UCT HPC cluster

JOB DETAILS FOR JOB 874711

captured Fri May 29 08:20:01 SAST 2026

MaxRAM=10.1G
MaxVMSize=0G
AveCPUFreq=800K
AveDiskRead=1744420322
AveDiskWrite=1090189

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=9242 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=00:15:11 TimeLimit=1-23:30:00 TimeMin=N/A
   SubmitTime=2026-05-29T08:02:19 EligibleTime=2026-05-29T08:04:50
   AccrueTime=Unknown
   StartTime=2026-05-29T08:04:50 EndTime=2026-05-31T07:34:50 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-05-29T08:04:50 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:807284
   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=19,gres/gpu=4,gres/gpu:ampere=4
   AllocTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:4
     Nodes=srvrocgpu010 CPU_IDs=0-7 Mem=73136 GRES=gpu:ampere:4(IDX:0-3)
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/run_xlstm_diagnostic.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-874711.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-874711.out
   Power=
   TresPerNode=gres/gpu:ampere:4
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 874711

captured Fri May 29 08:20:34 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=9242 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:15:19 TimeLimit=1-23:30:00 TimeMin=N/A
   SubmitTime=2026-05-29T08:02:19 EligibleTime=2026-05-29T08:04:50
   AccrueTime=Unknown
   StartTime=2026-05-29T08:04:50 EndTime=2026-05-29T08:20:09 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-05-29T08:04:50 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:807284
   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=19,gres/gpu=4,gres/gpu:ampere=4
   AllocTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:4
     Nodes=srvrocgpu010 CPU_IDs=0-7 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/run_xlstm_diagnostic.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-874711.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-874711.out
   Power=
   TresPerNode=gres/gpu:ampere:4
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 874711

captured Fri May 29 08:21:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=9242 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:15:19 TimeLimit=1-23:30:00 TimeMin=N/A
   SubmitTime=2026-05-29T08:02:19 EligibleTime=2026-05-29T08:04:50
   AccrueTime=Unknown
   StartTime=2026-05-29T08:04:50 EndTime=2026-05-29T08:20:09 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-05-29T08:04:50 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:807284
   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=19,gres/gpu=4,gres/gpu:ampere=4
   AllocTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:4
     Nodes=srvrocgpu010 CPU_IDs=0-7 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/run_xlstm_diagnostic.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-874711.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-874711.out
   Power=
   TresPerNode=gres/gpu:ampere:4
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 874711

captured Fri May 29 08:21:33 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=9242 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:15:19 TimeLimit=1-23:30:00 TimeMin=N/A
   SubmitTime=2026-05-29T08:02:19 EligibleTime=2026-05-29T08:04:50
   AccrueTime=Unknown
   StartTime=2026-05-29T08:04:50 EndTime=2026-05-29T08:20:09 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-05-29T08:04:50 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:807284
   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=19,gres/gpu=4,gres/gpu:ampere=4
   AllocTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:4
     Nodes=srvrocgpu010 CPU_IDs=0-7 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/run_xlstm_diagnostic.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-874711.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-874711.out
   Power=
   TresPerNode=gres/gpu:ampere:4
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 874711

captured Fri May 29 08:22:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=9242 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:15:19 TimeLimit=1-23:30:00 TimeMin=N/A
   SubmitTime=2026-05-29T08:02:19 EligibleTime=2026-05-29T08:04:50
   AccrueTime=Unknown
   StartTime=2026-05-29T08:04:50 EndTime=2026-05-29T08:20:09 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-05-29T08:04:50 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:807284
   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=19,gres/gpu=4,gres/gpu:ampere=4
   AllocTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:4
     Nodes=srvrocgpu010 CPU_IDs=0-7 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/run_xlstm_diagnostic.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-874711.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-874711.out
   Power=
   TresPerNode=gres/gpu:ampere:4
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL