wangchanberta-fine-tune-fin-news-sentiment-finnlp-th
This model is a fine-tuned version of nlp-chula/augment-sentiment-finnlp-th on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8258
- Accuracy: 0.7516
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5974 | 1.0 | 3054 | 0.5813 | 0.7310 |
| 0.5319 | 2.0 | 6108 | 0.5835 | 0.7457 |
| 0.444 | 3.0 | 9162 | 0.6145 | 0.7446 |
| 0.3585 | 4.0 | 12216 | 0.6913 | 0.7523 |
| 0.2813 | 5.0 | 15270 | 0.8258 | 0.7516 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0