{ "wandb_run": "run-20260701_005129-3hqobzfs", "wandb_output_log": "/mnt/mole/SDPO/L2T/wandb/run-20260701_005129-3hqobzfs/files/output.log", "metric_key": "val-aux/sciknoweval/reward/mean@16", "evals": [ { "step": 10, "mean16": 0.6894946808510638 }, { "step": 20, "mean16": 0.706781914893617 }, { "step": 30, "mean16": 0.7473404255319149 }, { "step": 40, "mean16": 0.754654255319149 }, { "step": 50, "mean16": 0.7632978723404256 }, { "step": 60, "mean16": 0.7785904255319149 }, { "step": 70, "mean16": 0.7699468085106383 }, { "step": 80, "mean16": 0.773936170212766 }, { "step": 90, "mean16": 0.7799202127659575 }, { "step": 100, "mean16": 0.7805851063829787 } ], "best_step": 100, "best_mean16": 0.7805851063829787, "final_step": 100, "final_mean16": 0.7805851063829787 }