Rahil Verma
@RahilVerma13
Building Applied Compute
加入 December 2020
49 正在關注 98 粉絲
This has saved me countless hours
We're sharing a key step towards enabling Continual Learning at Applied Compute.
In On-Policy Self-Distillation, the teacher model supervises training with privileged information: a hint. The training signal depends heavily on hint quality, but manually refining hints across runs is impractical, and isolating their individual impact is difficult. We instead optimize hints automatically using efficient proxies for their eventual training value.
顯示更多
