---
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: Action_model
  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: 0.7666666666666667
---

<!-- 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. -->

# Action_model

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: 1.0234
- Accuracy: 0.7667

## 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: 0.0001
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.4299        | 0.32  | 100  | 0.7981          | 0.7457   |
| 0.3903        | 0.64  | 200  | 0.7173          | 0.7771   |
| 0.4296        | 0.96  | 300  | 0.6869          | 0.7876   |
| 0.3589        | 1.27  | 400  | 0.9108          | 0.7314   |
| 0.3007        | 1.59  | 500  | 0.9720          | 0.7133   |
| 0.2817        | 1.91  | 600  | 0.8504          | 0.7486   |
| 0.2754        | 2.23  | 700  | 0.9009          | 0.7410   |
| 0.2226        | 2.55  | 800  | 0.9020          | 0.7495   |
| 0.285         | 2.87  | 900  | 1.0012          | 0.7295   |
| 0.2307        | 3.18  | 1000 | 0.8204          | 0.7810   |
| 0.2398        | 3.5   | 1100 | 0.8857          | 0.7695   |
| 0.1948        | 3.82  | 1200 | 0.9110          | 0.7571   |
| 0.1962        | 4.14  | 1300 | 0.9775          | 0.7533   |
| 0.2159        | 4.46  | 1400 | 0.9719          | 0.7457   |
| 0.1361        | 4.78  | 1500 | 0.9262          | 0.7571   |
| 0.1898        | 5.1   | 1600 | 0.9130          | 0.7705   |
| 0.1153        | 5.41  | 1700 | 1.0409          | 0.7438   |
| 0.1489        | 5.73  | 1800 | 1.0176          | 0.7495   |
| 0.1515        | 6.05  | 1900 | 1.0507          | 0.7486   |
| 0.1126        | 6.37  | 2000 | 1.1423          | 0.7210   |
| 0.1319        | 6.69  | 2100 | 1.1008          | 0.7467   |
| 0.1424        | 7.01  | 2200 | 1.0798          | 0.7419   |
| 0.0955        | 7.32  | 2300 | 1.0767          | 0.7505   |
| 0.1077        | 7.64  | 2400 | 1.0920          | 0.7457   |
| 0.1048        | 7.96  | 2500 | 1.0040          | 0.7733   |
| 0.0965        | 8.28  | 2600 | 1.0384          | 0.7610   |
| 0.0995        | 8.6   | 2700 | 1.0423          | 0.7648   |
| 0.1213        | 8.92  | 2800 | 1.0544          | 0.7619   |
| 0.0863        | 9.24  | 2900 | 1.0454          | 0.7629   |
| 0.0926        | 9.55  | 3000 | 1.0380          | 0.7676   |
| 0.0536        | 9.87  | 3100 | 1.0234          | 0.7667   |


### Framework versions

- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2