UCT HPC cluster

JOB DETAILS FOR JOB 68056

captured Mon Feb 3 23:44:01 SAST 2025

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

JobId=68056 JobName=bone_gen
   UserId=vvnmax002(1221868618 Max Van Veen) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7360 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=02:06:42 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-02-03T21:37:19 EligibleTime=2025-02-03T21:37:19
   AccrueTime=2025-02-03T21:37:19
   StartTime=2025-02-03T21:37:19 EndTime=2025-02-05T21:37:19 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-02-03T21:37:19 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-68056.out
   StdIn=/dev/null
   StdOut=/home/vvnmax002/OneTrainer/slurm-68056.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 68056

captured Mon Feb 3 23:44:42 SAST 2025

JobId=68056 JobName=bone_gen
   UserId=vvnmax002(1221868618 Max Van Veen) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7360 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=02:06:49 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-02-03T21:37:19 EligibleTime=2025-02-03T21:37:19
   AccrueTime=2025-02-03T21:37:19
   StartTime=2025-02-03T21:37:19 EndTime=2025-02-03T23:44:08 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-02-03T21:37:19 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-68056.out
   StdIn=/dev/null
   StdOut=/home/vvnmax002/OneTrainer/slurm-68056.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 68056

captured Mon Feb 3 23:45:01 SAST 2025

JobId=68056 JobName=bone_gen
   UserId=vvnmax002(1221868618 Max Van Veen) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7360 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=02:06:49 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-02-03T21:37:19 EligibleTime=2025-02-03T21:37:19
   AccrueTime=2025-02-03T21:37:19
   StartTime=2025-02-03T21:37:19 EndTime=2025-02-03T23:44:08 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-02-03T21:37:19 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-68056.out
   StdIn=/dev/null
   StdOut=/home/vvnmax002/OneTrainer/slurm-68056.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 68056

captured Mon Feb 3 23:45:42 SAST 2025

JobId=68056 JobName=bone_gen
   UserId=vvnmax002(1221868618 Max Van Veen) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7360 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=02:06:49 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-02-03T21:37:19 EligibleTime=2025-02-03T21:37:19
   AccrueTime=2025-02-03T21:37:19
   StartTime=2025-02-03T21:37:19 EndTime=2025-02-03T23:44:08 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-02-03T21:37:19 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-68056.out
   StdIn=/dev/null
   StdOut=/home/vvnmax002/OneTrainer/slurm-68056.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 68056

captured Mon Feb 3 23:46:01 SAST 2025

JobId=68056 JobName=bone_gen
   UserId=vvnmax002(1221868618 Max Van Veen) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7360 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=02:06:49 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-02-03T21:37:19 EligibleTime=2025-02-03T21:37:19
   AccrueTime=2025-02-03T21:37:19
   StartTime=2025-02-03T21:37:19 EndTime=2025-02-03T23:44:08 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-02-03T21:37:19 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-68056.out
   StdIn=/dev/null
   StdOut=/home/vvnmax002/OneTrainer/slurm-68056.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=VVNMAX002@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT