---
license: mit
tags:
- generated_from_trainer
model-index:
- name: gpt2-thai-romanization
  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. -->

# gpt2-thai-romanization

This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9597

## 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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 23741
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 1.4961        | 1.0   | 2968  | 1.4161          |
| 1.3384        | 2.0   | 5936  | 1.2793          |
| 1.2067        | 3.0   | 8904  | 1.1694          |
| 1.1307        | 4.0   | 11872 | 1.0987          |
| 1.0965        | 5.0   | 14840 | 1.0531          |
| 1.045         | 6.0   | 17808 | 1.0233          |
| 1.0179        | 7.0   | 20776 | 1.0021          |
| 0.9902        | 8.0   | 23744 | 0.9826          |
| 0.9405        | 9.0   | 26712 | 0.9660          |
| 0.9145        | 10.0  | 29680 | 0.9597          |


### Framework versions

- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Tokenizers 0.13.2