Update README.md
Browse files
README.md
CHANGED
|
@@ -37,9 +37,9 @@ model-index:
|
|
| 37 |
type: openai_humanneval
|
| 38 |
name: OpenAI HumanEval
|
| 39 |
metrics:
|
| 40 |
-
- name: pass@1 (t=0.
|
| 41 |
type: pass@1
|
| 42 |
-
value:
|
| 43 |
- name: pass@10 (t=0.8)
|
| 44 |
type: pass@10
|
| 45 |
value: 65.755
|
|
@@ -49,9 +49,9 @@ model-index:
|
|
| 49 |
type: mbpp
|
| 50 |
name: Mostly Basic Python Problems (mbpp)
|
| 51 |
metrics:
|
| 52 |
-
- name: pass@1 (t=0.
|
| 53 |
type: pass@1
|
| 54 |
-
value: 39.
|
| 55 |
- name: pass@10 (t=0.8)
|
| 56 |
type: pass@10
|
| 57 |
value: 59.895
|
|
@@ -61,7 +61,7 @@ model-index:
|
|
| 61 |
type: race
|
| 62 |
name: RACE
|
| 63 |
metrics:
|
| 64 |
-
- name: accuracy
|
| 65 |
type: accuracy
|
| 66 |
value: 41.148
|
| 67 |
- task:
|
|
@@ -70,7 +70,10 @@ model-index:
|
|
| 70 |
type: mmlu
|
| 71 |
name: Measuring Massive Multitask Language Understanding (MMLU)
|
| 72 |
metrics:
|
| 73 |
-
- name: accuracy
|
|
|
|
|
|
|
|
|
|
| 74 |
type: accuracy
|
| 75 |
value: 52.789
|
| 76 |
- task:
|
|
@@ -79,7 +82,7 @@ model-index:
|
|
| 79 |
type: truthful_qa
|
| 80 |
name: Truthful QA
|
| 81 |
metrics:
|
| 82 |
-
- name: accuracy
|
| 83 |
type: accuracy
|
| 84 |
value: 47.29
|
| 85 |
- task:
|
|
@@ -100,7 +103,7 @@ model-index:
|
|
| 100 |
type: copa
|
| 101 |
name: COPA
|
| 102 |
metrics:
|
| 103 |
-
- name: accuracy
|
| 104 |
type: accuracy
|
| 105 |
value: 85
|
| 106 |
- task:
|
|
@@ -109,7 +112,7 @@ model-index:
|
|
| 109 |
type: boolq
|
| 110 |
name: Boolq
|
| 111 |
metrics:
|
| 112 |
-
- name: accuracy
|
| 113 |
type: accuracy
|
| 114 |
value: 82.783
|
| 115 |
- task:
|
|
@@ -118,7 +121,7 @@ model-index:
|
|
| 118 |
type: openbookqa
|
| 119 |
name: Openbook QA
|
| 120 |
metrics:
|
| 121 |
-
- name: accuracy
|
| 122 |
type: accuracy
|
| 123 |
value: 42
|
| 124 |
- task:
|
|
@@ -139,7 +142,7 @@ model-index:
|
|
| 139 |
type: piqa
|
| 140 |
name: PIQA
|
| 141 |
metrics:
|
| 142 |
-
- name: accuracy
|
| 143 |
type: accuracy
|
| 144 |
value: 77.856
|
| 145 |
- task:
|
|
@@ -148,7 +151,7 @@ model-index:
|
|
| 148 |
type: ai2_arc
|
| 149 |
name: ARC (Easy)
|
| 150 |
metrics:
|
| 151 |
-
- name: accuracy
|
| 152 |
type: accuracy
|
| 153 |
value: 70.328
|
| 154 |
- task:
|
|
|
|
| 37 |
type: openai_humanneval
|
| 38 |
name: OpenAI HumanEval
|
| 39 |
metrics:
|
| 40 |
+
- name: pass@1 (t=0.2)
|
| 41 |
type: pass@1
|
| 42 |
+
value: 34.116
|
| 43 |
- name: pass@10 (t=0.8)
|
| 44 |
type: pass@10
|
| 45 |
value: 65.755
|
|
|
|
| 49 |
type: mbpp
|
| 50 |
name: Mostly Basic Python Problems (mbpp)
|
| 51 |
metrics:
|
| 52 |
+
- name: pass@1 (t=0.1)
|
| 53 |
type: pass@1
|
| 54 |
+
value: 39.112
|
| 55 |
- name: pass@10 (t=0.8)
|
| 56 |
type: pass@10
|
| 57 |
value: 59.895
|
|
|
|
| 61 |
type: race
|
| 62 |
name: RACE
|
| 63 |
metrics:
|
| 64 |
+
- name: accuracy (0 shot)
|
| 65 |
type: accuracy
|
| 66 |
value: 41.148
|
| 67 |
- task:
|
|
|
|
| 70 |
type: mmlu
|
| 71 |
name: Measuring Massive Multitask Language Understanding (MMLU)
|
| 72 |
metrics:
|
| 73 |
+
- name: accuracy (5 shot)
|
| 74 |
+
type: accuracy
|
| 75 |
+
value: 53.215
|
| 76 |
+
- name: accuracy (0 shot)
|
| 77 |
type: accuracy
|
| 78 |
value: 52.789
|
| 79 |
- task:
|
|
|
|
| 82 |
type: truthful_qa
|
| 83 |
name: Truthful QA
|
| 84 |
metrics:
|
| 85 |
+
- name: accuracy (0 shot)
|
| 86 |
type: accuracy
|
| 87 |
value: 47.29
|
| 88 |
- task:
|
|
|
|
| 103 |
type: copa
|
| 104 |
name: COPA
|
| 105 |
metrics:
|
| 106 |
+
- name: accuracy (0 shot)
|
| 107 |
type: accuracy
|
| 108 |
value: 85
|
| 109 |
- task:
|
|
|
|
| 112 |
type: boolq
|
| 113 |
name: Boolq
|
| 114 |
metrics:
|
| 115 |
+
- name: accuracy (0 shot)
|
| 116 |
type: accuracy
|
| 117 |
value: 82.783
|
| 118 |
- task:
|
|
|
|
| 121 |
type: openbookqa
|
| 122 |
name: Openbook QA
|
| 123 |
metrics:
|
| 124 |
+
- name: accuracy (0 shot)
|
| 125 |
type: accuracy
|
| 126 |
value: 42
|
| 127 |
- task:
|
|
|
|
| 142 |
type: piqa
|
| 143 |
name: PIQA
|
| 144 |
metrics:
|
| 145 |
+
- name: accuracy (0 shot)
|
| 146 |
type: accuracy
|
| 147 |
value: 77.856
|
| 148 |
- task:
|
|
|
|
| 151 |
type: ai2_arc
|
| 152 |
name: ARC (Easy)
|
| 153 |
metrics:
|
| 154 |
+
- name: accuracy (0 shot)
|
| 155 |
type: accuracy
|
| 156 |
value: 70.328
|
| 157 |
- task:
|