Model save

README.md

@@ -0,0 +1,79 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+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: 0.2293
+- Accuracy: 0.9405
+- Precision: 0.9395
+- Recall: 0.9420
+- F1: 0.9402
+
+## 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 | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.8589        | 0.3   | 100  | 0.5618          | 0.8714   | 0.8981    | 0.8620 | 0.8696 |
+| 0.6973        | 0.6   | 200  | 0.5544          | 0.8608   | 0.8742    | 0.8690 | 0.8630 |
+| 0.4078        | 0.9   | 300  | 0.4671          | 0.8831   | 0.8915    | 0.8840 | 0.8812 |
+| 0.3818        | 1.2   | 400  | 0.4203          | 0.8884   | 0.9017    | 0.8864 | 0.8877 |
+| 0.2262        | 1.5   | 500  | 0.3481          | 0.9107   | 0.9177    | 0.9085 | 0.9098 |
+| 0.2137        | 1.8   | 600  | 0.3761          | 0.9022   | 0.9094    | 0.9027 | 0.9026 |
+| 0.4515        | 2.1   | 700  | 0.3722          | 0.9044   | 0.9091    | 0.9041 | 0.9017 |
+| 0.3024        | 2.4   | 800  | 0.3105          | 0.9203   | 0.9198    | 0.9220 | 0.9188 |
+| 0.1748        | 2.7   | 900  | 0.2767          | 0.9288   | 0.9274    | 0.9293 | 0.9272 |
+| 0.1959        | 3.0   | 1000 | 0.2825          | 0.9256   | 0.9318    | 0.9243 | 0.9230 |
+| 0.1663        | 3.3   | 1100 | 0.2549          | 0.9341   | 0.9362    | 0.9366 | 0.9356 |
+| 0.0513        | 3.6   | 1200 | 0.2254          | 0.9416   | 0.9436    | 0.9422 | 0.9424 |
+| 0.1478        | 3.9   | 1300 | 0.2293          | 0.9405   | 0.9395    | 0.9420 | 0.9402 |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

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": "4.39.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5e836d3398a19623ddbd799d794037d33e6821c4a15c0b41602f1319b7a4e10
+size 343279344

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

runs/Apr09_19-13-47_dcd6c694ee6d/events.out.tfevents.1712690184.dcd6c694ee6d.985.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eeef3d7cd9286c5da3fa7967aa6b3f412bd09241570ac78718eb859b6e4092c
+size 7030

runs/Apr09_19-13-47_dcd6c694ee6d/events.out.tfevents.1712690267.dcd6c694ee6d.985.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e4a0912840c4fb4605e65d047c624b93134de05cb77503dafac9450bedad46e
+size 39919

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a81b835e5642bd802ff15acfcde5a7768463237f15df4a3180f27431970634cd
+size 4920