Upload folder using huggingface_hub

checkpoint-2500/config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "dima806/fast_food_image_detection",
+  "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": "4.38.2"
+}

checkpoint-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e449fb2047c493850c63944ec78f69d53e056aa68e76b08e2a825fb3828e9bd1
+size 343248584

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c07703279b80c0c3373a4a381a0b68ffcd61a7bac35f55bf1b16f4f73b12891e
+size 686617605

checkpoint-2500/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-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78111858a949b75b1440bbba6d9bdb3f55762aa2fcf3e465dbdcdc42be57a290
+size 14575

checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:580423f007d6dc6795f171a7af04cb8adc879b55c3b16bc635ee8497e361256f
+size 627

checkpoint-2500/trainer_state.json

@@ -0,0 +1,101 @@
+{
+  "best_metric": 0.13462364673614502,
+  "best_model_checkpoint": "fast_food_image_detection/checkpoint-2500",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.28725844621658325,
+      "learning_rate": 1.6326530612244897e-06,
+      "loss": 0.225,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9757074881041823,
+      "eval_loss": 0.14208008348941803,
+      "eval_runtime": 39.2448,
+      "eval_samples_per_second": 101.746,
+      "eval_steps_per_second": 12.741,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.3262328803539276,
+      "learning_rate": 1.2244897959183673e-06,
+      "loss": 0.2101,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9769596794390183,
+      "eval_loss": 0.13922728598117828,
+      "eval_runtime": 38.0806,
+      "eval_samples_per_second": 104.856,
+      "eval_steps_per_second": 13.13,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.27534928917884827,
+      "learning_rate": 8.163265306122449e-07,
+      "loss": 0.1932,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9774605559729527,
+      "eval_loss": 0.1367102861404419,
+      "eval_runtime": 37.9368,
+      "eval_samples_per_second": 105.254,
+      "eval_steps_per_second": 13.18,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.9497718811035156,
+      "learning_rate": 4.0816326530612243e-07,
+      "loss": 0.1909,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9769596794390183,
+      "eval_loss": 0.13517306745052338,
+      "eval_runtime": 37.8037,
+      "eval_samples_per_second": 105.625,
+      "eval_steps_per_second": 13.226,
+      "step": 2000
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.22323879599571228,
+      "learning_rate": 0.0,
+      "loss": 0.1859,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9774605559729527,
+      "eval_loss": 0.13462364673614502,
+      "eval_runtime": 38.526,
+      "eval_samples_per_second": 103.644,
+      "eval_steps_per_second": 12.978,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 6.188179040444621e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f339c0d35d4ee4484ca0d8a29340cf2b74ada3041c946af1d48551812f5c5cdf
+size 4411

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "_name_or_path": "dima806/fast_food_image_detection",
   "architectures": [
     "ViTForImageClassification"
   ],
@@ -44,5 +44,5 @@
   "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.33.2"
+  "transformers_version": "4.38.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67f4bce159e02981d75807f4f261829df11b7dd757d18435dddda9d68aa00202
+oid sha256:e449fb2047c493850c63944ec78f69d53e056aa68e76b08e2a825fb3828e9bd1
 size 343248584

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc571c7d815ec521e54b5b3d97a0ec0ea1da172ed008cd3674264e66c861caff
-size 4027
+oid sha256:f339c0d35d4ee4484ca0d8a29340cf2b74ada3041c946af1d48551812f5c5cdf
+size 4411