distilbert-base-uncased-trustairlab-jailbreak-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: 0.1294
- Accuracy: 0.9595
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 |
|---|---|---|---|---|
| 0.4828 | 1.0 | 4240 | 0.1938 | 0.9305 |
| 0.3309 | 2.0 | 8480 | 0.1615 | 0.9463 |
| 0.1351 | 3.0 | 12720 | 0.1614 | 0.9521 |
| 0.2537 | 4.0 | 16960 | 0.1668 | 0.9574 |
| 0.1638 | 5.0 | 21200 | 0.1295 | 0.9594 |
| 0.1145 | 6.0 | 25440 | 0.1667 | 0.9588 |
| 0.0597 | 7.0 | 29680 | 0.1706 | 0.9598 |
| 0.0529 | 8.0 | 33920 | 0.1880 | 0.9600 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2