README.md

metadata

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

TGPT-2-345M

This model is a fine-tuned version of on an Thai Wikipedia dataset. It achieves the following results on the evaluation set:

• Train Loss: 2.6217
• Train Accuracy: 0.5400
• Epoch: 3

Model description

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	0
2.8630	0.5107	1
2.6217	0.5400	2

Framework versions

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