UCT HPC cluster

JOB DETAILS FOR JOB 788756

captured Tue Apr 28 17:59:01 SAST 2026

MaxRAM=7.3G
MaxVMSize=0G
AveCPUFreq=2M
AveDiskRead=12464189166
AveDiskWrite=2108582725

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7616 Nice=0 Account=a100free QOS=a100free
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:03:35 TimeLimit=00:30:00 TimeMin=N/A
   SubmitTime=2026-04-28T17:55:26 EligibleTime=2026-04-28T17:55:26
   AccrueTime=2026-04-28T17:55:26
   StartTime=2026-04-28T17:55:26 EndTime=2026-04-28T18:25:26 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-28T17:55:26 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc101:1338973
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=2 NumTasks=2 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=2,mem=32G,node=1,billing=6,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=2,mem=32G,node=1,billing=6,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=16,28 Mem=32768 GRES=gpu:ampere:1(IDX:2)
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/XPert/experiment/NM/scripts/mlp/_epoch1_repro/run_all.sbatch
   WorkDir=/scratch/bxxjin001/XPert
   StdErr=/scratch/bxxjin001/XPert/experiment/NM/scripts/mlp/_epoch1_repro/slurm_788756.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/XPert/experiment/NM/scripts/mlp/_epoch1_repro/slurm_788756.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 788756

captured Tue Apr 28 17:59:35 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7616 Nice=0 Account=a100free QOS=a100free
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:04:04 TimeLimit=00:30:00 TimeMin=N/A
   SubmitTime=2026-04-28T17:55:26 EligibleTime=2026-04-28T17:55:26
   AccrueTime=2026-04-28T17:55:26
   StartTime=2026-04-28T17:55:26 EndTime=2026-04-28T17:59:30 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-28T17:55:26 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc101:1338973
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=2 NumTasks=2 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=2,mem=32G,node=1,billing=6,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=2,mem=32G,node=1,billing=6,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=16,28 Mem=32768 GRES=
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/XPert/experiment/NM/scripts/mlp/_epoch1_repro/run_all.sbatch
   WorkDir=/scratch/bxxjin001/XPert
   StdErr=/scratch/bxxjin001/XPert/experiment/NM/scripts/mlp/_epoch1_repro/slurm_788756.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/XPert/experiment/NM/scripts/mlp/_epoch1_repro/slurm_788756.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 788756

captured Tue Apr 28 18:00:01 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7616 Nice=0 Account=a100free QOS=a100free
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:04:04 TimeLimit=00:30:00 TimeMin=N/A
   SubmitTime=2026-04-28T17:55:26 EligibleTime=2026-04-28T17:55:26
   AccrueTime=2026-04-28T17:55:26
   StartTime=2026-04-28T17:55:26 EndTime=2026-04-28T17:59:30 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-28T17:55:26 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc101:1338973
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=2 NumTasks=2 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=2,mem=32G,node=1,billing=6,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=2,mem=32G,node=1,billing=6,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=16,28 Mem=32768 GRES=
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/XPert/experiment/NM/scripts/mlp/_epoch1_repro/run_all.sbatch
   WorkDir=/scratch/bxxjin001/XPert
   StdErr=/scratch/bxxjin001/XPert/experiment/NM/scripts/mlp/_epoch1_repro/slurm_788756.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/XPert/experiment/NM/scripts/mlp/_epoch1_repro/slurm_788756.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 788756

captured Tue Apr 28 18:00:36 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7616 Nice=0 Account=a100free QOS=a100free
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:04:04 TimeLimit=00:30:00 TimeMin=N/A
   SubmitTime=2026-04-28T17:55:26 EligibleTime=2026-04-28T17:55:26
   AccrueTime=2026-04-28T17:55:26
   StartTime=2026-04-28T17:55:26 EndTime=2026-04-28T17:59:30 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-28T17:55:26 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc101:1338973
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=2 NumTasks=2 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=2,mem=32G,node=1,billing=6,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=2,mem=32G,node=1,billing=6,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=16,28 Mem=32768 GRES=
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/XPert/experiment/NM/scripts/mlp/_epoch1_repro/run_all.sbatch
   WorkDir=/scratch/bxxjin001/XPert
   StdErr=/scratch/bxxjin001/XPert/experiment/NM/scripts/mlp/_epoch1_repro/slurm_788756.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/XPert/experiment/NM/scripts/mlp/_epoch1_repro/slurm_788756.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 788756

captured Tue Apr 28 18:01:01 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7616 Nice=0 Account=a100free QOS=a100free
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:04:04 TimeLimit=00:30:00 TimeMin=N/A
   SubmitTime=2026-04-28T17:55:26 EligibleTime=2026-04-28T17:55:26
   AccrueTime=2026-04-28T17:55:26
   StartTime=2026-04-28T17:55:26 EndTime=2026-04-28T17:59:30 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-28T17:55:26 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc101:1338973
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=2 NumTasks=2 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=2,mem=32G,node=1,billing=6,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=2,mem=32G,node=1,billing=6,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=16,28 Mem=32768 GRES=
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/XPert/experiment/NM/scripts/mlp/_epoch1_repro/run_all.sbatch
   WorkDir=/scratch/bxxjin001/XPert
   StdErr=/scratch/bxxjin001/XPert/experiment/NM/scripts/mlp/_epoch1_repro/slurm_788756.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/XPert/experiment/NM/scripts/mlp/_epoch1_repro/slurm_788756.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 788756

captured Tue Apr 28 18:01:35 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7616 Nice=0 Account=a100free QOS=a100free
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:04:04 TimeLimit=00:30:00 TimeMin=N/A
   SubmitTime=2026-04-28T17:55:26 EligibleTime=2026-04-28T17:55:26
   AccrueTime=2026-04-28T17:55:26
   StartTime=2026-04-28T17:55:26 EndTime=2026-04-28T17:59:30 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-28T17:55:26 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc101:1338973
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=2 NumTasks=2 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=2,mem=32G,node=1,billing=6,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=2,mem=32G,node=1,billing=6,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=16,28 Mem=32768 GRES=
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/XPert/experiment/NM/scripts/mlp/_epoch1_repro/run_all.sbatch
   WorkDir=/scratch/bxxjin001/XPert
   StdErr=/scratch/bxxjin001/XPert/experiment/NM/scripts/mlp/_epoch1_repro/slurm_788756.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/XPert/experiment/NM/scripts/mlp/_epoch1_repro/slurm_788756.out
   Power=
   TresPerNode=gres/gpu:ampere:1