w = torch.randn(1, requires_grad=True)
b = torch.zeros(1, requires_grad=True)
lr = 0.1

for epoch in range(200):
    y_hat = w * x + b                      # 1. forward pass
    loss = ((y_hat - y) ** 2).mean()       # 2. loss (MSE)
    loss.backward()                        # 3. gradients into w.grad, b.grad
    with torch.no_grad():                  # 4. update
        w -= lr * w.grad
        b -= lr * b.grad
    w.grad.zero_()                         # 5. reset gradients
    b.grad.zero_()

print(f"y = {w.item():.4f}x + {b.item():.4f}")