feat: add dry-run mode to offline generators and improve docs#411
Open
aydnOktay wants to merge 4 commits intoNousResearch:mainfrom
Open
feat: add dry-run mode to offline generators and improve docs#411aydnOktay wants to merge 4 commits intoNousResearch:mainfrom
aydnOktay wants to merge 4 commits intoNousResearch:mainfrom
Conversation
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR adds a
--dry-runmode to bothatropos-sft-genandatropos-dpo-genand updates the docs to make offline data generation and Windows setup easier.What’s included
New
--dry-runmode for offline generatorsatropos-sft-gengains ansft_dry_runhelper that:GET /batch,atropos-dpo-gengains a symmetricdpo_dry_runhelper with the same behavior.--dry-runflag to trigger these checks:atropos-sft-gen ... --dry-runatropos-dpo-gen ... --dry-runMore actionable error messages
GET /batch.Unit tests for the new behavior
atroposlib/tests/test_offline_cli_dry_run.pyverifies:sft_dry_run/dpo_dry_runcallAutoTokenizer.from_pretrainedand hit the API,--dry-runis passed instead of running a full data grab.Documentation improvements
README.md:--dry-runstep before collecting SFT data.run-apiand an example environment,atropos-sft-genwith--dry-runand then generating data.Why
before writing large datasets.
--dry-runmode shortens this feedback loop and avoids accidental mutations to the rollout server state.How to use
SFT dry-run
atropos-sft-gen path/to/output.jsonl
--tokenizer Qwen/Qwen2.5-1.5B-Instruct
--dry-run
DPO dry-run
atropos-dpo-gen path/to/output.jsonl
--tokenizer Qwen/Qwen2.5-1.5B-Instruct
--dry-run