metadata

language:
  - en
datasets:
  - Open-Orca/OpenOrca
  - jackhhao/jailbreak-classification
metrics:
  - accuracy
library_name: transformers
pipeline_tag: text-classification
tags:
  - jailbreak
  - security
  - moderation
  - prompt-injection

Jailbreak Classifier

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

Training Details

Training Data

Fine-tuned on the jailbreak-classification dataset.

Training Procedure

Training Hyperparameters

Fine-tuning hyper-parameters(on train(0.8) and val(0.2))

learning_rate = 5e-5
train_batch_size = 8
eval_batch_size = 8
lr_scheduler_type = linear
num_train_epochs = 5.0

second fine-tuning hyper-parameters(on train and test)

learning_rate = 1e-5
train_batch_size = 8
eval_batch_size = 8
lr_scheduler_type = linear
num_train_epochs = 3.0