UCT HPC cluster

JOB DETAILS FOR JOB 1232997

captured Fri Aug 14 14:31:01 SAST 2026

MaxRAM=1.2G
MaxVMSize=0G
AveCPUFreq=1.98M
AveDiskRead=254453013
AveDiskWrite=320749174

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8029 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=00:00:35 TimeLimit=04:00:00 TimeMin=N/A
   SubmitTime=2026-08-14T14:28:34 EligibleTime=2026-08-14T14:28:34
   AccrueTime=2026-08-14T14:28:37
   StartTime=2026-08-14T14:30:26 EndTime=2026-08-14T18:30:26 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-14T14:30:26 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc101:2802215
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=48G,node=1,billing=9,gres/gpu=1
   AllocTRES=cpu=4,mem=48G,node=1,billing=9,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=0-1,28-29 Mem=49152 GRES=gpu:ampere80:1(IDX:0)
   MinCPUsNode=6 MinMemoryNode=48G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/ORION/chemCPA/runs/phase_c2m_foldlocal_l5_ensemble_persistent_basal_adapter_direct_chemcpa_r1_20260814T120106Z/jobs/p4_train.sbatch
   WorkDir=/scratch/bxxjin001/ORION/chemCPA/runs/phase_c2m_foldlocal_l5_ensemble_persistent_basal_adapter_direct_chemcpa_r1_20260814T120106Z
   StdErr=/scratch/bxxjin001/ORION/chemCPA/runs/phase_c2m_foldlocal_l5_ensemble_persistent_basal_adapter_direct_chemcpa_r1_20260814T120106Z/logs/p4train_1232997.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/chemCPA/runs/phase_c2m_foldlocal_l5_ensemble_persistent_basal_adapter_direct_chemcpa_r1_20260814T120106Z/logs/p4train_1232997.out
   Power=
   TresPerNode=gres/gpu:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1232997

captured Fri Aug 14 14:31:59 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8029 Nice=0 Account=a100free QOS=a100free
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:01:31 TimeLimit=04:00:00 TimeMin=N/A
   SubmitTime=2026-08-14T14:28:34 EligibleTime=2026-08-14T14:28:34
   AccrueTime=2026-08-14T14:28:37
   StartTime=2026-08-14T14:30:26 EndTime=2026-08-14T14:31:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-14T14:30:26 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc101:2802215
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=48G,node=1,billing=9,gres/gpu=1
   AllocTRES=cpu=4,mem=48G,node=1,billing=9,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=0-1,28-29 Mem=49152 GRES=
   MinCPUsNode=6 MinMemoryNode=48G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/ORION/chemCPA/runs/phase_c2m_foldlocal_l5_ensemble_persistent_basal_adapter_direct_chemcpa_r1_20260814T120106Z/jobs/p4_train.sbatch
   WorkDir=/scratch/bxxjin001/ORION/chemCPA/runs/phase_c2m_foldlocal_l5_ensemble_persistent_basal_adapter_direct_chemcpa_r1_20260814T120106Z
   StdErr=/scratch/bxxjin001/ORION/chemCPA/runs/phase_c2m_foldlocal_l5_ensemble_persistent_basal_adapter_direct_chemcpa_r1_20260814T120106Z/logs/p4train_1232997.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/chemCPA/runs/phase_c2m_foldlocal_l5_ensemble_persistent_basal_adapter_direct_chemcpa_r1_20260814T120106Z/logs/p4train_1232997.out
   Power=
   TresPerNode=gres/gpu:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1232997

