bert_tone_model
This model is a fine-tuned version of bert-base-chinese on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2304
- Accuracy: 0.9796
- Macro F1: 0.9785
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: 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
|---|---|---|---|---|---|
| 0.9949 | 1.0 | 15 | 0.5712 | 0.7551 | 0.6869 |
| 0.5235 | 2.0 | 30 | 0.3814 | 0.9184 | 0.9132 |
| 0.3750 | 3.0 | 45 | 0.2849 | 0.9592 | 0.9569 |
| 0.2251 | 4.0 | 60 | 0.2432 | 0.9592 | 0.9569 |
| 0.1959 | 5.0 | 75 | 0.2304 | 0.9796 | 0.9785 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.23.1