legal-bert-cuad-risk-analyzer
This model is a fine-tuned version of nlpaueb/legal-bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.3410
- F1: 0.0106
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 336 | 3.3880 | 0.0048 |
| 6.8408 | 2.0 | 672 | 3.3921 | 0.0072 |
| 6.7062 | 3.0 | 1008 | 3.3780 | 0.0090 |
| 6.7062 | 4.0 | 1344 | 3.3591 | 0.0084 |
| 6.5719 | 5.0 | 1680 | 3.3621 | 0.0061 |
| 6.5001 | 6.0 | 2016 | 3.3828 | 0.0059 |
| 6.5001 | 7.0 | 2352 | 3.3970 | 0.0066 |
| 6.3904 | 8.0 | 2688 | 3.4140 | 0.0048 |
| 6.3042 | 9.0 | 3024 | 3.4417 | 0.0039 |
| 6.3042 | 10.0 | 3360 | 3.4631 | 0.0025 |
| 6.1978 | 11.0 | 3696 | 3.4738 | 0.0028 |
| 6.1852 | 12.0 | 4032 | 3.5027 | 0.0013 |
| 6.1852 | 13.0 | 4368 | 3.5194 | 0.0 |
| 6.1082 | 14.0 | 4704 | 3.5289 | 0.0012 |
| 6.0711 | 15.0 | 5040 | 3.5338 | 0.0011 |
Framework versions
- Transformers 5.13.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2