JOB DETAILS FOR JOB 1326145

captured Wed Sep 9 10:45:02 SAST 2026

MaxRAM=0G
MaxVMSize=0G
AveCPUFreq=
AveDiskRead=
AveDiskWrite=

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7799 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:30 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-09-09T10:17:23 EligibleTime=2026-09-09T10:17:23
   AccrueTime=2026-09-09T10:17:23
   StartTime=2026-09-09T10:44:32 EndTime=2026-09-11T10:44:32 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-09T10:44:32 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1291605
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=32G,node=1,billing=12,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=32G,node=1,billing=12,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=1,4-10 Mem=32768 GRES=gpu:ampere:1(IDX:2)
   MinCPUsNode=8 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=(null)
   WorkDir=/home/lmbanr001/masters/sallm_snapshots/pure-gdn-base-corrected-20260908-v2
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-base-corrected-g2-a10040-20260909.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-base-corrected-g2-a10040-20260909.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
UCT HPC clusterJOB DETAILS FOR JOB 1326145

captured Wed Sep 9 10:45:41 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7799 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:38 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-09-09T10:17:23 EligibleTime=2026-09-09T10:17:23
   AccrueTime=2026-09-09T10:17:23
   StartTime=2026-09-09T10:44:32 EndTime=2026-09-09T10:45:10 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-09T10:44:32 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1291605
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=32G,node=1,billing=12,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=32G,node=1,billing=12,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=1,4-10 Mem=32768 GRES=
   MinCPUsNode=8 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=(null)
   WorkDir=/home/lmbanr001/masters/sallm_snapshots/pure-gdn-base-corrected-20260908-v2
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-base-corrected-g2-a10040-20260909.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-base-corrected-g2-a10040-20260909.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
UCT HPC clusterJOB DETAILS FOR JOB 1326145

captured Wed Sep 9 10:46:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7799 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:38 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-09-09T10:17:23 EligibleTime=2026-09-09T10:17:23
   AccrueTime=2026-09-09T10:17:23
   StartTime=2026-09-09T10:44:32 EndTime=2026-09-09T10:45:10 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-09T10:44:32 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1291605
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=32G,node=1,billing=12,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=32G,node=1,billing=12,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=1,4-10 Mem=32768 GRES=
   MinCPUsNode=8 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=(null)
   WorkDir=/home/lmbanr001/masters/sallm_snapshots/pure-gdn-base-corrected-20260908-v2
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-base-corrected-g2-a10040-20260909.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-base-corrected-g2-a10040-20260909.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
UCT HPC clusterJOB DETAILS FOR JOB 1326145

captured Wed Sep 9 10:46:39 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7799 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:38 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-09-09T10:17:23 EligibleTime=2026-09-09T10:17:23
   AccrueTime=2026-09-09T10:17:23
   StartTime=2026-09-09T10:44:32 EndTime=2026-09-09T10:45:10 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-09T10:44:32 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1291605
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=32G,node=1,billing=12,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=32G,node=1,billing=12,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=1,4-10 Mem=32768 GRES=
   MinCPUsNode=8 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=(null)
   WorkDir=/home/lmbanr001/masters/sallm_snapshots/pure-gdn-base-corrected-20260908-v2
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-base-corrected-g2-a10040-20260909.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/gdn-base-corrected-g2-a10040-20260909.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8