Update README.md
Browse files
README.md
CHANGED
|
@@ -13,7 +13,72 @@ tags: []
|
|
| 13 |
| | |none | 25|acc_norm|0.2423|± |0.0125|
|
| 14 |
|truthfulqa_mc2| 2|none | 0|acc |0.4356|± |0.0151|
|
| 15 |
|winogrande| 1|none | 5|acc |0.5138|± | 0.014|
|
| 16 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model Details
|
| 19 |
|
|
|
|
| 13 |
| | |none | 25|acc_norm|0.2423|± |0.0125|
|
| 14 |
|truthfulqa_mc2| 2|none | 0|acc |0.4356|± |0.0151|
|
| 15 |
|winogrande| 1|none | 5|acc |0.5138|± | 0.014|
|
| 16 |
+
|hellaswag| 1|none | 10|acc |0.2938|± |0.0045|
|
| 17 |
+
| | |none | 10|acc_norm|0.3242|± |0.0047|
|
| 18 |
+
|gsm8k| 3|strict-match | 5|exact_match|0.0129|± |0.0031|
|
| 19 |
+
| | |flexible-extract| 5|exact_match|0.0197|± |0.0038|
|
| 20 |
+
|
| 21 |
+
### MMLU *(0.2649701754385965, 0.004451753262466369)*
|
| 22 |
+
|
| 23 |
+
| Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
|
| 24 |
+
|-----------------------------------|------:|------|-----:|------|-----:|---|-----:|
|
| 25 |
+
|world_religions | 0|none | 5|acc |0.2281|± |0.0322|
|
| 26 |
+
|virology | 0|none | 5|acc |0.1747|± |0.0296|
|
| 27 |
+
|us_foreign_policy | 0|none | 5|acc |0.2600|± |0.0441|
|
| 28 |
+
|sociology | 0|none | 5|acc |0.2736|± |0.0315|
|
| 29 |
+
|security_studies | 0|none | 5|acc |0.4000|± |0.0314|
|
| 30 |
+
|public_relations | 0|none | 5|acc |0.2273|± |0.0401|
|
| 31 |
+
|professional_psychology | 0|none | 5|acc |0.2467|± |0.0174|
|
| 32 |
+
|professional_medicine | 0|none | 5|acc |0.4485|± |0.0302|
|
| 33 |
+
|professional_law | 0|none | 5|acc |0.2490|± |0.0110|
|
| 34 |
+
|professional_accounting | 0|none | 5|acc |0.2340|± |0.0253|
|
| 35 |
+
|prehistory | 0|none | 5|acc |0.2315|± |0.0235|
|
| 36 |
+
|philosophy | 0|none | 5|acc |0.2154|± |0.0234|
|
| 37 |
+
|nutrition | 0|none | 5|acc |0.2516|± |0.0248|
|
| 38 |
+
|moral_scenarios | 0|none | 5|acc |0.2536|± |0.0146|
|
| 39 |
+
|moral_disputes | 0|none | 5|acc |0.1879|± |0.0210|
|
| 40 |
+
|miscellaneous | 0|none | 5|acc |0.2197|± |0.0148|
|
| 41 |
+
|medical_genetics | 0|none | 5|acc |0.1900|± |0.0394|
|
| 42 |
+
|marketing | 0|none | 5|acc |0.1923|± |0.0258|
|
| 43 |
+
|management | 0|none | 5|acc |0.3301|± |0.0466|
|
| 44 |
+
|machine_learning | 0|none | 5|acc |0.1875|± |0.0370|
|
| 45 |
+
|logical_fallacies | 0|none | 5|acc |0.2577|± |0.0344|
|
| 46 |
+
|jurisprudence | 0|none | 5|acc |0.2222|± |0.0402|
|
| 47 |
+
|international_law | 0|none | 5|acc |0.3802|± |0.0443|
|
| 48 |
+
|human_sexuality | 0|none | 5|acc |0.2137|± |0.0360|
|
| 49 |
+
|human_aging | 0|none | 5|acc |0.1121|± |0.0212|
|
| 50 |
+
|high_school_world_history | 0|none | 5|acc |0.2743|± |0.0290|
|
| 51 |
+
|high_school_us_history | 0|none | 5|acc |0.2353|± |0.0298|
|
| 52 |
+
|high_school_statistics | 0|none | 5|acc |0.4722|± |0.0340|
|
| 53 |
+
|high_school_psychology | 0|none | 5|acc |0.3358|± |0.0202|
|
| 54 |
+
|high_school_physics | 0|none | 5|acc |0.3245|± |0.0382|
|
| 55 |
+
|high_school_microeconomics | 0|none | 5|acc |0.2605|± |0.0285|
|
| 56 |
+
|high_school_mathematics | 0|none | 5|acc |0.2741|± |0.0272|
|
| 57 |
+
|high_school_macroeconomics | 0|none | 5|acc |0.3615|± |0.0244|
|
| 58 |
+
|high_school_government_and_politics| 0|none | 5|acc |0.3679|± |0.0348|
|
| 59 |
+
|high_school_geography | 0|none | 5|acc |0.3535|± |0.0341|
|
| 60 |
+
|high_school_european_history | 0|none | 5|acc |0.2485|± |0.0337|
|
| 61 |
+
|high_school_computer_science | 0|none | 5|acc |0.1600|± |0.0368|
|
| 62 |
+
|high_school_chemistry | 0|none | 5|acc |0.2709|± |0.0313|
|
| 63 |
+
|high_school_biology | 0|none | 5|acc |0.3032|± |0.0261|
|
| 64 |
+
|global_facts | 0|none | 5|acc |0.2500|± |0.0435|
|
| 65 |
+
|formal_logic | 0|none | 5|acc |0.1587|± |0.0327|
|
| 66 |
+
|elementary_mathematics | 0|none | 5|acc |0.2857|± |0.0233|
|
| 67 |
+
|electrical_engineering | 0|none | 5|acc |0.2483|± |0.0360|
|
| 68 |
+
|econometrics | 0|none | 5|acc |0.2895|± |0.0427|
|
| 69 |
+
|conceptual_physics | 0|none | 5|acc |0.2894|± |0.0296|
|
| 70 |
+
|computer_security | 0|none | 5|acc |0.1900|± |0.0394|
|
| 71 |
+
|college_physics | 0|none | 5|acc |0.2451|± |0.0428|
|
| 72 |
+
|college_medicine | 0|none | 5|acc |0.2775|± |0.0341|
|
| 73 |
+
|college_mathematics | 0|none | 5|acc |0.2800|± |0.0451|
|
| 74 |
+
|college_computer_science | 0|none | 5|acc |0.2400|± |0.0429|
|
| 75 |
+
|college_chemistry | 0|none | 5|acc |0.3300|± |0.0473|
|
| 76 |
+
|college_biology | 0|none | 5|acc |0.2639|± |0.0369|
|
| 77 |
+
|clinical_knowledge | 0|none | 5|acc |0.3094|± |0.0285|
|
| 78 |
+
|business_ethics | 0|none | 5|acc |0.1900|± |0.0394|
|
| 79 |
+
|astronomy | 0|none | 5|acc |0.2303|± |0.0343|
|
| 80 |
+
|anatomy | 0|none | 5|acc |0.3259|± |0.0405|
|
| 81 |
+
|abstract_algebra | 0|none | 5|acc |0.2700|± |0.0446|
|
| 82 |
|
| 83 |
## Model Details
|
| 84 |
|