Update README.md
Browse files
README.md
CHANGED
|
@@ -6,3 +6,65 @@
|
|
| 6 |
|winogrande| 1|none | 5|acc |0.5154|± | 0.014|
|
| 7 |
|hellaswag| 1|none | 10|acc |0.2822|± |0.0045|
|
| 8 |
| | |none | 10|acc_norm|0.3009|± |0.0046|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
|winogrande| 1|none | 5|acc |0.5154|± | 0.014|
|
| 7 |
|hellaswag| 1|none | 10|acc |0.2822|± |0.0045|
|
| 8 |
| | |none | 10|acc_norm|0.3009|± |0.0046|
|
| 9 |
+
|
| 10 |
+
0.26024912280701756
|
| 11 |
+
|
| 12 |
+
| Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
|
| 13 |
+
|-----------------------------------|------:|------|-----:|------|-----:|---|-----:|
|
| 14 |
+
|abstract_algebra | 0|none | 5|acc |0.3100|± |0.0465|
|
| 15 |
+
|anatomy | 0|none | 5|acc |0.2667|± |0.0382|
|
| 16 |
+
|astronomy | 0|none | 5|acc |0.1776|± |0.0311|
|
| 17 |
+
|business_ethics | 0|none | 5|acc |0.2200|± |0.0416|
|
| 18 |
+
|clinical_knowledge | 0|none | 5|acc |0.2528|± |0.0267|
|
| 19 |
+
|college_biology | 0|none | 5|acc |0.2153|± |0.0344|
|
| 20 |
+
|college_chemistry | 0|none | 5|acc |0.2300|± |0.0423|
|
| 21 |
+
|college_computer_science | 0|none | 5|acc |0.3400|± |0.0476|
|
| 22 |
+
|college_mathematics | 0|none | 5|acc |0.3200|± |0.0469|
|
| 23 |
+
|college_medicine | 0|none | 5|acc |0.2370|± |0.0324|
|
| 24 |
+
|college_physics | 0|none | 5|acc |0.1961|± |0.0395|
|
| 25 |
+
|computer_security | 0|none | 5|acc |0.2700|± |0.0446|
|
| 26 |
+
|conceptual_physics | 0|none | 5|acc |0.2383|± |0.0279|
|
| 27 |
+
|econometrics | 0|none | 5|acc |0.2982|± |0.0430|
|
| 28 |
+
|electrical_engineering | 0|none | 5|acc |0.2552|± |0.0363|
|
| 29 |
+
|elementary_mathematics | 0|none | 5|acc |0.2513|± |0.0223|
|
| 30 |
+
|formal_logic | 0|none | 5|acc |0.1667|± |0.0333|
|
| 31 |
+
|global_facts | 0|none | 5|acc |0.1600|± |0.0368|
|
| 32 |
+
|high_school_biology | 0|none | 5|acc |0.3000|± |0.0261|
|
| 33 |
+
|high_school_chemistry | 0|none | 5|acc |0.2167|± |0.0290|
|
| 34 |
+
|high_school_computer_science | 0|none | 5|acc |0.2300|± |0.0423|
|
| 35 |
+
|high_school_european_history | 0|none | 5|acc |0.2242|± |0.0326|
|
| 36 |
+
|high_school_geography | 0|none | 5|acc |0.3283|± |0.0335|
|
| 37 |
+
|high_school_government_and_politics| 0|none | 5|acc |0.3627|± |0.0347|
|
| 38 |
+
|high_school_macroeconomics | 0|none | 5|acc |0.3513|± |0.0242|
|
| 39 |
+
|high_school_mathematics | 0|none | 5|acc |0.2630|± |0.0268|
|
| 40 |
+
|high_school_microeconomics | 0|none | 5|acc |0.3067|± |0.0300|
|
| 41 |
+
|high_school_physics | 0|none | 5|acc |0.2583|± |0.0357|
|
| 42 |
+
|high_school_psychology | 0|none | 5|acc |0.3174|± |0.0200|
|
| 43 |
+
|high_school_statistics | 0|none | 5|acc |0.4722|± |0.0340|
|
| 44 |
+
|high_school_us_history | 0|none | 5|acc |0.2353|± |0.0298|
|
| 45 |
+
|high_school_world_history | 0|none | 5|acc |0.2616|± |0.0286|
|
| 46 |
+
|human_aging | 0|none | 5|acc |0.2108|± |0.0274|
|
| 47 |
+
|human_sexuality | 0|none | 5|acc |0.2977|± |0.0401|
|
| 48 |
+
|international_law | 0|none | 5|acc |0.2645|± |0.0403|
|
| 49 |
+
|jurisprudence | 0|none | 5|acc |0.2130|± |0.0396|
|
| 50 |
+
|logical_fallacies | 0|none | 5|acc |0.2331|± |0.0332|
|
| 51 |
+
|machine_learning | 0|none | 5|acc |0.2857|± |0.0429|
|
| 52 |
+
|management | 0|none | 5|acc |0.1748|± |0.0376|
|
| 53 |
+
|marketing | 0|none | 5|acc |0.1838|± |0.0254|
|
| 54 |
+
|medical_genetics | 0|none | 5|acc |0.3000|± |0.0461|
|
| 55 |
+
|miscellaneous | 0|none | 5|acc |0.2720|± |0.0159|
|
| 56 |
+
|moral_disputes | 0|none | 5|acc |0.2457|± |0.0232|
|
| 57 |
+
|moral_scenarios | 0|none | 5|acc |0.2391|± |0.0143|
|
| 58 |
+
|nutrition | 0|none | 5|acc |0.2255|± |0.0239|
|
| 59 |
+
|philosophy | 0|none | 5|acc |0.1961|± |0.0226|
|
| 60 |
+
|prehistory | 0|none | 5|acc |0.2284|± |0.0234|
|
| 61 |
+
|professional_accounting | 0|none | 5|acc |0.2553|± |0.0260|
|
| 62 |
+
|professional_law | 0|none | 5|acc |0.2458|± |0.0110|
|
| 63 |
+
|professional_medicine | 0|none | 5|acc |0.4485|± |0.0302|
|
| 64 |
+
|professional_psychology | 0|none | 5|acc |0.2516|± |0.0176|
|
| 65 |
+
|public_relations | 0|none | 5|acc |0.2727|± |0.0427|
|
| 66 |
+
|security_studies | 0|none | 5|acc |0.3551|± |0.0306|
|
| 67 |
+
|sociology | 0|none | 5|acc |0.2587|± |0.0310|
|
| 68 |
+
|us_foreign_policy | 0|none | 5|acc |0.2100|± |0.0409|
|
| 69 |
+
|virology | 0|none | 5|acc |0.2229|± |0.0324|
|
| 70 |
+
|world_religions | 0|none | 5|acc |0.2105|± |0.0313|
|