metadata
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: bert-base-chinese-finetuned-split
results: []
bert-base-chinese-finetuned-split
This model is a fine-tuned version of bert-base-chinese on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0177
- F1: 1.0
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: 27
- eval_batch_size: 27
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 3.8485 | 1.0 | 1 | 1.9458 | 0.0 |
| 2.0072 | 2.0 | 2 | 0.8351 | 0.0 |
| 0.8935 | 3.0 | 3 | 0.4898 | 0.0 |
| 0.5205 | 4.0 | 4 | 0.3869 | 0.0 |
| 0.4011 | 5.0 | 5 | 0.2898 | 0.0 |
| 0.3135 | 6.0 | 6 | 0.2673 | 0.0769 |
| 0.291 | 7.0 | 7 | 0.2318 | 0.2143 |
| 0.2611 | 8.0 | 8 | 0.1855 | 0.0769 |
| 0.2101 | 9.0 | 9 | 0.1557 | 0.2759 |
| 0.1809 | 10.0 | 10 | 0.1254 | 0.5714 |
| 0.1661 | 11.0 | 11 | 0.1004 | 0.8636 |
| 0.1307 | 12.0 | 12 | 0.0840 | 0.96 |
| 0.1081 | 13.0 | 13 | 0.0696 | 0.96 |
| 0.0942 | 14.0 | 14 | 0.0540 | 0.96 |
| 0.071 | 15.0 | 15 | 0.0407 | 0.9796 |
| 0.0659 | 16.0 | 16 | 0.0318 | 0.9796 |
| 0.0492 | 17.0 | 17 | 0.0256 | 0.9796 |
| 0.0426 | 18.0 | 18 | 0.0214 | 1.0 |
| 0.0407 | 19.0 | 19 | 0.0189 | 1.0 |
| 0.0354 | 20.0 | 20 | 0.0177 | 1.0 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.12.0+cu102
- Datasets 1.18.4
- Tokenizers 0.12.1