---
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-5-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: 0.8616666666666667
    - name: Precision
      type: precision
      value: 0.8756807267844546
    - name: Recall
      type: recall
      value: 0.8616666666666667
    - name: F1
      type: f1
      value: 0.8604478619877372
---

<!-- 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-5-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: 0.5091
- Accuracy: 0.8617
- Precision: 0.8757
- Recall: 0.8617
- F1: 0.8604

## 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     |
|:-------------:|:-------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.2613        | 0.3333  | 100  | 0.6234          | 0.7883   | 0.8364    | 0.7883 | 0.7915 |
| 0.1745        | 0.6667  | 200  | 0.7693          | 0.7342   | 0.7739    | 0.7342 | 0.7088 |
| 0.1303        | 1.0     | 300  | 0.5091          | 0.8617   | 0.8757    | 0.8617 | 0.8604 |
| 0.0163        | 1.3333  | 400  | 0.5309          | 0.8708   | 0.8869    | 0.8708 | 0.8706 |
| 0.009         | 1.6667  | 500  | 0.9663          | 0.7725   | 0.8345    | 0.7725 | 0.7706 |
| 0.0221        | 2.0     | 600  | 1.3265          | 0.7225   | 0.8133    | 0.7225 | 0.7219 |
| 0.0053        | 2.3333  | 700  | 0.8728          | 0.8408   | 0.8727    | 0.8408 | 0.8366 |
| 0.0031        | 2.6667  | 800  | 0.9499          | 0.8258   | 0.8596    | 0.8258 | 0.8225 |
| 0.0733        | 3.0     | 900  | 0.8135          | 0.8558   | 0.8840    | 0.8558 | 0.8554 |
| 0.0026        | 3.3333  | 1000 | 0.6858          | 0.885    | 0.8963    | 0.885  | 0.8826 |
| 0.0028        | 3.6667  | 1100 | 0.8497          | 0.8608   | 0.9004    | 0.8608 | 0.8631 |
| 0.0021        | 4.0     | 1200 | 1.0722          | 0.81     | 0.8493    | 0.81   | 0.8114 |
| 0.0023        | 4.3333  | 1300 | 0.7217          | 0.8742   | 0.8742    | 0.8742 | 0.8737 |
| 0.0243        | 4.6667  | 1400 | 0.8721          | 0.8467   | 0.8627    | 0.8467 | 0.8449 |
| 0.004         | 5.0     | 1500 | 0.8314          | 0.8425   | 0.8500    | 0.8425 | 0.8402 |
| 0.0011        | 5.3333  | 1600 | 0.9170          | 0.8367   | 0.8362    | 0.8367 | 0.8347 |
| 0.0008        | 5.6667  | 1700 | 0.9080          | 0.8475   | 0.8536    | 0.8475 | 0.8452 |
| 0.0017        | 6.0     | 1800 | 0.8709          | 0.855    | 0.8642    | 0.855  | 0.8527 |
| 0.0007        | 6.3333  | 1900 | 0.7878          | 0.8808   | 0.8899    | 0.8808 | 0.8777 |
| 0.0006        | 6.6667  | 2000 | 0.7954          | 0.8825   | 0.8926    | 0.8825 | 0.8795 |
| 0.0007        | 7.0     | 2100 | 1.0196          | 0.8475   | 0.8640    | 0.8475 | 0.8438 |
| 0.0005        | 7.3333  | 2200 | 1.0647          | 0.8508   | 0.8665    | 0.8508 | 0.8463 |
| 0.0005        | 7.6667  | 2300 | 1.2970          | 0.8125   | 0.8430    | 0.8125 | 0.8111 |
| 0.0005        | 8.0     | 2400 | 1.2049          | 0.8167   | 0.8214    | 0.8167 | 0.8143 |
| 0.0021        | 8.3333  | 2500 | 0.9407          | 0.8642   | 0.8663    | 0.8642 | 0.8602 |
| 0.0006        | 8.6667  | 2600 | 1.8421          | 0.7258   | 0.8273    | 0.7258 | 0.7256 |
| 0.0005        | 9.0     | 2700 | 1.6230          | 0.76     | 0.7921    | 0.76   | 0.7555 |
| 0.0116        | 9.3333  | 2800 | 1.2096          | 0.8258   | 0.8495    | 0.8258 | 0.8182 |
| 0.0004        | 9.6667  | 2900 | 1.4233          | 0.8158   | 0.8258    | 0.8158 | 0.8111 |
| 0.0006        | 10.0    | 3000 | 1.5142          | 0.7775   | 0.8340    | 0.7775 | 0.7760 |
| 0.0004        | 10.3333 | 3100 | 0.8260          | 0.875    | 0.8833    | 0.875  | 0.8715 |
| 0.0004        | 10.6667 | 3200 | 0.8945          | 0.8642   | 0.8754    | 0.8642 | 0.8631 |
| 0.0003        | 11.0    | 3300 | 0.9189          | 0.865    | 0.8658    | 0.865  | 0.8596 |
| 0.0003        | 11.3333 | 3400 | 0.6929          | 0.8917   | 0.8926    | 0.8917 | 0.8882 |
| 0.0003        | 11.6667 | 3500 | 0.7764          | 0.8908   | 0.9000    | 0.8908 | 0.8879 |
| 0.0003        | 12.0    | 3600 | 0.9250          | 0.8617   | 0.8749    | 0.8617 | 0.8598 |
| 0.0002        | 12.3333 | 3700 | 0.9109          | 0.865    | 0.8772    | 0.865  | 0.8628 |
| 0.0002        | 12.6667 | 3800 | 0.9101          | 0.865    | 0.8772    | 0.865  | 0.8628 |
| 0.0002        | 13.0    | 3900 | 0.9113          | 0.8675   | 0.8792    | 0.8675 | 0.8653 |
| 0.0002        | 13.3333 | 4000 | 0.9124          | 0.8683   | 0.8800    | 0.8683 | 0.8662 |
| 0.0002        | 13.6667 | 4100 | 0.9130          | 0.8683   | 0.8800    | 0.8683 | 0.8662 |
| 0.0002        | 14.0    | 4200 | 0.9124          | 0.8683   | 0.8800    | 0.8683 | 0.8662 |
| 0.0002        | 14.3333 | 4300 | 0.9125          | 0.8683   | 0.8800    | 0.8683 | 0.8662 |
| 0.0002        | 14.6667 | 4400 | 0.9130          | 0.8683   | 0.8800    | 0.8683 | 0.8662 |
| 0.0002        | 15.0    | 4500 | 0.9131          | 0.8683   | 0.8800    | 0.8683 | 0.8662 |


### Framework versions

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