UCT HPC cluster

JOB DETAILS FOR JOB 68041

captured Mon Feb 3 21:16:02 SAST 2025

MaxRAM=104.9G
MaxVMSize=0G
AveCPUFreq=202K
AveDiskRead=19465538690
AveDiskWrite=33746120551

JobId=68041 JobName=bone_gen
   UserId=vvnmax002(1221868618 Max Van Veen) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7364 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=02:10:01 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-02-03T19:06:01 EligibleTime=2025-02-03T19:06:01
   AccrueTime=2025-02-03T19:06:01
   StartTime=2025-02-03T19:06:01 EndTime=2025-02-05T19:06:01 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-02-03T19:06:01 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3003503
   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=2-7,26-31 Mem=120000 GRES=gpu:l40s:1(IDX:1)
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/vvnmax002/OneTrainer/job.sh
   WorkDir=/home/vvnmax002/OneTrainer
   StdErr=/home/vvnmax002/OneTrainer/slurm-68041.out
   StdIn=/dev/null
   StdOut=/home/vvnmax002/OneTrainer/slurm-68041.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=VVNMAX002@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 68041

captured Mon Feb 3 21:16:40 SAST 2025

JobId=68041 JobName=bone_gen
   UserId=vvnmax002(1221868618 Max Van Veen) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7364 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=02:10:17 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-02-03T19:06:01 EligibleTime=2025-02-03T19:06:01
   AccrueTime=2025-02-03T19:06:01
   StartTime=2025-02-03T19:06:01 EndTime=2025-02-03T21:16:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-02-03T19:06:01 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3003503
   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=2-7,26-31 Mem=120000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/vvnmax002/OneTrainer/job.sh
   WorkDir=/home/vvnmax002/OneTrainer
   StdErr=/home/vvnmax002/OneTrainer/slurm-68041.out
   StdIn=/dev/null
   StdOut=/home/vvnmax002/OneTrainer/slurm-68041.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=VVNMAX002@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 68041

captured Mon Feb 3 21:17:01 SAST 2025

JobId=68041 JobName=bone_gen
   UserId=vvnmax002(1221868618 Max Van Veen) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7364 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=02:10:17 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-02-03T19:06:01 EligibleTime=2025-02-03T19:06:01
   AccrueTime=2025-02-03T19:06:01
   StartTime=2025-02-03T19:06:01 EndTime=2025-02-03T21:16:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-02-03T19:06:01 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3003503
   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=2-7,26-31 Mem=120000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/vvnmax002/OneTrainer/job.sh
   WorkDir=/home/vvnmax002/OneTrainer
   StdErr=/home/vvnmax002/OneTrainer/slurm-68041.out
   StdIn=/dev/null
   StdOut=/home/vvnmax002/OneTrainer/slurm-68041.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=VVNMAX002@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 68041

captured Mon Feb 3 21:17:40 SAST 2025

JobId=68041 JobName=bone_gen
   UserId=vvnmax002(1221868618 Max Van Veen) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7364 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=02:10:17 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-02-03T19:06:01 EligibleTime=2025-02-03T19:06:01
   AccrueTime=2025-02-03T19:06:01
   StartTime=2025-02-03T19:06:01 EndTime=2025-02-03T21:16:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-02-03T19:06:01 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3003503
   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=2-7,26-31 Mem=120000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/vvnmax002/OneTrainer/job.sh
   WorkDir=/home/vvnmax002/OneTrainer
   StdErr=/home/vvnmax002/OneTrainer/slurm-68041.out
   StdIn=/dev/null
   StdOut=/home/vvnmax002/OneTrainer/slurm-68041.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=VVNMAX002@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 68041

captured Mon Feb 3 21:18:01 SAST 2025

JobId=68041 JobName=bone_gen
   UserId=vvnmax002(1221868618 Max Van Veen) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7364 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=02:10:17 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-02-03T19:06:01 EligibleTime=2025-02-03T19:06:01
   AccrueTime=2025-02-03T19:06:01
   StartTime=2025-02-03T19:06:01 EndTime=2025-02-03T21:16:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-02-03T19:06:01 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3003503
   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=2-7,26-31 Mem=120000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/vvnmax002/OneTrainer/job.sh
   WorkDir=/home/vvnmax002/OneTrainer
   StdErr=/home/vvnmax002/OneTrainer/slurm-68041.out
   StdIn=/dev/null
   StdOut=/home/vvnmax002/OneTrainer/slurm-68041.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=VVNMAX002@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT