feature: allow disabling debugger_hook_config (#1194)

Author: knakad

src/sagemaker/estimator.py

@@ -327,7 +327,7 @@ def _prepare_for_training(self, job_name=None):
                 self.output_path = "s3://{}/".format(self.sagemaker_session.default_bucket())
 
         # Prepare rules and debugger configs for training.
-        if self.rules and not self.debugger_hook_config:
+        if self.rules and self.debugger_hook_config is None:
             self.debugger_hook_config = DebuggerHookConfig(s3_output_path=self.output_path)
         # If an object was provided without an S3 URI is not provided, default it for the customer.
         if self.debugger_hook_config and not self.debugger_hook_config.s3_output_path:
@@ -378,7 +378,7 @@ def _prepare_collection_configs(self):
             for rule in self.rules:
                 self.collection_configs.update(rule.collection_configs)
         # Add the CollectionConfigs from DebuggerHookConfig to the set.
-        if self.debugger_hook_config is not None:
+        if self.debugger_hook_config:
             self.collection_configs.update(self.debugger_hook_config.collection_configs or [])
 
     def latest_job_debugger_artifacts_path(self):
@@ -1676,6 +1676,8 @@ def _validate_and_set_debugger_configs(self):
         """
         if self.debugger_hook_config is None:
             self.debugger_hook_config = DebuggerHookConfig(s3_output_path=self.output_path)
+        elif not self.debugger_hook_config:
+            self.debugger_hook_config = None
 
     def _stage_user_code_in_s3(self):
         """Upload the user training script to s3 and return the location.

tests/integ/test_debugger.py

@@ -435,6 +435,38 @@ def test_mxnet_with_all_rules_and_configs(sagemaker_session, mxnet_full_version,
         _wait_and_assert_that_no_rule_jobs_errored(training_job=mx.latest_training_job)
 
 
+def test_mxnet_with_debugger_hook_config_disabled(
+    sagemaker_session, mxnet_full_version, cpu_instance_type
+):
+    with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
+        script_path = os.path.join(DATA_DIR, "mxnet_mnist", "mnist_gluon.py")
+        data_path = os.path.join(DATA_DIR, "mxnet_mnist")
+
+        mx = MXNet(
+            entry_point=script_path,
+            role="SageMakerRole",
+            framework_version=mxnet_full_version,
+            py_version=PYTHON_VERSION,
+            train_instance_count=1,
+            train_instance_type=cpu_instance_type,
+            sagemaker_session=sagemaker_session,
+            debugger_hook_config=False,
+        )
+
+        train_input = mx.sagemaker_session.upload_data(
+            path=os.path.join(data_path, "train"), key_prefix="integ-test-data/mxnet_mnist/train"
+        )
+        test_input = mx.sagemaker_session.upload_data(
+            path=os.path.join(data_path, "test"), key_prefix="integ-test-data/mxnet_mnist/test"
+        )
+
+        mx.fit({"train": train_input, "test": test_input})
+
+        job_description = mx.latest_training_job.describe()
+
+        assert job_description.get("DebugHookConfig") is None
+
+
 def _get_custom_rule(session):
     script_path = os.path.join(DATA_DIR, "mxnet_mnist", "my_custom_rule.py")