Verbose is not turned off in LightGBM

solution

Let's add verbose_eval = False to the train function.

gbm = lgb.train(params,
                lgb_train,,
                valid_sets=lgb_eval,
                verbose_eval=False,)<<<<<<<<<<<<<

How it didn't work 1

If you read the Parameters page of the documentation

verbosity, default = 1, type = int, aliases: verbose controls the level of LightGBM’s verbosity < 0: Fatal, = 0: Error (Warning), = 1: Info, > 1: Debug

Although it is written like this, it does not work even if you set verbose = -1.

How it didn't work 2

Also, if you look it up on the net gb_train = lgb.Dataset(X_train, y_train, params={'verbose': -1}, free_raw_data=False) I also see it, but this is also useless.

Reason

LightGBM's Verbose may control the output of errors, etc., not the output of learning status. Please let me know.