---
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-fake-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-fake-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: 0.3455
- Accuracy: 0.8541

## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 2000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| 0.5416        | 0.1264 | 100  | 0.5593          | 0.7081   |
| 0.5299        | 0.2528 | 200  | 0.5342          | 0.7422   |
| 0.5503        | 0.3793 | 300  | 0.4875          | 0.7717   |
| 0.5561        | 0.5057 | 400  | 0.4622          | 0.7941   |
| 0.5581        | 0.6321 | 500  | 0.5501          | 0.7457   |
| 0.5845        | 0.7585 | 600  | 0.5088          | 0.7475   |
| 0.5695        | 0.8850 | 700  | 0.4740          | 0.7860   |
| 0.5406        | 1.0114 | 800  | 0.4856          | 0.7816   |
| 0.5353        | 1.1378 | 900  | 0.4252          | 0.8156   |
| 0.5345        | 1.2642 | 1000 | 0.5014          | 0.7762   |
| 0.5105        | 1.3906 | 1100 | 0.4800          | 0.7860   |
| 0.5266        | 1.5171 | 1200 | 0.4618          | 0.7959   |
| 0.4709        | 1.6435 | 1300 | 0.3906          | 0.8281   |
| 0.4624        | 1.7699 | 1400 | 0.4208          | 0.8129   |
| 0.4677        | 1.8963 | 1500 | 0.4207          | 0.8174   |
| 0.4478        | 2.0228 | 1600 | 0.3557          | 0.8478   |
| 0.4451        | 2.1492 | 1700 | 0.3546          | 0.8442   |
| 0.3796        | 2.2756 | 1800 | 0.3199          | 0.8720   |
| 0.4358        | 2.4020 | 1900 | 0.3308          | 0.8603   |
| 0.3373        | 2.5284 | 2000 | 0.3455          | 0.8541   |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1