UCT HPC cluster

JOB DETAILS FOR JOB 59095

captured Sun Dec 22 13:21:02 SAST 2024

MaxRAM=10.2G
MaxVMSize=0G
AveCPUFreq=4M
AveDiskRead=1744899860
AveDiskWrite=489781872

JobId=59095 JobName=bash
   UserId=vvnmax002(1221868618 Max Van Veen) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7271 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=0 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:29:49 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2024-12-22T12:51:13 EligibleTime=2024-12-22T12:51:13
   AccrueTime=Unknown
   StartTime=2024-12-22T12:51:13 EndTime=2024-12-24T12:51:13 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2024-12-22T12:51:13 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:328921
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,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=4-7,28-31 Mem=80000 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=bash
   WorkDir=/home/vvnmax002/flux/OneTrainer
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 59095

captured Sun Dec 22 13:21:32 SAST 2024

JobId=59095 JobName=bash
   UserId=vvnmax002(1221868618 Max Van Veen) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7271 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=0 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:30:04 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2024-12-22T12:51:13 EligibleTime=2024-12-22T12:51:13
   AccrueTime=Unknown
   StartTime=2024-12-22T12:51:13 EndTime=2024-12-22T13:21:17 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2024-12-22T12:51:13 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:328921
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,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=4-7,28-31 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=bash
   WorkDir=/home/vvnmax002/flux/OneTrainer
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 59095

captured Sun Dec 22 13:22:01 SAST 2024

JobId=59095 JobName=bash
   UserId=vvnmax002(1221868618 Max Van Veen) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7271 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=0 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:30:04 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2024-12-22T12:51:13 EligibleTime=2024-12-22T12:51:13
   AccrueTime=Unknown
   StartTime=2024-12-22T12:51:13 EndTime=2024-12-22T13:21:17 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2024-12-22T12:51:13 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:328921
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,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=4-7,28-31 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=bash
   WorkDir=/home/vvnmax002/flux/OneTrainer
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 59095

captured Sun Dec 22 13:22:32 SAST 2024

JobId=59095 JobName=bash
   UserId=vvnmax002(1221868618 Max Van Veen) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7271 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=0 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:30:04 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2024-12-22T12:51:13 EligibleTime=2024-12-22T12:51:13
   AccrueTime=Unknown
   StartTime=2024-12-22T12:51:13 EndTime=2024-12-22T13:21:17 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2024-12-22T12:51:13 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:328921
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,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=4-7,28-31 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=bash
   WorkDir=/home/vvnmax002/flux/OneTrainer
   Power=
   TresPerNode=gres/gpu:l40s:1