bert-finetuned-ner
This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0655
- Precision: 0.9313
- Recall: 0.9512
- F1: 0.9411
- Accuracy: 0.9867
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 |
---|---|---|---|---|---|---|---|
0.0449 | 1.0 | 1756 | 0.0654 | 0.9107 | 0.9359 | 0.9231 | 0.9832 |
0.0271 | 2.0 | 3512 | 0.0645 | 0.9325 | 0.9485 | 0.9404 | 0.9861 |
0.0133 | 3.0 | 5268 | 0.0655 | 0.9313 | 0.9512 | 0.9411 | 0.9867 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 2