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: 0.0858
- Precition: 0.9363
- Recall: 0.9522
- F1: 0.9442
- Accuracy: 0.9866
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 | Precition | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.0081 | 1.0 | 1756 | 0.0914 | 0.9273 | 0.9446 | 0.9359 | 0.9848 |
0.012 | 2.0 | 3512 | 0.0852 | 0.9321 | 0.9478 | 0.9399 | 0.9857 |
0.0036 | 3.0 | 5268 | 0.0858 | 0.9363 | 0.9522 | 0.9442 | 0.9866 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
- Downloads last month
- 9
Dataset used to train hieule/bert-finetuned-ner
Evaluation results
- Recall on conll2003self-reported0.952
- F1 on conll2003self-reported0.944
- Accuracy on conll2003self-reported0.987