xgboost.callback.TrainingCheckPoint Class Reference

Inheritance diagram for xgboost.callback.TrainingCheckPoint:

Public Member Functions
None	__init__ (self, Union[str, os.PathLike] directory, str name="model", bool as_pickle=False, int iterations=100)
bool	after_iteration (self, _Model model, int epoch, TrainingCallback.EvalsLog evals_log)
Public Member Functions inherited from xgboost.callback.TrainingCallback
_Model	before_training (self, _Model model)
_Model	after_training (self, _Model model)
bool	before_iteration (self, _Model model, int epoch, EvalsLog evals_log)

Protected Attributes
	_path
	_name
	_as_pickle
	_iterations
	_epoch

Additional Inherited Members
Static Public Attributes inherited from xgboost.callback.TrainingCallback
	EvalsLog = Dict[str, Dict[str, _ScoreList]]

Detailed Description

Checkpointing operation.

.. versionadded:: 1.3.0

Parameters
----------

directory :
    Output model directory.
name :
    pattern of output model file.  Models will be saved as name_0.json, name_1.json,
    name_2.json ....
as_pickle :
    When set to True, all training parameters will be saved in pickle format, instead
    of saving only the model.
iterations :
    Interval of checkpointing.  Checkpointing is slow so setting a larger number can
    reduce performance hit.

Constructor & Destructor Documentation

__init__()

None xgboost.callback.TrainingCheckPoint.__init__	(		self,
		Union[str, os.PathLike]	directory,
		str	name = "model",
		bool	as_pickle = False,
		int	iterations = 100
	)

Reimplemented from xgboost.callback.TrainingCallback.

Member Function Documentation

after_iteration()

bool xgboost.callback.TrainingCheckPoint.after_iteration	(		self,
		_Model	model,
		int	epoch,
		TrainingCallback.EvalsLog	evals_log
	)

Run after each iteration.  Return True when training should stop.

Reimplemented from xgboost.callback.TrainingCallback.

---

The documentation for this class was generated from the following file:

• External/xgboost/python-package/xgboost/callback.py