total loss unexpected increase, and then it goes down

[QianLingjun]

when i train Mask-rcnn with Resnet-101-FPN, thr total loss unexpected increase show in tensorboard. this phenomenon appear more than once.

I have a question: Why does this happen? and what causes this phenomenon? Is it normal or not? Thinks

[github-actions]

You've chosen to report an unexpected problem or bug. Unless you already know the root cause of it, please include details about it by filling the issue template.
The following information is missing: "Instructions To Reproduce the Issue and Full Logs"; "Your Environment";