Thomas Wang
commited on
Commit
·
874fa44
1
Parent(s):
3f4b529
Fix #98
Browse files
README.md
CHANGED
|
@@ -619,7 +619,7 @@ And multiple different metrics for specific tasks. _(More evaluation metrics for
|
|
| 619 |
See this repository for JSON files: https://github.com/bigscience-workshop/evaluation-results
|
| 620 |
|
| 621 |
| Task | Language | Metric | BLOOM-176B | OPT-175B* |
|
| 622 |
-
|:--------|:-----------------|:------------------------|-------------:|------------:|
|
| 623 |
| humaneval | python | pass@1 ↑ | 0.155 | 0.0 |
|
| 624 |
| humaneval | python | pass@10 ↑ | 0.328 | 0.0 |
|
| 625 |
| humaneval | python | pass@100 ↑ | 0.572 | 0.003 |
|
|
|
|
| 619 |
See this repository for JSON files: https://github.com/bigscience-workshop/evaluation-results
|
| 620 |
|
| 621 |
| Task | Language | Metric | BLOOM-176B | OPT-175B* |
|
| 622 |
+
|:--------|:-----------------|:------------------------|-------------:|------------:|
|
| 623 |
| humaneval | python | pass@1 ↑ | 0.155 | 0.0 |
|
| 624 |
| humaneval | python | pass@10 ↑ | 0.328 | 0.0 |
|
| 625 |
| humaneval | python | pass@100 ↑ | 0.572 | 0.003 |
|