Skip to content

Experiment hyperparameters that Lorraine tunes  #6

Description

@vxbrandon

Do hyperparameters sweeps with hyperparameters that Lorraine tunes:

data_sizes = [100, 200, 1600]
val_props = [.0, .1, .25, .5, .75, .9]
num_neumann_terms in [1, 0, -1]
seed in [1, 2, 3]

Use the hyperparams_sweep.py file in the hyperparameters_sweep branch.

I looked at this and this. If anyone could find other hyperparameters that Lorraine tuned, please let me know!

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

Labels

No labels
No labels

Type

No type

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions