Glow training problem: the train loss has a sudden rise (inf) when learning rate up 1e-3 from 0

Hi, I met a cuda runtime error as following:
RuntimeError: svd_cuda: the updating process of SBDSDC did not converge (error: 22)
Recently, I am studying normalizing flow, such as Glow, however, a strange svd problem has arisen when I try to train Glow from scratch. In my opinion, due to Glow contains “tensor.slogdet()” operation in affine coupling layer, it may involve SVD decomposition, and thus casue above problem.
Specifically, I first use a small learning rate, such as 1e-6, the training loss begins to fall slowly. However, when the learning rate reaches 0.0004, the training loss has a sudden rise (inf) and the error information is presented as above.
How can I avoid this error during training process of Glow?

I also encountered a similar problem