Share via

TabularLimitSettings Class

Limit settings for a AutoML Table Verticals.

Constructor

TabularLimitSettings(*, enable_early_termination: bool | None = None, exit_score: float | None = None, max_concurrent_trials: int | None = None, max_cores_per_trial: int | None = None, max_nodes: int | None = None, max_trials: int | None = None, timeout_minutes: int | None = None, trial_timeout_minutes: int | None = None)

Parameters

Name Description
enable_early_termination
Required
bool

Whether to enable early termination if the score is not improving in the short term. The default is True.
exit_score
Required
float

Target score for experiment. The experiment terminates after this score is reached.
max_concurrent_trials
Required
int

Maximum number of concurrent AutoML iterations.
max_cores_per_trial
Required
int

The maximum number of threads to use for a given training iteration.
max_nodes
Required
int

[Experimental] The maximum number of nodes to use for distributed training.

  • For forecasting, each model is trained using max(2, int(max_nodes / max_concurrent_trials)) nodes.

  • For classification/regression, each model is trained using max_nodes nodes.

Note- This parameter is in public preview and might change in future.
max_trials
Required
int

Maximum number of AutoML iterations.
timeout_minutes
Required
int

AutoML job timeout.
trial_timeout_minutes
Required
int

AutoML job timeout.

Keyword-Only Parameters

Name Description
enable_early_termination
Default value: None
exit_score
Default value: None
max_concurrent_trials
Default value: None
max_cores_per_trial
Default value: None
max_nodes
Default value: None
max_trials
Default value: None
timeout_minutes
Default value: None
trial_timeout_minutes
Default value: None