dpo-selective-redteaming

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

dpo-selective-redteaming

This model is a fine-tuned version of HuggingFaceH4/zephyr-7b-beta on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3718.4153
• Rewards/chosen: -0.4246
• Rewards/rejected: -0.4942
• Rewards/accuracies: 0.5239
• Rewards/margins: 0.0696
• Rewards/safe Rewards: -0.4398
• Rewards/unsafe Rewards: -0.4005
• Logps/rejected: -216.6940
• Logps/chosen: -198.2132
• Logits/rejected: -2.6603
• Logits/chosen: -2.6191

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-07
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2
• Datasets 2.14.6
• Tokenizers 0.15.0