num_epochs, learning_rate, weight_decay, batch_size = 100, 0.01, 0, 64 x_train, x_valid, y_train, y_valid = train_test_split(train_features, train_labels, test_size = 0.2,random_state=66) model=linreg train_ls, valid_ls, theta = train(model, x_train, y_train, x_valid, y_valid, num_epochs, learning_rate, weight_decay, batch_size) print(f'训练log rmse: {float(train_ls[-1]):f}, 'f'验证log rmse: {float(valid_ls[-1]):f}') plot(list(range(1, num_epochs + 1)), [train_ls, valid_ls], xlabel='epoch', ylabel='rmse', xlim=[1, num_epochs], legend=['train', 'valid'], yscale='log') 帮我写个注释

# 设置超参数
num_epochs, learning_rate, weight_decay, batch_size = 100, 0.01, 0, 64

# 将训练数据划分为训练集和验证集
x_train, x_valid, y_train, y_valid = train_test_split(train_features, train_labels, test_size = 0.2,random_state=66)

# 创建线性回归模型
model = linreg

# 训练模型并返回训练过程中的损失和参数
train_ls, valid_ls, theta = train(model, x_train, y_train, x_valid, y_valid, num_epochs, learning_rate, weight_decay, batch_size)

# 输出训练集和验证集的最终log rmse
print(f'训练log rmse: {float(train_ls[-1]):f}, 'f'验证log rmse: {float(valid_ls[-1]):f}')

# 绘制训练集和验证集的损失随epoch变化的曲线图
plot(list(range(1, num_epochs + 1)), [train_ls, valid_ls],
xlabel='epoch', ylabel='rmse', xlim=[1, num_epochs],
legend=['train', 'valid'], yscale='log')