---
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: 0.7876190476190477
---

<!-- 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: 0.9250
- Accuracy: 0.7876

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.1285        | 0.32  | 100  | 1.0131          | 0.7743   |
| 0.7868        | 0.64  | 200  | 0.7684          | 0.7867   |
| 0.6015        | 0.96  | 300  | 0.7090          | 0.7714   |
| 0.5209        | 1.27  | 400  | 0.7650          | 0.7571   |
| 0.4536        | 1.59  | 500  | 0.7826          | 0.7419   |
| 0.4069        | 1.91  | 600  | 0.6878          | 0.7876   |
| 0.3244        | 2.23  | 700  | 0.9184          | 0.7238   |
| 0.2618        | 2.55  | 800  | 0.8178          | 0.7552   |
| 0.342         | 2.87  | 900  | 0.8192          | 0.7648   |
| 0.2778        | 3.18  | 1000 | 0.7542          | 0.7848   |
| 0.2331        | 3.5   | 1100 | 0.8133          | 0.7695   |
| 0.2426        | 3.82  | 1200 | 0.9022          | 0.7476   |
| 0.2363        | 4.14  | 1300 | 0.9009          | 0.7619   |
| 0.2143        | 4.46  | 1400 | 0.8545          | 0.7790   |
| 0.1624        | 4.78  | 1500 | 0.9543          | 0.7533   |
| 0.2302        | 5.1   | 1600 | 0.8138          | 0.78     |
| 0.1682        | 5.41  | 1700 | 0.8490          | 0.7790   |
| 0.1674        | 5.73  | 1800 | 0.9097          | 0.7724   |
| 0.1595        | 6.05  | 1900 | 1.0542          | 0.7486   |
| 0.1335        | 6.37  | 2000 | 0.8957          | 0.7876   |
| 0.1696        | 6.69  | 2100 | 0.8860          | 0.7781   |
| 0.148         | 7.01  | 2200 | 0.9529          | 0.7733   |
| 0.1281        | 7.32  | 2300 | 0.9364          | 0.7848   |
| 0.1274        | 7.64  | 2400 | 0.9252          | 0.7676   |
| 0.1585        | 7.96  | 2500 | 0.9068          | 0.7914   |
| 0.0985        | 8.28  | 2600 | 0.9400          | 0.7829   |
| 0.1211        | 8.6   | 2700 | 0.9464          | 0.7790   |
| 0.1459        | 8.92  | 2800 | 0.9800          | 0.7695   |
| 0.1221        | 9.24  | 2900 | 0.9457          | 0.78     |
| 0.1072        | 9.55  | 3000 | 0.9209          | 0.7857   |
| 0.0607        | 9.87  | 3100 | 0.9250          | 0.7876   |


### Framework versions

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