UCT HPC cluster

JOB DETAILS FOR JOB 300054

captured Mon Oct 6 19:58:42 SAST 2025

MaxRAM=29.9G
MaxVMSize=0G
AveCPUFreq=682K
AveDiskRead=99830032518
AveDiskWrite=68141803700

JobId=300054 JobName=MMS_Model_DAT
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7114 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=01:22:21 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-06T14:34:15 EligibleTime=2025-10-06T14:34:15
   AccrueTime=2025-10-06T18:14:15
   StartTime=2025-10-06T18:36:21 EndTime=2025-10-08T18:36:21 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-06T18:36:21 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:744861
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=5-6,29-30 Mem=40000 GRES=gpu:l40s:1(IDX:3)
   MinCPUsNode=1 MinMemoryCPU=10000M 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.sh
   WorkDir=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition
   StdErr=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-300054.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-300054.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=skscla001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 300054

captured Mon Oct 6 19:59:02 SAST 2025

JobId=300054 JobName=MMS_Model_DAT
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7114 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=01:22:38 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-06T14:34:15 EligibleTime=2025-10-06T14:34:15
   AccrueTime=2025-10-06T18:14:15
   StartTime=2025-10-06T18:36:21 EndTime=2025-10-06T19:58:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-06T18:36:21 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:744861
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=5-6,29-30 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M 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.sh
   WorkDir=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition
   StdErr=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-300054.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-300054.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=skscla001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 300054

captured Mon Oct 6 19:59:41 SAST 2025

JobId=300054 JobName=MMS_Model_DAT
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7114 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=01:22:38 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-06T14:34:15 EligibleTime=2025-10-06T14:34:15
   AccrueTime=2025-10-06T18:14:15
   StartTime=2025-10-06T18:36:21 EndTime=2025-10-06T19:58:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-06T18:36:21 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:744861
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=5-6,29-30 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M 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.sh
   WorkDir=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition
   StdErr=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-300054.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-300054.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=skscla001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 300054

captured Mon Oct 6 20:00:01 SAST 2025

JobId=300054 JobName=MMS_Model_DAT
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7114 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=01:22:38 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-06T14:34:15 EligibleTime=2025-10-06T14:34:15
   AccrueTime=2025-10-06T18:14:15
   StartTime=2025-10-06T18:36:21 EndTime=2025-10-06T19:58:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-06T18:36:21 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:744861
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=5-6,29-30 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M 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.sh
   WorkDir=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition
   StdErr=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-300054.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-300054.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=skscla001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 300054

captured Mon Oct 6 20:00:47 SAST 2025

JobId=300054 JobName=MMS_Model_DAT
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7114 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=01:22:38 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-06T14:34:15 EligibleTime=2025-10-06T14:34:15
   AccrueTime=2025-10-06T18:14:15
   StartTime=2025-10-06T18:36:21 EndTime=2025-10-06T19:58:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-06T18:36:21 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:744861
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=5-6,29-30 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M 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.sh
   WorkDir=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition
   StdErr=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-300054.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-300054.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=skscla001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 300054

captured Mon Oct 6 20:01:01 SAST 2025

JobId=300054 JobName=MMS_Model_DAT
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7114 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=01:22:38 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-06T14:34:15 EligibleTime=2025-10-06T14:34:15
   AccrueTime=2025-10-06T18:14:15
   StartTime=2025-10-06T18:36:21 EndTime=2025-10-06T19:58:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-06T18:36:21 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:744861
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=5-6,29-30 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M 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.sh
   WorkDir=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition
   StdErr=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-300054.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/experiments/transformers/examples/pytorch/speech-recognition/slurm-300054.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=skscla001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT