UCT HPC cluster

JOB DETAILS FOR JOB 303423

captured Thu Oct 9 11:13:01 SAST 2025

MaxRAM=4.3G
MaxVMSize=0G
AveCPUFreq=4M
AveDiskRead=2993751394
AveDiskWrite=4787953

JobId=303423 JobName=hp_004_lr1e-05_b0.05
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7100 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=00:00:20 TimeLimit=03:00:00 TimeMin=N/A
   SubmitTime=2025-10-09T11:12:17 EligibleTime=2025-10-09T11:12:17
   AccrueTime=2025-10-09T11:12:18
   StartTime=2025-10-09T11:12:41 EndTime=2025-10-09T14:12:41 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T11:12:41 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc103:3923954
   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=3-4,28-29 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/repro2/experiment/hyperparam_search_20251009_111200/scripts/job_004.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro2/experiment
   StdErr=/scratch/bxxjin001/TranSiGen/repro2/experiment/hyperparam_search_20251009_111200/logs/slurm_303423.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro2/experiment/hyperparam_search_20251009_111200/logs/slurm_303423.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 303423

captured Thu Oct 9 11:13:39 SAST 2025

JobId=303423 JobName=hp_004_lr1e-05_b0.05
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7100 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=00:00:48 TimeLimit=03:00:00 TimeMin=N/A
   SubmitTime=2025-10-09T11:12:17 EligibleTime=2025-10-09T11:12:17
   AccrueTime=2025-10-09T11:12:18
   StartTime=2025-10-09T11:12:41 EndTime=2025-10-09T11:13:29 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T11:12:41 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc103:3923954
   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=3-4,28-29 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/repro2/experiment/hyperparam_search_20251009_111200/scripts/job_004.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro2/experiment
   StdErr=/scratch/bxxjin001/TranSiGen/repro2/experiment/hyperparam_search_20251009_111200/logs/slurm_303423.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro2/experiment/hyperparam_search_20251009_111200/logs/slurm_303423.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 303423

captured Thu Oct 9 11:14:01 SAST 2025

JobId=303423 JobName=hp_004_lr1e-05_b0.05
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7100 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=00:00:48 TimeLimit=03:00:00 TimeMin=N/A
   SubmitTime=2025-10-09T11:12:17 EligibleTime=2025-10-09T11:12:17
   AccrueTime=2025-10-09T11:12:18
   StartTime=2025-10-09T11:12:41 EndTime=2025-10-09T11:13:29 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T11:12:41 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc103:3923954
   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=3-4,28-29 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/repro2/experiment/hyperparam_search_20251009_111200/scripts/job_004.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro2/experiment
   StdErr=/scratch/bxxjin001/TranSiGen/repro2/experiment/hyperparam_search_20251009_111200/logs/slurm_303423.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro2/experiment/hyperparam_search_20251009_111200/logs/slurm_303423.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 303423

captured Thu Oct 9 11:14:38 SAST 2025

JobId=303423 JobName=hp_004_lr1e-05_b0.05
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7100 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=00:00:48 TimeLimit=03:00:00 TimeMin=N/A
   SubmitTime=2025-10-09T11:12:17 EligibleTime=2025-10-09T11:12:17
   AccrueTime=2025-10-09T11:12:18
   StartTime=2025-10-09T11:12:41 EndTime=2025-10-09T11:13:29 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T11:12:41 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc103:3923954
   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=3-4,28-29 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/repro2/experiment/hyperparam_search_20251009_111200/scripts/job_004.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro2/experiment
   StdErr=/scratch/bxxjin001/TranSiGen/repro2/experiment/hyperparam_search_20251009_111200/logs/slurm_303423.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro2/experiment/hyperparam_search_20251009_111200/logs/slurm_303423.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 303423

captured Thu Oct 9 11:15:01 SAST 2025

JobId=303423 JobName=hp_004_lr1e-05_b0.05
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7100 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=00:00:48 TimeLimit=03:00:00 TimeMin=N/A
   SubmitTime=2025-10-09T11:12:17 EligibleTime=2025-10-09T11:12:17
   AccrueTime=2025-10-09T11:12:18
   StartTime=2025-10-09T11:12:41 EndTime=2025-10-09T11:13:29 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T11:12:41 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc103:3923954
   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=3-4,28-29 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/repro2/experiment/hyperparam_search_20251009_111200/scripts/job_004.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro2/experiment
   StdErr=/scratch/bxxjin001/TranSiGen/repro2/experiment/hyperparam_search_20251009_111200/logs/slurm_303423.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro2/experiment/hyperparam_search_20251009_111200/logs/slurm_303423.out
   Power=
   TresPerNode=gres/gpu:l40s:1