UCT HPC cluster

JOB DETAILS FOR JOB 111588

captured Sat Apr 19 11:50:36 SAST 2025

MaxRAM=18.5G
MaxVMSize=0G
AveCPUFreq=4K
AveDiskRead=5676807862
AveDiskWrite=17312095176

JobId=111588 JobName=med_simplify
   UserId=khlnom004(465054079 Nomonde Khalo) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7311 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=1-23:59:43 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-04-17T11:50:53 EligibleTime=2025-04-17T11:50:53
   AccrueTime=2025-04-17T11:50:53
   StartTime=2025-04-17T11:50:53 EndTime=2025-04-19T11:50:53 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-17T11:50:53 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2653061
   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=0-1,24-25 Mem=40000 GRES=gpu:l40s:1(IDX:0)
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/khlnom004/khlnom004/SAE_pretraining.sh
   WorkDir=/scratch/khlnom004/khlnom004
   StdErr=/scratch/khlnom004/khlnom004/slurm-111588.out
   StdIn=/dev/null
   StdOut=/scratch/khlnom004/khlnom004/slurm-111588.out
   Power=
   TresPerNode=gres/gpu:l40s
   MailUser=khlnom004@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 111588

captured Sat Apr 19 11:51:01 SAST 2025

JobId=111588 JobName=med_simplify
   UserId=khlnom004(465054079 Nomonde Khalo) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7311 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:02 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-04-17T11:50:53 EligibleTime=2025-04-17T11:50:53
   AccrueTime=2025-04-17T11:50:53
   StartTime=2025-04-17T11:50:53 EndTime=2025-04-19T11:50:55 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-17T11:50:53 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2653061
   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=0-1,24-25 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/khlnom004/khlnom004/SAE_pretraining.sh
   WorkDir=/scratch/khlnom004/khlnom004
   StdErr=/scratch/khlnom004/khlnom004/slurm-111588.out
   StdIn=/dev/null
   StdOut=/scratch/khlnom004/khlnom004/slurm-111588.out
   Power=
   TresPerNode=gres/gpu:l40s
   MailUser=khlnom004@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 111588

captured Sat Apr 19 11:51:34 SAST 2025

JobId=111588 JobName=med_simplify
   UserId=khlnom004(465054079 Nomonde Khalo) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7311 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:02 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-04-17T11:50:53 EligibleTime=2025-04-17T11:50:53
   AccrueTime=2025-04-17T11:50:53
   StartTime=2025-04-17T11:50:53 EndTime=2025-04-19T11:50:55 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-17T11:50:53 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2653061
   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=0-1,24-25 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/khlnom004/khlnom004/SAE_pretraining.sh
   WorkDir=/scratch/khlnom004/khlnom004
   StdErr=/scratch/khlnom004/khlnom004/slurm-111588.out
   StdIn=/dev/null
   StdOut=/scratch/khlnom004/khlnom004/slurm-111588.out
   Power=
   TresPerNode=gres/gpu:l40s
   MailUser=khlnom004@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 111588

captured Sat Apr 19 11:52:01 SAST 2025

JobId=111588 JobName=med_simplify
   UserId=khlnom004(465054079 Nomonde Khalo) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7311 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:02 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-04-17T11:50:53 EligibleTime=2025-04-17T11:50:53
   AccrueTime=2025-04-17T11:50:53
   StartTime=2025-04-17T11:50:53 EndTime=2025-04-19T11:50:55 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-17T11:50:53 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2653061
   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=0-1,24-25 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/khlnom004/khlnom004/SAE_pretraining.sh
   WorkDir=/scratch/khlnom004/khlnom004
   StdErr=/scratch/khlnom004/khlnom004/slurm-111588.out
   StdIn=/dev/null
   StdOut=/scratch/khlnom004/khlnom004/slurm-111588.out
   Power=
   TresPerNode=gres/gpu:l40s
   MailUser=khlnom004@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 111588

captured Sat Apr 19 11:52:34 SAST 2025

JobId=111588 JobName=med_simplify
   UserId=khlnom004(465054079 Nomonde Khalo) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7311 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:02 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-04-17T11:50:53 EligibleTime=2025-04-17T11:50:53
   AccrueTime=2025-04-17T11:50:53
   StartTime=2025-04-17T11:50:53 EndTime=2025-04-19T11:50:55 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-17T11:50:53 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2653061
   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=0-1,24-25 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/khlnom004/khlnom004/SAE_pretraining.sh
   WorkDir=/scratch/khlnom004/khlnom004
   StdErr=/scratch/khlnom004/khlnom004/slurm-111588.out
   StdIn=/dev/null
   StdOut=/scratch/khlnom004/khlnom004/slurm-111588.out
   Power=
   TresPerNode=gres/gpu:l40s
   MailUser=khlnom004@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 111588

captured Sat Apr 19 11:53:01 SAST 2025

JobId=111588 JobName=med_simplify
   UserId=khlnom004(465054079 Nomonde Khalo) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7311 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:02 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-04-17T11:50:53 EligibleTime=2025-04-17T11:50:53
   AccrueTime=2025-04-17T11:50:53
   StartTime=2025-04-17T11:50:53 EndTime=2025-04-19T11:50:55 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-17T11:50:53 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2653061
   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=0-1,24-25 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/khlnom004/khlnom004/SAE_pretraining.sh
   WorkDir=/scratch/khlnom004/khlnom004
   StdErr=/scratch/khlnom004/khlnom004/slurm-111588.out
   StdIn=/dev/null
   StdOut=/scratch/khlnom004/khlnom004/slurm-111588.out
   Power=
   TresPerNode=gres/gpu:l40s
   MailUser=khlnom004@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT