UCT HPC cluster

JOB DETAILS FOR JOB 1335759

captured Mon Sep 14 17:15:38 SAST 2026

MaxRAM=15.5G
MaxVMSize=0G
AveCPUFreq=453K
AveDiskRead=10083131962
AveDiskWrite=15675750213

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7950 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=02:22:41 TimeLimit=16:00:00 TimeMin=N/A
   SubmitTime=2026-09-14T11:32:24 EligibleTime=2026-09-14T11:32:24
   AccrueTime=2026-09-14T11:32:24
   StartTime=2026-09-14T14:52:57 EndTime=2026-09-15T06:52:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-14T14:52:57 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2490045
   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=96G,node=1,billing=18,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=96G,node=1,billing=18,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=7,13,16-21 Mem=98304 GRES=gpu:ampere:1(IDX:3)
   MinCPUsNode=11 MinMemoryNode=96G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/pos-generation-recovery-20260914-v1/.audit/run_pos_generation_recovery_train_20260914.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm/results/standardized_adapter_recovery_20260914_hex_v1/slurm/train-1335756_0.err
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/standardized_adapter_recovery_20260914_hex_v1/slurm/train-1335756_0.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1335759

captured Mon Sep 14 17:16:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7950 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=2:0
   DerivedExitCode=0:0
   RunTime=02:23:03 TimeLimit=16:00:00 TimeMin=N/A
   SubmitTime=2026-09-14T11:32:24 EligibleTime=2026-09-14T11:32:24
   AccrueTime=2026-09-14T11:32:24
   StartTime=2026-09-14T14:52:57 EndTime=2026-09-14T17:16:00 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-14T14:52:57 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2490045
   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=96G,node=1,billing=18,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=96G,node=1,billing=18,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=7,13,16-21 Mem=98304 GRES=
   MinCPUsNode=11 MinMemoryNode=96G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/pos-generation-recovery-20260914-v1/.audit/run_pos_generation_recovery_train_20260914.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm/results/standardized_adapter_recovery_20260914_hex_v1/slurm/train-1335756_0.err
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/standardized_adapter_recovery_20260914_hex_v1/slurm/train-1335756_0.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1335759

captured Mon Sep 14 17:16:37 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7950 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=2:0
   DerivedExitCode=0:0
   RunTime=02:23:03 TimeLimit=16:00:00 TimeMin=N/A
   SubmitTime=2026-09-14T11:32:24 EligibleTime=2026-09-14T11:32:24
   AccrueTime=2026-09-14T11:32:24
   StartTime=2026-09-14T14:52:57 EndTime=2026-09-14T17:16:00 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-14T14:52:57 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2490045
   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=96G,node=1,billing=18,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=96G,node=1,billing=18,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=7,13,16-21 Mem=98304 GRES=
   MinCPUsNode=11 MinMemoryNode=96G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/pos-generation-recovery-20260914-v1/.audit/run_pos_generation_recovery_train_20260914.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm/results/standardized_adapter_recovery_20260914_hex_v1/slurm/train-1335756_0.err
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/standardized_adapter_recovery_20260914_hex_v1/slurm/train-1335756_0.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1335759

captured Mon Sep 14 17:17:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7950 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=2:0
   DerivedExitCode=0:0
   RunTime=02:23:03 TimeLimit=16:00:00 TimeMin=N/A
   SubmitTime=2026-09-14T11:32:24 EligibleTime=2026-09-14T11:32:24
   AccrueTime=2026-09-14T11:32:24
   StartTime=2026-09-14T14:52:57 EndTime=2026-09-14T17:16:00 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-14T14:52:57 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2490045
   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=96G,node=1,billing=18,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=96G,node=1,billing=18,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=7,13,16-21 Mem=98304 GRES=
   MinCPUsNode=11 MinMemoryNode=96G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/pos-generation-recovery-20260914-v1/.audit/run_pos_generation_recovery_train_20260914.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm/results/standardized_adapter_recovery_20260914_hex_v1/slurm/train-1335756_0.err
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/standardized_adapter_recovery_20260914_hex_v1/slurm/train-1335756_0.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1335759

captured Mon Sep 14 17:17:37 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7950 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=2:0
   DerivedExitCode=0:0
   RunTime=02:23:03 TimeLimit=16:00:00 TimeMin=N/A
   SubmitTime=2026-09-14T11:32:24 EligibleTime=2026-09-14T11:32:24
   AccrueTime=2026-09-14T11:32:24
   StartTime=2026-09-14T14:52:57 EndTime=2026-09-14T17:16:00 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-14T14:52:57 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2490045
   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=96G,node=1,billing=18,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=96G,node=1,billing=18,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=7,13,16-21 Mem=98304 GRES=
   MinCPUsNode=11 MinMemoryNode=96G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/pos-generation-recovery-20260914-v1/.audit/run_pos_generation_recovery_train_20260914.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm/results/standardized_adapter_recovery_20260914_hex_v1/slurm/train-1335756_0.err
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/standardized_adapter_recovery_20260914_hex_v1/slurm/train-1335756_0.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL

UCT HPC clusterJOB DETAILS FOR JOB 1335759

captured Mon Sep 14 17:18:01 SAST 2026

lmbanr001(733329384 Anri Lombard) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7950 Nice=0 Account=nlpgroup QOS=nlpgroup
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=2:0
   DerivedExitCode=0:0
   RunTime=02:23:03 TimeLimit=16:00:00 TimeMin=N/A
   SubmitTime=2026-09-14T11:32:24 EligibleTime=2026-09-14T11:32:24
   AccrueTime=2026-09-14T11:32:24
   StartTime=2026-09-14T14:52:57 EndTime=2026-09-14T17:16:00 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-14T14:52:57 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc001:2490045
   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=96G,node=1,billing=18,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=96G,node=1,billing=18,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=7,13,16-21 Mem=98304 GRES=
   MinCPUsNode=11 MinMemoryNode=96G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/lmbanr001/masters/sallm_snapshots/pos-generation-recovery-20260914-v1/.audit/run_pos_generation_recovery_train_20260914.sbatch
   WorkDir=/home/lmbanr001
   StdErr=/scratch/lmbanr001/masters/sallm/results/standardized_adapter_recovery_20260914_hex_v1/slurm/train-1335756_0.err
   StdIn=/dev/null
   StdOut=/scratch/lmbanr001/masters/sallm/results/standardized_adapter_recovery_20260914_hex_v1/slurm/train-1335756_0.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:8
   MailUser=lmbanr001 MailType=END,FAIL