Update README.md

README.md

@@ -17,7 +17,7 @@ Instruction tuned with the following parameters:
 - Micro Batch Size 32 over 4xH100, gradient accumulation steps = 1
 - AdamW with learning rate 5e-5
 
-## Evaluation Results
+# Evaluation Results
 
 ### HuggingFace Leaderboard
 
@@ -30,16 +30,12 @@ For comparison the GSM8K score for the original `metamath/MetaMath-Mistral-7B` w
 ### MT-Bench
 
 ########## First turn ##########
-                                          score
-model                               turn       
-fewshot_metamath_orcavicuna_mistral 1       6.9
+                                             
+Score: 6.9
 
 ########## Second turn ##########
-                                            score
-model                               turn         
-fewshot_metamath_orcavicuna_mistral 2     6.51875
+
+Score: 6.51875
 
 ########## Average ##########
-                                        score
-model                                        
-fewshot_metamath_orcavicuna_mistral  6.709375
+Score: 6.709375