JOB DETAILS FOR JOB 1342339

captured Wed Sep 16 04:44:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8280 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=PENDING Reason=Resources Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=04:00:00 TimeMin=N/A
   SubmitTime=2026-09-15T09:00:34 EligibleTime=2026-09-16T01:56:15
   AccrueTime=2026-09-15T23:34:44
   StartTime=2026-09-16T08:24:39 EndTime=2026-09-16T12:24:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-16T04:43:52 Scheduler=Backfill:*
   Partition=a100 AllocNode:Sid=srvrochpc001:1645598
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList= SchedNodeList=srvrocgpu010
   NumNodes=1-1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=17,gres/gpu=2,gres/gpu:ampere=2
   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=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260914_v3/audit/run_mzansilm_sib_mono_recovery_v3_20260914.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260914_v3/logs/training-1337543_4.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260914_v3/logs/training-1337543_4.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL
UCT HPC clusterJOB DETAILS FOR JOB 1342339

captured Wed Sep 16 04:44:43 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8280 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=00:00:14 TimeLimit=04:00:00 TimeMin=N/A
   SubmitTime=2026-09-15T09:00:34 EligibleTime=2026-09-16T01:56:15
   AccrueTime=2026-09-15T23:34:44
   StartTime=2026-09-16T04:44:26 EndTime=2026-09-16T04:44:40 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-16T04:44:26 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1645598
   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=17,gres/gpu=2,gres/gpu:ampere=2
   AllocTRES=cpu=8,mem=73136M,node=1,billing=17,gres/gpu=2,gres/gpu:ampere=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:2
     Nodes=srvrocgpu010 CPU_IDs=0-3,6-9 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260914_v3/audit/run_mzansilm_sib_mono_recovery_v3_20260914.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260914_v3/logs/training-1337543_4.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260914_v3/logs/training-1337543_4.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL
UCT HPC clusterJOB DETAILS FOR JOB 1342339

captured Wed Sep 16 04:45:31 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8280 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=00:00:14 TimeLimit=04:00:00 TimeMin=N/A
   SubmitTime=2026-09-15T09:00:34 EligibleTime=2026-09-16T01:56:15
   AccrueTime=2026-09-15T23:34:44
   StartTime=2026-09-16T04:44:26 EndTime=2026-09-16T04:44:40 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-16T04:44:26 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1645598
   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=17,gres/gpu=2,gres/gpu:ampere=2
   AllocTRES=cpu=8,mem=73136M,node=1,billing=17,gres/gpu=2,gres/gpu:ampere=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:2
     Nodes=srvrocgpu010 CPU_IDs=0-3,6-9 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260914_v3/audit/run_mzansilm_sib_mono_recovery_v3_20260914.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260914_v3/logs/training-1337543_4.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260914_v3/logs/training-1337543_4.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL
UCT HPC clusterJOB DETAILS FOR JOB 1342339

captured Wed Sep 16 04:46:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8280 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=00:00:14 TimeLimit=04:00:00 TimeMin=N/A
   SubmitTime=2026-09-15T09:00:34 EligibleTime=2026-09-16T01:56:15
   AccrueTime=2026-09-15T23:34:44
   StartTime=2026-09-16T04:44:26 EndTime=2026-09-16T04:44:40 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-16T04:44:26 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:1645598
   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=17,gres/gpu=2,gres/gpu:ampere=2
   AllocTRES=cpu=8,mem=73136M,node=1,billing=17,gres/gpu=2,gres/gpu:ampere=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:2
     Nodes=srvrocgpu010 CPU_IDs=0-3,6-9 Mem=73136 GRES=
   MinCPUsNode=8 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260914_v3/audit/run_mzansilm_sib_mono_recovery_v3_20260914.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260914_v3/logs/training-1337543_4.out
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm_recovery/mzansilm_sib_mono_20260914_v3/logs/training-1337543_4.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL