Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ model-index:
|
|
| 14 |
type: hellaswag
|
| 15 |
name: hellaswag
|
| 16 |
metrics:
|
| 17 |
-
- type:
|
| 18 |
value: 27.7
|
| 19 |
- name: task_2
|
| 20 |
results:
|
|
@@ -24,7 +24,7 @@ model-index:
|
|
| 24 |
type: ARC
|
| 25 |
name: ARC
|
| 26 |
metrics:
|
| 27 |
-
- type:
|
| 28 |
value: 22.4
|
| 29 |
- name: task_3
|
| 30 |
results:
|
|
@@ -34,7 +34,7 @@ model-index:
|
|
| 34 |
type: MMLU
|
| 35 |
name: MMLU
|
| 36 |
metrics:
|
| 37 |
-
- type:
|
| 38 |
value: 24.9
|
| 39 |
|
| 40 |
- name: task_4
|
|
@@ -45,6 +45,6 @@ model-index:
|
|
| 45 |
type: TruthfulQA
|
| 46 |
name: TruthfulQA
|
| 47 |
metrics:
|
| 48 |
-
- type:
|
| 49 |
value: 46.5
|
| 50 |
---
|
|
|
|
| 14 |
type: hellaswag
|
| 15 |
name: hellaswag
|
| 16 |
metrics:
|
| 17 |
+
- type: acc_norm
|
| 18 |
value: 27.7
|
| 19 |
- name: task_2
|
| 20 |
results:
|
|
|
|
| 24 |
type: ARC
|
| 25 |
name: ARC
|
| 26 |
metrics:
|
| 27 |
+
- type: acc_norm
|
| 28 |
value: 22.4
|
| 29 |
- name: task_3
|
| 30 |
results:
|
|
|
|
| 34 |
type: MMLU
|
| 35 |
name: MMLU
|
| 36 |
metrics:
|
| 37 |
+
- type: acc
|
| 38 |
value: 24.9
|
| 39 |
|
| 40 |
- name: task_4
|
|
|
|
| 45 |
type: TruthfulQA
|
| 46 |
name: TruthfulQA
|
| 47 |
metrics:
|
| 48 |
+
- type: mc2
|
| 49 |
value: 46.5
|
| 50 |
---
|