Update README.md
Browse files
README.md
CHANGED
@@ -14,4 +14,123 @@ language:
|
|
14 |
| Task |Version| Metric |Value | |Stderr|
|
15 |
|---------|------:|--------|-----:|---|-----:|
|
16 |
|hellaswag| 0|acc |0.2698|± |0.0044|
|
17 |
-
| | |acc_norm|**0.2735**|± |0.0044|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
| Task |Version| Metric |Value | |Stderr|
|
15 |
|---------|------:|--------|-----:|---|-----:|
|
16 |
|hellaswag| 0|acc |0.2698|± |0.0044|
|
17 |
+
| | |acc_norm|**0.2735**|± |0.0044|
|
18 |
+
|
19 |
+
| Task |Version| Metric |Value | |Stderr|
|
20 |
+
|-------------------------------------------------|------:|--------|-----:|---|-----:|
|
21 |
+
|hendrycksTest-abstract_algebra | 1|acc |0.2200|± |0.0416|
|
22 |
+
| | |acc_norm|0.2200|± |0.0416|
|
23 |
+
|hendrycksTest-anatomy | 1|acc |0.3333|± |0.0407|
|
24 |
+
| | |acc_norm|0.3333|± |0.0407|
|
25 |
+
|hendrycksTest-astronomy | 1|acc |0.2237|± |0.0339|
|
26 |
+
| | |acc_norm|0.2237|± |0.0339|
|
27 |
+
|hendrycksTest-business_ethics | 1|acc |0.2000|± |0.0402|
|
28 |
+
| | |acc_norm|0.2000|± |0.0402|
|
29 |
+
|hendrycksTest-clinical_knowledge | 1|acc |0.2189|± |0.0254|
|
30 |
+
| | |acc_norm|0.2189|± |0.0254|
|
31 |
+
|hendrycksTest-college_biology | 1|acc |0.2083|± |0.0340|
|
32 |
+
| | |acc_norm|0.2083|± |0.0340|
|
33 |
+
|hendrycksTest-college_chemistry | 1|acc |0.3400|± |0.0476|
|
34 |
+
| | |acc_norm|0.3400|± |0.0476|
|
35 |
+
|hendrycksTest-college_computer_science | 1|acc |0.3100|± |0.0465|
|
36 |
+
| | |acc_norm|0.3100|± |0.0465|
|
37 |
+
|hendrycksTest-college_mathematics | 1|acc |0.3100|± |0.0465|
|
38 |
+
| | |acc_norm|0.3100|± |0.0465|
|
39 |
+
|hendrycksTest-college_medicine | 1|acc |0.2197|± |0.0316|
|
40 |
+
| | |acc_norm|0.2197|± |0.0316|
|
41 |
+
|hendrycksTest-college_physics | 1|acc |0.3431|± |0.0472|
|
42 |
+
| | |acc_norm|0.3431|± |0.0472|
|
43 |
+
|hendrycksTest-computer_security | 1|acc |0.2000|± |0.0402|
|
44 |
+
| | |acc_norm|0.2000|± |0.0402|
|
45 |
+
|hendrycksTest-conceptual_physics | 1|acc |0.2809|± |0.0294|
|
46 |
+
| | |acc_norm|0.2809|± |0.0294|
|
47 |
+
|hendrycksTest-econometrics | 1|acc |0.2544|± |0.0410|
|
48 |
+
| | |acc_norm|0.2544|± |0.0410|
|
49 |
+
|hendrycksTest-electrical_engineering | 1|acc |0.2414|± |0.0357|
|
50 |
+
| | |acc_norm|0.2414|± |0.0357|
|
51 |
+
|hendrycksTest-elementary_mathematics | 1|acc |0.2566|± |0.0225|
|
52 |
+
| | |acc_norm|0.2566|± |0.0225|
|
53 |
+
|hendrycksTest-formal_logic | 1|acc |0.1825|± |0.0346|
|
54 |
+
| | |acc_norm|0.1825|± |0.0346|
|
55 |
+
|hendrycksTest-global_facts | 1|acc |0.2000|± |0.0402|
|
56 |
+
| | |acc_norm|0.2000|± |0.0402|
|
57 |
+
|hendrycksTest-high_school_biology | 1|acc |0.3161|± |0.0265|
|
58 |
+
| | |acc_norm|0.3161|± |0.0265|
|
59 |
+
|hendrycksTest-high_school_chemistry | 1|acc |0.2759|± |0.0314|
|
60 |
+
| | |acc_norm|0.2759|± |0.0314|
|
61 |
+
|hendrycksTest-high_school_computer_science | 1|acc |0.2400|± |0.0429|
|
62 |
+
| | |acc_norm|0.2400|± |0.0429|
|
63 |
+
|hendrycksTest-high_school_european_history | 1|acc |0.2909|± |0.0355|
|
64 |
+
| | |acc_norm|0.2909|± |0.0355|
|
65 |
+
|hendrycksTest-high_school_geography | 1|acc |0.3535|± |0.0341|
|
66 |
+
| | |acc_norm|0.3535|± |0.0341|
|
67 |
+
|hendrycksTest-high_school_government_and_politics| 1|acc |0.2280|± |0.0303|
|
68 |
+
| | |acc_norm|0.2280|± |0.0303|
|
69 |
+
|hendrycksTest-high_school_macroeconomics | 1|acc |0.2051|± |0.0205|
|
70 |
+
| | |acc_norm|0.2051|± |0.0205|
|
71 |
+
|hendrycksTest-high_school_mathematics | 1|acc |0.2630|± |0.0268|
|
72 |
+
| | |acc_norm|0.2630|± |0.0268|
|
73 |
+
|hendrycksTest-high_school_microeconomics | 1|acc |0.3403|± |0.0308|
|
74 |
+
| | |acc_norm|0.3403|± |0.0308|
|
75 |
+
|hendrycksTest-high_school_physics | 1|acc |0.2384|± |0.0348|
|
76 |
+
| | |acc_norm|0.2384|± |0.0348|
|
77 |
+
|hendrycksTest-high_school_psychology | 1|acc |0.2257|± |0.0179|
|
78 |
+
| | |acc_norm|0.2257|± |0.0179|
|
79 |
+
|hendrycksTest-high_school_statistics | 1|acc |0.4722|± |0.0340|
|
80 |
+
| | |acc_norm|0.4722|± |0.0340|
|
81 |
+
|hendrycksTest-high_school_us_history | 1|acc |0.2206|± |0.0291|
|
82 |
+
| | |acc_norm|0.2206|± |0.0291|
|
83 |
+
|hendrycksTest-high_school_world_history | 1|acc |0.2658|± |0.0288|
|
84 |
+
| | |acc_norm|0.2658|± |0.0288|
|
85 |
+
|hendrycksTest-human_aging | 1|acc |0.2063|± |0.0272|
|
86 |
+
| | |acc_norm|0.2063|± |0.0272|
|
87 |
+
|hendrycksTest-human_sexuality | 1|acc |0.2366|± |0.0373|
|
88 |
+
| | |acc_norm|0.2366|± |0.0373|
|
89 |
+
|hendrycksTest-international_law | 1|acc |0.2562|± |0.0398|
|
90 |
+
| | |acc_norm|0.2562|± |0.0398|
|
91 |
+
|hendrycksTest-jurisprudence | 1|acc |0.2130|± |0.0396|
|
92 |
+
| | |acc_norm|0.2130|± |0.0396|
|
93 |
+
|hendrycksTest-logical_fallacies | 1|acc |0.2393|± |0.0335|
|
94 |
+
| | |acc_norm|0.2393|± |0.0335|
|
95 |
+
|hendrycksTest-machine_learning | 1|acc |0.2054|± |0.0383|
|
96 |
+
| | |acc_norm|0.2054|± |0.0383|
|
97 |
+
|hendrycksTest-management | 1|acc |0.1942|± |0.0392|
|
98 |
+
| | |acc_norm|0.1942|± |0.0392|
|
99 |
+
|hendrycksTest-marketing | 1|acc |0.1923|± |0.0258|
|
100 |
+
| | |acc_norm|0.1923|± |0.0258|
|
101 |
+
|hendrycksTest-medical_genetics | 1|acc |0.3000|± |0.0461|
|
102 |
+
| | |acc_norm|0.3000|± |0.0461|
|
103 |
+
|hendrycksTest-miscellaneous | 1|acc |0.2708|± |0.0159|
|
104 |
+
| | |acc_norm|0.2708|± |0.0159|
|
105 |
+
|hendrycksTest-moral_disputes | 1|acc |0.2168|± |0.0222|
|
106 |
+
| | |acc_norm|0.2168|± |0.0222|
|
107 |
+
|hendrycksTest-moral_scenarios | 1|acc |0.2313|± |0.0141|
|
108 |
+
| | |acc_norm|0.2313|± |0.0141|
|
109 |
+
|hendrycksTest-nutrition | 1|acc |0.2222|± |0.0238|
|
110 |
+
| | |acc_norm|0.2222|± |0.0238|
|
111 |
+
|hendrycksTest-philosophy | 1|acc |0.2315|± |0.0240|
|
112 |
+
| | |acc_norm|0.2315|± |0.0240|
|
113 |
+
|hendrycksTest-prehistory | 1|acc |0.2963|± |0.0254|
|
114 |
+
| | |acc_norm|0.2963|± |0.0254|
|
115 |
+
|hendrycksTest-professional_accounting | 1|acc |0.2589|± |0.0261|
|
116 |
+
| | |acc_norm|0.2589|± |0.0261|
|
117 |
+
|hendrycksTest-professional_law | 1|acc |0.2490|± |0.0110|
|
118 |
+
| | |acc_norm|0.2490|± |0.0110|
|
119 |
+
|hendrycksTest-professional_medicine | 1|acc |0.4375|± |0.0301|
|
120 |
+
| | |acc_norm|0.4375|± |0.0301|
|
121 |
+
|hendrycksTest-professional_psychology | 1|acc |0.2271|± |0.0169|
|
122 |
+
| | |acc_norm|0.2271|± |0.0169|
|
123 |
+
|hendrycksTest-public_relations | 1|acc |0.2455|± |0.0412|
|
124 |
+
| | |acc_norm|0.2455|± |0.0412|
|
125 |
+
|hendrycksTest-security_studies | 1|acc |0.2367|± |0.0272|
|
126 |
+
| | |acc_norm|0.2367|± |0.0272|
|
127 |
+
|hendrycksTest-sociology | 1|acc |0.2438|± |0.0304|
|
128 |
+
| | |acc_norm|0.2438|± |0.0304|
|
129 |
+
|hendrycksTest-us_foreign_policy | 1|acc |0.2900|± |0.0456|
|
130 |
+
| | |acc_norm|0.2900|± |0.0456|
|
131 |
+
|hendrycksTest-virology | 1|acc |0.1928|± |0.0307|
|
132 |
+
| | |acc_norm|0.1928|± |0.0307|
|
133 |
+
|hendrycksTest-world_religions | 1|acc |0.1813|± |0.0295|
|
134 |
+
| | |acc_norm|0.1813|± |0.0295|
|
135 |
+
|
136 |
+
average is 0.2553175438596491 ??
|