How to display validation performance?

[2g-XzenG]

Hello,

Thanks for sharing this great work! ExplainableBoostingClassifier has a default parameter for early stopping and validation split. I am wondering if the performance on the validation dataset can be display in some way. Thank you in advance!

[interpret-ml]

Hi @1230pitchanqw ,

Thanks for bringing this up. We currently log the validation performance of every 10th epoch in our logging system. You can enable this by running the following utility function at the top of your file:

from interpret.develop import register_log

register_log('output.txt', level="DEBUG")

However, the logs contain other messages captured during the training process as well. We currently don't support only logging the validation metric, but can look into this in the future. Glad to hear you're enjoying the package!

-InterpretML Team

[paulbkoch]

Closing this issue as it seems to be a duplicate of issue https://github.com/interpretml/interpret/issues/7 .