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.
More from Fun
- Joke: Aschenbrenner means 'burns things to ashes' in German — nominative determinism strikes — minhnguyen · 2026-11-21
- Jensen Huang repeatedly interrupted Mistral CEO at panel: "You're not even speaking human" — mattturck · 2026-11-21
- ERC reviewer rejects LLM autoformalization proposal: "tried without good results" — marc_lelarge · 2026-11-21
- Yacine: 'It might be over for OpenAI — and the killer isn't Claude, it's Gemini' — yacineMTB · 2026-11-21
- Ark: an AI-made musical horror tale set in a world where the sun never rises — SoullessGamesDev · 2026-11-21
- Parody 'NYT Exclusive': Jensen Huang returned a Raiders tape to Blockbuster unrewound in 1996 — Dan_Jeffries1 · 2026-11-21