---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
datasets:
- medmnist-v2
metrics:
- accuracy
- precision
- recall
- f1
base_model: microsoft/swin-large-patch4-window7-224-in22k
model-index:
- name: derma-swin-large-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-swin-large-finetuned

This model is a fine-tuned version of [microsoft/swin-large-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-large-patch4-window7-224-in22k) on the medmnist-v2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5530
- Accuracy: 0.7875
- Precision: 0.6308
- Recall: 0.6101
- F1: 0.6150

## 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     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.8516        | 1.0   | 109  | 0.7470          | 0.7547   | 0.5456    | 0.3914 | 0.4188 |
| 0.7738        | 2.0   | 219  | 0.8953          | 0.7168   | 0.4225    | 0.4459 | 0.3577 |
| 0.6994        | 3.0   | 328  | 0.6593          | 0.7607   | 0.6257    | 0.5059 | 0.5105 |
| 0.6731        | 4.0   | 438  | 0.6145          | 0.7717   | 0.6322    | 0.5001 | 0.5383 |
| 0.7266        | 5.0   | 547  | 0.6839          | 0.7398   | 0.5520    | 0.5344 | 0.4935 |
| 0.6388        | 6.0   | 657  | 0.6243          | 0.7667   | 0.6117    | 0.5063 | 0.5338 |
| 0.6495        | 7.0   | 766  | 0.6161          | 0.7827   | 0.6357    | 0.6153 | 0.6163 |
| 0.5639        | 8.0   | 876  | 0.5752          | 0.7836   | 0.6018    | 0.5912 | 0.5931 |
| 0.6012        | 9.0   | 985  | 0.5508          | 0.7926   | 0.6303    | 0.6195 | 0.6176 |
| 0.5468        | 9.95  | 1090 | 0.5665          | 0.7856   | 0.6470    | 0.6288 | 0.6355 |


### Framework versions

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