UCT HPC cluster

JOB DETAILS FOR JOB 282072

captured Wed Sep 17 12:16:36 SAST 2025

JobId=282072 JobName=ddpm_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7796 Nice=0 Account=a100free QOS=a100free
   JobState=PENDING Reason=AssocGrpGRES Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-09-17T12:16:21 EligibleTime=2025-09-17T12:16:21
   AccrueTime=2025-09-17T12:16:21
   StartTime=Unknown EndTime=Unknown Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-09-17T12:16:21 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrocgpu014.uct.ac.za:1963123
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1-1 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=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   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/sept/17sept/guided-diffusion/run_train_extended.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/sept/17sept/guided-diffusion
   StdErr=/scratch/mrpcol001/Diffusion_job/sept/17sept/guided-diffusion/slurm-282072.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/sept/17sept/guided-diffusion/slurm-282072.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 282072

captured Wed Sep 17 12:17:02 SAST 2025

JobId=282072 JobName=ddpm_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7796 Nice=0 Account=a100free QOS=a100free
   JobState=CANCELLED Reason=AssocGrpGRES Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-09-17T12:16:21 EligibleTime=2025-09-17T12:16:21
   AccrueTime=2025-09-17T12:16:21
   StartTime=2025-09-17T12:16:49 EndTime=2025-09-17T12:16:49 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-09-17T12:16:21 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrocgpu014.uct.ac.za:1963123
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   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=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   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/sept/17sept/guided-diffusion/run_train_extended.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/sept/17sept/guided-diffusion
   StdErr=/scratch/mrpcol001/Diffusion_job/sept/17sept/guided-diffusion/slurm-282072.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/sept/17sept/guided-diffusion/slurm-282072.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 282072

captured Wed Sep 17 12:17:37 SAST 2025

JobId=282072 JobName=ddpm_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7796 Nice=0 Account=a100free QOS=a100free
   JobState=CANCELLED Reason=AssocGrpGRES Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-09-17T12:16:21 EligibleTime=2025-09-17T12:16:21
   AccrueTime=2025-09-17T12:16:21
   StartTime=2025-09-17T12:16:49 EndTime=2025-09-17T12:16:49 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-09-17T12:16:21 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrocgpu014.uct.ac.za:1963123
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   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=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   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/sept/17sept/guided-diffusion/run_train_extended.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/sept/17sept/guided-diffusion
   StdErr=/scratch/mrpcol001/Diffusion_job/sept/17sept/guided-diffusion/slurm-282072.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/sept/17sept/guided-diffusion/slurm-282072.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 282072

captured Wed Sep 17 12:18:01 SAST 2025

JobId=282072 JobName=ddpm_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7796 Nice=0 Account=a100free QOS=a100free
   JobState=CANCELLED Reason=AssocGrpGRES Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-09-17T12:16:21 EligibleTime=2025-09-17T12:16:21
   AccrueTime=2025-09-17T12:16:21
   StartTime=2025-09-17T12:16:49 EndTime=2025-09-17T12:16:49 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-09-17T12:16:21 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrocgpu014.uct.ac.za:1963123
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   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=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   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/sept/17sept/guided-diffusion/run_train_extended.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/sept/17sept/guided-diffusion
   StdErr=/scratch/mrpcol001/Diffusion_job/sept/17sept/guided-diffusion/slurm-282072.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/sept/17sept/guided-diffusion/slurm-282072.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 282072

captured Wed Sep 17 12:18:36 SAST 2025

JobId=282072 JobName=ddpm_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7796 Nice=0 Account=a100free QOS=a100free
   JobState=CANCELLED Reason=AssocGrpGRES Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-09-17T12:16:21 EligibleTime=2025-09-17T12:16:21
   AccrueTime=2025-09-17T12:16:21
   StartTime=2025-09-17T12:16:49 EndTime=2025-09-17T12:16:49 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-09-17T12:16:21 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrocgpu014.uct.ac.za:1963123
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   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=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   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/sept/17sept/guided-diffusion/run_train_extended.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/sept/17sept/guided-diffusion
   StdErr=/scratch/mrpcol001/Diffusion_job/sept/17sept/guided-diffusion/slurm-282072.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/sept/17sept/guided-diffusion/slurm-282072.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 282072

captured Wed Sep 17 12:19:01 SAST 2025

JobId=282072 JobName=ddpm_model
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7796 Nice=0 Account=a100free QOS=a100free
   JobState=CANCELLED Reason=AssocGrpGRES Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=20:00:00 TimeMin=N/A
   SubmitTime=2025-09-17T12:16:21 EligibleTime=2025-09-17T12:16:21
   AccrueTime=2025-09-17T12:16:21
   StartTime=2025-09-17T12:16:49 EndTime=2025-09-17T12:16:49 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-09-17T12:16:21 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrocgpu014.uct.ac.za:1963123
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   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=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   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/sept/17sept/guided-diffusion/run_train_extended.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/sept/17sept/guided-diffusion
   StdErr=/scratch/mrpcol001/Diffusion_job/sept/17sept/guided-diffusion/slurm-282072.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/sept/17sept/guided-diffusion/slurm-282072.out
   Power=
   TresPerNode=gres/gpu:ampere:1