fix typo

README.md

@@ -129,7 +129,7 @@ Perplexity: [https://en.wikipedia.org/wiki/Perplexity](https://en.wikipedia.org/
 #### Testing Data
 
 The IMDB dataset from Stanford NLP comes pre-split into training and testing data of 25k reviews each. Our preprocessing, which included the chunking of concatenated, tokenized inputs
-into chunks of 256 tokens, increased these respective splits by approximately ~5k records each. We apply a single masking function to the evluation dataset before testinf as mentioned above.
+into chunks of 256 tokens, increased these respective splits by approximately ~5k records each. We apply a single masking function to the evaluation dataset before testing as mentioned above.
 
 ### Results