UCT HPC cluster

JOB DETAILS FOR JOB 1342861

captured Wed Sep 16 11:30:01 SAST 2026

MaxRAM=4.6G
MaxVMSize=0G
AveCPUFreq=800K
AveDiskRead=8831203714
AveDiskWrite=21548233

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8129 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=00:04:16 TimeLimit=04:00:00 TimeMin=N/A
   SubmitTime=2026-09-16T11:18:57 EligibleTime=2026-09-16T11:18:57
   AccrueTime=2026-09-16T11:18:57
   StartTime=2026-09-16T11:25:45 EndTime=2026-09-16T15:25:45 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-16T11:25:45 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:232122
   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=0-3,12-15 Mem=73136 GRES=gpu:ampere:2(IDX:0,3)
   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-1342861_0.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260916_v4r2/logs/training-1342861_0.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1342861

captured Wed Sep 16 11:30:52 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8129 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=00:04:59 TimeLimit=04:00:00 TimeMin=N/A
   SubmitTime=2026-09-16T11:18:57 EligibleTime=2026-09-16T11:18:57
   AccrueTime=2026-09-16T11:18:57
   StartTime=2026-09-16T11:25:45 EndTime=2026-09-16T11:30:44 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-16T11:25:45 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:232122
   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=0-3,12-15 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-1342861_0.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260916_v4r2/logs/training-1342861_0.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1342861

captured Wed Sep 16 11:31:32 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8129 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=00:04:59 TimeLimit=04:00:00 TimeMin=N/A
   SubmitTime=2026-09-16T11:18:57 EligibleTime=2026-09-16T11:18:57
   AccrueTime=2026-09-16T11:18:57
   StartTime=2026-09-16T11:25:45 EndTime=2026-09-16T11:30:44 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-16T11:25:45 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:232122
   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=0-3,12-15 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-1342861_0.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260916_v4r2/logs/training-1342861_0.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1342861

captured Wed Sep 16 11:32:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8129 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=00:04:59 TimeLimit=04:00:00 TimeMin=N/A
   SubmitTime=2026-09-16T11:18:57 EligibleTime=2026-09-16T11:18:57
   AccrueTime=2026-09-16T11:18:57
   StartTime=2026-09-16T11:25:45 EndTime=2026-09-16T11:30:44 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-16T11:25:45 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:232122
   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=0-3,12-15 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-1342861_0.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260916_v4r2/logs/training-1342861_0.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1342861

captured Wed Sep 16 11:32:45 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8129 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=00:04:59 TimeLimit=04:00:00 TimeMin=N/A
   SubmitTime=2026-09-16T11:18:57 EligibleTime=2026-09-16T11:18:57
   AccrueTime=2026-09-16T11:18:57
   StartTime=2026-09-16T11:25:45 EndTime=2026-09-16T11:30:44 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-16T11:25:45 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:232122
   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=0-3,12-15 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-1342861_0.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260916_v4r2/logs/training-1342861_0.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1342861

captured Wed Sep 16 11:33:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8129 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=00:04:59 TimeLimit=04:00:00 TimeMin=N/A
   SubmitTime=2026-09-16T11:18:57 EligibleTime=2026-09-16T11:18:57
   AccrueTime=2026-09-16T11:18:57
   StartTime=2026-09-16T11:25:45 EndTime=2026-09-16T11:30:44 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-16T11:25:45 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:232122
   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=0-3,12-15 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-1342861_0.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260916_v4r2/logs/training-1342861_0.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL