Allow training on custom datasets without test splits when run_test=False

[AHolliday]

What does this PR do?

Modified main.py so that if the user passes run_test=False, the test-split dataset and dataloader are not created in Model.train(). This way, the user is not required to define a test split in their dataset if they don't intend to use it.

Related Issue(s): Fixes issue #260

Type of Change

• Bug fix (non-breaking change that fixes an issue)

Testing

• [ x ] I have tested this change locally
• [ ] I have added/updated tests for this change

Test details:
There is currently no test set for main.py, so I have not added any tests.

Checklist

• [ x ] My code follows the style guidelines of this project
• [ x ] I have performed a self-review of my own code
• [ x ] I have commented my code where necessary, particularly in hard-to-understand areas
• [ x ] My changes generate no new warnings or errors
• [ x ] I have updated the documentation accordingly (if applicable)

I have read the CLA Document and I sign the CLA.

[CLAassistant]

All committers have signed the CLA.