improve test robustness for Normalize (#1518)

Summary:
Pull Request resolved: #1518

see title. This bumps the tolerances. This was flaky locally.

Reviewed By: Balandat

Differential Revision: D41482368

fbshipit-source-id: 74f99b17cd3597cd2005cf05768ff41e2723fb6a

Author: sdaulton

test/models/transforms/test_input.py

@@ -232,7 +232,7 @@ def test_normalize(self):
 
                 nlz.eval()
                 X_unnlzd = nlz.untransform(X_nlzd)
-                self.assertAllClose(X, X_unnlzd, atol=1e-4, rtol=1e-4)
+                self.assertAllClose(X, X_unnlzd, atol=1e-3, rtol=1e-3)
                 expected_bounds = torch.cat(
                     [X.min(dim=-2, keepdim=True)[0], X.max(dim=-2, keepdim=True)[0]],
                     dim=-2,