UCT HPC cluster

JOB DETAILS FOR JOB 300591

captured Tue Oct 7 23:21:01 SAST 2025

MaxRAM=10.6G
MaxVMSize=0G
AveCPUFreq=11K
AveDiskRead=9094524033
AveDiskWrite=7262628214

JobId=300591 JobName=leaky_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7084 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=10:24:26 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-07T12:56:35 EligibleTime=2025-10-07T12:56:35
   AccrueTime=2025-10-07T12:56:35
   StartTime=2025-10-07T12:56:35 EndTime=2025-10-09T12:56:35 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-07T12:56:35 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu012.uct.ac.za:2337287
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=6,mem=60000M,node=1,billing=11,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=5-7,30-32 Mem=60000 GRES=gpu:l40s:1(IDX:3)
   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/oct/07oct/palette I2I/submit_palette.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/07oct/palette I2I
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/07oct/palette I2I/slurm-300591.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/07oct/palette I2I/slurm-300591.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 300591

captured Tue Oct 7 23:21:34 SAST 2025

JobId=300591 JobName=leaky_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7084 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=10:24:39 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-07T12:56:35 EligibleTime=2025-10-07T12:56:35
   AccrueTime=2025-10-07T12:56:35
   StartTime=2025-10-07T12:56:35 EndTime=2025-10-07T23:21:14 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-07T12:56:35 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu012.uct.ac.za:2337287
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=6,mem=60000M,node=1,billing=11,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=5-7,30-32 Mem=60000 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/oct/07oct/palette I2I/submit_palette.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/07oct/palette I2I
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/07oct/palette I2I/slurm-300591.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/07oct/palette I2I/slurm-300591.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 300591

captured Tue Oct 7 23:22:01 SAST 2025

JobId=300591 JobName=leaky_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7084 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=10:24:39 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-07T12:56:35 EligibleTime=2025-10-07T12:56:35
   AccrueTime=2025-10-07T12:56:35
   StartTime=2025-10-07T12:56:35 EndTime=2025-10-07T23:21:14 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-07T12:56:35 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu012.uct.ac.za:2337287
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=6,mem=60000M,node=1,billing=11,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=5-7,30-32 Mem=60000 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/oct/07oct/palette I2I/submit_palette.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/07oct/palette I2I
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/07oct/palette I2I/slurm-300591.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/07oct/palette I2I/slurm-300591.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 300591

captured Tue Oct 7 23:22:34 SAST 2025

JobId=300591 JobName=leaky_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7084 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=10:24:39 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-07T12:56:35 EligibleTime=2025-10-07T12:56:35
   AccrueTime=2025-10-07T12:56:35
   StartTime=2025-10-07T12:56:35 EndTime=2025-10-07T23:21:14 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-07T12:56:35 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu012.uct.ac.za:2337287
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=6,mem=60000M,node=1,billing=11,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=5-7,30-32 Mem=60000 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/oct/07oct/palette I2I/submit_palette.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/07oct/palette I2I
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/07oct/palette I2I/slurm-300591.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/07oct/palette I2I/slurm-300591.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 300591

captured Tue Oct 7 23:23:01 SAST 2025

JobId=300591 JobName=leaky_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7084 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=10:24:39 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-07T12:56:35 EligibleTime=2025-10-07T12:56:35
   AccrueTime=2025-10-07T12:56:35
   StartTime=2025-10-07T12:56:35 EndTime=2025-10-07T23:21:14 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-07T12:56:35 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu012.uct.ac.za:2337287
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=6,mem=60000M,node=1,billing=11,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=5-7,30-32 Mem=60000 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/oct/07oct/palette I2I/submit_palette.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/07oct/palette I2I
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/07oct/palette I2I/slurm-300591.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/07oct/palette I2I/slurm-300591.out
   Power=
   TresPerNode=gres/gpu:l40s:1