File tree Expand file tree Collapse file tree 2 files changed +8
-6
lines changed
src/sagemaker/remote_function Expand file tree Collapse file tree 2 files changed +8
-6
lines changed Original file line number Diff line number Diff line change @@ -284,8 +284,9 @@ def remote(
284284 use_torchrun (bool): Specifies whether to use torchrun for distributed training.
285285 Defaults to ``False``.
286286
287- nproc_per_node (int): Specifies the number of processes per node for distributed training.
288- Defaults to ``1``. This is defined automatically configured on the instance type.
287+ nproc_per_node (int): Specifies the number of processes per node for
288+ distributed training. Defaults to ``1``.
289+ This is defined automatically configured on the instance type.
289290 """
290291
291292 def _remote (func ):
@@ -728,8 +729,9 @@ def __init__(
728729 use_torchrun (bool): Specifies whether to use torchrun for distributed training.
729730 Defaults to ``False``.
730731
731- nproc_per_node (int): Specifies the number of processes per node for distributed training.
732- Defaults to ``1``. This is defined automatically configured on the instance type.
732+ nproc_per_node (int): Specifies the number of processes per node for
733+ distributed training. Defaults to ``1``.
734+ This is defined automatically configured on the instance type.
733735 """
734736 self .max_parallel_jobs = max_parallel_jobs
735737
Original file line number Diff line number Diff line change @@ -536,13 +536,13 @@ def main(sys_args=None):
536536
537537 if os .path .exists (RESOURCE_CONFIG ):
538538 try :
539- logger .info (f "Found { RESOURCE_CONFIG } " )
539+ logger .info ("Found %s" , RESOURCE_CONFIG )
540540 with open (RESOURCE_CONFIG , "r" ) as f :
541541 resource_config = json .load (f )
542542 set_env (resource_config = resource_config )
543543 except (json .JSONDecodeError , FileNotFoundError ) as e :
544544 # Optionally, you might want to log this error
545- logger .info (f" Error processing { RESOURCE_CONFIG } : { str (e )} " )
545+ logger .info ("ERROR: Error processing %s: %s" , RESOURCE_CONFIG , str (e ))
546546
547547 exit_code = SUCCESS_EXIT_CODE
548548 except Exception as e : # pylint: disable=broad-except
You can’t perform that action at this time.
0 commit comments