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: 0.0634
- Precision: 0.9378
- Recall: 0.9509
- F1: 0.9443
- Accuracy: 0.9862
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 |
---|---|---|---|---|---|---|---|
0.0792 | 1.0 | 1756 | 0.0841 | 0.9079 | 0.9325 | 0.9200 | 0.9790 |
0.0394 | 2.0 | 3512 | 0.0571 | 0.9292 | 0.9478 | 0.9384 | 0.9861 |
0.0252 | 3.0 | 5268 | 0.0634 | 0.9378 | 0.9509 | 0.9443 | 0.9862 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.15.2
- Downloads last month
- 0
Model tree for benshafat/bert-finetuned-ner
Base model
google-bert/bert-base-casedDataset used to train benshafat/bert-finetuned-ner
Evaluation results
- Precision on conll2003validation set self-reported0.938
- Recall on conll2003validation set self-reported0.951
- F1 on conll2003validation set self-reported0.944
- Accuracy on conll2003validation set self-reported0.986