[Bug]: Cannot control logging

[endymion]

What happened?

I need to disable this logging:

2024-02-29 15:28:44,749 - INFO - 

POST Request Sent from LiteLLM:
curl -X POST \
https://api.openai.com/v1/ \
-d '{'model': 'gpt-3.5-turbo', 'messages': [{'role': 'system',...
...

My output has been overwhelmed with this logging since I switched to LiteLLM yesterday and it's just too much. It's causing many problems.

This does not work:

litellm.set_verbose=False

This also has zero effect on the logging:

def litellm_logger(*args, **kwargs):
    pass
    
...

    def llm_request(self, messages, tools=None, tool_choice=None):
        return litellm.completion(
            model=self.model_name,
            messages=messages,
            ...
            logger_fn=litellm_logger
        )

Those are the two options in the documentation for controlling logging, but neither seems to work. Is this a bug of some kind? Is there some way to disable the logging?

I like the idea of this, but the cost will be too high if I can't control the logging.

Relevant log output

2024-02-29 15:28:44,749 - INFO - 

POST Request Sent from LiteLLM:
curl -X POST \
https://api.openai.com/v1/ \
-d '{'model': 'gpt-3.5-turbo', 'messages': [{'role': 'system', ...

### Twitter / LinkedIn details

_No response_