verl/examples/grpo_trainer/run_qwen3-8b_npu.sh at 92a1cda881e8f8d07b72d3190c56cf5ae214c245 · ChibiQuest/verl · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
set -x

project_name='GRPO-Qwen3'
exp_name='GRPO-Qwen3-8B-npu'
gen_tp=2
RAY_DATA_HOME=${RAY_DATA_HOME:-"${HOME}/verl"}
MODEL_PATH=${MODEL_PATH:-"${RAY_DATA_HOME}/models/Qwen3-8B"}
CKPTS_DIR=${CKPTS_DIR:-"${RAY_DATA_HOME}/ckpts/${project_name}/${exp_name}"}
TRAIN_FILE=${TRAIN_FILE:-"${RAY_DATA_HOME}/data/dapo-math-17k.parquet"}
TEST_FILE=${TEST_FILE:-"${RAY_DATA_HOME}/data/aime-2024.parquet"}

python3 -m verl.trainer.main_ppo \
    algorithm.adv_estimator=grpo \
    data.train_files="${TRAIN_FILE}" \
    data.val_files="${TEST_FILE}" \
    data.train_batch_size=256 \
    data.max_prompt_length=512 \
    data.max_response_length=1024 \
    data.filter_overlong_prompts=True \
    data.truncation='error' \
    actor_rollout_ref.model.path=${MODEL_PATH} \
    actor_rollout_ref.actor.optim.lr=1e-6 \
    actor_rollout_ref.model.use_remove_padding=True \
    actor_rollout_ref.actor.ppo_mini_batch_size=64 \
    actor_rollout_ref.actor.ppo_micro_batch_size_per_gpu=10 \
    actor_rollout_ref.actor.use_kl_loss=True \
    actor_rollout_ref.actor.kl_loss_coef=0.001 \
    actor_rollout_ref.actor.kl_loss_type=low_var_kl \
    actor_rollout_ref.actor.entropy_coeff=0 \
    actor_rollout_ref.actor.use_torch_compile=False \
    actor_rollout_ref.ref.use_torch_compile=False \
    actor_rollout_ref.model.enable_gradient_checkpointing=True \
    actor_rollout_ref.actor.fsdp_config.param_offload=False \
    actor_rollout_ref.actor.fsdp_config.optimizer_offload=False \
    actor_rollout_ref.rollout.log_prob_micro_batch_size_per_gpu=32 \
    actor_rollout_ref.rollout.tensor_model_parallel_size=${gen_tp} \
    actor_rollout_ref.rollout.name=vllm \
    actor_rollout_ref.rollout.gpu_memory_utilization=0.6 \
    actor_rollout_ref.rollout.n=5 \
    actor_rollout_ref.ref.log_prob_micro_batch_size_per_gpu=32 \
    actor_rollout_ref.ref.fsdp_config.param_offload=True \
    algorithm.use_kl_in_reward=False \
    trainer.critic_warmup=0 \
    trainer.logger='["console","wandb"]' \
    trainer.project_name="${project_name}" \
    trainer.experiment_name="${exp_name}" \
    trainer.n_gpus_per_node=8 \
    trainer.nnodes=1 \
    trainer.default_local_dir=${CKPTS_DIR} \
    trainer.resume_mode=auto \
    actor_rollout_ref.actor.fsdp_config.forward_prefetch=True \
    actor_rollout_ref.ref.fsdp_config.forward_prefetch=True \
    ++actor_rollout_ref.actor.entropy_from_logits_with_chunking=True \
    ++actor_rollout_ref.ref.entropy_from_logits_with_chunking=True \
    ++actor_rollout_ref.rollout.checkpoint_engine.update_weights_bucket_megabytes=4096 \
    trainer.val_before_train=True \
    trainer.save_freq=5 \
    trainer.test_freq=5 \
    trainer.total_epochs=15