JOB DETAILS FOR JOB 152780

captured Fri May 30 02:23:01 SAST 2025

MaxRAM=0.5G
MaxVMSize=0G
AveCPUFreq=3.30M
AveDiskRead=135866739
AveDiskWrite=21580

JobId=152780 JobName=opt_1000
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7406 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:10 TimeLimit=10:00:00 TimeMin=N/A
   SubmitTime=2025-05-30T02:22:51 EligibleTime=2025-05-30T02:22:51
   AccrueTime=2025-05-30T02:22:51
   StartTime=2025-05-30T02:22:51 EndTime=2025-05-30T12:22:51 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-05-30T02:22:51 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc200:1809822
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=12 NumTasks=1 CPUs/Task=12 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=12,mem=100G,node=1,billing=22,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=12,mem=100G,node=1,billing=22,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=4-9,28-33 Mem=102400 GRES=gpu:l40s:1(IDX:2)
   MinCPUsNode=12 MinMemoryNode=100G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DS/test_memorization_gpu.sh
   WorkDir=/scratch/bxxjin001/DS
   StdErr=/scratch/bxxjin001/DS/opt_1000_152780.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DS/opt_1000_152780.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:12
UCT HPC clusterJOB DETAILS FOR JOB 152780

captured Fri May 30 02:23:32 SAST 2025

JobId=152780 JobName=opt_1000
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7406 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=2:0
   DerivedExitCode=0:0
   RunTime=00:00:12 TimeLimit=10:00:00 TimeMin=N/A
   SubmitTime=2025-05-30T02:22:51 EligibleTime=2025-05-30T02:22:51
   AccrueTime=2025-05-30T02:22:51
   StartTime=2025-05-30T02:22:51 EndTime=2025-05-30T02:23:03 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-05-30T02:22:51 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc200:1809822
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=12 NumTasks=1 CPUs/Task=12 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=12,mem=100G,node=1,billing=22,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=12,mem=100G,node=1,billing=22,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=4-9,28-33 Mem=102400 GRES=
   MinCPUsNode=12 MinMemoryNode=100G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DS/test_memorization_gpu.sh
   WorkDir=/scratch/bxxjin001/DS
   StdErr=/scratch/bxxjin001/DS/opt_1000_152780.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DS/opt_1000_152780.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:12
UCT HPC clusterJOB DETAILS FOR JOB 152780

captured Fri May 30 02:24:01 SAST 2025

JobId=152780 JobName=opt_1000
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7406 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=2:0
   DerivedExitCode=0:0
   RunTime=00:00:12 TimeLimit=10:00:00 TimeMin=N/A
   SubmitTime=2025-05-30T02:22:51 EligibleTime=2025-05-30T02:22:51
   AccrueTime=2025-05-30T02:22:51
   StartTime=2025-05-30T02:22:51 EndTime=2025-05-30T02:23:03 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-05-30T02:22:51 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc200:1809822
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=12 NumTasks=1 CPUs/Task=12 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=12,mem=100G,node=1,billing=22,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=12,mem=100G,node=1,billing=22,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=4-9,28-33 Mem=102400 GRES=
   MinCPUsNode=12 MinMemoryNode=100G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DS/test_memorization_gpu.sh
   WorkDir=/scratch/bxxjin001/DS
   StdErr=/scratch/bxxjin001/DS/opt_1000_152780.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DS/opt_1000_152780.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:12
UCT HPC clusterJOB DETAILS FOR JOB 152780

captured Fri May 30 02:24:32 SAST 2025

JobId=152780 JobName=opt_1000
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7406 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=2:0
   DerivedExitCode=0:0
   RunTime=00:00:12 TimeLimit=10:00:00 TimeMin=N/A
   SubmitTime=2025-05-30T02:22:51 EligibleTime=2025-05-30T02:22:51
   AccrueTime=2025-05-30T02:22:51
   StartTime=2025-05-30T02:22:51 EndTime=2025-05-30T02:23:03 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-05-30T02:22:51 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc200:1809822
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=12 NumTasks=1 CPUs/Task=12 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=12,mem=100G,node=1,billing=22,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=12,mem=100G,node=1,billing=22,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=4-9,28-33 Mem=102400 GRES=
   MinCPUsNode=12 MinMemoryNode=100G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DS/test_memorization_gpu.sh
   WorkDir=/scratch/bxxjin001/DS
   StdErr=/scratch/bxxjin001/DS/opt_1000_152780.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DS/opt_1000_152780.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:12
UCT HPC clusterJOB DETAILS FOR JOB 152780

captured Fri May 30 02:25:01 SAST 2025

JobId=152780 JobName=opt_1000
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7406 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=2:0
   DerivedExitCode=0:0
   RunTime=00:00:12 TimeLimit=10:00:00 TimeMin=N/A
   SubmitTime=2025-05-30T02:22:51 EligibleTime=2025-05-30T02:22:51
   AccrueTime=2025-05-30T02:22:51
   StartTime=2025-05-30T02:22:51 EndTime=2025-05-30T02:23:03 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-05-30T02:22:51 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc200:1809822
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=12 NumTasks=1 CPUs/Task=12 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=12,mem=100G,node=1,billing=22,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=12,mem=100G,node=1,billing=22,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=4-9,28-33 Mem=102400 GRES=
   MinCPUsNode=12 MinMemoryNode=100G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DS/test_memorization_gpu.sh
   WorkDir=/scratch/bxxjin001/DS
   StdErr=/scratch/bxxjin001/DS/opt_1000_152780.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DS/opt_1000_152780.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:12