# run on 4xH100
# make sure your current working directory is the root of the project

set -x
export HYDRA_FULL_ERROR=1
export VLLM_USE_V1=1
ulimit -n 65535

PROJECT_DIR="$(pwd)"
CONFIG_PATH="$PROJECT_DIR/examples/sglang_multiturn/config"

python3 -u -m verl.trainer.main_ppo \
    --config-path="$CONFIG_PATH" \
    --config-name='gsm8k_multiturn_grpo' \
    algorithm.adv_estimator=grpo \
    data.train_batch_size=128 \
    data.max_prompt_length=1024 \
    data.max_response_length=1024 \
    data.filter_overlong_prompts=True \
    data.truncation='error' \
    data.return_raw_chat=True \
    actor_rollout_ref.model.path=/vllm-workspace/Qwen2.5-3B-Instruct \
    actor_rollout_ref.model.use_remove_padding=True \
    actor_rollout_ref.actor.use_torch_compile=False \
    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=16 \
    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=16 \
    actor_rollout_ref.rollout.tensor_model_parallel_size=4 \
    actor_rollout_ref.rollout.name=vllm \
    actor_rollout_ref.rollout.mode=async \
    actor_rollout_ref.rollout.gpu_memory_utilization=0.5 \
    actor_rollout_ref.rollout.n=8 \
    actor_rollout_ref.ref.log_prob_micro_batch_size_per_gpu=16 \
    actor_rollout_ref.ref.fsdp_config.param_offload=True \
    algorithm.use_kl_in_reward=False \
    trainer.val_before_train=True \
    trainer.critic_warmup=0 \
    trainer.logger='["console", "swanlab"]' \
    trainer.project_name='gsm8k_async_rl_0904' \
    trainer.experiment_name='qwen2.5-3b_function_rm-gsm8k-async-vllm-ascend-multi-w-tool-verify-n16-4cards_0904' \
    trainer.n_gpus_per_node=4 \
    trainer.nnodes=1 \
    trainer.save_freq=10 \
    trainer.test_freq=10 \
    trainer.total_training_steps=100 \
    actor_rollout_ref.actor.ppo_max_token_len_per_gpu=8192 \
    actor_rollout_ref.rollout.log_prob_max_token_len_per_gpu=8192 \
    actor_rollout_ref.ref.log_prob_max_token_len_per_gpu=8192 \
    critic.ppo_max_token_len_per_gpu=8192 \
    critic.forward_max_token_len_per_gpu=8192 \
    data.train_files=$HOME/data/gsm8k/train.parquet \
    data.val_files=$HOME/data/gsm8k/test.parquet \
    actor_rollout_ref.rollout.multi_turn.enable=True \
    actor_rollout_ref.rollout.multi_turn.format=hermes \
    actor_rollout_ref.rollout.multi_turn.tool_config_path="$PROJECT_DIR/examples/sglang_multiturn/config/tool_config/gsm8k_tool_config.yaml" \
    actor_rollout_ref.rollout.multi_turn.max_user_turns=1 \
    trainer.device=npu $@