diff --git a/function.py b/function.py
index 2219d25..9d768a6 100644
--- a/function.py
+++ b/function.py
@@ -1,14 +1,8 @@
 import numpy as np
 import pandas as pd
 from sklearn.preprocessing import StandardScaler
-from sklearn.model_selection import train_test_split
 
 
-"""
-实验说明:
-- 自行编写实现数据加载与预测病马死亡的对率回归算法。
-"""
-
 id = "202210423130"
 name = "董秋"
 
@@ -27,7 +21,7 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000, lambda_reg=0.01):
     m, n = X.shape
     weights = np.zeros(n)
 
-    for _ in range(iterations):
+    for i in range(iterations):
         z = np.dot(X, weights)
         predictions = 1 / (1 + np.exp(-z))
         gradient = np.dot(X.T, (predictions - y)) / m
@@ -37,6 +31,9 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000, lambda_reg=0.01):
 
         weights -= learning_rate * gradient
 
+        # 动态调整学习率，逐渐减小
+        learning_rate *= 0.99  # 每次迭代将学习率乘以0.99
+
     return weights
 
 
@@ -92,7 +89,6 @@ def preprocess_data(X):
 
 
 if __name__ == "__main__":
-    # 以下代码可用于测试，可自行随意修改
     # 加载训练集
     X_train, y_train = load_data("./data/horse-colic.data")
     X_train = preprocess_data(X_train)
@@ -102,7 +98,7 @@ if __name__ == "__main__":
     X_test = preprocess_data(X_test)
 
     # 训练对率回归模型
-    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000, lambda_reg=0.01)
+    weights = train_logreg(X_train, y_train, learning_rate=0.1, iterations=1000, lambda_reg=0.01)
 
     # 测试单个数据
     y_pred = predict_logreg(X_test[11], weights)