Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,69 @@ tags: []
|
|
| 14 |
|winogrande| 1|none | 5|acc |0.5107|± | 0.014|
|
| 15 |
|hellaswag| 1|none | 10|acc |0.2753|± |0.0045|
|
| 16 |
| | |none | 10|acc_norm|0.2857|± |0.0045|
|
| 17 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model Details
|
| 20 |
|
|
|
|
| 14 |
|winogrande| 1|none | 5|acc |0.5107|± | 0.014|
|
| 15 |
|hellaswag| 1|none | 10|acc |0.2753|± |0.0045|
|
| 16 |
| | |none | 10|acc_norm|0.2857|± |0.0045|
|
| 17 |
+
|gsm8k| 3|strict-match | 5|exact_match|0.0061|± |0.0021|
|
| 18 |
+
| | |flexible-extract| 5|exact_match|0.0129|± |0.0031|
|
| 19 |
+
|
| 20 |
+
### MMLU *(0.2534122807017544, 0.004405796567928279)*
|
| 21 |
+
| Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
|
| 22 |
+
|-----------------------------------|------:|------|-----:|------|-----:|---|-----:|
|
| 23 |
+
|world_religions | 0|none | 5|acc |0.2222|± |0.0319|
|
| 24 |
+
|virology | 0|none | 5|acc |0.1988|± |0.0311|
|
| 25 |
+
|us_foreign_policy | 0|none | 5|acc |0.2300|± |0.0423|
|
| 26 |
+
|sociology | 0|none | 5|acc |0.2338|± |0.0299|
|
| 27 |
+
|security_studies | 0|none | 5|acc |0.3673|± |0.0309|
|
| 28 |
+
|public_relations | 0|none | 5|acc |0.2273|± |0.0401|
|
| 29 |
+
|professional_psychology | 0|none | 5|acc |0.2402|± |0.0173|
|
| 30 |
+
|professional_medicine | 0|none | 5|acc |0.4265|± |0.0300|
|
| 31 |
+
|professional_law | 0|none | 5|acc |0.2419|± |0.0109|
|
| 32 |
+
|professional_accounting | 0|none | 5|acc |0.2589|± |0.0261|
|
| 33 |
+
|prehistory | 0|none | 5|acc |0.2716|± |0.0247|
|
| 34 |
+
|philosophy | 0|none | 5|acc |0.2412|± |0.0243|
|
| 35 |
+
|nutrition | 0|none | 5|acc |0.2516|± |0.0248|
|
| 36 |
+
|moral_scenarios | 0|none | 5|acc |0.2514|± |0.0145|
|
| 37 |
+
|moral_disputes | 0|none | 5|acc |0.2139|± |0.0221|
|
| 38 |
+
|miscellaneous | 0|none | 5|acc |0.2644|± |0.0158|
|
| 39 |
+
|medical_genetics | 0|none | 5|acc |0.3000|± |0.0461|
|
| 40 |
+
|marketing | 0|none | 5|acc |0.1923|± |0.0258|
|
| 41 |
+
|management | 0|none | 5|acc |0.1942|± |0.0392|
|
| 42 |
+
|machine_learning | 0|none | 5|acc |0.2500|± |0.0411|
|
| 43 |
+
|logical_fallacies | 0|none | 5|acc |0.2638|± |0.0346|
|
| 44 |
+
|jurisprudence | 0|none | 5|acc |0.1759|± |0.0368|
|
| 45 |
+
|international_law | 0|none | 5|acc |0.3554|± |0.0437|
|
| 46 |
+
|human_sexuality | 0|none | 5|acc |0.2443|± |0.0377|
|
| 47 |
+
|human_aging | 0|none | 5|acc |0.1928|± |0.0265|
|
| 48 |
+
|high_school_world_history | 0|none | 5|acc |0.2700|± |0.0289|
|
| 49 |
+
|high_school_us_history | 0|none | 5|acc |0.2990|± |0.0321|
|
| 50 |
+
|high_school_statistics | 0|none | 5|acc |0.4074|± |0.0335|
|
| 51 |
+
|high_school_psychology | 0|none | 5|acc |0.2422|± |0.0184|
|
| 52 |
+
|high_school_physics | 0|none | 5|acc |0.2053|± |0.0330|
|
| 53 |
+
|high_school_microeconomics | 0|none | 5|acc |0.2479|± |0.0280|
|
| 54 |
+
|high_school_mathematics | 0|none | 5|acc |0.2815|± |0.0274|
|
| 55 |
+
|high_school_macroeconomics | 0|none | 5|acc |0.2128|± |0.0208|
|
| 56 |
+
|high_school_government_and_politics| 0|none | 5|acc |0.2435|± |0.0310|
|
| 57 |
+
|high_school_geography | 0|none | 5|acc |0.3232|± |0.0333|
|
| 58 |
+
|high_school_european_history | 0|none | 5|acc |0.2848|± |0.0352|
|
| 59 |
+
|high_school_computer_science | 0|none | 5|acc |0.2800|± |0.0451|
|
| 60 |
+
|high_school_chemistry | 0|none | 5|acc |0.2906|± |0.0319|
|
| 61 |
+
|high_school_biology | 0|none | 5|acc |0.3032|± |0.0261|
|
| 62 |
+
|global_facts | 0|none | 5|acc |0.1600|± |0.0368|
|
| 63 |
+
|formal_logic | 0|none | 5|acc |0.1429|± |0.0313|
|
| 64 |
+
|elementary_mathematics | 0|none | 5|acc |0.2434|± |0.0221|
|
| 65 |
+
|electrical_engineering | 0|none | 5|acc |0.2483|± |0.0360|
|
| 66 |
+
|econometrics | 0|none | 5|acc |0.2544|± |0.0410|
|
| 67 |
+
|conceptual_physics | 0|none | 5|acc |0.3064|± |0.0301|
|
| 68 |
+
|computer_security | 0|none | 5|acc |0.1700|± |0.0378|
|
| 69 |
+
|college_physics | 0|none | 5|acc |0.2745|± |0.0444|
|
| 70 |
+
|college_medicine | 0|none | 5|acc |0.2601|± |0.0335|
|
| 71 |
+
|college_mathematics | 0|none | 5|acc |0.2500|± |0.0435|
|
| 72 |
+
|college_computer_science | 0|none | 5|acc |0.2900|± |0.0456|
|
| 73 |
+
|college_chemistry | 0|none | 5|acc |0.2400|± |0.0429|
|
| 74 |
+
|college_biology | 0|none | 5|acc |0.2500|± |0.0362|
|
| 75 |
+
|clinical_knowledge | 0|none | 5|acc |0.2075|± |0.0250|
|
| 76 |
+
|business_ethics | 0|none | 5|acc |0.2000|± |0.0402|
|
| 77 |
+
|astronomy | 0|none | 5|acc |0.1974|± |0.0324|
|
| 78 |
+
|anatomy | 0|none | 5|acc |0.3185|± |0.0402|
|
| 79 |
+
|abstract_algebra | 0|none | 5|acc |0.2300|± |0.0423|
|
| 80 |
|
| 81 |
## Model Details
|
| 82 |
|