bert-ner
This model is a fine-tuned version of bert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0648
- Precision: 0.9420
- Recall: 0.9513
- F1: 0.9466
- Accuracy: 0.9864
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: 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 |
---|---|---|---|---|---|---|---|
0.2234 | 1.0 | 878 | 0.0648 | 0.9110 | 0.9327 | 0.9217 | 0.9821 |
0.0443 | 2.0 | 1756 | 0.0552 | 0.9345 | 0.9432 | 0.9388 | 0.9854 |
0.0258 | 3.0 | 2634 | 0.0571 | 0.9385 | 0.9451 | 0.9418 | 0.9856 |
0.0139 | 4.0 | 3512 | 0.0623 | 0.9413 | 0.9500 | 0.9456 | 0.9863 |
0.0098 | 5.0 | 4390 | 0.0648 | 0.9420 | 0.9513 | 0.9466 | 0.9864 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
- Downloads last month
- 9
Finetuned from
Dataset used to train fahmiaziz/bert-ner
Evaluation results
- Precision on conll2003validation set self-reported0.942
- Recall on conll2003validation set self-reported0.951
- F1 on conll2003validation set self-reported0.947
- Accuracy on conll2003validation set self-reported0.986