diff --git a/examples/run_classifier.py b/examples/run_classifier.py
index 75692ef3..990b390f 100644
--- a/examples/run_classifier.py
+++ b/examples/run_classifier.py
@@ -555,7 +555,8 @@ def main():
                         if args.fp16 and args.loss_scale != 1.0:
                             # scale down gradients for fp16 training
                             for param in model.parameters():
-                                param.grad.data = param.grad.data / args.loss_scale
+                                if param.grad is not None:
+                                    param.grad.data = param.grad.data / args.loss_scale
                         is_nan = set_optimizer_params_grad(param_optimizer, model.named_parameters(), test_nan=True)
                         if is_nan:
                             logger.info("FP16 TRAINING: Nan in gradients, reducing loss scaling")
diff --git a/examples/run_squad.py b/examples/run_squad.py
index 3b546362..b1667576 100644
--- a/examples/run_squad.py
+++ b/examples/run_squad.py
@@ -898,7 +898,8 @@ def main():
                         if args.fp16 and args.loss_scale != 1.0:
                             # scale down gradients for fp16 training
                             for param in model.parameters():
-                                param.grad.data = param.grad.data / args.loss_scale
+                                if param.grad is not None:
+                                    param.grad.data = param.grad.data / args.loss_scale
                         is_nan = set_optimizer_params_grad(param_optimizer, model.named_parameters(), test_nan=True)
                         if is_nan:
                             logger.info("FP16 TRAINING: Nan in gradients, reducing loss scaling")