{ "wandb_run": "run-20260630_014254-tpv9xlh5", "wandb_output_log": "/mnt/mole/SDPO/L2T/wandb/run-20260630_014254-tpv9xlh5/files/output.log", "metric_key": "val-aux/sciknoweval/reward/mean@16", "evals": [ { "step": 10, "mean16": 0.6376329787234043 }, { "step": 20, "mean16": 0.7406914893617021 }, { "step": 30, "mean16": 0.7659574468085106 }, { "step": 40, "mean16": 0.7586436170212766 }, { "step": 50, "mean16": 0.7672872340425532 }, { "step": 60, "mean16": 0.7719414893617021 }, { "step": 70, "mean16": 0.7293882978723404 }, { "step": 80, "mean16": 0.7300531914893617 }, { "step": 90, "mean16": 0.7400265957446809 }, { "step": 100, "mean16": 0.7626329787234043 } ], "best_step": 60, "best_mean16": 0.7719414893617021, "final_step": 100, "final_mean16": 0.7626329787234043 }