---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224-v20
  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. -->

# vit-base-patch16-224-v20

This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0823
- Accuracy: 0.9741

## 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: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 7

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.1733        | 1.0   | 190  | 0.2635          | 0.9185   |
| 0.1673        | 2.0   | 380  | 0.1489          | 0.9544   |
| 0.1224        | 3.0   | 570  | 0.1266          | 0.9552   |
| 0.0599        | 4.0   | 760  | 0.1134          | 0.9626   |
| 0.0322        | 5.0   | 950  | 0.1289          | 0.9581   |
| 0.0358        | 6.0   | 1140 | 0.0737          | 0.9756   |
| 0.0156        | 7.0   | 1330 | 0.0823          | 0.9741   |


### Framework versions

- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Tokenizers 0.13.3