Hi fellow participants. I'm done with the challenge, just a few touch ups. I just wanted to ask a question. How much of the dataset did you guys use? all the patient cases (2 Tb) or lesser. I used only around 200 patient cases, and my model seems to be highly accurate, and I am kind of worried if it's just overfitting.

So guys, if I could get a public opinion on your respective training data size choices, it would be much appreciated. I can just fine tune it a bit more to avoid any weird outputs during inference.