JOB DETAILS FOR JOB 243205

captured Mon Aug 25 16:38:01 SAST 2025

MaxRAM=7.3G
MaxVMSize=0G
AveCPUFreq=3.18M
AveDiskRead=3605231845
AveDiskWrite=98614

JobId=243205 JobName=leaky_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7099 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=00:00:07 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T16:37:54 EligibleTime=2025-08-25T16:37:54
   AccrueTime=2025-08-25T16:37:54
   StartTime=2025-08-25T16:37:54 EndTime=2025-08-27T16:37:54 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:37:54 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:1294475
   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=0,2,4,24-25,28 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/august/25aug/job.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/august/25aug
   StdErr=/scratch/mrpcol001/Diffusion_job/august/25aug/slurm-243205.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/august/25aug/slurm-243205.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   

UCT HPC clusterJOB DETAILS FOR JOB 243205

captured Mon Aug 25 16:38:44 SAST 2025

JobId=243205 JobName=leaky_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7099 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=00:00:22 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T16:37:54 EligibleTime=2025-08-25T16:37:54
   AccrueTime=2025-08-25T16:37:54
   StartTime=2025-08-25T16:37:54 EndTime=2025-08-25T16:38:16 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:37:54 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:1294475
   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=0,2,4,24-25,28 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/august/25aug/job.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/august/25aug
   StdErr=/scratch/mrpcol001/Diffusion_job/august/25aug/slurm-243205.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/august/25aug/slurm-243205.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   

UCT HPC clusterJOB DETAILS FOR JOB 243205

captured Mon Aug 25 16:39:01 SAST 2025

JobId=243205 JobName=leaky_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7099 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=00:00:22 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T16:37:54 EligibleTime=2025-08-25T16:37:54
   AccrueTime=2025-08-25T16:37:54
   StartTime=2025-08-25T16:37:54 EndTime=2025-08-25T16:38:16 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:37:54 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:1294475
   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=0,2,4,24-25,28 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/august/25aug/job.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/august/25aug
   StdErr=/scratch/mrpcol001/Diffusion_job/august/25aug/slurm-243205.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/august/25aug/slurm-243205.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   

UCT HPC clusterJOB DETAILS FOR JOB 243205

captured Mon Aug 25 16:39:44 SAST 2025

JobId=243205 JobName=leaky_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7099 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=00:00:22 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T16:37:54 EligibleTime=2025-08-25T16:37:54
   AccrueTime=2025-08-25T16:37:54
   StartTime=2025-08-25T16:37:54 EndTime=2025-08-25T16:38:16 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:37:54 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:1294475
   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=0,2,4,24-25,28 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/august/25aug/job.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/august/25aug
   StdErr=/scratch/mrpcol001/Diffusion_job/august/25aug/slurm-243205.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/august/25aug/slurm-243205.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   

UCT HPC clusterJOB DETAILS FOR JOB 243205

captured Mon Aug 25 16:40:01 SAST 2025

JobId=243205 JobName=leaky_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7099 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=00:00:22 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T16:37:54 EligibleTime=2025-08-25T16:37:54
   AccrueTime=2025-08-25T16:37:54
   StartTime=2025-08-25T16:37:54 EndTime=2025-08-25T16:38:16 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:37:54 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:1294475
   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=0,2,4,24-25,28 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/august/25aug/job.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/august/25aug
   StdErr=/scratch/mrpcol001/Diffusion_job/august/25aug/slurm-243205.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/august/25aug/slurm-243205.out
   Power=
   TresPerNode=gres/gpu:l40s:1