UCT HPC cluster

JOB DETAILS FOR JOB 329566

captured Fri Oct 31 08:09:01 SAST 2025

MaxRAM=6.1G
MaxVMSize=0G
AveCPUFreq=29K
AveDiskRead=5308266744
AveDiskWrite=17859072327

JobId=329566 JobName=vae_pcc_500ep
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7142 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=20:27:35 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-30T11:41:25 EligibleTime=2025-10-30T11:41:25
   AccrueTime=2025-10-30T11:41:26
   StartTime=2025-10-30T11:41:26 EndTime=2025-10-31T11:41:26 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-30T11:41:26 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:3879934
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=7 NumTasks=4 CPUs/Task=2 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=64G,node=1,billing=10,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=7,mem=64G,node=1,billing=13,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=4:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu013 CPU_IDs=2-5,26-28 Mem=65536 GRES=gpu:l40s:1(IDX:2)
   MinCPUsNode=7 MinMemoryNode=64G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/TranSiGen/VAE/scripts/submit_vae_pcc_500epochs.sh
   WorkDir=/scratch/bxxjin001/TranSiGen
   StdErr=/scratch/bxxjin001/TranSiGen/VAE/logs/vae_pcc_500ep_329566.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/VAE/logs/vae_pcc_500ep_329566.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 329566

captured Fri Oct 31 08:09:33 SAST 2025

JobId=329566 JobName=vae_pcc_500ep
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7142 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=20:27:48 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-30T11:41:25 EligibleTime=2025-10-30T11:41:25
   AccrueTime=2025-10-30T11:41:26
   StartTime=2025-10-30T11:41:26 EndTime=2025-10-31T08:09:14 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-30T11:41:26 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:3879934
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=7 NumTasks=4 CPUs/Task=2 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=64G,node=1,billing=10,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=7,mem=64G,node=1,billing=13,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=4:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu013 CPU_IDs=2-5,26-28 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/VAE/scripts/submit_vae_pcc_500epochs.sh
   WorkDir=/scratch/bxxjin001/TranSiGen
   StdErr=/scratch/bxxjin001/TranSiGen/VAE/logs/vae_pcc_500ep_329566.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/VAE/logs/vae_pcc_500ep_329566.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 329566

captured Fri Oct 31 08:10:01 SAST 2025

JobId=329566 JobName=vae_pcc_500ep
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7142 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=20:27:48 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-30T11:41:25 EligibleTime=2025-10-30T11:41:25
   AccrueTime=2025-10-30T11:41:26
   StartTime=2025-10-30T11:41:26 EndTime=2025-10-31T08:09:14 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-30T11:41:26 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:3879934
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=7 NumTasks=4 CPUs/Task=2 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=64G,node=1,billing=10,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=7,mem=64G,node=1,billing=13,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=4:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu013 CPU_IDs=2-5,26-28 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/VAE/scripts/submit_vae_pcc_500epochs.sh
   WorkDir=/scratch/bxxjin001/TranSiGen
   StdErr=/scratch/bxxjin001/TranSiGen/VAE/logs/vae_pcc_500ep_329566.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/VAE/logs/vae_pcc_500ep_329566.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 329566

captured Fri Oct 31 08:10:34 SAST 2025

JobId=329566 JobName=vae_pcc_500ep
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7142 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=20:27:48 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-30T11:41:25 EligibleTime=2025-10-30T11:41:25
   AccrueTime=2025-10-30T11:41:26
   StartTime=2025-10-30T11:41:26 EndTime=2025-10-31T08:09:14 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-30T11:41:26 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:3879934
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=7 NumTasks=4 CPUs/Task=2 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=64G,node=1,billing=10,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=7,mem=64G,node=1,billing=13,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=4:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu013 CPU_IDs=2-5,26-28 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/VAE/scripts/submit_vae_pcc_500epochs.sh
   WorkDir=/scratch/bxxjin001/TranSiGen
   StdErr=/scratch/bxxjin001/TranSiGen/VAE/logs/vae_pcc_500ep_329566.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/VAE/logs/vae_pcc_500ep_329566.out
   Power=
   TresPerNode=gres/gpu:l40s:1