JOB DETAILS FOR JOB 152945

captured Sat May 31 18:28:32 SAST 2025

MaxRAM=1.4G
MaxVMSize=0G
AveCPUFreq=2.87M
AveDiskRead=355135749
AveDiskWrite=160963130

JobId=152945 JobName=ddpm
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7349 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=00:10:50 TimeLimit=05:00:00 TimeMin=N/A
   SubmitTime=2025-05-31T18:17:42 EligibleTime=2025-05-31T18:17:42
   AccrueTime=2025-05-31T18:17:42
   StartTime=2025-05-31T18:17:42 EndTime=2025-05-31T23:17:42 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-05-31T18:17:42 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3998119
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   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=srvrocgpu012 CPU_IDs=0-2,24-26 Mem=60000 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/ddpm_model/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/ddpm_model
   StdErr=/scratch/mrpcol001/Diffusion_job/ddpm_model/slurm-152945.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/ddpm_model/slurm-152945.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 152945

captured Sat May 31 18:29:01 SAST 2025

JobId=152945 JobName=ddpm
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7349 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=00:11:15 TimeLimit=05:00:00 TimeMin=N/A
   SubmitTime=2025-05-31T18:17:42 EligibleTime=2025-05-31T18:17:42
   AccrueTime=2025-05-31T18:17:42
   StartTime=2025-05-31T18:17:42 EndTime=2025-05-31T18:28:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-05-31T18:17:42 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3998119
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   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=srvrocgpu012 CPU_IDs=0-2,24-26 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/ddpm_model/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/ddpm_model
   StdErr=/scratch/mrpcol001/Diffusion_job/ddpm_model/slurm-152945.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/ddpm_model/slurm-152945.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 152945

captured Sat May 31 18:29:31 SAST 2025

JobId=152945 JobName=ddpm
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7349 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=00:11:15 TimeLimit=05:00:00 TimeMin=N/A
   SubmitTime=2025-05-31T18:17:42 EligibleTime=2025-05-31T18:17:42
   AccrueTime=2025-05-31T18:17:42
   StartTime=2025-05-31T18:17:42 EndTime=2025-05-31T18:28:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-05-31T18:17:42 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3998119
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   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=srvrocgpu012 CPU_IDs=0-2,24-26 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/ddpm_model/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/ddpm_model
   StdErr=/scratch/mrpcol001/Diffusion_job/ddpm_model/slurm-152945.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/ddpm_model/slurm-152945.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 152945

captured Sat May 31 18:30:01 SAST 2025

JobId=152945 JobName=ddpm
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7349 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=00:11:15 TimeLimit=05:00:00 TimeMin=N/A
   SubmitTime=2025-05-31T18:17:42 EligibleTime=2025-05-31T18:17:42
   AccrueTime=2025-05-31T18:17:42
   StartTime=2025-05-31T18:17:42 EndTime=2025-05-31T18:28:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-05-31T18:17:42 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3998119
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   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=srvrocgpu012 CPU_IDs=0-2,24-26 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/ddpm_model/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/ddpm_model
   StdErr=/scratch/mrpcol001/Diffusion_job/ddpm_model/slurm-152945.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/ddpm_model/slurm-152945.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 152945

captured Sat May 31 18:30:32 SAST 2025

JobId=152945 JobName=ddpm
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7349 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=00:11:15 TimeLimit=05:00:00 TimeMin=N/A
   SubmitTime=2025-05-31T18:17:42 EligibleTime=2025-05-31T18:17:42
   AccrueTime=2025-05-31T18:17:42
   StartTime=2025-05-31T18:17:42 EndTime=2025-05-31T18:28:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-05-31T18:17:42 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3998119
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   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=srvrocgpu012 CPU_IDs=0-2,24-26 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/ddpm_model/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/ddpm_model
   StdErr=/scratch/mrpcol001/Diffusion_job/ddpm_model/slurm-152945.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/ddpm_model/slurm-152945.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 152945

captured Sat May 31 18:31:02 SAST 2025

JobId=152945 JobName=ddpm
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7349 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=00:11:15 TimeLimit=05:00:00 TimeMin=N/A
   SubmitTime=2025-05-31T18:17:42 EligibleTime=2025-05-31T18:17:42
   AccrueTime=2025-05-31T18:17:42
   StartTime=2025-05-31T18:17:42 EndTime=2025-05-31T18:28:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-05-31T18:17:42 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3998119
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   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=srvrocgpu012 CPU_IDs=0-2,24-26 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/ddpm_model/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/ddpm_model
   StdErr=/scratch/mrpcol001/Diffusion_job/ddpm_model/slurm-152945.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/ddpm_model/slurm-152945.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=mrpcol001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT