Model save

README.md

@@ -0,0 +1,74 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: finetuned-indian-food
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# finetuned-indian-food
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2259
+- Accuracy: 0.9490
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 1.0574        | 0.3003 | 100  | 0.9445          | 0.8576   |
+| 0.8399        | 0.6006 | 200  | 0.5542          | 0.8863   |
+| 0.6418        | 0.9009 | 300  | 0.5741          | 0.8672   |
+| 0.3785        | 1.2012 | 400  | 0.4702          | 0.8842   |
+| 0.4451        | 1.5015 | 500  | 0.3685          | 0.9118   |
+| 0.4535        | 1.8018 | 600  | 0.3781          | 0.9097   |
+| 0.4618        | 2.1021 | 700  | 0.3000          | 0.9288   |
+| 0.2321        | 2.4024 | 800  | 0.3146          | 0.9182   |
+| 0.1816        | 2.7027 | 900  | 0.3045          | 0.9214   |
+| 0.2332        | 3.0030 | 1000 | 0.3446          | 0.9044   |
+| 0.1173        | 3.3033 | 1100 | 0.2381          | 0.9416   |
+| 0.2694        | 3.6036 | 1200 | 0.2146          | 0.9426   |
+| 0.1227        | 3.9039 | 1300 | 0.2259          | 0.9490   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,68 @@
+{
+  "_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": "butter_naan",
+    "10": "kaathi_rolls",
+    "11": "kadai_paneer",
+    "12": "kulfi",
+    "13": "masala_dosa",
+    "14": "momos",
+    "15": "paani_puri",
+    "16": "pakode",
+    "17": "pav_bhaji",
+    "18": "pizza",
+    "19": "samosa",
+    "2": "chai",
+    "3": "chapati",
+    "4": "chole_bhature",
+    "5": "dal_makhani",
+    "6": "dhokla",
+    "7": "fried_rice",
+    "8": "idli",
+    "9": "jalebi"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "burger": "0",
+    "butter_naan": "1",
+    "chai": "2",
+    "chapati": "3",
+    "chole_bhature": "4",
+    "dal_makhani": "5",
+    "dhokla": "6",
+    "fried_rice": "7",
+    "idli": "8",
+    "jalebi": "9",
+    "kaathi_rolls": "10",
+    "kadai_paneer": "11",
+    "kulfi": "12",
+    "masala_dosa": "13",
+    "momos": "14",
+    "paani_puri": "15",
+    "pakode": "16",
+    "pav_bhaji": "17",
+    "pizza": "18",
+    "samosa": "19"
+  },
+  "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": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad0fa315798f747ad8e0c49eba13519e5c47139b3970bd16f429917d66ae7322
+size 343279344

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": "ViTFeatureExtractor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/Oct17_14-21-43_609077bf8eb4/events.out.tfevents.1729174930.609077bf8eb4.269.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6fce82769cc59ae7e06fbb9af45aa92c4a9d2b0458a276b1927761a74a07253
+size 38246

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10d23a19b6e4356ac3aa61cf5b339942670d55c583709f81b10e445dc02ae272
+size 5176