---
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- 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 the indian_food_images dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2313
- Accuracy: 0.9458

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.4578        | 0.3   | 100  | 0.3982          | 0.8842   |
| 0.3823        | 0.6   | 200  | 0.4436          | 0.8863   |
| 0.4317        | 0.9   | 300  | 0.4027          | 0.8820   |
| 0.3051        | 1.2   | 400  | 0.3762          | 0.8895   |
| 0.1829        | 1.5   | 500  | 0.3679          | 0.9086   |
| 0.2193        | 1.8   | 600  | 0.3046          | 0.9235   |
| 0.1673        | 2.1   | 700  | 0.3170          | 0.9224   |
| 0.2694        | 2.4   | 800  | 0.2726          | 0.9341   |
| 0.1209        | 2.7   | 900  | 0.2777          | 0.9288   |
| 0.146         | 3.0   | 1000 | 0.2415          | 0.9384   |
| 0.1515        | 3.3   | 1100 | 0.2313          | 0.9458   |
| 0.1645        | 3.6   | 1200 | 0.2394          | 0.9437   |
| 0.1142        | 3.9   | 1300 | 0.2325          | 0.9447   |


### Framework versions

- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Tokenizers 0.14.1