Update README.md
Browse files
README.md
CHANGED
|
@@ -15,7 +15,77 @@ tags: []
|
|
| 15 |
|
| 16 |
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
|
| 18 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
- **Developed by:** [More Information Needed]
|
| 21 |
- **Funded by [optional]:** [More Information Needed]
|
|
|
|
| 15 |
|
| 16 |
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
|
| 18 |
+
| Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
|
| 19 |
+
|-------------|------:|------|-----:|--------|-----:|---|-----:|
|
| 20 |
+
|arc_challenge| 1|none | 25|acc |0.1792|± |0.0112|
|
| 21 |
+
| | |none | 25|acc_norm|0.2065|± |0.0118|
|
| 22 |
+
|truthfulqa_mc2| 2|none | 0|acc |0.4553|± |0.0154|
|
| 23 |
+
|winogrande| 1|none | 5|acc |0.4972|± |0.0141|
|
| 24 |
+
|hellaswag| 1|none | 10|acc |0.2703|± |0.0044|
|
| 25 |
+
| | |none | 10|acc_norm|0.2796|± |0.0045|
|
| 26 |
+
|gsm8k| 3|strict-match | 5|exact_match|0.0000|± |0.0000|
|
| 27 |
+
| | |flexible-extract| 5|exact_match|0.0144|± |0.0033|
|
| 28 |
+
|
| 29 |
+
(0.24656842105263158, 0.004373961821155628)
|
| 30 |
+
| Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
|
| 31 |
+
|-----------------------------------|------:|------|-----:|------|-----:|---|-----:|
|
| 32 |
+
|world_religions | 0|none | 5|acc |0.2573|± |0.0335|
|
| 33 |
+
|virology | 0|none | 5|acc |0.2831|± |0.0351|
|
| 34 |
+
|us_foreign_policy | 0|none | 5|acc |0.2500|± |0.0435|
|
| 35 |
+
|sociology | 0|none | 5|acc |0.2438|± |0.0304|
|
| 36 |
+
|security_studies | 0|none | 5|acc |0.2327|± |0.0270|
|
| 37 |
+
|public_relations | 0|none | 5|acc |0.2273|± |0.0401|
|
| 38 |
+
|professional_psychology | 0|none | 5|acc |0.2500|± |0.0175|
|
| 39 |
+
|professional_medicine | 0|none | 5|acc |0.4485|± |0.0302|
|
| 40 |
+
|professional_law | 0|none | 5|acc |0.2458|± |0.0110|
|
| 41 |
+
|professional_accounting | 0|none | 5|acc |0.2624|± |0.0262|
|
| 42 |
+
|prehistory | 0|none | 5|acc |0.2130|± |0.0228|
|
| 43 |
+
|philosophy | 0|none | 5|acc |0.1929|± |0.0224|
|
| 44 |
+
|nutrition | 0|none | 5|acc |0.2222|± |0.0238|
|
| 45 |
+
|moral_scenarios | 0|none | 5|acc |0.2380|± |0.0142|
|
| 46 |
+
|moral_disputes | 0|none | 5|acc |0.2486|± |0.0233|
|
| 47 |
+
|miscellaneous | 0|none | 5|acc |0.2644|± |0.0158|
|
| 48 |
+
|medical_genetics | 0|none | 5|acc |0.3000|± |0.0461|
|
| 49 |
+
|marketing | 0|none | 5|acc |0.1752|± |0.0249|
|
| 50 |
+
|management | 0|none | 5|acc |0.1748|± |0.0376|
|
| 51 |
+
|machine_learning | 0|none | 5|acc |0.2500|± |0.0411|
|
| 52 |
+
|logical_fallacies | 0|none | 5|acc |0.2945|± |0.0358|
|
| 53 |
+
|jurisprudence | 0|none | 5|acc |0.2593|± |0.0424|
|
| 54 |
+
|international_law | 0|none | 5|acc |0.2479|± |0.0394|
|
| 55 |
+
|human_sexuality | 0|none | 5|acc |0.2595|± |0.0384|
|
| 56 |
+
|human_aging | 0|none | 5|acc |0.2466|± |0.0289|
|
| 57 |
+
|high_school_world_history | 0|none | 5|acc |0.2911|± |0.0296|
|
| 58 |
+
|high_school_us_history | 0|none | 5|acc |0.2794|± |0.0315|
|
| 59 |
+
|high_school_statistics | 0|none | 5|acc |0.4722|± |0.0340|
|
| 60 |
+
|high_school_psychology | 0|none | 5|acc |0.1927|± |0.0169|
|
| 61 |
+
|high_school_physics | 0|none | 5|acc |0.1987|± |0.0326|
|
| 62 |
+
|high_school_microeconomics | 0|none | 5|acc |0.2227|± |0.0270|
|
| 63 |
+
|high_school_mathematics | 0|none | 5|acc |0.2667|± |0.0270|
|
| 64 |
+
|high_school_macroeconomics | 0|none | 5|acc |0.2103|± |0.0207|
|
| 65 |
+
|high_school_government_and_politics| 0|none | 5|acc |0.2435|± |0.0310|
|
| 66 |
+
|high_school_geography | 0|none | 5|acc |0.1717|± |0.0269|
|
| 67 |
+
|high_school_european_history | 0|none | 5|acc |0.2485|± |0.0337|
|
| 68 |
+
|high_school_computer_science | 0|none | 5|acc |0.2700|± |0.0446|
|
| 69 |
+
|high_school_chemistry | 0|none | 5|acc |0.2906|± |0.0319|
|
| 70 |
+
|high_school_biology | 0|none | 5|acc |0.2774|± |0.0255|
|
| 71 |
+
|global_facts | 0|none | 5|acc |0.1600|± |0.0368|
|
| 72 |
+
|formal_logic | 0|none | 5|acc |0.1508|± |0.0320|
|
| 73 |
+
|elementary_mathematics | 0|none | 5|acc |0.2540|± |0.0224|
|
| 74 |
+
|electrical_engineering | 0|none | 5|acc |0.2414|± |0.0357|
|
| 75 |
+
|econometrics | 0|none | 5|acc |0.2544|± |0.0410|
|
| 76 |
+
|conceptual_physics | 0|none | 5|acc |0.2638|± |0.0288|
|
| 77 |
+
|computer_security | 0|none | 5|acc |0.2600|± |0.0441|
|
| 78 |
+
|college_physics | 0|none | 5|acc |0.2157|± |0.0409|
|
| 79 |
+
|college_medicine | 0|none | 5|acc |0.2081|± |0.0310|
|
| 80 |
+
|college_mathematics | 0|none | 5|acc |0.2300|± |0.0423|
|
| 81 |
+
|college_computer_science | 0|none | 5|acc |0.3100|± |0.0465|
|
| 82 |
+
|college_chemistry | 0|none | 5|acc |0.2000|± |0.0402|
|
| 83 |
+
|college_biology | 0|none | 5|acc |0.2431|± |0.0359|
|
| 84 |
+
|clinical_knowledge | 0|none | 5|acc |0.2415|± |0.0263|
|
| 85 |
+
|business_ethics | 0|none | 5|acc |0.1600|± |0.0368|
|
| 86 |
+
|astronomy | 0|none | 5|acc |0.1776|± |0.0311|
|
| 87 |
+
|anatomy | 0|none | 5|acc |0.3407|± |0.0409|
|
| 88 |
+
|abstract_algebra | 0|none | 5|acc |0.2200|± |0.0416|
|
| 89 |
|
| 90 |
- **Developed by:** [More Information Needed]
|
| 91 |
- **Funded by [optional]:** [More Information Needed]
|