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

Default EarlyStopping strategy #45

Open
ml-evs opened this issue Apr 13, 2021 · 0 comments
Open

Default EarlyStopping strategy #45

ml-evs opened this issue Apr 13, 2021 · 0 comments
Labels
question Further information is requested

Comments

@ml-evs
Copy link
Collaborator

ml-evs commented Apr 13, 2021

As of #44, our strategy is to monitor the loss and stop early by default when performing hyperparameter optimisation. We do not, however, restore the best weights (those with the lowest loss).

Questions:

  • should we monitor validation loss by default instead?
  • should we restore the best weights for the given preset?
@ml-evs ml-evs added the question Further information is requested label Apr 13, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
question Further information is requested
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@ml-evs