diff --git a/.jenkins/test/config/dependent_packages.yaml b/.jenkins/test/config/dependent_packages.yaml
index 72069bf798764f622e190b5beafb3b4d505ebcc6..39ca2851681a0b50be8fdc8cbd0fe70190d3609c 100644
--- a/.jenkins/test/config/dependent_packages.yaml
+++ b/.jenkins/test/config/dependent_packages.yaml
@@ -1,2 +1,2 @@
 mindspore:
-  'https://repo.mindspore.cn/mindspore/mindspore/version/202505/20250526/master_20250526010017_b6f48709740e52a1daf206553f742609a0998bae_newest/'
\ No newline at end of file
+  'https://repo.mindspore.cn/mindspore/mindspore/version/202505/20250529/master_20250529010018_c66603449f1452339350f621ebf006fcedae187b_newest/'
\ No newline at end of file
diff --git a/tools/rules/line_rules.py b/tools/rules/line_rules.py
index fe4796237b8e2ae07dd5ef1ee2a7f0da06779a15..b21ca2d7116e4695bda249207d090ea8e9b4e4fd 100644
--- a/tools/rules/line_rules.py
+++ b/tools/rules/line_rules.py
@@ -136,7 +136,7 @@ LINE_RULES = {
 +    # run backward
 +    grad_ = C.GradOperation(True, True, True)
 +    weights = model.trainable_params()
-+    _pynative_executor.check_run(grad_, config.forward_step_func, weights, None, input_tensor[0])
++    _pynative_executor.check_run(grad_, config.forward_step_func, weights, None, input_tensor[0], create_graph=False)
 +    _pynative_executor.grad(config.forward_step_func, grad_, weights, None, input_tensor[0], output_tensor_grad[0])
  
      # Collect the grad of the input_tensor.