Update README.md

README.md

@@ -34,7 +34,7 @@ This model is not intended to be used directly, but rather to be fine-tuned for
 | ARC-Easy | 65.19% | 60.69% | -6.9% |
 | BoolQ | 64.16% | 51.22% | -20.2% |
 | LAMBADA-OpenAI | 62.20% | 59.64% | -4.1% |
-| LAMBADA-Standard | 53.46% | 54.61% | -2.2% |
+| LAMBADA-Standard | 53.46% | 54.61% | +2.2% |
 
 ### Key Findings
 - Surprisingly, an improvement is observed on the LAMBADA-Standard benchmark, with a 2.2% relative increase in accuracy.