Open launchauto opened 3 years ago
The uploaded txt log_rank0.txt is one of the eight gpus pretrain logs. And the uploaded txt log_rank7.txt is one of the eight gpus linear evaluation logs. log_rank7.txt
I also encountered the same problem.
@launchauto @michuanhaohao me too, but I run it with precision O0. Did you run with the O0 precision? log_rank0.txt
我也遇到了这个问题!loss一直是16永远不会下降?
怎么才能不适用apex混合精度呢?我使用swin transformer进行训练的时候,loss就会下降并且收敛。然而,我注意到swin transformer工程当中没有使用apex混合精度
Is it normal for the loss value to be around 16? Has anyone encountered this problem?
怎么才能不适合用apex混合精度呢?我用swin transformer进行训练的时候,loss就会下降并收敛。不过,我注意到swin transformer工程中没有使用apex混
请问您的问题解决了吗
loss值在16左右正常吗?有没有人遇到过这个问题?
loss值在16左右正常吗?有没有人遇到过这个问题?
我也是
Excuse me, have you solved the problem that loss drops to 8.9 and then rises in the opposite direction? Is it caused by apex mixed precision training?
请问,loss下降到8.9然后反方向上升的问题解决了吗?是顶点混合精度训练导致的吗?
没有/(ㄒoㄒ)/~~
会不会是loss函数的问题呀 这个代码你还在关注吗,我的loss从开始就是16 降不下去
不会是loss随便数的问题呀这个代号你还在关注吗,我的loss从开始就是16降不下
我也没有解决。。
Hi authors, I have pretrianed your moby_swin_tiny model using 8 Tesla V100 GPU and reproduced your results in downstream task. I get 74.394% on linear evaluation and 43.1% on COCO object detection task, 39.3% on COCO segmentation task. But the loss and grad_norm is really weired during training. Can you show me your log? Here is my log. The loss drops to 7 and then rises to 16, then never drop again. During the pretraining task, the grad norm average value sometimes rises to infinite. log_rank0.txt