set -x

python3 -m verl.trainer.main_ppo \
    algorithm.adv_estimator=gae \
    data.train_files=$HOME/data/gsm8k/train.parquet \
    data.val_files=$HOME/data/gsm8k/test.parquet \
    data.train_batch_size=512 \
    data.max_prompt_length=1024 \
    data.max_response_length=512 \
    data.filter_overlong_prompts=True \
    data.truncation='error' \
    actor_rollout_ref.model.path=google/gemma-2-2b-it \
    actor_rollout_ref.actor.optim.lr=1e-6 \
    actor_rollout_ref.model.use_remove_padding=False \
    actor_rollout_ref.actor.ppo_mini_batch_size=128 \
    actor_rollout_ref.actor.ppo_micro_batch_size_per_gpu=4 \
    actor_rollout_ref.actor.fsdp_config.param_offload=False \
    actor_rollout_ref.actor.fsdp_config.optimizer_offload=False \
    actor_rollout_ref.actor.use_kl_loss=False \
    actor_rollout_ref.rollout.log_prob_micro_batch_size_per_gpu=4 \
    actor_rollout_ref.rollout.tensor_model_parallel_size=2 \
    actor_rollout_ref.rollout.name=vllm \
    actor_rollout_ref.rollout.gpu_memory_utilization=0.4 \
    critic.optim.lr=1e-5 \
    critic.model.use_remove_padding=False \
    critic.model.path=google/gemma-2-2b-it \
    critic.model.enable_gradient_checkpointing=False \
    critic.ppo_micro_batch_size_per_gpu=4 \
    critic.model.fsdp_config.param_offload=False \
    critic.model.fsdp_config.optimizer_offload=False \
    algorithm.use_kl_in_reward=False \
    trainer.critic_warmup=0 \
    trainer.logger=['console','wandb'] \
    trainer.project_name='verl_example' \
    trainer.experiment_name='gemma2b_function_rm' \
    trainer.n_gpus_per_node=2 \
    trainer.nnodes=1 \
    trainer.save_freq=-1 \
    trainer.test_freq=10 \
    trainer.total_epochs=15 $@