Update README.md
Browse files
README.md
CHANGED
|
@@ -69,7 +69,7 @@ model-index:
|
|
| 69 |
type: race
|
| 70 |
name: RACE
|
| 71 |
metrics:
|
| 72 |
-
- name:
|
| 73 |
type: accuracy
|
| 74 |
value: 41.148
|
| 75 |
- task:
|
|
@@ -78,10 +78,10 @@ model-index:
|
|
| 78 |
type: mmlu
|
| 79 |
name: Measuring Massive Multitask Language Understanding (MMLU)
|
| 80 |
metrics:
|
| 81 |
-
- name:
|
| 82 |
type: accuracy
|
| 83 |
value: 53.215
|
| 84 |
-
- name:
|
| 85 |
type: accuracy
|
| 86 |
value: 52.789
|
| 87 |
- task:
|
|
@@ -90,7 +90,7 @@ model-index:
|
|
| 90 |
type: truthful_qa
|
| 91 |
name: Truthful QA
|
| 92 |
metrics:
|
| 93 |
-
- name:
|
| 94 |
type: accuracy
|
| 95 |
value: 47.29
|
| 96 |
- task:
|
|
@@ -99,10 +99,10 @@ model-index:
|
|
| 99 |
type: winogrande
|
| 100 |
name: Winogrande
|
| 101 |
metrics:
|
| 102 |
-
- name:
|
| 103 |
type: accuracy
|
| 104 |
value: 70.639
|
| 105 |
-
- name:
|
| 106 |
type: accuracy
|
| 107 |
value: 68.114
|
| 108 |
- task:
|
|
@@ -111,7 +111,7 @@ model-index:
|
|
| 111 |
type: copa
|
| 112 |
name: COPA
|
| 113 |
metrics:
|
| 114 |
-
- name:
|
| 115 |
type: accuracy
|
| 116 |
value: 85
|
| 117 |
- task:
|
|
@@ -120,7 +120,7 @@ model-index:
|
|
| 120 |
type: boolq
|
| 121 |
name: Boolq
|
| 122 |
metrics:
|
| 123 |
-
- name:
|
| 124 |
type: accuracy
|
| 125 |
value: 82.783
|
| 126 |
- task:
|
|
@@ -129,7 +129,7 @@ model-index:
|
|
| 129 |
type: openbookqa
|
| 130 |
name: Openbook QA
|
| 131 |
metrics:
|
| 132 |
-
- name:
|
| 133 |
type: accuracy
|
| 134 |
value: 42
|
| 135 |
- task:
|
|
@@ -138,10 +138,10 @@ model-index:
|
|
| 138 |
type: hellaSwag
|
| 139 |
name: HellaSwag
|
| 140 |
metrics:
|
| 141 |
-
- name:
|
| 142 |
type: accuracy
|
| 143 |
value: 76.12
|
| 144 |
-
- name:
|
| 145 |
type: accuracy
|
| 146 |
value: 73.312
|
| 147 |
- task:
|
|
@@ -150,7 +150,7 @@ model-index:
|
|
| 150 |
type: piqa
|
| 151 |
name: PIQA
|
| 152 |
metrics:
|
| 153 |
-
- name:
|
| 154 |
type: accuracy
|
| 155 |
value: 77.856
|
| 156 |
- task:
|
|
@@ -159,7 +159,7 @@ model-index:
|
|
| 159 |
type: ai2_arc
|
| 160 |
name: ARC (Easy)
|
| 161 |
metrics:
|
| 162 |
-
- name:
|
| 163 |
type: accuracy
|
| 164 |
value: 70.328
|
| 165 |
- task:
|
|
@@ -168,10 +168,10 @@ model-index:
|
|
| 168 |
type: ai2_arc
|
| 169 |
name: ARC (Challenge)
|
| 170 |
metrics:
|
| 171 |
-
- name:
|
| 172 |
type: accuracy
|
| 173 |
value: 51.706
|
| 174 |
-
- name:
