JOB DETAILS FOR JOB 159035

captured Wed Jun 11 14:56:01 SAST 2025

MaxRAM=4.8G
MaxVMSize=0G
AveCPUFreq=94K
AveDiskRead=3751793262
AveDiskWrite=209081861

JobId=159035 JobName=train_256
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7380 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=12:16:19 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-06-11T02:39:42 EligibleTime=2025-06-11T02:39:42
   AccrueTime=2025-06-11T02:39:42
   StartTime=2025-06-11T02:39:42 EndTime=2025-06-11T22:39:42 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-11T02:39:42 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:478037
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=10 NumTasks=10 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=10,mem=100000M,node=1,billing=19,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=10,mem=100000M,node=1,billing=19,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=2-6,24,27-30 Mem=100000 GRES=gpu:l40s:1(IDX:0)
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/model_27may/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/model_27may
   StdErr=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-159035.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-159035.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=mrpcol001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
   

UCT HPC clusterJOB DETAILS FOR JOB 159035

captured Wed Jun 11 14:56:37 SAST 2025

JobId=159035 JobName=train_256
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7380 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=120:0
   DerivedExitCode=0:0
   RunTime=12:16:37 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-06-11T02:39:42 EligibleTime=2025-06-11T02:39:42
   AccrueTime=2025-06-11T02:39:42
   StartTime=2025-06-11T02:39:42 EndTime=2025-06-11T14:56:19 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-11T02:39:42 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:478037
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=10 NumTasks=10 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=10,mem=100000M,node=1,billing=19,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=10,mem=100000M,node=1,billing=19,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=2-6,24,27-30 Mem=100000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/model_27may/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/model_27may
   StdErr=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-159035.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-159035.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=mrpcol001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
   

UCT HPC clusterJOB DETAILS FOR JOB 159035

captured Wed Jun 11 14:57:01 SAST 2025

JobId=159035 JobName=train_256
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7380 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=120:0
   DerivedExitCode=0:0
   RunTime=12:16:37 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-06-11T02:39:42 EligibleTime=2025-06-11T02:39:42
   AccrueTime=2025-06-11T02:39:42
   StartTime=2025-06-11T02:39:42 EndTime=2025-06-11T14:56:19 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-11T02:39:42 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:478037
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=10 NumTasks=10 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=10,mem=100000M,node=1,billing=19,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=10,mem=100000M,node=1,billing=19,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=2-6,24,27-30 Mem=100000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/model_27may/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/model_27may
   StdErr=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-159035.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-159035.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=mrpcol001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
   

UCT HPC clusterJOB DETAILS FOR JOB 159035

captured Wed Jun 11 14:57:37 SAST 2025

JobId=159035 JobName=train_256
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7380 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=120:0
   DerivedExitCode=0:0
   RunTime=12:16:37 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-06-11T02:39:42 EligibleTime=2025-06-11T02:39:42
   AccrueTime=2025-06-11T02:39:42
   StartTime=2025-06-11T02:39:42 EndTime=2025-06-11T14:56:19 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-11T02:39:42 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:478037
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=10 NumTasks=10 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=10,mem=100000M,node=1,billing=19,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=10,mem=100000M,node=1,billing=19,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=2-6,24,27-30 Mem=100000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/model_27may/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/model_27may
   StdErr=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-159035.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-159035.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=mrpcol001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT
   

UCT HPC clusterJOB DETAILS FOR JOB 159035

captured Wed Jun 11 14:58:02 SAST 2025

JobId=159035 JobName=train_256
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7380 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=120:0
   DerivedExitCode=0:0
   RunTime=12:16:37 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-06-11T02:39:42 EligibleTime=2025-06-11T02:39:42
   AccrueTime=2025-06-11T02:39:42
   StartTime=2025-06-11T02:39:42 EndTime=2025-06-11T14:56:19 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-06-11T02:39:42 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:478037
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=10 NumTasks=10 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=10,mem=100000M,node=1,billing=19,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=10,mem=100000M,node=1,billing=19,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=2-6,24,27-30 Mem=100000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/model_27may/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/model_27may
   StdErr=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-159035.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-159035.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=mrpcol001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT