---
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-Michel_Daudon_-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: 0.8135731807031888
    - name: Precision
      type: precision
      value: 0.8642509111347894
    - name: Recall
      type: recall
      value: 0.8135731807031888
    - name: F1
      type: f1
      value: 0.8123876857104402
---

<!-- 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-Michel_Daudon_-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: 0.6804
- Accuracy: 0.8136
- Precision: 0.8643
- Recall: 0.8136
- F1: 0.8124

## 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     |
|:-------------:|:-------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.1898        | 0.3333  | 100  | 0.9163          | 0.7294   | 0.7512    | 0.7294 | 0.7288 |
| 0.2681        | 0.6667  | 200  | 0.6804          | 0.8136   | 0.8643    | 0.8136 | 0.8124 |
| 0.1036        | 1.0     | 300  | 0.9091          | 0.7939   | 0.8124    | 0.7939 | 0.7880 |
| 0.1047        | 1.3333  | 400  | 1.5065          | 0.6566   | 0.6964    | 0.6566 | 0.6685 |
| 0.0449        | 1.6667  | 500  | 0.9248          | 0.7833   | 0.7988    | 0.7833 | 0.7893 |
| 0.1781        | 2.0     | 600  | 1.1234          | 0.7621   | 0.7926    | 0.7621 | 0.7607 |
| 0.1509        | 2.3333  | 700  | 1.1867          | 0.7465   | 0.7468    | 0.7465 | 0.7396 |
| 0.1324        | 2.6667  | 800  | 1.3904          | 0.7433   | 0.7586    | 0.7433 | 0.7329 |
| 0.0037        | 3.0     | 900  | 1.3699          | 0.7408   | 0.7950    | 0.7408 | 0.7441 |
| 0.0025        | 3.3333  | 1000 | 1.2225          | 0.7433   | 0.7667    | 0.7433 | 0.7448 |
| 0.0587        | 3.6667  | 1100 | 1.4635          | 0.7244   | 0.7766    | 0.7244 | 0.7274 |
| 0.0422        | 4.0     | 1200 | 1.4949          | 0.7433   | 0.7599    | 0.7433 | 0.7398 |
| 0.0084        | 4.3333  | 1300 | 1.2363          | 0.7841   | 0.7863    | 0.7841 | 0.7788 |
| 0.0796        | 4.6667  | 1400 | 1.5322          | 0.7392   | 0.7473    | 0.7392 | 0.7419 |
| 0.003         | 5.0     | 1500 | 1.6031          | 0.7294   | 0.7752    | 0.7294 | 0.7319 |
| 0.0012        | 5.3333  | 1600 | 1.0992          | 0.8062   | 0.8066    | 0.8062 | 0.8056 |
| 0.0009        | 5.6667  | 1700 | 2.1569          | 0.6999   | 0.7144    | 0.6999 | 0.6907 |
| 0.0022        | 6.0     | 1800 | 2.2827          | 0.6312   | 0.6385    | 0.6312 | 0.6195 |
| 0.0009        | 6.3333  | 1900 | 1.8713          | 0.7089   | 0.7476    | 0.7089 | 0.6997 |
| 0.0012        | 6.6667  | 2000 | 1.9461          | 0.6983   | 0.6983    | 0.6983 | 0.6788 |
| 0.0006        | 7.0     | 2100 | 1.8889          | 0.7114   | 0.7217    | 0.7114 | 0.6998 |
| 0.0006        | 7.3333  | 2200 | 1.9514          | 0.6991   | 0.7212    | 0.6991 | 0.6794 |
| 0.0005        | 7.6667  | 2300 | 1.9619          | 0.7138   | 0.6644    | 0.7138 | 0.6726 |
| 0.0013        | 8.0     | 2400 | 1.7297          | 0.7490   | 0.7589    | 0.7490 | 0.7493 |
| 0.0005        | 8.3333  | 2500 | 2.2490          | 0.6950   | 0.7015    | 0.6950 | 0.6914 |
| 0.0004        | 8.6667  | 2600 | 2.2431          | 0.6975   | 0.7039    | 0.6975 | 0.6932 |
| 0.0009        | 9.0     | 2700 | 1.8096          | 0.7490   | 0.7593    | 0.7490 | 0.7443 |
| 0.0003        | 9.3333  | 2800 | 1.9490          | 0.7375   | 0.7450    | 0.7375 | 0.7353 |
| 0.0011        | 9.6667  | 2900 | 2.0860          | 0.7294   | 0.7239    | 0.7294 | 0.7153 |
| 0.0003        | 10.0    | 3000 | 1.9343          | 0.7383   | 0.7468    | 0.7383 | 0.7399 |
| 0.0004        | 10.3333 | 3100 | 1.9158          | 0.7457   | 0.7513    | 0.7457 | 0.7464 |
| 0.0003        | 10.6667 | 3200 | 1.9289          | 0.7465   | 0.7526    | 0.7465 | 0.7475 |
| 0.0802        | 11.0    | 3300 | 2.0591          | 0.7375   | 0.7487    | 0.7375 | 0.7404 |
| 0.0565        | 11.3333 | 3400 | 2.2480          | 0.7016   | 0.7854    | 0.7016 | 0.7131 |
| 0.0003        | 11.6667 | 3500 | 1.7115          | 0.7539   | 0.8088    | 0.7539 | 0.7572 |
| 0.0003        | 12.0    | 3600 | 1.9888          | 0.7195   | 0.7679    | 0.7195 | 0.7222 |
| 0.0003        | 12.3333 | 3700 | 2.0141          | 0.7179   | 0.7227    | 0.7179 | 0.7133 |
| 0.0002        | 12.6667 | 3800 | 2.0314          | 0.7089   | 0.7158    | 0.7089 | 0.7081 |
| 0.0002        | 13.0    | 3900 | 1.8735          | 0.7187   | 0.7291    | 0.7187 | 0.7220 |
| 0.0002        | 13.3333 | 4000 | 1.8854          | 0.7179   | 0.7281    | 0.7179 | 0.7210 |
| 0.0002        | 13.6667 | 4100 | 1.8931          | 0.7179   | 0.7281    | 0.7179 | 0.7210 |
| 0.0002        | 14.0    | 4200 | 1.8992          | 0.7179   | 0.7285    | 0.7179 | 0.7212 |
| 0.0002        | 14.3333 | 4300 | 1.9039          | 0.7179   | 0.7285    | 0.7179 | 0.7212 |
| 0.0002        | 14.6667 | 4400 | 1.9063          | 0.7179   | 0.7285    | 0.7179 | 0.7212 |
| 0.0002        | 15.0    | 4500 | 1.9073          | 0.7179   | 0.7285    | 0.7179 | 0.7212 |


### Framework versions

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