When I use my own bin file for training, the following error occurs. I sincerely look forward to your reply, no matter how I repay you

/home/xl/anaconda3/envs/test/lib/python3.5/site-packages/mxnet/module/base_module.py:504: UserWarning: Optimizer created manually outside Module but rescale_grad is not normalized to 1.0/batch_size/num_workers (1.0 vs. 0.3333333333333333). Is this intended?
optimizer_params=optimizer_params)
call reset()
Traceback (most recent call last):
File "/home/xl/1mxnetinsight/insightface-master/src/data.py", line 873, in next
label, s, bbox, landmark = self.next_sample()
File "/home/xl/1mxnetinsight/insightface-master/src/data.py", line 766, in next_sample
raise StopIteration
StopIteration

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "train.py", line 1025, in
main()
File "train.py", line 1022, in main
train_net(args)
File "train.py", line 1016, in train_net
epoch_end_callback = epoch_cb )
File "/home/xl/anaconda3/envs/test/lib/python3.5/site-packages/mxnet/module/base_module.py", line 520, in fit
next_data_batch = next(data_iter)
File "/home/xl/anaconda3/envs/test/lib/python3.5/site-packages/mxnet/io/io.py", line 230, in __next__
return self.next()
File "/home/xl/1mxnetinsight/insightface-master/src/data.py", line 945, in next
raise StopIteration
StopIteration

the commond is : CUDA_VISIBLE_DEVICES='0' python -u train.py --network r100 --data-dir /home/xl/1mxnetinsight/insightface-master/datasets/17_faces_datasets --ckpt 2 --target 17_faces --version-se 0 --per-batch-size 3 --prefix /media/xl/绿叶启动盘/save/model --verbose 10 --lr 0.00001