captured Fri Aug 14 14:32:31 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8029 Nice=0 Account=a100free QOS=a100free
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:01:31 TimeLimit=04:00:00 TimeMin=N/A
   SubmitTime=2026-08-14T14:28:34 EligibleTime=2026-08-14T14:28:34
   AccrueTime=2026-08-14T14:28:37
   StartTime=2026-08-14T14:30:26 EndTime=2026-08-14T14:31:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-14T14:30:26 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc101:2802215
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=48G,node=1,billing=9,gres/gpu=1
   AllocTRES=cpu=4,mem=48G,node=1,billing=9,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=0-1,28-29 Mem=49152 GRES=
   MinCPUsNode=6 MinMemoryNode=48G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/ORION/chemCPA/runs/phase_c2m_foldlocal_l5_ensemble_persistent_basal_adapter_direct_chemcpa_r1_20260814T120106Z/jobs/p4_train.sbatch
   WorkDir=/scratch/bxxjin001/ORION/chemCPA/runs/phase_c2m_foldlocal_l5_ensemble_persistent_basal_adapter_direct_chemcpa_r1_20260814T120106Z
   StdErr=/scratch/bxxjin001/ORION/chemCPA/runs/phase_c2m_foldlocal_l5_ensemble_persistent_basal_adapter_direct_chemcpa_r1_20260814T120106Z/logs/p4train_1232997.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/chemCPA/runs/phase_c2m_foldlocal_l5_ensemble_persistent_basal_adapter_direct_chemcpa_r1_20260814T120106Z/logs/p4train_1232997.out
   Power=
   TresPerNode=gres/gpu:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1232997

captured Fri Aug 14 14:33:01 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8029 Nice=0 Account=a100free QOS=a100free
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:01:31 TimeLimit=04:00:00 TimeMin=N/A
   SubmitTime=2026-08-14T14:28:34 EligibleTime=2026-08-14T14:28:34
   AccrueTime=2026-08-14T14:28:37
   StartTime=2026-08-14T14:30:26 EndTime=2026-08-14T14:31:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-14T14:30:26 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc101:2802215
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=48G,node=1,billing=9,gres/gpu=1
   AllocTRES=cpu=4,mem=48G,node=1,billing=9,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=0-1,28-29 Mem=49152 GRES=
   MinCPUsNode=6 MinMemoryNode=48G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/ORION/chemCPA/runs/phase_c2m_foldlocal_l5_ensemble_persistent_basal_adapter_direct_chemcpa_r1_20260814T120106Z/jobs/p4_train.sbatch
   WorkDir=/scratch/bxxjin001/ORION/chemCPA/runs/phase_c2m_foldlocal_l5_ensemble_persistent_basal_adapter_direct_chemcpa_r1_20260814T120106Z
   StdErr=/scratch/bxxjin001/ORION/chemCPA/runs/phase_c2m_foldlocal_l5_ensemble_persistent_basal_adapter_direct_chemcpa_r1_20260814T120106Z/logs/p4train_1232997.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/chemCPA/runs/phase_c2m_foldlocal_l5_ensemble_persistent_basal_adapter_direct_chemcpa_r1_20260814T120106Z/logs/p4train_1232997.out
   Power=
   TresPerNode=gres/gpu:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1232997

captured Fri Aug 14 14:33:59 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8029 Nice=0 Account=a100free QOS=a100free
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:01:31 TimeLimit=04:00:00 TimeMin=N/A
   SubmitTime=2026-08-14T14:28:34 EligibleTime=2026-08-14T14:28:34
   AccrueTime=2026-08-14T14:28:37
   StartTime=2026-08-14T14:30:26 EndTime=2026-08-14T14:31:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-08-14T14:30:26 Scheduler=Backfill
   Partition=a100 AllocNode:Sid=srvrochpc101:2802215
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=48G,node=1,billing=9,gres/gpu=1
   AllocTRES=cpu=4,mem=48G,node=1,billing=9,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=0-1,28-29 Mem=49152 GRES=
   MinCPUsNode=6 MinMemoryNode=48G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/ORION/chemCPA/runs/phase_c2m_foldlocal_l5_ensemble_persistent_basal_adapter_direct_chemcpa_r1_20260814T120106Z/jobs/p4_train.sbatch
   WorkDir=/scratch/bxxjin001/ORION/chemCPA/runs/phase_c2m_foldlocal_l5_ensemble_persistent_basal_adapter_direct_chemcpa_r1_20260814T120106Z
   StdErr=/scratch/bxxjin001/ORION/chemCPA/runs/phase_c2m_foldlocal_l5_ensemble_persistent_basal_adapter_direct_chemcpa_r1_20260814T120106Z/logs/p4train_1232997.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/chemCPA/runs/phase_c2m_foldlocal_l5_ensemble_persistent_basal_adapter_direct_chemcpa_r1_20260814T120106Z/logs/p4train_1232997.out
   Power=
   TresPerNode=gres/gpu:1
   TresPerTask=cpu:4