---
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: 0.7695238095238095
---

<!-- 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: 1.1418
- Accuracy: 0.7695

## 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: 16
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.3203        | 0.16  | 100  | 1.1810          | 0.7448   |
| 0.998         | 0.32  | 200  | 0.8925          | 0.7705   |
| 0.765         | 0.48  | 300  | 0.8199          | 0.7638   |
| 0.6521        | 0.64  | 400  | 0.8276          | 0.7371   |
| 0.7612        | 0.8   | 500  | 0.8631          | 0.7210   |
| 0.5894        | 0.96  | 600  | 0.8176          | 0.7476   |
| 0.5381        | 1.11  | 700  | 0.7965          | 0.7524   |
| 0.4066        | 1.27  | 800  | 0.8102          | 0.7486   |
| 0.4825        | 1.43  | 900  | 0.7498          | 0.7743   |
| 0.4955        | 1.59  | 1000 | 0.9752          | 0.7019   |
| 0.3945        | 1.75  | 1100 | 0.8150          | 0.7381   |
| 0.4142        | 1.91  | 1200 | 0.7953          | 0.7610   |
| 0.3915        | 2.07  | 1300 | 0.8141          | 0.7638   |
| 0.3937        | 2.23  | 1400 | 0.7882          | 0.7705   |
| 0.3144        | 2.39  | 1500 | 0.8657          | 0.7514   |
| 0.3143        | 2.55  | 1600 | 1.0562          | 0.7086   |
| 0.3884        | 2.71  | 1700 | 1.0502          | 0.7162   |
| 0.3472        | 2.87  | 1800 | 0.8506          | 0.7571   |
| 0.2545        | 3.03  | 1900 | 1.0029          | 0.7210   |
| 0.2213        | 3.18  | 2000 | 0.8099          | 0.7933   |
| 0.3429        | 3.34  | 2100 | 0.9166          | 0.7467   |
| 0.3478        | 3.5   | 2200 | 0.9202          | 0.7562   |
| 0.2247        | 3.66  | 2300 | 0.9859          | 0.7638   |
| 0.2873        | 3.82  | 2400 | 1.0161          | 0.7390   |
| 0.2815        | 3.98  | 2500 | 0.9631          | 0.7590   |
| 0.1706        | 4.14  | 2600 | 0.9996          | 0.7419   |
| 0.1709        | 4.3   | 2700 | 1.1969          | 0.7029   |
| 0.2847        | 4.46  | 2800 | 1.0896          | 0.7276   |
| 0.286         | 4.62  | 2900 | 0.9894          | 0.7629   |
| 0.2066        | 4.78  | 3000 | 1.0704          | 0.7486   |
| 0.1579        | 4.94  | 3100 | 0.9728          | 0.7810   |
| 0.1716        | 5.1   | 3200 | 1.1834          | 0.7124   |
| 0.1584        | 5.25  | 3300 | 1.0278          | 0.7524   |
| 0.1419        | 5.41  | 3400 | 1.1342          | 0.7371   |
| 0.2002        | 5.57  | 3500 | 1.1519          | 0.7324   |
| 0.1987        | 5.73  | 3600 | 1.0742          | 0.7562   |
| 0.1207        | 5.89  | 3700 | 1.1579          | 0.7381   |
| 0.1403        | 6.05  | 3800 | 1.1007          | 0.7305   |
| 0.1569        | 6.21  | 3900 | 1.1128          | 0.7467   |
| 0.1763        | 6.37  | 4000 | 1.0720          | 0.7524   |
| 0.2426        | 6.53  | 4100 | 1.1484          | 0.7248   |
| 0.1434        | 6.69  | 4200 | 1.1790          | 0.7343   |
| 0.2191        | 6.85  | 4300 | 1.1169          | 0.7486   |
| 0.2062        | 7.01  | 4400 | 1.1300          | 0.7610   |
| 0.1495        | 7.17  | 4500 | 1.1477          | 0.7495   |
| 0.1261        | 7.32  | 4600 | 1.0891          | 0.7657   |
| 0.12          | 7.48  | 4700 | 1.1359          | 0.76     |
| 0.1396        | 7.64  | 4800 | 1.1230          | 0.7410   |
| 0.0728        | 7.8   | 4900 | 1.1210          | 0.7552   |
| 0.175         | 7.96  | 5000 | 1.1204          | 0.7505   |
| 0.1214        | 8.12  | 5100 | 1.1064          | 0.7543   |
| 0.1218        | 8.28  | 5200 | 1.0232          | 0.7771   |
| 0.1556        | 8.44  | 5300 | 1.0489          | 0.7771   |
| 0.1019        | 8.6   | 5400 | 1.0916          | 0.7752   |
| 0.1446        | 8.76  | 5500 | 1.1856          | 0.7505   |
| 0.1348        | 8.92  | 5600 | 1.1380          | 0.7638   |
| 0.1402        | 9.08  | 5700 | 1.1233          | 0.7695   |
| 0.1075        | 9.24  | 5800 | 1.1472          | 0.7629   |
| 0.0991        | 9.39  | 5900 | 1.1530          | 0.7648   |
| 0.081         | 9.55  | 6000 | 1.1586          | 0.7629   |
| 0.0724        | 9.71  | 6100 | 1.1591          | 0.7676   |
| 0.0399        | 9.87  | 6200 | 1.1418          | 0.7695   |


### Framework versions

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