test fewshot.py, get the below fatal error.
pytorch 1.10.0
for step, inputs in enumerate(train_dataloader):
if use_cuda:
inputs = inputs.cuda()
logits = prompt_model(inputs)
labels = inputs['label']
loss = loss_func(logits, labels)
loss.backward() # it causes the fatal error.
torch.nn.utils.clip_grad_norm_(prompt_model.parameters(), 1.0)
tot_loss += loss.item()
optimizer1.step()
one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [20, 1076]], which is output 0 of SoftmaxBackward0, is at version 1; expected version 0 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!
test fewshot.py, get the below fatal error.
pytorch 1.10.0
one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [20, 1076]], which is output 0 of SoftmaxBackward0, is at version 1; expected version 0 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!