Update README.md
Browse files
README.md
CHANGED
|
@@ -18,8 +18,8 @@ model-index:
|
|
| 18 |
name: MMLU
|
| 19 |
type: MMLU
|
| 20 |
metrics:
|
| 21 |
-
- name:
|
| 22 |
-
type:
|
| 23 |
value: 38.73
|
| 24 |
verified: true
|
| 25 |
- task:
|
|
@@ -28,8 +28,8 @@ model-index:
|
|
| 28 |
name: IFEval
|
| 29 |
type: IFEval
|
| 30 |
metrics:
|
| 31 |
-
- name:
|
| 32 |
-
type:
|
| 33 |
value: 44.01
|
| 34 |
verified: true
|
| 35 |
- task:
|
|
@@ -38,8 +38,8 @@ model-index:
|
|
| 38 |
name: GSM8K
|
| 39 |
type: GSM8K
|
| 40 |
metrics:
|
| 41 |
-
- name:
|
| 42 |
-
type:
|
| 43 |
value: 34.80
|
| 44 |
verified: true
|
| 45 |
- task:
|
|
@@ -48,8 +48,8 @@ model-index:
|
|
| 48 |
name: MATH
|
| 49 |
type: MATH
|
| 50 |
metrics:
|
| 51 |
-
- name:
|
| 52 |
-
type:
|
| 53 |
value: 6.64
|
| 54 |
verified: true
|
| 55 |
- task:
|
|
@@ -58,8 +58,8 @@ model-index:
|
|
| 58 |
name: HumanEval
|
| 59 |
type: HumanEval
|
| 60 |
metrics:
|
| 61 |
-
- name:
|
| 62 |
-
type:
|
| 63 |
value: 26.22
|
| 64 |
verified: true
|
| 65 |
- task:
|
|
@@ -68,8 +68,8 @@ model-index:
|
|
| 68 |
name: MBPP
|
| 69 |
type: MBPP
|
| 70 |
metrics:
|
| 71 |
-
- name:
|
| 72 |
-
type:
|
| 73 |
value: 31.40
|
| 74 |
verified: true
|
| 75 |
- task:
|
|
@@ -78,8 +78,8 @@ model-index:
|
|
| 78 |
name: Hellaswag
|
| 79 |
type: Hellaswag
|
| 80 |
metrics:
|
| 81 |
-
- name:
|
| 82 |
-
type:
|
| 83 |
value: 44.86
|
| 84 |
verified: true
|
| 85 |
- task:
|
|
@@ -88,8 +88,8 @@ model-index:
|
|
| 88 |
name: GPQA
|
| 89 |
type: GPQA
|
| 90 |
metrics:
|
| 91 |
-
- name:
|
| 92 |
-
type:
|
| 93 |
value: 11.11
|
| 94 |
verified: true
|
| 95 |
metrics:
|
|
|
|
| 18 |
name: MMLU
|
| 19 |
type: MMLU
|
| 20 |
metrics:
|
| 21 |
+
- name: weighted accuracy
|
| 22 |
+
type: weighted accuracy
|
| 23 |
value: 38.73
|
| 24 |
verified: true
|
| 25 |
- task:
|
|
|
|
| 28 |
name: IFEval
|
| 29 |
type: IFEval
|
| 30 |
metrics:
|
| 31 |
+
- name: overall accuracy
|
| 32 |
+
type: overall accuracy
|
| 33 |
value: 44.01
|
| 34 |
verified: true
|
| 35 |
- task:
|
|
|
|
| 38 |
name: GSM8K
|
| 39 |
type: GSM8K
|
| 40 |
metrics:
|
| 41 |
+
- name: accuracy
|
| 42 |
+
type: accuracy
|
| 43 |
value: 34.80
|
| 44 |
verified: true
|
| 45 |
- task:
|
|
|
|
| 48 |
name: MATH
|
| 49 |
type: MATH
|
| 50 |
metrics:
|
| 51 |
+
- name: accuracy
|
| 52 |
+
type: accuracy
|
| 53 |
value: 6.64
|
| 54 |
verified: true
|
| 55 |
- task:
|
|
|
|
| 58 |
name: HumanEval
|
| 59 |
type: HumanEval
|
| 60 |
metrics:
|
| 61 |
+
- name: humaneval_pass@1
|
| 62 |
+
type: humaneval_pass@1
|
| 63 |
value: 26.22
|
| 64 |
verified: true
|
| 65 |
- task:
|
|
|
|
| 68 |
name: MBPP
|
| 69 |
type: MBPP
|
| 70 |
metrics:
|
| 71 |
+
- name: score
|
| 72 |
+
type: score
|
| 73 |
value: 31.40
|
| 74 |
verified: true
|
| 75 |
- task:
|
|
|
|
| 78 |
name: Hellaswag
|
| 79 |
type: Hellaswag
|
| 80 |
metrics:
|
| 81 |
+
- name: accuracy
|
| 82 |
+
type: accuracy
|
| 83 |
value: 44.86
|
| 84 |
verified: true
|
| 85 |
- task:
|
|
|
|
| 88 |
name: GPQA
|
| 89 |
type: GPQA
|
| 90 |
metrics:
|
| 91 |
+
- name: accuracy
|
| 92 |
+
type: accuracy
|
| 93 |
value: 11.11
|
| 94 |
verified: true
|
| 95 |
metrics:
|