Determining equation using Tensorflow

equation.py

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

size = 10000
def generate_data(size):
    x = np.array(np.random.rand(size,))
    y = 8 * (x**2) + 8*x + 5
    return x,y
    
train_x,train_y = generate_data(size)

x = tf.placeholder(tf.float32,shape=(None,))
y = tf.placeholder(tf.float32,shape=(None,))
    
A = tf.Variable(np.random.normal(),dtype=tf.float32)
B = tf.Variable(np.random.normal(),dtype=tf.float32)
C = tf.Variable(np.random.normal(),dtype=tf.float32)
p1 = tf.Variable(np.random.normal(),dtype=tf.float32)

y_pred = A * x ** p1 + B * x + C
loss = tf.reduce_mean(tf.square((y_pred - y)))
optimizer = tf.train.AdamOptimizer(0.01).minimize(loss)
iterations = 0
loss_hist = []
with tf.Session() as session:
    session.run(tf.global_variables_initializer())
    loss_val = 1000
    while(loss_val > 0.000000001):
        loss_val,_ = session.run([loss,optimizer],feed_dict={x:train_x,y:train_y})
        iterations = iterations + 1
        if iterations%5000 == 0:
            print(iterations," ",loss_val)
        loss_hist.append(loss_val)
    print("After {} Iterations : \n".format(iterations))
    print("Equation : \t y = {:2f}x^{} + {}x + {}".format(A.eval(),p1.eval(),B.eval(),C.eval()))
    
plt.plot(loss_hist)
plt.xlabel("Iterations")
plt.ylabel("loss value")
plt.title("minimum loss : {}".format(str(min(loss_hist))))
plt.show()