wangchanberta_sentiment
This model is a fine-tuned version of airesearch/wangchanberta-base-att-spm-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8945
- Accuracy: 0.6252
- F1 Macro: 0.6074
- F1 Pos: 0.5013
- F1 Neu: 0.6088
- F1 Neg: 0.712
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-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Pos | F1 Neu | F1 Neg |
|---|---|---|---|---|---|---|---|---|
| 0.7822 | 1.0 | 4500 | 0.8166 | 0.6242 | 0.6021 | 0.4857 | 0.6104 | 0.7101 |
| 0.7515 | 2.0 | 9000 | 0.8428 | 0.6362 | 0.6017 | 0.4536 | 0.6377 | 0.7138 |
| 0.6871 | 3.0 | 13500 | 0.8369 | 0.6428 | 0.6153 | 0.4862 | 0.6413 | 0.7183 |
| 0.708 | 4.0 | 18000 | 0.8369 | 0.6145 | 0.6023 | 0.5102 | 0.581 | 0.7157 |
| 0.5887 | 5.0 | 22500 | 0.8945 | 0.6252 | 0.6074 | 0.5013 | 0.6088 | 0.712 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.20.3
- Downloads last month
- 4