fix: drop claude-sonnet-4-20250514 from evaluator allowlist (#6009)

Remove anthropic.claude-sonnet-4-20250514-v1:0 from the LLM-as-Judge
evaluator allowlist and re-point the docstring examples and unit-test
default judge model to anthropic.claude-sonnet-4-5-20250929-v1:0.

Author: jam-jee

sagemaker-train/src/sagemaker/train/constants.py

@@ -67,7 +67,6 @@ def get_sagemaker_hub_name() -> str:
     "mistral.mistral-large-2402-v1:0": ["us-west-2", "us-east-1", "eu-west-1"],
     "meta.llama3-1-70b-instruct-v1:0": ["us-west-2", "us-east-1"],
     "anthropic.claude-3-haiku-20240307-v1:0": ["us-west-2", "us-east-1", "ap-northeast-1", "eu-west-1"],
-    "anthropic.claude-sonnet-4-20250514-v1:0": ["us-west-2", "us-east-1", "ap-northeast-1", "eu-west-1"],
     "anthropic.claude-haiku-4-5-20251001-v1:0": ["us-west-2", "us-east-1", "ap-northeast-1", "eu-west-1"],
     "anthropic.claude-sonnet-4-5-20250929-v1:0": ["us-west-2", "us-east-1", "ap-northeast-1", "eu-west-1"],
     "anthropic.claude-opus-4-5-20251101-v1:0": ["us-west-2", "us-east-1", "ap-northeast-1", "eu-west-1"],

sagemaker-train/src/sagemaker/train/evaluate/llm_as_judge_evaluator.py

@@ -110,7 +110,7 @@ class LLMAsJudgeEvaluator(BaseEvaluator):
             # Both formats work - with or without 'Builtin.' prefix
             evaluator = LLMAsJudgeEvaluator(
                 base_model="llama-3-3-70b-instruct",
-                evaluator_model="anthropic.claude-sonnet-4-20250514-v1:0",
+                evaluator_model="anthropic.claude-sonnet-4-5-20250929-v1:0",
                 dataset="s3://my-bucket/my-dataset.jsonl",
                 builtin_metrics=["Correctness", "Helpfulness"],  # Prefix optional
                 mlflow_resource_arn="arn:aws:sagemaker:us-west-2:123456789012:mlflow-tracking-server/my-server",
@@ -144,7 +144,7 @@ class LLMAsJudgeEvaluator(BaseEvaluator):
             # Example evaluating only custom model (skip base model)
             evaluator = LLMAsJudgeEvaluator(
                 base_model="llama-3-3-70b-instruct",
-                evaluator_model="anthropic.claude-sonnet-4-20250514-v1:0",
+                evaluator_model="anthropic.claude-sonnet-4-5-20250929-v1:0",
                 dataset="s3://my-bucket/my-dataset.jsonl",
                 builtin_metrics=["Correctness"],  # Prefix optional
                 evaluate_base_model=False,
@@ -776,7 +776,7 @@ def evaluate(self):
             
                 evaluator = LLMAsJudgeEvaluator(
                     base_model="llama-3-3-70b-instruct",
-                    evaluator_model="anthropic.claude-sonnet-4-20250514-v1:0",
+                    evaluator_model="anthropic.claude-sonnet-4-5-20250929-v1:0",
                     dataset="s3://my-bucket/my-dataset.jsonl",
                     builtin_metrics=["Correctness", "Helpfulness"],
                     s3_output_path="s3://my-bucket/output"

sagemaker-train/tests/unit/train/evaluate/test_llm_as_judge_evaluator.py

@@ -31,7 +31,7 @@
 DEFAULT_MODEL_PACKAGE_GROUP_ARN = "arn:aws:sagemaker:us-west-2:123456789012:model-package-group/test-group"
 DEFAULT_BASE_MODEL_ARN = "arn:aws:sagemaker:us-west-2:aws:hub-content/SageMakerPublicHub/Model/llama3-2-1b-instruct/1.0.0"
 DEFAULT_ARTIFACT_ARN = "arn:aws:sagemaker:us-west-2:123456789012:artifact/test-artifact"
-DEFAULT_EVALUATOR_MODEL = "anthropic.claude-sonnet-4-20250514-v1:0"
+DEFAULT_EVALUATOR_MODEL = "anthropic.claude-sonnet-4-5-20250929-v1:0"
 
 
 @patch('sagemaker.train.common_utils.model_resolution._resolve_base_model')
@@ -851,7 +851,6 @@ def test_llm_as_judge_evaluator_valid_evaluator_models(mock_artifact, mock_resol
     # (covered by test_llm_as_judge_evaluator_region_restriction).
     valid_models = [
         "anthropic.claude-3-haiku-20240307-v1:0",
-        "anthropic.claude-sonnet-4-20250514-v1:0",
         "anthropic.claude-haiku-4-5-20251001-v1:0",
         "anthropic.claude-sonnet-4-5-20250929-v1:0",
         "anthropic.claude-opus-4-5-20251101-v1:0",