Data classification: Training failed with model builder error "Index was outside the bounds of the array".

[v-Hailishi]

System Information (please complete the following information):
Windows OS: Windows-11-Enterprise-21H2
ML.Net Model Builder 2022: 16.13.10.22513701 (Main Build)
Microsoft Visual Studio Enterprise: 2022(17.3.6)
.Net: 6.0

Describe the bug

• On which step of the process did you run into an issue:
  Training failed with model builder error "Index was outside the bounds of the array" when choosing "SentimentText" as Label and using metric "Log-Loss Reduction".

Data Source
https://testpass.blob.core.windows.net/test-pass-data/wikipedia-detox-250-line-data.tsv

To Reproduce
Steps to reproduce the behavior:

1. Select Create a new project from the Visual Studio 2022 start window.
2. Choose the C# Console App (.NET Core6.0) project template.
3. Add model builder by right click on the project.
4. Select Data classification scenario.
5. On Data page, select the data source and choose SentimentText column as label.
6. On the Train page, choose metric "Log-Loss Reduction", then click "Start training" button.
7. You will see that training failed with model builder error "Index was outside the bounds of the array".

Expected behavior
Training successful.

Screenshot

Additional context:
After the error occurs, .mbconfig file cannot be saved successfully with error "Value cannot be null".

[zewditu]

This issue happens when The logloss- reduction is infinity.

@LittleLittleCloud how we are dealing with infinity values metrics?

[luisquintanilla]

May be related to dotnet/machinelearning#6361