|
--- |
|
base_model: mistralai/Mistral-Nemo-Instruct-2407 |
|
datasets: allenai/wildjailbreak |
|
tags: |
|
- trl |
|
- sft |
|
- red-teamer-model |
|
- jailbreaking |
|
- generated_from_trainer |
|
--- |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) on the [wildjailbreak](https://huggingface.co/datasets/allenai/wildjailbreak) dataset. Only the `adversarial_harmful` data types have been used for training. |
|
|
|
## Uses |
|
|
|
This model is intended to be used for red-teaming purposes only. It generates prompts that are likely to evade existing LLMs' content filters based on the user's input. |
|
|
|
→ The HarmBench evaluation will be released soon. |
|
|
|
## Training Hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-05 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine_with_restarts |
|
- lr_scheduler_warmup_ratio: 0.05 |
|
- num_epochs: 1 |
|
|
|
## Results |
|
|
|
| Epoch | Step | Validation Loss | Training Loss | |
|
|:------:|:----:|:---------------:|:-------------:| |
|
| 0.0982 | 20 | 1.2933 | 1.3425 | |
|
| 0.1965 | 40 | 1.1966 | 1.2067 | |
|
| 0.2947 | 60 | 1.1594 | 1.1544 | |
|
| 0.3930 | 80 | 1.1386 | 1.1427 | |
|
| 0.4912 | 100 | 1.1259 | 1.1235 | |
|
| 0.5895 | 120 | 1.1179 | 1.1167 | |
|
| 0.6877 | 140 | 1.1129 | 1.1153 | |
|
| 0.7860 | 160 | 1.1098 | 1.1118 | |
|
| 0.8842 | 180 | 1.1086 | 1.1112 | |
|
| 0.9825 | 200 | 1.1083 | 1.1113 | |