<!-- 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_50_classA
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: 1.4503
- F1: 0.6348
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.7149 | 1.0 | 1582 | 0.9541 | 0.6683 |
| 0.5199 | 2.0 | 3164 | 1.1329 | 0.6635 |
| 0.4678 | 3.0 | 4746 | 1.1535 | 0.6516 |
| 0.4338 | 4.0 | 6328 | 1.1667 | 0.6516 |
| 0.4052 | 5.0 | 7910 | 1.2930 | 0.6492 |
| 0.3817 | 6.0 | 9492 | 1.3078 | 0.6372 |
| 0.3798 | 7.0 | 11074 | 1.3624 | 0.6325 |
| 0.3738 | 8.0 | 12656 | 1.3872 | 0.6325 |
| 0.3612 | 9.0 | 14238 | 1.4459 | 0.6348 |
| 0.3501 | 10.0 | 15820 | 1.4503 | 0.6348 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1
