flair.trainers.plugins.AnnealingPlugin

class flair.trainers.plugins.AnnealingPlugin(base_path, min_learning_rate, anneal_factor, patience, initial_extra_patience, anneal_with_restarts)View on GitHub

Bases: TrainerPlugin

Plugin for annealing logic in Flair.

__init__(base_path, min_learning_rate, anneal_factor, patience, initial_extra_patience, anneal_with_restarts)View on GitHub

Initialize the base plugin.

Methods

__init__(base_path, min_learning_rate, ...)	Initialize the base plugin.
after_evaluation(current_model_is_best, ...)	Scheduler step of AnnealOnPlateau.
after_setup(train_with_dev, optimizer, **kw)	Initialize different schedulers, including anneal target for AnnealOnPlateau, batch_growth_annealing, loading schedulers.
attach_to(pluggable)	Attach this plugin to a Pluggable.
detach()	Detach a plugin from the Pluggable it is attached to.
get_state()
hook([first_arg])	Convience function for BasePlugin.mark_func_as_hook).
mark_func_as_hook(func, *events)	Mark method as a hook triggered by the Pluggable.
store_learning_rate()

Attributes

attach_to_all_processes	If set, the plugin will be attached to all processes when distributed, not just the main process.
corpus
model
pluggable
trainer

store_learning_rate()View on GitHub

after_setup(train_with_dev, optimizer, **kw)View on GitHub

Initialize different schedulers, including anneal target for AnnealOnPlateau, batch_growth_annealing, loading schedulers.

after_evaluation(current_model_is_best, validation_scores, **kw)View on GitHub

Scheduler step of AnnealOnPlateau.

get_state()View on GitHub

Return type:

dict[str, Any]