Remote monitoring of DL models

Please describe the problem that you’re facing and the enhancements that
you’d like to see. Feel free to include screenshots or code samples.

Describe the feature and the current behavior/state.
An app or a website that lets you remotely monitor your deep learning model's metrics. It can also notify you when your model has completed training or has crashed. I have worked on this before and I wish it could come inbuilt with Tensorflow. You can check out that project here.

Will this change the current api? How?
There will be a few miscellaneous codes added to the tensorflow library.

Who will benefit with this feature?
This will benefit the researchers who are training huge models. This will save them a lot of time.