Closed zhongshijun closed 1 month ago
I used the data and train parameters provided by paper, and the model started to diverge after training for 35 epochs. How many epoch did the author train? Use the early stopping strategy?
Thanks!
I used the data and train parameters provided by paper, and the model started to diverge after training for 35 epochs. How many epoch did the author train? Use the early stopping strategy?
Thanks!