---
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: vit-base-kidney-stone-Jonathan_El-Beze_-w256_1k_v1-_SUR
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: imagefolder
      type: imagefolder
      config: default
      split: test
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.9075
    - name: Precision
      type: precision
      value: 0.9136222146251665
    - name: Recall
      type: recall
      value: 0.9075
    - name: F1
      type: f1
      value: 0.904614447173649
---

<!-- 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-kidney-stone-Jonathan_El-Beze_-w256_1k_v1-_SUR

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 imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4946
- Accuracy: 0.9075
- Precision: 0.9136
- Recall: 0.9075
- F1: 0.9046

## 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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
|:-------------:|:-------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.2895        | 0.6667  | 100  | 0.5586          | 0.795    | 0.8452    | 0.795  | 0.7997 |
| 0.0848        | 1.3333  | 200  | 0.8609          | 0.7975   | 0.8401    | 0.7975 | 0.7883 |
| 0.0782        | 2.0     | 300  | 0.7032          | 0.81     | 0.8414    | 0.81   | 0.8116 |
| 0.0158        | 2.6667  | 400  | 0.7198          | 0.8342   | 0.8570    | 0.8342 | 0.8336 |
| 0.0327        | 3.3333  | 500  | 0.7624          | 0.8458   | 0.8484    | 0.8458 | 0.8448 |
| 0.0044        | 4.0     | 600  | 0.6172          | 0.8792   | 0.8926    | 0.8792 | 0.8769 |
| 0.0032        | 4.6667  | 700  | 0.7772          | 0.8517   | 0.8589    | 0.8517 | 0.8496 |
| 0.0026        | 5.3333  | 800  | 0.8897          | 0.8375   | 0.8478    | 0.8375 | 0.8351 |
| 0.0033        | 6.0     | 900  | 0.4946          | 0.9075   | 0.9136    | 0.9075 | 0.9046 |
| 0.0019        | 6.6667  | 1000 | 0.6971          | 0.8725   | 0.8727    | 0.8725 | 0.8716 |
| 0.0016        | 7.3333  | 1100 | 0.7355          | 0.8692   | 0.8711    | 0.8692 | 0.8685 |
| 0.0136        | 8.0     | 1200 | 0.9004          | 0.8675   | 0.8900    | 0.8675 | 0.8613 |
| 0.0013        | 8.6667  | 1300 | 0.7646          | 0.875    | 0.8837    | 0.875  | 0.8715 |
| 0.0011        | 9.3333  | 1400 | 0.7833          | 0.875    | 0.8786    | 0.875  | 0.8729 |
| 0.0009        | 10.0    | 1500 | 0.7968          | 0.8767   | 0.8800    | 0.8767 | 0.8747 |
| 0.0009        | 10.6667 | 1600 | 0.8085          | 0.8758   | 0.8790    | 0.8758 | 0.8738 |
| 0.0008        | 11.3333 | 1700 | 0.8175          | 0.8758   | 0.8790    | 0.8758 | 0.8738 |
| 0.0008        | 12.0    | 1800 | 0.8242          | 0.8767   | 0.8801    | 0.8767 | 0.8746 |
| 0.0007        | 12.6667 | 1900 | 0.8292          | 0.8767   | 0.8801    | 0.8767 | 0.8746 |
| 0.0007        | 13.3333 | 2000 | 0.8335          | 0.8775   | 0.8812    | 0.8775 | 0.8754 |
| 0.0007        | 14.0    | 2100 | 0.8363          | 0.8775   | 0.8812    | 0.8775 | 0.8754 |
| 0.0007        | 14.6667 | 2200 | 0.8376          | 0.8775   | 0.8812    | 0.8775 | 0.8754 |


### Framework versions

- Transformers 4.48.2
- Pytorch 2.6.0+cu126
- Datasets 3.2.0
- Tokenizers 0.21.0