The Custom Document Classification Model Training in Document Intelligence Studio encounters an internal server error after running for 2 hours.

supree Greetings & Welcome to Microsoft Q&A forum!

Model training failure: InternalServerError: An unexpected error occurred.

I understand that you are getting an issue while training of a custom classification model. Please see below suggestions for more details.

"InternalServerError: An unexpected error occurred," is a generic error that can occur due to server issues.

Please share more detailed error logs for further assistance. Also, I would suggest you, retry the training process after some time.

Model training failure: ContentSourceNotAccessible: Content is not accessible: Invalid data URL

This error indicates that the data source you provided is not accessible. This could be due to incorrect URLs, permissions, or network issues.

Double check if you have access to training dataset incase if it is uploaded to Azure Blob Storage.

Verify that the data URL is correct and accessible from the environment where the model is being trained.

InvalidContentSourceFormat: Invalid content source: Could not read build content. Model training failure:

The error message "InvalidContentSourceFormat: Invalid content source: Could not read build content" suggests that there may be an issue with the format of the content source you're using.

Please make sure your training data set follows the input requirements for Document Intelligence. see Build and train a custom classification model for more details.

Do let me know if that helps or have any further queries.