Upload eval_results/Qwen/Qwen2.5-72B-Instruct/main/mixeval/results_2024-09-23T15-01-32.json with huggingface_hub
Browse files
eval_results/Qwen/Qwen2.5-72B-Instruct/main/mixeval/results_2024-09-23T15-01-32.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"overall score (final score)": 0.861,
|
3 |
+
"DROP": 0.897,
|
4 |
+
"BBH": 0.928,
|
5 |
+
"MATH": 0.95,
|
6 |
+
"GSM8k": 0.964,
|
7 |
+
"TriviaQA": 0.836,
|
8 |
+
"AGIEval": 0.748,
|
9 |
+
"MMLU": 0.827,
|
10 |
+
"MBPP": 1.0,
|
11 |
+
"BoolQ": 0.874,
|
12 |
+
"HellaSwag": 0.906,
|
13 |
+
"GPQA": 0.25,
|
14 |
+
"PIQA": 0.938,
|
15 |
+
"ARC": 0.989,
|
16 |
+
"OpenBookQA": 0.977,
|
17 |
+
"SIQA": 0.816,
|
18 |
+
"CommonsenseQA": 0.868,
|
19 |
+
"WinoGrande": 0.667
|
20 |
+
}
|