Update README.md
Browse files
README.md
CHANGED
|
@@ -41,20 +41,20 @@ Qwen3-4B 기반의 LLM 모델로 한국어 및 영어 데이터셋을 사용하
|
|
| 41 |
|
| 42 |
|Groups|Version|Filter|n-shot| Metric | |Value | |Stderr|
|
| 43 |
|------|------:|------|------|--------|---|-----:|---|------|
|
| 44 |
-
|haerae| 1|none |
|
| 45 |
-
| | |none |
|
| 46 |
-
|kobest| 1|none |
|
| 47 |
-
| | |none |
|
| 48 |
-
| | |none |
|
| 49 |
|
| 50 |
|
| 51 |
| Groups |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
| 52 |
|-------------------------------|------:|------|------|-----------|---|-----:|---|-----:|
|
| 53 |
-
|kmmlu_direct | 2|none |
|
| 54 |
-
| - kmmlu_direct_applied_science| 2|none |
|
| 55 |
-
| - kmmlu_direct_humss | 2|none |
|
| 56 |
-
| - kmmlu_direct_other | 2|none |
|
| 57 |
-
| - kmmlu_direct_stem | 2|none |
|
| 58 |
|
| 59 |
|
| 60 |
```python
|
|
|
|
| 41 |
|
| 42 |
|Groups|Version|Filter|n-shot| Metric | |Value | |Stderr|
|
| 43 |
|------|------:|------|------|--------|---|-----:|---|------|
|
| 44 |
+
|haerae| 1|none | 0|acc |↑ |0.6654|± |0.0140|
|
| 45 |
+
| | |none | 0|acc_norm|↑ |0.6654|± |0.0140|
|
| 46 |
+
|kobest| 1|none | 0|acc |↑ |0.7768|± |0.0057|
|
| 47 |
+
| | |none | 0|acc_norm|↑ |0.5880|± |0.0220|
|
| 48 |
+
| | |none | 0|f1 |↑ |0.7764|± | N/A|
|
| 49 |
|
| 50 |
|
| 51 |
| Groups |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
| 52 |
|-------------------------------|------:|------|------|-----------|---|-----:|---|-----:|
|
| 53 |
+
|kmmlu_direct | 2|none | 0|exact_match|↑ |0.5212|± |0.0026|
|
| 54 |
+
| - kmmlu_direct_applied_science| 2|none | 0|exact_match|↑ |0.4997|± |0.0046|
|
| 55 |
+
| - kmmlu_direct_humss | 2|none | 0|exact_match|↑ |0.5365|± |0.0068|
|
| 56 |
+
| - kmmlu_direct_other | 2|none | 0|exact_match|↑ |0.5130|± |0.0053|
|
| 57 |
+
| - kmmlu_direct_stem | 2|none | 0|exact_match|↑ |0.5455|± |0.0048|
|
| 58 |
|
| 59 |
|
| 60 |
```python
|