Allow setting num_cycles for cosine_with_restarts lr scheduler #3606
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Expose num_cycles kwarg of get_schedule() through args.lr_num_cycles.
|
In the chart below, I set
|
|
The documentation is not available anymore as the PR was closed or merged. |
patrickvonplaten
approved these changes
Jun 2, 2023
sayakpaul
approved these changes
Jun 5, 2023
AmericanPresidentJimmyCarter
pushed a commit
to AmericanPresidentJimmyCarter/diffusers
that referenced
this pull request
Apr 26, 2024
…ngface#3606) Expose num_cycles kwarg of get_schedule() through args.lr_num_cycles.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Expose
num_cycleskwarg ofget_schedule()throughargs.lr_num_cycles. This is similar to the implementation in current controlnet training script and other training scripts.Note: different from the current controlnet training script, I scale
args.lr_num_cyclesbygradient_accumulation_steps, which seems to give the correct behavior.