Update HyperPodPytorchJob (#52)

* Add HyperpodPytorchJob

* update to class methods

* update to class methods

* Address feedback

* Fix bug

* Update HyperPodPytorchJob

* Fix dependency

* Add status

* Add list_pods and get_logs_from_pod

* Add error handling and metadata

* Add example notebook

* Fix bug

---------

Co-authored-by: pintaoz <[email protected]>

Author: pintaoz-aws

sagemaker-hyperpod/examples/training_sdk_example.ipynb

@@ -1,15 +1,15 @@
-from typing import Dict, List, Optional, Self
+from typing import Dict, List, Optional
 from pydantic import Field, ConfigDict, BaseModel
 
 
 class Metadata(BaseModel):
     """Metadata class"""
 
-    name: Optional[str] = Field(
+    name: str = Field(
         description="Name must match the name of one entry in pod.spec.resourceClaims of the Pod where this field is used. It makes that resource available inside a container."
     )
     namespace: Optional[str] = Field(
-        default=None,
+        default="default",
         description="Name must match the name of one entry in pod.spec.resourceClaims of the Pod where this field is used. It makes that resource available inside a container.",
     )
     labels: Optional[Dict[str, str]] = Field(

sagemaker-hyperpod/src/sagemaker/hyperpod/inference/config/common.py

@@ -2957,8 +2957,8 @@ class RunPolicy(BaseModel):
     )
 
 
-class HyperPodPytorchJobSpec(BaseModel):
-    """HyperPodPytorchJobSpec defines the desired state of HyperPodPytorchJob"""
+class _HyperPodPytorchJob(BaseModel):
+    """Config defines the desired state of HyperPodPytorchJob"""
 
     model_config = ConfigDict(extra="forbid")