UCT HPC cluster

JOB DETAILS FOR JOB 1343004

captured Wed Sep 16 17:59:49 SAST 2026

MaxRAM=0G
MaxVMSize=0G
AveCPUFreq=
AveDiskRead=
AveDiskWrite=

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8240 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=00:56:09 TimeLimit=04:00:00 TimeMin=N/A
   SubmitTime=2026-09-16T11:47:30 EligibleTime=2026-09-16T17:03:40
   AccrueTime=2026-09-16T13:17:06
   StartTime=2026-09-16T17:03:40 EndTime=2026-09-16T21:03:40 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-16T17:03:40 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:601721
   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=8-15 Mem=73136 GRES=gpu:ampere:2(IDX:2-3)
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260916_v4r2/audit/run_mzansilm_sib_mono_recovery_v4r2_20260916.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260916_v4r2/logs/training-1343004_5.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260916_v4r2/logs/training-1343004_5.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1343004

captured Wed Sep 16 18:00:31 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8240 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=00:56:24 TimeLimit=04:00:00 TimeMin=N/A
   SubmitTime=2026-09-16T11:47:30 EligibleTime=2026-09-16T17:03:40
   AccrueTime=2026-09-16T13:17:06
   StartTime=2026-09-16T17:03:40 EndTime=2026-09-16T18:00:04 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-16T17:03:40 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:601721
   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=8-15 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260916_v4r2/audit/run_mzansilm_sib_mono_recovery_v4r2_20260916.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260916_v4r2/logs/training-1343004_5.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260916_v4r2/logs/training-1343004_5.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1343004

captured Wed Sep 16 18:01:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8240 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=00:56:24 TimeLimit=04:00:00 TimeMin=N/A
   SubmitTime=2026-09-16T11:47:30 EligibleTime=2026-09-16T17:03:40
   AccrueTime=2026-09-16T13:17:06
   StartTime=2026-09-16T17:03:40 EndTime=2026-09-16T18:00:04 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-16T17:03:40 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:601721
   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=8-15 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260916_v4r2/audit/run_mzansilm_sib_mono_recovery_v4r2_20260916.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260916_v4r2/logs/training-1343004_5.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260916_v4r2/logs/training-1343004_5.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1343004

captured Wed Sep 16 18:01:45 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8240 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=00:56:24 TimeLimit=04:00:00 TimeMin=N/A
   SubmitTime=2026-09-16T11:47:30 EligibleTime=2026-09-16T17:03:40
   AccrueTime=2026-09-16T13:17:06
   StartTime=2026-09-16T17:03:40 EndTime=2026-09-16T18:00:04 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-16T17:03:40 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:601721
   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=8-15 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260916_v4r2/audit/run_mzansilm_sib_mono_recovery_v4r2_20260916.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260916_v4r2/logs/training-1343004_5.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260916_v4r2/logs/training-1343004_5.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1343004

captured Wed Sep 16 18:02:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8240 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=00:56:24 TimeLimit=04:00:00 TimeMin=N/A
   SubmitTime=2026-09-16T11:47:30 EligibleTime=2026-09-16T17:03:40
   AccrueTime=2026-09-16T13:17:06
   StartTime=2026-09-16T17:03:40 EndTime=2026-09-16T18:00:04 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-16T17:03:40 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:601721
   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=8-15 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260916_v4r2/audit/run_mzansilm_sib_mono_recovery_v4r2_20260916.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260916_v4r2/logs/training-1343004_5.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260916_v4r2/logs/training-1343004_5.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL