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: 0.0563
- Precision: 0.9411
- Recall: 0.9524
- F1: 0.9467
- Accuracy: 0.9872
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 |
---|---|---|---|---|---|---|---|
0.0797 | 1.0 | 1756 | 0.0740 | 0.9148 | 0.9382 | 0.9264 | 0.9813 |
0.0416 | 2.0 | 3512 | 0.0544 | 0.9309 | 0.9498 | 0.9403 | 0.9862 |
0.0237 | 3.0 | 5268 | 0.0563 | 0.9411 | 0.9524 | 0.9467 | 0.9872 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1
- Downloads last month
- 9
Finetuned from
Dataset used to train Treether/bert-finetuned-ner
Evaluation results
- Precision on conll2003validation set self-reported0.941
- Recall on conll2003validation set self-reported0.952
- F1 on conll2003validation set self-reported0.947
- Accuracy on conll2003validation set self-reported0.987