docs: large tech doc edit #303

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Merged

terrykong merged 36 commits into main from tk/jgerh/reinforcer-docs

May 6, 2025

Contributor

terrykong commented May 1, 2025 •

edited

Loading

Replaces #168 (rebased)

github-actions bot added documentation CI labels

terrykong force-pushed the tk/jgerh/reinforcer-docs branch 2 times, most recently from 7125a27 to 3aba70c Compare

May 1, 2025 22:14

terrykong closed this

terrykong force-pushed the tk/jgerh/reinforcer-docs branch from 3aba70c to ebb46c3 Compare

May 1, 2025 22:17

terrykong reopened this

github-actions bot removed the CI label

terrykong mentioned this pull request

docs: large tech edit #168

Closed

4 tasks

terrykong requested review from SahilJain314, parthchadha and jgerh

May 2, 2025 16:48

jgerh reviewed

View reviewed changes

Contributor

jgerh left a comment

Completed review of files and provided a few copyedits and suggested text additions for intros.

docs/adding-new-models.md Show resolved Hide resolved

docs/cluster.md Show resolved Hide resolved

docs/design-docs/chat-datasets.md Show resolved Hide resolved

docs/design-docs/design-and-philosophy.md Outdated Show resolved Hide resolved

docs/design-docs/logger.md Show resolved Hide resolved

docs/testing.md Outdated Show resolved Hide resolved

docs/adding-new-models.md Outdated Show resolved Hide resolved

docs/design-docs/checkpointing.md Outdated Show resolved Hide resolved

docs/design-docs/checkpointing.md Outdated Show resolved Hide resolved

docs/design-docs/checkpointing.md Outdated Show resolved Hide resolved

jgerh reviewed

View reviewed changes

Contributor

jgerh left a comment

Completed review of files and provided a few copyedits and suggested text additions for intros.

docs/design-docs/checkpointing.md Outdated Show resolved Hide resolved

README.md Show resolved Hide resolved

README.md Show resolved Hide resolved

terrykong and others added 16 commits

May 6, 2025 12:02


          tech edit

60ba494

Signed-off-by: Terry Kong <terryk@nvidia.com>


          add dummy spaces to let checkpointing be reviewable

d16225c

Signed-off-by: Terry Kong <terryk@nvidia.com>


          Update docs/design-docs/checkpointing.md

b1c9b04

Co-authored-by: jgerh <163925524+jgerh@users.noreply.github.com>
Signed-off-by: Terry Kong <terrycurtiskong@gmail.com>
Signed-off-by: Terry Kong <terryk@nvidia.com>


          Update docs/design-docs/checkpointing.md

789074e

Co-authored-by: jgerh <163925524+jgerh@users.noreply.github.com>
Signed-off-by: Terry Kong <terrycurtiskong@gmail.com>
Signed-off-by: Terry Kong <terryk@nvidia.com>


          Update docs/design-docs/checkpointing.md

aa292ff

Co-authored-by: jgerh <163925524+jgerh@users.noreply.github.com>
Signed-off-by: Terry Kong <terrycurtiskong@gmail.com>
Signed-off-by: Terry Kong <terryk@nvidia.com>


          Update docs/adding-new-models.md

603b483

Co-authored-by: jgerh <163925524+jgerh@users.noreply.github.com>
Signed-off-by: Terry Kong <terrycurtiskong@gmail.com>
Signed-off-by: Terry Kong <terryk@nvidia.com>


          Update docs/testing.md

c9f905d

Co-authored-by: jgerh <163925524+jgerh@users.noreply.github.com>
Signed-off-by: Terry Kong <terrycurtiskong@gmail.com>
Signed-off-by: Terry Kong <terryk@nvidia.com>


          tech edit

7a0e446

Signed-off-by: Terry Kong <terryk@nvidia.com>


          done

d7649a7

Signed-off-by: Terry Kong <terryk@nvidia.com>


          done

31a2d47

Signed-off-by: Terry Kong <terryk@nvidia.com>


          period

838ae4a

Signed-off-by: Terry Kong <terryk@nvidia.com>


          Revert "done"

f766a97

This reverts commit 043e186.

Signed-off-by: Terry Kong <terryk@nvidia.com>


          done

bbd0d34

Signed-off-by: Terry Kong <terryk@nvidia.com>


          done

bb73f36

Signed-off-by: Terry Kong <terryk@nvidia.com>


          done

bd86cc3

Signed-off-by: Terry Kong <terryk@nvidia.com>


          period

6e7269b

Signed-off-by: Terry Kong <terryk@nvidia.com>

terrykong and others added 19 commits

May 6, 2025 12:02


          Update docs/guides/eval.md

51d3399

Co-authored-by: jgerh <163925524+jgerh@users.noreply.github.com>
Signed-off-by: Terry Kong <terrycurtiskong@gmail.com>
Signed-off-by: Terry Kong <terryk@nvidia.com>


          done

8c86c03

Signed-off-by: Terry Kong <terryk@nvidia.com>


          Update docs/guides/grpo.md

00f9404

Co-authored-by: jgerh <163925524+jgerh@users.noreply.github.com>
Signed-off-by: Terry Kong <terrycurtiskong@gmail.com>
Signed-off-by: Terry Kong <terryk@nvidia.com>

fix

f4b5009

Signed-off-by: Terry Kong <terryk@nvidia.com>


          Update docs/guides/grpo.md

58ac141

Co-authored-by: jgerh <163925524+jgerh@users.noreply.github.com>
Signed-off-by: Terry Kong <terrycurtiskong@gmail.com>
Signed-off-by: Terry Kong <terryk@nvidia.com>


          done

cccf25f

Signed-off-by: Terry Kong <terryk@nvidia.com>


          Update docs/guides/sft.md

1ee6043

Co-authored-by: jgerh <163925524+jgerh@users.noreply.github.com>
Signed-off-by: Terry Kong <terrycurtiskong@gmail.com>
Signed-off-by: Terry Kong <terryk@nvidia.com>


          done

5703b2f

Signed-off-by: Terry Kong <terryk@nvidia.com>


          done

6bcf735

Signed-off-by: Terry Kong <terryk@nvidia.com>


          done

86eb41d

Signed-off-by: Terry Kong <terryk@nvidia.com>


          revet

c396f25

Signed-off-by: Terry Kong <terryk@nvidia.com>

go

e37928d

Signed-off-by: Terry Kong <terryk@nvidia.com>

fix

a9cb407

Signed-off-by: Terry Kong <terryk@nvidia.com>


          capitalize

e438f73

Signed-off-by: Terry Kong <terryk@nvidia.com>


          revert

4603adc

Signed-off-by: Terry Kong <terryk@nvidia.com>

fix

e8021a0

Signed-off-by: Terry Kong <terryk@nvidia.com>

go

83ae377

Signed-off-by: Terry Kong <terryk@nvidia.com>

ok

b95ac5b

Signed-off-by: Terry Kong <terryk@nvidia.com>

fix

87aa887

Signed-off-by: Terry Kong <terryk@nvidia.com>

terrykong force-pushed the tk/jgerh/reinforcer-docs branch from ab3bdc1 to 87aa887 Compare

May 6, 2025 19:02


          lint

d9edcb7

Signed-off-by: Terry Kong <terryk@nvidia.com>

jgerh approved these changes

View reviewed changes

terrykong added this pull request to the merge queue

Merged via the queue into main with commit e3f8936

13 checks passed

terrykong deleted the tk/jgerh/reinforcer-docs branch

May 6, 2025 21:12

YzjiaoNvd pushed a commit to YzjiaoNvd/NeMo-RL that referenced this pull request


          docs: large tech doc edit (NVIDIA-NeMo#303)

ef94c59

Signed-off-by: Terry Kong <terryk@nvidia.com>
Signed-off-by: Terry Kong <terrycurtiskong@gmail.com>
Co-authored-by: jgerh <163925524+jgerh@users.noreply.github.com>

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels