You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
vibed/edu/.beans/edu-abdu--write-10-cross-en...

383 B

title status type priority created_at updated_at parent
Write §10: Cross-entropy loss and the training loop completed task normal 2026-03-13T22:02:02Z 2026-03-16T02:30:26Z edu-u2w7

Next-token prediction loss: cross-entropy over the vocab. Adam optimiser. Training loop structure: batch → forward → loss → backward → step. No bells and whistles.