调整为标准格式

README.md

@@ -118,7 +118,7 @@ Hugging Face模型下载地址：
 #### 集群训练
 ```
     cd ptuning/slurm_scripts
-    bash run.sh
+    bash run_train.sh
 ```
 注意：请根据自己的需求配置其中的模型路径、数据集路径、batchsize、学习率等参数；
 

ptuning/slurm_scripts/run_train.sh → ptuning/multi_nodel/run_train.sh

-#!/bin/bash
-#SBATCH -p kshdnormal01
-#SBATCH -N 4
-#SBATCH --cpus-per-task=1
-#SBATCH --ntasks-per-node=32
-#SBATCH --mem 100G
-#SBATCH --gres=dcu:4
-#SBATCH -J chatglm
-#SBATCH -o logs/pt-%j.out
-#SBATCH -e logs/pt-%j.err
 ulimit -u 200000
 
 export OMP_NUM_THREADS=1
@@ -19,23 +9,17 @@ export NCCL_PLUGIN_P2P=ucx
 export NCCL_SOCKET_IFNAME=ib0
 export NCCL_P2P_LEVEL=5
 export NCCL_NET_PLUGIN=none
-unset RCCL_NCHANNELS
-unset NCCL_NET_GDR_LEVEL
-rm -rf ./hostfile/*
 
-echo "START TIME: $(date)"
-hostfile=./hostfile/$SLURM_JOB_ID
-scontrol show hostnames $SLURM_JOB_NODELIST > ${hostfile}
 
 
-for i in `cat $hostfile`
-do
-    echo ${i} slots=4 >> `pwd`/hostfile/hostfile-dl-$SLURM_JOB_ID
-done
+echo "START TIME: $(date)"
+hostfile=./hostfile
+
 np=$(cat $hostfile|sort|uniq |wc -l)
-np=$(($np*4))
+np=$(($np*8))
+
 nodename=$(cat $hostfile |sed -n "1p")
 dist_url=`echo $nodename | awk '{print $1}'`
-echo ${dist_url}
-mpirun -np $np --hostfile hostfile/hostfile-dl-$SLURM_JOB_ID --bind-to none `pwd`/run_train_single.sh $dist_url
-
+which mpirun
+mpirun -np $np --allow-run-as-root --hostfile hostfile --bind-to none --mca btl_tcp_if_include $dist_url run_train_single.sh
+echo "END TIME: $(date)"

ptuning/slurm_scripts/run_train_single.sh → ptuning/multi_nodel/run_train_single.sh

@@ -4,15 +4,12 @@ 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
 export NCCL_DEBUG=INFO
-export NCCL_NET_GDR_LEVEL=SYS
 export NCCL_NET_PLUGIN=none
-unset RCCL_NCHANNELS
-unset NCCL_NET_GDR_LEVEL
+
 lrank=$OMPI_COMM_WORLD_LOCAL_RANK
 echo "LRANK===============================$lrank"
 RANK=$OMPI_COMM_WORLD_RANK
@@ -42,29 +39,55 @@ APP="python3 ../main.py \
     --fp16 \
     --local_rank $lrank "
 
+
+
 case ${lrank} in
 [0])
-  export HIP_VISIBLE_DEVICES=0,1,2,3
+  export HIP_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
   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 HIP_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
   export UCX_NET_DEVICES=mlx5_1:1
   export UCX_IB_PCI_BW=mlx5_1:50Gbs
-  numactl --cpunodebind=1 --membind=1 ${APP}
+  numactl --cpunodebind=0 --membind=0 ${APP}
   ;;
 [2])
-  export HIP_VISIBLE_DEVICES=0,1,2,3
+  export HIP_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
   export UCX_NET_DEVICES=mlx5_2:1
   export UCX_IB_PCI_BW=mlx5_2:50Gbs
-  numactl --cpunodebind=2 --membind=2 ${APP}
+  numactl --cpunodebind=0 --membind=0 ${APP}
   ;;
 [3])
-  export HIP_VISIBLE_DEVICES=0,1,2,3
+  export HIP_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
   export UCX_NET_DEVICES=mlx5_3:1
   export UCX_IB_PCI_BW=mlx5_3:50Gbs
+  numactl --cpunodebind=0 --membind=0 ${APP}
+  ;;
+[4])
+  export HIP_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
+  export UCX_NET_DEVICES=mlx5_4:1
+  export UCX_IB_PCI_BW=mlx5_4:50Gbs
+  numactl --cpunodebind=3 --membind=3 ${APP}
+  ;;
+[5])
+  export HIP_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
+  export UCX_NET_DEVICES=mlx5_5:1
+  export UCX_IB_PCI_BW=mlx5_5:50Gbs
   numactl --cpunodebind=3 --membind=3 ${APP}
   ;;
+[6])
+  export HIP_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
+  export UCX_NET_DEVICES=mlx5_6:1
+  export UCX_IB_PCI_BW=mlx5_6:50Gbs
+  numactl --cpunodebind=3 --membind=3 ${APP}
+  ;;
+[7])
+  export HIP_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
+  export UCX_NET_DEVICES=mlx5_7:1
+  export UCX_IB_PCI_BW=mlx5_7:50Gbs
+  numactl --cpunodebind=3 --membind=3 ${APP}
+  ;;  
 esac

ptuning/slurm_scripts/run.sh

-#/bin/bash
-
-mkdir -p logs
-#rm -rf log/*
-mkdir -p pt_output
-mkdir -p hostfile
-
-sbatch run_train.sh