bert-large-finetuned-ner
This model is a fine-tuned version of bert-large-cased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0535
- Precision: 0.9484
- Recall: 0.9598
- F1: 0.9541
- Accuracy: 0.9893
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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0661 | 1.0 | 1756 | 0.0568 | 0.9261 | 0.9446 | 0.9353 | 0.9850 |
| 0.0282 | 2.0 | 3512 | 0.0555 | 0.9469 | 0.9551 | 0.9510 | 0.9883 |
| 0.0156 | 3.0 | 5268 | 0.0535 | 0.9484 | 0.9598 | 0.9541 | 0.9893 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.1.0+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0