多卡train_full Pixtral-12B一段时间后报错: torch.distributed.elastic.multiprocessing.errors.ChildFailedError #2000
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: label_issue | |
| on: | |
| issues: | |
| types: | |
| - opened | |
| jobs: | |
| label_issue: | |
| runs-on: ubuntu-latest | |
| permissions: | |
| issues: write | |
| steps: | |
| - env: | |
| GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} | |
| ISSUE_URL: ${{ github.event.issue.html_url }} | |
| ISSUE_TITLE: ${{ github.event.issue.title }} | |
| run: | | |
| LABEL="" | |
| NPU_KEYWORDS=(npu huawei ascend 华为 昇腾) | |
| ISSUE_TITLE_LOWER=$(echo $ISSUE_TITLE | tr '[:upper:]' '[:lower:]') | |
| for KEYWORD in ${NPU_KEYWORDS[@]}; do | |
| if [[ $ISSUE_TITLE_LOWER == *$KEYWORD* ]] && [[ $ISSUE_TITLE_LOWER != *input* ]]; then | |
| LABEL="npu" | |
| break | |
| fi | |
| done | |
| if [ -n "$LABEL" ]; then | |
| gh issue edit $ISSUE_URL --add-label $LABEL | |
| fi |