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: 0.0157
- 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: 17
- eval_batch_size: 17
- 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 |
|---|---|---|---|---|
| 3.6953 | 1.0 | 1 | 1.6141 | 0.0 |
| 1.7882 | 2.0 | 2 | 0.7202 | 0.0 |
| 0.7714 | 3.0 | 3 | 0.5327 | 0.0 |
| 0.5498 | 4.0 | 4 | 0.4039 | 0.0 |
| 0.4295 | 5.0 | 5 | 0.3020 | 0.0 |
| 0.3318 | 6.0 | 6 | 0.2653 | 0.3 |
| 0.3066 | 7.0 | 7 | 0.2074 | 0.4545 |
| 0.2533 | 8.0 | 8 | 0.1701 | 0.6923 |
| 0.213 | 9.0 | 9 | 0.1390 | 0.7857 |
| 0.1726 | 10.0 | 10 | 0.1184 | 0.8000 |
| 0.1448 | 11.0 | 11 | 0.0978 | 0.7742 |
| 0.1246 | 12.0 | 12 | 0.0664 | 0.9412 |
| 0.0947 | 13.0 | 13 | 0.0449 | 0.9714 |
| 0.0688 | 14.0 | 14 | 0.0330 | 0.9714 |
| 0.0628 | 15.0 | 15 | 0.0261 | 0.9714 |
| 0.0539 | 16.0 | 16 | 0.0232 | 0.9714 |
| 0.0367 | 17.0 | 17 | 0.0218 | 0.9714 |
| 0.0345 | 18.0 | 18 | 0.0194 | 0.9714 |
| 0.0256 | 19.0 | 19 | 0.0171 | 0.9714 |
| 0.0238 | 20.0 | 20 | 0.0157 | 1.0 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.12.0+cu102
- Datasets 1.18.4
- Tokenizers 0.12.1