bert-ner-chunks
This model is a fine-tuned version of bert-base-cased on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2207
- Precision: 0.8917
- Recall: 0.9214
- F1: 0.9063
- Accuracy: 0.9730
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
- num_epochs: 5
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
Precision |
Recall |
F1 |
Accuracy |
| 0.077 |
1.0 |
1756 |
0.0741 |
0.9068 |
0.9334 |
0.9199 |
0.9795 |
| 0.0443 |
2.0 |
3512 |
0.0649 |
0.9172 |
0.9428 |
0.9298 |
0.9841 |
| 0.0265 |
3.0 |
5268 |
0.0578 |
0.9250 |
0.9488 |
0.9368 |
0.9863 |
| 0.0109 |
4.0 |
7024 |
0.0651 |
0.9347 |
0.9492 |
0.9419 |
0.9866 |
| 0.005 |
5.0 |
8780 |
0.0692 |
0.9354 |
0.9502 |
0.9427 |
0.9869 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
