distilbert-base-uncased-finetuned-ner-conll
This model is a fine-tuned version of distilbert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0618
- Precision: 0.9275
- Recall: 0.9358
- F1: 0.9316
- Accuracy: 0.9837
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 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 |
|---|---|---|---|---|---|---|---|
| 0.2391 | 1.0 | 878 | 0.0698 | 0.8993 | 0.9191 | 0.9091 | 0.9797 |
| 0.0529 | 2.0 | 1756 | 0.0609 | 0.92 | 0.9340 | 0.9269 | 0.9829 |
| 0.0304 | 3.0 | 2634 | 0.0618 | 0.9275 | 0.9358 | 0.9316 | 0.9837 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1