jmajkutewicz/Llama-3.1-Tulu-3-8B-DPO_ultrafeedback

Tülu3 8B aligned with DPO on UltraFeedback with β=0.01

This repo contains LoRA adapter created by aligning Tülu3 8B on the UltraFeedback Binarized dataset using Direct Preference Optimization (DPO). It was trained as a series of models for studying DPO alignment.

Model details

• Base model: allenai/Llama-3.1-Tulu-3-8B-SFT
• Preference dataset: HuggingFaceH4/ultrafeedback_binarized
• DPO beta: 0.01
• Training framework: PEFT/LoRA

See the base model card for usage and chat template details.

Training hyperparameters

• Epochs: 1
• Batch size: 8
• Learning rate: 1e-05
• Learning rate scheduler: cosine
• Learning rate warmup ratio: 0.1
• Gradient accumulation: 2
• LoRA:
  • rank: 64
  • alpha: 64
  • dropout: 0.05
  • target modules: [q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj]

License

This adapter is released under Meta's Llama 3.1 Community License Agreement. Llama 3.1 is © Meta Platforms, Inc.

Citation

If this work was helpful, please cite:

TBA