search

zhuchen03 / gradinit

Learning to Initialize Neural Networks for Stable and Efficient Training
134 stars 12 forks source link

Code to run fairseq IWSLT experiments? #2

Open sshleifer opened 2 years ago

sshleifer commented 2 years ago

I would love to test your method out on language modeling tasks in fairseq.

Do you have the code to make table 2 (or just the GradInit rows in Table 2) handy?

frankang commented 2 years ago

Same, waiting for the code on IWSLT. @zhuchen03

zhuchen03 commented 2 years ago

Maybe it is too late, but the code is now available!