<!-- 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. -->
ckiplab-bert-chinese-david-ner
This model is a fine-tuned version of ckiplab/bert-base-chinese on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2218
- Precision: 0.8209
- Recall: 0.8379
- F1: 0.8294
- Accuracy: 0.9452
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2628 | 1.4 | 500 | 0.2450 | 0.8287 | 0.8172 | 0.8229 | 0.9390 |
| 0.0773 | 2.8 | 1000 | 0.2218 | 0.8209 | 0.8379 | 0.8294 | 0.9452 |
Framework versions
- Transformers 4.29.0.dev0
- Pytorch 1.10.1+cu113
- Datasets 2.11.0
- Tokenizers 0.13.3
