Upload folder using huggingface_hub

checkpoint-3750/config.json

@@ -0,0 +1,34 @@
+{
+  "_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": "Sandal",
+    "1": "Boot",
+    "2": "Shoe"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Boot": 1,
+    "Sandal": 0,
+    "Shoe": 2
+  },
+  "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": "4.33.0"
+}

checkpoint-3750/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a98efbdf24cd65e983ea6461b4b2ceba7ba55ab2eda520aab2696736fe1c964
+size 686574597

checkpoint-3750/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
+  }
+}

checkpoint-3750/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94999e3ffc5bd040ff741799719ff28cb66f4d929cb49d2456fd90a107429e69
+size 343271789

checkpoint-3750/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d40fe73c0dd76560ea91a195e3b7d9a50ebc0ae28dc5b5c9f024cbd02d2792f3
+size 14575

checkpoint-3750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07b1a1e8f3e7421a9e6ea897d130f4c3143c046f573f471153baf5908135f440
+size 627

checkpoint-3750/trainer_state.json

@@ -0,0 +1,151 @@
+{
+  "best_metric": 0.04055546224117279,
+  "best_model_checkpoint": "footwear_image_detection/checkpoint-3750",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 3750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.988,
+      "eval_loss": 0.09857043623924255,
+      "eval_runtime": 27.2979,
+      "eval_samples_per_second": 109.898,
+      "eval_steps_per_second": 13.737,
+      "step": 375
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 8.783783783783785e-06,
+      "loss": 0.2913,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.991,
+      "eval_loss": 0.06188898906111717,
+      "eval_runtime": 27.1425,
+      "eval_samples_per_second": 110.528,
+      "eval_steps_per_second": 13.816,
+      "step": 750
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 7.4324324324324324e-06,
+      "loss": 0.045,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9883333333333333,
+      "eval_loss": 0.05572636052966118,
+      "eval_runtime": 26.8966,
+      "eval_samples_per_second": 111.538,
+      "eval_steps_per_second": 13.942,
+      "step": 1125
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6.081081081081082e-06,
+      "loss": 0.0264,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.991,
+      "eval_loss": 0.04708857834339142,
+      "eval_runtime": 26.8084,
+      "eval_samples_per_second": 111.905,
+      "eval_steps_per_second": 13.988,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9903333333333333,
+      "eval_loss": 0.0462254174053669,
+      "eval_runtime": 27.0947,
+      "eval_samples_per_second": 110.723,
+      "eval_steps_per_second": 13.84,
+      "step": 1875
+    },
+    {
+      "epoch": 5.33,
+      "learning_rate": 4.72972972972973e-06,
+      "loss": 0.0202,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9913333333333333,
+      "eval_loss": 0.04317467287182808,
+      "eval_runtime": 26.9525,
+      "eval_samples_per_second": 111.307,
+      "eval_steps_per_second": 13.913,
+      "step": 2250
+    },
+    {
+      "epoch": 6.67,
+      "learning_rate": 3.3783783783783788e-06,
+      "loss": 0.0137,
+      "step": 2500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9903333333333333,
+      "eval_loss": 0.04381159320473671,
+      "eval_runtime": 27.1278,
+      "eval_samples_per_second": 110.588,
+      "eval_steps_per_second": 13.823,
+      "step": 2625
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2.0270270270270273e-06,
+      "loss": 0.0113,
+      "step": 3000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9903333333333333,
+      "eval_loss": 0.0411774106323719,
+      "eval_runtime": 27.0085,
+      "eval_samples_per_second": 111.076,
+      "eval_steps_per_second": 13.885,
+      "step": 3000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9906666666666667,
+      "eval_loss": 0.04207724705338478,
+      "eval_runtime": 27.4798,
+      "eval_samples_per_second": 109.171,
+      "eval_steps_per_second": 13.646,
+      "step": 3375
+    },
+    {
+      "epoch": 9.33,
+      "learning_rate": 6.756756756756758e-07,
+      "loss": 0.0092,
+      "step": 3500
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9906666666666667,
+      "eval_loss": 0.04055546224117279,
+      "eval_runtime": 26.9342,
+      "eval_samples_per_second": 111.382,
+      "eval_steps_per_second": 13.923,
+      "step": 3750
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3750,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 9.29912209809408e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3750/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1731fb814b8cdfc420e4112616dd22ae598902c61f632cc74a00d6a64b9f8d70
+size 4027

config.json

@@ -0,0 +1,34 @@
+{
+  "_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": "Sandal",
+    "1": "Boot",
+    "2": "Shoe"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Boot": 1,
+    "Sandal": 0,
+    "Shoe": 2
+  },
+  "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": "4.33.0"
+}

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
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94999e3ffc5bd040ff741799719ff28cb66f4d929cb49d2456fd90a107429e69
+size 343271789

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1731fb814b8cdfc420e4112616dd22ae598902c61f632cc74a00d6a64b9f8d70
+size 4027