Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72c604aa110b6aa499d3bad032202645bba3606afde9e8676d3bb055f3406bc5
+oid sha256:87f9b7df98ccdc1e8384a65f7d7ab62a9ed3cd881e6e94e22b8db398f5bb9455
 size 343242432

run-1/checkpoint-20/config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "anger",
+    "1": "contempt",
+    "2": "disgust",
+    "3": "fear",
+    "4": "happy",
+    "5": "neutral",
+    "6": "sad",
+    "7": "surprise"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "anger": "0",
+    "contempt": "1",
+    "disgust": "2",
+    "fear": "3",
+    "happy": "4",
+    "neutral": "5",
+    "sad": "6",
+    "surprise": "7"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2"
+}

run-1/checkpoint-20/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c8f79b101958b738e19f4d3a4f834c2ef5705c54d57ba4b64d831c1a8cb94a1
+size 343242432

run-1/checkpoint-20/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5d184de142bce0a24f8cdcc64818a9af228ebe8ef3435806f40582634668537
+size 686605754

run-1/checkpoint-20/preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

run-1/checkpoint-20/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83f925d90a08b776e0ab30d6b04595c492e66b69f5a47c1cd5f0b86dddfe5873
+size 14244

run-1/checkpoint-20/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a0b311e614c616e54a3eca6a21bf67c618571267989ebd162e9d83d379c3b3c
+size 1064

run-1/checkpoint-20/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": 0.14375,
+  "best_model_checkpoint": "model/image_classification/run-1/checkpoint-20",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 20,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9903935194015503,
+      "learning_rate": 5.668350980311898e-06,
+      "loss": 2.0775,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.125,
+      "eval_loss": 2.0746703147888184,
+      "eval_runtime": 0.7378,
+      "eval_samples_per_second": 216.85,
+      "eval_steps_per_second": 13.553,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6741117835044861,
+      "learning_rate": 2.834175490155949e-06,
+      "loss": 2.065,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.14375,
+      "eval_loss": 2.071667432785034,
+      "eval_runtime": 1.4059,
+      "eval_samples_per_second": 113.809,
+      "eval_steps_per_second": 7.113,
+      "step": 20
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 30,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.919508074463232e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.652273823421063e-06,
+    "per_device_train_batch_size": 32
+  }
+}

run-1/checkpoint-20/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e43cb07a25b426fd13f9c7d4436393f951461633c9c65632d9eb37ca6dfe3588
+size 5176

run-1/checkpoint-30/config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "anger",
+    "1": "contempt",
+    "2": "disgust",
+    "3": "fear",
+    "4": "happy",
+    "5": "neutral",
+    "6": "sad",
+    "7": "surprise"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "anger": "0",
+    "contempt": "1",
+    "disgust": "2",
+    "fear": "3",
+    "happy": "4",
+    "neutral": "5",
+    "sad": "6",
+    "surprise": "7"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2"
+}

run-1/checkpoint-30/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0bda784550f565e1162797620bb219a5818e5fcca3cc1a7ef85ecf1f73bbba7
+size 343242432

run-1/checkpoint-30/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5800d3e5c61c9e58af967a4b17008555515d220bb40db2487c23a0f5889876a
+size 686605754

run-1/checkpoint-30/preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

run-1/checkpoint-30/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c6adff979f9014b2454268eddca4e8037130bba68679c8fdb4378cbee10cdd0
+size 14244

run-1/checkpoint-30/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d832ec3bded697f535803ac4d3cececb6de9de2f92cdd4bd9cdcf04100c7040
+size 1064

run-1/checkpoint-30/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": 0.14375,
+  "best_model_checkpoint": "model/image_classification/run-1/checkpoint-20",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 30,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9903935194015503,
+      "learning_rate": 5.668350980311898e-06,
+      "loss": 2.0775,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.125,
+      "eval_loss": 2.0746703147888184,
+      "eval_runtime": 0.7378,
+      "eval_samples_per_second": 216.85,
+      "eval_steps_per_second": 13.553,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6741117835044861,
+      "learning_rate": 2.834175490155949e-06,
+      "loss": 2.065,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.14375,
+      "eval_loss": 2.071667432785034,
+      "eval_runtime": 1.4059,
+      "eval_samples_per_second": 113.809,
+      "eval_steps_per_second": 7.113,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.832188606262207,
+      "learning_rate": 0.0,
+      "loss": 2.0598,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.125,
+      "eval_loss": 2.0695128440856934,
+      "eval_runtime": 1.1417,
+      "eval_samples_per_second": 140.138,
+      "eval_steps_per_second": 8.759,
+      "step": 30
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 30,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4879262111694848e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.652273823421063e-06,
+    "per_device_train_batch_size": 32
+  }
+}

run-1/checkpoint-30/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e43cb07a25b426fd13f9c7d4436393f951461633c9c65632d9eb37ca6dfe3588
+size 5176

run-2/checkpoint-5/config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "anger",
+    "1": "contempt",
+    "2": "disgust",
+    "3": "fear",
+    "4": "happy",
+    "5": "neutral",
+    "6": "sad",
+    "7": "surprise"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "anger": "0",
+    "contempt": "1",
+    "disgust": "2",
+    "fear": "3",
+    "happy": "4",
+    "neutral": "5",
+    "sad": "6",
+    "surprise": "7"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2"
+}

run-2/checkpoint-5/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87f9b7df98ccdc1e8384a65f7d7ab62a9ed3cd881e6e94e22b8db398f5bb9455
+size 343242432

run-2/checkpoint-5/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b70abe7ad86fa081b7d20c6f244fdb58f71bfebcffda661cc98bf46393ed1163
+size 686605754

run-2/checkpoint-5/preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

run-2/checkpoint-5/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:827048ccfd9536f41a4f2cb3f515c1457a5168650a4a7030e7df9eae593d1b5c
+size 14244

run-2/checkpoint-5/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ddf2ed795c1835dd4b84806401fe617e9eac0d0b1bb234b72b2fa47450b4505
+size 1064

run-2/checkpoint-5/trainer_state.json

@@ -0,0 +1,45 @@
+{
+  "best_metric": 0.125,
+  "best_model_checkpoint": "model/image_classification/run-2/checkpoint-5",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 5,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.125,
+      "eval_loss": 2.0662779808044434,
+      "eval_runtime": 0.8979,
+      "eval_samples_per_second": 178.192,
+      "eval_steps_per_second": 11.137,
+      "step": 5
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 15,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.262045561221751e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-2/checkpoint-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:158be39f5943f4f1726b0d83cb3357c01c77f59f4d4914df54869d0c58dd59e8
+size 5176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e43cb07a25b426fd13f9c7d4436393f951461633c9c65632d9eb37ca6dfe3588
+oid sha256:158be39f5943f4f1726b0d83cb3357c01c77f59f4d4914df54869d0c58dd59e8
 size 5176