UCT HPC cluster

JOB DETAILS FOR JOB 1077006

captured Wed Jul 22 22:02:02 SAST 2026

MaxRAM=3.8G
MaxVMSize=0G
AveCPUFreq=143K
AveDiskRead=845149530
AveDiskWrite=558013243

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8427 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=01:49:27 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-07-22T16:01:16 EligibleTime=2026-07-22T16:01:17
   AccrueTime=2026-07-22T16:01:17
   StartTime=2026-07-22T20:12:35 EndTime=2026-07-24T20:12:35 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-07-22T20:12:35 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:4137362
   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=20-27 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=/home/lmbanr001/masters/sallm/scripts/launch_gdn_afrihg_hpo_r1.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-1077006_1.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-1077006_1.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1077006

captured Wed Jul 22 22:02:37 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8427 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=01:49:47 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-07-22T16:01:16 EligibleTime=2026-07-22T16:01:17
   AccrueTime=2026-07-22T16:01:17
   StartTime=2026-07-22T20:12:35 EndTime=2026-07-22T22:02:22 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-07-22T20:12:35 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:4137362
   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=20-27 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/launch_gdn_afrihg_hpo_r1.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-1077006_1.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-1077006_1.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1077006

captured Wed Jul 22 22:03:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8427 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=01:49:47 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-07-22T16:01:16 EligibleTime=2026-07-22T16:01:17
   AccrueTime=2026-07-22T16:01:17
   StartTime=2026-07-22T20:12:35 EndTime=2026-07-22T22:02:22 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-07-22T20:12:35 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:4137362
   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=20-27 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/launch_gdn_afrihg_hpo_r1.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-1077006_1.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-1077006_1.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1077006

captured Wed Jul 22 22:03:36 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8427 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=01:49:47 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-07-22T16:01:16 EligibleTime=2026-07-22T16:01:17
   AccrueTime=2026-07-22T16:01:17
   StartTime=2026-07-22T20:12:35 EndTime=2026-07-22T22:02:22 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-07-22T20:12:35 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:4137362
   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=20-27 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/launch_gdn_afrihg_hpo_r1.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-1077006_1.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-1077006_1.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1077006

captured Wed Jul 22 22:04:02 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8427 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=01:49:47 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-07-22T16:01:16 EligibleTime=2026-07-22T16:01:17
   AccrueTime=2026-07-22T16:01:17
   StartTime=2026-07-22T20:12:35 EndTime=2026-07-22T22:02:22 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-07-22T20:12:35 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:4137362
   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=20-27 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/launch_gdn_afrihg_hpo_r1.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-1077006_1.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-1077006_1.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1077006

captured Wed Jul 22 22:04:37 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8427 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=01:49:47 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-07-22T16:01:16 EligibleTime=2026-07-22T16:01:17
   AccrueTime=2026-07-22T16:01:17
   StartTime=2026-07-22T20:12:35 EndTime=2026-07-22T22:02:22 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-07-22T20:12:35 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:4137362
   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=20-27 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/launch_gdn_afrihg_hpo_r1.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-1077006_1.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-1077006_1.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL