Update README.md

README.md

@@ -22,6 +22,22 @@ Continue finetuning https://huggingface.co/meta-llama/Llama-3.2-3B on highly cur
 ## MalayMMLU
 
 ```
+                              Model   Accuracy   shot by_letter        category
+0  Llama-3.2-3B-Malaysian-Reasoning  57.347524  0shot      True            STEM
+1  Llama-3.2-3B-Malaysian-Reasoning  59.653308  0shot      True        Language
+2  Llama-3.2-3B-Malaysian-Reasoning  57.690084  0shot      True  Social science
+3  Llama-3.2-3B-Malaysian-Reasoning  57.639722  0shot      True          Others
+4  Llama-3.2-3B-Malaysian-Reasoning  60.045506  0shot      True      Humanities
+{'Social science': 6918, 'Language': 6288, 'Humanities': 4395, 'Others': 4169, 'STEM': 2443}
+Model : Llama-3.2-3B-Malaysian-Reasoning
+Metric : first
+Shot : 0shot
+average accuracy 58.58423161111799
+accuracy for STEM 57.34752353663528
+accuracy for Language 59.65330788804071
+accuracy for Social science 57.6900838392599
+accuracy for Others 57.639721755816744
+accuracy for Humanities 60.04550625711035
 ```
 
 ## Training session