diff --git a/pytorch_lightning/models/trainer.py b/pytorch_lightning/models/trainer.py index d0f262ea..9cf75f4c 100644 --- a/pytorch_lightning/models/trainer.py +++ b/pytorch_lightning/models/trainer.py @@ -514,6 +514,7 @@ class Trainer(TrainerIO): dist.init_process_group("nccl", rank=self.proc_rank, world_size=self.world_size) + def __resolve_root_node_address(self): try: root_node = os.environ['SLURM_NODELIST'].split(' ')[0] @@ -521,6 +522,9 @@ class Trainer(TrainerIO): if '[' in root_node: name = root_node.split('[')[0] number = root_node.split(',')[0] + if '-' in number: + number = number.split('-')[0] + number = re.sub('[^0-9]', '', number) root_node = name + number