Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b348e1a4f66bdcef233a2a203dbe1cd2b2907bc994c21608fbf3bf1d92130aa
+oid sha256:5d7ea09d3f819964c751cdc9d2cdab371fbdffd74ba249593d52221f18d2bc7b
 size 343242432

run-3/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-3/checkpoint-20/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50e11d788c48ad12252fa88228c8464ea0c6334c08c85f1a1eed49a21158bf63
+size 343242432

run-3/checkpoint-20/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abcda00f31fc5b419bef54eab1293ba712f7aa22e58fe9b0d651e99bdb4df5d5
+size 686605754

run-3/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-3/checkpoint-20/rng_state.pth

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

run-3/checkpoint-20/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:148e6cb85a170183c5c2f95fca83421a6c447f3cd473aedf432de6730e37b951
+size 1064

run-3/checkpoint-20/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": 0.1375,
+  "best_model_checkpoint": "model/image_classification/run-3/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": 0.8163558840751648,
+      "learning_rate": 1.96917647162269e-06,
+      "loss": 2.0789,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.11875,
+      "eval_loss": 2.078460693359375,
+      "eval_runtime": 0.7985,
+      "eval_samples_per_second": 200.371,
+      "eval_steps_per_second": 12.523,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6774879693984985,
+      "learning_rate": 9.84588235811345e-07,
+      "loss": 2.074,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.1375,
+      "eval_loss": 2.078967332839966,
+      "eval_runtime": 0.9313,
+      "eval_samples_per_second": 171.797,
+      "eval_steps_per_second": 10.737,
+      "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": 2.6583882366906316e-06,
+    "per_device_train_batch_size": 32
+  }
+}

run-3/checkpoint-20/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bacc069379f9a76a0421661769f4154c4f2fafc76fc9b7073cda486d359056fa
+size 5176

run-3/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-3/checkpoint-30/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f82c0b1c4586ec4ea2e96ecf59d51ad5f631b788c8445c78133061c52860c526
+size 343242432

run-3/checkpoint-30/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:564f8537b5c24b9956c342519c9d24627af7a06e8965031765c6fb8f47e75f24
+size 686605754

run-3/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-3/checkpoint-30/rng_state.pth

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

run-3/checkpoint-30/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d68c87e4bcdf1897991d9ec1467f65521fd724d80e9e74b25fb8f76195c12d71
+size 1064

run-3/checkpoint-30/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": 0.1375,
+  "best_model_checkpoint": "model/image_classification/run-3/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": 0.8163558840751648,
+      "learning_rate": 1.96917647162269e-06,
+      "loss": 2.0789,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.11875,
+      "eval_loss": 2.078460693359375,
+      "eval_runtime": 0.7985,
+      "eval_samples_per_second": 200.371,
+      "eval_steps_per_second": 12.523,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6774879693984985,
+      "learning_rate": 9.84588235811345e-07,
+      "loss": 2.074,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.1375,
+      "eval_loss": 2.078967332839966,
+      "eval_runtime": 0.9313,
+      "eval_samples_per_second": 171.797,
+      "eval_steps_per_second": 10.737,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.8743719458580017,
+      "learning_rate": 0.0,
+      "loss": 2.0732,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.09375,
+      "eval_loss": 2.0778565406799316,
+      "eval_runtime": 1.6395,
+      "eval_samples_per_second": 97.588,
+      "eval_steps_per_second": 6.099,
+      "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": 2.6583882366906316e-06,
+    "per_device_train_batch_size": 32
+  }
+}

run-3/checkpoint-30/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bacc069379f9a76a0421661769f4154c4f2fafc76fc9b7073cda486d359056fa
+size 5176

run-4/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-4/checkpoint-20/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d7ea09d3f819964c751cdc9d2cdab371fbdffd74ba249593d52221f18d2bc7b
+size 343242432

run-4/checkpoint-20/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af74cf582a8f00a1835f9e5fad3fe75c731cb9ac0869962e6977f48c7cdb245c
+size 686605754

run-4/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-4/checkpoint-20/rng_state.pth

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

run-4/checkpoint-20/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e17a96617e94c2e38260317c359e9c8eb9af8b3a3154b01c80aa1af31493fe1
+size 1064

run-4/checkpoint-20/trainer_state.json

@@ -0,0 +1,59 @@
+{
+  "best_metric": 0.13125,
+  "best_model_checkpoint": "model/image_classification/run-4/checkpoint-20",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 20,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.0558984279632568,
+      "learning_rate": 1.1573843762670946e-05,
+      "loss": 2.0691,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.9791191816329956,
+      "learning_rate": 9.259075010136756e-06,
+      "loss": 2.0787,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.13125,
+      "eval_loss": 2.066149950027466,
+      "eval_runtime": 0.8295,
+      "eval_samples_per_second": 192.878,
+      "eval_steps_per_second": 12.055,
+      "step": 20
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 60,
+  "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": 4.959754037231616e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.2499751263684622e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-4/checkpoint-20/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d82ed6666d931a5598f0a45acdc17365e7e100844132b2632459ef561b790720
+size 5176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bacc069379f9a76a0421661769f4154c4f2fafc76fc9b7073cda486d359056fa
+oid sha256:d82ed6666d931a5598f0a45acdc17365e7e100844132b2632459ef561b790720
 size 5176