← All questions
HardAI MLTechnical

A reproduction matches sample IDs and logits, but loss and gradient norms are exactly three times larger for a three-example batch. What do you inspect before another full run?

1Give yourself 5 minutes
2Answer out loud, not in your head
3Then compare with the answer below
0

Reference answer

Then expect these follow-ups

  • What if the loss matches but the optimizer step differs?

Free to read · better with Enzo

Practice this out loud with Enzo

Enzo runs it as a mock interview, pushes back with follow-ups, and grades you on the rubric.

Next question