Skip to content

Model converging on forces but energy RMSE is very high #30

Description

@tnshp

I am trying to train the sGDML on glycine transition dataset. The model converges on force giving rmse ~ 0.45 but on energy it gives RMSE ~ 4 and doesnt even converge on increasing training points. I have also set the use_E flag to true but still same results.

Activity

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

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions