UCT HPC cluster

JOB DETAILS FOR JOB 345549

captured Tue Nov 18 13:48:01 SAST 2025

MaxRAM=13.6G
MaxVMSize=0G
AveCPUFreq=91K
AveDiskRead=11409455036
AveDiskWrite=54686892741

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7132 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=12:54:14 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-11-18T00:46:26 EligibleTime=2025-11-18T00:46:26
   AccrueTime=2025-11-18T00:46:26
   StartTime=2025-11-18T00:53:47 EndTime=2025-11-20T00:53:47 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-18T00:53:47 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu014.uct.ac.za:4101074
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu015 CPU_IDs=0-1,10-11,24-25,34-35 Mem=80000 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/mrpcol001/Diffusion_job/nov/05nov/cond_2/scripts/shell/train_2label.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/nov/05nov/cond_2/scripts/shell
   StdErr=/scratch/mrpcol001/Diffusion_job/nov/05nov/cond_2/scripts/shell/slurm-345549.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/nov/05nov/cond_2/scripts/shell/slurm-345549.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 345549

captured Tue Nov 18 13:48:38 SAST 2025

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7132 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=12:54:49 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-11-18T00:46:26 EligibleTime=2025-11-18T00:46:26
   AccrueTime=2025-11-18T00:46:26
   StartTime=2025-11-18T00:53:47 EndTime=2025-11-18T13:48:36 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-18T00:53:47 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu014.uct.ac.za:4101074
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu015 CPU_IDs=0-1,10-11,24-25,34-35 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/nov/05nov/cond_2/scripts/shell/train_2label.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/nov/05nov/cond_2/scripts/shell
   StdErr=/scratch/mrpcol001/Diffusion_job/nov/05nov/cond_2/scripts/shell/slurm-345549.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/nov/05nov/cond_2/scripts/shell/slurm-345549.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 345549

captured Tue Nov 18 13:49:01 SAST 2025

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7132 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=12:54:49 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-11-18T00:46:26 EligibleTime=2025-11-18T00:46:26
   AccrueTime=2025-11-18T00:46:26
   StartTime=2025-11-18T00:53:47 EndTime=2025-11-18T13:48:36 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-18T00:53:47 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu014.uct.ac.za:4101074
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu015 CPU_IDs=0-1,10-11,24-25,34-35 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/nov/05nov/cond_2/scripts/shell/train_2label.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/nov/05nov/cond_2/scripts/shell
   StdErr=/scratch/mrpcol001/Diffusion_job/nov/05nov/cond_2/scripts/shell/slurm-345549.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/nov/05nov/cond_2/scripts/shell/slurm-345549.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 345549

captured Tue Nov 18 13:49:38 SAST 2025

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7132 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=12:54:49 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-11-18T00:46:26 EligibleTime=2025-11-18T00:46:26
   AccrueTime=2025-11-18T00:46:26
   StartTime=2025-11-18T00:53:47 EndTime=2025-11-18T13:48:36 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-18T00:53:47 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu014.uct.ac.za:4101074
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu015 CPU_IDs=0-1,10-11,24-25,34-35 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/nov/05nov/cond_2/scripts/shell/train_2label.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/nov/05nov/cond_2/scripts/shell
   StdErr=/scratch/mrpcol001/Diffusion_job/nov/05nov/cond_2/scripts/shell/slurm-345549.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/nov/05nov/cond_2/scripts/shell/slurm-345549.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 345549

captured Tue Nov 18 13:50:01 SAST 2025

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7132 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=12:54:49 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-11-18T00:46:26 EligibleTime=2025-11-18T00:46:26
   AccrueTime=2025-11-18T00:46:26
   StartTime=2025-11-18T00:53:47 EndTime=2025-11-18T13:48:36 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-18T00:53:47 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu014.uct.ac.za:4101074
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu015 CPU_IDs=0-1,10-11,24-25,34-35 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/nov/05nov/cond_2/scripts/shell/train_2label.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/nov/05nov/cond_2/scripts/shell
   StdErr=/scratch/mrpcol001/Diffusion_job/nov/05nov/cond_2/scripts/shell/slurm-345549.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/nov/05nov/cond_2/scripts/shell/slurm-345549.out
   Power=
   TresPerNode=gres/gpu:l40s:1