Update emerging_optimizers/orthogonalized_optimizers/muon.py

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Signed-off-by: Hao Wu <[email protected]>

Author: skyw

emerging_optimizers/orthogonalized_optimizers/muon.py

@@ -61,7 +61,7 @@ class Muon(OrthogonalizedOptimizer):
             ["simple", "quintic", "polar_express"].
         num_ns_steps: The number of iteration steps to use in the Newton-Schulz iteration.
         scale_mode: The type of scale factor to use for the update. Defaults to "spectral" style scaling.
-        extra_scale_factor: The additional scale factor to use for the update. Set it to 0.2 can closely match
+        extra_scale_factor: The additional scale factor to use for the update. Setting it to 0.2 can closely match
             the update RMS norm of AdamW as suggested by https://arxiv.org/abs/2502.16982.
         use_syrk: Whether to use the Triton kernel for the Newton-Schulz iteration.
     """