UCT HPC cluster

JOB DETAILS FOR JOB 941626

captured Fri Jun 19 23:48:37 SAST 2026

MaxRAM=2.1G
MaxVMSize=0G
AveCPUFreq=1.26M
AveDiskRead=943796955
AveDiskWrite=4787426

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8475 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:39:10 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-06-19T13:00:41 EligibleTime=2026-06-19T13:00:41
   AccrueTime=2026-06-19T13:00:43
   StartTime=2026-06-19T23:09:27 EndTime=2026-06-21T23:09:27 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-06-19T23:09:27 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1103357
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=2-3,6-11 Mem=73136 GRES=gpu:ampere80:1(IDX:1)
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/launch_hpo.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-941626.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-941626.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 941626

captured Fri Jun 19 23:49:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8475 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:39:32 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-06-19T13:00:41 EligibleTime=2026-06-19T13:00:41
   AccrueTime=2026-06-19T13:00:43
   StartTime=2026-06-19T23:09:27 EndTime=2026-06-19T23:48:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-06-19T23:09:27 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1103357
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=2-3,6-11 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/launch_hpo.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-941626.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-941626.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 941626

captured Fri Jun 19 23:49:37 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8475 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:39:32 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-06-19T13:00:41 EligibleTime=2026-06-19T13:00:41
   AccrueTime=2026-06-19T13:00:43
   StartTime=2026-06-19T23:09:27 EndTime=2026-06-19T23:48:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-06-19T23:09:27 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1103357
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=2-3,6-11 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/launch_hpo.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-941626.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-941626.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 941626

captured Fri Jun 19 23:50:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8475 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:39:32 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-06-19T13:00:41 EligibleTime=2026-06-19T13:00:41
   AccrueTime=2026-06-19T13:00:43
   StartTime=2026-06-19T23:09:27 EndTime=2026-06-19T23:48:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-06-19T23:09:27 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1103357
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=2-3,6-11 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/launch_hpo.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-941626.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-941626.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 941626

captured Fri Jun 19 23:50:38 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8475 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:39:32 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-06-19T13:00:41 EligibleTime=2026-06-19T13:00:41
   AccrueTime=2026-06-19T13:00:43
   StartTime=2026-06-19T23:09:27 EndTime=2026-06-19T23:48:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-06-19T23:09:27 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1103357
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=2-3,6-11 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/launch_hpo.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-941626.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-941626.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 941626

captured Fri Jun 19 23:51:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8475 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:39:32 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-06-19T13:00:41 EligibleTime=2026-06-19T13:00:41
   AccrueTime=2026-06-19T13:00:43
   StartTime=2026-06-19T23:09:27 EndTime=2026-06-19T23:48:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-06-19T23:09:27 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1103357
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=2-3,6-11 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/launch_hpo.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-941626.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-941626.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL