Skip to content

Fix: Add mlflowconfig to eval base model #5745

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
mollyheamazon wants to merge 2 commits into
base: master
Choose a base branch
from
+22 −7
Open

Fix: Add mlflowconfig to eval base model #5745

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a85f62e
Add mlflowconfig to eval
mollyheamazon Apr 10, 2026
65d1b41
Update unit and integ test
mollyheamazon Apr 11, 2026
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
12 changes: 12 additions & 0 deletions sagemaker-train/src/sagemaker/train/evaluate/pipeline_templates.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -326,6 +326,10 @@
LLMAJ_TEMPLATE_BASE_MODEL_ONLY = """{
"Version": "2020-12-01",
"Metadata": {},
"MlflowConfig": {
"MlflowResourceArn": "{{ mlflow_resource_arn }}"{% if mlflow_experiment_name %},
"MlflowExperimentName": "{{ mlflow_experiment_name }}"{% endif %}
},
"Parameters": [],
"Steps": [
{
Expand Down Expand Up @@ -457,6 +461,10 @@
DETERMINISTIC_TEMPLATE_BASE_MODEL_ONLY = """{
"Version": "2020-12-01",
"Metadata": {},
"MlflowConfig": {
"MlflowResourceArn": "{{ mlflow_resource_arn }}"{% if mlflow_experiment_name %},
"MlflowExperimentName": "{{ mlflow_experiment_name }}"{% endif %}
},
"Parameters": [],
"Steps": [
{
Expand Down Expand Up @@ -843,6 +851,10 @@
CUSTOM_SCORER_TEMPLATE_BASE_MODEL_ONLY = """{
"Version": "2020-12-01",
"Metadata": {},
"MlflowConfig": {
"MlflowResourceArn": "{{ mlflow_resource_arn }}"{% if mlflow_experiment_name %},
"MlflowExperimentName": "{{ mlflow_experiment_name }}"{% endif %}
},
"Parameters": [],
"Steps": [
{
Expand Down
2 changes: 1 addition & 1 deletion sagemaker-train/tests/integ/train/test_benchmark_evaluator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -307,7 +307,7 @@ def test_benchmark_evaluation_base_model_only(self):
benchmark=Benchmark.MMLU,
model=BASE_MODEL_ONLY_CONFIG["base_model_id"],
s3_output_path=BASE_MODEL_ONLY_CONFIG["s3_output_path"],
# mlflow_resource_arn=BASE_MODEL_ONLY_CONFIG["mlflow_tracking_server_arn"],
mlflow_resource_arn=BASE_MODEL_ONLY_CONFIG["mlflow_tracking_server_arn"],
base_eval_name="integ-test-base-model-only",
# Note: model_package_group not needed for JumpStart models
)
Expand Down
15 changes: 9 additions & 6 deletions sagemaker-train/tests/unit/train/evaluate/test_pipeline_templates.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -317,8 +317,9 @@ def test_deterministic_base_model_only_with_all_params(self):

base_model_step = pipeline_def["Steps"][0]

# Verify MLflow config is not present in BASE_MODEL_ONLY template
assert "MlflowConfig" not in pipeline_def
# Verify MLflow config is present in BASE_MODEL_ONLY template
assert "MlflowConfig" in pipeline_def
assert pipeline_def["MlflowConfig"]["MlflowResourceArn"] == BASE_CONTEXT["mlflow_resource_arn"]

# Verify KMS key
assert base_model_step["Arguments"]["OutputDataConfig"]["KmsKeyId"] == context["kms_key_id"]
Expand Down Expand Up @@ -403,8 +404,9 @@ def test_custom_scorer_base_model_only_minimal(self):

pipeline_def = json.loads(rendered)

# Verify MLflow config is not present in BASE_MODEL_ONLY template
assert "MlflowConfig" not in pipeline_def
# Verify MLflow config is present in BASE_MODEL_ONLY template
assert "MlflowConfig" in pipeline_def
assert pipeline_def["MlflowConfig"]["MlflowResourceArn"] == BASE_CONTEXT["mlflow_resource_arn"]

# Should have only 1 step
assert len(pipeline_def["Steps"]) == 1
Expand Down Expand Up @@ -574,8 +576,9 @@ def test_llmaj_base_model_only_minimal(self):

pipeline_def = json.loads(rendered)

# Verify MLflow config is not present in BASE_MODEL_ONLY template
assert "MlflowConfig" not in pipeline_def
# Verify MLflow config is present in BASE_MODEL_ONLY template
assert "MlflowConfig" in pipeline_def
assert pipeline_def["MlflowConfig"]["MlflowResourceArn"] == BASE_CONTEXT["mlflow_resource_arn"]

# Should have 2 steps: EvaluateBaseInferenceModel and EvaluateBaseModelMetrics
assert len(pipeline_def["Steps"]) == 2
Expand Down
Loading