UCT HPC cluster

JOB DETAILS FOR JOB 417910

captured Sat Jan 10 06:15:01 SAST 2026

MaxRAM=6.3G
MaxVMSize=0G
AveCPUFreq=1K
AveDiskRead=5741994963
AveDiskWrite=237649057

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7578 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=11:07:14 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-01-09T19:07:46 EligibleTime=2026-01-09T19:07:46
   AccrueTime=2026-01-09T19:07:47
   StartTime=2026-01-09T19:07:47 EndTime=2026-01-11T19:07:47 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-09T19:07:47 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:775067
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=3,gres/gpu=2
   AllocTRES=cpu=4,mem=36568M,node=1,billing=9,gres/gpu=2,gres/gpu:ampere=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:2
     Nodes=srvrocgpu010 CPU_IDs=0-1,28-29 Mem=36568 GRES=gpu:ampere:2(IDX:0-1)
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/resume_hpo.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-417910.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-417910.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:2
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 417910

captured Sat Jan 10 06:15:35 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7578 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=11:07:45 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-01-09T19:07:46 EligibleTime=2026-01-09T19:07:46
   AccrueTime=2026-01-09T19:07:47
   StartTime=2026-01-09T19:07:47 EndTime=2026-01-10T06:15:32 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-09T19:07:47 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:775067
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=3,gres/gpu=2
   AllocTRES=cpu=4,mem=36568M,node=1,billing=9,gres/gpu=2,gres/gpu:ampere=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:2
     Nodes=srvrocgpu010 CPU_IDs=0-1,28-29 Mem=36568 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/resume_hpo.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-417910.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-417910.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:2
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 417910

captured Sat Jan 10 06:16:02 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7578 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=11:07:45 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-01-09T19:07:46 EligibleTime=2026-01-09T19:07:46
   AccrueTime=2026-01-09T19:07:47
   StartTime=2026-01-09T19:07:47 EndTime=2026-01-10T06:15:32 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-09T19:07:47 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:775067
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=3,gres/gpu=2
   AllocTRES=cpu=4,mem=36568M,node=1,billing=9,gres/gpu=2,gres/gpu:ampere=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:2
     Nodes=srvrocgpu010 CPU_IDs=0-1,28-29 Mem=36568 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/resume_hpo.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-417910.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-417910.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:2
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 417910

captured Sat Jan 10 06:16:34 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7578 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=11:07:45 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-01-09T19:07:46 EligibleTime=2026-01-09T19:07:46
   AccrueTime=2026-01-09T19:07:47
   StartTime=2026-01-09T19:07:47 EndTime=2026-01-10T06:15:32 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-09T19:07:47 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:775067
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=3,gres/gpu=2
   AllocTRES=cpu=4,mem=36568M,node=1,billing=9,gres/gpu=2,gres/gpu:ampere=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:2
     Nodes=srvrocgpu010 CPU_IDs=0-1,28-29 Mem=36568 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/resume_hpo.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-417910.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-417910.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:2
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 417910

captured Sat Jan 10 06:17:02 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7578 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=11:07:45 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-01-09T19:07:46 EligibleTime=2026-01-09T19:07:46
   AccrueTime=2026-01-09T19:07:47
   StartTime=2026-01-09T19:07:47 EndTime=2026-01-10T06:15:32 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-09T19:07:47 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:775067
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=3,gres/gpu=2
   AllocTRES=cpu=4,mem=36568M,node=1,billing=9,gres/gpu=2,gres/gpu:ampere=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:2
     Nodes=srvrocgpu010 CPU_IDs=0-1,28-29 Mem=36568 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/resume_hpo.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-417910.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-417910.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:2
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL