JOB DETAILS FOR JOB 160960

captured Mon Jun 16 04:23:42 SAST 2025

JobId=160960 JobName=sinu_4ly
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7260 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=00:00:08 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-06-16T04:23:25 EligibleTime=2025-06-16T04:23:25
   AccrueTime=2025-06-16T04:23:25
   StartTime=2025-06-16T04:23:25 EndTime=2025-06-16T04:23:33 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-16T04:23:25 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3400490
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=10 NumTasks=10 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=10,mem=100000M,node=1,billing=19,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=10,mem=100000M,node=1,billing=19,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=10-14,34-38 Mem=100000 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-160960.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-160960.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 160960

captured Mon Jun 16 04:24:01 SAST 2025

JobId=160960 JobName=sinu_4ly
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7260 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=00:00:08 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-06-16T04:23:25 EligibleTime=2025-06-16T04:23:25
   AccrueTime=2025-06-16T04:23:25
   StartTime=2025-06-16T04:23:25 EndTime=2025-06-16T04:23:33 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-16T04:23:25 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3400490
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=10 NumTasks=10 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=10,mem=100000M,node=1,billing=19,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=10,mem=100000M,node=1,billing=19,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=10-14,34-38 Mem=100000 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-160960.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-160960.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 160960

captured Mon Jun 16 04:24:37 SAST 2025

JobId=160960 JobName=sinu_4ly
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7260 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=00:00:08 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-06-16T04:23:25 EligibleTime=2025-06-16T04:23:25
   AccrueTime=2025-06-16T04:23:25
   StartTime=2025-06-16T04:23:25 EndTime=2025-06-16T04:23:33 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-16T04:23:25 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3400490
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=10 NumTasks=10 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=10,mem=100000M,node=1,billing=19,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=10,mem=100000M,node=1,billing=19,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=10-14,34-38 Mem=100000 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-160960.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-160960.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 160960

captured Mon Jun 16 04:25:01 SAST 2025

JobId=160960 JobName=sinu_4ly
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7260 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=00:00:08 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-06-16T04:23:25 EligibleTime=2025-06-16T04:23:25
   AccrueTime=2025-06-16T04:23:25
   StartTime=2025-06-16T04:23:25 EndTime=2025-06-16T04:23:33 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-16T04:23:25 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3400490
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=10 NumTasks=10 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=10,mem=100000M,node=1,billing=19,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=10,mem=100000M,node=1,billing=19,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=10-14,34-38 Mem=100000 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-160960.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-160960.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=mrpcol001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT