0.000199	time 0.5947 (0.6126)	model_time 0.5945 (0.6027)	loss 2.0469 (2.7830)	grad_norm 1.5689 (2.8580/1.3483)	mem 24308MB
[2025-01-19 04:16:07 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][150/312]	eta 0:01:39 lr 0.000199	time 0.6816 (0.6124)	model_time 0.6815 (0.6031)	loss 3.1748 (2.7852)	grad_norm 1.4781 (2.8203/1.3208)	mem 24308MB
[2025-01-19 04:16:13 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][160/312]	eta 0:01:32 lr 0.000199	time 0.5975 (0.6109)	model_time 0.5970 (0.6022)	loss 2.9599 (2.7837)	grad_norm 2.4256 (2.8236/1.2947)	mem 24308MB
[2025-01-19 04:16:19 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][170/312]	eta 0:01:26 lr 0.000198	time 0.5797 (0.6113)	model_time 0.5796 (0.6031)	loss 3.0648 (2.7826)	grad_norm 3.5944 (2.8590/1.2880)	mem 24308MB
[2025-01-19 04:16:25 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][180/312]	eta 0:01:20 lr 0.000198	time 0.7040 (0.6112)	model_time 0.7038 (0.6035)	loss 3.0712 (2.7809)	grad_norm 3.4921 (2.8573/1.2714)	mem 24308MB
[2025-01-19 04:16:31 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][190/312]	eta 0:01:14 lr 0.000198	time 0.6632 (0.6115)	model_time 0.6627 (0.6041)	loss 2.5332 (2.7819)	grad_norm 1.4685 (2.8811/1.2918)	mem 24308MB
[2025-01-19 04:16:37 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][200/312]	eta 0:01:08 lr 0.000198	time 0.5942 (0.6120)	model_time 0.5941 (0.6050)	loss 2.9958 (2.7971)	grad_norm 1.6953 (2.8821/1.2972)	mem 24308MB
[2025-01-19 04:16:43 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][210/312]	eta 0:01:02 lr 0.000197	time 0.5864 (0.6114)	model_time 0.5859 (0.6047)	loss 2.1398 (2.7889)	grad_norm 3.4339 (2.8635/1.2860)	mem 24308MB
[2025-01-19 04:16:49 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][220/312]	eta 0:00:56 lr 0.000197	time 0.5812 (0.6118)	model_time 0.5810 (0.6054)	loss 2.1325 (2.7864)	grad_norm 1.6076 (2.8405/1.2773)	mem 24308MB
[2025-01-19 04:16:56 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][230/312]	eta 0:00:50 lr 0.000197	time 0.6854 (0.6119)	model_time 0.6853 (0.6057)	loss 3.6035 (2.7995)	grad_norm 2.1796 (2.8546/1.2789)	mem 24308MB
[2025-01-19 04:17:01 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][240/312]	eta 0:00:43 lr 0.000197	time 0.5861 (0.6111)	model_time 0.5856 (0.6052)	loss 3.1813 (2.8003)	grad_norm 5.9247 (2.8940/1.3192)	mem 24308MB
[2025-01-19 04:17:08 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][250/312]	eta 0:00:37 lr 0.000196	time 0.6124 (0.6107)	model_time 0.6119 (0.6050)	loss 3.0931 (2.8053)	grad_norm 1.6083 (2.9125/1.3231)	mem 24308MB
[2025-01-19 04:17:13 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][260/312]	eta 0:00:31 lr 0.000196	time 0.5747 (0.6098)	model_time 0.5745 (0.6043)	loss 3.5496 (2.8052)	grad_norm 1.5644 (2.9191/1.3280)	mem 24308MB
[2025-01-19 04:17:19 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][270/312]	eta 0:00:25 lr 0.000196	time 0.6635 (0.6097)	model_time 0.6633 (0.6044)	loss 2.4928 (2.8008)	grad_norm 2.4669 (2.9525/1.3503)	mem 24308MB
[2025-01-19 04:17:25 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][280/312]	eta 0:00:19 lr 0.000196	time 0.5759 (0.6089)	model_time 0.5753 (0.6038)	loss 3.5189 (2.8025)	grad_norm 2.3804 (2.9502/1.3320)	mem 24308MB
[2025-01-19 04:17:31 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][290/312]	eta 0:00:13 lr 0.000195	time 0.5755 (0.6090)	model_time 0.5750 (0.6040)	loss 2.7587 (2.8000)	grad_norm 5.9114 (2.9815/1.3560)	mem 24308MB
[2025-01-19 04:17:38 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][300/312]	eta 0:00:07 lr 0.000195	time 0.6859 (0.6094)	model_time 0.6858 (0.6046)	loss 3.4693 (2.8020)	grad_norm 1.2284 (2.9706/1.3614)	mem 24308MB
[2025-01-19 04:17:44 internimage_s_1k_224] (main.py 510): INFO Train: [261/300][310/312]	eta 0:00:01 lr 0.000195	time 0.5705 (0.6089)	model_time 0.5704 (0.6042)	loss 2.8764 (2.8051)	grad_norm 1.3337 (2.9692/1.3550)	mem 24308MB
[2025-01-19 04:17:44 internimage_s_1k_224] (main.py 519): INFO EPOCH 261 training takes 0:03:09
[2025-01-19 04:17:44 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_261.pth saving......
[2025-01-19 04:17:46 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_261.pth saved !!!
[2025-01-19 04:17:54 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.693 (7.693)	Loss 0.7144 (0.7144)	Acc@1 85.962 (85.962)	Acc@5 97.705 (97.705)	Mem 24308MB
[2025-01-19 04:17:57 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.028)	Loss 0.8987 (0.8001)	Acc@1 80.640 (83.800)	Acc@5 95.752 (96.768)	Mem 24308MB
[2025-01-19 04:17:58 internimage_s_1k_224] (main.py 575): INFO [Epoch:261] * Acc@1 83.663 Acc@5 96.773
[2025-01-19 04:17:58 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.7%
[2025-01-19 04:17:58 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.71%
[2025-01-19 04:18:07 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.926 (8.926)	Loss 0.6971 (0.6971)	Acc@1 85.693 (85.693)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 04:18:11 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (1.219)	Loss 0.8821 (0.7707)	Acc@1 79.663 (83.700)	Acc@5 96.313 (96.780)	Mem 24308MB
[2025-01-19 04:18:11 internimage_s_1k_224] (main.py 575): INFO [Epoch:261] * Acc@1 83.565 Acc@5 96.797
[2025-01-19 04:18:11 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.6%
[2025-01-19 04:18:11 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:18:13 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:18:13 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.57%
[2025-01-19 04:18:16 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][0/312]	eta 0:11:48 lr 0.000195	time 2.2723 (2.2723)	model_time 0.5966 (0.5966)	loss 2.5310 (2.5310)	grad_norm 4.1291 (4.1291/0.0000)	mem 24308MB
[2025-01-19 04:18:22 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][10/312]	eta 0:03:56 lr 0.000194	time 0.5780 (0.7828)	model_time 0.5775 (0.6301)	loss 3.2156 (2.6505)	grad_norm 1.6494 (3.0472/1.3013)	mem 24308MB
[2025-01-19 04:18:28 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][20/312]	eta 0:03:24 lr 0.000194	time 0.5732 (0.6991)	model_time 0.5731 (0.6190)	loss 3.1365 (2.6475)	grad_norm 2.3061 (2.9272/1.1258)	mem 24308MB
[2025-01-19 04:18:34 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][30/312]	eta 0:03:10 lr 0.000194	time 0.6547 (0.6746)	model_time 0.6546 (0.6202)	loss 3.1433 (2.7121)	grad_norm 2.0217 (2.6996/1.0191)	mem 24308MB
[2025-01-19 04:18:40 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][40/312]	eta 0:02:59 lr 0.000194	time 0.6829 (0.6586)	model_time 0.6825 (0.6174)	loss 2.5022 (2.7238)	grad_norm 2.4437 (2.5746/0.9489)	mem 24308MB
[2025-01-19 04:18:46 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][50/312]	eta 0:02:49 lr 0.000193	time 0.5899 (0.6462)	model_time 0.5744 (0.6126)	loss 3.0900 (2.7390)	grad_norm 2.3263 (2.5818/0.9084)	mem 24308MB
[2025-01-19 04:18:52 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][60/312]	eta 0:02:40 lr 0.000193	time 0.5733 (0.6376)	model_time 0.5731 (0.6095)	loss 3.2845 (2.7646)	grad_norm 1.9860 (2.6807/0.9602)	mem 24308MB
[2025-01-19 04:18:58 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][70/312]	eta 0:02:32 lr 0.000193	time 0.5784 (0.6317)	model_time 0.5783 (0.6075)	loss 3.0935 (2.7908)	grad_norm 1.4474 (2.6542/0.9560)	mem 24308MB
[2025-01-19 04:19:04 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][80/312]	eta 0:02:26 lr 0.000193	time 0.5906 (0.6299)	model_time 0.5904 (0.6086)	loss 2.9369 (2.7955)	grad_norm 5.3051 (2.6441/0.9611)	mem 24308MB
[2025-01-19 04:19:10 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][90/312]	eta 0:02:18 lr 0.000192	time 0.5988 (0.6257)	model_time 0.5986 (0.6067)	loss 2.7222 (2.7917)	grad_norm 1.4268 (2.6678/0.9894)	mem 24308MB
[2025-01-19 04:19:17 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][100/312]	eta 0:02:12 lr 0.000192	time 0.6704 (0.6261)	model_time 0.6700 (0.6090)	loss 3.2252 (2.7928)	grad_norm 3.0672 (2.7232/1.0275)	mem 24308MB
[2025-01-19 04:19:23 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][110/312]	eta 0:02:06 lr 0.000192	time 0.5976 (0.6246)	model_time 0.5975 (0.6090)	loss 3.3053 (2.8102)	grad_norm 1.4341 (2.6791/1.0444)	mem 24308MB
[2025-01-19 04:19:29 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][120/312]	eta 0:01:59 lr 0.000192	time 0.5877 (0.6242)	model_time 0.5875 (0.6099)	loss 3.0621 (2.8123)	grad_norm 1.9475 (2.6162/1.0439)	mem 24308MB
[2025-01-19 04:19:35 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][130/312]	eta 0:01:53 lr 0.000191	time 0.5771 (0.6250)	model_time 0.5766 (0.6117)	loss 3.2700 (2.8203)	grad_norm 2.0274 (2.6665/1.1307)	mem 24308MB
[2025-01-19 04:19:41 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][140/312]	eta 0:01:47 lr 0.000191	time 0.6828 (0.6237)	model_time 0.6827 (0.6114)	loss 2.2805 (2.8072)	grad_norm 3.0570 (2.6849/1.1246)	mem 24308MB
[2025-01-19 04:19:47 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][150/312]	eta 0:01:40 lr 0.000191	time 0.5808 (0.6226)	model_time 0.5806 (0.6111)	loss 2.8610 (2.8032)	grad_norm 3.2585 (2.7161/1.1590)	mem 24308MB
[2025-01-19 04:19:53 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][160/312]	eta 0:01:34 lr 0.000191	time 0.6065 (0.6214)	model_time 0.6063 (0.6105)	loss 3.4119 (2.8216)	grad_norm 3.2934 (2.7064/1.1302)	mem 24308MB
[2025-01-19 04:20:00 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][170/312]	eta 0:01:28 lr 0.000190	time 0.5915 (0.6210)	model_time 0.5913 (0.6108)	loss 3.2084 (2.8165)	grad_norm 2.9514 (2.7143/1.1432)	mem 24308MB
[2025-01-19 04:20:06 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][180/312]	eta 0:01:21 lr 0.000190	time 0.5769 (0.6199)	model_time 0.5762 (0.6102)	loss 2.7424 (2.8060)	grad_norm 5.1373 (2.7510/1.1824)	mem 24308MB
[2025-01-19 04:20:12 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][190/312]	eta 0:01:15 lr 0.000190	time 0.5902 (0.6187)	model_time 0.5897 (0.6095)	loss 3.4769 (2.8099)	grad_norm 2.8977 (2.7355/1.1727)	mem 24308MB
[2025-01-19 04:20:18 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][200/312]	eta 0:01:09 lr 0.000190	time 0.5908 (0.6183)	model_time 0.5907 (0.6096)	loss 1.8058 (2.8026)	grad_norm 2.1463 (2.7513/1.1622)	mem 24308MB
[2025-01-19 04:20:24 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][210/312]	eta 0:01:02 lr 0.000189	time 0.5751 (0.6169)	model_time 0.5750 (0.6086)	loss 2.9712 (2.8048)	grad_norm 2.1839 (2.7686/1.1691)	mem 24308MB
[2025-01-19 04:20:30 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][220/312]	eta 0:00:56 lr 0.000189	time 0.6660 (0.6180)	model_time 0.6659 (0.6100)	loss 2.5680 (2.8083)	grad_norm 3.3195 (2.7836/1.1596)	mem 24308MB
[2025-01-19 04:20:36 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][230/312]	eta 0:00:50 lr 0.000189	time 0.6138 (0.6174)	model_time 0.6134 (0.6097)	loss 3.2829 (2.8146)	grad_norm 2.2158 (2.7690/1.1621)	mem 24308MB
[2025-01-19 04:20:42 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][240/312]	eta 0:00:44 lr 0.000189	time 0.5863 (0.6173)	model_time 0.5862 (0.6099)	loss 2.4984 (2.8190)	grad_norm 3.3629 (2.7440/1.1540)	mem 24308MB
[2025-01-19 04:20:49 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][250/312]	eta 0:00:38 lr 0.000188	time 0.5833 (0.6177)	model_time 0.5831 (0.6106)	loss 2.8138 (2.8280)	grad_norm 2.7127 (2.7411/1.1364)	mem 24308MB
[2025-01-19 04:20:55 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][260/312]	eta 0:00:32 lr 0.000188	time 0.6757 (0.6175)	model_time 0.6753 (0.6106)	loss 3.1224 (2.8306)	grad_norm 2.9904 (2.7417/1.1236)	mem 24308MB
[2025-01-19 04:21:01 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][270/312]	eta 0:00:25 lr 0.000188	time 0.5803 (0.6168)	model_time 0.5801 (0.6102)	loss 1.6198 (2.8282)	grad_norm 3.3460 (2.7478/1.1145)	mem 24308MB
[2025-01-19 04:21:07 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][280/312]	eta 0:00:19 lr 0.000188	time 0.6088 (0.6165)	model_time 0.6082 (0.6101)	loss 2.7688 (2.8353)	grad_norm 2.3260 (2.7620/1.1310)	mem 24308MB
[2025-01-19 04:21:13 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][290/312]	eta 0:00:13 lr 0.000187	time 0.7147 (0.6166)	model_time 0.7143 (0.6104)	loss 2.9765 (2.8328)	grad_norm 4.0283 (2.7855/1.1370)	mem 24308MB
[2025-01-19 04:21:19 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][300/312]	eta 0:00:07 lr 0.000187	time 0.5630 (0.6158)	model_time 0.5629 (0.6098)	loss 3.1758 (2.8334)	grad_norm 1.6440 (2.8001/1.1485)	mem 24308MB
[2025-01-19 04:21:25 internimage_s_1k_224] (main.py 510): INFO Train: [262/300][310/312]	eta 0:00:01 lr 0.000187	time 0.5708 (0.6148)	model_time 0.5707 (0.6090)	loss 3.1242 (2.8375)	grad_norm 3.1193 (2.7952/1.1278)	mem 24308MB
[2025-01-19 04:21:25 internimage_s_1k_224] (main.py 519): INFO EPOCH 262 training takes 0:03:11
[2025-01-19 04:21:25 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_262.pth saving......
[2025-01-19 04:21:27 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_262.pth saved !!!
[2025-01-19 04:21:35 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.893 (7.893)	Loss 0.6958 (0.6958)	Acc@1 86.182 (86.182)	Acc@5 97.998 (97.998)	Mem 24308MB
[2025-01-19 04:21:39 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.050)	Loss 0.8945 (0.7855)	Acc@1 80.249 (83.936)	Acc@5 95.825 (96.846)	Mem 24308MB
[2025-01-19 04:21:39 internimage_s_1k_224] (main.py 575): INFO [Epoch:262] * Acc@1 83.763 Acc@5 96.851
[2025-01-19 04:21:39 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.8%
[2025-01-19 04:21:39 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 04:21:41 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 04:21:41 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.76%
[2025-01-19 04:21:49 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.984 (7.984)	Loss 0.6968 (0.6968)	Acc@1 85.718 (85.718)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 04:21:52 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.046)	Loss 0.8814 (0.7703)	Acc@1 79.712 (83.720)	Acc@5 96.313 (96.784)	Mem 24308MB
[2025-01-19 04:21:52 internimage_s_1k_224] (main.py 575): INFO [Epoch:262] * Acc@1 83.587 Acc@5 96.801
[2025-01-19 04:21:52 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.6%
[2025-01-19 04:21:52 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:21:55 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:21:55 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.59%
[2025-01-19 04:21:57 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][0/312]	eta 0:11:41 lr 0.000187	time 2.2477 (2.2477)	model_time 0.6069 (0.6069)	loss 2.5700 (2.5700)	grad_norm 1.5543 (1.5543/0.0000)	mem 24308MB
[2025-01-19 04:22:03 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][10/312]	eta 0:03:48 lr 0.000187	time 0.6047 (0.7554)	model_time 0.6045 (0.6059)	loss 2.9527 (2.8108)	grad_norm 4.7596 (2.9093/1.1160)	mem 24308MB
[2025-01-19 04:22:09 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][20/312]	eta 0:03:17 lr 0.000186	time 0.5937 (0.6774)	model_time 0.5935 (0.5989)	loss 2.3729 (2.8699)	grad_norm 3.2897 (3.0086/0.9178)	mem 24308MB
[2025-01-19 04:22:15 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][30/312]	eta 0:03:05 lr 0.000186	time 0.6563 (0.6585)	model_time 0.6562 (0.6052)	loss 2.9449 (2.9331)	grad_norm 3.1384 (2.7413/0.9626)	mem 24308MB
[2025-01-19 04:22:21 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][40/312]	eta 0:02:56 lr 0.000186	time 0.5779 (0.6477)	model_time 0.5775 (0.6074)	loss 2.7036 (2.8919)	grad_norm 3.0913 (3.0864/1.2970)	mem 24308MB
[2025-01-19 04:22:28 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][50/312]	eta 0:02:49 lr 0.000186	time 0.5854 (0.6469)	model_time 0.5852 (0.6144)	loss 3.1729 (2.9167)	grad_norm 2.3977 (3.0672/1.2254)	mem 24308MB
[2025-01-19 04:22:34 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][60/312]	eta 0:02:41 lr 0.000185	time 0.5999 (0.6427)	model_time 0.5997 (0.6155)	loss 2.5941 (2.8525)	grad_norm 1.5144 (2.9863/1.2306)	mem 24308MB
[2025-01-19 04:22:40 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][70/312]	eta 0:02:34 lr 0.000185	time 0.6825 (0.6379)	model_time 0.6824 (0.6145)	loss 3.2603 (2.8800)	grad_norm 1.4862 (2.9658/1.1898)	mem 24308MB
[2025-01-19 04:22:46 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][80/312]	eta 0:02:26 lr 0.000185	time 0.5977 (0.6333)	model_time 0.5975 (0.6127)	loss 3.1280 (2.8294)	grad_norm 3.4862 (2.9457/1.1591)	mem 24308MB
[2025-01-19 04:22:52 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][90/312]	eta 0:02:19 lr 0.000185	time 0.5926 (0.6305)	model_time 0.5924 (0.6121)	loss 2.7624 (2.8371)	grad_norm 1.3450 (2.8522/1.1496)	mem 24308MB
[2025-01-19 04:22:58 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][100/312]	eta 0:02:13 lr 0.000184	time 0.6093 (0.6286)	model_time 0.6088 (0.6120)	loss 1.9382 (2.8097)	grad_norm 3.3551 (2.8246/1.1432)	mem 24308MB
[2025-01-19 04:23:04 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][110/312]	eta 0:02:06 lr 0.000184	time 0.6129 (0.6281)	model_time 0.6127 (0.6130)	loss 3.0922 (2.8153)	grad_norm 2.5977 (2.8468/1.1344)	mem 24308MB
[2025-01-19 04:23:10 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][120/312]	eta 0:02:00 lr 0.000184	time 0.5949 (0.6254)	model_time 0.5946 (0.6115)	loss 1.6983 (2.8116)	grad_norm 2.7878 (2.8405/1.1198)	mem 24308MB
[2025-01-19 04:23:16 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][130/312]	eta 0:01:53 lr 0.000184	time 0.6719 (0.6240)	model_time 0.6715 (0.6111)	loss 2.8826 (2.8045)	grad_norm 3.2218 (2.8219/1.1072)	mem 24308MB
[2025-01-19 04:23:22 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][140/312]	eta 0:01:46 lr 0.000183	time 0.5897 (0.6221)	model_time 0.5896 (0.6101)	loss 3.1065 (2.8107)	grad_norm 1.5302 (2.7790/1.1153)	mem 24308MB
[2025-01-19 04:23:28 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][150/312]	eta 0:01:40 lr 0.000183	time 0.7022 (0.6213)	model_time 0.7021 (0.6101)	loss 2.5377 (2.8103)	grad_norm 2.2958 (2.7729/1.1050)	mem 24308MB
[2025-01-19 04:23:35 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][160/312]	eta 0:01:34 lr 0.000183	time 0.6628 (0.6213)	model_time 0.6623 (0.6107)	loss 3.2175 (2.8085)	grad_norm 2.2896 (2.7600/1.0934)	mem 24308MB
[2025-01-19 04:23:41 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][170/312]	eta 0:01:28 lr 0.000183	time 0.5742 (0.6206)	model_time 0.5740 (0.6106)	loss 2.8102 (2.8033)	grad_norm 3.7473 (2.7690/1.0970)	mem 24308MB
[2025-01-19 04:23:47 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][180/312]	eta 0:01:22 lr 0.000182	time 0.6741 (0.6212)	model_time 0.6740 (0.6118)	loss 3.3176 (2.8112)	grad_norm 1.6588 (2.7549/1.1010)	mem 24308MB
[2025-01-19 04:23:53 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][190/312]	eta 0:01:15 lr 0.000182	time 0.5928 (0.6196)	model_time 0.5927 (0.6106)	loss 2.7230 (2.8038)	grad_norm 2.3190 (2.7450/1.0967)	mem 24308MB
[2025-01-19 04:23:59 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][200/312]	eta 0:01:09 lr 0.000182	time 0.5730 (0.6194)	model_time 0.5726 (0.6109)	loss 2.9151 (2.8028)	grad_norm 2.1996 (2.7754/1.1579)	mem 24308MB
[2025-01-19 04:24:05 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][210/312]	eta 0:01:03 lr 0.000182	time 0.5734 (0.6186)	model_time 0.5732 (0.6105)	loss 2.8451 (2.8019)	grad_norm 1.9953 (2.7509/1.1497)	mem 24308MB
[2025-01-19 04:24:11 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][220/312]	eta 0:00:56 lr 0.000181	time 0.5764 (0.6177)	model_time 0.5762 (0.6099)	loss 3.0973 (2.7936)	grad_norm 2.7410 (2.7232/1.1425)	mem 24308MB
[2025-01-19 04:24:17 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][230/312]	eta 0:00:50 lr 0.000181	time 0.6034 (0.6175)	model_time 0.6032 (0.6100)	loss 1.9797 (2.7864)	grad_norm 3.3031 (2.7088/1.1251)	mem 24308MB
[2025-01-19 04:24:23 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][240/312]	eta 0:00:44 lr 0.000181	time 0.5712 (0.6165)	model_time 0.5707 (0.6093)	loss 2.9478 (2.7981)	grad_norm 5.3360 (2.7648/1.1836)	mem 24308MB
[2025-01-19 04:24:29 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][250/312]	eta 0:00:38 lr 0.000181	time 0.6797 (0.6166)	model_time 0.6795 (0.6097)	loss 2.9060 (2.7998)	grad_norm 2.4239 (2.7536/1.1706)	mem 24308MB
[2025-01-19 04:24:35 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][260/312]	eta 0:00:32 lr 0.000180	time 0.5867 (0.6160)	model_time 0.5865 (0.6093)	loss 3.1482 (2.8005)	grad_norm 4.6344 (2.7541/1.1736)	mem 24308MB
[2025-01-19 04:24:41 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][270/312]	eta 0:00:25 lr 0.000180	time 0.5777 (0.6151)	model_time 0.5775 (0.6087)	loss 3.4130 (2.7974)	grad_norm 1.2929 (2.7484/1.1736)	mem 24308MB
[2025-01-19 04:24:48 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][280/312]	eta 0:00:19 lr 0.000180	time 0.5844 (0.6155)	model_time 0.5843 (0.6093)	loss 2.7683 (2.7943)	grad_norm 2.8629 (2.7800/1.1996)	mem 24308MB
[2025-01-19 04:24:54 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][290/312]	eta 0:00:13 lr 0.000180	time 0.6735 (0.6159)	model_time 0.6731 (0.6099)	loss 2.9573 (2.7980)	grad_norm 3.2965 (2.7698/1.1866)	mem 24308MB
[2025-01-19 04:25:00 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][300/312]	eta 0:00:07 lr 0.000179	time 0.6526 (0.6158)	model_time 0.6525 (0.6100)	loss 2.2413 (2.7921)	grad_norm 3.4788 (2.7761/1.1896)	mem 24308MB
[2025-01-19 04:25:06 internimage_s_1k_224] (main.py 510): INFO Train: [263/300][310/312]	eta 0:00:01 lr 0.000179	time 0.5705 (0.6146)	model_time 0.5704 (0.6090)	loss 3.2288 (2.7935)	grad_norm 3.2684 (2.7995/1.1932)	mem 24308MB
[2025-01-19 04:25:06 internimage_s_1k_224] (main.py 519): INFO EPOCH 263 training takes 0:03:11
[2025-01-19 04:25:06 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_263.pth saving......
[2025-01-19 04:25:08 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_263.pth saved !!!
[2025-01-19 04:25:16 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.963 (7.963)	Loss 0.7096 (0.7096)	Acc@1 86.108 (86.108)	Acc@5 97.852 (97.852)	Mem 24308MB
[2025-01-19 04:25:20 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.067)	Loss 0.8978 (0.7903)	Acc@1 80.444 (83.862)	Acc@5 95.874 (96.797)	Mem 24308MB
[2025-01-19 04:25:20 internimage_s_1k_224] (main.py 575): INFO [Epoch:263] * Acc@1 83.699 Acc@5 96.791
[2025-01-19 04:25:20 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.7%
[2025-01-19 04:25:20 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.76%
[2025-01-19 04:25:29 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.046 (9.046)	Loss 0.6964 (0.6964)	Acc@1 85.693 (85.693)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 04:25:34 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.221)	Loss 0.8807 (0.7698)	Acc@1 79.785 (83.751)	Acc@5 96.265 (96.780)	Mem 24308MB
[2025-01-19 04:25:34 internimage_s_1k_224] (main.py 575): INFO [Epoch:263] * Acc@1 83.617 Acc@5 96.795
[2025-01-19 04:25:34 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.6%
[2025-01-19 04:25:34 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:25:36 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:25:36 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.62%
[2025-01-19 04:25:39 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][0/312]	eta 0:13:00 lr 0.000179	time 2.5019 (2.5019)	model_time 0.5963 (0.5963)	loss 2.6977 (2.6977)	grad_norm 2.2659 (2.2659/0.0000)	mem 24308MB
[2025-01-19 04:25:45 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][10/312]	eta 0:03:57 lr 0.000179	time 0.5845 (0.7871)	model_time 0.5842 (0.6135)	loss 2.0148 (2.7806)	grad_norm 1.5642 (2.5256/0.8933)	mem 24308MB
[2025-01-19 04:25:51 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][20/312]	eta 0:03:25 lr 0.000179	time 0.5927 (0.7035)	model_time 0.5925 (0.6125)	loss 2.9385 (2.8366)	grad_norm 2.5588 (2.3067/0.7465)	mem 24308MB
[2025-01-19 04:25:57 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][30/312]	eta 0:03:09 lr 0.000178	time 0.5742 (0.6724)	model_time 0.5737 (0.6106)	loss 3.0887 (2.7050)	grad_norm 2.2969 (2.3430/0.7559)	mem 24308MB
[2025-01-19 04:26:03 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][40/312]	eta 0:02:58 lr 0.000178	time 0.5908 (0.6565)	model_time 0.5906 (0.6097)	loss 2.9831 (2.7435)	grad_norm 5.5102 (2.4989/0.9521)	mem 24308MB
[2025-01-19 04:26:09 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][50/312]	eta 0:02:49 lr 0.000178	time 0.6556 (0.6454)	model_time 0.6551 (0.6077)	loss 2.8871 (2.7941)	grad_norm 4.3106 (2.6438/1.0691)	mem 24308MB
[2025-01-19 04:26:15 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][60/312]	eta 0:02:40 lr 0.000178	time 0.5860 (0.6389)	model_time 0.5859 (0.6073)	loss 2.8835 (2.7905)	grad_norm 2.2267 (2.7296/1.0811)	mem 24308MB
[2025-01-19 04:26:21 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][70/312]	eta 0:02:33 lr 0.000177	time 0.5749 (0.6326)	model_time 0.5744 (0.6054)	loss 1.8670 (2.7866)	grad_norm 3.2643 (2.9153/1.1705)	mem 24308MB
[2025-01-19 04:26:27 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][80/312]	eta 0:02:25 lr 0.000177	time 0.5728 (0.6284)	model_time 0.5726 (0.6046)	loss 3.1606 (2.7999)	grad_norm 1.6136 (2.9278/1.1721)	mem 24308MB
[2025-01-19 04:26:33 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][90/312]	eta 0:02:19 lr 0.000177	time 0.5973 (0.6267)	model_time 0.5968 (0.6054)	loss 2.7026 (2.8188)	grad_norm 1.7994 (2.8547/1.1669)	mem 24308MB
[2025-01-19 04:26:40 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][100/312]	eta 0:02:12 lr 0.000177	time 0.6581 (0.6264)	model_time 0.6579 (0.6072)	loss 2.0934 (2.8061)	grad_norm 6.4981 (2.8555/1.1872)	mem 24308MB
[2025-01-19 04:26:46 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][110/312]	eta 0:02:06 lr 0.000176	time 0.6565 (0.6253)	model_time 0.6564 (0.6078)	loss 2.9497 (2.8104)	grad_norm 3.8892 (2.8333/1.1496)	mem 24308MB
[2025-01-19 04:26:52 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][120/312]	eta 0:01:59 lr 0.000176	time 0.5877 (0.6246)	model_time 0.5872 (0.6085)	loss 2.7280 (2.7979)	grad_norm 1.4322 (2.7982/1.1295)	mem 24308MB
[2025-01-19 04:26:58 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][130/312]	eta 0:01:53 lr 0.000176	time 0.5972 (0.6236)	model_time 0.5971 (0.6086)	loss 2.7553 (2.8074)	grad_norm 3.1442 (2.8323/1.1508)	mem 24308MB
[2025-01-19 04:27:04 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][140/312]	eta 0:01:47 lr 0.000176	time 0.5894 (0.6224)	model_time 0.5889 (0.6085)	loss 3.4944 (2.8209)	grad_norm 1.8746 (2.8196/1.1441)	mem 24308MB
[2025-01-19 04:27:10 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][150/312]	eta 0:01:40 lr 0.000175	time 0.6591 (0.6225)	model_time 0.6589 (0.6095)	loss 2.1808 (2.8236)	grad_norm 2.0139 (2.8035/1.1406)	mem 24308MB
[2025-01-19 04:27:16 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][160/312]	eta 0:01:34 lr 0.000175	time 0.5946 (0.6216)	model_time 0.5942 (0.6094)	loss 2.1647 (2.8170)	grad_norm 7.2624 (2.7840/1.1801)	mem 24308MB
[2025-01-19 04:27:22 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][170/312]	eta 0:01:28 lr 0.000175	time 0.5958 (0.6200)	model_time 0.5956 (0.6085)	loss 3.2784 (2.8237)	grad_norm 2.1748 (2.8155/1.1709)	mem 24308MB
[2025-01-19 04:27:28 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][180/312]	eta 0:01:21 lr 0.000175	time 0.5948 (0.6193)	model_time 0.5946 (0.6084)	loss 3.1635 (2.8385)	grad_norm 1.7608 (2.7895/1.1559)	mem 24308MB
[2025-01-19 04:27:34 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][190/312]	eta 0:01:15 lr 0.000174	time 0.5827 (0.6180)	model_time 0.5822 (0.6077)	loss 3.1126 (2.8404)	grad_norm 1.0936 (2.7700/1.1376)	mem 24308MB
[2025-01-19 04:27:40 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][200/312]	eta 0:01:09 lr 0.000174	time 0.6263 (0.6171)	model_time 0.6258 (0.6073)	loss 3.5159 (2.8339)	grad_norm 2.1668 (2.7486/1.1224)	mem 24308MB
[2025-01-19 04:27:46 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][210/312]	eta 0:01:02 lr 0.000174	time 0.5770 (0.6170)	model_time 0.5766 (0.6076)	loss 2.8594 (2.8291)	grad_norm 1.5703 (2.7455/1.1169)	mem 24308MB
[2025-01-19 04:27:53 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][220/312]	eta 0:00:56 lr 0.000174	time 0.5883 (0.6165)	model_time 0.5879 (0.6075)	loss 3.0403 (2.8302)	grad_norm 2.8762 (2.7456/1.1100)	mem 24308MB
[2025-01-19 04:27:59 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][230/312]	eta 0:00:50 lr 0.000173	time 0.5878 (0.6169)	model_time 0.5876 (0.6083)	loss 2.8463 (2.8320)	grad_norm 2.2096 (2.7424/1.1135)	mem 24308MB
[2025-01-19 04:28:05 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][240/312]	eta 0:00:44 lr 0.000173	time 0.5734 (0.6170)	model_time 0.5729 (0.6086)	loss 3.3510 (2.8365)	grad_norm 2.7851 (2.7390/1.1103)	mem 24308MB
[2025-01-19 04:28:11 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][250/312]	eta 0:00:38 lr 0.000173	time 0.6593 (0.6169)	model_time 0.6589 (0.6089)	loss 2.9179 (2.8442)	grad_norm 3.2887 (2.7259/1.1037)	mem 24308MB
[2025-01-19 04:28:17 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][260/312]	eta 0:00:32 lr 0.000173	time 0.5976 (0.6164)	model_time 0.5971 (0.6087)	loss 3.2317 (2.8447)	grad_norm 1.3535 (2.7101/1.0934)	mem 24308MB
[2025-01-19 04:28:23 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][270/312]	eta 0:00:25 lr 0.000173	time 0.5850 (0.6155)	model_time 0.5846 (0.6081)	loss 2.6241 (2.8349)	grad_norm 6.7434 (2.7317/1.1124)	mem 24308MB
[2025-01-19 04:28:29 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][280/312]	eta 0:00:19 lr 0.000172	time 0.8453 (0.6160)	model_time 0.8451 (0.6088)	loss 2.8969 (2.8357)	grad_norm 4.1988 (2.7811/1.1595)	mem 24308MB
[2025-01-19 04:28:35 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][290/312]	eta 0:00:13 lr 0.000172	time 0.5886 (0.6150)	model_time 0.5881 (0.6080)	loss 2.9877 (2.8311)	grad_norm 1.8927 (2.7775/1.1437)	mem 24308MB
[2025-01-19 04:28:41 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][300/312]	eta 0:00:07 lr 0.000172	time 0.5635 (0.6143)	model_time 0.5633 (0.6076)	loss 2.0378 (2.8162)	grad_norm 6.0083 (2.7845/1.1526)	mem 24308MB
[2025-01-19 04:28:47 internimage_s_1k_224] (main.py 510): INFO Train: [264/300][310/312]	eta 0:00:01 lr 0.000172	time 0.5699 (0.6132)	model_time 0.5698 (0.6067)	loss 2.8639 (2.8217)	grad_norm 2.3372 (2.7939/1.1567)	mem 24308MB
[2025-01-19 04:28:48 internimage_s_1k_224] (main.py 519): INFO EPOCH 264 training takes 0:03:11
[2025-01-19 04:28:48 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_264.pth saving......
[2025-01-19 04:28:49 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_264.pth saved !!!
[2025-01-19 04:28:57 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.745 (7.745)	Loss 0.7126 (0.7126)	Acc@1 86.133 (86.133)	Acc@5 97.705 (97.705)	Mem 24308MB
[2025-01-19 04:29:01 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.049)	Loss 0.9057 (0.7914)	Acc@1 80.273 (83.964)	Acc@5 95.801 (96.746)	Mem 24308MB
[2025-01-19 04:29:01 internimage_s_1k_224] (main.py 575): INFO [Epoch:264] * Acc@1 83.781 Acc@5 96.747
[2025-01-19 04:29:01 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.8%
[2025-01-19 04:29:01 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 04:29:03 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 04:29:03 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.78%
[2025-01-19 04:29:18 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 14.370 (14.370)	Loss 0.6960 (0.6960)	Acc@1 85.693 (85.693)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 04:29:25 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (2.006)	Loss 0.8799 (0.7693)	Acc@1 79.761 (83.769)	Acc@5 96.216 (96.786)	Mem 24308MB
[2025-01-19 04:29:25 internimage_s_1k_224] (main.py 575): INFO [Epoch:264] * Acc@1 83.643 Acc@5 96.805
[2025-01-19 04:29:25 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.6%
[2025-01-19 04:29:25 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:29:28 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:29:28 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.64%
[2025-01-19 04:29:30 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][0/312]	eta 0:11:37 lr 0.000172	time 2.2367 (2.2367)	model_time 0.5983 (0.5983)	loss 2.8673 (2.8673)	grad_norm 5.6317 (5.6317/0.0000)	mem 24308MB
[2025-01-19 04:29:36 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][10/312]	eta 0:03:48 lr 0.000171	time 0.5776 (0.7576)	model_time 0.5774 (0.6075)	loss 3.4393 (2.7222)	grad_norm 2.0360 (3.7076/1.3398)	mem 24308MB
[2025-01-19 04:29:42 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][20/312]	eta 0:03:23 lr 0.000171	time 0.5862 (0.6978)	model_time 0.5860 (0.6190)	loss 1.7078 (2.7980)	grad_norm 4.6472 (3.9757/1.5749)	mem 24308MB
[2025-01-19 04:29:49 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][30/312]	eta 0:03:09 lr 0.000171	time 0.5882 (0.6734)	model_time 0.5878 (0.6199)	loss 2.7953 (2.7908)	grad_norm 1.6073 (3.7283/1.4352)	mem 24308MB
[2025-01-19 04:29:55 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][40/312]	eta 0:02:59 lr 0.000171	time 0.5843 (0.6594)	model_time 0.5839 (0.6189)	loss 2.7825 (2.7958)	grad_norm 2.3643 (3.4438/1.4059)	mem 24308MB
[2025-01-19 04:30:01 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][50/312]	eta 0:02:50 lr 0.000170	time 0.6054 (0.6494)	model_time 0.6052 (0.6168)	loss 2.9584 (2.7789)	grad_norm 3.8959 (3.2135/1.3811)	mem 24308MB
[2025-01-19 04:30:07 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][60/312]	eta 0:02:41 lr 0.000170	time 0.6020 (0.6420)	model_time 0.6019 (0.6146)	loss 3.1165 (2.7527)	grad_norm 1.7979 (3.0147/1.3520)	mem 24308MB
[2025-01-19 04:30:13 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][70/312]	eta 0:02:34 lr 0.000170	time 0.5876 (0.6372)	model_time 0.5872 (0.6136)	loss 2.6721 (2.7418)	grad_norm 2.4294 (2.9786/1.2956)	mem 24308MB
[2025-01-19 04:30:19 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][80/312]	eta 0:02:26 lr 0.000170	time 0.6557 (0.6316)	model_time 0.6553 (0.6109)	loss 3.4535 (2.7837)	grad_norm 5.0111 (3.1134/1.6370)	mem 24308MB
[2025-01-19 04:30:25 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][90/312]	eta 0:02:19 lr 0.000169	time 0.6973 (0.6295)	model_time 0.6972 (0.6111)	loss 2.8250 (2.7904)	grad_norm 5.3792 (3.1662/1.6566)	mem 24308MB
[2025-01-19 04:30:31 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][100/312]	eta 0:02:12 lr 0.000169	time 0.6038 (0.6255)	model_time 0.6034 (0.6088)	loss 2.0851 (2.7772)	grad_norm 1.6280 (3.1013/1.6176)	mem 24308MB
[2025-01-19 04:30:37 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][110/312]	eta 0:02:05 lr 0.000169	time 0.5867 (0.6237)	model_time 0.5866 (0.6085)	loss 3.0528 (2.7817)	grad_norm 1.8221 (3.0166/1.5805)	mem 24308MB
[2025-01-19 04:30:43 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][120/312]	eta 0:01:59 lr 0.000169	time 0.5937 (0.6216)	model_time 0.5936 (0.6076)	loss 3.0215 (2.7743)	grad_norm 4.6015 (2.9702/1.5382)	mem 24308MB
[2025-01-19 04:30:49 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][130/312]	eta 0:01:52 lr 0.000168	time 0.7494 (0.6203)	model_time 0.7492 (0.6074)	loss 1.5019 (2.7737)	grad_norm 1.8239 (2.9527/1.5162)	mem 24308MB
[2025-01-19 04:30:55 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][140/312]	eta 0:01:46 lr 0.000168	time 0.6840 (0.6211)	model_time 0.6838 (0.6091)	loss 2.8816 (2.7545)	grad_norm 3.6520 (2.9155/1.4811)	mem 24308MB
[2025-01-19 04:31:01 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][150/312]	eta 0:01:40 lr 0.000168	time 0.5749 (0.6213)	model_time 0.5747 (0.6100)	loss 3.6078 (2.7721)	grad_norm 2.4444 (2.8988/1.4667)	mem 24308MB
[2025-01-19 04:31:08 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][160/312]	eta 0:01:34 lr 0.000168	time 0.5946 (0.6215)	model_time 0.5942 (0.6109)	loss 3.2838 (2.7714)	grad_norm 2.8982 (2.9385/1.4926)	mem 24308MB
[2025-01-19 04:31:14 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][170/312]	eta 0:01:28 lr 0.000167	time 0.5916 (0.6204)	model_time 0.5915 (0.6105)	loss 3.1393 (2.7794)	grad_norm 3.9360 (2.9816/1.4864)	mem 24308MB
[2025-01-19 04:31:20 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][180/312]	eta 0:01:21 lr 0.000167	time 0.6125 (0.6201)	model_time 0.6123 (0.6107)	loss 2.5971 (2.7870)	grad_norm 2.8359 (2.9785/1.4621)	mem 24308MB
[2025-01-19 04:31:26 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][190/312]	eta 0:01:15 lr 0.000167	time 0.5779 (0.6195)	model_time 0.5777 (0.6105)	loss 2.2104 (2.7845)	grad_norm 2.0369 (2.9438/1.4405)	mem 24308MB
[2025-01-19 04:31:32 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][200/312]	eta 0:01:09 lr 0.000167	time 0.5931 (0.6181)	model_time 0.5926 (0.6096)	loss 2.8598 (2.7894)	grad_norm 2.0755 (2.9521/1.4370)	mem 24308MB
[2025-01-19 04:31:38 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][210/312]	eta 0:01:03 lr 0.000167	time 0.6038 (0.6178)	model_time 0.6036 (0.6096)	loss 2.1685 (2.7803)	grad_norm 2.1717 (2.9433/1.4108)	mem 24308MB
[2025-01-19 04:31:44 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][220/312]	eta 0:00:56 lr 0.000166	time 0.5951 (0.6166)	model_time 0.5946 (0.6088)	loss 2.7374 (2.7862)	grad_norm 6.9633 (2.9865/1.4454)	mem 24308MB
[2025-01-19 04:31:50 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][230/312]	eta 0:00:50 lr 0.000166	time 0.5869 (0.6164)	model_time 0.5867 (0.6090)	loss 2.4367 (2.7925)	grad_norm 1.9180 (3.0028/1.4556)	mem 24308MB
[2025-01-19 04:31:56 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][240/312]	eta 0:00:44 lr 0.000166	time 0.5734 (0.6157)	model_time 0.5733 (0.6085)	loss 3.2368 (2.7815)	grad_norm 3.2864 (2.9903/1.4379)	mem 24308MB
[2025-01-19 04:32:02 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][250/312]	eta 0:00:38 lr 0.000166	time 0.7023 (0.6152)	model_time 0.7022 (0.6082)	loss 3.2308 (2.7894)	grad_norm 4.0333 (3.0152/1.4290)	mem 24308MB
[2025-01-19 04:32:09 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][260/312]	eta 0:00:32 lr 0.000165	time 0.5814 (0.6162)	model_time 0.5810 (0.6096)	loss 2.9909 (2.7939)	grad_norm 2.9147 (3.0225/1.4322)	mem 24308MB
[2025-01-19 04:32:15 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][270/312]	eta 0:00:25 lr 0.000165	time 0.6726 (0.6172)	model_time 0.6725 (0.6107)	loss 2.7019 (2.7932)	grad_norm 3.0837 (3.0378/1.4133)	mem 24308MB
[2025-01-19 04:32:21 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][280/312]	eta 0:00:19 lr 0.000165	time 0.5836 (0.6166)	model_time 0.5832 (0.6104)	loss 3.0248 (2.7911)	grad_norm 3.4063 (3.0417/1.4171)	mem 24308MB
[2025-01-19 04:32:27 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][290/312]	eta 0:00:13 lr 0.000165	time 0.6191 (0.6164)	model_time 0.6186 (0.6104)	loss 1.8693 (2.7930)	grad_norm 3.5821 (3.0605/1.4150)	mem 24308MB
[2025-01-19 04:32:33 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][300/312]	eta 0:00:07 lr 0.000164	time 0.5690 (0.6158)	model_time 0.5689 (0.6100)	loss 2.9270 (2.7909)	grad_norm 3.0500 (3.0420/1.3956)	mem 24308MB
[2025-01-19 04:32:39 internimage_s_1k_224] (main.py 510): INFO Train: [265/300][310/312]	eta 0:00:01 lr 0.000164	time 0.5747 (0.6156)	model_time 0.5746 (0.6099)	loss 2.9722 (2.7887)	grad_norm 2.3972 (3.0081/1.3884)	mem 24308MB
[2025-01-19 04:32:40 internimage_s_1k_224] (main.py 519): INFO EPOCH 265 training takes 0:03:12
[2025-01-19 04:32:40 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_265.pth saving......
[2025-01-19 04:32:42 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_265.pth saved !!!
[2025-01-19 04:32:49 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.673 (7.673)	Loss 0.7017 (0.7017)	Acc@1 86.353 (86.353)	Acc@5 97.754 (97.754)	Mem 24308MB
[2025-01-19 04:32:53 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.053)	Loss 0.8991 (0.7833)	Acc@1 80.420 (84.011)	Acc@5 95.801 (96.731)	Mem 24308MB
[2025-01-19 04:32:53 internimage_s_1k_224] (main.py 575): INFO [Epoch:265] * Acc@1 83.843 Acc@5 96.741
[2025-01-19 04:32:53 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.8%
[2025-01-19 04:32:53 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 04:32:55 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 04:32:55 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.84%
[2025-01-19 04:33:03 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.775 (7.775)	Loss 0.6957 (0.6957)	Acc@1 85.742 (85.742)	Acc@5 97.852 (97.852)	Mem 24308MB
[2025-01-19 04:33:07 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.135 (1.035)	Loss 0.8793 (0.7689)	Acc@1 79.858 (83.789)	Acc@5 96.191 (96.786)	Mem 24308MB
[2025-01-19 04:33:07 internimage_s_1k_224] (main.py 575): INFO [Epoch:265] * Acc@1 83.663 Acc@5 96.803
[2025-01-19 04:33:07 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.7%
[2025-01-19 04:33:07 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:33:09 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:33:09 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.66%
[2025-01-19 04:33:12 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][0/312]	eta 0:12:38 lr 0.000164	time 2.4327 (2.4327)	model_time 0.6202 (0.6202)	loss 3.0399 (3.0399)	grad_norm 2.6926 (2.6926/0.0000)	mem 24308MB
[2025-01-19 04:33:18 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][10/312]	eta 0:03:49 lr 0.000164	time 0.5999 (0.7611)	model_time 0.5997 (0.5960)	loss 2.9676 (2.8038)	grad_norm 2.9977 (2.9226/0.7314)	mem 24308MB
[2025-01-19 04:33:24 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][20/312]	eta 0:03:20 lr 0.000164	time 0.5995 (0.6867)	model_time 0.5990 (0.6000)	loss 2.9668 (2.7582)	grad_norm 2.9084 (2.7196/0.8102)	mem 24308MB
[2025-01-19 04:33:30 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][30/312]	eta 0:03:06 lr 0.000163	time 0.5840 (0.6607)	model_time 0.5837 (0.6019)	loss 2.1988 (2.7521)	grad_norm 2.8384 (2.7863/0.8035)	mem 24308MB
[2025-01-19 04:33:36 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][40/312]	eta 0:02:55 lr 0.000163	time 0.5785 (0.6459)	model_time 0.5783 (0.6013)	loss 3.3805 (2.7366)	grad_norm 2.4309 (3.0371/1.0887)	mem 24308MB
[2025-01-19 04:33:42 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][50/312]	eta 0:02:46 lr 0.000163	time 0.5937 (0.6370)	model_time 0.5935 (0.6011)	loss 3.1330 (2.7447)	grad_norm 1.2040 (2.8970/1.0679)	mem 24308MB
[2025-01-19 04:33:48 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][60/312]	eta 0:02:38 lr 0.000163	time 0.5758 (0.6291)	model_time 0.5757 (0.5991)	loss 2.4133 (2.7359)	grad_norm 3.0642 (2.8052/1.0320)	mem 24308MB
[2025-01-19 04:33:54 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][70/312]	eta 0:02:32 lr 0.000163	time 0.5768 (0.6287)	model_time 0.5764 (0.6028)	loss 2.1601 (2.7052)	grad_norm 2.2045 (2.7848/1.0082)	mem 24308MB
[2025-01-19 04:34:00 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][80/312]	eta 0:02:25 lr 0.000162	time 0.5848 (0.6288)	model_time 0.5846 (0.6061)	loss 2.9060 (2.7403)	grad_norm 2.2094 (2.8022/1.0165)	mem 24308MB
[2025-01-19 04:34:06 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][90/312]	eta 0:02:19 lr 0.000162	time 0.6797 (0.6286)	model_time 0.6795 (0.6083)	loss 3.1858 (2.7596)	grad_norm 2.2713 (2.7847/0.9732)	mem 24308MB
[2025-01-19 04:34:13 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][100/312]	eta 0:02:12 lr 0.000162	time 0.5778 (0.6263)	model_time 0.5776 (0.6080)	loss 2.9545 (2.7687)	grad_norm 2.2899 (2.7656/0.9817)	mem 24308MB
[2025-01-19 04:34:19 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][110/312]	eta 0:02:06 lr 0.000162	time 0.5844 (0.6262)	model_time 0.5843 (0.6095)	loss 3.1630 (2.7604)	grad_norm 4.0755 (2.8522/1.0917)	mem 24308MB
[2025-01-19 04:34:25 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][120/312]	eta 0:01:59 lr 0.000161	time 0.5854 (0.6246)	model_time 0.5853 (0.6092)	loss 2.2097 (2.7564)	grad_norm 1.9996 (2.8904/1.2472)	mem 24308MB
[2025-01-19 04:34:31 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][130/312]	eta 0:01:53 lr 0.000161	time 0.5755 (0.6218)	model_time 0.5754 (0.6076)	loss 2.6289 (2.7692)	grad_norm 2.9252 (2.8707/1.2164)	mem 24308MB
[2025-01-19 04:34:37 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][140/312]	eta 0:01:46 lr 0.000161	time 0.5935 (0.6216)	model_time 0.5934 (0.6083)	loss 2.9737 (2.7760)	grad_norm 1.2725 (2.8590/1.1881)	mem 24308MB
[2025-01-19 04:34:43 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][150/312]	eta 0:01:40 lr 0.000161	time 0.5777 (0.6198)	model_time 0.5772 (0.6074)	loss 3.3585 (2.7807)	grad_norm 4.6820 (2.8801/1.1839)	mem 24308MB
[2025-01-19 04:34:49 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][160/312]	eta 0:01:34 lr 0.000161	time 0.5742 (0.6184)	model_time 0.5741 (0.6068)	loss 3.2105 (2.7849)	grad_norm 1.8368 (2.9499/1.2743)	mem 24308MB
[2025-01-19 04:34:55 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][170/312]	eta 0:01:27 lr 0.000160	time 0.5845 (0.6170)	model_time 0.5843 (0.6061)	loss 2.9245 (2.7805)	grad_norm 2.4985 (3.0055/1.3535)	mem 24308MB
[2025-01-19 04:35:01 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][180/312]	eta 0:01:21 lr 0.000160	time 0.5843 (0.6157)	model_time 0.5838 (0.6053)	loss 3.3243 (2.7887)	grad_norm 1.7842 (3.0046/1.3426)	mem 24308MB
[2025-01-19 04:35:07 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][190/312]	eta 0:01:15 lr 0.000160	time 0.6782 (0.6173)	model_time 0.6779 (0.6074)	loss 3.0079 (2.7732)	grad_norm 2.4131 (2.9571/1.3273)	mem 24308MB
[2025-01-19 04:35:13 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][200/312]	eta 0:01:09 lr 0.000160	time 0.5912 (0.6171)	model_time 0.5908 (0.6077)	loss 2.9994 (2.7814)	grad_norm 2.6253 (2.9351/1.3133)	mem 24308MB
[2025-01-19 04:35:20 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][210/312]	eta 0:01:02 lr 0.000159	time 0.6904 (0.6175)	model_time 0.6903 (0.6085)	loss 3.1378 (2.7860)	grad_norm 3.1644 (2.9602/1.3039)	mem 24308MB
[2025-01-19 04:35:26 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][220/312]	eta 0:00:56 lr 0.000159	time 0.6123 (0.6175)	model_time 0.6121 (0.6088)	loss 3.1671 (2.7948)	grad_norm 2.8966 (3.0114/1.3458)	mem 24308MB
[2025-01-19 04:35:32 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][230/312]	eta 0:00:50 lr 0.000159	time 0.6506 (0.6168)	model_time 0.6501 (0.6085)	loss 3.5006 (2.8008)	grad_norm 3.6659 (3.0262/1.3380)	mem 24308MB
[2025-01-19 04:35:38 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][240/312]	eta 0:00:44 lr 0.000159	time 0.6860 (0.6168)	model_time 0.6856 (0.6088)	loss 3.2864 (2.8000)	grad_norm 4.2044 (3.0149/1.3199)	mem 24308MB
[2025-01-19 04:35:44 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][250/312]	eta 0:00:38 lr 0.000158	time 0.5825 (0.6156)	model_time 0.5821 (0.6079)	loss 3.4354 (2.8013)	grad_norm 2.1910 (3.0355/1.3274)	mem 24308MB
[2025-01-19 04:35:50 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][260/312]	eta 0:00:32 lr 0.000158	time 0.5884 (0.6156)	model_time 0.5883 (0.6082)	loss 2.0068 (2.7886)	grad_norm 2.9264 (3.0657/1.3310)	mem 24308MB
[2025-01-19 04:35:56 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][270/312]	eta 0:00:25 lr 0.000158	time 0.5834 (0.6148)	model_time 0.5829 (0.6077)	loss 3.1290 (2.7984)	grad_norm 3.3116 (3.0837/1.3551)	mem 24308MB
[2025-01-19 04:36:02 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][280/312]	eta 0:00:19 lr 0.000158	time 0.5737 (0.6145)	model_time 0.5736 (0.6076)	loss 3.2647 (2.8016)	grad_norm 3.9021 (3.0865/1.3462)	mem 24308MB
[2025-01-19 04:36:08 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][290/312]	eta 0:00:13 lr 0.000158	time 0.6176 (0.6137)	model_time 0.6173 (0.6070)	loss 3.1015 (2.8069)	grad_norm 5.4541 (3.1140/1.3499)	mem 24308MB
[2025-01-19 04:36:14 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][300/312]	eta 0:00:07 lr 0.000157	time 0.5693 (0.6130)	model_time 0.5692 (0.6065)	loss 1.9987 (2.8035)	grad_norm 4.1010 (3.1138/1.3395)	mem 24308MB
[2025-01-19 04:36:20 internimage_s_1k_224] (main.py 510): INFO Train: [266/300][310/312]	eta 0:00:01 lr 0.000157	time 0.6698 (0.6126)	model_time 0.6697 (0.6063)	loss 2.4246 (2.8020)	grad_norm 4.4498 (3.1426/1.3474)	mem 24308MB
[2025-01-19 04:36:20 internimage_s_1k_224] (main.py 519): INFO EPOCH 266 training takes 0:03:11
[2025-01-19 04:36:20 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_266.pth saving......
[2025-01-19 04:36:22 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_266.pth saved !!!
[2025-01-19 04:36:30 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.741 (7.741)	Loss 0.6985 (0.6985)	Acc@1 86.133 (86.133)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 04:36:34 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.033)	Loss 0.9013 (0.7891)	Acc@1 79.932 (84.013)	Acc@5 95.996 (96.813)	Mem 24308MB
[2025-01-19 04:36:34 internimage_s_1k_224] (main.py 575): INFO [Epoch:266] * Acc@1 83.829 Acc@5 96.797
[2025-01-19 04:36:34 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.8%
[2025-01-19 04:36:34 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.84%
[2025-01-19 04:36:43 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.958 (8.958)	Loss 0.6952 (0.6952)	Acc@1 85.791 (85.791)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 04:36:47 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.211)	Loss 0.8786 (0.7684)	Acc@1 79.810 (83.794)	Acc@5 96.167 (96.786)	Mem 24308MB
[2025-01-19 04:36:47 internimage_s_1k_224] (main.py 575): INFO [Epoch:266] * Acc@1 83.671 Acc@5 96.799
[2025-01-19 04:36:47 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.7%
[2025-01-19 04:36:47 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:36:50 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:36:50 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.67%
[2025-01-19 04:36:52 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][0/312]	eta 0:13:52 lr 0.000157	time 2.6685 (2.6685)	model_time 0.6063 (0.6063)	loss 3.0970 (3.0970)	grad_norm 3.6279 (3.6279/0.0000)	mem 24308MB
[2025-01-19 04:36:59 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][10/312]	eta 0:04:04 lr 0.000157	time 0.5836 (0.8099)	model_time 0.5835 (0.6221)	loss 3.2553 (2.8975)	grad_norm 1.3722 (2.3971/0.7723)	mem 24308MB
[2025-01-19 04:37:05 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][20/312]	eta 0:03:28 lr 0.000157	time 0.5972 (0.7144)	model_time 0.5970 (0.6159)	loss 3.2708 (2.8624)	grad_norm 2.9695 (3.0766/1.6321)	mem 24308MB
[2025-01-19 04:37:11 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][30/312]	eta 0:03:14 lr 0.000156	time 0.6078 (0.6889)	model_time 0.6077 (0.6221)	loss 2.4475 (2.7457)	grad_norm 1.5337 (2.9895/1.4884)	mem 24308MB
[2025-01-19 04:37:17 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][40/312]	eta 0:03:01 lr 0.000156	time 0.6690 (0.6677)	model_time 0.6689 (0.6171)	loss 2.7650 (2.7508)	grad_norm 5.4855 (3.2503/1.5090)	mem 24308MB
[2025-01-19 04:37:23 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][50/312]	eta 0:02:51 lr 0.000156	time 0.5872 (0.6559)	model_time 0.5870 (0.6152)	loss 2.6412 (2.7467)	grad_norm 5.1280 (3.2947/1.4744)	mem 24308MB
[2025-01-19 04:37:29 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][60/312]	eta 0:02:42 lr 0.000156	time 0.5769 (0.6458)	model_time 0.5765 (0.6117)	loss 1.9570 (2.7214)	grad_norm 2.1415 (3.3003/1.5559)	mem 24308MB
[2025-01-19 04:37:35 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][70/312]	eta 0:02:34 lr 0.000155	time 0.5858 (0.6400)	model_time 0.5856 (0.6107)	loss 2.8278 (2.7254)	grad_norm 2.1801 (3.1486/1.5046)	mem 24308MB
[2025-01-19 04:37:41 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][80/312]	eta 0:02:27 lr 0.000155	time 0.5936 (0.6348)	model_time 0.5931 (0.6090)	loss 2.6345 (2.7093)	grad_norm 3.4586 (3.0652/1.4483)	mem 24308MB
[2025-01-19 04:37:47 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][90/312]	eta 0:02:20 lr 0.000155	time 0.6605 (0.6319)	model_time 0.6603 (0.6089)	loss 3.1172 (2.7304)	grad_norm 2.4484 (2.9694/1.4175)	mem 24308MB
[2025-01-19 04:37:53 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][100/312]	eta 0:02:13 lr 0.000155	time 0.6064 (0.6279)	model_time 0.6060 (0.6071)	loss 2.6060 (2.7232)	grad_norm 2.4539 (2.9139/1.3815)	mem 24308MB
[2025-01-19 04:37:59 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][110/312]	eta 0:02:06 lr 0.000155	time 0.5993 (0.6250)	model_time 0.5991 (0.6061)	loss 3.3451 (2.7431)	grad_norm 3.2368 (2.8570/1.3523)	mem 24308MB
[2025-01-19 04:38:05 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][120/312]	eta 0:01:59 lr 0.000154	time 0.6119 (0.6243)	model_time 0.6115 (0.6069)	loss 2.7829 (2.7501)	grad_norm 1.9685 (2.8108/1.3135)	mem 24308MB
[2025-01-19 04:38:12 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][130/312]	eta 0:01:53 lr 0.000154	time 0.5898 (0.6256)	model_time 0.5897 (0.6095)	loss 1.9936 (2.7438)	grad_norm 1.3329 (2.7384/1.2926)	mem 24308MB
[2025-01-19 04:38:18 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][140/312]	eta 0:01:47 lr 0.000154	time 0.5782 (0.6243)	model_time 0.5781 (0.6093)	loss 3.0192 (2.7350)	grad_norm 2.3019 (2.7200/1.2662)	mem 24308MB
[2025-01-19 04:38:24 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][150/312]	eta 0:01:41 lr 0.000154	time 0.5864 (0.6236)	model_time 0.5862 (0.6096)	loss 2.7120 (2.7392)	grad_norm 5.9641 (2.7677/1.2927)	mem 24308MB
[2025-01-19 04:38:30 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][160/312]	eta 0:01:34 lr 0.000153	time 0.6733 (0.6227)	model_time 0.6731 (0.6095)	loss 2.9470 (2.7647)	grad_norm 6.8717 (2.9127/1.4943)	mem 24308MB
[2025-01-19 04:38:36 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][170/312]	eta 0:01:28 lr 0.000153	time 0.6062 (0.6220)	model_time 0.6060 (0.6096)	loss 3.1711 (2.7704)	grad_norm 3.8229 (2.9798/1.5537)	mem 24308MB
[2025-01-19 04:38:42 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][180/312]	eta 0:01:21 lr 0.000153	time 0.6432 (0.6209)	model_time 0.6427 (0.6091)	loss 2.6652 (2.7751)	grad_norm 2.9721 (3.0299/1.5799)	mem 24308MB
[2025-01-19 04:38:48 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][190/312]	eta 0:01:15 lr 0.000153	time 0.5874 (0.6208)	model_time 0.5872 (0.6096)	loss 2.4573 (2.7687)	grad_norm 1.2001 (3.0581/1.5748)	mem 24308MB
[2025-01-19 04:38:54 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][200/312]	eta 0:01:09 lr 0.000153	time 0.5938 (0.6195)	model_time 0.5934 (0.6089)	loss 2.7855 (2.7751)	grad_norm 2.2737 (3.0600/1.5450)	mem 24308MB
[2025-01-19 04:39:00 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][210/312]	eta 0:01:03 lr 0.000152	time 0.6625 (0.6187)	model_time 0.6623 (0.6086)	loss 2.7212 (2.7697)	grad_norm 3.9538 (3.0665/1.5375)	mem 24308MB
[2025-01-19 04:39:06 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][220/312]	eta 0:00:56 lr 0.000152	time 0.5880 (0.6173)	model_time 0.5879 (0.6076)	loss 3.0752 (2.7619)	grad_norm 1.3603 (3.0361/1.5209)	mem 24308MB
[2025-01-19 04:39:12 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][230/312]	eta 0:00:50 lr 0.000152	time 0.5996 (0.6165)	model_time 0.5994 (0.6072)	loss 1.8626 (2.7649)	grad_norm 2.0595 (2.9981/1.5017)	mem 24308MB
[2025-01-19 04:39:18 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][240/312]	eta 0:00:44 lr 0.000152	time 0.5851 (0.6165)	model_time 0.5849 (0.6075)	loss 2.2077 (2.7614)	grad_norm 1.8315 (2.9611/1.4874)	mem 24308MB
[2025-01-19 04:39:25 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][250/312]	eta 0:00:38 lr 0.000151	time 0.5810 (0.6173)	model_time 0.5809 (0.6087)	loss 3.4514 (2.7627)	grad_norm 1.6993 (2.9305/1.4709)	mem 24308MB
[2025-01-19 04:39:31 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][260/312]	eta 0:00:32 lr 0.000151	time 0.5890 (0.6169)	model_time 0.5886 (0.6087)	loss 3.0186 (2.7660)	grad_norm 5.2930 (2.9160/1.4591)	mem 24308MB
[2025-01-19 04:39:37 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][270/312]	eta 0:00:25 lr 0.000151	time 0.5768 (0.6167)	model_time 0.5766 (0.6088)	loss 2.8022 (2.7666)	grad_norm 1.4207 (2.8912/1.4442)	mem 24308MB
[2025-01-19 04:39:43 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][280/312]	eta 0:00:19 lr 0.000151	time 0.5780 (0.6163)	model_time 0.5779 (0.6086)	loss 2.6201 (2.7687)	grad_norm 5.3677 (2.9025/1.4378)	mem 24308MB
[2025-01-19 04:39:49 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][290/312]	eta 0:00:13 lr 0.000151	time 0.5870 (0.6163)	model_time 0.5863 (0.6088)	loss 2.6866 (2.7770)	grad_norm 2.6846 (2.9046/1.4317)	mem 24308MB
[2025-01-19 04:39:55 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][300/312]	eta 0:00:07 lr 0.000150	time 0.5701 (0.6157)	model_time 0.5700 (0.6085)	loss 3.1114 (2.7750)	grad_norm 4.9512 (2.9143/1.4418)	mem 24308MB
[2025-01-19 04:40:01 internimage_s_1k_224] (main.py 510): INFO Train: [267/300][310/312]	eta 0:00:01 lr 0.000150	time 0.5735 (0.6149)	model_time 0.5734 (0.6079)	loss 2.8351 (2.7824)	grad_norm 2.3795 (2.9440/1.4478)	mem 24308MB
[2025-01-19 04:40:02 internimage_s_1k_224] (main.py 519): INFO EPOCH 267 training takes 0:03:11
[2025-01-19 04:40:02 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_267.pth saving......
[2025-01-19 04:40:03 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_267.pth saved !!!
[2025-01-19 04:40:12 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.168 (8.168)	Loss 0.6889 (0.6889)	Acc@1 85.938 (85.938)	Acc@5 98.022 (98.022)	Mem 24308MB
[2025-01-19 04:40:15 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.086)	Loss 0.8713 (0.7711)	Acc@1 80.591 (84.044)	Acc@5 96.118 (96.877)	Mem 24308MB
[2025-01-19 04:40:16 internimage_s_1k_224] (main.py 575): INFO [Epoch:267] * Acc@1 83.893 Acc@5 96.855
[2025-01-19 04:40:16 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.9%
[2025-01-19 04:40:16 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 04:40:17 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 04:40:17 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.89%
[2025-01-19 04:40:26 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.103 (8.103)	Loss 0.6947 (0.6947)	Acc@1 85.840 (85.840)	Acc@5 97.900 (97.900)	Mem 24308MB
[2025-01-19 04:40:30 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.098)	Loss 0.8778 (0.7680)	Acc@1 79.834 (83.816)	Acc@5 96.191 (96.802)	Mem 24308MB
[2025-01-19 04:40:30 internimage_s_1k_224] (main.py 575): INFO [Epoch:267] * Acc@1 83.695 Acc@5 96.813
[2025-01-19 04:40:30 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.7%
[2025-01-19 04:40:30 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:40:32 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:40:32 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.70%
[2025-01-19 04:40:35 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][0/312]	eta 0:12:41 lr 0.000150	time 2.4394 (2.4394)	model_time 0.5900 (0.5900)	loss 2.6128 (2.6128)	grad_norm 3.6520 (3.6520/0.0000)	mem 24308MB
[2025-01-19 04:40:41 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][10/312]	eta 0:03:50 lr 0.000150	time 0.5881 (0.7629)	model_time 0.5879 (0.5945)	loss 2.8365 (2.9040)	grad_norm 3.1987 (2.8357/0.6582)	mem 24308MB
[2025-01-19 04:40:47 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][20/312]	eta 0:03:19 lr 0.000150	time 0.6026 (0.6840)	model_time 0.6025 (0.5956)	loss 2.9644 (2.8158)	grad_norm 3.1952 (2.7695/0.8634)	mem 24308MB
[2025-01-19 04:40:53 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][30/312]	eta 0:03:05 lr 0.000149	time 0.5872 (0.6569)	model_time 0.5867 (0.5970)	loss 2.7413 (2.7827)	grad_norm 2.8319 (2.7229/0.8478)	mem 24308MB
[2025-01-19 04:40:59 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][40/312]	eta 0:02:54 lr 0.000149	time 0.5858 (0.6411)	model_time 0.5857 (0.5957)	loss 3.2876 (2.7680)	grad_norm 2.6289 (2.7541/0.9337)	mem 24308MB
[2025-01-19 04:41:05 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][50/312]	eta 0:02:46 lr 0.000149	time 0.5813 (0.6362)	model_time 0.5811 (0.5996)	loss 2.8868 (2.7996)	grad_norm 2.9269 (2.6754/0.9262)	mem 24308MB
[2025-01-19 04:41:11 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][60/312]	eta 0:02:40 lr 0.000149	time 0.6568 (0.6350)	model_time 0.6564 (0.6043)	loss 3.0152 (2.8196)	grad_norm 2.8452 (2.7594/1.0980)	mem 24308MB
[2025-01-19 04:41:17 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][70/312]	eta 0:02:33 lr 0.000149	time 0.6829 (0.6329)	model_time 0.6823 (0.6065)	loss 2.7050 (2.8175)	grad_norm 1.7752 (2.8801/1.2092)	mem 24308MB
[2025-01-19 04:41:23 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][80/312]	eta 0:02:26 lr 0.000148	time 0.5761 (0.6293)	model_time 0.5755 (0.6061)	loss 3.0878 (2.8264)	grad_norm 2.3736 (3.0225/1.3154)	mem 24308MB
[2025-01-19 04:41:29 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][90/312]	eta 0:02:19 lr 0.000148	time 0.5767 (0.6263)	model_time 0.5766 (0.6057)	loss 1.9073 (2.8102)	grad_norm 2.0094 (3.0544/1.3088)	mem 24308MB
[2025-01-19 04:41:35 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][100/312]	eta 0:02:12 lr 0.000148	time 0.5900 (0.6259)	model_time 0.5895 (0.6072)	loss 3.1867 (2.7997)	grad_norm 3.4422 (3.0665/1.2570)	mem 24308MB
[2025-01-19 04:41:41 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][110/312]	eta 0:02:05 lr 0.000148	time 0.5833 (0.6231)	model_time 0.5829 (0.6061)	loss 2.3638 (2.7945)	grad_norm 1.9544 (2.9726/1.2495)	mem 24308MB
[2025-01-19 04:41:48 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][120/312]	eta 0:01:59 lr 0.000148	time 0.7060 (0.6227)	model_time 0.7058 (0.6071)	loss 3.0330 (2.7937)	grad_norm 2.0593 (2.9161/1.2265)	mem 24308MB
[2025-01-19 04:41:54 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][130/312]	eta 0:01:52 lr 0.000147	time 0.5923 (0.6208)	model_time 0.5918 (0.6064)	loss 2.6254 (2.7980)	grad_norm 2.8738 (2.9597/1.2095)	mem 24308MB
[2025-01-19 04:42:00 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][140/312]	eta 0:01:46 lr 0.000147	time 0.5826 (0.6194)	model_time 0.5824 (0.6059)	loss 3.1421 (2.7994)	grad_norm 4.6111 (3.0616/1.2780)	mem 24308MB
[2025-01-19 04:42:06 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][150/312]	eta 0:01:40 lr 0.000147	time 0.5867 (0.6187)	model_time 0.5865 (0.6061)	loss 3.0775 (2.7969)	grad_norm 2.1830 (3.0224/1.2527)	mem 24308MB
[2025-01-19 04:42:12 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][160/312]	eta 0:01:33 lr 0.000147	time 0.5924 (0.6171)	model_time 0.5920 (0.6052)	loss 2.8919 (2.8054)	grad_norm 2.3577 (3.0402/1.2514)	mem 24308MB
[2025-01-19 04:42:18 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][170/312]	eta 0:01:27 lr 0.000146	time 0.5880 (0.6170)	model_time 0.5878 (0.6058)	loss 3.0171 (2.8076)	grad_norm 2.4725 (3.0187/1.2417)	mem 24308MB
[2025-01-19 04:42:24 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][180/312]	eta 0:01:21 lr 0.000146	time 0.6737 (0.6172)	model_time 0.6735 (0.6066)	loss 3.1868 (2.8039)	grad_norm 3.9347 (3.0030/1.2352)	mem 24308MB
[2025-01-19 04:42:30 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][190/312]	eta 0:01:15 lr 0.000146	time 0.5940 (0.6167)	model_time 0.5938 (0.6066)	loss 1.9800 (2.8071)	grad_norm 2.1661 (2.9726/1.2210)	mem 24308MB
[2025-01-19 04:42:36 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][200/312]	eta 0:01:09 lr 0.000146	time 0.5938 (0.6177)	model_time 0.5933 (0.6081)	loss 2.9069 (2.8136)	grad_norm 2.4684 (2.9391/1.2028)	mem 24308MB
[2025-01-19 04:42:42 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][210/312]	eta 0:01:02 lr 0.000146	time 0.6504 (0.6172)	model_time 0.6502 (0.6080)	loss 2.3249 (2.8166)	grad_norm 1.9487 (2.9344/1.1940)	mem 24308MB
[2025-01-19 04:42:49 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][220/312]	eta 0:00:56 lr 0.000145	time 0.5736 (0.6178)	model_time 0.5735 (0.6091)	loss 3.1814 (2.8044)	grad_norm 2.0678 (2.9492/1.1920)	mem 24308MB
[2025-01-19 04:42:55 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][230/312]	eta 0:00:50 lr 0.000145	time 0.6000 (0.6172)	model_time 0.5998 (0.6088)	loss 3.1783 (2.8078)	grad_norm 2.6085 (2.9493/1.1920)	mem 24308MB
[2025-01-19 04:43:01 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][240/312]	eta 0:00:44 lr 0.000145	time 0.6735 (0.6167)	model_time 0.6733 (0.6087)	loss 2.2654 (2.7998)	grad_norm 3.8373 (2.9355/1.1826)	mem 24308MB
[2025-01-19 04:43:07 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][250/312]	eta 0:00:38 lr 0.000145	time 0.5832 (0.6158)	model_time 0.5830 (0.6081)	loss 2.0755 (2.7952)	grad_norm 2.5805 (2.9266/1.1834)	mem 24308MB
[2025-01-19 04:43:13 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][260/312]	eta 0:00:31 lr 0.000145	time 0.5724 (0.6154)	model_time 0.5723 (0.6079)	loss 3.1373 (2.8045)	grad_norm 3.7746 (2.9532/1.1974)	mem 24308MB
[2025-01-19 04:43:19 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][270/312]	eta 0:00:25 lr 0.000144	time 0.6369 (0.6148)	model_time 0.6367 (0.6075)	loss 2.7088 (2.8089)	grad_norm 1.7587 (2.9878/1.2304)	mem 24308MB
[2025-01-19 04:43:25 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][280/312]	eta 0:00:19 lr 0.000144	time 0.5842 (0.6142)	model_time 0.5836 (0.6072)	loss 3.1228 (2.8081)	grad_norm 3.0044 (3.0060/1.2391)	mem 24308MB
[2025-01-19 04:43:31 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][290/312]	eta 0:00:13 lr 0.000144	time 0.5772 (0.6142)	model_time 0.5770 (0.6075)	loss 2.2265 (2.7993)	grad_norm 1.9399 (3.0344/1.2538)	mem 24308MB
[2025-01-19 04:43:37 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][300/312]	eta 0:00:07 lr 0.000144	time 0.5682 (0.6141)	model_time 0.5681 (0.6075)	loss 2.1215 (2.7944)	grad_norm 2.7746 (3.0175/1.2414)	mem 24308MB
[2025-01-19 04:43:43 internimage_s_1k_224] (main.py 510): INFO Train: [268/300][310/312]	eta 0:00:01 lr 0.000143	time 0.5690 (0.6140)	model_time 0.5689 (0.6077)	loss 2.5704 (2.7919)	grad_norm 3.2167 (3.0465/1.2675)	mem 24308MB
[2025-01-19 04:43:44 internimage_s_1k_224] (main.py 519): INFO EPOCH 268 training takes 0:03:11
[2025-01-19 04:43:44 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_268.pth saving......
[2025-01-19 04:43:46 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_268.pth saved !!!
[2025-01-19 04:43:54 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.221 (8.221)	Loss 0.6971 (0.6971)	Acc@1 86.279 (86.279)	Acc@5 97.949 (97.949)	Mem 24308MB
[2025-01-19 04:43:58 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.081)	Loss 0.8898 (0.7887)	Acc@1 80.566 (84.024)	Acc@5 96.143 (96.835)	Mem 24308MB
[2025-01-19 04:43:58 internimage_s_1k_224] (main.py 575): INFO [Epoch:268] * Acc@1 83.879 Acc@5 96.837
[2025-01-19 04:43:58 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.9%
[2025-01-19 04:43:58 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.89%
[2025-01-19 04:44:07 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.277 (9.277)	Loss 0.6943 (0.6943)	Acc@1 85.840 (85.840)	Acc@5 97.900 (97.900)	Mem 24308MB
[2025-01-19 04:44:12 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.240)	Loss 0.8771 (0.7676)	Acc@1 79.834 (83.838)	Acc@5 96.167 (96.802)	Mem 24308MB
[2025-01-19 04:44:12 internimage_s_1k_224] (main.py 575): INFO [Epoch:268] * Acc@1 83.717 Acc@5 96.815
[2025-01-19 04:44:12 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.7%
[2025-01-19 04:44:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:44:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:44:14 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.72%
[2025-01-19 04:44:17 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][0/312]	eta 0:13:32 lr 0.000143	time 2.6052 (2.6052)	model_time 0.6342 (0.6342)	loss 2.9975 (2.9975)	grad_norm 1.8415 (1.8415/0.0000)	mem 24308MB
[2025-01-19 04:44:23 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][10/312]	eta 0:04:02 lr 0.000143	time 0.5905 (0.8019)	model_time 0.5903 (0.6225)	loss 3.0447 (2.9334)	grad_norm 2.2828 (2.1742/0.5086)	mem 24308MB
[2025-01-19 04:44:29 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][20/312]	eta 0:03:27 lr 0.000143	time 0.6701 (0.7104)	model_time 0.6697 (0.6161)	loss 2.6271 (2.8008)	grad_norm 2.8632 (2.3737/0.6624)	mem 24308MB
[2025-01-19 04:44:35 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][30/312]	eta 0:03:10 lr 0.000143	time 0.6781 (0.6772)	model_time 0.6779 (0.6133)	loss 2.9017 (2.7411)	grad_norm 3.8450 (2.5504/0.7954)	mem 24308MB
[2025-01-19 04:44:41 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][40/312]	eta 0:03:00 lr 0.000143	time 0.5996 (0.6630)	model_time 0.5992 (0.6146)	loss 2.7025 (2.7417)	grad_norm 2.2033 (2.7882/1.0370)	mem 24308MB
[2025-01-19 04:44:47 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][50/312]	eta 0:02:51 lr 0.000142	time 0.6408 (0.6529)	model_time 0.6404 (0.6139)	loss 1.8234 (2.7299)	grad_norm 1.2994 (2.7824/1.0411)	mem 24308MB
[2025-01-19 04:44:54 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][60/312]	eta 0:02:43 lr 0.000142	time 0.5823 (0.6494)	model_time 0.5821 (0.6168)	loss 3.2446 (2.7438)	grad_norm 1.6393 (2.7775/1.0192)	mem 24308MB
[2025-01-19 04:45:00 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][70/312]	eta 0:02:35 lr 0.000142	time 0.5841 (0.6430)	model_time 0.5837 (0.6148)	loss 2.3036 (2.7564)	grad_norm 6.2018 (2.8923/1.0874)	mem 24308MB
[2025-01-19 04:45:06 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][80/312]	eta 0:02:27 lr 0.000142	time 0.6699 (0.6377)	model_time 0.6694 (0.6131)	loss 2.5218 (2.7629)	grad_norm 3.8951 (2.9628/1.0938)	mem 24308MB
[2025-01-19 04:45:12 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][90/312]	eta 0:02:20 lr 0.000142	time 0.5761 (0.6330)	model_time 0.5757 (0.6110)	loss 2.4351 (2.7909)	grad_norm 3.4261 (3.0307/1.1246)	mem 24308MB
[2025-01-19 04:45:18 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][100/312]	eta 0:02:13 lr 0.000141	time 0.5934 (0.6307)	model_time 0.5930 (0.6108)	loss 2.1600 (2.7780)	grad_norm 3.6908 (2.9927/1.1352)	mem 24308MB
[2025-01-19 04:45:24 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][110/312]	eta 0:02:07 lr 0.000141	time 0.5785 (0.6297)	model_time 0.5784 (0.6115)	loss 2.9849 (2.7801)	grad_norm 1.8745 (2.9620/1.1164)	mem 24308MB
[2025-01-19 04:45:30 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][120/312]	eta 0:02:00 lr 0.000141	time 0.5985 (0.6280)	model_time 0.5983 (0.6113)	loss 2.9802 (2.7924)	grad_norm 2.5628 (2.9443/1.0921)	mem 24308MB
[2025-01-19 04:45:36 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][130/312]	eta 0:01:54 lr 0.000141	time 0.5766 (0.6273)	model_time 0.5762 (0.6119)	loss 2.8030 (2.7853)	grad_norm 1.8891 (2.9054/1.0696)	mem 24308MB
[2025-01-19 04:45:42 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][140/312]	eta 0:01:47 lr 0.000140	time 0.6623 (0.6259)	model_time 0.6618 (0.6116)	loss 2.2753 (2.7773)	grad_norm 4.0718 (2.9043/1.0716)	mem 24308MB
[2025-01-19 04:45:48 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][150/312]	eta 0:01:41 lr 0.000140	time 0.6711 (0.6249)	model_time 0.6707 (0.6115)	loss 3.4059 (2.7786)	grad_norm 1.8931 (2.8874/1.0984)	mem 24308MB
[2025-01-19 04:45:54 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][160/312]	eta 0:01:34 lr 0.000140	time 0.5759 (0.6231)	model_time 0.5758 (0.6105)	loss 3.5661 (2.7853)	grad_norm 3.6426 (2.8654/1.0817)	mem 24308MB
[2025-01-19 04:46:00 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][170/312]	eta 0:01:28 lr 0.000140	time 0.5860 (0.6214)	model_time 0.5855 (0.6095)	loss 3.1736 (2.8019)	grad_norm 1.7210 (2.8549/1.0995)	mem 24308MB
[2025-01-19 04:46:06 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][180/312]	eta 0:01:21 lr 0.000140	time 0.5795 (0.6212)	model_time 0.5793 (0.6099)	loss 2.7876 (2.7987)	grad_norm 2.8894 (2.8369/1.0819)	mem 24308MB
[2025-01-19 04:46:12 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][190/312]	eta 0:01:15 lr 0.000139	time 0.6158 (0.6199)	model_time 0.6154 (0.6093)	loss 2.7899 (2.7942)	grad_norm 2.5232 (2.8071/1.0668)	mem 24308MB
[2025-01-19 04:46:18 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][200/312]	eta 0:01:09 lr 0.000139	time 0.6741 (0.6194)	model_time 0.6735 (0.6092)	loss 3.2951 (2.7978)	grad_norm 2.4798 (2.8782/1.1485)	mem 24308MB
[2025-01-19 04:46:24 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][210/312]	eta 0:01:03 lr 0.000139	time 0.5922 (0.6180)	model_time 0.5920 (0.6083)	loss 3.1270 (2.7934)	grad_norm 2.5669 (2.9037/1.1416)	mem 24308MB
[2025-01-19 04:46:30 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][220/312]	eta 0:00:56 lr 0.000139	time 0.5919 (0.6176)	model_time 0.5917 (0.6083)	loss 3.0296 (2.7939)	grad_norm 5.0449 (2.8968/1.1334)	mem 24308MB
[2025-01-19 04:46:37 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][230/312]	eta 0:00:50 lr 0.000139	time 0.5816 (0.6182)	model_time 0.5814 (0.6093)	loss 3.2617 (2.7968)	grad_norm 1.2664 (2.8684/1.1306)	mem 24308MB
[2025-01-19 04:46:43 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][240/312]	eta 0:00:44 lr 0.000138	time 0.5860 (0.6194)	model_time 0.5859 (0.6109)	loss 1.8892 (2.7964)	grad_norm 2.0926 (2.8400/1.1270)	mem 24308MB
[2025-01-19 04:46:49 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][250/312]	eta 0:00:38 lr 0.000138	time 0.6730 (0.6196)	model_time 0.6729 (0.6114)	loss 3.0756 (2.8025)	grad_norm 1.7130 (2.8396/1.1310)	mem 24308MB
[2025-01-19 04:46:55 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][260/312]	eta 0:00:32 lr 0.000138	time 0.5745 (0.6186)	model_time 0.5740 (0.6107)	loss 3.3604 (2.7989)	grad_norm 2.1426 (2.8232/1.1189)	mem 24308MB
[2025-01-19 04:47:02 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][270/312]	eta 0:00:25 lr 0.000138	time 0.6512 (0.6189)	model_time 0.6511 (0.6112)	loss 2.9040 (2.7939)	grad_norm 2.1031 (2.8135/1.1079)	mem 24308MB
[2025-01-19 04:47:08 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][280/312]	eta 0:00:19 lr 0.000138	time 0.5755 (0.6181)	model_time 0.5753 (0.6107)	loss 3.3469 (2.8005)	grad_norm 3.8747 (2.8205/1.1149)	mem 24308MB
[2025-01-19 04:47:14 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][290/312]	eta 0:00:13 lr 0.000137	time 0.5836 (0.6173)	model_time 0.5834 (0.6102)	loss 2.9075 (2.7898)	grad_norm 2.4651 (2.8108/1.1038)	mem 24308MB
[2025-01-19 04:47:20 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][300/312]	eta 0:00:07 lr 0.000137	time 0.5710 (0.6170)	model_time 0.5709 (0.6101)	loss 3.0702 (2.7958)	grad_norm 4.1663 (2.8192/1.0962)	mem 24308MB
[2025-01-19 04:47:26 internimage_s_1k_224] (main.py 510): INFO Train: [269/300][310/312]	eta 0:00:01 lr 0.000137	time 0.5701 (0.6158)	model_time 0.5699 (0.6091)	loss 2.4489 (2.7970)	grad_norm 7.5231 (2.8773/1.1669)	mem 24308MB
[2025-01-19 04:47:26 internimage_s_1k_224] (main.py 519): INFO EPOCH 269 training takes 0:03:12
[2025-01-19 04:47:26 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_269.pth saving......
[2025-01-19 04:47:28 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_269.pth saved !!!
[2025-01-19 04:47:36 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.903 (7.903)	Loss 0.6968 (0.6968)	Acc@1 85.986 (85.986)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 04:47:39 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.053)	Loss 0.8919 (0.7824)	Acc@1 80.615 (84.151)	Acc@5 96.094 (96.866)	Mem 24308MB
[2025-01-19 04:47:40 internimage_s_1k_224] (main.py 575): INFO [Epoch:269] * Acc@1 83.963 Acc@5 96.859
[2025-01-19 04:47:40 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.0%
[2025-01-19 04:47:40 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 04:47:42 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 04:47:42 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.96%
[2025-01-19 04:47:49 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.945 (7.945)	Loss 0.6939 (0.6939)	Acc@1 85.864 (85.864)	Acc@5 97.900 (97.900)	Mem 24308MB
[2025-01-19 04:47:53 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.044)	Loss 0.8764 (0.7672)	Acc@1 79.834 (83.836)	Acc@5 96.191 (96.813)	Mem 24308MB
[2025-01-19 04:47:53 internimage_s_1k_224] (main.py 575): INFO [Epoch:269] * Acc@1 83.715 Acc@5 96.827
[2025-01-19 04:47:53 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.7%
[2025-01-19 04:47:53 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.72%
[2025-01-19 04:47:57 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][0/312]	eta 0:19:14 lr 0.000137	time 3.7012 (3.7012)	model_time 1.6131 (1.6131)	loss 2.8877 (2.8877)	grad_norm 3.8607 (3.8607/0.0000)	mem 24308MB
[2025-01-19 04:48:03 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][10/312]	eta 0:04:28 lr 0.000137	time 0.5947 (0.8887)	model_time 0.5945 (0.6985)	loss 3.2407 (2.7491)	grad_norm 5.2926 (3.7969/1.0876)	mem 24308MB
[2025-01-19 04:48:09 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][20/312]	eta 0:03:38 lr 0.000136	time 0.5853 (0.7472)	model_time 0.5851 (0.6474)	loss 3.1314 (2.7160)	grad_norm 1.9514 (3.4347/1.1153)	mem 24308MB
[2025-01-19 04:48:15 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][30/312]	eta 0:03:18 lr 0.000136	time 0.6711 (0.7031)	model_time 0.6710 (0.6354)	loss 2.5042 (2.7489)	grad_norm 3.4261 (3.2586/1.0983)	mem 24308MB
[2025-01-19 04:48:21 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][40/312]	eta 0:03:05 lr 0.000136	time 0.6950 (0.6819)	model_time 0.6948 (0.6306)	loss 2.9173 (2.7819)	grad_norm 2.6852 (3.2135/1.0579)	mem 24308MB
[2025-01-19 04:48:28 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][50/312]	eta 0:02:56 lr 0.000136	time 0.6860 (0.6731)	model_time 0.6856 (0.6318)	loss 3.5450 (2.7926)	grad_norm 1.1031 (3.2997/1.2753)	mem 24308MB
[2025-01-19 04:48:34 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][60/312]	eta 0:02:47 lr 0.000136	time 0.5764 (0.6634)	model_time 0.5759 (0.6288)	loss 2.2862 (2.7986)	grad_norm 5.1882 (3.3922/1.2975)	mem 24308MB
[2025-01-19 04:48:40 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][70/312]	eta 0:02:38 lr 0.000135	time 0.5926 (0.6541)	model_time 0.5924 (0.6243)	loss 2.8939 (2.8133)	grad_norm 1.3196 (3.2513/1.2987)	mem 24308MB
[2025-01-19 04:48:46 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][80/312]	eta 0:02:30 lr 0.000135	time 0.5886 (0.6491)	model_time 0.5882 (0.6230)	loss 2.9309 (2.8118)	grad_norm 1.7607 (3.2061/1.2976)	mem 24308MB
[2025-01-19 04:48:52 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][90/312]	eta 0:02:22 lr 0.000135	time 0.5862 (0.6434)	model_time 0.5860 (0.6201)	loss 3.0529 (2.8442)	grad_norm 1.5487 (3.1986/1.3033)	mem 24308MB
[2025-01-19 04:48:58 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][100/312]	eta 0:02:15 lr 0.000135	time 0.6049 (0.6393)	model_time 0.6044 (0.6182)	loss 2.6260 (2.8377)	grad_norm 4.7752 (3.2289/1.3242)	mem 24308MB
[2025-01-19 04:49:04 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][110/312]	eta 0:02:08 lr 0.000135	time 0.6749 (0.6370)	model_time 0.6747 (0.6178)	loss 2.6096 (2.8316)	grad_norm 2.7851 (3.1500/1.3091)	mem 24308MB
[2025-01-19 04:49:10 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][120/312]	eta 0:02:01 lr 0.000134	time 0.5890 (0.6336)	model_time 0.5888 (0.6160)	loss 3.2108 (2.8318)	grad_norm 2.9628 (3.0861/1.2872)	mem 24308MB
[2025-01-19 04:49:16 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][130/312]	eta 0:01:54 lr 0.000134	time 0.5800 (0.6312)	model_time 0.5795 (0.6149)	loss 2.3738 (2.8268)	grad_norm 3.8411 (3.0892/1.2790)	mem 24308MB
[2025-01-19 04:49:22 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][140/312]	eta 0:01:48 lr 0.000134	time 0.5783 (0.6289)	model_time 0.5782 (0.6137)	loss 2.2856 (2.8104)	grad_norm 5.1827 (3.1137/1.3076)	mem 24308MB
[2025-01-19 04:49:28 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][150/312]	eta 0:01:41 lr 0.000134	time 0.6755 (0.6273)	model_time 0.6750 (0.6131)	loss 3.0772 (2.8093)	grad_norm 5.2500 (3.2284/1.4007)	mem 24308MB
[2025-01-19 04:49:34 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][160/312]	eta 0:01:35 lr 0.000134	time 0.5950 (0.6263)	model_time 0.5949 (0.6129)	loss 1.8142 (2.8041)	grad_norm 5.6005 (3.2907/1.4776)	mem 24308MB
[2025-01-19 04:49:40 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][170/312]	eta 0:01:28 lr 0.000133	time 0.6664 (0.6265)	model_time 0.6660 (0.6139)	loss 3.3046 (2.8048)	grad_norm 2.7437 (3.2722/1.4507)	mem 24308MB
[2025-01-19 04:49:47 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][180/312]	eta 0:01:22 lr 0.000133	time 0.5758 (0.6272)	model_time 0.5757 (0.6153)	loss 2.9845 (2.8171)	grad_norm 2.4303 (3.2261/1.4288)	mem 24308MB
[2025-01-19 04:49:53 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][190/312]	eta 0:01:16 lr 0.000133	time 0.5946 (0.6258)	model_time 0.5944 (0.6145)	loss 2.5291 (2.8005)	grad_norm 6.5903 (3.2554/1.4289)	mem 24308MB
[2025-01-19 04:49:59 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][200/312]	eta 0:01:10 lr 0.000133	time 0.5845 (0.6263)	model_time 0.5839 (0.6155)	loss 3.0794 (2.7947)	grad_norm 1.8688 (3.2563/1.4083)	mem 24308MB
[2025-01-19 04:50:05 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][210/312]	eta 0:01:03 lr 0.000133	time 0.5787 (0.6249)	model_time 0.5783 (0.6146)	loss 2.6906 (2.7818)	grad_norm 6.2093 (3.2684/1.4128)	mem 24308MB
[2025-01-19 04:50:11 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][220/312]	eta 0:00:57 lr 0.000132	time 0.5779 (0.6237)	model_time 0.5777 (0.6139)	loss 2.9371 (2.7848)	grad_norm 2.7396 (3.2524/1.3934)	mem 24308MB
[2025-01-19 04:50:17 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][230/312]	eta 0:00:51 lr 0.000132	time 0.6538 (0.6232)	model_time 0.6536 (0.6138)	loss 3.2289 (2.7843)	grad_norm 3.3437 (3.2782/1.3946)	mem 24308MB
[2025-01-19 04:50:23 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][240/312]	eta 0:00:44 lr 0.000132	time 0.6863 (0.6220)	model_time 0.6861 (0.6129)	loss 3.4103 (2.7838)	grad_norm 2.7184 (3.2644/1.3858)	mem 24308MB
[2025-01-19 04:50:29 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][250/312]	eta 0:00:38 lr 0.000132	time 0.6002 (0.6215)	model_time 0.6001 (0.6128)	loss 1.6747 (2.7835)	grad_norm 3.7142 (3.2959/1.3981)	mem 24308MB
[2025-01-19 04:50:35 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][260/312]	eta 0:00:32 lr 0.000132	time 0.6088 (0.6208)	model_time 0.6084 (0.6124)	loss 3.4653 (2.7923)	grad_norm 5.5240 (3.3028/1.3941)	mem 24308MB
[2025-01-19 04:50:41 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][270/312]	eta 0:00:26 lr 0.000131	time 0.6582 (0.6198)	model_time 0.6578 (0.6118)	loss 3.4825 (2.8013)	grad_norm 2.5996 (3.3010/1.3849)	mem 24308MB
[2025-01-19 04:50:47 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][280/312]	eta 0:00:19 lr 0.000131	time 0.5985 (0.6198)	model_time 0.5984 (0.6120)	loss 2.1919 (2.7872)	grad_norm 2.6618 (3.2659/1.3755)	mem 24308MB
[2025-01-19 04:50:54 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][290/312]	eta 0:00:13 lr 0.000131	time 0.5769 (0.6199)	model_time 0.5767 (0.6124)	loss 2.9930 (2.7892)	grad_norm 1.8938 (3.2272/1.3707)	mem 24308MB
[2025-01-19 04:51:00 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][300/312]	eta 0:00:07 lr 0.000131	time 0.6522 (0.6203)	model_time 0.6521 (0.6130)	loss 2.8359 (2.7856)	grad_norm 2.5511 (3.2090/1.3719)	mem 24308MB
[2025-01-19 04:51:06 internimage_s_1k_224] (main.py 510): INFO Train: [270/300][310/312]	eta 0:00:01 lr 0.000131	time 0.5694 (0.6190)	model_time 0.5693 (0.6119)	loss 2.0095 (2.7838)	grad_norm 2.8542 (3.1665/1.3676)	mem 24308MB
[2025-01-19 04:51:06 internimage_s_1k_224] (main.py 519): INFO EPOCH 270 training takes 0:03:13
[2025-01-19 04:51:06 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_270.pth saving......
[2025-01-19 04:51:08 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_270.pth saved !!!
