Skip to content

Instantly share code, notes, and snippets.

@staceysv
Created May 6, 2021 18:07
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save staceysv/8998d5192e13f05b4c2176b60b359694 to your computer and use it in GitHub Desktop.
Save staceysv/8998d5192e13f05b4c2176b60b359694 to your computer and use it in GitHub Desktop.
sweep config for molecular solubility deepchem tutorial
name: dnn cling test
project: deepchem_molsol
description: go deeper and wider on FC net
program: ml_train.py
method: bayes
metric:
name: r2
goal: maximize
parameters:
batch_size:
values: [8, 16, 32]
layers:
values: ["1000 500 100", "200 100 50 10", "200 50 10", "1000 500 100 50 10", "500 100 50 10"]
lr:
values: [0.003, 0.004, 0.005, 0.01, 0.02, 0.03, 0.05]
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment