Added results for 7B v1.1 model

README.md

@@ -713,39 +713,49 @@ All results reported below are on a 5-shot setting.
   </tr></thead>
 <tbody>
   <tr>
-    <td>Commonsense Reasoning</td>
+    <td rowspan="2">Commonsense Reasoning</td>
+    <td>copa_es</td>
+    <td>acc</td>
+    <td>86</td>
+  </tr>
+  <tr>
     <td>xstorycloze_es</td>
     <td>acc</td>
-    <td>74.06</td>
+    <td>74.32</td>
   </tr>
   <tr>
     <td rowspan="2">NLI</td>
     <td>wnli_es</td>
     <td>acc</td>
-    <td>46.48</td>
+    <td>59.15</td>
   </tr>
   <tr>
     <td>xnli_es</td>
     <td>acc</td>
-    <td>46.47</td>
+    <td>46.59</td>
   </tr>
   <tr>
     <td>Paraphrasing</td>
     <td>paws_es</td>
     <td>acc</td>
-    <td>57.65</td>
+    <td>60.3</td>
+  </tr>
+  <tr>
+    <td rowspan="2">QA</td>
+    <td>openbookqa_es</td>
+    <td>acc</td>
+    <td>41.6</td>
   </tr>
   <tr>
-    <td>QA</td>
     <td>xquad_es</td>
     <td>acc</td>
-    <td>71.48</td>
+    <td>72.26</td>
   </tr>
   <tr>
     <td>Translation</td>
     <td>flores_es</td>
     <td>bleu</td>
-    <td>23.56</td>
+    <td>23.43</td>
   </tr>
 </tbody>
 </table>
@@ -764,66 +774,66 @@ All results reported below are on a 5-shot setting.
     <td rowspan="2">Commonsense Reasoning</td>
     <td>copa_ca</td>
     <td>acc</td>
-    <td>80.8</td>
+    <td>84</td>
   </tr>
   <tr>
     <td>xstorycloze_ca</td>
     <td>acc</td>
-    <td>73.73</td>
+    <td>75.51</td>
   </tr>
   <tr>
     <td rowspan="2">NLI</td>
     <td>wnli_ca</td>
     <td>acc</td>
-    <td>56.34</td>
+    <td>59.15</td>
   </tr>
   <tr>
     <td>xnli_ca</td>
     <td>acc</td>
-    <td>49.4</td>
+    <td>50.16</td>
   </tr>
   <tr>
     <td rowspan="2">Paraphrasing</td>
     <td>parafraseja</td>
     <td>acc</td>
-    <td>64.88</td>
+    <td>65.83</td>
   </tr>
   <tr>
     <td>paws_ca</td>
     <td>acc</td>
-    <td>61.5</td>
+    <td>67.45</td>
   </tr>
   <tr>
     <td rowspan="5">QA</td>
     <td>arc_ca_easy</td>
     <td>acc</td>
-    <td>69.23</td>
+    <td>71.72</td>
   </tr>
   <tr>
     <td>arc_ca_challenge</td>
     <td>acc</td>
-    <td>44.54</td>
+    <td>45.56</td>
   </tr>
   <tr>
     <td>openbookqa_ca</td>
     <td>acc</td>
-    <td>36.8</td>
+    <td>38.8</td>
   </tr>
   <tr>
     <td>piqa_ca</td>
     <td>acc</td>
-    <td>70.35</td>
+    <td>71.27</td>
   </tr>
   <tr>
     <td>siqa_ca</td>
     <td>acc</td>
-    <td>48.26</td>
+    <td>49.85</td>
   </tr>
   <tr>
     <td>Translation</td>
     <td>flores_ca</td>
     <td>bleu</td>
-    <td>30.34</td>
+    <td>30.63</td>
   </tr>
 </tbody></table>
 