[2025-01-19 04:51:16 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.921 (7.921)	Loss 0.6991 (0.6991)	Acc@1 86.133 (86.133)	Acc@5 97.729 (97.729)	Mem 24308MB
[2025-01-19 04:51:20 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.056)	Loss 0.8878 (0.7821)	Acc@1 80.176 (84.009)	Acc@5 96.240 (96.891)	Mem 24308MB
[2025-01-19 04:51:20 internimage_s_1k_224] (main.py 575): INFO [Epoch:270] * Acc@1 83.835 Acc@5 96.895
[2025-01-19 04:51:20 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.8%
[2025-01-19 04:51:20 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.96%
[2025-01-19 04:51:36 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.781 (15.781)	Loss 0.6935 (0.6935)	Acc@1 85.889 (85.889)	Acc@5 97.900 (97.900)	Mem 24308MB
[2025-01-19 04:51:45 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (2.288)	Loss 0.8759 (0.7668)	Acc@1 79.883 (83.862)	Acc@5 96.191 (96.811)	Mem 24308MB
[2025-01-19 04:51:45 internimage_s_1k_224] (main.py 575): INFO [Epoch:270] * Acc@1 83.743 Acc@5 96.827
[2025-01-19 04:51:45 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.7%
[2025-01-19 04:51:45 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:51:48 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:51:48 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.74%
[2025-01-19 04:51:50 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][0/312]	eta 0:13:29 lr 0.000131	time 2.5950 (2.5950)	model_time 0.6240 (0.6240)	loss 2.4634 (2.4634)	grad_norm 2.2965 (2.2965/0.0000)	mem 24308MB
[2025-01-19 04:51:57 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][10/312]	eta 0:04:01 lr 0.000130	time 0.5913 (0.7991)	model_time 0.5911 (0.6187)	loss 3.0160 (2.8096)	grad_norm 1.6042 (2.6801/1.0138)	mem 24308MB
[2025-01-19 04:52:03 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][20/312]	eta 0:03:25 lr 0.000130	time 0.5741 (0.7038)	model_time 0.5739 (0.6091)	loss 2.1391 (2.7787)	grad_norm 5.7389 (3.3321/1.7210)	mem 24308MB
[2025-01-19 04:52:09 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][30/312]	eta 0:03:09 lr 0.000130	time 0.5857 (0.6717)	model_time 0.5855 (0.6074)	loss 2.2787 (2.7705)	grad_norm 3.6802 (3.3610/1.7111)	mem 24308MB
[2025-01-19 04:52:15 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][40/312]	eta 0:02:58 lr 0.000130	time 0.5920 (0.6572)	model_time 0.5919 (0.6086)	loss 2.0934 (2.7811)	grad_norm 4.1593 (3.3067/1.6118)	mem 24308MB
[2025-01-19 04:52:21 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][50/312]	eta 0:02:48 lr 0.000130	time 0.5752 (0.6438)	model_time 0.5751 (0.6046)	loss 2.8436 (2.8100)	grad_norm 3.4310 (3.3441/1.5471)	mem 24308MB
[2025-01-19 04:52:27 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][60/312]	eta 0:02:40 lr 0.000129	time 0.5875 (0.6387)	model_time 0.5873 (0.6059)	loss 2.5698 (2.7989)	grad_norm 2.4743 (3.2528/1.5020)	mem 24308MB
[2025-01-19 04:52:33 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][70/312]	eta 0:02:33 lr 0.000129	time 0.6139 (0.6327)	model_time 0.6137 (0.6044)	loss 2.4051 (2.7722)	grad_norm 3.0815 (3.1450/1.4421)	mem 24308MB
[2025-01-19 04:52:39 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][80/312]	eta 0:02:25 lr 0.000129	time 0.5967 (0.6275)	model_time 0.5966 (0.6027)	loss 2.5227 (2.7771)	grad_norm 1.7818 (3.0928/1.4044)	mem 24308MB
[2025-01-19 04:52:45 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][90/312]	eta 0:02:18 lr 0.000129	time 0.5799 (0.6258)	model_time 0.5795 (0.6037)	loss 3.3615 (2.7918)	grad_norm 5.8968 (3.1376/1.4103)	mem 24308MB
[2025-01-19 04:52:51 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][100/312]	eta 0:02:12 lr 0.000129	time 0.5768 (0.6255)	model_time 0.5763 (0.6055)	loss 2.2964 (2.7743)	grad_norm 1.6050 (3.0345/1.3827)	mem 24308MB
[2025-01-19 04:52:57 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][110/312]	eta 0:02:06 lr 0.000128	time 0.6757 (0.6254)	model_time 0.6751 (0.6072)	loss 3.2631 (2.7843)	grad_norm 5.3612 (3.1335/1.4199)	mem 24308MB
[2025-01-19 04:53:03 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][120/312]	eta 0:01:59 lr 0.000128	time 0.5734 (0.6239)	model_time 0.5732 (0.6071)	loss 2.9025 (2.7916)	grad_norm 2.0751 (3.1028/1.3734)	mem 24308MB
[2025-01-19 04:53:10 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][130/312]	eta 0:01:53 lr 0.000128	time 0.5955 (0.6237)	model_time 0.5951 (0.6082)	loss 3.3391 (2.8209)	grad_norm 2.0596 (3.0363/1.3588)	mem 24308MB
[2025-01-19 04:53:16 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][140/312]	eta 0:01:47 lr 0.000128	time 0.5937 (0.6225)	model_time 0.5935 (0.6081)	loss 3.0190 (2.8179)	grad_norm 2.7208 (3.0367/1.3423)	mem 24308MB
[2025-01-19 04:53:21 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][150/312]	eta 0:01:40 lr 0.000128	time 0.5819 (0.6205)	model_time 0.5817 (0.6071)	loss 3.2002 (2.8145)	grad_norm 1.8853 (3.0067/1.3461)	mem 24308MB
[2025-01-19 04:53:28 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][160/312]	eta 0:01:34 lr 0.000127	time 0.6612 (0.6197)	model_time 0.6610 (0.6070)	loss 3.1802 (2.8202)	grad_norm 2.7485 (2.9904/1.3163)	mem 24308MB
[2025-01-19 04:53:34 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][170/312]	eta 0:01:27 lr 0.000127	time 0.5966 (0.6184)	model_time 0.5961 (0.6064)	loss 3.0004 (2.8316)	grad_norm 1.8518 (2.9368/1.3046)	mem 24308MB
[2025-01-19 04:53:40 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][180/312]	eta 0:01:21 lr 0.000127	time 0.5893 (0.6179)	model_time 0.5892 (0.6066)	loss 3.0741 (2.8157)	grad_norm 1.9729 (2.9565/1.2990)	mem 24308MB
[2025-01-19 04:53:46 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][190/312]	eta 0:01:15 lr 0.000127	time 0.5901 (0.6166)	model_time 0.5896 (0.6059)	loss 2.1950 (2.8183)	grad_norm 1.7150 (2.9412/1.2762)	mem 24308MB
[2025-01-19 04:53:51 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][200/312]	eta 0:01:08 lr 0.000127	time 0.6033 (0.6155)	model_time 0.6028 (0.6052)	loss 2.9288 (2.8119)	grad_norm 2.7440 (2.9392/1.2700)	mem 24308MB
[2025-01-19 04:53:58 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][210/312]	eta 0:01:02 lr 0.000126	time 0.6105 (0.6158)	model_time 0.6101 (0.6060)	loss 2.0439 (2.8035)	grad_norm 2.6737 (2.9392/1.2554)	mem 24308MB
[2025-01-19 04:54:04 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][220/312]	eta 0:00:56 lr 0.000126	time 0.5814 (0.6156)	model_time 0.5812 (0.6063)	loss 3.0117 (2.8012)	grad_norm 3.4796 (2.9472/1.2539)	mem 24308MB
[2025-01-19 04:54:10 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][230/312]	eta 0:00:50 lr 0.000126	time 0.5847 (0.6162)	model_time 0.5846 (0.6073)	loss 2.7546 (2.7980)	grad_norm 2.3417 (2.9532/1.2494)	mem 24308MB
[2025-01-19 04:54:16 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][240/312]	eta 0:00:44 lr 0.000126	time 0.5983 (0.6167)	model_time 0.5981 (0.6082)	loss 3.0372 (2.7976)	grad_norm 3.2472 (2.9823/1.2668)	mem 24308MB
[2025-01-19 04:54:23 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][250/312]	eta 0:00:38 lr 0.000126	time 0.5852 (0.6165)	model_time 0.5850 (0.6082)	loss 2.9569 (2.8004)	grad_norm 3.9580 (3.0011/1.2725)	mem 24308MB
[2025-01-19 04:54:29 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][260/312]	eta 0:00:32 lr 0.000126	time 0.6470 (0.6162)	model_time 0.6468 (0.6083)	loss 3.3137 (2.8028)	grad_norm 2.7050 (3.0296/1.2833)	mem 24308MB
[2025-01-19 04:54:35 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][270/312]	eta 0:00:25 lr 0.000125	time 0.5732 (0.6154)	model_time 0.5730 (0.6077)	loss 3.2035 (2.8020)	grad_norm 2.7568 (3.0757/1.3461)	mem 24308MB
[2025-01-19 04:54:41 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][280/312]	eta 0:00:19 lr 0.000125	time 0.6175 (0.6148)	model_time 0.6168 (0.6074)	loss 2.3571 (2.7998)	grad_norm 3.4063 (3.0944/1.3647)	mem 24308MB
[2025-01-19 04:54:47 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][290/312]	eta 0:00:13 lr 0.000125	time 0.5783 (0.6143)	model_time 0.5781 (0.6071)	loss 3.1389 (2.8052)	grad_norm 4.6673 (3.0841/1.3623)	mem 24308MB
[2025-01-19 04:54:53 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][300/312]	eta 0:00:07 lr 0.000125	time 0.5699 (0.6139)	model_time 0.5698 (0.6069)	loss 3.3169 (2.8100)	grad_norm 1.7714 (3.0791/1.3515)	mem 24308MB
[2025-01-19 04:54:58 internimage_s_1k_224] (main.py 510): INFO Train: [271/300][310/312]	eta 0:00:01 lr 0.000125	time 0.5709 (0.6126)	model_time 0.5708 (0.6059)	loss 3.1720 (2.8134)	grad_norm 6.2460 (3.1077/1.3643)	mem 24308MB
[2025-01-19 04:54:59 internimage_s_1k_224] (main.py 519): INFO EPOCH 271 training takes 0:03:11
[2025-01-19 04:54:59 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_271.pth saving......
[2025-01-19 04:55:01 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_271.pth saved !!!
[2025-01-19 04:55:09 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.122 (8.122)	Loss 0.6921 (0.6921)	Acc@1 86.108 (86.108)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 04:55:12 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.134 (1.045)	Loss 0.8766 (0.7748)	Acc@1 80.933 (84.098)	Acc@5 96.045 (96.853)	Mem 24308MB
[2025-01-19 04:55:13 internimage_s_1k_224] (main.py 575): INFO [Epoch:271] * Acc@1 83.911 Acc@5 96.861
[2025-01-19 04:55:13 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.9%
[2025-01-19 04:55:13 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.96%
[2025-01-19 04:55:22 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.071 (9.071)	Loss 0.6931 (0.6931)	Acc@1 85.840 (85.840)	Acc@5 97.900 (97.900)	Mem 24308MB
[2025-01-19 04:55:26 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.233)	Loss 0.8751 (0.7664)	Acc@1 79.858 (83.856)	Acc@5 96.216 (96.824)	Mem 24308MB
[2025-01-19 04:55:26 internimage_s_1k_224] (main.py 575): INFO [Epoch:271] * Acc@1 83.741 Acc@5 96.837
[2025-01-19 04:55:26 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.7%
[2025-01-19 04:55:26 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.74%
[2025-01-19 04:55:29 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][0/312]	eta 0:15:45 lr 0.000125	time 3.0307 (3.0307)	model_time 1.5097 (1.5097)	loss 3.1117 (3.1117)	grad_norm 1.2224 (1.2224/0.0000)	mem 24308MB
[2025-01-19 04:55:35 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][10/312]	eta 0:04:11 lr 0.000124	time 0.5943 (0.8315)	model_time 0.5942 (0.6929)	loss 2.9416 (2.5230)	grad_norm 3.5058 (3.6657/1.6563)	mem 24308MB
[2025-01-19 04:55:42 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][20/312]	eta 0:03:32 lr 0.000124	time 0.6020 (0.7279)	model_time 0.6015 (0.6552)	loss 2.7521 (2.7060)	grad_norm 1.7590 (3.1338/1.6351)	mem 24308MB
[2025-01-19 04:55:48 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][30/312]	eta 0:03:15 lr 0.000124	time 0.5807 (0.6915)	model_time 0.5802 (0.6421)	loss 3.1117 (2.7474)	grad_norm 1.4453 (2.9565/1.4264)	mem 24308MB
[2025-01-19 04:55:54 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][40/312]	eta 0:03:03 lr 0.000124	time 0.5752 (0.6752)	model_time 0.5751 (0.6377)	loss 2.0494 (2.7089)	grad_norm 2.8074 (3.1107/1.3834)	mem 24308MB
[2025-01-19 04:56:00 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][50/312]	eta 0:02:53 lr 0.000124	time 0.5929 (0.6626)	model_time 0.5926 (0.6325)	loss 3.2105 (2.7561)	grad_norm 3.2050 (3.0448/1.3107)	mem 24308MB
[2025-01-19 04:56:06 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][60/312]	eta 0:02:45 lr 0.000123	time 0.5960 (0.6559)	model_time 0.5956 (0.6306)	loss 2.5620 (2.7878)	grad_norm 3.4958 (2.9424/1.2534)	mem 24308MB
[2025-01-19 04:56:12 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][70/312]	eta 0:02:36 lr 0.000123	time 0.5895 (0.6477)	model_time 0.5891 (0.6259)	loss 2.5707 (2.7921)	grad_norm 2.6563 (2.9705/1.2026)	mem 24308MB
[2025-01-19 04:56:18 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][80/312]	eta 0:02:28 lr 0.000123	time 0.5921 (0.6418)	model_time 0.5920 (0.6227)	loss 2.4515 (2.8043)	grad_norm 2.7103 (2.9169/1.1706)	mem 24308MB
[2025-01-19 04:56:24 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][90/312]	eta 0:02:21 lr 0.000123	time 0.5915 (0.6366)	model_time 0.5910 (0.6195)	loss 3.0757 (2.8075)	grad_norm 2.3475 (2.8928/1.1199)	mem 24308MB
[2025-01-19 04:56:30 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][100/312]	eta 0:02:14 lr 0.000123	time 0.5854 (0.6337)	model_time 0.5850 (0.6183)	loss 1.7751 (2.7993)	grad_norm 2.3124 (2.8630/1.0995)	mem 24308MB
[2025-01-19 04:56:36 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][110/312]	eta 0:02:07 lr 0.000122	time 0.6733 (0.6315)	model_time 0.6732 (0.6174)	loss 2.5669 (2.8053)	grad_norm 3.0755 (2.8798/1.1401)	mem 24308MB
[2025-01-19 04:56:42 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][120/312]	eta 0:02:00 lr 0.000122	time 0.6102 (0.6289)	model_time 0.6097 (0.6160)	loss 2.4896 (2.8031)	grad_norm 1.4172 (2.8379/1.1188)	mem 24308MB
[2025-01-19 04:56:48 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][130/312]	eta 0:01:54 lr 0.000122	time 0.5863 (0.6266)	model_time 0.5861 (0.6146)	loss 1.7522 (2.7882)	grad_norm 1.2343 (2.8161/1.1133)	mem 24308MB
[2025-01-19 04:56:54 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][140/312]	eta 0:01:47 lr 0.000122	time 0.5750 (0.6258)	model_time 0.5746 (0.6146)	loss 3.0707 (2.7933)	grad_norm 4.7307 (2.8852/1.1544)	mem 24308MB
[2025-01-19 04:57:01 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][150/312]	eta 0:01:41 lr 0.000122	time 0.5875 (0.6259)	model_time 0.5874 (0.6154)	loss 2.1353 (2.7763)	grad_norm 3.6509 (2.9263/1.1850)	mem 24308MB
[2025-01-19 04:57:07 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][160/312]	eta 0:01:35 lr 0.000121	time 0.5966 (0.6255)	model_time 0.5961 (0.6157)	loss 2.9347 (2.7740)	grad_norm 2.1822 (2.8719/1.1752)	mem 24308MB
[2025-01-19 04:57:13 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][170/312]	eta 0:01:28 lr 0.000121	time 0.5840 (0.6245)	model_time 0.5836 (0.6152)	loss 3.0119 (2.7739)	grad_norm 3.0445 (2.8488/1.1555)	mem 24308MB
[2025-01-19 04:57:19 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][180/312]	eta 0:01:22 lr 0.000121	time 0.6674 (0.6242)	model_time 0.6670 (0.6154)	loss 2.6811 (2.7756)	grad_norm 3.5615 (2.8475/1.1362)	mem 24308MB
[2025-01-19 04:57:25 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][190/312]	eta 0:01:15 lr 0.000121	time 0.6144 (0.6228)	model_time 0.6140 (0.6144)	loss 3.0315 (2.7671)	grad_norm 1.5165 (2.8038/1.1289)	mem 24308MB
[2025-01-19 04:57:31 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][200/312]	eta 0:01:09 lr 0.000121	time 0.5930 (0.6216)	model_time 0.5929 (0.6136)	loss 2.9692 (2.7585)	grad_norm 1.7939 (2.7971/1.1479)	mem 24308MB
[2025-01-19 04:57:37 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][210/312]	eta 0:01:03 lr 0.000121	time 0.6875 (0.6206)	model_time 0.6871 (0.6130)	loss 3.0881 (2.7579)	grad_norm 3.6576 (2.7944/1.1349)	mem 24308MB
[2025-01-19 04:57:43 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][220/312]	eta 0:00:56 lr 0.000120	time 0.5766 (0.6195)	model_time 0.5764 (0.6122)	loss 2.6663 (2.7475)	grad_norm 3.7822 (2.7730/1.1241)	mem 24308MB
[2025-01-19 04:57:49 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][230/312]	eta 0:00:50 lr 0.000120	time 0.6408 (0.6191)	model_time 0.6406 (0.6121)	loss 2.5002 (2.7460)	grad_norm 2.6872 (2.7692/1.1094)	mem 24308MB
[2025-01-19 04:57:55 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][240/312]	eta 0:00:44 lr 0.000120	time 0.5822 (0.6182)	model_time 0.5820 (0.6114)	loss 3.0639 (2.7608)	grad_norm 1.5019 (2.7479/1.1038)	mem 24308MB
[2025-01-19 04:58:01 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][250/312]	eta 0:00:38 lr 0.000120	time 0.5945 (0.6170)	model_time 0.5943 (0.6106)	loss 2.5277 (2.7642)	grad_norm 4.9598 (2.7374/1.0992)	mem 24308MB
[2025-01-19 04:58:07 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][260/312]	eta 0:00:32 lr 0.000120	time 0.5775 (0.6172)	model_time 0.5770 (0.6109)	loss 2.0409 (2.7532)	grad_norm 2.4399 (2.7231/1.0841)	mem 24308MB
[2025-01-19 04:58:14 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][270/312]	eta 0:00:25 lr 0.000119	time 0.5803 (0.6176)	model_time 0.5799 (0.6116)	loss 2.8253 (2.7575)	grad_norm 3.3815 (2.7374/1.0882)	mem 24308MB
[2025-01-19 04:58:20 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][280/312]	eta 0:00:19 lr 0.000119	time 0.5861 (0.6179)	model_time 0.5860 (0.6121)	loss 2.8800 (2.7686)	grad_norm 2.0470 (2.7688/1.1128)	mem 24308MB
[2025-01-19 04:58:26 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][290/312]	eta 0:00:13 lr 0.000119	time 0.6929 (0.6179)	model_time 0.6927 (0.6122)	loss 2.4827 (2.7650)	grad_norm 3.0869 (2.7856/1.1289)	mem 24308MB
[2025-01-19 04:58:32 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][300/312]	eta 0:00:07 lr 0.000119	time 0.6498 (0.6171)	model_time 0.6497 (0.6116)	loss 2.9442 (2.7740)	grad_norm 4.3854 (2.8039/1.1317)	mem 24308MB
[2025-01-19 04:58:38 internimage_s_1k_224] (main.py 510): INFO Train: [272/300][310/312]	eta 0:00:01 lr 0.000119	time 0.6458 (0.6161)	model_time 0.6457 (0.6108)	loss 2.4579 (2.7730)	grad_norm 2.8750 (2.7453/1.0851)	mem 24308MB
[2025-01-19 04:58:38 internimage_s_1k_224] (main.py 519): INFO EPOCH 272 training takes 0:03:12
[2025-01-19 04:58:38 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_272.pth saving......
[2025-01-19 04:58:40 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_272.pth saved !!!
[2025-01-19 04:58:48 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.561 (7.561)	Loss 0.6967 (0.6967)	Acc@1 85.815 (85.815)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 04:58:52 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.022)	Loss 0.8766 (0.7774)	Acc@1 80.493 (84.000)	Acc@5 96.265 (96.806)	Mem 24308MB
[2025-01-19 04:58:52 internimage_s_1k_224] (main.py 575): INFO [Epoch:272] * Acc@1 83.863 Acc@5 96.813
[2025-01-19 04:58:52 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.9%
[2025-01-19 04:58:52 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.96%
[2025-01-19 04:59:01 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.994 (8.994)	Loss 0.6928 (0.6928)	Acc@1 85.864 (85.864)	Acc@5 97.925 (97.925)	Mem 24308MB
[2025-01-19 04:59:05 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.208)	Loss 0.8744 (0.7660)	Acc@1 79.858 (83.900)	Acc@5 96.216 (96.820)	Mem 24308MB
[2025-01-19 04:59:05 internimage_s_1k_224] (main.py 575): INFO [Epoch:272] * Acc@1 83.783 Acc@5 96.833
[2025-01-19 04:59:05 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.8%
[2025-01-19 04:59:05 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 04:59:08 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 04:59:08 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.78%
[2025-01-19 04:59:10 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][0/312]	eta 0:10:57 lr 0.000119	time 2.1084 (2.1084)	model_time 0.6050 (0.6050)	loss 2.9127 (2.9127)	grad_norm 2.6009 (2.6009/0.0000)	mem 24308MB
[2025-01-19 04:59:16 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][10/312]	eta 0:03:43 lr 0.000118	time 0.5760 (0.7400)	model_time 0.5758 (0.6031)	loss 3.0133 (2.7118)	grad_norm 2.7826 (2.7719/1.0898)	mem 24308MB
[2025-01-19 04:59:22 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][20/312]	eta 0:03:15 lr 0.000118	time 0.5894 (0.6692)	model_time 0.5892 (0.5973)	loss 1.8985 (2.6284)	grad_norm 3.1471 (2.8666/1.2464)	mem 24308MB
[2025-01-19 04:59:28 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][30/312]	eta 0:03:03 lr 0.000118	time 0.5896 (0.6511)	model_time 0.5891 (0.6022)	loss 2.6442 (2.6561)	grad_norm 3.3814 (3.2821/1.4347)	mem 24308MB
[2025-01-19 04:59:34 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][40/312]	eta 0:02:53 lr 0.000118	time 0.5831 (0.6382)	model_time 0.5828 (0.6012)	loss 3.2705 (2.7189)	grad_norm 5.9544 (3.3159/1.6410)	mem 24308MB
[2025-01-19 04:59:40 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][50/312]	eta 0:02:45 lr 0.000118	time 0.6001 (0.6306)	model_time 0.5997 (0.6008)	loss 3.4134 (2.7630)	grad_norm 1.5612 (3.3054/1.5880)	mem 24308MB
[2025-01-19 04:59:46 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][60/312]	eta 0:02:37 lr 0.000118	time 0.6016 (0.6246)	model_time 0.6011 (0.5996)	loss 2.8310 (2.7617)	grad_norm 3.1753 (3.1818/1.5328)	mem 24308MB
[2025-01-19 04:59:52 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][70/312]	eta 0:02:30 lr 0.000117	time 0.6743 (0.6238)	model_time 0.6741 (0.6022)	loss 2.3593 (2.7525)	grad_norm 1.8222 (3.1160/1.4919)	mem 24308MB
[2025-01-19 04:59:58 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][80/312]	eta 0:02:24 lr 0.000117	time 0.7548 (0.6245)	model_time 0.7543 (0.6056)	loss 2.9516 (2.7317)	grad_norm 1.7369 (3.1008/1.4360)	mem 24308MB
[2025-01-19 05:00:04 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][90/312]	eta 0:02:18 lr 0.000117	time 0.6845 (0.6237)	model_time 0.6841 (0.6068)	loss 2.7360 (2.7270)	grad_norm 4.1383 (3.1349/1.4370)	mem 24308MB
[2025-01-19 05:00:10 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][100/312]	eta 0:02:11 lr 0.000117	time 0.5871 (0.6223)	model_time 0.5867 (0.6071)	loss 2.8258 (2.7192)	grad_norm 6.1263 (3.1562/1.4394)	mem 24308MB
[2025-01-19 05:00:17 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][110/312]	eta 0:02:05 lr 0.000117	time 0.5930 (0.6214)	model_time 0.5929 (0.6075)	loss 3.0539 (2.7188)	grad_norm 5.0250 (3.1343/1.4152)	mem 24308MB
[2025-01-19 05:00:23 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][120/312]	eta 0:01:59 lr 0.000116	time 0.5900 (0.6208)	model_time 0.5894 (0.6080)	loss 2.8425 (2.7267)	grad_norm 1.8455 (3.0931/1.4028)	mem 24308MB
[2025-01-19 05:00:29 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][130/312]	eta 0:01:52 lr 0.000116	time 0.5840 (0.6192)	model_time 0.5838 (0.6073)	loss 2.8095 (2.7149)	grad_norm 4.8760 (3.1061/1.3668)	mem 24308MB
[2025-01-19 05:00:35 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][140/312]	eta 0:01:46 lr 0.000116	time 0.5856 (0.6170)	model_time 0.5854 (0.6060)	loss 3.2803 (2.7236)	grad_norm 3.4312 (3.1378/1.3761)	mem 24308MB
[2025-01-19 05:00:41 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][150/312]	eta 0:01:40 lr 0.000116	time 0.5896 (0.6176)	model_time 0.5891 (0.6073)	loss 2.2314 (2.7283)	grad_norm 3.3509 (3.1338/1.3488)	mem 24308MB
[2025-01-19 05:00:47 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][160/312]	eta 0:01:33 lr 0.000116	time 0.6007 (0.6164)	model_time 0.6005 (0.6067)	loss 2.7403 (2.7349)	grad_norm 1.8196 (3.1130/1.3161)	mem 24308MB
[2025-01-19 05:00:53 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][170/312]	eta 0:01:27 lr 0.000115	time 0.5905 (0.6155)	model_time 0.5903 (0.6063)	loss 1.9884 (2.7339)	grad_norm 2.6756 (3.0969/1.3465)	mem 24308MB
[2025-01-19 05:00:59 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][180/312]	eta 0:01:21 lr 0.000115	time 0.5980 (0.6143)	model_time 0.5975 (0.6056)	loss 3.2263 (2.7449)	grad_norm 6.7062 (3.1228/1.3481)	mem 24308MB
[2025-01-19 05:01:05 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][190/312]	eta 0:01:14 lr 0.000115	time 0.6811 (0.6146)	model_time 0.6809 (0.6063)	loss 2.8919 (2.7545)	grad_norm 2.4388 (3.1041/1.3271)	mem 24308MB
[2025-01-19 05:01:11 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][200/312]	eta 0:01:08 lr 0.000115	time 0.6724 (0.6152)	model_time 0.6720 (0.6073)	loss 1.6593 (2.7446)	grad_norm 2.1059 (3.0835/1.3064)	mem 24308MB
[2025-01-19 05:01:18 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][210/312]	eta 0:01:02 lr 0.000115	time 0.5866 (0.6158)	model_time 0.5864 (0.6083)	loss 2.9286 (2.7440)	grad_norm 1.2541 (3.0438/1.2974)	mem 24308MB
[2025-01-19 05:01:24 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][220/312]	eta 0:00:56 lr 0.000115	time 0.6740 (0.6157)	model_time 0.6736 (0.6085)	loss 2.1523 (2.7427)	grad_norm 2.6857 (3.0131/1.2828)	mem 24308MB
[2025-01-19 05:01:30 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][230/312]	eta 0:00:50 lr 0.000114	time 0.5832 (0.6153)	model_time 0.5831 (0.6083)	loss 2.2799 (2.7462)	grad_norm 2.6795 (3.0108/1.2820)	mem 24308MB
[2025-01-19 05:01:36 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][240/312]	eta 0:00:44 lr 0.000114	time 0.5788 (0.6148)	model_time 0.5783 (0.6082)	loss 2.2977 (2.7373)	grad_norm 2.7797 (3.0063/1.2692)	mem 24308MB
[2025-01-19 05:01:42 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][250/312]	eta 0:00:38 lr 0.000114	time 0.5907 (0.6143)	model_time 0.5906 (0.6079)	loss 3.3818 (2.7386)	grad_norm 1.5831 (2.9999/1.2596)	mem 24308MB
[2025-01-19 05:01:48 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][260/312]	eta 0:00:31 lr 0.000114	time 0.5994 (0.6134)	model_time 0.5991 (0.6072)	loss 3.2969 (2.7487)	grad_norm 2.1609 (3.0347/1.3030)	mem 24308MB
[2025-01-19 05:01:54 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][270/312]	eta 0:00:25 lr 0.000114	time 0.5977 (0.6134)	model_time 0.5973 (0.6074)	loss 3.4424 (2.7537)	grad_norm 2.1951 (3.0227/1.3053)	mem 24308MB
[2025-01-19 05:02:00 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][280/312]	eta 0:00:19 lr 0.000114	time 0.5742 (0.6131)	model_time 0.5737 (0.6073)	loss 3.0447 (2.7582)	grad_norm 2.8665 (3.0013/1.2996)	mem 24308MB
[2025-01-19 05:02:06 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][290/312]	eta 0:00:13 lr 0.000113	time 0.6025 (0.6125)	model_time 0.6023 (0.6069)	loss 3.0718 (2.7594)	grad_norm 2.8842 (2.9790/1.2938)	mem 24308MB
[2025-01-19 05:02:12 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][300/312]	eta 0:00:07 lr 0.000113	time 0.5696 (0.6114)	model_time 0.5695 (0.6060)	loss 3.0089 (2.7633)	grad_norm 4.0276 (2.9910/1.2941)	mem 24308MB
[2025-01-19 05:02:18 internimage_s_1k_224] (main.py 510): INFO Train: [273/300][310/312]	eta 0:00:01 lr 0.000113	time 0.5698 (0.6109)	model_time 0.5697 (0.6056)	loss 3.1446 (2.7631)	grad_norm 2.7219 (2.9982/1.2995)	mem 24308MB
[2025-01-19 05:02:18 internimage_s_1k_224] (main.py 519): INFO EPOCH 273 training takes 0:03:10
[2025-01-19 05:02:18 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_273.pth saving......
[2025-01-19 05:02:20 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_273.pth saved !!!
[2025-01-19 05:02:28 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.255 (8.255)	Loss 0.6967 (0.6967)	Acc@1 85.693 (85.693)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 05:02:32 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.067)	Loss 0.8854 (0.7787)	Acc@1 80.469 (84.089)	Acc@5 96.191 (96.842)	Mem 24308MB
[2025-01-19 05:02:32 internimage_s_1k_224] (main.py 575): INFO [Epoch:273] * Acc@1 83.947 Acc@5 96.837
[2025-01-19 05:02:32 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.9%
[2025-01-19 05:02:32 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.96%
[2025-01-19 05:02:41 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.093 (9.093)	Loss 0.6924 (0.6924)	Acc@1 85.889 (85.889)	Acc@5 97.925 (97.925)	Mem 24308MB
[2025-01-19 05:02:45 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.219)	Loss 0.8738 (0.7656)	Acc@1 80.005 (83.944)	Acc@5 96.240 (96.822)	Mem 24308MB
[2025-01-19 05:02:46 internimage_s_1k_224] (main.py 575): INFO [Epoch:273] * Acc@1 83.821 Acc@5 96.835
[2025-01-19 05:02:46 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.8%
[2025-01-19 05:02:46 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:02:48 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:02:48 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.82%
[2025-01-19 05:02:50 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][0/312]	eta 0:11:48 lr 0.000113	time 2.2715 (2.2715)	model_time 0.6054 (0.6054)	loss 3.1256 (3.1256)	grad_norm 3.3058 (3.3058/0.0000)	mem 24308MB
[2025-01-19 05:02:56 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][10/312]	eta 0:03:55 lr 0.000113	time 0.7071 (0.7814)	model_time 0.7069 (0.6296)	loss 3.0477 (2.7339)	grad_norm 3.1141 (4.0273/1.4147)	mem 24308MB
[2025-01-19 05:03:03 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][20/312]	eta 0:03:26 lr 0.000113	time 0.5872 (0.7069)	model_time 0.5870 (0.6273)	loss 3.1259 (2.6145)	grad_norm 1.3839 (3.6418/1.4484)	mem 24308MB
[2025-01-19 05:03:09 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][30/312]	eta 0:03:11 lr 0.000112	time 0.5931 (0.6796)	model_time 0.5930 (0.6255)	loss 3.0937 (2.6356)	grad_norm 4.4252 (3.4975/1.3587)	mem 24308MB
[2025-01-19 05:03:15 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][40/312]	eta 0:03:00 lr 0.000112	time 0.6505 (0.6629)	model_time 0.6500 (0.6219)	loss 2.9608 (2.6882)	grad_norm 4.3331 (3.4188/1.2874)	mem 24308MB
[2025-01-19 05:03:21 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][50/312]	eta 0:02:51 lr 0.000112	time 0.5985 (0.6539)	model_time 0.5984 (0.6209)	loss 3.0463 (2.6941)	grad_norm 2.7960 (3.3306/1.3008)	mem 24308MB
[2025-01-19 05:03:27 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][60/312]	eta 0:02:42 lr 0.000112	time 0.5993 (0.6450)	model_time 0.5988 (0.6173)	loss 2.7494 (2.7195)	grad_norm 2.6609 (3.2398/1.2569)	mem 24308MB
[2025-01-19 05:03:33 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][70/312]	eta 0:02:34 lr 0.000112	time 0.5789 (0.6387)	model_time 0.5784 (0.6149)	loss 3.0515 (2.7492)	grad_norm 1.6182 (3.1147/1.2568)	mem 24308MB
[2025-01-19 05:03:39 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][80/312]	eta 0:02:27 lr 0.000112	time 0.6145 (0.6354)	model_time 0.6143 (0.6145)	loss 2.9757 (2.7782)	grad_norm 3.6080 (3.0699/1.2256)	mem 24308MB
[2025-01-19 05:03:45 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][90/312]	eta 0:02:20 lr 0.000111	time 0.6003 (0.6322)	model_time 0.6001 (0.6135)	loss 2.9153 (2.7747)	grad_norm 5.1169 (3.1212/1.2315)	mem 24308MB
[2025-01-19 05:03:51 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][100/312]	eta 0:02:13 lr 0.000111	time 0.5831 (0.6290)	model_time 0.5827 (0.6121)	loss 2.4945 (2.7729)	grad_norm 4.2928 (3.1154/1.2175)	mem 24308MB
[2025-01-19 05:03:57 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][110/312]	eta 0:02:06 lr 0.000111	time 0.5895 (0.6257)	model_time 0.5894 (0.6104)	loss 2.6112 (2.7756)	grad_norm 2.0519 (3.0417/1.1938)	mem 24308MB
[2025-01-19 05:04:03 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][120/312]	eta 0:01:59 lr 0.000111	time 0.5979 (0.6244)	model_time 0.5977 (0.6102)	loss 2.5678 (2.7726)	grad_norm 1.3142 (2.9695/1.1889)	mem 24308MB
[2025-01-19 05:04:10 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][130/312]	eta 0:01:53 lr 0.000111	time 0.6145 (0.6251)	model_time 0.6144 (0.6120)	loss 1.9134 (2.7544)	grad_norm 3.1055 (2.9348/1.1594)	mem 24308MB
[2025-01-19 05:04:16 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][140/312]	eta 0:01:47 lr 0.000110	time 0.5874 (0.6247)	model_time 0.5870 (0.6125)	loss 2.8418 (2.7689)	grad_norm 2.4422 (2.9260/1.1316)	mem 24308MB
[2025-01-19 05:04:22 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][150/312]	eta 0:01:40 lr 0.000110	time 0.5839 (0.6234)	model_time 0.5837 (0.6120)	loss 2.3400 (2.7733)	grad_norm 3.3322 (2.9270/1.0984)	mem 24308MB
[2025-01-19 05:04:28 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][160/312]	eta 0:01:34 lr 0.000110	time 0.6613 (0.6231)	model_time 0.6612 (0.6124)	loss 2.9785 (2.7735)	grad_norm 3.9389 (3.0241/1.2333)	mem 24308MB
[2025-01-19 05:04:34 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][170/312]	eta 0:01:28 lr 0.000110	time 0.5896 (0.6227)	model_time 0.5893 (0.6126)	loss 2.0151 (2.7799)	grad_norm 2.3913 (3.0298/1.2339)	mem 24308MB
[2025-01-19 05:04:40 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][180/312]	eta 0:01:21 lr 0.000110	time 0.5992 (0.6211)	model_time 0.5987 (0.6116)	loss 2.2356 (2.7746)	grad_norm 2.2267 (3.0156/1.2234)	mem 24308MB
[2025-01-19 05:04:46 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][190/312]	eta 0:01:15 lr 0.000110	time 0.5876 (0.6196)	model_time 0.5871 (0.6105)	loss 2.6966 (2.7700)	grad_norm 5.2943 (3.0021/1.2223)	mem 24308MB
[2025-01-19 05:04:52 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][200/312]	eta 0:01:09 lr 0.000109	time 0.5753 (0.6192)	model_time 0.5751 (0.6105)	loss 2.2685 (2.7704)	grad_norm 1.7751 (3.0101/1.2174)	mem 24308MB
[2025-01-19 05:04:58 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][210/312]	eta 0:01:03 lr 0.000109	time 0.6221 (0.6187)	model_time 0.6220 (0.6105)	loss 3.0471 (2.7777)	grad_norm 1.3830 (3.0971/1.3870)	mem 24308MB
[2025-01-19 05:05:04 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][220/312]	eta 0:00:56 lr 0.000109	time 0.5738 (0.6176)	model_time 0.5737 (0.6097)	loss 2.3321 (2.7750)	grad_norm 3.3976 (3.1046/1.3914)	mem 24308MB
[2025-01-19 05:05:10 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][230/312]	eta 0:00:50 lr 0.000109	time 0.5888 (0.6164)	model_time 0.5883 (0.6088)	loss 3.0969 (2.7804)	grad_norm 5.0020 (3.1118/1.3775)	mem 24308MB
[2025-01-19 05:05:16 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][240/312]	eta 0:00:44 lr 0.000109	time 0.5799 (0.6154)	model_time 0.5797 (0.6081)	loss 3.1484 (2.7837)	grad_norm 3.5065 (3.1046/1.3622)	mem 24308MB
[2025-01-19 05:05:22 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][250/312]	eta 0:00:38 lr 0.000109	time 0.5917 (0.6154)	model_time 0.5912 (0.6084)	loss 2.7419 (2.7782)	grad_norm 4.4971 (3.1198/1.3565)	mem 24308MB
[2025-01-19 05:05:29 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][260/312]	eta 0:00:32 lr 0.000108	time 0.6596 (0.6165)	model_time 0.6594 (0.6097)	loss 2.9006 (2.7813)	grad_norm 2.9619 (3.0957/1.3410)	mem 24308MB
[2025-01-19 05:05:35 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][270/312]	eta 0:00:25 lr 0.000108	time 0.5907 (0.6161)	model_time 0.5905 (0.6096)	loss 2.8273 (2.7865)	grad_norm 2.4808 (3.0728/1.3340)	mem 24308MB
[2025-01-19 05:05:41 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][280/312]	eta 0:00:19 lr 0.000108	time 0.5789 (0.6157)	model_time 0.5787 (0.6094)	loss 2.9275 (2.7863)	grad_norm 1.7238 (3.0677/1.3210)	mem 24308MB
[2025-01-19 05:05:47 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][290/312]	eta 0:00:13 lr 0.000108	time 0.5822 (0.6157)	model_time 0.5819 (0.6096)	loss 2.9200 (2.7870)	grad_norm 3.4115 (3.0626/1.3215)	mem 24308MB
[2025-01-19 05:05:53 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][300/312]	eta 0:00:07 lr 0.000108	time 0.5700 (0.6148)	model_time 0.5699 (0.6089)	loss 3.1368 (2.7860)	grad_norm 2.0897 (3.0403/1.3205)	mem 24308MB
[2025-01-19 05:05:59 internimage_s_1k_224] (main.py 510): INFO Train: [274/300][310/312]	eta 0:00:01 lr 0.000108	time 0.5687 (0.6137)	model_time 0.5686 (0.6080)	loss 1.9449 (2.7829)	grad_norm 1.3174 (2.9980/1.3123)	mem 24308MB
[2025-01-19 05:05:59 internimage_s_1k_224] (main.py 519): INFO EPOCH 274 training takes 0:03:11
[2025-01-19 05:05:59 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_274.pth saving......
[2025-01-19 05:06:01 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_274.pth saved !!!
[2025-01-19 05:06:09 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.984 (7.984)	Loss 0.6951 (0.6951)	Acc@1 86.133 (86.133)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 05:06:13 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.043)	Loss 0.8813 (0.7789)	Acc@1 80.371 (84.049)	Acc@5 96.069 (96.862)	Mem 24308MB
[2025-01-19 05:06:13 internimage_s_1k_224] (main.py 575): INFO [Epoch:274] * Acc@1 83.911 Acc@5 96.863
[2025-01-19 05:06:13 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 83.9%
[2025-01-19 05:06:13 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.96%
[2025-01-19 05:06:22 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.944 (8.944)	Loss 0.6920 (0.6920)	Acc@1 85.889 (85.889)	Acc@5 97.925 (97.925)	Mem 24308MB
[2025-01-19 05:06:26 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.209)	Loss 0.8731 (0.7652)	Acc@1 79.980 (83.953)	Acc@5 96.240 (96.833)	Mem 24308MB
[2025-01-19 05:06:26 internimage_s_1k_224] (main.py 575): INFO [Epoch:274] * Acc@1 83.835 Acc@5 96.847
[2025-01-19 05:06:26 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.8%
[2025-01-19 05:06:26 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:06:29 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:06:29 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.84%
[2025-01-19 05:06:31 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][0/312]	eta 0:09:52 lr 0.000107	time 1.9006 (1.9006)	model_time 0.5978 (0.5978)	loss 1.9721 (1.9721)	grad_norm 1.2554 (1.2554/0.0000)	mem 24308MB
[2025-01-19 05:06:37 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][10/312]	eta 0:03:40 lr 0.000107	time 0.5831 (0.7301)	model_time 0.5829 (0.6114)	loss 2.4525 (2.4768)	grad_norm 1.8455 (2.0150/0.6503)	mem 24308MB
[2025-01-19 05:06:43 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][20/312]	eta 0:03:15 lr 0.000107	time 0.5785 (0.6682)	model_time 0.5781 (0.6059)	loss 2.3908 (2.6990)	grad_norm 1.9855 (2.2127/0.8118)	mem 24308MB
[2025-01-19 05:06:49 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][30/312]	eta 0:03:02 lr 0.000107	time 0.5861 (0.6462)	model_time 0.5857 (0.6039)	loss 2.9534 (2.7501)	grad_norm 1.8383 (2.2929/0.7923)	mem 24308MB
[2025-01-19 05:06:55 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][40/312]	eta 0:02:52 lr 0.000107	time 0.5938 (0.6324)	model_time 0.5937 (0.6003)	loss 2.9311 (2.7387)	grad_norm 1.9088 (2.4202/0.9548)	mem 24308MB
[2025-01-19 05:07:01 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][50/312]	eta 0:02:44 lr 0.000107	time 0.5951 (0.6285)	model_time 0.5947 (0.6026)	loss 3.2231 (2.7980)	grad_norm 2.6572 (2.4797/0.9324)	mem 24308MB
[2025-01-19 05:07:07 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][60/312]	eta 0:02:38 lr 0.000106	time 0.6856 (0.6277)	model_time 0.6854 (0.6060)	loss 2.8349 (2.8183)	grad_norm 3.4267 (2.5834/0.9946)	mem 24308MB
[2025-01-19 05:07:13 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][70/312]	eta 0:02:32 lr 0.000106	time 0.5778 (0.6292)	model_time 0.5774 (0.6106)	loss 3.1231 (2.8137)	grad_norm 1.2835 (2.7008/1.0841)	mem 24308MB
[2025-01-19 05:07:20 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][80/312]	eta 0:02:25 lr 0.000106	time 0.5860 (0.6276)	model_time 0.5855 (0.6112)	loss 2.7838 (2.7942)	grad_norm 3.9323 (2.8430/1.1712)	mem 24308MB
[2025-01-19 05:07:26 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][90/312]	eta 0:02:18 lr 0.000106	time 0.5757 (0.6248)	model_time 0.5755 (0.6102)	loss 2.7885 (2.7674)	grad_norm 5.4554 (2.8398/1.1828)	mem 24308MB
[2025-01-19 05:07:32 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][100/312]	eta 0:02:12 lr 0.000106	time 0.5765 (0.6235)	model_time 0.5761 (0.6103)	loss 1.7810 (2.7487)	grad_norm 2.2515 (2.8331/1.1758)	mem 24308MB
[2025-01-19 05:07:38 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][110/312]	eta 0:02:05 lr 0.000106	time 0.5835 (0.6213)	model_time 0.5833 (0.6092)	loss 2.7728 (2.7504)	grad_norm 3.9990 (2.8754/1.1588)	mem 24308MB
[2025-01-19 05:07:44 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][120/312]	eta 0:01:59 lr 0.000105	time 0.5862 (0.6198)	model_time 0.5858 (0.6087)	loss 2.7062 (2.7508)	grad_norm 3.6002 (2.8672/1.1561)	mem 24308MB
[2025-01-19 05:07:50 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][130/312]	eta 0:01:52 lr 0.000105	time 0.5768 (0.6196)	model_time 0.5766 (0.6093)	loss 2.5684 (2.7337)	grad_norm 1.7598 (2.8950/1.1687)	mem 24308MB
[2025-01-19 05:07:56 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][140/312]	eta 0:01:46 lr 0.000105	time 0.5822 (0.6188)	model_time 0.5821 (0.6092)	loss 2.7073 (2.7362)	grad_norm 2.2858 (2.9383/1.1863)	mem 24308MB
[2025-01-19 05:08:02 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][150/312]	eta 0:01:39 lr 0.000105	time 0.5872 (0.6173)	model_time 0.5871 (0.6083)	loss 3.3842 (2.7455)	grad_norm 1.9487 (2.8942/1.1730)	mem 24308MB
[2025-01-19 05:08:08 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][160/312]	eta 0:01:33 lr 0.000105	time 0.5794 (0.6154)	model_time 0.5788 (0.6069)	loss 2.4960 (2.7498)	grad_norm 2.7126 (2.8842/1.1621)	mem 24308MB
[2025-01-19 05:08:14 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][170/312]	eta 0:01:27 lr 0.000105	time 0.6652 (0.6149)	model_time 0.6650 (0.6069)	loss 2.7006 (2.7464)	grad_norm 3.4714 (2.9047/1.1708)	mem 24308MB
[2025-01-19 05:08:20 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][180/312]	eta 0:01:21 lr 0.000104	time 0.7008 (0.6162)	model_time 0.7006 (0.6087)	loss 3.0226 (2.7589)	grad_norm 3.0253 (2.9093/1.1713)	mem 24308MB
[2025-01-19 05:08:27 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][190/312]	eta 0:01:15 lr 0.000104	time 0.6038 (0.6183)	model_time 0.6036 (0.6112)	loss 3.0345 (2.7604)	grad_norm 2.4171 (2.8848/1.1583)	mem 24308MB
[2025-01-19 05:08:33 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][200/312]	eta 0:01:09 lr 0.000104	time 0.5860 (0.6183)	model_time 0.5856 (0.6114)	loss 2.9473 (2.7611)	grad_norm 3.7244 (2.8717/1.1478)	mem 24308MB
[2025-01-19 05:08:39 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][210/312]	eta 0:01:03 lr 0.000104	time 0.5915 (0.6177)	model_time 0.5911 (0.6111)	loss 2.2531 (2.7621)	grad_norm 1.4447 (2.8681/1.1287)	mem 24308MB
[2025-01-19 05:08:45 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][220/312]	eta 0:00:56 lr 0.000104	time 0.6042 (0.6177)	model_time 0.6040 (0.6115)	loss 2.9997 (2.7632)	grad_norm 5.1800 (2.8459/1.1400)	mem 24308MB
[2025-01-19 05:08:51 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][230/312]	eta 0:00:50 lr 0.000104	time 0.5927 (0.6167)	model_time 0.5923 (0.6107)	loss 1.8845 (2.7573)	grad_norm 3.3607 (2.8286/1.1330)	mem 24308MB
[2025-01-19 05:08:57 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][240/312]	eta 0:00:44 lr 0.000103	time 0.5874 (0.6161)	model_time 0.5870 (0.6103)	loss 1.8585 (2.7546)	grad_norm 1.7628 (2.8433/1.1443)	mem 24308MB
[2025-01-19 05:09:03 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][250/312]	eta 0:00:38 lr 0.000103	time 0.6004 (0.6159)	model_time 0.6003 (0.6103)	loss 1.6213 (2.7394)	grad_norm 3.2325 (2.8471/1.1335)	mem 24308MB
[2025-01-19 05:09:10 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][260/312]	eta 0:00:32 lr 0.000103	time 0.5933 (0.6167)	model_time 0.5931 (0.6113)	loss 1.6544 (2.7380)	grad_norm 1.4874 (2.8376/1.1274)	mem 24308MB
[2025-01-19 05:09:16 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][270/312]	eta 0:00:25 lr 0.000103	time 0.5871 (0.6163)	model_time 0.5867 (0.6111)	loss 3.1611 (2.7412)	grad_norm 5.4378 (2.8807/1.1664)	mem 24308MB
[2025-01-19 05:09:22 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][280/312]	eta 0:00:19 lr 0.000103	time 0.5754 (0.6153)	model_time 0.5752 (0.6102)	loss 3.4095 (2.7373)	grad_norm 3.2330 (2.8925/1.1646)	mem 24308MB
[2025-01-19 05:09:28 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][290/312]	eta 0:00:13 lr 0.000103	time 0.5988 (0.6150)	model_time 0.5986 (0.6101)	loss 2.8770 (2.7359)	grad_norm 4.7005 (2.9023/1.1571)	mem 24308MB
[2025-01-19 05:09:34 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][300/312]	eta 0:00:07 lr 0.000102	time 0.5671 (0.6148)	model_time 0.5670 (0.6101)	loss 1.9686 (2.7377)	grad_norm 6.5821 (2.9415/1.1748)	mem 24308MB
[2025-01-19 05:09:40 internimage_s_1k_224] (main.py 510): INFO Train: [275/300][310/312]	eta 0:00:01 lr 0.000102	time 0.6481 (0.6150)	model_time 0.6480 (0.6104)	loss 2.1487 (2.7382)	grad_norm 4.4184 (2.9488/1.1790)	mem 24308MB
[2025-01-19 05:09:41 internimage_s_1k_224] (main.py 519): INFO EPOCH 275 training takes 0:03:11
[2025-01-19 05:09:41 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_275.pth saving......
[2025-01-19 05:09:42 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_275.pth saved !!!
[2025-01-19 05:09:52 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.323 (9.323)	Loss 0.6914 (0.6914)	Acc@1 86.084 (86.084)	Acc@5 97.852 (97.852)	Mem 24308MB
[2025-01-19 05:09:56 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.235)	Loss 0.8730 (0.7713)	Acc@1 81.104 (84.133)	Acc@5 96.240 (96.877)	Mem 24308MB
[2025-01-19 05:09:56 internimage_s_1k_224] (main.py 575): INFO [Epoch:275] * Acc@1 83.987 Acc@5 96.883
[2025-01-19 05:09:56 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.0%
[2025-01-19 05:09:56 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 05:09:58 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 05:09:58 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 83.99%
[2025-01-19 05:10:06 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.846 (7.846)	Loss 0.6917 (0.6917)	Acc@1 85.889 (85.889)	Acc@5 97.900 (97.900)	Mem 24308MB
[2025-01-19 05:10:10 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.132 (1.053)	Loss 0.8725 (0.7649)	Acc@1 80.103 (83.975)	Acc@5 96.265 (96.844)	Mem 24308MB
[2025-01-19 05:10:10 internimage_s_1k_224] (main.py 575): INFO [Epoch:275] * Acc@1 83.861 Acc@5 96.857
[2025-01-19 05:10:10 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.9%
[2025-01-19 05:10:10 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:10:12 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:10:12 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.86%
[2025-01-19 05:10:15 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][0/312]	eta 0:10:49 lr 0.000102	time 2.0813 (2.0813)	model_time 0.6069 (0.6069)	loss 2.9328 (2.9328)	grad_norm 1.2758 (1.2758/0.0000)	mem 24308MB
[2025-01-19 05:10:21 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][10/312]	eta 0:03:45 lr 0.000102	time 0.5923 (0.7460)	model_time 0.5920 (0.6117)	loss 2.4597 (2.8285)	grad_norm 1.4997 (2.4280/0.9173)	mem 24308MB
[2025-01-19 05:10:27 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][20/312]	eta 0:03:18 lr 0.000102	time 0.5942 (0.6807)	model_time 0.5940 (0.6102)	loss 2.6926 (2.8311)	grad_norm 2.4957 (2.5175/1.1234)	mem 24308MB
[2025-01-19 05:10:33 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][30/312]	eta 0:03:06 lr 0.000102	time 0.6675 (0.6620)	model_time 0.6673 (0.6141)	loss 3.1337 (2.7825)	grad_norm 1.8468 (2.6504/1.1220)	mem 24308MB
[2025-01-19 05:10:39 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][40/312]	eta 0:02:55 lr 0.000102	time 0.5912 (0.6468)	model_time 0.5907 (0.6105)	loss 3.4509 (2.7859)	grad_norm 1.4561 (3.0238/1.3753)	mem 24308MB
[2025-01-19 05:10:45 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][50/312]	eta 0:02:47 lr 0.000101	time 0.5883 (0.6380)	model_time 0.5882 (0.6088)	loss 2.4841 (2.7782)	grad_norm 4.0080 (3.1586/1.4122)	mem 24308MB
[2025-01-19 05:10:51 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][60/312]	eta 0:02:39 lr 0.000101	time 0.5743 (0.6338)	model_time 0.5741 (0.6093)	loss 2.3977 (2.7384)	grad_norm 2.7719 (3.2340/1.5032)	mem 24308MB
[2025-01-19 05:10:57 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][70/312]	eta 0:02:32 lr 0.000101	time 0.5892 (0.6297)	model_time 0.5890 (0.6086)	loss 1.6462 (2.7593)	grad_norm 2.1585 (3.2212/1.4503)	mem 24308MB
[2025-01-19 05:11:03 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][80/312]	eta 0:02:25 lr 0.000101	time 0.5776 (0.6260)	model_time 0.5771 (0.6074)	loss 2.7868 (2.7534)	grad_norm 1.5448 (3.0904/1.4189)	mem 24308MB
[2025-01-19 05:11:09 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][90/312]	eta 0:02:18 lr 0.000101	time 0.5919 (0.6221)	model_time 0.5917 (0.6056)	loss 2.9119 (2.7663)	grad_norm 2.1414 (2.9626/1.3917)	mem 24308MB
[2025-01-19 05:11:15 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][100/312]	eta 0:02:11 lr 0.000101	time 0.6422 (0.6206)	model_time 0.6420 (0.6057)	loss 2.4166 (2.7609)	grad_norm 2.2171 (2.8833/1.3559)	mem 24308MB
[2025-01-19 05:11:21 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][110/312]	eta 0:02:05 lr 0.000100	time 0.6620 (0.6205)	model_time 0.6615 (0.6069)	loss 3.0379 (2.7410)	grad_norm 2.4073 (2.8839/1.3376)	mem 24308MB
[2025-01-19 05:11:28 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][120/312]	eta 0:01:59 lr 0.000100	time 0.5922 (0.6216)	model_time 0.5921 (0.6091)	loss 3.1085 (2.7201)	grad_norm 7.0135 (2.9669/1.3946)	mem 24308MB
[2025-01-19 05:11:34 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][130/312]	eta 0:01:52 lr 0.000100	time 0.5852 (0.6203)	model_time 0.5851 (0.6087)	loss 2.6129 (2.7221)	grad_norm 1.3608 (2.9616/1.3900)	mem 24308MB
[2025-01-19 05:11:40 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][140/312]	eta 0:01:46 lr 0.000100	time 0.6858 (0.6190)	model_time 0.6853 (0.6082)	loss 3.3397 (2.7158)	grad_norm 2.3489 (2.9424/1.3597)	mem 24308MB
[2025-01-19 05:11:46 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][150/312]	eta 0:01:40 lr 0.000100	time 0.6805 (0.6192)	model_time 0.6803 (0.6091)	loss 2.6089 (2.7346)	grad_norm 4.9246 (2.9490/1.3458)	mem 24308MB
[2025-01-19 05:11:52 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][160/312]	eta 0:01:33 lr 0.000100	time 0.5933 (0.6183)	model_time 0.5931 (0.6088)	loss 2.5520 (2.7110)	grad_norm 2.1240 (2.9336/1.3300)	mem 24308MB
[2025-01-19 05:11:58 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][170/312]	eta 0:01:27 lr 0.000099	time 0.5992 (0.6173)	model_time 0.5988 (0.6083)	loss 2.3970 (2.7022)	grad_norm 1.3475 (2.9219/1.3255)	mem 24308MB
[2025-01-19 05:12:04 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][180/312]	eta 0:01:21 lr 0.000099	time 0.5786 (0.6166)	model_time 0.5784 (0.6081)	loss 3.5672 (2.7055)	grad_norm 2.2756 (2.9271/1.3479)	mem 24308MB
[2025-01-19 05:12:10 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][190/312]	eta 0:01:15 lr 0.000099	time 0.5663 (0.6163)	model_time 0.5662 (0.6083)	loss 2.1503 (2.7153)	grad_norm 6.2842 (2.9613/1.3588)	mem 24308MB
[2025-01-19 05:12:16 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][200/312]	eta 0:01:08 lr 0.000099	time 0.5815 (0.6156)	model_time 0.5813 (0.6079)	loss 2.6140 (2.7291)	grad_norm 1.8494 (2.9398/1.3746)	mem 24308MB
[2025-01-19 05:12:22 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][210/312]	eta 0:01:02 lr 0.000099	time 0.5946 (0.6146)	model_time 0.5945 (0.6073)	loss 3.2654 (2.7319)	grad_norm 3.2044 (2.9416/1.3730)	mem 24308MB
[2025-01-19 05:12:28 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][220/312]	eta 0:00:56 lr 0.000099	time 0.7028 (0.6144)	model_time 0.7026 (0.6074)	loss 3.0512 (2.7376)	grad_norm 3.0485 (2.9332/1.3527)	mem 24308MB
[2025-01-19 05:12:35 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][230/312]	eta 0:00:50 lr 0.000098	time 0.5860 (0.6149)	model_time 0.5859 (0.6081)	loss 3.0112 (2.7417)	grad_norm 3.3867 (2.9114/1.3359)	mem 24308MB
[2025-01-19 05:12:41 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][240/312]	eta 0:00:44 lr 0.000098	time 0.5970 (0.6158)	model_time 0.5965 (0.6093)	loss 2.8838 (2.7466)	grad_norm 1.7609 (2.9057/1.3294)	mem 24308MB
[2025-01-19 05:12:47 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][250/312]	eta 0:00:38 lr 0.000098	time 0.8427 (0.6162)	model_time 0.8425 (0.6100)	loss 3.0434 (2.7362)	grad_norm 4.1999 (2.9256/1.3227)	mem 24308MB
[2025-01-19 05:12:53 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][260/312]	eta 0:00:32 lr 0.000098	time 0.6737 (0.6157)	model_time 0.6736 (0.6097)	loss 3.1390 (2.7376)	grad_norm 2.3933 (2.9214/1.3160)	mem 24308MB
[2025-01-19 05:12:59 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][270/312]	eta 0:00:25 lr 0.000098	time 0.6121 (0.6154)	model_time 0.6119 (0.6096)	loss 2.3181 (2.7371)	grad_norm 2.7534 (2.9019/1.3101)	mem 24308MB
[2025-01-19 05:13:05 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][280/312]	eta 0:00:19 lr 0.000098	time 0.5826 (0.6152)	model_time 0.5821 (0.6096)	loss 2.8821 (2.7388)	grad_norm 2.1078 (2.8910/1.3167)	mem 24308MB
[2025-01-19 05:13:11 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][290/312]	eta 0:00:13 lr 0.000098	time 0.5798 (0.6145)	model_time 0.5796 (0.6091)	loss 3.0685 (2.7370)	grad_norm 6.4215 (2.9440/1.3450)	mem 24308MB
[2025-01-19 05:13:17 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][300/312]	eta 0:00:07 lr 0.000097	time 0.5717 (0.6138)	model_time 0.5716 (0.6086)	loss 2.8272 (2.7356)	grad_norm 1.8663 (2.9597/1.3413)	mem 24308MB
[2025-01-19 05:13:23 internimage_s_1k_224] (main.py 510): INFO Train: [276/300][310/312]	eta 0:00:01 lr 0.000097	time 0.6430 (0.6133)	model_time 0.6429 (0.6082)	loss 3.0728 (2.7430)	grad_norm 1.8974 (2.9511/1.3405)	mem 24308MB
[2025-01-19 05:13:24 internimage_s_1k_224] (main.py 519): INFO EPOCH 276 training takes 0:03:11
[2025-01-19 05:13:24 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_276.pth saving......
[2025-01-19 05:13:26 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_276.pth saved !!!
[2025-01-19 05:13:34 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.895 (7.895)	Loss 0.7043 (0.7043)	Acc@1 86.182 (86.182)	Acc@5 97.949 (97.949)	Mem 24308MB
[2025-01-19 05:13:37 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.026)	Loss 0.8871 (0.7862)	Acc@1 80.859 (84.246)	Acc@5 96.240 (96.875)	Mem 24308MB
[2025-01-19 05:13:37 internimage_s_1k_224] (main.py 575): INFO [Epoch:276] * Acc@1 84.079 Acc@5 96.869
[2025-01-19 05:13:37 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 05:13:37 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 05:13:39 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 05:13:39 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.08%
[2025-01-19 05:13:50 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 11.381 (11.381)	Loss 0.6914 (0.6914)	Acc@1 85.913 (85.913)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 05:13:58 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.697)	Loss 0.8719 (0.7645)	Acc@1 80.200 (84.018)	Acc@5 96.240 (96.846)	Mem 24308MB
[2025-01-19 05:13:58 internimage_s_1k_224] (main.py 575): INFO [Epoch:276] * Acc@1 83.899 Acc@5 96.859
[2025-01-19 05:13:58 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.9%
[2025-01-19 05:13:58 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:14:00 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:14:00 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.90%
[2025-01-19 05:14:02 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][0/312]	eta 0:11:42 lr 0.000097	time 2.2508 (2.2508)	model_time 0.6003 (0.6003)	loss 3.0933 (3.0933)	grad_norm 2.9065 (2.9065/0.0000)	mem 24308MB
[2025-01-19 05:14:08 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][10/312]	eta 0:03:46 lr 0.000097	time 0.5947 (0.7492)	model_time 0.5945 (0.5988)	loss 2.7312 (2.7004)	grad_norm 1.5767 (2.7327/1.0572)	mem 24308MB
[2025-01-19 05:14:14 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][20/312]	eta 0:03:16 lr 0.000097	time 0.5751 (0.6741)	model_time 0.5746 (0.5952)	loss 3.1333 (2.8271)	grad_norm 2.4863 (2.7611/1.0158)	mem 24308MB
[2025-01-19 05:14:20 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][30/312]	eta 0:03:02 lr 0.000097	time 0.5816 (0.6479)	model_time 0.5814 (0.5943)	loss 3.0004 (2.7803)	grad_norm 3.9182 (2.6653/1.0424)	mem 24308MB
[2025-01-19 05:14:27 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][40/312]	eta 0:02:56 lr 0.000097	time 0.6697 (0.6488)	model_time 0.6695 (0.6082)	loss 2.8622 (2.7871)	grad_norm 3.8583 (2.7057/1.0770)	mem 24308MB
[2025-01-19 05:14:33 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][50/312]	eta 0:02:48 lr 0.000096	time 0.5778 (0.6449)	model_time 0.5776 (0.6121)	loss 2.4639 (2.7631)	grad_norm 2.3835 (2.7168/1.1210)	mem 24308MB
[2025-01-19 05:14:39 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][60/312]	eta 0:02:41 lr 0.000096	time 0.6254 (0.6391)	model_time 0.6249 (0.6117)	loss 2.8889 (2.7666)	grad_norm 2.4339 (2.7585/1.1732)	mem 24308MB
[2025-01-19 05:14:45 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][70/312]	eta 0:02:33 lr 0.000096	time 0.6067 (0.6353)	model_time 0.6062 (0.6117)	loss 2.7776 (2.7265)	grad_norm 2.8996 (2.7520/1.1227)	mem 24308MB
[2025-01-19 05:14:51 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][80/312]	eta 0:02:27 lr 0.000096	time 0.5845 (0.6337)	model_time 0.5843 (0.6130)	loss 2.9672 (2.6938)	grad_norm 6.3143 (2.7356/1.1913)	mem 24308MB
[2025-01-19 05:14:58 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][90/312]	eta 0:02:20 lr 0.000096	time 0.6035 (0.6313)	model_time 0.6030 (0.6128)	loss 3.1937 (2.7044)	grad_norm 1.6991 (2.6470/1.1678)	mem 24308MB
[2025-01-19 05:15:04 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][100/312]	eta 0:02:13 lr 0.000096	time 0.6064 (0.6279)	model_time 0.6062 (0.6112)	loss 1.8377 (2.7119)	grad_norm 3.9594 (2.6715/1.1298)	mem 24308MB
[2025-01-19 05:15:10 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][110/312]	eta 0:02:06 lr 0.000095	time 0.6888 (0.6260)	model_time 0.6886 (0.6108)	loss 2.0280 (2.7095)	grad_norm 2.1058 (2.6496/1.1048)	mem 24308MB
[2025-01-19 05:15:16 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][120/312]	eta 0:02:00 lr 0.000095	time 0.6750 (0.6260)	model_time 0.6748 (0.6120)	loss 3.1066 (2.7324)	grad_norm 1.4159 (2.5883/1.0911)	mem 24308MB
[2025-01-19 05:15:22 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][130/312]	eta 0:01:53 lr 0.000095	time 0.6019 (0.6236)	model_time 0.6017 (0.6107)	loss 1.9899 (2.7142)	grad_norm 3.1245 (2.6035/1.0774)	mem 24308MB
[2025-01-19 05:15:28 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][140/312]	eta 0:01:46 lr 0.000095	time 0.5792 (0.6211)	model_time 0.5787 (0.6090)	loss 3.2750 (2.7076)	grad_norm 1.6168 (2.5628/1.0612)	mem 24308MB
[2025-01-19 05:15:34 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][150/312]	eta 0:01:40 lr 0.000095	time 0.5709 (0.6193)	model_time 0.5708 (0.6081)	loss 3.0816 (2.7113)	grad_norm 1.6088 (2.6035/1.1067)	mem 24308MB
[2025-01-19 05:15:40 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][160/312]	eta 0:01:34 lr 0.000095	time 0.6553 (0.6200)	model_time 0.6551 (0.6094)	loss 3.3417 (2.7201)	grad_norm 4.9017 (2.6363/1.1458)	mem 24308MB
[2025-01-19 05:15:46 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][170/312]	eta 0:01:28 lr 0.000094	time 0.5879 (0.6199)	model_time 0.5875 (0.6099)	loss 2.5140 (2.7120)	grad_norm 2.4294 (2.7490/1.2722)	mem 24308MB
[2025-01-19 05:15:52 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][180/312]	eta 0:01:21 lr 0.000094	time 0.5732 (0.6195)	model_time 0.5730 (0.6100)	loss 3.2099 (2.7129)	grad_norm 4.2645 (2.7460/1.2490)	mem 24308MB
[2025-01-19 05:15:58 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][190/312]	eta 0:01:15 lr 0.000094	time 0.5651 (0.6189)	model_time 0.5647 (0.6099)	loss 3.1419 (2.7161)	grad_norm 3.3981 (2.7489/1.2334)	mem 24308MB
[2025-01-19 05:16:05 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][200/312]	eta 0:01:09 lr 0.000094	time 0.5820 (0.6196)	model_time 0.5819 (0.6111)	loss 3.3639 (2.7205)	grad_norm 3.9698 (2.7745/1.2384)	mem 24308MB
[2025-01-19 05:16:11 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][210/312]	eta 0:01:03 lr 0.000094	time 0.5921 (0.6197)	model_time 0.5917 (0.6115)	loss 1.8914 (2.7118)	grad_norm 1.1768 (2.7766/1.2413)	mem 24308MB
[2025-01-19 05:16:17 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][220/312]	eta 0:00:56 lr 0.000094	time 0.5902 (0.6186)	model_time 0.5898 (0.6108)	loss 3.3547 (2.7304)	grad_norm 3.7187 (2.7773/1.2262)	mem 24308MB
[2025-01-19 05:16:23 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][230/312]	eta 0:00:50 lr 0.000094	time 0.6987 (0.6179)	model_time 0.6982 (0.6104)	loss 2.9575 (2.7189)	grad_norm 4.0667 (2.8255/1.2620)	mem 24308MB
[2025-01-19 05:16:29 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][240/312]	eta 0:00:44 lr 0.000093	time 0.5871 (0.6176)	model_time 0.5864 (0.6104)	loss 2.8650 (2.7210)	grad_norm 3.6084 (2.8497/1.2681)	mem 24308MB
[2025-01-19 05:16:35 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][250/312]	eta 0:00:38 lr 0.000093	time 0.6730 (0.6169)	model_time 0.6725 (0.6100)	loss 2.5790 (2.7198)	grad_norm 3.1003 (2.8782/1.2759)	mem 24308MB
[2025-01-19 05:16:41 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][260/312]	eta 0:00:32 lr 0.000093	time 0.5986 (0.6158)	model_time 0.5982 (0.6091)	loss 2.0943 (2.7241)	grad_norm 3.5966 (2.8891/1.2646)	mem 24308MB
[2025-01-19 05:16:47 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][270/312]	eta 0:00:25 lr 0.000093	time 0.5760 (0.6149)	model_time 0.5756 (0.6084)	loss 2.3535 (2.7167)	grad_norm 4.4526 (2.8765/1.2562)	mem 24308MB
[2025-01-19 05:16:53 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][280/312]	eta 0:00:19 lr 0.000093	time 0.6764 (0.6156)	model_time 0.6760 (0.6094)	loss 2.8645 (2.7154)	grad_norm 3.2755 (2.8566/1.2486)	mem 24308MB
[2025-01-19 05:16:59 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][290/312]	eta 0:00:13 lr 0.000093	time 0.5844 (0.6155)	model_time 0.5843 (0.6095)	loss 2.6157 (2.7191)	grad_norm 4.2877 (2.8581/1.2398)	mem 24308MB
[2025-01-19 05:17:05 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][300/312]	eta 0:00:07 lr 0.000092	time 0.5694 (0.6150)	model_time 0.5693 (0.6091)	loss 2.4894 (2.7170)	grad_norm 1.7053 (2.8701/1.2396)	mem 24308MB
[2025-01-19 05:17:11 internimage_s_1k_224] (main.py 510): INFO Train: [277/300][310/312]	eta 0:00:01 lr 0.000092	time 0.5718 (0.6144)	model_time 0.5717 (0.6088)	loss 2.4824 (2.7212)	grad_norm 4.1566 (2.9102/1.2783)	mem 24308MB
[2025-01-19 05:17:12 internimage_s_1k_224] (main.py 519): INFO EPOCH 277 training takes 0:03:11
[2025-01-19 05:17:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_277.pth saving......
[2025-01-19 05:17:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_277.pth saved !!!
[2025-01-19 05:17:21 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.795 (7.795)	Loss 0.7039 (0.7039)	Acc@1 86.206 (86.206)	Acc@5 97.900 (97.900)	Mem 24308MB
[2025-01-19 05:17:25 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.057)	Loss 0.8863 (0.7846)	Acc@1 80.762 (84.138)	Acc@5 96.143 (96.811)	Mem 24308MB
[2025-01-19 05:17:25 internimage_s_1k_224] (main.py 575): INFO [Epoch:277] * Acc@1 83.983 Acc@5 96.819
[2025-01-19 05:17:25 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.0%
[2025-01-19 05:17:25 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.08%
[2025-01-19 05:17:34 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.036 (9.036)	Loss 0.6911 (0.6911)	Acc@1 85.938 (85.938)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 05:17:39 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.224)	Loss 0.8712 (0.7642)	Acc@1 80.151 (84.029)	Acc@5 96.216 (96.839)	Mem 24308MB
[2025-01-19 05:17:39 internimage_s_1k_224] (main.py 575): INFO [Epoch:277] * Acc@1 83.909 Acc@5 96.855
[2025-01-19 05:17:39 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 83.9%
[2025-01-19 05:17:39 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:17:41 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:17:41 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.91%
[2025-01-19 05:17:44 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][0/312]	eta 0:10:54 lr 0.000092	time 2.0989 (2.0989)	model_time 0.6003 (0.6003)	loss 1.7379 (1.7379)	grad_norm 7.5651 (7.5651/0.0000)	mem 24308MB
[2025-01-19 05:17:50 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][10/312]	eta 0:03:46 lr 0.000092	time 0.5800 (0.7510)	model_time 0.5798 (0.6145)	loss 2.6769 (2.6850)	grad_norm 4.8757 (4.4513/1.8042)	mem 24308MB
[2025-01-19 05:17:56 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][20/312]	eta 0:03:23 lr 0.000092	time 0.6835 (0.6969)	model_time 0.6833 (0.6252)	loss 2.7663 (2.6848)	grad_norm 1.6525 (4.0034/1.6698)	mem 24308MB
[2025-01-19 05:18:02 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][30/312]	eta 0:03:07 lr 0.000092	time 0.5711 (0.6640)	model_time 0.5707 (0.6154)	loss 2.7870 (2.7095)	grad_norm 4.0059 (3.6373/1.5539)	mem 24308MB
[2025-01-19 05:18:08 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][40/312]	eta 0:02:57 lr 0.000092	time 0.6011 (0.6508)	model_time 0.6007 (0.6139)	loss 2.4655 (2.6684)	grad_norm 3.3594 (3.6254/1.4942)	mem 24308MB
[2025-01-19 05:18:14 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][50/312]	eta 0:02:48 lr 0.000092	time 0.5861 (0.6431)	model_time 0.5859 (0.6134)	loss 2.9638 (2.7146)	grad_norm 1.4666 (3.4962/1.5597)	mem 24308MB
[2025-01-19 05:18:20 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][60/312]	eta 0:02:40 lr 0.000091	time 0.5787 (0.6367)	model_time 0.5782 (0.6117)	loss 2.8301 (2.7336)	grad_norm 2.8058 (3.3218/1.5160)	mem 24308MB
[2025-01-19 05:18:26 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][70/312]	eta 0:02:32 lr 0.000091	time 0.5810 (0.6302)	model_time 0.5805 (0.6087)	loss 2.8292 (2.6931)	grad_norm 2.2140 (3.2021/1.4577)	mem 24308MB
[2025-01-19 05:18:32 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][80/312]	eta 0:02:25 lr 0.000091	time 0.6374 (0.6258)	model_time 0.6373 (0.6070)	loss 2.2066 (2.7141)	grad_norm 1.4476 (3.1279/1.4072)	mem 24308MB
[2025-01-19 05:18:39 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][90/312]	eta 0:02:19 lr 0.000091	time 0.5771 (0.6274)	model_time 0.5769 (0.6105)	loss 2.9788 (2.7312)	grad_norm 1.8340 (3.0872/1.4111)	mem 24308MB
[2025-01-19 05:18:45 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][100/312]	eta 0:02:12 lr 0.000091	time 0.5788 (0.6266)	model_time 0.5783 (0.6114)	loss 2.7147 (2.7327)	grad_norm 2.8088 (3.1560/1.4146)	mem 24308MB
[2025-01-19 05:18:51 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][110/312]	eta 0:02:06 lr 0.000091	time 0.6630 (0.6251)	model_time 0.6628 (0.6112)	loss 2.8047 (2.7476)	grad_norm 2.8510 (3.1354/1.3741)	mem 24308MB
[2025-01-19 05:18:57 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][120/312]	eta 0:01:59 lr 0.000091	time 0.5970 (0.6245)	model_time 0.5968 (0.6118)	loss 2.5509 (2.7253)	grad_norm 3.3180 (3.1538/1.3930)	mem 24308MB
[2025-01-19 05:19:03 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][130/312]	eta 0:01:53 lr 0.000090	time 0.5847 (0.6241)	model_time 0.5846 (0.6123)	loss 3.3404 (2.7271)	grad_norm 3.5152 (3.1260/1.3794)	mem 24308MB
[2025-01-19 05:19:09 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][140/312]	eta 0:01:47 lr 0.000090	time 0.5943 (0.6233)	model_time 0.5939 (0.6123)	loss 3.4699 (2.7293)	grad_norm 5.5202 (3.1281/1.3737)	mem 24308MB
[2025-01-19 05:19:15 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][150/312]	eta 0:01:40 lr 0.000090	time 0.5865 (0.6216)	model_time 0.5863 (0.6113)	loss 3.2863 (2.7318)	grad_norm 3.0495 (3.1498/1.3777)	mem 24308MB
[2025-01-19 05:19:21 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][160/312]	eta 0:01:34 lr 0.000090	time 0.5713 (0.6206)	model_time 0.5708 (0.6109)	loss 2.8885 (2.7402)	grad_norm 7.2621 (3.1958/1.4070)	mem 24308MB
[2025-01-19 05:19:27 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][170/312]	eta 0:01:28 lr 0.000090	time 0.5834 (0.6199)	model_time 0.5830 (0.6108)	loss 3.0497 (2.7545)	grad_norm 2.9458 (3.2416/1.4495)	mem 24308MB
[2025-01-19 05:19:34 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][180/312]	eta 0:01:21 lr 0.000090	time 0.5862 (0.6193)	model_time 0.5860 (0.6106)	loss 2.6055 (2.7581)	grad_norm 5.1340 (3.2470/1.4383)	mem 24308MB
[2025-01-19 05:19:40 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][190/312]	eta 0:01:15 lr 0.000089	time 0.5838 (0.6179)	model_time 0.5837 (0.6097)	loss 3.2480 (2.7668)	grad_norm 4.6266 (3.2456/1.4279)	mem 24308MB
[2025-01-19 05:19:45 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][200/312]	eta 0:01:09 lr 0.000089	time 0.5894 (0.6165)	model_time 0.5892 (0.6087)	loss 3.5682 (2.7749)	grad_norm 1.9203 (3.2392/1.4380)	mem 24308MB
[2025-01-19 05:19:52 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][210/312]	eta 0:01:02 lr 0.000089	time 0.8716 (0.6176)	model_time 0.8714 (0.6101)	loss 2.0733 (2.7765)	grad_norm 3.5299 (3.2393/1.4132)	mem 24308MB
[2025-01-19 05:19:58 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][220/312]	eta 0:00:56 lr 0.000089	time 0.6597 (0.6175)	model_time 0.6592 (0.6104)	loss 3.0636 (2.7646)	grad_norm 1.7336 (3.2376/1.4170)	mem 24308MB
[2025-01-19 05:20:04 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][230/312]	eta 0:00:50 lr 0.000089	time 0.6528 (0.6173)	model_time 0.6526 (0.6105)	loss 1.8376 (2.7596)	grad_norm 2.7584 (3.2340/1.4193)	mem 24308MB
[2025-01-19 05:20:10 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][240/312]	eta 0:00:44 lr 0.000089	time 0.5702 (0.6165)	model_time 0.5697 (0.6099)	loss 2.8188 (2.7669)	grad_norm 3.2225 (3.2360/1.4027)	mem 24308MB
[2025-01-19 05:20:16 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][250/312]	eta 0:00:38 lr 0.000089	time 0.6048 (0.6163)	model_time 0.6047 (0.6100)	loss 2.4488 (2.7726)	grad_norm 2.8296 (3.2058/1.3902)	mem 24308MB
[2025-01-19 05:20:22 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][260/312]	eta 0:00:32 lr 0.000088	time 0.5775 (0.6161)	model_time 0.5773 (0.6100)	loss 3.0042 (2.7734)	grad_norm 1.7330 (3.2016/1.4038)	mem 24308MB
[2025-01-19 05:20:28 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][270/312]	eta 0:00:25 lr 0.000088	time 0.5843 (0.6156)	model_time 0.5839 (0.6097)	loss 2.9348 (2.7671)	grad_norm 2.0229 (3.1748/1.3900)	mem 24308MB
[2025-01-19 05:20:34 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][280/312]	eta 0:00:19 lr 0.000088	time 0.6032 (0.6150)	model_time 0.6027 (0.6093)	loss 2.3017 (2.7566)	grad_norm 3.6777 (3.1754/1.3898)	mem 24308MB
[2025-01-19 05:20:40 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][290/312]	eta 0:00:13 lr 0.000088	time 0.5801 (0.6146)	model_time 0.5799 (0.6091)	loss 3.0016 (2.7525)	grad_norm 3.2936 (3.1868/1.3828)	mem 24308MB
[2025-01-19 05:20:46 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][300/312]	eta 0:00:07 lr 0.000088	time 0.5687 (0.6141)	model_time 0.5685 (0.6087)	loss 3.2702 (2.7572)	grad_norm 3.0085 (3.1479/1.3520)	mem 24308MB
[2025-01-19 05:20:52 internimage_s_1k_224] (main.py 510): INFO Train: [278/300][310/312]	eta 0:00:01 lr 0.000088	time 0.5668 (0.6127)	model_time 0.5667 (0.6075)	loss 2.6039 (2.7582)	grad_norm 2.1144 (3.0922/1.3200)	mem 24308MB
[2025-01-19 05:20:53 internimage_s_1k_224] (main.py 519): INFO EPOCH 278 training takes 0:03:11
[2025-01-19 05:20:53 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_278.pth saving......
[2025-01-19 05:20:54 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_278.pth saved !!!
[2025-01-19 05:21:02 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.877 (7.877)	Loss 0.7011 (0.7011)	Acc@1 85.913 (85.913)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 05:21:06 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.060)	Loss 0.8746 (0.7769)	Acc@1 81.030 (84.177)	Acc@5 96.216 (96.875)	Mem 24308MB
[2025-01-19 05:21:06 internimage_s_1k_224] (main.py 575): INFO [Epoch:278] * Acc@1 84.011 Acc@5 96.897
[2025-01-19 05:21:06 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.0%
[2025-01-19 05:21:06 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.08%
[2025-01-19 05:21:15 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.936 (8.936)	Loss 0.6909 (0.6909)	Acc@1 85.986 (85.986)	Acc@5 97.852 (97.852)	Mem 24308MB
[2025-01-19 05:21:20 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.210)	Loss 0.8707 (0.7639)	Acc@1 80.249 (84.078)	Acc@5 96.216 (96.844)	Mem 24308MB
[2025-01-19 05:21:20 internimage_s_1k_224] (main.py 575): INFO [Epoch:278] * Acc@1 83.955 Acc@5 96.859
[2025-01-19 05:21:20 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.0%
[2025-01-19 05:21:20 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:21:22 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:21:22 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.96%
[2025-01-19 05:21:25 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][0/312]	eta 0:12:08 lr 0.000088	time 2.3363 (2.3363)	model_time 0.6280 (0.6280)	loss 2.7378 (2.7378)	grad_norm 1.7639 (1.7639/0.0000)	mem 24308MB
[2025-01-19 05:21:30 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][10/312]	eta 0:03:44 lr 0.000088	time 0.5978 (0.7437)	model_time 0.5977 (0.5881)	loss 2.2871 (2.5476)	grad_norm 3.0319 (2.4710/0.6626)	mem 24308MB
[2025-01-19 05:21:37 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][20/312]	eta 0:03:22 lr 0.000087	time 0.6879 (0.6940)	model_time 0.6878 (0.6123)	loss 2.7512 (2.6841)	grad_norm 2.9720 (2.8686/1.3832)	mem 24308MB
[2025-01-19 05:21:43 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][30/312]	eta 0:03:09 lr 0.000087	time 0.7236 (0.6721)	model_time 0.7232 (0.6166)	loss 3.0645 (2.6905)	grad_norm 1.5853 (3.0460/1.5032)	mem 24308MB
[2025-01-19 05:21:49 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][40/312]	eta 0:02:58 lr 0.000087	time 0.5878 (0.6560)	model_time 0.5876 (0.6140)	loss 3.3461 (2.6787)	grad_norm 3.7535 (3.2028/1.4363)	mem 24308MB
[2025-01-19 05:21:55 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][50/312]	eta 0:02:48 lr 0.000087	time 0.5920 (0.6446)	model_time 0.5916 (0.6107)	loss 3.0440 (2.6835)	grad_norm 2.8810 (3.3516/1.4812)	mem 24308MB
[2025-01-19 05:22:01 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][60/312]	eta 0:02:41 lr 0.000087	time 0.6447 (0.6401)	model_time 0.6442 (0.6117)	loss 1.9995 (2.6915)	grad_norm 2.6937 (3.4083/1.4321)	mem 24308MB
[2025-01-19 05:22:07 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][70/312]	eta 0:02:33 lr 0.000087	time 0.5774 (0.6350)	model_time 0.5773 (0.6106)	loss 3.0695 (2.7216)	grad_norm 5.5668 (3.3506/1.4203)	mem 24308MB
[2025-01-19 05:22:13 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][80/312]	eta 0:02:26 lr 0.000087	time 0.5721 (0.6312)	model_time 0.5717 (0.6098)	loss 3.2788 (2.7229)	grad_norm 3.5539 (3.3631/1.3662)	mem 24308MB
[2025-01-19 05:22:19 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][90/312]	eta 0:02:19 lr 0.000086	time 0.5819 (0.6287)	model_time 0.5817 (0.6095)	loss 3.1161 (2.7054)	grad_norm 2.4297 (3.2737/1.3367)	mem 24308MB
[2025-01-19 05:22:25 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][100/312]	eta 0:02:12 lr 0.000086	time 0.5974 (0.6256)	model_time 0.5972 (0.6083)	loss 3.3021 (2.6958)	grad_norm 4.7759 (3.3087/1.3712)	mem 24308MB
[2025-01-19 05:22:31 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][110/312]	eta 0:02:05 lr 0.000086	time 0.5807 (0.6232)	model_time 0.5803 (0.6075)	loss 2.9134 (2.7002)	grad_norm 4.7917 (3.3358/1.3605)	mem 24308MB
[2025-01-19 05:22:37 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][120/312]	eta 0:01:59 lr 0.000086	time 0.6126 (0.6208)	model_time 0.6125 (0.6063)	loss 2.2574 (2.6998)	grad_norm 1.4450 (3.2362/1.3607)	mem 24308MB
[2025-01-19 05:22:43 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][130/312]	eta 0:01:52 lr 0.000086	time 0.5797 (0.6182)	model_time 0.5795 (0.6048)	loss 2.8576 (2.7124)	grad_norm 4.2890 (3.1763/1.3473)	mem 24308MB
[2025-01-19 05:22:49 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][140/312]	eta 0:01:46 lr 0.000086	time 0.7161 (0.6181)	model_time 0.7157 (0.6056)	loss 2.6618 (2.7308)	grad_norm 3.1019 (3.1703/1.3333)	mem 24308MB
[2025-01-19 05:22:56 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][150/312]	eta 0:01:40 lr 0.000086	time 0.6626 (0.6191)	model_time 0.6622 (0.6074)	loss 3.5096 (2.7361)	grad_norm 1.3369 (3.1301/1.3232)	mem 24308MB
[2025-01-19 05:23:02 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][160/312]	eta 0:01:34 lr 0.000085	time 0.5765 (0.6191)	model_time 0.5763 (0.6082)	loss 2.7663 (2.7272)	grad_norm 2.0960 (3.0700/1.3091)	mem 24308MB
[2025-01-19 05:23:08 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][170/312]	eta 0:01:27 lr 0.000085	time 0.5851 (0.6177)	model_time 0.5850 (0.6073)	loss 1.7714 (2.7271)	grad_norm 1.3954 (3.0330/1.3004)	mem 24308MB
[2025-01-19 05:23:14 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][180/312]	eta 0:01:21 lr 0.000085	time 0.5776 (0.6167)	model_time 0.5772 (0.6069)	loss 2.9537 (2.7283)	grad_norm 2.1724 (3.0453/1.2878)	mem 24308MB
[2025-01-19 05:23:20 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][190/312]	eta 0:01:15 lr 0.000085	time 0.7041 (0.6170)	model_time 0.7037 (0.6077)	loss 2.9870 (2.7326)	grad_norm 5.4030 (3.0578/1.3006)	mem 24308MB
[2025-01-19 05:23:26 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][200/312]	eta 0:01:09 lr 0.000085	time 0.5867 (0.6163)	model_time 0.5865 (0.6074)	loss 3.2113 (2.7402)	grad_norm 2.9917 (3.0419/1.2853)	mem 24308MB
[2025-01-19 05:23:32 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][210/312]	eta 0:01:02 lr 0.000085	time 0.6143 (0.6150)	model_time 0.6138 (0.6066)	loss 3.1134 (2.7499)	grad_norm 2.9712 (3.0639/1.2847)	mem 24308MB
[2025-01-19 05:23:38 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][220/312]	eta 0:00:56 lr 0.000085	time 0.5695 (0.6148)	model_time 0.5691 (0.6067)	loss 2.5732 (2.7591)	grad_norm 3.0325 (3.1006/1.3210)	mem 24308MB
[2025-01-19 05:23:44 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][230/312]	eta 0:00:50 lr 0.000084	time 0.5986 (0.6141)	model_time 0.5981 (0.6064)	loss 1.9544 (2.7507)	grad_norm 1.9726 (3.0899/1.3025)	mem 24308MB
[2025-01-19 05:23:50 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][240/312]	eta 0:00:44 lr 0.000084	time 0.5970 (0.6136)	model_time 0.5966 (0.6062)	loss 3.4007 (2.7540)	grad_norm 2.6370 (3.0992/1.2976)	mem 24308MB
[2025-01-19 05:23:56 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][250/312]	eta 0:00:37 lr 0.000084	time 0.5927 (0.6126)	model_time 0.5922 (0.6055)	loss 3.1013 (2.7512)	grad_norm 1.5513 (3.0903/1.2920)	mem 24308MB
[2025-01-19 05:24:02 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][260/312]	eta 0:00:31 lr 0.000084	time 0.5944 (0.6124)	model_time 0.5942 (0.6055)	loss 2.9281 (2.7556)	grad_norm 5.6505 (3.0853/1.3108)	mem 24308MB
[2025-01-19 05:24:08 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][270/312]	eta 0:00:25 lr 0.000084	time 0.6732 (0.6136)	model_time 0.6731 (0.6069)	loss 3.3490 (2.7557)	grad_norm 2.5597 (3.1005/1.3220)	mem 24308MB
[2025-01-19 05:24:15 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][280/312]	eta 0:00:19 lr 0.000084	time 0.5670 (0.6136)	model_time 0.5668 (0.6072)	loss 2.7295 (2.7591)	grad_norm 2.5975 (3.1139/1.3307)	mem 24308MB
[2025-01-19 05:24:21 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][290/312]	eta 0:00:13 lr 0.000084	time 0.5766 (0.6129)	model_time 0.5764 (0.6067)	loss 2.8934 (2.7623)	grad_norm 3.5380 (3.0870/1.3230)	mem 24308MB
[2025-01-19 05:24:27 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][300/312]	eta 0:00:07 lr 0.000083	time 0.5869 (0.6126)	model_time 0.5868 (0.6065)	loss 2.7826 (2.7592)	grad_norm 4.6660 (3.0892/1.3266)	mem 24308MB
[2025-01-19 05:24:33 internimage_s_1k_224] (main.py 510): INFO Train: [279/300][310/312]	eta 0:00:01 lr 0.000083	time 0.5689 (0.6123)	model_time 0.5688 (0.6064)	loss 3.3033 (2.7641)	grad_norm 4.4306 (3.1309/1.3553)	mem 24308MB
[2025-01-19 05:24:33 internimage_s_1k_224] (main.py 519): INFO EPOCH 279 training takes 0:03:10
[2025-01-19 05:24:33 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_279.pth saving......
[2025-01-19 05:24:35 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_279.pth saved !!!
[2025-01-19 05:24:43 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.860 (7.860)	Loss 0.7031 (0.7031)	Acc@1 85.986 (85.986)	Acc@5 97.778 (97.778)	Mem 24308MB
[2025-01-19 05:24:47 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.030)	Loss 0.8790 (0.7791)	Acc@1 81.055 (84.157)	Acc@5 96.094 (96.853)	Mem 24308MB
[2025-01-19 05:24:47 internimage_s_1k_224] (main.py 575): INFO [Epoch:279] * Acc@1 83.987 Acc@5 96.851
[2025-01-19 05:24:47 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.0%
[2025-01-19 05:24:47 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.08%
[2025-01-19 05:24:56 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.894 (8.894)	Loss 0.6907 (0.6907)	Acc@1 85.962 (85.962)	Acc@5 97.852 (97.852)	Mem 24308MB
[2025-01-19 05:25:00 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.202)	Loss 0.8702 (0.7636)	Acc@1 80.273 (84.084)	Acc@5 96.216 (96.851)	Mem 24308MB
[2025-01-19 05:25:00 internimage_s_1k_224] (main.py 575): INFO [Epoch:279] * Acc@1 83.965 Acc@5 96.863
[2025-01-19 05:25:00 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.0%
[2025-01-19 05:25:00 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:25:02 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:25:02 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.97%
[2025-01-19 05:25:04 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][0/312]	eta 0:10:53 lr 0.000083	time 2.0955 (2.0955)	model_time 0.5824 (0.5824)	loss 3.3173 (3.3173)	grad_norm 1.7634 (1.7634/0.0000)	mem 24308MB
[2025-01-19 05:25:10 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][10/312]	eta 0:03:44 lr 0.000083	time 0.5750 (0.7428)	model_time 0.5748 (0.6049)	loss 2.2367 (2.9391)	grad_norm 5.3552 (3.2864/1.3238)	mem 24308MB
[2025-01-19 05:25:16 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][20/312]	eta 0:03:15 lr 0.000083	time 0.5655 (0.6705)	model_time 0.5650 (0.5981)	loss 2.9095 (2.7888)	grad_norm 4.1740 (3.1840/1.3883)	mem 24308MB
[2025-01-19 05:25:23 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][30/312]	eta 0:03:05 lr 0.000083	time 0.5865 (0.6577)	model_time 0.5864 (0.6084)	loss 3.0009 (2.7733)	grad_norm 5.2024 (3.2264/1.3885)	mem 24308MB
[2025-01-19 05:25:29 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][40/312]	eta 0:02:55 lr 0.000083	time 0.6461 (0.6439)	model_time 0.6457 (0.6066)	loss 3.4550 (2.7425)	grad_norm 3.2560 (3.2584/1.4117)	mem 24308MB
[2025-01-19 05:25:34 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][50/312]	eta 0:02:45 lr 0.000083	time 0.6010 (0.6336)	model_time 0.6008 (0.6035)	loss 2.8448 (2.7188)	grad_norm 3.3157 (3.2837/1.3790)	mem 24308MB
[2025-01-19 05:25:40 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][60/312]	eta 0:02:37 lr 0.000082	time 0.5851 (0.6259)	model_time 0.5850 (0.6007)	loss 2.8683 (2.7338)	grad_norm 2.6211 (3.2527/1.3836)	mem 24308MB
[2025-01-19 05:25:46 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][70/312]	eta 0:02:30 lr 0.000082	time 0.5860 (0.6236)	model_time 0.5855 (0.6019)	loss 1.9016 (2.7374)	grad_norm 1.7043 (3.4053/1.5171)	mem 24308MB
[2025-01-19 05:25:53 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][80/312]	eta 0:02:24 lr 0.000082	time 0.5902 (0.6243)	model_time 0.5898 (0.6052)	loss 2.8617 (2.7105)	grad_norm 5.8075 (3.4369/1.4956)	mem 24308MB
[2025-01-19 05:25:59 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][90/312]	eta 0:02:18 lr 0.000082	time 0.5633 (0.6245)	model_time 0.5629 (0.6075)	loss 2.3374 (2.7343)	grad_norm 6.5515 (3.5181/1.5135)	mem 24308MB
[2025-01-19 05:26:05 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][100/312]	eta 0:02:11 lr 0.000082	time 0.6357 (0.6221)	model_time 0.6355 (0.6067)	loss 3.1995 (2.7388)	grad_norm 7.1233 (3.5431/1.5092)	mem 24308MB
[2025-01-19 05:26:11 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][110/312]	eta 0:02:05 lr 0.000082	time 0.6396 (0.6200)	model_time 0.6391 (0.6060)	loss 2.5678 (2.7232)	grad_norm 2.3449 (3.5285/1.5370)	mem 24308MB
[2025-01-19 05:26:17 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][120/312]	eta 0:01:59 lr 0.000082	time 0.5905 (0.6199)	model_time 0.5900 (0.6070)	loss 2.9192 (2.7124)	grad_norm 2.3749 (3.4673/1.5004)	mem 24308MB
[2025-01-19 05:26:23 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][130/312]	eta 0:01:52 lr 0.000081	time 0.6040 (0.6188)	model_time 0.6038 (0.6068)	loss 2.8098 (2.7200)	grad_norm 2.4908 (3.3674/1.4940)	mem 24308MB
[2025-01-19 05:26:29 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][140/312]	eta 0:01:46 lr 0.000081	time 0.5969 (0.6169)	model_time 0.5967 (0.6058)	loss 2.8453 (2.7286)	grad_norm 3.3986 (3.3673/1.4515)	mem 24308MB
[2025-01-19 05:26:35 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][150/312]	eta 0:01:39 lr 0.000081	time 0.5688 (0.6169)	model_time 0.5686 (0.6065)	loss 2.7988 (2.7078)	grad_norm 3.2138 (3.3586/1.4426)	mem 24308MB
[2025-01-19 05:26:41 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][160/312]	eta 0:01:33 lr 0.000081	time 0.6788 (0.6154)	model_time 0.6786 (0.6056)	loss 3.0360 (2.7086)	grad_norm 1.7296 (3.3294/1.4412)	mem 24308MB
[2025-01-19 05:26:47 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][170/312]	eta 0:01:27 lr 0.000081	time 0.5824 (0.6141)	model_time 0.5823 (0.6048)	loss 3.0006 (2.7178)	grad_norm 2.5239 (3.3166/1.4457)	mem 24308MB
[2025-01-19 05:26:53 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][180/312]	eta 0:01:20 lr 0.000081	time 0.5777 (0.6126)	model_time 0.5775 (0.6038)	loss 3.0167 (2.7146)	grad_norm 4.9762 (3.2908/1.4481)	mem 24308MB
[2025-01-19 05:26:59 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][190/312]	eta 0:01:14 lr 0.000081	time 0.5850 (0.6130)	model_time 0.5843 (0.6046)	loss 3.0409 (2.7193)	grad_norm 5.2196 (3.3053/1.4538)	mem 24308MB
[2025-01-19 05:27:06 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][200/312]	eta 0:01:08 lr 0.000081	time 0.6771 (0.6139)	model_time 0.6767 (0.6060)	loss 2.6872 (2.7225)	grad_norm 3.3887 (3.3249/1.4521)	mem 24308MB
[2025-01-19 05:27:12 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][210/312]	eta 0:01:02 lr 0.000080	time 0.5771 (0.6137)	model_time 0.5769 (0.6061)	loss 3.0371 (2.7256)	grad_norm 2.6256 (3.2870/1.4360)	mem 24308MB
[2025-01-19 05:27:18 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][220/312]	eta 0:00:56 lr 0.000080	time 0.6214 (0.6142)	model_time 0.6212 (0.6069)	loss 2.5460 (2.7355)	grad_norm 1.9828 (3.2746/1.4281)	mem 24308MB
[2025-01-19 05:27:24 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][230/312]	eta 0:00:50 lr 0.000080	time 0.5872 (0.6133)	model_time 0.5868 (0.6064)	loss 2.9366 (2.7340)	grad_norm 5.3431 (3.2659/1.4182)	mem 24308MB
[2025-01-19 05:27:30 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][240/312]	eta 0:00:44 lr 0.000080	time 0.5647 (0.6132)	model_time 0.5645 (0.6066)	loss 2.6055 (2.7316)	grad_norm 2.9358 (3.2560/1.4053)	mem 24308MB
[2025-01-19 05:27:36 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][250/312]	eta 0:00:38 lr 0.000080	time 0.6282 (0.6134)	model_time 0.6277 (0.6070)	loss 2.8936 (2.7398)	grad_norm 3.8298 (3.2346/1.3998)	mem 24308MB
[2025-01-19 05:27:42 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][260/312]	eta 0:00:31 lr 0.000080	time 0.5980 (0.6125)	model_time 0.5975 (0.6063)	loss 2.4671 (2.7323)	grad_norm 1.7174 (3.1991/1.3891)	mem 24308MB
[2025-01-19 05:27:48 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][270/312]	eta 0:00:25 lr 0.000080	time 0.5791 (0.6128)	model_time 0.5786 (0.6069)	loss 2.9307 (2.7422)	grad_norm 1.8789 (3.1793/1.3780)	mem 24308MB
[2025-01-19 05:27:54 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][280/312]	eta 0:00:19 lr 0.000079	time 0.6040 (0.6119)	model_time 0.6035 (0.6061)	loss 1.9196 (2.7394)	grad_norm 1.9093 (3.1761/1.3672)	mem 24308MB
[2025-01-19 05:28:00 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][290/312]	eta 0:00:13 lr 0.000079	time 0.5960 (0.6117)	model_time 0.5958 (0.6061)	loss 1.7958 (2.7368)	grad_norm 1.9996 (3.1631/1.3509)	mem 24308MB
[2025-01-19 05:28:06 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][300/312]	eta 0:00:07 lr 0.000079	time 0.5656 (0.6109)	model_time 0.5655 (0.6054)	loss 3.1608 (2.7385)	grad_norm 3.2263 (3.1453/1.3428)	mem 24308MB
[2025-01-19 05:28:12 internimage_s_1k_224] (main.py 510): INFO Train: [280/300][310/312]	eta 0:00:01 lr 0.000079	time 0.6450 (0.6098)	model_time 0.6449 (0.6045)	loss 2.2874 (2.7366)	grad_norm 2.8888 (3.1375/1.3366)	mem 24308MB
[2025-01-19 05:28:13 internimage_s_1k_224] (main.py 519): INFO EPOCH 280 training takes 0:03:10
[2025-01-19 05:28:13 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_280.pth saving......
[2025-01-19 05:28:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_280.pth saved !!!
[2025-01-19 05:28:22 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.850 (7.850)	Loss 0.7020 (0.7020)	Acc@1 86.060 (86.060)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 05:28:26 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.019)	Loss 0.8736 (0.7758)	Acc@1 80.811 (84.175)	Acc@5 96.265 (96.868)	Mem 24308MB
[2025-01-19 05:28:26 internimage_s_1k_224] (main.py 575): INFO [Epoch:280] * Acc@1 84.011 Acc@5 96.873
[2025-01-19 05:28:26 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.0%
[2025-01-19 05:28:26 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.08%
[2025-01-19 05:28:35 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.165 (9.165)	Loss 0.6905 (0.6905)	Acc@1 85.938 (85.938)	Acc@5 97.852 (97.852)	Mem 24308MB
[2025-01-19 05:28:39 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.231)	Loss 0.8697 (0.7633)	Acc@1 80.298 (84.100)	Acc@5 96.240 (96.857)	Mem 24308MB
[2025-01-19 05:28:39 internimage_s_1k_224] (main.py 575): INFO [Epoch:280] * Acc@1 83.975 Acc@5 96.861
[2025-01-19 05:28:39 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.0%
[2025-01-19 05:28:40 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:28:42 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:28:42 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.98%
[2025-01-19 05:28:44 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][0/312]	eta 0:10:46 lr 0.000079	time 2.0726 (2.0726)	model_time 0.6016 (0.6016)	loss 2.7682 (2.7682)	grad_norm 2.7732 (2.7732/0.0000)	mem 24308MB
[2025-01-19 05:28:50 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][10/312]	eta 0:03:55 lr 0.000079	time 0.6974 (0.7785)	model_time 0.6970 (0.6443)	loss 1.9588 (2.6572)	grad_norm 2.0264 (2.4931/0.5777)	mem 24308MB
[2025-01-19 05:28:56 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][20/312]	eta 0:03:24 lr 0.000079	time 0.5864 (0.7013)	model_time 0.5863 (0.6309)	loss 3.0317 (2.7030)	grad_norm 3.9960 (2.6808/1.0296)	mem 24308MB
[2025-01-19 05:29:03 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][30/312]	eta 0:03:09 lr 0.000079	time 0.5860 (0.6707)	model_time 0.5856 (0.6228)	loss 2.7853 (2.7385)	grad_norm 1.8040 (2.5492/0.9332)	mem 24308MB
[2025-01-19 05:29:08 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][40/312]	eta 0:02:57 lr 0.000079	time 0.5842 (0.6525)	model_time 0.5841 (0.6163)	loss 2.9172 (2.7247)	grad_norm 1.5351 (2.5856/1.0029)	mem 24308MB
[2025-01-19 05:29:15 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][50/312]	eta 0:02:49 lr 0.000078	time 0.5718 (0.6488)	model_time 0.5716 (0.6196)	loss 2.2425 (2.7267)	grad_norm 2.5154 (2.5595/0.9324)	mem 24308MB
[2025-01-19 05:29:21 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][60/312]	eta 0:02:41 lr 0.000078	time 0.5825 (0.6423)	model_time 0.5823 (0.6178)	loss 2.7129 (2.7233)	grad_norm 1.8323 (2.6573/1.0769)	mem 24308MB
[2025-01-19 05:29:27 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][70/312]	eta 0:02:33 lr 0.000078	time 0.5855 (0.6344)	model_time 0.5851 (0.6133)	loss 2.8682 (2.7166)	grad_norm 6.3783 (2.8269/1.3029)	mem 24308MB
[2025-01-19 05:29:33 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][80/312]	eta 0:02:26 lr 0.000078	time 0.6656 (0.6324)	model_time 0.6654 (0.6139)	loss 3.5298 (2.7452)	grad_norm 4.0810 (2.8905/1.3251)	mem 24308MB
[2025-01-19 05:29:39 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][90/312]	eta 0:02:19 lr 0.000078	time 0.5901 (0.6271)	model_time 0.5897 (0.6106)	loss 2.7139 (2.7605)	grad_norm 2.3550 (2.9639/1.3155)	mem 24308MB
[2025-01-19 05:29:45 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][100/312]	eta 0:02:12 lr 0.000078	time 0.5885 (0.6245)	model_time 0.5881 (0.6096)	loss 3.1468 (2.7615)	grad_norm 1.7005 (2.9360/1.2847)	mem 24308MB
[2025-01-19 05:29:51 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][110/312]	eta 0:02:05 lr 0.000078	time 0.5859 (0.6214)	model_time 0.5858 (0.6077)	loss 3.3293 (2.7568)	grad_norm 3.8055 (2.8852/1.2698)	mem 24308MB
[2025-01-19 05:29:57 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][120/312]	eta 0:01:58 lr 0.000078	time 0.5819 (0.6196)	model_time 0.5814 (0.6071)	loss 2.3085 (2.7563)	grad_norm 3.7260 (2.8856/1.2533)	mem 24308MB
[2025-01-19 05:30:03 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][130/312]	eta 0:01:53 lr 0.000077	time 0.5906 (0.6221)	model_time 0.5904 (0.6105)	loss 2.7996 (2.7606)	grad_norm 2.9643 (2.9022/1.2375)	mem 24308MB
[2025-01-19 05:30:10 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][140/312]	eta 0:01:47 lr 0.000077	time 0.5811 (0.6229)	model_time 0.5809 (0.6121)	loss 2.2908 (2.7616)	grad_norm 2.7396 (2.9135/1.2205)	mem 24308MB
[2025-01-19 05:30:16 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][150/312]	eta 0:01:40 lr 0.000077	time 0.6073 (0.6217)	model_time 0.6069 (0.6116)	loss 2.5811 (2.7485)	grad_norm 1.7946 (2.8529/1.2065)	mem 24308MB
[2025-01-19 05:30:21 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][160/312]	eta 0:01:34 lr 0.000077	time 0.6019 (0.6196)	model_time 0.6014 (0.6101)	loss 3.5287 (2.7490)	grad_norm 1.4150 (2.8345/1.2049)	mem 24308MB
[2025-01-19 05:30:28 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][170/312]	eta 0:01:28 lr 0.000077	time 0.6276 (0.6202)	model_time 0.6272 (0.6112)	loss 2.2176 (2.7344)	grad_norm 2.9804 (2.8477/1.2079)	mem 24308MB
[2025-01-19 05:30:34 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][180/312]	eta 0:01:21 lr 0.000077	time 0.5994 (0.6201)	model_time 0.5990 (0.6115)	loss 2.9896 (2.7419)	grad_norm 2.5676 (2.8346/1.1918)	mem 24308MB
[2025-01-19 05:30:40 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][190/312]	eta 0:01:15 lr 0.000077	time 0.5793 (0.6185)	model_time 0.5791 (0.6104)	loss 3.4070 (2.7423)	grad_norm 2.1726 (2.8393/1.1938)	mem 24308MB
[2025-01-19 05:30:46 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][200/312]	eta 0:01:09 lr 0.000076	time 0.6827 (0.6186)	model_time 0.6825 (0.6109)	loss 3.1276 (2.7445)	grad_norm 2.8845 (2.8463/1.1862)	mem 24308MB
[2025-01-19 05:30:52 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][210/312]	eta 0:01:02 lr 0.000076	time 0.5798 (0.6174)	model_time 0.5796 (0.6100)	loss 3.0461 (2.7494)	grad_norm 2.0092 (2.8488/1.1797)	mem 24308MB
[2025-01-19 05:30:58 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][220/312]	eta 0:00:56 lr 0.000076	time 0.5888 (0.6171)	model_time 0.5882 (0.6100)	loss 3.1105 (2.7510)	grad_norm 7.2836 (2.8758/1.2097)	mem 24308MB
[2025-01-19 05:31:04 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][230/312]	eta 0:00:50 lr 0.000076	time 0.5837 (0.6160)	model_time 0.5833 (0.6093)	loss 3.2596 (2.7467)	grad_norm 3.1253 (2.9207/1.2524)	mem 24308MB
[2025-01-19 05:31:10 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][240/312]	eta 0:00:44 lr 0.000076	time 0.6413 (0.6159)	model_time 0.6408 (0.6094)	loss 2.7619 (2.7344)	grad_norm 4.1184 (2.9507/1.2689)	mem 24308MB
[2025-01-19 05:31:16 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][250/312]	eta 0:00:38 lr 0.000076	time 0.6845 (0.6163)	model_time 0.6841 (0.6100)	loss 2.9633 (2.7369)	grad_norm 4.5712 (2.9824/1.2685)	mem 24308MB
[2025-01-19 05:31:23 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][260/312]	eta 0:00:32 lr 0.000076	time 0.5846 (0.6165)	model_time 0.5845 (0.6105)	loss 2.0962 (2.7372)	grad_norm 2.0344 (2.9948/1.2836)	mem 24308MB
[2025-01-19 05:31:29 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][270/312]	eta 0:00:25 lr 0.000076	time 0.5848 (0.6165)	model_time 0.5846 (0.6107)	loss 2.7949 (2.7314)	grad_norm 2.2081 (2.9716/1.2711)	mem 24308MB
[2025-01-19 05:31:35 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][280/312]	eta 0:00:19 lr 0.000075	time 0.6295 (0.6158)	model_time 0.6290 (0.6101)	loss 3.0545 (2.7316)	grad_norm 6.0461 (2.9905/1.2785)	mem 24308MB
[2025-01-19 05:31:41 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][290/312]	eta 0:00:13 lr 0.000075	time 0.6739 (0.6165)	model_time 0.6735 (0.6111)	loss 3.0351 (2.7396)	grad_norm 5.8238 (3.0482/1.3330)	mem 24308MB
[2025-01-19 05:31:47 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][300/312]	eta 0:00:07 lr 0.000075	time 0.5690 (0.6162)	model_time 0.5689 (0.6109)	loss 2.6694 (2.7309)	grad_norm 2.0841 (3.0504/1.3413)	mem 24308MB
[2025-01-19 05:31:53 internimage_s_1k_224] (main.py 510): INFO Train: [281/300][310/312]	eta 0:00:01 lr 0.000075	time 0.5749 (0.6147)	model_time 0.5749 (0.6096)	loss 3.1477 (2.7417)	grad_norm 1.2216 (3.0654/1.3485)	mem 24308MB
[2025-01-19 05:31:54 internimage_s_1k_224] (main.py 519): INFO EPOCH 281 training takes 0:03:11
[2025-01-19 05:31:54 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_281.pth saving......
[2025-01-19 05:31:55 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_281.pth saved !!!
[2025-01-19 05:32:07 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 11.436 (11.436)	Loss 0.6919 (0.6919)	Acc@1 86.279 (86.279)	Acc@5 97.681 (97.681)	Mem 24308MB
[2025-01-19 05:32:11 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.427)	Loss 0.8756 (0.7714)	Acc@1 80.884 (84.286)	Acc@5 96.216 (96.884)	Mem 24308MB
[2025-01-19 05:32:11 internimage_s_1k_224] (main.py 575): INFO [Epoch:281] * Acc@1 84.141 Acc@5 96.881
[2025-01-19 05:32:11 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 05:32:11 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 05:32:13 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 05:32:13 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.14%
[2025-01-19 05:32:21 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.954 (7.954)	Loss 0.6903 (0.6903)	Acc@1 85.962 (85.962)	Acc@5 97.852 (97.852)	Mem 24308MB
[2025-01-19 05:32:25 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.058)	Loss 0.8692 (0.7631)	Acc@1 80.322 (84.118)	Acc@5 96.240 (96.855)	Mem 24308MB
[2025-01-19 05:32:25 internimage_s_1k_224] (main.py 575): INFO [Epoch:281] * Acc@1 83.991 Acc@5 96.859
[2025-01-19 05:32:25 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.0%
[2025-01-19 05:32:25 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:32:27 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:32:27 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 83.99%
[2025-01-19 05:32:29 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][0/312]	eta 0:11:55 lr 0.000075	time 2.2929 (2.2929)	model_time 0.6091 (0.6091)	loss 3.2211 (3.2211)	grad_norm 3.3533 (3.3533/0.0000)	mem 24308MB
[2025-01-19 05:32:35 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][10/312]	eta 0:03:51 lr 0.000075	time 0.5801 (0.7661)	model_time 0.5799 (0.6127)	loss 3.0961 (2.8405)	grad_norm 1.8490 (2.3889/0.4903)	mem 24308MB
[2025-01-19 05:32:41 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][20/312]	eta 0:03:20 lr 0.000075	time 0.6016 (0.6856)	model_time 0.6011 (0.6052)	loss 2.8457 (2.7610)	grad_norm 1.8928 (2.6426/0.6012)	mem 24308MB
[2025-01-19 05:32:47 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][30/312]	eta 0:03:06 lr 0.000075	time 0.5790 (0.6599)	model_time 0.5788 (0.6053)	loss 3.3098 (2.7408)	grad_norm 2.0096 (2.5668/0.7053)	mem 24308MB
[2025-01-19 05:32:53 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][40/312]	eta 0:02:54 lr 0.000075	time 0.5885 (0.6424)	model_time 0.5882 (0.6010)	loss 3.0399 (2.6780)	grad_norm 2.7255 (2.5212/0.6865)	mem 24308MB
[2025-01-19 05:32:59 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][50/312]	eta 0:02:46 lr 0.000074	time 0.5868 (0.6359)	model_time 0.5789 (0.6024)	loss 2.9152 (2.6668)	grad_norm 3.0895 (2.5197/0.6941)	mem 24308MB
[2025-01-19 05:33:06 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][60/312]	eta 0:02:39 lr 0.000074	time 0.5915 (0.6341)	model_time 0.5914 (0.6060)	loss 3.0832 (2.6820)	grad_norm 2.1015 (2.6861/1.0052)	mem 24308MB
[2025-01-19 05:33:12 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][70/312]	eta 0:02:32 lr 0.000074	time 0.5947 (0.6306)	model_time 0.5940 (0.6065)	loss 2.6448 (2.6748)	grad_norm 1.7904 (2.8023/1.0896)	mem 24308MB
[2025-01-19 05:33:18 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][80/312]	eta 0:02:25 lr 0.000074	time 0.6012 (0.6278)	model_time 0.6007 (0.6066)	loss 3.1101 (2.6737)	grad_norm 4.5984 (3.0368/1.4432)	mem 24308MB
[2025-01-19 05:33:24 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][90/312]	eta 0:02:18 lr 0.000074	time 0.6616 (0.6242)	model_time 0.6614 (0.6053)	loss 3.3646 (2.7035)	grad_norm 4.3209 (3.0116/1.4015)	mem 24308MB
[2025-01-19 05:33:30 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][100/312]	eta 0:02:12 lr 0.000074	time 0.6659 (0.6236)	model_time 0.6657 (0.6065)	loss 1.8963 (2.6790)	grad_norm 2.7975 (2.9187/1.3690)	mem 24308MB
[2025-01-19 05:33:36 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][110/312]	eta 0:02:05 lr 0.000074	time 0.5898 (0.6225)	model_time 0.5893 (0.6069)	loss 2.9315 (2.6808)	grad_norm 2.1551 (2.8424/1.3450)	mem 24308MB
[2025-01-19 05:33:42 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][120/312]	eta 0:01:58 lr 0.000074	time 0.5910 (0.6197)	model_time 0.5909 (0.6054)	loss 3.0790 (2.6810)	grad_norm 4.4400 (2.8507/1.3247)	mem 24308MB
[2025-01-19 05:33:48 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][130/312]	eta 0:01:52 lr 0.000073	time 0.5904 (0.6186)	model_time 0.5902 (0.6054)	loss 2.9759 (2.6870)	grad_norm 1.9918 (2.8128/1.3159)	mem 24308MB
[2025-01-19 05:33:54 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][140/312]	eta 0:01:46 lr 0.000073	time 0.5735 (0.6166)	model_time 0.5733 (0.6043)	loss 3.1367 (2.6819)	grad_norm 1.8407 (2.8035/1.2825)	mem 24308MB
[2025-01-19 05:34:00 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][150/312]	eta 0:01:39 lr 0.000073	time 0.6100 (0.6154)	model_time 0.6098 (0.6039)	loss 2.2814 (2.6711)	grad_norm 1.6675 (2.8256/1.2957)	mem 24308MB
[2025-01-19 05:34:06 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][160/312]	eta 0:01:33 lr 0.000073	time 0.5873 (0.6141)	model_time 0.5871 (0.6032)	loss 2.9580 (2.6715)	grad_norm 3.0770 (2.8808/1.3458)	mem 24308MB
[2025-01-19 05:34:12 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][170/312]	eta 0:01:27 lr 0.000073	time 0.5877 (0.6133)	model_time 0.5875 (0.6031)	loss 2.7339 (2.6876)	grad_norm 3.2512 (2.9214/1.3576)	mem 24308MB
[2025-01-19 05:34:18 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][180/312]	eta 0:01:21 lr 0.000073	time 0.5861 (0.6139)	model_time 0.5857 (0.6042)	loss 2.8675 (2.6834)	grad_norm 2.4574 (2.9902/1.4094)	mem 24308MB
[2025-01-19 05:34:24 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][190/312]	eta 0:01:14 lr 0.000073	time 0.5817 (0.6143)	model_time 0.5813 (0.6051)	loss 1.8289 (2.6960)	grad_norm 2.9950 (3.0107/1.3912)	mem 24308MB
[2025-01-19 05:34:30 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][200/312]	eta 0:01:08 lr 0.000073	time 0.5834 (0.6141)	model_time 0.5832 (0.6053)	loss 2.6752 (2.6993)	grad_norm 1.8522 (2.9634/1.3796)	mem 24308MB
[2025-01-19 05:34:36 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][210/312]	eta 0:01:02 lr 0.000073	time 0.5785 (0.6129)	model_time 0.5780 (0.6046)	loss 3.1690 (2.7102)	grad_norm 2.4750 (2.9486/1.3524)	mem 24308MB
[2025-01-19 05:34:43 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][220/312]	eta 0:00:56 lr 0.000072	time 0.7557 (0.6140)	model_time 0.7555 (0.6059)	loss 2.5257 (2.7102)	grad_norm 3.6825 (2.9361/1.3345)	mem 24308MB
[2025-01-19 05:34:49 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][230/312]	eta 0:00:50 lr 0.000072	time 0.5948 (0.6136)	model_time 0.5946 (0.6059)	loss 3.0738 (2.7074)	grad_norm 3.9958 (2.9542/1.3183)	mem 24308MB
[2025-01-19 05:34:55 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][240/312]	eta 0:00:44 lr 0.000072	time 0.5726 (0.6128)	model_time 0.5721 (0.6054)	loss 1.8804 (2.7029)	grad_norm 1.2065 (2.9439/1.2996)	mem 24308MB
[2025-01-19 05:35:01 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][250/312]	eta 0:00:37 lr 0.000072	time 0.6630 (0.6129)	model_time 0.6629 (0.6058)	loss 2.7173 (2.6970)	grad_norm 2.7354 (2.9395/1.2937)	mem 24308MB
[2025-01-19 05:35:07 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][260/312]	eta 0:00:31 lr 0.000072	time 0.5977 (0.6125)	model_time 0.5976 (0.6057)	loss 3.3685 (2.7008)	grad_norm 4.8959 (2.9486/1.2820)	mem 24308MB
[2025-01-19 05:35:13 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][270/312]	eta 0:00:25 lr 0.000072	time 0.6018 (0.6119)	model_time 0.6014 (0.6053)	loss 2.4731 (2.6991)	grad_norm 1.8180 (2.9419/1.2694)	mem 24308MB
[2025-01-19 05:35:19 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][280/312]	eta 0:00:19 lr 0.000072	time 0.5817 (0.6113)	model_time 0.5815 (0.6049)	loss 2.4316 (2.7017)	grad_norm 1.8492 (2.9215/1.2584)	mem 24308MB
[2025-01-19 05:35:25 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][290/312]	eta 0:00:13 lr 0.000072	time 0.5963 (0.6111)	model_time 0.5961 (0.6049)	loss 3.0839 (2.7076)	grad_norm 1.8906 (2.9012/1.2478)	mem 24308MB
[2025-01-19 05:35:31 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][300/312]	eta 0:00:07 lr 0.000071	time 0.5695 (0.6111)	model_time 0.5694 (0.6051)	loss 3.1168 (2.7144)	grad_norm 2.5600 (2.8763/1.2373)	mem 24308MB
[2025-01-19 05:35:37 internimage_s_1k_224] (main.py 510): INFO Train: [282/300][310/312]	eta 0:00:01 lr 0.000071	time 0.6482 (0.6108)	model_time 0.6481 (0.6050)	loss 3.1926 (2.7153)	grad_norm 2.0087 (2.8962/1.2437)	mem 24308MB
[2025-01-19 05:35:38 internimage_s_1k_224] (main.py 519): INFO EPOCH 282 training takes 0:03:10
[2025-01-19 05:35:38 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_282.pth saving......
[2025-01-19 05:35:39 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_282.pth saved !!!
[2025-01-19 05:35:47 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.759 (7.759)	Loss 0.7044 (0.7044)	Acc@1 85.913 (85.913)	Acc@5 97.778 (97.778)	Mem 24308MB
[2025-01-19 05:35:51 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.039)	Loss 0.8832 (0.7786)	Acc@1 80.591 (84.226)	Acc@5 96.118 (96.871)	Mem 24308MB
[2025-01-19 05:35:51 internimage_s_1k_224] (main.py 575): INFO [Epoch:282] * Acc@1 84.075 Acc@5 96.879
[2025-01-19 05:35:51 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 05:35:51 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.14%
[2025-01-19 05:36:00 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.122 (9.122)	Loss 0.6902 (0.6902)	Acc@1 85.962 (85.962)	Acc@5 97.852 (97.852)	Mem 24308MB
[2025-01-19 05:36:08 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.588)	Loss 0.8687 (0.7628)	Acc@1 80.322 (84.126)	Acc@5 96.240 (96.848)	Mem 24308MB
[2025-01-19 05:36:09 internimage_s_1k_224] (main.py 575): INFO [Epoch:282] * Acc@1 83.997 Acc@5 96.853
[2025-01-19 05:36:09 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.0%
[2025-01-19 05:36:09 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:36:11 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:36:11 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 84.00%
[2025-01-19 05:36:13 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][0/312]	eta 0:11:14 lr 0.000071	time 2.1617 (2.1617)	model_time 0.5987 (0.5987)	loss 1.8568 (1.8568)	grad_norm 1.3991 (1.3991/0.0000)	mem 24308MB
[2025-01-19 05:36:19 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][10/312]	eta 0:03:48 lr 0.000071	time 0.5817 (0.7569)	model_time 0.5815 (0.6145)	loss 2.6922 (2.6352)	grad_norm 1.4132 (2.4123/0.8041)	mem 24308MB
[2025-01-19 05:36:25 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][20/312]	eta 0:03:18 lr 0.000071	time 0.6088 (0.6788)	model_time 0.6086 (0.6040)	loss 1.9539 (2.6167)	grad_norm 4.5140 (2.7815/1.0310)	mem 24308MB
[2025-01-19 05:36:31 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][30/312]	eta 0:03:06 lr 0.000071	time 0.5790 (0.6600)	model_time 0.5788 (0.6092)	loss 2.5249 (2.7070)	grad_norm 1.4877 (2.5715/0.9531)	mem 24308MB
[2025-01-19 05:36:37 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][40/312]	eta 0:02:56 lr 0.000071	time 0.5891 (0.6472)	model_time 0.5887 (0.6087)	loss 2.1208 (2.6416)	grad_norm 2.3151 (2.5359/0.9566)	mem 24308MB
[2025-01-19 05:36:43 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][50/312]	eta 0:02:46 lr 0.000071	time 0.5774 (0.6351)	model_time 0.5772 (0.6041)	loss 2.5733 (2.6314)	grad_norm 2.4844 (2.5470/0.9306)	mem 24308MB
[2025-01-19 05:36:49 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][60/312]	eta 0:02:39 lr 0.000071	time 0.5937 (0.6318)	model_time 0.5935 (0.6058)	loss 1.9861 (2.6703)	grad_norm 2.1627 (2.5343/0.9232)	mem 24308MB
[2025-01-19 05:36:55 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][70/312]	eta 0:02:31 lr 0.000070	time 0.6098 (0.6268)	model_time 0.6097 (0.6044)	loss 2.4853 (2.6979)	grad_norm 1.8413 (2.5255/0.9205)	mem 24308MB
[2025-01-19 05:37:01 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][80/312]	eta 0:02:24 lr 0.000070	time 0.5832 (0.6227)	model_time 0.5830 (0.6030)	loss 2.9200 (2.7211)	grad_norm 5.2338 (2.5717/0.9320)	mem 24308MB
[2025-01-19 05:37:07 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][90/312]	eta 0:02:17 lr 0.000070	time 0.5884 (0.6201)	model_time 0.5882 (0.6025)	loss 2.9400 (2.7528)	grad_norm 1.9254 (2.6575/0.9971)	mem 24308MB
[2025-01-19 05:37:13 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][100/312]	eta 0:02:11 lr 0.000070	time 0.5800 (0.6191)	model_time 0.5799 (0.6032)	loss 2.3470 (2.7476)	grad_norm 2.5353 (2.6870/1.0285)	mem 24308MB
[2025-01-19 05:37:19 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][110/312]	eta 0:02:04 lr 0.000070	time 0.5944 (0.6184)	model_time 0.5942 (0.6039)	loss 2.9287 (2.7601)	grad_norm 2.5428 (2.7013/1.0155)	mem 24308MB
[2025-01-19 05:37:26 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][120/312]	eta 0:01:58 lr 0.000070	time 0.6681 (0.6187)	model_time 0.6676 (0.6054)	loss 2.8595 (2.7412)	grad_norm 4.1847 (2.7823/1.1128)	mem 24308MB
[2025-01-19 05:37:32 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][130/312]	eta 0:01:52 lr 0.000070	time 0.5736 (0.6175)	model_time 0.5733 (0.6052)	loss 1.6278 (2.7377)	grad_norm 2.2386 (2.8662/1.1437)	mem 24308MB
[2025-01-19 05:37:38 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][140/312]	eta 0:01:45 lr 0.000070	time 0.5957 (0.6162)	model_time 0.5953 (0.6048)	loss 3.0378 (2.7560)	grad_norm 1.7427 (2.9274/1.2330)	mem 24308MB
[2025-01-19 05:37:44 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][150/312]	eta 0:01:39 lr 0.000070	time 0.7073 (0.6168)	model_time 0.7069 (0.6061)	loss 2.8773 (2.7531)	grad_norm 2.4512 (2.9391/1.2286)	mem 24308MB
[2025-01-19 05:37:50 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][160/312]	eta 0:01:33 lr 0.000069	time 0.5774 (0.6169)	model_time 0.5773 (0.6068)	loss 2.9841 (2.7636)	grad_norm 3.2526 (2.9115/1.2129)	mem 24308MB
[2025-01-19 05:37:56 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][170/312]	eta 0:01:27 lr 0.000069	time 0.5794 (0.6158)	model_time 0.5792 (0.6063)	loss 2.8654 (2.7572)	grad_norm 1.8564 (2.9042/1.1978)	mem 24308MB
[2025-01-19 05:38:02 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][180/312]	eta 0:01:21 lr 0.000069	time 0.5793 (0.6150)	model_time 0.5791 (0.6060)	loss 3.2007 (2.7656)	grad_norm 3.5301 (2.8835/1.1950)	mem 24308MB
[2025-01-19 05:38:08 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][190/312]	eta 0:01:14 lr 0.000069	time 0.5798 (0.6139)	model_time 0.5797 (0.6054)	loss 2.6424 (2.7638)	grad_norm 3.1228 (2.8673/1.1760)	mem 24308MB
[2025-01-19 05:38:14 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][200/312]	eta 0:01:08 lr 0.000069	time 0.5839 (0.6131)	model_time 0.5838 (0.6050)	loss 1.8432 (2.7581)	grad_norm 2.2621 (2.8473/1.1611)	mem 24308MB
[2025-01-19 05:38:20 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][210/312]	eta 0:01:02 lr 0.000069	time 0.6322 (0.6125)	model_time 0.6320 (0.6047)	loss 2.4271 (2.7644)	grad_norm 1.8810 (2.8459/1.1633)	mem 24308MB
[2025-01-19 05:38:26 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][220/312]	eta 0:00:56 lr 0.000069	time 0.5915 (0.6124)	model_time 0.5913 (0.6050)	loss 2.3853 (2.7597)	grad_norm 1.5602 (2.8451/1.1692)	mem 24308MB
[2025-01-19 05:38:32 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][230/312]	eta 0:00:50 lr 0.000069	time 0.5857 (0.6123)	model_time 0.5853 (0.6052)	loss 2.6627 (2.7628)	grad_norm 3.3116 (2.8386/1.1654)	mem 24308MB
[2025-01-19 05:38:38 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][240/312]	eta 0:00:44 lr 0.000069	time 0.5904 (0.6122)	model_time 0.5900 (0.6054)	loss 2.9511 (2.7589)	grad_norm 6.2490 (2.8566/1.1976)	mem 24308MB
[2025-01-19 05:38:44 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][250/312]	eta 0:00:37 lr 0.000068	time 0.5788 (0.6123)	model_time 0.5786 (0.6057)	loss 2.1442 (2.7650)	grad_norm 3.4653 (2.8716/1.2056)	mem 24308MB
[2025-01-19 05:38:50 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][260/312]	eta 0:00:31 lr 0.000068	time 0.5936 (0.6115)	model_time 0.5934 (0.6052)	loss 2.8310 (2.7645)	grad_norm 2.5044 (2.8793/1.1977)	mem 24308MB
[2025-01-19 05:38:57 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][270/312]	eta 0:00:25 lr 0.000068	time 0.6619 (0.6118)	model_time 0.6615 (0.6056)	loss 2.1838 (2.7605)	grad_norm 3.3952 (2.8731/1.1829)	mem 24308MB
[2025-01-19 05:39:03 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][280/312]	eta 0:00:19 lr 0.000068	time 0.6117 (0.6119)	model_time 0.6116 (0.6060)	loss 2.9274 (2.7648)	grad_norm 4.5483 (2.8895/1.1791)	mem 24308MB
[2025-01-19 05:39:09 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][290/312]	eta 0:00:13 lr 0.000068	time 0.5783 (0.6113)	model_time 0.5781 (0.6056)	loss 3.0620 (2.7613)	grad_norm 2.9592 (2.8867/1.1713)	mem 24308MB
[2025-01-19 05:39:14 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][300/312]	eta 0:00:07 lr 0.000068	time 0.5701 (0.6104)	model_time 0.5700 (0.6048)	loss 1.6972 (2.7660)	grad_norm 1.8925 (2.8776/1.1556)	mem 24308MB
[2025-01-19 05:39:20 internimage_s_1k_224] (main.py 510): INFO Train: [283/300][310/312]	eta 0:00:01 lr 0.000068	time 0.5670 (0.6097)	model_time 0.5669 (0.6043)	loss 3.0710 (2.7635)	grad_norm 5.1872 (2.8965/1.1592)	mem 24308MB
[2025-01-19 05:39:21 internimage_s_1k_224] (main.py 519): INFO EPOCH 283 training takes 0:03:10
[2025-01-19 05:39:21 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_283.pth saving......
[2025-01-19 05:39:23 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_283.pth saved !!!
[2025-01-19 05:39:31 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.891 (7.891)	Loss 0.6917 (0.6917)	Acc@1 85.889 (85.889)	Acc@5 97.925 (97.925)	Mem 24308MB
[2025-01-19 05:39:34 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.024)	Loss 0.8802 (0.7715)	Acc@1 80.957 (84.144)	Acc@5 96.069 (96.866)	Mem 24308MB
[2025-01-19 05:39:34 internimage_s_1k_224] (main.py 575): INFO [Epoch:283] * Acc@1 83.991 Acc@5 96.871
[2025-01-19 05:39:34 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.0%
[2025-01-19 05:39:34 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.14%
[2025-01-19 05:39:43 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.879 (8.879)	Loss 0.6900 (0.6900)	Acc@1 85.962 (85.962)	Acc@5 97.852 (97.852)	Mem 24308MB
[2025-01-19 05:39:48 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.208)	Loss 0.8684 (0.7626)	Acc@1 80.396 (84.146)	Acc@5 96.265 (96.866)	Mem 24308MB
[2025-01-19 05:39:48 internimage_s_1k_224] (main.py 575): INFO [Epoch:283] * Acc@1 84.011 Acc@5 96.871
[2025-01-19 05:39:48 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.0%
[2025-01-19 05:39:48 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:39:50 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:39:50 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 84.01%
[2025-01-19 05:39:52 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][0/312]	eta 0:11:46 lr 0.000068	time 2.2638 (2.2638)	model_time 0.5901 (0.5901)	loss 2.5815 (2.5815)	grad_norm 3.3141 (3.3141/0.0000)	mem 24308MB
[2025-01-19 05:39:58 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][10/312]	eta 0:03:47 lr 0.000068	time 0.5971 (0.7519)	model_time 0.5970 (0.5994)	loss 2.8343 (2.9015)	grad_norm 3.6220 (3.6483/1.0474)	mem 24308MB
[2025-01-19 05:40:04 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][20/312]	eta 0:03:18 lr 0.000068	time 0.5844 (0.6791)	model_time 0.5840 (0.5990)	loss 2.5237 (2.8894)	grad_norm 3.0446 (3.5571/0.9837)	mem 24308MB
[2025-01-19 05:40:10 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][30/312]	eta 0:03:04 lr 0.000067	time 0.5792 (0.6544)	model_time 0.5787 (0.6000)	loss 2.9058 (2.8615)	grad_norm 2.5716 (3.3076/1.0167)	mem 24308MB
[2025-01-19 05:40:16 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][40/312]	eta 0:02:55 lr 0.000067	time 0.6668 (0.6463)	model_time 0.6667 (0.6051)	loss 2.9723 (2.8151)	grad_norm 1.6240 (3.0787/1.0006)	mem 24308MB
[2025-01-19 05:40:23 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][50/312]	eta 0:02:47 lr 0.000067	time 0.5711 (0.6407)	model_time 0.5710 (0.6075)	loss 2.6258 (2.8116)	grad_norm 1.2995 (3.0122/1.0053)	mem 24308MB
[2025-01-19 05:40:29 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][60/312]	eta 0:02:40 lr 0.000067	time 0.6627 (0.6365)	model_time 0.6622 (0.6087)	loss 2.5103 (2.7872)	grad_norm 4.0165 (3.0544/1.0980)	mem 24308MB
[2025-01-19 05:40:35 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][70/312]	eta 0:02:33 lr 0.000067	time 0.5788 (0.6326)	model_time 0.5786 (0.6086)	loss 1.8636 (2.7973)	grad_norm 2.8037 (2.9913/1.0708)	mem 24308MB
[2025-01-19 05:40:41 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][80/312]	eta 0:02:26 lr 0.000067	time 0.6784 (0.6319)	model_time 0.6780 (0.6109)	loss 2.7304 (2.7896)	grad_norm 2.2015 (2.9300/1.0533)	mem 24308MB
[2025-01-19 05:40:47 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][90/312]	eta 0:02:19 lr 0.000067	time 0.5821 (0.6299)	model_time 0.5820 (0.6112)	loss 3.1383 (2.8124)	grad_norm 1.8021 (2.8888/1.0362)	mem 24308MB
[2025-01-19 05:40:53 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][100/312]	eta 0:02:12 lr 0.000067	time 0.6182 (0.6273)	model_time 0.6178 (0.6104)	loss 2.9357 (2.7840)	grad_norm 3.1745 (2.8493/1.0190)	mem 24308MB
[2025-01-19 05:40:59 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][110/312]	eta 0:02:06 lr 0.000067	time 0.6571 (0.6247)	model_time 0.6569 (0.6093)	loss 3.3738 (2.7761)	grad_norm 4.5551 (2.8394/1.0247)	mem 24308MB
[2025-01-19 05:41:05 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][120/312]	eta 0:01:59 lr 0.000066	time 0.6482 (0.6234)	model_time 0.6480 (0.6092)	loss 3.0480 (2.7807)	grad_norm 3.1991 (2.8246/1.0000)	mem 24308MB
[2025-01-19 05:41:11 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][130/312]	eta 0:01:53 lr 0.000066	time 0.5950 (0.6216)	model_time 0.5946 (0.6085)	loss 2.9186 (2.7625)	grad_norm 4.7393 (2.9598/1.1012)	mem 24308MB
[2025-01-19 05:41:17 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][140/312]	eta 0:01:46 lr 0.000066	time 0.5724 (0.6198)	model_time 0.5719 (0.6075)	loss 1.9183 (2.7574)	grad_norm 1.8007 (2.9926/1.1268)	mem 24308MB
[2025-01-19 05:41:23 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][150/312]	eta 0:01:40 lr 0.000066	time 0.5775 (0.6188)	model_time 0.5773 (0.6074)	loss 2.7597 (2.7595)	grad_norm 2.4013 (3.0158/1.1416)	mem 24308MB
[2025-01-19 05:41:29 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][160/312]	eta 0:01:33 lr 0.000066	time 0.6531 (0.6179)	model_time 0.6527 (0.6071)	loss 2.7026 (2.7599)	grad_norm 2.9299 (3.0281/1.1392)	mem 24308MB
[2025-01-19 05:41:36 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][170/312]	eta 0:01:27 lr 0.000066	time 0.5776 (0.6184)	model_time 0.5774 (0.6083)	loss 3.1876 (2.7447)	grad_norm 4.5089 (3.0348/1.1408)	mem 24308MB
[2025-01-19 05:41:42 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][180/312]	eta 0:01:21 lr 0.000066	time 0.7061 (0.6185)	model_time 0.7057 (0.6089)	loss 2.4745 (2.7456)	grad_norm 2.4621 (3.0018/1.1415)	mem 24308MB
[2025-01-19 05:41:48 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][190/312]	eta 0:01:15 lr 0.000066	time 0.5825 (0.6186)	model_time 0.5824 (0.6095)	loss 2.8798 (2.7443)	grad_norm 1.4441 (3.0010/1.1724)	mem 24308MB
[2025-01-19 05:41:54 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][200/312]	eta 0:01:09 lr 0.000066	time 0.6883 (0.6180)	model_time 0.6881 (0.6093)	loss 1.8144 (2.7394)	grad_norm 3.5236 (2.9744/1.1669)	mem 24308MB
[2025-01-19 05:42:01 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][210/312]	eta 0:01:03 lr 0.000065	time 0.5793 (0.6189)	model_time 0.5789 (0.6106)	loss 1.5862 (2.7349)	grad_norm 2.4915 (2.9744/1.1613)	mem 24308MB
[2025-01-19 05:42:07 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][220/312]	eta 0:00:56 lr 0.000065	time 0.5857 (0.6188)	model_time 0.5852 (0.6108)	loss 2.8792 (2.7399)	grad_norm 4.2811 (2.9578/1.1525)	mem 24308MB
[2025-01-19 05:42:13 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][230/312]	eta 0:00:50 lr 0.000065	time 0.6605 (0.6181)	model_time 0.6601 (0.6104)	loss 3.2331 (2.7484)	grad_norm 3.0173 (2.9390/1.1447)	mem 24308MB
[2025-01-19 05:42:19 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][240/312]	eta 0:00:44 lr 0.000065	time 0.5700 (0.6174)	model_time 0.5699 (0.6101)	loss 2.0696 (2.7386)	grad_norm 3.2567 (2.9403/1.1381)	mem 24308MB
[2025-01-19 05:42:25 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][250/312]	eta 0:00:38 lr 0.000065	time 0.5736 (0.6168)	model_time 0.5734 (0.6097)	loss 2.3095 (2.7382)	grad_norm 4.6630 (2.9498/1.1345)	mem 24308MB
[2025-01-19 05:42:31 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][260/312]	eta 0:00:32 lr 0.000065	time 0.5654 (0.6158)	model_time 0.5653 (0.6090)	loss 2.9726 (2.7371)	grad_norm 2.8605 (2.9465/1.1296)	mem 24308MB
[2025-01-19 05:42:37 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][270/312]	eta 0:00:25 lr 0.000065	time 0.6976 (0.6157)	model_time 0.6971 (0.6091)	loss 2.8165 (2.7405)	grad_norm 3.6112 (2.9565/1.1250)	mem 24308MB
[2025-01-19 05:42:43 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][280/312]	eta 0:00:19 lr 0.000065	time 0.5862 (0.6150)	model_time 0.5857 (0.6086)	loss 3.3200 (2.7414)	grad_norm 2.6517 (2.9440/1.1198)	mem 24308MB
[2025-01-19 05:42:49 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][290/312]	eta 0:00:13 lr 0.000065	time 0.5953 (0.6154)	model_time 0.5951 (0.6093)	loss 2.9369 (2.7385)	grad_norm 5.8625 (2.9456/1.1300)	mem 24308MB
[2025-01-19 05:42:55 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][300/312]	eta 0:00:07 lr 0.000065	time 0.5682 (0.6150)	model_time 0.5681 (0.6091)	loss 2.9176 (2.7437)	grad_norm 4.2892 (2.9653/1.1523)	mem 24308MB
[2025-01-19 05:43:01 internimage_s_1k_224] (main.py 510): INFO Train: [284/300][310/312]	eta 0:00:01 lr 0.000064	time 0.5575 (0.6150)	model_time 0.5574 (0.6093)	loss 2.9510 (2.7431)	grad_norm 1.8487 (2.9307/1.1521)	mem 24308MB
[2025-01-19 05:43:02 internimage_s_1k_224] (main.py 519): INFO EPOCH 284 training takes 0:03:11
[2025-01-19 05:43:02 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_284.pth saving......
[2025-01-19 05:43:04 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_284.pth saved !!!
[2025-01-19 05:43:11 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.742 (7.742)	Loss 0.6963 (0.6963)	Acc@1 86.060 (86.060)	Acc@5 97.900 (97.900)	Mem 24308MB
[2025-01-19 05:43:15 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.038)	Loss 0.8774 (0.7742)	Acc@1 80.713 (84.175)	Acc@5 96.191 (96.871)	Mem 24308MB
[2025-01-19 05:43:15 internimage_s_1k_224] (main.py 575): INFO [Epoch:284] * Acc@1 84.001 Acc@5 96.865
[2025-01-19 05:43:15 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.0%
[2025-01-19 05:43:15 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.14%
[2025-01-19 05:43:24 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.004 (9.004)	Loss 0.6898 (0.6898)	Acc@1 85.938 (85.938)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 05:43:29 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.220)	Loss 0.8680 (0.7623)	Acc@1 80.518 (84.180)	Acc@5 96.265 (96.862)	Mem 24308MB
[2025-01-19 05:43:29 internimage_s_1k_224] (main.py 575): INFO [Epoch:284] * Acc@1 84.037 Acc@5 96.867
[2025-01-19 05:43:29 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.0%
[2025-01-19 05:43:29 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:43:31 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:43:31 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 84.04%
[2025-01-19 05:43:33 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][0/312]	eta 0:11:58 lr 0.000064	time 2.3026 (2.3026)	model_time 0.6014 (0.6014)	loss 2.3674 (2.3674)	grad_norm 1.9293 (1.9293/0.0000)	mem 24308MB
[2025-01-19 05:43:40 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][10/312]	eta 0:03:54 lr 0.000064	time 0.5807 (0.7756)	model_time 0.5806 (0.6207)	loss 2.7000 (2.8454)	grad_norm 5.7683 (3.0203/1.5414)	mem 24308MB
[2025-01-19 05:43:46 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][20/312]	eta 0:03:23 lr 0.000064	time 0.6716 (0.6982)	model_time 0.6714 (0.6169)	loss 2.8062 (2.8073)	grad_norm 4.6162 (3.9260/1.5576)	mem 24308MB
[2025-01-19 05:43:52 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][30/312]	eta 0:03:07 lr 0.000064	time 0.5804 (0.6650)	model_time 0.5782 (0.6098)	loss 2.9514 (2.7531)	grad_norm 4.9078 (4.0120/1.4055)	mem 24308MB
[2025-01-19 05:43:58 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][40/312]	eta 0:02:57 lr 0.000064	time 0.6588 (0.6511)	model_time 0.6586 (0.6092)	loss 2.4471 (2.7473)	grad_norm 3.6145 (3.8819/1.4016)	mem 24308MB
[2025-01-19 05:44:04 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][50/312]	eta 0:02:47 lr 0.000064	time 0.5824 (0.6406)	model_time 0.5822 (0.6068)	loss 2.5829 (2.7626)	grad_norm 1.6029 (3.6835/1.4435)	mem 24308MB
[2025-01-19 05:44:10 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][60/312]	eta 0:02:39 lr 0.000064	time 0.6052 (0.6341)	model_time 0.6049 (0.6058)	loss 2.6058 (2.7584)	grad_norm 3.2648 (3.5512/1.4313)	mem 24308MB
[2025-01-19 05:44:16 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][70/312]	eta 0:02:32 lr 0.000064	time 0.5951 (0.6295)	model_time 0.5947 (0.6052)	loss 2.9685 (2.7552)	grad_norm 1.4324 (3.4544/1.4516)	mem 24308MB
[2025-01-19 05:44:22 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][80/312]	eta 0:02:25 lr 0.000064	time 0.5757 (0.6259)	model_time 0.5755 (0.6045)	loss 3.2568 (2.7647)	grad_norm 2.8666 (3.4461/1.3997)	mem 24308MB
[2025-01-19 05:44:28 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][90/312]	eta 0:02:18 lr 0.000063	time 0.5909 (0.6234)	model_time 0.5904 (0.6040)	loss 1.8396 (2.7510)	grad_norm 4.8035 (3.4102/1.3743)	mem 24308MB
[2025-01-19 05:44:34 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][100/312]	eta 0:02:12 lr 0.000063	time 0.6875 (0.6235)	model_time 0.6874 (0.6060)	loss 1.9420 (2.7106)	grad_norm 2.1124 (3.2844/1.3670)	mem 24308MB
[2025-01-19 05:44:40 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][110/312]	eta 0:02:05 lr 0.000063	time 0.5978 (0.6213)	model_time 0.5974 (0.6053)	loss 2.9934 (2.7161)	grad_norm 1.4657 (3.1930/1.3564)	mem 24308MB
[2025-01-19 05:44:46 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][120/312]	eta 0:01:59 lr 0.000063	time 0.6733 (0.6207)	model_time 0.6732 (0.6060)	loss 2.7839 (2.7228)	grad_norm 2.5442 (3.1070/1.3351)	mem 24308MB
[2025-01-19 05:44:52 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][130/312]	eta 0:01:52 lr 0.000063	time 0.5856 (0.6206)	model_time 0.5855 (0.6070)	loss 2.4294 (2.7136)	grad_norm 2.1617 (3.0357/1.3176)	mem 24308MB
[2025-01-19 05:44:59 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][140/312]	eta 0:01:46 lr 0.000063	time 0.5901 (0.6207)	model_time 0.5897 (0.6080)	loss 2.6222 (2.7239)	grad_norm 2.0435 (3.0021/1.2960)	mem 24308MB
[2025-01-19 05:45:05 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][150/312]	eta 0:01:40 lr 0.000063	time 0.5833 (0.6194)	model_time 0.5832 (0.6075)	loss 1.8065 (2.7081)	grad_norm 1.9702 (2.9898/1.2735)	mem 24308MB
[2025-01-19 05:45:11 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][160/312]	eta 0:01:33 lr 0.000063	time 0.5923 (0.6182)	model_time 0.5922 (0.6070)	loss 1.7790 (2.7094)	grad_norm 5.6737 (2.9992/1.2673)	mem 24308MB
[2025-01-19 05:45:17 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][170/312]	eta 0:01:27 lr 0.000063	time 0.5870 (0.6173)	model_time 0.5869 (0.6068)	loss 3.0013 (2.7019)	grad_norm 3.5685 (2.9742/1.2503)	mem 24308MB
[2025-01-19 05:45:23 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][180/312]	eta 0:01:21 lr 0.000063	time 0.5906 (0.6165)	model_time 0.5904 (0.6066)	loss 1.9245 (2.6890)	grad_norm 5.4613 (3.0015/1.2442)	mem 24308MB
[2025-01-19 05:45:29 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][190/312]	eta 0:01:15 lr 0.000062	time 0.5970 (0.6156)	model_time 0.5968 (0.6061)	loss 3.2252 (2.6887)	grad_norm 1.4941 (2.9882/1.2617)	mem 24308MB
[2025-01-19 05:45:35 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][200/312]	eta 0:01:08 lr 0.000062	time 0.5730 (0.6146)	model_time 0.5726 (0.6056)	loss 2.9074 (2.6900)	grad_norm 2.4120 (2.9838/1.2416)	mem 24308MB
[2025-01-19 05:45:41 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][210/312]	eta 0:01:02 lr 0.000062	time 0.5741 (0.6145)	model_time 0.5740 (0.6059)	loss 2.0881 (2.6971)	grad_norm 1.5324 (2.9419/1.2348)	mem 24308MB
[2025-01-19 05:45:47 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][220/312]	eta 0:00:56 lr 0.000062	time 0.6734 (0.6148)	model_time 0.6730 (0.6066)	loss 3.0298 (2.7013)	grad_norm 2.8769 (2.9239/1.2114)	mem 24308MB
[2025-01-19 05:45:53 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][230/312]	eta 0:00:50 lr 0.000062	time 0.5929 (0.6147)	model_time 0.5924 (0.6068)	loss 2.4096 (2.7002)	grad_norm 2.3646 (2.9222/1.2129)	mem 24308MB
[2025-01-19 05:45:59 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][240/312]	eta 0:00:44 lr 0.000062	time 0.6599 (0.6155)	model_time 0.6597 (0.6080)	loss 2.5408 (2.6981)	grad_norm 1.5574 (2.9140/1.2065)	mem 24308MB
[2025-01-19 05:46:06 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][250/312]	eta 0:00:38 lr 0.000062	time 0.5790 (0.6153)	model_time 0.5789 (0.6080)	loss 2.3991 (2.6841)	grad_norm 1.2476 (2.8902/1.1990)	mem 24308MB
[2025-01-19 05:46:12 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][260/312]	eta 0:00:31 lr 0.000062	time 0.5698 (0.6151)	model_time 0.5697 (0.6081)	loss 2.7434 (2.6854)	grad_norm 2.8107 (2.9060/1.2354)	mem 24308MB
[2025-01-19 05:46:18 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][270/312]	eta 0:00:25 lr 0.000062	time 0.5929 (0.6146)	model_time 0.5928 (0.6078)	loss 3.0043 (2.6886)	grad_norm 1.8617 (2.8906/1.2265)	mem 24308MB
[2025-01-19 05:46:24 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][280/312]	eta 0:00:19 lr 0.000062	time 0.5743 (0.6139)	model_time 0.5741 (0.6074)	loss 2.7672 (2.6895)	grad_norm 1.4352 (2.8902/1.2294)	mem 24308MB
[2025-01-19 05:46:30 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][290/312]	eta 0:00:13 lr 0.000061	time 0.5794 (0.6134)	model_time 0.5792 (0.6071)	loss 3.1541 (2.6913)	grad_norm 2.4438 (2.8901/1.2148)	mem 24308MB
[2025-01-19 05:46:35 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][300/312]	eta 0:00:07 lr 0.000061	time 0.5702 (0.6127)	model_time 0.5701 (0.6065)	loss 2.2856 (2.6872)	grad_norm 2.0242 (2.8823/1.2234)	mem 24308MB
[2025-01-19 05:46:41 internimage_s_1k_224] (main.py 510): INFO Train: [285/300][310/312]	eta 0:00:01 lr 0.000061	time 0.5704 (0.6120)	model_time 0.5704 (0.6061)	loss 2.6363 (2.6834)	grad_norm 3.4128 (2.8705/1.1973)	mem 24308MB
[2025-01-19 05:46:42 internimage_s_1k_224] (main.py 519): INFO EPOCH 285 training takes 0:03:10
[2025-01-19 05:46:42 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_285.pth saving......
