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: 0.0248
- 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: 22
- eval_batch_size: 22
- 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 |
|---|---|---|---|---|
| 4.227 | 1.0 | 1 | 2.1377 | 0.0 |
| 2.2277 | 2.0 | 2 | 0.8621 | 0.0 |
| 0.9409 | 3.0 | 3 | 0.5773 | 0.0 |
| 0.5981 | 4.0 | 4 | 0.4644 | 0.0 |
| 0.4765 | 5.0 | 5 | 0.3439 | 0.0 |
| 0.3635 | 6.0 | 6 | 0.3140 | 0.0 |
| 0.349 | 7.0 | 7 | 0.2688 | 0.0 |
| 0.3031 | 8.0 | 8 | 0.2333 | 0.0 |
| 0.2643 | 9.0 | 9 | 0.2003 | 0.0870 |
| 0.2364 | 10.0 | 10 | 0.1592 | 0.5333 |
| 0.1909 | 11.0 | 11 | 0.1369 | 0.8571 |
| 0.1674 | 12.0 | 12 | 0.1230 | 0.8980 |
| 0.1414 | 13.0 | 13 | 0.0983 | 0.9362 |
| 0.1274 | 14.0 | 14 | 0.0718 | 0.9778 |
| 0.0944 | 15.0 | 15 | 0.0531 | 1.0 |
| 0.0833 | 16.0 | 16 | 0.0405 | 1.0 |
| 0.0727 | 17.0 | 17 | 0.0328 | 1.0 |
| 0.0557 | 18.0 | 18 | 0.0284 | 1.0 |
| 0.0514 | 19.0 | 19 | 0.0259 | 1.0 |
| 0.0456 | 20.0 | 20 | 0.0248 | 1.0 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.12.0+cu102
- Datasets 1.18.4
- Tokenizers 0.12.1