README.md

---
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- generated_from_trainer
metrics:
- accuracy
- recall
- f1
- precision
model-index:
- name: vit-base-16-thesis-demo-ISIC-multi-class
  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-16-thesis-demo-ISIC-multi-class

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 ahishamm/isic_enhanced_dec_balanced dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0906
- Accuracy: 0.9748
- Recall: 0.9748
- F1: 0.9748
- Precision: 0.9748

## 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 | Recall | F1     | Precision |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|
| 0.575         | 0.98  | 50   | 0.4132          | 0.8491   | 0.8491 | 0.8491 | 0.8491    |
| 0.2771        | 1.96  | 100  | 0.2329          | 0.9182   | 0.9182 | 0.9182 | 0.9182    |
| 0.1703        | 2.94  | 150  | 0.1821          | 0.9497   | 0.9497 | 0.9497 | 0.9497    |
| 0.1186        | 3.92  | 200  | 0.0906          | 0.9748   | 0.9748 | 0.9748 | 0.9748    |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0