|
| 175 |
type: accuracy
|
| 176 |
value: 44.625
|
| 177 |
- task:
|
|
|
|
| 69 |
type: race
|
| 70 |
name: RACE
|
| 71 |
metrics:
|
| 72 |
+
- name: Accuracy (0 shot)
|
| 73 |
type: accuracy
|
| 74 |
value: 41.148
|
| 75 |
- task:
|
|
|
|
| 78 |
type: mmlu
|
| 79 |
name: Measuring Massive Multitask Language Understanding (MMLU)
|
| 80 |
metrics:
|
| 81 |
+
- name: Accuracy (5 shot)
|
| 82 |
type: accuracy
|
| 83 |
value: 53.215
|
| 84 |
+
- name: Accuracy (0 shot)
|
| 85 |
type: accuracy
|
| 86 |
value: 52.789
|
| 87 |
- task:
|
|
|
|
| 90 |
type: truthful_qa
|
| 91 |
name: Truthful QA
|
| 92 |
metrics:
|
| 93 |
+
- name: Accuracy (0 shot)
|
| 94 |
type: accuracy
|
| 95 |
value: 47.29
|
| 96 |
- task:
|
|
|
|
| 99 |
type: winogrande
|
| 100 |
name: Winogrande
|
| 101 |
metrics:
|
| 102 |
+
- name: Accuracy (5 shot)
|
| 103 |
type: accuracy
|
| 104 |
value: 70.639
|
| 105 |
+
- name: Accuracy (0 shot)
|
| 106 |
type: accuracy
|
| 107 |
value: 68.114
|
| 108 |
- task:
|
|
|
|
| 111 |
type: copa
|
| 112 |
name: COPA
|
| 113 |
metrics:
|
| 114 |
+
- name: Accuracy (0 shot)
|
| 115 |
type: accuracy
|
| 116 |
value: 85
|
| 117 |
- task:
|
|
|
|
| 120 |
type: boolq
|
| 121 |
name: Boolq
|
| 122 |
metrics:
|
| 123 |
+
- name: Accuracy (0 shot)
|
| 124 |
type: accuracy
|
| 125 |
value: 82.783
|
| 126 |
- task:
|
|
|
|
| 129 |
type: openbookqa
|
| 130 |
name: Openbook QA
|
| 131 |
metrics:
|
| 132 |
+
- name: Accuracy (0 shot)
|
| 133 |
type: accuracy
|
| 134 |
value: 42
|
| 135 |
- task:
|
|
|
|
| 138 |
type: hellaSwag
|
| 139 |
name: HellaSwag
|
| 140 |
metrics:
|
| 141 |
+
- name: Accuracy (10-shot)
|
| 142 |
type: accuracy
|
| 143 |
value: 76.12
|
| 144 |
+
- name: Accuracy (0-shot)
|
| 145 |
type: accuracy
|
| 146 |
value: 73.312
|
| 147 |
- task:
|
|
|
|
| 150 |
type: piqa
|
| 151 |
name: PIQA
|
| 152 |
metrics:
|
| 153 |
+
- name: Accuracy (0 shot)
|
| 154 |
type: accuracy
|
| 155 |
value: 77.856
|
| 156 |
- task:
|
|
|
|
| 159 |
type: ai2_arc
|
| 160 |
name: ARC (Easy)
|
| 161 |
metrics:
|
| 162 |
+
- name: Accuracy (0 shot)
|
| 163 |
type: accuracy
|
| 164 |
value: 70.328
|
| 165 |
- task:
|
|
|
|
| 168 |
type: ai2_arc
|
| 169 |
name: ARC (Challenge)
|
| 170 |
metrics:
|
| 171 |
+
- name: Accuracy (25-shot)
|
| 172 |
type: accuracy
|
| 173 |
value: 51.706
|
| 174 |
+
- name: Accuracy (0-shot)
|
| 175 |
type: accuracy
|
| 176 |
value: 44.625
|
| 177 |
- task:
|