UCT HPC cluster

JOB DETAILS FOR JOB 300096

captured Mon Oct 6 17:21:40 SAST 2025

MaxRAM=0G
MaxVMSize=0G
AveCPUFreq=
AveDiskRead=
AveDiskWrite=

JobId=300096 JobName=transigen_bug_test
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7139 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=00:18:02 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-06T17:03:37 EligibleTime=2025-10-06T17:03:37
   AccrueTime=2025-10-06T17:03:38
   StartTime=2025-10-06T17:03:38 EndTime=2025-10-08T17:03:38 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-06T17:03:38 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc102:112992
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   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=srvrocgpu014 CPU_IDs=0-1,24-25 Mem=65536 GRES=gpu:l40s:1(IDX:0)
   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/train_bug_test.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro/experiment
   StdErr=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_300096.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_300096.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 300096

captured Mon Oct 6 17:22:01 SAST 2025

JobId=300096 JobName=transigen_bug_test
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7139 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:18:04 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-06T17:03:37 EligibleTime=2025-10-06T17:03:37
   AccrueTime=2025-10-06T17:03:38
   StartTime=2025-10-06T17:03:38 EndTime=2025-10-06T17:21:42 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-06T17:03:38 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc102:112992
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   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=srvrocgpu014 CPU_IDs=0-1,24-25 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/train_bug_test.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro/experiment
   StdErr=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_300096.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_300096.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 300096

captured Mon Oct 6 17:22:39 SAST 2025

JobId=300096 JobName=transigen_bug_test
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7139 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:18:04 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-06T17:03:37 EligibleTime=2025-10-06T17:03:37
   AccrueTime=2025-10-06T17:03:38
   StartTime=2025-10-06T17:03:38 EndTime=2025-10-06T17:21:42 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-06T17:03:38 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc102:112992
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   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=srvrocgpu014 CPU_IDs=0-1,24-25 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/train_bug_test.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro/experiment
   StdErr=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_300096.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_300096.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 300096

captured Mon Oct 6 17:23:01 SAST 2025

JobId=300096 JobName=transigen_bug_test
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7139 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:18:04 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-06T17:03:37 EligibleTime=2025-10-06T17:03:37
   AccrueTime=2025-10-06T17:03:38
   StartTime=2025-10-06T17:03:38 EndTime=2025-10-06T17:21:42 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-06T17:03:38 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc102:112992
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   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=srvrocgpu014 CPU_IDs=0-1,24-25 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/train_bug_test.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro/experiment
   StdErr=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_300096.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_300096.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 300096

captured Mon Oct 6 17:23:40 SAST 2025

JobId=300096 JobName=transigen_bug_test
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7139 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:18:04 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-06T17:03:37 EligibleTime=2025-10-06T17:03:37
   AccrueTime=2025-10-06T17:03:38
   StartTime=2025-10-06T17:03:38 EndTime=2025-10-06T17:21:42 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-06T17:03:38 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc102:112992
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   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=srvrocgpu014 CPU_IDs=0-1,24-25 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/train_bug_test.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro/experiment
   StdErr=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_300096.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_300096.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 300096

captured Mon Oct 6 17:24:01 SAST 2025

JobId=300096 JobName=transigen_bug_test
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7139 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:18:04 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-06T17:03:37 EligibleTime=2025-10-06T17:03:37
   AccrueTime=2025-10-06T17:03:38
   StartTime=2025-10-06T17:03:38 EndTime=2025-10-06T17:21:42 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-06T17:03:38 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc102:112992
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   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=srvrocgpu014 CPU_IDs=0-1,24-25 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/train_bug_test.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/repro/experiment
   StdErr=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_300096.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/repro/experiment/logs/slurm_300096.out
   Power=
   TresPerNode=gres/gpu:l40s:1