| 03/06 17:10:13 - OpenCompass - INFO - Task [my_api/siqa] | |
| /export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/site-packages/transformers/utils/generic.py:311: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead. | |
| torch.utils._pytree._register_pytree_node( | |
| /export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/site-packages/transformers/utils/generic.py:311: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead. | |
| torch.utils._pytree._register_pytree_node( | |
| Python 3.10.13 (main, Sep 11 2023, 13:44:35) [GCC 11.2.0] | |
| Type 'copyright', 'credits' or 'license' for more information | |
| IPython 8.22.2 -- An enhanced Interactive Python. Type '?' for help. | |
| In [1]: [2024-03-06 17:22:48,542] torch.distributed.elastic.agent.server.api: [WARNING] Received Signals.SIGINT death signal, shutting down workers | |
| [2024-03-06 17:22:48,543] torch.distributed.elastic.multiprocessing.api: [WARNING] Sending process 235854 closing signal SIGINT | |
| [2024-03-06 17:22:48,642] torch.distributed.elastic.multiprocessing.api: [WARNING] Sending process 235854 closing signal SIGTERM | |
| Traceback (most recent call last): | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 727, in run | |
| result = self._invoke_run(role) | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 868, in _invoke_run | |
| time.sleep(monitor_interval) | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 62, in _terminate_process_handler | |
| raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval) | |
| torch.distributed.elastic.multiprocessing.api.SignalException: Process 235781 got signal: 2 | |
| During handling of the above exception, another exception occurred: | |
| Traceback (most recent call last): | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 734, in run | |
| self._shutdown(e.sigval) | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/local_elastic_agent.py", line 311, in _shutdown | |
| self._pcontext.close(death_sig) | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 318, in close | |
| self._close(death_sig=death_sig, timeout=timeout) | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 706, in _close | |
| handler.proc.wait(time_to_wait) | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/subprocess.py", line 1209, in wait | |
| return self._wait(timeout=timeout) | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/subprocess.py", line 1953, in _wait | |
| time.sleep(delay) | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 62, in _terminate_process_handler | |
| raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval) | |
| torch.distributed.elastic.multiprocessing.api.SignalException: Process 235781 got signal: 2 | |
| During handling of the above exception, another exception occurred: | |
| Traceback (most recent call last): | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/bin/torchrun", line 8, in <module> | |
| sys.exit(main()) | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 347, in wrapper | |
| return f(*args, **kwargs) | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/site-packages/torch/distributed/run.py", line 812, in main | |
| run(args) | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/site-packages/torch/distributed/run.py", line 803, in run | |
| elastic_launch( | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 135, in __call__ | |
| return launch_agent(self._config, self._entrypoint, list(args)) | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 259, in launch_agent | |
| result = agent.run() | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/site-packages/torch/distributed/elastic/metrics/api.py", line 123, in wrapper | |
| result = f(*args, **kwargs) | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 739, in run | |
| self._shutdown() | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/local_elastic_agent.py", line 311, in _shutdown | |
| self._pcontext.close(death_sig) | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 318, in close | |
| self._close(death_sig=death_sig, timeout=timeout) | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 706, in _close | |
| handler.proc.wait(time_to_wait) | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/subprocess.py", line 1209, in wait | |
| return self._wait(timeout=timeout) | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/subprocess.py", line 1953, in _wait | |
| time.sleep(delay) | |
| File "/export/home/tanwentao1/anaconda3/envs/opencompass/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 62, in _terminate_process_handler | |
| raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval) | |
| torch.distributed.elastic.multiprocessing.api.SignalException: Process 235781 got signal: 2 | |