UCT HPC cluster

JOB DETAILS FOR JOB 601820

captured Tue Mar 17 09:09:35 SAST 2026

MaxRAM=4.9G
MaxVMSize=0G
AveCPUFreq=6K
AveDiskRead=16466415736
AveDiskWrite=733268745

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8160 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=1-23:59:58 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-03-15T09:09:35 EligibleTime=2026-03-15T09:09:35
   AccrueTime=Unknown
   StartTime=2026-03-15T09:09:37 EndTime=2026-03-17T09:09:37 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-03-15T09:09:37 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:682078
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=17,gres/gpu=2,gres/gpu:ampere=2
   AllocTRES=cpu=8,mem=73136M,node=1,billing=17,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=0-7 Mem=73136 GRES=gpu:ampere:2(IDX:0-1)
   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/resume_hpo.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-601820.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-601820.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 601820

captured Tue Mar 17 09:10:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8160 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:13 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-03-15T09:09:35 EligibleTime=2026-03-15T09:09:35
   AccrueTime=Unknown
   StartTime=2026-03-15T09:09:37 EndTime=2026-03-17T09:09:50 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-03-15T09:09:37 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:682078
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=17,gres/gpu=2,gres/gpu:ampere=2
   AllocTRES=cpu=8,mem=73136M,node=1,billing=17,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=0-7 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/resume_hpo.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-601820.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-601820.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 601820

captured Tue Mar 17 09:10:35 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8160 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:13 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-03-15T09:09:35 EligibleTime=2026-03-15T09:09:35
   AccrueTime=Unknown
   StartTime=2026-03-15T09:09:37 EndTime=2026-03-17T09:09:50 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-03-15T09:09:37 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:682078
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=17,gres/gpu=2,gres/gpu:ampere=2
   AllocTRES=cpu=8,mem=73136M,node=1,billing=17,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=0-7 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/resume_hpo.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-601820.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-601820.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 601820

captured Tue Mar 17 09:11:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8160 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:13 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-03-15T09:09:35 EligibleTime=2026-03-15T09:09:35
   AccrueTime=Unknown
   StartTime=2026-03-15T09:09:37 EndTime=2026-03-17T09:09:50 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-03-15T09:09:37 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:682078
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=17,gres/gpu=2,gres/gpu:ampere=2
   AllocTRES=cpu=8,mem=73136M,node=1,billing=17,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=0-7 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/resume_hpo.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-601820.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-601820.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 601820

captured Tue Mar 17 09:11:35 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8160 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:13 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-03-15T09:09:35 EligibleTime=2026-03-15T09:09:35
   AccrueTime=Unknown
   StartTime=2026-03-15T09:09:37 EndTime=2026-03-17T09:09:50 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-03-15T09:09:37 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:682078
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=17,gres/gpu=2,gres/gpu:ampere=2
   AllocTRES=cpu=8,mem=73136M,node=1,billing=17,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=0-7 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/resume_hpo.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-601820.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-601820.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL