UCT HPC cluster

JOB DETAILS FOR JOB 61766

captured Sat Jan 11 10:54:32 SAST 2025

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

JobId=61766 JobName=sa_lang_gpt
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8156 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:17 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-01-11T10:54:15 EligibleTime=2025-01-11T10:54:15
   AccrueTime=2025-01-11T10:54:15
   StartTime=2025-01-11T10:54:15 EndTime=2025-01-13T10:54:15 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-01-11T10:54:15 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:2814856
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=36568M,node=1,billing=8,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=4,mem=36568M,node=1,billing=8,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=0-1,28-29 Mem=36568 GRES=gpu:ampere:1(IDX:0)
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/modded-nanogpt/run.sh
   WorkDir=/home/lmbanr001/masters/modded-nanogpt
   StdErr=/home/lmbanr001/masters/modded-nanogpt/slurm-61766.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/modded-nanogpt/slurm-61766.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 61766

captured Sat Jan 11 10:55:01 SAST 2025

JobId=61766 JobName=sa_lang_gpt
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8156 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:19 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-01-11T10:54:15 EligibleTime=2025-01-11T10:54:15
   AccrueTime=2025-01-11T10:54:15
   StartTime=2025-01-11T10:54:15 EndTime=2025-01-11T10:54:34 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-01-11T10:54:15 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:2814856
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=36568M,node=1,billing=8,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=4,mem=36568M,node=1,billing=8,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=0-1,28-29 Mem=36568 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/modded-nanogpt/run.sh
   WorkDir=/home/lmbanr001/masters/modded-nanogpt
   StdErr=/home/lmbanr001/masters/modded-nanogpt/slurm-61766.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/modded-nanogpt/slurm-61766.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 61766

captured Sat Jan 11 10:55:32 SAST 2025

JobId=61766 JobName=sa_lang_gpt
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8156 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:19 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-01-11T10:54:15 EligibleTime=2025-01-11T10:54:15
   AccrueTime=2025-01-11T10:54:15
   StartTime=2025-01-11T10:54:15 EndTime=2025-01-11T10:54:34 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-01-11T10:54:15 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:2814856
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=36568M,node=1,billing=8,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=4,mem=36568M,node=1,billing=8,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=0-1,28-29 Mem=36568 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/modded-nanogpt/run.sh
   WorkDir=/home/lmbanr001/masters/modded-nanogpt
   StdErr=/home/lmbanr001/masters/modded-nanogpt/slurm-61766.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/modded-nanogpt/slurm-61766.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 61766

captured Sat Jan 11 10:56:02 SAST 2025

JobId=61766 JobName=sa_lang_gpt
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8156 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:19 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-01-11T10:54:15 EligibleTime=2025-01-11T10:54:15
   AccrueTime=2025-01-11T10:54:15
   StartTime=2025-01-11T10:54:15 EndTime=2025-01-11T10:54:34 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-01-11T10:54:15 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:2814856
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=36568M,node=1,billing=8,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=4,mem=36568M,node=1,billing=8,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=0-1,28-29 Mem=36568 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/modded-nanogpt/run.sh
   WorkDir=/home/lmbanr001/masters/modded-nanogpt
   StdErr=/home/lmbanr001/masters/modded-nanogpt/slurm-61766.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/modded-nanogpt/slurm-61766.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 61766

captured Sat Jan 11 10:56:33 SAST 2025

JobId=61766 JobName=sa_lang_gpt
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8156 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:19 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-01-11T10:54:15 EligibleTime=2025-01-11T10:54:15
   AccrueTime=2025-01-11T10:54:15
   StartTime=2025-01-11T10:54:15 EndTime=2025-01-11T10:54:34 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-01-11T10:54:15 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:2814856
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=36568M,node=1,billing=8,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=4,mem=36568M,node=1,billing=8,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=0-1,28-29 Mem=36568 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/modded-nanogpt/run.sh
   WorkDir=/home/lmbanr001/masters/modded-nanogpt
   StdErr=/home/lmbanr001/masters/modded-nanogpt/slurm-61766.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/modded-nanogpt/slurm-61766.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 61766

captured Sat Jan 11 10:57:01 SAST 2025

JobId=61766 JobName=sa_lang_gpt
   UserId=lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8156 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:00:19 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2025-01-11T10:54:15 EligibleTime=2025-01-11T10:54:15
   AccrueTime=2025-01-11T10:54:15
   StartTime=2025-01-11T10:54:15 EndTime=2025-01-11T10:54:34 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-01-11T10:54:15 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001.uct.ac.za:2814856
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=36568M,node=1,billing=8,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=4,mem=36568M,node=1,billing=8,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=0-1,28-29 Mem=36568 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/lmbanr001/masters/modded-nanogpt/run.sh
   WorkDir=/home/lmbanr001/masters/modded-nanogpt
   StdErr=/home/lmbanr001/masters/modded-nanogpt/slurm-61766.out
   StdIn=/dev/null
   StdOut=/home/lmbanr001/masters/modded-nanogpt/slurm-61766.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   MailUser=lmbanr001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT