bert-vir_naeus-ner
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0198
- Precision: 0.8539
- Recall: 0.9225
- F1: 0.8869
- Accuracy: 0.9934
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 |
|---|---|---|---|---|---|---|---|
| 0.0248 | 1.0 | 2949 | 0.0215 | 0.8156 | 0.8921 | 0.8521 | 0.9919 |
| 0.0165 | 2.0 | 5898 | 0.0194 | 0.8376 | 0.9170 | 0.8755 | 0.9930 |
| 0.0096 | 3.0 | 8847 | 0.0198 | 0.8539 | 0.9225 | 0.8869 | 0.9934 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.0