To preview this task, watch the video beginning at 00:04.

You need a project to store the tuning experiment. Watch a video to see how to create a sandbox project and associate a service. Then follow the steps to verify that you have an existing project or create a project.

To preview this task, watch the video beginning at 00:19.

You can test your tuned model in the Prompt Lab. Follow these steps to test your tuned model:

1. Return to the watsonx home screen.

2. Verify that your sandbox project is selected.

   

3. Click the Open Prompt Lab tile.

4. Select your tuned model.

   1. Click the model drop-down list, and select View all foundation models.
   2. Select the granite-13b-instruct-v2 model.
   3. Click Select model.

5. Click the Structured tab.

6. For the Instruction, type:

   Summarize customer complaints
   

7. Provide the examples and test input.

   Example input and output

   Example input	Example output
   I forgot in my initial date I was using Capital One and this debt was in their hands and never was done.	Debt collection, sub-product: credit card debt, issue: took or threatened to take negative or legal action sub-issue
   I am a victim of identity theft and this debt does not belong to me. Please see the identity theft report and legal affidavit.	Debt collection, sub-product, I do not know, issue. attempts to collect debt not owed. sub-issue debt was a result of identity theft

   
   

8. In the Try text field, copy and paste the following prompt:

   After I reviewed my credit report, I am still seeing information that is reporting on my credit file that is not mine. please help me in getting these items removed from my credit file.
   

9. Click Generate, and review the results. Note the output for the base model so that you can compare this output to the output from the tuned model.

10. Click Save work > Save as.

11. Select Prompt template.

12. For the name, type Base model prompt.

13. For the Task, select Summarization.

14. Select View in project after saving.

15. Click Save.

To preview this task, watch the video beginning at 01:12.

You need to add the training data to your project. On the Resource hub page, you can find the customer complaints data set. This data set includes fictitious data of typical customer complaints regarding credit reports. Follow these steps to add the data set from the Resource hub to the project:

1. Access the Customer complaints data set on the Resource hub page.
2. Click Add to project.
3. Select your sandbox project.
4. Click Add.
5. Click View project to see the asset in your project.

To preview this task, watch the video beginning at 01:32.

Now you are ready to create a tuning experiment in your sandbox project that uses the data set you just added to the project. Follow these steps to create a Tuning experiment:

1. Return to the watsonx home screen.

2. Verify that your sandbox project is selected.

   

3. Click Tune a foundation model with labeled data.

4. For the name, type:

   Summarize customer complaints tuned model
   

5. For the description, type:

   Tuning Studio experiment to tune a foundation model to handle customer complaints.
   

6. Click Create. The Tuning Studio displays.

To preview this task, watch the video beginning at 01:47.

In the Tuning Studio, you can configure the tuning experiment. The foundation model to tune is completed for you. Follow these steps to configure the tuning experiment:

1. For the foundation model to tune, click Select a foundation model.

   1. Select granite-13b-instruct-v2.

   2. Click Select.

2. Select Text for the method to initialize the prompt. There are two options:

   • Text: Uses text that you specify.
   • Random: Uses values that are generated for you as part of the tuning experiment.

3. For the Text field, type:

   Summarize the complaint provided into one sentence.
   

   The following table shows example text for each task type:

   title

   Task type	Example
   Classification	Classify whether the sentiment of each comment is Positive or Negative
   Generation	Make the case for allowing employees to work from home a few days a week
   Summarization	Summarize the main points from a meeting transcript

   
   

4. Select Summarization for the task type that most closely matches what you want the model to do. There are three task types:

   • Summarization generates text that describes the main ideas that are expressed in a body of text.
   • Generation generates text such as a promotional email.
   • Classification predicts categorical labels from features. For example, given a set of customer comments, you might want to label each statement as a question or a problem. When you use the classification task, you need to list the class labels that you want the model to use. Specify the same labels that are used in your tuning training data.

5. Select your training data from the project.

   1. Click Select from project.
   2. Click Data asset.
   3. Select the customer complaints training data.json file.
   4. Click Select asset.
   5. Click Start tuning.

To preview this task, watch the video beginning at 03:17.

When the experiment run is complete, you see the tuned model and the Loss function chart. Loss function measures the difference between predicted and actual results with each training run. Follow these steps to view the loss function chart and the tuned model:

1. Review the Loss function chart. A downward sloping curve means that the model is getting better at generating the expected output.

   

2. Below the chart, click the Summarize customer complaints tuned model.

3. Scroll through the model details.

4. Click Deploy.

5. For the name, type: Summarize customer complaints tuned model

6. For the Deployment container, select Deployment space.

7. For the Target deployment space, select an existing deployment space. If you don't have an existing deployment space, follow these steps:

   1. For the Target deployment space, select Create a new deployment space.
   2. For the deployment space name, type: Foundation models deployment space
   3. Select a storage service from the list.
   4. Select your provisioned machine learning service from the list.
   5. Click Create.
   6. Click Close.
   7. For the Target deployment space, verify that Foundation models deployment space is selected.

8. Check the View deployment in deployment space after creating option.

9. Click Create.

10. On the Deployments page, click the Summarize customer complaints tuned model deployment to view the details.

To preview this task, watch the video beginning at 04:04.

You can test your tuned model in the Prompt Lab. Follow these steps to test your tuned model:

1. From the model deployment page, click Open in prompt lab, and then select your sandbox project. The Prompt Lab displays.

2. Select your tuned model.

   1. Click the model drop-down list, and select View all foundation models.
   2. Select the Summarize customer complaints tuned model model.
   3. Click Select model.

3. On the Structured mode page, type the Instruction: Summarize customer complaints

4. On the Structured mode page, provide the examples and test input.

   Example input and output

   Example input	Example output
   I forgot in my initial date I was using Capital One and this debt was in their hands and never was done.	Debt collection, sub-product: credit card debt, issue: took or threatened to take negative or legal action sub-issue
   I am a victim of identity theft and this debt does not belong to me. Please see the identity theft report and legal affidavit.	Debt collection, sub-product, I do not know, issue. attempts to collect debt not owed. sub-issue debt was a result of identity theft

   
   

5. In the Try text field, copy and paste the following prompt:

   After I reviewed my credit report, I am still seeing information that is reporting on my credit file that is not mine. please help me in getting these items removed from my credit file.
   

6. Click Generate, and review the results. Compare the output from the base model with this output from the tuned model.