20250625081011
This model is a fine-tuned version of bkai-foundation-models/vietnamese-bi-encoder on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1301
- F1: 0.8911
- Roc Auc: 0.9325
- Accuracy: 0.7212
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: 0.0002
- train_batch_size: 64
- eval_batch_size: 128
- 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: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.2435 | 0.7800 | 1500 | 0.1512 | 0.8669 | 0.9144 | 0.6629 |
| 0.1301 | 1.5601 | 3000 | 0.1365 | 0.8778 | 0.9231 | 0.6902 |
| 0.1137 | 2.3401 | 4500 | 0.1299 | 0.8866 | 0.9285 | 0.7104 |
| 0.093 | 3.1201 | 6000 | 0.1286 | 0.8904 | 0.9314 | 0.7196 |
| 0.0788 | 3.9002 | 7500 | 0.1294 | 0.8913 | 0.9324 | 0.7214 |
| 0.0745 | 4.6802 | 9000 | 0.1301 | 0.8911 | 0.9325 | 0.7212 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.7.1+cu118
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- 18
Model tree for irene-ng/review_classify_cat
Base model
bkai-foundation-models/vietnamese-bi-encoder