UCT HPC cluster

JOB DETAILS FOR JOB 993918

captured Sat Jul 4 10:52:01 SAST 2026

MaxRAM=12.9G
MaxVMSize=0G
AveCPUFreq=7K
AveDiskRead=555222440
AveDiskWrite=18139441523

01476962(465151495 Francois Meyer) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8153 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=16:45:02 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-07-03T18:06:58 EligibleTime=2026-07-03T18:06:58
   AccrueTime=2026-07-03T18:06:58
   StartTime=2026-07-03T18:06:59 EndTime=2026-07-05T18:06:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-07-03T18:06:59 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1526862
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=36568M,node=1,billing=8,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=4,mem=36568M,node=1,billing=8,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=0-1,28-29 Mem=36568 GRES=gpu:ampere80:1(IDX:0)
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/01476962/subseglm/train_subseggpt.sh
   WorkDir=/home/01476962/subseglm
   StdErr=/home/01476962/subseglm/logs/train_subseggpt_993918.log
   StdIn=/dev/null
   StdOut=/home/01476962/subseglm/logs/train_subseggpt_993918.log
   Power=
   TresPerNode=gres/gpu:ampere80:1

UCT HPC clusterJOB DETAILS FOR JOB 993918

captured Sat Jul 4 10:52:36 SAST 2026

01476962(465151495 Francois Meyer) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8153 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=16:45:37 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-07-03T18:06:58 EligibleTime=2026-07-03T18:06:58
   AccrueTime=2026-07-03T18:06:58
   StartTime=2026-07-03T18:06:59 EndTime=2026-07-04T10:52:36 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-07-03T18:06:59 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1526862
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=36568M,node=1,billing=8,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=4,mem=36568M,node=1,billing=8,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=0-1,28-29 Mem=36568 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/01476962/subseglm/train_subseggpt.sh
   WorkDir=/home/01476962/subseglm
   StdErr=/home/01476962/subseglm/logs/train_subseggpt_993918.log
   StdIn=/dev/null
   StdOut=/home/01476962/subseglm/logs/train_subseggpt_993918.log
   Power=
   TresPerNode=gres/gpu:ampere80:1

UCT HPC clusterJOB DETAILS FOR JOB 993918

captured Sat Jul 4 10:53:01 SAST 2026

01476962(465151495 Francois Meyer) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8153 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=16:45:37 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-07-03T18:06:58 EligibleTime=2026-07-03T18:06:58
   AccrueTime=2026-07-03T18:06:58
   StartTime=2026-07-03T18:06:59 EndTime=2026-07-04T10:52:36 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-07-03T18:06:59 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1526862
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=36568M,node=1,billing=8,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=4,mem=36568M,node=1,billing=8,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=0-1,28-29 Mem=36568 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/01476962/subseglm/train_subseggpt.sh
   WorkDir=/home/01476962/subseglm
   StdErr=/home/01476962/subseglm/logs/train_subseggpt_993918.log
   StdIn=/dev/null
   StdOut=/home/01476962/subseglm/logs/train_subseggpt_993918.log
   Power=
   TresPerNode=gres/gpu:ampere80:1

UCT HPC clusterJOB DETAILS FOR JOB 993918

captured Sat Jul 4 10:53:37 SAST 2026

01476962(465151495 Francois Meyer) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8153 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=16:45:37 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-07-03T18:06:58 EligibleTime=2026-07-03T18:06:58
   AccrueTime=2026-07-03T18:06:58
   StartTime=2026-07-03T18:06:59 EndTime=2026-07-04T10:52:36 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-07-03T18:06:59 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1526862
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=36568M,node=1,billing=8,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=4,mem=36568M,node=1,billing=8,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=0-1,28-29 Mem=36568 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/01476962/subseglm/train_subseggpt.sh
   WorkDir=/home/01476962/subseglm
   StdErr=/home/01476962/subseglm/logs/train_subseggpt_993918.log
   StdIn=/dev/null
   StdOut=/home/01476962/subseglm/logs/train_subseggpt_993918.log
   Power=
   TresPerNode=gres/gpu:ampere80:1

UCT HPC clusterJOB DETAILS FOR JOB 993918

captured Sat Jul 4 10:54:01 SAST 2026

01476962(465151495 Francois Meyer) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8153 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=16:45:37 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-07-03T18:06:58 EligibleTime=2026-07-03T18:06:58
   AccrueTime=2026-07-03T18:06:58
   StartTime=2026-07-03T18:06:59 EndTime=2026-07-04T10:52:36 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-07-03T18:06:59 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1526862
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=36568M,node=1,billing=8,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=4,mem=36568M,node=1,billing=8,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=0-1,28-29 Mem=36568 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/01476962/subseglm/train_subseggpt.sh
   WorkDir=/home/01476962/subseglm
   StdErr=/home/01476962/subseglm/logs/train_subseggpt_993918.log
   StdIn=/dev/null
   StdOut=/home/01476962/subseglm/logs/train_subseggpt_993918.log
   Power=
   TresPerNode=gres/gpu:ampere80:1

UCT HPC clusterJOB DETAILS FOR JOB 993918

captured Sat Jul 4 10:54:36 SAST 2026

01476962(465151495 Francois Meyer) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8153 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=16:45:37 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-07-03T18:06:58 EligibleTime=2026-07-03T18:06:58
   AccrueTime=2026-07-03T18:06:58
   StartTime=2026-07-03T18:06:59 EndTime=2026-07-04T10:52:36 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-07-03T18:06:59 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1526862
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=36568M,node=1,billing=8,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=4,mem=36568M,node=1,billing=8,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=0-1,28-29 Mem=36568 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/01476962/subseglm/train_subseggpt.sh
   WorkDir=/home/01476962/subseglm
   StdErr=/home/01476962/subseglm/logs/train_subseggpt_993918.log
   StdIn=/dev/null
   StdOut=/home/01476962/subseglm/logs/train_subseggpt_993918.log
   Power=
   TresPerNode=gres/gpu:ampere80:1