LSTM Time step?

Question

Good afternoon to everyone,

I am kind of a newbie in programming so I am sorry if I make stupid comments of questions

I was building an LSTM model in which I have 4 different inputs such as air temp, air humidity, wind speed etc... and I need to produce an output of wind power forecast.

MY dataset is one year long and the time step is 1 hour. I first struggled when making the LSTM as I needed my input dimension to be 3D andI found a solution online and applied it. But now I need to change my time step to see what performs better in my model but I do not have any idea in how to change it.

My code looks like:

import tensorflow as tf
import csv
from sklearn.model_selection import train_test_split
import numpy as np
import matplotlib.pyplot as plt
import time

#Read DATA
with open("full_year_data.csv") as f:
    reader = csv.reader(f)
    next(reader)
    data = []
    for row in reader:
        data.append({
            "inputs": [float(cell) for cell in row[:4]],
            "output": [float(cell) for cell in row[4:]]
        })

#separate data into training and testing groups
inputs = [row["inputs"] for row in data]
inputs = np.array(inputs) #shape = (743, 4)
output = [row["output"] for row in data]
output = np.array(output) #shape= (743,1)

X_training, X_testing, y_training, y_testing = train_test_split(
    inputs, output, test_size=0.25
)


X_training = np.expand_dims(X_training,1)
X_testing = np.expand_dims(X_testing,1)

nodes_hidden = 
Learning_algorithm = tf.keras.optimizers.Adam()

model2 = tf.keras.models.Sequential()
model2.add(tf.keras.layers.LSTM(units = nodes_hidden, return_sequences =True, input_shape=X_training.shape[1:], activation='relu'))
model2.add(tf.keras.layers.LSTM(units = nodes_hidden, return_sequences =True, activation='relu'))
model2.add(tf.keras.layers.LSTM(units = nodes_hidden, return_sequences =True, activation='relu'))
model2.add(tf.keras.layers.LSTM(units = nodes_hidden, return_sequences =True, activation='relu'))
model2.add(tf.keras.layers.Dense(1, activation='sigmoid'))

model2.compile(optimizer = 'adam', loss = 'mean_squared_error')

model2.fit(X_training, y_training, epochs=100, batch_size=0)
model2.evaluate(X_testing, y_testing, verbose=2)

I am using Tensorflow and keras to make my LSTM model, any help on how I can change my time steps for testing will be really appreciate it

Thanks for yout time!