Update documentation-with-new-changes branch with latest changes from main (#190)

* Fix training test (#184)

* Fix SDK training test: Add wait time before refresh

* Fix training tests in canaries

* Update logging information for submitting and deleting training job (#189)

Co-authored-by: pintaoz <pintaoz@amazon.com>

---------

Co-authored-by: Zhaoqi <zhaoqiwang.baruch@gmail.com>
Co-authored-by: pintaoz-aws <167920275+pintaoz-aws@users.noreply.github.com>
Co-authored-by: pintaoz <pintaoz@amazon.com>

Author: 4 people

src/sagemaker/hyperpod/cli/commands/training.py

@@ -1,16 +1,7 @@
 import click
-import logging
-import os
-import yaml
-import shutil
-import subprocess
-from pathlib import Path
 from sagemaker.hyperpod.training.hyperpod_pytorch_job import HyperPodPytorchJob
 from sagemaker.hyperpod.common.config import Metadata
-import tempfile
-from typing import List, Dict, Any, Optional, Callable, get_args, get_origin, Literal
 from sagemaker.hyperpod.cli.training_utils import generate_click_command
-from importlib.metadata import entry_points
 from hyperpod_pytorch_job_template.registry import SCHEMA_REGISTRY
 from sagemaker.hyperpod.common.telemetry.telemetry_logging import (
     _hyperpod_telemetry_emitter,

src/sagemaker/hyperpod/training/hyperpod_pytorch_job.py

@@ -3,8 +3,8 @@
     _HyperPodPytorchJob, HyperPodPytorchJobStatus
 )
 from sagemaker.hyperpod.common.config.metadata import Metadata
-from kubernetes import client, config, __version__ as kubernetes_client_version
-from typing import List, Optional, ClassVar, Tuple
+from kubernetes import client, config
+from typing import List, Optional, ClassVar
 from sagemaker.hyperpod.common.utils import (
     handle_exception,
     get_default_namespace,
@@ -84,7 +84,7 @@ def create(self, debug=False):
                 plural=PLURAL,
                 body=config,
             )
-            logger.info("Successfully submitted HyperPodPytorchJob!")
+            logger.info(f"Successfully submitted HyperPodPytorchJob '{self.metadata.name}'!")
         except Exception as e:
             logger.error(f"Failed to create HyperPodPytorchJob {self.metadata.name}!")
             handle_exception(e, self.metadata.name, self.metadata.namespace)
@@ -131,7 +131,7 @@ def delete(self):
                 plural=PLURAL,
                 name=self.metadata.name,
             )
-            logger.info(f"Successful deleted HyperPodPytorchJob!")
+            logger.info(f"Successful deleted HyperPodPytorchJob '{self.metadata.name}'!")
         except Exception as e:
             logger.error(f"Failed to delete HyperPodPytorchJob {self.metadata.name}!")
             handle_exception(e, self.metadata.name, self.metadata.namespace)

test/integration_tests/training/cli/test_cli_training.py

@@ -27,16 +27,6 @@ def test_list_clusters(self, cluster_name):
         """Test listing clusters """
         assert cluster_name
 
-    def test_set_cluster_context(self, cluster_name):
-        """Test setting cluster context."""
-        result = execute_command([
-            "hyp", "set-cluster-context",
-            "--cluster-name", cluster_name
-        ])
-        assert result.returncode == 0
-        context_line = result.stdout.strip().splitlines()[-1]
-        assert any(text in context_line for text in ["Updated context", "Added new context"])
-
     def test_get_cluster_context(self):
         """Test getting current cluster context."""
         result = execute_command(["hyp", "get-cluster-context"])

test/integration_tests/training/sdk/test_sdk_training.py

@@ -70,10 +70,9 @@ def test_list_jobs(self, pytorch_job):
         job_names = [job.metadata.name for job in jobs]
         assert pytorch_job.metadata.name in job_names
 
-    #
     def test_refresh_job(self, pytorch_job):
         pytorch_job.refresh()
-        time.sleep(15)
+        time.sleep(30)
         assert pytorch_job.status is not None, "Job status should not be None"
         logger.info(f"Refreshed job status:\n{yaml.dump(pytorch_job.status)}")