|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: google-bert/bert-base-chinese |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: ner_based_bert-base-chinese_withBadcase_replaceSpace |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# ner_based_bert-base-chinese_withBadcase_replaceSpace |
|
|
|
|
|
This model is a fine-tuned version of [google-bert/bert-base-chinese](https://huggingface.co/google-bert/bert-base-chinese) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0138 |
|
|
- Precision: 0.9505 |
|
|
- Recall: 0.9655 |
|
|
- F1: 0.9579 |
|
|
- Accuracy: 0.9969 |
|
|
|
|
|
## 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: 128 |
|
|
- eval_batch_size: 128 |
|
|
- seed: 42 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_steps: 20 |
|
|
- training_steps: 6520 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
|
| 0.1507 | 1.0 | 652 | 0.0249 | 0.8949 | 0.9105 | 0.9026 | 0.9928 | |
|
|
| 0.0256 | 2.0 | 1304 | 0.0189 | 0.9186 | 0.9245 | 0.9215 | 0.9945 | |
|
|
| 0.0195 | 3.0 | 1956 | 0.0169 | 0.9237 | 0.9470 | 0.9352 | 0.9952 | |
|
|
| 0.0131 | 4.0 | 2608 | 0.0161 | 0.9299 | 0.9499 | 0.9398 | 0.9956 | |
|
|
| 0.0114 | 5.0 | 3260 | 0.0149 | 0.9311 | 0.9607 | 0.9457 | 0.9959 | |
|
|
| 0.01 | 6.0 | 3912 | 0.0146 | 0.9395 | 0.9600 | 0.9497 | 0.9962 | |
|
|
| 0.0072 | 7.0 | 4564 | 0.0139 | 0.9480 | 0.9562 | 0.9521 | 0.9965 | |
|
|
| 0.0065 | 8.0 | 5216 | 0.0133 | 0.9431 | 0.9655 | 0.9542 | 0.9966 | |
|
|
| 0.0059 | 9.0 | 5868 | 0.0134 | 0.9501 | 0.9640 | 0.9570 | 0.9968 | |
|
|
| 0.0042 | 10.0 | 6520 | 0.0138 | 0.9505 | 0.9655 | 0.9579 | 0.9969 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.54.0 |
|
|
- Pytorch 2.7.0+cu128 |
|
|
- Datasets 4.0.0 |
|
|
- Tokenizers 0.21.4 |
|
|
|
