Update README.md
Browse files
README.md
CHANGED
|
@@ -27,4 +27,69 @@ also sorry I just realized theres some residual from where I copied the model co
|
|
| 27 |
|truthfulqa_mc2| 2|none | 0|acc |0.4599|± |0.0154|
|
| 28 |
|winogrande| 1|none | 5|acc |0.5083|± |0.0141|
|
| 29 |
|hellaswag| 1|none | 10|acc |0.2728|± |0.0044|
|
| 30 |
-
| | |none | 10|acc_norm|0.2815|± |0.0045|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
|truthfulqa_mc2| 2|none | 0|acc |0.4599|± |0.0154|
|
| 28 |
|winogrande| 1|none | 5|acc |0.5083|± |0.0141|
|
| 29 |
|hellaswag| 1|none | 10|acc |0.2728|± |0.0044|
|
| 30 |
+
| | |none | 10|acc_norm|0.2815|± |0.0045|
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
### mmlu
|
| 34 |
+
|
| 35 |
+
mean is 0.26394385964912276 i think
|
| 36 |
+
|
| 37 |
+
| Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
|
| 38 |
+
|-----------------------------------|------:|------|-----:|------|-----:|---|-----:|
|
| 39 |
+
|world_religions | 0|none | 5|acc |0.1988|± |0.0306|
|
| 40 |
+
|virology | 0|none | 5|acc |0.1928|± |0.0307|
|
| 41 |
+
|us_foreign_policy | 0|none | 5|acc |0.2600|± |0.0441|
|
| 42 |
+
|sociology | 0|none | 5|acc |0.2438|± |0.0304|
|
| 43 |
+
|security_studies | 0|none | 5|acc |0.4000|± |0.0314|
|
| 44 |
+
|public_relations | 0|none | 5|acc |0.2273|± |0.0401|
|
| 45 |
+
|professional_psychology | 0|none | 5|acc |0.2484|± |0.0175|
|
| 46 |
+
|professional_medicine | 0|none | 5|acc |0.4485|± |0.0302|
|
| 47 |
+
|professional_law | 0|none | 5|acc |0.2445|± |0.0110|
|
| 48 |
+
|professional_accounting | 0|none | 5|acc |0.2482|± |0.0258|
|
| 49 |
+
|prehistory | 0|none | 5|acc |0.2562|± |0.0243|
|
| 50 |
+
|philosophy | 0|none | 5|acc |0.2186|± |0.0235|
|
| 51 |
+
|nutrition | 0|none | 5|acc |0.2941|± |0.0261|
|
| 52 |
+
|moral_scenarios | 0|none | 5|acc |0.2503|± |0.0145|
|
| 53 |
+
|moral_disputes | 0|none | 5|acc |0.1965|± |0.0214|
|
| 54 |
+
|miscellaneous | 0|none | 5|acc |0.2554|± |0.0156|
|
| 55 |
+
|medical_genetics | 0|none | 5|acc |0.3000|± |0.0461|
|
| 56 |
+
|marketing | 0|none | 5|acc |0.1966|± |0.0260|
|
| 57 |
+
|management | 0|none | 5|acc |0.1942|± |0.0392|
|
| 58 |
+
|machine_learning | 0|none | 5|acc |0.2321|± |0.0401|
|
| 59 |
+
|logical_fallacies | 0|none | 5|acc |0.2331|± |0.0332|
|
| 60 |
+
|jurisprudence | 0|none | 5|acc |0.2407|± |0.0413|
|
| 61 |
+
|international_law | 0|none | 5|acc |0.3719|± |0.0441|
|
| 62 |
+
|human_sexuality | 0|none | 5|acc |0.2137|± |0.0360|
|
| 63 |
+
|human_aging | 0|none | 5|acc |0.2646|± |0.0296|
|
| 64 |
+
|high_school_world_history | 0|none | 5|acc |0.2489|± |0.0281|
|
| 65 |
+
|high_school_us_history | 0|none | 5|acc |0.2304|± |0.0296|
|
| 66 |
+
|high_school_statistics | 0|none | 5|acc |0.4722|± |0.0340|
|
| 67 |
+
|high_school_psychology | 0|none | 5|acc |0.3083|± |0.0198|
|
| 68 |
+
|high_school_physics | 0|none | 5|acc |0.3046|± |0.0376|
|
| 69 |
+
|high_school_microeconomics | 0|none | 5|acc |0.3361|± |0.0307|
|
| 70 |
+
|high_school_mathematics | 0|none | 5|acc |0.2630|± |0.0268|
|
| 71 |
+
|high_school_macroeconomics | 0|none | 5|acc |0.3231|± |0.0237|
|
| 72 |
+
|high_school_government_and_politics| 0|none | 5|acc |0.3523|± |0.0345|
|
| 73 |
+
|high_school_geography | 0|none | 5|acc |0.3384|± |0.0337|
|
| 74 |
+
|high_school_european_history | 0|none | 5|acc |0.2909|± |0.0355|
|
| 75 |
+
|high_school_computer_science | 0|none | 5|acc |0.2600|± |0.0441|
|
| 76 |
+
|high_school_chemistry | 0|none | 5|acc |0.2709|± |0.0313|
|
| 77 |
+
|high_school_biology | 0|none | 5|acc |0.3161|± |0.0265|
|
| 78 |
+
|global_facts | 0|none | 5|acc |0.1800|± |0.0386|
|
| 79 |
+
|formal_logic | 0|none | 5|acc |0.1667|± |0.0333|
|
| 80 |
+
|elementary_mathematics | 0|none | 5|acc |0.2540|± |0.0224|
|
| 81 |
+
|electrical_engineering | 0|none | 5|acc |0.3103|± |0.0386|
|
| 82 |
+
|econometrics | 0|none | 5|acc |0.2895|± |0.0427|
|
| 83 |
+
|conceptual_physics | 0|none | 5|acc |0.2553|± |0.0285|
|
| 84 |
+
|computer_security | 0|none | 5|acc |0.1900|± |0.0394|
|
| 85 |
+
|college_physics | 0|none | 5|acc |0.3431|± |0.0472|
|
| 86 |
+
|college_medicine | 0|none | 5|acc |0.2312|± |0.0321|
|
| 87 |
+
|college_mathematics | 0|none | 5|acc |0.1800|± |0.0386|
|
| 88 |
+
|college_computer_science | 0|none | 5|acc |0.3000|± |0.0461|
|
| 89 |
+
|college_chemistry | 0|none | 5|acc |0.2900|± |0.0456|
|
| 90 |
+
|college_biology | 0|none | 5|acc |0.2083|± |0.0340|
|
| 91 |
+
|clinical_knowledge | 0|none | 5|acc |0.2038|± |0.0248|
|
| 92 |
+
|business_ethics | 0|none | 5|acc |0.2100|± |0.0409|
|
| 93 |
+
|astronomy | 0|none | 5|acc |0.1908|± |0.0320|
|
| 94 |
+
|anatomy | 0|none | 5|acc |0.2963|± |0.0394|
|
| 95 |
+
|abstract_algebra | 0|none | 5|acc |0.2000|± |0.0402|
|