无损训练集和低准确率

Question

当我对我的神经网络进行训练时，我得到的结果是 loss = nan 和 0.65 我的数据是小 14 个自变量和一个变量和二进制输出，我的矩阵是 60x14，我用隐藏两层，参数如下：

classifier = Sequential()

classifier.add(Dense(units = 7, kernel_initializer = "uniform", activation = "relu", input_dim = 13))

classifier.add(Dense(units = 7, kernel_initializer = "uniform", activation = "relu"))

classifier.add(Dense(units = 1, kernel_initializer = "uniform", activation = "sigmoid"))

classifier.compile(optimizer = "adam", loss = "binary_crossentropy", metrics = ["accuracy"])

classifier.fit(X_train, y_train, batch_size= 6, epochs= 100)

我可以更改批量大小和时期，但我的问题是因为我看不到损失