UCT HPC cluster

JOB DETAILS FOR JOB 1282017

captured Tue Sep 1 15:41:01 SAST 2026

MaxRAM=3.3G
MaxVMSize=0G
AveCPUFreq=19K
AveDiskRead=2228376964
AveDiskWrite=1550052978

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7753 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=06:01:15 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-09-01T09:39:46 EligibleTime=2026-09-01T09:39:46
   AccrueTime=2026-09-01T09:39:46
   StartTime=2026-09-01T09:39:46 EndTime=2026-09-02T09:39:46 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-01T09:39:46 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:3743630
   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=28-35 Mem=73136 GRES=gpu:ampere80:1(IDX:3)
   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/pure-gdn-t2x-official-test-20260901-v2-daf6d8cf/scripts/run_pure_gdn_validation_trial.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-mono-ner-xho-s42-c1-1282017.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-mono-ner-xho-s42-c1-1282017.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1282017

captured Tue Sep 1 15:41:42 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7753 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=06:01:32 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-09-01T09:39:46 EligibleTime=2026-09-01T09:39:46
   AccrueTime=2026-09-01T09:39:46
   StartTime=2026-09-01T09:39:46 EndTime=2026-09-01T15:41:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-01T09:39:46 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:3743630
   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=28-35 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/pure-gdn-t2x-official-test-20260901-v2-daf6d8cf/scripts/run_pure_gdn_validation_trial.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-mono-ner-xho-s42-c1-1282017.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-mono-ner-xho-s42-c1-1282017.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1282017

captured Tue Sep 1 15:42:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7753 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=06:01:32 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-09-01T09:39:46 EligibleTime=2026-09-01T09:39:46
   AccrueTime=2026-09-01T09:39:46
   StartTime=2026-09-01T09:39:46 EndTime=2026-09-01T15:41:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-01T09:39:46 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:3743630
   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=28-35 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/pure-gdn-t2x-official-test-20260901-v2-daf6d8cf/scripts/run_pure_gdn_validation_trial.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-mono-ner-xho-s42-c1-1282017.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-mono-ner-xho-s42-c1-1282017.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1282017

captured Tue Sep 1 15:42:42 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7753 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=06:01:32 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-09-01T09:39:46 EligibleTime=2026-09-01T09:39:46
   AccrueTime=2026-09-01T09:39:46
   StartTime=2026-09-01T09:39:46 EndTime=2026-09-01T15:41:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-01T09:39:46 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:3743630
   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=28-35 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/pure-gdn-t2x-official-test-20260901-v2-daf6d8cf/scripts/run_pure_gdn_validation_trial.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-mono-ner-xho-s42-c1-1282017.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-mono-ner-xho-s42-c1-1282017.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1282017

captured Tue Sep 1 15:43:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7753 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=06:01:32 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-09-01T09:39:46 EligibleTime=2026-09-01T09:39:46
   AccrueTime=2026-09-01T09:39:46
   StartTime=2026-09-01T09:39:46 EndTime=2026-09-01T15:41:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-01T09:39:46 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:3743630
   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=28-35 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/pure-gdn-t2x-official-test-20260901-v2-daf6d8cf/scripts/run_pure_gdn_validation_trial.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-mono-ner-xho-s42-c1-1282017.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-mono-ner-xho-s42-c1-1282017.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL