Change torchrun args to use _ instead of -, - is the new format, but looks like _ still works for backward compat with old versions. Fix #1742

Author: rwightman

distributed_train.sh

@@ -1,5 +1,5 @@
 #!/bin/bash
 NUM_PROC=$1
 shift
-torchrun --nproc-per-node=$NUM_PROC train.py "$@"
+torchrun --nproc_per_node=$NUM_PROC train.py "$@"