Update README.md

README.md

@@ -114,9 +114,10 @@ The library used is [lm-evaluation-harness repository](https://github.com/Eleuth
 
 
 #### Main Results
-| Model |  ARC | HellaSwag | MMLU |
-|------------------------|----------|--------|------|
-| **Llama-3.1-8B-Instruct** | **73** | **71.1** | **87.9** |
+| Model |  ARC | HellaSwag | MMLU | IFEval | 
+|------------------------|----------|--------|------|--------|
+| **Llama-3.1-8B-Instruct** | **52.05** | **** | **42.07** | **42.14**|
+| **Llama-3.1-10B-Instruct** | **50.42** | **57.81** | **35.62** | **35.67** |
 
 
 #### Scripts to generate evalution results
@@ -127,7 +128,7 @@ pip install lm-eval>=0.4.7
 
 from lm_eval import evaluator
 
-tasks_list = ["arc_challenge", "gpqa", "ifeval", "mmlu_pro", "hellaswag"]  # Benchmark dataset
+tasks_list = ["arc_challenge", "ifeval", "mmlu_pro", "hellaswag"]  # Benchmark dataset
 
 model_path='rwmasood/llama-3.1-10b-instruct'
 model_name_or_path = "./output/checkpoint-2800"