{ "wandb_run": "run-20260630_205146-nqai27su", "wandb_output_log": "/mnt/mole/SDPO/L2T/wandb/run-20260630_205146-nqai27su/files/output.log", "metric_key": "val-aux/sciknoweval/reward/mean@16", "evals": [ { "step": 10, "mean16": 0.34375 }, { "step": 20, "mean16": 0.40125 }, { "step": 30, "mean16": 0.5325 }, { "step": 40, "mean16": 0.55625 }, { "step": 50, "mean16": 0.5675 }, { "step": 60, "mean16": 0.5775 }, { "step": 70, "mean16": 0.55875 }, { "step": 80, "mean16": 0.52 }, { "step": 90, "mean16": 0.54375 }, { "step": 100, "mean16": 0.565 } ], "best_step": 60, "best_mean16": 0.5775, "final_step": 100, "final_mean16": 0.565 }