Jailbreak Classifier

Classifies prompts as jailbreaks or benign. This is a fine-tune checkpoint of bert-base-uncased on the jailbreak-classification dataaset.

Training Details

Training Data

Fine-tuned on the jailbreak-classification dataaset.

Training Procedure

Training Hyperparameters

Fine-tuning hyper-parameters:

• learning_rate = 5e-5
• per_device_train_batch_size = 8
• per_device_eval_batch_size = 8
• lr_scheduler_type = linear
• num_train_epochs = 5.0