Skip to content

fix(train): Skip default instance_type/instance_count when instance_groups is set #5564

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
mufaddal-rohawala wants to merge 1 commit into
base: master
Choose a base branch
from
Open

fix(train): Skip default instance_type/instance_count when instance_groups is set #5564

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 24 additions & 14 deletions sagemaker-train/src/sagemaker/train/defaults.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -100,12 +100,15 @@ def get_compute(compute: Optional[Compute] = None) -> Compute:
volume_size_in_gb=DEFAULT_VOLUME_SIZE,
)
logger.info(f"Compute not provided. Using default:\n{compute}")
if compute.instance_type is None:
compute.instance_type = DEFAULT_INSTANCE_TYPE
logger.info(f"Instance type not provided. Using default:\n{DEFAULT_INSTANCE_TYPE}")
if compute.instance_count is None:
compute.instance_count = DEFAULT_INSTANCE_COUNT
logger.info(f"Instance count not provided. Using default:\n{compute.instance_count}")
if not compute.instance_groups:
if compute.instance_type is None:
compute.instance_type = DEFAULT_INSTANCE_TYPE
logger.info(f"Instance type not provided. Using default:\n{DEFAULT_INSTANCE_TYPE}")
if compute.instance_count is None:
compute.instance_count = DEFAULT_INSTANCE_COUNT
logger.info(
f"Instance count not provided. Using default:\n{compute.instance_count}"
)
if compute.volume_size_in_gb is None:
compute.volume_size_in_gb = DEFAULT_VOLUME_SIZE
logger.info(f"Volume size not provided. Using default:\n{compute.volume_size_in_gb}")
Expand Down Expand Up @@ -225,21 +228,28 @@ def get_compute(
),
)
logger.info(f"Compute not provided. Using default compute:\n{compute}")
if compute.instance_type is None and training_components_model.DefaultTrainingInstanceType:
compute.instance_type = training_components_model.DefaultTrainingInstanceType
logger.info(
f"Instance type not provided. Using default instance type:\n{compute.instance_type}"
)
if not compute.instance_groups:
if (
compute.instance_type is None
and training_components_model.DefaultTrainingInstanceType
):
compute.instance_type = training_components_model.DefaultTrainingInstanceType
logger.info(
f"Instance type not provided. Using default instance type:"
f"\n{compute.instance_type}"
)
if compute.instance_count is None:
compute.instance_count = DEFAULT_INSTANCE_COUNT
logger.info(
f"Instance count not provided. Using default instance count:\n{compute}"
)
if compute.volume_size_in_gb is None:
compute.volume_size_in_gb = (
training_components_model.TrainingVolumeSize or DEFAULT_VOLUME_SIZE
)
logger.info(
f"Volume size not provided. Using default volume size:\n{compute.volume_size_in_gb}"
)
if compute.instance_count is None:
compute.instance_count = DEFAULT_INSTANCE_COUNT
logger.info(f"Instance count not provided. Using default instance count:\n{compute}")
return compute

def get_networking(
Expand Down
Loading