#!/bin/bash
export HSA_FORCE_FINE_GRAIN_PCIE=1
export MIOPEN_FIND_MODE=3
export MIOPEN_COMPILE_PARALLEL_LEVEL=1
export NCCL_PLUGIN_P2P=ucx
export RCCL_NCHANNELS=2
export NCCL_SOCKET_IFNAME=ib0
export NCCL_P2P_LEVEL=5
export NCCL_IB_HCA=mlx5_0  #0号网卡

export MASTER_ADDR=${1}
lrank=$OMPI_COMM_WORLD_LOCAL_RANK
export LOCAL_RANK=$OMPI_COMM_WORLD_LOCAL_RANK
export RANK=$OMPI_COMM_WORLD_RANK
export WORLD_SIZE=$OMPI_COMM_WORLD_SIZE
export MASTER_PORT=12365


APP="python3 ../src/train_bash.py --stage sft \
    --model_name_or_path ../../baichuan-13b-base \
    --do_train \
    --template default \
    --dataset alpaca_gpt4_en \
    --finetuning_type lora \
    --lora_rank 16 \
    --lora_target W_pack,o_proj,gate_proj,down_proj,up_proj \
    --output_dir out/baichuan-7b-lora-test7 \
    --per_device_train_batch_size 1 \
    --per_device_eval_batch_size 1 \
    --gradient_accumulation_steps 1 \
    --preprocessing_num_workers 8 \
    --lr_scheduler_type cosine \
    --logging_steps 10 \
    --save_steps 2 \
    --eval_steps 2 \
    --learning_rate 1e-4 \
    --max_grad_norm 0.5 \
    --num_train_epochs 1.0 \
    --val_size 0.001 \
    --evaluation_strategy steps \
    --load_best_model_at_end \
    --plot_loss \
    --fp16 \
    --deepspeed deepspeed.json
"

case ${lrank} in
[0])
  export HIP_VISIBLE_DEVICES=0,1,2,3
  export UCX_NET_DEVICES=mlx5_0:1
  export UCX_IB_PCI_BW=mlx5_0:50Gbs
  numactl --cpunodebind=0 --membind=0 ${APP}
  ;;
[1])
  export HIP_VISIBLE_DEVICES=0,1,2,3
  export UCX_NET_DEVICES=mlx5_1:1
  export UCX_IB_PCI_BW=mlx5_1:50Gbs
  numactl --cpunodebind=1 --membind=1 ${APP}
  ;;
[2])
  export HIP_VISIBLE_DEVICES=0,1,2,3
  export UCX_NET_DEVICES=mlx5_2:1
  export UCX_IB_PCI_BW=mlx5_2:50Gbs
  numactl --cpunodebind=2 --membind=2 ${APP}
  ;;
[3])
  export HIP_VISIBLE_DEVICES=0,1,2,3
  export UCX_NET_DEVICES=mlx5_3:1
  export UCX_IB_PCI_BW=mlx5_3:50Gbs
  numactl --cpunodebind=3 --membind=3 ${APP}
  ;;
esac