Update README.md

README.md

@@ -101,7 +101,7 @@ MAX_SEQUENCE_LENGTH = 2048
 ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
 ds = ds.shuffle(seed=42)
 
-dampening_frac=0.01
+dampening_frac=0.05
 
 def data_collator(batch):
     assert len(batch) == 1, "Only batch size of 1 is supported for calibration"
@@ -193,44 +193,63 @@ lm_eval \
       <td rowspan="7"><b>OpenLLM V1</b></td>
       <td>ARC Challenge</td>
       <td>72.53%</td>
-      <td>%</td>
-      <td>%</td>
+      <td>70.82%</td>
+      <td>97.65%</td>
     </tr>
     <tr>
       <td>GSM8K</td>
       <td>92.12%</td>
-      <td>%</td>
-      <td>%</td>
+      <td>85.75%</td>
+      <td>93.09%</td>
     </tr>
     <tr>
       <td>Hellaswag</td>
       <td>85.78%</td>
-      <td>%</td>
-      <td>%</td>
+      <td>85.05%</td>
+      <td>99.15%</td>
     </tr>
     <tr>
       <td>MMLU</td>
       <td>77.53%</td>
-      <td>%</td>
-      <td>%</td>
+      <td>76.37%</td>
+      <td>98.50%</td>
     </tr>
     <tr>
       <td>Truthfulqa (mc2)</td>
       <td>62.20%</td>
-      <td>%</td>
-      <td>%</td>
+      <td>61.73%</td>
+      <td>99.24%</td>
     </tr>
     <tr>
       <td>Winogrande</td>
       <td>79.40%</td>
-      <td>%</td>
-      <td>%</td>
+      <td>79.72%</td>
+      <td>100.40%</td>
     </tr>
     <tr>
       <td><b>Average Score</b></td>
       <td><b>78.26%</b></td>
-      <td><b>%</b></td>
-      <td><b>%</b></td>
+      <td><b>76.57%</b></td>
+      <td><b>97.84%</b></td>
+    </tr>
+    <tr>
+      <td rowspan="3"><b>Vision Evals</b></td>
+      <td>MMMU (val)</td>
+      <td>50.89%</td>	
+      <td>51.78%</td>
+      <td>101.75%</td>
+    </tr>
+    <tr>
+      <td>ChartQA</td>
+      <td>72.16%</td>
+      <td>72.20%</td>
+      <td>100.06%</td>
+    </tr>
+    <tr>
+      <td><b>Average Score</b></td>
+      <td><b>61.53%</b></td>
+      <td><b>61.99%</b></td>
+      <td><b>100.90%</b></td>
     </tr>
   </tbody>
 </table>