Override steps as epoch in Mlflow logger

[SimonLalan7]

Description

Currently, there is a heated debate in the PytorchLightning community on the appropriate behavior of logging
onStep=False and onEpoch=True metrics. These metrics will be logged with based on the global step unit for the x-axis, which complicates the data analysis when using a logger such as mlflow to interpret metrics. The goal of this PR is to implement a workaround found by the community to override the step metrics so it is based on epochs instead, allowing a better understanding of the behavior of the model, regardless of batchsize.

here is the original issue

Type of change

What types of changes does your code introduce? Put an x in all the boxes that apply:

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Other

How Has This Been Tested?

If the added changes are already cover by tests, skip that section.
Otherwise, please describe tests that you added to the pytest codebase (if applicable).

this was tested locally on a different model, but should work correctly on the others too

Screenshots (if applicable):

Checklist:

If you're unsure about any of these, don't hesitate to ask. We're here to help!

• My code follows the code style of this project
• I have performed a self-review of my own code
• My PR has a descriptive title
• My code follows PEP8 (most of it)
• My code have the proper documentation in the code
• I have made corresponding changes to the documentation (if applicable)
• My changes generate no new errors
• My code is covered by the existing tests (if applicable)
• My code includes tests that show that my feature works
• My PR passes Travis CI tests

If your PR does not fulfill all of the requirements in the checklist above, that's OK! If you need help, @-mention a maintainer and/or add the Status: Help Needed label.