When ever i try to run step 2 i get this RuntimeError: CUDA out of memory. Tried to allocate 2.18 GiB (GPU 0; 6.00 GiB total capacity; 2.47 GiB already allocated; 2.14 GiB free; 32.82 MiB cached), Problem is that its using gpu 0 instead of gpu 1 which is my Nvidia graphics card, and anything i do never works.