Muennighoff
commited on
Commit
•
aed9e73
1
Parent(s):
58660e8
Remove dup space
Browse files
README.md
CHANGED
@@ -2326,9 +2326,9 @@ See this repository for JSON files: https://github.com/bigscience-workshop/evalu
|
|
2326 |
| winogrande | eng | acc ↑ | 0.71 | 0.736 |
|
2327 |
| wnli (Median of 6 prompts) | eng | acc ↑ | 0.57 | 0.563 |
|
2328 |
| wsc (Median of 11 prompts) | eng | acc ↑ | 0.519 | 0.413 |
|
2329 |
-
| humaneval | python | pass@1
|
2330 |
-
| humaneval | python | pass@10
|
2331 |
-
| humaneval | python | pass@100
|
2332 |
|
2333 |
|
2334 |
**Train-time Evaluation:**
|
|
|
2326 |
| winogrande | eng | acc ↑ | 0.71 | 0.736 |
|
2327 |
| wnli (Median of 6 prompts) | eng | acc ↑ | 0.57 | 0.563 |
|
2328 |
| wsc (Median of 11 prompts) | eng | acc ↑ | 0.519 | 0.413 |
|
2329 |
+
| humaneval | python | pass@1 ↑ | 0.155 | 0.0 |
|
2330 |
+
| humaneval | python | pass@10 ↑ | 0.322 | 0.0 |
|
2331 |
+
| humaneval | python | pass@100 ↑ | 0.555 | 0.003 |
|
2332 |
|
2333 |
|
2334 |
**Train-time Evaluation:**
|