Update README.md
Browse files
README.md
CHANGED
|
@@ -5,4 +5,65 @@
|
|
| 5 |
|truthfulqa_mc2| 2|none | 0|acc |0.4726|± |0.0156|
|
| 6 |
|winogrande| 1|none | 5|acc |0.4964|± |0.0141|
|
| 7 |
|hellaswag| 1|none | 10|acc |0.2725|± |0.0044|
|
| 8 |
-
| | |none | 10|acc_norm|0.2794|± |0.0045|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
|truthfulqa_mc2| 2|none | 0|acc |0.4726|± |0.0156|
|
| 6 |
|winogrande| 1|none | 5|acc |0.4964|± |0.0141|
|
| 7 |
|hellaswag| 1|none | 10|acc |0.2725|± |0.0044|
|
| 8 |
+
| | |none | 10|acc_norm|0.2794|± |0.0045|
|
| 9 |
+
0.2563298245614035
|
| 10 |
+
|
| 11 |
+
| Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
|
| 12 |
+
|-----------------------------------|------:|------|-----:|------|-----:|---|-----:|
|
| 13 |
+
|abstract_algebra | 0|none | 5|acc |0.2900|± |0.0456|
|
| 14 |
+
|anatomy | 0|none | 5|acc |0.2815|± |0.0389|
|
| 15 |
+
|astronomy | 0|none | 5|acc |0.1776|± |0.0311|
|
| 16 |
+
|business_ethics | 0|none | 5|acc |0.1700|± |0.0378|
|
| 17 |
+
|clinical_knowledge | 0|none | 5|acc |0.2113|± |0.0251|
|
| 18 |
+
|college_biology | 0|none | 5|acc |0.2292|± |0.0351|
|
| 19 |
+
|college_chemistry | 0|none | 5|acc |0.1800|± |0.0386|
|
| 20 |
+
|college_computer_science | 0|none | 5|acc |0.3000|± |0.0461|
|
| 21 |
+
|college_mathematics | 0|none | 5|acc |0.2800|± |0.0451|
|
| 22 |
+
|college_medicine | 0|none | 5|acc |0.2023|± |0.0306|
|
| 23 |
+
|college_physics | 0|none | 5|acc |0.2451|± |0.0428|
|
| 24 |
+
|computer_security | 0|none | 5|acc |0.2800|± |0.0451|
|
| 25 |
+
|conceptual_physics | 0|none | 5|acc |0.2723|± |0.0291|
|
| 26 |
+
|econometrics | 0|none | 5|acc |0.2456|± |0.0405|
|
| 27 |
+
|electrical_engineering | 0|none | 5|acc |0.2207|± |0.0346|
|
| 28 |
+
|elementary_mathematics | 0|none | 5|acc |0.2540|± |0.0224|
|
| 29 |
+
|formal_logic | 0|none | 5|acc |0.1587|± |0.0327|
|
| 30 |
+
|global_facts | 0|none | 5|acc |0.2200|± |0.0416|
|
| 31 |
+
|high_school_biology | 0|none | 5|acc |0.2161|± |0.0234|
|
| 32 |
+
|high_school_chemistry | 0|none | 5|acc |0.2808|± |0.0316|
|
| 33 |
+
|high_school_computer_science | 0|none | 5|acc |0.2000|± |0.0402|
|
| 34 |
+
|high_school_european_history | 0|none | 5|acc |0.2303|± |0.0329|
|
| 35 |
+
|high_school_geography | 0|none | 5|acc |0.2828|± |0.0321|
|
| 36 |
+
|high_school_government_and_politics| 0|none | 5|acc |0.2539|± |0.0314|
|
| 37 |
+
|high_school_macroeconomics | 0|none | 5|acc |0.3282|± |0.0238|
|
| 38 |
+
|high_school_mathematics | 0|none | 5|acc |0.2630|± |0.0268|
|
| 39 |
+
|high_school_microeconomics | 0|none | 5|acc |0.3487|± |0.0310|
|
| 40 |
+
|high_school_physics | 0|none | 5|acc |0.3245|± |0.0382|
|
| 41 |
+
|high_school_psychology | 0|none | 5|acc |0.2514|± |0.0186|
|
| 42 |
+
|high_school_statistics | 0|none | 5|acc |0.4722|± |0.0340|
|
| 43 |
+
|high_school_us_history | 0|none | 5|acc |0.3039|± |0.0323|
|
| 44 |
+
|high_school_world_history | 0|none | 5|acc |0.2616|± |0.0286|
|
| 45 |
+
|human_aging | 0|none | 5|acc |0.2377|± |0.0286|
|
| 46 |
+
|human_sexuality | 0|none | 5|acc |0.2672|± |0.0388|
|
| 47 |
+
|international_law | 0|none | 5|acc |0.2397|± |0.0390|
|
| 48 |
+
|jurisprudence | 0|none | 5|acc |0.2593|± |0.0424|
|
| 49 |
+
|logical_fallacies | 0|none | 5|acc |0.2331|± |0.0332|
|
| 50 |
+
|machine_learning | 0|none | 5|acc |0.3214|± |0.0443|
|
| 51 |
+
|management | 0|none | 5|acc |0.1748|± |0.0376|
|
| 52 |
+
|marketing | 0|none | 5|acc |0.2265|± |0.0274|
|
| 53 |
+
|medical_genetics | 0|none | 5|acc |0.3000|± |0.0461|
|
| 54 |
+
|miscellaneous | 0|none | 5|acc |0.2401|± |0.0153|
|
| 55 |
+
|moral_disputes | 0|none | 5|acc |0.2399|± |0.0230|
|
| 56 |
+
|moral_scenarios | 0|none | 5|acc |0.2358|± |0.0142|
|
| 57 |
+
|nutrition | 0|none | 5|acc |0.2320|± |0.0242|
|
| 58 |
+
|philosophy | 0|none | 5|acc |0.2026|± |0.0228|
|
| 59 |
+
|prehistory | 0|none | 5|acc |0.2284|± |0.0234|
|
| 60 |
+
|professional_accounting | 0|none | 5|acc |0.2376|± |0.0254|
|
| 61 |
+
|professional_law | 0|none | 5|acc |0.2379|± |0.0109|
|
| 62 |
+
|professional_medicine | 0|none | 5|acc |0.4412|± |0.0302|
|
| 63 |
+
|professional_psychology | 0|none | 5|acc |0.2500|± |0.0175|
|
| 64 |
+
|public_relations | 0|none | 5|acc |0.1818|± |0.0369|
|
| 65 |
+
|security_studies | 0|none | 5|acc |0.3429|± |0.0304|
|
| 66 |
+
|sociology | 0|none | 5|acc |0.2438|± |0.0304|
|
| 67 |
+
|us_foreign_policy | 0|none | 5|acc |0.2900|± |0.0456|
|
| 68 |
+
|virology | 0|none | 5|acc |0.2892|± |0.0353|
|
| 69 |
+
|world_religions | 0|none | 5|acc |0.2222|± |0.0319|
|