您好，模型运行，然后立马退出显示运行成功，请问是什么原因

[2879982985]

#! /bin/bash
NUM_WORKERS=1
NUM_GPUS_PER_WORKER=1
MP_SIZE=1

script_path=$(realpath $0)
script_dir=$(dirname $script_path)
main_dir=$(dirname $script_dir)
MODEL_TYPE="XrayGLM"
MODEL_ARGS="--max_source_length 64
--max_target_length 256
--lora_rank 10
--pre_seq_len 4"

#OPTIONS_SAT="SAT_HOME=$1" #"SAT_HOME=/raid/dm/sat_models"
OPTIONS_NCCL="NCCL_DEBUG=info NCCL_IB_DISABLE=0 NCCL_NET_GDR_LEVEL=2"
HOST_FILE_PATH="hostfile"
HOST_FILE_PATH="hostfile_single"

train_data="./data/Xray/openi-zh.json"
eval_data="./data/Xray/openi-zh.json"

gpt_options="
--experiment-name finetune-$MODEL_TYPE
--model-parallel-size ${MP_SIZE}
--mode finetune
--train-iters 300
--resume-dataloader
$MODEL_ARGS
--train-data ${train_data}
--valid-data ${eval_data}
--distributed-backend nccl
--lr-decay-style cosine
--warmup .02
--checkpoint-activations
--save-interval 3000
--eval-interval 10000
--save "./checkpoints"
--split 1
--eval-iters 10
--eval-batch-size 8
--zero-stage 1
--lr 0.0001
--batch-size 8
--skip-init
--fp16
--use_lora
"

run_cmd="${OPTIONS_NCCL} ${OPTIONS_SAT} deepspeed --master_port 16666 --hostfile ${HOST_FILE_PATH} finetune_XrayGLM.py ${gpt_options}"
echo ${run_cmd}
eval ${run_cmd}

set +x

[2879982985]

这是输出的内容：(Xray) root@qzedu-NF5280M6:/data/ymj/XrayGLM-main/XrayGLM-main# bash finetune_XrayGLM.sh
NCCL_DEBUG=info NCCL_IB_DISABLE=0 NCCL_NET_GDR_LEVEL=2 deepspeed --master_port 16666 --hostfile hostfile_single finetune_XrayGLM.py --experiment-name finetune-XrayGLM --model-parallel-size 1 --mode finetune --train-iters 300 --resume-dataloader --max_source_length 64 --max_target_length 256 --lora_rank 10 --pre_seq_len 4 --train-data ./data/Xray/openi-zh.json --valid-data ./data/Xray/openi-zh.json --distributed-backend nccl --lr-decay-style cosine --warmup .02 --checkpoint-activations --save-interval 3000 --eval-interval 10000 --save ./checkpoints --split 1 --eval-iters 10 --eval-batch-size 8 --zero-stage 1 --lr 0.0001 --batch-size 8 --skip-init --fp16 --use_lora
[2024-10-16 11:01:15,299] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[2024-10-16 11:01:17,425] [WARNING] [runner.py:215:fetch_hostfile] Unable to find hostfile, will proceed with training with local resources only.
Detected VISIBLE_DEVICES=0: setting --include=localhost:0
[2024-10-16 11:01:17,425] [INFO] [runner.py:607:main] cmd = /home/zhuqirui/.conda/envs/Xray/bin/python -u -m deepspeed.launcher.launch --world_info=eyJsb2NhbGhvc3QiOiBbMF19 --master_addr=127.0.0.1 --master_port=16666 --enable_each_rank_log=None finetune_XrayGLM.py --experiment-name finetune-XrayGLM --model-parallel-size 1 --mode finetune --train-iters 300 --resume-dataloader --max_source_length 64 --max_target_length 256 --lora_rank 10 --pre_seq_len 4 --train-data ./data/Xray/openi-zh.json --valid-data ./data/Xray/openi-zh.json --distributed-backend nccl --lr-decay-style cosine --warmup .02 --checkpoint-activations --save-interval 3000 --eval-interval 10000 --save ./checkpoints --split 1 --eval-iters 10 --eval-batch-size 8 --zero-stage 1 --lr 0.0001 --batch-size 8 --skip-init --fp16 --use_lora
[2024-10-16 11:01:18,931] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[2024-10-16 11:01:21,018] [INFO] [launch.py:139:main] 0 NCCL_DEBUG=info
[2024-10-16 11:01:21,018] [INFO] [launch.py:139:main] 0 NCCL_NET_GDR_LEVEL=2
[2024-10-16 11:01:21,018] [INFO] [launch.py:139:main] 0 NCCL_IB_DISABLE=0
[2024-10-16 11:01:21,018] [INFO] [launch.py:146:main] WORLD INFO DICT: {'localhost': [0]}
[2024-10-16 11:01:21,018] [INFO] [launch.py:152:main] nnodes=1, num_local_procs=1, node_rank=0
[2024-10-16 11:01:21,018] [INFO] [launch.py:163:main] global_rank_mapping=defaultdict(<class 'list'>, {'localhost': [0]})
[2024-10-16 11:01:21,018] [INFO] [launch.py:164:main] dist_world_size=1
[2024-10-16 11:01:21,018] [INFO] [launch.py:168:main] Setting CUDA_VISIBLE_DEVICES=0
[2024-10-16 11:01:21,030] [INFO] [launch.py:256:main] process 38741 spawned with command: ['/home/zhuqirui/.conda/envs/Xray/bin/python', '-u', 'finetune_XrayGLM.py', '--local_rank=0', '--experiment-name', 'finetune-XrayGLM', '--model-parallel-size', '1', '--mode', 'finetune', '--train-iters', '300', '--resume-dataloader', '--max_source_length', '64', '--max_target_length', '256', '--lora_rank', '10', '--pre_seq_len', '4', '--train-data', './data/Xray/openi-zh.json', '--valid-data', './data/Xray/openi-zh.json', '--distributed-backend', 'nccl', '--lr-decay-style', 'cosine', '--warmup', '.02', '--checkpoint-activations', '--save-interval', '3000', '--eval-interval', '10000', '--save', './checkpoints', '--split', '1', '--eval-iters', '10', '--eval-batch-size', '8', '--zero-stage', '1', '--lr', '0.0001', '--batch-size', '8', '--skip-init', '--fp16', '--use_lora']
[2024-10-16 11:01:22,499] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[2024-10-16 11:01:27,036] [INFO] [launch.py:351:main] Process 38741 exits successfully.
(Xray) root@qzedu-NF5280M6:/data/ymj/XrayGLM-main/XrayGLM-main#