{ "wandb_run": "run-20260630_003605-tfw9z9dp", "wandb_output_log": "/mnt/mole/SDPO/L2T/wandb/run-20260630_003605-tfw9z9dp/files/output.log", "metric_key": "val-aux/sciknoweval/reward/mean@16", "evals": [ { "step": 10, "mean16": 0.6775265957446809 }, { "step": 20, "mean16": 0.7253989361702128 }, { "step": 30, "mean16": 0.7712765957446809 }, { "step": 40, "mean16": 0.7832446808510638 }, { "step": 50, "mean16": 0.5877659574468085 }, { "step": 60, "mean16": 0.6163563829787234 }, { "step": 70, "mean16": 0.7001329787234043 }, { "step": 80, "mean16": 0.668218085106383 }, { "step": 90, "mean16": 0.6788563829787234 }, { "step": 100, "mean16": 0.6615691489361702 } ], "best_step": 40, "best_mean16": 0.7832446808510638, "final_step": 100, "final_mean16": 0.6615691489361702 }