JOB DETAILS FOR JOB 111413

captured Wed Apr 16 04:39:01 SAST 2025

MaxRAM=6.7G
MaxVMSize=0G
AveCPUFreq=2.60M
AveDiskRead=3138668922
AveDiskWrite=3596545

JobId=111413 JobName=sallm_xlstm_tune
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8910 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:06:58 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-04-16T04:32:03 EligibleTime=2025-04-16T04:32:03
   AccrueTime=2025-04-16T04:32:03
   StartTime=2025-04-16T04:32:03 EndTime=2025-04-18T04:32:03 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-16T04:32:03 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:2598751
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere80=4
   AllocTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere80=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:4
     Nodes=srvrocgpu011 CPU_IDs=0-3,28-31 Mem=73136 GRES=gpu:ampere80:4(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/xlstm_training/bayesian_optimizer.sh
   WorkDir=/home/lmbanr001/masters/sallm/xlstm_training
   StdErr=/home/lmbanr001/masters/sallm/xlstm_training/slurm-111413.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/xlstm_training/slurm-111413.out
   Power=
   TresPerNode=gres/gpu:ampere80:4
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
UCT HPC clusterJOB DETAILS FOR JOB 111413

captured Wed Apr 16 04:39:32 SAST 2025

JobId=111413 JobName=sallm_xlstm_tune
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8910 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:07:07 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-04-16T04:32:03 EligibleTime=2025-04-16T04:32:03
   AccrueTime=2025-04-16T04:32:03
   StartTime=2025-04-16T04:32:03 EndTime=2025-04-16T04:39:10 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-16T04:32:03 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:2598751
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere80=4
   AllocTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere80=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:4
     Nodes=srvrocgpu011 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/xlstm_training/bayesian_optimizer.sh
   WorkDir=/home/lmbanr001/masters/sallm/xlstm_training
   StdErr=/home/lmbanr001/masters/sallm/xlstm_training/slurm-111413.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/xlstm_training/slurm-111413.out
   Power=
   TresPerNode=gres/gpu:ampere80:4
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
UCT HPC clusterJOB DETAILS FOR JOB 111413

captured Wed Apr 16 04:40:02 SAST 2025

JobId=111413 JobName=sallm_xlstm_tune
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8910 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:07:07 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-04-16T04:32:03 EligibleTime=2025-04-16T04:32:03
   AccrueTime=2025-04-16T04:32:03
   StartTime=2025-04-16T04:32:03 EndTime=2025-04-16T04:39:10 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-16T04:32:03 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:2598751
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere80=4
   AllocTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere80=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:4
     Nodes=srvrocgpu011 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/xlstm_training/bayesian_optimizer.sh
   WorkDir=/home/lmbanr001/masters/sallm/xlstm_training
   StdErr=/home/lmbanr001/masters/sallm/xlstm_training/slurm-111413.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/xlstm_training/slurm-111413.out
   Power=
   TresPerNode=gres/gpu:ampere80:4
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
UCT HPC clusterJOB DETAILS FOR JOB 111413

captured Wed Apr 16 04:40:33 SAST 2025

JobId=111413 JobName=sallm_xlstm_tune
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8910 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:07:07 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-04-16T04:32:03 EligibleTime=2025-04-16T04:32:03
   AccrueTime=2025-04-16T04:32:03
   StartTime=2025-04-16T04:32:03 EndTime=2025-04-16T04:39:10 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-16T04:32:03 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:2598751
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere80=4
   AllocTRES=cpu=8,mem=73136M,node=1,billing=19,gres/gpu=4,gres/gpu:ampere80=4
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:4
     Nodes=srvrocgpu011 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/xlstm_training/bayesian_optimizer.sh
   WorkDir=/home/lmbanr001/masters/sallm/xlstm_training
   StdErr=/home/lmbanr001/masters/sallm/xlstm_training/slurm-111413.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/xlstm_training/slurm-111413.out
   Power=
   TresPerNode=gres/gpu:ampere80:4
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT