UCT HPC cluster

JOB DETAILS FOR JOB 1369676

captured Fri Sep 25 00:34:37 SAST 2026

MaxRAM=1.2G
MaxVMSize=0G
AveCPUFreq=800K
AveDiskRead=1275179671
AveDiskWrite=2961579

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7467 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=00:09:51 TimeLimit=06:00:00 TimeMin=N/A
   SubmitTime=2026-09-25T00:24:45 EligibleTime=2026-09-25T00:24:45
   AccrueTime=2026-09-25T00:24:45
   StartTime=2026-09-25T00:24:46 EndTime=2026-09-25T06:24:46 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-25T00:24:46 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:236428
   ReqNodeList=(null) ExcNodeList=srvrocgpu009
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=48G,node=1,billing=9,gres/gpu=1
   AllocTRES=cpu=4,mem=48G,node=1,billing=9,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=17-18,37-38 Mem=49152 GRES=gpu:ampere:1(IDX:3)
   MinCPUsNode=6 MinMemoryNode=48G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/padding-diagnostic-20260924/diag.sbatch
   WorkDir=/scratch/lmbanr001/masters/sallm_snapshots/padding-diagnostic-20260924
   StdErr=/scratch/lmbanr001/masters/sallm/results/padding_diagnostic_20260924/slurm/pad-diag-1369676.err
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/padding_diagnostic_20260924/slurm/pad-diag-1369676.out
   Power=
   TresPerNode=gres/gpu:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1369676

captured Fri Sep 25 00:35:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7467 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=00:09:58 TimeLimit=06:00:00 TimeMin=N/A
   SubmitTime=2026-09-25T00:24:45 EligibleTime=2026-09-25T00:24:45
   AccrueTime=2026-09-25T00:24:45
   StartTime=2026-09-25T00:24:46 EndTime=2026-09-25T00:34:44 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-25T00:24:46 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:236428
   ReqNodeList=(null) ExcNodeList=srvrocgpu009
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=48G,node=1,billing=9,gres/gpu=1
   AllocTRES=cpu=4,mem=48G,node=1,billing=9,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=17-18,37-38 Mem=49152 GRES=
   MinCPUsNode=6 MinMemoryNode=48G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/padding-diagnostic-20260924/diag.sbatch
   WorkDir=/scratch/lmbanr001/masters/sallm_snapshots/padding-diagnostic-20260924
   StdErr=/scratch/lmbanr001/masters/sallm/results/padding_diagnostic_20260924/slurm/pad-diag-1369676.err
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/padding_diagnostic_20260924/slurm/pad-diag-1369676.out
   Power=
   TresPerNode=gres/gpu:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1369676

captured Fri Sep 25 00:35:38 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7467 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=00:09:58 TimeLimit=06:00:00 TimeMin=N/A
   SubmitTime=2026-09-25T00:24:45 EligibleTime=2026-09-25T00:24:45
   AccrueTime=2026-09-25T00:24:45
   StartTime=2026-09-25T00:24:46 EndTime=2026-09-25T00:34:44 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-25T00:24:46 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:236428
   ReqNodeList=(null) ExcNodeList=srvrocgpu009
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=48G,node=1,billing=9,gres/gpu=1
   AllocTRES=cpu=4,mem=48G,node=1,billing=9,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=17-18,37-38 Mem=49152 GRES=
   MinCPUsNode=6 MinMemoryNode=48G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/padding-diagnostic-20260924/diag.sbatch
   WorkDir=/scratch/lmbanr001/masters/sallm_snapshots/padding-diagnostic-20260924
   StdErr=/scratch/lmbanr001/masters/sallm/results/padding_diagnostic_20260924/slurm/pad-diag-1369676.err
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/padding_diagnostic_20260924/slurm/pad-diag-1369676.out
   Power=
   TresPerNode=gres/gpu:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1369676

captured Fri Sep 25 00:36:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7467 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=00:09:58 TimeLimit=06:00:00 TimeMin=N/A
   SubmitTime=2026-09-25T00:24:45 EligibleTime=2026-09-25T00:24:45
   AccrueTime=2026-09-25T00:24:45
   StartTime=2026-09-25T00:24:46 EndTime=2026-09-25T00:34:44 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-25T00:24:46 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:236428
   ReqNodeList=(null) ExcNodeList=srvrocgpu009
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=48G,node=1,billing=9,gres/gpu=1
   AllocTRES=cpu=4,mem=48G,node=1,billing=9,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=17-18,37-38 Mem=49152 GRES=
   MinCPUsNode=6 MinMemoryNode=48G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/padding-diagnostic-20260924/diag.sbatch
   WorkDir=/scratch/lmbanr001/masters/sallm_snapshots/padding-diagnostic-20260924
   StdErr=/scratch/lmbanr001/masters/sallm/results/padding_diagnostic_20260924/slurm/pad-diag-1369676.err
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/padding_diagnostic_20260924/slurm/pad-diag-1369676.out
   Power=
   TresPerNode=gres/gpu:1
   TresPerTask=cpu:4