{ "wandb_run": "run-20260701_023114-1704cjhy", "wandb_output_log": "/mnt/mole/SDPO/L2T/wandb/run-20260701_023114-1704cjhy/files/output.log", "metric_key": "val-aux/sciknoweval/reward/mean@16", "evals": [ { "step": 10, "mean16": 0.699468085106383 }, { "step": 20, "mean16": 0.7253989361702128 }, { "step": 30, "mean16": 0.7539893617021277 }, { "step": 40, "mean16": 0.7632978723404256 }, { "step": 50, "mean16": 0.7613031914893617 }, { "step": 60, "mean16": 0.7340425531914894 }, { "step": 70, "mean16": 0.7460106382978723 }, { "step": 80, "mean16": 0.7480053191489362 }, { "step": 90, "mean16": 0.7613031914893617 }, { "step": 100, "mean16": 0.7905585106382979 } ], "best_step": 100, "best_mean16": 0.7905585106382979, "final_step": 100, "final_mean16": 0.7905585106382979 }