UCT HPC cluster

JOB DETAILS FOR JOB 161706

captured Mon Jun 16 17:57:38 SAST 2025

MaxRAM=0G
MaxVMSize=0G
AveCPUFreq=
AveDiskRead=
AveDiskWrite=

JobId=161706 JobName=MiTCP_Multi
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7281 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=00:20:39 TimeLimit=06:00:00 TimeMin=N/A
   SubmitTime=2025-06-16T17:36:59 EligibleTime=2025-06-16T17:36:59
   AccrueTime=2025-06-16T17:36:59
   StartTime=2025-06-16T17:36:59 EndTime=2025-06-16T23:36:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-16T17:36:59 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:513171
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=12 NumTasks=12 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=12,mem=120000M,node=1,billing=23,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=12,mem=120000M,node=1,billing=23,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=11-16,34-39 Mem=120000 GRES=gpu:l40s:1(IDX:3)
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/submit_train_mini.sh
   WorkDir=/scratch/bxxjin001/DDR/code
   StdErr=/scratch/bxxjin001/DDR/logs/train_multi_161706.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/logs/train_multi_161706.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=END

UCT HPC clusterJOB DETAILS FOR JOB 161706

captured Mon Jun 16 17:58:02 SAST 2025

JobId=161706 JobName=MiTCP_Multi
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7281 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:20:44 TimeLimit=06:00:00 TimeMin=N/A
   SubmitTime=2025-06-16T17:36:59 EligibleTime=2025-06-16T17:36:59
   AccrueTime=2025-06-16T17:36:59
   StartTime=2025-06-16T17:36:59 EndTime=2025-06-16T17:57:43 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-16T17:36:59 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:513171
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=12 NumTasks=12 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=12,mem=120000M,node=1,billing=23,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=12,mem=120000M,node=1,billing=23,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=11-16,34-39 Mem=120000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/submit_train_mini.sh
   WorkDir=/scratch/bxxjin001/DDR/code
   StdErr=/scratch/bxxjin001/DDR/logs/train_multi_161706.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/logs/train_multi_161706.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=END

UCT HPC clusterJOB DETAILS FOR JOB 161706

captured Mon Jun 16 17:58:43 SAST 2025

JobId=161706 JobName=MiTCP_Multi
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7281 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:20:44 TimeLimit=06:00:00 TimeMin=N/A
   SubmitTime=2025-06-16T17:36:59 EligibleTime=2025-06-16T17:36:59
   AccrueTime=2025-06-16T17:36:59
   StartTime=2025-06-16T17:36:59 EndTime=2025-06-16T17:57:43 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-16T17:36:59 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:513171
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=12 NumTasks=12 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=12,mem=120000M,node=1,billing=23,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=12,mem=120000M,node=1,billing=23,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=11-16,34-39 Mem=120000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/submit_train_mini.sh
   WorkDir=/scratch/bxxjin001/DDR/code
   StdErr=/scratch/bxxjin001/DDR/logs/train_multi_161706.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/logs/train_multi_161706.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=END

UCT HPC clusterJOB DETAILS FOR JOB 161706

captured Mon Jun 16 17:59:01 SAST 2025

JobId=161706 JobName=MiTCP_Multi
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7281 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:20:44 TimeLimit=06:00:00 TimeMin=N/A
   SubmitTime=2025-06-16T17:36:59 EligibleTime=2025-06-16T17:36:59
   AccrueTime=2025-06-16T17:36:59
   StartTime=2025-06-16T17:36:59 EndTime=2025-06-16T17:57:43 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-16T17:36:59 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:513171
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=12 NumTasks=12 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=12,mem=120000M,node=1,billing=23,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=12,mem=120000M,node=1,billing=23,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=11-16,34-39 Mem=120000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/submit_train_mini.sh
   WorkDir=/scratch/bxxjin001/DDR/code
   StdErr=/scratch/bxxjin001/DDR/logs/train_multi_161706.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/logs/train_multi_161706.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=END

UCT HPC clusterJOB DETAILS FOR JOB 161706

captured Mon Jun 16 17:59:43 SAST 2025

JobId=161706 JobName=MiTCP_Multi
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7281 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:20:44 TimeLimit=06:00:00 TimeMin=N/A
   SubmitTime=2025-06-16T17:36:59 EligibleTime=2025-06-16T17:36:59
   AccrueTime=2025-06-16T17:36:59
   StartTime=2025-06-16T17:36:59 EndTime=2025-06-16T17:57:43 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-16T17:36:59 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:513171
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=12 NumTasks=12 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=12,mem=120000M,node=1,billing=23,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=12,mem=120000M,node=1,billing=23,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=11-16,34-39 Mem=120000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/submit_train_mini.sh
   WorkDir=/scratch/bxxjin001/DDR/code
   StdErr=/scratch/bxxjin001/DDR/logs/train_multi_161706.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/logs/train_multi_161706.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=END

UCT HPC clusterJOB DETAILS FOR JOB 161706

captured Mon Jun 16 18:00:01 SAST 2025

JobId=161706 JobName=MiTCP_Multi
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7281 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:20:44 TimeLimit=06:00:00 TimeMin=N/A
   SubmitTime=2025-06-16T17:36:59 EligibleTime=2025-06-16T17:36:59
   AccrueTime=2025-06-16T17:36:59
   StartTime=2025-06-16T17:36:59 EndTime=2025-06-16T17:57:43 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-16T17:36:59 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:513171
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=12 NumTasks=12 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=12,mem=120000M,node=1,billing=23,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=12,mem=120000M,node=1,billing=23,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=11-16,34-39 Mem=120000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/submit_train_mini.sh
   WorkDir=/scratch/bxxjin001/DDR/code
   StdErr=/scratch/bxxjin001/DDR/logs/train_multi_161706.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/logs/train_multi_161706.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=END