UCT HPC cluster

JOB DETAILS FOR JOB 304487

captured Fri Oct 10 22:07:02 SAST 2025

JobId=304487 JobName=vae_debug_test
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7094 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=00:00:03 TimeLimit=01:00:00 TimeMin=N/A
   SubmitTime=2025-10-10T22:06:46 EligibleTime=2025-10-10T22:06:46
   AccrueTime=2025-10-10T22:06:46
   StartTime=2025-10-10T22:06:46 EndTime=2025-10-10T22:06:49 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-10T22:06:46 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc100:2281294
   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=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=srvrocgpu013 CPU_IDs=2,4,28-29 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/20251210_vae_loading_diagnosis/test_debug_version.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro/experiment/20251210_vae_loading_diagnosis
   StdErr=/scratch/bxxjin001/TranSiGen/repro/experiment/20251210_vae_loading_diagnosis/logs/vae_debug_304487.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro/experiment/20251210_vae_loading_diagnosis/logs/vae_debug_304487.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 304487

captured Fri Oct 10 22:07:34 SAST 2025

JobId=304487 JobName=vae_debug_test
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7094 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=00:00:03 TimeLimit=01:00:00 TimeMin=N/A
   SubmitTime=2025-10-10T22:06:46 EligibleTime=2025-10-10T22:06:46
   AccrueTime=2025-10-10T22:06:46
   StartTime=2025-10-10T22:06:46 EndTime=2025-10-10T22:06:49 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-10T22:06:46 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc100:2281294
   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=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=srvrocgpu013 CPU_IDs=2,4,28-29 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/20251210_vae_loading_diagnosis/test_debug_version.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro/experiment/20251210_vae_loading_diagnosis
   StdErr=/scratch/bxxjin001/TranSiGen/repro/experiment/20251210_vae_loading_diagnosis/logs/vae_debug_304487.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro/experiment/20251210_vae_loading_diagnosis/logs/vae_debug_304487.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 304487

captured Fri Oct 10 22:08:01 SAST 2025

JobId=304487 JobName=vae_debug_test
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7094 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=00:00:03 TimeLimit=01:00:00 TimeMin=N/A
   SubmitTime=2025-10-10T22:06:46 EligibleTime=2025-10-10T22:06:46
   AccrueTime=2025-10-10T22:06:46
   StartTime=2025-10-10T22:06:46 EndTime=2025-10-10T22:06:49 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-10T22:06:46 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc100:2281294
   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=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=srvrocgpu013 CPU_IDs=2,4,28-29 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/20251210_vae_loading_diagnosis/test_debug_version.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro/experiment/20251210_vae_loading_diagnosis
   StdErr=/scratch/bxxjin001/TranSiGen/repro/experiment/20251210_vae_loading_diagnosis/logs/vae_debug_304487.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro/experiment/20251210_vae_loading_diagnosis/logs/vae_debug_304487.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 304487

captured Fri Oct 10 22:08:33 SAST 2025

JobId=304487 JobName=vae_debug_test
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7094 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=00:00:03 TimeLimit=01:00:00 TimeMin=N/A
   SubmitTime=2025-10-10T22:06:46 EligibleTime=2025-10-10T22:06:46
   AccrueTime=2025-10-10T22:06:46
   StartTime=2025-10-10T22:06:46 EndTime=2025-10-10T22:06:49 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-10T22:06:46 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc100:2281294
   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=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=srvrocgpu013 CPU_IDs=2,4,28-29 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/20251210_vae_loading_diagnosis/test_debug_version.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro/experiment/20251210_vae_loading_diagnosis
   StdErr=/scratch/bxxjin001/TranSiGen/repro/experiment/20251210_vae_loading_diagnosis/logs/vae_debug_304487.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro/experiment/20251210_vae_loading_diagnosis/logs/vae_debug_304487.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 304487

captured Fri Oct 10 22:09:01 SAST 2025

JobId=304487 JobName=vae_debug_test
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7094 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=00:00:03 TimeLimit=01:00:00 TimeMin=N/A
   SubmitTime=2025-10-10T22:06:46 EligibleTime=2025-10-10T22:06:46
   AccrueTime=2025-10-10T22:06:46
   StartTime=2025-10-10T22:06:46 EndTime=2025-10-10T22:06:49 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-10T22:06:46 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc100:2281294
   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=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=srvrocgpu013 CPU_IDs=2,4,28-29 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/20251210_vae_loading_diagnosis/test_debug_version.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro/experiment/20251210_vae_loading_diagnosis
   StdErr=/scratch/bxxjin001/TranSiGen/repro/experiment/20251210_vae_loading_diagnosis/logs/vae_debug_304487.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro/experiment/20251210_vae_loading_diagnosis/logs/vae_debug_304487.out
   Power=
   TresPerNode=gres/gpu:l40s:1