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: 0.0149
- 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: 26
- eval_batch_size: 26
- 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 |
|---|---|---|---|---|
| 3.3649 | 1.0 | 1 | 1.5647 | 0.0 |
| 1.6645 | 2.0 | 2 | 0.7201 | 0.0 |
| 0.8002 | 3.0 | 3 | 0.5081 | 0.0 |
| 0.5252 | 4.0 | 4 | 0.3935 | 0.0 |
| 0.4039 | 5.0 | 5 | 0.3012 | 0.0 |
| 0.331 | 6.0 | 6 | 0.2515 | 0.0 |
| 0.2797 | 7.0 | 7 | 0.2132 | 0.1538 |
| 0.2396 | 8.0 | 8 | 0.1771 | 0.4 |
| 0.2098 | 9.0 | 9 | 0.1444 | 0.5882 |
| 0.1802 | 10.0 | 10 | 0.1197 | 0.8372 |
| 0.1413 | 11.0 | 11 | 0.0972 | 0.8372 |
| 0.1195 | 12.0 | 12 | 0.0741 | 0.9333 |
| 0.0962 | 13.0 | 13 | 0.0551 | 0.9565 |
| 0.0774 | 14.0 | 14 | 0.0413 | 1.0 |
| 0.0641 | 15.0 | 15 | 0.0323 | 1.0 |
| 0.0517 | 16.0 | 16 | 0.0256 | 1.0 |
| 0.0425 | 17.0 | 17 | 0.0211 | 1.0 |
| 0.035 | 18.0 | 18 | 0.0184 | 1.0 |
| 0.031 | 19.0 | 19 | 0.0161 | 1.0 |
| 0.0295 | 20.0 | 20 | 0.0149 | 1.0 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.12.0+cu102
- Datasets 1.18.4
- Tokenizers 0.12.1