UCT HPC cluster

JOB DETAILS FOR JOB 601809

captured Mon Mar 16 22:32:01 SAST 2026

MaxRAM=5.5G
MaxVMSize=0G
AveCPUFreq=10K
AveDiskRead=50789031855
AveDiskWrite=1231438418

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8112 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=1-13:33:24 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-03-15T08:58:34 EligibleTime=2026-03-15T08:58:34
   AccrueTime=2026-03-15T08:58:36
   StartTime=2026-03-15T08:58:37 EndTime=2026-03-17T08:58:37 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-03-15T08:58:37 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:561382
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=36568M,node=1,billing=9,gres/gpu=2,gres/gpu:ampere=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=8-11 Mem=36568 GRES=gpu:ampere:2(IDX:2-3)
   MinCPUsNode=4 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-601809.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-601809.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:4
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 601809

captured Mon Mar 16 22:32:45 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8112 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=1-13:33:52 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-03-15T08:58:34 EligibleTime=2026-03-15T08:58:34
   AccrueTime=2026-03-15T08:58:36
   StartTime=2026-03-15T08:58:37 EndTime=2026-03-16T22:32:29 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-03-15T08:58:37 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:561382
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=36568M,node=1,billing=9,gres/gpu=2,gres/gpu:ampere=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=8-11 Mem=36568 GRES=
   MinCPUsNode=4 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-601809.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-601809.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:4
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 601809

captured Mon Mar 16 22:33:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8112 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=1-13:33:52 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-03-15T08:58:34 EligibleTime=2026-03-15T08:58:34
   AccrueTime=2026-03-15T08:58:36
   StartTime=2026-03-15T08:58:37 EndTime=2026-03-16T22:32:29 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-03-15T08:58:37 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:561382
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=36568M,node=1,billing=9,gres/gpu=2,gres/gpu:ampere=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=8-11 Mem=36568 GRES=
   MinCPUsNode=4 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-601809.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-601809.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:4
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 601809

captured Mon Mar 16 22:33:42 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8112 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=1-13:33:52 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-03-15T08:58:34 EligibleTime=2026-03-15T08:58:34
   AccrueTime=2026-03-15T08:58:36
   StartTime=2026-03-15T08:58:37 EndTime=2026-03-16T22:32:29 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-03-15T08:58:37 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:561382
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=36568M,node=1,billing=9,gres/gpu=2,gres/gpu:ampere=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=8-11 Mem=36568 GRES=
   MinCPUsNode=4 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-601809.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-601809.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:4
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 601809

captured Mon Mar 16 22:34:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8112 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=1-13:33:52 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-03-15T08:58:34 EligibleTime=2026-03-15T08:58:34
   AccrueTime=2026-03-15T08:58:36
   StartTime=2026-03-15T08:58:37 EndTime=2026-03-16T22:32:29 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-03-15T08:58:37 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:561382
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=36568M,node=1,billing=9,gres/gpu=2,gres/gpu:ampere=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=8-11 Mem=36568 GRES=
   MinCPUsNode=4 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-601809.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-601809.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:4
   MailUser=lmbanr001 MailType=END,FAIL