metadata
library_name: transformers
base_model: clicknext/phayathaibert
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Sentiment_PhayaThaiBERT
results: []
Sentiment_PhayaThaiBERT
This model is a fine-tuned version of clicknext/phayathaibert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4796
- Accuracy: 0.7420
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6755 | 1.0 | 512 | 0.7123 | 0.6874 |
| 0.5049 | 2.0 | 1024 | 0.7168 | 0.7147 |
| 0.3099 | 3.0 | 1536 | 0.8684 | 0.7369 |
| 0.2249 | 4.0 | 2048 | 1.0743 | 0.7369 |
| 0.1696 | 5.0 | 2560 | 1.2089 | 0.7267 |
| 0.1126 | 6.0 | 3072 | 1.3945 | 0.7443 |
| 0.0709 | 7.0 | 3584 | 1.4796 | 0.7420 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1