metadata
license: gpl-3.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-chinese-finetuned-ner_0220_J_ORIDATA
results: []
bert-base-chinese-finetuned-ner_0220_J_ORIDATA
This model is a fine-tuned version of ckiplab/bert-base-chinese-ner on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4109
- Precision: 0.9088
- Recall: 0.9581
- F1: 0.9328
- Accuracy: 0.9478
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.5095 | 1.0 | 884 | 0.2940 | 0.8565 | 0.9269 | 0.8903 | 0.9355 |
| 0.2381 | 2.0 | 1768 | 0.2669 | 0.8910 | 0.9474 | 0.9184 | 0.9442 |
| 0.2057 | 3.0 | 2652 | 0.2566 | 0.9011 | 0.9507 | 0.9252 | 0.9438 |
| 0.1856 | 4.0 | 3536 | 0.2811 | 0.9053 | 0.9507 | 0.9275 | 0.9414 |
| 0.1386 | 5.0 | 4420 | 0.3108 | 0.9019 | 0.9523 | 0.9265 | 0.9481 |
| 0.1224 | 6.0 | 5304 | 0.3265 | 0.8978 | 0.9532 | 0.9247 | 0.9430 |
| 0.0891 | 7.0 | 6188 | 0.3601 | 0.9071 | 0.9548 | 0.9303 | 0.9471 |
| 0.08 | 8.0 | 7072 | 0.3555 | 0.8931 | 0.9540 | 0.9225 | 0.9458 |
| 0.0547 | 9.0 | 7956 | 0.4065 | 0.9089 | 0.9589 | 0.9332 | 0.9482 |
| 0.0539 | 10.0 | 8840 | 0.4109 | 0.9088 | 0.9581 | 0.9328 | 0.9478 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.13.0+cu117
- Datasets 2.8.0
- Tokenizers 0.12.1