UCT HPC cluster

JOB DETAILS FOR JOB 1337549

captured Tue Sep 15 10:56:31 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7841 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=PENDING Reason=Priority Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=12:30:00 TimeMin=N/A
   SubmitTime=2026-09-15T09:05:44 EligibleTime=2026-09-15T09:05:44
   AccrueTime=Unknown
   StartTime=Unknown EndTime=Unknown Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-15T10:56:18 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1702096
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1-1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80G,node=1,billing=17,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=9 MinMemoryNode=80G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_recovery/xlstm_sib_mono_reconstruction_20260914_v2/audit/run_xlstm_sib_mono_reconstruction_serial_20260915.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm_recovery/xlstm_sib_mono_reconstruction_20260914_v2/logs/training-serial-1337549.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm_recovery/xlstm_sib_mono_reconstruction_20260914_v2/logs/training-serial-1337549.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1337549

captured Tue Sep 15 10:57:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7841 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=Priority Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=12:30:00 TimeMin=N/A
   SubmitTime=2026-09-15T09:05:44 EligibleTime=2026-09-15T09:05:44
   AccrueTime=Unknown
   StartTime=2026-09-15T10:56:37 EndTime=2026-09-15T10:56:37 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-15T10:56:37 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc001:1702096
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1 NumCPUs=8 NumTasks=N/A CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80G,node=1,billing=17,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=9 MinMemoryNode=80G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_recovery/xlstm_sib_mono_reconstruction_20260914_v2/audit/run_xlstm_sib_mono_reconstruction_serial_20260915.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm_recovery/xlstm_sib_mono_reconstruction_20260914_v2/logs/training-serial-1337549.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm_recovery/xlstm_sib_mono_reconstruction_20260914_v2/logs/training-serial-1337549.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1337549

captured Tue Sep 15 10:57:42 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7841 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=Priority Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=12:30:00 TimeMin=N/A
   SubmitTime=2026-09-15T09:05:44 EligibleTime=2026-09-15T09:05:44
   AccrueTime=Unknown
   StartTime=2026-09-15T10:56:37 EndTime=2026-09-15T10:56:37 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-15T10:56:37 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc001:1702096
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1 NumCPUs=8 NumTasks=N/A CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80G,node=1,billing=17,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=9 MinMemoryNode=80G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_recovery/xlstm_sib_mono_reconstruction_20260914_v2/audit/run_xlstm_sib_mono_reconstruction_serial_20260915.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm_recovery/xlstm_sib_mono_reconstruction_20260914_v2/logs/training-serial-1337549.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm_recovery/xlstm_sib_mono_reconstruction_20260914_v2/logs/training-serial-1337549.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1337549

captured Tue Sep 15 10:58:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7841 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=Priority Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=12:30:00 TimeMin=N/A
   SubmitTime=2026-09-15T09:05:44 EligibleTime=2026-09-15T09:05:44
   AccrueTime=Unknown
   StartTime=2026-09-15T10:56:37 EndTime=2026-09-15T10:56:37 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-15T10:56:37 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc001:1702096
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1 NumCPUs=8 NumTasks=N/A CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80G,node=1,billing=17,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=9 MinMemoryNode=80G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_recovery/xlstm_sib_mono_reconstruction_20260914_v2/audit/run_xlstm_sib_mono_reconstruction_serial_20260915.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm_recovery/xlstm_sib_mono_reconstruction_20260914_v2/logs/training-serial-1337549.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm_recovery/xlstm_sib_mono_reconstruction_20260914_v2/logs/training-serial-1337549.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL