Update README.md

README.md

@@ -45,9 +45,9 @@ print(tokenizer.decode(outputs[0]))
 
 Model evaluation metrics and results.
 
-| Benchmark                                      | Metric        | Llama-2-7b-evolcodealpaca  | Llama-2-7b-pruned50-retrained-evolcodealpaca |
-|------------------------------------------------|---------------|-------------|-------------------------------|
-| [HumanEval](https://arxiv.org/abs/2107.03374)  | pass@1        | xxxx        | xxxx                          |
+| Benchmark                                      | Metric        | Llama-2-7b-evolcodealpaca  |
+|------------------------------------------------|---------------|-------------|
+| [HumanEval](https://arxiv.org/abs/2107.03374)  | pass@1        | 32.03       |
 
 ## Model Training Details