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: 0.0620
- Precision: 0.9307
- Recall: 0.9498
- F1: 0.9402
- Accuracy: 0.9860
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 |
---|---|---|---|---|---|---|---|
0.0868 | 1.0 | 1756 | 0.0699 | 0.9197 | 0.9352 | 0.9274 | 0.9821 |
0.0324 | 2.0 | 3512 | 0.0659 | 0.9202 | 0.9455 | 0.9327 | 0.9849 |
0.0162 | 3.0 | 5268 | 0.0620 | 0.9307 | 0.9498 | 0.9402 | 0.9860 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
- Downloads last month
- 27
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Dataset used to train huynguyen208/bert-finetuned-ner
Evaluation results
- Precision on conll2003self-reported0.931
- Recall on conll2003self-reported0.950
- F1 on conll2003self-reported0.940
- Accuracy on conll2003self-reported0.986