UCT HPC cluster

JOB DETAILS FOR JOB 94132

captured Tue Mar 11 09:42:01 SAST 2025

MaxRAM=3.8G
MaxVMSize=0G
AveCPUFreq=799K
AveDiskRead=1613888254
AveDiskWrite=534057182

JobId=94132 JobName=NeMo
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7738 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:32 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-03-11T09:41:30 EligibleTime=2025-03-11T09:41:30
   AccrueTime=2025-03-11T09:41:30
   StartTime=2025-03-11T09:41:30 EndTime=2025-03-13T09:41:30 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-03-11T09:41:30 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:1159534
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   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:ampere80=1
   AllocTRES=cpu=1,mem=9142M,node=1,billing=2,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 Mem=9142 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=/scratch/skscla001/speech/accsr-daga23/run_nemo.sh
   WorkDir=/scratch/skscla001/speech/accsr-daga23
   StdErr=/scratch/skscla001/speech/accsr-daga23/slurm-94132.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/speech/accsr-daga23/slurm-94132.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=skscla001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 94132

captured Tue Mar 11 09:42:34 SAST 2025

JobId=94132 JobName=NeMo
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7738 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:43 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-03-11T09:41:30 EligibleTime=2025-03-11T09:41:30
   AccrueTime=2025-03-11T09:41:30
   StartTime=2025-03-11T09:41:30 EndTime=2025-03-11T09:42:13 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-03-11T09:41:30 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:1159534
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   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:ampere80=1
   AllocTRES=cpu=1,mem=9142M,node=1,billing=2,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 Mem=9142 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/skscla001/speech/accsr-daga23/run_nemo.sh
   WorkDir=/scratch/skscla001/speech/accsr-daga23
   StdErr=/scratch/skscla001/speech/accsr-daga23/slurm-94132.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/speech/accsr-daga23/slurm-94132.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=skscla001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 94132

captured Tue Mar 11 09:43:01 SAST 2025

JobId=94132 JobName=NeMo
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7738 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:43 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-03-11T09:41:30 EligibleTime=2025-03-11T09:41:30
   AccrueTime=2025-03-11T09:41:30
   StartTime=2025-03-11T09:41:30 EndTime=2025-03-11T09:42:13 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-03-11T09:41:30 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:1159534
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   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:ampere80=1
   AllocTRES=cpu=1,mem=9142M,node=1,billing=2,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 Mem=9142 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/skscla001/speech/accsr-daga23/run_nemo.sh
   WorkDir=/scratch/skscla001/speech/accsr-daga23
   StdErr=/scratch/skscla001/speech/accsr-daga23/slurm-94132.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/speech/accsr-daga23/slurm-94132.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=skscla001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 94132

captured Tue Mar 11 09:43:34 SAST 2025

JobId=94132 JobName=NeMo
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7738 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:43 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-03-11T09:41:30 EligibleTime=2025-03-11T09:41:30
   AccrueTime=2025-03-11T09:41:30
   StartTime=2025-03-11T09:41:30 EndTime=2025-03-11T09:42:13 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-03-11T09:41:30 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:1159534
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   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:ampere80=1
   AllocTRES=cpu=1,mem=9142M,node=1,billing=2,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 Mem=9142 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/skscla001/speech/accsr-daga23/run_nemo.sh
   WorkDir=/scratch/skscla001/speech/accsr-daga23
   StdErr=/scratch/skscla001/speech/accsr-daga23/slurm-94132.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/speech/accsr-daga23/slurm-94132.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=skscla001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT