JOB DETAILS FOR JOB 380086

captured Fri Nov 28 11:42:43 SAST 2025

MaxRAM=0.8G
MaxVMSize=0G
AveCPUFreq=800K
AveDiskRead=449393113
AveDiskWrite=91045

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7791 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=00:00:45 TimeLimit=02:00:00 TimeMin=N/A
   SubmitTime=2025-11-28T11:41:58 EligibleTime=2025-11-28T11:41:58
   AccrueTime=2025-11-28T11:41:58
   StartTime=2025-11-28T11:41:58 EndTime=2025-11-28T13:41:58 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-28T11:41:58 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc121.uct.ac.za:3613746
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=32G,node=1,billing=12,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=32G,node=1,billing=12,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=0-3,29-32 Mem=32768 GRES=gpu:ampere:1(IDX:1)
   MinCPUsNode=8 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/TranSiGen/GEM/boost/submit_boost_torchrun_test.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/GEM/boost
   StdErr=/scratch/bxxjin001/TranSiGen/GEM/boost/logs/slurm_outputs/boost_torchrun_test_380086.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/GEM/boost/logs/slurm_outputs/boost_torchrun_test_380086.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
UCT HPC clusterJOB DETAILS FOR JOB 380086

captured Fri Nov 28 11:43:01 SAST 2025

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7791 Nice=0 Account=a100free QOS=a100free
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:58 TimeLimit=02:00:00 TimeMin=N/A
   SubmitTime=2025-11-28T11:41:58 EligibleTime=2025-11-28T11:41:58
   AccrueTime=2025-11-28T11:41:58
   StartTime=2025-11-28T11:41:58 EndTime=2025-11-28T11:42:56 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-28T11:41:58 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc121.uct.ac.za:3613746
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=32G,node=1,billing=12,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=32G,node=1,billing=12,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=0-3,29-32 Mem=32768 GRES=
   MinCPUsNode=8 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/TranSiGen/GEM/boost/submit_boost_torchrun_test.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/GEM/boost
   StdErr=/scratch/bxxjin001/TranSiGen/GEM/boost/logs/slurm_outputs/boost_torchrun_test_380086.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/GEM/boost/logs/slurm_outputs/boost_torchrun_test_380086.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
UCT HPC clusterJOB DETAILS FOR JOB 380086

captured Fri Nov 28 11:43:42 SAST 2025

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7791 Nice=0 Account=a100free QOS=a100free
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:58 TimeLimit=02:00:00 TimeMin=N/A
   SubmitTime=2025-11-28T11:41:58 EligibleTime=2025-11-28T11:41:58
   AccrueTime=2025-11-28T11:41:58
   StartTime=2025-11-28T11:41:58 EndTime=2025-11-28T11:42:56 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-28T11:41:58 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc121.uct.ac.za:3613746
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=32G,node=1,billing=12,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=32G,node=1,billing=12,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=0-3,29-32 Mem=32768 GRES=
   MinCPUsNode=8 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/TranSiGen/GEM/boost/submit_boost_torchrun_test.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/GEM/boost
   StdErr=/scratch/bxxjin001/TranSiGen/GEM/boost/logs/slurm_outputs/boost_torchrun_test_380086.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/GEM/boost/logs/slurm_outputs/boost_torchrun_test_380086.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
UCT HPC clusterJOB DETAILS FOR JOB 380086

captured Fri Nov 28 11:44:01 SAST 2025

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7791 Nice=0 Account=a100free QOS=a100free
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:58 TimeLimit=02:00:00 TimeMin=N/A
   SubmitTime=2025-11-28T11:41:58 EligibleTime=2025-11-28T11:41:58
   AccrueTime=2025-11-28T11:41:58
   StartTime=2025-11-28T11:41:58 EndTime=2025-11-28T11:42:56 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-28T11:41:58 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc121.uct.ac.za:3613746
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=1 CPUs/Task=8 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=32G,node=1,billing=12,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=32G,node=1,billing=12,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=0-3,29-32 Mem=32768 GRES=
   MinCPUsNode=8 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/TranSiGen/GEM/boost/submit_boost_torchrun_test.sh
   WorkDir=/scratch/bxxjin001/TranSiGen/GEM/boost
   StdErr=/scratch/bxxjin001/TranSiGen/GEM/boost/logs/slurm_outputs/boost_torchrun_test_380086.err
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/TranSiGen/GEM/boost/logs/slurm_outputs/boost_torchrun_test_380086.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8