Traceback (most recent call last):
File "/data/liaohuanxuan/mt-dnn/train.py", line 793, in <module>
main()
File "/data/liaohuanxuan/mt-dnn/train.py", line 681, in main
model.update(batch_meta, batch_data)
File "/data/liaohuanxuan/mt-dnn/mt_dnn/model.py", line 260, in update
logits = self.mnetwork(*inputs)
File "/data/liaohuanxuan/micromamba/envs/former/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "/data/liaohuanxuan/micromamba/envs/former/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1040, in forward
output = self._run_ddp_forward(*inputs, **kwargs)
File "/data/liaohuanxuan/micromamba/envs/former/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1000, in _run_ddp_forward
return module_to_run(*inputs[0], **kwargs[0])
File "/data/liaohuanxuan/micromamba/envs/former/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "/data/liaohuanxuan/mt-dnn/mt_dnn/matcher.py", line 151, in forward
last_hidden_state, all_hidden_states = self.encode(
File "/data/liaohuanxuan/mt-dnn/mt_dnn/matcher.py", line 110, in encode
outputs = self.bert(
File "/data/liaohuanxuan/micromamba/envs/former/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "/data/liaohuanxuan/micromamba/envs/former/lib/python3.10/site-packages/transformers/models/bert/modeling_bert.py", line 1011, in forward
embedding_output = self.embeddings(
File "/data/liaohuanxuan/micromamba/envs/former/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "/data/liaohuanxuan/micromamba/envs/former/lib/python3.10/site-packages/transformers/models/bert/modeling_bert.py", line 235, in forward
inputs_embeds = self.word_embeddings(input_ids)
File "/data/liaohuanxuan/micromamba/envs/former/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "/data/liaohuanxuan/micromamba/envs/former/lib/python3.10/site-packages/torch/nn/modules/sparse.py", line 160, in forward
return F.embedding(
File "/data/liaohuanxuan/micromamba/envs/former/lib/python3.10/site-packages/torch/nn/functional.py", line 2210, in embedding
return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:1 and cuda:0! (when checking argument for argument index in method wrapper__index_select)
WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 9696 closing signal SIGTERM
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 1 (pid: 9697) of binary: /data/liaohuanxuan/micromamba/envs/former/bin/python
Traceback (most recent call last):
File "/data/liaohuanxuan/micromamba/envs/former/lib/python3.10/runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/data/liaohuanxuan/micromamba/envs/former/lib/python3.10/runpy.py", line 86, in _run_code
exec(code, run_globals)
File "/data/liaohuanxuan/micromamba/envs/former/lib/python3.10/site-packages/torch/distributed/launch.py", line 195, in <module>
main()
File "/data/liaohuanxuan/micromamba/envs/former/lib/python3.10/site-packages/torch/distributed/launch.py", line 191, in main
launch(args)
File "/data/liaohuanxuan/micromamba/envs/former/lib/python3.10/site-packages/torch/distributed/launch.py", line 176, in launch
run(args)
File "/data/liaohuanxuan/micromamba/envs/former/lib/python3.10/site-packages/torch/distributed/run.py", line 753, in run
elastic_launch(
File "/data/liaohuanxuan/micromamba/envs/former/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 132, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/data/liaohuanxuan/micromamba/envs/former/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 246, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
============================================================
train.py FAILED
------------------------------------------------------------
Failures:
<NO_OTHER_FAILURES>
------------------------------------------------------------
Root Cause (first observed failure):
[0]:
time : 2023-06-17_05:55:32
host : ubuntu138
rank : 1 (local_rank: 1)
exitcode : 1 (pid: 9697)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
============================================================
why it error on the not same device