News for hackers. Stuff that matters.

A comment on Reproduce GPT-2 (124M) in llm.c in 90 minutes for $20. Parent comment

Re:Reproduce GPT-2 (124M) in llm.c in 90 minutes for $20 by Manabu-eo on Wednesday May 29, 2024 @06:16PM (#40517705)
How much % of the theoretical FLOPs are you getting with those 7900 XTX on training?
[ Parent | on HN ]
Re:Reproduce GPT-2 (124M) in llm.c in 90 minutes for $20 by anthonix1 on Wednesday May 29, 2024 @07:07PM (#40518173)
55.4% in the last run, at running temperature
[ Parent | on HN ]