UCT HPC cluster

JOB DETAILS FOR JOB 750175

captured Tue Apr 21 04:15:02 SAST 2026

MaxRAM=2.8G
MaxVMSize=0G
AveCPUFreq=107K
AveDiskRead=1252868174
AveDiskWrite=1580458383

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7904 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=04:01:07 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-04-20T20:55:01 EligibleTime=2026-04-20T20:55:01
   AccrueTime=2026-04-20T20:55:02
   StartTime=2026-04-21T00:13:55 EndTime=2026-04-23T00:13:55 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-21T00:13:55 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2012932
   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=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=28-35 Mem=73136 GRES=gpu:ampere: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/train_final_model.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-750175.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-750175.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 750175

captured Tue Apr 21 04:15:37 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7904 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=04:01:23 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-04-20T20:55:01 EligibleTime=2026-04-20T20:55:01
   AccrueTime=2026-04-20T20:55:02
   StartTime=2026-04-21T00:13:55 EndTime=2026-04-21T04:15:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-21T00:13:55 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2012932
   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=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=28-35 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/train_final_model.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-750175.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-750175.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 750175

captured Tue Apr 21 04:16:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7904 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=04:01:23 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-04-20T20:55:01 EligibleTime=2026-04-20T20:55:01
   AccrueTime=2026-04-20T20:55:02
   StartTime=2026-04-21T00:13:55 EndTime=2026-04-21T04:15:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-21T00:13:55 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2012932
   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=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=28-35 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/train_final_model.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-750175.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-750175.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 750175

captured Tue Apr 21 04:16:36 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7904 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=04:01:23 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-04-20T20:55:01 EligibleTime=2026-04-20T20:55:01
   AccrueTime=2026-04-20T20:55:02
   StartTime=2026-04-21T00:13:55 EndTime=2026-04-21T04:15:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-21T00:13:55 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2012932
   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=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=28-35 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/train_final_model.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-750175.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-750175.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 750175

captured Tue Apr 21 04:17:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7904 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=04:01:23 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-04-20T20:55:01 EligibleTime=2026-04-20T20:55:01
   AccrueTime=2026-04-20T20:55:02
   StartTime=2026-04-21T00:13:55 EndTime=2026-04-21T04:15:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-21T00:13:55 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2012932
   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=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=28-35 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/train_final_model.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-750175.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-750175.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 750175

captured Tue Apr 21 04:17:36 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7904 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=04:01:23 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-04-20T20:55:01 EligibleTime=2026-04-20T20:55:01
   AccrueTime=2026-04-20T20:55:02
   StartTime=2026-04-21T00:13:55 EndTime=2026-04-21T04:15:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-21T00:13:55 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2012932
   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=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=28-35 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/train_final_model.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-750175.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-750175.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL