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.

Sign up for GitHub

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

Jump to bottom

Improve our mup implementation #837

Draft
wants to merge 5 commits into
base: main
Choose a base branch
from
Draft

Improve our mup implementation #837

Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
bf59c12
Add remaining mup params from paper's list. Add prototype support for…
Quentin-Anthony Mar 10, 2023
5f09348
Merge branch 'main' into improved-mup
Quentin-Anthony Mar 15, 2023
585efea
Update NeoXArgs docs automatically
invalid-email-address Mar 15, 2023
4ab0c08
Fixed syntax errors in training.py and added requirements-mup file
curt-tigges Apr 12, 2023
54f82ca
Fixed misc bugs in mup implementation
curt-tigges Apr 24, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Update NeoXArgs docs automatically
  • Loading branch information
github-actions committed Mar 15, 2023
commit 585efeab4ed06bf6408957c22fa03b1892905e72
10 changes: 9 additions & 1 deletion configs/neox_arguments.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,7 +111,7 @@ Logging Arguments

- **git_hash**: str

Default = ebaeec1
Default = 5f09348

current git hash of repository

Expand Down Expand Up @@ -1548,6 +1548,14 @@ Training Arguments



- **mup_deferred_init**: bool

Default = False

Whether to fully initialize the base and delta models (set to true for big target models)



## NeoXArgsDeepspeedConfig

Args for deepspeed config
Expand Down