<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
legal_text_classifier_10_class
This model is a fine-tuned version of aubmindlab/bert-base-arabertv2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2908
- F1: 0.9329
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 84 | 0.7287 | 0.8255 |
| No log | 2.0 | 168 | 0.3221 | 0.9262 |
| No log | 3.0 | 252 | 0.3014 | 0.9060 |
| No log | 4.0 | 336 | 0.3104 | 0.9128 |
| No log | 5.0 | 420 | 0.2636 | 0.9262 |
| 0.4014 | 6.0 | 504 | 0.2793 | 0.9262 |
| 0.4014 | 7.0 | 588 | 0.2509 | 0.9262 |
| 0.4014 | 8.0 | 672 | 0.2715 | 0.9329 |
| 0.4014 | 9.0 | 756 | 0.2688 | 0.9329 |
| 0.4014 | 10.0 | 840 | 0.2850 | 0.9329 |
| 0.4014 | 11.0 | 924 | 0.2972 | 0.9329 |
| 0.069 | 12.0 | 1008 | 0.2783 | 0.9329 |
| 0.069 | 13.0 | 1092 | 0.2942 | 0.9329 |
| 0.069 | 14.0 | 1176 | 0.2725 | 0.9329 |
| 0.069 | 15.0 | 1260 | 0.2594 | 0.9329 |
| 0.069 | 16.0 | 1344 | 0.2768 | 0.9329 |
| 0.069 | 17.0 | 1428 | 0.2889 | 0.9329 |
| 0.0447 | 18.0 | 1512 | 0.2908 | 0.9329 |
| 0.0447 | 19.0 | 1596 | 0.2880 | 0.9329 |
| 0.0447 | 20.0 | 1680 | 0.2908 | 0.9329 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1
