Update README.md
Browse files
README.md
CHANGED
|
@@ -206,13 +206,13 @@ This version of the lm-evaluation-harness includes versions of ARC-Challenge, GS
|
|
| 206 |
</td>
|
| 207 |
</tr>
|
| 208 |
<tr>
|
| 209 |
-
<td>
|
| 210 |
</td>
|
| 211 |
-
<td>
|
| 212 |
</td>
|
| 213 |
-
<td>
|
| 214 |
</td>
|
| 215 |
-
<td>
|
| 216 |
</td>
|
| 217 |
</tr>
|
| 218 |
<tr>
|
|
|
|
| 206 |
</td>
|
| 207 |
</tr>
|
| 208 |
<tr>
|
| 209 |
+
<td>Hellaswag (10-shot)
|
| 210 |
</td>
|
| 211 |
+
<td>61.01
|
| 212 |
</td>
|
| 213 |
+
<td>60.95
|
| 214 |
</td>
|
| 215 |
+
<td>99.9%
|
| 216 |
</td>
|
| 217 |
</tr>
|
| 218 |
<tr>
|