UCT HPC cluster

JOB DETAILS FOR JOB 384725

captured Fri Nov 28 15:51:01 SAST 2025

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7773 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=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-11-28T15:49:37 EligibleTime=2025-11-28T15:49:37
   AccrueTime=2025-11-28T15:49:37
   StartTime=2025-11-30T04:09:58 EndTime=2025-12-02T04:09:58 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-28T15:50:57 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:216500
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1-1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=5,gres/gpu=4
   AllocTRES=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=1 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_mamba.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-384725.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-384725.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:4
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 384725

captured Fri Nov 28 15:51:35 SAST 2025

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7773 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=Resources 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=2025-11-28T15:49:37 EligibleTime=2025-11-28T15:49:37
   AccrueTime=2025-11-28T15:49:37
   StartTime=2025-11-28T15:51:03 EndTime=2025-11-28T15:51:03 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-28T15:50:57 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:216500
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1 NumCPUs=8 NumTasks=N/A CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=5,gres/gpu=4
   AllocTRES=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=1 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_mamba.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-384725.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-384725.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:4
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 384725

captured Fri Nov 28 15:52:01 SAST 2025

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7773 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=Resources 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=2025-11-28T15:49:37 EligibleTime=2025-11-28T15:49:37
   AccrueTime=2025-11-28T15:49:37
   StartTime=2025-11-28T15:51:03 EndTime=2025-11-28T15:51:03 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-28T15:50:57 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:216500
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1 NumCPUs=8 NumTasks=N/A CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=5,gres/gpu=4
   AllocTRES=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=1 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_mamba.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-384725.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-384725.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:4
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 384725

captured Fri Nov 28 15:52:35 SAST 2025

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7773 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=Resources 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=2025-11-28T15:49:37 EligibleTime=2025-11-28T15:49:37
   AccrueTime=2025-11-28T15:49:37
   StartTime=2025-11-28T15:51:03 EndTime=2025-11-28T15:51:03 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-28T15:50:57 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:216500
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1 NumCPUs=8 NumTasks=N/A CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=5,gres/gpu=4
   AllocTRES=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=1 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_mamba.sh
   WorkDir=/home/lmbanr001/masters/sallm
   StdErr=/home/lmbanr001/masters/sallm/slurm-384725.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-384725.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:4
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL