Update README.md
Browse files
README.md
CHANGED
|
@@ -11,9 +11,72 @@ tags: []
|
|
| 11 |
| | |none | 25|acc_norm|0.2389|± |0.0125|
|
| 12 |
|truthfulqa_mc2| 2|none | 0|acc |0.4297|± |0.0152|
|
| 13 |
|winogrande| 1|none | 5|acc |0.5217|± | 0.014|
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
## Model Details
|
| 18 |
|
| 19 |
### Model Description
|
|
|
|
| 11 |
| | |none | 25|acc_norm|0.2389|± |0.0125|
|
| 12 |
|truthfulqa_mc2| 2|none | 0|acc |0.4297|± |0.0152|
|
| 13 |
|winogrande| 1|none | 5|acc |0.5217|± | 0.014|
|
| 14 |
+
|hellaswag| 1|none | 10|acc |0.2923|± |0.0045|
|
| 15 |
+
| | |none | 10|acc_norm|0.3198|± |0.0047|
|
| 16 |
+
|gsm8k| 3|strict-match | 5|exact_match|0.0068|± |0.0023|
|
| 17 |
+
| | |flexible-extract| 5|exact_match|0.0167|± |0.0035|
|
| 18 |
+
|
| 19 |
+
### MMLU *(0.26727368421052633, 0.004481878288705264)*
|
| 20 |
+
|
| 21 |
+
| Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
|
| 22 |
+
|-----------------------------------|------:|------|-----:|------|-----:|---|-----:|
|
| 23 |
+
|world_religions | 0|none | 5|acc |0.2515|± |0.0333|
|
| 24 |
+
|virology | 0|none | 5|acc |0.2470|± |0.0336|
|
| 25 |
+
|us_foreign_policy | 0|none | 5|acc |0.2600|± |0.0441|
|
| 26 |
+
|sociology | 0|none | 5|acc |0.2090|± |0.0287|
|
| 27 |
+
|security_studies | 0|none | 5|acc |0.4041|± |0.0314|
|
| 28 |
+
|public_relations | 0|none | 5|acc |0.2182|± |0.0396|
|
| 29 |
+
|professional_psychology | 0|none | 5|acc |0.2386|± |0.0172|
|
| 30 |
+
|professional_medicine | 0|none | 5|acc |0.4338|± |0.0301|
|
| 31 |
+
|professional_law | 0|none | 5|acc |0.2464|± |0.0110|
|
| 32 |
+
|professional_accounting | 0|none | 5|acc |0.2482|± |0.0258|
|
| 33 |
+
|prehistory | 0|none | 5|acc |0.2284|± |0.0234|
|
| 34 |
+
|philosophy | 0|none | 5|acc |0.2733|± |0.0253|
|
| 35 |
+
|nutrition | 0|none | 5|acc |0.2810|± |0.0257|
|
| 36 |
+
|moral_scenarios | 0|none | 5|acc |0.2268|± |0.0140|
|
| 37 |
+
|moral_disputes | 0|none | 5|acc |0.2572|± |0.0235|
|
| 38 |
+
|miscellaneous | 0|none | 5|acc |0.2146|± |0.0147|
|
| 39 |
+
|medical_genetics | 0|none | 5|acc |0.3300|± |0.0473|
|
| 40 |
+
|marketing | 0|none | 5|acc |0.1880|± |0.0256|
|
| 41 |
+
|management | 0|none | 5|acc |0.3107|± |0.0458|
|
| 42 |
+
|machine_learning | 0|none | 5|acc |0.1339|± |0.0323|
|
| 43 |
+
|logical_fallacies | 0|none | 5|acc |0.2638|± |0.0346|
|
| 44 |
+
|jurisprudence | 0|none | 5|acc |0.2315|± |0.0408|
|
| 45 |
+
|international_law | 0|none | 5|acc |0.3636|± |0.0439|
|
| 46 |
+
|human_sexuality | 0|none | 5|acc |0.2290|± |0.0369|
|
| 47 |
+
|human_aging | 0|none | 5|acc |0.2242|± |0.0280|
|
| 48 |
+
|high_school_world_history | 0|none | 5|acc |0.2700|± |0.0289|
|
| 49 |
+
|high_school_us_history | 0|none | 5|acc |0.3039|± |0.0323|
|
| 50 |
+
|high_school_statistics | 0|none | 5|acc |0.4259|± |0.0337|
|
| 51 |
+
|high_school_psychology | 0|none | 5|acc |0.3138|± |0.0199|
|
| 52 |
+
|high_school_physics | 0|none | 5|acc |0.2384|± |0.0348|
|
| 53 |
+
|high_school_microeconomics | 0|none | 5|acc |0.2395|± |0.0277|
|
| 54 |
+
|high_school_mathematics | 0|none | 5|acc |0.2963|± |0.0278|
|
| 55 |
+
|high_school_macroeconomics | 0|none | 5|acc |0.3410|± |0.0240|
|
| 56 |
+
|high_school_government_and_politics| 0|none | 5|acc |0.3627|± |0.0347|
|
| 57 |
+
|high_school_geography | 0|none | 5|acc |0.3131|± |0.0330|
|
| 58 |
+
|high_school_european_history | 0|none | 5|acc |0.2848|± |0.0352|
|
| 59 |
+
|high_school_computer_science | 0|none | 5|acc |0.2400|± |0.0429|
|
| 60 |
+
|high_school_chemistry | 0|none | 5|acc |0.2611|± |0.0309|
|
| 61 |
+
|high_school_biology | 0|none | 5|acc |0.3097|± |0.0263|
|
| 62 |
+
|global_facts | 0|none | 5|acc |0.2800|± |0.0451|
|
| 63 |
+
|formal_logic | 0|none | 5|acc |0.1825|± |0.0346|
|
| 64 |
+
|elementary_mathematics | 0|none | 5|acc |0.2646|± |0.0227|
|
| 65 |
+
|electrical_engineering | 0|none | 5|acc |0.2690|± |0.0370|
|
| 66 |
+
|econometrics | 0|none | 5|acc |0.2368|± |0.0400|
|
| 67 |
+
|conceptual_physics | 0|none | 5|acc |0.2979|± |0.0299|
|
| 68 |
+
|computer_security | 0|none | 5|acc |0.1900|± |0.0394|
|
| 69 |
+
|college_physics | 0|none | 5|acc |0.2549|± |0.0434|
|
| 70 |
+
|college_medicine | 0|none | 5|acc |0.2197|± |0.0316|
|
| 71 |
+
|college_mathematics | 0|none | 5|acc |0.2700|± |0.0446|
|
| 72 |
+
|college_computer_science | 0|none | 5|acc |0.2200|± |0.0416|
|
| 73 |
+
|college_chemistry | 0|none | 5|acc |0.3000|± |0.0461|
|
| 74 |
+
|college_biology | 0|none | 5|acc |0.2778|± |0.0375|
|
| 75 |
+
|clinical_knowledge | 0|none | 5|acc |0.3094|± |0.0285|
|
| 76 |
+
|business_ethics | 0|none | 5|acc |0.1800|± |0.0386|
|
| 77 |
+
|astronomy | 0|none | 5|acc |0.2697|± |0.0361|
|
| 78 |
+
|anatomy | 0|none | 5|acc |0.2593|± |0.0379|
|
| 79 |
+
|abstract_algebra | 0|none | 5|acc |0.2400|± |0.0429|
|
| 80 |
## Model Details
|
| 81 |
|
| 82 |
### Model Description
|