finetuned-wav2vec2-jailbreak-roleplay

This model is a fine-tuned version of assoni2002/wav2vec2-jailbreak-classification_new on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2063
• Accuracy: 0.95

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: 1e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.4178	1.0	5	0.9412	0.6
0.4836	2.0	10	0.4918	0.8
0.3961	3.0	15	0.3995	0.85
0.3672	4.0	20	0.3872	0.85
0.3326	5.0	25	0.3846	0.85

Framework versions

• Transformers 4.53.3
• Pytorch 2.7.1+cu126
• Datasets 4.0.0
• Tokenizers 0.21.2