Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

About Original Nth Farthest #3

Open
vanzytay opened this issue Oct 20, 2018 · 8 comments
Open

About Original Nth Farthest #3

vanzytay opened this issue Oct 20, 2018 · 8 comments

Comments

@vanzytay
Copy link

Hey!

I've been wondering if you have tried the original Nth Farthest code (from Sonnet) on a 16GB Ram GPU. I keep running into memory errors no matter what I do (on a Volta GPU).

Wondering if you have any clue. (Sorry this is not directly related to your repository), just wondering if you got the original Sonnet version to work.

Thanks!

@L0SG
Copy link
Owner

L0SG commented Oct 20, 2018

Hi!

Sadly I have not tried to run the official Sonnet code myself, and just ported the core implementation of RMC with the Sonnet code just for the reference. So I'm afraid i could not share any useful pointers.

The Nth farthest task implementation is from the contributor. (Mind if I ask about this topic, @jessicayung ?)

Side note here, I've been running train_nth_farthest on my TITAN Xp about 5 days now, and checking now, it did break the 25% barrier and reached 91%. Haven't logged anything so I'll try to compare the results with the one form the paper soon.

@vanzytay
Copy link
Author

Hey! Thanks for the quick reply!

Wow, thanks. I'll use your version in my experiments!

@vanzytay
Copy link
Author

@L0SG Hey there, one more question. I started running your N-Farthest script. It seems to still hover around 0.25 (it's been 1 day). Could you describe if there is a sudden spike in performance (to 91%) or at roughly how many epoch does it take to reach somewhere along that score! And is the default hyperparameters correct for achieving this result? Thanks!

@L0SG
Copy link
Owner

L0SG commented Oct 22, 2018 via email

@jessicayung
Copy link
Contributor

@vanzytay The hyperparameters in this implementation were set based on the paper first and the official Sonnet implementation second. Not sure if there were differences between the two. Let me know if you find any problems. I spoke with one of the authors and they did say that the RRNN tends to run for a while before having something like an 'aha' moment and having a spike in performance (as shown in the graphs in the paper).

Also really glad to hear that the implementation's broken the 25% barrier, thanks for running it for longer Sang-gil!

@vanzytay
Copy link
Author

Thanks @L0SG and @jessicayung for your replies!

@L0SG
Copy link
Owner

L0SG commented Nov 13, 2018

I've uploaded a bit overdue experimental results of the nth farthest task. Definitely takes way longer than the reported results from the paper. I will play with other hyperparameters when I have spare GPU resources available.

@vanzytay
Copy link
Author

@L0SG Thanks!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants