Upload README.md
Browse files
README.md
CHANGED
|
@@ -71,6 +71,19 @@ python finetune.py \
|
|
| 71 |
|
| 72 |
- Follow up as [beomi/LM-Harness](https://github.com/Beomi/ko-lm-evaluation-harness)
|
| 73 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |
gpt2 (pretrained=PracticeLLM/Twice-KoSOLAR-16.1B-test), limit: None, provide_description: False, num_fewshot: 0, batch_size: None
|
| 75 |
| Task |Version| Metric |Value | |Stderr|
|
| 76 |
|----------------|------:|--------|-----:|---|-----:|
|
|
|
|
| 71 |
|
| 72 |
- Follow up as [beomi/LM-Harness](https://github.com/Beomi/ko-lm-evaluation-harness)
|
| 73 |
```
|
| 74 |
+
gpt2 (pretrained=PracticeLLM/Twice-KoSOLAR-16.1B-instruct-test), limit: None, provide_description: False, num_fewshot: 0, batch_size: None
|
| 75 |
+
| Task |Version| Metric |Value | |Stderr|
|
| 76 |
+
|----------------|------:|--------|-----:|---|-----:|
|
| 77 |
+
|kobest_boolq | 0|acc |0.5100|± |0.0133|
|
| 78 |
+
| | |macro_f1|0.3527|± |0.0079|
|
| 79 |
+
|kobest_copa | 0|acc |0.6740|± |0.0148|
|
| 80 |
+
| | |macro_f1|0.6732|± |0.0148|
|
| 81 |
+
|kobest_hellaswag| 0|acc |0.4640|± |0.0223|
|
| 82 |
+
| | |acc_norm|0.5480|± |0.0223|
|
| 83 |
+
| | |macro_f1|0.4585|± |0.0223|
|
| 84 |
+
|kobest_sentineg | 0|acc |0.6574|± |0.0238|
|
| 85 |
+
| | |macro_f1|0.6184|± |0.0253|
|
| 86 |
+
|
| 87 |
gpt2 (pretrained=PracticeLLM/Twice-KoSOLAR-16.1B-test), limit: None, provide_description: False, num_fewshot: 0, batch_size: None
|
| 88 |
| Task |Version| Metric |Value | |Stderr|
|
| 89 |
|----------------|------:|--------|-----:|---|-----:|
|