UCT HPC cluster

JOB DETAILS FOR JOB 303293

captured Thu Oct 9 13:13:34 SAST 2025

MaxRAM=10.5G
MaxVMSize=0G
AveCPUFreq=27K
AveDiskRead=7071580804
AveDiskWrite=10664800452

JobId=303293 JobName=leaky_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7084 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=15:18:21 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-08T21:55:13 EligibleTime=2025-10-08T21:55:13
   AccrueTime=2025-10-08T21:55:13
   StartTime=2025-10-08T21:55:13 EndTime=2025-10-10T21:55:13 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-08T21:55:13 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu013.uct.ac.za:3148698
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu013 CPU_IDs=0-2,25-27 Mem=60000 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.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/diff_model
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-303293.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-303293.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 303293

captured Thu Oct 9 13:14:01 SAST 2025

JobId=303293 JobName=leaky_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7084 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=15:18:27 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-08T21:55:13 EligibleTime=2025-10-08T21:55:13
   AccrueTime=2025-10-08T21:55:13
   StartTime=2025-10-08T21:55:13 EndTime=2025-10-09T13:13:40 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-08T21:55:13 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu013.uct.ac.za:3148698
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu013 CPU_IDs=0-2,25-27 Mem=60000 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.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/diff_model
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-303293.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-303293.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 303293

captured Thu Oct 9 13:14:34 SAST 2025

JobId=303293 JobName=leaky_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7084 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=15:18:27 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-08T21:55:13 EligibleTime=2025-10-08T21:55:13
   AccrueTime=2025-10-08T21:55:13
   StartTime=2025-10-08T21:55:13 EndTime=2025-10-09T13:13:40 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-08T21:55:13 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu013.uct.ac.za:3148698
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu013 CPU_IDs=0-2,25-27 Mem=60000 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.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/diff_model
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-303293.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-303293.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 303293

captured Thu Oct 9 13:15:01 SAST 2025

JobId=303293 JobName=leaky_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7084 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=15:18:27 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-08T21:55:13 EligibleTime=2025-10-08T21:55:13
   AccrueTime=2025-10-08T21:55:13
   StartTime=2025-10-08T21:55:13 EndTime=2025-10-09T13:13:40 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-08T21:55:13 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu013.uct.ac.za:3148698
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu013 CPU_IDs=0-2,25-27 Mem=60000 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.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/diff_model
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-303293.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-303293.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 303293

captured Thu Oct 9 13:15:33 SAST 2025

JobId=303293 JobName=leaky_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7084 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=15:18:27 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-08T21:55:13 EligibleTime=2025-10-08T21:55:13
   AccrueTime=2025-10-08T21:55:13
   StartTime=2025-10-08T21:55:13 EndTime=2025-10-09T13:13:40 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-08T21:55:13 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu013.uct.ac.za:3148698
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu013 CPU_IDs=0-2,25-27 Mem=60000 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.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/diff_model
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-303293.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-303293.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 303293

captured Thu Oct 9 13:16:01 SAST 2025

JobId=303293 JobName=leaky_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7084 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=15:18:27 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-08T21:55:13 EligibleTime=2025-10-08T21:55:13
   AccrueTime=2025-10-08T21:55:13
   StartTime=2025-10-08T21:55:13 EndTime=2025-10-09T13:13:40 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-08T21:55:13 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu013.uct.ac.za:3148698
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu013 CPU_IDs=0-2,25-27 Mem=60000 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.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/diff_model
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-303293.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/diff_model/slurm-303293.out
   Power=
   TresPerNode=gres/gpu:l40s:1