Negation_Scope_Detection_NubEs_Only_Negations_Training_Testing_mBERT_fine_tuned
This model is a fine-tuned version of bert-base-multilingual-cased on Nubes (Only negations - Training + Testing) dataset. It achieves the following results on the evaluation set:
- Loss: 0.1704
- Precision: 0.9240
- Recall: 0.9345
- F1: 0.9292
- Accuracy: 0.9792
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 |
|---|---|---|---|---|---|---|---|
| 0.0348 | 1.0 | 1726 | 0.1148 | 0.9060 | 0.9279 | 0.9168 | 0.9772 |
| 0.0218 | 2.0 | 3452 | 0.1222 | 0.9239 | 0.9181 | 0.9210 | 0.9782 |
| 0.0158 | 3.0 | 5178 | 0.1287 | 0.9211 | 0.9288 | 0.9249 | 0.9786 |
| 0.0149 | 4.0 | 6904 | 0.1520 | 0.9248 | 0.9191 | 0.9219 | 0.9782 |
| 0.0069 | 5.0 | 8630 | 0.1699 | 0.9239 | 0.9275 | 0.9257 | 0.9785 |
| 0.0037 | 6.0 | 10356 | 0.1599 | 0.9273 | 0.9308 | 0.9290 | 0.9793 |
| 0.0023 | 7.0 | 12082 | 0.1704 | 0.9240 | 0.9345 | 0.9292 | 0.9792 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2