[2025-01-19 05:46:44 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_285.pth saved !!!
[2025-01-19 05:46:52 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.910 (7.910)	Loss 0.6942 (0.6942)	Acc@1 86.206 (86.206)	Acc@5 97.852 (97.852)	Mem 24308MB
[2025-01-19 05:46:55 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.046)	Loss 0.8712 (0.7731)	Acc@1 80.835 (84.248)	Acc@5 96.289 (96.891)	Mem 24308MB
[2025-01-19 05:46:56 internimage_s_1k_224] (main.py 575): INFO [Epoch:285] * Acc@1 84.067 Acc@5 96.883
[2025-01-19 05:46:56 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 05:46:56 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.14%
[2025-01-19 05:47:04 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.882 (8.882)	Loss 0.6897 (0.6897)	Acc@1 85.962 (85.962)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 05:47:09 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.217)	Loss 0.8676 (0.7621)	Acc@1 80.542 (84.200)	Acc@5 96.289 (96.875)	Mem 24308MB
[2025-01-19 05:47:09 internimage_s_1k_224] (main.py 575): INFO [Epoch:285] * Acc@1 84.057 Acc@5 96.877
[2025-01-19 05:47:09 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.1%
[2025-01-19 05:47:09 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:47:12 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:47:12 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 84.06%
[2025-01-19 05:47:14 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][0/312]	eta 0:11:00 lr 0.000061	time 2.1158 (2.1158)	model_time 0.5852 (0.5852)	loss 2.1752 (2.1752)	grad_norm 1.6900 (1.6900/0.0000)	mem 24308MB
[2025-01-19 05:47:20 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][10/312]	eta 0:03:45 lr 0.000061	time 0.5678 (0.7463)	model_time 0.5676 (0.6068)	loss 2.7704 (2.6407)	grad_norm 6.4511 (2.9815/1.2998)	mem 24308MB
[2025-01-19 05:47:26 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][20/312]	eta 0:03:17 lr 0.000061	time 0.6108 (0.6768)	model_time 0.6106 (0.6036)	loss 2.9633 (2.6106)	grad_norm 1.7507 (2.7977/1.1480)	mem 24308MB
[2025-01-19 05:47:32 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][30/312]	eta 0:03:07 lr 0.000061	time 0.5814 (0.6661)	model_time 0.5810 (0.6163)	loss 2.8108 (2.6194)	grad_norm 1.5939 (2.8077/1.0887)	mem 24308MB
[2025-01-19 05:47:39 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][40/312]	eta 0:02:58 lr 0.000061	time 0.5822 (0.6564)	model_time 0.5820 (0.6187)	loss 2.9796 (2.6545)	grad_norm 1.8638 (2.7187/1.0625)	mem 24308MB
[2025-01-19 05:47:45 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][50/312]	eta 0:02:49 lr 0.000061	time 0.6739 (0.6471)	model_time 0.6738 (0.6168)	loss 2.6272 (2.7081)	grad_norm 3.6159 (2.6866/1.0017)	mem 24308MB
[2025-01-19 05:47:51 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][60/312]	eta 0:02:41 lr 0.000061	time 0.6206 (0.6407)	model_time 0.6204 (0.6153)	loss 2.6097 (2.7217)	grad_norm 5.1240 (2.7049/0.9782)	mem 24308MB
[2025-01-19 05:47:57 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][70/312]	eta 0:02:34 lr 0.000061	time 0.5859 (0.6366)	model_time 0.5857 (0.6147)	loss 3.0998 (2.7317)	grad_norm 3.8117 (2.7203/0.9556)	mem 24308MB
[2025-01-19 05:48:03 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][80/312]	eta 0:02:26 lr 0.000060	time 0.6025 (0.6318)	model_time 0.6020 (0.6126)	loss 2.3090 (2.7368)	grad_norm 2.0366 (2.6767/0.9181)	mem 24308MB
[2025-01-19 05:48:09 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][90/312]	eta 0:02:19 lr 0.000060	time 0.5942 (0.6271)	model_time 0.5940 (0.6099)	loss 2.9602 (2.7241)	grad_norm 2.7152 (2.6762/0.9341)	mem 24308MB
[2025-01-19 05:48:15 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][100/312]	eta 0:02:12 lr 0.000060	time 0.5943 (0.6259)	model_time 0.5941 (0.6104)	loss 2.5953 (2.7232)	grad_norm 1.9670 (2.6818/0.9555)	mem 24308MB
[2025-01-19 05:48:21 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][110/312]	eta 0:02:06 lr 0.000060	time 0.7328 (0.6252)	model_time 0.7323 (0.6110)	loss 2.9241 (2.7372)	grad_norm 3.8644 (2.7490/1.0147)	mem 24308MB
[2025-01-19 05:48:27 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][120/312]	eta 0:01:59 lr 0.000060	time 0.5899 (0.6227)	model_time 0.5895 (0.6096)	loss 2.7785 (2.7187)	grad_norm 3.2645 (2.7866/1.0212)	mem 24308MB
[2025-01-19 05:48:33 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][130/312]	eta 0:01:53 lr 0.000060	time 0.5827 (0.6217)	model_time 0.5826 (0.6096)	loss 1.6585 (2.7110)	grad_norm 2.1739 (2.8073/1.0259)	mem 24308MB
[2025-01-19 05:48:39 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][140/312]	eta 0:01:46 lr 0.000060	time 0.5857 (0.6203)	model_time 0.5852 (0.6091)	loss 1.7664 (2.7050)	grad_norm 5.1183 (2.8783/1.1461)	mem 24308MB
[2025-01-19 05:48:45 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][150/312]	eta 0:01:40 lr 0.000060	time 0.5802 (0.6214)	model_time 0.5800 (0.6109)	loss 3.0051 (2.7113)	grad_norm 4.8350 (2.9042/1.1630)	mem 24308MB
[2025-01-19 05:48:52 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][160/312]	eta 0:01:34 lr 0.000060	time 0.5770 (0.6211)	model_time 0.5765 (0.6111)	loss 3.2163 (2.7218)	grad_norm 2.6884 (2.8985/1.1543)	mem 24308MB
[2025-01-19 05:48:58 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][170/312]	eta 0:01:28 lr 0.000060	time 0.5881 (0.6202)	model_time 0.5878 (0.6108)	loss 2.9395 (2.7100)	grad_norm 3.7123 (2.9029/1.1697)	mem 24308MB
[2025-01-19 05:49:04 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][180/312]	eta 0:01:21 lr 0.000060	time 0.6957 (0.6201)	model_time 0.6955 (0.6112)	loss 2.8416 (2.7218)	grad_norm 1.9926 (2.8845/1.1648)	mem 24308MB
[2025-01-19 05:49:10 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][190/312]	eta 0:01:15 lr 0.000059	time 0.5924 (0.6199)	model_time 0.5923 (0.6115)	loss 3.0743 (2.7243)	grad_norm 3.0870 (2.8820/1.1606)	mem 24308MB
[2025-01-19 05:49:16 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][200/312]	eta 0:01:09 lr 0.000059	time 0.5904 (0.6192)	model_time 0.5901 (0.6111)	loss 3.2292 (2.7370)	grad_norm 1.6543 (2.8899/1.1549)	mem 24308MB
[2025-01-19 05:49:22 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][210/312]	eta 0:01:03 lr 0.000059	time 0.5801 (0.6177)	model_time 0.5800 (0.6100)	loss 2.6133 (2.7419)	grad_norm 1.8562 (2.8801/1.1382)	mem 24308MB
[2025-01-19 05:49:28 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][220/312]	eta 0:00:56 lr 0.000059	time 0.5980 (0.6173)	model_time 0.5975 (0.6100)	loss 2.7548 (2.7461)	grad_norm 2.0505 (2.8579/1.1195)	mem 24308MB
[2025-01-19 05:49:34 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][230/312]	eta 0:00:50 lr 0.000059	time 0.5914 (0.6166)	model_time 0.5903 (0.6095)	loss 3.1239 (2.7437)	grad_norm 2.5620 (2.8721/1.1093)	mem 24308MB
[2025-01-19 05:49:40 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][240/312]	eta 0:00:44 lr 0.000059	time 0.5837 (0.6169)	model_time 0.5832 (0.6101)	loss 3.2113 (2.7463)	grad_norm 3.1155 (2.8831/1.1006)	mem 24308MB
[2025-01-19 05:49:47 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][250/312]	eta 0:00:38 lr 0.000059	time 0.8058 (0.6171)	model_time 0.8056 (0.6106)	loss 2.9645 (2.7436)	grad_norm 4.2841 (2.9105/1.1409)	mem 24308MB
[2025-01-19 05:49:52 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][260/312]	eta 0:00:32 lr 0.000059	time 0.5915 (0.6162)	model_time 0.5911 (0.6098)	loss 2.6664 (2.7453)	grad_norm 5.3050 (2.9281/1.1605)	mem 24308MB
[2025-01-19 05:49:59 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][270/312]	eta 0:00:25 lr 0.000059	time 0.6097 (0.6162)	model_time 0.6095 (0.6101)	loss 2.8479 (2.7462)	grad_norm 2.3894 (2.9279/1.1529)	mem 24308MB
[2025-01-19 05:50:05 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][280/312]	eta 0:00:19 lr 0.000059	time 0.6139 (0.6173)	model_time 0.6137 (0.6115)	loss 2.9812 (2.7523)	grad_norm 1.2007 (2.9194/1.1501)	mem 24308MB
[2025-01-19 05:50:11 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][290/312]	eta 0:00:13 lr 0.000059	time 0.5963 (0.6171)	model_time 0.5958 (0.6114)	loss 2.3229 (2.7481)	grad_norm 3.0321 (2.9110/1.1430)	mem 24308MB
[2025-01-19 05:50:17 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][300/312]	eta 0:00:07 lr 0.000058	time 0.6505 (0.6164)	model_time 0.6504 (0.6108)	loss 1.7648 (2.7420)	grad_norm 2.9470 (2.9165/1.1339)	mem 24308MB
[2025-01-19 05:50:23 internimage_s_1k_224] (main.py 510): INFO Train: [286/300][310/312]	eta 0:00:01 lr 0.000058	time 0.5672 (0.6164)	model_time 0.5671 (0.6111)	loss 2.7380 (2.7440)	grad_norm 2.2587 (2.9112/1.1246)	mem 24308MB
[2025-01-19 05:50:24 internimage_s_1k_224] (main.py 519): INFO EPOCH 286 training takes 0:03:12
[2025-01-19 05:50:24 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_286.pth saving......
[2025-01-19 05:50:26 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_286.pth saved !!!
[2025-01-19 05:50:35 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.713 (8.713)	Loss 0.6968 (0.6968)	Acc@1 86.157 (86.157)	Acc@5 97.949 (97.949)	Mem 24308MB
[2025-01-19 05:50:39 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.171)	Loss 0.8773 (0.7750)	Acc@1 80.615 (84.204)	Acc@5 96.167 (96.904)	Mem 24308MB
[2025-01-19 05:50:39 internimage_s_1k_224] (main.py 575): INFO [Epoch:286] * Acc@1 84.019 Acc@5 96.913
[2025-01-19 05:50:39 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.0%
[2025-01-19 05:50:39 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.14%
[2025-01-19 05:50:49 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 10.518 (10.518)	Loss 0.6895 (0.6895)	Acc@1 85.938 (85.938)	Acc@5 97.900 (97.900)	Mem 24308MB
[2025-01-19 05:50:54 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.383)	Loss 0.8672 (0.7619)	Acc@1 80.542 (84.211)	Acc@5 96.289 (96.897)	Mem 24308MB
[2025-01-19 05:50:54 internimage_s_1k_224] (main.py 575): INFO [Epoch:286] * Acc@1 84.065 Acc@5 96.897
[2025-01-19 05:50:54 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.1%
[2025-01-19 05:50:54 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:50:57 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:50:57 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 84.07%
[2025-01-19 05:50:59 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][0/312]	eta 0:10:20 lr 0.000058	time 1.9876 (1.9876)	model_time 0.6030 (0.6030)	loss 2.6326 (2.6326)	grad_norm 4.1954 (4.1954/0.0000)	mem 24308MB
[2025-01-19 05:51:05 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][10/312]	eta 0:03:41 lr 0.000058	time 0.5852 (0.7326)	model_time 0.5851 (0.6064)	loss 2.9419 (2.8171)	grad_norm 2.3718 (3.1032/1.2268)	mem 24308MB
[2025-01-19 05:51:11 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][20/312]	eta 0:03:15 lr 0.000058	time 0.6755 (0.6710)	model_time 0.6753 (0.6047)	loss 2.8542 (2.7842)	grad_norm 3.0992 (3.0911/1.2529)	mem 24308MB
[2025-01-19 05:51:17 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][30/312]	eta 0:03:02 lr 0.000058	time 0.5903 (0.6479)	model_time 0.5901 (0.6029)	loss 2.7995 (2.7187)	grad_norm 2.3477 (2.8585/1.1717)	mem 24308MB
[2025-01-19 05:51:23 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][40/312]	eta 0:02:52 lr 0.000058	time 0.5889 (0.6346)	model_time 0.5887 (0.6005)	loss 2.9277 (2.7310)	grad_norm 1.8931 (2.7560/1.0749)	mem 24308MB
[2025-01-19 05:51:29 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][50/312]	eta 0:02:44 lr 0.000058	time 0.5754 (0.6295)	model_time 0.5753 (0.6020)	loss 3.2340 (2.7777)	grad_norm 2.6586 (2.7461/1.0314)	mem 24308MB
[2025-01-19 05:51:35 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][60/312]	eta 0:02:37 lr 0.000058	time 0.6877 (0.6261)	model_time 0.6876 (0.6030)	loss 2.8685 (2.7826)	grad_norm 2.1750 (2.7247/1.0684)	mem 24308MB
[2025-01-19 05:51:41 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][70/312]	eta 0:02:30 lr 0.000058	time 0.6047 (0.6223)	model_time 0.6046 (0.6024)	loss 2.7753 (2.7904)	grad_norm 2.9757 (2.7118/1.0320)	mem 24308MB
[2025-01-19 05:51:47 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][80/312]	eta 0:02:24 lr 0.000058	time 0.6949 (0.6228)	model_time 0.6947 (0.6053)	loss 1.7803 (2.7990)	grad_norm 1.4473 (2.7694/1.0885)	mem 24308MB
[2025-01-19 05:51:54 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][90/312]	eta 0:02:18 lr 0.000058	time 0.6701 (0.6223)	model_time 0.6700 (0.6067)	loss 2.3259 (2.7554)	grad_norm 2.2801 (2.8184/1.1296)	mem 24308MB
[2025-01-19 05:52:00 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][100/312]	eta 0:02:11 lr 0.000057	time 0.5966 (0.6212)	model_time 0.5964 (0.6071)	loss 3.0590 (2.7684)	grad_norm 5.0549 (2.8259/1.1614)	mem 24308MB
[2025-01-19 05:52:06 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][110/312]	eta 0:02:05 lr 0.000057	time 0.5782 (0.6206)	model_time 0.5777 (0.6077)	loss 2.2102 (2.7823)	grad_norm 4.7337 (2.9379/1.2312)	mem 24308MB
[2025-01-19 05:52:12 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][120/312]	eta 0:01:59 lr 0.000057	time 0.6563 (0.6200)	model_time 0.6558 (0.6082)	loss 3.0575 (2.7809)	grad_norm 2.2357 (2.9163/1.2305)	mem 24308MB
[2025-01-19 05:52:18 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][130/312]	eta 0:01:52 lr 0.000057	time 0.5784 (0.6192)	model_time 0.5783 (0.6082)	loss 3.4616 (2.7833)	grad_norm 1.3427 (2.9590/1.2837)	mem 24308MB
[2025-01-19 05:52:24 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][140/312]	eta 0:01:46 lr 0.000057	time 0.6577 (0.6177)	model_time 0.6573 (0.6075)	loss 3.4595 (2.7754)	grad_norm 3.6257 (2.9496/1.2676)	mem 24308MB
[2025-01-19 05:52:30 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][150/312]	eta 0:01:39 lr 0.000057	time 0.5927 (0.6166)	model_time 0.5925 (0.6070)	loss 2.7594 (2.7635)	grad_norm 3.6303 (2.9770/1.2516)	mem 24308MB
[2025-01-19 05:52:36 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][160/312]	eta 0:01:33 lr 0.000057	time 0.5822 (0.6153)	model_time 0.5820 (0.6063)	loss 2.9789 (2.7688)	grad_norm 2.0762 (3.0076/1.2811)	mem 24308MB
[2025-01-19 05:52:42 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][170/312]	eta 0:01:27 lr 0.000057	time 0.5661 (0.6149)	model_time 0.5659 (0.6064)	loss 2.7777 (2.7516)	grad_norm 1.9050 (2.9588/1.2625)	mem 24308MB
[2025-01-19 05:52:48 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][180/312]	eta 0:01:21 lr 0.000057	time 0.6843 (0.6143)	model_time 0.6838 (0.6062)	loss 3.0312 (2.7618)	grad_norm 3.1729 (2.9515/1.2441)	mem 24308MB
[2025-01-19 05:52:54 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][190/312]	eta 0:01:14 lr 0.000057	time 0.6942 (0.6140)	model_time 0.6940 (0.6063)	loss 2.0840 (2.7425)	grad_norm 2.1097 (2.9762/1.2547)	mem 24308MB
[2025-01-19 05:53:01 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][200/312]	eta 0:01:08 lr 0.000057	time 0.6889 (0.6154)	model_time 0.6887 (0.6082)	loss 2.8118 (2.7513)	grad_norm 1.9409 (2.9573/1.2456)	mem 24308MB
[2025-01-19 05:53:07 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][210/312]	eta 0:01:02 lr 0.000056	time 0.5870 (0.6148)	model_time 0.5868 (0.6079)	loss 2.5461 (2.7454)	grad_norm 4.7208 (2.9736/1.2595)	mem 24308MB
[2025-01-19 05:53:13 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][220/312]	eta 0:00:56 lr 0.000056	time 0.5746 (0.6153)	model_time 0.5742 (0.6086)	loss 2.9539 (2.7509)	grad_norm 2.5341 (2.9610/1.2718)	mem 24308MB
[2025-01-19 05:53:19 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][230/312]	eta 0:00:50 lr 0.000056	time 0.5701 (0.6150)	model_time 0.5699 (0.6086)	loss 1.7148 (2.7497)	grad_norm 1.5332 (2.9485/1.2622)	mem 24308MB
[2025-01-19 05:53:25 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][240/312]	eta 0:00:44 lr 0.000056	time 0.6667 (0.6154)	model_time 0.6665 (0.6092)	loss 2.7654 (2.7540)	grad_norm 2.5671 (2.9248/1.2483)	mem 24308MB
[2025-01-19 05:53:31 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][250/312]	eta 0:00:38 lr 0.000056	time 0.6641 (0.6152)	model_time 0.6638 (0.6092)	loss 3.2483 (2.7519)	grad_norm 1.8683 (2.8862/1.2401)	mem 24308MB
[2025-01-19 05:53:37 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][260/312]	eta 0:00:31 lr 0.000056	time 0.5949 (0.6145)	model_time 0.5947 (0.6088)	loss 3.1141 (2.7530)	grad_norm 3.6010 (2.8535/1.2326)	mem 24308MB
[2025-01-19 05:53:43 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][270/312]	eta 0:00:25 lr 0.000056	time 0.5849 (0.6145)	model_time 0.5847 (0.6090)	loss 2.9335 (2.7615)	grad_norm 1.6426 (2.8547/1.2167)	mem 24308MB
[2025-01-19 05:53:49 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][280/312]	eta 0:00:19 lr 0.000056	time 0.7043 (0.6141)	model_time 0.7041 (0.6087)	loss 2.8031 (2.7606)	grad_norm 4.2040 (2.8809/1.2461)	mem 24308MB
[2025-01-19 05:53:55 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][290/312]	eta 0:00:13 lr 0.000056	time 0.6026 (0.6135)	model_time 0.6021 (0.6083)	loss 2.2682 (2.7602)	grad_norm 3.9364 (2.8695/1.2385)	mem 24308MB
[2025-01-19 05:54:01 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][300/312]	eta 0:00:07 lr 0.000056	time 0.5698 (0.6125)	model_time 0.5697 (0.6075)	loss 3.0989 (2.7609)	grad_norm 2.9211 (2.8635/1.2233)	mem 24308MB
[2025-01-19 05:54:07 internimage_s_1k_224] (main.py 510): INFO Train: [287/300][310/312]	eta 0:00:01 lr 0.000056	time 0.5690 (0.6119)	model_time 0.5689 (0.6070)	loss 2.8553 (2.7560)	grad_norm 1.8637 (2.8470/1.2202)	mem 24308MB
[2025-01-19 05:54:08 internimage_s_1k_224] (main.py 519): INFO EPOCH 287 training takes 0:03:10
[2025-01-19 05:54:08 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_287.pth saving......
[2025-01-19 05:54:10 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_287.pth saved !!!
[2025-01-19 05:54:18 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.083 (8.083)	Loss 0.7006 (0.7006)	Acc@1 86.011 (86.011)	Acc@5 97.852 (97.852)	Mem 24308MB
[2025-01-19 05:54:22 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.065)	Loss 0.8779 (0.7761)	Acc@1 80.884 (84.237)	Acc@5 96.094 (96.904)	Mem 24308MB
[2025-01-19 05:54:22 internimage_s_1k_224] (main.py 575): INFO [Epoch:287] * Acc@1 84.089 Acc@5 96.911
[2025-01-19 05:54:22 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 05:54:22 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.14%
[2025-01-19 05:54:31 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.895 (8.895)	Loss 0.6893 (0.6893)	Acc@1 86.011 (86.011)	Acc@5 97.900 (97.900)	Mem 24308MB
[2025-01-19 05:54:35 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.205)	Loss 0.8667 (0.7617)	Acc@1 80.542 (84.222)	Acc@5 96.313 (96.902)	Mem 24308MB
[2025-01-19 05:54:35 internimage_s_1k_224] (main.py 575): INFO [Epoch:287] * Acc@1 84.079 Acc@5 96.901
[2025-01-19 05:54:35 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.1%
[2025-01-19 05:54:35 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:54:38 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:54:38 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 84.08%
[2025-01-19 05:54:40 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][0/312]	eta 0:11:41 lr 0.000056	time 2.2494 (2.2494)	model_time 0.5922 (0.5922)	loss 1.6311 (1.6311)	grad_norm 2.2048 (2.2048/0.0000)	mem 24308MB
[2025-01-19 05:54:46 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][10/312]	eta 0:03:55 lr 0.000056	time 0.6673 (0.7805)	model_time 0.6670 (0.6295)	loss 2.6415 (2.4966)	grad_norm 1.7772 (2.0879/0.4417)	mem 24308MB
[2025-01-19 05:54:52 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][20/312]	eta 0:03:25 lr 0.000055	time 0.5829 (0.7021)	model_time 0.5827 (0.6229)	loss 2.7642 (2.5913)	grad_norm 1.5102 (2.3849/0.9408)	mem 24308MB
[2025-01-19 05:54:58 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][30/312]	eta 0:03:09 lr 0.000055	time 0.5903 (0.6733)	model_time 0.5901 (0.6195)	loss 2.4758 (2.6078)	grad_norm 5.0859 (2.5360/1.0360)	mem 24308MB
[2025-01-19 05:55:05 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][40/312]	eta 0:02:59 lr 0.000055	time 0.6814 (0.6596)	model_time 0.6812 (0.6188)	loss 3.4843 (2.6637)	grad_norm 1.9092 (2.8401/1.3088)	mem 24308MB
[2025-01-19 05:55:11 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][50/312]	eta 0:02:51 lr 0.000055	time 0.6695 (0.6534)	model_time 0.6693 (0.6203)	loss 3.1535 (2.6709)	grad_norm 5.4984 (2.8956/1.2696)	mem 24308MB
[2025-01-19 05:55:17 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][60/312]	eta 0:02:42 lr 0.000055	time 0.6579 (0.6457)	model_time 0.6577 (0.6177)	loss 2.8543 (2.6963)	grad_norm 2.1365 (2.8142/1.2193)	mem 24308MB
[2025-01-19 05:55:23 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][70/312]	eta 0:02:34 lr 0.000055	time 0.6761 (0.6385)	model_time 0.6757 (0.6144)	loss 2.6610 (2.6950)	grad_norm 1.7731 (2.7472/1.1715)	mem 24308MB
[2025-01-19 05:55:29 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][80/312]	eta 0:02:27 lr 0.000055	time 0.5954 (0.6360)	model_time 0.5952 (0.6149)	loss 3.0437 (2.6619)	grad_norm 4.0592 (2.7947/1.2010)	mem 24308MB
[2025-01-19 05:55:35 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][90/312]	eta 0:02:20 lr 0.000055	time 0.5840 (0.6321)	model_time 0.5838 (0.6132)	loss 3.0991 (2.6889)	grad_norm 4.5064 (2.9732/1.3590)	mem 24308MB
[2025-01-19 05:55:41 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][100/312]	eta 0:02:13 lr 0.000055	time 0.6831 (0.6289)	model_time 0.6829 (0.6119)	loss 2.5723 (2.6906)	grad_norm 2.9757 (3.0392/1.3624)	mem 24308MB
[2025-01-19 05:55:47 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][110/312]	eta 0:02:06 lr 0.000055	time 0.6026 (0.6253)	model_time 0.6021 (0.6098)	loss 3.0288 (2.7126)	grad_norm 1.9747 (2.9420/1.3505)	mem 24308MB
[2025-01-19 05:55:53 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][120/312]	eta 0:02:00 lr 0.000055	time 0.7784 (0.6255)	model_time 0.7782 (0.6112)	loss 2.8066 (2.7278)	grad_norm 4.8945 (2.9735/1.3296)	mem 24308MB
[2025-01-19 05:55:59 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][130/312]	eta 0:01:53 lr 0.000055	time 0.5849 (0.6242)	model_time 0.5844 (0.6110)	loss 2.4987 (2.7071)	grad_norm 4.0020 (2.9779/1.3052)	mem 24308MB
[2025-01-19 05:56:06 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][140/312]	eta 0:01:47 lr 0.000054	time 0.5934 (0.6236)	model_time 0.5930 (0.6113)	loss 2.3283 (2.6958)	grad_norm 1.9682 (2.9926/1.2952)	mem 24308MB
[2025-01-19 05:56:12 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][150/312]	eta 0:01:40 lr 0.000054	time 0.5724 (0.6228)	model_time 0.5723 (0.6113)	loss 2.9640 (2.6891)	grad_norm 2.6162 (3.0176/1.2833)	mem 24308MB
[2025-01-19 05:56:18 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][160/312]	eta 0:01:34 lr 0.000054	time 0.6944 (0.6219)	model_time 0.6942 (0.6111)	loss 2.9539 (2.6708)	grad_norm 6.6600 (3.0309/1.2907)	mem 24308MB
[2025-01-19 05:56:24 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][170/312]	eta 0:01:28 lr 0.000054	time 0.6875 (0.6216)	model_time 0.6872 (0.6114)	loss 3.2123 (2.6720)	grad_norm 3.0911 (3.0936/1.3156)	mem 24308MB
[2025-01-19 05:56:30 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][180/312]	eta 0:01:21 lr 0.000054	time 0.6591 (0.6209)	model_time 0.6589 (0.6112)	loss 2.6639 (2.6694)	grad_norm 3.1703 (3.1365/1.3279)	mem 24308MB
[2025-01-19 05:56:36 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][190/312]	eta 0:01:15 lr 0.000054	time 0.6666 (0.6200)	model_time 0.6664 (0.6108)	loss 2.8830 (2.6675)	grad_norm 6.3534 (3.1515/1.3307)	mem 24308MB
[2025-01-19 05:56:42 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][200/312]	eta 0:01:09 lr 0.000054	time 0.6054 (0.6198)	model_time 0.6052 (0.6110)	loss 2.8510 (2.6668)	grad_norm 2.4502 (3.1630/1.3252)	mem 24308MB
[2025-01-19 05:56:48 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][210/312]	eta 0:01:03 lr 0.000054	time 0.5812 (0.6189)	model_time 0.5810 (0.6105)	loss 3.0301 (2.6712)	grad_norm 5.2100 (3.1709/1.3283)	mem 24308MB
[2025-01-19 05:56:54 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][220/312]	eta 0:00:56 lr 0.000054	time 0.5879 (0.6179)	model_time 0.5877 (0.6099)	loss 2.9933 (2.6724)	grad_norm 4.5293 (3.1749/1.3417)	mem 24308MB
[2025-01-19 05:57:00 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][230/312]	eta 0:00:50 lr 0.000054	time 0.5897 (0.6168)	model_time 0.5895 (0.6092)	loss 3.0550 (2.6797)	grad_norm 3.6999 (3.1678/1.3405)	mem 24308MB
[2025-01-19 05:57:06 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][240/312]	eta 0:00:44 lr 0.000054	time 0.5841 (0.6163)	model_time 0.5839 (0.6090)	loss 2.5411 (2.6745)	grad_norm 3.8499 (3.1470/1.3292)	mem 24308MB
[2025-01-19 05:57:12 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][250/312]	eta 0:00:38 lr 0.000054	time 0.5690 (0.6165)	model_time 0.5688 (0.6094)	loss 2.9196 (2.6860)	grad_norm 2.1689 (3.1340/1.3217)	mem 24308MB
[2025-01-19 05:57:18 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][260/312]	eta 0:00:32 lr 0.000054	time 0.5842 (0.6164)	model_time 0.5840 (0.6096)	loss 3.3507 (2.6895)	grad_norm 4.5232 (3.1771/1.3421)	mem 24308MB
[2025-01-19 05:57:25 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][270/312]	eta 0:00:25 lr 0.000053	time 0.5850 (0.6163)	model_time 0.5848 (0.6097)	loss 1.8747 (2.6941)	grad_norm 4.3411 (3.2015/1.3425)	mem 24308MB
[2025-01-19 05:57:31 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][280/312]	eta 0:00:19 lr 0.000053	time 0.5878 (0.6157)	model_time 0.5877 (0.6093)	loss 2.7404 (2.6983)	grad_norm 1.6703 (3.2289/1.3620)	mem 24308MB
[2025-01-19 05:57:37 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][290/312]	eta 0:00:13 lr 0.000053	time 0.8349 (0.6163)	model_time 0.8347 (0.6101)	loss 1.7429 (2.6933)	grad_norm 2.9704 (3.2215/1.3519)	mem 24308MB
[2025-01-19 05:57:43 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][300/312]	eta 0:00:07 lr 0.000053	time 0.6641 (0.6162)	model_time 0.6640 (0.6102)	loss 2.2239 (2.6884)	grad_norm 1.7016 (3.1969/1.3442)	mem 24308MB
[2025-01-19 05:57:49 internimage_s_1k_224] (main.py 510): INFO Train: [288/300][310/312]	eta 0:00:01 lr 0.000053	time 0.5697 (0.6149)	model_time 0.5696 (0.6091)	loss 3.3874 (2.6831)	grad_norm 1.9462 (3.2085/1.3413)	mem 24308MB
[2025-01-19 05:57:49 internimage_s_1k_224] (main.py 519): INFO EPOCH 288 training takes 0:03:11
[2025-01-19 05:57:50 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_288.pth saving......
[2025-01-19 05:57:51 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_288.pth saved !!!
[2025-01-19 05:58:00 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.477 (8.477)	Loss 0.6882 (0.6882)	Acc@1 86.255 (86.255)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 05:58:04 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.105)	Loss 0.8709 (0.7680)	Acc@1 80.542 (84.291)	Acc@5 96.191 (96.902)	Mem 24308MB
[2025-01-19 05:58:04 internimage_s_1k_224] (main.py 575): INFO [Epoch:288] * Acc@1 84.121 Acc@5 96.905
[2025-01-19 05:58:04 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 05:58:04 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.14%
[2025-01-19 05:58:19 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.388 (15.388)	Loss 0.6892 (0.6892)	Acc@1 86.035 (86.035)	Acc@5 97.900 (97.900)	Mem 24308MB
[2025-01-19 05:58:28 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (2.238)	Loss 0.8664 (0.7615)	Acc@1 80.566 (84.226)	Acc@5 96.313 (96.897)	Mem 24308MB
[2025-01-19 05:58:29 internimage_s_1k_224] (main.py 575): INFO [Epoch:288] * Acc@1 84.085 Acc@5 96.897
[2025-01-19 05:58:29 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.1%
[2025-01-19 05:58:29 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 05:58:31 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 05:58:31 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 84.09%
[2025-01-19 05:58:33 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][0/312]	eta 0:11:48 lr 0.000053	time 2.2695 (2.2695)	model_time 0.6055 (0.6055)	loss 2.7741 (2.7741)	grad_norm 2.1024 (2.1024/0.0000)	mem 24308MB
[2025-01-19 05:58:39 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][10/312]	eta 0:03:47 lr 0.000053	time 0.5695 (0.7537)	model_time 0.5693 (0.6022)	loss 2.8826 (2.8724)	grad_norm 2.0553 (3.0988/1.4105)	mem 24308MB
[2025-01-19 05:58:45 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][20/312]	eta 0:03:18 lr 0.000053	time 0.6070 (0.6814)	model_time 0.5908 (0.6001)	loss 2.3651 (2.7775)	grad_norm 1.5406 (3.3074/1.4978)	mem 24308MB
[2025-01-19 05:58:51 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][30/312]	eta 0:03:05 lr 0.000053	time 0.5948 (0.6570)	model_time 0.5944 (0.6018)	loss 2.1889 (2.7845)	grad_norm 1.5857 (3.3391/1.3615)	mem 24308MB
[2025-01-19 05:58:57 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][40/312]	eta 0:02:54 lr 0.000053	time 0.5754 (0.6420)	model_time 0.5752 (0.6002)	loss 2.6756 (2.7662)	grad_norm 1.5598 (3.1064/1.3042)	mem 24308MB
[2025-01-19 05:59:03 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][50/312]	eta 0:02:46 lr 0.000053	time 0.5786 (0.6365)	model_time 0.5784 (0.6028)	loss 1.9035 (2.7350)	grad_norm 2.3097 (3.0165/1.2339)	mem 24308MB
[2025-01-19 05:59:10 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][60/312]	eta 0:02:39 lr 0.000053	time 0.5872 (0.6332)	model_time 0.5870 (0.6050)	loss 3.0214 (2.7211)	grad_norm 2.2335 (3.0291/1.1952)	mem 24308MB
[2025-01-19 05:59:16 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][70/312]	eta 0:02:33 lr 0.000053	time 0.5904 (0.6325)	model_time 0.5902 (0.6082)	loss 2.7878 (2.7343)	grad_norm 2.1195 (3.1758/1.2621)	mem 24308MB
[2025-01-19 05:59:22 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][80/312]	eta 0:02:25 lr 0.000053	time 0.5912 (0.6292)	model_time 0.5910 (0.6079)	loss 3.1782 (2.7401)	grad_norm 3.0464 (3.1601/1.3052)	mem 24308MB
[2025-01-19 05:59:28 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][90/312]	eta 0:02:18 lr 0.000052	time 0.5851 (0.6253)	model_time 0.5849 (0.6063)	loss 2.9247 (2.7375)	grad_norm 1.9672 (3.1322/1.2885)	mem 24308MB
[2025-01-19 05:59:34 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][100/312]	eta 0:02:12 lr 0.000052	time 0.6083 (0.6251)	model_time 0.6081 (0.6079)	loss 2.9060 (2.7296)	grad_norm 3.7012 (3.0667/1.2615)	mem 24308MB
[2025-01-19 05:59:40 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][110/312]	eta 0:02:06 lr 0.000052	time 0.5831 (0.6247)	model_time 0.5829 (0.6090)	loss 3.0659 (2.7484)	grad_norm 3.7393 (3.0815/1.2519)	mem 24308MB
[2025-01-19 05:59:46 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][120/312]	eta 0:01:59 lr 0.000052	time 0.6045 (0.6224)	model_time 0.6044 (0.6080)	loss 2.3790 (2.7494)	grad_norm 2.4668 (3.1266/1.3379)	mem 24308MB
[2025-01-19 05:59:52 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][130/312]	eta 0:01:53 lr 0.000052	time 0.5871 (0.6217)	model_time 0.5870 (0.6083)	loss 1.8749 (2.7305)	grad_norm 3.3863 (3.0943/1.3225)	mem 24308MB
[2025-01-19 05:59:58 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][140/312]	eta 0:01:46 lr 0.000052	time 0.5800 (0.6196)	model_time 0.5795 (0.6072)	loss 1.7839 (2.7187)	grad_norm 1.5736 (3.1293/1.3298)	mem 24308MB
[2025-01-19 06:00:04 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][150/312]	eta 0:01:40 lr 0.000052	time 0.5746 (0.6188)	model_time 0.5744 (0.6072)	loss 2.8658 (2.7301)	grad_norm 2.9754 (3.0836/1.3135)	mem 24308MB
[2025-01-19 06:00:10 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][160/312]	eta 0:01:33 lr 0.000052	time 0.6153 (0.6176)	model_time 0.6147 (0.6066)	loss 2.0578 (2.7124)	grad_norm 2.9754 (3.0399/1.3014)	mem 24308MB
[2025-01-19 06:00:17 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][170/312]	eta 0:01:27 lr 0.000052	time 0.5872 (0.6169)	model_time 0.5867 (0.6065)	loss 2.3177 (2.6971)	grad_norm 1.5569 (2.9873/1.2863)	mem 24308MB
[2025-01-19 06:00:23 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][180/312]	eta 0:01:21 lr 0.000052	time 0.6758 (0.6165)	model_time 0.6756 (0.6068)	loss 2.9596 (2.7116)	grad_norm 2.8381 (2.9800/1.2637)	mem 24308MB
[2025-01-19 06:00:29 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][190/312]	eta 0:01:15 lr 0.000052	time 0.5819 (0.6171)	model_time 0.5817 (0.6078)	loss 1.7565 (2.7015)	grad_norm 2.5343 (2.9790/1.2758)	mem 24308MB
[2025-01-19 06:00:35 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][200/312]	eta 0:01:09 lr 0.000052	time 0.7153 (0.6167)	model_time 0.7150 (0.6078)	loss 2.8376 (2.7009)	grad_norm 4.0632 (2.9777/1.2671)	mem 24308MB
[2025-01-19 06:00:41 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][210/312]	eta 0:01:02 lr 0.000052	time 0.5765 (0.6155)	model_time 0.5760 (0.6070)	loss 2.4502 (2.7073)	grad_norm 1.9772 (2.9867/1.2660)	mem 24308MB
[2025-01-19 06:00:47 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][220/312]	eta 0:00:56 lr 0.000051	time 0.5882 (0.6161)	model_time 0.5880 (0.6080)	loss 3.0329 (2.7053)	grad_norm 2.7878 (3.0331/1.2825)	mem 24308MB
[2025-01-19 06:00:53 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][230/312]	eta 0:00:50 lr 0.000051	time 0.5936 (0.6161)	model_time 0.5934 (0.6083)	loss 2.8353 (2.6981)	grad_norm 3.8117 (3.0484/1.2933)	mem 24308MB
[2025-01-19 06:00:59 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][240/312]	eta 0:00:44 lr 0.000051	time 0.5947 (0.6149)	model_time 0.5945 (0.6075)	loss 3.0032 (2.7136)	grad_norm 2.1817 (3.0510/1.2884)	mem 24308MB
[2025-01-19 06:01:05 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][250/312]	eta 0:00:38 lr 0.000051	time 0.5773 (0.6149)	model_time 0.5770 (0.6077)	loss 3.0593 (2.7212)	grad_norm 3.7207 (3.0290/1.2768)	mem 24308MB
[2025-01-19 06:01:11 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][260/312]	eta 0:00:31 lr 0.000051	time 0.5796 (0.6142)	model_time 0.5794 (0.6073)	loss 2.5154 (2.7261)	grad_norm 1.6367 (3.0056/1.2644)	mem 24308MB
[2025-01-19 06:01:17 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][270/312]	eta 0:00:25 lr 0.000051	time 0.6108 (0.6137)	model_time 0.6106 (0.6071)	loss 2.2301 (2.7288)	grad_norm 1.8638 (2.9790/1.2541)	mem 24308MB
[2025-01-19 06:01:24 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][280/312]	eta 0:00:19 lr 0.000051	time 0.5900 (0.6139)	model_time 0.5897 (0.6075)	loss 3.1666 (2.7329)	grad_norm 2.0659 (2.9633/1.2475)	mem 24308MB
[2025-01-19 06:01:30 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][290/312]	eta 0:00:13 lr 0.000051	time 0.6462 (0.6136)	model_time 0.6460 (0.6074)	loss 2.4309 (2.7239)	grad_norm 1.4208 (2.9486/1.2422)	mem 24308MB
[2025-01-19 06:01:36 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][300/312]	eta 0:00:07 lr 0.000051	time 0.6789 (0.6135)	model_time 0.6788 (0.6075)	loss 2.9879 (2.7233)	grad_norm 3.5789 (2.9507/1.2530)	mem 24308MB
[2025-01-19 06:01:42 internimage_s_1k_224] (main.py 510): INFO Train: [289/300][310/312]	eta 0:00:01 lr 0.000051	time 0.5668 (0.6132)	model_time 0.5667 (0.6074)	loss 2.7509 (2.7250)	grad_norm 6.7725 (3.0121/1.3067)	mem 24308MB
[2025-01-19 06:01:42 internimage_s_1k_224] (main.py 519): INFO EPOCH 289 training takes 0:03:11
[2025-01-19 06:01:42 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_289.pth saving......
[2025-01-19 06:01:44 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_289.pth saved !!!
