The Kyrgyz Wikipedia (kywiki) training pipeline got stuck at the step where it generates backtesting data as shown in the screenshot below:
This is likely to be caused by the same sentence tokenization issue affecting hywiki in: T327371
Further investigation is required to fix this issue.
| Status | Subtype | Assigned | Task | ||
|---|---|---|---|---|---|
| Open | lbowmaker | T307881 Scaling of link suggestions service | |||
| In Progress | Trizek-WMF | T304110 [EPIC] Deploy "add a link" to all Wikipedias | |||
| Resolved | Urbanecm_WMF | T308135 Deploy "add a link" to 10th round of wikis | |||
| Resolved | kevinbazira | T329817 Kyrgyz Wikipedia model training pipeline failed |
kywiki has been added to wikis that will be deployed in the 11th round T308136
The sentence tokenization bug has been fixed in T327371#8631149