Clean up
Browse files
eval_results/HuggingFaceH4/zephyr-7b-beta/main/mixeval
DELETED
@@ -1,20 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"overall score (final score)": 0.6890000000000001,
|
3 |
-
"DROP": 0.767,
|
4 |
-
"BBH": 0.758,
|
5 |
-
"MATH": 0.44,
|
6 |
-
"GSM8k": 0.725,
|
7 |
-
"TriviaQA": 0.741,
|
8 |
-
"AGIEval": 0.472,
|
9 |
-
"MMLU": 0.655,
|
10 |
-
"MBPP": 0.0,
|
11 |
-
"BoolQ": 0.771,
|
12 |
-
"HellaSwag": 0.38,
|
13 |
-
"GPQA": 0.0,
|
14 |
-
"PIQA": 0.865,
|
15 |
-
"ARC": 0.88,
|
16 |
-
"OpenBookQA": 0.75,
|
17 |
-
"SIQA": 0.561,
|
18 |
-
"CommonsenseQA": 0.712,
|
19 |
-
"WinoGrande": 0.667
|
20 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
eval_results/HuggingFaceH4/zephyr-7b-beta/main/mixeval_hard
DELETED
@@ -1,19 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"overall score (final score)": 0.35350000000000004,
|
3 |
-
"MATH": 0.581,
|
4 |
-
"BBH": 0.719,
|
5 |
-
"DROP": 0.492,
|
6 |
-
"GSM8k": 0.518,
|
7 |
-
"AGIEval": 0.211,
|
8 |
-
"TriviaQA": 0.363,
|
9 |
-
"MBPP": 0.0,
|
10 |
-
"MMLU": 0.242,
|
11 |
-
"HellaSwag": 0.279,
|
12 |
-
"BoolQ": 0.378,
|
13 |
-
"GPQA": 0.25,
|
14 |
-
"PIQA": 0.5,
|
15 |
-
"OpenBookQA": 0.5,
|
16 |
-
"ARC": 0.0,
|
17 |
-
"CommonsenseQA": 0.4,
|
18 |
-
"SIQA": 0.25
|
19 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|