With using the fp8, after the interruption of training, and then continue , there may be a little difference in loss. Is this caused by the fp8 mechanism? #2557
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
| # Copyright (c) 2022-2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | |
| # | |
| # See LICENSE for license information. | |
| # A workflow to trigger ci on hybrid infra (github + self hosted runner) | |
| name: TE-CI Trigger | |
| on: | |
| issue_comment: | |
| types: [created] | |
| jobs: | |
| Authorization: | |
| name: Authorization | |
| runs-on: blossom | |
| outputs: | |
| args: ${{ env.args }} | |
| # This job only runs for pull request comments | |
| if: | | |
| contains( 'ptrendx,ksivaman,schetlur-nv,timmoon10,zlsh80826,mingxu1067,cyanguwa,nzmora-nvidia,galagam,nouiz,denera,sudhakarsingh27,Oleg-Goncharov,', format('{0},', github.actor)) && | |
| startsWith(github.event.comment.body, '/te-ci') | |
| steps: | |
| - name: Check if comment is issued by authorized person | |
| run: blossom-ci | |
| env: | |
| OPERATION: 'AUTH' | |
| REPO_TOKEN: ${{ secrets.GITHUB_TOKEN }} | |
| REPO_KEY_DATA: ${{ secrets.BLOSSOM_KEY }} | |
| Vulnerability-scan: | |
| name: Vulnerability scan | |
| needs: [Authorization] | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout code | |
| uses: actions/checkout@v2 | |
| with: | |
| repository: ${{ fromJson(needs.Authorization.outputs.args).repo }} | |
| ref: ${{ fromJson(needs.Authorization.outputs.args).ref }} | |
| lfs: 'true' | |
| - name: Run blossom action | |
| uses: NVIDIA/blossom-action@main | |
| env: | |
| REPO_TOKEN: ${{ secrets.GITHUB_TOKEN }} | |
| REPO_KEY_DATA: ${{ secrets.BLOSSOM_KEY }} | |
| with: | |
| args1: ${{ fromJson(needs.Authorization.outputs.args).args1 }} | |
| args2: ${{ fromJson(needs.Authorization.outputs.args).args2 }} | |
| args3: ${{ fromJson(needs.Authorization.outputs.args).args3 }} | |
| Job-trigger: | |
| name: Start ci job | |
| needs: [Vulnerability-scan] | |
| runs-on: blossom | |
| steps: | |
| - name: Start ci job | |
| run: blossom-ci | |
| env: | |
| OPERATION: 'START-CI-JOB' | |
| CI_SERVER: ${{ secrets.CI_SERVER }} | |
| REPO_TOKEN: ${{ secrets.GITHUB_TOKEN }} |