UCT HPC cluster

JOB DETAILS FOR JOB 173439

captured Mon Jun 30 22:38:33 SAST 2025

MaxRAM=19.5G
MaxVMSize=0G
AveCPUFreq=1.11M
AveDiskRead=35190180663
AveDiskWrite=38753770903

JobId=173439 JobName=MMS_52_model
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7762 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=00:49:08 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-06-30T21:49:25 EligibleTime=2025-06-30T21:49:25
   AccrueTime=2025-06-30T21:49:25
   StartTime=2025-06-30T21:49:25 EndTime=2025-07-02T21:49:25 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-30T21:49:25 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:2700798
   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=3-4,31-32 Mem=36568 GRES=gpu:ampere80:1(IDX:2)
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/skscla001/experiments/datasets/run_mms_1b_f_52_swa.sh
   WorkDir=/scratch/skscla001/experiments/datasets
   StdErr=/scratch/skscla001/experiments/datasets/slurm-173439.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/experiments/datasets/slurm-173439.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 173439

captured Mon Jun 30 22:39:01 SAST 2025

JobId=173439 JobName=MMS_52_model
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7762 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=00:49:16 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-06-30T21:49:25 EligibleTime=2025-06-30T21:49:25
   AccrueTime=2025-06-30T21:49:25
   StartTime=2025-06-30T21:49:25 EndTime=2025-06-30T22:38:41 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-30T21:49:25 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:2700798
   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=3-4,31-32 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/datasets/run_mms_1b_f_52_swa.sh
   WorkDir=/scratch/skscla001/experiments/datasets
   StdErr=/scratch/skscla001/experiments/datasets/slurm-173439.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/experiments/datasets/slurm-173439.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 173439

captured Mon Jun 30 22:39:33 SAST 2025

JobId=173439 JobName=MMS_52_model
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7762 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=00:49:16 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-06-30T21:49:25 EligibleTime=2025-06-30T21:49:25
   AccrueTime=2025-06-30T21:49:25
   StartTime=2025-06-30T21:49:25 EndTime=2025-06-30T22:38:41 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-30T21:49:25 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:2700798
   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=3-4,31-32 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/datasets/run_mms_1b_f_52_swa.sh
   WorkDir=/scratch/skscla001/experiments/datasets
   StdErr=/scratch/skscla001/experiments/datasets/slurm-173439.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/experiments/datasets/slurm-173439.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 173439

captured Mon Jun 30 22:40:01 SAST 2025

JobId=173439 JobName=MMS_52_model
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7762 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=00:49:16 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-06-30T21:49:25 EligibleTime=2025-06-30T21:49:25
   AccrueTime=2025-06-30T21:49:25
   StartTime=2025-06-30T21:49:25 EndTime=2025-06-30T22:38:41 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-30T21:49:25 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:2700798
   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=3-4,31-32 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/datasets/run_mms_1b_f_52_swa.sh
   WorkDir=/scratch/skscla001/experiments/datasets
   StdErr=/scratch/skscla001/experiments/datasets/slurm-173439.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/experiments/datasets/slurm-173439.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 173439

captured Mon Jun 30 22:40:33 SAST 2025

JobId=173439 JobName=MMS_52_model
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7762 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=00:49:16 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-06-30T21:49:25 EligibleTime=2025-06-30T21:49:25
   AccrueTime=2025-06-30T21:49:25
   StartTime=2025-06-30T21:49:25 EndTime=2025-06-30T22:38:41 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-30T21:49:25 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:2700798
   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=3-4,31-32 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/datasets/run_mms_1b_f_52_swa.sh
   WorkDir=/scratch/skscla001/experiments/datasets
   StdErr=/scratch/skscla001/experiments/datasets/slurm-173439.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/experiments/datasets/slurm-173439.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 173439

captured Mon Jun 30 22:41:01 SAST 2025

JobId=173439 JobName=MMS_52_model
   UserId=skscla001(465151106 Claytone Sikasote) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7762 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=00:49:16 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-06-30T21:49:25 EligibleTime=2025-06-30T21:49:25
   AccrueTime=2025-06-30T21:49:25
   StartTime=2025-06-30T21:49:25 EndTime=2025-06-30T22:38:41 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-30T21:49:25 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:2700798
   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=3-4,31-32 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/datasets/run_mms_1b_f_52_swa.sh
   WorkDir=/scratch/skscla001/experiments/datasets
   StdErr=/scratch/skscla001/experiments/datasets/slurm-173439.out
   StdIn=/dev/null
   StdOut=/scratch/skscla001/experiments/datasets/slurm-173439.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=skscla001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT