UCT HPC cluster

JOB DETAILS FOR JOB 966424

captured Sun Jun 28 21:26:40 SAST 2026

MaxRAM=2.6G
MaxVMSize=0G
AveCPUFreq=2.61M
AveDiskRead=1019671793
AveDiskWrite=27245

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8197 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:01:40 TimeLimit=03:00:00 TimeMin=N/A
   SubmitTime=2026-06-28T21:25:00 EligibleTime=2026-06-28T21:25:00
   AccrueTime=Unknown
   StartTime=2026-06-28T21:25:00 EndTime=2026-06-29T00:25:00 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-06-28T21:25:00 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc001:3668050
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=4-7,14-17 Mem=73136 GRES=gpu:ampere80:1(IDX:2)
   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=/scratch/lmbanr001/masters/sallm/logs/jobs/task-head-llama-pos-zul-966424_27.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/task-head-llama-pos-zul-966424_27.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 966424

captured Sun Jun 28 21:27:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8197 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:01:53 TimeLimit=03:00:00 TimeMin=N/A
   SubmitTime=2026-06-28T21:25:00 EligibleTime=2026-06-28T21:25:00
   AccrueTime=Unknown
   StartTime=2026-06-28T21:25:00 EndTime=2026-06-28T21:26:53 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-06-28T21:25:00 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc001:3668050
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=4-7,14-17 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=/scratch/lmbanr001/masters/sallm/logs/jobs/task-head-llama-pos-zul-966424_27.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/task-head-llama-pos-zul-966424_27.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 966424

captured Sun Jun 28 21:27:40 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8197 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:01:53 TimeLimit=03:00:00 TimeMin=N/A
   SubmitTime=2026-06-28T21:25:00 EligibleTime=2026-06-28T21:25:00
   AccrueTime=Unknown
   StartTime=2026-06-28T21:25:00 EndTime=2026-06-28T21:26:53 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-06-28T21:25:00 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc001:3668050
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=4-7,14-17 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=/scratch/lmbanr001/masters/sallm/logs/jobs/task-head-llama-pos-zul-966424_27.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/task-head-llama-pos-zul-966424_27.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 966424

captured Sun Jun 28 21:28:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8197 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:01:53 TimeLimit=03:00:00 TimeMin=N/A
   SubmitTime=2026-06-28T21:25:00 EligibleTime=2026-06-28T21:25:00
   AccrueTime=Unknown
   StartTime=2026-06-28T21:25:00 EndTime=2026-06-28T21:26:53 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-06-28T21:25:00 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc001:3668050
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=4-7,14-17 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=/scratch/lmbanr001/masters/sallm/logs/jobs/task-head-llama-pos-zul-966424_27.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/task-head-llama-pos-zul-966424_27.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 966424

captured Sun Jun 28 21:28:40 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8197 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:01:53 TimeLimit=03:00:00 TimeMin=N/A
   SubmitTime=2026-06-28T21:25:00 EligibleTime=2026-06-28T21:25:00
   AccrueTime=Unknown
   StartTime=2026-06-28T21:25:00 EndTime=2026-06-28T21:26:53 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-06-28T21:25:00 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc001:3668050
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=4-7,14-17 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=/scratch/lmbanr001/masters/sallm/logs/jobs/task-head-llama-pos-zul-966424_27.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/task-head-llama-pos-zul-966424_27.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL