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: 0.0614
- Overall precision: 0.9382
- Overall recall: 0.9507
- Overall f1: 0.9444
- Overall accuracy: 0.9870
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Overall precision | Overall recall | Overall f1 | Overall accuracy |
|---|---|---|---|---|---|---|---|
| 0.0748 | 1.0 | 1756 | 0.0606 | 0.9095 | 0.9372 | 0.9232 | 0.9828 |
| 0.0334 | 2.0 | 3512 | 0.0652 | 0.9332 | 0.9482 | 0.9406 | 0.9860 |
| 0.0192 | 3.0 | 5268 | 0.0614 | 0.9382 | 0.9507 | 0.9444 | 0.9870 |
Framework versions
- Transformers 4.53.0
- Pytorch 2.7.1+cu118
- Datasets 3.6.0
- Tokenizers 0.21.2