wangchanberta-xet_hyp-params

This model is a fine-tuned version of Thammarak/wangchanBERTa-QA-thaiqa_squad on the Dataxet FAQs dataset. It achieves the following results on the evaluation set:

• Loss: 0.0194

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: 1e-06
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss
0.0098	1.0	187	0.0195
0.02	2.0	374	0.0194
0.022	3.0	561	0.0194
0.0193	4.0	748	0.0194
0.0146	5.0	935	0.0194
0.0188	6.0	1122	0.0194
0.0296	7.0	1309	0.0194
0.0244	8.0	1496	0.0193
0.0035	9.0	1683	0.0193
0.0153	10.0	1870	0.0194
0.0188	11.0	2057	0.0193
0.0171	12.0	2244	0.0193
0.0415	13.0	2431	0.0194
0.0115	14.0	2618	0.0194

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2