@abhishikthsagar I was running the resnet34 model from the first notebook (https://github.com/fastai/course-v3/blob/master/nbs/dl1/lesson1-pets.ipynb) which is what I assumed you were referring to based on the original post in the thread but correct me if I’m wrong.
I ended up upping the batch size (I don’t have it in front of me) but I was averaging around 30s per epoch after that.