← 返回卡片

原书出处

Designing Large Language Model Applications

First Edition · 核验版本的摘录快照 · 导入于 2026-11-14T13:54:13.953Z

weighted loss scheme during training. The note can be much longer than the answer, and thus equally weighting the loss across all tokens will lead to the note getting significantly more importance during training. This harms model convergence. The weighted loss scheme involves calculating loss across answer tokens 50% of the time.

此预览只包含定位所需的摘录和上下文。

原书定位详情

来源:a19c7933-4eda-4176-aebd-30fe7e1ad292

正文位置:extracted/Designing Large Language Model Applications/_epub-src/OEBPS/ch12.html

EPUB SHA-256:1b4d2347fec2f949fcddfbaf4fad597a1ae20887a096cfae64c59a619b4781bf