anil_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: 0.0610
- Precision: 0.9352
- Recall: 0.9517
- F1: 0.9434
- Accuracy: 0.9862
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 |
|---|---|---|---|---|---|---|---|
| 0.0897 | 1.0 | 1756 | 0.0690 | 0.9246 | 0.9325 | 0.9285 | 0.9820 |
| 0.0329 | 2.0 | 3512 | 0.0629 | 0.9301 | 0.9492 | 0.9395 | 0.9862 |
| 0.0172 | 3.0 | 5268 | 0.0610 | 0.9352 | 0.9517 | 0.9434 | 0.9862 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2