Why do the training results differ from experiment to experiment？
1215372621 opened this issue · 0 comments
1215372621 commented
During the process of running your code, I found that the training results of each experiment were different, and it seems that the results of the second training are always better than the first one. I don't know if it's because I haven't set it up properly. Even if seed is set to the same value, the results will still be different each time.