UCT HPC cluster

JOB DETAILS FOR JOB 314987

captured Tue Oct 21 13:29:01 SAST 2025

MaxRAM=14.5G
MaxVMSize=0G
AveCPUFreq=1.04M
AveDiskRead=37218920250
AveDiskWrite=29317212083

JobId=314987 JobName=MMS_Model_DAT
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7768 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=00:47:21 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-21T11:47:59 EligibleTime=2025-10-21T11:47:59
   AccrueTime=2025-10-21T11:47:59
   StartTime=2025-10-21T12:41:41 EndTime=2025-10-23T12:41:41 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-21T12:41:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:586438
   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=6-7,34-35 Mem=36568 GRES=gpu:ampere80:1(IDX:3)
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/run_asr_ctc_dat_bem_wandb_a100.sh
   WorkDir=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition
   StdErr=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-314987.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-314987.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 314987

captured Tue Oct 21 13:29:34 SAST 2025

JobId=314987 JobName=MMS_Model_DAT
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7768 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=00:47:34 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-21T11:47:59 EligibleTime=2025-10-21T11:47:59
   AccrueTime=2025-10-21T11:47:59
   StartTime=2025-10-21T12:41:41 EndTime=2025-10-21T13:29:15 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-21T12:41:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:586438
   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=6-7,34-35 Mem=36568 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/run_asr_ctc_dat_bem_wandb_a100.sh
   WorkDir=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition
   StdErr=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-314987.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-314987.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 314987

captured Tue Oct 21 13:30:01 SAST 2025

JobId=314987 JobName=MMS_Model_DAT
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7768 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=00:47:34 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-21T11:47:59 EligibleTime=2025-10-21T11:47:59
   AccrueTime=2025-10-21T11:47:59
   StartTime=2025-10-21T12:41:41 EndTime=2025-10-21T13:29:15 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-21T12:41:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:586438
   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=6-7,34-35 Mem=36568 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/run_asr_ctc_dat_bem_wandb_a100.sh
   WorkDir=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition
   StdErr=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-314987.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-314987.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 314987

captured Tue Oct 21 13:30:34 SAST 2025

JobId=314987 JobName=MMS_Model_DAT
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7768 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=00:47:34 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-21T11:47:59 EligibleTime=2025-10-21T11:47:59
   AccrueTime=2025-10-21T11:47:59
   StartTime=2025-10-21T12:41:41 EndTime=2025-10-21T13:29:15 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-21T12:41:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:586438
   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=6-7,34-35 Mem=36568 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/run_asr_ctc_dat_bem_wandb_a100.sh
   WorkDir=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition
   StdErr=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-314987.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-314987.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 314987

captured Tue Oct 21 13:31:01 SAST 2025

JobId=314987 JobName=MMS_Model_DAT
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7768 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=00:47:34 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-21T11:47:59 EligibleTime=2025-10-21T11:47:59
   AccrueTime=2025-10-21T11:47:59
   StartTime=2025-10-21T12:41:41 EndTime=2025-10-21T13:29:15 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-21T12:41:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:586438
   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=6-7,34-35 Mem=36568 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/run_asr_ctc_dat_bem_wandb_a100.sh
   WorkDir=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition
   StdErr=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-314987.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-314987.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 314987

captured Tue Oct 21 13:31:34 SAST 2025

JobId=314987 JobName=MMS_Model_DAT
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7768 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=00:47:34 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-21T11:47:59 EligibleTime=2025-10-21T11:47:59
   AccrueTime=2025-10-21T11:47:59
   StartTime=2025-10-21T12:41:41 EndTime=2025-10-21T13:29:15 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-21T12:41:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:586438
   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=6-7,34-35 Mem=36568 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/run_asr_ctc_dat_bem_wandb_a100.sh
   WorkDir=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition
   StdErr=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-314987.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-314987.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=skscla001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT