Update README.md
Browse files
README.md
CHANGED
@@ -51,15 +51,15 @@ pipeline_tag: text-generation
|
|
51 |
|
52 |
| Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
|
53 |
|-------------------------|-------|------|-----:|------|-----:|---|-----:|
|
54 |
-
|KMMLU |N/A |none | 0|acc |
|
55 |
|KMMLU |N/A |none | 5|acc |0.3969|± |0.0816|
|
56 |
|KoBEST-HellaSwag | 0|none | 0|acc |0.4260|± |0.0221|
|
57 |
-
|KoBEST-HellaSwag | 0|none | 5|acc |
|
58 |
|KoBEST-BoolQ | 0|none | 0|acc |0.7792|± |0.0111|
|
59 |
|KoBEST-BoolQ | 0|none | 5|acc |0.8925|± |0.0083|
|
60 |
|KoBEST-COPA | 0|none | 0|acc |0.6670|± |0.0149|
|
61 |
|KoBEST-COPA | 0|none | 5|acc |0.7070|± |0.0144|
|
62 |
-
|KoBEST-SentiNeg | 0|none | 0|acc |
|
63 |
|KoBEST-SentiNeg | 0|none | 5|acc |0.9219|± |0.0135|
|
64 |
|
65 |
<br>
|
@@ -77,7 +77,7 @@ pipeline_tag: text-generation
|
|
77 |
|COPA | 1|none | 0|acc |0.8300|± |0.0378|
|
78 |
|COPA | 1|none | 5|acc |0.9300|± |0.0256|
|
79 |
|truthfulqa |N/A |none | 0|acc |0.4249|± |0.0023|
|
80 |
-
|truthfulqa |N/A |none | 5|acc |
|
81 |
|
82 |
|
83 |
---
|
|
|
51 |
|
52 |
| Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
|
53 |
|-------------------------|-------|------|-----:|------|-----:|---|-----:|
|
54 |
+
|KMMLU |N/A |none | 0|acc |0.3329|± |0.0794|
|
55 |
|KMMLU |N/A |none | 5|acc |0.3969|± |0.0816|
|
56 |
|KoBEST-HellaSwag | 0|none | 0|acc |0.4260|± |0.0221|
|
57 |
+
|KoBEST-HellaSwag | 0|none | 5|acc |0.4260|± |0.0221|
|
58 |
|KoBEST-BoolQ | 0|none | 0|acc |0.7792|± |0.0111|
|
59 |
|KoBEST-BoolQ | 0|none | 5|acc |0.8925|± |0.0083|
|
60 |
|KoBEST-COPA | 0|none | 0|acc |0.6670|± |0.0149|
|
61 |
|KoBEST-COPA | 0|none | 5|acc |0.7070|± |0.0144|
|
62 |
+
|KoBEST-SentiNeg | 0|none | 0|acc |0.7582|± |0.0215|
|
63 |
|KoBEST-SentiNeg | 0|none | 5|acc |0.9219|± |0.0135|
|
64 |
|
65 |
<br>
|
|
|
77 |
|COPA | 1|none | 0|acc |0.8300|± |0.0378|
|
78 |
|COPA | 1|none | 5|acc |0.9300|± |0.0256|
|
79 |
|truthfulqa |N/A |none | 0|acc |0.4249|± |0.0023|
|
80 |
+
|truthfulqa |N/A |none | 5|acc | - |± | - |
|
81 |
|
82 |
|
83 |
---
|