mirror of
https://github.com/volcengine/verl.git
synced 2025-10-20 13:43:50 +08:00
b79263ad60
### What does this PR do?
[perf] refactor part 2: Profiler ci test and fixes
### Checklist Before Starting
- [ ] Search for similar PRs. Paste at least one query link here: ...
- [ ] 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
> For changes that can not be tested by CI (e.g., algorithm
implementation, new model support), validate by experiment(s) and show
results like training curve plots, evaluation results, etc.
### API and Usage Example
> Demonstrate how the API changes if any, and provide usage example(s)
if possible.
```python
# Add code snippet or script demonstrating how to use this
```
### Design & Code Changes
> Demonstrate the high-level design if this PR is complex, and list the
specific changes.
### Checklist Before Submitting
> [!IMPORTANT]
> Please check all the following items before requesting a review,
otherwise the reviewer might deprioritize this PR for review.
- [ ] Read the [Contribute
Guide](https://github.com/volcengine/verl/blob/main/CONTRIBUTING.md).
- [ ] 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).
(If not accessible, please try [the Feishu group
(飞书群)](https://applink.larkoffice.com/client/chat/chatter/add_by_link?link_token=772jd4f1-cd91-441e-a820-498c6614126a).)
66 lines
2.6 KiB
Bash
66 lines
2.6 KiB
Bash
set -x
|
|
|
|
# Example runnable on H20 * 8
|
|
|
|
export CUDA_DEVICE_MAX_CONNECTIONS=1 # For megatron communication/computation overlapping
|
|
|
|
gsm8k_train_path=$HOME/data/gsm8k/train.parquet
|
|
gsm8k_test_path=$HOME/data/gsm8k/test.parquet
|
|
math_train_path=$HOME/data/math/train.parquet
|
|
math_test_path=$HOME/data/math/test.parquet
|
|
|
|
train_files=${train_files:-"$gsm8k_train_path"}
|
|
test_files=${test_files:-"$gsm8k_test_path"}
|
|
|
|
# Nsight profiling configuration
|
|
PROFILE_STEPS="[1]" # or [] or null
|
|
PROFILE_RANKS_ALL=False # or True
|
|
PROFILE_RANKS=[0,4]
|
|
DISCRETE=True # or True
|
|
|
|
python3 -m verl.trainer.main_ppo --config-path=./config --config-name='ppo_megatron_trainer'\
|
|
algorithm.adv_estimator=gae \
|
|
data.train_files="$train_files" \
|
|
data.val_files="$test_files" \
|
|
data.train_batch_size=256 \
|
|
data.max_prompt_length=1024 \
|
|
data.max_response_length=512 \
|
|
data.filter_overlong_prompts=True \
|
|
data.truncation='error' \
|
|
actor_rollout_ref.model.path=deepseek-ai/deepseek-llm-7b-chat \
|
|
actor_rollout_ref.actor.optim.lr=1e-6 \
|
|
actor_rollout_ref.actor.ppo_mini_batch_size=64 \
|
|
actor_rollout_ref.actor.ppo_micro_batch_size_per_gpu=4 \
|
|
actor_rollout_ref.actor.megatron.pipeline_model_parallel_size=2 \
|
|
actor_rollout_ref.actor.megatron.tensor_model_parallel_size=2 \
|
|
actor_rollout_ref.actor.use_kl_loss=False \
|
|
actor_rollout_ref.actor.profiler.enable=True \
|
|
actor_rollout_ref.actor.profiler.ranks=$PROFILE_RANKS \
|
|
actor_rollout_ref.actor.profiler.all_ranks=$PROFILE_RANKS_ALL \
|
|
actor_rollout_ref.rollout.log_prob_micro_batch_size_per_gpu=4 \
|
|
actor_rollout_ref.rollout.tensor_model_parallel_size=2 \
|
|
actor_rollout_ref.rollout.name=vllm \
|
|
actor_rollout_ref.rollout.gpu_memory_utilization=0.8 \
|
|
actor_rollout_ref.ref.megatron.pipeline_model_parallel_size=2 \
|
|
actor_rollout_ref.ref.megatron.tensor_model_parallel_size=2 \
|
|
critic.optim.lr=1e-5 \
|
|
critic.model.path=deepseek-ai/deepseek-llm-7b-chat \
|
|
critic.ppo_micro_batch_size_per_gpu=4 \
|
|
critic.profiler.enable=True \
|
|
critic.profiler.ranks=$PROFILE_RANKS \
|
|
critic.profiler.all_ranks=$PROFILE_RANKS_ALL \
|
|
algorithm.use_kl_in_reward=False \
|
|
trainer.critic_warmup=0 \
|
|
trainer.logger='["console","wandb"]' \
|
|
trainer.project_name='verl_ppo_gsm8k_math_examples' \
|
|
trainer.experiment_name='deepseek_llm_7b_megatron' \
|
|
trainer.n_gpus_per_node=8 \
|
|
trainer.nnodes=1 \
|
|
trainer.save_freq=-1 \
|
|
trainer.test_freq=-1 \
|
|
trainer.total_epochs=100 \
|
|
trainer.total_training_steps=1 \
|
|
global_profiler.tool=nsys \
|
|
global_profiler.steps=$PROFILE_STEPS \
|
|
global_profiler.global_tool_config.nsys.discrete=$DISCRETE $@
|