UCT HPC cluster

JOB DETAILS FOR JOB 788767

captured Tue Apr 28 18:42:35 SAST 2026

MaxRAM=5.6G
MaxVMSize=0G
AveCPUFreq=800K
AveDiskRead=7503727092
AveDiskWrite=27461315050

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=00:38:54 TimeLimit=01:30:00 TimeMin=N/A
   SubmitTime=2026-04-28T18:03:41 EligibleTime=2026-04-28T18:03:41
   AccrueTime=2026-04-28T18:03:41
   StartTime=2026-04-28T18:03:41 EndTime=2026-04-28T19:33:41 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-28T18:03:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc101:1348080
   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/experiments/phase3_mlp_baseline/default_retrain_2026-04-28/run_retrain.sbatch
   WorkDir=/scratch/bxxjin001/XPert
   StdErr=/scratch/bxxjin001/XPert/experiment/NM/experiments/phase3_mlp_baseline/default_retrain_2026-04-28/slurm_788767.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/XPert/experiment/NM/experiments/phase3_mlp_baseline/default_retrain_2026-04-28/slurm_788767.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 788767

captured Tue Apr 28 18:43:01 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=00:39:13 TimeLimit=01:30:00 TimeMin=N/A
   SubmitTime=2026-04-28T18:03:41 EligibleTime=2026-04-28T18:03:41
   AccrueTime=2026-04-28T18:03:41
   StartTime=2026-04-28T18:03:41 EndTime=2026-04-28T18:42:54 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-28T18:03:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc101:1348080
   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/experiments/phase3_mlp_baseline/default_retrain_2026-04-28/run_retrain.sbatch
   WorkDir=/scratch/bxxjin001/XPert
   StdErr=/scratch/bxxjin001/XPert/experiment/NM/experiments/phase3_mlp_baseline/default_retrain_2026-04-28/slurm_788767.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/XPert/experiment/NM/experiments/phase3_mlp_baseline/default_retrain_2026-04-28/slurm_788767.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 788767

captured Tue Apr 28 18:43:35 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=00:39:13 TimeLimit=01:30:00 TimeMin=N/A
   SubmitTime=2026-04-28T18:03:41 EligibleTime=2026-04-28T18:03:41
   AccrueTime=2026-04-28T18:03:41
   StartTime=2026-04-28T18:03:41 EndTime=2026-04-28T18:42:54 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-28T18:03:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc101:1348080
   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/experiments/phase3_mlp_baseline/default_retrain_2026-04-28/run_retrain.sbatch
   WorkDir=/scratch/bxxjin001/XPert
   StdErr=/scratch/bxxjin001/XPert/experiment/NM/experiments/phase3_mlp_baseline/default_retrain_2026-04-28/slurm_788767.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/XPert/experiment/NM/experiments/phase3_mlp_baseline/default_retrain_2026-04-28/slurm_788767.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 788767

captured Tue Apr 28 18:44:01 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=00:39:13 TimeLimit=01:30:00 TimeMin=N/A
   SubmitTime=2026-04-28T18:03:41 EligibleTime=2026-04-28T18:03:41
   AccrueTime=2026-04-28T18:03:41
   StartTime=2026-04-28T18:03:41 EndTime=2026-04-28T18:42:54 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-28T18:03:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc101:1348080
   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/experiments/phase3_mlp_baseline/default_retrain_2026-04-28/run_retrain.sbatch
   WorkDir=/scratch/bxxjin001/XPert
   StdErr=/scratch/bxxjin001/XPert/experiment/NM/experiments/phase3_mlp_baseline/default_retrain_2026-04-28/slurm_788767.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/XPert/experiment/NM/experiments/phase3_mlp_baseline/default_retrain_2026-04-28/slurm_788767.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 788767

captured Tue Apr 28 18:44:34 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=00:39:13 TimeLimit=01:30:00 TimeMin=N/A
   SubmitTime=2026-04-28T18:03:41 EligibleTime=2026-04-28T18:03:41
   AccrueTime=2026-04-28T18:03:41
   StartTime=2026-04-28T18:03:41 EndTime=2026-04-28T18:42:54 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-28T18:03:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc101:1348080
   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/experiments/phase3_mlp_baseline/default_retrain_2026-04-28/run_retrain.sbatch
   WorkDir=/scratch/bxxjin001/XPert
   StdErr=/scratch/bxxjin001/XPert/experiment/NM/experiments/phase3_mlp_baseline/default_retrain_2026-04-28/slurm_788767.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/XPert/experiment/NM/experiments/phase3_mlp_baseline/default_retrain_2026-04-28/slurm_788767.out
   Power=
   TresPerNode=gres/gpu:ampere:1