JOB DETAILS FOR JOB 418780

captured Sun Jan 11 17:19:01 SAST 2026

MaxRAM=36.5G
MaxVMSize=0G
AveCPUFreq=4M
AveDiskRead=6707761070
AveDiskWrite=34000838183

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7097 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=00:05:24 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-01-11T17:13:36 EligibleTime=2026-01-11T17:13:36
   AccrueTime=2026-01-11T17:13:36
   StartTime=2026-01-11T17:13:37 EndTime=2026-01-13T17:13:37 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-11T17:13:37 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:1713887
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=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=srvrocgpu016 CPU_IDs=0-3,24-27 Mem=80000 GRES=gpu:l40s:4(IDX:0-3)
   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/train_final_xlstm.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-418780.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-418780.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:4
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL
   

UCT HPC clusterJOB DETAILS FOR JOB 418780

captured Sun Jan 11 17:19:34 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7097 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=00:05:35 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-01-11T17:13:36 EligibleTime=2026-01-11T17:13:36
   AccrueTime=2026-01-11T17:13:36
   StartTime=2026-01-11T17:13:37 EndTime=2026-01-11T17:19:12 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-11T17:13:37 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:1713887
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=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=srvrocgpu016 CPU_IDs=0-3,24-27 Mem=80000 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/train_final_xlstm.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-418780.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-418780.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:4
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL
   

UCT HPC clusterJOB DETAILS FOR JOB 418780

captured Sun Jan 11 17:20:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7097 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=00:05:35 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-01-11T17:13:36 EligibleTime=2026-01-11T17:13:36
   AccrueTime=2026-01-11T17:13:36
   StartTime=2026-01-11T17:13:37 EndTime=2026-01-11T17:19:12 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-11T17:13:37 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:1713887
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=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=srvrocgpu016 CPU_IDs=0-3,24-27 Mem=80000 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/train_final_xlstm.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-418780.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-418780.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:4
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL
   

UCT HPC clusterJOB DETAILS FOR JOB 418780

captured Sun Jan 11 17:20:34 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7097 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=00:05:35 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-01-11T17:13:36 EligibleTime=2026-01-11T17:13:36
   AccrueTime=2026-01-11T17:13:36
   StartTime=2026-01-11T17:13:37 EndTime=2026-01-11T17:19:12 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-11T17:13:37 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:1713887
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=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=srvrocgpu016 CPU_IDs=0-3,24-27 Mem=80000 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/train_final_xlstm.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-418780.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-418780.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:4
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL
   

UCT HPC clusterJOB DETAILS FOR JOB 418780

captured Sun Jan 11 17:21:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7097 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=00:05:35 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-01-11T17:13:36 EligibleTime=2026-01-11T17:13:36
   AccrueTime=2026-01-11T17:13:36
   StartTime=2026-01-11T17:13:37 EndTime=2026-01-11T17:19:12 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-11T17:13:37 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:1713887
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=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=srvrocgpu016 CPU_IDs=0-3,24-27 Mem=80000 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/train_final_xlstm.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-418780.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-418780.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:4
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL