Get hyperparameter choice inside the function create_model()

[harshilpatel312]

In order to plot training history, I'm using tensorboard callback. I would like to name my models on the basis of the hyperparameters being evaluated at that moment. Something like:

tensorboard = TensorBoard(log_dir="logs/{0}-{1}-{2}".format(param1, param2, param3)
model.fit(x_train, y_train,
              batch_size=1024,
              epochs=10,
              callbacks=[tensorboard],
              verbose=1,
              validation_split=0.1)

Is there a way to get the hyperparameters being evaluated inside the create_model function?