ML pro tip: make both axes logarithmic and max out smoothing, and any loss curve looks fine

willdepue · x · 2026-11-21

willdepue shares a tongue-in-cheek ML tip: if your training charts look terrible and you're panicking, just set both X and Y axes to logarithmic and turn smoothing to max — "problem solved." He attaches a training dashboard showing loss curves in log-log coordinates and quotes Fritz Houtermans: "even my grandmother looks like a straight line on a log-log plot." A self-aware joke about making bad training runs look presentable.

Related event: OpenAI staffer's tip: fix ugly loss curves with log-log axes and max smoothing(2 posts)→

Original post →

More from Fun

Fun channel →