JOB DETAILS FOR JOB 190560

captured Wed Jul 30 07:41:01 SAST 2025

MaxRAM=0.2G
MaxVMSize=0G
AveCPUFreq=800K
AveDiskRead=33031411
AveDiskWrite=15133

JobId=190560 JobName=model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7767 Nice=0 Account=a100free QOS=a100free
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:03 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-07-30T07:40:58 EligibleTime=2025-07-30T07:40:58
   AccrueTime=2025-07-30T07:40:58
   StartTime=2025-07-30T07:40:58 EndTime=2025-07-31T03:40:58 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-07-30T07:40:58 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:2373274
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=10 NumTasks=10 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=0-4,28-31,35 Mem=91420 GRES=gpu:ampere:1(IDX:0)
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/30july/a100.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/30july
   StdErr=/scratch/mrpcol001/Diffusion_job/30july/slurm-190560.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/30july/slurm-190560.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   

UCT HPC clusterJOB DETAILS FOR JOB 190560

captured Wed Jul 30 07:41:33 SAST 2025

JobId=190560 JobName=model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7767 Nice=0 Account=a100free QOS=a100free
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:11 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-07-30T07:40:58 EligibleTime=2025-07-30T07:40:58
   AccrueTime=2025-07-30T07:40:58
   StartTime=2025-07-30T07:40:58 EndTime=2025-07-30T07:41:09 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-07-30T07:40:58 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:2373274
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=10 NumTasks=10 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=0-4,28-31,35 Mem=91420 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/30july/a100.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/30july
   StdErr=/scratch/mrpcol001/Diffusion_job/30july/slurm-190560.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/30july/slurm-190560.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   

UCT HPC clusterJOB DETAILS FOR JOB 190560

captured Wed Jul 30 07:42:01 SAST 2025

JobId=190560 JobName=model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7767 Nice=0 Account=a100free QOS=a100free
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:11 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-07-30T07:40:58 EligibleTime=2025-07-30T07:40:58
   AccrueTime=2025-07-30T07:40:58
   StartTime=2025-07-30T07:40:58 EndTime=2025-07-30T07:41:09 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-07-30T07:40:58 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:2373274
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=10 NumTasks=10 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=0-4,28-31,35 Mem=91420 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/30july/a100.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/30july
   StdErr=/scratch/mrpcol001/Diffusion_job/30july/slurm-190560.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/30july/slurm-190560.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   

UCT HPC clusterJOB DETAILS FOR JOB 190560

captured Wed Jul 30 07:42:32 SAST 2025

JobId=190560 JobName=model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7767 Nice=0 Account=a100free QOS=a100free
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:11 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-07-30T07:40:58 EligibleTime=2025-07-30T07:40:58
   AccrueTime=2025-07-30T07:40:58
   StartTime=2025-07-30T07:40:58 EndTime=2025-07-30T07:41:09 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-07-30T07:40:58 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:2373274
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=10 NumTasks=10 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=0-4,28-31,35 Mem=91420 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/30july/a100.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/30july
   StdErr=/scratch/mrpcol001/Diffusion_job/30july/slurm-190560.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/30july/slurm-190560.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   

UCT HPC clusterJOB DETAILS FOR JOB 190560

captured Wed Jul 30 07:43:01 SAST 2025

JobId=190560 JobName=model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7767 Nice=0 Account=a100free QOS=a100free
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:11 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-07-30T07:40:58 EligibleTime=2025-07-30T07:40:58
   AccrueTime=2025-07-30T07:40:58
   StartTime=2025-07-30T07:40:58 EndTime=2025-07-30T07:41:09 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-07-30T07:40:58 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:2373274
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=10 NumTasks=10 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=0-4,28-31,35 Mem=91420 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/30july/a100.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/30july
   StdErr=/scratch/mrpcol001/Diffusion_job/30july/slurm-190560.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/30july/slurm-190560.out
   Power=
   TresPerNode=gres/gpu:ampere:1