bert-base-cased-prompt_tuning-legal
This model is a fine-tuned version of google-bert/bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5850
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6333 | 1.0 | 61 | 0.6080 |
| 0.6333 | 2.0 | 122 | 0.6031 |
| 0.6287 | 3.0 | 183 | 0.5988 |
| 0.6373 | 4.0 | 244 | 0.5951 |
| 0.6121 | 5.0 | 305 | 0.5920 |
| 0.6222 | 6.0 | 366 | 0.5895 |
| 0.6215 | 7.0 | 427 | 0.5876 |
| 0.6162 | 8.0 | 488 | 0.5861 |
| 0.6093 | 9.0 | 549 | 0.5853 |
| 0.6206 | 10.0 | 610 | 0.5850 |
Framework versions
- PEFT 0.16.0
- Transformers 4.53.2
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.2