JOB DETAILS FOR JOB 68050

captured Mon Feb 3 22:33:02 SAST 2025

MaxRAM=3.9G
MaxVMSize=0G
AveCPUFreq=232K
AveDiskRead=22701404325
AveDiskWrite=30293607

JobId=68050 JobName=balanced_sallm
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7409 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=01:18:57 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-02-03T21:14:05 EligibleTime=2025-02-03T21:14:05
   AccrueTime=2025-02-03T21:14:05
   StartTime=2025-02-03T21:14:05 EndTime=2025-02-05T21:14:05 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-02-03T21:14:05 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3617051
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=2 NumTasks=2 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=2,mem=20000M,node=1,billing=3,gres/gpu=2,gres/gpu:l40s=2
   AllocTRES=cpu=2,mem=20000M,node=1,billing=3,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu012 CPU_IDs=8,32 Mem=20000 GRES=gpu:l40s:2(IDX:2-3)
   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/transformer_training/1_l40_balanced_dataset_training.sh
   WorkDir=/home/lmbanr001/masters/sallm/transformer_training
   StdErr=/home/lmbanr001/masters/sallm/transformer_training/slurm-68050.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/transformer_training/slurm-68050.out
   Power=
   TresPerNode=gres/gpu:l40s:2
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
UCT HPC clusterJOB DETAILS FOR JOB 68050

captured Mon Feb 3 22:33:41 SAST 2025

JobId=68050 JobName=balanced_sallm
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7409 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=01:19:17 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-02-03T21:14:05 EligibleTime=2025-02-03T21:14:05
   AccrueTime=2025-02-03T21:14:05
   StartTime=2025-02-03T21:14:05 EndTime=2025-02-03T22:33:22 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-02-03T21:14:05 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3617051
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=2 NumTasks=2 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=2,mem=20000M,node=1,billing=3,gres/gpu=2,gres/gpu:l40s=2
   AllocTRES=cpu=2,mem=20000M,node=1,billing=3,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu012 CPU_IDs=8,32 Mem=20000 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/transformer_training/1_l40_balanced_dataset_training.sh
   WorkDir=/home/lmbanr001/masters/sallm/transformer_training
   StdErr=/home/lmbanr001/masters/sallm/transformer_training/slurm-68050.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/transformer_training/slurm-68050.out
   Power=
   TresPerNode=gres/gpu:l40s:2
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
UCT HPC clusterJOB DETAILS FOR JOB 68050

captured Mon Feb 3 22:34:01 SAST 2025

JobId=68050 JobName=balanced_sallm
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7409 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=01:19:17 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-02-03T21:14:05 EligibleTime=2025-02-03T21:14:05
   AccrueTime=2025-02-03T21:14:05
   StartTime=2025-02-03T21:14:05 EndTime=2025-02-03T22:33:22 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-02-03T21:14:05 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3617051
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=2 NumTasks=2 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=2,mem=20000M,node=1,billing=3,gres/gpu=2,gres/gpu:l40s=2
   AllocTRES=cpu=2,mem=20000M,node=1,billing=3,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu012 CPU_IDs=8,32 Mem=20000 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/transformer_training/1_l40_balanced_dataset_training.sh
   WorkDir=/home/lmbanr001/masters/sallm/transformer_training
   StdErr=/home/lmbanr001/masters/sallm/transformer_training/slurm-68050.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/transformer_training/slurm-68050.out
   Power=
   TresPerNode=gres/gpu:l40s:2
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
UCT HPC clusterJOB DETAILS FOR JOB 68050

captured Mon Feb 3 22:34:41 SAST 2025

JobId=68050 JobName=balanced_sallm
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7409 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=01:19:17 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-02-03T21:14:05 EligibleTime=2025-02-03T21:14:05
   AccrueTime=2025-02-03T21:14:05
   StartTime=2025-02-03T21:14:05 EndTime=2025-02-03T22:33:22 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-02-03T21:14:05 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3617051
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=2 NumTasks=2 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=2,mem=20000M,node=1,billing=3,gres/gpu=2,gres/gpu:l40s=2
   AllocTRES=cpu=2,mem=20000M,node=1,billing=3,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu012 CPU_IDs=8,32 Mem=20000 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/transformer_training/1_l40_balanced_dataset_training.sh
   WorkDir=/home/lmbanr001/masters/sallm/transformer_training
   StdErr=/home/lmbanr001/masters/sallm/transformer_training/slurm-68050.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/transformer_training/slurm-68050.out
   Power=
   TresPerNode=gres/gpu:l40s:2
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
UCT HPC clusterJOB DETAILS FOR JOB 68050

captured Mon Feb 3 22:35:01 SAST 2025

JobId=68050 JobName=balanced_sallm
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7409 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=01:19:17 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-02-03T21:14:05 EligibleTime=2025-02-03T21:14:05
   AccrueTime=2025-02-03T21:14:05
   StartTime=2025-02-03T21:14:05 EndTime=2025-02-03T22:33:22 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-02-03T21:14:05 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3617051
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=2 NumTasks=2 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=2,mem=20000M,node=1,billing=3,gres/gpu=2,gres/gpu:l40s=2
   AllocTRES=cpu=2,mem=20000M,node=1,billing=3,gres/gpu=2,gres/gpu:l40s=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:2
     Nodes=srvrocgpu012 CPU_IDs=8,32 Mem=20000 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/transformer_training/1_l40_balanced_dataset_training.sh
   WorkDir=/home/lmbanr001/masters/sallm/transformer_training
   StdErr=/home/lmbanr001/masters/sallm/transformer_training/slurm-68050.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/sallm/transformer_training/slurm-68050.out
   Power=
   TresPerNode=gres/gpu:l40s:2
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT