Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,70 @@ damn it
|
|
| 16 |
|winogrande| 1|none | 5|acc |0.502|± |0.0141|
|
| 17 |
|hellaswag| 1|none | 10|acc |0.2726|± |0.0044|
|
| 18 |
| | |none | 10|acc_norm|0.2797|± |0.0045|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model Details
|
| 21 |
|
|
|
|
| 16 |
|winogrande| 1|none | 5|acc |0.502|± |0.0141|
|
| 17 |
|hellaswag| 1|none | 10|acc |0.2726|± |0.0044|
|
| 18 |
| | |none | 10|acc_norm|0.2797|± |0.0045|
|
| 19 |
+
|gsm8k| 3|strict-match | 5|exact_match|0.0091|± |0.0026|
|
| 20 |
+
| | |flexible-extract| 5|exact_match|0.0152|± |0.0034|
|
| 21 |
+
|
| 22 |
+
### MMLU *(0.26217543859649123, 0.004475258065090056)*
|
| 23 |
+
|
| 24 |
+
| Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
|
| 25 |
+
|-----------------------------------|------:|------|-----:|------|-----:|---|-----:|
|
| 26 |
+
|world_religions | 0|none | 5|acc |0.2164|± |0.0316|
|
| 27 |
+
|virology | 0|none | 5|acc |0.1988|± |0.0311|
|
| 28 |
+
|us_foreign_policy | 0|none | 5|acc |0.3200|± |0.0469|
|
| 29 |
+
|sociology | 0|none | 5|acc |0.2338|± |0.0299|
|
| 30 |
+
|security_studies | 0|none | 5|acc |0.2367|± |0.0272|
|
| 31 |
+
|public_relations | 0|none | 5|acc |0.2455|± |0.0412|
|
| 32 |
+
|professional_psychology | 0|none | 5|acc |0.2467|± |0.0174|
|
| 33 |
+
|professional_medicine | 0|none | 5|acc |0.4412|± |0.0302|
|
| 34 |
+
|professional_law | 0|none | 5|acc |0.2666|± |0.0113|
|
| 35 |
+
|professional_accounting | 0|none | 5|acc |0.2553|± |0.0260|
|
| 36 |
+
|prehistory | 0|none | 5|acc |0.2870|± |0.0252|
|
| 37 |
+
|philosophy | 0|none | 5|acc |0.3023|± |0.0261|
|
| 38 |
+
|nutrition | 0|none | 5|acc |0.2157|± |0.0236|
|
| 39 |
+
|moral_scenarios | 0|none | 5|acc |0.2469|± |0.0144|
|
| 40 |
+
|moral_disputes | 0|none | 5|acc |0.2168|± |0.0222|
|
| 41 |
+
|miscellaneous | 0|none | 5|acc |0.2720|± |0.0159|
|
| 42 |
+
|medical_genetics | 0|none | 5|acc |0.3000|± |0.0461|
|
| 43 |
+
|marketing | 0|none | 5|acc |0.1966|± |0.0260|
|
| 44 |
+
|management | 0|none | 5|acc |0.1942|± |0.0392|
|
| 45 |
+
|machine_learning | 0|none | 5|acc |0.2411|± |0.0406|
|
| 46 |
+
|logical_fallacies | 0|none | 5|acc |0.2331|± |0.0332|
|
| 47 |
+
|jurisprudence | 0|none | 5|acc |0.2130|± |0.0396|
|
| 48 |
+
|international_law | 0|none | 5|acc |0.3554|± |0.0437|
|
| 49 |
+
|human_sexuality | 0|none | 5|acc |0.2824|± |0.0395|
|
| 50 |
+
|human_aging | 0|none | 5|acc |0.3139|± |0.0311|
|
| 51 |
+
|high_school_world_history | 0|none | 5|acc |0.2489|± |0.0281|
|
| 52 |
+
|high_school_us_history | 0|none | 5|acc |0.2157|± |0.0289|
|
| 53 |
+
|high_school_statistics | 0|none | 5|acc |0.4722|± |0.0340|
|
| 54 |
+
|high_school_psychology | 0|none | 5|acc |0.2055|± |0.0173|
|
| 55 |
+
|high_school_physics | 0|none | 5|acc |0.3113|± |0.0378|
|
| 56 |
+
|high_school_microeconomics | 0|none | 5|acc |0.2857|± |0.0293|
|
| 57 |
+
|high_school_mathematics | 0|none | 5|acc |0.2667|± |0.0270|
|
| 58 |
+
|high_school_macroeconomics | 0|none | 5|acc |0.2179|± |0.0209|
|
| 59 |
+
|high_school_government_and_politics| 0|none | 5|acc |0.2539|± |0.0314|
|
| 60 |
+
|high_school_geography | 0|none | 5|acc |0.2475|± |0.0307|
|
| 61 |
+
|high_school_european_history | 0|none | 5|acc |0.2606|± |0.0343|
|
| 62 |
+
|high_school_computer_science | 0|none | 5|acc |0.2000|± |0.0402|
|
| 63 |
+
|high_school_chemistry | 0|none | 5|acc |0.2857|± |0.0318|
|
| 64 |
+
|high_school_biology | 0|none | 5|acc |0.3161|± |0.0265|
|
| 65 |
+
|global_facts | 0|none | 5|acc |0.3100|± |0.0465|
|
| 66 |
+
|formal_logic | 0|none | 5|acc |0.1508|± |0.0320|
|
| 67 |
+
|elementary_mathematics | 0|none | 5|acc |0.2566|± |0.0225|
|
| 68 |
+
|electrical_engineering | 0|none | 5|acc |0.2414|± |0.0357|
|
| 69 |
+
|econometrics | 0|none | 5|acc |0.2456|± |0.0405|
|
| 70 |
+
|conceptual_physics | 0|none | 5|acc |0.2979|± |0.0299|
|
| 71 |
+
|computer_security | 0|none | 5|acc |0.1600|± |0.0368|
|
| 72 |
+
|college_physics | 0|none | 5|acc |0.3039|± |0.0458|
|
| 73 |
+
|college_medicine | 0|none | 5|acc |0.2254|± |0.0319|
|
| 74 |
+
|college_mathematics | 0|none | 5|acc |0.2300|± |0.0423|
|
| 75 |
+
|college_computer_science | 0|none | 5|acc |0.3300|± |0.0473|
|
| 76 |
+
|college_chemistry | 0|none | 5|acc |0.4200|± |0.0496|
|
| 77 |
+
|college_biology | 0|none | 5|acc |0.2500|± |0.0362|
|
| 78 |
+
|clinical_knowledge | 0|none | 5|acc |0.2189|± |0.0254|
|
| 79 |
+
|business_ethics | 0|none | 5|acc |0.2100|± |0.0409|
|
| 80 |
+
|astronomy | 0|none | 5|acc |0.1711|± |0.0306|
|
| 81 |
+
|anatomy | 0|none | 5|acc |0.3333|± |0.0407|
|
| 82 |
+
|abstract_algebra | 0|none | 5|acc |0.2700|± |0.0446|
|
| 83 |
|
| 84 |
## Model Details
|
| 85 |
|