---
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-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: 0.7579721995094031
    - name: Precision
      type: precision
      value: 0.7873382616180895
    - name: Recall
      type: recall
      value: 0.7579721995094031
    - name: F1
      type: f1
      value: 0.7484690650364032
---

<!-- 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-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: 0.8337
- Accuracy: 0.7580
- Precision: 0.7873
- Recall: 0.7580
- F1: 0.7485

## 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     |
|:-------------:|:-------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.1701        | 0.6667  | 100  | 0.8337          | 0.7580   | 0.7873    | 0.7580 | 0.7485 |
| 0.1078        | 1.3333  | 200  | 0.9744          | 0.7392   | 0.7683    | 0.7392 | 0.7328 |
| 0.0149        | 2.0     | 300  | 1.1815          | 0.7490   | 0.8429    | 0.7490 | 0.7488 |
| 0.0518        | 2.6667  | 400  | 1.3244          | 0.7522   | 0.8024    | 0.7522 | 0.7474 |
| 0.008         | 3.3333  | 500  | 1.0330          | 0.7727   | 0.8049    | 0.7727 | 0.7753 |
| 0.0058        | 4.0     | 600  | 1.2145          | 0.7490   | 0.7861    | 0.7490 | 0.7510 |
| 0.0031        | 4.6667  | 700  | 0.9566          | 0.8013   | 0.7999    | 0.8013 | 0.7994 |
| 0.0026        | 5.3333  | 800  | 1.3827          | 0.7678   | 0.8112    | 0.7678 | 0.7710 |
| 0.0141        | 6.0     | 900  | 1.0396          | 0.8078   | 0.8238    | 0.8078 | 0.8029 |
| 0.0194        | 6.6667  | 1000 | 1.3622          | 0.7514   | 0.7612    | 0.7514 | 0.7525 |
| 0.0015        | 7.3333  | 1100 | 1.1867          | 0.7784   | 0.8293    | 0.7784 | 0.7784 |
| 0.0012        | 8.0     | 1200 | 1.5671          | 0.7269   | 0.7813    | 0.7269 | 0.7367 |
| 0.0011        | 8.6667  | 1300 | 1.2410          | 0.7629   | 0.7779    | 0.7629 | 0.7682 |
| 0.001         | 9.3333  | 1400 | 1.2369          | 0.7899   | 0.8155    | 0.7899 | 0.7849 |
| 0.0009        | 10.0    | 1500 | 1.2282          | 0.7915   | 0.8187    | 0.7915 | 0.7878 |
| 0.0008        | 10.6667 | 1600 | 1.2243          | 0.7948   | 0.8223    | 0.7948 | 0.7917 |
| 0.0008        | 11.3333 | 1700 | 1.2258          | 0.7989   | 0.8256    | 0.7989 | 0.7957 |
| 0.0007        | 12.0    | 1800 | 1.2286          | 0.7997   | 0.8262    | 0.7997 | 0.7965 |
| 0.0007        | 12.6667 | 1900 | 1.2296          | 0.7989   | 0.8245    | 0.7989 | 0.7957 |
| 0.0007        | 13.3333 | 2000 | 1.2314          | 0.7989   | 0.8245    | 0.7989 | 0.7957 |
| 0.0006        | 14.0    | 2100 | 1.2325          | 0.7997   | 0.8252    | 0.7997 | 0.7967 |
| 0.0006        | 14.6667 | 2200 | 1.2330          | 0.8005   | 0.8258    | 0.8005 | 0.7978 |


### Framework versions

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