JOB DETAILS FOR JOB 1238982

captured Sun Aug 16 10:20:01 SAST 2026

MaxRAM=1.2G
MaxVMSize=0G
AveCPUFreq=800K
AveDiskRead=1401973422
AveDiskWrite=324003

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8255 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=00:01:00 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-08-16T10:19:00 EligibleTime=2026-08-16T10:19:00
   AccrueTime=2026-08-16T10:19:00
   StartTime=2026-08-16T10:19:01 EndTime=2026-08-17T10:19:01 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-16T10:19:01 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1348703
   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=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,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=0-1,4-9 Mem=73136 GRES=gpu:ampere:1(IDX:1)
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm_snapshots/pure-gdn-hpo-poscache-lastlogit-20260816-61ce254f/scripts/run_pos_stage_b_with_cache_gate.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-pure_gdn-pos-stage_b-b1-seed42-cachegate-v2-1238982.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-pure_gdn-pos-stage_b-b1-seed42-cachegate-v2-1238982.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL
UCT HPC clusterJOB DETAILS FOR JOB 1238982

captured Sun Aug 16 10:20:36 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8255 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=00:01:33 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-08-16T10:19:00 EligibleTime=2026-08-16T10:19:00
   AccrueTime=2026-08-16T10:19:00
   StartTime=2026-08-16T10:19:01 EndTime=2026-08-16T10:20:34 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-16T10:19:01 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1348703
   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=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,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=0-1,4-9 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm_snapshots/pure-gdn-hpo-poscache-lastlogit-20260816-61ce254f/scripts/run_pos_stage_b_with_cache_gate.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-pure_gdn-pos-stage_b-b1-seed42-cachegate-v2-1238982.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-pure_gdn-pos-stage_b-b1-seed42-cachegate-v2-1238982.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL
UCT HPC clusterJOB DETAILS FOR JOB 1238982

captured Sun Aug 16 10:21:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8255 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=00:01:33 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-08-16T10:19:00 EligibleTime=2026-08-16T10:19:00
   AccrueTime=2026-08-16T10:19:00
   StartTime=2026-08-16T10:19:01 EndTime=2026-08-16T10:20:34 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-16T10:19:01 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1348703
   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=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,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=0-1,4-9 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm_snapshots/pure-gdn-hpo-poscache-lastlogit-20260816-61ce254f/scripts/run_pos_stage_b_with_cache_gate.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-pure_gdn-pos-stage_b-b1-seed42-cachegate-v2-1238982.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-pure_gdn-pos-stage_b-b1-seed42-cachegate-v2-1238982.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL
UCT HPC clusterJOB DETAILS FOR JOB 1238982

captured Sun Aug 16 10:21:37 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8255 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=00:01:33 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-08-16T10:19:00 EligibleTime=2026-08-16T10:19:00
   AccrueTime=2026-08-16T10:19:00
   StartTime=2026-08-16T10:19:01 EndTime=2026-08-16T10:20:34 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-16T10:19:01 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1348703
   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=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,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=0-1,4-9 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm_snapshots/pure-gdn-hpo-poscache-lastlogit-20260816-61ce254f/scripts/run_pos_stage_b_with_cache_gate.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-pure_gdn-pos-stage_b-b1-seed42-cachegate-v2-1238982.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-pure_gdn-pos-stage_b-b1-seed42-cachegate-v2-1238982.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL
UCT HPC clusterJOB DETAILS FOR JOB 1238982

captured Sun Aug 16 10:22:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8255 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=00:01:33 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-08-16T10:19:00 EligibleTime=2026-08-16T10:19:00
   AccrueTime=2026-08-16T10:19:00
   StartTime=2026-08-16T10:19:01 EndTime=2026-08-16T10:20:34 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-16T10:19:01 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1348703
   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=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,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=0-1,4-9 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm_snapshots/pure-gdn-hpo-poscache-lastlogit-20260816-61ce254f/scripts/run_pos_stage_b_with_cache_gate.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-pure_gdn-pos-stage_b-b1-seed42-cachegate-v2-1238982.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/logs/jobs/hpo-pure_gdn-pos-stage_b-b1-seed42-cachegate-v2-1238982.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL