distilbert-base-uncased-jailbreakv-28k-augmented
This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0050
- Accuracy: 0.9980
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 |
|---|---|---|---|---|
| 0.0002 | 1.0 | 7840 | 0.0170 | 0.9955 |
| 0.0002 | 2.0 | 15680 | 0.0166 | 0.9963 |
| 0.0147 | 3.0 | 23520 | 0.0093 | 0.9973 |
| 0.0152 | 4.0 | 31360 | 0.0073 | 0.9978 |
| 0.0197 | 5.0 | 39200 | 0.0075 | 0.9978 |
| 0.0047 | 6.0 | 47040 | 0.0078 | 0.9980 |
| 0.0066 | 7.0 | 54880 | 0.0050 | 0.9980 |
| 0.0000 | 8.0 | 62720 | 0.0056 | 0.9980 |
| 0.0105 | 9.0 | 70560 | 0.0055 | 0.9979 |
| 0.0132 | 10.0 | 78400 | 0.0062 | 0.9978 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2