Upload eval_results/iopo-exp/uf-l31-dpo-base-armo-iter1/main/mixeval/results_2024-09-02T14-00-52.json with huggingface_hub
Browse files
eval_results/iopo-exp/uf-l31-dpo-base-armo-iter1/main/mixeval/results_2024-09-02T14-00-52.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"overall score (final score)": 0.7905,
|
| 3 |
+
"DROP": 0.897,
|
| 4 |
+
"BBH": 0.933,
|
| 5 |
+
"MATH": 0.755,
|
| 6 |
+
"GSM8k": 0.958,
|
| 7 |
+
"TriviaQA": 0.772,
|
| 8 |
+
"AGIEval": 0.593,
|
| 9 |
+
"MMLU": 0.729,
|
| 10 |
+
"MBPP": 0.0,
|
| 11 |
+
"BoolQ": 0.851,
|
| 12 |
+
"HellaSwag": 0.801,
|
| 13 |
+
"GPQA": 0.25,
|
| 14 |
+
"PIQA": 0.844,
|
| 15 |
+
"ARC": 0.88,
|
| 16 |
+
"OpenBookQA": 0.795,
|
| 17 |
+
"SIQA": 0.633,
|
| 18 |
+
"CommonsenseQA": 0.811,
|
| 19 |
+
"WinoGrande": 0.333
|
| 20 |
+
}
|