Negation_Scope_Detection_NubEs_Training_Testing_mBERT_fine_tuned
This model is a fine-tuned version of bert-base-multilingual-cased on Nubes (Training + Testing) dataset. It achieves the following results on the evaluation set:
- Loss: 0.2020
- Precision: 0.8911
- Recall: 0.9059
- F1: 0.8984
- Accuracy: 0.9696
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: 5e-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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.189 | 1.0 | 1726 | 0.1664 | 0.8333 | 0.8544 | 0.8437 | 0.9591 |
| 0.14 | 2.0 | 3452 | 0.1588 | 0.8548 | 0.8821 | 0.8682 | 0.9598 |
| 0.0866 | 3.0 | 5178 | 0.1497 | 0.8856 | 0.8853 | 0.8854 | 0.9664 |
| 0.0504 | 4.0 | 6904 | 0.1633 | 0.8747 | 0.8965 | 0.8855 | 0.9668 |
| 0.0311 | 5.0 | 8630 | 0.1870 | 0.8942 | 0.8984 | 0.8963 | 0.9689 |
| 0.0147 | 6.0 | 10356 | 0.1913 | 0.8829 | 0.9041 | 0.8934 | 0.9684 |
| 0.007 | 7.0 | 12082 | 0.2020 | 0.8911 | 0.9059 | 0.8984 | 0.9696 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2