bert-base-cased-finetuned-ner-conll2003
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: 0.0583
- Precision: 0.9322
- Recall: 0.9485
- F1: 0.9403
- Accuracy: 0.9859
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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 |
|---|---|---|---|---|---|---|---|
| 0.2182 | 1.0 | 878 | 0.0648 | 0.8983 | 0.9310 | 0.9144 | 0.9812 |
| 0.0460 | 2.0 | 1756 | 0.0591 | 0.9253 | 0.9438 | 0.9344 | 0.9847 |
| 0.0241 | 3.0 | 2634 | 0.0583 | 0.9322 | 0.9485 | 0.9403 | 0.9859 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2