UCT HPC cluster

JOB DETAILS FOR JOB 304154

captured Thu Oct 9 16:46:02 SAST 2025

MaxRAM=4G
MaxVMSize=0G
AveCPUFreq=289K
AveDiskRead=9955558250
AveDiskWrite=7188568013

JobId=304154 JobName=transigen_beta05
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7095 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=00:49:52 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-09T15:56:09 EligibleTime=2025-10-09T15:56:09
   AccrueTime=Unknown
   StartTime=2025-10-09T15:56:10 EndTime=2025-10-11T15:56:10 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T15:56:10 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc103:4045142
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=64G,node=1,billing=10,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=64G,node=1,billing=10,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu014 CPU_IDs=2-3,26-27 Mem=65536 GRES=gpu:l40s:1(IDX:1)
   MinCPUsNode=7 MinMemoryNode=64G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/TranSiGen/repro/experiment/train_beta_05.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro/experiment
   StdErr=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_beta05_304154.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_beta05_304154.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 304154

captured Thu Oct 9 16:46:34 SAST 2025

JobId=304154 JobName=transigen_beta05
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7095 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=00:50:05 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-09T15:56:09 EligibleTime=2025-10-09T15:56:09
   AccrueTime=Unknown
   StartTime=2025-10-09T15:56:10 EndTime=2025-10-09T16:46:15 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T15:56:10 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc103:4045142
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=64G,node=1,billing=10,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=64G,node=1,billing=10,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu014 CPU_IDs=2-3,26-27 Mem=65536 GRES=
   MinCPUsNode=7 MinMemoryNode=64G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/TranSiGen/repro/experiment/train_beta_05.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro/experiment
   StdErr=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_beta05_304154.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_beta05_304154.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 304154

captured Thu Oct 9 16:47:01 SAST 2025

JobId=304154 JobName=transigen_beta05
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7095 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=00:50:05 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-09T15:56:09 EligibleTime=2025-10-09T15:56:09
   AccrueTime=Unknown
   StartTime=2025-10-09T15:56:10 EndTime=2025-10-09T16:46:15 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T15:56:10 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc103:4045142
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=64G,node=1,billing=10,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=64G,node=1,billing=10,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu014 CPU_IDs=2-3,26-27 Mem=65536 GRES=
   MinCPUsNode=7 MinMemoryNode=64G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/TranSiGen/repro/experiment/train_beta_05.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro/experiment
   StdErr=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_beta05_304154.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_beta05_304154.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 304154

captured Thu Oct 9 16:47:33 SAST 2025

JobId=304154 JobName=transigen_beta05
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7095 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=00:50:05 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-09T15:56:09 EligibleTime=2025-10-09T15:56:09
   AccrueTime=Unknown
   StartTime=2025-10-09T15:56:10 EndTime=2025-10-09T16:46:15 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T15:56:10 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc103:4045142
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=64G,node=1,billing=10,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=64G,node=1,billing=10,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu014 CPU_IDs=2-3,26-27 Mem=65536 GRES=
   MinCPUsNode=7 MinMemoryNode=64G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/TranSiGen/repro/experiment/train_beta_05.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro/experiment
   StdErr=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_beta05_304154.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_beta05_304154.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 304154

captured Thu Oct 9 16:48:01 SAST 2025

JobId=304154 JobName=transigen_beta05
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7095 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=00:50:05 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-09T15:56:09 EligibleTime=2025-10-09T15:56:09
   AccrueTime=Unknown
   StartTime=2025-10-09T15:56:10 EndTime=2025-10-09T16:46:15 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T15:56:10 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc103:4045142
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=64G,node=1,billing=10,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=64G,node=1,billing=10,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu014 CPU_IDs=2-3,26-27 Mem=65536 GRES=
   MinCPUsNode=7 MinMemoryNode=64G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/TranSiGen/repro/experiment/train_beta_05.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro/experiment
   StdErr=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_beta05_304154.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_beta05_304154.out
   Power=
   TresPerNode=gres/gpu:l40s:1