---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swinv2-tiny-patch4-window8-256-finetuned-thai
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: imagefolder
      type: imagefolder
      config: default
      split: val
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.87375
---

<!-- 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. -->

# swinv2-tiny-patch4-window8-256-finetuned-thai

This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4391
- Accuracy: 0.8738

## 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: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 7

### Training results

| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|:-------------:|:-----:|:----:|:--------:|:---------------:|
| 2.6781        | 0.99  | 47   | 0.5475   | 1.8040          |
| 1.3191        | 1.99  | 94   | 0.745    | 0.9501          |
| 1.078         | 2.98  | 141  | 0.7969   | 0.7767          |
| 0.9125        | 3.99  | 188  | 0.6060   | 0.8406          |
| 0.7527        | 4.99  | 235  | 0.5214   | 0.8575          |
| 0.6852        | 5.98  | 282  | 0.4588   | 0.8656          |
| 0.6233        | 6.98  | 329  | 0.4391   | 0.8738          |


### Framework versions

- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3