The training conversations of fn on rows with known answers
(contract/baked.md, "The examples table"): one per row, function,
messages (the prompt, then the reply: the loss belongs on the reply
only), tag, weight, row_id, split (a seeded share held out) and
source ("data"). Turning messages into tokens is the student's own
chat template's rule, so any trainer can train on them, and a model trained
on them is called by baked() with the same messages.
The training conversations of
fnon rows with known answers (contract/baked.md, "The examples table"): one per row,function,messages(the prompt, then the reply: the loss belongs on the reply only),tag,weight,row_id,split(a seeded share held out) andsource("data"). Turning messages into tokens is the student's own chat template's rule, so any trainer can train on them, and a model trained on them is called bybaked()with the same messages.