results_v5
This model is a fine-tuned version of vinai/phobert-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9704
- Accuracy: 0.7354
- F1: 0.7342
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: 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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 56 | 0.9918 | 0.5605 | 0.5758 |
| No log | 2.0 | 112 | 0.9572 | 0.6368 | 0.6227 |
| No log | 3.0 | 168 | 0.9271 | 0.6009 | 0.6131 |
| No log | 4.0 | 224 | 0.9041 | 0.6054 | 0.6211 |
| No log | 5.0 | 280 | 0.8567 | 0.6951 | 0.6980 |
| No log | 6.0 | 336 | 0.8839 | 0.6726 | 0.6816 |
| No log | 7.0 | 392 | 0.9662 | 0.7175 | 0.7139 |
| No log | 8.0 | 448 | 1.0542 | 0.7309 | 0.7159 |
| 0.5698 | 9.0 | 504 | 1.0043 | 0.7265 | 0.7193 |
| 0.5698 | 10.0 | 560 | 0.9704 | 0.7354 | 0.7342 |
Framework versions
- Transformers 5.22.1
- Pytorch 2.14.1+cu130
- Datasets 2.20.0
- Tokenizers 0.23.3