---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
datasets:
- medmnist-v2
metrics:
- accuracy
- precision
- recall
- f1
base_model: microsoft/beit-base-patch16-224-pt22k-ft22k
model-index:
- name: organc-beit-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. -->

# organc-beit-base-finetuned

This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on the medmnist-v2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2503
- Accuracy: 0.9256
- Precision: 0.9228
- Recall: 0.9137
- F1: 0.9175

## 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     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.8262        | 1.0   | 203  | 0.2666          | 0.8867   | 0.9002    | 0.8322 | 0.8260 |
| 0.6431        | 2.0   | 406  | 0.1514          | 0.9536   | 0.9486    | 0.9377 | 0.9397 |
| 0.6986        | 3.0   | 609  | 0.1179          | 0.9766   | 0.9710    | 0.9769 | 0.9730 |
| 0.5797        | 4.0   | 813  | 0.1045          | 0.9766   | 0.9756    | 0.9768 | 0.9758 |
| 0.5475        | 5.0   | 1016 | 0.1281          | 0.9707   | 0.9677    | 0.9662 | 0.9659 |
| 0.5518        | 6.0   | 1219 | 0.0765          | 0.9833   | 0.9791    | 0.9842 | 0.9813 |
| 0.5167        | 7.0   | 1422 | 0.1065          | 0.9724   | 0.9785    | 0.9701 | 0.9735 |
| 0.4417        | 8.0   | 1626 | 0.1027          | 0.9824   | 0.9848    | 0.9834 | 0.9837 |
| 0.3555        | 9.0   | 1829 | 0.1286          | 0.9774   | 0.9838    | 0.9778 | 0.9803 |
| 0.3552        | 9.99  | 2030 | 0.1046          | 0.9845   | 0.9882    | 0.9857 | 0.9867 |


### Framework versions

- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2