Tune a model

Tune a model

This page shows you how to interact with Vertex AI to tune a model by using the side panel in Colab Enterprise.

To access Google Cloud services and APIs by running code in your Colab Enterprise notebook, you can use the credentials associated with your Google Account. To learn more, see Access Google Cloud services and APIs.

The side panel is an additional way to interact with Vertex AI to tune models without leaving the Colab Enterprise interface.

The side panel appears on the Colab Enterprise Notebooks page whenever you have one or more notebooks open.

Model tuning in Vertex AI

Model tuning is an effective way to customize large models to your tasks. It's a key step to improving the model's quality and efficiency. Model tuning provides the following benefits:

• Higher quality for your specific tasks
• Increased model robustness
• Lower inference latency and cost due to shorter prompts

For an overview of Vertex AI model tuning for Gemini, see Introduction to tuning.

Before you begin

1. Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.

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

   Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

   Go to project selector

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

4. Enable the Vertex AI, Dataform, and Compute Engine APIs.

   Enable the APIs

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

   Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

   Go to project selector

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

7. Enable the Vertex AI, Dataform, and Compute Engine APIs.

   Enable the APIs

Required roles

To ensure that your user account has the necessary permissions to use the side panel in a Colab Enterprise notebook, ask your administrator to grant your user account the following IAM roles on the project:

• Colab Enterprise User (roles/aiplatform.colabEnterpriseUser)
• Vertex AI User (roles/aiplatform.user)

For more information about granting roles, see Manage access to projects, folders, and organizations.

Your administrator might also be able to give your user account the required permissions through custom roles or other predefined roles.

One or more of the required roles includes the dataform.repositories.list permission. Users who are granted the dataform.repositories.list permission or the Code Creator (roles/dataform.codeCreator) role in a project can list the names of code assets in that project by using the Dataform API or the Dataform command-line interface (CLI). Non-administrators using BigQuery Studio can only see code assets that they created or that were shared with them.

Tune a model

You can tune a model in Vertex AI by using the side panel in Colab Enterprise.

1. In the Google Cloud console, go to the Colab Enterprise Notebooks page.

   Go to Notebooks

2. In the Region menu, select the region that contains your notebook.

3. On the My notebooks tab, click the notebook that you want to open. If you haven't created a notebook yet, create a notebook.

4. To the right of your notebook, in the side panel, click the  Tuning button.

   The side panel expands the Tuning tab.

5. Click the Tune a Gemini model button.

   Colab Enterprise adds code cells to your notebook for tuning a Gemini model.

6. In your notebook, find the code cell that stores parameter values. You'll use these parameters to interact with Vertex AI.

7. Update the values for the following parameters:

   • PROJECT_ID: The ID of the project that your notebook is in.
   • REGION: The region that your notebook is in.
   • TUNED_MODEL_DISPLAY_NAME: The name of your tuned model.

8. In the next code cell, update the model tuning parameters:

   • source_model: The Gemini model that you want to use, for example, gemini-1.0-pro-002.
   • train_dataset: The URL of your training dataset.
   • validation_dataset: The URL of your validation dataset.
   • Adjust the remaining parameters as needed.

9. Run the code cells that the side panel added to your notebook.

10. After the last code cell runs, click the  View tuning job button that appears.

11. The side panel shows information about your model tuning job.

    • The Monitor tab shows tuning metrics when the metrics are ready.
    • The Dataset tab shows a summary and metrics about your dataset after the dataset has been processed.
    • The Details tab shows information about your tuning job, such as the tuning method and the base model (source model) that you used.

12. After the tuning job has completed, you can go directly from the Tuning details tab to a page where you can test your model. Click Test.

    The Google Cloud console opens to the Vertex AI Text chat page, where you can test your model.

View details of a tuning job

You can view the details of a tuning job, even if you didn't create and run the tuning job in Colab Enterprise. You can view a tuning job's details by using the side panel in Colab Enterprise.

1. In the Google Cloud console, go to the Colab Enterprise Notebooks page.

   Go to Notebooks

2. In the Region menu, select the region that contains your notebook.

3. On the My notebooks tab, click the notebook that you want to open. If you haven't created a notebook yet, create a notebook.

4. To the right of your notebook, in the side panel, click the  Tuning button.

   The side panel expands the Tuning tab.

5. Click the View tuning job details button.

   Colab Enterprise adds code cells to your notebook for getting the details of a tuning job.

6. In your notebook, find the code cell that stores parameter values. You'll use these parameters to interact with Vertex AI.

7. Update the values for the following parameters:

   • PROJECT_ID: The ID of the project that your notebook is in.
   • REGION: The region that your notebook is in.
   • TUNING_JOB_ID: The ID of your Vertex AI tuning job.

8. Run the code cells that the side panel added to your notebook.

9. After the last code cell runs, click the  View tuning job button that appears.

10. The side panel shows information about your model tuning job.

    • The Monitor tab shows tuning metrics when the metrics are ready.
    • The Dataset tab shows a summary and metrics about your dataset after the dataset has been processed.
    • The Details tab shows information about your tuning job, such as the tuning method and the base model (source model) that you used.

What's next

• Learn more about model tuning in Vertex AI.

• To learn more about model tuning parameters, see Tune Gemini models by using supervised fine-tuning.