JOB DETAILS FOR JOB 160764

captured Sun Jun 15 00:04:01 SAST 2025

MaxRAM=1.2G
MaxVMSize=0G
AveCPUFreq=2.85M
AveDiskRead=636290010
AveDiskWrite=159527

JobId=160764 JobName=cos_noise
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7238 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=00:13:07 TimeLimit=10:00:00 TimeMin=N/A
   SubmitTime=2025-06-14T23:50:54 EligibleTime=2025-06-14T23:50:54
   AccrueTime=2025-06-14T23:50:54
   StartTime=2025-06-14T23:50:54 EndTime=2025-06-15T09:50:54 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-14T23:50:54 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2835934
   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=0-3,24-27 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/model_27may/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/model_27may
   StdErr=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-160764.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-160764.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=mrpcol001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
   

UCT HPC clusterJOB DETAILS FOR JOB 160764

captured Sun Jun 15 00:04:42 SAST 2025

JobId=160764 JobName=cos_noise
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7238 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:13:45 TimeLimit=10:00:00 TimeMin=N/A
   SubmitTime=2025-06-14T23:50:54 EligibleTime=2025-06-14T23:50:54
   AccrueTime=2025-06-14T23:50:54
   StartTime=2025-06-14T23:50:54 EndTime=2025-06-15T00:04:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-14T23:50:54 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2835934
   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=0-3,24-27 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/model_27may/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/model_27may
   StdErr=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-160764.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-160764.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=mrpcol001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
   

UCT HPC clusterJOB DETAILS FOR JOB 160764

captured Sun Jun 15 00:05:01 SAST 2025

JobId=160764 JobName=cos_noise
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7238 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:13:45 TimeLimit=10:00:00 TimeMin=N/A
   SubmitTime=2025-06-14T23:50:54 EligibleTime=2025-06-14T23:50:54
   AccrueTime=2025-06-14T23:50:54
   StartTime=2025-06-14T23:50:54 EndTime=2025-06-15T00:04:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-14T23:50:54 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2835934
   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=0-3,24-27 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/model_27may/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/model_27may
   StdErr=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-160764.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-160764.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=mrpcol001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
   

UCT HPC clusterJOB DETAILS FOR JOB 160764

captured Sun Jun 15 00:05:43 SAST 2025

JobId=160764 JobName=cos_noise
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7238 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:13:45 TimeLimit=10:00:00 TimeMin=N/A
   SubmitTime=2025-06-14T23:50:54 EligibleTime=2025-06-14T23:50:54
   AccrueTime=2025-06-14T23:50:54
   StartTime=2025-06-14T23:50:54 EndTime=2025-06-15T00:04:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-14T23:50:54 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2835934
   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=0-3,24-27 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/model_27may/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/model_27may
   StdErr=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-160764.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-160764.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=mrpcol001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
   

UCT HPC clusterJOB DETAILS FOR JOB 160764

captured Sun Jun 15 00:06:01 SAST 2025

JobId=160764 JobName=cos_noise
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7238 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:13:45 TimeLimit=10:00:00 TimeMin=N/A
   SubmitTime=2025-06-14T23:50:54 EligibleTime=2025-06-14T23:50:54
   AccrueTime=2025-06-14T23:50:54
   StartTime=2025-06-14T23:50:54 EndTime=2025-06-15T00:04:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-14T23:50:54 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2835934
   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=0-3,24-27 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/model_27may/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/model_27may
   StdErr=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-160764.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-160764.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=mrpcol001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
   

UCT HPC clusterJOB DETAILS FOR JOB 160764

captured Sun Jun 15 00:06:42 SAST 2025

JobId=160764 JobName=cos_noise
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7238 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:13:45 TimeLimit=10:00:00 TimeMin=N/A
   SubmitTime=2025-06-14T23:50:54 EligibleTime=2025-06-14T23:50:54
   AccrueTime=2025-06-14T23:50:54
   StartTime=2025-06-14T23:50:54 EndTime=2025-06-15T00:04:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-14T23:50:54 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2835934
   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=0-3,24-27 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/model_27may/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/model_27may
   StdErr=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-160764.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-160764.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=mrpcol001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
   

UCT HPC clusterJOB DETAILS FOR JOB 160764

captured Sun Jun 15 00:07:01 SAST 2025

JobId=160764 JobName=cos_noise
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7238 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:13:45 TimeLimit=10:00:00 TimeMin=N/A
   SubmitTime=2025-06-14T23:50:54 EligibleTime=2025-06-14T23:50:54
   AccrueTime=2025-06-14T23:50:54
   StartTime=2025-06-14T23:50:54 EndTime=2025-06-15T00:04:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-14T23:50:54 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:2835934
   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=0-3,24-27 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/model_27may/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/model_27may
   StdErr=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-160764.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-160764.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=mrpcol001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT