DistilBERT-finetuned-ner-conll2003
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: 0.0594
- Precision: 0.9293
- Recall: 0.9424
- F1: 0.9358
- Accuracy: 0.9861
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 |
|---|---|---|---|---|---|---|---|
| 0.0807 | 1.0 | 1756 | 0.0581 | 0.9156 | 0.9317 | 0.9236 | 0.9845 |
| 0.0364 | 2.0 | 3512 | 0.0567 | 0.9252 | 0.9384 | 0.9317 | 0.9852 |
| 0.0202 | 3.0 | 5268 | 0.0594 | 0.9293 | 0.9424 | 0.9358 | 0.9861 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3