difficulty

[PanXGzhu]

When I run the FashionIQ dataset again, it generates such a warning：
Training loop started
0%
0/140 [00:00<?，?it/s]/homt
/px/miniconda3/envs/cir_sprc/lib/python3.9/sit
optimizer.step(). In PyTorch 1.1.0 and later, you
should call them in the opposite order:`optim
e-packages/torch/optim/lr_scheduler.py:139:Use
Warning: Detected call oflr_scheduler.step() befor
izer.step()beforelr_scheduler.step(). Fai
ure to do this will result in PyTorch skipping the fi
st value of the learning rate schedule. See more det
ils at https://pytorch.org/docs/stable/optim.h
tml#how-to-adjust-learning-rate
warnings.warn("Detected call of'lr scheduler
step() beforeoptimizer.step()
[0/30]loss itc:2.515,loss_rtc:3.010，loss_a
ign:0.195，:100%

And why is it at 0% when the training loop started?

I really hope you can help me solve this problem. Thank you

[PanXGzhu]

[PanXGzhu]