JOB DETAILS FOR JOB 339699

captured Mon Nov 10 23:30:38 SAST 2025

MaxRAM=5.3G
MaxVMSize=0G
AveCPUFreq=800K
AveDiskRead=4003031845
AveDiskWrite=2589720

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7830 Nice=0 Account=a100free QOS=a100free
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:05:11 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-11-10T23:25:27 EligibleTime=2025-11-10T23:25:27
   AccrueTime=2025-11-10T23:25:27
   StartTime=2025-11-10T23:25:27 EndTime=2025-11-11T19:25:27 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-10T23:25:27 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrocgpu010.uct.ac.za:3135212
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=10 NumTasks=10 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=2-6,31-35 Mem=91420 GRES=gpu:ampere:1(IDX:2)
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned/submit_training.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned
   StdErr=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned/slurm-339699.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned/slurm-339699.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   MailUser=mrpcol001@myuct.ac.za MailType=BEGIN,END,FAIL
   

UCT HPC clusterJOB DETAILS FOR JOB 339699

captured Mon Nov 10 23:31:01 SAST 2025

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7830 Nice=0 Account=a100free QOS=a100free
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:05:30 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-11-10T23:25:27 EligibleTime=2025-11-10T23:25:27
   AccrueTime=2025-11-10T23:25:27
   StartTime=2025-11-10T23:25:27 EndTime=2025-11-10T23:30:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-10T23:25:27 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrocgpu010.uct.ac.za:3135212
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=10 NumTasks=10 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=2-6,31-35 Mem=91420 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned/submit_training.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned
   StdErr=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned/slurm-339699.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned/slurm-339699.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   MailUser=mrpcol001@myuct.ac.za MailType=BEGIN,END,FAIL
   

UCT HPC clusterJOB DETAILS FOR JOB 339699

captured Mon Nov 10 23:31:38 SAST 2025

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7830 Nice=0 Account=a100free QOS=a100free
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:05:30 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-11-10T23:25:27 EligibleTime=2025-11-10T23:25:27
   AccrueTime=2025-11-10T23:25:27
   StartTime=2025-11-10T23:25:27 EndTime=2025-11-10T23:30:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-10T23:25:27 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrocgpu010.uct.ac.za:3135212
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=10 NumTasks=10 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=2-6,31-35 Mem=91420 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned/submit_training.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned
   StdErr=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned/slurm-339699.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned/slurm-339699.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   MailUser=mrpcol001@myuct.ac.za MailType=BEGIN,END,FAIL
   

UCT HPC clusterJOB DETAILS FOR JOB 339699

captured Mon Nov 10 23:32:01 SAST 2025

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7830 Nice=0 Account=a100free QOS=a100free
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:05:30 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-11-10T23:25:27 EligibleTime=2025-11-10T23:25:27
   AccrueTime=2025-11-10T23:25:27
   StartTime=2025-11-10T23:25:27 EndTime=2025-11-10T23:30:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-10T23:25:27 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrocgpu010.uct.ac.za:3135212
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=10 NumTasks=10 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=2-6,31-35 Mem=91420 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned/submit_training.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned
   StdErr=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned/slurm-339699.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned/slurm-339699.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   MailUser=mrpcol001@myuct.ac.za MailType=BEGIN,END,FAIL
   

UCT HPC clusterJOB DETAILS FOR JOB 339699

captured Mon Nov 10 23:32:37 SAST 2025

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7830 Nice=0 Account=a100free QOS=a100free
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:05:30 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-11-10T23:25:27 EligibleTime=2025-11-10T23:25:27
   AccrueTime=2025-11-10T23:25:27
   StartTime=2025-11-10T23:25:27 EndTime=2025-11-10T23:30:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-10T23:25:27 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrocgpu010.uct.ac.za:3135212
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=10 NumTasks=10 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=2-6,31-35 Mem=91420 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned/submit_training.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned
   StdErr=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned/slurm-339699.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned/slurm-339699.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   MailUser=mrpcol001@myuct.ac.za MailType=BEGIN,END,FAIL
   

UCT HPC clusterJOB DETAILS FOR JOB 339699

captured Mon Nov 10 23:33:01 SAST 2025

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7830 Nice=0 Account=a100free QOS=a100free
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:05:30 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-11-10T23:25:27 EligibleTime=2025-11-10T23:25:27
   AccrueTime=2025-11-10T23:25:27
   StartTime=2025-11-10T23:25:27 EndTime=2025-11-10T23:30:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-10T23:25:27 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrocgpu010.uct.ac.za:3135212
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=10 NumTasks=10 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=2-6,31-35 Mem=91420 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned/submit_training.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned
   StdErr=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned/slurm-339699.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/nov/10nov/tuned/slurm-339699.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   MailUser=mrpcol001@myuct.ac.za MailType=BEGIN,END,FAIL