diff --git a/train.py b/train.py index e9cdf1e..78cd1c1 100644 --- a/train.py +++ b/train.py @@ -9,7 +9,9 @@ To run with DDP on 4 gpus on 1 node, example: $ torchrun --standalone --nproc_per_node=4 train.py To run with DDP on 4 gpus across 2 nodes, example: +- Run on the first (master) node: $ torchrun --nproc_per_node=8 --nnodes=2 --node_rank=0 --master_addr=123.456.123.456 --master_port=1234 train.py +- Run on the worker node: $ torchrun --nproc_per_node=8 --nnodes=2 --node_rank=1 --master_addr=123.456.123.456 --master_port=1234 train.py """