You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
File "/content/ChatDoctor/train_lora.py", line 17, in
from peft import ( # noqa: E402
ImportError: cannot import name 'BottleneckConfig' from 'peft' (/usr/local/lib/python3.10/dist-packages/peft/init.py)
Traceback (most recent call last):
File "/content/ChatDoctor/train_lora.py", line 17, in
from peft import ( # noqa: E402
ImportError: cannot import name 'BottleneckConfig' from 'peft' (/usr/local/lib/python3.10/dist-packages/peft/init.py)
Traceback (most recent call last):
File "/content/ChatDoctor/train_lora.py", line 17, in
from peft import ( # noqa: E402
ImportError: cannot import name 'BottleneckConfig' from 'peft' (/usr/local/lib/python3.10/dist-packages/peft/init.py)
Traceback (most recent call last):
File "/content/ChatDoctor/train_lora.py", line 17, in
from peft import ( # noqa: E402
ImportError: cannot import name 'BottleneckConfig' from 'peft' (/usr/local/lib/python3.10/dist-packages/peft/init.py)
Traceback (most recent call last):
File "/content/ChatDoctor/train_lora.py", line 17, in
from peft import ( # noqa: E402Traceback (most recent call last):
ImportError: cannot import name 'BottleneckConfig' from 'peft' (/usr/local/lib/python3.10/dist-packages/peft/init.py)
File "/content/ChatDoctor/train_lora.py", line 17, in
from peft import ( # noqa: E402
ImportError: cannot import name 'BottleneckConfig' from 'peft' (/usr/local/lib/python3.10/dist-packages/peft/init.py)
[2024-02-09 11:16:17,756] torch.distributed.elastic.multiprocessing.api: [ERROR] failed (exitcode: 1) local_rank: 0 (pid: 17760) of binary: /usr/bin/python3
Traceback (most recent call last):
File "/usr/local/bin/torchrun", line 8, in
sys.exit(main())
File "/usr/local/lib/python3.10/dist-packages/torch/distributed/elastic/multiprocessing/errors/init.py", line 346, in wrapper
return f(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/distributed/run.py", line 806, in main
run(args)
File "/usr/local/lib/python3.10/dist-packages/torch/distributed/run.py", line 797, in run
elastic_launch(
File "/usr/local/lib/python3.10/dist-packages/torch/distributed/launcher/api.py", line 134, in call
return launch_agent(self._config, self._entrypoint, list(args))
File "/usr/local/lib/python3.10/dist-packages/torch/distributed/launcher/api.py", line 264, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
File "/content/ChatDoctor/train_lora.py", line 17, in
from peft import ( # noqa: E402
ImportError: cannot import name 'BottleneckConfig' from 'peft' (/usr/local/lib/python3.10/dist-packages/peft/init.py)
Traceback (most recent call last):
File "/content/ChatDoctor/train_lora.py", line 17, in
from peft import ( # noqa: E402
ImportError: cannot import name 'BottleneckConfig' from 'peft' (/usr/local/lib/python3.10/dist-packages/peft/init.py)
Traceback (most recent call last):
File "/content/ChatDoctor/train_lora.py", line 17, in
from peft import ( # noqa: E402
ImportError: cannot import name 'BottleneckConfig' from 'peft' (/usr/local/lib/python3.10/dist-packages/peft/init.py)
Traceback (most recent call last):
File "/content/ChatDoctor/train_lora.py", line 17, in
from peft import ( # noqa: E402
ImportError: cannot import name 'BottleneckConfig' from 'peft' (/usr/local/lib/python3.10/dist-packages/peft/init.py)
Traceback (most recent call last):
File "/content/ChatDoctor/train_lora.py", line 17, in
from peft import ( # noqa: E402Traceback (most recent call last):
ImportError: cannot import name 'BottleneckConfig' from 'peft' (/usr/local/lib/python3.10/dist-packages/peft/init.py)
File "/content/ChatDoctor/train_lora.py", line 17, in
from peft import ( # noqa: E402
ImportError: cannot import name 'BottleneckConfig' from 'peft' (/usr/local/lib/python3.10/dist-packages/peft/init.py)
[2024-02-09 11:16:17,756] torch.distributed.elastic.multiprocessing.api: [ERROR] failed (exitcode: 1) local_rank: 0 (pid: 17760) of binary: /usr/bin/python3
Traceback (most recent call last):
File "/usr/local/bin/torchrun", line 8, in
sys.exit(main())
File "/usr/local/lib/python3.10/dist-packages/torch/distributed/elastic/multiprocessing/errors/init.py", line 346, in wrapper
return f(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/distributed/run.py", line 806, in main
run(args)
File "/usr/local/lib/python3.10/dist-packages/torch/distributed/run.py", line 797, in run
elastic_launch(
File "/usr/local/lib/python3.10/dist-packages/torch/distributed/launcher/api.py", line 134, in call
return launch_agent(self._config, self._entrypoint, list(args))
File "/usr/local/lib/python3.10/dist-packages/torch/distributed/launcher/api.py", line 264, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
/content/ChatDoctor/train_lora.py FAILED
Failures:
[1]:
time : 2024-02-09_11:16:17
host : 10ca0fca3068
rank : 1 (local_rank: 1)
exitcode : 1 (pid: 17761)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
[2]:
time : 2024-02-09_11:16:17
host : 10ca0fca3068
rank : 2 (local_rank: 2)
exitcode : 1 (pid: 17762)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
[3]:
time : 2024-02-09_11:16:17
host : 10ca0fca3068
rank : 3 (local_rank: 3)
exitcode : 1 (pid: 17763)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
[4]:
time : 2024-02-09_11:16:17
host : 10ca0fca3068
rank : 4 (local_rank: 4)
exitcode : 1 (pid: 17764)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
[5]:
time : 2024-02-09_11:16:17
host : 10ca0fca3068
rank : 5 (local_rank: 5)
exitcode : 1 (pid: 17765)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
Root Cause (first observed failure):
[0]:
time : 2024-02-09_11:16:17
host : 10ca0fca3068
rank : 0 (local_rank: 0)
exitcode : 1 (pid: 17760)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
The text was updated successfully, but these errors were encountered: