原书出处
Designing Large Language Model Applications
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.
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