UCT HPC cluster

JOB DETAILS FOR JOB 242528

captured Sun Aug 24 23:41:01 SAST 2025

MaxRAM=3.2G
MaxVMSize=0G
AveCPUFreq=796K
AveDiskRead=235864880
AveDiskWrite=15981477907

JobId=242528 JobName=MiTCP_LINCS
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7090 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=01:26:04 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-08-24T22:14:57 EligibleTime=2025-08-24T22:14:57
   AccrueTime=2025-08-24T22:14:57
   StartTime=2025-08-24T22:14:57 EndTime=2025-08-26T22:14:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-24T22:14:57 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc100:4142158
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu013 CPU_IDs=4-5,28-29 Mem=40000 GRES=gpu:l40s:1(IDX:3)
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250825/scripts/submit_training.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250825/scripts
   StdErr=/scratch/bxxjin001/DDR/code/20250825/logs/MiTCP_LINCS_242528.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250825/logs/MiTCP_LINCS_242528.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 242528

captured Sun Aug 24 23:41:35 SAST 2025

JobId=242528 JobName=MiTCP_LINCS
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7090 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=01:26:28 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-08-24T22:14:57 EligibleTime=2025-08-24T22:14:57
   AccrueTime=2025-08-24T22:14:57
   StartTime=2025-08-24T22:14:57 EndTime=2025-08-24T23:41:25 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-24T22:14:57 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc100:4142158
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu013 CPU_IDs=4-5,28-29 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250825/scripts/submit_training.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250825/scripts
   StdErr=/scratch/bxxjin001/DDR/code/20250825/logs/MiTCP_LINCS_242528.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250825/logs/MiTCP_LINCS_242528.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 242528

captured Sun Aug 24 23:42:01 SAST 2025

JobId=242528 JobName=MiTCP_LINCS
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7090 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=01:26:28 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-08-24T22:14:57 EligibleTime=2025-08-24T22:14:57
   AccrueTime=2025-08-24T22:14:57
   StartTime=2025-08-24T22:14:57 EndTime=2025-08-24T23:41:25 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-24T22:14:57 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc100:4142158
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu013 CPU_IDs=4-5,28-29 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250825/scripts/submit_training.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250825/scripts
   StdErr=/scratch/bxxjin001/DDR/code/20250825/logs/MiTCP_LINCS_242528.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250825/logs/MiTCP_LINCS_242528.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 242528

captured Sun Aug 24 23:42:35 SAST 2025

JobId=242528 JobName=MiTCP_LINCS
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7090 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=01:26:28 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-08-24T22:14:57 EligibleTime=2025-08-24T22:14:57
   AccrueTime=2025-08-24T22:14:57
   StartTime=2025-08-24T22:14:57 EndTime=2025-08-24T23:41:25 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-24T22:14:57 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc100:4142158
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu013 CPU_IDs=4-5,28-29 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250825/scripts/submit_training.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250825/scripts
   StdErr=/scratch/bxxjin001/DDR/code/20250825/logs/MiTCP_LINCS_242528.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250825/logs/MiTCP_LINCS_242528.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 242528

captured Sun Aug 24 23:43:02 SAST 2025

JobId=242528 JobName=MiTCP_LINCS
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7090 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=01:26:28 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-08-24T22:14:57 EligibleTime=2025-08-24T22:14:57
   AccrueTime=2025-08-24T22:14:57
   StartTime=2025-08-24T22:14:57 EndTime=2025-08-24T23:41:25 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-24T22:14:57 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc100:4142158
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu013 CPU_IDs=4-5,28-29 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250825/scripts/submit_training.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250825/scripts
   StdErr=/scratch/bxxjin001/DDR/code/20250825/logs/MiTCP_LINCS_242528.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250825/logs/MiTCP_LINCS_242528.out
   Power=
   TresPerNode=gres/gpu:l40s:1