Supervised Fine Tuning with Gemini for Question & Answering - GSP1269

Overview

This lab provides a hands-on introduction to fine-tuning Gemini generative models using Vertex AI's Supervised Tuning feature. You'll learn how to leverage your own labeled data to refine a base Gemini model, adapting it to excel at specific tasks like classification, summarization, question answering, and chat.

The fine-tuning process involves these key steps:

• Data Preparation: Providing high-quality, well-labeled training data is crucial. Your data directly influences the model's performance and helps mitigate potential biases.

• Training: Experiment with different training configurations to optimize the model for your target task. This iterative process allows you to maximize the model's potential.

• Evaluation: Carefully select evaluation metrics and a separate dataset to accurately assess the fine-tuned model's performance.

Recommended Configurations:

To guide your fine-tuning journey, we provide recommended starting points for various tasks:

Prerequisites

Before starting this lab, you should be familiar with:

• Basic Python programming.

• General API concepts.

• Running Python code in a Jupyter notebook on Vertex AI Workbench.

Objectives

In this lab, you will:

• Understand the process to utilize supervised fine-tuning.

• Enhance results from Gemini using data from BigQuery.

• Fine-tune Gemini using question & answer data from StackOverflow.

Setup and requirements

Before you click the Start Lab button

Read these instructions. Labs are timed and you cannot pause them. The timer, which starts when you click Start Lab, shows how long Google Cloud resources are made available to you.

This hands-on lab lets you do the lab activities in a real cloud environment, not in a simulation or demo environment. It does so by giving you new, temporary credentials you use to sign in and access Google Cloud for the duration of the lab.

To complete this lab, you need:

• Access to a standard internet browser (Chrome browser recommended).

Note: Use an Incognito (recommended) or private browser window to run this lab. This prevents conflicts between your personal account and the student account, which may cause extra charges incurred to your personal account.

• Time to complete the lab—remember, once you start, you cannot pause a lab.

Note: Use only the student account for this lab. If you use a different Google Cloud account, you may incur charges to that account.

How to start your lab and sign in to the Google Cloud console

1. Click the Start Lab button. If you need to pay for the lab, a dialog opens for you to select your payment method. On the left is the Lab Details pane with the following:

   • The Open Google Cloud console button

   • Time remaining

   • The temporary credentials that you must use for this lab

   • Other information, if needed, to step through this lab

2. Click Open Google Cloud console (or right-click and select Open Link in Incognito Window if you are running the Chrome browser).

   The lab spins up resources, and then opens another tab that shows the Sign in page.

   Tip: Arrange the tabs in separate windows, side-by-side.

   Note: If you see the Choose an account dialog, click Use Another Account.

3. If necessary, copy the Username below and paste it into the Sign in dialog.

    student-04-bfc71c7a430a@qwiklabs.net
   

   You can also find the Username in the Lab Details pane.

4. Click Next.

5. Copy the Password below and paste it into the Welcome dialog.

    cJ4qNckZwmGD
   

   You can also find the Password in the Lab Details pane.

6. Click Next.

   Important: You must use the credentials the lab provides you. Do not use your Google Cloud account credentials.

   Note: Using your own Google Cloud account for this lab may incur extra charges.

7. Click through the subsequent pages:

   • Accept the terms and conditions.

   • Do not add recovery options or two-factor authentication (because this is a temporary account).

   • Do not sign up for free trials.

After a few moments, the Google Cloud console opens in this tab.

Note: To access Google Cloud products and services, click the Navigation menu or type the service or product name in the Search field.

Task 1. Open the notebook in Vertex AI Workbench

1. In the Google Cloud console, on the Navigation menu (), click Vertex AI > Workbench.

2. Find the vertex-ai-jupyterlab instance and click on the Open JupyterLab button.

The JupyterLab interface for your Workbench instance opens in a new browser tab.

Task 2. Set up the notebook

1. Open the supervised_finetuning_using_gemini file.

2. In the Select Kernel dialog, choose Python 3 from the list of available kernels.

3. Run through the Getting Started and the Import libraries sections of the notebook.

   • For Project ID, use qwiklabs-gcp-03-ade10c4fd947, and for Location, use us-central1.

Note: You can skip any notebook cells that are noted Colab only. If you experience a 429 response from any of the notebook cell executions, wait 1 minute before running the cell again to proceed.

Click Check my progress to verify the objective.

Import libraries and set up the notebook.

Check my progress

Task 3. Create dataset in required format

In this section, you will create training, validation and test datasets used to modify and evaluate the fine-tuned model.

1. Run through the Create Dataset in required format section of the notebook.

• For BUCKET_NAME, use qwiklabs-gcp-03-ade10c4fd947.

Click Check my progress to verify the objective.

Create dataset in required format.

Check my progress

Task 4. Test the Gemini Model

In this section, you will generate a configuration and make a test call to Gemini using the python SDK.

1. Run through the Test the Gemini model section of the notebook.

Click Check my progress to verify the objective.

Test the Gemini Model.

Check my progress

Task 5. Evaluation before model tuning

In this section, you will evaluate the Gemini models performance prior to fine-tuning it with supplemental data.

1. Run through the Evaluation before model tuning section of the notebook.

Click Check my progress to verify the objective.

Evaluate the Gemini model on the test dataset before tuning.

Check my progress

Task 6. Load tuned Generative Model

In this section, you will load the tuned generative model and call the Gemini API.

1. Run through the Load tuned Generative Model section of the notebook.

Note: The tuning job will take several minutes to complete. Wait for the tuning job to complete before proceeding to subsequent cells of the notebook.

Click Check my progress to verify the objective.

Load tuned Generative Model.

---

Solution of Lab