{ "method": "ronpo-ablation", "mode": "full_expect", "pair_variant": "bestadv_sample1", "ronpo_policy_pair_mode": "best_vs_adversary", "adversary_selection": "sample", "seed": 42, "status": "completed", "returncode": 0, "completed_at": "2026-07-11T23:03:13Z", "source_dataset": "/NHNHOME/WORKSPACE/26msit001_A/BASE/aipr_lab_sjkim_eval/revision_qwen3_8b/full_iter1/precomputed/avg_oracle", "dataset": "/NHNHOME/WORKSPACE/26msit001_A/BASE/aipr_lab_sjkim_eval/revision_qwen3_8b/full_iter1/precomputed/full_expect_bestadv_sample1", "pairs": "/NHNHOME/WORKSPACE/26msit001_A/BASE/aipr_lab_sjkim_eval/revision_qwen3_8b/full_iter1/pairs/full_expect_bestadv_sample1", "output_dir": "/NHNHOME/WORKSPACE/26msit001_A/BASE/aipr_lab_sjkim_eval/revision_qwen3_8b/full_iter1/train/ronpo_full_expect_s42_ronpo-bestadv-20260712-0750-r3-sample1_lr5e7_a1_s75_sft5e3", "config": "/NHNHOME/WORKSPACE/26msit001_A/BASE/aipr_lab_sjkim_eval/revision_qwen3_8b/full_iter1/train/ronpo_full_expect_s42_ronpo-bestadv-20260712-0750-r3-sample1_lr5e7_a1_s75_sft5e3/config.yaml", "train_metrics_exists": true, "trainer_state_exists": true }