<!-- 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. -->
bert-finetuned-ner
This model is a fine-tuned version of bert-base-cased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0613
- Precision: 0.9376
- Recall: 0.9527
- F1: 0.9451
- Accuracy: 0.9866
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0886 | 1.0 | 1756 | 0.0764 | 0.9176 | 0.9315 | 0.9245 | 0.9801 |
| 0.0342 | 2.0 | 3512 | 0.0618 | 0.9292 | 0.9482 | 0.9386 | 0.9859 |
| 0.0168 | 3.0 | 5268 | 0.0613 | 0.9376 | 0.9527 | 0.9451 | 0.9866 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
