JOB DETAILS FOR JOB 1488636

captured Thu Oct 15 13:02:01 SAST 2026

MaxRAM=13.3G
MaxVMSize=0G
AveCPUFreq=143K
AveDiskRead=39661484298
AveDiskWrite=197733464

fdgjer001(1476211153 Jeremiah Fadugba) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7801 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=00:51:40 TimeLimit=06:00:00 TimeMin=N/A
   SubmitTime=2026-10-15T12:09:49 EligibleTime=2026-10-15T12:09:49
   AccrueTime=2026-10-15T12:09:49
   StartTime=2026-10-15T12:10:21 EndTime=2026-10-15T18:10:21 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-15T12:10:21 Scheduler=Backfill
   Partition=l40s AllocNode:Sid=srvrochpc101:3620289
   ReqNodeList=(null) ExcNodeList=srvrocgpu013
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=12 NumTasks=1 CPUs/Task=12 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=12,mem=96G,node=1,billing=21,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=12,mem=96G,node=1,billing=21,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu016 CPU_IDs=3,6,8-17 Mem=98304 GRES=gpu:l40s:1(IDX:2)
   MinCPUsNode=12 MinMemoryNode=96G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/fdgjer001/unrolled-pet-pp/scripts/train_array.sh
   WorkDir=/home/fdgjer001/unrolled-pet-pp
   StdErr=/home/fdgjer001/unrolled-pet-pp/work/logs/train_1488634_1.out
   StdIn=/dev/null
   StdOut=/home/fdgjer001/unrolled-pet-pp/work/logs/train_1488634_1.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:12
   

UCT HPC clusterJOB DETAILS FOR JOB 1488636

captured Thu Oct 15 13:02:36 SAST 2026

fdgjer001(1476211153 Jeremiah Fadugba) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7801 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=00:51:48 TimeLimit=06:00:00 TimeMin=N/A
   SubmitTime=2026-10-15T12:09:49 EligibleTime=2026-10-15T12:09:49
   AccrueTime=2026-10-15T12:09:49
   StartTime=2026-10-15T12:10:21 EndTime=2026-10-15T13:02:09 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-15T12:10:21 Scheduler=Backfill
   Partition=l40s AllocNode:Sid=srvrochpc101:3620289
   ReqNodeList=(null) ExcNodeList=srvrocgpu013
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=12 NumTasks=1 CPUs/Task=12 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=12,mem=96G,node=1,billing=21,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=12,mem=96G,node=1,billing=21,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu016 CPU_IDs=3,6,8-17 Mem=98304 GRES=
   MinCPUsNode=12 MinMemoryNode=96G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/fdgjer001/unrolled-pet-pp/scripts/train_array.sh
   WorkDir=/home/fdgjer001/unrolled-pet-pp
   StdErr=/home/fdgjer001/unrolled-pet-pp/work/logs/train_1488634_1.out
   StdIn=/dev/null
   StdOut=/home/fdgjer001/unrolled-pet-pp/work/logs/train_1488634_1.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:12
   

UCT HPC clusterJOB DETAILS FOR JOB 1488636

captured Thu Oct 15 13:03:01 SAST 2026

fdgjer001(1476211153 Jeremiah Fadugba) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7801 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=00:51:48 TimeLimit=06:00:00 TimeMin=N/A
   SubmitTime=2026-10-15T12:09:49 EligibleTime=2026-10-15T12:09:49
   AccrueTime=2026-10-15T12:09:49
   StartTime=2026-10-15T12:10:21 EndTime=2026-10-15T13:02:09 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-15T12:10:21 Scheduler=Backfill
   Partition=l40s AllocNode:Sid=srvrochpc101:3620289
   ReqNodeList=(null) ExcNodeList=srvrocgpu013
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=12 NumTasks=1 CPUs/Task=12 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=12,mem=96G,node=1,billing=21,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=12,mem=96G,node=1,billing=21,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu016 CPU_IDs=3,6,8-17 Mem=98304 GRES=
   MinCPUsNode=12 MinMemoryNode=96G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/fdgjer001/unrolled-pet-pp/scripts/train_array.sh
   WorkDir=/home/fdgjer001/unrolled-pet-pp
   StdErr=/home/fdgjer001/unrolled-pet-pp/work/logs/train_1488634_1.out
   StdIn=/dev/null
   StdOut=/home/fdgjer001/unrolled-pet-pp/work/logs/train_1488634_1.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:12
   

UCT HPC clusterJOB DETAILS FOR JOB 1488636

captured Thu Oct 15 13:03:36 SAST 2026

fdgjer001(1476211153 Jeremiah Fadugba) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7801 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=00:51:48 TimeLimit=06:00:00 TimeMin=N/A
   SubmitTime=2026-10-15T12:09:49 EligibleTime=2026-10-15T12:09:49
   AccrueTime=2026-10-15T12:09:49
   StartTime=2026-10-15T12:10:21 EndTime=2026-10-15T13:02:09 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-15T12:10:21 Scheduler=Backfill
   Partition=l40s AllocNode:Sid=srvrochpc101:3620289
   ReqNodeList=(null) ExcNodeList=srvrocgpu013
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=12 NumTasks=1 CPUs/Task=12 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=12,mem=96G,node=1,billing=21,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=12,mem=96G,node=1,billing=21,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu016 CPU_IDs=3,6,8-17 Mem=98304 GRES=
   MinCPUsNode=12 MinMemoryNode=96G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/fdgjer001/unrolled-pet-pp/scripts/train_array.sh
   WorkDir=/home/fdgjer001/unrolled-pet-pp
   StdErr=/home/fdgjer001/unrolled-pet-pp/work/logs/train_1488634_1.out
   StdIn=/dev/null
   StdOut=/home/fdgjer001/unrolled-pet-pp/work/logs/train_1488634_1.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:12
   

UCT HPC clusterJOB DETAILS FOR JOB 1488636

captured Thu Oct 15 13:04:02 SAST 2026

fdgjer001(1476211153 Jeremiah Fadugba) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7801 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=00:51:48 TimeLimit=06:00:00 TimeMin=N/A
   SubmitTime=2026-10-15T12:09:49 EligibleTime=2026-10-15T12:09:49
   AccrueTime=2026-10-15T12:09:49
   StartTime=2026-10-15T12:10:21 EndTime=2026-10-15T13:02:09 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-15T12:10:21 Scheduler=Backfill
   Partition=l40s AllocNode:Sid=srvrochpc101:3620289
   ReqNodeList=(null) ExcNodeList=srvrocgpu013
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=12 NumTasks=1 CPUs/Task=12 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=12,mem=96G,node=1,billing=21,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=12,mem=96G,node=1,billing=21,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu016 CPU_IDs=3,6,8-17 Mem=98304 GRES=
   MinCPUsNode=12 MinMemoryNode=96G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/fdgjer001/unrolled-pet-pp/scripts/train_array.sh
   WorkDir=/home/fdgjer001/unrolled-pet-pp
   StdErr=/home/fdgjer001/unrolled-pet-pp/work/logs/train_1488634_1.out
   StdIn=/dev/null
   StdOut=/home/fdgjer001/unrolled-pet-pp/work/logs/train_1488634_1.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:12