UCT HPC cluster

JOB DETAILS FOR JOB 1165989

captured Sun Aug 2 19:52:01 SAST 2026

MaxRAM=9.6G
MaxVMSize=0G
AveCPUFreq=2.17M
AveDiskRead=4672419541
AveDiskWrite=2069153912

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8563 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=00:07:15 TimeLimit=02:00:00 TimeMin=N/A
   SubmitTime=2026-08-02T19:44:43 EligibleTime=2026-08-02T19:44:43
   AccrueTime=2026-08-02T19:44:46
   StartTime=2026-08-02T19:44:46 EndTime=2026-08-02T21:44:46 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-02T19:44:46 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1424553
   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=17,gres/gpu=2,gres/gpu:ampere80=2
   AllocTRES=cpu=8,mem=73136M,node=1,billing=17,gres/gpu=2,gres/gpu:ampere80=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:2
     Nodes=srvrocgpu011 CPU_IDs=0-4,10-12 Mem=73136 GRES=gpu:ampere80:2(IDX:0,2)
   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/scripts/run_pure_gdn_a10080_canary.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-1165989.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-1165989.out
   Power=
   TresPerNode=gres/gpu:ampere80:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1165989

captured Sun Aug 2 19:52:56 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8563 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=00:08:01 TimeLimit=02:00:00 TimeMin=N/A
   SubmitTime=2026-08-02T19:44:43 EligibleTime=2026-08-02T19:44:43
   AccrueTime=2026-08-02T19:44:46
   StartTime=2026-08-02T19:44:46 EndTime=2026-08-02T19:52:47 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-02T19:44:46 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1424553
   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=17,gres/gpu=2,gres/gpu:ampere80=2
   AllocTRES=cpu=8,mem=73136M,node=1,billing=17,gres/gpu=2,gres/gpu:ampere80=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:2
     Nodes=srvrocgpu011 CPU_IDs=0-4,10-12 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/scripts/run_pure_gdn_a10080_canary.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-1165989.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-1165989.out
   Power=
   TresPerNode=gres/gpu:ampere80:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1165989

captured Sun Aug 2 19:53:31 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8563 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=00:08:01 TimeLimit=02:00:00 TimeMin=N/A
   SubmitTime=2026-08-02T19:44:43 EligibleTime=2026-08-02T19:44:43
   AccrueTime=2026-08-02T19:44:46
   StartTime=2026-08-02T19:44:46 EndTime=2026-08-02T19:52:47 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-02T19:44:46 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1424553
   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=17,gres/gpu=2,gres/gpu:ampere80=2
   AllocTRES=cpu=8,mem=73136M,node=1,billing=17,gres/gpu=2,gres/gpu:ampere80=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:2
     Nodes=srvrocgpu011 CPU_IDs=0-4,10-12 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/scripts/run_pure_gdn_a10080_canary.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-1165989.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-1165989.out
   Power=
   TresPerNode=gres/gpu:ampere80:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1165989

captured Sun Aug 2 19:54:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8563 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=00:08:01 TimeLimit=02:00:00 TimeMin=N/A
   SubmitTime=2026-08-02T19:44:43 EligibleTime=2026-08-02T19:44:43
   AccrueTime=2026-08-02T19:44:46
   StartTime=2026-08-02T19:44:46 EndTime=2026-08-02T19:52:47 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-02T19:44:46 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1424553
   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=17,gres/gpu=2,gres/gpu:ampere80=2
   AllocTRES=cpu=8,mem=73136M,node=1,billing=17,gres/gpu=2,gres/gpu:ampere80=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:2
     Nodes=srvrocgpu011 CPU_IDs=0-4,10-12 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/scripts/run_pure_gdn_a10080_canary.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-1165989.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-1165989.out
   Power=
   TresPerNode=gres/gpu:ampere80:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1165989

captured Sun Aug 2 19:54:56 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8563 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=00:08:01 TimeLimit=02:00:00 TimeMin=N/A
   SubmitTime=2026-08-02T19:44:43 EligibleTime=2026-08-02T19:44:43
   AccrueTime=2026-08-02T19:44:46
   StartTime=2026-08-02T19:44:46 EndTime=2026-08-02T19:52:47 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-02T19:44:46 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1424553
   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=17,gres/gpu=2,gres/gpu:ampere80=2
   AllocTRES=cpu=8,mem=73136M,node=1,billing=17,gres/gpu=2,gres/gpu:ampere80=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:2
     Nodes=srvrocgpu011 CPU_IDs=0-4,10-12 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/scripts/run_pure_gdn_a10080_canary.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-1165989.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-1165989.out
   Power=
   TresPerNode=gres/gpu:ampere80:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL