Added reults for 2B 1.1 model

README.md

@@ -718,36 +718,36 @@ All results reported below are on a 5-shot setting.
     <td>Commonsense Reasoning</td>
     <td>xstorycloze_es</td>
     <td>acc</td>
-    <td>64.92</td>
+    <td>64.73</td>
   </tr>
   <tr>
     <td rowspan="2">NLI</td>
     <td>wnli_es</td>
     <td>acc</td>
-    <td>54.93</td>
+    <td>56.34</td>
   </tr>
   <tr>
     <td>xnli_es</td>
     <td>acc</td>
-    <td>44.98</td>
+    <td>44.74</td>
   </tr>
   <tr>
     <td>Paraphrasing</td>
     <td>paws_es</td>
     <td>acc</td>
-    <td>52.05</td>
+    <td>55.95</td>
   </tr>
   <tr>
     <td>QA</td>
     <td>xquad_es</td>
     <td>acc</td>
-    <td>54.32</td>
+    <td>57.59</td>
   </tr>
   <tr>
     <td>Translation</td>
     <td>flores_es</td>
     <td>bleu</td>
-    <td>11.46</td>
+    <td>20.05</td>
   </tr>
 </tbody>
 </table>
@@ -766,12 +766,12 @@ All results reported below are on a 5-shot setting.
     <td rowspan="2">Commonsense Reasoning</td>
     <td>copa_ca</td>
     <td>acc</td>
-    <td>68.80</td>
+    <td>70.2</td>
   </tr>
   <tr>
     <td>xstorycloze_ca</td>
     <td>acc</td>
-    <td>65.72</td>
+    <td>66.38</td>
   </tr>
   <tr>
     <td rowspan="2">NLI</td>
@@ -782,50 +782,50 @@ All results reported below are on a 5-shot setting.
   <tr>
     <td>xnli_ca</td>
     <td>acc</td>
-    <td>48.07</td>
+    <td>48.15</td>
   </tr>
   <tr>
     <td rowspan="2">Paraphrasing</td>
     <td>parafraseja</td>
     <td>acc</td>
-    <td>58.55</td>
+    <td>61.35</td>
   </tr>
   <tr>
     <td>paws_ca</td>
     <td>acc</td>
-    <td>55.15</td>
+    <td>57.05</td>
   </tr>
   <tr>
     <td rowspan="5">QA</td>
     <td>arc_ca_easy</td>
     <td>acc</td>
-    <td>54.76</td>
+    <td>55.3</td>
   </tr>
   <tr>
     <td>arc_ca_challenge</td>
     <td>acc</td>
-    <td>30.55</td>
+    <td>27.65</td>
   </tr>
   <tr>
     <td>openbookqa_ca</td>
     <td>acc</td>
-    <td>27.40</td>
+    <td>29.40</td>
   </tr>
   <tr>
     <td>piqa_ca</td>
     <td>acc</td>
-    <td>62.89</td>
+    <td>63.82</td>
   </tr>
   <tr>
     <td>siqa_ca</td>
     <td>acc</td>
-    <td>41.91</td>
+    <td>43.04</td>
   </tr>
   <tr>
     <td>Translation</td>
     <td>flores_ca</td>
     <td>bleu</td>
-    <td>14.70</td>
+    <td>24.93</td>
   </tr>
 </tbody></table>
 
@@ -843,51 +843,51 @@ All results reported below are on a 5-shot setting.
     <td rowspan="2">Commonsense Reasoning</td>
     <td>xcopa_eu</td>
     <td>acc</td>
-    <td>55.60</td>
+    <td>58</td>
   </tr>
   <tr>
     <td>xstorycloze_eu</td>
     <td>acc</td>
-    <td>57.64</td>
+    <td>58.97</td>
   </tr>
   <tr>
     <td rowspan="2">NLI</td>
     <td>wnli_eu</td>
     <td>acc</td>
-    <td>56.34</td>
+    <td>43.66</td>
   </tr>
   <tr>
     <td>xnli_eu</td>
     <td>acc</td>
-    <td>39.78</td>
+    <td>42.03</td>
   </tr>
   <tr>
     <td rowspan="3">QA</td>
     <td>eus_exams</td>
     <td>acc</td>
-    <td>23.72</td>
+    <td>26.11</td>
   </tr>
   <tr>
     <td>eus_proficiency</td>
     <td>acc</td>
-    <td>23.37</td>
+    <td>24.09</td>
   </tr>
   <tr>
     <td>eus_trivia</td>
     <td>acc</td>
-    <td>27.58</td>
+    <td>28.05</td>
   </tr>
   <tr>
     <td>Reading Comprehension</td>
     <td>eus_reading</td>
     <td>acc</td>
-    <td>27.84</td>
+    <td>28.41</td>
   </tr>
   <tr>
     <td>Translation</td>
     <td>flores_eu</td>
     <td>bleu</td>
-    <td>3.58</td>
+    <td>8.96</td>
   </tr>
 </tbody></table>
 
@@ -905,24 +905,24 @@ All results reported below are on a 5-shot setting.
     <td rowspan="2">Paraphrasing</td>
     <td>parafrases_gl</td>
     <td>acc</td>
-    <td>54.08</td>
+    <td>56.08</td>
   </tr>
   <tr>
     <td>paws_gl</td>
     <td>acc</td>
-    <td>53.30</td>
+    <td>54.85</td>
   </tr>
   <tr>
     <td>QA</td>
     <td>openbookqa_gl</td>
     <td>acc</td>
-    <td>30.80</td>
+    <td>25.4</td>
   </tr>
   <tr>
     <td>Translation</td>
     <td>flores_gl</td>
     <td>bleu</td>
-    <td>12.86</td>
+    <td>22.38</td>
   </tr>
 </tbody>
 </table>
@@ -946,35 +946,35 @@ All results reported below are on a 5-shot setting.
   <tr>
     <td>xstorycloze_en</td>
     <td>acc</td>
-    <td>73.06</td>
+    <td>71.81</td>
   </tr>
   <tr>
     <td rowspan="2">NLI</td>
     <td>wnli</td>
     <td>acc</td>
-    <td>56.34</td>
+    <td>52.11</td>
   </tr>
   <tr>
     <td>xnli_en</td>
     <td>acc</td>
-    <td>47.35</td>
+    <td>46.47</td>
   </tr>
   <tr>
     <td>Paraphrasing</td>
     <td>paws *</td>
     <td>acc</td>
-    <td>55.95</td>
+    <td>56.5</td>
   </tr>
   <tr>
     <td rowspan="6">QA</td>
     <td>arc_easy</td>
     <td>acc</td>
-    <td>74.07</td>
+    <td>72.14</td>
   </tr>
   <tr>
     <td>arc_challenge</td>
     <td>acc</td>
-    <td>37.63</td>
+    <td>35.41</td>
   </tr>
   <tr>
     <td>openbookqa</td>
@@ -984,17 +984,17 @@ All results reported below are on a 5-shot setting.
   <tr>
     <td>piqa</td>
     <td>acc</td>
-    <td>74.86</td>
+    <td>73.61</td>
   </tr>
   <tr>
     <td>social_iqa</td>
     <td>acc</td>
-    <td>46.62</td>
+    <td>44.78</td>
   </tr>
   <tr>
-    <td>squad_en **</td>
+    <td>xquad_en **</td>
     <td>acc</td>
-    <td>44.38</td>
+    <td>64.87</td>
   </tr>
 </tbody></table>