Update README.md
Browse files
README.md
CHANGED
@@ -13,9 +13,77 @@ tags: []
|
|
13 |
|
14 |
### Model Description
|
15 |
|
16 |
-
|
17 |
-
|
18 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
- **Developed by:** [More Information Needed]
|
21 |
- **Funded by [optional]:** [More Information Needed]
|
|
|
13 |
|
14 |
### Model Description
|
15 |
|
16 |
+
| Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
|
17 |
+
|-------------|------:|------|-----:|--------|-----:|---|-----:|
|
18 |
+
|arc_challenge| 1|none | 25|acc |0.1775|± |0.0112|
|
19 |
+
| | |none | 25|acc_norm|0.2065|± |0.0118|
|
20 |
+
|truthfulqa_mc2| 2|none | 0|acc |0.4633|± |0.0155|
|
21 |
+
|winogrande| 1|none | 5|acc |0.5075|± |0.0141|
|
22 |
+
|hellaswag| 1|none | 10|acc |0.2685|± |0.0044|
|
23 |
+
| | |none | 10|acc_norm|0.2746|± |0.0045|
|
24 |
+
|gsm8k| 3|strict-match | 5|exact_match|0.0023|± |0.0013|
|
25 |
+
| | |flexible-extract| 5|exact_match|0.0152|± |0.0034|
|
26 |
+
|
27 |
+
(0.26113333333333333, 0.004443523026985591)
|
28 |
+
| Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
|
29 |
+
|-----------------------------------|------:|------|-----:|------|-----:|---|-----:|
|
30 |
+
|world_religions | 0|none | 5|acc |0.2047|± |0.0309|
|
31 |
+
|virology | 0|none | 5|acc |0.1807|± |0.0300|
|
32 |
+
|us_foreign_policy | 0|none | 5|acc |0.2700|± |0.0446|
|
33 |
+
|sociology | 0|none | 5|acc |0.2488|± |0.0306|
|
34 |
+
|security_studies | 0|none | 5|acc |0.3347|± |0.0302|
|
35 |
+
|public_relations | 0|none | 5|acc |0.2273|± |0.0401|
|
36 |
+
|professional_psychology | 0|none | 5|acc |0.2042|± |0.0163|
|
37 |
+
|professional_medicine | 0|none | 5|acc |0.4485|± |0.0302|
|
38 |
+
|professional_law | 0|none | 5|acc |0.2458|± |0.0110|
|
39 |
+
|professional_accounting | 0|none | 5|acc |0.2163|± |0.0246|
|
40 |
+
|prehistory | 0|none | 5|acc |0.2222|± |0.0231|
|
41 |
+
|philosophy | 0|none | 5|acc |0.2379|± |0.0242|
|
42 |
+
|nutrition | 0|none | 5|acc |0.2810|± |0.0257|
|
43 |
+
|moral_scenarios | 0|none | 5|acc |0.2659|± |0.0148|
|
44 |
+
|moral_disputes | 0|none | 5|acc |0.2428|± |0.0231|
|
45 |
+
|miscellaneous | 0|none | 5|acc |0.2375|± |0.0152|
|
46 |
+
|medical_genetics | 0|none | 5|acc |0.3000|± |0.0461|
|
47 |
+
|marketing | 0|none | 5|acc |0.1966|± |0.0260|
|
48 |
+
|management | 0|none | 5|acc |0.1553|± |0.0359|
|
49 |
+
|machine_learning | 0|none | 5|acc |0.3304|± |0.0446|
|
50 |
+
|logical_fallacies | 0|none | 5|acc |0.2331|± |0.0332|
|
51 |
+
|jurisprudence | 0|none | 5|acc |0.2407|± |0.0413|
|
52 |
+
|international_law | 0|none | 5|acc |0.3306|± |0.0429|
|
53 |
+
|human_sexuality | 0|none | 5|acc |0.2595|± |0.0384|
|
54 |
+
|human_aging | 0|none | 5|acc |0.2063|± |0.0272|
|
55 |
+
|high_school_world_history | 0|none | 5|acc |0.2658|± |0.0288|
|
56 |
+
|high_school_us_history | 0|none | 5|acc |0.2745|± |0.0313|
|
57 |
+
|high_school_statistics | 0|none | 5|acc |0.4722|± |0.0340|
|
58 |
+
|high_school_psychology | 0|none | 5|acc |0.2330|± |0.0181|
|
59 |
+
|high_school_physics | 0|none | 5|acc |0.3311|± |0.0384|
|
60 |
+
|high_school_microeconomics | 0|none | 5|acc |0.3403|± |0.0308|
|
61 |
+
|high_school_mathematics | 0|none | 5|acc |0.2630|± |0.0268|
|
62 |
+
|high_school_macroeconomics | 0|none | 5|acc |0.3205|± |0.0237|
|
63 |
+
|high_school_government_and_politics| 0|none | 5|acc |0.3679|± |0.0348|
|
64 |
+
|high_school_geography | 0|none | 5|acc |0.3283|± |0.0335|
|
65 |
+
|high_school_european_history | 0|none | 5|acc |0.2606|± |0.0343|
|
66 |
+
|high_school_computer_science | 0|none | 5|acc |0.2800|± |0.0451|
|
67 |
+
|high_school_chemistry | 0|none | 5|acc |0.2956|± |0.0321|
|
68 |
+
|high_school_biology | 0|none | 5|acc |0.3194|± |0.0265|
|
69 |
+
|global_facts | 0|none | 5|acc |0.1600|± |0.0368|
|
70 |
+
|formal_logic | 0|none | 5|acc |0.1825|± |0.0346|
|
71 |
+
|elementary_mathematics | 0|none | 5|acc |0.2487|± |0.0223|
|
72 |
+
|electrical_engineering | 0|none | 5|acc |0.2966|± |0.0381|
|
73 |
+
|econometrics | 0|none | 5|acc |0.2632|± |0.0414|
|
74 |
+
|conceptual_physics | 0|none | 5|acc |0.2553|± |0.0285|
|
75 |
+
|computer_security | 0|none | 5|acc |0.1800|± |0.0386|
|
76 |
+
|college_physics | 0|none | 5|acc |0.2451|± |0.0428|
|
77 |
+
|college_medicine | 0|none | 5|acc |0.2312|± |0.0321|
|
78 |
+
|college_mathematics | 0|none | 5|acc |0.3200|± |0.0469|
|
79 |
+
|college_computer_science | 0|none | 5|acc |0.3000|± |0.0461|
|
80 |
+
|college_chemistry | 0|none | 5|acc |0.1800|± |0.0386|
|
81 |
+
|college_biology | 0|none | 5|acc |0.2778|± |0.0375|
|
82 |
+
|clinical_knowledge | 0|none | 5|acc |0.2340|± |0.0261|
|
83 |
+
|business_ethics | 0|none | 5|acc |0.2100|± |0.0409|
|
84 |
+
|astronomy | 0|none | 5|acc |0.1776|± |0.0311|
|
85 |
+
|anatomy | 0|none | 5|acc |0.2296|± |0.0363|
|
86 |
+
|abstract_algebra | 0|none | 5|acc |0.2200|± |0.0416|
|
87 |
|
88 |
- **Developed by:** [More Information Needed]
|
89 |
- **Funded by [optional]:** [More Information Needed]
|