UCT HPC cluster

JOB DETAILS FOR JOB 569622

captured Tue Feb 24 04:04:02 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7664 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=PENDING Reason=Resources Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-02-23T19:46:29 EligibleTime=2026-02-23T19:46:29
   AccrueTime=2026-02-23T19:46:29
   StartTime=2026-02-24T20:33:21 EndTime=2026-02-26T20:33:21 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-02-24T04:03:51 Scheduler=Backfill:*
   Partition=l40s AllocNode:Sid=srvrochpc001:3087197
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList= SchedNodeList=srvrocgpu016
   NumNodes=1-1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   AllocTRES=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=8 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/train_final_mamba.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-569622.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-569622.out
   Power=
   TresPerNode=gres/gpu:l40s:4
   TresPerTask=cpu:8
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 569622

captured Tue Feb 24 04:04:34 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7664 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:22 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-02-23T19:46:29 EligibleTime=2026-02-23T19:46:29
   AccrueTime=2026-02-23T19:46:29
   StartTime=2026-02-24T04:04:04 EndTime=2026-02-24T04:04:26 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-02-24T04:04:04 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:3087197
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:4
     Nodes=srvrocgpu015 CPU_IDs=0-7 Mem=80000 GRES=
   MinCPUsNode=8 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/train_final_mamba.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-569622.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-569622.out
   Power=
   TresPerNode=gres/gpu:l40s:4
   TresPerTask=cpu:8
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 569622

captured Tue Feb 24 04:05:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7664 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:22 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-02-23T19:46:29 EligibleTime=2026-02-23T19:46:29
   AccrueTime=2026-02-23T19:46:29
   StartTime=2026-02-24T04:04:04 EndTime=2026-02-24T04:04:26 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-02-24T04:04:04 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:3087197
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:4
     Nodes=srvrocgpu015 CPU_IDs=0-7 Mem=80000 GRES=
   MinCPUsNode=8 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/train_final_mamba.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-569622.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-569622.out
   Power=
   TresPerNode=gres/gpu:l40s:4
   TresPerTask=cpu:8
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 569622

captured Tue Feb 24 04:05:34 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7664 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:22 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-02-23T19:46:29 EligibleTime=2026-02-23T19:46:29
   AccrueTime=2026-02-23T19:46:29
   StartTime=2026-02-24T04:04:04 EndTime=2026-02-24T04:04:26 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-02-24T04:04:04 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:3087197
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:4
     Nodes=srvrocgpu015 CPU_IDs=0-7 Mem=80000 GRES=
   MinCPUsNode=8 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/train_final_mamba.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-569622.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-569622.out
   Power=
   TresPerNode=gres/gpu:l40s:4
   TresPerTask=cpu:8
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 569622

captured Tue Feb 24 04:06:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7664 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:22 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-02-23T19:46:29 EligibleTime=2026-02-23T19:46:29
   AccrueTime=2026-02-23T19:46:29
   StartTime=2026-02-24T04:04:04 EndTime=2026-02-24T04:04:26 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-02-24T04:04:04 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:3087197
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:4
     Nodes=srvrocgpu015 CPU_IDs=0-7 Mem=80000 GRES=
   MinCPUsNode=8 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/train_final_mamba.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-569622.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-569622.out
   Power=
   TresPerNode=gres/gpu:l40s:4
   TresPerTask=cpu:8
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 569622

captured Tue Feb 24 04:06:33 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7664 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:22 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-02-23T19:46:29 EligibleTime=2026-02-23T19:46:29
   AccrueTime=2026-02-23T19:46:29
   StartTime=2026-02-24T04:04:04 EndTime=2026-02-24T04:04:26 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-02-24T04:04:04 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:3087197
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:4
     Nodes=srvrocgpu015 CPU_IDs=0-7 Mem=80000 GRES=
   MinCPUsNode=8 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/scripts/train_final_mamba.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-569622.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-569622.out
   Power=
   TresPerNode=gres/gpu:l40s:4
   TresPerTask=cpu:8
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL