| _key | core | string | |
| ancestors | core | array<string> | |
| best_trial_id | core | int64 | The best trial_id across all training runs. |
| creation_time | core | int64 | Output only. The time when this model was created, in millisecs since the epoch. |
| datadog_display_name | core | string | |
| default_trial_id | core | int64 | Output only. The default trial_id to use in TVFs when the trial_id is not passed in. For single-objective [hyperparameter tuning](/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-hp-tuning-overview) models, this is the best trial ID. For multi-objective [hyperparameter tuning](/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-hp-tuning-overview) models, this is the smallest trial ID among all Pareto optimal trials. |
| description | core | string | Optional. A user-friendly description of this model. |
| encryption_configuration | core | json | Custom encryption configuration (e.g., Cloud KMS keys). This shows the encryption configuration of the model data while stored in BigQuery storage. This field can be used with PatchModel to update encryption key for an already encrypted model. |
| etag | core | string | Output only. A hash of this resource. |
| expiration_time | core | int64 | Optional. The time when this model expires, in milliseconds since the epoch. If not present, the model will persist indefinitely. Expired models will be deleted and their storage reclaimed. The defaultTableExpirationMs property of the encapsulating dataset can be used to set a default expirationTime on newly created models. |
| feature_columns | core | json | Output only. Input feature columns that were used to train this model. |
| friendly_name | core | string | Optional. A descriptive name for this model. |
| hparam_search_spaces | core | json | Output only. All hyperparameter search spaces in this model. |
| hparam_trials | core | json | Output only. Trials of a [hyperparameter tuning](/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-hp-tuning-overview) model sorted by trial_id. |
| label_columns | core | json | Output only. Label columns that were used to train this model. The output of the model will have a "predicted_" prefix to these columns. |
| labels | core | array<string> | |
| last_modified_time | core | int64 | Output only. The time when this model was last modified, in millisecs since the epoch. |
| location | core | string | Output only. The geographic location where the model resides. This value is inherited from the dataset. |
| model_reference | core | json | Required. Unique identifier for this model. |
| model_type | core | string | Output only. Type of the model resource. Possible values: ['MODEL_TYPE_UNSPECIFIED', 'LINEAR_REGRESSION', 'LOGISTIC_REGRESSION', 'KMEANS', 'MATRIX_FACTORIZATION', 'DNN_CLASSIFIER', 'TENSORFLOW', 'DNN_REGRESSOR', 'XGBOOST', 'BOOSTED_TREE_REGRESSOR', 'BOOSTED_TREE_CLASSIFIER', 'ARIMA', 'AUTOML_REGRESSOR', 'AUTOML_CLASSIFIER', 'PCA', 'DNN_LINEAR_COMBINED_CLASSIFIER', 'DNN_LINEAR_COMBINED_REGRESSOR', 'AUTOENCODER', 'ARIMA_PLUS', 'ARIMA_PLUS_XREG', 'RANDOM_FOREST_REGRESSOR', 'RANDOM_FOREST_CLASSIFIER', 'TENSORFLOW_LITE', 'ONNX']. Values descriptions: ['', 'Linear regression model.', 'Logistic regression based classification model.', 'K-means clustering model.', 'Matrix factorization model.', 'DNN classifier model.', 'An imported TensorFlow model.', 'DNN regressor model.', 'An imported XGBoost model.', 'Boosted tree regressor model.', 'Boosted tree classifier model.', 'ARIMA model.', 'AutoML Tables regression model.', 'AutoML Tables classification model.', 'Prinpical Component Analysis model.', 'Wide-and-deep classifier model.', 'Wide-and-deep regressor model.', 'Autoencoder model.', 'New name for the ARIMA model.', 'ARIMA with external regressors.', 'Random forest regressor model.', 'Random forest classifier model.', 'An imported TensorFlow Lite model.', 'An imported ONNX model.'] |
| optimal_trial_ids | core | array<int64> | Output only. For single-objective [hyperparameter tuning](/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-hp-tuning-overview) models, it only contains the best trial. For multi-objective [hyperparameter tuning](/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-hp-tuning-overview) models, it contains all Pareto optimal trials sorted by trial_id. |
| organization_id | core | string | |
| parent | core | string | |
| project_id | core | string | |
| project_number | core | string | |
| remote_model_info | core | json | Output only. Remote model info |
| resource_name | core | string | |
| tags | core | hstore | |
| training_runs | core | json | Information for all training runs in increasing order of start_time. |
