Created GRPOTrainerWithEval subclass for different evaluation reward functions - #8
Closed
jamesbraza wants to merge 3 commits into
Closed
Created GRPOTrainerWithEval subclass for different evaluation reward functions#8jamesbraza wants to merge 3 commits into
GRPOTrainerWithEval subclass for different evaluation reward functions#8jamesbraza wants to merge 3 commits into