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: 0.0601
- Precision: 0.9395
- Recall: 0.9542
- F1: 0.9468
- Accuracy: 0.9868
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 |
---|---|---|---|---|---|---|---|
0.0784 | 1.0 | 1756 | 0.0813 | 0.9078 | 0.9308 | 0.9192 | 0.9793 |
0.0402 | 2.0 | 3512 | 0.0573 | 0.9294 | 0.9467 | 0.9380 | 0.9854 |
0.0233 | 3.0 | 5268 | 0.0601 | 0.9395 | 0.9542 | 0.9468 | 0.9868 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 9
Finetuned from
Dataset used to train David-ing/BertFinetunedNer0
Evaluation results
- Precision on conll2003validation set self-reported0.940
- Recall on conll2003validation set self-reported0.954
- F1 on conll2003validation set self-reported0.947
- Accuracy on conll2003validation set self-reported0.987