Negation_Scope_Detection_NubEs_Only_Negations_Training_Development_mBERT_fine_tuned
This model is a fine-tuned version of bert-base-multilingual-cased on Nubes (Only negations - Training + Development) dataset. It achieves the following results on the evaluation set:
- Loss: 0.1139
- Precision: 0.9292
- Recall: 0.9467
- F1: 0.9379
- Accuracy: 0.9832
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 |
|---|---|---|---|---|---|---|---|
| 0.1071 | 1.0 | 1726 | 0.0879 | 0.9155 | 0.9006 | 0.9080 | 0.9773 |
| 0.0796 | 2.0 | 3452 | 0.0922 | 0.8709 | 0.9361 | 0.9023 | 0.9747 |
| 0.0492 | 3.0 | 5178 | 0.0894 | 0.9217 | 0.9336 | 0.9276 | 0.9811 |
| 0.0298 | 4.0 | 6904 | 0.0932 | 0.9150 | 0.9376 | 0.9261 | 0.9802 |
| 0.0179 | 5.0 | 8630 | 0.1100 | 0.9330 | 0.9365 | 0.9348 | 0.9826 |
| 0.0127 | 6.0 | 10356 | 0.1094 | 0.9398 | 0.9342 | 0.9370 | 0.9830 |
| 0.0032 | 7.0 | 12082 | 0.1139 | 0.9292 | 0.9467 | 0.9379 | 0.9832 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2