import torch
import torch.nn as nn
import torch.optim as optim

# Initialize model, loss, and optimizer
model = NeuralNetwork()
criterion = nn.BCELoss()
optimizer = optim.SGD(model.parameters(), lr=0.1)

# Training loop
epochs = 100
for epoch in range(epochs):
    # Forward pass
    predictions = model(X)
    loss = criterion(predictions, y)

    # Backward pass
    optimizer.zero_grad()  # Clear previous gradients
    loss.backward()        # Compute gradients
    optimizer.step()       # Update parameters

    if epoch % 20 == 0:
        print(f"Epoch {epoch}, Loss: {loss.item():.4f}")

        __
        __