---
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- image-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-finetuned_ASL_Isolated_Swin_dataset2
  results: []
---

<!-- 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. -->

# swin-tiny-patch4-window7-224-finetuned_ASL_Isolated_Swin_dataset2

This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the ASL_Isolated_Swin_dataset dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0640
- Accuracy: 0.9846

## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.39          | 1.09  | 100  | 1.1827          | 0.6346   |
| 0.8972        | 2.17  | 200  | 0.6287          | 0.7808   |
| 0.4884        | 3.26  | 300  | 0.2927          | 0.8962   |
| 0.4179        | 4.35  | 400  | 0.1795          | 0.9423   |
| 0.4169        | 5.43  | 500  | 0.1564          | 0.95     |
| 0.3427        | 6.52  | 600  | 0.1426          | 0.95     |
| 0.2939        | 7.61  | 700  | 0.1174          | 0.9731   |
| 0.1605        | 8.7   | 800  | 0.0640          | 0.9846   |
| 0.1865        | 9.78  | 900  | 0.0702          | 0.9808   |


### Framework versions

- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1