JOB DETAILS FOR JOB 111697

captured Fri Apr 18 05:18:01 SAST 2025

JobId=111697 JobName=sallm_xlstm_tune
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8775 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=PENDING Reason=Resources Dependency=(null)
   Requeue=1 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=2025-04-18T05:17:41 EligibleTime=2025-04-18T05:17:41
   AccrueTime=2025-04-18T05:17:41
   StartTime=2025-04-19T15:36:32 EndTime=2025-04-21T15:36:32 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-18T05:17:52 Scheduler=Backfill:*
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:3605841
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1-1 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:ampere=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/xlstm_training/bayesian_optimizer.sh
   WorkDir=/home/lmbanr001/masters/sallm/xlstm_training
   StdErr=/home/lmbanr001/masters/sallm/xlstm_training/slurm-111697.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/xlstm_training/slurm-111697.out
   Power=
   TresPerNode=gres/gpu:ampere:4
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
   

UCT HPC clusterJOB DETAILS FOR JOB 111697

captured Fri Apr 18 05:18:33 SAST 2025

JobId=111697 JobName=sallm_xlstm_tune
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8775 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=Resources Dependency=(null)
   Requeue=1 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=2025-04-18T05:17:41 EligibleTime=2025-04-18T05:17:41
   AccrueTime=2025-04-18T05:17:41
   StartTime=2025-04-18T05:18:21 EndTime=2025-04-18T05:18:21 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-18T05:18:03 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:3605841
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   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:ampere=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/xlstm_training/bayesian_optimizer.sh
   WorkDir=/home/lmbanr001/masters/sallm/xlstm_training
   StdErr=/home/lmbanr001/masters/sallm/xlstm_training/slurm-111697.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/xlstm_training/slurm-111697.out
   Power=
   TresPerNode=gres/gpu:ampere:4
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
   

UCT HPC clusterJOB DETAILS FOR JOB 111697

captured Fri Apr 18 05:19:01 SAST 2025

JobId=111697 JobName=sallm_xlstm_tune
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8775 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=Resources Dependency=(null)
   Requeue=1 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=2025-04-18T05:17:41 EligibleTime=2025-04-18T05:17:41
   AccrueTime=2025-04-18T05:17:41
   StartTime=2025-04-18T05:18:21 EndTime=2025-04-18T05:18:21 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-18T05:18:03 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:3605841
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   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:ampere=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/xlstm_training/bayesian_optimizer.sh
   WorkDir=/home/lmbanr001/masters/sallm/xlstm_training
   StdErr=/home/lmbanr001/masters/sallm/xlstm_training/slurm-111697.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/xlstm_training/slurm-111697.out
   Power=
   TresPerNode=gres/gpu:ampere:4
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
   

UCT HPC clusterJOB DETAILS FOR JOB 111697

captured Fri Apr 18 05:19:33 SAST 2025

JobId=111697 JobName=sallm_xlstm_tune
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8775 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=Resources Dependency=(null)
   Requeue=1 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=2025-04-18T05:17:41 EligibleTime=2025-04-18T05:17:41
   AccrueTime=2025-04-18T05:17:41
   StartTime=2025-04-18T05:18:21 EndTime=2025-04-18T05:18:21 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-18T05:18:03 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:3605841
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   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:ampere=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/xlstm_training/bayesian_optimizer.sh
   WorkDir=/home/lmbanr001/masters/sallm/xlstm_training
   StdErr=/home/lmbanr001/masters/sallm/xlstm_training/slurm-111697.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/xlstm_training/slurm-111697.out
   Power=
   TresPerNode=gres/gpu:ampere:4
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
   

UCT HPC clusterJOB DETAILS FOR JOB 111697

captured Fri Apr 18 05:20:01 SAST 2025

JobId=111697 JobName=sallm_xlstm_tune
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8775 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=CANCELLED Reason=Resources Dependency=(null)
   Requeue=1 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=2025-04-18T05:17:41 EligibleTime=2025-04-18T05:17:41
   AccrueTime=2025-04-18T05:17:41
   StartTime=2025-04-18T05:18:21 EndTime=2025-04-18T05:18:21 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-04-18T05:18:03 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:3605841
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   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:ampere=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/xlstm_training/bayesian_optimizer.sh
   WorkDir=/home/lmbanr001/masters/sallm/xlstm_training
   StdErr=/home/lmbanr001/masters/sallm/xlstm_training/slurm-111697.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/xlstm_training/slurm-111697.out
   Power=
   TresPerNode=gres/gpu:ampere:4
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT