Add tensorboard logging

[KAEYL98]

Feature request

What is the expected behavior?
Add support for tensorboard log files as an optional option to model parameters

What is motivation or use case for adding/changing the behavior?
Better tracking of different runs when tuning hyper parameters

How should this be implemented in your opinion?
Utilize existing torch.utils.tensorboard methods provided by pytorch

Are you willing to work on this yourself?
Not sure

[Optimox]

I think this would create an unnecessary dependency to the library. Logs for tabular data at each iteration have been enough for everyone when using XGBoost or any other model so I don't think it worth making things more complicated.