Use platform logs

This page describes how to use platform logs generated by AML AI as part of Cloud Logging. AML AI uses the Logging API service name financialservices.googleapis.com to log the activity of:

Engine config creation (tuning)
Model creation (training)
Backtest operations
Prediction operations

Before you begin

To view and manage logs, make sure you have the correct IAM permissions and roles.

Platform logging activation status

The platform logs for AML AI are always active (can't be turned off).

Log severity

AML AI log entries use three severity levels:

NOTICE for entries sent when operations start or succeed
ERROR for entries about the end of failed operations
INFO for entries about operation progress

View platform logs

To view platform logs, follow the instructions below:

Console

To view platform logs in the Google Cloud console:

Navigate to the Logs Explorer:

Go to the Logs Explorer
Select the appropriate Google Cloud project.

In the Query field, enter the following query command:

logName=("projects/PROJECT_ID/logs/financialservices.googleapis.com%2Fbacktest" OR 
"projects/PROJECT_ID/logs/financialservices.googleapis.com%2Fengine_config_creation" OR 
"projects/PROJECT_ID/logs/financialservices.googleapis.com%2Fmodel_creation" OR 
"projects/PROJECT_ID/logs/financialservices.googleapis.com%2Fprediction")

where:

PROJECT_ID is the ID of the project you want to debug or monitor. For example, my-project.

Click Run query.

For more information about the Logs Explorer, see Logs Explorer Overview and Using the Logs Explorer.

gcloud

The gcloud command-line tool provides a command-line interface to Cloud Logging.

To view the logs for your project, run the following command:

gcloud logging read 'logName=("projects/PROJECT_ID/logs/financialservices.googleapis.com%2Fbacktest" OR 
"projects/PROJECT_ID/logs/financialservices.googleapis.com%2Fengine_config_creation" OR 
"projects/PROJECT_ID/logs/financialservices.googleapis.com%2Fmodel_creation" OR 
"projects/PROJECT_ID/logs/financialservices.googleapis.com%2Fprediction")' --project=PROJECT_ID

where PROJECT_ID is the ID for your Google Cloud project.

For more information about using the gcloud tool with Cloud Logging, see gcloud logging.

Understand platform logs

This section describes how to understand specific platform logs for AML AI.

START log

Logs with eventKind=START are generated when the operation starts its execution.

The following is an example of a log of starting a prediction run.

jsonPayload:
  '@type': type.googleapis.com/google.cloud.financialservices.logging.v1.PredictionLog
  engineVersion: projects/PROJECT_ID/locations/REGION_ID/instances/INSTANCE_ID/engineVersions/ENGINE_VERSION_ID
  eventKind: START
  predictionResult:
    dataset: projects/PROJECT_ID/locations/REGION_ID/instances/INSTANCE_ID/datasets/DATASET_ID
    endTime: '2023-05-31T00:00:00Z'
    model: projects/PROJECT_ID/locations/REGION_ID/instances/INSTANCE_ID/models/MODEL_ID
    outputs:
      explainabilityDestination:
        tableUri: bq://PROJECT_ID.DATASET_ID.EXPLAINABILITY_TABLE_ID
        writeDisposition: WRITE_EMPTY
      predictionDestination:
        tableUri: bq://PROJECT_ID.DATASET_ID.PREDICTION_TABLE_ID
        writeDisposition: WRITE_EMPTY
logName: projects/PROJECT_ID/logs/financialservices.googleapis.com%2Fprediction
operation:
  first: true
  id: projects/PROJECT_NUMBER/locations/REGION_ID/operations/OPERATION_ID
  producer: financialservices.googleapis.com
receiveTimestamp: '2023-06-07T12:30:48.417285528Z'
resource:
  labels:
    instance_id: INSTANCE_ID
    location: REGION_ID
    prediction_result_id: PREDICTION_ID
    resource_container: projects/PROJECT_NUMBER
  type: financialservices.googleapis.com/PredictionResult

You can add additional commands in the Logs Explorer Query field to narrow down the displayed logs.

Add the following command to display all started prediction runs on a selected dataset:

logName="projects/PROJECT_ID/logs/financialservices.googleapis.com%2Fprediction" AND
jsonPayload.predictionResult.dataset="projects/PROJECT_ID/locations/REGION_ID/instances/INSTANCE_ID/datasets/DATASET_ID" AND
jsonPayload.eventKind="START"

PROGRESS log

Logs with eventKind=PROGRESS are informing about the progress of an operation.

