Update newton example doc to clearly state failure using physx eval (#572)

## Summary
This is a doc change requested by QA in
https://nvbugspro.nvidia.com/bug/6063011
It clarifies that evaluated newton trained model using physx is expected
to completely fail the dexsuite task.

Author: qianl-nv

docs/pages/example_workflows/dexsuite_lift/step_3_evaluation.rst

@@ -78,7 +78,9 @@ At the end of the run, metrics are printed to the console:
         dexsuite_lift
 
    However, the model behaviour may differ significantly when training and
-   evaluation use different physics backends.
+   evaluation use different physics backends. The above model, which was
+   trained with Newton, fails to grasp or lift the cube completely when
+   evaluated with PhysX.
 
 
 Parallel Environment Evaluation