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: 0.0675
- Precision: 0.9276
- Recall: 0.9470
- F1: 0.9372
- Accuracy: 0.9853
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 |
---|---|---|---|---|---|---|---|
0.078 | 1.0 | 1756 | 0.0712 | 0.9212 | 0.9364 | 0.9287 | 0.9829 |
0.0288 | 2.0 | 3512 | 0.0682 | 0.9281 | 0.9472 | 0.9375 | 0.9853 |
0.0149 | 3.0 | 5268 | 0.0675 | 0.9276 | 0.9470 | 0.9372 | 0.9853 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2
- Downloads last month
- 1
Dataset used to train Dewa/bert-finetuned-ner
Evaluation results
- Precision on conll2003validation set self-reported0.928
- Recall on conll2003validation set self-reported0.947
- F1 on conll2003validation set self-reported0.937
- Accuracy on conll2003validation set self-reported0.985