arabic-offensive-comment-model
This model is a fine-tuned version of aubmindlab/bert-base-arabertv02-twitter on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2989
- Accuracy: 0.9167
- F1: 0.8197
- Precision: 0.8507
- Recall: 0.7959
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 | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.3048 | 1.0 | 675 | 0.2989 | 0.9167 | 0.8197 | 0.8507 | 0.7959 |
| 0.1519 | 2.0 | 1350 | 0.4141 | 0.915 | 0.8341 | 0.8268 | 0.8420 |
| 0.0398 | 3.0 | 2025 | 0.5259 | 0.9033 | 0.8105 | 0.8049 | 0.8163 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3