【代码报错】TerminatedWorkerError Traceback
由faketact创建,最终由small_q 被浏览 16 用户
调优报错:TerminatedWorkerError
为什么32个G的内存,还会报这个错,而且晚上一直出现。
TerminatedWorkerError Traceback (most recent call last) Cell In[2], line 78 75 parameters_list.append(parameters) # 添加参数字典 77 # 运行调优 ---> 78 result = M.tune.run("search", parameters_list) File /opt/pyenv/versions/3.11.8/lib/python3.11/site-packages/bigmodule/tune.py:255, in run(self, name, parameters, workers) File /opt/pyenv/versions/3.11.8/lib/python3.11/site-packages/joblib/parallel.py:2007, in Parallel.call(self, iterable) 2001 # The first item from the output is blank, but it makes the interpreter 2002 # progress until it enters the Try/Except block of the generator and 2003 # reach the first `yield` statement. This starts the aynchronous 2004 # dispatch of the tasks to the workers. 2005 next(output) -> 2007 return output if self.return_generator else list(output) File /opt/pyenv/versions/3.11.8/lib/python3.11/site-packages/joblib/parallel.py:1650, in Parallel._get_outputs(self, iterator, pre_dispatch) 1647 yield 1649 with self._backend.retrieval_context(): -> 1650 yield from self._retrieve() 1652 except GeneratorExit: 1653 # The generator has been garbage collected before being fully 1654 # consumed. This aborts the remaining tasks if possible and warn 1655 # the user if necessary. 1656 self._exception = True File /opt/pyenv/versions/3.11.8/lib/python3.11/site-packages/joblib/parallel.py:1754, in Parallel._retrieve(self) 1747 while self._wait_retrieval(): 1748 1749 # If the callback thread of a worker has signaled that its task 1750 # triggered an exception, or if the retrieval loop has raised an 1751 # exception (e.g. `GeneratorExit`), exit the loop and surface the 1752 # worker traceback. 1753 if self._aborting: -> 1754 self._raise_error_fast() 1755 break 1757 # If the next job is not ready for retrieval yet, we just wait for 1758 # async callbacks to progress. File /opt/pyenv/versions/3.11.8/lib/python3.11/site-packages/joblib/parallel.py:1789, in Parallel._raise_error_fast(self) 1785 # If this error job exists, immediatly raise the error by 1786 # calling get_result. This job might not exists if abort has been 1787 # called directly or if the generator is gc'ed. 1788 if error_job is not None: -> 1789 error_job.get_result(self.timeout) File /opt/pyenv/versions/3.11.8/lib/python3.11/site-packages/joblib/parallel.py:745, in BatchCompletionCallBack.get_result(self, timeout) 739 backend = self.parallel._backend 741 if backend.supports_retrieve_callback: 742 # We assume that the result has already been retrieved by the 743 # callback thread, and is stored internally. It's just waiting to 744 # be returned. --> 745 return self._return_or_raise() 747 # For other backends, the main thread needs to run the retrieval step. 748 try: File /opt/pyenv/versions/3.11.8/lib/python3.11/site-packages/joblib/parallel.py:763, in BatchCompletionCallBack._return_or_raise(self) 761 try: 762 if self.status == TASK_ERROR: --> 763 raise self._result 764 return self._result 765 finally: TerminatedWorkerError: A worker process managed by the executor was unexpectedly terminated. This could be caused by a segmentation fault while calling the function or by an excessive memory usage causing the Operating System to kill the worker. The exit codes of the workers are {SIGKILL(-9)}
\