@@ -841,51 +851,51 @@ All results reported below are on a 5-shot setting.
     <td rowspan="2">Commonsense Reasoning</td>
     <td>xcopa_eu</td>
     <td>acc</td>
-    <td>68</td>
+    <td>68.8</td>
   </tr>
   <tr>
     <td>xstorycloze_eu</td>
     <td>acc</td>
-    <td>64.79</td>
+    <td>66.12</td>
   </tr>
   <tr>
     <td rowspan="2">NLI</td>
     <td>wnli_eu</td>
     <td>acc</td>
-    <td>38.03</td>
+    <td>57.75</td>
   </tr>
   <tr>
     <td>xnli_eu</td>
     <td>acc</td>
-    <td>42.85</td>
+    <td>43.51</td>
   </tr>
   <tr>
     <td rowspan="3">QA</td>
     <td>eus_exams</td>
     <td>acc</td>
-    <td>38.41</td>
+    <td>41.04</td>
   </tr>
   <tr>
     <td>eus_proficiency</td>
     <td>acc</td>
-    <td>31.13</td>
+    <td>39.72</td>
   </tr>
   <tr>
     <td>eus_trivia</td>
     <td>acc</td>
-    <td>45.36</td>
+    <td>52.36</td>
   </tr>
   <tr>
     <td>Reading Comprehension</td>
     <td>eus_reading</td>
     <td>acc</td>
-    <td>33.24</td>
+    <td>33.52</td>
   </tr>
   <tr>
     <td>Translation</td>
     <td>flores_eu</td>
     <td>bleu</td>
-    <td>16.29</td>
+    <td>16.95</td>
   </tr>
 </tbody></table>
 
@@ -903,24 +913,24 @@ All results reported below are on a 5-shot setting.
     <td rowspan="2">Paraphrasing</td>
     <td>parafrases_gl</td>
     <td>acc</td>
-    <td>58.84</td>
+    <td>54.42</td>
   </tr>
   <tr>
     <td>paws_gl</td>
     <td>acc</td>
-    <td>60.85</td>
+    <td>63.2</td>
   </tr>
   <tr>
     <td>QA</td>
     <td>openbookqa_gl</td>
     <td>acc</td>
-    <td>34.6</td>
+    <td>34.4</td>
   </tr>
   <tr>
     <td>Translation</td>
     <td>flores_gl</td>
     <td>bleu</td>
-    <td>27.98</td>
+    <td>27.75</td>
   </tr>
 </tbody>
 </table>
@@ -939,60 +949,60 @@ All results reported below are on a 5-shot setting.
     <td rowspan="2">Commonsense Reasoning</td>
     <td>copa</td>
     <td>acc</td>
-    <td>90</td>
+    <td>91</td>
   </tr>
   <tr>
     <td>xstorycloze_en</td>
     <td>acc</td>
-    <td>79.22</td>
+    <td>79.09</td>
   </tr>
   <tr>
     <td rowspan="2">NLI</td>
     <td>wnli</td>
     <td>acc</td>
-    <td>52.11</td>
+    <td>56.34</td>
   </tr>
   <tr>
     <td>xnli_en</td>
     <td>acc</td>
-    <td>47.27</td>
+    <td>50</td>
   </tr>
   <tr>
     <td>Paraphrasing</td>
     <td>paws *</td>
     <td>acc</td>
-    <td>59.6</td>
+    <td>64.05</td>
   </tr>
   <tr>
     <td rowspan="6">QA</td>
     <td>arc_easy</td>
     <td>acc</td>
-    <td>81.36</td>
+    <td>82.2</td>
   </tr>
   <tr>
     <td>arc_challenge</td>
     <td>acc</td>
-    <td>50.6</td>
+    <td>52.82</td>
   </tr>
   <tr>
     <td>openbookqa</td>
     <td>acc</td>
-    <td>34.4</td>
+    <td>36</td>
   </tr>
   <tr>
     <td>piqa</td>
     <td>acc</td>
-    <td>78.78</td>
+    <td>80.03</td>
   </tr>
   <tr>
     <td>social_iqa</td>
     <td>acc</td>
-    <td>50.15</td>
+    <td>50.31</td>
   </tr>
   <tr>
-    <td>squad_en **</td>
+    <td>xquad_en **</td>
     <td>acc</td>
-    <td>78.06</td>
+    <td>77.74</td>
   </tr>
 </tbody></table>