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: 0.0629
- Precision: 0.9356
- Recall: 0.9509
- F1: 0.9432
- 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 | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.0743 | 1.0 | 1756 | 0.0638 | 0.9066 | 0.9325 | 0.9194 | 0.9814 |
0.0354 | 2.0 | 3512 | 0.0688 | 0.9325 | 0.9460 | 0.9392 | 0.9849 |
0.0225 | 3.0 | 5268 | 0.0629 | 0.9356 | 0.9509 | 0.9432 | 0.9866 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 2
Finetuned from
Dataset used to train Qyzi/bert-finetuned-ner
Evaluation results
- Precision on conll2003validation set self-reported0.936
- Recall on conll2003validation set self-reported0.951
- F1 on conll2003validation set self-reported0.943
- Accuracy on conll2003validation set self-reported0.987