[2025-01-19 06:01:53 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.363 (8.363)	Loss 0.7008 (0.7008)	Acc@1 85.913 (85.913)	Acc@5 97.949 (97.949)	Mem 24308MB
[2025-01-19 06:01:56 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.101)	Loss 0.8780 (0.7768)	Acc@1 80.518 (84.146)	Acc@5 96.289 (96.937)	Mem 24308MB
[2025-01-19 06:01:57 internimage_s_1k_224] (main.py 575): INFO [Epoch:289] * Acc@1 83.991 Acc@5 96.939
[2025-01-19 06:01:57 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.0%
[2025-01-19 06:01:57 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.14%
[2025-01-19 06:02:06 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.043 (9.043)	Loss 0.6890 (0.6890)	Acc@1 86.035 (86.035)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 06:02:10 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.229)	Loss 0.8661 (0.7613)	Acc@1 80.591 (84.248)	Acc@5 96.289 (96.893)	Mem 24308MB
[2025-01-19 06:02:10 internimage_s_1k_224] (main.py 575): INFO [Epoch:289] * Acc@1 84.103 Acc@5 96.893
[2025-01-19 06:02:10 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.1%
[2025-01-19 06:02:10 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 06:02:13 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 06:02:13 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 84.10%
[2025-01-19 06:02:15 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][0/312]	eta 0:10:49 lr 0.000051	time 2.0812 (2.0812)	model_time 0.5975 (0.5975)	loss 2.8366 (2.8366)	grad_norm 2.8872 (2.8872/0.0000)	mem 24308MB
[2025-01-19 06:02:21 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][10/312]	eta 0:03:42 lr 0.000051	time 0.5743 (0.7354)	model_time 0.5742 (0.6002)	loss 3.0730 (2.6567)	grad_norm 2.2025 (2.8152/1.0927)	mem 24308MB
[2025-01-19 06:02:27 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][20/312]	eta 0:03:17 lr 0.000051	time 0.6561 (0.6775)	model_time 0.6559 (0.6065)	loss 2.9591 (2.7157)	grad_norm 2.1193 (3.2320/1.5688)	mem 24308MB
[2025-01-19 06:02:33 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][30/312]	eta 0:03:06 lr 0.000051	time 0.5792 (0.6605)	model_time 0.5790 (0.6123)	loss 2.3487 (2.6930)	grad_norm 2.2528 (3.1595/1.4890)	mem 24308MB
[2025-01-19 06:02:39 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][40/312]	eta 0:02:56 lr 0.000051	time 0.6153 (0.6476)	model_time 0.6152 (0.6110)	loss 2.8825 (2.6642)	grad_norm 4.6237 (3.2010/1.4351)	mem 24308MB
[2025-01-19 06:02:45 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][50/312]	eta 0:02:46 lr 0.000051	time 0.6520 (0.6372)	model_time 0.6515 (0.6077)	loss 2.3458 (2.7027)	grad_norm 2.0003 (3.0730/1.3912)	mem 24308MB
[2025-01-19 06:02:51 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][60/312]	eta 0:02:39 lr 0.000050	time 0.6835 (0.6333)	model_time 0.6832 (0.6086)	loss 2.6425 (2.7170)	grad_norm 3.6022 (3.0557/1.3249)	mem 24308MB
[2025-01-19 06:02:57 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][70/312]	eta 0:02:31 lr 0.000050	time 0.5895 (0.6278)	model_time 0.5893 (0.6065)	loss 2.9602 (2.7384)	grad_norm 1.9569 (3.1281/1.3630)	mem 24308MB
[2025-01-19 06:03:03 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][80/312]	eta 0:02:24 lr 0.000050	time 0.5853 (0.6245)	model_time 0.5851 (0.6058)	loss 2.9152 (2.7434)	grad_norm 4.2134 (3.1013/1.3584)	mem 24308MB
[2025-01-19 06:03:09 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][90/312]	eta 0:02:17 lr 0.000050	time 0.5942 (0.6214)	model_time 0.5940 (0.6047)	loss 3.2154 (2.7241)	grad_norm 1.8000 (3.0280/1.3518)	mem 24308MB
[2025-01-19 06:03:15 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][100/312]	eta 0:02:11 lr 0.000050	time 0.5777 (0.6203)	model_time 0.5775 (0.6052)	loss 2.5927 (2.6968)	grad_norm 5.1471 (3.1124/1.3511)	mem 24308MB
[2025-01-19 06:03:21 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][110/312]	eta 0:02:05 lr 0.000050	time 0.5839 (0.6190)	model_time 0.5837 (0.6052)	loss 2.8555 (2.6921)	grad_norm 4.1403 (3.0845/1.3106)	mem 24308MB
[2025-01-19 06:03:28 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][120/312]	eta 0:01:59 lr 0.000050	time 0.6670 (0.6208)	model_time 0.6668 (0.6081)	loss 3.2158 (2.6923)	grad_norm 1.2432 (3.0313/1.2831)	mem 24308MB
[2025-01-19 06:03:34 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][130/312]	eta 0:01:52 lr 0.000050	time 0.5647 (0.6194)	model_time 0.5645 (0.6077)	loss 2.9513 (2.6886)	grad_norm 2.0539 (2.9968/1.2495)	mem 24308MB
[2025-01-19 06:03:40 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][140/312]	eta 0:01:46 lr 0.000050	time 0.6611 (0.6197)	model_time 0.6610 (0.6088)	loss 3.0851 (2.6794)	grad_norm 2.7455 (3.0143/1.2468)	mem 24308MB
[2025-01-19 06:03:46 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][150/312]	eta 0:01:40 lr 0.000050	time 0.5811 (0.6196)	model_time 0.5809 (0.6094)	loss 2.9900 (2.6877)	grad_norm 2.8676 (3.0488/1.2361)	mem 24308MB
[2025-01-19 06:03:53 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][160/312]	eta 0:01:34 lr 0.000050	time 0.6780 (0.6208)	model_time 0.6778 (0.6112)	loss 1.8197 (2.6797)	grad_norm 3.0026 (3.0247/1.2074)	mem 24308MB
[2025-01-19 06:03:59 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][170/312]	eta 0:01:27 lr 0.000050	time 0.6015 (0.6189)	model_time 0.6009 (0.6098)	loss 2.6915 (2.6898)	grad_norm 1.6655 (2.9792/1.2009)	mem 24308MB
[2025-01-19 06:04:05 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][180/312]	eta 0:01:21 lr 0.000050	time 0.6838 (0.6190)	model_time 0.6836 (0.6105)	loss 1.8792 (2.6865)	grad_norm 2.0652 (2.9580/1.2027)	mem 24308MB
[2025-01-19 06:04:11 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][190/312]	eta 0:01:15 lr 0.000050	time 0.5808 (0.6180)	model_time 0.5807 (0.6099)	loss 2.3491 (2.6778)	grad_norm 2.3099 (2.9832/1.2244)	mem 24308MB
[2025-01-19 06:04:17 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][200/312]	eta 0:01:09 lr 0.000050	time 0.5751 (0.6170)	model_time 0.5749 (0.6092)	loss 2.8448 (2.6809)	grad_norm 3.1404 (2.9619/1.2086)	mem 24308MB
[2025-01-19 06:04:23 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][210/312]	eta 0:01:02 lr 0.000049	time 0.5939 (0.6159)	model_time 0.5937 (0.6085)	loss 2.8738 (2.6807)	grad_norm 1.5066 (2.9343/1.2053)	mem 24308MB
[2025-01-19 06:04:29 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][220/312]	eta 0:00:56 lr 0.000049	time 0.5856 (0.6157)	model_time 0.5852 (0.6087)	loss 2.9781 (2.6939)	grad_norm 3.8472 (2.9236/1.2022)	mem 24308MB
[2025-01-19 06:04:35 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][230/312]	eta 0:00:50 lr 0.000049	time 0.5848 (0.6150)	model_time 0.5846 (0.6082)	loss 3.0508 (2.7050)	grad_norm 2.3781 (2.8965/1.1899)	mem 24308MB
[2025-01-19 06:04:41 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][240/312]	eta 0:00:44 lr 0.000049	time 0.6427 (0.6155)	model_time 0.6426 (0.6090)	loss 2.5359 (2.7113)	grad_norm 3.2292 (2.9205/1.2011)	mem 24308MB
[2025-01-19 06:04:47 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][250/312]	eta 0:00:38 lr 0.000049	time 0.5784 (0.6150)	model_time 0.5782 (0.6087)	loss 3.0040 (2.7166)	grad_norm 5.0550 (2.9345/1.2032)	mem 24308MB
[2025-01-19 06:04:53 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][260/312]	eta 0:00:32 lr 0.000049	time 0.6766 (0.6154)	model_time 0.6762 (0.6094)	loss 3.0880 (2.7099)	grad_norm 4.0694 (2.9916/1.2542)	mem 24308MB
[2025-01-19 06:04:59 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][270/312]	eta 0:00:25 lr 0.000049	time 0.5870 (0.6152)	model_time 0.5868 (0.6094)	loss 2.7544 (2.7073)	grad_norm 5.5037 (2.9702/1.2578)	mem 24308MB
[2025-01-19 06:05:06 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][280/312]	eta 0:00:19 lr 0.000049	time 0.6908 (0.6152)	model_time 0.6903 (0.6095)	loss 1.9648 (2.7080)	grad_norm 2.6661 (2.9585/1.2513)	mem 24308MB
[2025-01-19 06:05:11 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][290/312]	eta 0:00:13 lr 0.000049	time 0.6121 (0.6142)	model_time 0.6119 (0.6087)	loss 2.9944 (2.7094)	grad_norm 1.5311 (2.9405/1.2479)	mem 24308MB
[2025-01-19 06:05:17 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][300/312]	eta 0:00:07 lr 0.000049	time 0.5661 (0.6137)	model_time 0.5660 (0.6084)	loss 2.7492 (2.7143)	grad_norm 3.0457 (2.9327/1.2337)	mem 24308MB
[2025-01-19 06:05:23 internimage_s_1k_224] (main.py 510): INFO Train: [290/300][310/312]	eta 0:00:01 lr 0.000049	time 0.6500 (0.6130)	model_time 0.6499 (0.6078)	loss 2.1392 (2.7212)	grad_norm 2.1956 (2.9261/1.2296)	mem 24308MB
[2025-01-19 06:05:24 internimage_s_1k_224] (main.py 519): INFO EPOCH 290 training takes 0:03:11
[2025-01-19 06:05:24 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_290.pth saving......
[2025-01-19 06:05:26 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_290.pth saved !!!
[2025-01-19 06:05:34 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.961 (7.961)	Loss 0.6938 (0.6938)	Acc@1 86.133 (86.133)	Acc@5 97.754 (97.754)	Mem 24308MB
[2025-01-19 06:05:37 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.037)	Loss 0.8703 (0.7721)	Acc@1 80.566 (84.202)	Acc@5 96.313 (96.913)	Mem 24308MB
[2025-01-19 06:05:37 internimage_s_1k_224] (main.py 575): INFO [Epoch:290] * Acc@1 84.041 Acc@5 96.905
[2025-01-19 06:05:37 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.0%
[2025-01-19 06:05:37 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.14%
[2025-01-19 06:05:46 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.797 (8.797)	Loss 0.6889 (0.6889)	Acc@1 86.035 (86.035)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 06:05:50 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.136 (1.187)	Loss 0.8658 (0.7612)	Acc@1 80.615 (84.244)	Acc@5 96.289 (96.895)	Mem 24308MB
[2025-01-19 06:05:51 internimage_s_1k_224] (main.py 575): INFO [Epoch:290] * Acc@1 84.103 Acc@5 96.895
[2025-01-19 06:05:51 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.1%
[2025-01-19 06:05:51 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 84.10%
[2025-01-19 06:05:54 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][0/312]	eta 0:17:52 lr 0.000049	time 3.4368 (3.4368)	model_time 2.0945 (2.0945)	loss 2.5212 (2.5212)	grad_norm 4.8652 (4.8652/0.0000)	mem 24308MB
[2025-01-19 06:06:00 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][10/312]	eta 0:04:18 lr 0.000049	time 0.5758 (0.8576)	model_time 0.5756 (0.7352)	loss 3.0122 (2.6079)	grad_norm 4.9912 (3.7921/1.3979)	mem 24308MB
[2025-01-19 06:06:06 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][20/312]	eta 0:03:35 lr 0.000049	time 0.5978 (0.7373)	model_time 0.5973 (0.6730)	loss 1.7654 (2.6599)	grad_norm 2.4764 (3.4850/1.2016)	mem 24308MB
[2025-01-19 06:06:12 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][30/312]	eta 0:03:16 lr 0.000049	time 0.6628 (0.6954)	model_time 0.6626 (0.6518)	loss 3.0620 (2.6959)	grad_norm 5.7523 (3.6749/1.5915)	mem 24308MB
[2025-01-19 06:06:18 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][40/312]	eta 0:03:02 lr 0.000049	time 0.5859 (0.6717)	model_time 0.5857 (0.6386)	loss 3.2449 (2.7243)	grad_norm 4.9792 (3.6027/1.4850)	mem 24308MB
[2025-01-19 06:06:24 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][50/312]	eta 0:02:53 lr 0.000048	time 0.5865 (0.6612)	model_time 0.5861 (0.6346)	loss 2.1233 (2.7135)	grad_norm 5.1983 (3.5492/1.4621)	mem 24308MB
[2025-01-19 06:06:31 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][60/312]	eta 0:02:45 lr 0.000048	time 0.5775 (0.6562)	model_time 0.5773 (0.6338)	loss 2.1648 (2.7082)	grad_norm 1.8783 (3.3829/1.4108)	mem 24308MB
[2025-01-19 06:06:37 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][70/312]	eta 0:02:37 lr 0.000048	time 0.5818 (0.6490)	model_time 0.5813 (0.6297)	loss 2.8495 (2.7549)	grad_norm 5.2881 (3.4079/1.3822)	mem 24308MB
[2025-01-19 06:06:43 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][80/312]	eta 0:02:30 lr 0.000048	time 0.8154 (0.6475)	model_time 0.8152 (0.6306)	loss 3.1473 (2.7622)	grad_norm 2.1358 (3.3262/1.3990)	mem 24308MB
[2025-01-19 06:06:49 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][90/312]	eta 0:02:22 lr 0.000048	time 0.6952 (0.6423)	model_time 0.6951 (0.6271)	loss 2.9747 (2.7717)	grad_norm 2.3970 (3.2476/1.3828)	mem 24308MB
[2025-01-19 06:06:55 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][100/312]	eta 0:02:15 lr 0.000048	time 0.5791 (0.6378)	model_time 0.5789 (0.6241)	loss 1.8148 (2.7641)	grad_norm 1.8905 (3.2111/1.4166)	mem 24308MB
[2025-01-19 06:07:01 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][110/312]	eta 0:02:08 lr 0.000048	time 0.7077 (0.6358)	model_time 0.7075 (0.6234)	loss 2.8533 (2.7682)	grad_norm 2.3845 (3.1692/1.4022)	mem 24308MB
[2025-01-19 06:07:07 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][120/312]	eta 0:02:01 lr 0.000048	time 0.6373 (0.6335)	model_time 0.6368 (0.6220)	loss 3.2067 (2.7500)	grad_norm 3.7859 (3.1200/1.3804)	mem 24308MB
[2025-01-19 06:07:13 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][130/312]	eta 0:01:54 lr 0.000048	time 0.6645 (0.6303)	model_time 0.6641 (0.6197)	loss 2.0067 (2.7566)	grad_norm 2.6686 (3.0838/1.3605)	mem 24308MB
[2025-01-19 06:07:19 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][140/312]	eta 0:01:48 lr 0.000048	time 0.6908 (0.6286)	model_time 0.6905 (0.6187)	loss 3.1911 (2.7689)	grad_norm 2.2442 (3.0602/1.3569)	mem 24308MB
[2025-01-19 06:07:25 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][150/312]	eta 0:01:41 lr 0.000048	time 0.5986 (0.6269)	model_time 0.5985 (0.6176)	loss 3.0195 (2.7657)	grad_norm 1.7647 (3.0341/1.3463)	mem 24308MB
[2025-01-19 06:07:31 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][160/312]	eta 0:01:35 lr 0.000048	time 0.5899 (0.6257)	model_time 0.5897 (0.6169)	loss 2.6961 (2.7602)	grad_norm 1.0320 (3.0258/1.3361)	mem 24308MB
[2025-01-19 06:07:38 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][170/312]	eta 0:01:28 lr 0.000048	time 0.6990 (0.6266)	model_time 0.6986 (0.6184)	loss 2.6474 (2.7613)	grad_norm 1.9420 (3.0148/1.3426)	mem 24308MB
[2025-01-19 06:07:44 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][180/312]	eta 0:01:22 lr 0.000048	time 0.5740 (0.6254)	model_time 0.5735 (0.6176)	loss 3.1764 (2.7571)	grad_norm 2.0721 (2.9753/1.3300)	mem 24308MB
[2025-01-19 06:07:50 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][190/312]	eta 0:01:16 lr 0.000048	time 0.5837 (0.6246)	model_time 0.5835 (0.6172)	loss 3.0760 (2.7513)	grad_norm 3.3043 (2.9605/1.3086)	mem 24308MB
[2025-01-19 06:07:56 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][200/312]	eta 0:01:09 lr 0.000048	time 0.6984 (0.6247)	model_time 0.6980 (0.6176)	loss 3.1195 (2.7523)	grad_norm 5.2477 (3.0073/1.3563)	mem 24308MB
[2025-01-19 06:08:02 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][210/312]	eta 0:01:03 lr 0.000048	time 0.6654 (0.6236)	model_time 0.6652 (0.6169)	loss 1.9802 (2.7453)	grad_norm 1.5626 (2.9993/1.3434)	mem 24308MB
[2025-01-19 06:08:08 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][220/312]	eta 0:00:57 lr 0.000047	time 0.5854 (0.6225)	model_time 0.5852 (0.6161)	loss 2.5282 (2.7360)	grad_norm 1.9130 (2.9793/1.3382)	mem 24308MB
[2025-01-19 06:08:14 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][230/312]	eta 0:00:50 lr 0.000047	time 0.5773 (0.6218)	model_time 0.5768 (0.6156)	loss 2.4603 (2.7291)	grad_norm 4.3457 (2.9867/1.3355)	mem 24308MB
[2025-01-19 06:08:20 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][240/312]	eta 0:00:44 lr 0.000047	time 0.5921 (0.6213)	model_time 0.5917 (0.6153)	loss 1.6320 (2.7281)	grad_norm 3.7304 (2.9962/1.3612)	mem 24308MB
[2025-01-19 06:08:26 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][250/312]	eta 0:00:38 lr 0.000047	time 0.6661 (0.6208)	model_time 0.6657 (0.6151)	loss 3.3257 (2.7296)	grad_norm 3.2607 (3.0274/1.3751)	mem 24308MB
[2025-01-19 06:08:32 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][260/312]	eta 0:00:32 lr 0.000047	time 0.5811 (0.6199)	model_time 0.5807 (0.6144)	loss 2.7757 (2.7368)	grad_norm 2.9760 (3.0218/1.3570)	mem 24308MB
[2025-01-19 06:08:39 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][270/312]	eta 0:00:26 lr 0.000047	time 0.5806 (0.6198)	model_time 0.5804 (0.6145)	loss 3.0125 (2.7342)	grad_norm 5.0344 (3.0373/1.3861)	mem 24308MB
[2025-01-19 06:08:45 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][280/312]	eta 0:00:19 lr 0.000047	time 0.5804 (0.6191)	model_time 0.5803 (0.6140)	loss 2.6830 (2.7365)	grad_norm 4.1890 (3.0353/1.3693)	mem 24308MB
[2025-01-19 06:08:51 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][290/312]	eta 0:00:13 lr 0.000047	time 0.6674 (0.6188)	model_time 0.6670 (0.6138)	loss 2.9105 (2.7412)	grad_norm 3.8937 (3.0213/1.3562)	mem 24308MB
[2025-01-19 06:08:57 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][300/312]	eta 0:00:07 lr 0.000047	time 0.5607 (0.6184)	model_time 0.5606 (0.6135)	loss 2.8931 (2.7426)	grad_norm 4.3848 (2.9987/1.3456)	mem 24308MB
[2025-01-19 06:09:03 internimage_s_1k_224] (main.py 510): INFO Train: [291/300][310/312]	eta 0:00:01 lr 0.000047	time 0.6472 (0.6182)	model_time 0.6471 (0.6136)	loss 2.4338 (2.7372)	grad_norm 4.9731 (2.9863/1.3333)	mem 24308MB
[2025-01-19 06:09:03 internimage_s_1k_224] (main.py 519): INFO EPOCH 291 training takes 0:03:12
[2025-01-19 06:09:03 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_291.pth saving......
[2025-01-19 06:09:05 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_291.pth saved !!!
[2025-01-19 06:09:13 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.016 (8.016)	Loss 0.6984 (0.6984)	Acc@1 86.328 (86.328)	Acc@5 97.778 (97.778)	Mem 24308MB
[2025-01-19 06:09:17 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.055)	Loss 0.8788 (0.7752)	Acc@1 80.786 (84.291)	Acc@5 96.216 (96.888)	Mem 24308MB
[2025-01-19 06:09:17 internimage_s_1k_224] (main.py 575): INFO [Epoch:291] * Acc@1 84.113 Acc@5 96.901
[2025-01-19 06:09:17 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 06:09:17 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.14%
[2025-01-19 06:09:26 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.304 (9.304)	Loss 0.6888 (0.6888)	Acc@1 86.011 (86.011)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 06:09:31 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.237)	Loss 0.8654 (0.7611)	Acc@1 80.566 (84.246)	Acc@5 96.289 (96.902)	Mem 24308MB
[2025-01-19 06:09:31 internimage_s_1k_224] (main.py 575): INFO [Epoch:291] * Acc@1 84.103 Acc@5 96.903
[2025-01-19 06:09:31 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.1%
[2025-01-19 06:09:31 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 06:09:33 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 06:09:33 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 84.10%
[2025-01-19 06:09:36 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][0/312]	eta 0:12:21 lr 0.000047	time 2.3752 (2.3752)	model_time 0.6260 (0.6260)	loss 3.0430 (3.0430)	grad_norm 4.7760 (4.7760/0.0000)	mem 24308MB
[2025-01-19 06:09:42 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][10/312]	eta 0:03:52 lr 0.000047	time 0.5725 (0.7694)	model_time 0.5723 (0.6100)	loss 2.1036 (2.6808)	grad_norm 1.8208 (2.9246/1.1747)	mem 24308MB
[2025-01-19 06:09:48 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][20/312]	eta 0:03:23 lr 0.000047	time 0.5895 (0.6955)	model_time 0.5891 (0.6118)	loss 2.9692 (2.6480)	grad_norm 5.8071 (3.1530/1.3263)	mem 24308MB
[2025-01-19 06:09:54 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][30/312]	eta 0:03:07 lr 0.000047	time 0.5961 (0.6646)	model_time 0.5956 (0.6078)	loss 2.2574 (2.7114)	grad_norm 3.1717 (2.7759/1.2602)	mem 24308MB
[2025-01-19 06:10:00 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][40/312]	eta 0:02:56 lr 0.000047	time 0.5902 (0.6494)	model_time 0.5898 (0.6063)	loss 2.7549 (2.7817)	grad_norm 2.0944 (2.7163/1.1795)	mem 24308MB
[2025-01-19 06:10:06 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][50/312]	eta 0:02:47 lr 0.000047	time 0.5843 (0.6411)	model_time 0.5841 (0.6065)	loss 2.9328 (2.8078)	grad_norm 2.3621 (2.6378/1.1144)	mem 24308MB
[2025-01-19 06:10:12 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][60/312]	eta 0:02:40 lr 0.000047	time 0.5868 (0.6356)	model_time 0.5863 (0.6065)	loss 1.9791 (2.8015)	grad_norm 3.6922 (2.8638/1.3501)	mem 24308MB
[2025-01-19 06:10:18 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][70/312]	eta 0:02:32 lr 0.000047	time 0.5927 (0.6313)	model_time 0.5925 (0.6062)	loss 2.9222 (2.8207)	grad_norm 2.9004 (2.9015/1.3418)	mem 24308MB
[2025-01-19 06:10:24 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][80/312]	eta 0:02:25 lr 0.000047	time 0.5756 (0.6282)	model_time 0.5751 (0.6062)	loss 1.7590 (2.7772)	grad_norm 3.0372 (2.9279/1.2980)	mem 24308MB
[2025-01-19 06:10:30 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][90/312]	eta 0:02:19 lr 0.000046	time 0.6672 (0.6263)	model_time 0.6671 (0.6067)	loss 2.9195 (2.7472)	grad_norm 2.5725 (2.9609/1.3024)	mem 24308MB
[2025-01-19 06:10:36 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][100/312]	eta 0:02:12 lr 0.000046	time 0.5777 (0.6251)	model_time 0.5772 (0.6074)	loss 2.2540 (2.7542)	grad_norm 3.4362 (2.9876/1.2901)	mem 24308MB
[2025-01-19 06:10:43 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][110/312]	eta 0:02:06 lr 0.000046	time 0.5803 (0.6252)	model_time 0.5799 (0.6090)	loss 3.2885 (2.7458)	grad_norm 2.3771 (3.0157/1.2718)	mem 24308MB
[2025-01-19 06:10:49 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][120/312]	eta 0:01:59 lr 0.000046	time 0.5951 (0.6238)	model_time 0.5947 (0.6089)	loss 2.9087 (2.7265)	grad_norm 1.7535 (3.0290/1.2931)	mem 24308MB
[2025-01-19 06:10:55 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][130/312]	eta 0:01:53 lr 0.000046	time 0.5932 (0.6238)	model_time 0.5931 (0.6101)	loss 2.9228 (2.7284)	grad_norm 3.6462 (3.0432/1.3162)	mem 24308MB
[2025-01-19 06:11:01 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][140/312]	eta 0:01:47 lr 0.000046	time 0.5893 (0.6232)	model_time 0.5891 (0.6105)	loss 3.0045 (2.7239)	grad_norm 2.0460 (3.0278/1.2853)	mem 24308MB
[2025-01-19 06:11:07 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][150/312]	eta 0:01:40 lr 0.000046	time 0.5775 (0.6220)	model_time 0.5770 (0.6100)	loss 2.9237 (2.7279)	grad_norm 1.3264 (2.9904/1.2770)	mem 24308MB
[2025-01-19 06:11:13 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][160/312]	eta 0:01:34 lr 0.000046	time 0.5841 (0.6210)	model_time 0.5839 (0.6097)	loss 3.1149 (2.7339)	grad_norm 1.8420 (2.9404/1.2699)	mem 24308MB
[2025-01-19 06:11:19 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][170/312]	eta 0:01:28 lr 0.000046	time 0.5861 (0.6204)	model_time 0.5859 (0.6098)	loss 3.3870 (2.7434)	grad_norm 1.5413 (2.8964/1.2565)	mem 24308MB
[2025-01-19 06:11:25 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][180/312]	eta 0:01:21 lr 0.000046	time 0.5948 (0.6192)	model_time 0.5944 (0.6092)	loss 3.0285 (2.7380)	grad_norm 1.5063 (2.8632/1.2495)	mem 24308MB
[2025-01-19 06:11:32 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][190/312]	eta 0:01:15 lr 0.000046	time 0.5959 (0.6197)	model_time 0.5954 (0.6102)	loss 2.9564 (2.7335)	grad_norm 1.4774 (2.8355/1.2257)	mem 24308MB
[2025-01-19 06:11:38 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][200/312]	eta 0:01:09 lr 0.000046	time 0.5917 (0.6187)	model_time 0.5915 (0.6096)	loss 3.0384 (2.7454)	grad_norm 3.2610 (2.8315/1.2052)	mem 24308MB
[2025-01-19 06:11:44 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][210/312]	eta 0:01:03 lr 0.000046	time 0.5959 (0.6177)	model_time 0.5954 (0.6090)	loss 2.6521 (2.7439)	grad_norm 1.4421 (2.8261/1.2018)	mem 24308MB
[2025-01-19 06:11:50 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][220/312]	eta 0:00:56 lr 0.000046	time 0.5782 (0.6177)	model_time 0.5778 (0.6094)	loss 3.3019 (2.7476)	grad_norm 1.3377 (2.7923/1.1901)	mem 24308MB
[2025-01-19 06:11:56 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][230/312]	eta 0:00:50 lr 0.000046	time 0.5779 (0.6175)	model_time 0.5777 (0.6096)	loss 2.1128 (2.7301)	grad_norm 1.9351 (2.7732/1.1754)	mem 24308MB
[2025-01-19 06:12:02 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][240/312]	eta 0:00:44 lr 0.000046	time 0.5767 (0.6168)	model_time 0.5762 (0.6092)	loss 2.8325 (2.7309)	grad_norm 2.0333 (2.7940/1.1724)	mem 24308MB
[2025-01-19 06:12:08 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][250/312]	eta 0:00:38 lr 0.000046	time 0.6043 (0.6179)	model_time 0.6041 (0.6105)	loss 2.4943 (2.7155)	grad_norm 3.8485 (2.7923/1.1659)	mem 24308MB
[2025-01-19 06:12:14 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][260/312]	eta 0:00:32 lr 0.000046	time 0.5944 (0.6174)	model_time 0.5939 (0.6103)	loss 2.4505 (2.7099)	grad_norm 1.9634 (2.8453/1.2221)	mem 24308MB
[2025-01-19 06:12:21 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][270/312]	eta 0:00:25 lr 0.000046	time 0.5781 (0.6168)	model_time 0.5780 (0.6100)	loss 3.1388 (2.7137)	grad_norm 4.8066 (2.8930/1.2552)	mem 24308MB
[2025-01-19 06:12:27 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][280/312]	eta 0:00:19 lr 0.000045	time 0.6752 (0.6165)	model_time 0.6750 (0.6099)	loss 2.9608 (2.7102)	grad_norm 2.7939 (2.8879/1.2466)	mem 24308MB
[2025-01-19 06:12:33 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][290/312]	eta 0:00:13 lr 0.000045	time 0.6680 (0.6161)	model_time 0.6678 (0.6098)	loss 2.6581 (2.7066)	grad_norm 2.5241 (2.8774/1.2301)	mem 24308MB
[2025-01-19 06:12:39 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][300/312]	eta 0:00:07 lr 0.000045	time 0.5708 (0.6155)	model_time 0.5707 (0.6093)	loss 2.7717 (2.7118)	grad_norm 1.4082 (2.8653/1.2311)	mem 24308MB
[2025-01-19 06:12:44 internimage_s_1k_224] (main.py 510): INFO Train: [292/300][310/312]	eta 0:00:01 lr 0.000045	time 0.5712 (0.6146)	model_time 0.5711 (0.6086)	loss 2.9879 (2.7101)	grad_norm 3.1088 (2.8756/1.2569)	mem 24308MB
[2025-01-19 06:12:45 internimage_s_1k_224] (main.py 519): INFO EPOCH 292 training takes 0:03:11
[2025-01-19 06:12:45 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_292.pth saving......
[2025-01-19 06:12:47 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_292.pth saved !!!
[2025-01-19 06:12:55 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.974 (7.974)	Loss 0.7061 (0.7061)	Acc@1 86.230 (86.230)	Acc@5 97.852 (97.852)	Mem 24308MB
[2025-01-19 06:12:58 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.038)	Loss 0.8777 (0.7782)	Acc@1 80.811 (84.246)	Acc@5 96.313 (96.911)	Mem 24308MB
[2025-01-19 06:12:59 internimage_s_1k_224] (main.py 575): INFO [Epoch:292] * Acc@1 84.097 Acc@5 96.915
[2025-01-19 06:12:59 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 06:12:59 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.14%
[2025-01-19 06:13:08 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.983 (8.983)	Loss 0.6888 (0.6888)	Acc@1 86.011 (86.011)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 06:13:12 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.214)	Loss 0.8652 (0.7610)	Acc@1 80.591 (84.251)	Acc@5 96.289 (96.906)	Mem 24308MB
[2025-01-19 06:13:12 internimage_s_1k_224] (main.py 575): INFO [Epoch:292] * Acc@1 84.107 Acc@5 96.905
[2025-01-19 06:13:12 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.1%
[2025-01-19 06:13:12 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saving......
[2025-01-19 06:13:14 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_ema_best.pth saved !!!
[2025-01-19 06:13:14 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 84.11%
[2025-01-19 06:13:17 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][0/312]	eta 0:12:20 lr 0.000045	time 2.3720 (2.3720)	model_time 0.5915 (0.5915)	loss 2.3830 (2.3830)	grad_norm 3.6454 (3.6454/0.0000)	mem 24308MB
[2025-01-19 06:13:23 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][10/312]	eta 0:03:53 lr 0.000045	time 0.6601 (0.7732)	model_time 0.6600 (0.6111)	loss 2.9851 (2.5878)	grad_norm 3.4389 (2.4631/0.8810)	mem 24308MB
[2025-01-19 06:13:29 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][20/312]	eta 0:03:21 lr 0.000045	time 0.5844 (0.6896)	model_time 0.5840 (0.6045)	loss 2.6419 (2.6385)	grad_norm 2.9120 (2.5838/0.8133)	mem 24308MB
[2025-01-19 06:13:35 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][30/312]	eta 0:03:08 lr 0.000045	time 0.6671 (0.6668)	model_time 0.6666 (0.6091)	loss 2.5846 (2.6736)	grad_norm 1.6871 (2.5683/0.8956)	mem 24308MB
[2025-01-19 06:13:41 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][40/312]	eta 0:02:57 lr 0.000045	time 0.7220 (0.6530)	model_time 0.7216 (0.6092)	loss 2.8962 (2.7273)	grad_norm 5.0596 (2.6140/0.9699)	mem 24308MB
[2025-01-19 06:13:48 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][50/312]	eta 0:02:49 lr 0.000045	time 0.5986 (0.6473)	model_time 0.5981 (0.6120)	loss 3.4922 (2.7546)	grad_norm 2.1004 (2.5690/1.0100)	mem 24308MB
[2025-01-19 06:13:54 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][60/312]	eta 0:02:41 lr 0.000045	time 0.5870 (0.6423)	model_time 0.5865 (0.6127)	loss 2.1422 (2.7327)	grad_norm 2.3446 (2.6438/1.0568)	mem 24308MB
[2025-01-19 06:14:00 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][70/312]	eta 0:02:34 lr 0.000045	time 0.6712 (0.6387)	model_time 0.6710 (0.6133)	loss 2.5928 (2.7312)	grad_norm 2.6025 (2.7547/1.0849)	mem 24308MB
[2025-01-19 06:14:06 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][80/312]	eta 0:02:27 lr 0.000045	time 0.6815 (0.6353)	model_time 0.6811 (0.6130)	loss 3.2721 (2.7264)	grad_norm 4.8826 (2.8184/1.1280)	mem 24308MB
[2025-01-19 06:14:12 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][90/312]	eta 0:02:20 lr 0.000045	time 0.5737 (0.6312)	model_time 0.5733 (0.6113)	loss 1.9927 (2.7007)	grad_norm 3.6680 (2.8911/1.1330)	mem 24308MB
[2025-01-19 06:14:18 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][100/312]	eta 0:02:13 lr 0.000045	time 0.5780 (0.6311)	model_time 0.5776 (0.6131)	loss 3.4974 (2.6982)	grad_norm 2.1304 (2.8720/1.1204)	mem 24308MB
[2025-01-19 06:14:24 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][110/312]	eta 0:02:06 lr 0.000045	time 0.6146 (0.6282)	model_time 0.6144 (0.6118)	loss 2.9608 (2.7052)	grad_norm 4.6513 (2.8696/1.1111)	mem 24308MB
[2025-01-19 06:14:30 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][120/312]	eta 0:02:00 lr 0.000045	time 0.6903 (0.6267)	model_time 0.6899 (0.6116)	loss 2.9444 (2.7151)	grad_norm 4.1964 (2.9018/1.1556)	mem 24308MB
[2025-01-19 06:14:36 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][130/312]	eta 0:01:53 lr 0.000045	time 0.6417 (0.6249)	model_time 0.6412 (0.6109)	loss 2.4814 (2.7205)	grad_norm 4.0949 (2.9382/1.1584)	mem 24308MB
[2025-01-19 06:14:42 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][140/312]	eta 0:01:47 lr 0.000045	time 0.6019 (0.6227)	model_time 0.6017 (0.6097)	loss 2.9889 (2.7154)	grad_norm 2.9898 (3.0816/1.3518)	mem 24308MB
[2025-01-19 06:14:48 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][150/312]	eta 0:01:40 lr 0.000045	time 0.6342 (0.6221)	model_time 0.6340 (0.6100)	loss 3.3340 (2.7212)	grad_norm 2.8055 (3.1505/1.3693)	mem 24308MB
[2025-01-19 06:14:55 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][160/312]	eta 0:01:34 lr 0.000045	time 0.6763 (0.6217)	model_time 0.6759 (0.6103)	loss 2.9249 (2.7320)	grad_norm 4.5571 (3.1776/1.3773)	mem 24308MB
[2025-01-19 06:15:01 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][170/312]	eta 0:01:28 lr 0.000045	time 0.5871 (0.6200)	model_time 0.5869 (0.6092)	loss 3.0381 (2.7352)	grad_norm 2.0387 (3.1445/1.3605)	mem 24308MB
[2025-01-19 06:15:07 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][180/312]	eta 0:01:21 lr 0.000044	time 0.5770 (0.6199)	model_time 0.5769 (0.6097)	loss 3.1242 (2.7435)	grad_norm 2.4859 (3.1536/1.3464)	mem 24308MB
[2025-01-19 06:15:13 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][190/312]	eta 0:01:15 lr 0.000044	time 0.6586 (0.6196)	model_time 0.6582 (0.6099)	loss 2.7334 (2.7288)	grad_norm 3.0110 (3.1595/1.3439)	mem 24308MB
[2025-01-19 06:15:19 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][200/312]	eta 0:01:09 lr 0.000044	time 0.5867 (0.6187)	model_time 0.5865 (0.6094)	loss 2.9147 (2.7331)	grad_norm 8.1334 (3.2478/1.4351)	mem 24308MB
[2025-01-19 06:15:25 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][210/312]	eta 0:01:03 lr 0.000044	time 0.5850 (0.6178)	model_time 0.5849 (0.6090)	loss 3.4498 (2.7303)	grad_norm 3.1124 (3.3314/1.5208)	mem 24308MB
[2025-01-19 06:15:31 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][220/312]	eta 0:00:56 lr 0.000044	time 0.5759 (0.6174)	model_time 0.5754 (0.6089)	loss 2.5591 (2.7313)	grad_norm 1.7657 (3.3945/1.5649)	mem 24308MB
[2025-01-19 06:15:37 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][230/312]	eta 0:00:50 lr 0.000044	time 0.5924 (0.6166)	model_time 0.5922 (0.6084)	loss 3.0549 (2.7230)	grad_norm 2.4882 (3.3610/1.5433)	mem 24308MB
[2025-01-19 06:15:43 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][240/312]	eta 0:00:44 lr 0.000044	time 0.5830 (0.6159)	model_time 0.5829 (0.6081)	loss 2.1504 (2.7266)	grad_norm 2.9782 (3.3547/1.5335)	mem 24308MB
[2025-01-19 06:15:49 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][250/312]	eta 0:00:38 lr 0.000044	time 0.5812 (0.6156)	model_time 0.5810 (0.6081)	loss 1.8223 (2.7277)	grad_norm 1.9849 (3.3392/1.5225)	mem 24308MB
[2025-01-19 06:15:55 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][260/312]	eta 0:00:31 lr 0.000044	time 0.6010 (0.6151)	model_time 0.6005 (0.6078)	loss 2.7465 (2.7244)	grad_norm 2.7711 (3.3257/1.5057)	mem 24308MB
[2025-01-19 06:16:01 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][270/312]	eta 0:00:25 lr 0.000044	time 0.5938 (0.6151)	model_time 0.5936 (0.6081)	loss 2.7987 (2.7254)	grad_norm 3.5637 (3.2890/1.4953)	mem 24308MB
[2025-01-19 06:16:07 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][280/312]	eta 0:00:19 lr 0.000044	time 0.6660 (0.6155)	model_time 0.6656 (0.6087)	loss 2.7554 (2.7209)	grad_norm 2.0668 (3.2643/1.4793)	mem 24308MB
[2025-01-19 06:16:13 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][290/312]	eta 0:00:13 lr 0.000044	time 0.5901 (0.6149)	model_time 0.5900 (0.6084)	loss 2.6159 (2.7240)	grad_norm 1.8752 (3.2259/1.4726)	mem 24308MB
[2025-01-19 06:16:20 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][300/312]	eta 0:00:07 lr 0.000044	time 0.5762 (0.6149)	model_time 0.5761 (0.6086)	loss 2.2166 (2.7278)	grad_norm 3.0426 (3.2061/1.4559)	mem 24308MB
[2025-01-19 06:16:26 internimage_s_1k_224] (main.py 510): INFO Train: [293/300][310/312]	eta 0:00:01 lr 0.000044	time 0.6306 (0.6146)	model_time 0.6305 (0.6084)	loss 2.8264 (2.7208)	grad_norm 1.1170 (3.2193/1.4514)	mem 24308MB
[2025-01-19 06:16:26 internimage_s_1k_224] (main.py 519): INFO EPOCH 293 training takes 0:03:11
[2025-01-19 06:16:26 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_293.pth saving......
[2025-01-19 06:16:28 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_293.pth saved !!!
[2025-01-19 06:16:36 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.621 (7.621)	Loss 0.6962 (0.6962)	Acc@1 86.255 (86.255)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 06:16:40 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.048)	Loss 0.8739 (0.7715)	Acc@1 80.566 (84.280)	Acc@5 96.167 (96.893)	Mem 24308MB
[2025-01-19 06:16:40 internimage_s_1k_224] (main.py 575): INFO [Epoch:293] * Acc@1 84.143 Acc@5 96.895
[2025-01-19 06:16:40 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 06:16:40 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 06:16:42 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 06:16:42 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.14%
[2025-01-19 06:16:49 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.905 (7.905)	Loss 0.6887 (0.6887)	Acc@1 86.011 (86.011)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 06:16:53 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.036)	Loss 0.8649 (0.7609)	Acc@1 80.615 (84.246)	Acc@5 96.289 (96.906)	Mem 24308MB
[2025-01-19 06:16:53 internimage_s_1k_224] (main.py 575): INFO [Epoch:293] * Acc@1 84.099 Acc@5 96.905
[2025-01-19 06:16:53 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.1%
[2025-01-19 06:16:53 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 84.11%
[2025-01-19 06:16:56 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][0/312]	eta 0:16:07 lr 0.000044	time 3.1008 (3.1008)	model_time 1.2555 (1.2555)	loss 2.9524 (2.9524)	grad_norm 2.2903 (2.2903/0.0000)	mem 24308MB
[2025-01-19 06:17:02 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][10/312]	eta 0:04:15 lr 0.000044	time 0.5751 (0.8452)	model_time 0.5749 (0.6771)	loss 2.4981 (2.7887)	grad_norm 1.5351 (2.4354/0.9207)	mem 24308MB
[2025-01-19 06:17:08 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][20/312]	eta 0:03:33 lr 0.000044	time 0.5762 (0.7300)	model_time 0.5757 (0.6409)	loss 2.9121 (2.6532)	grad_norm 3.3374 (2.5963/0.9945)	mem 24308MB
[2025-01-19 06:17:15 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][30/312]	eta 0:03:16 lr 0.000044	time 0.5892 (0.6959)	model_time 0.5890 (0.6354)	loss 3.1147 (2.6988)	grad_norm 1.7967 (2.4726/0.9433)	mem 24308MB
[2025-01-19 06:17:21 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][40/312]	eta 0:03:03 lr 0.000044	time 0.5773 (0.6755)	model_time 0.5769 (0.6296)	loss 2.2637 (2.6498)	grad_norm 1.8001 (2.4621/0.9249)	mem 24308MB
[2025-01-19 06:17:27 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][50/312]	eta 0:02:52 lr 0.000044	time 0.5888 (0.6593)	model_time 0.5887 (0.6224)	loss 2.6996 (2.6481)	grad_norm 5.3310 (2.5479/1.0370)	mem 24308MB
[2025-01-19 06:17:33 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][60/312]	eta 0:02:43 lr 0.000044	time 0.5889 (0.6502)	model_time 0.5887 (0.6193)	loss 3.0236 (2.6506)	grad_norm 1.4109 (2.5848/1.0293)	mem 24308MB
[2025-01-19 06:17:39 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][70/312]	eta 0:02:36 lr 0.000044	time 0.5948 (0.6446)	model_time 0.5947 (0.6180)	loss 2.0066 (2.6508)	grad_norm 3.0149 (2.6522/1.0866)	mem 24308MB
[2025-01-19 06:17:45 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][80/312]	eta 0:02:28 lr 0.000044	time 0.5860 (0.6422)	model_time 0.5856 (0.6188)	loss 2.9629 (2.6474)	grad_norm 4.1931 (2.7496/1.1251)	mem 24308MB
[2025-01-19 06:17:51 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][90/312]	eta 0:02:21 lr 0.000044	time 0.5889 (0.6387)	model_time 0.5887 (0.6178)	loss 2.2840 (2.6451)	grad_norm 2.2263 (2.8752/1.2188)	mem 24308MB
[2025-01-19 06:17:57 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][100/312]	eta 0:02:14 lr 0.000044	time 0.5855 (0.6341)	model_time 0.5850 (0.6153)	loss 2.7302 (2.6439)	grad_norm 1.8159 (2.8837/1.2279)	mem 24308MB
[2025-01-19 06:18:04 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][110/312]	eta 0:02:08 lr 0.000043	time 0.5825 (0.6344)	model_time 0.5821 (0.6172)	loss 2.6806 (2.6493)	grad_norm 4.7324 (2.9302/1.2398)	mem 24308MB
[2025-01-19 06:18:10 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][120/312]	eta 0:02:01 lr 0.000043	time 0.5860 (0.6319)	model_time 0.5855 (0.6161)	loss 2.3467 (2.6409)	grad_norm 1.4313 (2.8821/1.2282)	mem 24308MB
[2025-01-19 06:18:16 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][130/312]	eta 0:01:54 lr 0.000043	time 0.5799 (0.6304)	model_time 0.5797 (0.6158)	loss 1.7691 (2.6269)	grad_norm 1.4116 (2.8701/1.2336)	mem 24308MB
[2025-01-19 06:18:22 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][140/312]	eta 0:01:48 lr 0.000043	time 0.5909 (0.6284)	model_time 0.5908 (0.6148)	loss 2.5399 (2.6259)	grad_norm 4.5823 (2.8434/1.2195)	mem 24308MB
[2025-01-19 06:18:28 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][150/312]	eta 0:01:41 lr 0.000043	time 0.6702 (0.6287)	model_time 0.6700 (0.6160)	loss 3.1680 (2.6264)	grad_norm 2.3320 (2.8172/1.2111)	mem 24308MB
[2025-01-19 06:18:34 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][160/312]	eta 0:01:35 lr 0.000043	time 0.5992 (0.6265)	model_time 0.5991 (0.6146)	loss 2.7374 (2.6267)	grad_norm 2.0220 (2.8176/1.2378)	mem 24308MB
[2025-01-19 06:18:40 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][170/312]	eta 0:01:28 lr 0.000043	time 0.5764 (0.6252)	model_time 0.5762 (0.6139)	loss 2.8679 (2.6353)	grad_norm 3.8751 (2.8213/1.2106)	mem 24308MB
[2025-01-19 06:18:46 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][180/312]	eta 0:01:22 lr 0.000043	time 0.5888 (0.6238)	model_time 0.5887 (0.6131)	loss 2.1878 (2.6333)	grad_norm 2.2685 (2.8368/1.2028)	mem 24308MB
[2025-01-19 06:18:52 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][190/312]	eta 0:01:16 lr 0.000043	time 0.5927 (0.6230)	model_time 0.5922 (0.6128)	loss 3.2786 (2.6387)	grad_norm 3.2977 (2.8270/1.2009)	mem 24308MB
[2025-01-19 06:18:58 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][200/312]	eta 0:01:09 lr 0.000043	time 0.5923 (0.6233)	model_time 0.5919 (0.6136)	loss 2.2300 (2.6382)	grad_norm 3.3365 (2.8505/1.1877)	mem 24308MB
[2025-01-19 06:19:05 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][210/312]	eta 0:01:03 lr 0.000043	time 0.5855 (0.6233)	model_time 0.5853 (0.6141)	loss 2.3055 (2.6443)	grad_norm 2.1929 (2.8327/1.1734)	mem 24308MB
[2025-01-19 06:19:11 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][220/312]	eta 0:00:57 lr 0.000043	time 0.6001 (0.6221)	model_time 0.5996 (0.6133)	loss 2.6536 (2.6465)	grad_norm 2.5787 (2.8508/1.1880)	mem 24308MB
[2025-01-19 06:19:17 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][230/312]	eta 0:00:51 lr 0.000043	time 0.5815 (0.6224)	model_time 0.5814 (0.6139)	loss 3.4285 (2.6515)	grad_norm 4.2293 (2.8645/1.1701)	mem 24308MB
[2025-01-19 06:19:23 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][240/312]	eta 0:00:44 lr 0.000043	time 0.6831 (0.6219)	model_time 0.6829 (0.6138)	loss 2.5135 (2.6568)	grad_norm 3.2272 (2.8724/1.1715)	mem 24308MB
[2025-01-19 06:19:29 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][250/312]	eta 0:00:38 lr 0.000043	time 0.5784 (0.6215)	model_time 0.5782 (0.6137)	loss 3.2624 (2.6593)	grad_norm 4.4755 (2.8850/1.1919)	mem 24308MB
[2025-01-19 06:19:35 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][260/312]	eta 0:00:32 lr 0.000043	time 0.5775 (0.6209)	model_time 0.5773 (0.6133)	loss 2.4330 (2.6656)	grad_norm 2.4884 (2.8769/1.1870)	mem 24308MB
[2025-01-19 06:19:41 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][270/312]	eta 0:00:26 lr 0.000043	time 0.6846 (0.6206)	model_time 0.6845 (0.6133)	loss 3.0523 (2.6694)	grad_norm 1.5618 (2.8487/1.1814)	mem 24308MB
[2025-01-19 06:19:47 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][280/312]	eta 0:00:19 lr 0.000043	time 0.6020 (0.6196)	model_time 0.6018 (0.6126)	loss 3.2440 (2.6765)	grad_norm 4.4891 (2.8726/1.1920)	mem 24308MB
[2025-01-19 06:19:53 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][290/312]	eta 0:00:13 lr 0.000043	time 0.5925 (0.6188)	model_time 0.5923 (0.6120)	loss 2.6486 (2.6830)	grad_norm 3.4785 (2.8515/1.1853)	mem 24308MB
[2025-01-19 06:19:59 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][300/312]	eta 0:00:07 lr 0.000043	time 0.5739 (0.6181)	model_time 0.5738 (0.6115)	loss 2.1113 (2.6737)	grad_norm 1.7533 (2.8613/1.1872)	mem 24308MB
[2025-01-19 06:20:05 internimage_s_1k_224] (main.py 510): INFO Train: [294/300][310/312]	eta 0:00:01 lr 0.000043	time 0.5715 (0.6169)	model_time 0.5714 (0.6105)	loss 2.8449 (2.6722)	grad_norm 1.9451 (2.8536/1.1855)	mem 24308MB
[2025-01-19 06:20:06 internimage_s_1k_224] (main.py 519): INFO EPOCH 294 training takes 0:03:12
[2025-01-19 06:20:06 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_294.pth saving......
[2025-01-19 06:20:07 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_294.pth saved !!!
