UCT HPC cluster

JOB DETAILS FOR JOB 304232

captured Sat Oct 11 05:08:33 SAST 2025

MaxRAM=12.9G
MaxVMSize=0G
AveCPUFreq=19K
AveDiskRead=24353834169
AveDiskWrite=7304517926

JobId=304232 JobName=ddpm_camels_smart
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7100 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=1-06:50:20 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-09T22:18:13 EligibleTime=2025-10-09T22:18:13
   AccrueTime=2025-10-09T22:18:13
   StartTime=2025-10-09T22:18:13 EndTime=2025-10-11T22:18:13 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T22:18:13 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu013.uct.ac.za:3981120
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   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=srvrocgpu012 CPU_IDs=2,5-7,26-27,30-31 Mem=80000 GRES=gpu:l40s:1(IDX:1)
   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/oct/diff_model/submit_train_camels_smart.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/diff_model
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-304232.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-304232.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 304232

captured Sat Oct 11 05:09:01 SAST 2025

JobId=304232 JobName=ddpm_camels_smart
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7100 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=1-06:50:46 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-09T22:18:13 EligibleTime=2025-10-09T22:18:13
   AccrueTime=2025-10-09T22:18:13
   StartTime=2025-10-09T22:18:13 EndTime=2025-10-11T05:08:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T22:18:13 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu013.uct.ac.za:3981120
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   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=srvrocgpu012 CPU_IDs=2,5-7,26-27,30-31 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/oct/diff_model/submit_train_camels_smart.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/diff_model
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-304232.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-304232.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 304232

captured Sat Oct 11 05:09:33 SAST 2025

JobId=304232 JobName=ddpm_camels_smart
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7100 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=1-06:50:46 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-09T22:18:13 EligibleTime=2025-10-09T22:18:13
   AccrueTime=2025-10-09T22:18:13
   StartTime=2025-10-09T22:18:13 EndTime=2025-10-11T05:08:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T22:18:13 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu013.uct.ac.za:3981120
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   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=srvrocgpu012 CPU_IDs=2,5-7,26-27,30-31 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/oct/diff_model/submit_train_camels_smart.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/diff_model
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-304232.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-304232.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 304232

captured Sat Oct 11 05:10:01 SAST 2025

JobId=304232 JobName=ddpm_camels_smart
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7100 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=1-06:50:46 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-09T22:18:13 EligibleTime=2025-10-09T22:18:13
   AccrueTime=2025-10-09T22:18:13
   StartTime=2025-10-09T22:18:13 EndTime=2025-10-11T05:08:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T22:18:13 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu013.uct.ac.za:3981120
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   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=srvrocgpu012 CPU_IDs=2,5-7,26-27,30-31 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/oct/diff_model/submit_train_camels_smart.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/diff_model
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-304232.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-304232.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 304232

captured Sat Oct 11 05:10:33 SAST 2025

JobId=304232 JobName=ddpm_camels_smart
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7100 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=1-06:50:46 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-09T22:18:13 EligibleTime=2025-10-09T22:18:13
   AccrueTime=2025-10-09T22:18:13
   StartTime=2025-10-09T22:18:13 EndTime=2025-10-11T05:08:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T22:18:13 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu013.uct.ac.za:3981120
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   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=srvrocgpu012 CPU_IDs=2,5-7,26-27,30-31 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/oct/diff_model/submit_train_camels_smart.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/diff_model
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-304232.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-304232.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 304232

captured Sat Oct 11 05:11:01 SAST 2025

JobId=304232 JobName=ddpm_camels_smart
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7100 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=1-06:50:46 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-09T22:18:13 EligibleTime=2025-10-09T22:18:13
   AccrueTime=2025-10-09T22:18:13
   StartTime=2025-10-09T22:18:13 EndTime=2025-10-11T05:08:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T22:18:13 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu013.uct.ac.za:3981120
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   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=srvrocgpu012 CPU_IDs=2,5-7,26-27,30-31 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/oct/diff_model/submit_train_camels_smart.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/diff_model
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-304232.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-304232.out
   Power=
   TresPerNode=gres/gpu:l40s:1