Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87f9b7df98ccdc1e8384a65f7d7ab62a9ed3cd881e6e94e22b8db398f5bb9455
+oid sha256:2b348e1a4f66bdcef233a2a203dbe1cd2b2907bc994c21608fbf3bf1d92130aa
 size 343242432

run-2/checkpoint-10/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-10/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:494fab284b62746fb80391489da14d3a68a14bb24fa7152cf64096277d56a0ca
+size 343242432

run-2/checkpoint-10/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a9119023874941b61e73fafa118c9a20872d6beda5505072fc803db877e3e68
+size 686605754

run-2/checkpoint-10/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-10/rng_state.pth

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

run-2/checkpoint-10/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:406c09182af819af8d0c023c7112cc9b3c95338b9633b71f0533529789d0700d
+size 1064

run-2/checkpoint-10/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": 0.19375,
+  "best_model_checkpoint": "model/image_classification/run-2/checkpoint-10",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 10,
+  "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
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.554878294467926,
+      "learning_rate": 1.254632908162212e-05,
+      "loss": 2.0607,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.19375,
+      "eval_loss": 2.0514893531799316,
+      "eval_runtime": 0.8737,
+      "eval_samples_per_second": 183.139,
+      "eval_steps_per_second": 11.446,
+      "step": 10
+    }
+  ],
+  "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": 9.919508074463232e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.262045561221751e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-2/checkpoint-10/training_args.bin

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

run-2/checkpoint-15/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-15/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd170f9ba966b32bc90ea505175dbcccf2ccad033105c94c476919fe31ff900d
+size 343242432

run-2/checkpoint-15/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f0165c1800a8203e6a0f4dcbe95b66f027b400272f3f2b3c458f95c466aa4f1
+size 686605754

run-2/checkpoint-15/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-15/rng_state.pth

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

run-2/checkpoint-15/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:045b9544873e2db9b4c29a64710cd206f727f6be36c4911a707adafcb98aa3b8
+size 1064

run-2/checkpoint-15/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.2,
+  "best_model_checkpoint": "model/image_classification/run-2/checkpoint-15",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 15,
+  "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
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.554878294467926,
+      "learning_rate": 1.254632908162212e-05,
+      "loss": 2.0607,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.19375,
+      "eval_loss": 2.0514893531799316,
+      "eval_runtime": 0.8737,
+      "eval_samples_per_second": 183.139,
+      "eval_steps_per_second": 11.446,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.2,
+      "eval_loss": 2.045300245285034,
+      "eval_runtime": 1.0516,
+      "eval_samples_per_second": 152.149,
+      "eval_steps_per_second": 9.509,
+      "step": 15
+    }
+  ],
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.919508074463232e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.262045561221751e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-2/checkpoint-15/training_args.bin

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

run-3/checkpoint-10/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-10/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b348e1a4f66bdcef233a2a203dbe1cd2b2907bc994c21608fbf3bf1d92130aa
+size 343242432

run-3/checkpoint-10/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e6970221c29ba2821bf5fd7ba9568f7d9bb2617323b2db33da62777b7a92b0b
+size 686605754

run-3/checkpoint-10/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-10/rng_state.pth

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

run-3/checkpoint-10/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:093301e7cabcc6cc5fbb9dce9d148bb87f1241d584e812673234d245e47cba25
+size 1064

run-3/checkpoint-10/trainer_state.json

@@ -0,0 +1,52 @@
+{
+  "best_metric": 0.11875,
+  "best_model_checkpoint": "model/image_classification/run-3/checkpoint-10",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 10,
+  "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
+    }
+  ],
+  "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": 4.959754037231616e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.6583882366906316e-06,
+    "per_device_train_batch_size": 32
+  }
+}

run-3/checkpoint-10/training_args.bin

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:158be39f5943f4f1726b0d83cb3357c01c77f59f4d4914df54869d0c58dd59e8
+oid sha256:bacc069379f9a76a0421661769f4154c4f2fafc76fc9b7073cda486d359056fa
 size 5176