transformers/docs/source/en/main_classes/logging.md

Logging

🤗 Transformers has a centralized logging system, so that you can setup the verbosity of the library easily.

Currently the default verbosity of the library is WARNING.

To change the level of verbosity, just use one of the direct setters. For instance, here is how to change the verbosity to the INFO level.

import transformers

transformers.logging.set_verbosity_info()

You can also use the environment variable TRANSFORMERS_VERBOSITY to override the default verbosity. You can set it to one of the following: debug, info, warning, error, critical. For example:

TRANSFORMERS_VERBOSITY=error ./myprogram.py

Additionally, some warnings can be disabled by setting the environment variable TRANSFORMERS_NO_ADVISORY_WARNINGS to a true value, like 1. This will disable any warning that is logged using [logger.warning_advice]. For example:

TRANSFORMERS_NO_ADVISORY_WARNINGS=1 ./myprogram.py

Here is an example of how to use the same logger as the library in your own module or script:

from transformers.utils import logging

logging.set_verbosity_info()
logger = logging.get_logger("transformers")
logger.info("INFO")
logger.warning("WARN")

All the methods of this logging module are documented below, the main ones are [logging.get_verbosity] to get the current level of verbosity in the logger and [logging.set_verbosity] to set the verbosity to the level of your choice. In order (from the least verbose to the most verbose), those levels (with their corresponding int values in parenthesis) are:

• transformers.logging.CRITICAL or transformers.logging.FATAL (int value, 50): only report the most critical errors.
• transformers.logging.ERROR (int value, 40): only report errors.
• transformers.logging.WARNING or transformers.logging.WARN (int value, 30): only reports error and warnings. This the default level used by the library.
• transformers.logging.INFO (int value, 20): reports error, warnings and basic information.
• transformers.logging.DEBUG (int value, 10): report all information.

By default, tqdm progress bars will be displayed during model download. [logging.disable_progress_bar] and [logging.enable_progress_bar] can be used to suppress or unsuppress this behavior.

logging vs warnings

Python has two logging systems that are often used in conjunction: logging, which is explained above, and warnings, which allows further classification of warnings in specific buckets, e.g., FutureWarning for a feature or path that has already been deprecated and DeprecationWarning to indicate an upcoming deprecation.

We use both in the transformers library. We leverage and adapt logging's captureWarning method to allow management of these warning messages by the verbosity setters above.

What does that mean for developers of the library? We should respect the following heuristic:

• warnings should be favored for developers of the library and libraries dependent on transformers
• logging should be used for end-users of the library using it in every-day projects

See reference of the captureWarnings method below.

autodoc logging.captureWarnings

Base setters

autodoc logging.set_verbosity_error

autodoc logging.set_verbosity_warning

autodoc logging.set_verbosity_info

autodoc logging.set_verbosity_debug

Other functions

autodoc logging.get_verbosity

autodoc logging.set_verbosity

autodoc logging.get_logger

autodoc logging.enable_default_handler

autodoc logging.disable_default_handler

autodoc logging.enable_explicit_format

autodoc logging.reset_format

autodoc logging.enable_progress_bar

autodoc logging.disable_progress_bar