bert-finetuned-for-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: 0.1653
- Precision: 0.7733
- Recall: 0.7915
- F1: 0.7823
- Accuracy: 0.9493
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 |
---|---|---|---|---|---|---|---|
No log | 1.0 | 125 | 0.2616 | 0.6787 | 0.7156 | 0.6966 | 0.9261 |
No log | 2.0 | 250 | 0.1916 | 0.7397 | 0.7650 | 0.7522 | 0.9411 |
No log | 3.0 | 375 | 0.1653 | 0.7733 | 0.7915 | 0.7823 | 0.9493 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu117
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 9
Finetuned from
Dataset used to train sunny2309/bert-finetuned-for-ner
Evaluation results
- Precision on conll2003validation set self-reported0.773
- Recall on conll2003validation set self-reported0.791
- F1 on conll2003validation set self-reported0.782
- Accuracy on conll2003validation set self-reported0.949