JOB DETAILS FOR JOB 503000

captured Tue Feb 3 14:53:36 SAST 2026

MaxRAM=1.7G
MaxVMSize=0G
AveCPUFreq=3.30M
AveDiskRead=215406635
AveDiskWrite=42950

vvnmax002(1221868618 Max Van Veen) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7161 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:25 TimeLimit=1-16:00:00 TimeMin=N/A
   SubmitTime=2026-02-03T14:45:43 EligibleTime=2026-02-03T14:45:43
   AccrueTime=2026-02-03T14:45:43
   StartTime=2026-02-03T14:53:11 EndTime=2026-02-05T06:53:11 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-02-03T14:53:11 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:1232381
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=12 NumTasks=12 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=12,mem=120000M,node=1,billing=23,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=12,mem=120000M,node=1,billing=23,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=1-6,24,26,28-31 Mem=120000 GRES=gpu:l40s:1(IDX:1)
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/vvnmax002/OneTrainer/job_Flux.sh
   WorkDir=/home/vvnmax002/OneTrainer
   StdErr=/home/vvnmax002/OneTrainer/slurm-503000.out
   StdIn=/dev/null
   StdOut=/home/vvnmax002/OneTrainer/slurm-503000.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=VVNMAX002@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
UCT HPC clusterJOB DETAILS FOR JOB 503000

captured Tue Feb 3 14:54:01 SAST 2026

vvnmax002(1221868618 Max Van Veen) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7161 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:31 TimeLimit=1-16:00:00 TimeMin=N/A
   SubmitTime=2026-02-03T14:45:43 EligibleTime=2026-02-03T14:45:43
   AccrueTime=2026-02-03T14:45:43
   StartTime=2026-02-03T14:53:11 EndTime=2026-02-03T14:53:42 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-02-03T14:53:11 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:1232381
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=12 NumTasks=12 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=12,mem=120000M,node=1,billing=23,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=12,mem=120000M,node=1,billing=23,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=1-6,24,26,28-31 Mem=120000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/vvnmax002/OneTrainer/job_Flux.sh
   WorkDir=/home/vvnmax002/OneTrainer
   StdErr=/home/vvnmax002/OneTrainer/slurm-503000.out
   StdIn=/dev/null
   StdOut=/home/vvnmax002/OneTrainer/slurm-503000.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=VVNMAX002@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
UCT HPC clusterJOB DETAILS FOR JOB 503000

captured Tue Feb 3 14:54:36 SAST 2026

vvnmax002(1221868618 Max Van Veen) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7161 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:31 TimeLimit=1-16:00:00 TimeMin=N/A
   SubmitTime=2026-02-03T14:45:43 EligibleTime=2026-02-03T14:45:43
   AccrueTime=2026-02-03T14:45:43
   StartTime=2026-02-03T14:53:11 EndTime=2026-02-03T14:53:42 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-02-03T14:53:11 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:1232381
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=12 NumTasks=12 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=12,mem=120000M,node=1,billing=23,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=12,mem=120000M,node=1,billing=23,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=1-6,24,26,28-31 Mem=120000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/vvnmax002/OneTrainer/job_Flux.sh
   WorkDir=/home/vvnmax002/OneTrainer
   StdErr=/home/vvnmax002/OneTrainer/slurm-503000.out
   StdIn=/dev/null
   StdOut=/home/vvnmax002/OneTrainer/slurm-503000.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=VVNMAX002@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
UCT HPC clusterJOB DETAILS FOR JOB 503000

captured Tue Feb 3 14:55:01 SAST 2026

vvnmax002(1221868618 Max Van Veen) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7161 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:31 TimeLimit=1-16:00:00 TimeMin=N/A
   SubmitTime=2026-02-03T14:45:43 EligibleTime=2026-02-03T14:45:43
   AccrueTime=2026-02-03T14:45:43
   StartTime=2026-02-03T14:53:11 EndTime=2026-02-03T14:53:42 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-02-03T14:53:11 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:1232381
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=12 NumTasks=12 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=12,mem=120000M,node=1,billing=23,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=12,mem=120000M,node=1,billing=23,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=1-6,24,26,28-31 Mem=120000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/vvnmax002/OneTrainer/job_Flux.sh
   WorkDir=/home/vvnmax002/OneTrainer
   StdErr=/home/vvnmax002/OneTrainer/slurm-503000.out
   StdIn=/dev/null
   StdOut=/home/vvnmax002/OneTrainer/slurm-503000.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=VVNMAX002@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT