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.

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

Clean up yamls #58

Merged
merged 2 commits into from
Aug 21, 2023
Merged

Clean up yamls #58

merged 2 commits into from
Aug 21, 2023

Conversation

Landanjs
Copy link
Contributor

  • Remove diffusion2
  • Add the parameter paths to the composer command
  • Remove scale schedule ratio since we don't do that anymore
  • Remove 'batch_sizein the train and eval dataset config sincetrain.pydividestrain_batch_sizeandeval_batch_size` by the number of devices. To me, removing this improves clarity
  • Change multi-step LR schedule to linear LR schedule with alpha_f=0
  • Refactor compute to the more modern form, I think?

Copy link
Collaborator

@coryMosaicML coryMosaicML left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM! Thank you for doing this cleanup.

yamls/hydra-yamls/SD-2-base-256.yaml Show resolved Hide resolved
yamls/hydra-yamls/SD-2-base-256.yaml Show resolved Hide resolved
@Landanjs Landanjs merged commit ee8d0b2 into mosaicml:main Aug 21, 2023
7 checks passed
@Landanjs Landanjs deleted the landan/cleanup_yamls branch August 21, 2023 20:52
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants