JOB DETAILS FOR JOB 1332058

captured Sun Sep 13 10:06:01 SAST 2026

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

mwrsim003(733332728 ) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7930 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=2-08:28:06 TimeLimit=3-00:00:00 TimeMin=N/A
   SubmitTime=2026-09-10T18:43:46 EligibleTime=2026-09-10T18:43:46
   AccrueTime=2026-09-10T18:43:48
   StartTime=2026-09-11T01:37:55 EndTime=2026-09-14T01:37:55 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-11T01:37:55 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc104:463982
   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=0,13-16,28,41-44 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/run_pt_adapted.sh
   WorkDir=/home/mwrsim003/masters_code
   StdErr=/home/mwrsim003/masters_code/.logs/continual_pretrain/run_pt_adapted.sh_1332058.err
   StdIn=/dev/null
   StdOut=/home/mwrsim003/masters_code/.logs/continual_pretrain/run_pt_adapted.sh_1332058.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=mwrsim003@myuct.ac.za MailType=BEGIN,END,FAIL
UCT HPC clusterJOB DETAILS FOR JOB 1332058

captured Sun Sep 13 10:06:23 SAST 2026

mwrsim003(733332728 ) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7930 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=NODE_FAIL Reason=NodeDown FailedNode=srvrocgpu011 Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=2-08:28:11 TimeLimit=3-00:00:00 TimeMin=N/A
   SubmitTime=2026-09-10T18:43:46 EligibleTime=2026-09-10T18:43:46
   AccrueTime=2026-09-10T18:43:48
   StartTime=2026-09-11T01:37:55 EndTime=2026-09-13T10:06:06 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-11T01:37:55 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc104:463982
   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=0,13-16,28,41-44 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/run_pt_adapted.sh
   WorkDir=/home/mwrsim003/masters_code
   StdErr=/home/mwrsim003/masters_code/.logs/continual_pretrain/run_pt_adapted.sh_1332058.err
   StdIn=/dev/null
   StdOut=/home/mwrsim003/masters_code/.logs/continual_pretrain/run_pt_adapted.sh_1332058.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=mwrsim003@myuct.ac.za MailType=BEGIN,END,FAIL
UCT HPC clusterJOB DETAILS FOR JOB 1332058

captured Sun Sep 13 10:06:46 SAST 2026

mwrsim003(733332728 ) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7930 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=NODE_FAIL Reason=NodeDown FailedNode=srvrocgpu011 Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=2-08:28:11 TimeLimit=3-00:00:00 TimeMin=N/A
   SubmitTime=2026-09-10T18:43:46 EligibleTime=2026-09-10T18:43:46
   AccrueTime=2026-09-10T18:43:48
   StartTime=2026-09-11T01:37:55 EndTime=2026-09-13T10:06:06 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-11T01:37:55 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc104:463982
   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=0,13-16,28,41-44 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/run_pt_adapted.sh
   WorkDir=/home/mwrsim003/masters_code
   StdErr=/home/mwrsim003/masters_code/.logs/continual_pretrain/run_pt_adapted.sh_1332058.err
   StdIn=/dev/null
   StdOut=/home/mwrsim003/masters_code/.logs/continual_pretrain/run_pt_adapted.sh_1332058.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=mwrsim003@myuct.ac.za MailType=BEGIN,END,FAIL
UCT HPC clusterJOB DETAILS FOR JOB 1332058

captured Sun Sep 13 10:07:01 SAST 2026

mwrsim003(733332728 ) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7930 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=NODE_FAIL Reason=NodeDown FailedNode=srvrocgpu011 Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=2-08:28:11 TimeLimit=3-00:00:00 TimeMin=N/A
   SubmitTime=2026-09-10T18:43:46 EligibleTime=2026-09-10T18:43:46
   AccrueTime=2026-09-10T18:43:48
   StartTime=2026-09-11T01:37:55 EndTime=2026-09-13T10:06:06 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-11T01:37:55 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc104:463982
   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=0,13-16,28,41-44 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/run_pt_adapted.sh
   WorkDir=/home/mwrsim003/masters_code
   StdErr=/home/mwrsim003/masters_code/.logs/continual_pretrain/run_pt_adapted.sh_1332058.err
   StdIn=/dev/null
   StdOut=/home/mwrsim003/masters_code/.logs/continual_pretrain/run_pt_adapted.sh_1332058.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=mwrsim003@myuct.ac.za MailType=BEGIN,END,FAIL
UCT HPC clusterJOB DETAILS FOR JOB 1332058

captured Sun Sep 13 10:07:34 SAST 2026

mwrsim003(733332728 ) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7930 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=NODE_FAIL Reason=NodeDown FailedNode=srvrocgpu011 Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=2-08:28:11 TimeLimit=3-00:00:00 TimeMin=N/A
   SubmitTime=2026-09-10T18:43:46 EligibleTime=2026-09-10T18:43:46
   AccrueTime=2026-09-10T18:43:48
   StartTime=2026-09-11T01:37:55 EndTime=2026-09-13T10:06:06 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-11T01:37:55 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc104:463982
   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=0,13-16,28,41-44 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/run_pt_adapted.sh
   WorkDir=/home/mwrsim003/masters_code
   StdErr=/home/mwrsim003/masters_code/.logs/continual_pretrain/run_pt_adapted.sh_1332058.err
   StdIn=/dev/null
   StdOut=/home/mwrsim003/masters_code/.logs/continual_pretrain/run_pt_adapted.sh_1332058.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=mwrsim003@myuct.ac.za MailType=BEGIN,END,FAIL
UCT HPC clusterJOB DETAILS FOR JOB 1332058

captured Sun Sep 13 10:08:01 SAST 2026

mwrsim003(733332728 ) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7930 Nice=0 Account=nlpgroup80 QOS=nlpgroup80
   JobState=NODE_FAIL Reason=NodeDown FailedNode=srvrocgpu011 Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=2-08:28:11 TimeLimit=3-00:00:00 TimeMin=N/A
   SubmitTime=2026-09-10T18:43:46 EligibleTime=2026-09-10T18:43:46
   AccrueTime=2026-09-10T18:43:48
   StartTime=2026-09-11T01:37:55 EndTime=2026-09-13T10:06:06 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-11T01:37:55 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc104:463982
   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=0,13-16,28,41-44 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/run_pt_adapted.sh
   WorkDir=/home/mwrsim003/masters_code
   StdErr=/home/mwrsim003/masters_code/.logs/continual_pretrain/run_pt_adapted.sh_1332058.err
   StdIn=/dev/null
   StdOut=/home/mwrsim003/masters_code/.logs/continual_pretrain/run_pt_adapted.sh_1332058.out
   Power=
   TresPerNode=gres/gpu:ampere80:1
   MailUser=mwrsim003@myuct.ac.za MailType=BEGIN,END,FAIL