<!-- 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_somaire10
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: 0.7357
- F1: 0.6976
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 |
|---|---|---|---|---|
| No log | 1.0 | 188 | 1.2332 | 0.7096 |
| No log | 2.0 | 376 | 0.8667 | 0.7096 |
| 1.2755 | 3.0 | 564 | 0.7313 | 0.7425 |
| 1.2755 | 4.0 | 752 | 0.7238 | 0.7365 |
| 1.2755 | 5.0 | 940 | 0.7191 | 0.7335 |
| 0.5624 | 6.0 | 1128 | 0.6850 | 0.7216 |
| 0.5624 | 7.0 | 1316 | 0.7225 | 0.7126 |
| 0.4358 | 8.0 | 1504 | 0.7215 | 0.7126 |
| 0.4358 | 9.0 | 1692 | 0.7374 | 0.7006 |
| 0.4358 | 10.0 | 1880 | 0.7357 | 0.6976 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1
