export HIP_VISIBLE_DEVICES=0,1,2,3,4,5,6,7

#export ROCR_VISIBLE_DEVICES=$HIP_VISIBLE_DEVICES
#export CUDA_VISIBLE_DEVICES=$HIP_VISIBLE_DEVICES
export RAY_EXPERIMENTAL_NOSET_HIP_VISIBLE_DEVICES=1
#unset ROCR_VISIBLE_DEVICES
# PYTHONUNBUFFERED=1 python3 -m verl.trainer.main_ppo \
#  data.train_files=/data/gsm8k/train.parquet \
#  data.val_files=/data/gsm8k/test.parquet \
#  data.train_batch_size=256 \
#  data.max_prompt_length=512 \
#  data.max_response_length=256 \
#  actor_rollout_ref.model.path=/model/Qwen2.5-0.5B-Instruct \
#  actor_rollout_ref.actor.optim.lr=1e-6 \
#  actor_rollout_ref.actor.ppo_mini_batch_size=64 \
#  actor_rollout_ref.actor.ppo_micro_batch_size_per_gpu=4 \
#  actor_rollout_ref.rollout.log_prob_micro_batch_size_per_gpu=4 \
#  actor_rollout_ref.rollout.tensor_model_parallel_size=1 \
#  actor_rollout_ref.rollout.gpu_memory_utilization=0.4 \
#  actor_rollout_ref.ref.log_prob_micro_batch_size_per_gpu=4 \
#  critic.optim.lr=1e-5 \
#  critic.model.path=/model/Qwen2.5-0.5B-Instruct \
#  critic.ppo_micro_batch_size_per_gpu=4 \
#  algorithm.kl_ctrl.kl_coef=0.001 \
#  trainer.logger=console \
#  trainer.val_before_train=False \
#  trainer.n_gpus_per_node=1 \
#  trainer.nnodes=1 \
#  trainer.save_freq=10 \
#  trainer.test_freq=10 \
#  trainer.total_epochs=15 2>&1 | tee verl_demo.log

PYTHONUNBUFFERED=1 python3 -m verl.trainer.main_ppo \
 algorithm.adv_estimator=grpo \
 data.train_files=/data/gsm8k/train.parquet \
 data.val_files=/data/gsm8k/test.parquet \
 data.train_batch_size=1024 \
 data.max_prompt_length=512 \
 data.max_response_length=1024 \
 data.filter_overlong_prompts=True \
 data.truncation='error' \
 actor_rollout_ref.model.path=/model/Qwen2.5-0.5B-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=32 \
 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.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=1 \
 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 \
 trainer.critic_warmup=0 \
 trainer.logger=['console'] \
 trainer.project_name='test' \
 trainer.experiment_name='qwen2_5_0_5b_function_rm' \
 trainer.n_gpus_per_node=8 \
 trainer.default_local_dir=/verl/qwen2_5_14b_verl_grpo_8 \
 trainer.nnodes=1 \
 trainer.save_freq=5 \
 trainer.test_freq=5 \
 trainer.total_epochs=1


# export CUDA_VISIBLE_DEVICES=0
# export RAY_DISABLE_GPU_AUTODETECTION=1
# PYTHONUNBUFFERED=1 python3 -m verl.trainer.main_ppo \
#  data.train_files=/data/gsm8k/train.parquet \
#  data.val_files=/data/gsm8k/test.parquet \
#  data.train_batch_size=256 \
#  data.max_prompt_length=512 \
#  data.max_response_length=256 \
#  actor_rollout_ref.model.path=/model/Qwen2.5-0.5B-Instruct \
#  actor_rollout_ref.actor.optim.lr=1e-6 \
#  actor_rollout_ref.actor.ppo_mini_batch_size=64 \
#  actor_rollout_ref.actor.ppo_micro_batch_size_per_gpu=4 \
#  actor_rollout_ref.rollout.log_prob_micro_batch_size_per_gpu=4 \
#  actor_rollout_ref.rollout.tensor_model_parallel_size=1 \
#  actor_rollout_ref.rollout.gpu_memory_utilization=0.4 \
#  actor_rollout_ref.ref.log_prob_micro_batch_size_per_gpu=4 \
#  critic.optim.lr=1e-5 \
#  critic.model.path=/model/Qwen2.5-0.5B-Instruct \
#  critic.ppo_micro_batch_size_per_gpu=4 \
#  algorithm.kl_ctrl.kl_coef=0.001 \
#  trainer.logger=console \
#  trainer.val_before_train=False \
#  trainer.n_gpus_per_node=1 \
#  trainer.nnodes=1 \
#  trainer.save_freq=10 \
#  trainer.test_freq=10 \
#  trainer.total_epochs=15 2>&1 | tee verl_demo.log