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: 0.0606
- Precision: 0.9340
- Recall: 0.9510
- F1: 0.9425
- Accuracy: 0.9867
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 |
---|---|---|---|---|---|---|---|
0.0877 | 1.0 | 1756 | 0.0640 | 0.9132 | 0.9325 | 0.9227 | 0.9827 |
0.0336 | 2.0 | 3512 | 0.0615 | 0.9275 | 0.9480 | 0.9377 | 0.9861 |
0.0174 | 3.0 | 5268 | 0.0606 | 0.9340 | 0.9510 | 0.9425 | 0.9867 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 8
Dataset used to train steven-qi-zhao/bert-finetuned-ner
Evaluation results
- Precision on conll2003validation set self-reported0.934
- Recall on conll2003validation set self-reported0.951
- F1 on conll2003validation set self-reported0.942
- Accuracy on conll2003validation set self-reported0.987