{ "version": "28befdbd2782031fe8d67975", "source_checkpoint": "/private/StatePlay-main/outputs/rl_posttrain/study_v1/reward_model/versions/a-002280/checkpoints/step-00000132", "adapter_sha256": "81078f22d9cbdddde35f1c818d53bdf079316d88f30ca7ad63dc99e0c0e605e6", "selected_using": "validation_only" }