fix typos

README.md

@@ -54,10 +54,10 @@ See Appendix G of the paper for more details.
 ## Demos
 
 Thanks to the awesome work by the GitHub team and the Jupyter team, the Jupyter notebook (`.ipynb`)
-files can be render directly on GitHub.
+files can render directly on GitHub.
 We provide several notebooks (like [this one](./demos/cifar10/visualization.ipynb)) for you to
 easily get the usage of the optimizer.
-We also want to illustrate the rubost performance of AdaBound through these examples.
+We also want to illustrate the robust performance of AdaBound through these examples.
 
 For the full list of demos, please refer to [this page](./demos).
 

demos/README.md

@@ -2,7 +2,7 @@
 
 Here we provide some demos of using AdaBound on several benchmark tasks.
 The purpose of these demos is to give an example of how to use it your research, and also
-illustrate the rubost performance of AdaBound.
+illustrate the robust performance of AdaBound.
 
 In short, AdaBound can be regarded as an optimizer that dynamically transforms from Adam to SGD as
 the training step becomes larger.