bigscience-workshop / bigscience-workshop/petals
Random error when starting docker container again
- Dominant language
- Python
- Stars
- 10.6k
- Forks
- 650
- PR merge metrics
- No merged PRs in 30d
Description
When starting petals in docker, sometimes it will fail with the below error.
Steps:
1. Start petals with the below command
2. Exit petals with Ctrl-C
3. Restart the computer
4. Start petals with the below command again
Immediately re-running the command will succeed without error.
```bash
docker run --rm -p 31330:31330 --ipc host --gpus all --volume petals-cache:/cache --rm learningathome/petals:main python -m petals.cli.run_server --port 31330 stabilityai/StableBeluga2
```
Error message:
```
Aug 18 10:18:55.866 [INFO] Running Petals 2.0.0.post3
Aug 18 10:18:56.069 [INFO] A newer version 2.0.1.post2 is available. Please upgrade with: pip install --upgrade petals
Downloading (…)lve/main/config.json: 100%|██████████| 630/630 [00:00<00:00, 6.23MB/s]
Aug 18 10:18:56.764 [INFO] Make sure you follow the LLaMA's terms of use: https://bit.ly/llama2-license for LLaMA 2, https://bit.ly/llama-license for LLaMA 1
Aug 18 10:18:56.765 [INFO] Using DHT prefix: StableBeluga2-hf
Aug 18 10:19:11.835 [INFO] This server is accessible directly
Traceback (most recent call last):
File "/opt/conda/lib/python3.10/runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/opt/conda/lib/python3.10/runpy.py", line 86, in _run_code
exec(code, run_globals)
File "/home/petals/src/petals/cli/run_server.py", line 224, in
main()
File "/home/petals/src/petals/cli/run_server.py", line 208, in main
server = Server(
File "/home/petals/src/petals/server/server.py", line 135, in __init__
self.dht = DHT(
File "/opt/conda/lib/python3.10/site-packages/hivemind/dht/dht.py", line 88, in __init__
self.run_in_background(await_ready=await_ready)
File "/opt/conda/lib/python3.10/site-packages/hivemind/dht/dht.py", line 148, in run_in_background
self.wait_until_ready(timeout)
File "/opt/conda/lib/python3.10/site-packages/hivemind/dht/dht.py", line 151, in wait_until_ready
self._ready.result(timeout=timeout)
File "/opt/conda/lib/python3.10/site-packages/hivemind/utils/mpfuture.py", line 262, in result
return super().result(timeout)
File "/opt/conda/lib/python3.10/concurrent/futures/_base.py", line 458, in result
return self.__get_result()
File "/opt/conda/lib/python3.10/concurrent/futures/_base.py", line 403, in __get_result
raise self._exception
FileNotFoundError: [Errno 2] No such file or directory
```
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.