UCT HPC cluster

JOB DETAILS FOR JOB 1276350

captured Sat Aug 29 03:56:01 SAST 2026

MaxRAM=4.1G
MaxVMSize=0G
AveCPUFreq=148K
AveDiskRead=2570438350
AveDiskWrite=390737480

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7757 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=05:22:31 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-08-28T22:33:29 EligibleTime=2026-08-28T22:33:29
   AccrueTime=2026-08-28T22:33:29
   StartTime=2026-08-28T22:33:30 EndTime=2026-08-29T22:33:30 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-28T22:33:30 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2607389
   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=1-8 Mem=73136 GRES=gpu:ampere80:1(IDX:1)
   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_snapshots/uniform-adapter-hpo-general-a0-resume-correction-20260828-45fec06b/scripts/run_general_a0_corrected_resume.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-gdn-general-a0-resume-corrected-1276350.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-gdn-general-a0-resume-corrected-1276350.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1276350

captured Sat Aug 29 03:56:36 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7757 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=05:23:03 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-08-28T22:33:29 EligibleTime=2026-08-28T22:33:29
   AccrueTime=2026-08-28T22:33:29
   StartTime=2026-08-28T22:33:30 EndTime=2026-08-29T03:56:33 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-28T22:33:30 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2607389
   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=1-8 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_snapshots/uniform-adapter-hpo-general-a0-resume-correction-20260828-45fec06b/scripts/run_general_a0_corrected_resume.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-gdn-general-a0-resume-corrected-1276350.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-gdn-general-a0-resume-corrected-1276350.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1276350

captured Sat Aug 29 03:57:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7757 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=05:23:03 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-08-28T22:33:29 EligibleTime=2026-08-28T22:33:29
   AccrueTime=2026-08-28T22:33:29
   StartTime=2026-08-28T22:33:30 EndTime=2026-08-29T03:56:33 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-28T22:33:30 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2607389
   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=1-8 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_snapshots/uniform-adapter-hpo-general-a0-resume-correction-20260828-45fec06b/scripts/run_general_a0_corrected_resume.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-gdn-general-a0-resume-corrected-1276350.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-gdn-general-a0-resume-corrected-1276350.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1276350

captured Sat Aug 29 03:57:36 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7757 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=05:23:03 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-08-28T22:33:29 EligibleTime=2026-08-28T22:33:29
   AccrueTime=2026-08-28T22:33:29
   StartTime=2026-08-28T22:33:30 EndTime=2026-08-29T03:56:33 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-28T22:33:30 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2607389
   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=1-8 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_snapshots/uniform-adapter-hpo-general-a0-resume-correction-20260828-45fec06b/scripts/run_general_a0_corrected_resume.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-gdn-general-a0-resume-corrected-1276350.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-gdn-general-a0-resume-corrected-1276350.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1276350

captured Sat Aug 29 03:58:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7757 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=05:23:03 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-08-28T22:33:29 EligibleTime=2026-08-28T22:33:29
   AccrueTime=2026-08-28T22:33:29
   StartTime=2026-08-28T22:33:30 EndTime=2026-08-29T03:56:33 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-28T22:33:30 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2607389
   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=1-8 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_snapshots/uniform-adapter-hpo-general-a0-resume-correction-20260828-45fec06b/scripts/run_general_a0_corrected_resume.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-gdn-general-a0-resume-corrected-1276350.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-gdn-general-a0-resume-corrected-1276350.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1276350

captured Sat Aug 29 03:58:36 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7757 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=05:23:03 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-08-28T22:33:29 EligibleTime=2026-08-28T22:33:29
   AccrueTime=2026-08-28T22:33:29
   StartTime=2026-08-28T22:33:30 EndTime=2026-08-29T03:56:33 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-28T22:33:30 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2607389
   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=1-8 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_snapshots/uniform-adapter-hpo-general-a0-resume-correction-20260828-45fec06b/scripts/run_general_a0_corrected_resume.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-gdn-general-a0-resume-corrected-1276350.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-gdn-general-a0-resume-corrected-1276350.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL