Currently IntervenableModel.train() and IntervenableModel.evaluate() are helper methods for training and evaluating interventions in a simple interface. I am renaming these to train_alignment() and eval_alignment() so that train() and eval() can set the model state (so that HF trainer can be compatible with this interface).
I think we have not actually been using these in pyvene-based projects because they don't allow much customisation so this doesn't break much; just had to change one notebook.
Testing Done
Tested in current project and worked. Let's see if tests pass!
Checklist:
[x] My PR title strictly follows the format: [Your Priority] Your Title
Description
Currently
IntervenableModel.train()
andIntervenableModel.evaluate()
are helper methods for training and evaluating interventions in a simple interface. I am renaming these totrain_alignment()
andeval_alignment()
so thattrain()
andeval()
can set the model state (so that HF trainer can be compatible with this interface).I think we have not actually been using these in
pyvene
-based projects because they don't allow much customisation so this doesn't break much; just had to change one notebook.Testing Done
Tested in current project and worked. Let's see if tests pass!
Checklist:
[Your Priority] Your Title