UCT HPC cluster

JOB DETAILS FOR JOB 973394

captured Tue Jun 30 19:10:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=9236 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=PENDING Reason=AssocGrpGRES Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-06-30T19:09:24 EligibleTime=2026-06-30T19:09:24
   AccrueTime=2026-06-30T19:09:24
   StartTime=2026-07-02T13:52:11 EndTime=2026-07-04T13:52:11 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-06-30T19:09:38 Scheduler=Backfill:*
   Partition=a100 AllocNode:Sid=srvrochpc001:2498356
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1-1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4
   AllocTRES=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   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/scripts/train_final_gated_deltanet_a100_4x40_shallowwide_full_b6ga8_wandbtimeout_20260630.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-973394.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-973394.out
   Power=
   TresPerNode=gres/gpu:ampere:4
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 973394

captured Tue Jun 30 19:10:50 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=9236 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=AssocGrpGRES Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-06-30T19:09:24 EligibleTime=2026-06-30T19:09:24
   AccrueTime=2026-06-30T19:09:24
   StartTime=2026-06-30T19:10:17 EndTime=2026-06-30T19:10:17 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-06-30T19:10:08 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc001:2498356
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1 NumCPUs=8 NumTasks=N/A CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4
   AllocTRES=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   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/scripts/train_final_gated_deltanet_a100_4x40_shallowwide_full_b6ga8_wandbtimeout_20260630.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-973394.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-973394.out
   Power=
   TresPerNode=gres/gpu:ampere:4
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 973394

captured Tue Jun 30 19:11:31 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=9236 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=AssocGrpGRES Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-06-30T19:09:24 EligibleTime=2026-06-30T19:09:24
   AccrueTime=2026-06-30T19:09:24
   StartTime=2026-06-30T19:10:17 EndTime=2026-06-30T19:10:17 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-06-30T19:10:08 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc001:2498356
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1 NumCPUs=8 NumTasks=N/A CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4
   AllocTRES=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   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/scripts/train_final_gated_deltanet_a100_4x40_shallowwide_full_b6ga8_wandbtimeout_20260630.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-973394.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-973394.out
   Power=
   TresPerNode=gres/gpu:ampere:4
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 973394

captured Tue Jun 30 19:12:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=9236 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=AssocGrpGRES Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-06-30T19:09:24 EligibleTime=2026-06-30T19:09:24
   AccrueTime=2026-06-30T19:09:24
   StartTime=2026-06-30T19:10:17 EndTime=2026-06-30T19:10:17 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-06-30T19:10:08 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc001:2498356
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1 NumCPUs=8 NumTasks=N/A CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4
   AllocTRES=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   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/scripts/train_final_gated_deltanet_a100_4x40_shallowwide_full_b6ga8_wandbtimeout_20260630.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-973394.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-973394.out
   Power=
   TresPerNode=gres/gpu:ampere:4
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL