mirror of
https://github.com/volcengine/verl.git
synced 2025-10-20 13:43:50 +08:00
4de247fe4d
### Checklist Before Starting - [x] Search for similar PR(s). ### What does this PR do? - Unify the functionality of SGLangRollout and AsyncSGLangRollout, remove original SGLangRollout and rename AsyncSGLangRollout to SGLangRollout. - Make trivial changes due to modification in sglang==0.4.6.post5. ### High-Level Design > Demonstrate the high-level design if this PR is complex. ### Specific Changes > List the specific changes. ### API > Demonstrate how the API changes if any. ### Usage Example > Provide usage example(s) for easier usage. ```python # Add code snippet or script demonstrating how to use this ``` ### 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, evaluatuion results, etc. ### Additional Info. - **Issue Number**: Fixes issue # or discussion # if any. - **Training**: [Note which backend this PR will affect: FSDP, Megatron, both, or none] - **Inference**: [Note which backend this PR will affect: vLLM, SGLang, both, or none] ### Checklist Before Submitting - [ ] Read the [Contribute Guide](https://github.com/volcengine/verl?tab=readme-ov-file#contribution-guide). - [ ] Apply [pre-commit checks](https://github.com/volcengine/verl?tab=readme-ov-file#code-linting-and-formatting). - [ ] Add `[BREAKING]` to the PR title if it breaks any API. - [ ] Update the documentation about your changes in the [docs](https://github.com/volcengine/verl/tree/main/docs). - [ ] Add CI test(s) if necessary. --------- Co-authored-by: zyzshishui <@qq.com> Co-authored-by: Xiang Long <mindsculptor@yeah.net> Co-authored-by: ocss884 <ocss.lin@gmail.com> Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com> Co-authored-by: H <linhaibin.eric@gmail.com>
59 lines
2.6 KiB
Bash
59 lines
2.6 KiB
Bash
# run on 8xH100
|
|
# make sure your current working directory is the root of the project
|
|
|
|
set -x
|
|
|
|
huggingface-cli download Qwen/Qwen2.5-3B-Instruct --local-dir $HOME/models/Qwen/Qwen2.5-3B-Instruct
|
|
|
|
ulimit -n 65535
|
|
|
|
PROJECT_DIR="$(pwd)"
|
|
CONFIG_PATH="$PROJECT_DIR/examples/sglang_multiturn/config"
|
|
FSDP_STRATEGY=${FSDP_STRATEGY:-fsdp}
|
|
|
|
python3 -m verl.trainer.main_ppo \
|
|
--config-path="$CONFIG_PATH" \
|
|
--config-name='gsm8k_multiturn_grpo' \
|
|
algorithm.adv_estimator=grpo \
|
|
data.train_batch_size=256 \
|
|
data.max_prompt_length=1024 \
|
|
data.max_response_length=1024 \
|
|
data.filter_overlong_prompts=True \
|
|
data.truncation='error' \
|
|
data.return_raw_chat=True \
|
|
actor_rollout_ref.model.path=$HOME/models/Qwen/Qwen2.5-3B-Instruct \
|
|
actor_rollout_ref.actor.optim.lr=1e-6 \
|
|
actor_rollout_ref.model.use_remove_padding=True \
|
|
actor_rollout_ref.actor.ppo_mini_batch_size=256 \
|
|
actor_rollout_ref.actor.ppo_micro_batch_size_per_gpu=16 \
|
|
actor_rollout_ref.actor.use_kl_loss=True \
|
|
actor_rollout_ref.actor.kl_loss_coef=0.001 \
|
|
actor_rollout_ref.actor.kl_loss_type=low_var_kl \
|
|
actor_rollout_ref.actor.entropy_coeff=0 \
|
|
actor_rollout_ref.model.enable_gradient_checkpointing=True \
|
|
actor_rollout_ref.actor.strategy=$FSDP_STRATEGY \
|
|
actor_rollout_ref.actor.fsdp_config.param_offload=False \
|
|
actor_rollout_ref.actor.fsdp_config.optimizer_offload=False \
|
|
actor_rollout_ref.rollout.log_prob_micro_batch_size_per_gpu=32 \
|
|
actor_rollout_ref.rollout.tensor_model_parallel_size=2 \
|
|
actor_rollout_ref.rollout.name=sglang \
|
|
actor_rollout_ref.rollout.gpu_memory_utilization=0.5 \
|
|
actor_rollout_ref.rollout.n=8 \
|
|
actor_rollout_ref.ref.log_prob_micro_batch_size_per_gpu=32 \
|
|
actor_rollout_ref.ref.strategy=$FSDP_STRATEGY \
|
|
actor_rollout_ref.ref.fsdp_config.param_offload=True \
|
|
algorithm.use_kl_in_reward=False \
|
|
trainer.critic_warmup=0 \
|
|
trainer.logger=['console'] \
|
|
trainer.project_name='gsm8k_async_rl' \
|
|
trainer.experiment_name=qwen2.5-3b_function_rm-gsm8k-sgl-multi-w-tool-$FSDP_STRATEGY-rebased-0427-verify-n16 \
|
|
trainer.n_gpus_per_node=8 \
|
|
trainer.nnodes=1 \
|
|
trainer.save_freq=-1 \
|
|
trainer.test_freq=-1 \
|
|
data.train_files=$HOME/data/gsm8k_verl_sgl_multi_turn_preprocessed/train.parquet \
|
|
data.val_files=$HOME/data/gsm8k_verl_sgl_multi_turn_preprocessed/test.parquet \
|
|
actor_rollout_ref.rollout.multi_turn.tool_config_path="$PROJECT_DIR/examples/sglang_multiturn/config/tool_config/gsm8k_tool_config.yaml" \
|
|
trainer.val_before_train=False \
|
|
trainer.total_training_steps=1 $@
|