Update README.md

README.md

@@ -15,6 +15,10 @@ Everyday-Language-3B is a language model fine-tuned for generating natural, ever
 
 This fine-tuning process significantly improves the model's ability to produce coherent, contextually appropriate, and less repetitive text compared to its base version. It aims to better capture the nuances and patterns of typical conversational language.
 
+# HellaSwag Benchmark
+
+**An evaluation using a non-instruction-following method was performed on HellaSwag (1000 validation samples). By calculating the likelihood of each possible continuation, the model scored ~73.4% accuracy. This reflects its performance as a base text predictor on a commonsense task, separate from its intended use for generating everyday conversational text.**
+
 ## Intended Uses & Limitations
 
 **Intended Uses:**