One of the differentiated Tensors appears to not have been used in the graph. Set allow_unused=True

使用grad = torch.autograd.grad(loss, self._model.parameters())手动求梯度时，可能遇到该问题:

One of the differentiated Tensors appears to not have been used in the graph. Set allow_unused=True if this is the desired behavior.

原因是对loss反向求导时，self._model.parameters()中存在没有在链式法则内使用的tensor，也就是说模型中定义了某个layer或者需要求导的tensor，但是loss的计算图里不存在改layer或者该变量，此时需要检查模型代码，删掉改layer或者该变量