Files
verl/scripts/generate_trainer_config.sh
H d0c7bbbc05 [cfg] refactor: support +extra.any_key usage for the base dataclass config in verl (#2502)
### What does this PR do?

This PR makes update to the base config in verl:
- support +extra.any_key usage for the base config in verl.
- allow selective subfields to be frozen
- add a auto-generated config yaml file
`verl/trainer/config/_generated_ppo_trainer.yaml` for reference purpose,
in case the nested inheritance structure makes the config information
too scattered

### Checklist Before Starting

- [x] Search for similar PRs. Paste at least one query link here: ...
- [x] Format the PR title as `[{modules}] {type}: {description}` (This
will be checked by the CI)
- `{modules}` include `fsdp`, `megatron`, `sglang`, `vllm`, `rollout`,
`trainer`, `ci`, `training_utils`, `recipe`, `hardware`, `deployment`,
`ray`, `worker`, `single_controller`, `misc`, `perf`, `model`, `algo`,
`env`, `tool`, `ckpt`, `doc`, `data`
- If this PR involves multiple modules, separate them with `,` like
`[megatron, fsdp, doc]`
  - `{type}` is in `feat`, `fix`, `refactor`, `chore`, `test`
- If this PR breaks any API (CLI arguments, config, function signature,
etc.), add `[BREAKING]` to the beginning of the title.
  - Example: `[BREAKING][fsdp, megatron] feat: dynamic batching`

### Test

- added frozen field tests

### API and Usage Example

> Demonstrate how the API changes if any, and provide usage example(s)
if possible.

Now you can pass `--xx.profiler.extra.any_new_key=any_plain_value` in
command line to a dataclass inheriting `verl.BaseConfig`. This way we
can still pass dataclass configs inside verl but allow some flexiblity
in accepting new keys from users' adhoc usage.


### Checklist Before Submitting

> [!IMPORTANT]
> Please check all the following items before requesting a review,
otherwise the reviewer might deprioritize this PR for review.

- [x] Read the [Contribute
Guide](https://github.com/volcengine/verl/blob/main/CONTRIBUTING.md).
- [x] Apply [pre-commit
checks](https://github.com/volcengine/verl/blob/main/CONTRIBUTING.md#code-linting-and-formatting):
`pre-commit install && pre-commit run --all-files --show-diff-on-failure
--color=always`
- [ ] Add / Update [the
documentation](https://github.com/volcengine/verl/tree/main/docs).
- [ ] Add unit or end-to-end test(s) to [the CI
workflow](https://github.com/volcengine/verl/tree/main/.github/workflows)
to cover all the code. If not feasible, explain why: ...
- [ ] Once your PR is ready for CI, send a message in [the `ci-request`
channel](https://verl-project.slack.com/archives/C091TCESWB1) in [the
`verl` Slack
workspace](https://join.slack.com/t/verl-project/shared_invite/zt-3855yhg8g-CTkqXu~hKojPCmo7k_yXTQ).

---------

Co-authored-by: Lin <haibin@Lins-Laptop.hsd1.wa.comcast.net>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-07-15 09:06:56 +08:00

28 lines
1.2 KiB
Bash
Executable File

#!/usr/bin/env bash
set -euox pipefail
# 1. Dump the full config to a temp file
target_cfg=verl/trainer/config/_generated_ppo_trainer.yaml
tmp_header=$(mktemp)
tmp_cfg=$(mktemp)
echo "# This reference configration yaml is automatically generated via 'scripts/generate_trainer_config.sh'" > "$tmp_header"
echo "# in which it invokes 'python3 scripts/print_cfg.py --cfg job' to flatten the 'verl/trainer/config/ppo_trainer.yaml' config fields into a single file." >> "$tmp_header"
echo "# Do not modify this file directly." >> "$tmp_header"
echo "# The file is usually only for reference and never used." >> "$tmp_header"
echo "" >> "$tmp_header"
python3 scripts/print_cfg.py --cfg job > "$tmp_cfg"
# 2. Extract from the line starting with "actor_rollout_ref" onward
cat $tmp_header > $target_cfg
sed -n '/^actor_rollout_ref/,$p' "$tmp_cfg" >> $target_cfg
# 3. Clean up
rm "$tmp_cfg" "$tmp_header"
# 4. Verify that verl/trainer/config/_generated_ppo_trainer.yaml wasn't changed on disk
if ! git diff --exit-code -- "$target_cfg" >/dev/null; then
echo "$target_cfg is out of date. Please regenerate via 'scripts/generate_trainer_config.sh' and commit the changes."
exit 1
fi
echo "All good"
exit 0