Update README.md
Browse files
README.md
CHANGED
|
@@ -5,4 +5,65 @@
|
|
| 5 |
|truthfulqa_mc2| 2|none | 0|acc |0.4689|± |0.0156|
|
| 6 |
|winogrande| 1|none | 5|acc |0.5122|± | 0.014|
|
| 7 |
|hellaswag| 1|none | 10|acc |0.2697|± |0.0044|
|
| 8 |
-
| | |none | 10|acc_norm|0.2827|± |0.0045|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
|truthfulqa_mc2| 2|none | 0|acc |0.4689|± |0.0156|
|
| 6 |
|winogrande| 1|none | 5|acc |0.5122|± | 0.014|
|
| 7 |
|hellaswag| 1|none | 10|acc |0.2697|± |0.0044|
|
| 8 |
+
| | |none | 10|acc_norm|0.2827|± |0.0045|
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
| Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
|
| 12 |
+
|-----------------------------------|------:|------|-----:|------|-----:|---|-----:|
|
| 13 |
+
|abstract_algebra | 0|none | 5|acc |0.2200|± |0.0416|
|
| 14 |
+
|anatomy | 0|none | 5|acc |0.3333|± |0.0407|
|
| 15 |
+
|astronomy | 0|none | 5|acc |0.1776|± |0.0311|
|
| 16 |
+
|business_ethics | 0|none | 5|acc |0.2100|± |0.0409|
|
| 17 |
+
|clinical_knowledge | 0|none | 5|acc |0.2528|± |0.0267|
|
| 18 |
+
|college_biology | 0|none | 5|acc |0.2778|± |0.0375|
|
| 19 |
+
|college_chemistry | 0|none | 5|acc |0.1800|± |0.0386|
|
| 20 |
+
|college_computer_science | 0|none | 5|acc |0.1900|± |0.0394|
|
| 21 |
+
|college_mathematics | 0|none | 5|acc |0.2200|± |0.0416|
|
| 22 |
+
|college_medicine | 0|none | 5|acc |0.1965|± |0.0303|
|
| 23 |
+
|college_physics | 0|none | 5|acc |0.2451|± |0.0428|
|
| 24 |
+
|computer_security | 0|none | 5|acc |0.2000|± |0.0402|
|
| 25 |
+
|conceptual_physics | 0|none | 5|acc |0.2511|± |0.0283|
|
| 26 |
+
|econometrics | 0|none | 5|acc |0.2719|± |0.0419|
|
| 27 |
+
|electrical_engineering | 0|none | 5|acc |0.2138|± |0.0342|
|
| 28 |
+
|elementary_mathematics | 0|none | 5|acc |0.2460|± |0.0222|
|
| 29 |
+
|formal_logic | 0|none | 5|acc |0.1905|± |0.0351|
|
| 30 |
+
|global_facts | 0|none | 5|acc |0.1500|± |0.0359|
|
| 31 |
+
|high_school_biology | 0|none | 5|acc |0.3000|± |0.0261|
|
| 32 |
+
|high_school_chemistry | 0|none | 5|acc |0.2562|± |0.0307|
|
| 33 |
+
|high_school_computer_science | 0|none | 5|acc |0.2800|± |0.0451|
|
| 34 |
+
|high_school_european_history | 0|none | 5|acc |0.2788|± |0.0350|
|
| 35 |
+
|high_school_geography | 0|none | 5|acc |0.3232|± |0.0333|
|
| 36 |
+
|high_school_government_and_politics| 0|none | 5|acc |0.3212|± |0.0337|
|
| 37 |
+
|high_school_macroeconomics | 0|none | 5|acc |0.3308|± |0.0239|
|
| 38 |
+
|high_school_mathematics | 0|none | 5|acc |0.2593|± |0.0267|
|
| 39 |
+
|high_school_microeconomics | 0|none | 5|acc |0.2815|± |0.0292|
|
| 40 |
+
|high_school_physics | 0|none | 5|acc |0.2384|± |0.0348|
|
| 41 |
+
|high_school_psychology | 0|none | 5|acc |0.2716|± |0.0191|
|
| 42 |
+
|high_school_statistics | 0|none | 5|acc |0.4769|± |0.0341|
|
| 43 |
+
|high_school_us_history | 0|none | 5|acc |0.2598|± |0.0308|
|
| 44 |
+
|high_school_world_history | 0|none | 5|acc |0.2194|± |0.0269|
|
| 45 |
+
|human_aging | 0|none | 5|acc |0.2197|± |0.0278|
|
| 46 |
+
|human_sexuality | 0|none | 5|acc |0.2748|± |0.0392|
|
| 47 |
+
|international_law | 0|none | 5|acc |0.3306|± |0.0429|
|
| 48 |
+
|jurisprudence | 0|none | 5|acc |0.2130|± |0.0396|
|
| 49 |
+
|logical_fallacies | 0|none | 5|acc |0.2331|± |0.0332|
|
| 50 |
+
|machine_learning | 0|none | 5|acc |0.2232|± |0.0395|
|
| 51 |
+
|management | 0|none | 5|acc |0.2039|± |0.0399|
|
| 52 |
+
|marketing | 0|none | 5|acc |0.1966|± |0.0260|
|
| 53 |
+
|medical_genetics | 0|none | 5|acc |0.3000|± |0.0461|
|
| 54 |
+
|miscellaneous | 0|none | 5|acc |0.2580|± |0.0156|
|
| 55 |
+
|moral_disputes | 0|none | 5|acc |0.1850|± |0.0209|
|
| 56 |
+
|moral_scenarios | 0|none | 5|acc |0.2380|± |0.0142|
|
| 57 |
+
|nutrition | 0|none | 5|acc |0.3039|± |0.0263|
|
| 58 |
+
|philosophy | 0|none | 5|acc |0.1929|± |0.0224|
|
| 59 |
+
|prehistory | 0|none | 5|acc |0.2160|± |0.0229|
|
| 60 |
+
|professional_accounting | 0|none | 5|acc |0.2518|± |0.0259|
|
| 61 |
+
|professional_law | 0|none | 5|acc |0.2419|± |0.0109|
|
| 62 |
+
|professional_medicine | 0|none | 5|acc |0.4375|± |0.0301|
|
| 63 |
+
|professional_psychology | 0|none | 5|acc |0.2190|± |0.0167|
|
| 64 |
+
|public_relations | 0|none | 5|acc |0.2273|± |0.0401|
|
| 65 |
+
|security_studies | 0|none | 5|acc |0.3633|± |0.0308|
|
| 66 |
+
|sociology | 0|none | 5|acc |0.2338|± |0.0299|
|
| 67 |
+
|us_foreign_policy | 0|none | 5|acc |0.2900|± |0.0456|
|
| 68 |
+
|virology | 0|none | 5|acc |0.2169|± |0.0321|
|
| 69 |
+
|world_religions | 0|none | 5|acc |0.1930|± |0.0303|
|