Upload folder using huggingface_hub

checkpoint-5000/config.json

@@ -0,0 +1,48 @@
+{
+  "_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": "Burger",
+    "1": "Taco",
+    "2": "Baked Potato",
+    "3": "Hot Dog",
+    "4": "Pizza",
+    "5": "Sandwich",
+    "6": "Fries",
+    "7": "Donut",
+    "8": "Crispy Chicken",
+    "9": "Taquito"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Baked Potato": 2,
+    "Burger": 0,
+    "Crispy Chicken": 8,
+    "Donut": 7,
+    "Fries": 6,
+    "Hot Dog": 3,
+    "Pizza": 4,
+    "Sandwich": 5,
+    "Taco": 1,
+    "Taquito": 9
+  },
+  "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": "4.33.2"
+}

checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79cabe25aabed5d2fc2a9578e2309933223dc9aa251d1b0d552c4522e3ec78dd
+size 686617605

checkpoint-5000/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-5000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1861be2c1459c490e39271029afaca618a5b946ee516c67945e01d04ad6a52a2
+size 343293293

checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20d5431a9ae8bcb1ac6f0ecaaa1962bc68e8dfc3446a54269cfefd1b5c97006b
+size 14575

checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c69d779c30098c55eeeefef22b9e5b75c82c732144663189aae67506842585
+size 627

checkpoint-5000/trainer_state.json

@@ -0,0 +1,169 @@
+{
+  "best_metric": 0.22449803352355957,
+  "best_model_checkpoint": "fast_food_image_detection/checkpoint-5000",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 1.3913,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9303781617831205,
+      "eval_loss": 0.7382929921150208,
+      "eval_runtime": 40.7321,
+      "eval_samples_per_second": 98.031,
+      "eval_steps_per_second": 12.275,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8.08080808080808e-06,
+      "loss": 0.5444,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9421487603305785,
+      "eval_loss": 0.43648549914360046,
+      "eval_runtime": 40.3547,
+      "eval_samples_per_second": 98.948,
+      "eval_steps_per_second": 12.39,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7.070707070707071e-06,
+      "loss": 0.3594,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9479088404708239,
+      "eval_loss": 0.3400455117225647,
+      "eval_runtime": 40.1894,
+      "eval_samples_per_second": 99.354,
+      "eval_steps_per_second": 12.441,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6.060606060606061e-06,
+      "loss": 0.2776,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9484097170047583,
+      "eval_loss": 0.29507216811180115,
+      "eval_runtime": 39.7658,
+      "eval_samples_per_second": 100.413,
+      "eval_steps_per_second": 12.574,
+      "step": 2000
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 5.0505050505050515e-06,
+      "loss": 0.224,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.946656649135988,
+      "eval_loss": 0.2646792232990265,
+      "eval_runtime": 40.4198,
+      "eval_samples_per_second": 98.788,
+      "eval_steps_per_second": 12.37,
+      "step": 2500
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.04040404040404e-06,
+      "loss": 0.1861,
+      "step": 3000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9481592787377912,
+      "eval_loss": 0.24941706657409668,
+      "eval_runtime": 40.2727,
+      "eval_samples_per_second": 99.149,
+      "eval_steps_per_second": 12.415,
+      "step": 3000
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3.0303030303030305e-06,
+      "loss": 0.1594,
+      "step": 3500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.949411470072627,
+      "eval_loss": 0.2370135486125946,
+      "eval_runtime": 39.9648,
+      "eval_samples_per_second": 99.913,
+      "eval_steps_per_second": 12.511,
+      "step": 3500
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2.02020202020202e-06,
+      "loss": 0.1421,
+      "step": 4000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9499123466065614,
+      "eval_loss": 0.23112499713897705,
+      "eval_runtime": 39.8312,
+      "eval_samples_per_second": 100.248,
+      "eval_steps_per_second": 12.553,
+      "step": 4000
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 1.01010101010101e-06,
+      "loss": 0.1306,
+      "step": 4500
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9511645379413974,
+      "eval_loss": 0.22468866407871246,
+      "eval_runtime": 39.7602,
+      "eval_samples_per_second": 100.427,
+      "eval_steps_per_second": 12.575,
+      "step": 4500
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.1218,
+      "step": 5000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9506636614074631,
+      "eval_loss": 0.22449803352355957,
+      "eval_runtime": 39.6963,
+      "eval_samples_per_second": 100.589,
+      "eval_steps_per_second": 12.596,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5000,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.2376358080889242e+19,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc571c7d815ec521e54b5b3d97a0ec0ea1da172ed008cd3674264e66c861caff
+size 4027

config.json

@@ -0,0 +1,48 @@
+{
+  "_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": "Burger",
+    "1": "Taco",
+    "2": "Baked Potato",
+    "3": "Hot Dog",
+    "4": "Pizza",
+    "5": "Sandwich",
+    "6": "Fries",
+    "7": "Donut",
+    "8": "Crispy Chicken",
+    "9": "Taquito"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Baked Potato": 2,
+    "Burger": 0,
+    "Crispy Chicken": 8,
+    "Donut": 7,
+    "Fries": 6,
+    "Hot Dog": 3,
+    "Pizza": 4,
+    "Sandwich": 5,
+    "Taco": 1,
+    "Taquito": 9
+  },
+  "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": "4.33.2"
+}

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 sha256:1861be2c1459c490e39271029afaca618a5b946ee516c67945e01d04ad6a52a2
+size 343293293

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc571c7d815ec521e54b5b3d97a0ec0ea1da172ed008cd3674264e66c861caff
+size 4027