jailbreak-prompt-classification
This model is a fine-tuned version of ashield-ai/prompt-classification-bert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: nan
- F1: 0.4955
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 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: 100
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.0 | 1.0 | 6532 | nan | 0.4955 |
| 0.0 | 2.0 | 13064 | nan | 0.4955 |
| 0.0 | 3.0 | 19596 | nan | 0.4955 |
| 0.0 | 4.0 | 26128 | nan | 0.4955 |
| 0.0 | 5.0 | 32660 | nan | 0.4955 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.4.0+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 8
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for ashield-ai/jailbreak-prompt-classification
Base model
answerdotai/ModernBERT-base
Finetuned
ashield-ai/prompt-classification-bert