The following is an example of a log of creating a model. The completedTaskCount vs taskCount can be used to estimate the progress that was made on the model training.

jsonPayload:
  '@type': type.googleapis.com/google.cloud.financialservices.logging.v1.ModelCreationLog
  completedTaskCount: 11
  engineVersion: projects/PROJECT_ID/locations/REGION_ID/instances/INSTANCE_ID/engineVersions/ENGINE_VERSION_ID
  eventKind: PROGRESS
  model:
    endTime: '2023-05-31T00:00:00Z'
    engineConfig: projects/PROJECT_ID/locations/REGION_ID/instances/INSTANCE_ID/engineConfigs/ENGINE_CONFIG_ID
    engineVersion: projects/PROJECT_ID/locations/REGION_ID/instances/INSTANCE_ID/engineVersions/ENGINE_VERSION_ID
    lineOfBusiness: RETAIL
    primaryDataset: projects/PROJECT_ID/locations/REGION_ID/instances/INSTANCE_ID/datasets/DATASET_ID
    state: CREATING
  partyCount: '9246'
  taskCount: 16
logName: projects/PROJECT_ID/logs/financialservices.googleapis.com%2Fmodel_creation
operation:
  id: projects/PROJECT_NUMBER/locations/REGION_ID/operations/OPERATION_ID
  producer: financialservices.googleapis.com
receiveTimestamp: '2023-06-07T13:57:00.454668648Z'
resource:
  labels:
    instance_id: INSTANCE_ID
    location: REGION_ID
    model_id: MODEL_ID
    resource_container: projects/PROJECT_NUMBER
  type: financialservices.googleapis.com/Model
severity: INFO
timestamp: '2023-06-07T13:56:59.772973055Z'

END log

Logs with eventKind=END are produced when operation ends.

The following is an example of a log of a failed engine config creation. It contains the error about wrong data in the provided dataset.

jsonPayload:
  '@type': type.googleapis.com/google.cloud.financialservices.logging.v1.EngineConfigCreationLog
  completedTaskCount: 3
  engineConfig:
    engineVersion: projects/PROJECT_ID/locations/REGION_ID/instances/INSTANCE_ID/engineVersions/ENGINE_VERSION_ID
    lineOfBusiness: RETAIL
    performanceTarget:
      partyInvestigationsPerPeriodHint: '100'
    state: CREATING
    tuning:
      endTime: '2019-04-30T00:00:00Z'
      primaryDataset: projects/PROJECT_ID/locations/REGION_ID/instances/INSTANCE_ID/datasets/DATASET_ID
  eventKind: END
  operationStatus:
    code: 9
    details:
    - '@type': type.googleapis.com/google.rpc.ErrorInfo
      domain: financialservices.googleapis.com
      metadata:
        count: '15'
        data_field: party_id, validity_start_time
        data_table: party
        description: There is a duplicate primary key value in the database resulting
          in unique key violation. Note that for tables with validity_start_time,
          the primary key includes validity_start_time
        test: GROUP BY party_id, validity_start_time HAVING count(1) > 1
      reason: DUPLICATE_PRIMARY_KEY
    message: Dataset validation failed with 1 error. See error details for individual
      violations.
  partyCount: '9246'
  taskCount: 16
logName: projects/PROJECT_ID/logs/financialservices.googleapis.com%2Fengine_config_creation
operation:
  id: projects/PROJECT_NUMBER/locations/REGION_ID/operations/OPERATION_ID
  last: true
  producer: financialservices.googleapis.com
receiveTimestamp: '2023-06-07T14:26:30.214382295Z'
resource:
  labels:
    engine_config_id: ENGINE_CONFIG_ID
    instance_id: INSTANCE_ID
    location: REGION_ID
    resource_container: projects/PROJECT_NUMBER
  type: financialservices.googleapis.com/EngineConfig
severity: ERROR
timestamp: '2023-06-07T14:26:29.670913895Z'

To see all the create engine config error logs, use the filter below:

logName="projects/PROJECT_ID/logs/financialservices.googleapis.com%2Fengine_config_creation" AND
severity>=ERROR