The ML.TRIAL_INFO function
This document describes the ML.TRIAL_INFO
function, which lets you display
information about trials from a model that uses
hyperparameter tuning.
Syntax
ML.TRIAL_INFO(MODEL `project_id.dataset.model`)
Arguments
ML.TRIAL_INFO
takes the following arguments:
-
project_id
: Your project ID. -
dataset
: The BigQuery dataset that contains the model. -
model
: The name of the model.
Output
ML.TRIAL_INFO
returns one row per trial with the following columns:
-
trial_id
: anINT64
value that contains the ID assigned to each trial in the approximate order of trial execution.trial_id
values start from1
. -
hyperparameters
: aSTRUCT
value that contains the hyperparameters used in the trial. -
hparam_tuning_evaluation_metrics
: aSTRUCT
value that contains the evaluation metrics appropriate to the hyperparameter tuning objective specified by thehparam_tuning_objectives
argument in theCREATE MODEL
statement. Metrics are calculated from the evaluation data. For more information about the datasets used in hyperparameter tuning, see Data split. -
training_loss
: aFLOAT64
value that contains the loss of the trial during the last iteration, calculated using the training data. -
eval_loss
: aFLOAT64
value that contains the loss of the trial during the last iteration, calculated using the evaluation data. -
status
: aSTRING
value that contains the final status of the trial. Possible values include the following:-
SUCCEEDED
: the trial succeeded. -
FAILED
: the trial failed. -
INFEASIBLE
: the trial was not run due to an invalid combination of hyperparameters.
-
error_message
: aSTRING
value that contains the error message that is returned if the trial didn't succeed. For more information, see Error handling.is_optimal
: aBOOL
value that indicates whether the trial had the best objective value. If multiple trials are marked as optimal, then the trial with the smallesttrial_id
value is used as the default trial during model serving.
Example
The following query retrieves information of all trials for the model
mydataset.mymodel
in your default project:
SELECT * FROM ML.TRIAL_INFO(MODEL `mydataset.mymodel`)
What's next
- For information about hyperparameter tuning, see Hyperparameter tuning overview.
- For information about the supported SQL statements and functions for each model type, see End-to-end user journey for each model.