UCT HPC cluster

JOB DETAILS FOR JOB 118480

captured Sat Apr 26 05:36:42 SAST 2025

MaxRAM=8.7G
MaxVMSize=0G
AveCPUFreq=5K
AveDiskRead=613122146531
AveDiskWrite=1007020726

JobId=118480 JobName=sallm_xlstm_tune
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7737 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=1-23:59:57 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-04-24T05:36:45 EligibleTime=2025-04-24T05:36:45
   AccrueTime=2025-04-24T05:36:45
   StartTime=2025-04-24T05:36:45 EndTime=2025-04-26T05:36:45 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-24T05:36:45 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:150763
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:4
     Nodes=srvrocgpu015 CPU_IDs=0-3,24-27 Mem=80000 GRES=gpu:l40s:4(IDX:0-3)
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/xlstm_training/bayesian_optimizer.sh
   WorkDir=/home/lmbanr001/masters/sallm/xlstm_training
   StdErr=/home/lmbanr001/masters/sallm/xlstm_training/slurm-118480.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/xlstm_training/slurm-118480.out
   Power=
   TresPerNode=gres/gpu:l40s:4
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 118480

captured Sat Apr 26 05:37:01 SAST 2025

JobId=118480 JobName=sallm_xlstm_tune
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7737 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:12 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-04-24T05:36:45 EligibleTime=2025-04-24T05:36:45
   AccrueTime=2025-04-24T05:36:45
   StartTime=2025-04-24T05:36:45 EndTime=2025-04-26T05:36:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-24T05:36:45 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:150763
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:4
     Nodes=srvrocgpu015 CPU_IDs=0-3,24-27 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/xlstm_training/bayesian_optimizer.sh
   WorkDir=/home/lmbanr001/masters/sallm/xlstm_training
   StdErr=/home/lmbanr001/masters/sallm/xlstm_training/slurm-118480.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/xlstm_training/slurm-118480.out
   Power=
   TresPerNode=gres/gpu:l40s:4
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 118480

captured Sat Apr 26 05:37:43 SAST 2025

JobId=118480 JobName=sallm_xlstm_tune
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7737 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:12 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-04-24T05:36:45 EligibleTime=2025-04-24T05:36:45
   AccrueTime=2025-04-24T05:36:45
   StartTime=2025-04-24T05:36:45 EndTime=2025-04-26T05:36:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-24T05:36:45 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:150763
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:4
     Nodes=srvrocgpu015 CPU_IDs=0-3,24-27 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/xlstm_training/bayesian_optimizer.sh
   WorkDir=/home/lmbanr001/masters/sallm/xlstm_training
   StdErr=/home/lmbanr001/masters/sallm/xlstm_training/slurm-118480.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/xlstm_training/slurm-118480.out
   Power=
   TresPerNode=gres/gpu:l40s:4
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 118480

captured Sat Apr 26 05:38:02 SAST 2025

JobId=118480 JobName=sallm_xlstm_tune
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7737 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:12 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-04-24T05:36:45 EligibleTime=2025-04-24T05:36:45
   AccrueTime=2025-04-24T05:36:45
   StartTime=2025-04-24T05:36:45 EndTime=2025-04-26T05:36:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-24T05:36:45 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:150763
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:4
     Nodes=srvrocgpu015 CPU_IDs=0-3,24-27 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/xlstm_training/bayesian_optimizer.sh
   WorkDir=/home/lmbanr001/masters/sallm/xlstm_training
   StdErr=/home/lmbanr001/masters/sallm/xlstm_training/slurm-118480.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/xlstm_training/slurm-118480.out
   Power=
   TresPerNode=gres/gpu:l40s:4
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 118480

captured Sat Apr 26 05:38:44 SAST 2025

JobId=118480 JobName=sallm_xlstm_tune
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7737 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:12 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-04-24T05:36:45 EligibleTime=2025-04-24T05:36:45
   AccrueTime=2025-04-24T05:36:45
   StartTime=2025-04-24T05:36:45 EndTime=2025-04-26T05:36:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-24T05:36:45 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:150763
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:4
     Nodes=srvrocgpu015 CPU_IDs=0-3,24-27 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/xlstm_training/bayesian_optimizer.sh
   WorkDir=/home/lmbanr001/masters/sallm/xlstm_training
   StdErr=/home/lmbanr001/masters/sallm/xlstm_training/slurm-118480.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/xlstm_training/slurm-118480.out
   Power=
   TresPerNode=gres/gpu:l40s:4
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 118480

captured Sat Apr 26 05:39:01 SAST 2025

JobId=118480 JobName=sallm_xlstm_tune
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7737 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:12 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-04-24T05:36:45 EligibleTime=2025-04-24T05:36:45
   AccrueTime=2025-04-24T05:36:45
   StartTime=2025-04-24T05:36:45 EndTime=2025-04-26T05:36:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-24T05:36:45 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:150763
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu015
   BatchHost=srvrocgpu015
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=4,gres/gpu:l40s=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:4
     Nodes=srvrocgpu015 CPU_IDs=0-3,24-27 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/sallm/xlstm_training/bayesian_optimizer.sh
   WorkDir=/home/lmbanr001/masters/sallm/xlstm_training
   StdErr=/home/lmbanr001/masters/sallm/xlstm_training/slurm-118480.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/xlstm_training/slurm-118480.out
   Power=
   TresPerNode=gres/gpu:l40s:4
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT