about the the running rounds

[tudounizhu]

I am sorry to contact you but I have a question: You set epoch=100 in your source code. The early_stopping condition can be satisfied when epoch is 20+ or 30+ generally. I think in this situation, early stopping means that the model has been trained well. However, it will automatically run a few more rounds like this, beginning from epoch=1 until it meets the early stopping condition. I wonder why. Would you please kindly reply to me? Thank you very much.