torchrun --nproc_per_node=1 train.py --train_args_file train_args/Glm.yaml
Traceback (most recent call last):
File "/home/yierde/anaconda3/envs/tn/bin/torchrun", line 8, in
sys.exit(main())
^^^^^^
File "/home/yierde/anaconda3/envs/tn/lib/python3.11/site-packages/torch/distributed/elastic/multiprocessing/errors/init.py", line 346, in wrapper
return f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^
File "/home/yierde/anaconda3/envs/tn/lib/python3.11/site-packages/torch/distributed/run.py", line 762, in main
run(args)
File "/home/yierde/anaconda3/envs/tn/lib/python3.11/site-packages/torch/distributed/run.py", line 753, in run
elastic_launch(
File "/home/yierde/anaconda3/envs/tn/lib/python3.11/site-packages/torch/distributed/launcher/api.py", line 132, in call
return launch_agent(self._config, self._entrypoint, list(args))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/yierde/anaconda3/envs/tn/lib/python3.11/site-packages/torch/distributed/launcher/api.py", line 237, in launch_agent
result = agent.run()
^^^^^^^^^^^
File "/home/yierde/anaconda3/envs/tn/lib/python3.11/site-packages/torch/distributed/elastic/metrics/api.py", line 129, in wrapper
result = f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^
File "/home/yierde/anaconda3/envs/tn/lib/python3.11/site-packages/torch/distributed/elastic/agent/server/api.py", line 709, in run
result = self._invoke_run(role)
^^^^^^^^^^^^^^^^^^^^^^
File "/home/yierde/anaconda3/envs/tn/lib/python3.11/site-packages/torch/distributed/elastic/agent/server/api.py", line 844, in _invoke_run
self._initialize_workers(self._worker_group)
File "/home/yierde/anaconda3/envs/tn/lib/python3.11/site-packages/torch/distributed/elastic/metrics/api.py", line 129, in wrapper
result = f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^
File "/home/yierde/anaconda3/envs/tn/lib/python3.11/site-packages/torch/distributed/elastic/agent/server/api.py", line 681, in _initialize_workers
worker_ids = self._start_workers(worker_group)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/yierde/anaconda3/envs/tn/lib/python3.11/site-packages/torch/distributed/elastic/metrics/api.py", line 129, in wrapper
result = f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^
File "/home/yierde/anaconda3/envs/tn/lib/python3.11/site-packages/torch/distributed/elastic/agent/server/local_elastic_agent.py", line 271, in _start_workers
self._pcontext = start_processes(
^^^^^^^^^^^^^^^^
File "/home/yierde/anaconda3/envs/tn/lib/python3.11/site-packages/torch/distributed/elastic/multiprocessing/init.py", line 207, in start_processes
redirs = to_map(redirects, nprocs)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/yierde/anaconda3/envs/tn/lib/python3.11/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 162, in to_map
map[i] = val_or_map.get(i, Std.NONE)
^^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'get'
怎么解决它? 我没办法跑起来。。。