Update README.md
Browse files
README.md
CHANGED
@@ -27,9 +27,18 @@ LogicKor
|
|
27 |
| **Overall** | **5.73** | |
|
28 |
|
29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
|Task|Score|shot|
|
31 |
|---|---|---|
|
32 |
-
|ifeval|58.61|0|
|
33 |
|haerae|43.26|5|
|
34 |
-
|gsm8k-ko(strict-match)|42.68|5|
|
35 |
-
|gsm8k(strict-match)|73.77|5|
|
|
|
27 |
| **Overall** | **5.73** | |
|
28 |
|
29 |
|
30 |
+
| Tasks |Version| Filter |n-shot| Metric | |Value | |Stderr|
|
31 |
+
|--------|------:|----------------|-----:|-----------------------|---|-----:|---|------|
|
32 |
+
|gsm8k | 3|flexible-extract| 5|exact_match |↑ |0.7013|± |0.0126|
|
33 |
+
| | |strict-match | 5|exact_match |↑ |0.2418|± |0.0118|
|
34 |
+
|gsm8k-ko| 1|flexible-extract| 5|exact_match |↑ |0.4466|± |0.0137|
|
35 |
+
| | |strict-match | 5|exact_match |↑ |0.4420|± |0.0137|
|
36 |
+
|ifeval | 4|none | 0|inst_level_loose_acc |↑ |0.8549|± | N/A|
|
37 |
+
| | |none | 0|inst_level_strict_acc |↑ |0.8225|± | N/A|
|
38 |
+
| | |none | 0|prompt_level_loose_acc |↑ |0.7874|± |0.0176|
|
39 |
+
| | |none | 0|prompt_level_strict_acc|↑ |0.7468|± |0.0187|
|
40 |
+
|
41 |
+
|
42 |
|Task|Score|shot|
|
43 |
|---|---|---|
|
|
|
44 |
|haerae|43.26|5|
|
|
|
|