lewtun HF Staff commited on
Commit
ad3a605
·
verified ·
1 Parent(s): a3f3d23

Upload eval_results/HuggingFaceH4/llama-3.1-4b-dpo/v01.00/mixeval/results_2024-09-26T15-51-05.json with huggingface_hub

Browse files
eval_results/HuggingFaceH4/llama-3.1-4b-dpo/v01.00/mixeval/results_2024-09-26T15-51-05.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "overall score (final score)": 0.5820000000000001,
3
+ "DROP": 0.515,
4
+ "BBH": 0.689,
5
+ "MATH": 0.495,
6
+ "GSM8k": 0.74,
7
+ "TriviaQA": 0.482,
8
+ "AGIEval": 0.35,
9
+ "MMLU": 0.642,
10
+ "MBPP": 0.0,
11
+ "BoolQ": 0.754,
12
+ "HellaSwag": 0.579,
13
+ "GPQA": 0.25,
14
+ "PIQA": 0.771,
15
+ "ARC": 0.804,
16
+ "OpenBookQA": 0.705,
17
+ "SIQA": 0.663,
18
+ "CommonsenseQA": 0.708,
19
+ "WinoGrande": 0.667
20
+ }