Model save

README.md

@@ -0,0 +1,72 @@
+---
+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: 0.2534
+- Accuracy: 0.9330
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.5271        | 0.3   | 100  | 1.2775          | 0.7853   |
+| 0.8635        | 0.6   | 200  | 0.7137          | 0.8746   |
+| 0.6744        | 0.9   | 300  | 0.6281          | 0.8417   |
+| 0.4637        | 1.2   | 400  | 0.4672          | 0.8820   |
+| 0.4562        | 1.5   | 500  | 0.4433          | 0.8916   |
+| 0.456         | 1.8   | 600  | 0.3822          | 0.9054   |
+| 0.2996        | 2.1   | 700  | 0.3619          | 0.9150   |
+| 0.3554        | 2.4   | 800  | 0.3226          | 0.9245   |
+| 0.3111        | 2.7   | 900  | 0.3341          | 0.9192   |
+| 0.2667        | 3.0   | 1000 | 0.2828          | 0.9341   |
+| 0.2442        | 3.3   | 1100 | 0.2733          | 0.9299   |
+| 0.216         | 3.6   | 1200 | 0.2690          | 0.9288   |
+| 0.2237        | 3.9   | 1300 | 0.2534          | 0.9330   |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0+cu118
+- Tokenizers 0.14.1

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": "4.35.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08664dc3fa480859668b46bb6fb7cc8117fd357670ddc085d4243cd82db36c8d
+size 343279344

preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "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": 224
+}

runs/Nov03_08-11-17_b84efab5ccd4/events.out.tfevents.1698999157.b84efab5ccd4.190.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c195c4a790501a4a3b14978d2a0612bfa2b214b314526b047189cad2c6baed5
+size 30382

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bcc34aecaf3233855f62c731bab0beb9c7f18217f6a80416d1dfd436680e29c
+size 4536