atulkum / atulkum/pointer_summarizer

Training saturates early?

Open
#48 3 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
909
Forks
235
PR merge metrics
No merged PRs in 30d

Description

I'm using the same hypers but seeing this for my training curve. Why would this happen? Looks like the LR is too high but your curve with the same lr seems fine.

Screen Shot 2020-03-25 at 4 27 14 PM
Screen Shot 2020-03-25 at 4 27 23 PM

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.