search

emanjavacas / pie

A fully-fledge PyTorch package for Morphological Analysis, tailored to morphologically rich and historical languages.
MIT License
22 stars 10 forks source link

(Feature) Add the ability to use other optimizers and LRScheduler #78

Closed PonteIneptique closed 3 years ago

PonteIneptique commented 3 years ago

See #76

PonteIneptique commented 3 years ago

The new dependency is mostly here to bring other optimizers. I tested Ranger but there are many more. It did not yield better results though. But it provides space for researching on this front. Does that answer ? I agree on grouping LR Related parameters, I decided to not add a sub-dictionary because I was not sure which way you'd like to go. :)

emanjavacas commented 3 years ago

Alright. Then I'd keep that outside of main, since it's not clear whether it's useful or not.

On Sun, Dec 6, 2020 at 8:28 PM Thibault Clérice notifications@github.com wrote:

The new dependency is mostly here to bring other optimizers. I tested Ranger but there are many more. It did not yield better results though. But it provides space for researching on this front. Does that answer ? I agree on grouping LR Related parameters, I decided to not add a sub-dictionary because I was not sure which way you'd like to go. :)

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/emanjavacas/pie/pull/78#issuecomment-739550790, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABPIPI4RTZUTVUFI6LBIW6LSTPLOHANCNFSM4UPO3VSQ .

-- Enrique Manjavacas

PonteIneptique commented 3 years ago

No problem, there is also nothing urgent here (as everything is touching only the Trainer, not the deployed model). I am currently running same kind of test on a bigger corpus. Can we decided how how the parameters should be shown until then ?

PonteIneptique commented 3 years ago

Closed in favor of #79