Upload folder using huggingface_hub

checkpoint-1134/config.json

@@ -0,0 +1,32 @@
+{
+  "_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": "Baked Potato",
+    "1": "apple_pie"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Baked Potato": 0,
+    "apple_pie": 1
+  },
+  "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": "4.39.3"
+}

checkpoint-1134/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbe39dcd263362bba4aaec0247d070dfb7a9e1f8a39153b9b1983a379bb338b6
+size 343223968

checkpoint-1134/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a3742d91589a908750900fcadd6f1843c893a048e0e879040c4d694696ae58
+size 686568890

checkpoint-1134/preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "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-1134/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb4ab47388e87a7a9d8c510bcef311754c44d9dfd2b9c6daa5e2f66536255819
+size 14244

checkpoint-1134/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b5274038c1c81dbd1e8d3487cc376601f6040cc942326ac99d0c8f7f401cba1
+size 1064

checkpoint-1134/trainer_state.json

@@ -0,0 +1,197 @@
+{
+  "best_metric": 0.016031978651881218,
+  "best_model_checkpoint": "food_type_image_detection/checkpoint-1134",
+  "epoch": 18.0,
+  "eval_steps": 500,
+  "global_step": 1134,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.922,
+      "eval_loss": 0.4003147482872009,
+      "eval_runtime": 7.0601,
+      "eval_samples_per_second": 70.821,
+      "eval_steps_per_second": 8.923,
+      "step": 63
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.994,
+      "eval_loss": 0.10429825633764267,
+      "eval_runtime": 7.8197,
+      "eval_samples_per_second": 63.941,
+      "eval_steps_per_second": 8.057,
+      "step": 126
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.04940691217780113,
+      "eval_runtime": 7.0131,
+      "eval_samples_per_second": 71.295,
+      "eval_steps_per_second": 8.983,
+      "step": 189
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.998,
+      "eval_loss": 0.0376136340200901,
+      "eval_runtime": 6.8409,
+      "eval_samples_per_second": 73.09,
+      "eval_steps_per_second": 9.209,
+      "step": 252
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.998,
+      "eval_loss": 0.026698309928178787,
+      "eval_runtime": 6.8225,
+      "eval_samples_per_second": 73.287,
+      "eval_steps_per_second": 9.234,
+      "step": 315
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.998,
+      "eval_loss": 0.0241855401545763,
+      "eval_runtime": 6.9508,
+      "eval_samples_per_second": 71.935,
+      "eval_steps_per_second": 9.064,
+      "step": 378
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.998,
+      "eval_loss": 0.021219629794359207,
+      "eval_runtime": 6.7881,
+      "eval_samples_per_second": 73.659,
+      "eval_steps_per_second": 9.281,
+      "step": 441
+    },
+    {
+      "epoch": 7.94,
+      "grad_norm": 0.11136417835950851,
+      "learning_rate": 6.280991735537191e-06,
+      "loss": 0.1249,
+      "step": 500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.998,
+      "eval_loss": 0.019916247576475143,
+      "eval_runtime": 6.9679,
+      "eval_samples_per_second": 71.758,
+      "eval_steps_per_second": 9.042,
+      "step": 504
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.998,
+      "eval_loss": 0.018674828112125397,
+      "eval_runtime": 6.8471,
+      "eval_samples_per_second": 73.024,
+      "eval_steps_per_second": 9.201,
+      "step": 567
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.998,
+      "eval_loss": 0.017811430618166924,
+      "eval_runtime": 6.9477,
+      "eval_samples_per_second": 71.966,
+      "eval_steps_per_second": 9.068,
+      "step": 630
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.998,
+      "eval_loss": 0.01752582937479019,
+      "eval_runtime": 6.795,
+      "eval_samples_per_second": 73.583,
+      "eval_steps_per_second": 9.271,
+      "step": 693
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.998,
+      "eval_loss": 0.018632877618074417,
+      "eval_runtime": 6.9342,
+      "eval_samples_per_second": 72.107,
+      "eval_steps_per_second": 9.085,
+      "step": 756
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.998,
+      "eval_loss": 0.017416154965758324,
+      "eval_runtime": 6.9918,
+      "eval_samples_per_second": 71.512,
+      "eval_steps_per_second": 9.01,
+      "step": 819
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.998,
+      "eval_loss": 0.01664608344435692,
+      "eval_runtime": 6.7746,
+      "eval_samples_per_second": 73.805,
+      "eval_steps_per_second": 9.299,
+      "step": 882
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.998,
+      "eval_loss": 0.01622740924358368,
+      "eval_runtime": 6.9095,
+      "eval_samples_per_second": 72.364,
+      "eval_steps_per_second": 9.118,
+      "step": 945
+    },
+    {
+      "epoch": 15.87,
+      "grad_norm": 0.07710539549589157,
+      "learning_rate": 2.1487603305785124e-06,
+      "loss": 0.0115,
+      "step": 1000
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.998,
+      "eval_loss": 0.016459915786981583,
+      "eval_runtime": 6.744,
+      "eval_samples_per_second": 74.14,
+      "eval_steps_per_second": 9.342,
+      "step": 1008
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.998,
+      "eval_loss": 0.01649099588394165,
+      "eval_runtime": 6.8523,
+      "eval_samples_per_second": 72.968,
+      "eval_steps_per_second": 9.194,
+      "step": 1071
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.998,
+      "eval_loss": 0.016031978651881218,
+      "eval_runtime": 6.9894,
+      "eval_samples_per_second": 71.537,
+      "eval_steps_per_second": 9.014,
+      "step": 1134
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1260,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 2.789711626125312e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1134/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6650882927ec3600b36a44f3745d63dc84e8699f59d5ce1f6c4aead7d5590226
+size 4920

config.json

@@ -0,0 +1,32 @@
+{
+  "_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": "Baked Potato",
+    "1": "apple_pie"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Baked Potato": 0,
+    "apple_pie": 1
+  },
+  "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": "4.39.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbe39dcd263362bba4aaec0247d070dfb7a9e1f8a39153b9b1983a379bb338b6
+size 343223968

preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "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
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6650882927ec3600b36a44f3745d63dc84e8699f59d5ce1f6c4aead7d5590226
+size 4920