From d20395fccc83d654e728688b6d201164ca01aa7d Mon Sep 17 00:00:00 2001
From: "Bintang Alam Semesta W.A.M"
 <23573683+bintang-aswam@users.noreply.github.com>
Date: Thu, 10 Jul 2025 08:32:24 +0700
Subject: [PATCH] zero the gradients after updating weights

Manually zero the gradients after updating weights by using machine epsilon for standard float (64-bit).
---
 .../examples_autograd/polynomial_autograd.py         | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/beginner_source/examples_autograd/polynomial_autograd.py b/beginner_source/examples_autograd/polynomial_autograd.py
index 525d0c33ce9..eee92751f8c 100755
--- a/beginner_source/examples_autograd/polynomial_autograd.py
+++ b/beginner_source/examples_autograd/polynomial_autograd.py
@@ -40,7 +40,7 @@
 d = torch.randn((), dtype=dtype, requires_grad=True)
 
 learning_rate = 1e-6
-for t in range(2000):
+for t in range(int(1/(learning_rate))):
     # Forward pass: compute predicted y using operations on Tensors.
     y_pred = a + b * x + c * x ** 2 + d * x ** 3
 
@@ -67,9 +67,11 @@
         d -= learning_rate * d.grad
 
         # Manually zero the gradients after updating weights
-        a.grad = None
-        b.grad = None
-        c.grad = None
-        d.grad = None
+        # by using machine epsilon for standard float (64-bit)
+        import sys
+        a.grad = loss*sys.float_info.epsilon
+        b.grad = loss*sys.float_info.epsilon
+        c.grad = loss*sys.float_info.epsilon
+        d.grad = loss*sys.float_info.epsilon
 
 print(f'Result: y = {a.item()} + {b.item()} x + {c.item()} x^2 + {d.item()} x^3')