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

[Feature] Implement GrokFast optimizer #245

Merged
merged 8 commits into from
Jun 22, 2024
Merged

[Feature] Implement GrokFast optimizer #245

Changes from 1 commit
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
dbefc4b
build(deps): packages
kozistr Jun 22, 2024
01f94e0
docs: Grokfast
kozistr Jun 22, 2024
7a39a1e
docs: Grokfast
kozistr Jun 22, 2024
4609df4
feature: GrokFast optimizer
kozistr Jun 22, 2024
fca320d
update: GrokFast optimizer
kozistr Jun 22, 2024
88e75b8
update: GrokFast optimizer
kozistr Jun 22, 2024
e3398c7
docs: examples
kozistr Jun 22, 2024
3b56b70
docs: v3.0.1 changelog
kozistr Jun 22, 2024
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
docs: v3.0.1 changelog
  • Loading branch information
@kozistr
kozistr committed Jun 22, 2024
commit 3b56b704d13101f1d7cc2e9d24e7842029db33f4
2 changes: 2 additions & 0 deletions docs/changelogs/v3.0.1.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,8 @@
* support not-using-first-momentum when beta1 is not given
* default dtype for first momentum to `bfloat16`
* clip second momentum to 0.999
* Implement `GrokFast` optimizer. (#244, #245)
* [Accelerated Grokking by Amplifying Slow Gradients](https://arxiv.org/abs/2405.20233)

### Bug

Expand Down