Inverse Square Root Schedule

2000년 도입 · 논문 702편에서 사용

Inverse Square Root is a learning rate schedule 1 / $\sqrt{\max\left(n, k\right)}$ where $n$ is the current training iteration and $k$ is the number of warm-up steps. This sets a constant learning rate for the first $k$ steps, then exponentially decays the learning rate until pre-training is over.