Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b4041b832e1d62d87602abc5928e3175ebf3fddc0826bfff2b54773b121dcc1
+oid sha256:c166bd01fe477bd0ba2f0cf09f899378b0b8ca4ac2356363cf920cfaf46e4f89
 size 343242432

run-0/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-0/checkpoint-10/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1a566cbb6ff3a40afc4d650221abf2ba4fbf42b6a2906106767d6972016b1ec
+size 343242432

run-0/checkpoint-10/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abdeaabf25ece61b530a801a1071fe42c258e577d43d0f63c9f636065519c535
+size 686605754

run-0/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-0/checkpoint-10/rng_state.pth

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

run-0/checkpoint-10/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:428c7f2eb12c4b42e4575a3d3578451bfcb11004a0c7d2b87e69cb629824337c
+size 1064

run-0/checkpoint-10/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": 0.19375,
+  "best_model_checkpoint": "model/image_classification/run-0/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": 2.0665345191955566,
+      "eval_runtime": 1.0008,
+      "eval_samples_per_second": 159.877,
+      "eval_steps_per_second": 9.992,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5518031120300293,
+      "learning_rate": 1.2223590254554655e-05,
+      "loss": 2.0611,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.19375,
+      "eval_loss": 2.0526061058044434,
+      "eval_runtime": 1.6216,
+      "eval_samples_per_second": 98.67,
+      "eval_steps_per_second": 6.167,
+      "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": 3.17813346618421e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-0/checkpoint-10/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:744d69b76e42dd7d056d0c6b75ff3bca8540bf6f116f8829f049bd31671fdf46
+size 5176

run-0/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-0/checkpoint-15/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c166bd01fe477bd0ba2f0cf09f899378b0b8ca4ac2356363cf920cfaf46e4f89
+size 343242432

run-0/checkpoint-15/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d862d8290404e6871c2a7d282bde8c3a56e02e4ff1c39dcd198f40bb46afaa8
+size 686605754

run-0/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-0/checkpoint-15/rng_state.pth

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

run-0/checkpoint-15/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f06c6f07d43e2c650580df11ba68a2a432dc21d237c76d4cb04b878c2459654d
+size 1064

run-0/checkpoint-15/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.19375,
+  "best_model_checkpoint": "model/image_classification/run-0/checkpoint-10",
+  "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": 2.0665345191955566,
+      "eval_runtime": 1.0008,
+      "eval_samples_per_second": 159.877,
+      "eval_steps_per_second": 9.992,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5518031120300293,
+      "learning_rate": 1.2223590254554655e-05,
+      "loss": 2.0611,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.19375,
+      "eval_loss": 2.0526061058044434,
+      "eval_runtime": 1.6216,
+      "eval_samples_per_second": 98.67,
+      "eval_steps_per_second": 6.167,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.19375,
+      "eval_loss": 2.046643018722534,
+      "eval_runtime": 1.5063,
+      "eval_samples_per_second": 106.223,
+      "eval_steps_per_second": 6.639,
+      "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": 3.17813346618421e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-0/checkpoint-15/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:744d69b76e42dd7d056d0c6b75ff3bca8540bf6f116f8829f049bd31671fdf46
+size 5176