---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
datasets:
- medmnist-v2
metrics:
- accuracy
- precision
- recall
- f1
base_model: google/vit-base-patch16-224-in21k
model-index:
- name: derma-vit-base-finetuned
  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. -->

# derma-vit-base-finetuned

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 medmnist-v2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6135
- Accuracy: 0.7681
- Precision: 0.6821
- Recall: 0.5061
- F1: 0.5497

## 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: 0.005
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.7579        | 1.0   | 109  | 0.7045          | 0.7428   | 0.5204    | 0.3710 | 0.3927 |
| 0.7689        | 2.0   | 219  | 0.7512          | 0.7278   | 0.3964    | 0.3527 | 0.3573 |
| 0.7353        | 3.0   | 328  | 0.7191          | 0.7358   | 0.4630    | 0.4202 | 0.4002 |
| 0.8429        | 4.0   | 438  | 0.7858          | 0.6810   | 0.4280    | 0.1813 | 0.1851 |
| 0.7929        | 5.0   | 547  | 0.7013          | 0.7218   | 0.5158    | 0.3971 | 0.3523 |
| 0.6804        | 6.0   | 657  | 0.6822          | 0.7607   | 0.5011    | 0.4240 | 0.4391 |
| 0.6922        | 7.0   | 766  | 0.6533          | 0.7667   | 0.6762    | 0.5106 | 0.5227 |
| 0.6563        | 8.0   | 876  | 0.6758          | 0.7468   | 0.4548    | 0.4589 | 0.4496 |
| 0.6985        | 9.0   | 985  | 0.6264          | 0.7647   | 0.6451    | 0.4692 | 0.4915 |
| 0.6283        | 9.95  | 1090 | 0.6179          | 0.7677   | 0.5889    | 0.4796 | 0.5088 |


### Framework versions

- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2