---
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- image-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-lr-0.0001
  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-lr-0.0001

This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the skin-cancer dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5187
- Accuracy: 0.8360

## 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: 0.0001
- 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: 100
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.6008        | 0.31  | 100  | 0.5998          | 0.7836   |
| 0.5779        | 0.62  | 200  | 0.6118          | 0.7833   |
| 0.6891        | 0.93  | 300  | 0.5814          | 0.7777   |
| 0.3535        | 1.25  | 400  | 0.5594          | 0.7933   |
| 0.4055        | 1.56  | 500  | 0.5719          | 0.8135   |
| 0.2471        | 1.87  | 600  | 0.5536          | 0.7944   |
| 0.171         | 2.18  | 700  | 0.5376          | 0.8391   |
| 0.2159        | 2.49  | 800  | 0.5187          | 0.8360   |
| 0.1659        | 2.8   | 900  | 0.5849          | 0.8318   |
| 0.0554        | 3.12  | 1000 | 0.5457          | 0.8544   |
| 0.1125        | 3.43  | 1100 | 0.7324          | 0.8318   |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2