Proof by contradiction: they used batch size 6 because 7 was past the point of d... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

sillysaurusx on Nov 11, 2023 | parent | context | favorite | on: Google Cloud TPU Multislice Training

Proof by contradiction: they used batch size 6 because 7 was past the point of diminishing returns.

Join us for AI Startup School this June 16-17 in San Francisco!
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact