---
license: apache-2.0
language:
- th
pipeline_tag: text-generation
tags:
- TGPT
library_name: transformers
datasets:
- th_wikipedia
model-index:
- name: TGPT-2-345M
  results: []
widget:
- text: "ประเทศไทยเป็นประเทศที่"
- text: "กรุงเทพเคยเกิด"
- text: "ระบบสุริยะจักรวาลเป็น"
---

<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->

# TGPT-2-345M

This model is a fine-tuned version of [](https://huggingface.co/) on an th_wikipedia dataset.
It achieves the following results on the evaluation set:
- Train Loss: 3.5955
- Train Accuracy: 0.4289
- Epoch: 1

## Model description

GPT-2

## Intended uses & limitations

-

## Training and evaluation data

-

## Training procedure

-

### Training hyperparameters

The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32

### Training results

| Train Loss | Train Accuracy | Epoch |
|:----------:|:--------------:|:-----:|
| 3.5955     | 0.4289         | 1     |


### Framework versions

- Transformers 4.26.0
- TensorFlow 2.11.0
- Datasets 2.10.0
- Tokenizers 0.13.2