{"model_name": "1203_dpo_tune1e-6", "model_type": "dpo", "datasets": ["allenai/olmo-2-1124-7b-preference-mix"], "base_model": "allenai/open_instruct_dev", "wandb_path": "https://wandb.ai/ai2-llm/open_instruct_internal/runs/kltz8oig", "beaker_experiment": "https://beaker.org/ex/01JEF3E0MKF32JXGKMQ46K8TWY/", "beaker_datasets": ["https://beaker.org/ds/01JEF3E0P9QSR2A3RQ9W0PZV44", "https://beaker.org/ds/01JEF3E0W42HKMYE7GAAH9J4F3", "https://beaker.org/ds/01JEF3E125QD41XTAHDCQ01T83", "https://beaker.org/ds/01JEF3E18C6PEPPA3XXZRNXCYB"]}