Warning: Linker: (..) Unused DT entry

I was creating a python script using keras in termux with theano as a backend, because I can not install tensorflow in android, when I'm going to execute it it appears :

Using Theano backend
WARNING: linker: /data/data/com.termux/files/home/.theano/compiledir_Linux-3.18.19+-armv7l-with-libc--3.7.1-32/tmpmx5j8pis/m8dccfba9ba8331d682882b58b71f10b9964902caa05aab2e113780b563796fce.so: unused DT entry: type 0x1d arg 0x3ba
WARNING: linker: /data/data/com.termux/files/home/.theano/compiledir_Linux-3.18.19+-armv7l-with-libc--3.7.1-32/tmp3y_u2m51/m8d1bf9e79b85f534dfe998575c7e7ea4dd1c5d1dcc10f88b36d113cbd6c7a993.so: unused DT entry: type 0x1d arg 0x362
Epoch 1/100
5/5 [==============================] - 0s 5ms/step - loss: 4.8022
...
Epoch 100/100
5/5 [==============================] - 0s 5ms/step - loss: 3.1974e-14
WARNING: linker: /data/data/com.termux/files/home/.theano/compiledir_Linux-3.18.19+-armv7l-with-libc--3.7.1-32/tmpci2gf174/m5e618a30457958f05755e24c8e216abe250732682e64206030484fe296085b50.so: unused DT entry: type 0x1d arg 0x33d
11       # Resultado

How do I solve or hide these warnings?

Here I leave all the files:

~ / .keras / keras.json

{
    "floatx": "float32",
    "epsilon": 1e-07,
    "backend": "theano",
    "image_data_format": "channels_last"
}

~ / nn.py

import keras
import numpy as np

model = keras.models.Sequential([
    keras.layers.Dense(1, input_dim=1)
])

mse = keras.losses.mean_squared_error
sgd = keras.optimizers.SGD(lr=0.01, momentum=0.9, nesterov=True)

model.compile(loss=mse, optimizer=sgd)

x = np.array([1, 2, 3, 4, 5])
y = np.array([1, 3, 5, 7, 9])

model.fit(x, y, epochs=5, batch_size=1)
result = model.predict([6])
print(int(round(result[0][0])))

It does not exist or I do not know where it is .theanorc

Python 3.7.1

Keras 2.2.4

Theano 1.0.3

Clang 7.0.0