RuntimeError: the derivative for 'linalg_lstsq' is not implemented.

[w2obin]

Thanks for your awsome work!
When I reproduced your code, I occured this error. Could you please give me some suggestions?
Thanks.

start training : long_term_forecast_ETTm1_96_96_VCformer_ETTm1_ftM_sl96_ll48_pl96_dm512_nh8_el2_dl1_df1024_fc3_ebtimeF_dtTrue_Exp_0>>>>>>>>>>>>>>>>>>>>>>>>>>
train 34369
val 11425
test 11425
Traceback (most recent call last):
File "run.py", line 177, in
exp.train(setting)
File "/home/www/long-term-baselines/VCformer-main/exp/exp_long_term_forecasting.py", line 180, in train
loss.backward()
File "/home/www/anaconda3/lib/python3.8/site-packages/torch/_tensor.py", line 255, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs)
File "/home/www/anaconda3/lib/python3.8/site-packages/torch/autograd/init.py", line 147, in backward
Variable._execution_engine.run_backward(
RuntimeError: the derivative for 'linalg_lstsq' is not implemented.