{ "device": "mps", "n_episodes": 12, "eval_seed": 0, "max_new_tokens": 384, "baseline": { "model": "Qwen/Qwen3-0.6B", "mean_reward": 0.5394954166666667, "rewards": [ 0.49674999999999997, 0.6875500000000001, 0.05, 0.54325, 0.7235050000000001, 0.5267499999999999, 0.7247800000000001, 0.7245250000000001, 0.6965800000000001, 0.7235050000000001, 0.05, 0.5267499999999999 ], "components_mean": { "format_valid": 0.8333333333333334, "decision_match": 0.5, "score_alignment": 0.373025, "reason_quality": 0.0, "length_penalty": 1.0, "no_hallucination": 0.7791666666666667, "total": 0.5394954166666667 }, "wall_seconds": 107.62254476547241 }, "trained": { "model": "williyam/redrob-qwen-grpo", "mean_reward": 0.7129858675096833, "rewards": [ 0.5129642857142858, 0.9165815789473685, 0.5111792857142857, 0.515, 0.9074595454545454, 0.51275, 0.9070771428571428, 0.9172250000000001, 0.91517, 0.9152192857142857, 0.51224, 0.5129642857142858 ], "components_mean": { "format_valid": 1.0, "decision_match": 0.5, "score_alignment": 0.6529333333333334, "reason_quality": 0.7780835611756665, "length_penalty": 1.0, "no_hallucination": 0.6555555555555556, "total": 0.7129858675096833 }, "wall_seconds": 67.35159301757812 }, "uplift": 0.17349045084301662 }