lewtun HF Staff commited on
Commit
333bb2c
·
verified ·
1 Parent(s): cf460b7

Upload eval_results/mistralai/Mistral-7B-Instruct-v0.1/main/mixeval_hard/results_2024-10-04T07-53-05.json with huggingface_hub

Browse files
eval_results/mistralai/Mistral-7B-Instruct-v0.1/main/mixeval_hard/results_2024-10-04T07-53-05.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "overall score (final score)": 0.292,
3
+ "MATH": 0.375,
4
+ "BBH": 0.625,
5
+ "DROP": 0.371,
6
+ "GSM8k": 0.55,
7
+ "AGIEval": 0.254,
8
+ "TriviaQA": 0.19,
9
+ "MBPP": 0.5,
10
+ "MMLU": 0.255,
11
+ "HellaSwag": 0.246,
12
+ "BoolQ": 0.486,
13
+ "GPQA": 0.375,
14
+ "PIQA": 0.5,
15
+ "OpenBookQA": 0.125,
16
+ "ARC": 0.0,
17
+ "CommonsenseQA": 0.46,
18
+ "SIQA": 0.2
19
+ }