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: 0.0670
- Precision: 0.9329
- Recall: 0.9519
- F1: 0.9423
- 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 |
---|---|---|---|---|---|---|---|
0.025 | 1.0 | 1756 | 0.0677 | 0.9269 | 0.9472 | 0.9369 | 0.9848 |
0.0227 | 2.0 | 3512 | 0.0681 | 0.9302 | 0.9482 | 0.9391 | 0.9857 |
0.015 | 3.0 | 5268 | 0.0670 | 0.9329 | 0.9519 | 0.9423 | 0.9867 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 18
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for linqus/bert-finetuned-ner
Base model
google-bert/bert-base-casedDataset used to train linqus/bert-finetuned-ner
Evaluation results
- Precision on conll2003validation set self-reported0.933
- Recall on conll2003validation set self-reported0.952
- F1 on conll2003validation set self-reported0.942
- Accuracy on conll2003validation set self-reported0.987