Skip to content

[sglang] Fixing issues in examples/sglang_multiturn/search_r1_like/run_qwen2.5-3b_instruct_search_multiturn.sh #5114

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

Open
NLPJCL wants to merge 3 commits into
base: main
Choose a base branch
from
Open

[sglang] Fixing issues in examples/sglang_multiturn/search_r1_like/run_qwen2.5-3b_instruct_search_multiturn.sh #5114

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
9852145
Update multi-turn settings in run_qwen2.5 script
NLPJCL Jan 29, 2026
61121a7
Update search_multiturn_grpo.yaml
NLPJCL Jan 29, 2026
7ad8985
Update preprocess_search_r1_dataset.py
NLPJCL Jan 29, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Next Next commit
Update multi-turn settings in run_qwen2.5 script 
Modify the configuration of search-r1 to adapt it to the current agentloop.
  • Loading branch information
@NLPJCL
NLPJCL authored Jan 29, 2026
commit 98521459a0e1c00438709706c950befcadfada4d
6 changes: 5 additions & 1 deletion examples/sglang_multiturn/search_r1_like/run_qwen2.5-3b_instruct_search_multiturn.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,11 @@ python3 -m verl.trainer.main_ppo \
actor_rollout_ref.rollout.name=sglang \
actor_rollout_ref.rollout.gpu_memory_utilization=0.5 \
actor_rollout_ref.rollout.n=5 \
actor_rollout_ref.rollout.multi_turn.max_assistant_turns=2 \
actor_rollout_ref.rollout.mode=async \
actor_rollout_ref.rollout.agent.default_agent_loop=tool_agent \
actor_rollout_ref.rollout.multi_turn.max_tool_response_length=1024 \
actor_rollout_ref.rollout.multi_turn.max_assistant_turns=4 \
actor_rollout_ref.rollout.multi_turn.max_user_turns=4 \
actor_rollout_ref.ref.log_prob_micro_batch_size_per_gpu=8 \
actor_rollout_ref.ref.fsdp_config.param_offload=True \
algorithm.use_kl_in_reward=False \
Expand Down