lewtun HF Staff commited on
Commit
a0f5df9
·
verified ·
1 Parent(s): b59264d

Upload eval_results/HuggingFaceH4/zephyr-7b-beta/main/mixeval_hard/ with huggingface_hub

Browse files
eval_results/HuggingFaceH4/zephyr-7b-beta/main/mixeval_hard ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }