mirror of
https://github.com/volcengine/verl.git
synced 2025-10-20 21:53:50 +08:00
47 lines
1.9 KiB
Bash
47 lines
1.9 KiB
Bash
set -x
|
|
|
|
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="['$gsm8k_train_path', '$math_train_path']"
|
|
test_files="['$gsm8k_test_path', '$math_test_path']"
|
|
|
|
python3 -m verl.trainer.main_ppo \
|
|
data.train_files="$train_files" \
|
|
data.val_files="$test_files" \
|
|
data.train_batch_size=1024 \
|
|
data.val_batch_size=6312 \
|
|
data.max_prompt_length=1024 \
|
|
data.max_response_length=512 \
|
|
actor_rollout_ref.model.path=Qwen/Qwen2-7B-Instruct \
|
|
actor_rollout_ref.actor.optim.lr=1e-6 \
|
|
actor_rollout_ref.actor.ppo_mini_batch_size=256 \
|
|
actor_rollout_ref.actor.ppo_micro_batch_size=16 \
|
|
actor_rollout_ref.actor.fsdp_config.param_offload=False \
|
|
actor_rollout_ref.actor.fsdp_config.grad_offload=False \
|
|
actor_rollout_ref.actor.fsdp_config.optimizer_offload=False \
|
|
actor_rollout_ref.rollout.log_prob_micro_batch_size=16 \
|
|
actor_rollout_ref.rollout.tensor_model_parallel_size=2 \
|
|
actor_rollout_ref.rollout.name=vllm \
|
|
actor_rollout_ref.rollout.gpu_memory_utilization=0.4 \
|
|
actor_rollout_ref.ref.log_prob_micro_batch_size=16 \
|
|
actor_rollout_ref.ref.fsdp_config.param_offload=True \
|
|
critic.optim.lr=1e-5 \
|
|
critic.model.path=Qwen/Qwen2-7B-Instruct \
|
|
critic.model.enable_gradient_checkpointing=False \
|
|
critic.ppo_micro_batch_size=16 \
|
|
critic.model.fsdp_config.param_offload=False \
|
|
critic.model.fsdp_config.grad_offload=False \
|
|
critic.model.fsdp_config.optimizer_offload=False \
|
|
algorithm.kl_ctrl.kl_coef=0.001 \
|
|
trainer.critic_warmup=0 \
|
|
trainer.logger=['console','tracking'] \
|
|
trainer.project_name='verl_example' \
|
|
trainer.experiment_name='Qwen2-7B-Instruct_function_rm' \
|
|
trainer.n_gpus_per_node=8 \
|
|
trainer.nnodes=1 \
|
|
trainer.save_freq=-1 \
|
|
trainer.test_freq=10 \
|
|
trainer.total_epochs=15 |