Skip to content
This repository has been archived by the owner on Nov 1, 2024. It is now read-only.

Add test_sequence_parallel #605

Draft
wants to merge 49 commits into
base: main
Choose a base branch
from
Draft

Add test_sequence_parallel #605

wants to merge 49 commits into from

Commits on Jan 16, 2023

  1. Add test_sequence_parallel

    @bashnick
    bashnick committed Jan 16, 2023
    Configuration menu
    Copy the full SHA
    48e1956 View commit details
    Browse the repository at this point in the history

  2. try different version of apex

    @bashnick
    bashnick committed Jan 16, 2023
    Configuration menu
    Copy the full SHA
    4a3f111 View commit details
    Browse the repository at this point in the history

  3. try without sequence_parallel

    @bashnick
    bashnick committed Jan 16, 2023
    Configuration menu
    Copy the full SHA
    c90bbd2 View commit details
    Browse the repository at this point in the history

Commits on Jan 17, 2023

  1. try sequence_parallel separately

    @bashnick
    bashnick committed Jan 17, 2023
    Configuration menu
    Copy the full SHA
    b8a6afc View commit details
    Browse the repository at this point in the history

  2. try update torch to 1.13.1+cu117

    @bashnick
    bashnick committed Jan 17, 2023
    Configuration menu
    Copy the full SHA
    2978c77 View commit details
    Browse the repository at this point in the history

  3. try with torch=1.12.1+cu116

    @bashnick
    bashnick committed Jan 17, 2023
    Configuration menu
    Copy the full SHA
    67f765f View commit details
    Browse the repository at this point in the history

Commits on Jan 18, 2023

  1. try update environment

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    65d886b View commit details
    Browse the repository at this point in the history

  2. upd the config file

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    0bbebb9 View commit details
    Browse the repository at this point in the history

  3. debug config file env setup

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    08e9d88 View commit details
    Browse the repository at this point in the history

  4. add "source $BASH_ENV" before "source activate"

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    0fcf0a5 View commit details
    Browse the repository at this point in the history

  5. skip warning about the cuda versions mismatch

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    cf59b73 View commit details
    Browse the repository at this point in the history

  6. try different version of apex

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    ccc838c View commit details
    Browse the repository at this point in the history

  7. try revert back the ubuntu image and cuda 11.1

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    8f5723a View commit details
    Browse the repository at this point in the history

  8. checkout main branch in apex

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    95ab3f1 View commit details
    Browse the repository at this point in the history

  9. add back the checkout for apex

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    8e28d57 View commit details
    Browse the repository at this point in the history

  10. try cuda 11.6 image

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    8e42490 View commit details
    Browse the repository at this point in the history

  11. revert back to cuda 11.4

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    c9cd83c View commit details
    Browse the repository at this point in the history

  12. try update cuda to 11.6

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    75c7d4c View commit details
    Browse the repository at this point in the history

  13. fix format

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    f69786d View commit details
    Browse the repository at this point in the history

  14. try update cuda install

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    4e81303 View commit details
    Browse the repository at this point in the history

  15. update the keys for cuda repo

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    3334922 View commit details
    Browse the repository at this point in the history

  16. remove cuda-toolkit

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    b83768e View commit details
    Browse the repository at this point in the history

  17. try update the saving location

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    31257da View commit details
    Browse the repository at this point in the history

  18. try install cuda using the ubuntu package manager

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    72177a0 View commit details
    Browse the repository at this point in the history

  19. try most recent cuda version

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    c446855 View commit details
    Browse the repository at this point in the history

  20. try ubuntu 11.6

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    a7cfcdd View commit details
    Browse the repository at this point in the history

  21. clean previous cuda versions first

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    d1da22b View commit details
    Browse the repository at this point in the history

  22. try change image without cuda

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    ec4903a View commit details
    Browse the repository at this point in the history

  23. remove nvcc --version

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    dee4d68 View commit details
    Browse the repository at this point in the history

  24. remove conda-pack

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    df56434 View commit details
    Browse the repository at this point in the history

  25. try reload CUDA

    @bashnick
    bashnick committed Jan 18, 2023
    Configuration menu
    Copy the full SHA
    7affc3c View commit details
    Browse the repository at this point in the history

Commits on Jan 19, 2023

  1. try unload the nvidia kernel module first

    @bashnick
    bashnick committed Jan 19, 2023
    Configuration menu
    Copy the full SHA
    b5cfc41 View commit details
    Browse the repository at this point in the history

  2. try stop other nvidia processes before restarting

    @bashnick
    bashnick committed Jan 19, 2023
    Configuration menu
    Copy the full SHA
    3d616f7 View commit details
    Browse the repository at this point in the history

  3. revert back to cu11.1 and try with PT1.13+cu11.1

    @bashnick
    bashnick committed Jan 19, 2023
    Configuration menu
    Copy the full SHA
    9dff621 View commit details
    Browse the repository at this point in the history

  4. try with PT1.13+cu11.1 from source

    @bashnick
    bashnick committed Jan 19, 2023
    Configuration menu
    Copy the full SHA
    25778c1 View commit details
    Browse the repository at this point in the history

  5. small fix

    @bashnick
    bashnick committed Jan 19, 2023
    Configuration menu
    Copy the full SHA
    ed559e8 View commit details
    Browse the repository at this point in the history

  6. small fix with PATH

    @bashnick
    bashnick committed Jan 19, 2023
    Configuration menu
    Copy the full SHA
    8236c9c View commit details
    Browse the repository at this point in the history

  7. revert to PT 1.10.2+cu111

    @bashnick
    bashnick committed Jan 19, 2023
    Configuration menu
    Copy the full SHA
    0b8050c View commit details
    Browse the repository at this point in the history

  8. take PT from torch_stable

    @bashnick
    bashnick committed Jan 19, 2023
    Configuration menu
    Copy the full SHA
    50d9645 View commit details
    Browse the repository at this point in the history

  9. small changes

    @bashnick
    bashnick committed Jan 19, 2023
    Configuration menu
    Copy the full SHA
    a0f2807 View commit details
    Browse the repository at this point in the history

  10. try original config

    @bashnick
    bashnick committed Jan 19, 2023
    Configuration menu
    Copy the full SHA
    3b9ba76 View commit details
    Browse the repository at this point in the history

  11. try change to PT10.2

    @bashnick
    bashnick committed Jan 19, 2023
    Configuration menu
    Copy the full SHA
    89b1ba7 View commit details
    Browse the repository at this point in the history

  12. change checkouts for apex and fairscale

    @bashnick
    bashnick committed Jan 19, 2023
    Configuration menu
    Copy the full SHA
    f4cc998 View commit details
    Browse the repository at this point in the history

  13. remove checkout for apex

    @bashnick
    bashnick committed Jan 19, 2023
    Configuration menu
    Copy the full SHA
    125800f View commit details
    Browse the repository at this point in the history

  14. try python3.9

    @bashnick
    bashnick committed Jan 19, 2023
    Configuration menu
    Copy the full SHA
    e65d479 View commit details
    Browse the repository at this point in the history

Commits on Jan 20, 2023

  1. revert to initial setup

    @bashnick
    bashnick committed Jan 20, 2023
    Configuration menu
    Copy the full SHA
    428adb7 View commit details
    Browse the repository at this point in the history

  2. try upgrade pytorch after apex installation

    @bashnick
    bashnick committed Jan 20, 2023
    Configuration menu
    Copy the full SHA
    198f3b7 View commit details
    Browse the repository at this point in the history

  3. try with PT1.10.2+cu111

    @bashnick
    bashnick committed Jan 20, 2023
    Configuration menu
    Copy the full SHA
    e23fd62 View commit details
    Browse the repository at this point in the history

Commits on Jan 23, 2023

  1. try using a dockerhub image

    @bashnick
    bashnick committed Jan 23, 2023
    Configuration menu
    Copy the full SHA
    dd2b6f5 View commit details
    Browse the repository at this point in the history