{ "wandb_run": "run-20260630_103227-flhubvrx", "wandb_output_log": "/mnt/mole/SDPO/L2T/wandb/run-20260630_103227-flhubvrx/files/output.log", "metric_key": "val-aux/sciknoweval/reward/mean@16", "evals": [ { "step": 10, "mean16": 0.45535714285714285 }, { "step": 20, "mean16": 0.5964285714285714 }, { "step": 30, "mean16": 0.6720238095238096 }, { "step": 40, "mean16": 0.6904761904761905 }, { "step": 50, "mean16": 0.7211309523809524 }, { "step": 60, "mean16": 0.7389880952380953 }, { "step": 70, "mean16": 0.7458333333333333 }, { "step": 80, "mean16": 0.7651785714285714 }, { "step": 90, "mean16": 0.7642857142857142 }, { "step": 100, "mean16": 0.7949404761904761 } ], "best_step": 100, "best_mean16": 0.7949404761904761, "final_step": 100, "final_mean16": 0.7949404761904761 }