UCT HPC cluster

JOB DETAILS FOR JOB 1335178

captured Mon Sep 14 13:30:37 SAST 2026

MaxRAM=1.5G
MaxVMSize=0G
AveCPUFreq=800K
AveDiskRead=711810700
AveDiskWrite=194900

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8319 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=00:00:56 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-09-13T21:13:43 EligibleTime=2026-09-13T21:13:43
   AccrueTime=2026-09-13T21:13:43
   StartTime=2026-09-14T13:29:41 EndTime=2026-09-15T13:29:41 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-14T13:29:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2529060
   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=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=7,13,16-21 Mem=73136 GRES=gpu:ampere:1(IDX:3)
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/downstream-standardized-20260913-v1/.audit/run_standardized_hpo_trial_20260913.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm/results/downstream_standardized_20260913_v1/slurm/standardized-xlstm125-sib-stage_a-a0-seed42-1335178.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/downstream_standardized_20260913_v1/slurm/standardized-xlstm125-sib-stage_a-a0-seed42-1335178.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1335178

captured Mon Sep 14 13:31:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8319 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:01:00 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-09-13T21:13:43 EligibleTime=2026-09-13T21:13:43
   AccrueTime=2026-09-13T21:13:43
   StartTime=2026-09-14T13:29:41 EndTime=2026-09-14T13:30:41 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-14T13:29:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2529060
   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=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=7,13,16-21 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/downstream-standardized-20260913-v1/.audit/run_standardized_hpo_trial_20260913.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm/results/downstream_standardized_20260913_v1/slurm/standardized-xlstm125-sib-stage_a-a0-seed42-1335178.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/downstream_standardized_20260913_v1/slurm/standardized-xlstm125-sib-stage_a-a0-seed42-1335178.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1335178

captured Mon Sep 14 13:31:36 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8319 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:01:00 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-09-13T21:13:43 EligibleTime=2026-09-13T21:13:43
   AccrueTime=2026-09-13T21:13:43
   StartTime=2026-09-14T13:29:41 EndTime=2026-09-14T13:30:41 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-14T13:29:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2529060
   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=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=7,13,16-21 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/downstream-standardized-20260913-v1/.audit/run_standardized_hpo_trial_20260913.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm/results/downstream_standardized_20260913_v1/slurm/standardized-xlstm125-sib-stage_a-a0-seed42-1335178.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/downstream_standardized_20260913_v1/slurm/standardized-xlstm125-sib-stage_a-a0-seed42-1335178.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1335178

captured Mon Sep 14 13:32:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8319 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:01:00 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-09-13T21:13:43 EligibleTime=2026-09-13T21:13:43
   AccrueTime=2026-09-13T21:13:43
   StartTime=2026-09-14T13:29:41 EndTime=2026-09-14T13:30:41 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-14T13:29:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2529060
   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=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=7,13,16-21 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/downstream-standardized-20260913-v1/.audit/run_standardized_hpo_trial_20260913.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm/results/downstream_standardized_20260913_v1/slurm/standardized-xlstm125-sib-stage_a-a0-seed42-1335178.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/downstream_standardized_20260913_v1/slurm/standardized-xlstm125-sib-stage_a-a0-seed42-1335178.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1335178

captured Mon Sep 14 13:32:36 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8319 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:01:00 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-09-13T21:13:43 EligibleTime=2026-09-13T21:13:43
   AccrueTime=2026-09-13T21:13:43
   StartTime=2026-09-14T13:29:41 EndTime=2026-09-14T13:30:41 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-14T13:29:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2529060
   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=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=7,13,16-21 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/downstream-standardized-20260913-v1/.audit/run_standardized_hpo_trial_20260913.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm/results/downstream_standardized_20260913_v1/slurm/standardized-xlstm125-sib-stage_a-a0-seed42-1335178.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/downstream_standardized_20260913_v1/slurm/standardized-xlstm125-sib-stage_a-a0-seed42-1335178.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1335178

captured Mon Sep 14 13:33:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8319 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:01:00 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-09-13T21:13:43 EligibleTime=2026-09-13T21:13:43
   AccrueTime=2026-09-13T21:13:43
   StartTime=2026-09-14T13:29:41 EndTime=2026-09-14T13:30:41 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-14T13:29:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2529060
   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=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=7,13,16-21 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/downstream-standardized-20260913-v1/.audit/run_standardized_hpo_trial_20260913.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm/results/downstream_standardized_20260913_v1/slurm/standardized-xlstm125-sib-stage_a-a0-seed42-1335178.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/downstream_standardized_20260913_v1/slurm/standardized-xlstm125-sib-stage_a-a0-seed42-1335178.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL