JOB DETAILS FOR JOB 94406

captured Thu Mar 13 12:26:36 SAST 2025

MaxRAM=8.3G
MaxVMSize=0G
AveCPUFreq=3.30M
AveDiskRead=987745640
AveDiskWrite=8676018

JobId=94406 JobName=SOS_k_test_bce
   UserId=flcjam002(292170927 James Falconer) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7320 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=02:20:27 TimeLimit=12:00:00 TimeMin=N/A
   SubmitTime=2025-03-13T10:06:09 EligibleTime=2025-03-13T10:06:09
   AccrueTime=2025-03-13T10:06:09
   StartTime=2025-03-13T10:06:09 EndTime=2025-03-13T22:06:09 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-03-13T10:06:09 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3934411
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=24 Mem=10000 GRES=gpu:l40s:1(IDX:0)
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/flcjam002/k_fold_training_custom.sh
   WorkDir=/home/flcjam002
   StdErr=/home/flcjam002/slurm-94406.out
   StdIn=/dev/null
   StdOut=/home/flcjam002/slurm-94406.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=flcjam002@myuct.ac.za MailType=END,FAIL
   

UCT HPC clusterJOB DETAILS FOR JOB 94406

captured Thu Mar 13 12:27:01 SAST 2025

JobId=94406 JobName=SOS_k_test_bce
   UserId=flcjam002(292170927 James Falconer) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7320 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=OUT_OF_MEMORY Reason=OutOfMemory Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:125
   DerivedExitCode=0:0
   RunTime=02:20:33 TimeLimit=12:00:00 TimeMin=N/A
   SubmitTime=2025-03-13T10:06:09 EligibleTime=2025-03-13T10:06:09
   AccrueTime=2025-03-13T10:06:09
   StartTime=2025-03-13T10:06:09 EndTime=2025-03-13T12:26:42 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-03-13T10:06:09 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3934411
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=24 Mem=10000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/flcjam002/k_fold_training_custom.sh
   WorkDir=/home/flcjam002
   StdErr=/home/flcjam002/slurm-94406.out
   StdIn=/dev/null
   StdOut=/home/flcjam002/slurm-94406.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=flcjam002@myuct.ac.za MailType=END,FAIL
   

UCT HPC clusterJOB DETAILS FOR JOB 94406

captured Thu Mar 13 12:27:36 SAST 2025

JobId=94406 JobName=SOS_k_test_bce
   UserId=flcjam002(292170927 James Falconer) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7320 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=OUT_OF_MEMORY Reason=OutOfMemory Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:125
   DerivedExitCode=0:0
   RunTime=02:20:33 TimeLimit=12:00:00 TimeMin=N/A
   SubmitTime=2025-03-13T10:06:09 EligibleTime=2025-03-13T10:06:09
   AccrueTime=2025-03-13T10:06:09
   StartTime=2025-03-13T10:06:09 EndTime=2025-03-13T12:26:42 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-03-13T10:06:09 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3934411
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=24 Mem=10000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/flcjam002/k_fold_training_custom.sh
   WorkDir=/home/flcjam002
   StdErr=/home/flcjam002/slurm-94406.out
   StdIn=/dev/null
   StdOut=/home/flcjam002/slurm-94406.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=flcjam002@myuct.ac.za MailType=END,FAIL
   

UCT HPC clusterJOB DETAILS FOR JOB 94406

captured Thu Mar 13 12:28:01 SAST 2025

JobId=94406 JobName=SOS_k_test_bce
   UserId=flcjam002(292170927 James Falconer) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7320 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=OUT_OF_MEMORY Reason=OutOfMemory Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:125
   DerivedExitCode=0:0
   RunTime=02:20:33 TimeLimit=12:00:00 TimeMin=N/A
   SubmitTime=2025-03-13T10:06:09 EligibleTime=2025-03-13T10:06:09
   AccrueTime=2025-03-13T10:06:09
   StartTime=2025-03-13T10:06:09 EndTime=2025-03-13T12:26:42 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-03-13T10:06:09 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3934411
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=24 Mem=10000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/flcjam002/k_fold_training_custom.sh
   WorkDir=/home/flcjam002
   StdErr=/home/flcjam002/slurm-94406.out
   StdIn=/dev/null
   StdOut=/home/flcjam002/slurm-94406.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=flcjam002@myuct.ac.za MailType=END,FAIL
   

UCT HPC clusterJOB DETAILS FOR JOB 94406

captured Thu Mar 13 12:28:36 SAST 2025

JobId=94406 JobName=SOS_k_test_bce
   UserId=flcjam002(292170927 James Falconer) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7320 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=OUT_OF_MEMORY Reason=OutOfMemory Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:125
   DerivedExitCode=0:0
   RunTime=02:20:33 TimeLimit=12:00:00 TimeMin=N/A
   SubmitTime=2025-03-13T10:06:09 EligibleTime=2025-03-13T10:06:09
   AccrueTime=2025-03-13T10:06:09
   StartTime=2025-03-13T10:06:09 EndTime=2025-03-13T12:26:42 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-03-13T10:06:09 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3934411
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=24 Mem=10000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/flcjam002/k_fold_training_custom.sh
   WorkDir=/home/flcjam002
   StdErr=/home/flcjam002/slurm-94406.out
   StdIn=/dev/null
   StdOut=/home/flcjam002/slurm-94406.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=flcjam002@myuct.ac.za MailType=END,FAIL
   

UCT HPC clusterJOB DETAILS FOR JOB 94406

captured Thu Mar 13 12:29:01 SAST 2025

JobId=94406 JobName=SOS_k_test_bce
   UserId=flcjam002(292170927 James Falconer) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7320 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=OUT_OF_MEMORY Reason=OutOfMemory Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:125
   DerivedExitCode=0:0
   RunTime=02:20:33 TimeLimit=12:00:00 TimeMin=N/A
   SubmitTime=2025-03-13T10:06:09 EligibleTime=2025-03-13T10:06:09
   AccrueTime=2025-03-13T10:06:09
   StartTime=2025-03-13T10:06:09 EndTime=2025-03-13T12:26:42 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-03-13T10:06:09 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3934411
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=24 Mem=10000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/flcjam002/k_fold_training_custom.sh
   WorkDir=/home/flcjam002
   StdErr=/home/flcjam002/slurm-94406.out
   StdIn=/dev/null
   StdOut=/home/flcjam002/slurm-94406.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=flcjam002@myuct.ac.za MailType=END,FAIL