{ "wandb_run": "run-20260701_061001-b0l3abu5", "wandb_output_log": "/mnt/mole/SDPO/L2T/wandb/run-20260701_061001-b0l3abu5/files/output.log", "metric_key": "val-aux/tooluse/reward/mean@16", "evals": [ { "step": 10, "mean16": 0.5882352941176471 }, { "step": 20, "mean16": 0.6222426470588235 }, { "step": 30, "mean16": 0.6314338235294118 }, { "step": 40, "mean16": 0.6305147058823529 }, { "step": 50, "mean16": 0.6599264705882353 }, { "step": 60, "mean16": 0.6672794117647058 }, { "step": 70, "mean16": 0.6332720588235294 }, { "step": 80, "mean16": 0.6305147058823529 }, { "step": 90, "mean16": 0.6599264705882353 }, { "step": 100, "mean16": 0.640625 } ], "best_step": 60, "best_mean16": 0.6672794117647058, "final_step": 100, "final_mean16": 0.640625 }