google / google/ffn

Clarification on Training Steps

Open
#98 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
351
Forks
109
Avg merge
1d 8h
Merged PRs (30d)
7

Description

Hi Michał,

Thank you for your work and for sharing your scripts! I'm currently trying to reproduce the results, but my model didn’t seem to converge at the 10,000th step, as indicated in your scripts. Could you clarify how many steps you used when training the released checkpoints?

Thank you for your help!

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.