diff --git a/trainer/train_pretrain_vlm.py b/trainer/train_pretrain_vlm.py
index 7f684c4..403a1cb 100644
--- a/trainer/train_pretrain_vlm.py
+++ b/trainer/train_pretrain_vlm.py
@@ -95,7 +95,7 @@ if __name__ == "__main__":
     parser.add_argument("--learning_rate", type=float, default=4e-4, help="初始学习率")
     parser.add_argument("--device", type=str, default="cuda:0" if torch.cuda.is_available() else "cpu", help="训练设备")
     parser.add_argument("--dtype", type=str, default="bfloat16", help="混合精度类型")
-    parser.add_argument("--num_workers", type=int, default=8, help="数据加载线程数")
+    parser.add_argument("--num_workers", type=int, default=2, help="数据加载线程数")
     parser.add_argument("--accumulation_steps", type=int, default=1, help="梯度累积步数")
     parser.add_argument("--grad_clip", type=float, default=1.0, help="梯度裁剪阈值")
     parser.add_argument("--log_interval", type=int, default=100, help="日志打印间隔")
diff --git a/trainer/train_sft_vlm.py b/trainer/train_sft_vlm.py
index 5ebef0e..60972a8 100644
--- a/trainer/train_sft_vlm.py
+++ b/trainer/train_sft_vlm.py
@@ -95,7 +95,7 @@ if __name__ == "__main__":
     parser.add_argument("--learning_rate", type=float, default=5e-6, help="初始学习率")
     parser.add_argument("--device", type=str, default="cuda:0" if torch.cuda.is_available() else "cpu", help="训练设备")
     parser.add_argument("--dtype", type=str, default="bfloat16", help="混合精度类型")
-    parser.add_argument("--num_workers", type=int, default=8, help="数据加载线程数")
+    parser.add_argument("--num_workers", type=int, default=2, help="数据加载线程数")
     parser.add_argument("--accumulation_steps", type=int, default=1, help="梯度累积步数")
     parser.add_argument("--grad_clip", type=float, default=1.0, help="梯度裁剪阈值")
     parser.add_argument("--log_interval", type=int, default=100, help="日志打印间隔")