{ "base_model": "Qwen/Qwen3.5-2B", "arms": 12, "selection_steps": 40, "confirmation_steps": 100, "batch_size": 32, "max_seq_len": 2048, "n_eval_validation": 500, "n_eval_test": 500, "n_ifeval_secondary": 0, "planned_arm_steps": 840, "pilot_arms": 2, "pilot_steps": 10, "note": "IFEval dropped (downsizing step 1); LR grid, selection steps, seeds, test NLL unchanged" }