alexmarques commited on
Commit
88efeae
1 Parent(s): 517dbb1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -0
README.md CHANGED
@@ -159,6 +159,16 @@ This version of the lm-evaluation-harness includes versions of MMLU, ARC-Challen
159
  <td><strong>Recovery</strong>
160
  </td>
161
  </tr>
 
 
 
 
 
 
 
 
 
 
162
  <tr>
163
  <td>MMLU (CoT, 0-shot)
164
  </td>
@@ -229,6 +239,16 @@ This version of the lm-evaluation-harness includes versions of MMLU, ARC-Challen
229
  <td>101.2%
230
  </td>
231
  </tr>
 
 
 
 
 
 
 
 
 
 
232
  </table>
233
 
234
  ### Reproduction
 
159
  <td><strong>Recovery</strong>
160
  </td>
161
  </tr>
162
+ <tr>
163
+ <td>MMLU (5-shot)
164
+ </td>
165
+ <td>87.41
166
+ </td>
167
+ <td>87.47
168
+ </td>
169
+ <td>100.1%
170
+ </td>
171
+ </tr>
172
  <tr>
173
  <td>MMLU (CoT, 0-shot)
174
  </td>
 
239
  <td>101.2%
240
  </td>
241
  </tr>
242
+ <tr>
243
+ <td><strong>Average</strong>
244
+ </td>
245
+ <td><strong>86.73</strong>
246
+ </td>
247
+ <td><strong>86.89</strong>
248
+ </td>
249
+ <td><strong>100.2%</strong>
250
+ </td>
251
+ </tr>
252
  </table>
253
 
254
  ### Reproduction