oneonlee commited on
Commit
06f17be
·
verified ·
1 Parent(s): 3fff8ac

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +34 -7
README.md CHANGED
@@ -50,13 +50,40 @@ pipeline_tag: text-generation
50
 
51
  <br>
52
 
53
- - **AI-Harness evaluation** [[link]](https://github.com/Beomi/ko-lm-evaluation-harness)
54
-
55
-
56
- | Model | Copa | Copa | HellaSwag | HellaSwag | BoolQ | BoolQ | Sentineg | Sentineg |
57
- | --------------------- | ------ | ------ | --------- | --------- | ------ | ------ | -------- | -------- |
58
- | | 0-shot | 5-shot | 0-shot | 5-shot | 0-shot | 5-shot | 0-shot | 5-shot |
59
- | **KoSOLAR-gugutypus** | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
60
 
61
 
62
  ---
 
50
 
51
  <br>
52
 
53
+ - **(ENG) AI-Harness evaluation** [[link]](https://github.com/EleutherAI/lm-evaluation-harness)
54
+
55
+ | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
56
+ |------------------|-------|------|-----:|------|-----:|---|-----:|
57
+ |HellaSwag | 1|none | 0|acc |0.6075|± |0.0049|
58
+ |HellaSwag | 1|none | 5|acc || |
59
+ |BoolQ | 2|none | 0|acc |0.8737|± |0.0058|
60
+ |BoolQ | 2|none | 5|acc | |± | |
61
+ |COPA | 1|none | 0|acc |0.8300|± |0.0378|
62
+ |COPA | 1|none | 5|acc | |± | |
63
+ |MMLU |N/A |none | 0|acc |0.5826|± |0.1432|
64
+ |MMLU |N/A |none | 5|acc | |± | |
65
+ <!--| - humanities |N/A |none | 0|acc |0.5103|± |0.1669|
66
+ | - other |N/A |none | 0|acc |0.6662|± |0.1079|
67
+ | - social_sciences|N/A |none | 0|acc |0.6922|± |0.0979|
68
+ | - stem |N/A |none | 0|acc |0.5011|± |0.1159|-->
69
+
70
+
71
+
72
+ - **(KOR) AI-Harness evaluation** [[link]](https://github.com/Beomi/ko-lm-evaluation-harness)
73
+
74
+
75
+ | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
76
+ |-------------------------|-------|------|-----:|------|-----:|---|-----:|
77
+ |KoBEST-HellaSwag | |none | 0|acc | |± | |
78
+ |KoBEST-HellaSwag | |none | 5|acc | |± | |
79
+ |KoBEST-BoolQ | |none | 0|acc | |± | |
80
+ |KoBEST-BoolQ | |none | 5|acc | |± | |
81
+ |KoBEST-COPA | |none | 0|acc | |± | |
82
+ |KoBEST-COPA | |none | 5|acc | |± | |
83
+ |KoBEST-SentiNeg | |none | 0|acc | |± | |
84
+ |KoBEST-SentiNeg | |none | 5|acc | |± | |
85
+ |KoBEST-MMLU | |none | 0|acc | |± | |
86
+ |KoBEST-MMLU | |none | 5|acc | |± | |
87
 
88
 
89
  ---