<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
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: 0.0810
- Precision: 0.9396
- Recall: 0.9551
- F1: 0.9473
- Accuracy: 0.9878
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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.0221 | 1.0 | 1756 | 0.1039 | 0.9007 | 0.9278 | 0.9140 | 0.9797 |
0.0132 | 2.0 | 3512 | 0.0808 | 0.9286 | 0.9472 | 0.9378 | 0.9854 |
0.0092 | 3.0 | 5268 | 0.0827 | 0.9301 | 0.9488 | 0.9394 | 0.9857 |
0.006 | 4.0 | 7024 | 0.0781 | 0.9392 | 0.9542 | 0.9467 | 0.9878 |
0.0022 | 5.0 | 8780 | 0.0810 | 0.9396 | 0.9551 | 0.9473 | 0.9878 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2