Use tuning and evaluation to improve model performance

This document shows you how to create a BigQuery ML remote model that references a Vertex AI gemini-1.0-pro-002 model. You then use supervised tuning to tune the model with new training data, followed by evaluating the model with the ML.EVALUATE function.

This can help you address scenarios where you need to customize the hosted Vertex AI model, such as when the expected behavior of the model is hard to concisely define in a prompt, or when prompts don't produce expected results consistently enough. Supervised tuning also influences the model in the following ways:

  • Guides the model to return specific response styles—for example being more concise or more verbose.
  • Teaches the model new behaviors—for example responding to prompts as a specific persona.
  • Causes the model to update itself with new information.

Required permissions

  • To create a connection, you need the following Identity and Access Management (IAM) role:

    • roles/bigquery.connectionAdmin
  • To grant permissions to the connection's service account, you need the following permission:

    • resourcemanager.projects.setIamPolicy
  • To create the model using BigQuery ML, you need the following IAM permissions:

    • bigquery.jobs.create
    • bigquery.models.create
    • bigquery.models.getData
    • bigquery.models.updateData
    • bigquery.models.updateMetadata
  • To run inference, you need the following permissions:

    • bigquery.tables.getData on the table
    • bigquery.models.getData on the model
    • bigquery.jobs.create

Before you begin

  1. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

    Go to project selector

  2. Make sure that billing is enabled for your Google Cloud project.

  3. Enable the BigQuery, BigQuery Connection, Vertex AI, and Compute Engine APIs.

    Enable the APIs

Costs

In this document, you use the following billable components of Google Cloud:

  • BigQuery: You incur costs for the queries that you run in BigQuery.
  • BigQuery ML: You incur costs for the model that you create and the processing that you perform in BigQuery ML.
  • Vertex AI: You incur costs for calls to and supervised tuning of the gemini-1.0-pro-002 model.

To generate a cost estimate based on your projected usage, use the pricing calculator. New Google Cloud users might be eligible for a free trial.

For more information, see the following resources:

Create a dataset

Create a BigQuery dataset to store your ML model:

  1. In the Google Cloud console, go to the BigQuery page.

    Go to the BigQuery page

  2. In the Explorer pane, click your project name.

  3. Click View actions > Create dataset.

    Create dataset.

  4. On the Create dataset page, do the following:

    • For Dataset ID, enter bqml_tutorial.

    • For Location type, select Multi-region, and then select US (multiple regions in United States).

      The public datasets are stored in the US multi-region. For simplicity, store your dataset in the same location.

    • Leave the remaining default settings as they are, and click Create dataset.

      Create dataset page.

Create a connection

Create a Cloud resource connection and get the connection's service account ID. Create the connection in the same location as the dataset that you created in the previous step.

Select one of the following options:

Console

  1. Go to the BigQuery page.

    Go to BigQuery

  2. To create a connection, click Add, and then click Connections to external data sources.

  3. In the Connection type list, select Vertex AI remote models, remote functions and BigLake (Cloud Resource).

  4. In the Connection ID field, enter a name for your connection.

  5. Click Create connection.

  6. Click Go to connection.

  7. In the Connection info pane, copy the service account ID for use in a later step.

bq

  1. In a command-line environment, create a connection:

    bq mk --connection --location=REGION --project_id=PROJECT_ID \
        --connection_type=CLOUD_RESOURCE CONNECTION_ID

    The --project_id parameter overrides the default project.

    Replace the following:

    • REGION: your connection region
    • PROJECT_ID: your Google Cloud project ID
    • CONNECTION_ID: an ID for your connection

    When you create a connection resource, BigQuery creates a unique system service account and associates it with the connection.

    Troubleshooting: If you get the following connection error, update the Google Cloud SDK:

    Flags parsing error: flag --connection_type=CLOUD_RESOURCE: value should be one of...
    
  2. Retrieve and copy the service account ID for use in a later step:

    bq show --connection PROJECT_ID.REGION.CONNECTION_ID

    The output is similar to the following:

    name                          properties
    1234.REGION.CONNECTION_ID     {"serviceAccountId": "connection-1234-9u56h9@gcp-sa-bigquery-condel.iam.gserviceaccount.com"}
    

Terraform

Append the following section into your main.tf file.

 ## This creates a cloud resource connection.
 ## Note: The cloud resource nested object has only one output only field - serviceAccountId.
 resource "google_bigquery_connection" "connection" {
    connection_id = "CONNECTION_ID"
    project = "PROJECT_ID"
    location = "REGION"
    cloud_resource {}
}        
Replace the following:

  • CONNECTION_ID: an ID for your connection
  • PROJECT_ID: your Google Cloud project ID
  • REGION: your connection region

Give the connection's service account access

Grant your service account the Vertex AI Service Agent role so that the service account can access Vertex AI. Failure to grant this role results in an error. Select one of the following options:

Console

  1. Go to the IAM & Admin page.

    Go to IAM & Admin

  2. Click Grant access.

    The Add principals dialog opens.

  3. In the New principals field, enter the service account ID that you copied earlier.

  4. Click Select a role.

  5. In Filter, type Vertex AI Service Agent and then select that role.

  6. Click Save.

gcloud

Use the gcloud projects add-iam-policy-binding command:

gcloud projects add-iam-policy-binding 'PROJECT_NUMBER' --member='serviceAccount:MEMBER' --role='roles/aiplatform.serviceAgent' --condition=None

Replace the following:

  • PROJECT_NUMBER: your project number
  • MEMBER: the service account ID that you copied earlier

The service account associated with your connection is an instance of the BigQuery Connection Delegation Service Agent, so it is acceptable to assign a service agent role to it.

Give the Compute Engine default service account access

When you enable the Compute Engine API, the Compute Engine default service account is automatically granted the Editor role on the project, unless you have disabled this behavior for your project. If that's the case, then you must re-grant the Editor role to the Compute Engine default service account access so that it has sufficient permissions to create and tune a remote model.

Console

  1. Go to the IAM & Admin page.

    Go to IAM & Admin

  2. Click Grant Access.

  3. For New principals, enter the service account ID, which is PROJECT_NUMBER-compute@developer.gserviceaccount.com.

  4. Click Select a role.

  5. In Select a role, choose Basic, and then select Editor.

  6. Click Save.

gcloud

Use the gcloud projects add-iam-policy-binding command:

gcloud projects add-iam-policy-binding 'PROJECT_NUMBER' --member='serviceAccount:MEMBER' --role='roles/editor' --condition=None

Replace the following:

  • PROJECT_NUMBER: your project number.
  • MEMBER: the service account ID, which is PROJECT_NUMBER-compute@developer.gserviceaccount.com.

Create a tuning service agent

Create an instance of the Vertex AI Secure Fine Tuning Service Agent:

  1. Use the gcloud beta services identity create command to create the tuning service agent:

    gcloud beta services identity create --service=aiplatform.googleapis.com --project=PROJECT_NUMBER
    

    Replace PROJECT_NUMBER with your project number.

  2. Use the gcloud projects add-iam-policy-binding command to grant the tuning service agent the Vertex AI Tuning Service Agent (roles/aiplatform.tuningServiceAgent) role:

    gcloud projects add-iam-policy-binding 'PROJECT_NUMBER' --member='serviceAccount:service-PROJECT_NUMBER@gcp-sa-vertex-tune.iam.gserviceaccount.com' --role='roles/aiplatform.tuningServiceAgent'
    

    Replace PROJECT_NUMBER with your project number.

Create test tables

Create tables of training and evaluation data based on the public MTSamples dataset of transcribed medical reports. This dataset has an input_text column that contains the medical transcript and a output_text column that contains the label that best describes the category of the transcript, for example Allergy/Immunology, Dentistry, or Cardiovascular/Pulmonary. Also, create a table that contains the prompt data for medical transcript classification.

You import the medical transcription data from a public Cloud Storage bucket.

