UCT HPC cluster

JOB DETAILS FOR JOB 380247

captured Fri Nov 28 11:54:02 SAST 2025

MaxRAM=2.9G
MaxVMSize=0G
AveCPUFreq=1.70M
AveDiskRead=1313539916
AveDiskWrite=25991199

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8194 Nice=0 Account=a100free QOS=a100free
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:03:43 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2025-11-28T11:50:18 EligibleTime=2025-11-28T11:50:18
   AccrueTime=2025-11-28T11:50:19
   StartTime=2025-11-28T11:50:19 EndTime=2025-11-29T11:50:19 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-28T11:50:19 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc121.uct.ac.za:3623153
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=16 NumTasks=1 CPUs/Task=16 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=16,mem=64G,node=1,billing=24,gres/gpu=2,gres/gpu:ampere=2
   AllocTRES=cpu=16,mem=64G,node=1,billing=24,gres/gpu=2,gres/gpu:ampere=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:2
     Nodes=srvrocgpu010 CPU_IDs=0-7,29-36 Mem=65536 GRES=gpu:ampere:2(IDX:1-2)
   MinCPUsNode=16 MinMemoryNode=64G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/TranSiGen/GEM/boost/submit_boost_dual_a100_torchrun.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/GEM/boost
   StdErr=/scratch/bxxjin001/TranSiGen/GEM/boost/logs/slurm_outputs/boost_dual_a100_380247.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/GEM/boost/logs/slurm_outputs/boost_dual_a100_380247.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:16

UCT HPC clusterJOB DETAILS FOR JOB 380247

captured Fri Nov 28 11:54:42 SAST 2025

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8194 Nice=0 Account=a100free QOS=a100free
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:03:57 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2025-11-28T11:50:18 EligibleTime=2025-11-28T11:50:18
   AccrueTime=2025-11-28T11:50:19
   StartTime=2025-11-28T11:50:19 EndTime=2025-11-28T11:54:16 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-28T11:50:19 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc121.uct.ac.za:3623153
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=16 NumTasks=1 CPUs/Task=16 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=16,mem=64G,node=1,billing=24,gres/gpu=2,gres/gpu:ampere=2
   AllocTRES=cpu=16,mem=64G,node=1,billing=24,gres/gpu=2,gres/gpu:ampere=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:2
     Nodes=srvrocgpu010 CPU_IDs=0-7,29-36 Mem=65536 GRES=
   MinCPUsNode=16 MinMemoryNode=64G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/TranSiGen/GEM/boost/submit_boost_dual_a100_torchrun.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/GEM/boost
   StdErr=/scratch/bxxjin001/TranSiGen/GEM/boost/logs/slurm_outputs/boost_dual_a100_380247.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/GEM/boost/logs/slurm_outputs/boost_dual_a100_380247.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:16

UCT HPC clusterJOB DETAILS FOR JOB 380247

captured Fri Nov 28 11:55:01 SAST 2025

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8194 Nice=0 Account=a100free QOS=a100free
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:03:57 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2025-11-28T11:50:18 EligibleTime=2025-11-28T11:50:18
   AccrueTime=2025-11-28T11:50:19
   StartTime=2025-11-28T11:50:19 EndTime=2025-11-28T11:54:16 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-28T11:50:19 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc121.uct.ac.za:3623153
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=16 NumTasks=1 CPUs/Task=16 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=16,mem=64G,node=1,billing=24,gres/gpu=2,gres/gpu:ampere=2
   AllocTRES=cpu=16,mem=64G,node=1,billing=24,gres/gpu=2,gres/gpu:ampere=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:2
     Nodes=srvrocgpu010 CPU_IDs=0-7,29-36 Mem=65536 GRES=
   MinCPUsNode=16 MinMemoryNode=64G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/TranSiGen/GEM/boost/submit_boost_dual_a100_torchrun.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/GEM/boost
   StdErr=/scratch/bxxjin001/TranSiGen/GEM/boost/logs/slurm_outputs/boost_dual_a100_380247.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/GEM/boost/logs/slurm_outputs/boost_dual_a100_380247.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:16

UCT HPC clusterJOB DETAILS FOR JOB 380247

captured Fri Nov 28 11:55:42 SAST 2025

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8194 Nice=0 Account=a100free QOS=a100free
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:03:57 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2025-11-28T11:50:18 EligibleTime=2025-11-28T11:50:18
   AccrueTime=2025-11-28T11:50:19
   StartTime=2025-11-28T11:50:19 EndTime=2025-11-28T11:54:16 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-28T11:50:19 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc121.uct.ac.za:3623153
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=16 NumTasks=1 CPUs/Task=16 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=16,mem=64G,node=1,billing=24,gres/gpu=2,gres/gpu:ampere=2
   AllocTRES=cpu=16,mem=64G,node=1,billing=24,gres/gpu=2,gres/gpu:ampere=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:2
     Nodes=srvrocgpu010 CPU_IDs=0-7,29-36 Mem=65536 GRES=
   MinCPUsNode=16 MinMemoryNode=64G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/TranSiGen/GEM/boost/submit_boost_dual_a100_torchrun.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/GEM/boost
   StdErr=/scratch/bxxjin001/TranSiGen/GEM/boost/logs/slurm_outputs/boost_dual_a100_380247.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/GEM/boost/logs/slurm_outputs/boost_dual_a100_380247.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:16

UCT HPC clusterJOB DETAILS FOR JOB 380247

captured Fri Nov 28 11:56:01 SAST 2025

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8194 Nice=0 Account=a100free QOS=a100free
   JobState=CANCELLED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=00:03:57 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2025-11-28T11:50:18 EligibleTime=2025-11-28T11:50:18
   AccrueTime=2025-11-28T11:50:19
   StartTime=2025-11-28T11:50:19 EndTime=2025-11-28T11:54:16 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-28T11:50:19 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc121.uct.ac.za:3623153
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=16 NumTasks=1 CPUs/Task=16 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=16,mem=64G,node=1,billing=24,gres/gpu=2,gres/gpu:ampere=2
   AllocTRES=cpu=16,mem=64G,node=1,billing=24,gres/gpu=2,gres/gpu:ampere=2
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:2
     Nodes=srvrocgpu010 CPU_IDs=0-7,29-36 Mem=65536 GRES=
   MinCPUsNode=16 MinMemoryNode=64G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/TranSiGen/GEM/boost/submit_boost_dual_a100_torchrun.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/GEM/boost
   StdErr=/scratch/bxxjin001/TranSiGen/GEM/boost/logs/slurm_outputs/boost_dual_a100_380247.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/GEM/boost/logs/slurm_outputs/boost_dual_a100_380247.out
   Power=
   TresPerNode=gres/gpu:ampere:2
   TresPerTask=cpu:16