Commit
•
6f1d321
1
Parent(s):
728223f
Update README.md
Browse files
README.md
CHANGED
|
@@ -30,9 +30,12 @@ model-index:
|
|
| 30 |
|
| 31 |
- task:
|
| 32 |
type: text-generation
|
|
|
|
|
|
|
|
|
|
| 33 |
metrics:
|
| 34 |
-
- name:
|
| 35 |
-
type:
|
| 36 |
value: 59.81
|
| 37 |
verified: true
|
| 38 |
source:
|
|
@@ -41,8 +44,11 @@ model-index:
|
|
| 41 |
|
| 42 |
- task:
|
| 43 |
type: text-generation
|
|
|
|
|
|
|
|
|
|
| 44 |
metrics:
|
| 45 |
-
- name:
|
| 46 |
type: acc
|
| 47 |
value: 74.52
|
| 48 |
verified: true
|
|
@@ -52,8 +58,11 @@ model-index:
|
|
| 52 |
|
| 53 |
- task:
|
| 54 |
type: text-generation
|
|
|
|
|
|
|
|
|
|
| 55 |
metrics:
|
| 56 |
-
- name:
|
| 57 |
type: acc
|
| 58 |
value: 56.33
|
| 59 |
verified: true
|
|
@@ -63,9 +72,12 @@ model-index:
|
|
| 63 |
|
| 64 |
- task:
|
| 65 |
type: text-generation
|
|
|
|
|
|
|
|
|
|
| 66 |
metrics:
|
| 67 |
-
- name:
|
| 68 |
-
type:
|
| 69 |
value: 46.74
|
| 70 |
verified: true
|
| 71 |
source:
|
|
@@ -74,8 +86,11 @@ model-index:
|
|
| 74 |
|
| 75 |
- task:
|
| 76 |
type: text-generation
|
|
|
|
|
|
|
|
|
|
| 77 |
metrics:
|
| 78 |
-
- name:
|
| 79 |
type: acc
|
| 80 |
value: 75.06
|
| 81 |
verified: true
|
|
@@ -85,8 +100,11 @@ model-index:
|
|
| 85 |
|
| 86 |
- task:
|
| 87 |
type: text-generation
|
|
|
|
|
|
|
|
|
|
| 88 |
metrics:
|
| 89 |
-
- name:
|
| 90 |
type: acc
|
| 91 |
value: 50.64
|
| 92 |
verified: true
|
|
|
|
| 30 |
|
| 31 |
- task:
|
| 32 |
type: text-generation
|
| 33 |
+
dataset:
|
| 34 |
+
name: ARC (25-shot)
|
| 35 |
+
type: ai2_arc
|
| 36 |
metrics:
|
| 37 |
+
- name: Accuracy Norm
|
| 38 |
+
type: acc_norm
|
| 39 |
value: 59.81
|
| 40 |
verified: true
|
| 41 |
source:
|
|
|
|
| 44 |
|
| 45 |
- task:
|
| 46 |
type: text-generation
|
| 47 |
+
dataset:
|
| 48 |
+
name: Hellaswag (10-shot)
|
| 49 |
+
type: Hellaswag
|
| 50 |
metrics:
|
| 51 |
+
- name: Accuracy Norm
|
| 52 |
type: acc
|
| 53 |
value: 74.52
|
| 54 |
verified: true
|
|
|
|
| 58 |
|
| 59 |
- task:
|
| 60 |
type: text-generation
|
| 61 |
+
dataset:
|
| 62 |
+
name: MMLU (5-shot)
|
| 63 |
+
type: MMLU
|
| 64 |
metrics:
|
| 65 |
+
- name: Accuracy
|
| 66 |
type: acc
|
| 67 |
value: 56.33
|
| 68 |
verified: true
|
|
|
|
| 72 |
|
| 73 |
- task:
|
| 74 |
type: text-generation
|
| 75 |
+
dataset:
|
| 76 |
+
name: Truthful QA
|
| 77 |
+
type: Truthful_QA
|
| 78 |
metrics:
|
| 79 |
+
- name: Multi-true
|
| 80 |
+
type: mc2
|
| 81 |
value: 46.74
|
| 82 |
verified: true
|
| 83 |
source:
|
|
|
|
| 86 |
|
| 87 |
- task:
|
| 88 |
type: text-generation
|
| 89 |
+
dataset:
|
| 90 |
+
name: Winogrande (5-shot)
|
| 91 |
+
type: Winogrande
|
| 92 |
metrics:
|
| 93 |
+
- name: Accuracy
|
| 94 |
type: acc
|
| 95 |
value: 75.06
|
| 96 |
verified: true
|
|
|
|
| 100 |
|
| 101 |
- task:
|
| 102 |
type: text-generation
|
| 103 |
+
dataset:
|
| 104 |
+
name: GSM8K (5-shot)
|
| 105 |
+
type: GSM8K
|
| 106 |
metrics:
|
| 107 |
+
- name: Accuracy
|
| 108 |
type: acc
|
| 109 |
value: 50.64
|
| 110 |
verified: true
|