---
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: vit-pushup-form-classifier
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: imagefolder
      type: imagefolder
      config: default
      split: train
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.9733333333333334
    - name: F1
      type: f1
      value: 0.9733475783475783
    - name: Precision
      type: precision
      value: 0.9737081183656526
    - name: Recall
      type: recall
      value: 0.9733333333333334
---

<!-- 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-pushup-form-classifier

This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0633
- Accuracy: 0.9733
- F1: 0.9733
- Precision: 0.9737
- Recall: 0.9733

## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 0.2205        | 1.0   | 44   | 0.2602          | 0.8533   | 0.8532 | 0.8534    | 0.8533 |
| 0.1148        | 2.0   | 88   | 0.2138          | 0.9      | 0.9000 | 0.9       | 0.9    |
| 0.0869        | 3.0   | 132  | 0.2535          | 0.8933   | 0.8931 | 0.8942    | 0.8933 |
| 0.0592        | 4.0   | 176  | 0.1646          | 0.9      | 0.8997 | 0.9014    | 0.9    |
| 0.0559        | 5.0   | 220  | 0.1587          | 0.9267   | 0.9265 | 0.9283    | 0.9267 |
| 0.034         | 6.0   | 264  | 0.2178          | 0.9133   | 0.9129 | 0.9166    | 0.9133 |
| 0.0171        | 7.0   | 308  | 0.1712          | 0.9267   | 0.9266 | 0.9272    | 0.9267 |
| 0.0107        | 8.0   | 352  | 0.1740          | 0.9267   | 0.9265 | 0.9283    | 0.9267 |
| 0.0139        | 9.0   | 396  | 0.1631          | 0.9333   | 0.9332 | 0.9344    | 0.9333 |
| 0.0046        | 10.0  | 440  | 0.1692          | 0.9333   | 0.9331 | 0.9359    | 0.9333 |


### Framework versions

- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1