diff --git a/docs/QUICK_STARTED.md b/docs/QUICK_STARTED.md
index 5b687b35e72718be939b83299a5e9a799d6f5e79..c6649f71f7b41c2fda00141e20c16dffc1f93e40 100644
--- a/docs/QUICK_STARTED.md
+++ b/docs/QUICK_STARTED.md
@@ -2,7 +2,7 @@ English | [简体中文](QUICK_STARTED_cn.md)
 
 # Quick Start
 
-This tutorial fine-tunes a tiny dataset by pretrained detection model for users to get a model and learn PaddleDetection quickly. The model can be trained in around 15min with good performance.
+This tutorial fine-tunes a tiny dataset by pretrained detection model for users to get a model and learn PaddleDetection quickly. The model can be trained in around 20min with good performance.
 
 ## Data Preparation
 
diff --git a/docs/QUICK_STARTED_cn.md b/docs/QUICK_STARTED_cn.md
index 78c019a6bfe7bcb82ca5a42ea9d65cf26f397aeb..8c02ffb798250a0fa29db02ab7e4b38f04e4daac 100644
--- a/docs/QUICK_STARTED_cn.md
+++ b/docs/QUICK_STARTED_cn.md
@@ -2,7 +2,7 @@
 
 # 快速开始
 
-为了使得用户能够在很短的时间内快速产出模型，掌握PaddleDetection的使用方式，这篇教程通过一个预训练检测模型对小数据集进行finetune。在P40上单卡大约15min即可产出一个效果不错的模型。
+为了使得用户能够在很短的时间内快速产出模型，掌握PaddleDetection的使用方式，这篇教程通过一个预训练检测模型对小数据集进行finetune。在P40上单卡大约20min即可产出一个效果不错的模型。
 
 ## 数据准备