UCT HPC cluster

JOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:39:01 SAST 2025

MaxRAM=5.3G
MaxVMSize=0G
AveCPUFreq=681K
AveDiskRead=289806862
AveDiskWrite=33550390098

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:27:31 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-26T00:11:30 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=gpu:l40s:1(IDX:2)
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:39:44 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:40:01 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:40:46 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:41:01 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:41:43 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:42:01 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:42:44 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:43:01 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:43:43 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:44:01 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:44:43 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:45:01 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:45:46 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:46:01 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:46:43 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:47:01 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:47:43 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:48:02 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:48:44 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:49:01 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:49:43 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:50:01 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:50:46 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:51:01 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:51:43 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:52:01 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:52:43 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL

UCT HPC clusterJOB DETAILS FOR JOB 243153

captured Mon Aug 25 16:53:01 SAST 2025

JobId=243153 ArrayJobId=243153 ArrayTaskId=5 JobName=DDR_Train
   UserId=bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7085 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=00:28:09 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-08-25T15:58:32 EligibleTime=2025-08-25T15:58:32
   AccrueTime=2025-08-25T16:05:15
   StartTime=2025-08-25T16:11:30 EndTime=2025-08-25T16:39:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-08-25T16:11:30 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc101:2271435
   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=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,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=1,3,26-27 Mem=40000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/DDR/code/20250826/code/run_task.sh
   WorkDir=/scratch/bxxjin001/DDR/code/20250826/code
   StdErr=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/DDR/code/20250826/logs/parallel/train_243153_5.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=bxxjin001@myuct.ac.za MailType=FAIL