<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
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: 0.0610
- Precision: 0.9281
- Recall: 0.9473
- F1: 0.9376
- Accuracy: 0.9863
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 |
---|---|---|---|---|---|---|---|
0.0859 | 1.0 | 1756 | 0.0663 | 0.9088 | 0.9312 | 0.9199 | 0.9822 |
0.0331 | 2.0 | 3512 | 0.0622 | 0.9270 | 0.9461 | 0.9365 | 0.9856 |
0.016 | 3.0 | 5268 | 0.0610 | 0.9281 | 0.9473 | 0.9376 | 0.9863 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2