reduce verbosity of some log messages

[jameslamb]

Running a minimal example of cross-validation in the Python package (#6072 (comment)), I noticed some warning-level log messages that I believe should only be printed when users request more verbose logging.

[LightGBM] [Warning] Using self-defined objective function
[LightGBM] [Warning] Auto-choosing col-wise multi-threading, the overhead of testing was 0.006622 seconds.
You can set `force_col_wise=true` to remove the overhead.
[LightGBM] [Info] Total Bins 25500
[LightGBM] [Info] Number of data points in the train set: 6666, number of used features: 100
[LightGBM] [Warning] Using self-defined objective function
[LightGBM] [Warning] Auto-choosing col-wise multi-threading, the overhead of testing was 0.005703 seconds.
You can set `force_col_wise=true` to remove the overhead.
[LightGBM] [Info] Total Bins 25500
[LightGBM] [Info] Number of data points in the train set: 6666, number of used features: 100
[LightGBM] [Warning] Using self-defined objective function
[LightGBM] [Warning] Auto-choosing col-wise multi-threading, the overhead of testing was 0.006084 seconds.
You can set `force_col_wise=true` to remove the overhead.
[LightGBM] [Info] Total Bins 25500
[LightGBM] [Info] Number of data points in the train set: 6666, number of used features: 100
[LightGBM] [Warning] Using self-defined objective function
[LightGBM] [Warning] Using self-defined objective function
[LightGBM] [Warning] Using self-defined objective function

This PR proposes changing the level for those messages.

Notes for Reviewers

In my opinion, the following guidelines should be used to determine the level for log messages:

• FATAL
  • answers "why did LightGBM raise a runtime exception?"
• WARNING
  • alerts users to situations that might require their action (e.g. an unknown parameter, ignored parameters, inefficient configuration, etc.)
  • if possible, provides guidance on what specifics actions they should take
• INFO
  • the default information LightGBM users should see under normal use of the project's public API
• DEBUG
  • low-level details describing what LightGBM is doing, to help with troubleshooting and development

Do you agree? If so, I'll add that to the contributing documentation.

[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.