---
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-4-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: 0.745
    - name: Precision
      type: precision
      value: 0.7537315160415208
    - name: Recall
      type: recall
      value: 0.745
    - name: F1
      type: f1
      value: 0.7066624397064813
---

<!-- 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-4-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: 0.6379
- Accuracy: 0.745
- Precision: 0.7537
- Recall: 0.745
- F1: 0.7067

## 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: 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     |
|:-------------:|:-------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.3911        | 0.3333  | 100  | 0.6379          | 0.745    | 0.7537    | 0.745  | 0.7067 |
| 0.2601        | 0.6667  | 200  | 1.0005          | 0.6842   | 0.7312    | 0.6842 | 0.6523 |
| 0.1349        | 1.0     | 300  | 0.6380          | 0.8533   | 0.8720    | 0.8533 | 0.8518 |
| 0.0601        | 1.3333  | 400  | 1.1014          | 0.7217   | 0.7753    | 0.7217 | 0.7044 |
| 0.2132        | 1.6667  | 500  | 0.7327          | 0.8208   | 0.8438    | 0.8208 | 0.8197 |
| 0.0894        | 2.0     | 600  | 1.4871          | 0.7083   | 0.7449    | 0.7083 | 0.6682 |
| 0.0135        | 2.3333  | 700  | 0.9952          | 0.7883   | 0.8495    | 0.7883 | 0.7799 |
| 0.0042        | 2.6667  | 800  | 0.6547          | 0.8683   | 0.8729    | 0.8683 | 0.8679 |
| 0.0037        | 3.0     | 900  | 0.7970          | 0.8367   | 0.8739    | 0.8367 | 0.8370 |
| 0.0578        | 3.3333  | 1000 | 0.8231          | 0.845    | 0.8641    | 0.845  | 0.8436 |
| 0.0019        | 3.6667  | 1100 | 0.7459          | 0.8667   | 0.8771    | 0.8667 | 0.8655 |
| 0.2931        | 4.0     | 1200 | 0.9539          | 0.8292   | 0.8349    | 0.8292 | 0.8275 |
| 0.0017        | 4.3333  | 1300 | 0.8095          | 0.8408   | 0.8607    | 0.8408 | 0.8413 |
| 0.0018        | 4.6667  | 1400 | 0.7471          | 0.865    | 0.8690    | 0.865  | 0.8629 |
| 0.0014        | 5.0     | 1500 | 1.0642          | 0.7925   | 0.8148    | 0.7925 | 0.7915 |
| 0.0012        | 5.3333  | 1600 | 0.8130          | 0.8333   | 0.8372    | 0.8333 | 0.8334 |
| 0.001         | 5.6667  | 1700 | 1.1121          | 0.8133   | 0.8222    | 0.8133 | 0.8113 |
| 0.001         | 6.0     | 1800 | 0.7986          | 0.8475   | 0.8528    | 0.8475 | 0.8492 |
| 0.0008        | 6.3333  | 1900 | 0.7908          | 0.8708   | 0.8928    | 0.8708 | 0.8718 |
| 0.0007        | 6.6667  | 2000 | 0.7444          | 0.8842   | 0.8981    | 0.8842 | 0.8818 |
| 0.0028        | 7.0     | 2100 | 0.7492          | 0.87     | 0.8749    | 0.87   | 0.8677 |
| 0.0007        | 7.3333  | 2200 | 1.5649          | 0.7433   | 0.8440    | 0.7433 | 0.7117 |
| 0.0007        | 7.6667  | 2300 | 0.8539          | 0.8492   | 0.8679    | 0.8492 | 0.8492 |
| 0.0015        | 8.0     | 2400 | 0.8743          | 0.835    | 0.8553    | 0.835  | 0.8342 |
| 0.0006        | 8.3333  | 2500 | 0.7659          | 0.8583   | 0.8608    | 0.8583 | 0.8569 |
| 0.0005        | 8.6667  | 2600 | 0.7448          | 0.8642   | 0.8681    | 0.8642 | 0.8627 |
| 0.0005        | 9.0     | 2700 | 0.7439          | 0.8683   | 0.8726    | 0.8683 | 0.8666 |
| 0.0004        | 9.3333  | 2800 | 0.7444          | 0.8742   | 0.8807    | 0.8742 | 0.8725 |
| 0.0004        | 9.6667  | 2900 | 0.7484          | 0.8725   | 0.8790    | 0.8725 | 0.8707 |
| 0.0003        | 10.0    | 3000 | 0.7491          | 0.8708   | 0.8781    | 0.8708 | 0.8691 |
| 0.0003        | 10.3333 | 3100 | 0.7509          | 0.8717   | 0.8788    | 0.8717 | 0.8699 |
| 0.0003        | 10.6667 | 3200 | 0.7539          | 0.875    | 0.8827    | 0.875  | 0.8732 |
| 0.0003        | 11.0    | 3300 | 0.7572          | 0.8775   | 0.8853    | 0.8775 | 0.8756 |
| 0.0003        | 11.3333 | 3400 | 0.7598          | 0.8783   | 0.8866    | 0.8783 | 0.8765 |
| 0.0003        | 11.6667 | 3500 | 0.7626          | 0.8792   | 0.8873    | 0.8792 | 0.8772 |
| 0.0003        | 12.0    | 3600 | 0.7655          | 0.8792   | 0.8873    | 0.8792 | 0.8772 |
| 0.0003        | 12.3333 | 3700 | 0.7682          | 0.8792   | 0.8873    | 0.8792 | 0.8772 |
| 0.0003        | 12.6667 | 3800 | 0.7699          | 0.88     | 0.8880    | 0.88   | 0.8780 |
| 0.0002        | 13.0    | 3900 | 0.7723          | 0.8808   | 0.8887    | 0.8808 | 0.8788 |
| 0.0003        | 13.3333 | 4000 | 0.7747          | 0.88     | 0.8881    | 0.88   | 0.8779 |
| 0.0003        | 13.6667 | 4100 | 0.7761          | 0.88     | 0.8881    | 0.88   | 0.8779 |
| 0.0002        | 14.0    | 4200 | 0.7771          | 0.88     | 0.8881    | 0.88   | 0.8779 |
| 0.0002        | 14.3333 | 4300 | 0.7778          | 0.88     | 0.8881    | 0.88   | 0.8779 |
| 0.0002        | 14.6667 | 4400 | 0.7785          | 0.88     | 0.8881    | 0.88   | 0.8779 |
| 0.0002        | 15.0    | 4500 | 0.7787          | 0.88     | 0.8881    | 0.88   | 0.8779 |


### Framework versions

- Transformers 4.48.2
- Pytorch 2.6.0+cu126
- Datasets 3.1.0
- Tokenizers 0.21.0