UCT HPC cluster

JOB DETAILS FOR JOB 346393

captured Wed Nov 19 19:19:36 SAST 2025

MaxRAM=5.2G
MaxVMSize=0G
AveCPUFreq=6K
AveDiskRead=20337285580
AveDiskWrite=1369899570

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7099 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=1-01:51:01 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-11-18T14:59:58 EligibleTime=2025-11-18T14:59:58
   AccrueTime=2025-11-18T16:42:54
   StartTime=2025-11-18T17:28:35 EndTime=2025-11-20T17:28:35 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-18T17:28:35 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:3658275
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=2
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu015 CPU_IDs=0-1,24-25 Mem=40000 GRES=gpu:l40s:2(IDX:0-1)
   MinCPUsNode=1 MinMemoryCPU=10000M 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-346393.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-346393.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:2
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 346393

captured Wed Nov 19 19:20:01 SAST 2025

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7099 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=1-01:51:16 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-11-18T14:59:58 EligibleTime=2025-11-18T14:59:58
   AccrueTime=2025-11-18T16:42:54
   StartTime=2025-11-18T17:28:35 EndTime=2025-11-19T19:19:51 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-18T17:28:35 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:3658275
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=2
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu015 CPU_IDs=0-1,24-25 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M 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-346393.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-346393.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:2
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 346393

captured Wed Nov 19 19:20:37 SAST 2025

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7099 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=1-01:51:16 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-11-18T14:59:58 EligibleTime=2025-11-18T14:59:58
   AccrueTime=2025-11-18T16:42:54
   StartTime=2025-11-18T17:28:35 EndTime=2025-11-19T19:19:51 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-18T17:28:35 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:3658275
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=2
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu015 CPU_IDs=0-1,24-25 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M 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-346393.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-346393.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:2
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 346393

captured Wed Nov 19 19:21:01 SAST 2025

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7099 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=1-01:51:16 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-11-18T14:59:58 EligibleTime=2025-11-18T14:59:58
   AccrueTime=2025-11-18T16:42:54
   StartTime=2025-11-18T17:28:35 EndTime=2025-11-19T19:19:51 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-18T17:28:35 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:3658275
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=2
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu015 CPU_IDs=0-1,24-25 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M 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-346393.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-346393.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:2
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 346393

captured Wed Nov 19 19:21:37 SAST 2025

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7099 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=1-01:51:16 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-11-18T14:59:58 EligibleTime=2025-11-18T14:59:58
   AccrueTime=2025-11-18T16:42:54
   StartTime=2025-11-18T17:28:35 EndTime=2025-11-19T19:19:51 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-18T17:28:35 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:3658275
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=2
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu015 CPU_IDs=0-1,24-25 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M 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-346393.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-346393.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:2
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 346393

captured Wed Nov 19 19:22:01 SAST 2025

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7099 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=1-01:51:16 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-11-18T14:59:58 EligibleTime=2025-11-18T14:59:58
   AccrueTime=2025-11-18T16:42:54
   StartTime=2025-11-18T17:28:35 EndTime=2025-11-19T19:19:51 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-18T17:28:35 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:3658275
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=2
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu015 CPU_IDs=0-1,24-25 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M 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-346393.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-346393.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:2
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL