frozenleaves/verl
1
0
Fork 0
mirror of https://github.com/volcengine/verl.git synced 2025-10-20 13:43:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

[doc] fix: set use_dist_checkpointing to False for ref model in qwen3moe-30b script (#3198)

Browse Source 
### What does this PR do?

Set use_dist_checkpointing to False for ref model in qwen3moe-30b
script, because there is not dist_megatron_ckpt model path for ref
model.
This commit is contained in:
none0663
2025-08-25 12:33:24 +08:00
committed by GitHub
parent cb5818c6fc
commit 58c847b17f
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/grpo_trainer/run_qwen3moe-30b_megatron_96gb.sh
View File

@ -168,7 +168,7 @@ python3 -m verl.trainer.main_ppo --config-path=./config --config-name='ppo_megat
actor_rollout_ref.rollout.free_cache_engine=True \
actor_rollout_ref.ref.log_prob_micro_batch_size_per_gpu=${infer_ppo_micro_batch_size_per_gpu} \
actor_rollout_ref.ref.log_prob_max_token_len_per_gpu=${infer_ppo_max_token_len} \
actor_rollout_ref.ref.megatron.use_dist_checkpointing=True \
actor_rollout_ref.ref.megatron.use_dist_checkpointing=${USE_DIST_CKPT} \
actor_rollout_ref.ref.megatron.param_offload=${offload} \
actor_rollout_ref.ref.megatron.tensor_model_parallel_size=${REF_TP} \
actor_rollout_ref.ref.megatron.pipeline_model_parallel_size=${REF_PP} \
@ -192,4 +192,4 @@ python3 -m verl.trainer.main_ppo --config-path=./config --config-name='ppo_megat
trainer.save_freq=100 \
trainer.total_epochs=10 \
trainer.resume_mode=auto \
trainer.log_val_generations=10
trainer.log_val_generations=10