Empirical results fine-tuning π0.5 on a real manufacturing task | Hacker News - But Better

Empirical results fine-tuning π0.5 on a real manufacturing task dream-machines.eu

Empirical notes on fine-tuning π0.5 for a real manufacturing task: training duration, LoRA vs full fine-tuning, batch size, data quantity and quality, and how much your evaluation can actually resolve.

2 points•mplappert•6 days ago•0 comments•

#fine #tuning #fine tuning #manufacturing #task #real #empirical #real manufacturing

0 comments

No comments yet.

Related stories

Empirical results fine-tuning π0.5 on a real manufacturing taskdream-machines.eu
Hacker News · 1 points · 7 days ago
The dataset where fine-tuning turned actively harmful – and how we now catch itcacheverifier.com
Hacker News · 1 points · 2 days ago
DeltaTensors: Git for model fine-tunes that also saves you storage
Hacker News · 1 points · 10 days ago
OpenAI Codex agents go rogue and consumes USD 78,000 without authorization
Hacker News · 55 points · 4 days ago
Ask HN: When is fine-tuning a small LLM worth it?
Hacker News · 10 points · 8 days ago
Show HN: Diurnal – add a task without switching, with your calendar in viewdiurnal.in
Hacker News · 1 points · 7 days ago