UCT HPC cluster

JOB DETAILS FOR JOB 407979

captured Mon Dec 15 10:46:02 SAST 2025

MaxRAM=30G
MaxVMSize=0G
AveCPUFreq=2K
AveDiskRead=15264577136
AveDiskWrite=16399091775

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7829 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=1-23:59:27 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-12-13T10:46:10 EligibleTime=2025-12-13T10:46:10
   AccrueTime=2025-12-13T10:46:10
   StartTime=2025-12-13T10:46:35 EndTime=2025-12-15T10:46:35 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-12-13T10:46:35 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc001:3303641
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=5,gres/gpu=4
   AllocTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:4
     Nodes=srvrocgpu010 CPU_IDs=0-3,28-31 Mem=73136 GRES=gpu:ampere:4(IDX:0-3)
   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-407979.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-407979.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:4
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 407979

captured Mon Dec 15 10:46:51 SAST 2025

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7829 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:13 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-12-13T10:46:10 EligibleTime=2025-12-13T10:46:10
   AccrueTime=2025-12-13T10:46:10
   StartTime=2025-12-13T10:46:35 EndTime=2025-12-15T10:46:48 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-12-13T10:46:35 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc001:3303641
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=5,gres/gpu=4
   AllocTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:4
     Nodes=srvrocgpu010 CPU_IDs=0-3,28-31 Mem=73136 GRES=
   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-407979.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-407979.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:4
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 407979

captured Mon Dec 15 10:47:01 SAST 2025

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7829 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:13 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-12-13T10:46:10 EligibleTime=2025-12-13T10:46:10
   AccrueTime=2025-12-13T10:46:10
   StartTime=2025-12-13T10:46:35 EndTime=2025-12-15T10:46:48 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-12-13T10:46:35 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc001:3303641
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=5,gres/gpu=4
   AllocTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:4
     Nodes=srvrocgpu010 CPU_IDs=0-3,28-31 Mem=73136 GRES=
   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-407979.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-407979.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:4
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 407979

captured Mon Dec 15 10:47:36 SAST 2025

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7829 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:13 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-12-13T10:46:10 EligibleTime=2025-12-13T10:46:10
   AccrueTime=2025-12-13T10:46:10
   StartTime=2025-12-13T10:46:35 EndTime=2025-12-15T10:46:48 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-12-13T10:46:35 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc001:3303641
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=5,gres/gpu=4
   AllocTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:4
     Nodes=srvrocgpu010 CPU_IDs=0-3,28-31 Mem=73136 GRES=
   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-407979.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-407979.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:4
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 407979

captured Mon Dec 15 10:48:01 SAST 2025

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7829 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:13 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-12-13T10:46:10 EligibleTime=2025-12-13T10:46:10
   AccrueTime=2025-12-13T10:46:10
   StartTime=2025-12-13T10:46:35 EndTime=2025-12-15T10:46:48 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-12-13T10:46:35 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc001:3303641
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=5,gres/gpu=4
   AllocTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:4
     Nodes=srvrocgpu010 CPU_IDs=0-3,28-31 Mem=73136 GRES=
   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-407979.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-407979.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:4
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 407979

captured Mon Dec 15 10:48:35 SAST 2025

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7829 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:13 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-12-13T10:46:10 EligibleTime=2025-12-13T10:46:10
   AccrueTime=2025-12-13T10:46:10
   StartTime=2025-12-13T10:46:35 EndTime=2025-12-15T10:46:48 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-12-13T10:46:35 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc001:3303641
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=9142M,node=1,billing=5,gres/gpu=4
   AllocTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:4
     Nodes=srvrocgpu010 CPU_IDs=0-3,28-31 Mem=73136 GRES=
   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-407979.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/slurm-407979.out
   Power=
   CpusPerTres=gres/gpu:2
   TresPerNode=gres/gpu:4
   MailUser=LMBANR001@myuct.ac.za MailType=END,FAIL