UCT HPC cluster

JOB DETAILS FOR JOB 190479

captured Tue Jul 29 18:50:01 SAST 2025

MaxRAM=0G
MaxVMSize=0G
AveCPUFreq=
AveDiskRead=
AveDiskWrite=

JobId=190479 JobName=gemma-mmt-training
   UserId=chldin002(1221907385 Dineo Chiloane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7013 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=0 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=02:52:07 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-07-29T15:57:32 EligibleTime=2025-07-29T15:57:32
   AccrueTime=2025-07-29T15:57:32
   StartTime=2025-07-29T15:57:54 EndTime=2025-07-31T15:57:54 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-07-29T15:57:54 Scheduler=Backfill
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:4009431
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=1
   AllocTRES=cpu=1,mem=10000M,node=1,billing=1,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=36 Mem=10000 GRES=gpu:l40s:1(IDX:2)
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/bin/bash
   WorkDir=/home/chldin002
   Power=
   TresPerNode=gres/gpu:1

UCT HPC clusterJOB DETAILS FOR JOB 190479

captured Tue Jul 29 18:50:34 SAST 2025

JobId=190479 JobName=gemma-mmt-training
   UserId=chldin002(1221907385 Dineo Chiloane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7013 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=0 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=02:52:31 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-07-29T15:57:32 EligibleTime=2025-07-29T15:57:32
   AccrueTime=2025-07-29T15:57:32
   StartTime=2025-07-29T15:57:54 EndTime=2025-07-29T18:50:25 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-07-29T15:57:54 Scheduler=Backfill
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:4009431
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=1
   AllocTRES=cpu=1,mem=10000M,node=1,billing=1,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=36 Mem=10000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/bin/bash
   WorkDir=/home/chldin002
   Power=
   TresPerNode=gres/gpu:1

UCT HPC clusterJOB DETAILS FOR JOB 190479

captured Tue Jul 29 18:51:01 SAST 2025

JobId=190479 JobName=gemma-mmt-training
   UserId=chldin002(1221907385 Dineo Chiloane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7013 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=0 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=02:52:31 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-07-29T15:57:32 EligibleTime=2025-07-29T15:57:32
   AccrueTime=2025-07-29T15:57:32
   StartTime=2025-07-29T15:57:54 EndTime=2025-07-29T18:50:25 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-07-29T15:57:54 Scheduler=Backfill
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:4009431
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=1
   AllocTRES=cpu=1,mem=10000M,node=1,billing=1,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=36 Mem=10000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/bin/bash
   WorkDir=/home/chldin002
   Power=
   TresPerNode=gres/gpu:1

UCT HPC clusterJOB DETAILS FOR JOB 190479

captured Tue Jul 29 18:51:34 SAST 2025

JobId=190479 JobName=gemma-mmt-training
   UserId=chldin002(1221907385 Dineo Chiloane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7013 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=0 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=02:52:31 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-07-29T15:57:32 EligibleTime=2025-07-29T15:57:32
   AccrueTime=2025-07-29T15:57:32
   StartTime=2025-07-29T15:57:54 EndTime=2025-07-29T18:50:25 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-07-29T15:57:54 Scheduler=Backfill
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:4009431
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=1
   AllocTRES=cpu=1,mem=10000M,node=1,billing=1,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=36 Mem=10000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/bin/bash
   WorkDir=/home/chldin002
   Power=
   TresPerNode=gres/gpu:1

UCT HPC clusterJOB DETAILS FOR JOB 190479

captured Tue Jul 29 18:52:01 SAST 2025

JobId=190479 JobName=gemma-mmt-training
   UserId=chldin002(1221907385 Dineo Chiloane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7013 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=0 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=02:52:31 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-07-29T15:57:32 EligibleTime=2025-07-29T15:57:32
   AccrueTime=2025-07-29T15:57:32
   StartTime=2025-07-29T15:57:54 EndTime=2025-07-29T18:50:25 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-07-29T15:57:54 Scheduler=Backfill
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:4009431
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu013
   BatchHost=srvrocgpu013
   NumNodes=1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=10000M,node=1,billing=1,gres/gpu=1
   AllocTRES=cpu=1,mem=10000M,node=1,billing=1,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=36 Mem=10000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/bin/bash
   WorkDir=/home/chldin002
   Power=
   TresPerNode=gres/gpu:1