[R-package] stop automatically calculating eval metrics on training data in lightgbm()

[jameslamb]

Contributes to #4862.
Contributes to #5203.
Based on #5199 (comment).

Proposes removing the behavior in lightgbm::lightgbm() where the training data is automatically added to the model's list of validation sets if verbose > 1.

That means that the following two concerns will now be fully separated in lightgbm():

• "how verbose do I want LightGBM's logging to be?"
• "what datasets do I want to be used for early stopping, and evaluated after each boosting round?"

[github-actions]

This pull request has been automatically locked since there has not been any recent activity since it was closed. To start a new related discussion, open a new issue at https://github.com/microsoft/LightGBM/issues including a reference to this.