JOB DETAILS FOR JOB 474723

captured Fri Jan 23 18:41:36 SAST 2026

MaxRAM=2.4G
MaxVMSize=0G
AveCPUFreq=27K
AveDiskRead=1919759432
AveDiskWrite=378358801

mwrsim003(733332728 Simbarashe Mawere) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8469 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=04:15:48 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-01-22T10:46:33 EligibleTime=2026-01-22T10:46:33
   AccrueTime=2026-01-22T10:46:33
   StartTime=2026-01-23T14:25:48 EndTime=2026-01-24T14:25:48 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-23T14:25:48 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc116.uct.ac.za:3540807
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   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:ampere80=1
   AllocTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=0,3,11-13,28,31,39-41 Mem=91420 GRES=gpu:ampere80:1(IDX:0)
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/mwrsim003/masters_code/scripts/finetuning_job_continued.sh
   WorkDir=/home/mwrsim003/masters_code
   StdErr=/home/mwrsim003/masters_code/slurm-474723.out
   StdIn=/dev/null
   StdOut=/home/mwrsim003/masters_code/slurm-474723.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=mwrsim003@myuct.ac.za MailType=BEGIN,END,FAIL
   

UCT HPC clusterJOB DETAILS FOR JOB 474723

captured Fri Jan 23 18:42:01 SAST 2026

mwrsim003(733332728 Simbarashe Mawere) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8469 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=04:16:06 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-01-22T10:46:33 EligibleTime=2026-01-22T10:46:33
   AccrueTime=2026-01-22T10:46:33
   StartTime=2026-01-23T14:25:48 EndTime=2026-01-23T18:41:54 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-23T14:25:48 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc116.uct.ac.za:3540807
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   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:ampere80=1
   AllocTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=0,3,11-13,28,31,39-41 Mem=91420 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/mwrsim003/masters_code/scripts/finetuning_job_continued.sh
   WorkDir=/home/mwrsim003/masters_code
   StdErr=/home/mwrsim003/masters_code/slurm-474723.out
   StdIn=/dev/null
   StdOut=/home/mwrsim003/masters_code/slurm-474723.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=mwrsim003@myuct.ac.za MailType=BEGIN,END,FAIL
   

UCT HPC clusterJOB DETAILS FOR JOB 474723

captured Fri Jan 23 18:42:35 SAST 2026

mwrsim003(733332728 Simbarashe Mawere) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8469 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=04:16:06 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-01-22T10:46:33 EligibleTime=2026-01-22T10:46:33
   AccrueTime=2026-01-22T10:46:33
   StartTime=2026-01-23T14:25:48 EndTime=2026-01-23T18:41:54 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-23T14:25:48 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc116.uct.ac.za:3540807
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   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:ampere80=1
   AllocTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=0,3,11-13,28,31,39-41 Mem=91420 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/mwrsim003/masters_code/scripts/finetuning_job_continued.sh
   WorkDir=/home/mwrsim003/masters_code
   StdErr=/home/mwrsim003/masters_code/slurm-474723.out
   StdIn=/dev/null
   StdOut=/home/mwrsim003/masters_code/slurm-474723.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=mwrsim003@myuct.ac.za MailType=BEGIN,END,FAIL
   

UCT HPC clusterJOB DETAILS FOR JOB 474723

captured Fri Jan 23 18:43:01 SAST 2026

mwrsim003(733332728 Simbarashe Mawere) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8469 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=04:16:06 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-01-22T10:46:33 EligibleTime=2026-01-22T10:46:33
   AccrueTime=2026-01-22T10:46:33
   StartTime=2026-01-23T14:25:48 EndTime=2026-01-23T18:41:54 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-23T14:25:48 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc116.uct.ac.za:3540807
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   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:ampere80=1
   AllocTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=0,3,11-13,28,31,39-41 Mem=91420 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/mwrsim003/masters_code/scripts/finetuning_job_continued.sh
   WorkDir=/home/mwrsim003/masters_code
   StdErr=/home/mwrsim003/masters_code/slurm-474723.out
   StdIn=/dev/null
   StdOut=/home/mwrsim003/masters_code/slurm-474723.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=mwrsim003@myuct.ac.za MailType=BEGIN,END,FAIL
   

UCT HPC clusterJOB DETAILS FOR JOB 474723

captured Fri Jan 23 18:43:35 SAST 2026

mwrsim003(733332728 Simbarashe Mawere) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8469 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=04:16:06 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2026-01-22T10:46:33 EligibleTime=2026-01-22T10:46:33
   AccrueTime=2026-01-22T10:46:33
   StartTime=2026-01-23T14:25:48 EndTime=2026-01-23T18:41:54 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-01-23T14:25:48 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc116.uct.ac.za:3540807
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu011
   BatchHost=srvrocgpu011
   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:ampere80=1
   AllocTRES=cpu=10,mem=91420M,node=1,billing=19,gres/gpu=1,gres/gpu:ampere80=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere80:1
     Nodes=srvrocgpu011 CPU_IDs=0,3,11-13,28,31,39-41 Mem=91420 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/home/mwrsim003/masters_code/scripts/finetuning_job_continued.sh
   WorkDir=/home/mwrsim003/masters_code
   StdErr=/home/mwrsim003/masters_code/slurm-474723.out
   StdIn=/dev/null
   StdOut=/home/mwrsim003/masters_code/slurm-474723.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=mwrsim003@myuct.ac.za MailType=BEGIN,END,FAIL