UCT HPC cluster

JOB DETAILS FOR JOB 409731

captured Mon Dec 22 09:34:31 SAST 2025

MaxRAM=4.9G
MaxVMSize=0G
AveCPUFreq=11K
AveDiskRead=84427070340
AveDiskWrite=1254886916

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8630 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=1-13:25:10 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-12-20T05:42:25 EligibleTime=2025-12-20T05:42:25
   AccrueTime=2025-12-20T05:42:25
   StartTime=2025-12-20T20:09:21 EndTime=2025-12-22T20:09:21 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-12-20T20:09:21 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:622210
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=3,gres/gpu=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=2-3,30-31 Mem=36568 GRES=gpu:ampere:2(IDX:2-3)
   MinCPUsNode=1 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-409731.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-409731.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:2
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 409731

captured Mon Dec 22 09:35:01 SAST 2025

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8630 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=1-13:25:36 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-12-20T05:42:25 EligibleTime=2025-12-20T05:42:25
   AccrueTime=2025-12-20T05:42:25
   StartTime=2025-12-20T20:09:21 EndTime=2025-12-22T09:34:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-12-20T20:09:21 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:622210
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=3,gres/gpu=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=2-3,30-31 Mem=36568 GRES=
   MinCPUsNode=1 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-409731.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-409731.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:2
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 409731

captured Mon Dec 22 09:35:39 SAST 2025

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8630 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=1-13:25:36 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-12-20T05:42:25 EligibleTime=2025-12-20T05:42:25
   AccrueTime=2025-12-20T05:42:25
   StartTime=2025-12-20T20:09:21 EndTime=2025-12-22T09:34:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-12-20T20:09:21 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:622210
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=3,gres/gpu=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=2-3,30-31 Mem=36568 GRES=
   MinCPUsNode=1 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-409731.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-409731.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:2
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 409731

captured Mon Dec 22 09:36:01 SAST 2025

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8630 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=1-13:25:36 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-12-20T05:42:25 EligibleTime=2025-12-20T05:42:25
   AccrueTime=2025-12-20T05:42:25
   StartTime=2025-12-20T20:09:21 EndTime=2025-12-22T09:34:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-12-20T20:09:21 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:622210
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=3,gres/gpu=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=2-3,30-31 Mem=36568 GRES=
   MinCPUsNode=1 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-409731.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-409731.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:2
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL