UCT HPC cluster

JOB DETAILS FOR JOB 303416

captured Thu Oct 9 11:11:01 SAST 2025

JobId=303416 JobName=hp_007_lr1e-05_b0.05
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7087 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=PENDING Reason=QOSMaxGRESPerUser Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=02:00:00 TimeMin=N/A
   SubmitTime=2025-10-09T11:09:48 EligibleTime=2025-10-09T11:09:48
   AccrueTime=2025-10-09T11:10:56
   StartTime=Unknown EndTime=Unknown Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T11:10:56 Scheduler=Backfill:*
   Partition=l40s AllocNode:Sid=srvrochpc103:3921906
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1-1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=32G,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=4 MinMemoryNode=32G 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_110833/scripts/job_007.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro2/experiment
   StdErr=/scratch/bxxjin001/TranSiGen/repro2/experiment/hyperparam_search_20251009_110833/logs/slurm_303416.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro2/experiment/hyperparam_search_20251009_110833/logs/slurm_303416.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 303416

captured Thu Oct 9 11:11:38 SAST 2025

JobId=303416 JobName=hp_007_lr1e-05_b0.05
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7087 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=QOSMaxGRESPerUser Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=02:00:00 TimeMin=N/A
   SubmitTime=2025-10-09T11:09:48 EligibleTime=2025-10-09T11:09:48
   AccrueTime=2025-10-09T11:10:56
   StartTime=2025-10-09T11:11:04 EndTime=2025-10-09T11:11:04 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T11:11:03 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc103:3921906
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=32G,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=4 MinMemoryNode=32G 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_110833/scripts/job_007.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro2/experiment
   StdErr=/scratch/bxxjin001/TranSiGen/repro2/experiment/hyperparam_search_20251009_110833/logs/slurm_303416.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro2/experiment/hyperparam_search_20251009_110833/logs/slurm_303416.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 303416

captured Thu Oct 9 11:12:02 SAST 2025

JobId=303416 JobName=hp_007_lr1e-05_b0.05
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7087 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=QOSMaxGRESPerUser Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=02:00:00 TimeMin=N/A
   SubmitTime=2025-10-09T11:09:48 EligibleTime=2025-10-09T11:09:48
   AccrueTime=2025-10-09T11:10:56
   StartTime=2025-10-09T11:11:04 EndTime=2025-10-09T11:11:04 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T11:11:03 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc103:3921906
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=32G,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=4 MinMemoryNode=32G 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_110833/scripts/job_007.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro2/experiment
   StdErr=/scratch/bxxjin001/TranSiGen/repro2/experiment/hyperparam_search_20251009_110833/logs/slurm_303416.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro2/experiment/hyperparam_search_20251009_110833/logs/slurm_303416.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 303416

captured Thu Oct 9 11:12:39 SAST 2025

JobId=303416 JobName=hp_007_lr1e-05_b0.05
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7087 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=QOSMaxGRESPerUser Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=02:00:00 TimeMin=N/A
   SubmitTime=2025-10-09T11:09:48 EligibleTime=2025-10-09T11:09:48
   AccrueTime=2025-10-09T11:10:56
   StartTime=2025-10-09T11:11:04 EndTime=2025-10-09T11:11:04 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T11:11:03 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc103:3921906
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=32G,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=4 MinMemoryNode=32G 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_110833/scripts/job_007.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro2/experiment
   StdErr=/scratch/bxxjin001/TranSiGen/repro2/experiment/hyperparam_search_20251009_110833/logs/slurm_303416.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro2/experiment/hyperparam_search_20251009_110833/logs/slurm_303416.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 303416

captured Thu Oct 9 11:13:01 SAST 2025

JobId=303416 JobName=hp_007_lr1e-05_b0.05
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7087 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=QOSMaxGRESPerUser Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=02:00:00 TimeMin=N/A
   SubmitTime=2025-10-09T11:09:48 EligibleTime=2025-10-09T11:09:48
   AccrueTime=2025-10-09T11:10:56
   StartTime=2025-10-09T11:11:04 EndTime=2025-10-09T11:11:04 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-09T11:11:03 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc103:3921906
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=32G,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=4 MinMemoryNode=32G 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_110833/scripts/job_007.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro2/experiment
   StdErr=/scratch/bxxjin001/TranSiGen/repro2/experiment/hyperparam_search_20251009_110833/logs/slurm_303416.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro2/experiment/hyperparam_search_20251009_110833/logs/slurm_303416.out
   Power=
   TresPerNode=gres/gpu:l40s:1