[2025-01-19 06:20:15 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.726 (7.726)	Loss 0.6966 (0.6966)	Acc@1 86.206 (86.206)	Acc@5 97.852 (97.852)	Mem 24308MB
[2025-01-19 06:20:19 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.028)	Loss 0.8705 (0.7717)	Acc@1 80.664 (84.297)	Acc@5 96.289 (96.846)	Mem 24308MB
[2025-01-19 06:20:19 internimage_s_1k_224] (main.py 575): INFO [Epoch:294] * Acc@1 84.119 Acc@5 96.853
[2025-01-19 06:20:19 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 06:20:19 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.14%
[2025-01-19 06:20:30 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 11.108 (11.108)	Loss 0.6886 (0.6886)	Acc@1 86.011 (86.011)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 06:20:39 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.814)	Loss 0.8646 (0.7608)	Acc@1 80.615 (84.237)	Acc@5 96.289 (96.902)	Mem 24308MB
[2025-01-19 06:20:39 internimage_s_1k_224] (main.py 575): INFO [Epoch:294] * Acc@1 84.087 Acc@5 96.899
[2025-01-19 06:20:39 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.1%
[2025-01-19 06:20:39 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 84.11%
[2025-01-19 06:20:43 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][0/312]	eta 0:17:58 lr 0.000043	time 3.4560 (3.4560)	model_time 1.7942 (1.7942)	loss 2.9038 (2.9038)	grad_norm 1.6688 (1.6688/0.0000)	mem 24308MB
[2025-01-19 06:20:49 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][10/312]	eta 0:04:27 lr 0.000043	time 0.5810 (0.8852)	model_time 0.5808 (0.7338)	loss 2.0850 (2.6519)	grad_norm 2.5790 (2.8128/1.2708)	mem 24308MB
[2025-01-19 06:20:55 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][20/312]	eta 0:03:40 lr 0.000043	time 0.5792 (0.7538)	model_time 0.5790 (0.6744)	loss 2.7201 (2.6624)	grad_norm 3.0430 (2.9964/1.6314)	mem 24308MB
[2025-01-19 06:21:01 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][30/312]	eta 0:03:18 lr 0.000043	time 0.5797 (0.7049)	model_time 0.5796 (0.6510)	loss 2.9591 (2.6912)	grad_norm 2.1066 (2.9791/1.5783)	mem 24308MB
[2025-01-19 06:21:07 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][40/312]	eta 0:03:06 lr 0.000043	time 0.6742 (0.6853)	model_time 0.6741 (0.6444)	loss 2.1688 (2.6834)	grad_norm 3.9538 (2.9274/1.4537)	mem 24308MB
[2025-01-19 06:21:13 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][50/312]	eta 0:02:54 lr 0.000043	time 0.5775 (0.6666)	model_time 0.5774 (0.6337)	loss 2.3354 (2.7011)	grad_norm 1.7412 (2.9550/1.3733)	mem 24308MB
[2025-01-19 06:21:19 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][60/312]	eta 0:02:45 lr 0.000043	time 0.6690 (0.6583)	model_time 0.6686 (0.6307)	loss 2.8745 (2.6846)	grad_norm 1.3431 (2.8817/1.3310)	mem 24308MB
[2025-01-19 06:21:25 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][70/312]	eta 0:02:37 lr 0.000042	time 0.6463 (0.6503)	model_time 0.6461 (0.6266)	loss 1.9337 (2.6624)	grad_norm 2.0500 (2.7545/1.2839)	mem 24308MB
[2025-01-19 06:21:31 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][80/312]	eta 0:02:29 lr 0.000042	time 0.5856 (0.6424)	model_time 0.5852 (0.6216)	loss 3.0344 (2.6680)	grad_norm 2.2183 (2.7952/1.2416)	mem 24308MB
[2025-01-19 06:21:37 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][90/312]	eta 0:02:22 lr 0.000042	time 0.5772 (0.6399)	model_time 0.5767 (0.6213)	loss 3.0223 (2.6765)	grad_norm 6.4187 (2.8158/1.2455)	mem 24308MB
[2025-01-19 06:21:43 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][100/312]	eta 0:02:14 lr 0.000042	time 0.5864 (0.6355)	model_time 0.5863 (0.6187)	loss 2.5392 (2.6834)	grad_norm 3.4046 (2.7766/1.2291)	mem 24308MB
[2025-01-19 06:21:49 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][110/312]	eta 0:02:07 lr 0.000042	time 0.6020 (0.6333)	model_time 0.6018 (0.6180)	loss 3.2095 (2.6902)	grad_norm 3.2884 (2.7519/1.2143)	mem 24308MB
[2025-01-19 06:21:55 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][120/312]	eta 0:02:01 lr 0.000042	time 0.6713 (0.6305)	model_time 0.6711 (0.6164)	loss 1.7773 (2.6986)	grad_norm 1.6328 (2.7434/1.2289)	mem 24308MB
[2025-01-19 06:22:02 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][130/312]	eta 0:01:54 lr 0.000042	time 0.6665 (0.6297)	model_time 0.6663 (0.6167)	loss 2.3942 (2.7153)	grad_norm 3.5663 (2.7366/1.2221)	mem 24308MB
[2025-01-19 06:22:08 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][140/312]	eta 0:01:47 lr 0.000042	time 0.5770 (0.6275)	model_time 0.5768 (0.6154)	loss 2.4553 (2.7173)	grad_norm 3.0760 (2.7739/1.2371)	mem 24308MB
[2025-01-19 06:22:14 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][150/312]	eta 0:01:41 lr 0.000042	time 0.5787 (0.6258)	model_time 0.5785 (0.6144)	loss 2.6909 (2.7132)	grad_norm 1.8381 (2.7609/1.2275)	mem 24308MB
[2025-01-19 06:22:20 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][160/312]	eta 0:01:35 lr 0.000042	time 0.5814 (0.6251)	model_time 0.5812 (0.6144)	loss 2.7434 (2.7216)	grad_norm 5.2417 (2.7605/1.2138)	mem 24308MB
[2025-01-19 06:22:26 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][170/312]	eta 0:01:28 lr 0.000042	time 0.5761 (0.6239)	model_time 0.5756 (0.6138)	loss 2.7802 (2.7270)	grad_norm 2.6241 (2.7572/1.1985)	mem 24308MB
[2025-01-19 06:22:32 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][180/312]	eta 0:01:22 lr 0.000042	time 0.6654 (0.6231)	model_time 0.6652 (0.6135)	loss 3.0956 (2.7301)	grad_norm 2.2048 (2.7588/1.1953)	mem 24308MB
[2025-01-19 06:22:38 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][190/312]	eta 0:01:15 lr 0.000042	time 0.6691 (0.6223)	model_time 0.6689 (0.6132)	loss 2.1768 (2.7304)	grad_norm 3.3581 (2.7758/1.1803)	mem 24308MB
[2025-01-19 06:22:44 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][200/312]	eta 0:01:09 lr 0.000042	time 0.5738 (0.6207)	model_time 0.5733 (0.6120)	loss 2.2468 (2.7336)	grad_norm 2.1128 (2.7405/1.1665)	mem 24308MB
[2025-01-19 06:22:50 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][210/312]	eta 0:01:03 lr 0.000042	time 0.5754 (0.6203)	model_time 0.5750 (0.6120)	loss 1.6279 (2.7276)	grad_norm 3.6532 (2.7535/1.1744)	mem 24308MB
[2025-01-19 06:22:56 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][220/312]	eta 0:00:56 lr 0.000042	time 0.5861 (0.6193)	model_time 0.5859 (0.6114)	loss 3.1734 (2.7298)	grad_norm 1.6055 (2.7530/1.1740)	mem 24308MB
[2025-01-19 06:23:02 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][230/312]	eta 0:00:50 lr 0.000042	time 0.5782 (0.6190)	model_time 0.5778 (0.6113)	loss 3.2141 (2.7378)	grad_norm 4.5415 (2.7966/1.2215)	mem 24308MB
[2025-01-19 06:23:08 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][240/312]	eta 0:00:44 lr 0.000042	time 0.6570 (0.6184)	model_time 0.6565 (0.6111)	loss 2.1629 (2.7344)	grad_norm 2.9824 (2.8042/1.2046)	mem 24308MB
[2025-01-19 06:23:14 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][250/312]	eta 0:00:38 lr 0.000042	time 0.6689 (0.6184)	model_time 0.6687 (0.6113)	loss 2.9503 (2.7185)	grad_norm 1.4322 (2.8215/1.2232)	mem 24308MB
[2025-01-19 06:23:21 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][260/312]	eta 0:00:32 lr 0.000042	time 0.5775 (0.6185)	model_time 0.5770 (0.6117)	loss 2.6489 (2.7130)	grad_norm 1.1768 (2.8086/1.2191)	mem 24308MB
[2025-01-19 06:23:26 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][270/312]	eta 0:00:25 lr 0.000042	time 0.6659 (0.6178)	model_time 0.6654 (0.6112)	loss 3.2477 (2.7137)	grad_norm 2.2839 (2.7975/1.2073)	mem 24308MB
[2025-01-19 06:23:33 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][280/312]	eta 0:00:19 lr 0.000042	time 0.6026 (0.6174)	model_time 0.6025 (0.6110)	loss 3.4987 (2.7221)	grad_norm 1.1339 (2.7892/1.1979)	mem 24308MB
[2025-01-19 06:23:39 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][290/312]	eta 0:00:13 lr 0.000042	time 0.6048 (0.6175)	model_time 0.6047 (0.6113)	loss 2.8584 (2.7198)	grad_norm 3.1139 (2.7904/1.1891)	mem 24308MB
[2025-01-19 06:23:45 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][300/312]	eta 0:00:07 lr 0.000042	time 0.6406 (0.6170)	model_time 0.6405 (0.6110)	loss 2.6868 (2.7214)	grad_norm 2.3771 (2.7957/1.1771)	mem 24308MB
[2025-01-19 06:23:51 internimage_s_1k_224] (main.py 510): INFO Train: [295/300][310/312]	eta 0:00:01 lr 0.000042	time 0.5693 (0.6160)	model_time 0.5691 (0.6102)	loss 2.9468 (2.7241)	grad_norm 1.7380 (2.7863/1.1747)	mem 24308MB
[2025-01-19 06:23:51 internimage_s_1k_224] (main.py 519): INFO EPOCH 295 training takes 0:03:12
[2025-01-19 06:23:51 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_295.pth saving......
[2025-01-19 06:23:53 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_295.pth saved !!!
[2025-01-19 06:24:01 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.706 (7.706)	Loss 0.6935 (0.6935)	Acc@1 86.206 (86.206)	Acc@5 97.900 (97.900)	Mem 24308MB
[2025-01-19 06:24:05 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.134 (1.045)	Loss 0.8732 (0.7739)	Acc@1 80.908 (84.304)	Acc@5 96.362 (96.913)	Mem 24308MB
[2025-01-19 06:24:05 internimage_s_1k_224] (main.py 575): INFO [Epoch:295] * Acc@1 84.139 Acc@5 96.909
[2025-01-19 06:24:05 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 06:24:05 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.14%
[2025-01-19 06:24:14 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 9.123 (9.123)	Loss 0.6887 (0.6887)	Acc@1 86.035 (86.035)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 06:24:18 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.213)	Loss 0.8644 (0.7607)	Acc@1 80.615 (84.235)	Acc@5 96.338 (96.911)	Mem 24308MB
[2025-01-19 06:24:18 internimage_s_1k_224] (main.py 575): INFO [Epoch:295] * Acc@1 84.083 Acc@5 96.909
[2025-01-19 06:24:18 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.1%
[2025-01-19 06:24:18 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 84.11%
[2025-01-19 06:24:21 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][0/312]	eta 0:16:30 lr 0.000042	time 3.1753 (3.1753)	model_time 1.3713 (1.3713)	loss 2.1432 (2.1432)	grad_norm 1.5443 (1.5443/0.0000)	mem 24308MB
[2025-01-19 06:24:27 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][10/312]	eta 0:04:12 lr 0.000042	time 0.5931 (0.8353)	model_time 0.5929 (0.6710)	loss 2.4971 (2.7644)	grad_norm 1.9879 (3.1893/1.3004)	mem 24308MB
[2025-01-19 06:24:34 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][20/312]	eta 0:03:33 lr 0.000042	time 0.6476 (0.7312)	model_time 0.6471 (0.6449)	loss 1.7782 (2.5725)	grad_norm 1.5777 (2.7612/1.1935)	mem 24308MB
[2025-01-19 06:24:40 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][30/312]	eta 0:03:14 lr 0.000042	time 0.5938 (0.6884)	model_time 0.5935 (0.6299)	loss 1.8612 (2.6401)	grad_norm 2.1623 (2.5789/1.0927)	mem 24308MB
[2025-01-19 06:24:46 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][40/312]	eta 0:03:02 lr 0.000042	time 0.5763 (0.6713)	model_time 0.5759 (0.6269)	loss 3.0931 (2.6803)	grad_norm 3.1052 (2.7022/1.1283)	mem 24308MB
[2025-01-19 06:24:52 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][50/312]	eta 0:02:52 lr 0.000042	time 0.5831 (0.6570)	model_time 0.5830 (0.6213)	loss 2.9021 (2.6811)	grad_norm 4.1407 (2.9391/1.2819)	mem 24308MB
[2025-01-19 06:24:58 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][60/312]	eta 0:02:44 lr 0.000042	time 0.6502 (0.6508)	model_time 0.6501 (0.6208)	loss 1.9617 (2.6897)	grad_norm 2.6486 (2.9080/1.2310)	mem 24308MB
[2025-01-19 06:25:04 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][70/312]	eta 0:02:36 lr 0.000042	time 0.5641 (0.6458)	model_time 0.5639 (0.6200)	loss 2.5815 (2.6243)	grad_norm 3.5698 (2.9064/1.1882)	mem 24308MB
[2025-01-19 06:25:10 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][80/312]	eta 0:02:28 lr 0.000042	time 0.5928 (0.6389)	model_time 0.5926 (0.6162)	loss 2.1922 (2.6223)	grad_norm 4.0395 (2.8733/1.2112)	mem 24308MB
[2025-01-19 06:25:16 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][90/312]	eta 0:02:20 lr 0.000041	time 0.5795 (0.6351)	model_time 0.5791 (0.6148)	loss 3.4326 (2.6347)	grad_norm 1.6323 (2.8100/1.1689)	mem 24308MB
[2025-01-19 06:25:22 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][100/312]	eta 0:02:14 lr 0.000041	time 0.5866 (0.6335)	model_time 0.5864 (0.6152)	loss 3.3177 (2.6445)	grad_norm 2.8776 (2.8061/1.1421)	mem 24308MB
[2025-01-19 06:25:28 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][110/312]	eta 0:02:07 lr 0.000041	time 0.5805 (0.6317)	model_time 0.5801 (0.6151)	loss 3.0673 (2.6778)	grad_norm 1.2655 (2.8011/1.1380)	mem 24308MB
[2025-01-19 06:25:34 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][120/312]	eta 0:02:00 lr 0.000041	time 0.5768 (0.6288)	model_time 0.5767 (0.6135)	loss 3.1936 (2.6664)	grad_norm 4.3255 (2.8649/1.2287)	mem 24308MB
[2025-01-19 06:25:40 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][130/312]	eta 0:01:53 lr 0.000041	time 0.5727 (0.6263)	model_time 0.5723 (0.6121)	loss 2.7992 (2.6576)	grad_norm 4.2928 (2.9256/1.2330)	mem 24308MB
[2025-01-19 06:25:46 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][140/312]	eta 0:01:47 lr 0.000041	time 0.5915 (0.6255)	model_time 0.5913 (0.6123)	loss 2.7727 (2.6520)	grad_norm 4.7427 (2.9565/1.2669)	mem 24308MB
[2025-01-19 06:25:52 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][150/312]	eta 0:01:40 lr 0.000041	time 0.5730 (0.6230)	model_time 0.5728 (0.6106)	loss 2.4241 (2.6523)	grad_norm 3.2363 (2.9359/1.2440)	mem 24308MB
[2025-01-19 06:25:58 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][160/312]	eta 0:01:34 lr 0.000041	time 0.5817 (0.6220)	model_time 0.5815 (0.6104)	loss 3.0878 (2.6582)	grad_norm 2.6927 (2.9156/1.2334)	mem 24308MB
[2025-01-19 06:26:04 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][170/312]	eta 0:01:28 lr 0.000041	time 0.6553 (0.6212)	model_time 0.6549 (0.6102)	loss 1.9306 (2.6594)	grad_norm 3.6396 (2.9308/1.2210)	mem 24308MB
[2025-01-19 06:26:11 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][180/312]	eta 0:01:21 lr 0.000041	time 0.6937 (0.6211)	model_time 0.6931 (0.6108)	loss 2.7766 (2.6654)	grad_norm 2.5002 (2.9295/1.1997)	mem 24308MB
[2025-01-19 06:26:17 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][190/312]	eta 0:01:15 lr 0.000041	time 0.5751 (0.6205)	model_time 0.5749 (0.6107)	loss 2.8093 (2.6579)	grad_norm 3.8097 (2.9569/1.2032)	mem 24308MB
[2025-01-19 06:26:23 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][200/312]	eta 0:01:09 lr 0.000041	time 0.5833 (0.6188)	model_time 0.5831 (0.6095)	loss 2.8045 (2.6639)	grad_norm 3.9501 (2.9505/1.1913)	mem 24308MB
[2025-01-19 06:26:29 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][210/312]	eta 0:01:03 lr 0.000041	time 0.5739 (0.6183)	model_time 0.5735 (0.6094)	loss 2.9157 (2.6688)	grad_norm 3.1367 (2.9841/1.1935)	mem 24308MB
[2025-01-19 06:26:35 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][220/312]	eta 0:00:56 lr 0.000041	time 0.5975 (0.6186)	model_time 0.5974 (0.6100)	loss 1.9835 (2.6671)	grad_norm 1.4089 (2.9790/1.2023)	mem 24308MB
[2025-01-19 06:26:41 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][230/312]	eta 0:00:50 lr 0.000041	time 0.5966 (0.6180)	model_time 0.5964 (0.6097)	loss 2.3958 (2.6702)	grad_norm 3.2372 (2.9593/1.1935)	mem 24308MB
[2025-01-19 06:26:47 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][240/312]	eta 0:00:44 lr 0.000041	time 0.6006 (0.6173)	model_time 0.6004 (0.6094)	loss 3.1339 (2.6653)	grad_norm 3.0315 (2.9811/1.1882)	mem 24308MB
[2025-01-19 06:26:53 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][250/312]	eta 0:00:38 lr 0.000041	time 0.5946 (0.6164)	model_time 0.5944 (0.6088)	loss 2.2689 (2.6492)	grad_norm 2.0726 (2.9994/1.2495)	mem 24308MB
[2025-01-19 06:26:59 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][260/312]	eta 0:00:32 lr 0.000041	time 0.5840 (0.6162)	model_time 0.5835 (0.6088)	loss 2.3072 (2.6540)	grad_norm 4.4590 (2.9860/1.2383)	mem 24308MB
[2025-01-19 06:27:05 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][270/312]	eta 0:00:25 lr 0.000041	time 0.5786 (0.6153)	model_time 0.5785 (0.6082)	loss 2.5398 (2.6592)	grad_norm 3.2890 (2.9776/1.2262)	mem 24308MB
[2025-01-19 06:27:11 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][280/312]	eta 0:00:19 lr 0.000041	time 0.5774 (0.6149)	model_time 0.5770 (0.6081)	loss 3.0547 (2.6610)	grad_norm 3.3651 (3.0097/1.2367)	mem 24308MB
[2025-01-19 06:27:17 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][290/312]	eta 0:00:13 lr 0.000041	time 0.5876 (0.6146)	model_time 0.5872 (0.6080)	loss 3.0879 (2.6696)	grad_norm 4.9086 (3.0461/1.2426)	mem 24308MB
[2025-01-19 06:27:23 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][300/312]	eta 0:00:07 lr 0.000041	time 0.6771 (0.6143)	model_time 0.6771 (0.6079)	loss 2.6361 (2.6696)	grad_norm 3.2039 (3.0437/1.2327)	mem 24308MB
[2025-01-19 06:27:29 internimage_s_1k_224] (main.py 510): INFO Train: [296/300][310/312]	eta 0:00:01 lr 0.000041	time 0.6699 (0.6142)	model_time 0.6698 (0.6080)	loss 3.1671 (2.6737)	grad_norm 2.4830 (3.0018/1.2277)	mem 24308MB
[2025-01-19 06:27:30 internimage_s_1k_224] (main.py 519): INFO EPOCH 296 training takes 0:03:11
[2025-01-19 06:27:30 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_296.pth saving......
[2025-01-19 06:27:32 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_296.pth saved !!!
[2025-01-19 06:27:40 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.941 (7.941)	Loss 0.6944 (0.6944)	Acc@1 86.279 (86.279)	Acc@5 97.778 (97.778)	Mem 24308MB
[2025-01-19 06:27:43 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.058)	Loss 0.8689 (0.7698)	Acc@1 80.640 (84.275)	Acc@5 96.167 (96.866)	Mem 24308MB
[2025-01-19 06:27:44 internimage_s_1k_224] (main.py 575): INFO [Epoch:296] * Acc@1 84.129 Acc@5 96.873
[2025-01-19 06:27:44 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 06:27:44 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.14%
[2025-01-19 06:27:53 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.937 (8.937)	Loss 0.6887 (0.6887)	Acc@1 86.011 (86.011)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 06:27:57 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.203)	Loss 0.8642 (0.7607)	Acc@1 80.640 (84.222)	Acc@5 96.338 (96.913)	Mem 24308MB
[2025-01-19 06:27:57 internimage_s_1k_224] (main.py 575): INFO [Epoch:296] * Acc@1 84.073 Acc@5 96.909
[2025-01-19 06:27:57 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.1%
[2025-01-19 06:27:57 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 84.11%
[2025-01-19 06:28:00 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][0/312]	eta 0:15:41 lr 0.000041	time 3.0163 (3.0163)	model_time 1.6407 (1.6407)	loss 2.9491 (2.9491)	grad_norm 2.4932 (2.4932/0.0000)	mem 24308MB
[2025-01-19 06:28:06 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][10/312]	eta 0:04:07 lr 0.000041	time 0.5845 (0.8192)	model_time 0.5843 (0.6937)	loss 2.7602 (2.9382)	grad_norm 4.0091 (2.7427/0.8690)	mem 24308MB
[2025-01-19 06:28:12 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][20/312]	eta 0:03:29 lr 0.000041	time 0.5853 (0.7179)	model_time 0.5849 (0.6516)	loss 1.9046 (2.7213)	grad_norm 2.4836 (2.9594/0.9997)	mem 24308MB
[2025-01-19 06:28:18 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][30/312]	eta 0:03:14 lr 0.000041	time 0.5826 (0.6899)	model_time 0.5821 (0.6449)	loss 2.5242 (2.7667)	grad_norm 3.1181 (2.8526/0.9470)	mem 24308MB
[2025-01-19 06:28:25 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][40/312]	eta 0:03:02 lr 0.000041	time 0.5822 (0.6723)	model_time 0.5820 (0.6381)	loss 2.6892 (2.7666)	grad_norm 1.7156 (2.8796/1.1210)	mem 24308MB
[2025-01-19 06:28:31 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][50/312]	eta 0:02:52 lr 0.000041	time 0.5804 (0.6576)	model_time 0.5802 (0.6300)	loss 2.8852 (2.7793)	grad_norm 2.1782 (2.8502/1.0666)	mem 24308MB
[2025-01-19 06:28:36 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][60/312]	eta 0:02:43 lr 0.000041	time 0.5923 (0.6472)	model_time 0.5919 (0.6241)	loss 3.0314 (2.7830)	grad_norm 3.2914 (2.7977/1.0776)	mem 24308MB
[2025-01-19 06:28:43 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][70/312]	eta 0:02:35 lr 0.000041	time 0.6699 (0.6413)	model_time 0.6694 (0.6214)	loss 3.0036 (2.7709)	grad_norm 1.2935 (2.7587/1.0438)	mem 24308MB
[2025-01-19 06:28:48 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][80/312]	eta 0:02:27 lr 0.000041	time 0.5929 (0.6344)	model_time 0.5924 (0.6170)	loss 3.1723 (2.7585)	grad_norm 3.2186 (2.7159/1.0337)	mem 24308MB
[2025-01-19 06:28:54 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][90/312]	eta 0:02:20 lr 0.000041	time 0.6715 (0.6310)	model_time 0.6714 (0.6154)	loss 3.2251 (2.7615)	grad_norm 4.1574 (2.7757/1.0579)	mem 24308MB
[2025-01-19 06:29:00 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][100/312]	eta 0:02:13 lr 0.000041	time 0.6010 (0.6281)	model_time 0.6006 (0.6140)	loss 2.9564 (2.7572)	grad_norm 1.7353 (2.7664/1.0350)	mem 24308MB
[2025-01-19 06:29:07 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][110/312]	eta 0:02:06 lr 0.000041	time 0.5783 (0.6271)	model_time 0.5781 (0.6143)	loss 2.1845 (2.7518)	grad_norm 4.4599 (2.7835/1.0211)	mem 24308MB
[2025-01-19 06:29:13 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][120/312]	eta 0:02:00 lr 0.000041	time 0.5875 (0.6263)	model_time 0.5871 (0.6145)	loss 1.7016 (2.7382)	grad_norm 3.3408 (2.8330/1.0513)	mem 24308MB
[2025-01-19 06:29:19 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][130/312]	eta 0:01:53 lr 0.000041	time 0.6062 (0.6234)	model_time 0.6060 (0.6124)	loss 1.7405 (2.7197)	grad_norm 3.7026 (2.8974/1.1562)	mem 24308MB
[2025-01-19 06:29:25 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][140/312]	eta 0:01:46 lr 0.000041	time 0.5898 (0.6221)	model_time 0.5893 (0.6119)	loss 2.7341 (2.7265)	grad_norm 2.8083 (2.8436/1.1376)	mem 24308MB
[2025-01-19 06:29:31 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][150/312]	eta 0:01:40 lr 0.000041	time 0.5944 (0.6222)	model_time 0.5942 (0.6127)	loss 2.4378 (2.7167)	grad_norm 2.3426 (2.8370/1.1313)	mem 24308MB
[2025-01-19 06:29:37 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][160/312]	eta 0:01:34 lr 0.000041	time 0.6860 (0.6220)	model_time 0.6858 (0.6130)	loss 1.9829 (2.7035)	grad_norm 1.8488 (2.8341/1.1258)	mem 24308MB
[2025-01-19 06:29:43 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][170/312]	eta 0:01:28 lr 0.000041	time 0.5821 (0.6207)	model_time 0.5817 (0.6122)	loss 2.9241 (2.7103)	grad_norm 3.0428 (2.8394/1.1216)	mem 24308MB
[2025-01-19 06:29:49 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][180/312]	eta 0:01:21 lr 0.000041	time 0.5921 (0.6194)	model_time 0.5917 (0.6114)	loss 3.0796 (2.7060)	grad_norm 1.8538 (2.8433/1.1143)	mem 24308MB
[2025-01-19 06:29:55 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][190/312]	eta 0:01:15 lr 0.000041	time 0.6817 (0.6185)	model_time 0.6816 (0.6109)	loss 3.1296 (2.7029)	grad_norm 2.8620 (2.8842/1.1580)	mem 24308MB
[2025-01-19 06:30:01 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][200/312]	eta 0:01:09 lr 0.000041	time 0.6143 (0.6174)	model_time 0.6139 (0.6102)	loss 2.7669 (2.6990)	grad_norm 2.2404 (2.9153/1.2157)	mem 24308MB
[2025-01-19 06:30:07 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][210/312]	eta 0:01:02 lr 0.000041	time 0.7151 (0.6170)	model_time 0.7146 (0.6100)	loss 3.4500 (2.6922)	grad_norm 3.6982 (2.9769/1.2656)	mem 24308MB
[2025-01-19 06:30:13 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][220/312]	eta 0:00:56 lr 0.000041	time 0.5964 (0.6164)	model_time 0.5963 (0.6097)	loss 2.9644 (2.6937)	grad_norm 3.5161 (3.0202/1.2648)	mem 24308MB
[2025-01-19 06:30:19 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][230/312]	eta 0:00:50 lr 0.000041	time 0.5956 (0.6163)	model_time 0.5954 (0.6099)	loss 2.9384 (2.7001)	grad_norm 2.4927 (3.0053/1.2549)	mem 24308MB
[2025-01-19 06:30:26 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][240/312]	eta 0:00:44 lr 0.000041	time 0.6726 (0.6163)	model_time 0.6724 (0.6102)	loss 2.8782 (2.6983)	grad_norm 1.2952 (2.9935/1.2515)	mem 24308MB
[2025-01-19 06:30:31 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][250/312]	eta 0:00:38 lr 0.000041	time 0.6045 (0.6152)	model_time 0.6041 (0.6093)	loss 3.0490 (2.6973)	grad_norm 3.0477 (2.9907/1.2423)	mem 24308MB
[2025-01-19 06:30:37 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][260/312]	eta 0:00:31 lr 0.000041	time 0.5749 (0.6146)	model_time 0.5745 (0.6089)	loss 2.6031 (2.7047)	grad_norm 2.1556 (2.9500/1.2387)	mem 24308MB
[2025-01-19 06:30:44 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][270/312]	eta 0:00:25 lr 0.000040	time 0.6810 (0.6152)	model_time 0.6809 (0.6097)	loss 3.0116 (2.7036)	grad_norm 2.4991 (2.9460/1.2373)	mem 24308MB
[2025-01-19 06:30:50 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][280/312]	eta 0:00:19 lr 0.000040	time 0.5747 (0.6146)	model_time 0.5745 (0.6093)	loss 3.0439 (2.7156)	grad_norm 2.0387 (2.9417/1.2283)	mem 24308MB
[2025-01-19 06:30:56 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][290/312]	eta 0:00:13 lr 0.000040	time 0.5785 (0.6143)	model_time 0.5784 (0.6092)	loss 3.0351 (2.7219)	grad_norm 2.6193 (2.9203/1.2154)	mem 24308MB
[2025-01-19 06:31:02 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][300/312]	eta 0:00:07 lr 0.000040	time 0.5746 (0.6138)	model_time 0.5745 (0.6088)	loss 2.9949 (2.7300)	grad_norm 2.0251 (2.9195/1.2083)	mem 24308MB
[2025-01-19 06:31:08 internimage_s_1k_224] (main.py 510): INFO Train: [297/300][310/312]	eta 0:00:01 lr 0.000040	time 0.5690 (0.6129)	model_time 0.5689 (0.6081)	loss 2.9682 (2.7279)	grad_norm 2.5506 (2.9266/1.2084)	mem 24308MB
[2025-01-19 06:31:08 internimage_s_1k_224] (main.py 519): INFO EPOCH 297 training takes 0:03:11
[2025-01-19 06:31:08 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_297.pth saving......
[2025-01-19 06:31:10 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_297.pth saved !!!
[2025-01-19 06:31:18 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.985 (7.985)	Loss 0.6962 (0.6962)	Acc@1 86.377 (86.377)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 06:31:22 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.043)	Loss 0.8686 (0.7703)	Acc@1 80.737 (84.280)	Acc@5 96.265 (96.904)	Mem 24308MB
[2025-01-19 06:31:22 internimage_s_1k_224] (main.py 575): INFO [Epoch:297] * Acc@1 84.143 Acc@5 96.913
[2025-01-19 06:31:22 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 06:31:22 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 06:31:24 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 06:31:24 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.14%
[2025-01-19 06:31:32 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.941 (7.941)	Loss 0.6887 (0.6887)	Acc@1 86.011 (86.011)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 06:31:35 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.036)	Loss 0.8641 (0.7607)	Acc@1 80.615 (84.215)	Acc@5 96.313 (96.915)	Mem 24308MB
[2025-01-19 06:31:35 internimage_s_1k_224] (main.py 575): INFO [Epoch:297] * Acc@1 84.065 Acc@5 96.911
[2025-01-19 06:31:35 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.1%
[2025-01-19 06:31:35 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 84.11%
[2025-01-19 06:31:39 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][0/312]	eta 0:18:46 lr 0.000040	time 3.6103 (3.6103)	model_time 2.1080 (2.1080)	loss 2.9284 (2.9284)	grad_norm 2.8346 (2.8346/0.0000)	mem 24308MB
[2025-01-19 06:31:45 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][10/312]	eta 0:04:23 lr 0.000040	time 0.5940 (0.8736)	model_time 0.5936 (0.7366)	loss 2.5937 (2.8211)	grad_norm 2.5161 (2.5843/0.5999)	mem 24308MB
[2025-01-19 06:31:51 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][20/312]	eta 0:03:36 lr 0.000040	time 0.6023 (0.7431)	model_time 0.6022 (0.6704)	loss 2.2824 (2.7570)	grad_norm 2.0269 (3.2200/1.4090)	mem 24308MB
[2025-01-19 06:31:57 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][30/312]	eta 0:03:16 lr 0.000040	time 0.5763 (0.6985)	model_time 0.5761 (0.6492)	loss 2.7803 (2.7427)	grad_norm 2.0427 (3.3533/1.4650)	mem 24308MB
[2025-01-19 06:32:03 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][40/312]	eta 0:03:04 lr 0.000040	time 0.6634 (0.6781)	model_time 0.6633 (0.6407)	loss 3.4157 (2.8032)	grad_norm 1.9567 (3.1817/1.3551)	mem 24308MB
[2025-01-19 06:32:10 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][50/312]	eta 0:02:56 lr 0.000040	time 0.8776 (0.6756)	model_time 0.8774 (0.6454)	loss 1.7948 (2.8153)	grad_norm 3.6454 (3.2191/1.3313)	mem 24308MB
[2025-01-19 06:32:16 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][60/312]	eta 0:02:46 lr 0.000040	time 0.5885 (0.6627)	model_time 0.5880 (0.6374)	loss 2.5419 (2.7762)	grad_norm 5.8561 (3.1854/1.3270)	mem 24308MB
[2025-01-19 06:32:22 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][70/312]	eta 0:02:38 lr 0.000040	time 0.5889 (0.6548)	model_time 0.5884 (0.6330)	loss 3.2475 (2.7589)	grad_norm 3.5759 (3.1891/1.3112)	mem 24308MB
[2025-01-19 06:32:28 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][80/312]	eta 0:02:31 lr 0.000040	time 0.6719 (0.6524)	model_time 0.6714 (0.6333)	loss 2.7071 (2.7520)	grad_norm 2.7676 (3.1535/1.3222)	mem 24308MB
[2025-01-19 06:32:34 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][90/312]	eta 0:02:23 lr 0.000040	time 0.6711 (0.6481)	model_time 0.6707 (0.6310)	loss 1.8065 (2.7338)	grad_norm 3.2292 (3.1015/1.3052)	mem 24308MB
[2025-01-19 06:32:40 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][100/312]	eta 0:02:16 lr 0.000040	time 0.5801 (0.6438)	model_time 0.5799 (0.6284)	loss 2.2830 (2.7235)	grad_norm 4.0725 (3.1317/1.3218)	mem 24308MB
[2025-01-19 06:32:46 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][110/312]	eta 0:02:09 lr 0.000040	time 0.5764 (0.6403)	model_time 0.5759 (0.6263)	loss 3.0631 (2.7157)	grad_norm 3.1388 (3.2297/1.3447)	mem 24308MB
[2025-01-19 06:32:52 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][120/312]	eta 0:02:02 lr 0.000040	time 0.5811 (0.6363)	model_time 0.5807 (0.6233)	loss 3.2007 (2.7300)	grad_norm 2.1033 (3.2274/1.3276)	mem 24308MB
[2025-01-19 06:32:58 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][130/312]	eta 0:01:55 lr 0.000040	time 0.5843 (0.6341)	model_time 0.5842 (0.6221)	loss 2.8427 (2.7392)	grad_norm 1.2205 (3.2208/1.3367)	mem 24308MB
[2025-01-19 06:33:04 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][140/312]	eta 0:01:48 lr 0.000040	time 0.5749 (0.6318)	model_time 0.5748 (0.6207)	loss 1.9249 (2.7443)	grad_norm 2.2483 (3.1837/1.3124)	mem 24308MB
[2025-01-19 06:33:11 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][150/312]	eta 0:01:42 lr 0.000040	time 0.6075 (0.6304)	model_time 0.6074 (0.6200)	loss 3.0643 (2.7533)	grad_norm 3.4042 (3.2154/1.3245)	mem 24308MB
[2025-01-19 06:33:17 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][160/312]	eta 0:01:35 lr 0.000040	time 0.6842 (0.6291)	model_time 0.6838 (0.6193)	loss 2.7513 (2.7567)	grad_norm 2.1778 (3.2529/1.3693)	mem 24308MB
[2025-01-19 06:33:23 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][170/312]	eta 0:01:29 lr 0.000040	time 0.5922 (0.6288)	model_time 0.5920 (0.6195)	loss 2.8589 (2.7520)	grad_norm 2.4845 (3.2290/1.3468)	mem 24308MB
[2025-01-19 06:33:29 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][180/312]	eta 0:01:22 lr 0.000040	time 0.6109 (0.6276)	model_time 0.6105 (0.6188)	loss 3.0763 (2.7659)	grad_norm 2.2785 (3.1907/1.3371)	mem 24308MB
[2025-01-19 06:33:35 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][190/312]	eta 0:01:16 lr 0.000040	time 0.5821 (0.6264)	model_time 0.5816 (0.6180)	loss 2.0148 (2.7532)	grad_norm 3.9194 (3.1561/1.3206)	mem 24308MB
[2025-01-19 06:33:41 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][200/312]	eta 0:01:10 lr 0.000040	time 0.5801 (0.6255)	model_time 0.5799 (0.6176)	loss 3.0511 (2.7501)	grad_norm 4.6059 (3.1391/1.3113)	mem 24308MB
[2025-01-19 06:33:47 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][210/312]	eta 0:01:03 lr 0.000040	time 0.5976 (0.6250)	model_time 0.5974 (0.6174)	loss 2.5575 (2.7517)	grad_norm 2.6521 (3.1693/1.3884)	mem 24308MB
[2025-01-19 06:33:53 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][220/312]	eta 0:00:57 lr 0.000040	time 0.5737 (0.6239)	model_time 0.5732 (0.6166)	loss 3.4352 (2.7416)	grad_norm 4.7839 (3.1895/1.3952)	mem 24308MB
[2025-01-19 06:33:59 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][230/312]	eta 0:00:51 lr 0.000040	time 0.5932 (0.6230)	model_time 0.5930 (0.6160)	loss 2.9590 (2.7421)	grad_norm 1.6363 (3.2005/1.4052)	mem 24308MB
[2025-01-19 06:34:05 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][240/312]	eta 0:00:44 lr 0.000040	time 0.6088 (0.6217)	model_time 0.6084 (0.6150)	loss 3.0329 (2.7381)	grad_norm 1.8676 (3.1866/1.3944)	mem 24308MB
[2025-01-19 06:34:11 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][250/312]	eta 0:00:38 lr 0.000040	time 0.6042 (0.6210)	model_time 0.6040 (0.6145)	loss 1.7711 (2.7279)	grad_norm 4.2035 (3.2054/1.3935)	mem 24308MB
[2025-01-19 06:34:17 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][260/312]	eta 0:00:32 lr 0.000040	time 0.5954 (0.6205)	model_time 0.5953 (0.6143)	loss 1.8432 (2.7258)	grad_norm 2.2127 (3.2120/1.3894)	mem 24308MB
[2025-01-19 06:34:23 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][270/312]	eta 0:00:26 lr 0.000040	time 0.5722 (0.6202)	model_time 0.5720 (0.6142)	loss 1.9622 (2.7180)	grad_norm 7.2444 (3.2334/1.3958)	mem 24308MB
[2025-01-19 06:34:30 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][280/312]	eta 0:00:19 lr 0.000040	time 0.6001 (0.6201)	model_time 0.5999 (0.6144)	loss 3.0486 (2.7216)	grad_norm 3.8855 (3.2469/1.4018)	mem 24308MB
[2025-01-19 06:34:36 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][290/312]	eta 0:00:13 lr 0.000040	time 0.5832 (0.6202)	model_time 0.5831 (0.6146)	loss 1.9883 (2.7228)	grad_norm 3.1850 (3.2526/1.3939)	mem 24308MB
[2025-01-19 06:34:42 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][300/312]	eta 0:00:07 lr 0.000040	time 0.5758 (0.6195)	model_time 0.5757 (0.6141)	loss 2.9328 (2.7202)	grad_norm 1.8715 (3.2512/1.3862)	mem 24308MB
[2025-01-19 06:34:48 internimage_s_1k_224] (main.py 510): INFO Train: [298/300][310/312]	eta 0:00:01 lr 0.000040	time 0.6773 (0.6184)	model_time 0.6771 (0.6131)	loss 2.4992 (2.7183)	grad_norm 2.9786 (3.2647/1.3847)	mem 24308MB
[2025-01-19 06:34:48 internimage_s_1k_224] (main.py 519): INFO EPOCH 298 training takes 0:03:12
[2025-01-19 06:34:48 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_298.pth saving......
[2025-01-19 06:34:50 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_298.pth saved !!!
[2025-01-19 06:34:58 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.675 (7.675)	Loss 0.6947 (0.6947)	Acc@1 86.157 (86.157)	Acc@5 97.900 (97.900)	Mem 24308MB
[2025-01-19 06:35:02 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.046)	Loss 0.8737 (0.7728)	Acc@1 80.859 (84.322)	Acc@5 96.387 (96.908)	Mem 24308MB
[2025-01-19 06:35:02 internimage_s_1k_224] (main.py 575): INFO [Epoch:298] * Acc@1 84.163 Acc@5 96.915
[2025-01-19 06:35:02 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.2%
[2025-01-19 06:35:02 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saving......
[2025-01-19 06:35:04 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_best.pth saved !!!
[2025-01-19 06:35:04 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.16%
[2025-01-19 06:35:12 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 7.935 (7.935)	Loss 0.6886 (0.6886)	Acc@1 86.011 (86.011)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 06:35:15 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.048)	Loss 0.8638 (0.7606)	Acc@1 80.688 (84.235)	Acc@5 96.313 (96.922)	Mem 24308MB
[2025-01-19 06:35:15 internimage_s_1k_224] (main.py 575): INFO [Epoch:298] * Acc@1 84.081 Acc@5 96.917
[2025-01-19 06:35:15 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.1%
[2025-01-19 06:35:15 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 84.11%
[2025-01-19 06:35:19 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][0/312]	eta 0:17:13 lr 0.000040	time 3.3134 (3.3134)	model_time 1.5691 (1.5691)	loss 3.2286 (3.2286)	grad_norm 4.7317 (4.7317/0.0000)	mem 24308MB
[2025-01-19 06:35:25 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][10/312]	eta 0:04:22 lr 0.000040	time 0.5790 (0.8685)	model_time 0.5788 (0.7096)	loss 1.8164 (2.4098)	grad_norm 1.6608 (2.1756/0.8923)	mem 24308MB
[2025-01-19 06:35:31 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][20/312]	eta 0:03:37 lr 0.000040	time 0.6107 (0.7456)	model_time 0.6105 (0.6622)	loss 2.2056 (2.5278)	grad_norm 2.0357 (2.3532/0.8248)	mem 24308MB
[2025-01-19 06:35:37 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][30/312]	eta 0:03:17 lr 0.000040	time 0.6080 (0.7001)	model_time 0.6075 (0.6435)	loss 1.7317 (2.5835)	grad_norm 1.4402 (2.4603/0.9012)	mem 24308MB
[2025-01-19 06:35:43 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][40/312]	eta 0:03:04 lr 0.000040	time 0.6505 (0.6789)	model_time 0.6504 (0.6360)	loss 3.1999 (2.6204)	grad_norm 4.3378 (2.8034/1.0368)	mem 24308MB
[2025-01-19 06:35:49 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][50/312]	eta 0:02:53 lr 0.000040	time 0.6606 (0.6625)	model_time 0.6605 (0.6280)	loss 3.4397 (2.6708)	grad_norm 1.7680 (2.7373/1.0151)	mem 24308MB
[2025-01-19 06:35:55 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][60/312]	eta 0:02:44 lr 0.000040	time 0.5787 (0.6515)	model_time 0.5786 (0.6225)	loss 2.2002 (2.6643)	grad_norm 2.4703 (2.9015/1.0886)	mem 24308MB
[2025-01-19 06:36:01 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][70/312]	eta 0:02:36 lr 0.000040	time 0.5748 (0.6456)	model_time 0.5746 (0.6207)	loss 2.8041 (2.6817)	grad_norm 3.1204 (2.9222/1.0307)	mem 24308MB
[2025-01-19 06:36:07 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][80/312]	eta 0:02:28 lr 0.000040	time 0.5868 (0.6406)	model_time 0.5866 (0.6187)	loss 3.1243 (2.6740)	grad_norm 1.5475 (2.9527/1.0451)	mem 24308MB
[2025-01-19 06:36:13 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][90/312]	eta 0:02:21 lr 0.000040	time 0.5791 (0.6354)	model_time 0.5787 (0.6158)	loss 2.7918 (2.6695)	grad_norm 3.3707 (2.9626/1.0710)	mem 24308MB
[2025-01-19 06:36:20 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][100/312]	eta 0:02:15 lr 0.000040	time 0.6629 (0.6395)	model_time 0.6628 (0.6219)	loss 2.2241 (2.6645)	grad_norm 4.5430 (3.0586/1.1456)	mem 24308MB
[2025-01-19 06:36:26 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][110/312]	eta 0:02:08 lr 0.000040	time 0.5750 (0.6359)	model_time 0.5746 (0.6199)	loss 2.8898 (2.6511)	grad_norm 1.7649 (3.0652/1.2456)	mem 24308MB
[2025-01-19 06:36:32 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][120/312]	eta 0:02:01 lr 0.000040	time 0.6852 (0.6333)	model_time 0.6851 (0.6185)	loss 2.3163 (2.6425)	grad_norm 6.2866 (3.0857/1.2922)	mem 24308MB
[2025-01-19 06:36:38 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][130/312]	eta 0:01:55 lr 0.000040	time 0.6010 (0.6324)	model_time 0.6008 (0.6187)	loss 2.4106 (2.6582)	grad_norm 1.3248 (3.0356/1.2697)	mem 24308MB
[2025-01-19 06:36:44 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][140/312]	eta 0:01:48 lr 0.000040	time 0.5941 (0.6308)	model_time 0.5936 (0.6181)	loss 2.2487 (2.6533)	grad_norm 2.5066 (2.9791/1.2530)	mem 24308MB
[2025-01-19 06:36:50 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][150/312]	eta 0:01:41 lr 0.000040	time 0.5991 (0.6292)	model_time 0.5989 (0.6173)	loss 2.8795 (2.6741)	grad_norm 1.8412 (2.9690/1.2314)	mem 24308MB
[2025-01-19 06:36:56 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][160/312]	eta 0:01:35 lr 0.000040	time 0.6132 (0.6273)	model_time 0.6127 (0.6160)	loss 3.1209 (2.6831)	grad_norm 2.2511 (2.9893/1.2605)	mem 24308MB
[2025-01-19 06:37:02 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][170/312]	eta 0:01:28 lr 0.000040	time 0.5865 (0.6254)	model_time 0.5861 (0.6147)	loss 3.1782 (2.7002)	grad_norm 2.2771 (2.9696/1.2417)	mem 24308MB
[2025-01-19 06:37:08 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][180/312]	eta 0:01:22 lr 0.000040	time 0.6022 (0.6242)	model_time 0.6017 (0.6141)	loss 2.6271 (2.6995)	grad_norm 3.5848 (2.9435/1.2239)	mem 24308MB
[2025-01-19 06:37:14 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][190/312]	eta 0:01:15 lr 0.000040	time 0.5989 (0.6227)	model_time 0.5987 (0.6132)	loss 3.0994 (2.7071)	grad_norm 1.7285 (2.9201/1.2032)	mem 24308MB
[2025-01-19 06:37:21 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][200/312]	eta 0:01:09 lr 0.000040	time 0.5790 (0.6223)	model_time 0.5785 (0.6132)	loss 2.7494 (2.7129)	grad_norm 2.5886 (2.9274/1.1860)	mem 24308MB
[2025-01-19 06:37:26 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][210/312]	eta 0:01:03 lr 0.000040	time 0.5957 (0.6211)	model_time 0.5950 (0.6124)	loss 2.3157 (2.7166)	grad_norm 3.4038 (2.9643/1.2413)	mem 24308MB
[2025-01-19 06:37:33 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][220/312]	eta 0:00:57 lr 0.000040	time 0.5976 (0.6222)	model_time 0.5972 (0.6139)	loss 2.1499 (2.7165)	grad_norm 3.9809 (2.9493/1.2270)	mem 24308MB
[2025-01-19 06:37:39 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][230/312]	eta 0:00:50 lr 0.000040	time 0.5765 (0.6215)	model_time 0.5759 (0.6135)	loss 3.1324 (2.7144)	grad_norm 3.4406 (2.9363/1.2058)	mem 24308MB
[2025-01-19 06:37:45 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][240/312]	eta 0:00:44 lr 0.000040	time 0.5948 (0.6208)	model_time 0.5943 (0.6131)	loss 2.3375 (2.7179)	grad_norm 3.9288 (2.9531/1.2001)	mem 24308MB
[2025-01-19 06:37:51 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][250/312]	eta 0:00:38 lr 0.000040	time 0.6025 (0.6208)	model_time 0.6024 (0.6134)	loss 3.1105 (2.7167)	grad_norm 1.7401 (2.9489/1.1903)	mem 24308MB
[2025-01-19 06:37:57 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][260/312]	eta 0:00:32 lr 0.000040	time 0.5851 (0.6207)	model_time 0.5849 (0.6136)	loss 2.8437 (2.7123)	grad_norm 3.1894 (2.9286/1.1792)	mem 24308MB
[2025-01-19 06:38:03 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][270/312]	eta 0:00:26 lr 0.000040	time 0.5877 (0.6199)	model_time 0.5872 (0.6131)	loss 2.4044 (2.7081)	grad_norm 4.4795 (2.9204/1.1759)	mem 24308MB
[2025-01-19 06:38:09 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][280/312]	eta 0:00:19 lr 0.000040	time 0.5820 (0.6193)	model_time 0.5816 (0.6127)	loss 2.7696 (2.7074)	grad_norm 3.8146 (2.9140/1.1826)	mem 24308MB
[2025-01-19 06:38:16 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][290/312]	eta 0:00:13 lr 0.000040	time 0.5731 (0.6189)	model_time 0.5728 (0.6125)	loss 2.3849 (2.7093)	grad_norm 4.2396 (2.9333/1.1874)	mem 24308MB
[2025-01-19 06:38:22 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][300/312]	eta 0:00:07 lr 0.000040	time 0.5743 (0.6182)	model_time 0.5742 (0.6120)	loss 2.4242 (2.7073)	grad_norm 2.3579 (2.9252/1.1780)	mem 24308MB
[2025-01-19 06:38:27 internimage_s_1k_224] (main.py 510): INFO Train: [299/300][310/312]	eta 0:00:01 lr 0.000040	time 0.5757 (0.6168)	model_time 0.5756 (0.6108)	loss 1.9348 (2.7039)	grad_norm 2.9041 (2.9485/1.1708)	mem 24308MB
[2025-01-19 06:38:28 internimage_s_1k_224] (main.py 519): INFO EPOCH 299 training takes 0:03:12
[2025-01-19 06:38:28 internimage_s_1k_224] (utils.py 359): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_299.pth saving......
[2025-01-19 06:38:30 internimage_s_1k_224] (utils.py 361): INFO work_dirs/internimage_s_1k_224/ckpt_epoch_299.pth saved !!!
[2025-01-19 06:38:45 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 15.209 (15.209)	Loss 0.6957 (0.6957)	Acc@1 86.523 (86.523)	Acc@5 97.827 (97.827)	Mem 24308MB
[2025-01-19 06:38:49 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.757)	Loss 0.8685 (0.7716)	Acc@1 80.615 (84.302)	Acc@5 96.460 (96.955)	Mem 24308MB
[2025-01-19 06:38:49 internimage_s_1k_224] (main.py 575): INFO [Epoch:299] * Acc@1 84.141 Acc@5 96.959
[2025-01-19 06:38:49 internimage_s_1k_224] (main.py 340): INFO Accuracy of the network on the 50000 test images: 84.1%
[2025-01-19 06:38:49 internimage_s_1k_224] (main.py 355): INFO Max accuracy: 84.16%
[2025-01-19 06:38:58 internimage_s_1k_224] (main.py 568): INFO Test: [0/13]	Time 8.962 (8.962)	Loss 0.6884 (0.6884)	Acc@1 85.986 (85.986)	Acc@5 97.876 (97.876)	Mem 24308MB
[2025-01-19 06:39:02 internimage_s_1k_224] (main.py 568): INFO Test: [10/13]	Time 0.133 (1.199)	Loss 0.8636 (0.7605)	Acc@1 80.688 (84.255)	Acc@5 96.313 (96.917)	Mem 24308MB
[2025-01-19 06:39:03 internimage_s_1k_224] (main.py 575): INFO [Epoch:299] * Acc@1 84.097 Acc@5 96.917
[2025-01-19 06:39:03 internimage_s_1k_224] (main.py 360): INFO Accuracy of the ema network on the 50000 test images: 84.1%
[2025-01-19 06:39:03 internimage_s_1k_224] (main.py 375): INFO Max ema accuracy: 84.11%
[2025-01-19 06:39:03 internimage_s_1k_224] (main.py 379): INFO Training time 18:18:48