Created GRPOTrainerWithEval subclass for different evaluation reward functions - #9
Open
jamesbraza wants to merge 3 commits into
Open
Created GRPOTrainerWithEval subclass for different evaluation reward functions#9jamesbraza wants to merge 3 commits into
GRPOTrainerWithEval subclass for different evaluation reward functions#9jamesbraza wants to merge 3 commits into