Google Colab Tensorflow model not using all samples in epochs

Question

My training data has 10680 samples and I've set the fit like this:

model.fit(X, y, batch_size=32, epochs=5, verbose=1, validation_split=0.1)

Which means it should use 90% to train (9612 samples) and the other 10% to check, right?

But when I try to run it the epochs shown are:

Epoch 1/5
301/301 [==============================] - 25s 85ms/step - loss: nan - accuracy: 0.4999 - val_loss: nan - val_accuracy: 0

It's using only 301 samples to fit.

What am I doing wrong or not seeing here?

I know it's not right because it worked once (with 9612 samples).

This is the model:

keras.utils.normalize(X)

model = Sequential()

model.add(Conv2D(128, (3,3), input_shape = X.shape[1:]))
model.add(Activation("relu"))
model.add(MaxPooling2D(pool_size=(2,2)))

model.add(Conv2D(128, (3,3)))
model.add(Activation("relu"))
model.add(MaxPooling2D(pool_size=(2,2)))

model.add(Flatten()) # Converts 3D feature maps to 1D feature vectors

model.add(Dense(128, kernel_regularizer= tf.keras.regularizers.l2(5e-5)))
model.add(Activation("relu"))

model.add(Dense(1, kernel_regularizer=tf.keras.regularizers.l2(5e-5)))
model.add(Activation("sigmoid"))

sgd = tf.keras.optimizers.SGD(lr=0.001, decay=1e-6, momentum=0.9, nesterov=True)

model.compile(loss="binary_crossentropy",
              optimizer=sgd,
              metrics=['accuracy'])

model.summary()

Answer 1

I think the 301 there means the number of batches, so since you have 9612 data and set batch_size=32, the number of batches are expected to be 9612 / 32 = 300.375 -> 301