What does loss vs epoch indicate for recommendation system with MLP model which ran on keras

Question

plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()

what does loss really indicate i have used this one

model.compile(
optimizer=keras.optimizers.Adam(1e-3), 
loss=tf.keras.losses.MeanSquaredError(), 
metrics=metrics

)

is my model overfitted I have 4 layers in each layer I have used 120,60,25,1 neurons