UCT HPC cluster

JOB DETAILS FOR JOB 1335896

captured Wed Sep 16 08:24:44 SAST 2026

MaxRAM=3.5G
MaxVMSize=0G
AveCPUFreq=0
AveDiskRead=6042858460
AveDiskWrite=455062501

hwrlau002(1767299407 Laura Haworth) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8710 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=09:00:05 TimeLimit=09:00:00 TimeMin=N/A
   SubmitTime=2026-09-14T13:55:22 EligibleTime=2026-09-14T13:55:22
   AccrueTime=2026-09-14T13:55:22
   StartTime=2026-09-15T23:24:39 EndTime=2026-09-16T08:24:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-15T23:24:39 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:102393
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=2,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=1,mem=9142M,node=1,billing=2,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=40 Mem=9142 GRES=gpu:ampere: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/hwrlau002/pretrain_test.sh
   WorkDir=/home/hwrlau002
   StdErr=/home/hwrlau002/slurm-1335896.out
   StdIn=/dev/null
   StdOut=/home/hwrlau002/slurm-1335896.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   MailUser=hwrlau002@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 1335896

captured Wed Sep 16 08:25:01 SAST 2026

hwrlau002(1767299407 Laura Haworth) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8710 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=09:00:20 TimeLimit=09:00:00 TimeMin=N/A
   SubmitTime=2026-09-14T13:55:22 EligibleTime=2026-09-14T13:55:22
   AccrueTime=2026-09-14T13:55:22
   StartTime=2026-09-15T23:24:39 EndTime=2026-09-16T08:24:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-15T23:24:39 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:102393
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=2,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=1,mem=9142M,node=1,billing=2,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=40 Mem=9142 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/hwrlau002/pretrain_test.sh
   WorkDir=/home/hwrlau002
   StdErr=/home/hwrlau002/slurm-1335896.out
   StdIn=/dev/null
   StdOut=/home/hwrlau002/slurm-1335896.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   MailUser=hwrlau002@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 1335896

captured Wed Sep 16 08:25:52 SAST 2026

hwrlau002(1767299407 Laura Haworth) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8710 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=09:00:20 TimeLimit=09:00:00 TimeMin=N/A
   SubmitTime=2026-09-14T13:55:22 EligibleTime=2026-09-14T13:55:22
   AccrueTime=2026-09-14T13:55:22
   StartTime=2026-09-15T23:24:39 EndTime=2026-09-16T08:24:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-15T23:24:39 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:102393
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=2,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=1,mem=9142M,node=1,billing=2,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=40 Mem=9142 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/hwrlau002/pretrain_test.sh
   WorkDir=/home/hwrlau002
   StdErr=/home/hwrlau002/slurm-1335896.out
   StdIn=/dev/null
   StdOut=/home/hwrlau002/slurm-1335896.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   MailUser=hwrlau002@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 1335896

captured Wed Sep 16 08:26:31 SAST 2026

hwrlau002(1767299407 Laura Haworth) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8710 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=09:00:20 TimeLimit=09:00:00 TimeMin=N/A
   SubmitTime=2026-09-14T13:55:22 EligibleTime=2026-09-14T13:55:22
   AccrueTime=2026-09-14T13:55:22
   StartTime=2026-09-15T23:24:39 EndTime=2026-09-16T08:24:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-15T23:24:39 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:102393
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=2,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=1,mem=9142M,node=1,billing=2,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=40 Mem=9142 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/hwrlau002/pretrain_test.sh
   WorkDir=/home/hwrlau002
   StdErr=/home/hwrlau002/slurm-1335896.out
   StdIn=/dev/null
   StdOut=/home/hwrlau002/slurm-1335896.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   MailUser=hwrlau002@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 1335896

captured Wed Sep 16 08:27:01 SAST 2026

hwrlau002(1767299407 Laura Haworth) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8710 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=09:00:20 TimeLimit=09:00:00 TimeMin=N/A
   SubmitTime=2026-09-14T13:55:22 EligibleTime=2026-09-14T13:55:22
   AccrueTime=2026-09-14T13:55:22
   StartTime=2026-09-15T23:24:39 EndTime=2026-09-16T08:24:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-15T23:24:39 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:102393
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=2,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=1,mem=9142M,node=1,billing=2,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=40 Mem=9142 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/hwrlau002/pretrain_test.sh
   WorkDir=/home/hwrlau002
   StdErr=/home/hwrlau002/slurm-1335896.out
   StdIn=/dev/null
   StdOut=/home/hwrlau002/slurm-1335896.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   MailUser=hwrlau002@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT