diff --git a/orttraining/orttraining/test/model/training_runner_test.cc b/orttraining/orttraining/test/model/training_runner_test.cc
index 6e257b9943..b8be4dfd20 100644
--- a/orttraining/orttraining/test/model/training_runner_test.cc
+++ b/orttraining/orttraining/test/model/training_runner_test.cc
@@ -11,7 +11,6 @@
 #include "core/common/path_string.h"
 #include "core/platform/path_lib.h"
 #include "core/session/environment.h"
-#include "core/providers/cuda/cuda_execution_provider.h"
 #include "orttraining/models/runner/data_loader.h"
 #include "orttraining/models/runner/training_util.h"
 #include "test/util/include/default_providers.h"
diff --git a/orttraining/orttraining/test/session/training_session_test.cc b/orttraining/orttraining/test/session/training_session_test.cc
index 578d4ce1ce..ff2935c075 100644
--- a/orttraining/orttraining/test/session/training_session_test.cc
+++ b/orttraining/orttraining/test/session/training_session_test.cc
@@ -15,12 +15,6 @@
 
 #include "orttraining/training_ops/cpu/controlflow/event_pool.h"  // TODO: move with PipelineBatchPlanner
 
-#ifdef USE_CUDA
-#include "core/providers/cuda/cuda_execution_provider.h"
-#elif USE_ROCM
-#include "core/providers/rocm/rocm_execution_provider.h"
-#endif
-
 using namespace onnxruntime::logging;
 using namespace onnxruntime::training;
 using namespace google::protobuf::util;
@@ -34,7 +28,7 @@ static void RunTrainingSessionLoadOptimTests(std::string optim_name, bool mixed_
   auto config = MakeBasicTrainingConfig();
   if (mixed_precision) {
     TrainingSession::TrainingConfiguration::MixedPrecisionConfiguration mp{};
-    mp.use_mixed_precision_initializers=true;
+    mp.use_mixed_precision_initializers = true;
     config.mixed_precision_config = mp;
   }
   GenerateOptimizerConfig(optim_name, mixed_precision_moments, config);
diff --git a/orttraining/orttraining/test/session/training_session_test_utils.h b/orttraining/orttraining/test/session/training_session_test_utils.h
index 008947ddf9..ae84d8dc4e 100644
--- a/orttraining/orttraining/test/session/training_session_test_utils.h
+++ b/orttraining/orttraining/test/session/training_session_test_utils.h
@@ -17,7 +17,7 @@
 #include "orttraining/training_ops/cpu/controlflow/event_pool.h"  // TODO: move with PipelineBatchPlanner
 
 #ifdef USE_CUDA
-#include "core/providers/cuda/cuda_execution_provider.h"
+#include "core/providers/cuda/cuda_execution_provider_info.h"
 #elif USE_ROCM
 #include "core/providers/rocm/rocm_execution_provider.h"
 #endif
@@ -44,18 +44,18 @@ void GenerateOptimizerConfig(const std::string optimizer_name,
                              training::TrainingSession::TrainingConfiguration& config);
 
 template <class T>
-void GenerateOptimizerInitialState(const std::string& optimizer_op_name, 
-                                    const T init_moment_value, 
-                                    training::TrainingSession::OptimizerState& optimizer_state);
+void GenerateOptimizerInitialState(const std::string& optimizer_op_name,
+                                   const T init_moment_value,
+                                   training::TrainingSession::OptimizerState& optimizer_state);
 
-void SeparateStateTensors(const NameMLValMap& training_state, 
-                          NameMLValMap& model_state, 
+void SeparateStateTensors(const NameMLValMap& training_state,
+                          NameMLValMap& model_state,
                           training::TrainingSession::OptimizerState& optimizer_state);
 
 void VerifyState(const DataTransferManager& data_transfer_mgr, const NameMLValMap& expected_state, const NameMLValMap& actual_state);
 
-void VerifyOptimizerState(const DataTransferManager& data_transfer_manager, 
-                          const training::TrainingSession::OptimizerState& expected_state, 
+void VerifyOptimizerState(const DataTransferManager& data_transfer_manager,
+                          const training::TrainingSession::OptimizerState& expected_state,
                           const training::TrainingSession::OptimizerState& actual_state);
 
 std::unordered_set<std::string> GetModelOutputNames(const InferenceSession& session);