{"model_name": "multipref_dpo_human_overall", "model_type": "dpo", "datasets": ["ai2-adapt-dev/multipref-human-overall-binarized"], "base_model": "allenai/Llama-3.1-Tulu-3-8B-SFT", "wandb_path": "https://wandb.ai/ai2-llm/open_instruct_internal/runs/c2ucmm77", "beaker_experiment": "https://beaker.org/ex/01JKCNKK7CZS2NG0Z3481P37AZ/", "beaker_datasets": ["https://beaker.org/ds/01JKCNKK91B7CGG79CA9GKGH11"]}