JOB DETAILS FOR JOB 416042

captured Wed Jan 7 10:57:33 SAST 2026

nzmglo001(1221800295 Mbithe Nzomo) GroupId=1767200513(1767200513) MCS_label=N/A
   Priority=7551 Nice=0 Account=acsl QOS=acsl
   JobState=PENDING Reason=QOSMaxGRESPerUser Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=3-00:00:00 TimeMin=N/A
   SubmitTime=2026-01-07T10:57:24 EligibleTime=2026-01-07T10:57:24
   AccrueTime=2026-01-07T10:57:24
   StartTime=Unknown EndTime=Unknown Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-07T10:57:24 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc100:253577
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1-1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=54852M,node=1,billing=12,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/nzmglo001/train_script.sh
   WorkDir=/home/nzmglo001
   StdErr=/home/nzmglo001/~/logs/job_416042.err
   StdIn=/dev/null
   StdOut=/home/nzmglo001/~/logs/job_416042.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=nzmglo001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
UCT HPC clusterJOB DETAILS FOR JOB 416042

captured Wed Jan 7 10:58:01 SAST 2026

nzmglo001(1221800295 Mbithe Nzomo) GroupId=1767200513(1767200513) MCS_label=N/A
   Priority=7551 Nice=0 Account=acsl QOS=acsl
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:03 TimeLimit=3-00:00:00 TimeMin=N/A
   SubmitTime=2026-01-07T10:57:24 EligibleTime=2026-01-07T10:57:24
   AccrueTime=2026-01-07T10:57:24
   StartTime=2026-01-07T10:57:50 EndTime=2026-01-07T10:57:53 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-07T10:57:50 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc100:253577
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=54852M,node=1,billing=12,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=6,mem=54852M,node=1,billing=12,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=5-6,8,33-34,36 Mem=54852 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/nzmglo001/train_script.sh
   WorkDir=/home/nzmglo001
   StdErr=/home/nzmglo001/~/logs/job_416042.err
   StdIn=/dev/null
   StdOut=/home/nzmglo001/~/logs/job_416042.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=nzmglo001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
UCT HPC clusterJOB DETAILS FOR JOB 416042

captured Wed Jan 7 10:58:34 SAST 2026

nzmglo001(1221800295 Mbithe Nzomo) GroupId=1767200513(1767200513) MCS_label=N/A
   Priority=7551 Nice=0 Account=acsl QOS=acsl
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:03 TimeLimit=3-00:00:00 TimeMin=N/A
   SubmitTime=2026-01-07T10:57:24 EligibleTime=2026-01-07T10:57:24
   AccrueTime=2026-01-07T10:57:24
   StartTime=2026-01-07T10:57:50 EndTime=2026-01-07T10:57:53 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-07T10:57:50 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc100:253577
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=54852M,node=1,billing=12,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=6,mem=54852M,node=1,billing=12,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=5-6,8,33-34,36 Mem=54852 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/nzmglo001/train_script.sh
   WorkDir=/home/nzmglo001
   StdErr=/home/nzmglo001/~/logs/job_416042.err
   StdIn=/dev/null
   StdOut=/home/nzmglo001/~/logs/job_416042.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=nzmglo001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
UCT HPC clusterJOB DETAILS FOR JOB 416042

captured Wed Jan 7 10:59:01 SAST 2026

nzmglo001(1221800295 Mbithe Nzomo) GroupId=1767200513(1767200513) MCS_label=N/A
   Priority=7551 Nice=0 Account=acsl QOS=acsl
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:03 TimeLimit=3-00:00:00 TimeMin=N/A
   SubmitTime=2026-01-07T10:57:24 EligibleTime=2026-01-07T10:57:24
   AccrueTime=2026-01-07T10:57:24
   StartTime=2026-01-07T10:57:50 EndTime=2026-01-07T10:57:53 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-07T10:57:50 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc100:253577
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=54852M,node=1,billing=12,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=6,mem=54852M,node=1,billing=12,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=5-6,8,33-34,36 Mem=54852 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/nzmglo001/train_script.sh
   WorkDir=/home/nzmglo001
   StdErr=/home/nzmglo001/~/logs/job_416042.err
   StdIn=/dev/null
   StdOut=/home/nzmglo001/~/logs/job_416042.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=nzmglo001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
UCT HPC clusterJOB DETAILS FOR JOB 416042

captured Wed Jan 7 10:59:34 SAST 2026

nzmglo001(1221800295 Mbithe Nzomo) GroupId=1767200513(1767200513) MCS_label=N/A
   Priority=7551 Nice=0 Account=acsl QOS=acsl
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:03 TimeLimit=3-00:00:00 TimeMin=N/A
   SubmitTime=2026-01-07T10:57:24 EligibleTime=2026-01-07T10:57:24
   AccrueTime=2026-01-07T10:57:24
   StartTime=2026-01-07T10:57:50 EndTime=2026-01-07T10:57:53 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-07T10:57:50 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc100:253577
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=54852M,node=1,billing=12,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=6,mem=54852M,node=1,billing=12,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=5-6,8,33-34,36 Mem=54852 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/nzmglo001/train_script.sh
   WorkDir=/home/nzmglo001
   StdErr=/home/nzmglo001/~/logs/job_416042.err
   StdIn=/dev/null
   StdOut=/home/nzmglo001/~/logs/job_416042.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=nzmglo001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
UCT HPC clusterJOB DETAILS FOR JOB 416042

captured Wed Jan 7 11:00:02 SAST 2026

nzmglo001(1221800295 Mbithe Nzomo) GroupId=1767200513(1767200513) MCS_label=N/A
   Priority=7551 Nice=0 Account=acsl QOS=acsl
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:03 TimeLimit=3-00:00:00 TimeMin=N/A
   SubmitTime=2026-01-07T10:57:24 EligibleTime=2026-01-07T10:57:24
   AccrueTime=2026-01-07T10:57:24
   StartTime=2026-01-07T10:57:50 EndTime=2026-01-07T10:57:53 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-07T10:57:50 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc100:253577
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=54852M,node=1,billing=12,gres/gpu=1,gres/gpu:ampere80=1
   AllocTRES=cpu=6,mem=54852M,node=1,billing=12,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=5-6,8,33-34,36 Mem=54852 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/nzmglo001/train_script.sh
   WorkDir=/home/nzmglo001
   StdErr=/home/nzmglo001/~/logs/job_416042.err
   StdIn=/dev/null
   StdOut=/home/nzmglo001/~/logs/job_416042.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=nzmglo001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT