Upload folder using huggingface_hub

checkpoint-5124/config.json

@@ -0,0 +1,38 @@
+{
+  "_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": "Clog",
+    "1": "Brogue",
+    "2": "Sneaker",
+    "3": "Boat",
+    "4": "Ballet Flat"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Ballet Flat": 4,
+    "Boat": 3,
+    "Brogue": 1,
+    "Clog": 0,
+    "Sneaker": 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": "4.34.0"
+}

checkpoint-5124/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d45d0c5eeecea1f9741546b5d9df8e3f8924032ea08c55a9d7b64d3ca02b621
+size 686586885

checkpoint-5124/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-5124/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3071ca7b7b21f4709445e66d31efeceefb2ce908b64897c2853526d9b3e88fde
+size 343277933

checkpoint-5124/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4ded1914bae63de9093c94bdbad5d2576276222d7c50fce8cb3d6d1343f0953
+size 14575

checkpoint-5124/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aac1eab6852720eba06ae4e4117546f008df35335f75fdd7087395736177bb68
+size 627

checkpoint-5124/trainer_state.json

@@ -0,0 +1,205 @@
+{
+  "best_metric": 0.25261345505714417,
+  "best_model_checkpoint": "shoe_types_image_detection/checkpoint-5124",
+  "epoch": 14.0,
+  "eval_steps": 500,
+  "global_step": 5124,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8854309165526676,
+      "eval_loss": 0.6547091603279114,
+      "eval_runtime": 27.6336,
+      "eval_samples_per_second": 105.813,
+      "eval_steps_per_second": 13.245,
+      "step": 366
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 9.381017881705642e-06,
+      "loss": 0.929,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9069767441860465,
+      "eval_loss": 0.4280058741569519,
+      "eval_runtime": 27.286,
+      "eval_samples_per_second": 107.161,
+      "eval_steps_per_second": 13.413,
+      "step": 732
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 8.693259972489685e-06,
+      "loss": 0.3895,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9107387140902873,
+      "eval_loss": 0.3549589216709137,
+      "eval_runtime": 27.3324,
+      "eval_samples_per_second": 106.979,
+      "eval_steps_per_second": 13.391,
+      "step": 1098
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9227086183310533,
+      "eval_loss": 0.3061801791191101,
+      "eval_runtime": 27.1582,
+      "eval_samples_per_second": 107.665,
+      "eval_steps_per_second": 13.477,
+      "step": 1464
+    },
+    {
+      "epoch": 4.1,
+      "learning_rate": 8.005502063273727e-06,
+      "loss": 0.27,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9254445964432284,
+      "eval_loss": 0.2837773859500885,
+      "eval_runtime": 27.4061,
+      "eval_samples_per_second": 106.691,
+      "eval_steps_per_second": 13.355,
+      "step": 1830
+    },
+    {
+      "epoch": 5.46,
+      "learning_rate": 7.317744154057772e-06,
+      "loss": 0.209,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9271545827633378,
+      "eval_loss": 0.2699655592441559,
+      "eval_runtime": 27.4513,
+      "eval_samples_per_second": 106.516,
+      "eval_steps_per_second": 13.333,
+      "step": 2196
+    },
+    {
+      "epoch": 6.83,
+      "learning_rate": 6.629986244841816e-06,
+      "loss": 0.1763,
+      "step": 2500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9305745554035568,
+      "eval_loss": 0.2672628164291382,
+      "eval_runtime": 27.1946,
+      "eval_samples_per_second": 107.521,
+      "eval_steps_per_second": 13.459,
+      "step": 2562
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.93296853625171,
+      "eval_loss": 0.2592753767967224,
+      "eval_runtime": 27.3382,
+      "eval_samples_per_second": 106.957,
+      "eval_steps_per_second": 13.388,
+      "step": 2928
+    },
+    {
+      "epoch": 8.2,
+      "learning_rate": 5.94222833562586e-06,
+      "loss": 0.1361,
+      "step": 3000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9302325581395349,
+      "eval_loss": 0.25665760040283203,
+      "eval_runtime": 27.3467,
+      "eval_samples_per_second": 106.923,
+      "eval_steps_per_second": 13.384,
+      "step": 3294
+    },
+    {
+      "epoch": 9.56,
+      "learning_rate": 5.254470426409904e-06,
+      "loss": 0.1161,
+      "step": 3500
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9309165526675787,
+      "eval_loss": 0.2541131377220154,
+      "eval_runtime": 26.9744,
+      "eval_samples_per_second": 108.399,
+      "eval_steps_per_second": 13.568,
+      "step": 3660
+    },
+    {
+      "epoch": 10.93,
+      "learning_rate": 4.566712517193948e-06,
+      "loss": 0.1078,
+      "step": 4000
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.9326265389876881,
+      "eval_loss": 0.2612890899181366,
+      "eval_runtime": 26.9243,
+      "eval_samples_per_second": 108.601,
+      "eval_steps_per_second": 13.594,
+      "step": 4026
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.9333105335157319,
+      "eval_loss": 0.2545783817768097,
+      "eval_runtime": 26.9713,
+      "eval_samples_per_second": 108.412,
+      "eval_steps_per_second": 13.57,
+      "step": 4392
+    },
+    {
+      "epoch": 12.3,
+      "learning_rate": 3.8789546079779925e-06,
+      "loss": 0.0866,
+      "step": 4500
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.93296853625171,
+      "eval_loss": 0.2556893825531006,
+      "eval_runtime": 27.4119,
+      "eval_samples_per_second": 106.669,
+      "eval_steps_per_second": 13.352,
+      "step": 4758
+    },
+    {
+      "epoch": 13.66,
+      "learning_rate": 3.191196698762036e-06,
+      "loss": 0.0704,
+      "step": 5000
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.93296853625171,
+      "eval_loss": 0.25261345505714417,
+      "eval_runtime": 27.2484,
+      "eval_samples_per_second": 107.309,
+      "eval_steps_per_second": 13.432,
+      "step": 5124
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7320,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 1.268918952585442e+19,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5124/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e790ca92b29bfbfe248615f5f1f9eba04eba294942b1497ecdadaec61f08257
+size 4027

config.json

@@ -0,0 +1,38 @@
+{
+  "_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": "Clog",
+    "1": "Brogue",
+    "2": "Sneaker",
+    "3": "Boat",
+    "4": "Ballet Flat"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Ballet Flat": 4,
+    "Boat": 3,
+    "Brogue": 1,
+    "Clog": 0,
+    "Sneaker": 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": "4.34.0"
+}

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 sha256:3071ca7b7b21f4709445e66d31efeceefb2ce908b64897c2853526d9b3e88fde
+size 343277933

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e790ca92b29bfbfe248615f5f1f9eba04eba294942b1497ecdadaec61f08257
+size 4027