UCT HPC cluster

JOB DETAILS FOR JOB 328418

captured Fri Oct 31 02:47:33 SAST 2025

MaxRAM=1.1G
MaxVMSize=0G
AveCPUFreq=10K
AveDiskRead=4507967932
AveDiskWrite=1590043

JobId=328418 JobName=cosmology_inference
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7237 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=1-23:59:54 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-29T02:47:39 EligibleTime=2025-10-29T02:47:39
   AccrueTime=2025-10-29T02:47:39
   StartTime=2025-10-29T02:47:39 EndTime=2025-10-31T02:47:39 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-29T02:47:39 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu010.uct.ac.za:2840527
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,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=6-9,30-33 Mem=80000 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/diff_model/organized_files/models/organized/models/conditional_2label/conditional/submit_cosmology_inference.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/diff_model/organized_files/models/organized/models/conditional_2label/conditional
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/diff_model/organized_files/models/organized/models/conditional_2label/conditional/logs/slurm-328418.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/diff_model/organized_files/models/organized/models/conditional_2label/conditional/logs/slurm-328418.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 328418

captured Fri Oct 31 02:48:01 SAST 2025

JobId=328418 JobName=cosmology_inference
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7237 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETING Reason=TimeLimit Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:21 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-29T02:47:39 EligibleTime=2025-10-29T02:47:39
   AccrueTime=2025-10-29T02:47:39
   StartTime=2025-10-29T02:47:39 EndTime=2025-10-31T02:48:00 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-29T02:47:39 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu010.uct.ac.za:2840527
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,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=6-9,30-33 Mem=80000 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/diff_model/organized_files/models/organized/models/conditional_2label/conditional/submit_cosmology_inference.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/diff_model/organized_files/models/organized/models/conditional_2label/conditional
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/diff_model/organized_files/models/organized/models/conditional_2label/conditional/logs/slurm-328418.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/diff_model/organized_files/models/organized/models/conditional_2label/conditional/logs/slurm-328418.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 328418

captured Fri Oct 31 02:48:33 SAST 2025

JobId=328418 JobName=cosmology_inference
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7237 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:21 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-29T02:47:39 EligibleTime=2025-10-29T02:47:39
   AccrueTime=2025-10-29T02:47:39
   StartTime=2025-10-29T02:47:39 EndTime=2025-10-31T02:48:00 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-29T02:47:39 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu010.uct.ac.za:2840527
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,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=6-9,30-33 Mem=80000 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/diff_model/organized_files/models/organized/models/conditional_2label/conditional/submit_cosmology_inference.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/diff_model/organized_files/models/organized/models/conditional_2label/conditional
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/diff_model/organized_files/models/organized/models/conditional_2label/conditional/logs/slurm-328418.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/diff_model/organized_files/models/organized/models/conditional_2label/conditional/logs/slurm-328418.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 328418

captured Fri Oct 31 02:49:01 SAST 2025

JobId=328418 JobName=cosmology_inference
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7237 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:21 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-29T02:47:39 EligibleTime=2025-10-29T02:47:39
   AccrueTime=2025-10-29T02:47:39
   StartTime=2025-10-29T02:47:39 EndTime=2025-10-31T02:48:00 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-29T02:47:39 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu010.uct.ac.za:2840527
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,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=6-9,30-33 Mem=80000 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/diff_model/organized_files/models/organized/models/conditional_2label/conditional/submit_cosmology_inference.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/diff_model/organized_files/models/organized/models/conditional_2label/conditional
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/diff_model/organized_files/models/organized/models/conditional_2label/conditional/logs/slurm-328418.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/diff_model/organized_files/models/organized/models/conditional_2label/conditional/logs/slurm-328418.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 328418

captured Fri Oct 31 02:49:33 SAST 2025

JobId=328418 JobName=cosmology_inference
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7237 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:21 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-10-29T02:47:39 EligibleTime=2025-10-29T02:47:39
   AccrueTime=2025-10-29T02:47:39
   StartTime=2025-10-29T02:47:39 EndTime=2025-10-31T02:48:00 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-10-29T02:47:39 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu010.uct.ac.za:2840527
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,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=6-9,30-33 Mem=80000 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/diff_model/organized_files/models/organized/models/conditional_2label/conditional/submit_cosmology_inference.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/oct/diff_model/organized_files/models/organized/models/conditional_2label/conditional
   StdErr=/scratch/mrpcol001/Diffusion_job/oct/diff_model/organized_files/models/organized/models/conditional_2label/conditional/logs/slurm-328418.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/oct/diff_model/organized_files/models/organized/models/conditional_2label/conditional/logs/slurm-328418.out
   Power=
   TresPerNode=gres/gpu:l40s:1