[rank0]: Traceback (most recent call last):
[rank0]:   File "/workspace/kohya_ss/sd-scripts/flux_train.py", line 918, in <module>
[rank0]:     train(args)
[rank0]:   File "/workspace/kohya_ss/sd-scripts/flux_train.py", line 432, in train
[rank0]:     flux = accelerator.prepare(flux, device_placement=[not is_swapping_blocks])
[rank0]:   File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/accelerate/accelerator.py", line 1311, in prepare
[rank0]:     result = tuple(
[rank0]:   File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/accelerate/accelerator.py", line 1312, in <genexpr>
[rank0]:     self._prepare_one(obj, first_pass=True, device_placement=d) for obj, d in zip(args, device_placement)
[rank0]:   File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/accelerate/accelerator.py", line 1188, in _prepare_one
[rank0]:     return self.prepare_model(obj, device_placement=device_placement)
[rank0]:   File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/accelerate/accelerator.py", line 1452, in prepare_model
[rank0]:     model = torch.nn.parallel.DistributedDataParallel(
[rank0]:   File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 739, in __init__
[rank0]:     self._log_and_throw(
[rank0]:   File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1127, in _log_and_throw
[rank0]:     raise err_type(err_msg)
[rank0]: ValueError: DistributedDataParallel device_ids and output_device arguments only work with single-device/multiple-device GPU modules or CPU modules, but got device_ids [0], output_device 0, and module parameters {device(type='cpu')}.
[rank1]: Traceback (most recent call last):
[rank1]:   File "/workspace/kohya_ss/sd-scripts/flux_train.py", line 918, in <module>
[rank1]:     train(args)
[rank1]:   File "/workspace/kohya_ss/sd-scripts/flux_train.py", line 432, in train
[rank1]:     flux = accelerator.prepare(flux, device_placement=[not is_swapping_blocks])
[rank1]:   File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/accelerate/accelerator.py", line 1311, in prepare
[rank1]:     result = tuple(
[rank1]:   File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/accelerate/accelerator.py", line 1312, in <genexpr>
[rank1]:     self._prepare_one(obj, first_pass=True, device_placement=d) for obj, d in zip(args, device_placement)
[rank1]:   File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/accelerate/accelerator.py", line 1188, in _prepare_one
[rank1]:     return self.prepare_model(obj, device_placement=device_placement)
[rank1]:   File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/accelerate/accelerator.py", line 1452, in prepare_model
[rank1]:     model = torch.nn.parallel.DistributedDataParallel(
[rank1]:   File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 739, in __init__
[rank1]:     self._log_and_throw(
[rank1]:   File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1127, in _log_and_throw
[rank1]:     raise err_type(err_msg)
[rank1]: ValueError: DistributedDataParallel device_ids and output_device arguments only work with single-device/multiple-device GPU modules or CPU modules, but got device_ids [1], output_device 1, and module parameters {device(type='cpu')}.
W0920 12:50:23.568000 140317697544192 torch/distributed/elastic/multiprocessing/api.py:858] Sending process 1369 closing signal SIGTERM
E0920 12:50:23.682000 140317697544192 torch/distributed/elastic/multiprocessing/api.py:833] failed (exitcode: 1) local_rank: 0 (pid: 1368) of binary: /workspace/kohya_ss/venv/bin/python
Traceback (most recent call last):
  File "/workspace/kohya_ss/venv/bin/accelerate", line 8, in <module>
    sys.exit(main())
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/accelerate/commands/accelerate_cli.py", line 48, in main
    args.func(args)
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/accelerate/commands/launch.py", line 1097, in launch_command
    multi_gpu_launcher(args)
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/accelerate/commands/launch.py", line 734, in multi_gpu_launcher
    distrib_run.run(args)
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/torch/distributed/run.py", line 892, in run
    elastic_launch(
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 133, in __call__
    return launch_agent(self._config, self._entrypoint, list(args))
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 264, in launch_agent
    raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError: 
============================================================
/workspace/kohya_ss/sd-scripts/flux_train.py FAILED
------------------------------------------------------------
Failures:
  <NO_OTHER_FAILURES>
------------------------------------------------------------
Root Cause (first observed failure):
[0]:
  time      : 2024-09-20_12:50:23
  host      : 5e87f86b425f
  rank      : 0 (local_rank: 0)
  exitcode  : 1 (pid: 1368)
  error_file: <N/A>
  traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html