Upload eval_results/iopo-exp/uf-l31-dpo-base-armo-iter1/main/mixeval_hard/results_2024-09-02T13-36-40.json with huggingface_hub
Browse files
eval_results/iopo-exp/uf-l31-dpo-base-armo-iter1/main/mixeval_hard/results_2024-09-02T13-36-40.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"overall score (final score)": 0.5205,
|
3 |
+
"MATH": 0.85,
|
4 |
+
"BBH": 0.519,
|
5 |
+
"DROP": 0.772,
|
6 |
+
"GSM8k": 0.882,
|
7 |
+
"AGIEval": 0.296,
|
8 |
+
"TriviaQA": 0.511,
|
9 |
+
"MBPP": 0.0,
|
10 |
+
"MMLU": 0.385,
|
11 |
+
"HellaSwag": 0.443,
|
12 |
+
"BoolQ": 0.405,
|
13 |
+
"GPQA": 0.25,
|
14 |
+
"PIQA": 0.25,
|
15 |
+
"OpenBookQA": 0.625,
|
16 |
+
"ARC": 0.25,
|
17 |
+
"CommonsenseQA": 0.66,
|
18 |
+
"SIQA": 0.4
|
19 |
+
}
|