  1. In the Google Cloud console, go to the BigQuery page.

    Go to BigQuery

  2. In the query editor, run the following statement to create a table of evaluation data:

    LOAD DATA INTO
     `bqml_tutorial.medical_transcript_eval`
    FROM FILES(format='NEWLINE_DELIMITED_JSON',
      uris = ['gs://cloud-samples-data/vertex-ai/model-evaluation/peft_eval_sample.jsonl']);
  3. In the query editor, run the following statement to create a table of training data:

    LOAD DATA INTO
    `bqml_tutorial.medical_transcript_train`
    FROM FILES(format='NEWLINE_DELIMITED_JSON',
      uris = ['gs://cloud-samples-data/vertex-ai/model-evaluation/peft_train_sample.jsonl']);
  4. In the query editor, run the following statement to create a prompt table:

    CREATE OR REPLACE TABLE `bqml_tutorial.transcript_classification` AS
    (SELECT 'Please assign a label for the given medical transcript from among these labels [Allergy / Immunology, Autopsy, Bariatrics, Cardiovascular / Pulmonary, Chiropractic, Consult - History and Phy., Cosmetic / Plastic Surgery, Dentistry, Dermatology, Diets and Nutritions, Discharge Summary, ENT - Otolaryngology, Emergency Room Reports, Endocrinology, Gastroenterology, General Medicine, Hematology - Oncology, Hospice - Palliative Care, IME-QME-Work Comp etc., Lab Medicine - Pathology, Letters, Nephrology, Neurology, Neurosurgery, Obstetrics / Gynecology, Office Notes, Ophthalmology, Orthopedic, Pain Management, Pediatrics - Neonatal, Physical Medicine - Rehab, Podiatry, Psychiatry / Psychology, Radiology, Rheumatology, SOAP / Chart / Progress Notes, Sleep Medicine, Speech - Language, Surgery, Urology].' AS prompt);

Create a baseline model

Create a remote model over the Vertex AI gemini-1.0-pro-002 model that you can use to classify medical transcripts.

  1. In the Google Cloud console, go to the BigQuery page.

    Go to BigQuery

  2. In the query editor, run the following statement to create a remote model:

    CREATE OR REPLACE MODEL `bqml_tutorial.gemini-baseline`
    REMOTE WITH CONNECTION `LOCATION.CONNECTION_ID`
    OPTIONS (ENDPOINT ='gemini-1.0-pro-002');

    Replace the following:

    • LOCATION: the connection location.
    • CONNECTION_ID: the ID of your BigQuery connection.

      When you view the connection details in the Google Cloud console, the CONNECTION_ID is the value in the last section of the fully qualified connection ID that is shown in Connection ID, for example projects/myproject/locations/connection_location/connections/myconnection.

    The query takes several seconds to complete, after which the gemini-baseline model appears in the bqml_tutorial dataset in the Explorer pane. Because the query uses a CREATE MODEL statement to create a model, there are no query results.

Check baseline model performance

Run the ML.GENERATE_TEXT function with the remote model to see how it performs on the evaluation data without any tuning.

  1. In the Google Cloud console, go to the BigQuery page.

    Go to BigQuery

  2. In the query editor, run the following statement:

    SELECT *
    FROM
    ML.GENERATE_TEXT(
      MODEL `bqml_tutorial.gemini-baseline`,
      (
        SELECT
          CONCAT(
            (SELECT prompt from `bqml_tutorial.transcript_classification`), ' ',
            input_text) AS prompt,
            output_text AS label
        FROM
            `bqml_tutorial.medical_transcript_eval`
      ),
      STRUCT(TRUE AS flatten_json_output))
    ORDER BY ml_generate_text_llm_result;

    If you examine the output data and compare the ml_generate_text_llm_result and label values, you see that while the baseline model predicts many transcript classifications correctly, it classifies some transcripts incorrectly. The following is a representative example of incorrect output. In this example, the correct classification is Autopsy, not Pulmonary Embolism.

    +------------------------------------+---------------------------------+-------------------------------------------------------------------------+--------------+
    | ml_generate_text_llm_result        | ml_generate_text_rai_result     | ml_generate_text_status | prompt                                        | label        |
    +------------------------------------+---------------------------------+-------------------------------------------------------------------------+--------------+
    | ## Label:Pulmonary Embolism        | [{"category":1,"probability":1  |                         | Please assign a label for the given medical   | Autopsy      |
    |                                    | ,"probability_score":0.19433    |                         | transcript from among these labels [Allergy / |              |
    |                                    | "594,"severity":2,...           |                         | Immunology, Autopsy, Bariatrics,              |              |
    |                                    |                                 |                         | Cardiovascular / Pulmonary, Chiropractic,     |              |
    |                                    |                                 |                         | Consult - History and Phy., Cosmetic /        |              |
    |                                    |                                 |                         | Plastic Surgery, Dentistry, Dermatology,      |              |
    |                                    |                                 |                         | Diets and Nutritions, Discharge Summary, ENT  |              |
    |                                    |                                 |                         | - Otolaryngology, Emergency Room Reports,     |              |
    |                                    |                                 |                         | Endocrinology, Gastroenterology, General      |              |
    |                                    |                                 |                         | Medicine, Hematology - Oncology, Hospice -    |              |
    |                                    |                                 |                         | Palliative Care, IME-QME-Work Comp etc.,      |              |
    |                                    |                                 |                         | Lab Medicine - Pathology, Letters,            |              |
    |                                    |                                 |                         | Nephrology, Neurology, Neurosurgery,          |              |
    |                                    |                                 |                         | Obstetrics / Gynecology, Office Notes,        |              |
    |                                    |                                 |                         | Ophthalmology, Orthopedic, Pain Management,   |              |
    |                                    |                                 |                         | Pediatrics - Neonatal, Physical Medicine -    |              |
    |                                    |                                 |                         | Rehab, Podiatry, Psychiatry / Psychology,     |              |
    |                                    |                                 |                         | Radiology, Rheumatology, SOAP / Chart /       |              |
    |                                    |                                 |                         | Progress Notes, Sleep Medicine, Speech -      |              |
    |                                    |                                 |                         | Language, Surgery, Urology].                  |              |
    |                                    |                                 |                         | TRANSCRIPT:                                   |              |
    |                                    |                                 |                         | SUMMARY OF CLINICAL HISTORY:,                 |              |
    |                                    |                                 |                         | OF The patient was a 35-year-old              |              |
    |                                    |                                 |                         | African-American male with no                 |              |
    |                                    |                                 |                         | significant past medical history              |              |
    |                                    |                                 |                         | a who called EMS with shortness of breath     |              |
    |                                    |                                 |                         | had and chest pain.  Upon EMS                 |              |
    |                                    |                                 |                         | arrival, patient was...                       |              |
    +------------------------------------+---------------------------------+-------------------------------------------------------------------------+--------------+
    

Evaluate the baseline model

To perform a more detailed evaluation of the model performance, use the ML.EVALUATE function. This function computes model metrics, such as precision, recall, and F1 score, in order to see how the model's responses compare to ideal responses.

  1. In the Google Cloud console, go to the BigQuery page.

    Go to BigQuery

  2. In the query editor, run the following statement:

    SELECT
     *
    FROM
     ML.EVALUATE(
       MODEL `bqml_tutorial.gemini-baseline`,
       (
         SELECT
           CONCAT(
             (SELECT prompt FROM `bqml_tutorial.transcript_classification`), ' ',
             input_text) AS input_text,
             output_text
         FROM
           `bqml_tutorial.medical_transcript_eval`
       ),
       STRUCT('classification' AS task_type))
    ORDER BY label;

The output looks similar to the following:

   +------------------------------+----------------------------------+-------------------------------------------------------------------------+
   | precision           | recall              | f1_score            | label                      | evaluation_status                          |
   +---------------------+---------------------+---------------------+----------------------------+--------------------------------------------+
   | 0.0                 | 0.0                 | 0.0                 | Allergy / Immunology       | {                                          |
   |                     |                     |                     |                            |  "num_successful_rows": 474,               |
   |                     |                     |                     |                            |  "num_total_rows": 492                     |
   |                     |                     |                     |                            | }                                          |
   +---------------------+---------------------+ --------------------+----------------------------+--------------------------------------------+
   | 0.0                 | 0.0                 | 0.0                 | Autopsy                    | {                                          |
   |                     |                     |                     |                            |  "num_successful_rows": 474,               |
   |                     |                     |                     |                            |  "num_total_rows": 492                     |
   |                     |                     |                     |                            | }                                          |
   +---------------------+---------------------+--------------- -----+----------------------------+--------------------------------------------+
   | 0.0                 | 0.0                 | 0.0                 | Bariatrics                 | {                                          |
   |                     |                     |                     |                            |  "num_successful_rows": 474,               |
   |                     |                     |                     |                            |  "num_total_rows": 492                     |
   |                     |                     |                     |                            | }                                          |
   +---------------------+---------------------+---------------------+----------------------------+--------------------------------------------+
   

You can see that the baseline model doesn't perform well for this data, based on the low f1 scores. This indicates that it is worth performing supervised tuning to see if you can improve model performance for this use case.

Create a tuned model

Create a remote model very similar to the one you created in Create a model, but this time specifying the AS SELECT clause to provide the training data in order to tune the model. This query might take a couple of hours to complete.

  1. In the Google Cloud console, go to the BigQuery page.

    Go to BigQuery

  2. In the query editor, run the following statement to create a remote model:

    CREATE OR REPLACE MODEL `bqml_tutorial.gemini-tuned`
      REMOTE
        WITH CONNECTION `LOCATION.CONNECTION_ID`
      OPTIONS (
        endpoint = 'gemini-1.0-pro-002',
        max_iterations = 300,
        data_split_method = 'no_split')
    AS
    SELECT
      CONCAT(
        (SELECT prompt FROM `bqml_tutorial.transcript_classification`), ' ',
        input_text) AS prompt,
        output_text AS label
    FROM
      `bqml_tutorial.medical_transcript_train`;

    Replace the following:

    • LOCATION: the connection location.
    • CONNECTION_ID: the ID of your BigQuery connection.

      When you view the connection details in the Google Cloud console, the CONNECTION_ID is the value in the last section of the fully qualified connection ID that is shown in Connection ID, for example projects/myproject/locations/connection_location/connections/myconnection.

    The query might take several hours to complete, after which the gemini-tuned model appears in the bqml_tutorial dataset in the Explorer pane. Because the query uses a CREATE MODEL statement to create a model, there are no query results.

Check tuned model performance

Run the ML.GENERATE_TEXT function to see how the tuned model performs on the evaluation data.

  1. In the Google Cloud console, go to the BigQuery page.

    Go to BigQuery

  2. In the query editor, run the following statement:

    SELECT *
    FROM
      ML.GENERATE_TEXT(
        MODEL `bqml_tutorial.gemini-tuned`,
        (
          SELECT
            CONCAT(
              (SELECT prompt from `bqml_tutorial.transcript_classification`), ' ',
              input_text) AS prompt,
              output_text AS label
          FROM
            `bqml_tutorial.medical_transcript_eval`
        ),
        STRUCT(TRUE AS flatten_json_output))
    ORDER BY ml_generate_text_llm_result;

    If you examine the output data, you see that the tuned model classifies more transcripts correctly. The example you looked at earlier is now correctly classified as Cardiovascular/ Pulmonary.

