g-bert-NER
This model is a fine-tuned version of google-bert/bert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1387
- Precision: 0.8925
- Recall: 0.9102
- F1: 0.9013
- Accuracy: 0.9800
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1773 | 1.0 | 878 | 0.1028 | 0.8910 | 0.8947 | 0.8928 | 0.9781 |
| 0.036 | 2.0 | 1756 | 0.1125 | 0.8901 | 0.9132 | 0.9015 | 0.9793 |
| 0.0194 | 3.0 | 2634 | 0.1202 | 0.8948 | 0.9093 | 0.9020 | 0.9800 |
| 0.0112 | 4.0 | 3512 | 0.1346 | 0.8889 | 0.9136 | 0.9011 | 0.9794 |
| 0.0081 | 5.0 | 4390 | 0.1387 | 0.8925 | 0.9102 | 0.9013 | 0.9800 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1