Rooba
/
lightning
mirror of https://github.com/Lightning-AI/lightning.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

added fallback local init

This commit is contained in:
William Falcon 2019-07-13 10:13:52 -04:00
parent 9f41a9e8b7
commit 8b0cda84e7
1 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
pytorch_lightning/models/trainer.py
View File

@ -378,10 +378,14 @@ class Trainer(TrainerIO):
port = 12910
os.environ['MASTER_PORT'] = f'{port}'
sleep(self.proc_rank*0.5)
try:
root_node = os.environ['SLURM_NODELIST'].split(' ')[0]
except Exception as e:
root_node = '127.0.0.2'
root_node = os.environ['SLURM_NODELIST'].split(' ')[0]
os.environ['MASTER_ADDR'] = root_node
sleep(self.proc_rank*0.5)
dist.init_process_group("nccl", rank=self.proc_rank, world_size=self.world_size)
def __run_pretrain_routine(self, model):