bert-base-uncased-trustairlab-jailbreak-augmented
This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1346
- Accuracy: 0.9598
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 adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5493 | 1.0 | 4240 | 0.2043 | 0.9302 |
| 0.2353 | 2.0 | 8480 | 0.1689 | 0.9442 |
| 0.0884 | 3.0 | 12720 | 0.1558 | 0.9525 |
| 0.1884 | 4.0 | 16960 | 0.1752 | 0.9546 |
| 0.1707 | 5.0 | 21200 | 0.1340 | 0.9597 |
| 0.1012 | 6.0 | 25440 | 0.1505 | 0.9616 |
| 0.0637 | 7.0 | 29680 | 0.1591 | 0.9614 |
| 0.0655 | 8.0 | 33920 | 0.1762 | 0.9630 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2