Update README.md
Browse files
README.md
CHANGED
@@ -57,11 +57,11 @@ The following are the scores from our own evaluation.
|
|
57 |
|
58 |
| Metric | Value |
|
59 |
|-----------------------|-------|
|
60 |
-
| ARC (25-shot) |
|
61 |
| HellaSwag (10-shot) | xx |
|
62 |
| MMLU (5-shot) | xx |
|
63 |
-
| TruthfulQA (0-shot) |
|
64 |
-
| Winogrande (5-shot) |
|
65 |
| GSM8k (5-shot) | xx |
|
66 |
| **Avg.** | **xx** |
|
67 |
|
|
|
57 |
|
58 |
| Metric | Value |
|
59 |
|-----------------------|-------|
|
60 |
+
| ARC (25-shot) | 67.32 |
|
61 |
| HellaSwag (10-shot) | xx |
|
62 |
| MMLU (5-shot) | xx |
|
63 |
+
| TruthfulQA (0-shot) | 54.17 |
|
64 |
+
| Winogrande (5-shot) | 80.72 |
|
65 |
| GSM8k (5-shot) | xx |
|
66 |
| **Avg.** | **xx** |
|
67 |
|