phobert-base-v2-ed
This model is a fine-tuned version of vinai/phobert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0541
- F1 Micro: 0.7087
- F1 Macro: 0.0259
- Recall Micro: 0.5880
- Precision Micro: 0.8918
- Recall Macro: 0.0257
- Precision Macro: 0.0262
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 | F1 Micro | F1 Macro | Recall Micro | Precision Micro | Recall Macro | Precision Macro |
---|---|---|---|---|---|---|---|---|---|
0.069 | 1.0 | 1526 | 0.0706 | 0.6892 | 0.0243 | 0.6737 | 0.7054 | 0.0294 | 0.0207 |
0.0512 | 2.0 | 3052 | 0.0636 | 0.7055 | 0.0255 | 0.6165 | 0.8245 | 0.0269 | 0.0243 |
0.0629 | 3.0 | 4578 | 0.0577 | 0.7013 | 0.0257 | 0.5812 | 0.8840 | 0.0254 | 0.0260 |
0.0574 | 4.0 | 6104 | 0.0550 | 0.7120 | 0.0259 | 0.6024 | 0.8706 | 0.0263 | 0.0256 |
0.0375 | 5.0 | 7630 | 0.0541 | 0.7087 | 0.0259 | 0.5880 | 0.8918 | 0.0257 | 0.0262 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 1