I saw some tutorials and finally found the official tutorial is the most easiest to implement
https://pytorch.org/tutorials/beginner/transformer_tutorial.html
Usually we use blueqat cloud for quantum computing simulation and post API to quantum computers.
Now we have cuQuantum and powerful GPUs so I just tried benchmarking some Neural Network tutorials.
GPU NVIDIA V100 and CPU Intel(R) CPU @ 2.50GHz 1core
Just comparing one epoch benchmarking.
GPU
| end of epoch 1 | time: 72.37s | valid loss 5.80 | valid ppl 331.84
CPU
| end of epoch 1 | time: 3313.80s | valid loss 5.82 | valid ppl 336.48
GPU is about 46 times faster
