←News detail

lilianwengUpdated Oct 21 22:46

English translation is being prepared.

Quoted post

Stephen Roller

@stephenroller

English translation is being prepared.

View original

Some teams use sweeps, heuristics, or scaling laws to determine their training LR. At Character, we just have Noam Shazeer dial it to the right value. https://t.co/bJRqirA7YT

View original post

Body

The English body is being prepared. You can open the original source.

Source

lilianweng