---
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-augmented
  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-augmented

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: 0.7627
- Accuracy: 0.8096

## 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: 5e-05
- 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: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.2553        | 1.0   | 240  | 1.2678          | 0.4939   |
| 0.9239        | 2.0   | 480  | 0.9428          | 0.6534   |
| 0.5559        | 3.0   | 720  | 0.8016          | 0.7161   |
| 0.303         | 4.0   | 960  | 0.7304          | 0.7509   |
| 0.1581        | 5.0   | 1200 | 0.7179          | 0.7684   |
| 0.1043        | 6.0   | 1440 | 0.6920          | 0.7911   |
| 0.0394        | 7.0   | 1680 | 0.7819          | 0.7840   |
| 0.0214        | 8.0   | 1920 | 0.7248          | 0.8047   |
| 0.0173        | 9.0   | 2160 | 0.7635          | 0.8083   |
| 0.0114        | 10.0  | 2400 | 0.7627          | 0.8096   |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Tokenizers 0.19.1