    +-----------------------------+---------------------------------+-------------------------------------------------------------------------+----------------------------+
    | ml_generate_text_llm_result | ml_generate_text_rai_result     | ml_generate_text_status | prompt                                        | label                      |
    +-----------------------------+---------------------------------+-------------------------------------------------------------------------+----------------------------+
    |  Autopsy                    | [{"category":1,"probability":1  |                         | Please assign a label for the given medical   | Autopsy                    |
    |                             | ,"probability_score":0.19335938 |                         | transcript from among these labels [Allergy / |                            |
    |                             | ,"severity":2,"severity_scor... |                         | Immunology, Autopsy, Bariatrics,              |                            |
    |                             |                                 |                         | Cardiovascular / Pulmonary, Chiropractic,     |                            |
    |                             |                                 |                         | Consult - History and Phy., Cosmetic /        |                            |
    |                             |                                 |                         | Plastic Surgery, Dentistry, Dermatology,      |                            |
    |                             |                                 |                         | Diets and Nutritions, Discharge Summary, ENT  |                            |
    |                             |                                 |                         | - Otolaryngology, Emergency Room Reports,     |                            |
    |                             |                                 |                         | Endocrinology, Gastroenterology, General      |                            |
    |                             |                                 |                         | Medicine, Hematology - Oncology, Hospice -    |                            |
    |                             |                                 |                         | Palliative Care, IME-QME-Work Comp etc.,      |                            |
    |                             |                                 |                         | Lab Medicine - Pathology, Letters,            |                            |
    |                             |                                 |                         | Nephrology, Neurology, Neurosurgery,          |                            |
    |                             |                                 |                         | Obstetrics / Gynecology, Office Notes,        |                            |
    |                             |                                 |                         | Ophthalmology, Orthopedic, Pain Management,   |                            |
    |                             |                                 |                         | Pediatrics - Neonatal, Physical Medicine -    |                            |
    |                             |                                 |                         | Rehab, Podiatry, Psychiatry / Psychology,     |                            |
    |                             |                                 |                         | Radiology, Rheumatology, SOAP / Chart /       |                            |
    |                             |                                 |                         | Progress Notes, Sleep Medicine, Speech -      |                            |
    |                             |                                 |                         | Language, Surgery, Urology].                  |                            |
    |                             |                                 |                         | TRANSCRIPT:                                   |                            |
    |                             |                                 |                         | SUMMARY OF CLINICAL HISTORY:,                 |                            |
    |                             |                                 |                         | The patient was a 35-year-old                 |                            |
    |                             |                                 |                         | African-American male with no                 |                            |
    |                             |                                 |                         | significant past medical history              |                            |
    |                             |                                 |                         | a who called EMS with shortness of breath     |                            |
    |                             |                                 |                         | had and chest pain.  Upon EMS                 |                            |
    |                             |                                 |                         | arrival, patient was...                       |                            |
    +-----------------------------+---------------------------------+-------------------------------------------------------------------------+----------------------------+
    

Evaluate the tuned model

Use the ML.EVALUATE function to see how the tuned model's responses compare to ideal responses.

  1. In the Google Cloud console, go to the BigQuery page.

    Go to BigQuery

  2. In the query editor, run the following statement:

    SELECT
     *
    FROM
     ML.EVALUATE(
       MODEL `bqml_tutorial.gemini-tuned`,
       (
         SELECT
           CONCAT(
             (SELECT prompt from `bqml_tutorial.transcript_classification`), ' ',
               input_text) AS prompt,
               output_text AS label
         FROM
           `bqml_tutorial.medical_transcript_eval`
       ),
       STRUCT('classification' AS task_type))
       ORDER BY label;

The output looks similar to the following:

   +------------------------------+----------------------------------+-------------------------------------------------------------------------+
   | precision           | recall              | f1_score            | label                      | evaluation_status                          |
   +---------------------+---------------------+---------------------+----------------------------+--------------------------------------------+
   | 0.5                 | 0.66666666666666663 | 0.5714285714285714  | Allergy/Immunology         | {                                          |
   |                     |                     |                     |                            |  "num_successful_rows": 439,               |
   |                     |                     |                     |                            |  "num_total_rows": 492                     |
   |                     |                     |                     |                            | }                                          |
   +---------------------+---------------------+ --------------------+----------------------------+--------------------------------------------+
   | 1.0                 | 1.0                 | 1.0                 | Autopsy                    | {                                          |
   |                     |                     |                     |                            |  "num_successful_rows": 439,               |
   |                     |                     |                     |                            |  "num_total_rows": 492                     |
   |                     |                     |                     |                            | }                                          |
   +---------------------+---------------------+--------------- -----+----------------------------+--------------------------------------------+
   | 0.5                 | 1.0                 | 0.66666666666666663 | Bariatrics                 | {                                          |
   |                     |                     |                     |                            |  "num_successful_rows": 439,               |
   |                     |                     |                     |                            |  "num_total_rows": 492                     |
   |                     |                     |                     |                            | }                                          |
   +---------------------+---------------------+---------------------+----------------------------+--------------------------------------------+
   

You can see that even though the training dataset used only 519 examples, there is a marked improvement in performance as indicated by the higher f1 scores.

Clean up

  1. In the Google Cloud console, go to the Manage resources page.

    Go to Manage resources

  2. In the project list, select the project that you want to delete, and then click Delete.
  3. In the dialog, type the project ID, and then click Shut down to delete the project.